diff options
1283 files changed, 20464 insertions, 9872 deletions
@@ -108,6 +108,10 @@ Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> <javier@osg.samsung.com> <javier.martinez@collabora.co.uk> +Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com> +Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com> +Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com> +Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com> Jean Tourrilhes <jt@hpl.hp.com> <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com> Jeff Garzik <jgarzik@pretzel.yyz.us> @@ -196,7 +200,8 @@ Oleksij Rempel <linux@rempel-privat.de> <o.rempel@pengutronix.de> Oleksij Rempel <linux@rempel-privat.de> <ore@pengutronix.de> Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Patrick Mochel <mochel@digitalimplant.org> -Paul Burton <paul.burton@mips.com> <paul.burton@imgtec.com> +Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com> +Paul Burton <paulburton@kernel.org> <paul.burton@mips.com> Peter A Jonsson <pj@ludd.ltu.se> Peter Oruba <peter@oruba.de> Peter Oruba <peter.oruba@amd.com> @@ -229,6 +234,7 @@ Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com> Shuah Khan <shuah@kernel.org> <shuahkh@osg.samsung.com> Shuah Khan <shuah@kernel.org> <shuah.kh@samsung.com> +Simon Arlott <simon@octiron.net> <simon@fire.lp0.eu> Simon Kelley <simon@thekelleys.org.uk> Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr> Stephen Hemminger <shemminger@osdl.org> diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats index 2c44b4f1b060..70dcaf2481f4 100644 --- a/Documentation/ABI/testing/procfs-diskstats +++ b/Documentation/ABI/testing/procfs-diskstats @@ -29,4 +29,9 @@ Description: 17 - sectors discarded 18 - time spent discarding + Kernel 5.5+ appends two more fields for flush requests: + + 19 - flush requests completed successfully + 20 - time spent flushing + For more details refer to Documentation/admin-guide/iostats.rst diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index f8c7c7126bb1..ed8c14f161ee 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -15,6 +15,12 @@ Description: 9 - I/Os currently in progress 10 - time spent doing I/Os (ms) 11 - weighted time spent doing I/Os (ms) + 12 - discards completed + 13 - discards merged + 14 - sectors discarded + 15 - time spent discarding (ms) + 16 - flush requests completed + 17 - time spent flushing (ms) For more details refer Documentation/admin-guide/iostats.rst diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 06d0931119cc..fc20cde63d1e 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -486,6 +486,8 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds + /sys/devices/system/cpu/vulnerabilities/tsx_async_abort + /sys/devices/system/cpu/vulnerabilities/itlb_multihit Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst index a30aa91b5fbe..594095b54b29 100644 --- a/Documentation/admin-guide/device-mapper/dm-integrity.rst +++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst @@ -177,6 +177,11 @@ bitmap_flush_interval:number The bitmap flush interval in milliseconds. The metadata buffers are synchronized when this interval expires. +fix_padding + Use a smaller padding of the tag area that is more + space-efficient. If this option is not present, large padding is + used - that is for compatibility with older kernels. + The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can be changed when reloading the target (load an inactive table and swap the diff --git a/Documentation/admin-guide/device-mapper/dm-raid.rst b/Documentation/admin-guide/device-mapper/dm-raid.rst index 2fe255b130fb..f6344675e395 100644 --- a/Documentation/admin-guide/device-mapper/dm-raid.rst +++ b/Documentation/admin-guide/device-mapper/dm-raid.rst @@ -417,3 +417,5 @@ Version History deadlock/potential data corruption. Update superblock when specific devices are requested via rebuild. Fix RAID leg rebuild errors. + 1.15.0 Fix size extensions not being synchronized in case of new MD bitmap + pages allocated; also fix those not occuring after previous reductions diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 49311f3da6f2..0795e3c2643f 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -12,3 +12,5 @@ are configurable at compile, boot or run time. spectre l1tf mds + tsx_async_abort + multihit.rst diff --git a/Documentation/admin-guide/hw-vuln/multihit.rst b/Documentation/admin-guide/hw-vuln/multihit.rst new file mode 100644 index 000000000000..ba9988d8bce5 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/multihit.rst @@ -0,0 +1,163 @@ +iTLB multihit +============= + +iTLB multihit is an erratum where some processors may incur a machine check +error, possibly resulting in an unrecoverable CPU lockup, when an +instruction fetch hits multiple entries in the instruction TLB. This can +occur when the page size is changed along with either the physical address +or cache type. A malicious guest running on a virtualized system can +exploit this erratum to perform a denial of service attack. + + +Affected processors +------------------- + +Variations of this erratum are present on most Intel Core and Xeon processor +models. The erratum is not present on: + + - non-Intel processors + + - Some Atoms (Airmont, Bonnell, Goldmont, GoldmontPlus, Saltwell, Silvermont) + + - Intel processors that have the PSCHANGE_MC_NO bit set in the + IA32_ARCH_CAPABILITIES MSR. + + +Related CVEs +------------ + +The following CVE entry is related to this issue: + + ============== ================================================= + CVE-2018-12207 Machine Check Error Avoidance on Page Size Change + ============== ================================================= + + +Problem +------- + +Privileged software, including OS and virtual machine managers (VMM), are in +charge of memory management. A key component in memory management is the control +of the page tables. Modern processors use virtual memory, a technique that creates +the illusion of a very large memory for processors. This virtual space is split +into pages of a given size. Page tables translate virtual addresses to physical +addresses. + +To reduce latency when performing a virtual to physical address translation, +processors include a structure, called TLB, that caches recent translations. +There are separate TLBs for instruction (iTLB) and data (dTLB). + +Under this errata, instructions are fetched from a linear address translated +using a 4 KB translation cached in the iTLB. Privileged software modifies the +paging structure so that the same linear address using large page size (2 MB, 4 +MB, 1 GB) with a different physical address or memory type. After the page +structure modification but before the software invalidates any iTLB entries for +the linear address, a code fetch that happens on the same linear address may +cause a machine-check error which can result in a system hang or shutdown. + + +Attack scenarios +---------------- + +Attacks against the iTLB multihit erratum can be mounted from malicious +guests in a virtualized system. + + +iTLB multihit system information +-------------------------------- + +The Linux kernel provides a sysfs interface to enumerate the current iTLB +multihit status of the system:whether the system is vulnerable and which +mitigations are active. The relevant sysfs file is: + +/sys/devices/system/cpu/vulnerabilities/itlb_multihit + +The possible values in this file are: + +.. list-table:: + + * - Not affected + - The processor is not vulnerable. + * - KVM: Mitigation: Split huge pages + - Software changes mitigate this issue. + * - KVM: Vulnerable + - The processor is vulnerable, but no mitigation enabled + + +Enumeration of the erratum +-------------------------------- + +A new bit has been allocated in the IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) msr +and will be set on CPU's which are mitigated against this issue. + + ======================================= =========== =============================== + IA32_ARCH_CAPABILITIES MSR Not present Possibly vulnerable,check model + IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '0' Likely vulnerable,check model + IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '1' Not vulnerable + ======================================= =========== =============================== + + +Mitigation mechanism +------------------------- + +This erratum can be mitigated by restricting the use of large page sizes to +non-executable pages. This forces all iTLB entries to be 4K, and removes +the possibility of multiple hits. + +In order to mitigate the vulnerability, KVM initially marks all huge pages +as non-executable. If the guest attempts to execute in one of those pages, +the page is broken down into 4K pages, which are then marked executable. + +If EPT is disabled or not available on the host, KVM is in control of TLB +flushes and the problematic situation cannot happen. However, the shadow +EPT paging mechanism used by nested virtualization is vulnerable, because +the nested guest can trigger multiple iTLB hits by modifying its own +(non-nested) page tables. For simplicity, KVM will make large pages +non-executable in all shadow paging modes. + +Mitigation control on the kernel command line and KVM - module parameter +------------------------------------------------------------------------ + +The KVM hypervisor mitigation mechanism for marking huge pages as +non-executable can be controlled with a module parameter "nx_huge_pages=". +The kernel command line allows to control the iTLB multihit mitigations at +boot time with the option "kvm.nx_huge_pages=". + +The valid arguments for these options are: + + ========== ================================================================ + force Mitigation is enabled. In this case, the mitigation implements + non-executable huge pages in Linux kernel KVM module. All huge + pages in the EPT are marked as non-executable. + If a guest attempts to execute in one of those pages, the page is + broken down into 4K pages, which are then marked executable. + + off Mitigation is disabled. + + auto Enable mitigation only if the platform is affected and the kernel + was not booted with the "mitigations=off" command line parameter. + This is the default option. + ========== ================================================================ + + +Mitigation selection guide +-------------------------- + +1. No virtualization in use +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + The system is protected by the kernel unconditionally and no further + action is required. + +2. Virtualization with trusted guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + If the guest comes from a trusted source, you may assume that the guest will + not attempt to maliciously exploit these errata and no further action is + required. + +3. Virtualization with untrusted guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + If the guest comes from an untrusted source, the guest host kernel will need + to apply iTLB multihit mitigation via the kernel command line or kvm + module parameter. diff --git a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst new file mode 100644 index 000000000000..fddbd7579c53 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst @@ -0,0 +1,276 @@ +.. SPDX-License-Identifier: GPL-2.0 + +TAA - TSX Asynchronous Abort +====================================== + +TAA is a hardware vulnerability that allows unprivileged speculative access to +data which is available in various CPU internal buffers by using asynchronous +aborts within an Intel TSX transactional region. + +Affected processors +------------------- + +This vulnerability only affects Intel processors that support Intel +Transactional Synchronization Extensions (TSX) when the TAA_NO bit (bit 8) +is 0 in the IA32_ARCH_CAPABILITIES MSR. On processors where the MDS_NO bit +(bit 5) is 0 in the IA32_ARCH_CAPABILITIES MSR, the existing MDS mitigations +also mitigate against TAA. + +Whether a processor is affected or not can be read out from the TAA +vulnerability file in sysfs. See :ref:`tsx_async_abort_sys_info`. + +Related CVEs +------------ + +The following CVE entry is related to this TAA issue: + + ============== ===== =================================================== + CVE-2019-11135 TAA TSX Asynchronous Abort (TAA) condition on some + microprocessors utilizing speculative execution may + allow an authenticated user to potentially enable + information disclosure via a side channel with + local access. + ============== ===== =================================================== + +Problem +------- + +When performing store, load or L1 refill operations, processors write +data into temporary microarchitectural structures (buffers). The data in +those buffers can be forwarded to load operations as an optimization. + +Intel TSX is an extension to the x86 instruction set architecture that adds +hardware transactional memory support to improve performance of multi-threaded +software. TSX lets the processor expose and exploit concurrency hidden in an +application due to dynamically avoiding unnecessary synchronization. + +TSX supports atomic memory transactions that are either committed (success) or +aborted. During an abort, operations that happened within the transactional region +are rolled back. An asynchronous abort takes place, among other options, when a +different thread accesses a cache line that is also used within the transactional +region when that access might lead to a data race. + +Immediately after an uncompleted asynchronous abort, certain speculatively +executed loads may read data from those internal buffers and pass it to dependent +operations. This can be then used to infer the value via a cache side channel +attack. + +Because the buffers are potentially shared between Hyper-Threads cross +Hyper-Thread attacks are possible. + +The victim of a malicious actor does not need to make use of TSX. Only the +attacker needs to begin a TSX transaction and raise an asynchronous abort +which in turn potenitally leaks data stored in the buffers. + +More detailed technical information is available in the TAA specific x86 +architecture section: :ref:`Documentation/x86/tsx_async_abort.rst <tsx_async_abort>`. + + +Attack scenarios +---------------- + +Attacks against the TAA vulnerability can be implemented from unprivileged +applications running on hosts or guests. + +As for MDS, the attacker has no control over the memory addresses that can +be leaked. Only the victim is responsible for bringing data to the CPU. As +a result, the malicious actor has to sample as much data as possible and +then postprocess it to try to infer any useful information from it. + +A potential attacker only has read access to the data. Also, there is no direct +privilege escalation by using this technique. + + +.. _tsx_async_abort_sys_info: + +TAA system information +----------------------- + +The Linux kernel provides a sysfs interface to enumerate the current TAA status +of mitigated systems. The relevant sysfs file is: + +/sys/devices/system/cpu/vulnerabilities/tsx_async_abort + +The possible values in this file are: + +.. list-table:: + + * - 'Vulnerable' + - The CPU is affected by this vulnerability and the microcode and kernel mitigation are not applied. + * - 'Vulnerable: Clear CPU buffers attempted, no microcode' + - The system tries to clear the buffers but the microcode might not support the operation. + * - 'Mitigation: Clear CPU buffers' + - The microcode has been updated to clear the buffers. TSX is still enabled. + * - 'Mitigation: TSX disabled' + - TSX is disabled. + * - 'Not affected' + - The CPU is not affected by this issue. + +.. _ucode_needed: + +Best effort mitigation mode +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If the processor is vulnerable, but the availability of the microcode-based +mitigation mechanism is not advertised via CPUID the kernel selects a best +effort mitigation mode. This mode invokes the mitigation instructions +without a guarantee that they clear the CPU buffers. + +This is done to address virtualization scenarios where the host has the +microcode update applied, but the hypervisor is not yet updated to expose the +CPUID to the guest. If the host has updated microcode the protection takes +effect; otherwise a few CPU cycles are wasted pointlessly. + +The state in the tsx_async_abort sysfs file reflects this situation +accordingly. + + +Mitigation mechanism +-------------------- + +The kernel detects the affected CPUs and the presence of the microcode which is +required. If a CPU is affected and the microcode is available, then the kernel +enables the mitigation by default. + + +The mitigation can be controlled at boot time via a kernel command line option. +See :ref:`taa_mitigation_control_command_line`. + +.. _virt_mechanism: + +Virtualization mitigation +^^^^^^^^^^^^^^^^^^^^^^^^^ + +Affected systems where the host has TAA microcode and TAA is mitigated by +having disabled TSX previously, are not vulnerable regardless of the status +of the VMs. + +In all other cases, if the host either does not have the TAA microcode or +the kernel is not mitigated, the system might be vulnerable. + + +.. _taa_mitigation_control_command_line: + +Mitigation control on the kernel command line +--------------------------------------------- + +The kernel command line allows to control the TAA mitigations at boot time with +the option "tsx_async_abort=". The valid arguments for this option are: + + ============ ============================================================= + off This option disables the TAA mitigation on affected platforms. + If the system has TSX enabled (see next parameter) and the CPU + is affected, the system is vulnerable. + + full TAA mitigation is enabled. If TSX is enabled, on an affected + system it will clear CPU buffers on ring transitions. On + systems which are MDS-affected and deploy MDS mitigation, + TAA is also mitigated. Specifying this option on those + systems will have no effect. + + full,nosmt The same as tsx_async_abort=full, with SMT disabled on + vulnerable CPUs that have TSX enabled. This is the complete + mitigation. When TSX is disabled, SMT is not disabled because + CPU is not vulnerable to cross-thread TAA attacks. + ============ ============================================================= + +Not specifying this option is equivalent to "tsx_async_abort=full". + +The kernel command line also allows to control the TSX feature using the +parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used +to control the TSX feature and the enumeration of the TSX feature bits (RTM +and HLE) in CPUID. + +The valid options are: + + ============ ============================================================= + off Disables TSX on the system. + + Note that this option takes effect only on newer CPUs which are + not vulnerable to MDS, i.e., have MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 + and which get the new IA32_TSX_CTRL MSR through a microcode + update. This new MSR allows for the reliable deactivation of + the TSX functionality. + + on Enables TSX. + + Although there are mitigations for all known security + vulnerabilities, TSX has been known to be an accelerator for + several previous speculation-related CVEs, and so there may be + unknown security risks associated with leaving it enabled. + + auto Disables TSX if X86_BUG_TAA is present, otherwise enables TSX + on the system. + ============ ============================================================= + +Not specifying this option is equivalent to "tsx=off". + +The following combinations of the "tsx_async_abort" and "tsx" are possible. For +affected platforms tsx=auto is equivalent to tsx=off and the result will be: + + ========= ========================== ========================================= + tsx=on tsx_async_abort=full The system will use VERW to clear CPU + buffers. Cross-thread attacks are still + possible on SMT machines. + tsx=on tsx_async_abort=full,nosmt As above, cross-thread attacks on SMT + mitigated. + tsx=on tsx_async_abort=off The system is vulnerable. + tsx=off tsx_async_abort=full TSX might be disabled if microcode + provides a TSX control MSR. If so, + system is not vulnerable. + tsx=off tsx_async_abort=full,nosmt Ditto + tsx=off tsx_async_abort=off ditto + ========= ========================== ========================================= + + +For unaffected platforms "tsx=on" and "tsx_async_abort=full" does not clear CPU +buffers. For platforms without TSX control (MSR_IA32_ARCH_CAPABILITIES.MDS_NO=0) +"tsx" command line argument has no effect. + +For the affected platforms below table indicates the mitigation status for the +combinations of CPUID bit MD_CLEAR and IA32_ARCH_CAPABILITIES MSR bits MDS_NO +and TSX_CTRL_MSR. + + ======= ========= ============= ======================================== + MDS_NO MD_CLEAR TSX_CTRL_MSR Status + ======= ========= ============= ======================================== + 0 0 0 Vulnerable (needs microcode) + 0 1 0 MDS and TAA mitigated via VERW + 1 1 0 MDS fixed, TAA vulnerable if TSX enabled + because MD_CLEAR has no meaning and + VERW is not guaranteed to clear buffers + 1 X 1 MDS fixed, TAA can be mitigated by + VERW or TSX_CTRL_MSR + ======= ========= ============= ======================================== + +Mitigation selection guide +-------------------------- + +1. Trusted userspace and guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If all user space applications are from a trusted source and do not execute +untrusted code which is supplied externally, then the mitigation can be +disabled. The same applies to virtualized environments with trusted guests. + + +2. Untrusted userspace and guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If there are untrusted applications or guests on the system, enabling TSX +might allow a malicious actor to leak data from the host or from other +processes running on the same physical core. + +If the microcode is available and the TSX is disabled on the host, attacks +are prevented in a virtualized environment as well, even if the VMs do not +explicitly enable the mitigation. + + +.. _taa_default_mitigations: + +Default mitigations +------------------- + +The kernel's default action for vulnerable processors is: + + - Deploy TSX disable mitigation (tsx_async_abort=full tsx=off). diff --git a/Documentation/admin-guide/iostats.rst b/Documentation/admin-guide/iostats.rst index 5d63b18bd6d1..4f0462af3ca7 100644 --- a/Documentation/admin-guide/iostats.rst +++ b/Documentation/admin-guide/iostats.rst @@ -121,6 +121,15 @@ Field 15 -- # of milliseconds spent discarding This is the total number of milliseconds spent by all discards (as measured from __make_request() to end_that_request_last()). +Field 16 -- # of flush requests completed + This is the total number of flush requests completed successfully. + + Block layer combines flush requests and executes at most one at a time. + This counts flush requests executed by disk. Not tracked for partitions. + +Field 17 -- # of milliseconds spent flushing + This is the total number of milliseconds spent by all flush requests. + To avoid introducing performance bottlenecks, no locks are held while modifying these counters. This implies that minor inaccuracies may be introduced when changes collide, so (for instance) adding up all the diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a84a83f8881e..8dee8f68fe15 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2055,6 +2055,25 @@ KVM MMU at runtime. Default is 0 (off) + kvm.nx_huge_pages= + [KVM] Controls the software workaround for the + X86_BUG_ITLB_MULTIHIT bug. + force : Always deploy workaround. + off : Never deploy workaround. + auto : Deploy workaround based on the presence of + X86_BUG_ITLB_MULTIHIT. + + Default is 'auto'. + + If the software workaround is enabled for the host, + guests do need not to enable it for nested guests. + + kvm.nx_huge_pages_recovery_ratio= + [KVM] Controls how many 4KiB pages are periodically zapped + back to huge pages. 0 disables the recovery, otherwise if + the value is N KVM will zap 1/Nth of the 4KiB pages every + minute. The default is 60. + kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM. Default is 1 (enabled) @@ -2636,6 +2655,13 @@ ssbd=force-off [ARM64] l1tf=off [X86] mds=off [X86] + tsx_async_abort=off [X86] + kvm.nx_huge_pages=off [X86] + + Exceptions: + This does not have any effect on + kvm.nx_huge_pages when + kvm.nx_huge_pages=force. auto (default) Mitigate all CPU vulnerabilities, but leave SMT @@ -2651,6 +2677,7 @@ be fully mitigated, even if it means losing SMT. Equivalent to: l1tf=flush,nosmt [X86] mds=full,nosmt [X86] + tsx_async_abort=full,nosmt [X86] mminit_loglevel= [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this @@ -4848,6 +4875,71 @@ interruptions from clocksource watchdog are not acceptable). + tsx= [X86] Control Transactional Synchronization + Extensions (TSX) feature in Intel processors that + support TSX control. + + This parameter controls the TSX feature. The options are: + + on - Enable TSX on the system. Although there are + mitigations for all known security vulnerabilities, + TSX has been known to be an accelerator for + several previous speculation-related CVEs, and + so there may be unknown security risks associated + with leaving it enabled. + + off - Disable TSX on the system. (Note that this + option takes effect only on newer CPUs which are + not vulnerable to MDS, i.e., have + MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get + the new IA32_TSX_CTRL MSR through a microcode + update. This new MSR allows for the reliable + deactivation of the TSX functionality.) + + auto - Disable TSX if X86_BUG_TAA is present, + otherwise enable TSX on the system. + + Not specifying this option is equivalent to tsx=off. + + See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst + for more details. + + tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async + Abort (TAA) vulnerability. + + Similar to Micro-architectural Data Sampling (MDS) + certain CPUs that support Transactional + Synchronization Extensions (TSX) are vulnerable to an + exploit against CPU internal buffers which can forward + information to a disclosure gadget under certain + conditions. + + In vulnerable processors, the speculatively forwarded + data can be used in a cache side channel attack, to + access data to which the attacker does not have direct + access. + + This parameter controls the TAA mitigation. The + options are: + + full - Enable TAA mitigation on vulnerable CPUs + if TSX is enabled. + + full,nosmt - Enable TAA mitigation and disable SMT on + vulnerable CPUs. If TSX is disabled, SMT + is not disabled because CPU is not + vulnerable to cross-thread TAA attacks. + off - Unconditionally disable TAA mitigation + + Not specifying this option is equivalent to + tsx_async_abort=full. On CPUs which are MDS affected + and deploy MDS mitigation, TAA mitigation is not + required and doesn't provide any additional + mitigation. + + For details see: + Documentation/admin-guide/hw-vuln/tsx_async_abort.rst + turbografx.map[2|3]= [HW,JOY] TurboGraFX parallel port interface Format: diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index ab7ed2fd072f..5a09661330fc 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -91,6 +91,11 @@ stable kernels. | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_845719 | ++----------------+-----------------+-----------------+-----------------------------+ +| Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_843419 | ++----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX ITS | #22375,24313 | CAVIUM_ERRATUM_22375 | +----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX ITS | #23144 | CAVIUM_ERRATUM_23144 | @@ -126,7 +131,7 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | +----------------+-----------------+-----------------+-----------------------------+ -| Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | +| Qualcomm Tech. | Kryo/Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/block/stat.rst b/Documentation/block/stat.rst index 9c07bc22b0bc..77311335c08b 100644 --- a/Documentation/block/stat.rst +++ b/Documentation/block/stat.rst @@ -41,6 +41,8 @@ discard I/Os requests number of discard I/Os processed discard merges requests number of discard I/Os merged with in-queue I/O discard sectors sectors number of sectors discarded discard ticks milliseconds total wait time for discard requests +flush I/Os requests number of flush I/Os processed +flush ticks milliseconds total wait time for flush requests =============== ============= ================================================= read I/Os, write I/Os, discard I/0s @@ -48,6 +50,14 @@ read I/Os, write I/Os, discard I/0s These values increment when an I/O request completes. +flush I/Os +========== + +These values increment when an flush I/O request completes. + +Block layer combines flush requests and executes at most one at a time. +This counts flush requests executed by disk. Not tracked for partitions. + read merges, write merges, discard merges ========================================= @@ -62,8 +72,8 @@ discarded from this block device. The "sectors" in question are the standard UNIX 512-byte sectors, not any device- or filesystem-specific block size. The counters are incremented when the I/O completes. -read ticks, write ticks, discard ticks -====================================== +read ticks, write ticks, discard ticks, flush ticks +=================================================== These values count the number of milliseconds that I/O requests have waited on this block device. If there are multiple I/O requests waiting, diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml index c82c5e57d44c..9c7e70335ac0 100644 --- a/Documentation/devicetree/bindings/arm/rockchip.yaml +++ b/Documentation/devicetree/bindings/arm/rockchip.yaml @@ -496,12 +496,12 @@ properties: - description: Theobroma Systems RK3368-uQ7 with Haikou baseboard items: - - const: tsd,rk3368-uq7-haikou + - const: tsd,rk3368-lion-haikou - const: rockchip,rk3368 - description: Theobroma Systems RK3399-Q7 with Haikou baseboard items: - - const: tsd,rk3399-q7-haikou + - const: tsd,rk3399-puma-haikou - const: rockchip,rk3399 - description: Tronsmart Orion R68 Meta diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml index 27f38eed389e..d3e423fcb6c2 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/allwinner,sun4i-a10-csi.yaml# +$id: http://devicetree.org/schemas/media/allwinner,sun4i-a10-csi.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A10 CMOS Sensor Interface (CSI) Device Tree Bindings @@ -27,14 +27,12 @@ properties: clocks: items: - description: The CSI interface clock - - description: The CSI module clock - description: The CSI ISP clock - description: The CSI DRAM clock clock-names: items: - const: bus - - const: mod - const: isp - const: ram @@ -89,9 +87,8 @@ examples: compatible = "allwinner,sun7i-a20-csi0"; reg = <0x01c09000 0x1000>; interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI0>, - <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>; - clock-names = "bus", "mod", "isp", "ram"; + clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>; + clock-names = "bus", "isp", "ram"; resets = <&ccu RST_CSI0>; port { diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml index f83d888176cc..064b7dfc4252 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml @@ -33,13 +33,13 @@ patternProperties: allOf: - $ref: "/schemas/types.yaml#/definitions/string" - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, - ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI, - ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, - GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, - GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, I2C12, - I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, - I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC, - LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, + ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMC, + ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, + GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, + GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, + I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, + I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, + LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1, @@ -48,47 +48,45 @@ patternProperties: PWM8, PWM9, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3, RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10, SALT11, SALT12, SALT13, SALT14, SALT15, SALT16, SALT2, SALT3, SALT4, SALT5, - SALT6, SALT7, SALT8, SALT9, SD1, SD2, SD3, SD3DAT4, SD3DAT5, - SD3DAT6, SD3DAT7, SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO, - SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1, - SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11, - TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, TACH4, TACH5, - TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, THRU3, TXD1, - TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13, UART6, UART7, - UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, - WDTRST4, ] + SALT6, SALT7, SALT8, SALT9, SD1, SD2, SGPM1, SGPS1, SIOONCTRL, + SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, + SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, + TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, + TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, + THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13, + UART6, UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, + WDTRST3, WDTRST4, ] groups: allOf: - $ref: "/schemas/types.yaml#/definitions/string" - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, - ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI, - ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWQSPID, FWSPIWP, GPIT0, - GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, - GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, HVI3C3, HVI3C4, I2C1, - I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, - I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, - JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, - MACLINK1, MACLINK2, MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3, - MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4, - NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1, - NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4, OSCCLK, PEWAKE, - PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1, PWM12G0, PWM12G1, - PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0, PWM15G1, PWM2, PWM3, - PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1, PWM9G0, PWM9G1, QSPI1, - QSPI2, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3, - RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10G0, SALT10G1, - SALT11G0, SALT11G1, SALT12G0, SALT12G1, SALT13G0, SALT13G1, - SALT14G0, SALT14G1, SALT15G0, SALT15G1, SALT16G0, SALT16G1, - SALT2, SALT3, SALT4, SALT5, SALT6, SALT7, SALT8, SALT9G0, - SALT9G1, SD1, SD2, SD3, SD3DAT4, SD3DAT5, SD3DAT6, SD3DAT7, - SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, - SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1, SPI1WP, SPI2, - SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11, TACH12, TACH13, - TACH14, TACH15, TACH2, TACH3, TACH4, TACH5, TACH6, TACH7, TACH8, - TACH9, THRU0, THRU1, THRU2, THRU3, TXD1, TXD2, TXD3, TXD4, - UART10, UART11, UART12G0, UART12G1, UART13G0, UART13G1, UART6, - UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, - WDTRST4, ] + ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1, + EMMCG4, EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, + FWQSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, + GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, + GPIU7, HVI3C3, HVI3C4, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14, + I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, + I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD, + LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, MACLINK3, MACLINK4, + MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, + NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, + NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4, + OSCCLK, PEWAKE, PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1, + PWM12G0, PWM12G1, PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0, + PWM15G1, PWM2, PWM3, PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1, + PWM9G0, PWM9G1, QSPI1, QSPI2, RGMII1, RGMII2, RGMII3, RGMII4, + RMII1, RMII2, RMII3, RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, + SALT10G0, SALT10G1, SALT11G0, SALT11G1, SALT12G0, SALT12G1, + SALT13G0, SALT13G1, SALT14G0, SALT14G1, SALT15G0, SALT15G1, + SALT16G0, SALT16G1, SALT2, SALT3, SALT4, SALT5, SALT6, SALT7, + SALT8, SALT9G0, SALT9G1, SD1, SD2, SD3, SGPM1, SGPS1, SIOONCTRL, + SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, + SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, + TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, + TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, + THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12G0, + UART12G1, UART13G0, UART13G1, UART6, UART7, UART8, UART9, VB, + VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, WDTRST4, ] required: - compatible diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml index a78150c47aa2..f32416968197 100644 --- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml @@ -30,8 +30,8 @@ if: properties: compatible: enum: - - const: regulator-fixed - - const: regulator-fixed-clock + - regulator-fixed + - regulator-fixed-clock regulator-name: true diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index b261a3015f84..04819ad379c2 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -24,15 +24,17 @@ description: | properties: compatible: - items: - - enum: - - sifive,rocket0 - - sifive,e5 - - sifive,e51 - - sifive,u54-mc - - sifive,u54 - - sifive,u5 - - const: riscv + oneOf: + - items: + - enum: + - sifive,rocket0 + - sifive,e5 + - sifive,e51 + - sifive,u54-mc + - sifive,u54 + - sifive,u5 + - const: riscv + - const: riscv # Simulator only description: Identifies that the hart uses the RISC-V instruction set and identifies the type of the hart. @@ -66,12 +68,8 @@ properties: insensitive, letters in the riscv,isa string must be all lowercase to simplify parsing. - timebase-frequency: - type: integer - minimum: 1 - description: - Specifies the clock frequency of the system timer in Hz. - This value is common to all harts on a single system image. + # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here + timebase-frequency: false interrupt-controller: type: object @@ -93,7 +91,6 @@ properties: required: - riscv,isa - - timebase-frequency - interrupt-controller examples: diff --git a/Documentation/devicetree/bindings/security/tpm/google,cr50.txt b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt new file mode 100644 index 000000000000..cd69c2efdd37 --- /dev/null +++ b/Documentation/devicetree/bindings/security/tpm/google,cr50.txt @@ -0,0 +1,19 @@ +* H1 Secure Microcontroller with Cr50 Firmware on SPI Bus. + +H1 Secure Microcontroller running Cr50 firmware provides several +functions, including TPM-like functionality. It communicates over +SPI using the FIFO protocol described in the PTP Spec, section 6. + +Required properties: +- compatible: Should be "google,cr50". +- spi-max-frequency: Maximum SPI frequency. + +Example: + +&spi0 { + tpm@0 { + compatible = "google,cr50"; + reg = <0>; + spi-max-frequency = <800000>; + }; +}; diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst index 70e180e6b93d..207f0d24de69 100644 --- a/Documentation/driver-api/libata.rst +++ b/Documentation/driver-api/libata.rst @@ -250,23 +250,23 @@ High-level taskfile hooks :: - void (*qc_prep) (struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc); int (*qc_issue) (struct ata_queued_cmd *qc); -Higher-level hooks, these two hooks can potentially supercede several of +Higher-level hooks, these two hooks can potentially supersede several of the above taskfile/DMA engine hooks. ``->qc_prep`` is called after the buffers have been DMA-mapped, and is typically used to populate the -hardware's DMA scatter-gather table. Most drivers use the standard -:c:func:`ata_qc_prep` helper function, but more advanced drivers roll their -own. +hardware's DMA scatter-gather table. Some drivers use the standard +:c:func:`ata_bmdma_qc_prep` and :c:func:`ata_bmdma_dumb_qc_prep` helper +functions, but more advanced drivers roll their own. ``->qc_issue`` is used to make a command active, once the hardware and S/G tables have been prepared. IDE BMDMA drivers use the helper function -:c:func:`ata_qc_issue_prot` for taskfile protocol-based dispatch. More +:c:func:`ata_sff_qc_issue` for taskfile protocol-based dispatch. More advanced drivers implement their own ``->qc_issue``. -:c:func:`ata_qc_issue_prot` calls ``->tf_load()``, ``->bmdma_setup()``, and +:c:func:`ata_sff_qc_issue` calls ``->sff_tf_load()``, ``->bmdma_setup()``, and ``->bmdma_start()`` as necessary to initiate a transfer. Exception and probe handling (EH) diff --git a/Documentation/networking/device_drivers/intel/e100.rst b/Documentation/networking/device_drivers/intel/e100.rst index 2b9f4887beda..caf023cc88de 100644 --- a/Documentation/networking/device_drivers/intel/e100.rst +++ b/Documentation/networking/device_drivers/intel/e100.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -============================================================== -Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters -============================================================== +============================================================= +Linux Base Driver for the Intel(R) PRO/100 Family of Adapters +============================================================= June 1, 2018 @@ -21,7 +21,7 @@ Contents In This Release =============== -This file describes the Linux* Base Driver for the Intel(R) PRO/100 Family of +This file describes the Linux Base Driver for the Intel(R) PRO/100 Family of Adapters. This driver includes support for Itanium(R)2-based systems. For questions related to hardware requirements, refer to the documentation @@ -138,9 +138,9 @@ version 1.6 or later is required for this functionality. The latest release of ethtool can be found from https://www.kernel.org/pub/software/network/ethtool/ -Enabling Wake on LAN* (WoL) ---------------------------- -WoL is provided through the ethtool* utility. For instructions on +Enabling Wake on LAN (WoL) +-------------------------- +WoL is provided through the ethtool utility. For instructions on enabling WoL with ethtool, refer to the ethtool man page. WoL will be enabled on the system during the next shut down or reboot. For this driver version, in order to enable WoL, the e100 driver must be loaded diff --git a/Documentation/networking/device_drivers/intel/e1000.rst b/Documentation/networking/device_drivers/intel/e1000.rst index 956560b6e745..4aaae0f7d6ba 100644 --- a/Documentation/networking/device_drivers/intel/e1000.rst +++ b/Documentation/networking/device_drivers/intel/e1000.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -=========================================================== -Linux* Base Driver for Intel(R) Ethernet Network Connection -=========================================================== +========================================================== +Linux Base Driver for Intel(R) Ethernet Network Connection +========================================================== Intel Gigabit Linux driver. Copyright(c) 1999 - 2013 Intel Corporation. @@ -438,10 +438,10 @@ ethtool The latest release of ethtool can be found from https://www.kernel.org/pub/software/network/ethtool/ -Enabling Wake on LAN* (WoL) ---------------------------- +Enabling Wake on LAN (WoL) +-------------------------- - WoL is configured through the ethtool* utility. + WoL is configured through the ethtool utility. WoL will be enabled on the system during the next shut down or reboot. For this driver version, in order to enable WoL, the e1000 driver must be diff --git a/Documentation/networking/device_drivers/intel/e1000e.rst b/Documentation/networking/device_drivers/intel/e1000e.rst index 01999f05509c..f49cd370e7bf 100644 --- a/Documentation/networking/device_drivers/intel/e1000e.rst +++ b/Documentation/networking/device_drivers/intel/e1000e.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -====================================================== -Linux* Driver for Intel(R) Ethernet Network Connection -====================================================== +===================================================== +Linux Driver for Intel(R) Ethernet Network Connection +===================================================== Intel Gigabit Linux driver. Copyright(c) 2008-2018 Intel Corporation. @@ -338,7 +338,7 @@ and higher cannot be forced. Use the autonegotiation advertising setting to manually set devices for 1 Gbps and higher. Speed, duplex, and autonegotiation advertising are configured through the -ethtool* utility. +ethtool utility. Caution: Only experienced network administrators should force speed and duplex or change autonegotiation advertising manually. The settings at the switch must @@ -351,9 +351,9 @@ will not attempt to auto-negotiate with its link partner since those adapters operate only in full duplex and only at their native speed. -Enabling Wake on LAN* (WoL) ---------------------------- -WoL is configured through the ethtool* utility. +Enabling Wake on LAN (WoL) +-------------------------- +WoL is configured through the ethtool utility. WoL will be enabled on the system during the next shut down or reboot. For this driver version, in order to enable WoL, the e1000e driver must be loaded diff --git a/Documentation/networking/device_drivers/intel/fm10k.rst b/Documentation/networking/device_drivers/intel/fm10k.rst index ac3269e34f55..4d279e64e221 100644 --- a/Documentation/networking/device_drivers/intel/fm10k.rst +++ b/Documentation/networking/device_drivers/intel/fm10k.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -============================================================== -Linux* Base Driver for Intel(R) Ethernet Multi-host Controller -============================================================== +============================================================= +Linux Base Driver for Intel(R) Ethernet Multi-host Controller +============================================================= August 20, 2018 Copyright(c) 2015-2018 Intel Corporation. @@ -120,8 +120,8 @@ rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 m|v|t|s|d|f|n|r Known Issues/Troubleshooting ============================ -Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS under Linux KVM ---------------------------------------------------------------------------------------- +Enabling SR-IOV in a 64-bit Microsoft Windows Server 2012/R2 guest OS under Linux KVM +------------------------------------------------------------------------------------- KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This includes traditional PCIe devices, as well as SR-IOV-capable devices based on the Intel Ethernet Controller XL710. diff --git a/Documentation/networking/device_drivers/intel/i40e.rst b/Documentation/networking/device_drivers/intel/i40e.rst index 848fd388fa6e..8a9b18573688 100644 --- a/Documentation/networking/device_drivers/intel/i40e.rst +++ b/Documentation/networking/device_drivers/intel/i40e.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -================================================================== -Linux* Base Driver for the Intel(R) Ethernet Controller 700 Series -================================================================== +================================================================= +Linux Base Driver for the Intel(R) Ethernet Controller 700 Series +================================================================= Intel 40 Gigabit Linux driver. Copyright(c) 1999-2018 Intel Corporation. @@ -384,7 +384,7 @@ NOTE: You cannot set the speed for devices based on the Intel(R) Ethernet Network Adapter XXV710 based devices. Speed, duplex, and autonegotiation advertising are configured through the -ethtool* utility. +ethtool utility. Caution: Only experienced network administrators should force speed and duplex or change autonegotiation advertising manually. The settings at the switch must diff --git a/Documentation/networking/device_drivers/intel/iavf.rst b/Documentation/networking/device_drivers/intel/iavf.rst index cfc08842e32c..84ac7e75f363 100644 --- a/Documentation/networking/device_drivers/intel/iavf.rst +++ b/Documentation/networking/device_drivers/intel/iavf.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -================================================================== -Linux* Base Driver for Intel(R) Ethernet Adaptive Virtual Function -================================================================== +================================================================= +Linux Base Driver for Intel(R) Ethernet Adaptive Virtual Function +================================================================= Intel Ethernet Adaptive Virtual Function Linux driver. Copyright(c) 2013-2018 Intel Corporation. @@ -19,7 +19,7 @@ Contents Overview ======== -This file describes the iavf Linux* Base Driver. This driver was formerly +This file describes the iavf Linux Base Driver. This driver was formerly called i40evf. The iavf driver supports the below mentioned virtual function devices and diff --git a/Documentation/networking/device_drivers/intel/ice.rst b/Documentation/networking/device_drivers/intel/ice.rst index c220aa2711c6..ee43ea57d443 100644 --- a/Documentation/networking/device_drivers/intel/ice.rst +++ b/Documentation/networking/device_drivers/intel/ice.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -=================================================================== -Linux* Base Driver for the Intel(R) Ethernet Connection E800 Series -=================================================================== +================================================================== +Linux Base Driver for the Intel(R) Ethernet Connection E800 Series +================================================================== Intel ice Linux driver. Copyright(c) 2018 Intel Corporation. diff --git a/Documentation/networking/device_drivers/intel/igb.rst b/Documentation/networking/device_drivers/intel/igb.rst index fc8cfaa5dcfa..87e560fe5eaa 100644 --- a/Documentation/networking/device_drivers/intel/igb.rst +++ b/Documentation/networking/device_drivers/intel/igb.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -=========================================================== -Linux* Base Driver for Intel(R) Ethernet Network Connection -=========================================================== +========================================================== +Linux Base Driver for Intel(R) Ethernet Network Connection +========================================================== Intel Gigabit Linux driver. Copyright(c) 1999-2018 Intel Corporation. @@ -129,9 +129,9 @@ version is required for this functionality. Download it at: https://www.kernel.org/pub/software/network/ethtool/ -Enabling Wake on LAN* (WoL) ---------------------------- -WoL is configured through the ethtool* utility. +Enabling Wake on LAN (WoL) +-------------------------- +WoL is configured through the ethtool utility. WoL will be enabled on the system during the next shut down or reboot. For this driver version, in order to enable WoL, the igb driver must be loaded diff --git a/Documentation/networking/device_drivers/intel/igbvf.rst b/Documentation/networking/device_drivers/intel/igbvf.rst index 9cddabe8108e..557fc020ef31 100644 --- a/Documentation/networking/device_drivers/intel/igbvf.rst +++ b/Documentation/networking/device_drivers/intel/igbvf.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -============================================================ -Linux* Base Virtual Function Driver for Intel(R) 1G Ethernet -============================================================ +=========================================================== +Linux Base Virtual Function Driver for Intel(R) 1G Ethernet +=========================================================== Intel Gigabit Virtual Function Linux driver. Copyright(c) 1999-2018 Intel Corporation. diff --git a/Documentation/networking/device_drivers/intel/ixgbe.rst b/Documentation/networking/device_drivers/intel/ixgbe.rst index c7d25483fedb..f1d5233e5e51 100644 --- a/Documentation/networking/device_drivers/intel/ixgbe.rst +++ b/Documentation/networking/device_drivers/intel/ixgbe.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -============================================================================= -Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters -============================================================================= +=========================================================================== +Linux Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters +=========================================================================== Intel 10 Gigabit Linux driver. Copyright(c) 1999-2018 Intel Corporation. @@ -519,8 +519,8 @@ The offload is also supported for ixgbe's VFs, but the VF must be set as Known Issues/Troubleshooting ============================ -Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS ------------------------------------------------------------------------ +Enabling SR-IOV in a 64-bit Microsoft Windows Server 2012/R2 guest OS +--------------------------------------------------------------------- Linux KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This includes traditional PCIe devices, as well as SR-IOV-capable devices based on the Intel Ethernet Controller XL710. diff --git a/Documentation/networking/device_drivers/intel/ixgbevf.rst b/Documentation/networking/device_drivers/intel/ixgbevf.rst index 5d4977360157..76bbde736f21 100644 --- a/Documentation/networking/device_drivers/intel/ixgbevf.rst +++ b/Documentation/networking/device_drivers/intel/ixgbevf.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -============================================================= -Linux* Base Virtual Function Driver for Intel(R) 10G Ethernet -============================================================= +============================================================ +Linux Base Virtual Function Driver for Intel(R) 10G Ethernet +============================================================ Intel 10 Gigabit Virtual Function Linux driver. Copyright(c) 1999-2018 Intel Corporation. diff --git a/Documentation/networking/device_drivers/pensando/ionic.rst b/Documentation/networking/device_drivers/pensando/ionic.rst index 13935896bee6..c17d680cf334 100644 --- a/Documentation/networking/device_drivers/pensando/ionic.rst +++ b/Documentation/networking/device_drivers/pensando/ionic.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -========================================================== -Linux* Driver for the Pensando(R) Ethernet adapter family -========================================================== +======================================================== +Linux Driver for the Pensando(R) Ethernet adapter family +======================================================== Pensando Linux Ethernet driver. Copyright(c) 2019 Pensando Systems, Inc diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 49e95f438ed7..8d4ad1d1ae26 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -207,8 +207,8 @@ TCP variables: somaxconn - INTEGER Limit of socket listen() backlog, known in userspace as SOMAXCONN. - Defaults to 128. See also tcp_max_syn_backlog for additional tuning - for TCP sockets. + Defaults to 4096. (Was 128 before linux-5.4) + See also tcp_max_syn_backlog for additional tuning for TCP sockets. tcp_abort_on_overflow - BOOLEAN If listening service is too slow to accept new connections, @@ -408,11 +408,14 @@ tcp_max_orphans - INTEGER up to ~64K of unswappable memory. tcp_max_syn_backlog - INTEGER - Maximal number of remembered connection requests, which have not - received an acknowledgment from connecting client. + Maximal number of remembered connection requests (SYN_RECV), + which have not received an acknowledgment from connecting client. + This is a per-listener limit. The minimal value is 128 for low memory machines, and it will increase in proportion to the memory of machine. If server suffers from overload, try increasing this number. + Remember to also check /proc/sys/net/core/somaxconn + A SYN_RECV request socket consumes about 304 bytes of memory. tcp_max_tw_buckets - INTEGER Maximal number of timewait sockets held by system simultaneously. diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index 0dd3f748239f..f914e81fd3a6 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -436,6 +436,10 @@ by the driver: encryption. * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream but did not arrive in the expected order. + * ``tx_tls_skip_no_sync_data`` - number of TX packets which were part of + a TLS stream and arrived out-of-order, but skipped the HW offload routine + and went to the regular transmit flow as they were retransmissions of the + connection handshake. * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of a TLS stream dropped, because they arrived out of order and associated record could not be found. diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index af64c4bb4447..a8de2fbc1caa 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -27,6 +27,7 @@ x86-specific Documentation mds microcode resctrl_ui + tsx_async_abort usb-legacy-support i386/index x86_64/index diff --git a/Documentation/x86/tsx_async_abort.rst b/Documentation/x86/tsx_async_abort.rst new file mode 100644 index 000000000000..583ddc185ba2 --- /dev/null +++ b/Documentation/x86/tsx_async_abort.rst @@ -0,0 +1,117 @@ +.. SPDX-License-Identifier: GPL-2.0 + +TSX Async Abort (TAA) mitigation +================================ + +.. _tsx_async_abort: + +Overview +-------- + +TSX Async Abort (TAA) is a side channel attack on internal buffers in some +Intel processors similar to Microachitectural Data Sampling (MDS). In this +case certain loads may speculatively pass invalid data to dependent operations +when an asynchronous abort condition is pending in a Transactional +Synchronization Extensions (TSX) transaction. This includes loads with no +fault or assist condition. Such loads may speculatively expose stale data from +the same uarch data structures as in MDS, with same scope of exposure i.e. +same-thread and cross-thread. This issue affects all current processors that +support TSX. + +Mitigation strategy +------------------- + +a) TSX disable - one of the mitigations is to disable TSX. A new MSR +IA32_TSX_CTRL will be available in future and current processors after +microcode update which can be used to disable TSX. In addition, it +controls the enumeration of the TSX feature bits (RTM and HLE) in CPUID. + +b) Clear CPU buffers - similar to MDS, clearing the CPU buffers mitigates this +vulnerability. More details on this approach can be found in +:ref:`Documentation/admin-guide/hw-vuln/mds.rst <mds>`. + +Kernel internal mitigation modes +-------------------------------- + + ============= ============================================================ + off Mitigation is disabled. Either the CPU is not affected or + tsx_async_abort=off is supplied on the kernel command line. + + tsx disabled Mitigation is enabled. TSX feature is disabled by default at + bootup on processors that support TSX control. + + verw Mitigation is enabled. CPU is affected and MD_CLEAR is + advertised in CPUID. + + ucode needed Mitigation is enabled. CPU is affected and MD_CLEAR is not + advertised in CPUID. That is mainly for virtualization + scenarios where the host has the updated microcode but the + hypervisor does not expose MD_CLEAR in CPUID. It's a best + effort approach without guarantee. + ============= ============================================================ + +If the CPU is affected and the "tsx_async_abort" kernel command line parameter is +not provided then the kernel selects an appropriate mitigation depending on the +status of RTM and MD_CLEAR CPUID bits. + +Below tables indicate the impact of tsx=on|off|auto cmdline options on state of +TAA mitigation, VERW behavior and TSX feature for various combinations of +MSR_IA32_ARCH_CAPABILITIES bits. + +1. "tsx=off" + +========= ========= ============ ============ ============== =================== ====================== +MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=off +---------------------------------- ------------------------------------------------------------------------- +TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation + after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full +========= ========= ============ ============ ============== =================== ====================== + 0 0 0 HW default Yes Same as MDS Same as MDS + 0 0 1 Invalid case Invalid case Invalid case Invalid case + 0 1 0 HW default No Need ucode update Need ucode update + 0 1 1 Disabled Yes TSX disabled TSX disabled + 1 X 1 Disabled X None needed None needed +========= ========= ============ ============ ============== =================== ====================== + +2. "tsx=on" + +========= ========= ============ ============ ============== =================== ====================== +MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=on +---------------------------------- ------------------------------------------------------------------------- +TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation + after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full +========= ========= ============ ============ ============== =================== ====================== + 0 0 0 HW default Yes Same as MDS Same as MDS + 0 0 1 Invalid case Invalid case Invalid case Invalid case + 0 1 0 HW default No Need ucode update Need ucode update + 0 1 1 Enabled Yes None Same as MDS + 1 X 1 Enabled X None needed None needed +========= ========= ============ ============ ============== =================== ====================== + +3. "tsx=auto" + +========= ========= ============ ============ ============== =================== ====================== +MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=auto +---------------------------------- ------------------------------------------------------------------------- +TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation + after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full +========= ========= ============ ============ ============== =================== ====================== + 0 0 0 HW default Yes Same as MDS Same as MDS + 0 0 1 Invalid case Invalid case Invalid case Invalid case + 0 1 0 HW default No Need ucode update Need ucode update + 0 1 1 Disabled Yes TSX disabled TSX disabled + 1 X 1 Enabled X None needed None needed +========= ========= ============ ============ ============== =================== ====================== + +In the tables, TSX_CTRL_MSR is a new bit in MSR_IA32_ARCH_CAPABILITIES that +indicates whether MSR_IA32_TSX_CTRL is supported. + +There are two control bits in IA32_TSX_CTRL MSR: + + Bit 0: When set it disables the Restricted Transactional Memory (RTM) + sub-feature of TSX (will force all transactions to abort on the + XBEGIN instruction). + + Bit 1: When set it disables the enumeration of the RTM and HLE feature + (i.e. it will make CPUID(EAX=7).EBX{bit4} and + CPUID(EAX=7).EBX{bit11} read as 0). diff --git a/MAINTAINERS b/MAINTAINERS index a9fdec7aa27d..598749df53e2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -643,7 +643,7 @@ F: drivers/net/ethernet/alacritech/* FORCEDETH GIGABIT ETHERNET DRIVER M: Rain River <rain.1986.08.12@gmail.com> -M: Zhu Yanjun <yanjun.zhu@oracle.com> +M: Zhu Yanjun <zyjzyj2000@gmail.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/nvidia/* @@ -2323,11 +2323,13 @@ F: drivers/edac/altera_edac. ARM/SPREADTRUM SoC SUPPORT M: Orson Zhai <orsonzhai@gmail.com> -M: Baolin Wang <baolin.wang@linaro.org> +M: Baolin Wang <baolin.wang7@gmail.com> M: Chunyan Zhang <zhang.lyra@gmail.com> S: Maintained F: arch/arm64/boot/dts/sprd N: sprd +N: sc27xx +N: sc2731 ARM/STI ARCHITECTURE M: Patrice Chotard <patrice.chotard@st.com> @@ -3051,6 +3053,7 @@ M: Daniel Borkmann <daniel@iogearbox.net> R: Martin KaFai Lau <kafai@fb.com> R: Song Liu <songliubraving@fb.com> R: Yonghong Song <yhs@fb.com> +R: Andrii Nakryiko <andriin@fb.com> L: netdev@vger.kernel.org L: bpf@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git @@ -3096,7 +3099,7 @@ S: Supported F: arch/arm64/net/ BPF JIT for MIPS (32-BIT AND 64-BIT) -M: Paul Burton <paul.burton@mips.com> +M: Paul Burton <paulburton@kernel.org> L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Maintained @@ -3183,7 +3186,7 @@ N: bcm216* N: kona F: arch/arm/mach-bcm/ -BROADCOM BCM2835 ARM ARCHITECTURE +BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE M: Eric Anholt <eric@anholt.net> M: Stefan Wahren <wahrenst@gmx.net> L: bcm-kernel-feedback-list@broadcom.com @@ -3191,6 +3194,7 @@ L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/anholt/linux S: Maintained +N: bcm2711 N: bcm2835 F: drivers/staging/vc04_services @@ -3237,8 +3241,6 @@ S: Maintained F: drivers/usb/gadget/udc/bcm63xx_udc.* BROADCOM BCM7XXX ARM ARCHITECTURE -M: Brian Norris <computersforpeace@gmail.com> -M: Gregory Fong <gregory.0xf0@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> M: bcm-kernel-feedback-list@broadcom.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -3259,7 +3261,6 @@ S: Maintained F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE -M: Kevin Cernekee <cernekee@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> L: bcm-kernel-feedback-list@broadcom.com L: linux-mips@vger.kernel.org @@ -3743,7 +3744,6 @@ F: drivers/crypto/cavium/cpt/ CAVIUM THUNDERX2 ARM64 SOC M: Robert Richter <rrichter@cavium.com> -M: Jayachandran C <jnair@caviumnetworks.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm64/boot/dts/cavium/thunder2-99xx* @@ -8008,7 +8008,7 @@ S: Maintained F: drivers/usb/atm/ueagle-atm.c IMGTEC ASCII LCD DRIVER -M: Paul Burton <paul.burton@mips.com> +M: Paul Burton <paulburton@kernel.org> S: Maintained F: Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt F: drivers/auxdisplay/img-ascii-lcd.c @@ -8305,11 +8305,14 @@ F: drivers/hid/intel-ish-hid/ INTEL IOMMU (VT-d) M: David Woodhouse <dwmw2@infradead.org> +M: Lu Baolu <baolu.lu@linux.intel.com> L: iommu@lists.linux-foundation.org -T: git git://git.infradead.org/iommu-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git S: Supported -F: drivers/iommu/intel-iommu.c +F: drivers/iommu/dmar.c +F: drivers/iommu/intel*.[ch] F: include/linux/intel-iommu.h +F: include/linux/intel-svm.h INTEL IOP-ADMA DMA DRIVER R: Dan Williams <dan.j.williams@intel.com> @@ -8568,12 +8571,13 @@ F: include/linux/iova.h IO_URING M: Jens Axboe <axboe@kernel.dk> -L: linux-block@vger.kernel.org -L: linux-fsdevel@vger.kernel.org +L: io-uring@vger.kernel.org T: git git://git.kernel.dk/linux-block T: git git://git.kernel.dk/liburing S: Maintained F: fs/io_uring.c +F: fs/io-wq.c +F: fs/io-wq.h F: include/uapi/linux/io_uring.h IPMI SUBSYSTEM @@ -10525,8 +10529,12 @@ F: mm/memblock.c F: Documentation/core-api/boot-time-mm.rst MEMORY MANAGEMENT +M: Andrew Morton <akpm@linux-foundation.org> L: linux-mm@kvack.org W: http://www.linux-mm.org +T: quilt https://ozlabs.org/~akpm/mmotm/ +T: quilt https://ozlabs.org/~akpm/mmots/ +T: git git://github.com/hnaz/linux-mm.git S: Maintained F: include/linux/mm.h F: include/linux/gfp.h @@ -10833,7 +10841,7 @@ F: drivers/usb/image/microtek.* MIPS M: Ralf Baechle <ralf@linux-mips.org> -M: Paul Burton <paul.burton@mips.com> +M: Paul Burton <paulburton@kernel.org> M: James Hogan <jhogan@kernel.org> L: linux-mips@vger.kernel.org W: http://www.linux-mips.org/ @@ -10847,7 +10855,7 @@ F: arch/mips/ F: drivers/platform/mips/ MIPS BOSTON DEVELOPMENT BOARD -M: Paul Burton <paul.burton@mips.com> +M: Paul Burton <paulburton@kernel.org> L: linux-mips@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/clock/img,boston-clock.txt @@ -10857,7 +10865,7 @@ F: drivers/clk/imgtec/clk-boston.c F: include/dt-bindings/clock/boston-clock.h MIPS GENERIC PLATFORM -M: Paul Burton <paul.burton@mips.com> +M: Paul Burton <paulburton@kernel.org> L: linux-mips@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/power/mti,mips-cpc.txt @@ -11412,7 +11420,6 @@ F: include/trace/events/tcp.h NETWORKING [TLS] M: Boris Pismenny <borisp@mellanox.com> M: Aviad Yehezkel <aviadye@mellanox.com> -M: Dave Watson <davejwatson@fb.com> M: John Fastabend <john.fastabend@gmail.com> M: Daniel Borkmann <daniel@iogearbox.net> M: Jakub Kicinski <jakub.kicinski@netronome.com> @@ -11636,6 +11643,7 @@ F: drivers/nvme/target/fcloop.c NVM EXPRESS TARGET DRIVER M: Christoph Hellwig <hch@lst.de> M: Sagi Grimberg <sagi@grimberg.me> +M: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> L: linux-nvme@lists.infradead.org T: git://git.infradead.org/nvme.git W: http://git.infradead.org/nvme.git @@ -13910,7 +13918,7 @@ F: drivers/mtd/nand/raw/r852.h RISC-V ARCHITECTURE M: Paul Walmsley <paul.walmsley@sifive.com> -M: Palmer Dabbelt <palmer@sifive.com> +M: Palmer Dabbelt <palmer@dabbelt.com> M: Albert Ou <aou@eecs.berkeley.edu> L: linux-riscv@lists.infradead.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git @@ -14787,7 +14795,7 @@ F: drivers/media/usb/siano/ F: drivers/media/mmc/siano/ SIFIVE DRIVERS -M: Palmer Dabbelt <palmer@sifive.com> +M: Palmer Dabbelt <palmer@dabbelt.com> M: Paul Walmsley <paul.walmsley@sifive.com> L: linux-riscv@lists.infradead.org T: git git://github.com/sifive/riscv-linux.git @@ -14797,7 +14805,7 @@ N: sifive SIFIVE FU540 SYSTEM-ON-CHIP M: Paul Walmsley <paul.walmsley@sifive.com> -M: Palmer Dabbelt <palmer@sifive.com> +M: Palmer Dabbelt <palmer@dabbelt.com> L: linux-riscv@lists.infradead.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/pjw/sifive.git S: Supported @@ -17212,6 +17220,7 @@ F: virt/lib/ VIRTIO AND VHOST VSOCK DRIVER M: Stefan Hajnoczi <stefanha@redhat.com> +M: Stefano Garzarella <sgarzare@redhat.com> L: kvm@vger.kernel.org L: virtualization@lists.linux-foundation.org L: netdev@vger.kernel.org @@ -18037,6 +18046,7 @@ F: Documentation/vm/zsmalloc.rst ZSWAP COMPRESSED SWAP CACHING M: Seth Jennings <sjenning@redhat.com> M: Dan Streetman <ddstreet@ieee.org> +M: Vitaly Wool <vitaly.wool@konsulko.com> L: linux-mm@kvack.org S: Maintained F: mm/zswap.c @@ -2,8 +2,8 @@ VERSION = 5 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc4 -NAME = Nesting Opossum +EXTRAVERSION = +NAME = Kleptomaniac Octopus # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -917,6 +917,9 @@ ifeq ($(CONFIG_RELR),y) LDFLAGS_vmlinux += --pack-dyn-relocs=relr endif +# make the checker run with the right architecture +CHECKFLAGS += --arch=$(ARCH) + # insure the checker run with the right endianness CHECKFLAGS += $(if $(CONFIG_CPU_BIG_ENDIAN),-mbig-endian,-mlittle-endian) diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index bfc7f5f5d6f2..9acbeba832c0 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -65,6 +65,14 @@ clock-frequency = <33333333>; }; + reg_5v0: regulator-5v0 { + compatible = "regulator-fixed"; + + regulator-name = "5v0-supply"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + cpu_intc: cpu-interrupt-controller { compatible = "snps,archs-intc"; interrupt-controller; @@ -264,6 +272,21 @@ clocks = <&input_clk>; cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>, <&creg_gpio 1 GPIO_ACTIVE_LOW>; + + spi-flash@0 { + compatible = "sst26wf016b", "jedec,spi-nor"; + reg = <0>; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <4000000>; + }; + + adc@1 { + compatible = "ti,adc108s102"; + reg = <1>; + vref-supply = <®_5v0>; + spi-max-frequency = <1000000>; + }; }; creg_gpio: gpio@14b0 { diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 9b9a74444ce2..0974226fab55 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -32,6 +32,8 @@ CONFIG_INET=y CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set +CONFIG_MTD=y +CONFIG_MTD_SPI_NOR=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -55,6 +57,8 @@ CONFIG_GPIO_SYSFS=y CONFIG_GPIO_DWAPB=y CONFIG_GPIO_SNPS_CREG=y # CONFIG_HWMON is not set +CONFIG_REGULATOR=y +CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_DRM=y # CONFIG_DRM_FBDEV_EMULATION is not set CONFIG_DRM_UDL=y @@ -72,6 +76,8 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y CONFIG_DMADEVICES=y CONFIG_DW_AXI_DMAC=y +CONFIG_IIO=y +CONFIG_TI_ADC108S102=y CONFIG_EXT3_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 861a8aea51f9..661fd842ea97 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -614,8 +614,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev) /* loop thru all available h/w condition indexes */ for (i = 0; i < cc_bcr.c; i++) { write_aux_reg(ARC_REG_CC_INDEX, i); - cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); - cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); + cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0)); + cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1)); arc_pmu_map_hw_event(i, cc_name.str); arc_pmu_add_raw_event_attr(i, cc_name.str); diff --git a/arch/arm/boot/dts/am3874-iceboard.dts b/arch/arm/boot/dts/am3874-iceboard.dts index 883fb85135d4..1b4b2b0500e4 100644 --- a/arch/arm/boot/dts/am3874-iceboard.dts +++ b/arch/arm/boot/dts/am3874-iceboard.dts @@ -111,13 +111,13 @@ reg = <0x70>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c@0 { /* FMC A */ #address-cells = <1>; #size-cells = <0>; reg = <0>; - i2c-mux-idle-disconnect; }; i2c@1 { @@ -125,7 +125,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <1>; - i2c-mux-idle-disconnect; }; i2c@2 { @@ -133,7 +132,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <2>; - i2c-mux-idle-disconnect; }; i2c@3 { @@ -141,7 +139,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <3>; - i2c-mux-idle-disconnect; }; i2c@4 { @@ -149,14 +146,12 @@ #address-cells = <1>; #size-cells = <0>; reg = <4>; - i2c-mux-idle-disconnect; }; i2c@5 { #address-cells = <1>; #size-cells = <0>; reg = <5>; - i2c-mux-idle-disconnect; ina230@40 { compatible = "ti,ina230"; reg = <0x40>; shunt-resistor = <5000>; }; ina230@41 { compatible = "ti,ina230"; reg = <0x41>; shunt-resistor = <5000>; }; @@ -182,14 +177,12 @@ #address-cells = <1>; #size-cells = <0>; reg = <6>; - i2c-mux-idle-disconnect; }; i2c@7 { #address-cells = <1>; #size-cells = <0>; reg = <7>; - i2c-mux-idle-disconnect; u41: pca9575@20 { compatible = "nxp,pca9575"; diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts index 09a088f98566..b75af21069f9 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts @@ -113,6 +113,7 @@ #address-cells = <1>; #size-cells = <0>; pinctrl-0 = <&emmc_gpio34 &gpclk2_gpio43>; + bus-width = <4>; mmc-pwrseq = <&wifi_pwrseq>; non-removable; status = "okay"; diff --git a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi index 7c3cb7ece6cb..925cb37c22f0 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi +++ b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi @@ -9,6 +9,14 @@ reg = <0 0x40000000>; }; + leds { + /* + * Since there is no upstream GPIO driver yet, + * remove the incomplete node. + */ + /delete-node/ act; + }; + reg_3v3: fixed-regulator { compatible = "regulator-fixed"; regulator-name = "3V3"; diff --git a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi index 2a6ce87071f9..9e027b9a5f91 100644 --- a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi +++ b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi @@ -328,6 +328,10 @@ pinctrl-0 = <&pinctrl_pwm3>; }; +&snvs_pwrkey { + status = "okay"; +}; + &ssi2 { status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6-logicpd-som.dtsi b/arch/arm/boot/dts/imx6-logicpd-som.dtsi index 7ceae3573248..547fb141ec0c 100644 --- a/arch/arm/boot/dts/imx6-logicpd-som.dtsi +++ b/arch/arm/boot/dts/imx6-logicpd-som.dtsi @@ -207,6 +207,10 @@ vin-supply = <&sw1c_reg>; }; +&snvs_poweroff { + status = "okay"; +}; + &iomuxc { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_hog>; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index f3404dd10537..cf628465cd0a 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -230,6 +230,8 @@ accelerometer@1c { compatible = "fsl,mma8451"; reg = <0x1c>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_mma8451_int>; interrupt-parent = <&gpio6>; interrupts = <31 IRQ_TYPE_LEVEL_LOW>; }; @@ -628,6 +630,12 @@ >; }; + pinctrl_mma8451_int: mma8451intgrp { + fsl,pins = < + MX6QDL_PAD_EIM_BCLK__GPIO6_IO31 0xb0b1 + >; + }; + pinctrl_pwm3: pwm1grp { fsl,pins = < MX6QDL_PAD_SD4_DAT1__PWM3_OUT 0x1b0b1 diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 710f850e785c..e2e604d6ba0b 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -448,7 +448,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302d0000 0x10000>; interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT1_ROOT_CLK>, <&clks IMX7D_GPT1_ROOT_CLK>; clock-names = "ipg", "per"; }; @@ -457,7 +457,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302e0000 0x10000>; interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT2_ROOT_CLK>, <&clks IMX7D_GPT2_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; @@ -467,7 +467,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302f0000 0x10000>; interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT3_ROOT_CLK>, <&clks IMX7D_GPT3_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; @@ -477,7 +477,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x30300000 0x10000>; interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT4_ROOT_CLK>, <&clks IMX7D_GPT4_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 3fdd0a72f87f..506b118e511a 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -192,3 +192,7 @@ &twl_gpio { ti,use-leds; }; + +&twl_keypad { + status = "disabled"; +}; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 4454449de00c..a40fe8d49da6 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -369,7 +369,7 @@ compatible = "ti,wl1285", "ti,wl1283"; reg = <2>; /* gpio_100 with gpmc_wait2 pad as wakeirq */ - interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>, + interrupts-extended = <&gpio4 4 IRQ_TYPE_LEVEL_HIGH>, <&omap4_pmx_core 0x4e>; interrupt-names = "irq", "wakeup"; ref-clock-frequency = <26000000>; diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi index 14be2ecb62b1..55ea8b6189af 100644 --- a/arch/arm/boot/dts/omap4-panda-common.dtsi +++ b/arch/arm/boot/dts/omap4-panda-common.dtsi @@ -474,7 +474,7 @@ compatible = "ti,wl1271"; reg = <2>; /* gpio_53 with gpmc_ncs3 pad as wakeup */ - interrupts-extended = <&gpio2 21 IRQ_TYPE_EDGE_RISING>, + interrupts-extended = <&gpio2 21 IRQ_TYPE_LEVEL_HIGH>, <&omap4_pmx_core 0x3a>; interrupt-names = "irq", "wakeup"; ref-clock-frequency = <38400000>; diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts index 3c274965ff40..91480ac1f328 100644 --- a/arch/arm/boot/dts/omap4-sdp.dts +++ b/arch/arm/boot/dts/omap4-sdp.dts @@ -512,7 +512,7 @@ compatible = "ti,wl1281"; reg = <2>; interrupt-parent = <&gpio1>; - interrupts = <21 IRQ_TYPE_EDGE_RISING>; /* gpio 53 */ + interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; /* gpio 53 */ ref-clock-frequency = <26000000>; tcxo-clock-frequency = <26000000>; }; diff --git a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi index 6dbbc9b3229c..d0032213101e 100644 --- a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi +++ b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi @@ -69,7 +69,7 @@ compatible = "ti,wl1271"; reg = <2>; interrupt-parent = <&gpio2>; - interrupts = <9 IRQ_TYPE_EDGE_RISING>; /* gpio 41 */ + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; /* gpio 41 */ ref-clock-frequency = <38400000>; }; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 7fff555ee394..68ac04641bdb 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -362,7 +362,7 @@ pinctrl-names = "default"; pinctrl-0 = <&wlcore_irq_pin>; interrupt-parent = <&gpio1>; - interrupts = <14 IRQ_TYPE_EDGE_RISING>; /* gpio 14 */ + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>; /* gpio 14 */ ref-clock-frequency = <26000000>; }; }; diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi index fac2e57dcca9..4791834dacb2 100644 --- a/arch/arm/boot/dts/omap54xx-clocks.dtsi +++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi @@ -1146,7 +1146,7 @@ }; }; - gpu_cm: clock-controller@1500 { + gpu_cm: gpu_cm@1500 { compatible = "ti,omap4-cm"; reg = <0x1500 0x100>; #address-cells = <1>; diff --git a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi index e4a0d51ec3a8..0a3a7d66737b 100644 --- a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi @@ -609,13 +609,13 @@ <STM32_PINMUX('F', 6, AF9)>; /* QSPI_BK1_IO3 */ bias-disable; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; pins2 { pinmux = <STM32_PINMUX('B', 6, AF10)>; /* QSPI_BK1_NCS */ bias-pull-up; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; }; @@ -637,13 +637,13 @@ <STM32_PINMUX('G', 7, AF11)>; /* QSPI_BK2_IO3 */ bias-disable; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; pins2 { pinmux = <STM32_PINMUX('C', 0, AF10)>; /* QSPI_BK2_NCS */ bias-pull-up; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; }; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index 89d29b50c3f4..91fc0a315c49 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -183,14 +183,12 @@ ov5640: camera@3c { compatible = "ovti,ov5640"; - pinctrl-names = "default"; - pinctrl-0 = <&ov5640_pins>; reg = <0x3c>; clocks = <&clk_ext_camera>; clock-names = "xclk"; DOVDD-supply = <&v2v8>; - powerdown-gpios = <&stmfx_pinctrl 18 GPIO_ACTIVE_HIGH>; - reset-gpios = <&stmfx_pinctrl 19 GPIO_ACTIVE_LOW>; + powerdown-gpios = <&stmfx_pinctrl 18 (GPIO_ACTIVE_HIGH | GPIO_PUSH_PULL)>; + reset-gpios = <&stmfx_pinctrl 19 (GPIO_ACTIVE_LOW | GPIO_PUSH_PULL)>; rotation = <180>; status = "okay"; @@ -223,15 +221,8 @@ joystick_pins: joystick { pins = "gpio0", "gpio1", "gpio2", "gpio3", "gpio4"; - drive-push-pull; bias-pull-down; }; - - ov5640_pins: camera { - pins = "agpio2", "agpio3"; /* stmfx pins 18 & 19 */ - drive-push-pull; - output-low; - }; }; }; }; diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi index 9b11654a0a39..f98e0370c0bc 100644 --- a/arch/arm/boot/dts/stm32mp157c.dtsi +++ b/arch/arm/boot/dts/stm32mp157c.dtsi @@ -932,7 +932,7 @@ interrupt-names = "int0", "int1"; clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>; clock-names = "hclk", "cclk"; - bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>; + bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>; status = "disabled"; }; @@ -945,7 +945,7 @@ interrupt-names = "int0", "int1"; clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>; clock-names = "hclk", "cclk"; - bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>; + bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 874231be04e4..8aebefd6accf 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -380,9 +380,8 @@ compatible = "allwinner,sun7i-a20-csi0"; reg = <0x01c09000 0x1000>; interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI0>, - <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>; - clock-names = "bus", "mod", "isp", "ram"; + clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>; + clock-names = "bus", "isp", "ram"; resets = <&ccu RST_CSI0>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts index 568b90ece342..3bec3e0a81b2 100644 --- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts +++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts @@ -192,6 +192,7 @@ vqmmc-supply = <®_dldo1>; non-removable; wakeup-source; + keep-power-in-suspend; status = "okay"; brcmf: wifi@1 { diff --git a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts index dc8a5f37a1ef..c8ebb23c4e02 100644 --- a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts +++ b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts @@ -602,6 +602,7 @@ #address-cells = <1>; #size-cells = <0>; reg = <0x70>; + i2c-mux-idle-disconnect; sff0_i2c: i2c@1 { #address-cells = <1>; @@ -640,6 +641,7 @@ reg = <0x71>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; sff5_i2c: i2c@1 { #address-cells = <1>; diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index 01e3c0f4be92..231f8973bbb2 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -167,6 +167,7 @@ CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_DA8XX=y CONFIG_BACKLIGHT_PWM=m +CONFIG_BACKLIGHT_GPIO=m CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 9bfffbe22d53..0f7381ee0c37 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -276,6 +276,7 @@ CONFIG_VIDEO_OV5640=m CONFIG_VIDEO_OV5645=m CONFIG_IMX_IPUV3_CORE=y CONFIG_DRM=y +CONFIG_DRM_MSM=y CONFIG_DRM_PANEL_LVDS=y CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_PANEL_SEIKO_43WVF1G=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index d3f50971e451..40d7f1a4fc45 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -356,15 +356,15 @@ CONFIG_DRM_OMAP_CONNECTOR_HDMI=m CONFIG_DRM_OMAP_CONNECTOR_ANALOG_TV=m CONFIG_DRM_OMAP_PANEL_DPI=m CONFIG_DRM_OMAP_PANEL_DSI_CM=m -CONFIG_DRM_OMAP_PANEL_SONY_ACX565AKM=m -CONFIG_DRM_OMAP_PANEL_LGPHILIPS_LB035Q02=m -CONFIG_DRM_OMAP_PANEL_SHARP_LS037V7DW01=m -CONFIG_DRM_OMAP_PANEL_TPO_TD028TTEC1=m -CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m -CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m CONFIG_DRM_TILCDC=m CONFIG_DRM_PANEL_SIMPLE=m CONFIG_DRM_TI_TFP410=m +CONFIG_DRM_PANEL_LG_LB035Q02=m +CONFIG_DRM_PANEL_NEC_NL8048HL11=m +CONFIG_DRM_PANEL_SHARP_LS037V7DW01=m +CONFIG_DRM_PANEL_SONY_ACX565AKM=m +CONFIG_DRM_PANEL_TPO_TD028TTEC1=m +CONFIG_DRM_PANEL_TPO_TD043MTEA1=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MODE_HELPERS=y diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h index 567dbede4785..f1d0a7807cd0 100644 --- a/arch/arm/include/asm/domain.h +++ b/arch/arm/include/asm/domain.h @@ -82,7 +82,7 @@ #ifndef __ASSEMBLY__ #ifdef CONFIG_CPU_CP15_MMU -static inline unsigned int get_domain(void) +static __always_inline unsigned int get_domain(void) { unsigned int domain; @@ -94,7 +94,7 @@ static inline unsigned int get_domain(void) return domain; } -static inline void set_domain(unsigned val) +static __always_inline void set_domain(unsigned int val) { asm volatile( "mcr p15, 0, %0, c3, c0 @ set domain" @@ -102,12 +102,12 @@ static inline void set_domain(unsigned val) isb(); } #else -static inline unsigned int get_domain(void) +static __always_inline unsigned int get_domain(void) { return 0; } -static inline void set_domain(unsigned val) +static __always_inline void set_domain(unsigned int val) { } #endif diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 303248e5b990..98c6b91be4a8 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -22,7 +22,7 @@ * perform such accesses (eg, via list poison values) which could then * be exploited for priviledge escalation. */ -static inline unsigned int uaccess_save_and_enable(void) +static __always_inline unsigned int uaccess_save_and_enable(void) { #ifdef CONFIG_CPU_SW_DOMAIN_PAN unsigned int old_domain = get_domain(); @@ -37,7 +37,7 @@ static inline unsigned int uaccess_save_and_enable(void) #endif } -static inline void uaccess_restore(unsigned int flags) +static __always_inline void uaccess_restore(unsigned int flags) { #ifdef CONFIG_CPU_SW_DOMAIN_PAN /* Restore the user access mask */ diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index a7810be07da1..4a3982812a40 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -68,7 +68,7 @@ ENDPROC(__vet_atags) * The following fragment of code is executed with the MMU on in MMU mode, * and uses absolute addresses; this is not position independent. * - * r0 = cp#15 control register + * r0 = cp#15 control register (exc_ret for M-class) * r1 = machine ID * r2 = atags/dtb pointer * r9 = processor ID @@ -137,7 +137,8 @@ __mmap_switched_data: #ifdef CONFIG_CPU_CP15 .long cr_alignment @ r3 #else - .long 0 @ r3 +M_CLASS(.long exc_ret) @ r3 +AR_CLASS(.long 0) @ r3 #endif .size __mmap_switched_data, . - __mmap_switched_data diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index afa350f44dea..0fc814bbc34b 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -201,6 +201,8 @@ M_CLASS(streq r3, [r12, #PMSAv8_MAIR1]) bic r0, r0, #V7M_SCB_CCR_IC #endif str r0, [r12, V7M_SCB_CCR] + /* Pass exc_ret to __mmap_switched */ + mov r0, r10 #endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */ ret lr ENDPROC(__after_proc_init) diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c index 8062412be70f..9fc5c73cc0be 100644 --- a/arch/arm/mach-davinci/dm365.c +++ b/arch/arm/mach-davinci/dm365.c @@ -462,8 +462,8 @@ static s8 dm365_queue_priority_mapping[][2] = { }; static const struct dma_slave_map dm365_edma_map[] = { - { "davinci-mcbsp.0", "tx", EDMA_FILTER_PARAM(0, 2) }, - { "davinci-mcbsp.0", "rx", EDMA_FILTER_PARAM(0, 3) }, + { "davinci-mcbsp", "tx", EDMA_FILTER_PARAM(0, 2) }, + { "davinci-mcbsp", "rx", EDMA_FILTER_PARAM(0, 3) }, { "davinci_voicecodec", "tx", EDMA_FILTER_PARAM(0, 2) }, { "davinci_voicecodec", "rx", EDMA_FILTER_PARAM(0, 3) }, { "spi_davinci.2", "tx", EDMA_FILTER_PARAM(0, 10) }, diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index d942a3357090..2efd18e8824c 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -89,6 +89,13 @@ static struct iommu_platform_data omap3_iommu_pdata = { .reset_name = "mmu", .assert_reset = omap_device_assert_hardreset, .deassert_reset = omap_device_deassert_hardreset, + .device_enable = omap_device_enable, + .device_idle = omap_device_idle, +}; + +static struct iommu_platform_data omap3_iommu_isp_pdata = { + .device_enable = omap_device_enable, + .device_idle = omap_device_idle, }; static int omap3_sbc_t3730_twl_callback(struct device *dev, @@ -424,6 +431,8 @@ static struct iommu_platform_data omap4_iommu_pdata = { .reset_name = "mmu_cache", .assert_reset = omap_device_assert_hardreset, .deassert_reset = omap_device_deassert_hardreset, + .device_enable = omap_device_enable, + .device_idle = omap_device_idle, }; #endif @@ -617,6 +626,8 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = { #ifdef CONFIG_ARCH_OMAP3 OF_DEV_AUXDATA("ti,omap2-iommu", 0x5d000000, "5d000000.mmu", &omap3_iommu_pdata), + OF_DEV_AUXDATA("ti,omap2-iommu", 0x480bd400, "480bd400.mmu", + &omap3_iommu_isp_pdata), OF_DEV_AUXDATA("ti,omap3-smartreflex-core", 0x480cb000, "480cb000.smartreflex", &omap_sr_pdata[OMAP_SR_CORE]), OF_DEV_AUXDATA("ti,omap3-smartreflex-mpu-iva", 0x480c9000, diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index 239084cf8192..26cbce135338 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -481,14 +481,18 @@ static void sunxi_mc_smp_cpu_die(unsigned int l_cpu) static int sunxi_cpu_powerdown(unsigned int cpu, unsigned int cluster) { u32 reg; + int gating_bit = cpu; pr_debug("%s: cluster %u cpu %u\n", __func__, cluster, cpu); if (cpu >= SUNXI_CPUS_PER_CLUSTER || cluster >= SUNXI_NR_CLUSTERS) return -EINVAL; + if (is_a83t && cpu == 0) + gating_bit = 4; + /* gate processor power */ reg = readl(prcm_base + PRCM_PWROFF_GATING_REG(cluster)); - reg |= PRCM_PWROFF_GATING_REG_CORE(cpu); + reg |= PRCM_PWROFF_GATING_REG_CORE(gating_bit); writel(reg, prcm_base + PRCM_PWROFF_GATING_REG(cluster)); udelay(20); diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 04b36436cbc0..788c5cf46de5 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -324,7 +324,7 @@ union offset_union { __put32_unaligned_check("strbt", val, addr) static void -do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs *regs, union offset_union offset) +do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, union offset_union offset) { if (!LDST_U_BIT(instr)) offset.un = -offset.un; @@ -337,7 +337,7 @@ do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs } static int -do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *regs) +do_alignment_ldrhstrh(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd = RD_BITS(instr); @@ -386,8 +386,7 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r } static int -do_alignment_ldrdstrd(unsigned long addr, unsigned long instr, - struct pt_regs *regs) +do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd = RD_BITS(instr); unsigned int rd2; @@ -449,7 +448,7 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr, } static int -do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *regs) +do_alignment_ldrstr(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd = RD_BITS(instr); @@ -498,7 +497,7 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg * PU = 10 A B */ static int -do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *regs) +do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd, rn, correction, nr_regs, regbits; unsigned long eaddr, newaddr; @@ -539,7 +538,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg * processor for us. */ if (addr != eaddr) { - pr_err("LDMSTM: PC = %08lx, instr = %08lx, " + pr_err("LDMSTM: PC = %08lx, instr = %08x, " "addr = %08lx, eaddr = %08lx\n", instruction_pointer(regs), instr, addr, eaddr); show_regs(regs); @@ -716,10 +715,10 @@ thumb2arm(u16 tinstr) * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt) */ static void * -do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs, +do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs, union offset_union *poffset) { - unsigned long instr = *pinstr; + u32 instr = *pinstr; u16 tinst1 = (instr >> 16) & 0xffff; u16 tinst2 = instr & 0xffff; @@ -767,17 +766,48 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs, return NULL; } +static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst) +{ + u32 instr = 0; + int fault; + + if (user_mode(regs)) + fault = get_user(instr, ip); + else + fault = probe_kernel_address(ip, instr); + + *inst = __mem_to_opcode_arm(instr); + + return fault; +} + +static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst) +{ + u16 instr = 0; + int fault; + + if (user_mode(regs)) + fault = get_user(instr, ip); + else + fault = probe_kernel_address(ip, instr); + + *inst = __mem_to_opcode_thumb16(instr); + + return fault; +} + static int do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { union offset_union uninitialized_var(offset); - unsigned long instr = 0, instrptr; - int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs); + unsigned long instrptr; + int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs); unsigned int type; - unsigned int fault; + u32 instr = 0; u16 tinstr = 0; int isize = 4; int thumb2_32b = 0; + int fault; if (interrupts_enabled(regs)) local_irq_enable(); @@ -786,15 +816,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (thumb_mode(regs)) { u16 *ptr = (u16 *)(instrptr & ~1); - fault = probe_kernel_address(ptr, tinstr); - tinstr = __mem_to_opcode_thumb16(tinstr); + + fault = alignment_get_thumb(regs, ptr, &tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ - u16 tinst2 = 0; - fault = probe_kernel_address(ptr + 1, tinst2); - tinst2 = __mem_to_opcode_thumb16(tinst2); + u16 tinst2; + fault = alignment_get_thumb(regs, ptr + 1, &tinst2); instr = __opcode_thumb32_compose(tinstr, tinst2); thumb2_32b = 1; } else { @@ -803,8 +832,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) } } } else { - fault = probe_kernel_address((void *)instrptr, instr); - instr = __mem_to_opcode_arm(instr); + fault = alignment_get_arm(regs, (void *)instrptr, &instr); } if (fault) { @@ -926,7 +954,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) * Oops, we didn't handle the instruction. */ pr_err("Alignment trap: not handling instruction " - "%0*lx at [<%08lx>]\n", + "%0*x at [<%08lx>]\n", isize << 1, isize == 2 ? tinstr : instr, instrptr); ai_skipped += 1; @@ -936,7 +964,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) ai_user += 1; if (ai_usermode & UM_WARN) - printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx " + printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*x " "Address=0x%08lx FSR 0x%03x\n", current->comm, task_pid_nr(current), instrptr, isize << 1, diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 1448f144e7fb..1a49d503eafc 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -132,13 +132,11 @@ __v7m_setup_cont: dsb mov r6, lr @ save LR ldr sp, =init_thread_union + THREAD_START_SP - stmia sp, {r0-r3, r12} cpsie i svc #0 1: cpsid i - ldr r0, =exc_ret - orr lr, lr, #EXC_RET_THREADMODE_PROCESSSTACK - str lr, [r0] + /* Calculate exc_ret */ + orr r10, lr, #EXC_RET_THREADMODE_PROCESSSTACK ldmia sp, {r0-r3, r12} str r5, [r12, #11 * 4] @ restore the original SVC vector entry mov lr, r6 @ restore LR diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index 24f1aac366d6..d5b6e8159a33 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -63,3 +63,12 @@ reg = <1>; }; }; + +®_dc1sw { + /* + * Ethernet PHY needs 30ms to properly power up and some more + * to initialize. 100ms should be plenty of time to finish + * whole process. + */ + regulator-enable-ramp-delay = <100000>; +}; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts index e6fb9683f213..25099202c52c 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts @@ -159,6 +159,12 @@ }; ®_dc1sw { + /* + * Ethernet PHY needs 30ms to properly power up and some more + * to initialize. 100ms should be plenty of time to finish + * whole process. + */ + regulator-enable-ramp-delay = <100000>; regulator-name = "vcc-phy"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 3eccbdba7154..70f4cce6be43 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -142,15 +142,6 @@ clock-output-names = "ext-osc32k"; }; - pmu { - compatible = "arm,cortex-a53-pmu"; - interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>; - interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>; - }; - psci { compatible = "arm,psci-0.2"; method = "smc"; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi index 8a3a770e8f2c..56789ccf9454 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi @@ -42,13 +42,14 @@ pinmux: pinmux@14029c { compatible = "pinctrl-single"; - reg = <0x0014029c 0x250>; + reg = <0x0014029c 0x26c>; #address-cells = <1>; #size-cells = <1>; pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0xf>; pinctrl-single,gpio-range = < - &range 0 154 MODE_GPIO + &range 0 91 MODE_GPIO + &range 95 60 MODE_GPIO >; range: gpio-range { #pinctrl-single,gpio-range-cells = <3>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index 71e2e34400d4..0098dfdef96c 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -464,8 +464,7 @@ <&pinmux 108 16 27>, <&pinmux 135 77 6>, <&pinmux 141 67 4>, - <&pinmux 145 149 6>, - <&pinmux 151 91 4>; + <&pinmux 145 149 6>; }; i2c1: i2c@e0000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts index d98346da01df..078a5010228c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts @@ -127,7 +127,7 @@ status = "okay"; i2c-mux@77 { - compatible = "nxp,pca9847"; + compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 408e0ecdce6a..b032f3890c8c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -33,7 +33,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster0_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@1 { @@ -49,7 +49,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster0_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@100 { @@ -65,7 +65,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster1_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@101 { @@ -81,7 +81,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster1_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@200 { @@ -97,7 +97,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster2_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@201 { @@ -113,7 +113,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster2_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@300 { @@ -129,7 +129,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster3_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@301 { @@ -145,7 +145,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster3_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@400 { @@ -161,7 +161,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster4_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@401 { @@ -177,7 +177,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster4_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@500 { @@ -193,7 +193,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster5_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@501 { @@ -209,7 +209,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster5_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@600 { @@ -225,7 +225,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster6_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@601 { @@ -241,7 +241,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster6_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@700 { @@ -257,7 +257,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster7_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@701 { @@ -273,7 +273,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster7_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cluster0_l2: l2-cache0 { @@ -340,9 +340,9 @@ cache-level = <2>; }; - cpu_pw20: cpu-pw20 { + cpu_pw15: cpu-pw15 { compatible = "arm,idle-state"; - idle-state-name = "PW20"; + idle-state-name = "PW15"; arm,psci-suspend-param = <0x0>; entry-latency-us = <2000>; exit-latency-us = <2000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index 5f9d0da196e1..23c8fad7932b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -394,7 +394,7 @@ }; sdma2: dma-controller@302c0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x302c0000 0x10000>; interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA2_ROOT>, @@ -405,7 +405,7 @@ }; sdma3: dma-controller@302b0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x302b0000 0x10000>; interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA3_ROOT>, @@ -694,7 +694,7 @@ compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b40000 0x10000>; interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MM_CLK_DUMMY>, + clocks = <&clk IMX8MM_CLK_IPG_ROOT>, <&clk IMX8MM_CLK_NAND_USDHC_BUS>, <&clk IMX8MM_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -710,7 +710,7 @@ compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b50000 0x10000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MM_CLK_DUMMY>, + clocks = <&clk IMX8MM_CLK_IPG_ROOT>, <&clk IMX8MM_CLK_NAND_USDHC_BUS>, <&clk IMX8MM_CLK_USDHC2_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -724,7 +724,7 @@ compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b60000 0x10000>; interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MM_CLK_DUMMY>, + clocks = <&clk IMX8MM_CLK_IPG_ROOT>, <&clk IMX8MM_CLK_NAND_USDHC_BUS>, <&clk IMX8MM_CLK_USDHC3_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -737,7 +737,7 @@ }; sdma1: dma-controller@30bd0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>, diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 785f4c420fa4..43c4db312146 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -288,7 +288,7 @@ }; sdma3: dma-controller@302b0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x302b0000 0x10000>; interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA3_ROOT>, @@ -299,7 +299,7 @@ }; sdma2: dma-controller@302c0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x302c0000 0x10000>; interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA2_ROOT>, @@ -569,7 +569,7 @@ compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b40000 0x10000>; interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_DUMMY>, + clocks = <&clk IMX8MN_CLK_IPG_ROOT>, <&clk IMX8MN_CLK_NAND_USDHC_BUS>, <&clk IMX8MN_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -585,7 +585,7 @@ compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b50000 0x10000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_DUMMY>, + clocks = <&clk IMX8MN_CLK_IPG_ROOT>, <&clk IMX8MN_CLK_NAND_USDHC_BUS>, <&clk IMX8MN_CLK_USDHC2_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -599,7 +599,7 @@ compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b60000 0x10000>; interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_DUMMY>, + clocks = <&clk IMX8MN_CLK_IPG_ROOT>, <&clk IMX8MN_CLK_NAND_USDHC_BUS>, <&clk IMX8MN_CLK_USDHC3_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -612,7 +612,7 @@ }; sdma1: dma-controller@30bd0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi index af99473ada04..32ce14936b01 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi @@ -88,9 +88,9 @@ regulator-name = "0V9_ARM"; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1000000>; - gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>; - states = <1000000 0x0 - 900000 0x1>; + gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>; + states = <1000000 0x1 + 900000 0x0>; regulator-always-on; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 04115ca6bfb5..55a3d1c4bdf0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -850,7 +850,7 @@ "fsl,imx7d-usdhc"; reg = <0x30b40000 0x10000>; interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MQ_CLK_DUMMY>, + clocks = <&clk IMX8MQ_CLK_IPG_ROOT>, <&clk IMX8MQ_CLK_NAND_USDHC_BUS>, <&clk IMX8MQ_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -867,7 +867,7 @@ "fsl,imx7d-usdhc"; reg = <0x30b50000 0x10000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MQ_CLK_DUMMY>, + clocks = <&clk IMX8MQ_CLK_IPG_ROOT>, <&clk IMX8MQ_CLK_NAND_USDHC_BUS>, <&clk IMX8MQ_CLK_USDHC2_ROOT>; clock-names = "ipg", "ahb", "per"; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index d105986c6be1..5f350cc71a2f 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -60,11 +60,6 @@ gpio = <&gpiosb 0 GPIO_ACTIVE_HIGH>; }; - usb3_phy: usb3-phy { - compatible = "usb-nop-xceiv"; - vcc-supply = <&exp_usb3_vbus>; - }; - vsdc_reg: vsdc-reg { compatible = "regulator-gpio"; regulator-name = "vsdc"; @@ -255,10 +250,16 @@ status = "okay"; }; +&comphy2 { + connector { + compatible = "usb-a-connector"; + phy-supply = <&exp_usb3_vbus>; + }; +}; + &usb3 { status = "okay"; phys = <&comphy2 0>; - usb-phy = <&usb3_phy>; }; &mdio { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts index e152b0ca0290..b8066868a3fe 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts @@ -44,7 +44,7 @@ power-supply = <&pp3300_disp>; panel-timing { - clock-frequency = <266604720>; + clock-frequency = <266666667>; hactive = <2400>; hfront-porch = <48>; hback-porch = <84>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts index 0d1f5f9a0de9..c133e8d64b2a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts @@ -644,7 +644,7 @@ status = "okay"; u2phy0_host: host-port { - phy-supply = <&vcc5v0_host>; + phy-supply = <&vcc5v0_typec>; status = "okay"; }; @@ -712,7 +712,7 @@ &usbdrd_dwc3_0 { status = "okay"; - dr_mode = "otg"; + dr_mode = "host"; }; &usbdrd3_1 { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts index 0401d4ec1f45..e544deb61d28 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts @@ -173,7 +173,7 @@ regulator-always-on; regulator-boot-on; regulator-min-microvolt = <800000>; - regulator-max-microvolt = <1400000>; + regulator-max-microvolt = <1700000>; vin-supply = <&vcc5v0_sys>; }; }; @@ -247,8 +247,8 @@ rk808: pmic@1b { compatible = "rockchip,rk808"; reg = <0x1b>; - interrupt-parent = <&gpio1>; - interrupts = <21 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&gpio3>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; #clock-cells = <1>; clock-output-names = "xin32k", "rk808-clkout2"; pinctrl-names = "default"; @@ -574,7 +574,7 @@ pmic { pmic_int_l: pmic-int-l { - rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>; + rockchip,pins = <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>; }; vsel1_gpio: vsel1-gpio { @@ -624,7 +624,6 @@ &sdmmc { bus-width = <4>; - cap-mmc-highspeed; cap-sd-highspeed; cd-gpios = <&gpio0 7 GPIO_ACTIVE_LOW>; disable-wp; @@ -636,8 +635,7 @@ &sdhci { bus-width = <8>; - mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; + mmc-hs200-1_8v; non-removable; status = "okay"; }; diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index 5bf963830b17..c764cc8fb3b6 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -59,23 +59,6 @@ alternative_else_nop_endif #endif /* - * These macros are no-ops when UAO is present. - */ - .macro uaccess_disable_not_uao, tmp1, tmp2 - uaccess_ttbr0_disable \tmp1, \tmp2 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(1) -alternative_else_nop_endif - .endm - - .macro uaccess_enable_not_uao, tmp1, tmp2, tmp3 - uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(0) -alternative_else_nop_endif - .endm - -/* * Remove the address tag from a virtual address, if present. */ .macro untagged_addr, dst, addr diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index b1454d117cd2..aca07c2f6e6e 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -79,6 +79,7 @@ #define CAVIUM_CPU_PART_THUNDERX_83XX 0x0A3 #define CAVIUM_CPU_PART_THUNDERX2 0x0AF +#define BRCM_CPU_PART_BRAHMA_B53 0x100 #define BRCM_CPU_PART_VULCAN 0x516 #define QCOM_CPU_PART_FALKOR_V1 0x800 @@ -105,6 +106,7 @@ #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) #define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2) +#define MIDR_BRAHMA_B53 MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_BRAHMA_B53) #define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN) #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 9a21b84536f2..8dc6c5cdabe6 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -32,11 +32,11 @@ #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -80,8 +80,9 @@ #define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ +#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 8330810f699e..565aa45ef134 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -283,23 +283,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } -#define __HAVE_ARCH_PTE_SAME -static inline int pte_same(pte_t pte_a, pte_t pte_b) -{ - pteval_t lhs, rhs; - - lhs = pte_val(pte_a); - rhs = pte_val(pte_b); - - if (pte_present(pte_a)) - lhs &= ~PTE_RDONLY; - - if (pte_present(pte_b)) - rhs &= ~PTE_RDONLY; - - return (lhs == rhs); -} - /* * Huge pte definitions. */ diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 097d6bfac0b7..127712b0b970 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -378,20 +378,34 @@ do { \ extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); #define raw_copy_from_user(to, from, n) \ ({ \ - __arch_copy_from_user((to), __uaccess_mask_ptr(from), (n)); \ + unsigned long __acfu_ret; \ + uaccess_enable_not_uao(); \ + __acfu_ret = __arch_copy_from_user((to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __acfu_ret; \ }) extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); #define raw_copy_to_user(to, from, n) \ ({ \ - __arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n)); \ + unsigned long __actu_ret; \ + uaccess_enable_not_uao(); \ + __actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to), \ + (from), (n)); \ + uaccess_disable_not_uao(); \ + __actu_ret; \ }) extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n); #define raw_copy_in_user(to, from, n) \ ({ \ - __arch_copy_in_user(__uaccess_mask_ptr(to), \ - __uaccess_mask_ptr(from), (n)); \ + unsigned long __aciu_ret; \ + uaccess_enable_not_uao(); \ + __aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __aciu_ret; \ }) #define INLINE_COPY_TO_USER @@ -400,8 +414,11 @@ extern unsigned long __must_check __arch_copy_in_user(void __user *to, const voi extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n); static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { - if (access_ok(to, n)) + if (access_ok(to, n)) { + uaccess_enable_not_uao(); n = __arch_clear_user(__uaccess_mask_ptr(to), n); + uaccess_disable_not_uao(); + } return n; } #define clear_user __clear_user diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h index 0c731bfc7c8c..0c20a7c1bee5 100644 --- a/arch/arm64/include/asm/vdso/vsyscall.h +++ b/arch/arm64/include/asm/vdso/vsyscall.h @@ -31,13 +31,6 @@ int __arm64_get_clock_mode(struct timekeeper *tk) #define __arch_get_clock_mode __arm64_get_clock_mode static __always_inline -int __arm64_use_vsyscall(struct vdso_data *vdata) -{ - return !vdata[CS_HRES_COARSE].clock_mode; -} -#define __arch_use_vsyscall __arm64_use_vsyscall - -static __always_inline void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk) { vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6c3b10a41bd8..93f34b4eca25 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -489,6 +489,7 @@ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), {}, }; @@ -573,6 +574,7 @@ static const struct midr_range spectre_v2_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), { /* sentinel */ } }; @@ -659,17 +661,23 @@ static const struct midr_range arm64_harden_el2_vectors[] = { #endif #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI - -static const struct midr_range arm64_repeat_tlbi_cpus[] = { +static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009 - MIDR_RANGE(MIDR_QCOM_FALKOR_V1, 0, 0, 0, 0), + { + ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0) + }, + { + .midr_range.model = MIDR_QCOM_KRYO, + .matches = is_kryo_midr, + }, #endif #ifdef CONFIG_ARM64_ERRATUM_1286807 - MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + { + ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + }, #endif {}, }; - #endif #ifdef CONFIG_CAVIUM_ERRATUM_27456 @@ -737,6 +745,33 @@ static const struct midr_range erratum_1418040_list[] = { }; #endif +#ifdef CONFIG_ARM64_ERRATUM_845719 +static const struct midr_range erratum_845719_list[] = { + /* Cortex-A53 r0p[01234] */ + MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), + /* Brahma-B53 r0p[0] */ + MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + {}, +}; +#endif + +#ifdef CONFIG_ARM64_ERRATUM_843419 +static const struct arm64_cpu_capabilities erratum_843419_list[] = { + { + /* Cortex-A53 r0p[01234] */ + .matches = is_affected_midr_range, + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), + MIDR_FIXED(0x4, BIT(8)), + }, + { + /* Brahma-B53 r0p[0] */ + .matches = is_affected_midr_range, + ERRATA_MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + }, + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -768,19 +803,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_843419 { - /* Cortex-A53 r0p[01234] */ .desc = "ARM erratum 843419", .capability = ARM64_WORKAROUND_843419, - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), - MIDR_FIXED(0x4, BIT(8)), + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = cpucap_multi_entry_cap_matches, + .match_list = erratum_843419_list, }, #endif #ifdef CONFIG_ARM64_ERRATUM_845719 { - /* Cortex-A53 r0p[01234] */ .desc = "ARM erratum 845719", .capability = ARM64_WORKAROUND_845719, - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), + ERRATA_MIDR_RANGE_LIST(erratum_845719_list), }, #endif #ifdef CONFIG_CAVIUM_ERRATUM_23154 @@ -816,6 +850,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = cpucap_multi_entry_cap_matches, .match_list = qcom_erratum_1003_list, }, @@ -824,7 +859,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "Qualcomm erratum 1009, ARM erratum 1286807", .capability = ARM64_WORKAROUND_REPEAT_TLBI, - ERRATA_MIDR_RANGE_LIST(arm64_repeat_tlbi_cpus), + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = cpucap_multi_entry_cap_matches, + .match_list = arm64_repeat_tlbi_list, }, #endif #ifdef CONFIG_ARM64_ERRATUM_858921 diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 2071260a275b..46822afc57e0 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -632,6 +632,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); + if (!system_supports_32bit_el0()) + val |= ARMV8_PMU_PMCR_LC; __vcpu_sys_reg(vcpu, r->reg) = val; } @@ -682,6 +684,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, val = __vcpu_sys_reg(vcpu, PMCR_EL0); val &= ~ARMV8_PMU_PMCR_MASK; val |= p->regval & ARMV8_PMU_PMCR_MASK; + if (!system_supports_32bit_el0()) + val |= ARMV8_PMU_PMCR_LC; __vcpu_sys_reg(vcpu, PMCR_EL0) = val; kvm_pmu_handle_pmcr(vcpu, val); kvm_vcpu_pmu_restore_guest(vcpu); diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 10415572e82f..aeafc03e961a 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -20,7 +20,6 @@ * Alignment fixed up by hardware. */ ENTRY(__arch_clear_user) - uaccess_enable_not_uao x2, x3, x4 mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f @@ -40,7 +39,6 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2 b.mi 5f uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 - uaccess_disable_not_uao x2, x3 ret ENDPROC(__arch_clear_user) EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 680e74409ff9..ebb3c06cbb5d 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -54,10 +54,8 @@ end .req x5 ENTRY(__arch_copy_from_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 // Nothing to copy ret ENDPROC(__arch_copy_from_user) diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 0bedae3f3792..3d8153a1ebce 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -56,10 +56,8 @@ end .req x5 ENTRY(__arch_copy_in_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_in_user) diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 2d88c736e8f2..357eae2c18eb 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -53,10 +53,8 @@ end .req x5 ENTRY(__arch_copy_to_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_to_user) diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c index cbfcbe6470a5..bfa30b75b2b8 100644 --- a/arch/arm64/lib/uaccess_flushcache.c +++ b/arch/arm64/lib/uaccess_flushcache.c @@ -28,7 +28,11 @@ void memcpy_page_flushcache(char *to, struct page *page, size_t offset, unsigned long __copy_user_flushcache(void *to, const void __user *from, unsigned long n) { - unsigned long rc = __arch_copy_from_user(to, from, n); + unsigned long rc; + + uaccess_enable_not_uao(); + rc = __arch_copy_from_user(to, from, n); + uaccess_disable_not_uao(); /* See above */ __clean_dcache_area_pop(to, n - rc); diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c index 77a836e661c9..df69eaa453a1 100644 --- a/arch/mips/bcm63xx/prom.c +++ b/arch/mips/bcm63xx/prom.c @@ -84,7 +84,7 @@ void __init prom_init(void) * Here we will start up CPU1 in the background and ask it to * reconfigure itself then go back to sleep. */ - memcpy((void *)0xa0000200, &bmips_smp_movevec, 0x20); + memcpy((void *)0xa0000200, bmips_smp_movevec, 0x20); __sync(); set_c0_cause(C_SW0); cpumask_set_cpu(1, &bmips_booted_mask); diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h index bf6a8afd7ad2..581a6a3c66e4 100644 --- a/arch/mips/include/asm/bmips.h +++ b/arch/mips/include/asm/bmips.h @@ -75,11 +75,11 @@ static inline int register_bmips_smp_ops(void) #endif } -extern char bmips_reset_nmi_vec; -extern char bmips_reset_nmi_vec_end; -extern char bmips_smp_movevec; -extern char bmips_smp_int_vec; -extern char bmips_smp_int_vec_end; +extern char bmips_reset_nmi_vec[]; +extern char bmips_reset_nmi_vec_end[]; +extern char bmips_smp_movevec[]; +extern char bmips_smp_int_vec[]; +extern char bmips_smp_int_vec_end[]; extern int bmips_smp_enabled; extern int bmips_cpu_offset; diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h index e78462e8ca2e..b08825531e9f 100644 --- a/arch/mips/include/asm/vdso/gettimeofday.h +++ b/arch/mips/include/asm/vdso/gettimeofday.h @@ -24,6 +24,8 @@ #define VDSO_HAS_CLOCK_GETRES 1 +#define __VDSO_USE_SYSCALL ULLONG_MAX + #ifdef CONFIG_MIPS_CLOCK_VSYSCALL static __always_inline long gettimeofday_fallback( @@ -205,7 +207,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) break; #endif default: - cycle_now = 0; + cycle_now = __VDSO_USE_SYSCALL; break; } diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h index 195314732233..00d41b94ba31 100644 --- a/arch/mips/include/asm/vdso/vsyscall.h +++ b/arch/mips/include/asm/vdso/vsyscall.h @@ -28,13 +28,6 @@ int __mips_get_clock_mode(struct timekeeper *tk) } #define __arch_get_clock_mode __mips_get_clock_mode -static __always_inline -int __mips_use_vsyscall(struct vdso_data *vdata) -{ - return (vdata[CS_HRES_COARSE].clock_mode != VDSO_CLOCK_NONE); -} -#define __arch_use_vsyscall __mips_use_vsyscall - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 76fae9b79f13..712c15de6ab9 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -464,10 +464,10 @@ static void bmips_wr_vec(unsigned long dst, char *start, char *end) static inline void bmips_nmi_handler_setup(void) { - bmips_wr_vec(BMIPS_NMI_RESET_VEC, &bmips_reset_nmi_vec, - &bmips_reset_nmi_vec_end); - bmips_wr_vec(BMIPS_WARM_RESTART_VEC, &bmips_smp_int_vec, - &bmips_smp_int_vec_end); + bmips_wr_vec(BMIPS_NMI_RESET_VEC, bmips_reset_nmi_vec, + bmips_reset_nmi_vec_end); + bmips_wr_vec(BMIPS_WARM_RESTART_VEC, bmips_smp_int_vec, + bmips_smp_int_vec_end); } struct reset_vec_info { diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index e01cb33bfa1a..41bb91f05688 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -653,6 +653,13 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r, int restore_scratch) { if (restore_scratch) { + /* + * Ensure the MFC0 below observes the value written to the + * KScratch register by the prior MTC0. + */ + if (scratch_reg >= 0) + uasm_i_ehb(p); + /* Reset default page size */ if (PM_DEFAULT_MASK >> 16) { uasm_i_lui(p, tmp, PM_DEFAULT_MASK >> 16); @@ -667,12 +674,10 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r, uasm_i_mtc0(p, 0, C0_PAGEMASK); uasm_il_b(p, r, lid); } - if (scratch_reg >= 0) { - uasm_i_ehb(p); + if (scratch_reg >= 0) UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg); - } else { + else UASM_i_LW(p, 1, scratchpad_offset(0), 0); - } } else { /* Reset default page size */ if (PM_DEFAULT_MASK >> 16) { @@ -921,6 +926,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, } if (mode != not_refill && check_for_high_segbits) { uasm_l_large_segbits_fault(l, *p); + + if (mode == refill_scratch && scratch_reg >= 0) + uasm_i_ehb(p); + /* * We get here if we are an xsseg address, or if we are * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary. @@ -939,12 +948,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, uasm_i_jr(p, ptr); if (mode == refill_scratch) { - if (scratch_reg >= 0) { - uasm_i_ehb(p); + if (scratch_reg >= 0) UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg); - } else { + else UASM_i_LW(p, 1, scratchpad_offset(0), 0); - } } else { uasm_i_nop(p); } diff --git a/arch/mips/sgi-ip27/Kconfig b/arch/mips/sgi-ip27/Kconfig index ef3847e7aee0..e5b6cadbec85 100644 --- a/arch/mips/sgi-ip27/Kconfig +++ b/arch/mips/sgi-ip27/Kconfig @@ -38,10 +38,3 @@ config REPLICATE_KTEXT Say Y here to enable replicating the kernel text across multiple nodes in a NUMA cluster. This trades memory for speed. -config REPLICATE_EXHANDLERS - bool "Exception handler replication support" - depends on SGI_IP27 - help - Say Y here to enable replicating the kernel exception handlers - across multiple nodes in a NUMA cluster. This trades memory for - speed. diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c index 59d5375c9021..79a52c472782 100644 --- a/arch/mips/sgi-ip27/ip27-init.c +++ b/arch/mips/sgi-ip27/ip27-init.c @@ -69,23 +69,14 @@ static void per_hub_init(cnodeid_t cnode) hub_rtc_init(cnode); -#ifdef CONFIG_REPLICATE_EXHANDLERS - /* - * If this is not a headless node initialization, - * copy over the caliased exception handlers. - */ - if (get_compact_nodeid() == cnode) { - extern char except_vec2_generic, except_vec3_generic; - extern void build_tlb_refill_handler(void); - - memcpy((void *)(CKSEG0 + 0x100), &except_vec2_generic, 0x80); - memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x80); - build_tlb_refill_handler(); - memcpy((void *)(CKSEG0 + 0x100), (void *) CKSEG0, 0x80); - memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x100); + if (nasid) { + /* copy exception handlers from first node to current node */ + memcpy((void *)NODE_OFFSET_TO_K0(nasid, 0), + (void *)CKSEG0, 0x200); __flush_cache_all(); + /* switch to node local exception handlers */ + REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K); } -#endif } void per_cpu_init(void) diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index fb077a947575..8624a885d95b 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -332,11 +332,7 @@ static void __init mlreset(void) * thinks it is a node 0 address. */ REMOTE_HUB_S(nasid, PI_REGION_PRESENT, (region_mask | 1)); -#ifdef CONFIG_REPLICATE_EXHANDLERS - REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K); -#else REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_0); -#endif #ifdef LATER /* diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 1d1d748c227f..b96d74496977 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -2125,7 +2125,7 @@ ftrace_regs_caller: copy %rp, %r26 LDREG -FTRACE_FRAME_SIZE-PT_SZ_ALGN(%sp), %r25 ldo -8(%r25), %r25 - copy %r3, %arg2 + ldo -FTRACE_FRAME_SIZE(%r1), %arg2 b,l ftrace_function_trampoline, %rp copy %r1, %arg3 /* struct pt_regs */ diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 677e9babef80..f9dc597b0b86 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -91,6 +91,7 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end) { + addr &= 0xf0000000; /* align addr to start of segment */ barrier(); /* make sure thread.kuap is updated before playing with SRs */ while (addr < end) { mtsrin(sr, addr); diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 409c9bfb43d9..57c229a86f08 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -175,4 +175,7 @@ do { \ ARCH_DLINFO_CACHE_GEOMETRY; \ } while (0) +/* Relocate the kernel image to @final_address */ +void relocate(unsigned long final_address); + #endif /* _ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a4e7762dd286..100f1b57ec2f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -3249,7 +3249,20 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt) /* Switch to secure mode. */ prom_printf("Switching to secure mode.\n"); + /* + * The ultravisor will do an integrity check of the kernel image but we + * relocated it so the check will fail. Restore the original image by + * relocating it back to the kernel virtual base address. + */ + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate(KERNELBASE); + ret = enter_secure_mode(kbase, fdt); + + /* Relocate the kernel again. */ + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate(kbase); + if (ret != U_SUCCESS) { prom_printf("Returned %d from switching to secure mode.\n", ret); prom_rtas_os_term("Switch to secure mode failed.\n"); diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 78bab17b1396..b183ab9c5107 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -26,7 +26,8 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start logo_linux_clut224 btext_prepare_BAT reloc_got2 kernstart_addr memstart_addr linux_banner _stext -__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC." +__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC. +relocate" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 591bfb4bfd0f..a3f9c665bb5b 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1217,6 +1217,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc; int i, r = -EBUSY; + u32 vp_id; pr_devel("connect_vcpu(cpu=%d)\n", cpu); @@ -1228,25 +1229,32 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, return -EPERM; if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) return -EBUSY; - if (kvmppc_xive_find_server(vcpu->kvm, cpu)) { - pr_devel("Duplicate !\n"); - return -EEXIST; - } if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { pr_devel("Out of bounds !\n"); return -EINVAL; } - xc = kzalloc(sizeof(*xc), GFP_KERNEL); - if (!xc) - return -ENOMEM; /* We need to synchronize with queue provisioning */ mutex_lock(&xive->lock); + + vp_id = kvmppc_xive_vp(xive, cpu); + if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) { + pr_devel("Duplicate !\n"); + r = -EEXIST; + goto bail; + } + + xc = kzalloc(sizeof(*xc), GFP_KERNEL); + if (!xc) { + r = -ENOMEM; + goto bail; + } + vcpu->arch.xive_vcpu = xc; xc->xive = xive; xc->vcpu = vcpu; xc->server_num = cpu; - xc->vp_id = kvmppc_xive_vp(xive, cpu); + xc->vp_id = vp_id; xc->mfrr = 0xff; xc->valid = true; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 955b820ffd6d..fe3ed50e0818 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -220,6 +220,18 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); } +static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) +{ + struct kvm_vcpu *vcpu = NULL; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) + return true; + } + return false; +} + /* * Mapping between guest priorities and host priorities * is as follow. diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 248c1ea9e788..78b906ffa0d2 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -106,6 +106,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc = NULL; int rc; + u32 vp_id; pr_devel("native_connect_vcpu(server=%d)\n", server_num); @@ -124,7 +125,8 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, mutex_lock(&xive->lock); - if (kvmppc_xive_find_server(vcpu->kvm, server_num)) { + vp_id = kvmppc_xive_vp(xive, server_num); + if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) { pr_devel("Duplicate !\n"); rc = -EEXIST; goto bail; @@ -141,7 +143,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, xc->vcpu = vcpu; xc->server_num = server_num; - xc->vp_id = kvmppc_xive_vp(xive, server_num); + xc->vp_id = vp_id; xc->valid = true; vcpu->arch.irq_type = KVMPPC_IRQ_XIVE; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 02a59946a78a..be3517ef0574 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -1142,6 +1142,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) } /* + * If we have seen a tail call, we need a second pass. + * This is because bpf_jit_emit_common_epilogue() is called + * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen. + */ + if (cgctx.seen & SEEN_TAILCALL) { + cgctx.idx = 0; + if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) { + fp = org_fp; + goto out_addrs; + } + } + + /* * Pretend to build prologue, given the features we've seen. This will * update ctgtx.idx as it pretends to output instructions, then we can * calculate total size from idx. diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 6bc24a47e9ef..6f300ab7f0e9 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -42,7 +42,7 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); - if (eeh_has_flag(EEH_FORCE_DISABLED)) + if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED)) return; dev_dbg(&pdev->dev, "EEH: Setting up device\n"); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index fbd6e6b7bbf2..13e251699346 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void) return 0; } +static void pnv_flush_interrupts(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (xive_enabled()) + xive_flush_interrupt(); + else + icp_opal_flush_interrupt(); + } else { + icp_native_flush_interrupt(); + } +} + static void pnv_smp_cpu_kill_self(void) { + unsigned long srr1, unexpected_mask, wmask; unsigned int cpu; - unsigned long srr1, wmask; u64 lpcr_val; /* Standard hot unplug procedure */ - /* - * This hard disables local interurpts, ensuring we have no lazy - * irqs pending. - */ - WARN_ON(irqs_disabled()); - hard_irq_disable(); - WARN_ON(lazy_irq_pending()); idle_task_exit(); current->active_mm = NULL; /* for sanity */ @@ -173,6 +178,27 @@ static void pnv_smp_cpu_kill_self(void) wmask = SRR1_WAKEMASK_P8; /* + * This turns the irq soft-disabled state we're called with, into a + * hard-disabled state with pending irq_happened interrupts cleared. + * + * PACA_IRQ_DEC - Decrementer should be ignored. + * PACA_IRQ_HMI - Can be ignored, processing is done in real mode. + * PACA_IRQ_DBELL, EE, PMI - Unexpected. + */ + hard_irq_disable(); + if (generic_check_cpu_restart(cpu)) + goto out; + + unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS); + if (local_paca->irq_happened & unexpected_mask) { + if (local_paca->irq_happened & PACA_IRQ_EE) + pnv_flush_interrupts(); + DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n", + cpu, local_paca->irq_happened); + } + local_paca->irq_happened = PACA_IRQ_HARD_DIS; + + /* * We don't want to take decrementer interrupts while we are * offline, so clear LPCR:PECE1. We keep PECE2 (and * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in. @@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void) srr1 = pnv_cpu_offline(cpu); + WARN_ON_ONCE(!irqs_disabled()); WARN_ON(lazy_irq_pending()); /* @@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void) */ if (((srr1 & wmask) == SRR1_WAKEEE) || ((srr1 & wmask) == SRR1_WAKEHVI)) { - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (xive_enabled()) - xive_flush_interrupt(); - else - icp_opal_flush_interrupt(); - } else - icp_native_flush_interrupt(); + pnv_flush_interrupts(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); @@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void) */ lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1; pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); - +out: DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h index 07ceee8b1747..75604fec1b1b 100644 --- a/arch/riscv/include/asm/bug.h +++ b/arch/riscv/include/asm/bug.h @@ -12,7 +12,6 @@ #include <asm/asm.h> -#ifdef CONFIG_GENERIC_BUG #define __INSN_LENGTH_MASK _UL(0x3) #define __INSN_LENGTH_32 _UL(0x3) #define __COMPRESSED_INSN_MASK _UL(0xffff) @@ -20,7 +19,6 @@ #define __BUG_INSN_32 _UL(0x00100073) /* ebreak */ #define __BUG_INSN_16 _UL(0x9002) /* c.ebreak */ -#ifndef __ASSEMBLY__ typedef u32 bug_insn_t; #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS @@ -43,6 +41,7 @@ typedef u32 bug_insn_t; RISCV_SHORT " %2" #endif +#ifdef CONFIG_GENERIC_BUG #define __BUG_FLAGS(flags) \ do { \ __asm__ __volatile__ ( \ @@ -58,14 +57,10 @@ do { \ "i" (flags), \ "i" (sizeof(struct bug_entry))); \ } while (0) - -#endif /* !__ASSEMBLY__ */ #else /* CONFIG_GENERIC_BUG */ -#ifndef __ASSEMBLY__ #define __BUG_FLAGS(flags) do { \ __asm__ __volatile__ ("ebreak\n"); \ } while (0) -#endif /* !__ASSEMBLY__ */ #endif /* CONFIG_GENERIC_BUG */ #define BUG() do { \ @@ -79,15 +74,10 @@ do { \ #include <asm-generic/bug.h> -#ifndef __ASSEMBLY__ - struct pt_regs; struct task_struct; -extern void die(struct pt_regs *regs, const char *str); -extern void do_trap(struct pt_regs *regs, int signo, int code, - unsigned long addr); - -#endif /* !__ASSEMBLY__ */ +void die(struct pt_regs *regs, const char *str); +void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr); #endif /* _ASM_RISCV_BUG_H */ diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index fc1189ad3777..3ba4d93721d3 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -13,6 +13,7 @@ #include <linux/types.h> #include <asm/mmiowb.h> +#include <asm/pgtable.h> extern void __iomem *ioremap(phys_addr_t offset, unsigned long size); @@ -162,6 +163,12 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* + * I/O port access constants. + */ +#define IO_SPACE_LIMIT (PCI_IO_SIZE - 1) +#define PCI_IOBASE ((void __iomem *)PCI_IO_START) + +/* * Emulation routines for the port-mapped IO space used by some PCI drivers. * These are defined as being "fully synchronous", but also "not guaranteed to * be fully ordered with respect to other memory and I/O operations". We're diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h index 75576424c0f7..6e1b0e0325eb 100644 --- a/arch/riscv/include/asm/irq.h +++ b/arch/riscv/include/asm/irq.h @@ -7,6 +7,9 @@ #ifndef _ASM_RISCV_IRQ_H #define _ASM_RISCV_IRQ_H +#include <linux/interrupt.h> +#include <linux/linkage.h> + #define NR_IRQS 0 void riscv_timer_interrupt(void); diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 42292d99cc74..d3221017194d 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -7,6 +7,7 @@ #define _ASM_RISCV_PGTABLE_H #include <linux/mmzone.h> +#include <linux/sizes.h> #include <asm/pgtable-bits.h> @@ -86,6 +87,7 @@ extern pgd_t swapper_pg_dir[]; #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) +#define PCI_IO_SIZE SZ_16M /* * Roughly size the vmemmap space to be large enough to fit enough @@ -100,7 +102,10 @@ extern pgd_t swapper_pg_dir[]; #define vmemmap ((struct page *)VMEMMAP_START) -#define FIXADDR_TOP (VMEMMAP_START) +#define PCI_IO_END VMEMMAP_START +#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) +#define FIXADDR_TOP PCI_IO_START + #ifdef CONFIG_64BIT #define FIXADDR_SIZE PMD_SIZE #else @@ -184,10 +189,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); } -static inline pte_t mk_pte(struct page *page, pgprot_t prot) -{ - return pfn_pte(page_to_pfn(page), prot); -} +#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) @@ -428,9 +430,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#ifdef CONFIG_FLATMEM #define kern_addr_valid(addr) (1) /* FIXME */ -#endif extern void *dtb_early_va; extern void setup_bootmem(void); diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index f0227bdce0f0..ee4f0ac62c9d 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -6,6 +6,7 @@ #ifndef _ASM_RISCV_SWITCH_TO_H #define _ASM_RISCV_SWITCH_TO_H +#include <linux/sched/task_stack.h> #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/csr.h> diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index b1ade9a49347..a5ad00043104 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -10,6 +10,7 @@ #include <asm/processor.h> #include <asm/hwcap.h> #include <asm/smp.h> +#include <asm/switch_to.h> unsigned long elf_hwcap __read_mostly; #ifdef CONFIG_FPU diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h new file mode 100644 index 000000000000..105fb0496b24 --- /dev/null +++ b/arch/riscv/kernel/head.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 SiFive, Inc. + */ +#ifndef __ASM_HEAD_H +#define __ASM_HEAD_H + +#include <linux/linkage.h> +#include <linux/init.h> + +extern atomic_t hart_lottery; + +asmlinkage void do_page_fault(struct pt_regs *regs); +asmlinkage void __init setup_vm(uintptr_t dtb_pa); + +extern void *__cpu_up_stack_pointer[]; +extern void *__cpu_up_task_pointer[]; + +void __init parse_dtb(void); + +#endif /* __ASM_HEAD_H */ diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index 6d8659388c49..fffac6ddb0e0 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -24,7 +24,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } -asmlinkage void __irq_entry do_IRQ(struct pt_regs *regs) +asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index c9ae48333114..e264e59e596e 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -8,6 +8,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/moduleloader.h> unsigned long module_emit_got_entry(struct module *mod, unsigned long val) { diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index fb3a082362eb..85e3c39bb60b 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -7,6 +7,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> @@ -19,6 +20,7 @@ #include <asm/csr.h> #include <asm/string.h> #include <asm/switch_to.h> +#include <asm/thread_info.h> extern asmlinkage void ret_from_fork(void); extern asmlinkage void ret_from_kernel_thread(void); diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 368751438366..1252113ef8b2 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -148,7 +148,7 @@ long arch_ptrace(struct task_struct *child, long request, * Allows PTRACE_SYSCALL to work. These are called from entry.S in * {handle,ret_from}_syscall. */ -void do_syscall_trace_enter(struct pt_regs *regs) +__visible void do_syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) if (tracehook_report_syscall_entry(regs)) @@ -162,7 +162,7 @@ void do_syscall_trace_enter(struct pt_regs *regs) audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3); } -void do_syscall_trace_exit(struct pt_regs *regs) +__visible void do_syscall_trace_exit(struct pt_regs *regs) { audit_syscall_exit(regs); diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c index d0fe623bfb8f..aa56bb135ec4 100644 --- a/arch/riscv/kernel/reset.c +++ b/arch/riscv/kernel/reset.c @@ -4,6 +4,7 @@ */ #include <linux/reboot.h> +#include <linux/pm.h> #include <asm/sbi.h> static void default_power_off(void) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index a990a6cb184f..845ae0e12115 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -24,6 +24,8 @@ #include <asm/tlbflush.h> #include <asm/thread_info.h> +#include "head.h" + #ifdef CONFIG_DUMMY_CONSOLE struct screen_info screen_info = { .orig_video_lines = 30, diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index b14d7647d800..d0f6f212f5df 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -26,7 +26,7 @@ struct rt_sigframe { #ifdef CONFIG_FPU static long restore_fp_state(struct pt_regs *regs, - union __riscv_fp_state *sc_fpregs) + union __riscv_fp_state __user *sc_fpregs) { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; @@ -53,7 +53,7 @@ static long restore_fp_state(struct pt_regs *regs, } static long save_fp_state(struct pt_regs *regs, - union __riscv_fp_state *sc_fpregs) + union __riscv_fp_state __user *sc_fpregs) { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; @@ -292,8 +292,8 @@ static void do_signal(struct pt_regs *regs) * notification of userspace execution resumption * - triggered by the _TIF_WORK_MASK flags */ -asmlinkage void do_notify_resume(struct pt_regs *regs, - unsigned long thread_info_flags) +asmlinkage __visible void do_notify_resume(struct pt_regs *regs, + unsigned long thread_info_flags) { /* Handle pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index b18cd6c8e8fb..5c9ec78422c2 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -8,7 +8,9 @@ * Copyright (C) 2017 SiFive */ +#include <linux/cpu.h> #include <linux/interrupt.h> +#include <linux/profile.h> #include <linux/smp.h> #include <linux/sched.h> #include <linux/seq_file.h> diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 18ae6da5115e..261f4087cc39 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -29,6 +29,9 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/sbi.h> +#include <asm/smp.h> + +#include "head.h" void *__cpu_up_stack_pointer[NR_CPUS]; void *__cpu_up_task_pointer[NR_CPUS]; @@ -130,7 +133,7 @@ void __init smp_cpus_done(unsigned int max_cpus) /* * C entry point for a secondary processor. */ -asmlinkage void __init smp_callin(void) +asmlinkage __visible void __init smp_callin(void) { struct mm_struct *mm = &init_mm; diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c index e5dd52d8f633..f1ead9df96ca 100644 --- a/arch/riscv/kernel/syscall_table.c +++ b/arch/riscv/kernel/syscall_table.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h> #include <asm-generic/syscalls.h> #include <asm/vdso.h> +#include <asm/syscall.h> #undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 9dd1f2e64db1..6a53c02e9c73 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -7,6 +7,7 @@ #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> +#include <asm/processor.h> unsigned long riscv_timebase; EXPORT_SYMBOL_GPL(riscv_timebase); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 1ac75f7d0bff..473de3ae8bb7 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -3,6 +3,7 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> @@ -83,7 +84,7 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, } #define DO_ERROR_INFO(name, signo, code, str) \ -asmlinkage void name(struct pt_regs *regs) \ +asmlinkage __visible void name(struct pt_regs *regs) \ { \ do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \ } @@ -111,7 +112,6 @@ DO_ERROR_INFO(do_trap_ecall_s, DO_ERROR_INFO(do_trap_ecall_m, SIGILL, ILL_ILLTRP, "environment call from M-mode"); -#ifdef CONFIG_GENERIC_BUG static inline unsigned long get_break_insn_length(unsigned long pc) { bug_insn_t insn; @@ -120,28 +120,15 @@ static inline unsigned long get_break_insn_length(unsigned long pc) return 0; return (((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? 4UL : 2UL); } -#endif /* CONFIG_GENERIC_BUG */ -asmlinkage void do_trap_break(struct pt_regs *regs) +asmlinkage __visible void do_trap_break(struct pt_regs *regs) { - if (user_mode(regs)) { - force_sig_fault(SIGTRAP, TRAP_BRKPT, - (void __user *)(regs->sepc)); - return; - } -#ifdef CONFIG_GENERIC_BUG - { - enum bug_trap_type type; - - type = report_bug(regs->sepc, regs); - if (type == BUG_TRAP_TYPE_WARN) { - regs->sepc += get_break_insn_length(regs->sepc); - return; - } - } -#endif /* CONFIG_GENERIC_BUG */ - - die(regs, "Kernel BUG"); + if (user_mode(regs)) + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->sepc); + else if (report_bug(regs->sepc, regs) == BUG_TRAP_TYPE_WARN) + regs->sepc += get_break_insn_length(regs->sepc); + else + die(regs, "Kernel BUG"); } #ifdef CONFIG_GENERIC_BUG diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index c9c21e0d5641..484d95a70907 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -6,6 +6,7 @@ * Copyright (C) 2015 Regents of the University of California */ +#include <linux/elf.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/binfmts.h> @@ -25,7 +26,7 @@ static union { struct vdso_data data; u8 page[PAGE_SIZE]; } vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = &vdso_data_store.data; +static struct vdso_data *vdso_data = &vdso_data_store.data; static int __init vdso_init(void) { diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index beeb5d7f92ea..ca66d44156b6 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> +#include <asm/mmu_context.h> /* * When necessary, performs a deferred icache flush for the given MM context, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 96add1427a75..247b8c859c44 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -18,6 +18,8 @@ #include <asm/ptrace.h> #include <asm/tlbflush.h> +#include "../kernel/head.h" + /* * This routine handles page faults. It determines the address and the * problem, and then passes it off to one of the appropriate routines. diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 83f7d12042fb..573463d1c799 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -19,6 +19,8 @@ #include <asm/pgtable.h> #include <asm/io.h> +#include "../kernel/head.h" + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -337,8 +339,7 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) */ #ifndef __riscv_cmodel_medany -#error "setup_vm() is called from head.S before relocate so it should " - "not use absolute addressing." +#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing." #endif asmlinkage void __init setup_vm(uintptr_t dtb_pa) @@ -458,7 +459,7 @@ void __init paging_init(void) zone_sizes_init(); } -#ifdef CONFIG_SPARSEMEM +#ifdef CONFIG_SPARSEMEM_VMEMMAP int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { diff --git a/arch/riscv/mm/sifive_l2_cache.c b/arch/riscv/mm/sifive_l2_cache.c index 2e637ad71c05..a9ffff3277c7 100644 --- a/arch/riscv/mm/sifive_l2_cache.c +++ b/arch/riscv/mm/sifive_l2_cache.c @@ -142,7 +142,7 @@ static irqreturn_t l2_int_handler(int irq, void *device) return IRQ_HANDLED; } -int __init sifive_l2_init(void) +static int __init sifive_l2_init(void) { struct device_node *np; struct resource res; diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 596ca7cc4d7b..5367950510f6 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -101,10 +101,18 @@ static void handle_relocs(unsigned long offset) dynsym = (Elf64_Sym *) vmlinux.dynsym_start; for (rela = rela_start; rela < rela_end; rela++) { loc = rela->r_offset + offset; - val = rela->r_addend + offset; + val = rela->r_addend; r_sym = ELF64_R_SYM(rela->r_info); - if (r_sym) - val += dynsym[r_sym].st_value; + if (r_sym) { + if (dynsym[r_sym].st_shndx != SHN_UNDEF) + val += dynsym[r_sym].st_value + offset; + } else { + /* + * 0 == undefined symbol table index (STN_UNDEF), + * used for R_390_RELATIVE, only add KASLR offset + */ + val += offset; + } r_type = ELF64_R_TYPE(rela->r_info); rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0); if (rc) diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h index d827b5b9a32c..eaaefeceef6f 100644 --- a/arch/s390/include/asm/unwind.h +++ b/arch/s390/include/asm/unwind.h @@ -35,6 +35,7 @@ struct unwind_state { struct task_struct *task; struct pt_regs *regs; unsigned long sp, ip; + bool reuse_sp; int graph_idx; bool reliable; bool error; diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index b9d8fe45737a..8f8456816d83 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -69,18 +69,26 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); static ssize_t show_idle_time(struct device *dev, struct device_attribute *attr, char *buf) { + unsigned long long now, idle_time, idle_enter, idle_exit, in_idle; struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); - unsigned long long now, idle_time, idle_enter, idle_exit; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_time = READ_ONCE(idle->idle_time); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + idle_time += in_idle; return sprintf(buf, "%llu\n", idle_time >> 12); } DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); @@ -88,17 +96,24 @@ DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); u64 arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); - unsigned long long now, idle_enter, idle_exit; + unsigned long long now, idle_enter, idle_exit, in_idle; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - - return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0); + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + return cputime_to_nsecs(in_idle); } void arch_cpu_idle_enter(void) diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c index 3b664cb3ec4d..d5035de9020e 100644 --- a/arch/s390/kernel/machine_kexec_reloc.c +++ b/arch/s390/kernel/machine_kexec_reloc.c @@ -27,6 +27,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, *(u32 *)loc = val; break; case R_390_64: /* Direct 64 bit. */ + case R_390_GLOB_DAT: *(u64 *)loc = val; break; case R_390_PC16: /* PC relative 16 bit. */ diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index 8fc9daae47a2..a8204f952315 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -46,10 +46,15 @@ bool unwind_next_frame(struct unwind_state *state) regs = state->regs; if (unlikely(regs)) { - sp = READ_ONCE_NOCHECK(regs->gprs[15]); - if (unlikely(outside_of_stack(state, sp))) { - if (!update_stack_info(state, sp)) - goto out_err; + if (state->reuse_sp) { + sp = state->sp; + state->reuse_sp = false; + } else { + sp = READ_ONCE_NOCHECK(regs->gprs[15]); + if (unlikely(outside_of_stack(state, sp))) { + if (!update_stack_info(state, sp)) + goto out_err; + } } sf = (struct stack_frame *) sp; ip = READ_ONCE_NOCHECK(sf->gprs[8]); @@ -107,9 +112,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, { struct stack_info *info = &state->stack_info; unsigned long *mask = &state->stack_mask; + bool reliable, reuse_sp; struct stack_frame *sf; unsigned long ip; - bool reliable; memset(state, 0, sizeof(*state)); state->task = task; @@ -134,10 +139,12 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, if (regs) { ip = READ_ONCE_NOCHECK(regs->psw.addr); reliable = true; + reuse_sp = true; } else { sf = (struct stack_frame *) sp; ip = READ_ONCE_NOCHECK(sf->gprs[8]); reliable = false; + reuse_sp = false; } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -151,5 +158,6 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = sp; state->ip = ip; state->reliable = reliable; + state->reuse_sp = reuse_sp; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 510a18299196..a51c892f14f3 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -298,16 +298,16 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, } if (write) { - len = *lenp; - if (copy_from_user(buf, buffer, - len > sizeof(buf) ? sizeof(buf) : len)) + len = min(*lenp, sizeof(buf)); + if (copy_from_user(buf, buffer, len)) return -EFAULT; - buf[sizeof(buf) - 1] = '\0'; + buf[len - 1] = '\0'; cmm_skip_blanks(buf, &p); nr = simple_strtoul(p, &p, 0); cmm_skip_blanks(p, &p); seconds = simple_strtoul(p, &p, 0); cmm_set_timeout(nr, seconds); + *ppos += *lenp; } else { len = sprintf(buf, "%ld %ld\n", cmm_timeout_pages, cmm_timeout_seconds); @@ -315,9 +315,9 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, len = *lenp; if (copy_to_user(buffer, buf, len)) return -EFAULT; + *lenp = len; + *ppos += len; } - *lenp = len; - *ppos += len; return 0; } diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 324a23947585..997ffe46e953 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -65,14 +65,14 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. # -CFLAGS_REMOVE_vdso-note.o = -pg CFLAGS_REMOVE_vclock_gettime.o = -pg +CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) -CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) +CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m elf32_sparc -soname linux-gate.so.1 #This makes sure the $(obj) subdirectory exists even though vdso32/ diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 612535cd9706..6627d7c30f37 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1403,8 +1403,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, spin_unlock_irq(&ubd_dev->lock); - if (ret < 0) - blk_mq_requeue_request(req, true); + if (ret < 0) { + if (ret == -ENOMEM) + res = BLK_STS_RESOURCE; + else + res = BLK_STS_DEV_RESOURCE; + } return res; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d6e1faa28c58..8ef85139553f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1940,6 +1940,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +choice + prompt "TSX enable mode" + depends on CPU_SUP_INTEL + default X86_INTEL_TSX_MODE_OFF + help + Intel's TSX (Transactional Synchronization Extensions) feature + allows to optimize locking protocols through lock elision which + can lead to a noticeable performance boost. + + On the other hand it has been shown that TSX can be exploited + to form side channel attacks (e.g. TAA) and chances are there + will be more of those attacks discovered in the future. + + Therefore TSX is not enabled by default (aka tsx=off). An admin + might override this decision by tsx=on the command line parameter. + Even with TSX enabled, the kernel will attempt to enable the best + possible TAA mitigation setting depending on the microcode available + for the particular machine. + + This option allows to set the default tsx mode between tsx=on, =off + and =auto. See Documentation/admin-guide/kernel-parameters.txt for more + details. + + Say off if not sure, auto if TSX is in use but it should be used on safe + platforms or on if TSX is in use and the security aspect of tsx is not + relevant. + +config X86_INTEL_TSX_MODE_OFF + bool "off" + help + TSX is disabled if possible - equals to tsx=off command line parameter. + +config X86_INTEL_TSX_MODE_ON + bool "on" + help + TSX is always enabled on TSX capable HW - equals the tsx=on command + line parameter. + +config X86_INTEL_TSX_MODE_AUTO + bool "auto" + help + TSX is enabled on TSX capable HW that is believed to be safe against + side channel attacks- equals the tsx=auto command line parameter. +endchoice + config EFI bool "EFI runtime service support" depends on ACPI diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index d6662fdef300..82bc60c8acb2 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -13,6 +13,7 @@ #include <asm/e820/types.h> #include <asm/setup.h> #include <asm/desc.h> +#include <asm/boot.h> #include "../string.h" #include "eboot.h" @@ -813,7 +814,8 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) status = efi_relocate_kernel(sys_table, &bzimage_addr, hdr->init_size, hdr->init_size, hdr->pref_address, - hdr->kernel_alignment); + hdr->kernel_alignment, + LOAD_PHYSICAL_ADDR); if (status != EFI_SUCCESS) { efi_printk(sys_table, "efi_relocate_kernel() failed!\n"); goto fail; diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 5b35b7ea5d72..26c36357c4c9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { config &= ~perf_ibs->cnt_mask; - wrmsrl(hwc->config_base, config); + if (boot_cpu_data.x86 == 0x10) + wrmsrl(hwc->config_base, config); config &= ~perf_ibs->enable_mask; wrmsrl(hwc->config_base, config); } @@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = { }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, - .cnt_mask = IBS_OP_MAX_CNT, + .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT | + IBS_OP_CUR_CNT_RAND, .enable_mask = IBS_OP_ENABLE, .valid_mask = IBS_OP_VAL, .max_period = IBS_OP_MAX_CNT << 4, @@ -614,7 +616,7 @@ fail: if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 74e80ed9c6c4..05e43d0f430b 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -627,7 +627,7 @@ static struct topa *topa_alloc(int cpu, gfp_t gfp) * link as the 2nd entry in the table */ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) { - TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p); + TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p) >> TOPA_SHIFT; TOPA_ENTRY(&tp->topa, 1)->end = 1; } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 6fc2e06ab4c6..86467f85c383 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags) local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); uncore_enable_event(box, event); - if (box->n_active == 1) { - uncore_enable_box(box); + if (box->n_active == 1) uncore_pmu_start_hrtimer(box); - } } void uncore_pmu_event_stop(struct perf_event *event, int flags) @@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags) WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; - if (box->n_active == 0) { - uncore_disable_box(box); + if (box->n_active == 0) uncore_pmu_cancel_hrtimer(box); - } } if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { @@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event) return ret; } +static void uncore_pmu_enable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->enable_box) + uncore_pmu->type->ops->enable_box(box); +} + +static void uncore_pmu_disable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->disable_box) + uncore_pmu->type->ops->disable_box(box); +} + static ssize_t uncore_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { @@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) pmu->pmu = (struct pmu) { .attr_groups = pmu->type->attr_groups, .task_ctx_nr = perf_invalid_context, + .pmu_enable = uncore_pmu_enable, + .pmu_disable = uncore_pmu_disable, .event_init = uncore_pmu_event_init, .add = uncore_pmu_event_add, .del = uncore_pmu_event_del, diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index f36f7bebbc1b..bbfdaa720b45 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box, return -EINVAL; } -static inline void uncore_disable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->disable_box) - box->pmu->type->ops->disable_box(box); -} - -static inline void uncore_enable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->enable_box) - box->pmu->type->ops->enable_box(box); -} - static inline void uncore_disable_event(struct intel_uncore_box *box, struct perf_event *event) { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0652d3eed9bd..c4fbe379cc0b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -399,5 +399,7 @@ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 50eb430b0ad8..4fc61483919a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -312,9 +312,12 @@ struct kvm_rmap_head { struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; + struct list_head lpage_disallowed_link; + bool unsync; u8 mmu_valid_gen; bool mmio_cached; + bool lpage_disallowed; /* Can't be replaced by an equiv large page */ /* * The following two entries are used to key the shadow page in the @@ -859,6 +862,7 @@ struct kvm_arch { */ struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; + struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -933,6 +937,7 @@ struct kvm_arch { bool exception_payload_enabled; struct kvm_pmu_event_filter *pmu_event_filter; + struct task_struct *nx_lpage_recovery_thread; }; struct kvm_vm_stat { @@ -946,6 +951,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong nx_lpage_splits; ulong max_mmu_page_hash_collisions; }; @@ -1189,7 +1195,7 @@ struct kvm_x86_ops { int (*set_nested_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state); - void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); + bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 20ce682a2540..6a3124664289 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -93,6 +93,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -103,6 +115,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 80bc209c0708..5c24a7b35166 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -314,7 +314,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the @@ -337,7 +337,7 @@ static inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6e0a3b43d027..54f5d54280f6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -988,4 +988,11 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h index e00c9e875933..ac9fc51e2b18 100644 --- a/arch/x86/include/asm/vmware.h +++ b/arch/x86/include/asm/vmware.h @@ -4,6 +4,7 @@ #include <asm/cpufeatures.h> #include <asm/alternative.h> +#include <linux/stringify.h> /* * The hypercall definitions differ in the low word of the %edx argument @@ -20,8 +21,8 @@ */ /* Old port-based version */ -#define VMWARE_HYPERVISOR_PORT "0x5658" -#define VMWARE_HYPERVISOR_PORT_HB "0x5659" +#define VMWARE_HYPERVISOR_PORT 0x5658 +#define VMWARE_HYPERVISOR_PORT_HB 0x5659 /* Current vmcall / vmmcall version */ #define VMWARE_HYPERVISOR_HB BIT(0) @@ -29,7 +30,8 @@ /* The low bandwidth call. The low word of edx is presumed clear. */ #define VMWARE_HYPERCALL \ - ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT ", %%dx; inl (%%dx)", \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \ + "inl (%%dx), %%eax", \ "vmcall", X86_FEATURE_VMCALL, \ "vmmcall", X86_FEATURE_VMW_VMMCALL) @@ -38,7 +40,8 @@ * HB and OUT bits set. */ #define VMWARE_HYPERCALL_HB_OUT \ - ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep outsb", \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ + "rep outsb", \ "vmcall", X86_FEATURE_VMCALL, \ "vmmcall", X86_FEATURE_VMW_VMMCALL) @@ -47,7 +50,8 @@ * HB bit set. */ #define VMWARE_HYPERCALL_HB_IN \ - ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep insb", \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ + "rep insb", \ "vmcall", X86_FEATURE_VMCALL, \ "vmmcall", X86_FEATURE_VMW_VMMCALL) #endif diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 9e2dd2b296cd..2b0faf86da1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1586,9 +1586,6 @@ static void setup_local_APIC(void) { int cpu = smp_processor_id(); unsigned int value; -#ifdef CONFIG_X86_32 - int logical_apicid, ldr_apicid; -#endif if (disable_apic) { disable_ioapic_support(); @@ -1626,16 +1623,21 @@ static void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d7a1e5a9331c..890f60083eca 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -30,7 +30,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o +obj-y += intel.o intel_pconfig.o tsx.o obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 91c2561b905f..4c7b0fa15a19 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -105,6 +106,7 @@ void __init check_bugs(void) ssb_select_mitigation(); l1tf_select_mitigation(); mds_select_mitigation(); + taa_select_mitigation(); arch_smt_update(); @@ -269,6 +271,100 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ + if (taa_mitigation == TAA_MITIGATION_OFF) + goto out; + + if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + if (taa_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); + +out: + pr_info("%s\n", taa_strings[taa_mitigation]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -786,13 +882,10 @@ static void update_mds_branch_idle(void) } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" void cpu_bugs_smt_update(void) { - /* Enhanced IBRS implies STIBP. No update required. */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) - return; - mutex_lock(&spec_ctrl_mutex); switch (spectre_v2_user) { @@ -819,6 +912,17 @@ void cpu_bugs_smt_update(void) break; } + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1149,6 +1253,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -1304,11 +1411,24 @@ static ssize_t l1tf_show_state(char *buf) l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); +} #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} #endif static ssize_t mds_show_state(char *buf) @@ -1328,6 +1448,21 @@ static ssize_t mds_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1398,6 +1533,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MDS: return mds_show_state(buf); + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -1434,4 +1575,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9ae7d1bcd4f4..fffe21945374 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1016,13 +1016,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } -#define NO_SPECULATION BIT(0) -#define NO_MELTDOWN BIT(1) -#define NO_SSB BIT(2) -#define NO_L1TF BIT(3) -#define NO_MDS BIT(4) -#define MSBDS_ONLY BIT(5) -#define NO_SWAPGS BIT(6) +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) +#define NO_ITLB_MULTIHIT BIT(7) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1043,27 +1044,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ - VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1073,15 +1074,17 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { * good enough for our purposes. */ + VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT), + /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), {} }; @@ -1092,19 +1095,30 @@ static bool __init cpu_matches(unsigned long which) return m && !!(m->driver_data & which); } -static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +u64 x86_read_arch_cap_msr(void) { u64 ia32_cap = 0; + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + return ia32_cap; +} + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ + if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); + if (cpu_matches(NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1121,6 +1135,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (!cpu_matches(NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); + /* + * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when: + * - TSX is supported or + * - TSX_CTRL is present + * + * TSX_CTRL check is needed for cases when TSX could be disabled before + * the kernel boot e.g. kexec. + * TSX_CTRL check alone is not sufficient for cases when the microcode + * update is not present or running as guest that don't get TSX_CTRL. + */ + if (!(ia32_cap & ARCH_CAP_TAA_NO) && + (cpu_has(c, X86_FEATURE_RTM) || + (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + setup_force_cpu_bug(X86_BUG_TAA); + if (cpu_matches(NO_MELTDOWN)) return; @@ -1554,6 +1583,8 @@ void __init identify_boot_cpu(void) #endif cpu_detect_tlb(&boot_cpu_data); setup_cr_pinning(); + + tsx_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index c0e2407abdd6..38ab6e115eac 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -44,6 +44,22 @@ struct _tlb_table { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +#ifdef CONFIG_CPU_SUP_INTEL +enum tsx_ctrl_states { + TSX_CTRL_ENABLE, + TSX_CTRL_DISABLE, + TSX_CTRL_NOT_SUPPORTED, +}; + +extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; + +extern void __init tsx_init(void); +extern void tsx_enable(void); +extern void tsx_disable(void); +#else +static inline void tsx_init(void) { } +#endif /* CONFIG_CPU_SUP_INTEL */ + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); @@ -62,4 +78,6 @@ unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern u64 x86_read_arch_cap_msr(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c2fdc00df163..11d5c5950e2d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -762,6 +762,11 @@ static void init_intel(struct cpuinfo_x86 *c) detect_tme(c); init_intel_misc_features(c); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index efbd54cc4e69..055c8613b531 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } md.priv = of->kn->priv; resid = md.u.rid; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index a46dee8e78db..2e3b06d6bbc6 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, } rdtgrp = rdtgroup_kn_lock_live(of->kn); - rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; - rdt_last_cmd_puts("Directory was removed\n"); goto unlock; } @@ -2648,10 +2646,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, int ret; prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); - rdt_last_cmd_clear(); if (!prdtgrp) { ret = -ENODEV; - rdt_last_cmd_puts("Directory was removed\n"); goto out_unlock; } diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c new file mode 100644 index 000000000000..3e20d322bc98 --- /dev/null +++ b/arch/x86/kernel/cpu/tsx.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Transactional Synchronization Extensions (TSX) control. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Pawan Gupta <pawan.kumar.gupta@linux.intel.com> + */ + +#include <linux/cpufeature.h> + +#include <asm/cmdline.h> + +#include "cpu.h" + +enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; + +void tsx_disable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Force all transactions to immediately abort */ + tsx |= TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is not enumerated in CPUID. + * This is visible to userspace and will ensure they + * do not waste resources trying TSX transactions that + * will always abort. + */ + tsx |= TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +void tsx_enable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Enable the RTM feature in the cpu */ + tsx &= ~TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is enumerated in CPUID. + * This is visible to userspace and will ensure they + * can enumerate and use the TSX feature. + */ + tsx &= ~TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +static bool __init tsx_ctrl_is_supported(void) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); +} + +static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) +{ + if (boot_cpu_has_bug(X86_BUG_TAA)) + return TSX_CTRL_DISABLE; + + return TSX_CTRL_ENABLE; +} + +void __init tsx_init(void) +{ + char arg[5] = {}; + int ret; + + if (!tsx_ctrl_is_supported()) + return; + + ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg)); + if (ret >= 0) { + if (!strcmp(arg, "on")) { + tsx_ctrl_state = TSX_CTRL_ENABLE; + } else if (!strcmp(arg, "off")) { + tsx_ctrl_state = TSX_CTRL_DISABLE; + } else if (!strcmp(arg, "auto")) { + tsx_ctrl_state = x86_get_tsx_auto_mode(); + } else { + tsx_ctrl_state = TSX_CTRL_DISABLE; + pr_err("tsx: invalid option, defaulting to off\n"); + } + } else { + /* tsx= not provided */ + if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO)) + tsx_ctrl_state = x86_get_tsx_auto_mode(); + else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF)) + tsx_ctrl_state = TSX_CTRL_DISABLE; + else + tsx_ctrl_state = TSX_CTRL_ENABLE; + } + + if (tsx_ctrl_state == TSX_CTRL_DISABLE) { + tsx_disable(); + + /* + * tsx_disable() will change the state of the + * RTM CPUID bit. Clear it here since it is now + * expected to be not set. + */ + setup_clear_cpu_cap(X86_FEATURE_RTM); + } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { + + /* + * HW defaults TSX to be enabled at bootup. + * We may still need the TSX enable support + * during init for special cases like + * kexec after TSX is disabled. + */ + tsx_enable(); + + /* + * tsx_enable() will change the state of the + * RTM CPUID bit. Force it here since it is now + * expected to be set. + */ + setup_force_cpu_cap(X86_FEATURE_RTM); + } +} diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 753b8cfe8b8a..87b97897a881 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); + /* + * Handle the case where stack trace is collected _before_ + * cea_exception_stacks had been initialized. + */ + if (!begin) + return false; + end = begin + sizeof(struct cea_exception_stacks); /* Bail if @stack is outside the exception stack area. */ if (stk < begin || stk >= end) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6f6b1d04dadf..4cba91ec8049 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -710,6 +710,8 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3ec4, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c59454c382fd..7e322e2daaf5 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1505,6 +1505,9 @@ void __init tsc_init(void) return; } + if (tsc_clocksource_reliable || no_tsc_watchdog) + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9c5029cf6f3f..f68c0c753c38 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -363,7 +363,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 87b0fcc23ef8..b29d00b661ff 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -111,11 +111,6 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline u8 kvm_xapic_id(struct kvm_lapic *apic) -{ - return kvm_lapic_get_reg(apic, APIC_ID) >> 24; -} - static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) { return apic->vcpu->vcpu_id; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 2aad7e226fc0..1f5014852e20 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -242,4 +242,9 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base) return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); } +static inline u8 kvm_xapic_id(struct kvm_lapic *apic) +{ + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; +} + #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 24c23c66b226..2ce9da58611e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kthread.h> #include <asm/page.h> #include <asm/pat.h> @@ -47,6 +48,35 @@ #include <asm/kvm_page_track.h> #include "trace.h" +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +#ifdef CONFIG_PREEMPT_RT +/* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ +static uint __read_mostly nx_huge_pages_recovery_ratio = 0; +#else +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; +#endif + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -352,6 +382,11 @@ static inline bool spte_ad_need_write_protect(u64 spte) return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK; } +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); +} + static inline u64 spte_shadow_accessed_mask(u64 spte) { MMU_WARN_ON(is_mmio_spte(spte)); @@ -1190,6 +1225,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -1207,6 +1253,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); +} + static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, struct kvm_memory_slot *slot) { @@ -2792,6 +2845,9 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return list_unstable; } @@ -3013,6 +3069,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -3233,9 +3294,32 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) +{ + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, int map_writable, int level, kvm_pfn_t pfn, - bool prefault) + bool prefault, bool lpage_disallowed) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; @@ -3248,6 +3332,12 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, trace_kvm_mmu_spte_requested(gpa, level, pfn); for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == level) break; @@ -3258,6 +3348,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, it.level - 1, true, ACC_ALL); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -3306,7 +3398,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, * here. */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && + !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; @@ -3550,11 +3642,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - bool force_pt_level = false; + bool force_pt_level; kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + force_pt_level = lpage_disallowed; level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { /* @@ -3588,7 +3683,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault); + r = __direct_map(vcpu, v, write, map_writable, level, pfn, + prefault, false); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); @@ -4174,6 +4270,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; bool map_writable; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); @@ -4184,8 +4282,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); + force_pt_level = + lpage_disallowed || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL); level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { if (level > PT_DIRECTORY_LEVEL && @@ -4214,7 +4313,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault); + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, + prefault, lpage_disallowed); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); @@ -5914,9 +6014,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + !kvm_is_zone_device_pfn(pfn) && + PageTransCompoundMap(pfn_to_page(pfn))) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -6155,10 +6255,59 @@ static void kvm_set_mmio_spte_mask(void) kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); } +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + mutex_lock(&kvm->slots_lock); + kvm_mmu_zap_all_fast(kvm); + mutex_unlock(&kvm->slots_lock); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; +} + int kvm_mmu_module_init(void) { int ret = -ENOMEM; + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + /* * MMU roles use union aliasing which is, generally speaking, an * undefined behavior. However, we supposedly know how compilers behave @@ -6238,3 +6387,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 11f8ec89433b..d55674f44a18 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -210,4 +210,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 7d5cdb3af594..97b21e7fd013 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -614,13 +614,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; int top_level, ret; - gfn_t base_gfn; + gfn_t gfn, base_gfn; direct_access = gw->pte_access; @@ -665,13 +666,25 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - base_gfn = gw->gfn; + /* + * FNAME(page_fault) might have clobbered the bottom bits of + * gw->gfn, restore them from the virtual address. + */ + gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT); + base_gfn = gfn; trace_kvm_mmu_spte_requested(addr, gw->level, pfn); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); - base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel); + + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == hlevel) break; @@ -683,6 +696,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, sp = kvm_mmu_get_page(vcpu, base_gfn, addr, it.level - 1, true, direct_access); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -759,9 +774,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + bool force_pt_level = lpage_disallowed; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -851,7 +868,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (!force_pt_level) transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); + level, pfn, map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f8ecb6df5106..c5673bda4b66 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -734,8 +734,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -4591,6 +4597,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); + u32 id = kvm_xapic_id(vcpu->arch.apic); if (ldr == svm->ldr_reg) return 0; @@ -4598,7 +4605,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) avic_invalidate_logical_id_entry(vcpu); if (ldr) - ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr); + ret = avic_ldr_write(vcpu, id, ldr); if (!ret) svm->ldr_reg = ldr; @@ -4610,8 +4617,7 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) { u64 *old, *new; struct vcpu_svm *svm = to_svm(vcpu); - u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID); - u32 id = (apic_id_reg >> 24) & 0xff; + u32 id = kvm_xapic_id(vcpu->arch.apic); if (vcpu->vcpu_id == id) return 0; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e76eb4f07f6c..0e7c9301fe86 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2917,7 +2917,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); -static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -2937,19 +2937,18 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) vmx->nested.apic_access_page = NULL; } page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr); - /* - * If translation failed, no matter: This feature asks - * to exit when accessing the given address, and if it - * can never be accessed, this feature won't do - * anything anyway. - */ if (!is_error_page(page)) { vmx->nested.apic_access_page = page; hpa = page_to_phys(vmx->nested.apic_access_page); vmcs_write64(APIC_ACCESS_ADDR, hpa); } else { - secondary_exec_controls_clearbit(vmx, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; } } @@ -2994,6 +2993,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); + return true; } /* @@ -3032,13 +3032,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* * If from_vmentry is false, this is being called from state restore (either RSM * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. -+ * -+ * Returns: -+ * 0 - success, i.e. proceed with actual VMEnter -+ * 1 - consistency check VMExit -+ * -1 - consistency check VMFail + * + * Returns: + * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_ENTRY_VMFAIL: Consistency check VMFail + * NVMX_ENTRY_VMEXIT: Consistency check VMExit + * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error */ -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -3081,11 +3083,12 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) prepare_vmcs02_early(vmx, vmcs12); if (from_vmentry) { - nested_get_vmcs12_pages(vcpu); + if (unlikely(!nested_get_vmcs12_pages(vcpu))) + return NVMX_VMENTRY_KVM_INTERNAL_ERROR; if (nested_vmx_check_vmentry_hw(vcpu)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); - return -1; + return NVMX_VMENTRY_VMFAIL; } if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) @@ -3149,7 +3152,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ - return 0; + return NVMX_VMENTRY_SUCCESS; /* * A failed consistency check that leads to a VMExit during L1's @@ -3165,14 +3168,14 @@ vmentry_fail_vmexit: vmx_switch_vmcs(vcpu, &vmx->vmcs01); if (!from_vmentry) - return 1; + return NVMX_VMENTRY_VMEXIT; load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->exit_qualification = exit_qual; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) vmx->nested.need_vmcs12_to_shadow_sync = true; - return 1; + return NVMX_VMENTRY_VMEXIT; } /* @@ -3182,9 +3185,9 @@ vmentry_fail_vmexit: static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) { struct vmcs12 *vmcs12; + enum nvmx_vmentry_status status; struct vcpu_vmx *vmx = to_vmx(vcpu); u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); - int ret; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -3244,13 +3247,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ vmx->nested.nested_run_pending = 1; - ret = nested_vmx_enter_non_root_mode(vcpu, true); - vmx->nested.nested_run_pending = !ret; - if (ret > 0) - return 1; - else if (ret) - return nested_vmx_failValid(vcpu, - VMXERR_ENTRY_INVALID_CONTROL_FIELD); + status = nested_vmx_enter_non_root_mode(vcpu, true); + if (unlikely(status != NVMX_VMENTRY_SUCCESS)) + goto vmentry_failed; /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; @@ -3281,6 +3280,15 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return kvm_vcpu_halt(vcpu); } return 1; + +vmentry_failed: + vmx->nested.nested_run_pending = 0; + if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) + return 0; + if (status == NVMX_VMENTRY_VMEXIT) + return 1; + WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL); + return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); } /* diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 187d39bf0bf1..6280f33e5fa6 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -6,6 +6,16 @@ #include "vmcs12.h" #include "vmx.h" +/* + * Status returned by nested_vmx_enter_non_root_mode(): + */ +enum nvmx_vmentry_status { + NVMX_VMENTRY_SUCCESS, /* Entered VMX non-root mode */ + NVMX_VMENTRY_VMFAIL, /* Consistency check VMFail */ + NVMX_VMENTRY_VMEXIT, /* Consistency check VMExit */ + NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */ +}; + void vmx_leave_nested(struct kvm_vcpu *vcpu); void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, bool apicv); @@ -13,7 +23,8 @@ void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_vcpu_setup(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry); bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason); void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, u32 exit_intr_info, unsigned long exit_qualification); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e7970a2e8eae..04a8212704c1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -969,17 +969,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. @@ -1276,6 +1268,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block is the one expected to change PID.NDST and the + * wakeup handler expects the vCPU to be on the blocked_vcpu_list that + * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up + * correctly. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + goto after_clear_sn; + } + /* The full case. */ do { old.control = new.control = pi_desc->control; @@ -1291,6 +1295,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); +after_clear_sn: + /* * Clear SN before reading the bitmap. The VT-d firmware * writes the bitmap and reads SN atomically (5.2.3 in the @@ -1299,7 +1305,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) */ smp_mb__after_atomic(); - if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)) + if (!pi_is_pir_empty(pi_desc)) pi_set_on(pi_desc); } @@ -5543,14 +5549,6 @@ static int handle_encls(struct kvm_vcpu *vcpu) return 1; } -static int handle_unexpected_vmexit(struct kvm_vcpu *vcpu) -{ - kvm_skip_emulated_instruction(vcpu); - WARN_ONCE(1, "Unexpected VM-Exit Reason = 0x%x", - vmcs_read32(VM_EXIT_REASON)); - return 1; -} - /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5602,15 +5600,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_INVVPID] = handle_vmx_instruction, [EXIT_REASON_RDRAND] = handle_invalid_op, [EXIT_REASON_RDSEED] = handle_invalid_op, - [EXIT_REASON_XSAVES] = handle_unexpected_vmexit, - [EXIT_REASON_XRSTORS] = handle_unexpected_vmexit, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, - [EXIT_REASON_UMWAIT] = handle_unexpected_vmexit, - [EXIT_REASON_TPAUSE] = handle_unexpected_vmexit, }; static const int kvm_vmx_max_exit_handlers = @@ -6157,7 +6151,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) if (pi_test_on(&vmx->pi_desc)) { pi_clear_on(&vmx->pi_desc); /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); @@ -6187,7 +6181,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { - return pi_test_on(vcpu_to_pi_desc(vcpu)); + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + return pi_test_on(pi_desc) || + (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc)); } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index bee16687dc0b..5a0f34b1e226 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -355,6 +355,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); +} + static inline void pi_set_sn(struct pi_desc *pi_desc) { set_bit(POSTED_INTR_SN, @@ -373,6 +378,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + static inline int pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 661e2bf38526..5d530521f11d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -213,6 +213,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, { "largepages", VM_STAT(lpages, .mode = 0444) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -360,8 +361,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base); asmlinkage __visible void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ - if (!kvm_rebooting) - BUG(); + BUG_ON(!kvm_rebooting); } EXPORT_SYMBOL_GPL(kvm_spurious_fault); @@ -1133,13 +1133,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * - * This list is modified at module load time to reflect the + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) + * extract the supported MSRs from the related const lists. + * msrs_to_save is selected from the msrs_to_save_all to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs * may depend on host virtualization features rather than host cpu features. */ -static u32 msrs_to_save[] = { +static const u32 msrs_to_save_all[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1180,9 +1182,10 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, }; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; static unsigned num_msrs_to_save; -static u32 emulated_msrs[] = { +static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, @@ -1221,7 +1224,7 @@ static u32 emulated_msrs[] = { * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs. * We always support the "true" VMX control MSRs, even if the host * processor does not, so I am putting these registers here rather - * than in msrs_to_save. + * than in msrs_to_save_all. */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, @@ -1240,13 +1243,14 @@ static u32 emulated_msrs[] = { MSR_KVM_POLL_CONTROL, }; +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* * List of msr numbers which are used to expose MSR-based features that * can be used by a hypervisor to validate requested CPU features. */ -static u32 msr_based_features[] = { +static const u32 msr_based_features_all[] = { MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, MSR_IA32_VMX_PINBASED_CTLS, @@ -1271,6 +1275,7 @@ static u32 msr_based_features[] = { MSR_IA32_ARCH_CAPABILITIES, }; +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_features; static u64 kvm_get_arch_capabilities(void) @@ -1281,6 +1286,14 @@ static u64 kvm_get_arch_capabilities(void) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1299,6 +1312,25 @@ static u64 kvm_get_arch_capabilities(void) if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + /* + * On TAA affected systems, export MDS_NO=0 when: + * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1. + * - Updated microcode is present. This is detected by + * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures + * that VERW clears CPU buffers. + * + * When MDS_NO=0 is exported, guests deploy clear CPU buffer + * mitigation and don't complain: + * + * "Vulnerable: Clear CPU buffers attempted, no microcode" + * + * If TSX is disabled on the system, guests are also mitigated against + * TAA and clear CPU buffer mitigation is not required for guests. + */ + if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) && + (data & ARCH_CAP_TSX_CTRL_MSR)) + data &= ~ARCH_CAP_MDS_NO; + return data; } @@ -2537,6 +2569,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { vcpu->arch.pv_time_enabled = false; + vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) @@ -2702,8 +2735,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_KVM_SYSTEM_TIME: { struct kvm_arch *ka = &vcpu->kvm->arch; - kvmclock_reset(vcpu); - if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) { bool tmp = (msr == MSR_KVM_SYSTEM_TIME); @@ -2717,14 +2748,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ + vcpu->arch.pv_time_enabled = false; if (!(data & 1)) break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (!kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) - vcpu->arch.pv_time_enabled = false; - else vcpu->arch.pv_time_enabled = true; break; @@ -5093,22 +5123,26 @@ static void kvm_init_msr_list(void) { struct x86_pmu_capability x86_pmu; u32 dummy[2]; - unsigned i, j; + unsigned i; BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, - "Please update the fixed PMCs in msrs_to_save[]"); + "Please update the fixed PMCs in msrs_to_saved_all[]"); perf_get_x86_pmu_capability(&x86_pmu); - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { - if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) + num_msrs_to_save = 0; + num_emulated_msrs = 0; + num_msr_based_features = 0; + + for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { + if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) continue; /* * Even MSRs that are valid in the host may not be exposed * to the guests in some cases. */ - switch (msrs_to_save[i]) { + switch (msrs_to_save_all[i]) { case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported()) continue; @@ -5136,17 +5170,17 @@ static void kvm_init_msr_list(void) break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { if (!kvm_x86_ops->pt_supported() || - msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >= + msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: - if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >= + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) continue; break; case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: - if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) continue; } @@ -5154,34 +5188,25 @@ static void kvm_init_msr_list(void) break; } - if (j < i) - msrs_to_save[j] = msrs_to_save[i]; - j++; + msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; } - num_msrs_to_save = j; - for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i])) continue; - if (j < i) - emulated_msrs[j] = emulated_msrs[i]; - j++; + emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - num_emulated_msrs = j; - for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) { struct kvm_msr_entry msr; - msr.index = msr_based_features[i]; + msr.index = msr_based_features_all[i]; if (kvm_get_msr_feature(&msr)) continue; - if (j < i) - msr_based_features[j] = msr_based_features[i]; - j++; + msr_based_features[num_msr_based_features++] = msr_based_features_all[i]; } - num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -7941,8 +7966,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) - kvm_x86_ops->get_vmcs12_pages(vcpu); + if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) { + if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) { + r = 0; + goto out; + } + } if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) @@ -9427,6 +9456,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -9455,6 +9485,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return kvm_x86_ops->vm_init(kvm); } +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); +} + static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); @@ -9556,6 +9591,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(x86_set_memory_region); +void kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ + kvm_mmu_pre_destroy_vm(kvm); +} + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 58f79ab32358..5bfea374a160 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -117,6 +117,14 @@ static void __init xen_banner(void) printk(KERN_INFO "Xen version: %d.%d%s%s\n", version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); + +#ifdef CONFIG_X86_32 + pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n" + "Support for running as 32-bit PV-guest under Xen will soon be removed\n" + "from the Linux kernel!\n" + "Please use either a 64-bit kernel or switch to HVM or PVH mode!\n" + "WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"); +#endif } static void __init xen_pv_init_platform(void) diff --git a/block/Kconfig b/block/Kconfig index 41c0917ce622..c23094a14a2b 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -32,6 +32,9 @@ config BLK_RQ_ALLOC_TIME config BLK_SCSI_REQUEST bool +config BLK_CGROUP_RWSTAT + bool + config BLK_DEV_BSG bool "Block layer SG support v4" default y @@ -86,6 +89,7 @@ config BLK_DEV_ZONED config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y + select BLK_CGROUP_RWSTAT ---help--- Block layer bio throttling support. It can be used to limit the IO rate to a device. IO rate policies are per cgroup and diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index b89310a022ad..7df14133adc8 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -31,6 +31,7 @@ config IOSCHED_BFQ config BFQ_GROUP_IOSCHED bool "BFQ hierarchical scheduling support" depends on IOSCHED_BFQ && BLK_CGROUP + select BLK_CGROUP_RWSTAT ---help--- Enable hierarchical scheduling in BFQ, using the blkio diff --git a/block/Makefile b/block/Makefile index 9ef57ace90d4..205a5f2fef17 100644 --- a/block/Makefile +++ b/block/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o +obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 86a607cf19a1..cea0ae12f937 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -347,6 +347,14 @@ void bfqg_and_blkg_put(struct bfq_group *bfqg) bfqg_put(bfqg); } +void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq) +{ + struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg); + + blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq)); + blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1); +} + /* @stats = 0 */ static void bfqg_stats_reset(struct bfqg_stats *stats) { @@ -431,6 +439,8 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg) static void bfqg_stats_exit(struct bfqg_stats *stats) { + blkg_rwstat_exit(&stats->bytes); + blkg_rwstat_exit(&stats->ios); #ifdef CONFIG_BFQ_CGROUP_DEBUG blkg_rwstat_exit(&stats->merged); blkg_rwstat_exit(&stats->service_time); @@ -448,6 +458,10 @@ static void bfqg_stats_exit(struct bfqg_stats *stats) static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp) { + if (blkg_rwstat_init(&stats->bytes, gfp) || + blkg_rwstat_init(&stats->ios, gfp)) + return -ENOMEM; + #ifdef CONFIG_BFQ_CGROUP_DEBUG if (blkg_rwstat_init(&stats->merged, gfp) || blkg_rwstat_init(&stats->service_time, gfp) || @@ -1057,18 +1071,35 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of, return bfq_io_set_device_weight(of, buf, nbytes, off); } -#ifdef CONFIG_BFQ_CGROUP_DEBUG -static int bfqg_print_stat(struct seq_file *sf, void *v) +static int bfqg_print_rwstat(struct seq_file *sf, void *v) { - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, - &blkcg_policy_bfq, seq_cft(sf)->private, false); + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, + &blkcg_policy_bfq, seq_cft(sf)->private, true); return 0; } -static int bfqg_print_rwstat(struct seq_file *sf, void *v) +static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) { - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, - &blkcg_policy_bfq, seq_cft(sf)->private, true); + struct blkg_rwstat_sample sum; + + blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum); + return __blkg_prfill_rwstat(sf, pd, &sum); +} + +static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq, + seq_cft(sf)->private, true); + return 0; +} + +#ifdef CONFIG_BFQ_CGROUP_DEBUG +static int bfqg_print_stat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, + &blkcg_policy_bfq, seq_cft(sf)->private, false); return 0; } @@ -1097,15 +1128,6 @@ static u64 bfqg_prfill_stat_recursive(struct seq_file *sf, return __blkg_prfill_u64(sf, pd, sum); } -static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf, - struct blkg_policy_data *pd, int off) -{ - struct blkg_rwstat_sample sum; - - blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum); - return __blkg_prfill_rwstat(sf, pd, &sum); -} - static int bfqg_print_stat_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), @@ -1114,18 +1136,11 @@ static int bfqg_print_stat_recursive(struct seq_file *sf, void *v) return 0; } -static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq, - seq_cft(sf)->private, true); - return 0; -} - static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd, int off) { - u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes); + struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg); + u64 sum = blkg_rwstat_total(&bfqg->stats.bytes); return __blkg_prfill_u64(sf, pd, sum >> 9); } @@ -1142,8 +1157,8 @@ static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf, { struct blkg_rwstat_sample tmp; - blkg_rwstat_recursive_sum(pd->blkg, NULL, - offsetof(struct blkcg_gq, stat_bytes), &tmp); + blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq, + offsetof(struct bfq_group, stats.bytes), &tmp); return __blkg_prfill_u64(sf, pd, (tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9); @@ -1226,13 +1241,13 @@ struct cftype bfq_blkcg_legacy_files[] = { /* statistics, covers only the tasks in the bfqg */ { .name = "bfq.io_service_bytes", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes, + .private = offsetof(struct bfq_group, stats.bytes), + .seq_show = bfqg_print_rwstat, }, { .name = "bfq.io_serviced", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios, + .private = offsetof(struct bfq_group, stats.ios), + .seq_show = bfqg_print_rwstat, }, #ifdef CONFIG_BFQ_CGROUP_DEBUG { @@ -1269,13 +1284,13 @@ struct cftype bfq_blkcg_legacy_files[] = { /* the same statistics which cover the bfqg and its descendants */ { .name = "bfq.io_service_bytes_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes_recursive, + .private = offsetof(struct bfq_group, stats.bytes), + .seq_show = bfqg_print_rwstat_recursive, }, { .name = "bfq.io_serviced_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios_recursive, + .private = offsetof(struct bfq_group, stats.ios), + .seq_show = bfqg_print_rwstat_recursive, }, #ifdef CONFIG_BFQ_CGROUP_DEBUG { diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0319d6339822..ad4af4aaf2ce 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2713,6 +2713,28 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) } } + +static +void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + /* + * To prevent bfqq's service guarantees from being violated, + * bfqq may be left busy, i.e., queued for service, even if + * empty (see comments in __bfq_bfqq_expire() for + * details). But, if no process will send requests to bfqq any + * longer, then there is no point in keeping bfqq queued for + * service. In addition, keeping bfqq queued for service, but + * with no process ref any longer, may have caused bfqq to be + * freed when dequeued from service. But this is assumed to + * never happen. + */ + if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) && + bfqq != bfqd->in_service_queue) + bfq_del_bfqq_busy(bfqd, bfqq, false); + + bfq_put_queue(bfqq); +} + static void bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) @@ -2783,8 +2805,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, */ new_bfqq->pid = -1; bfqq->bic = NULL; - /* release process reference to bfqq */ - bfq_put_queue(bfqq); + bfq_release_process_ref(bfqd, bfqq); } static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, @@ -4899,7 +4920,7 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_put_cooperator(bfqq); - bfq_put_queue(bfqq); /* release process reference */ + bfq_release_process_ref(bfqd, bfqq); } static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) @@ -5001,8 +5022,7 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bfqq = bic_to_bfqq(bic, false); if (bfqq) { - /* release process reference on this queue */ - bfq_put_queue(bfqq); + bfq_release_process_ref(bfqd, bfqq); bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic); bic_set_bfqq(bic, bfqq, false); } @@ -5464,6 +5484,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool idle_timer_disabled = false; unsigned int cmd_flags; +#ifdef CONFIG_BFQ_GROUP_IOSCHED + if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio) + bfqg_stats_update_legacy_io(q, rq); +#endif spin_lock_irq(&bfqd->lock); if (blk_mq_sched_try_insert_merge(q, rq)) { spin_unlock_irq(&bfqd->lock); @@ -5963,7 +5987,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) bfq_put_cooperator(bfqq); - bfq_put_queue(bfqq); + bfq_release_process_ref(bfqq->bfqd, bfqq); return NULL; } diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 5d1a519640f6..8526f20c53bc 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -10,6 +10,8 @@ #include <linux/hrtimer.h> #include <linux/blk-cgroup.h> +#include "blk-cgroup-rwstat.h" + #define BFQ_IOPRIO_CLASSES 3 #define BFQ_CL_IDLE_TIMEOUT (HZ/5) @@ -809,6 +811,9 @@ struct bfq_stat { }; struct bfqg_stats { + /* basic stats */ + struct blkg_rwstat bytes; + struct blkg_rwstat ios; #ifdef CONFIG_BFQ_CGROUP_DEBUG /* number of ios merged */ struct blkg_rwstat merged; @@ -956,6 +961,7 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); /* ---------------- cgroups-support interface ---------------- */ +void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq); void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, unsigned int op); void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op); @@ -1062,6 +1068,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ char pid_str[MAX_PID_STR_LENGTH]; \ + if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \ + break; \ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ blk_add_cgroup_trace_msg((bfqd)->queue, \ bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \ @@ -1078,6 +1086,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq); #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ char pid_str[MAX_PID_STR_LENGTH]; \ + if (likely(!blk_trace_note_message_enabled((bfqd)->queue))) \ + break; \ bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH); \ blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str, \ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ diff --git a/block/bio.c b/block/bio.c index 8f0ed6228fc5..b1170ec18464 100644 --- a/block/bio.c +++ b/block/bio.c @@ -751,7 +751,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page, if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) return false; - if (bio->bi_vcnt > 0) { + if (bio->bi_vcnt > 0 && !bio_full(bio, len)) { struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page_is_mergeable(bv, page, len, off, same_page)) { diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c new file mode 100644 index 000000000000..85d5790ac49b --- /dev/null +++ b/block/blk-cgroup-rwstat.c @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT. + * Do not use in new code. + */ +#include "blk-cgroup-rwstat.h" + +int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) +{ + int i, ret; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); + if (ret) { + while (--i >= 0) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); + return ret; + } + atomic64_set(&rwstat->aux_cnt[i], 0); + } + return 0; +} +EXPORT_SYMBOL_GPL(blkg_rwstat_init); + +void blkg_rwstat_exit(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); +} +EXPORT_SYMBOL_GPL(blkg_rwstat_exit); + +/** + * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat + * @sf: seq_file to print to + * @pd: policy private data of interest + * @rwstat: rwstat to print + * + * Print @rwstat to @sf for the device assocaited with @pd. + */ +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat_sample *rwstat) +{ + static const char *rwstr[] = { + [BLKG_RWSTAT_READ] = "Read", + [BLKG_RWSTAT_WRITE] = "Write", + [BLKG_RWSTAT_SYNC] = "Sync", + [BLKG_RWSTAT_ASYNC] = "Async", + [BLKG_RWSTAT_DISCARD] = "Discard", + }; + const char *dname = blkg_dev_name(pd->blkg); + u64 v; + int i; + + if (!dname) + return 0; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + seq_printf(sf, "%s %s %llu\n", dname, rwstr[i], + rwstat->cnt[i]); + + v = rwstat->cnt[BLKG_RWSTAT_READ] + + rwstat->cnt[BLKG_RWSTAT_WRITE] + + rwstat->cnt[BLKG_RWSTAT_DISCARD]; + seq_printf(sf, "%s Total %llu\n", dname, v); + return v; +} +EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat); + +/** + * blkg_prfill_rwstat - prfill callback for blkg_rwstat + * @sf: seq_file to print to + * @pd: policy private data of interest + * @off: offset to the blkg_rwstat in @pd + * + * prfill callback for printing a blkg_rwstat. + */ +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off) +{ + struct blkg_rwstat_sample rwstat = { }; + + blkg_rwstat_read((void *)pd + off, &rwstat); + return __blkg_prfill_rwstat(sf, pd, &rwstat); +} +EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); + +/** + * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat + * @blkg: blkg of interest + * @pol: blkcg_policy which contains the blkg_rwstat + * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg + * @sum: blkg_rwstat_sample structure containing the results + * + * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its + * online descendants and their aux counts. The caller must be holding the + * queue lock for online tests. + * + * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it + * is at @off bytes into @blkg's blkg_policy_data of the policy. + */ +void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, + int off, struct blkg_rwstat_sample *sum) +{ + struct blkcg_gq *pos_blkg; + struct cgroup_subsys_state *pos_css; + unsigned int i; + + lockdep_assert_held(&blkg->q->queue_lock); + + rcu_read_lock(); + blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { + struct blkg_rwstat *rwstat; + + if (!pos_blkg->online) + continue; + + if (pol) + rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off; + else + rwstat = (void *)pos_blkg + off; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h new file mode 100644 index 000000000000..ee746919c41f --- /dev/null +++ b/block/blk-cgroup-rwstat.h @@ -0,0 +1,149 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT. + * Do not use in new code. + */ +#ifndef _BLK_CGROUP_RWSTAT_H +#define _BLK_CGROUP_RWSTAT_H + +#include <linux/blk-cgroup.h> + +enum blkg_rwstat_type { + BLKG_RWSTAT_READ, + BLKG_RWSTAT_WRITE, + BLKG_RWSTAT_SYNC, + BLKG_RWSTAT_ASYNC, + BLKG_RWSTAT_DISCARD, + + BLKG_RWSTAT_NR, + BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, +}; + +/* + * blkg_[rw]stat->aux_cnt is excluded for local stats but included for + * recursive. Used to carry stats of dead children. + */ +struct blkg_rwstat { + struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; + atomic64_t aux_cnt[BLKG_RWSTAT_NR]; +}; + +struct blkg_rwstat_sample { + u64 cnt[BLKG_RWSTAT_NR]; +}; + +static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, + unsigned int idx) +{ + return atomic64_read(&rwstat->aux_cnt[idx]) + + percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); +} + +int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp); +void blkg_rwstat_exit(struct blkg_rwstat *rwstat); +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat_sample *rwstat); +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off); +void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, + int off, struct blkg_rwstat_sample *sum); + + +/** + * blkg_rwstat_add - add a value to a blkg_rwstat + * @rwstat: target blkg_rwstat + * @op: REQ_OP and flags + * @val: value to add + * + * Add @val to @rwstat. The counters are chosen according to @rw. The + * caller is responsible for synchronizing calls to this function. + */ +static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, + unsigned int op, uint64_t val) +{ + struct percpu_counter *cnt; + + if (op_is_discard(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; + else if (op_is_write(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; + + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); + + if (op_is_sync(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; + + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); +} + +/** + * blkg_rwstat_read - read the current values of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Read the current snapshot of @rwstat and return it in the aux counts. + */ +static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, + struct blkg_rwstat_sample *result) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + result->cnt[i] = + percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); +} + +/** + * blkg_rwstat_total - read the total count of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Return the total count of @rwstat regardless of the IO direction. This + * function can be called without synchronization and takes care of u64 + * atomicity. + */ +static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) +{ + struct blkg_rwstat_sample tmp = { }; + + blkg_rwstat_read(rwstat, &tmp); + return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; +} + +/** + * blkg_rwstat_reset - reset a blkg_rwstat + * @rwstat: blkg_rwstat to reset + */ +static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + percpu_counter_set(&rwstat->cpu_cnt[i], 0); + atomic64_set(&rwstat->aux_cnt[i], 0); + } +} + +/** + * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count + * @to: the destination blkg_rwstat + * @from: the source + * + * Add @from's count including the aux one to @to's aux count. + */ +static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, + struct blkg_rwstat *from) +{ + u64 sum[BLKG_RWSTAT_NR]; + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]), + &to->aux_cnt[i]); +} +#endif /* _BLK_CGROUP_RWSTAT_H */ diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5d21027b1faf..708dea92dac8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -80,8 +80,7 @@ static void blkg_free(struct blkcg_gq *blkg) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); - blkg_rwstat_exit(&blkg->stat_ios); - blkg_rwstat_exit(&blkg->stat_bytes); + free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } @@ -146,7 +145,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, gfp_t gfp_mask) { struct blkcg_gq *blkg; - int i; + int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node); @@ -156,8 +155,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto err_free; - if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) || - blkg_rwstat_init(&blkg->stat_ios, gfp_mask)) + blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); + if (!blkg->iostat_cpu) goto err_free; blkg->q = q; @@ -167,6 +166,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); blkg->blkcg = blkcg; + u64_stats_init(&blkg->iostat.sync); + for_each_possible_cpu(cpu) + u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); + for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; @@ -393,7 +396,6 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; - struct blkcg_gq *parent = blkg->parent; int i; lockdep_assert_held(&blkg->q->queue_lock); @@ -410,11 +412,6 @@ static void blkg_destroy(struct blkcg_gq *blkg) pol->pd_offline_fn(blkg->pd[i]); } - if (parent) { - blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); - blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); - } - blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); @@ -464,7 +461,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; - int i; + int i, cpu; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); @@ -475,8 +472,12 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - blkg_rwstat_reset(&blkg->stat_bytes); - blkg_rwstat_reset(&blkg->stat_ios); + for_each_possible_cpu(cpu) { + struct blkg_iostat_set *bis = + per_cpu_ptr(blkg->iostat_cpu, cpu); + memset(bis, 0, sizeof(*bis)); + } + memset(&blkg->iostat, 0, sizeof(blkg->iostat)); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -560,186 +561,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); -/** - * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat - * @sf: seq_file to print to - * @pd: policy private data of interest - * @rwstat: rwstat to print - * - * Print @rwstat to @sf for the device assocaited with @pd. - */ -u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - const struct blkg_rwstat_sample *rwstat) -{ - static const char *rwstr[] = { - [BLKG_RWSTAT_READ] = "Read", - [BLKG_RWSTAT_WRITE] = "Write", - [BLKG_RWSTAT_SYNC] = "Sync", - [BLKG_RWSTAT_ASYNC] = "Async", - [BLKG_RWSTAT_DISCARD] = "Discard", - }; - const char *dname = blkg_dev_name(pd->blkg); - u64 v; - int i; - - if (!dname) - return 0; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - seq_printf(sf, "%s %s %llu\n", dname, rwstr[i], - rwstat->cnt[i]); - - v = rwstat->cnt[BLKG_RWSTAT_READ] + - rwstat->cnt[BLKG_RWSTAT_WRITE] + - rwstat->cnt[BLKG_RWSTAT_DISCARD]; - seq_printf(sf, "%s Total %llu\n", dname, v); - return v; -} -EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat); - -/** - * blkg_prfill_rwstat - prfill callback for blkg_rwstat - * @sf: seq_file to print to - * @pd: policy private data of interest - * @off: offset to the blkg_rwstat in @pd - * - * prfill callback for printing a blkg_rwstat. - */ -u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - int off) -{ - struct blkg_rwstat_sample rwstat = { }; - - blkg_rwstat_read((void *)pd + off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} -EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); - -static u64 blkg_prfill_rwstat_field(struct seq_file *sf, - struct blkg_policy_data *pd, int off) -{ - struct blkg_rwstat_sample rwstat = { }; - - blkg_rwstat_read((void *)pd->blkg + off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} - -/** - * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes - * @sf: seq_file to print to - * @v: unused - * - * To be used as cftype->seq_show to print blkg->stat_bytes. - * cftype->private must be set to the blkcg_policy. - */ -int blkg_print_stat_bytes(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_bytes), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_bytes); - -/** - * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios - * @sf: seq_file to print to - * @v: unused - * - * To be used as cftype->seq_show to print blkg->stat_ios. cftype->private - * must be set to the blkcg_policy. - */ -int blkg_print_stat_ios(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_ios), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_ios); - -static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf, - struct blkg_policy_data *pd, - int off) -{ - struct blkg_rwstat_sample rwstat; - - blkg_rwstat_recursive_sum(pd->blkg, NULL, off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} - -/** - * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes - * @sf: seq_file to print to - * @v: unused - */ -int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field_recursive, - (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_bytes), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive); - -/** - * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios - * @sf: seq_file to print to - * @v: unused - */ -int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field_recursive, - (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_ios), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive); - -/** - * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat - * @blkg: blkg of interest - * @pol: blkcg_policy which contains the blkg_rwstat - * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg - * @sum: blkg_rwstat_sample structure containing the results - * - * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its - * online descendants and their aux counts. The caller must be holding the - * queue lock for online tests. - * - * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it - * is at @off bytes into @blkg's blkg_policy_data of the policy. - */ -void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, - int off, struct blkg_rwstat_sample *sum) -{ - struct blkcg_gq *pos_blkg; - struct cgroup_subsys_state *pos_css; - unsigned int i; - - lockdep_assert_held(&blkg->q->queue_lock); - - rcu_read_lock(); - blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { - struct blkg_rwstat *rwstat; - - if (!pos_blkg->online) - continue; - - if (pol) - rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off; - else - rwstat = (void *)pos_blkg + off; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); - } - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); - /* Performs queue bypass and policy enabled checks then looks up blkg. */ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, const struct blkcg_policy *pol, @@ -923,20 +744,27 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; + cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + struct blkg_iostat_set *bis = &blkg->iostat; const char *dname; char *buf; - struct blkg_rwstat_sample rwstat; u64 rbytes, wbytes, rios, wios, dbytes, dios; size_t size = seq_get_buf(sf, &buf), off = 0; int i; bool has_stats = false; + unsigned seq; + + spin_lock_irq(&blkg->q->queue_lock); + + if (!blkg->online) + goto skip; dname = blkg_dev_name(blkg); if (!dname) - continue; + goto skip; /* * Hooray string manipulation, count is the size written NOT @@ -946,21 +774,16 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) */ off += scnprintf(buf+off, size-off, "%s ", dname); - spin_lock_irq(&blkg->q->queue_lock); - - blkg_rwstat_recursive_sum(blkg, NULL, - offsetof(struct blkcg_gq, stat_bytes), &rwstat); - rbytes = rwstat.cnt[BLKG_RWSTAT_READ]; - wbytes = rwstat.cnt[BLKG_RWSTAT_WRITE]; - dbytes = rwstat.cnt[BLKG_RWSTAT_DISCARD]; - - blkg_rwstat_recursive_sum(blkg, NULL, - offsetof(struct blkcg_gq, stat_ios), &rwstat); - rios = rwstat.cnt[BLKG_RWSTAT_READ]; - wios = rwstat.cnt[BLKG_RWSTAT_WRITE]; - dios = rwstat.cnt[BLKG_RWSTAT_DISCARD]; + do { + seq = u64_stats_fetch_begin(&bis->sync); - spin_unlock_irq(&blkg->q->queue_lock); + rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; + wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; + dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; + rios = bis->cur.ios[BLKG_IOSTAT_READ]; + wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; + dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; + } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { has_stats = true; @@ -999,6 +822,8 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) seq_commit(sf, -1); } } + skip: + spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); @@ -1294,6 +1119,77 @@ static int blkcg_can_attach(struct cgroup_taskset *tset) return ret; } +static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] = src->bytes[i]; + dst->ios[i] = src->ios[i]; + } +} + +static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] += src->bytes[i]; + dst->ios[i] += src->ios[i]; + } +} + +static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] -= src->bytes[i]; + dst->ios[i] -= src->ios[i]; + } +} + +static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct blkcg_gq *blkg; + + rcu_read_lock(); + + hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + struct blkcg_gq *parent = blkg->parent; + struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); + struct blkg_iostat cur, delta; + unsigned seq; + + /* fetch the current per-cpu values */ + do { + seq = u64_stats_fetch_begin(&bisc->sync); + blkg_iostat_set(&cur, &bisc->cur); + } while (u64_stats_fetch_retry(&bisc->sync, seq)); + + /* propagate percpu delta to global */ + u64_stats_update_begin(&blkg->iostat.sync); + blkg_iostat_set(&delta, &cur); + blkg_iostat_sub(&delta, &bisc->last); + blkg_iostat_add(&blkg->iostat.cur, &delta); + blkg_iostat_add(&bisc->last, &delta); + u64_stats_update_end(&blkg->iostat.sync); + + /* propagate global delta to parent */ + if (parent) { + u64_stats_update_begin(&parent->iostat.sync); + blkg_iostat_set(&delta, &blkg->iostat.cur); + blkg_iostat_sub(&delta, &blkg->iostat.last); + blkg_iostat_add(&parent->iostat.cur, &delta); + blkg_iostat_add(&blkg->iostat.last, &delta); + u64_stats_update_end(&parent->iostat.sync); + } + } + + rcu_read_unlock(); +} + static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; @@ -1326,6 +1222,7 @@ struct cgroup_subsys io_cgrp_subsys = { .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .can_attach = blkcg_can_attach, + .css_rstat_flush = blkcg_rstat_flush, .bind = blkcg_bind, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, diff --git a/block/blk-core.c b/block/blk-core.c index d5e668ec751b..a1e228752083 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -132,6 +132,9 @@ static const char *const blk_op_name[] = { REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), + REQ_OP_NAME(ZONE_OPEN), + REQ_OP_NAME(ZONE_CLOSE), + REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(SCSI_IN), @@ -336,14 +339,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying); */ void blk_cleanup_queue(struct request_queue *q) { + WARN_ON_ONCE(blk_queue_registered(q)); + /* mark @q DYING, no new request or merges will be allowed afterwards */ - mutex_lock(&q->sysfs_lock); blk_set_queue_dying(q); blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); blk_queue_flag_set(QUEUE_FLAG_DYING, q); - mutex_unlock(&q->sysfs_lock); /* * Drain all requests queued before DYING marking. Set DEAD flag to @@ -848,11 +851,7 @@ static inline int blk_partition_remap(struct bio *bio) if (unlikely(bio_check_ro(bio, p))) goto out; - /* - * Zone reset does not include bi_size so bio_sectors() is always 0. - * Include a test for the reset op code and perform the remap if needed. - */ - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) { + if (bio_sectors(bio)) { if (bio_check_eod(bio, part_nr_sects_read(p))) goto out; bio->bi_iter.bi_sector += p->start_sect; @@ -936,6 +935,9 @@ generic_make_request_checks(struct bio *bio) goto not_supported; break; case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: if (!blk_queue_is_zoned(q)) goto not_supported; break; diff --git a/block/blk-exec.c b/block/blk-exec.c index 1db44ca0f4a6..e20a852ae432 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -55,6 +55,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, rq->rq_disk = bd_disk; rq->end_io = done; + blk_account_io_start(rq, true); + /* * don't check dying flag for MQ because the request won't * be reused after dying flag is set diff --git a/block/blk-flush.c b/block/blk-flush.c index 1eec9cbe5a0a..1777346baf06 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -136,6 +136,17 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) blk_mq_add_to_requeue_list(rq, add_front, true); } +static void blk_account_io_flush(struct request *rq) +{ + struct hd_struct *part = &rq->rq_disk->part0; + + part_stat_lock(); + part_stat_inc(part, ios[STAT_FLUSH]); + part_stat_add(part, nsecs[STAT_FLUSH], + ktime_get_ns() - rq->start_time_ns); + part_stat_unlock(); +} + /** * blk_flush_complete_seq - complete flush sequence * @rq: PREFLUSH/FUA request being sequenced @@ -185,7 +196,7 @@ static void blk_flush_complete_seq(struct request *rq, case REQ_FSEQ_DONE: /* - * @rq was previously adjusted by blk_flush_issue() for + * @rq was previously adjusted by blk_insert_flush() for * flush sequencing and may already have gone through the * flush data request completion path. Restore @rq for * normal completion and end it. @@ -212,6 +223,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); struct blk_mq_hw_ctx *hctx; + blk_account_io_flush(flush_rq); + /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 2a3db80c1dce..e01267f99183 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1057,9 +1057,12 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) atomic64_set(&iocg->active_period, cur_period); /* already activated or breaking leaf-only constraint? */ - for (i = iocg->level; i > 0; i--) - if (!list_empty(&iocg->active_list)) + if (!list_empty(&iocg->active_list)) + goto succeed_unlock; + for (i = iocg->level - 1; i > 0; i--) + if (!list_empty(&iocg->ancestors[i]->active_list)) goto fail_unlock; + if (iocg->child_active_sum) goto fail_unlock; @@ -1101,6 +1104,7 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) ioc_start_period(ioc, now); } +succeed_unlock: spin_unlock_irq(&ioc->lock); return true; @@ -2110,10 +2114,10 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, goto einval; } - spin_lock_irq(&iocg->ioc->lock); + spin_lock(&iocg->ioc->lock); iocg->cfg_weight = v; weight_updated(iocg); - spin_unlock_irq(&iocg->ioc->lock); + spin_unlock(&iocg->ioc->lock); blkg_conf_finish(&ctx); return nbytes; diff --git a/block/blk-merge.c b/block/blk-merge.c index 48e6725b32ee..d783bdc4559b 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -293,7 +293,7 @@ split: void __blk_queue_split(struct request_queue *q, struct bio **bio, unsigned int *nr_segs) { - struct bio *split; + struct bio *split = NULL; switch (bio_op(*bio)) { case REQ_OP_DISCARD: @@ -309,6 +309,21 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio, nr_segs); break; default: + /* + * All drivers must accept single-segments bios that are <= + * PAGE_SIZE. This is a quick and dirty check that relies on + * the fact that bi_io_vec[0] is always valid if a bio has data. + * The check might lead to occasional false negatives when bios + * are cloned, but compared to the performance impact of cloned + * bios themselves the loop below doesn't matter anyway. + */ + if (!q->limits.chunk_sectors && + (*bio)->bi_vcnt == 1 && + ((*bio)->bi_io_vec[0].bv_len + + (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) { + *nr_segs = 1; + break; + } split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs); break; } diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index a0d3ce30fa08..062229395a50 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -74,10 +74,8 @@ static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr, if (!entry->show) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->show(ctx, page); + res = entry->show(ctx, page); mutex_unlock(&q->sysfs_lock); return res; } @@ -97,10 +95,8 @@ static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr, if (!entry->store) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->store(ctx, page, length); + res = entry->store(ctx, page, length); mutex_unlock(&q->sysfs_lock); return res; } @@ -120,10 +116,8 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj, if (!entry->show) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->show(hctx, page); + res = entry->show(hctx, page); mutex_unlock(&q->sysfs_lock); return res; } @@ -144,10 +138,8 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj, if (!entry->store) return -EIO; - res = -ENOENT; mutex_lock(&q->sysfs_lock); - if (!blk_queue_dying(q)) - res = entry->store(hctx, page, length); + res = entry->store(hctx, page, length); mutex_unlock(&q->sysfs_lock); return res; } @@ -166,20 +158,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx, static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) { + const size_t size = PAGE_SIZE - 1; unsigned int i, first = 1; - ssize_t ret = 0; + int ret = 0, pos = 0; for_each_cpu(i, hctx->cpumask) { if (first) - ret += sprintf(ret + page, "%u", i); + ret = snprintf(pos + page, size - pos, "%u", i); else - ret += sprintf(ret + page, ", %u", i); + ret = snprintf(pos + page, size - pos, ", %u", i); + + if (ret >= size - pos) + break; first = 0; + pos += ret; } - ret += sprintf(ret + page, "\n"); - return ret; + ret = snprintf(pos + page, size + 1 - pos, "\n"); + return pos + ret; } static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = { diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 008388e82b5c..fbacde454718 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -15,14 +15,6 @@ #include "blk-mq.h" #include "blk-mq-tag.h" -bool blk_mq_has_free_tags(struct blk_mq_tags *tags) -{ - if (!tags) - return true; - - return sbitmap_any_bit_clear(&tags->bitmap_tags.sb); -} - /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 61deab0b5a5a..15bc74acb57e 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -28,7 +28,6 @@ extern void blk_mq_free_tags(struct blk_mq_tags *tags); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); -extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); diff --git a/block/blk-mq.c b/block/blk-mq.c index ec791156e9cc..323c9cb28066 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -93,7 +93,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct mq_inflight { struct hd_struct *part; - unsigned int *inflight; + unsigned int inflight[2]; }; static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, @@ -102,45 +102,29 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, { struct mq_inflight *mi = priv; - /* - * index[0] counts the specific partition that was asked for. - */ if (rq->part == mi->part) - mi->inflight[0]++; + mi->inflight[rq_data_dir(rq)]++; return true; } unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) { - unsigned inflight[2]; - struct mq_inflight mi = { .part = part, .inflight = inflight, }; + struct mq_inflight mi = { .part = part }; - inflight[0] = inflight[1] = 0; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); - return inflight[0]; -} - -static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx, - struct request *rq, void *priv, - bool reserved) -{ - struct mq_inflight *mi = priv; - - if (rq->part == mi->part) - mi->inflight[rq_data_dir(rq)]++; - - return true; + return mi.inflight[0] + mi.inflight[1]; } void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]) { - struct mq_inflight mi = { .part = part, .inflight = inflight, }; + struct mq_inflight mi = { .part = part }; - inflight[0] = inflight[1] = 0; - blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi); + blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); + inflight[0] = mi.inflight[0]; + inflight[1] = mi.inflight[1]; } void blk_freeze_queue_start(struct request_queue *q) @@ -276,12 +260,6 @@ void blk_mq_wake_waiters(struct request_queue *q) blk_mq_tag_wakeup_all(hctx->tags, true); } -bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) -{ - return blk_mq_has_free_tags(hctx->tags); -} -EXPORT_SYMBOL(blk_mq_can_queue); - /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. @@ -663,18 +641,6 @@ bool blk_mq_complete_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_complete_request); -int blk_mq_request_started(struct request *rq) -{ - return blk_mq_rq_state(rq) != MQ_RQ_IDLE; -} -EXPORT_SYMBOL_GPL(blk_mq_request_started); - -int blk_mq_request_completed(struct request *rq) -{ - return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; -} -EXPORT_SYMBOL_GPL(blk_mq_request_completed); - void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; @@ -1064,7 +1030,7 @@ bool blk_mq_get_driver_tag(struct request *rq) bool shared; if (rq->tag != -1) - goto done; + return true; if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag)) data.flags |= BLK_MQ_REQ_RESERVED; @@ -1079,7 +1045,6 @@ bool blk_mq_get_driver_tag(struct request *rq) data.hctx->tags->rqs[rq->tag] = rq; } -done: return rq->tag != -1; } @@ -1486,7 +1451,7 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); -bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { int srcu_idx; bool need_run; @@ -1504,12 +1469,8 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) blk_mq_hctx_has_pending(hctx); hctx_unlock(hctx, srcu_idx); - if (need_run) { + if (need_run) __blk_mq_delay_run_hw_queue(hctx, async, 0); - return true; - } - - return false; } EXPORT_SYMBOL(blk_mq_run_hw_queue); @@ -2789,6 +2750,23 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, int i, j, end; struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx; + if (q->nr_hw_queues < set->nr_hw_queues) { + struct blk_mq_hw_ctx **new_hctxs; + + new_hctxs = kcalloc_node(set->nr_hw_queues, + sizeof(*new_hctxs), GFP_KERNEL, + set->numa_node); + if (!new_hctxs) + return; + if (hctxs) + memcpy(new_hctxs, hctxs, q->nr_hw_queues * + sizeof(*hctxs)); + q->queue_hw_ctx = new_hctxs; + q->nr_hw_queues = set->nr_hw_queues; + kfree(hctxs); + hctxs = new_hctxs; + } + /* protect against switching io scheduler */ mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { @@ -2844,19 +2822,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, mutex_unlock(&q->sysfs_lock); } -/* - * Maximum number of hardware queues we support. For single sets, we'll never - * have more than the CPUs (software queues). For multiple sets, the tag_set - * user may have set ->nr_hw_queues larger. - */ -static unsigned int nr_hw_queues(struct blk_mq_tag_set *set) -{ - if (set->nr_maps == 1) - return nr_cpu_ids; - - return max(set->nr_hw_queues, nr_cpu_ids); -} - struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q, bool elevator_init) @@ -2876,12 +2841,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); - q->nr_queues = nr_hw_queues(set); - q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)), - GFP_KERNEL, set->numa_node); - if (!q->queue_hw_ctx) - goto err_sys_init; - INIT_LIST_HEAD(&q->unused_hctx_list); spin_lock_init(&q->unused_hctx_lock); @@ -2929,7 +2888,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, err_hctxs: kfree(q->queue_hw_ctx); q->nr_hw_queues = 0; -err_sys_init: blk_mq_sysfs_deinit(q); err_poll: blk_stat_free_callback(q->poll_cb); @@ -3030,6 +2988,29 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) } } +static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set, + int cur_nr_hw_queues, int new_nr_hw_queues) +{ + struct blk_mq_tags **new_tags; + + if (cur_nr_hw_queues >= new_nr_hw_queues) + return 0; + + new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *), + GFP_KERNEL, set->numa_node); + if (!new_tags) + return -ENOMEM; + + if (set->tags) + memcpy(new_tags, set->tags, cur_nr_hw_queues * + sizeof(*set->tags)); + kfree(set->tags); + set->tags = new_tags; + set->nr_hw_queues = new_nr_hw_queues; + + return 0; +} + /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the @@ -3083,9 +3064,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; - set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *), - GFP_KERNEL, set->numa_node); - if (!set->tags) + if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0) return -ENOMEM; ret = -ENOMEM; @@ -3126,7 +3105,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; - for (i = 0; i < nr_hw_queues(set); i++) + for (i = 0; i < set->nr_hw_queues; i++) blk_mq_free_map_and_requests(set, i); for (j = 0; j < set->nr_maps; j++) { @@ -3271,10 +3250,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); /* - * Sync with blk_mq_queue_tag_busy_iter. - */ - synchronize_rcu(); - /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done * updating the new sw to hw queue mappings. @@ -3288,6 +3263,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_sysfs_unregister(q); } + if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) < + 0) + goto reregister; + prev_nr_hw_queues = set->nr_hw_queues; set->nr_hw_queues = nr_hw_queues; blk_mq_update_queue_map(set); @@ -3304,6 +3283,7 @@ fallback: blk_mq_map_swqueue(q); } +reregister: list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register(q); blk_mq_debugfs_register_hctxs(q); diff --git a/block/blk-mq.h b/block/blk-mq.h index 32c62c64e6c2..eaaca8fc1c28 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -128,15 +128,6 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_release(struct request_queue *q); -/** - * blk_mq_rq_state() - read the current MQ_RQ_* state of a request - * @rq: target request. - */ -static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) -{ - return READ_ONCE(rq->state); -} - static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 457d9ba3eb20..6e7ec87d49fa 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -42,17 +42,13 @@ static __latent_entropy void blk_done_softirq(struct softirq_action *h) static void trigger_softirq(void *data) { struct request *rq = data; - unsigned long flags; struct list_head *list; - local_irq_save(flags); list = this_cpu_ptr(&blk_cpu_done); list_add_tail(&rq->ipi_list, list); if (list->next == &rq->ipi_list) raise_softirq_irqoff(BLOCK_SOFTIRQ); - - local_irq_restore(flags); } /* diff --git a/block/blk-stat.c b/block/blk-stat.c index 940f15d600f8..7da302ff88d0 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -53,7 +53,7 @@ void blk_stat_add(struct request *rq, u64 now) struct request_queue *q = rq->q; struct blk_stat_callback *cb; struct blk_rq_stat *stat; - int bucket; + int bucket, cpu; u64 value; value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; @@ -61,6 +61,7 @@ void blk_stat_add(struct request *rq, u64 now) blk_throtl_stat_add(rq, value); rcu_read_lock(); + cpu = get_cpu(); list_for_each_entry_rcu(cb, &q->stats->callbacks, list) { if (!blk_stat_is_active(cb)) continue; @@ -69,10 +70,10 @@ void blk_stat_add(struct request *rq, u64 now) if (bucket < 0) continue; - stat = &get_cpu_ptr(cb->cpu_stat)[bucket]; + stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket]; blk_rq_stat_add(stat, value); - put_cpu_ptr(cb->cpu_stat); } + put_cpu(); rcu_read_unlock(); } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 46f5198be017..fca9b158f4a0 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -801,10 +801,6 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page) if (!entry->show) return -EIO; mutex_lock(&q->sysfs_lock); - if (blk_queue_dying(q)) { - mutex_unlock(&q->sysfs_lock); - return -ENOENT; - } res = entry->show(q, page); mutex_unlock(&q->sysfs_lock); return res; @@ -823,10 +819,6 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, q = container_of(kobj, struct request_queue, kobj); mutex_lock(&q->sysfs_lock); - if (blk_queue_dying(q)) { - mutex_unlock(&q->sysfs_lock); - return -ENOENT; - } res = entry->store(q, page, length); mutex_unlock(&q->sysfs_lock); return res; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 18f773e52dfb..98233c9c65a8 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -12,6 +12,7 @@ #include <linux/blktrace_api.h> #include <linux/blk-cgroup.h> #include "blk.h" +#include "blk-cgroup-rwstat.h" /* Max dispatch from a group in 1 round */ static int throtl_grp_quantum = 8; @@ -176,6 +177,9 @@ struct throtl_grp { unsigned int bio_cnt; /* total bios */ unsigned int bad_bio_cnt; /* bios exceeding latency threshold */ unsigned long bio_cnt_reset_time; + + struct blkg_rwstat stat_bytes; + struct blkg_rwstat stat_ios; }; /* We measure latency for request size from <= 4k to >= 1M */ @@ -489,6 +493,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, if (!tg) return NULL; + if (blkg_rwstat_init(&tg->stat_bytes, gfp)) + goto err_free_tg; + + if (blkg_rwstat_init(&tg->stat_ios, gfp)) + goto err_exit_stat_bytes; + throtl_service_queue_init(&tg->service_queue); for (rw = READ; rw <= WRITE; rw++) { @@ -513,6 +523,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD; return &tg->pd; + +err_exit_stat_bytes: + blkg_rwstat_exit(&tg->stat_bytes); +err_free_tg: + kfree(tg); + return NULL; } static void throtl_pd_init(struct blkg_policy_data *pd) @@ -611,6 +627,8 @@ static void throtl_pd_free(struct blkg_policy_data *pd) struct throtl_grp *tg = pd_to_tg(pd); del_timer_sync(&tg->service_queue.pending_timer); + blkg_rwstat_exit(&tg->stat_bytes); + blkg_rwstat_exit(&tg->stat_ios); kfree(tg); } @@ -1464,6 +1482,32 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of, return tg_set_conf(of, buf, nbytes, off, false); } +static int tg_print_rwstat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + blkg_prfill_rwstat, &blkcg_policy_throtl, + seq_cft(sf)->private, true); + return 0; +} + +static u64 tg_prfill_rwstat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct blkg_rwstat_sample sum; + + blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_throtl, off, + &sum); + return __blkg_prfill_rwstat(sf, pd, &sum); +} + +static int tg_print_rwstat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + tg_prfill_rwstat_recursive, &blkcg_policy_throtl, + seq_cft(sf)->private, true); + return 0; +} + static struct cftype throtl_legacy_files[] = { { .name = "throttle.read_bps_device", @@ -1491,23 +1535,23 @@ static struct cftype throtl_legacy_files[] = { }, { .name = "throttle.io_service_bytes", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_bytes, + .private = offsetof(struct throtl_grp, stat_bytes), + .seq_show = tg_print_rwstat, }, { .name = "throttle.io_service_bytes_recursive", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_bytes_recursive, + .private = offsetof(struct throtl_grp, stat_bytes), + .seq_show = tg_print_rwstat_recursive, }, { .name = "throttle.io_serviced", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_ios, + .private = offsetof(struct throtl_grp, stat_ios), + .seq_show = tg_print_rwstat, }, { .name = "throttle.io_serviced_recursive", - .private = (unsigned long)&blkcg_policy_throtl, - .seq_show = blkg_print_stat_ios_recursive, + .private = offsetof(struct throtl_grp, stat_ios), + .seq_show = tg_print_rwstat_recursive, }, { } /* terminate */ }; @@ -2127,7 +2171,16 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, WARN_ON_ONCE(!rcu_read_lock_held()); /* see throtl_charge_bio() */ - if (bio_flagged(bio, BIO_THROTTLED) || !tg->has_rules[rw]) + if (bio_flagged(bio, BIO_THROTTLED)) + goto out; + + if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) { + blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf, + bio->bi_iter.bi_size); + blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1); + } + + if (!tg->has_rules[rw]) goto out; spin_lock_irq(&q->queue_lock); diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 4bc5f260248a..6fad6f3f6980 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -93,172 +93,85 @@ unsigned int blkdev_nr_zones(struct block_device *bdev) if (!blk_queue_is_zoned(q)) return 0; - return __blkdev_nr_zones(q, bdev->bd_part->nr_sects); + return __blkdev_nr_zones(q, get_capacity(bdev->bd_disk)); } EXPORT_SYMBOL_GPL(blkdev_nr_zones); -/* - * Check that a zone report belongs to this partition, and if yes, fix its start - * sector and write pointer and return true. Return false otherwise. - */ -static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep) -{ - sector_t offset = get_start_sect(bdev); - - if (rep->start < offset) - return false; - - rep->start -= offset; - if (rep->start + rep->len > bdev->bd_part->nr_sects) - return false; - - if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL) - rep->wp = rep->start + rep->len; - else - rep->wp -= offset; - return true; -} - -static int blk_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) -{ - struct request_queue *q = disk->queue; - unsigned int z = 0, n, nrz = *nr_zones; - sector_t capacity = get_capacity(disk); - int ret; - - while (z < nrz && sector < capacity) { - n = nrz - z; - ret = disk->fops->report_zones(disk, sector, &zones[z], &n); - if (ret) - return ret; - if (!n) - break; - sector += blk_queue_zone_sectors(q) * n; - z += n; - } - - WARN_ON(z > *nr_zones); - *nr_zones = z; - - return 0; -} - /** * blkdev_report_zones - Get zones information * @bdev: Target block device * @sector: Sector from which to report zones - * @zones: Array of zone structures where to return the zones information - * @nr_zones: Number of zone structures in the zone array + * @nr_zones: Maximum number of zones to report + * @cb: Callback function called for each reported zone + * @data: Private data for the callback * * Description: - * Get zone information starting from the zone containing @sector. - * The number of zone information reported may be less than the number - * requested by @nr_zones. The number of zones actually reported is - * returned in @nr_zones. - * The caller must use memalloc_noXX_save/restore() calls to control - * memory allocations done within this function (zone array and command - * buffer allocation by the device driver). + * Get zone information starting from the zone containing @sector for at most + * @nr_zones, and call @cb for each zone reported by the device. + * To report all zones in a device starting from @sector, the BLK_ALL_ZONES + * constant can be passed to @nr_zones. + * Returns the number of zones reported by the device, or a negative errno + * value in case of failure. + * + * Note: The caller must use memalloc_noXX_save/restore() calls to control + * memory allocations done within this function. */ int blkdev_report_zones(struct block_device *bdev, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { - struct request_queue *q = bdev_get_queue(bdev); - unsigned int i, nrz; - int ret; - - if (!blk_queue_is_zoned(q)) - return -EOPNOTSUPP; + struct gendisk *disk = bdev->bd_disk; + sector_t capacity = get_capacity(disk); - /* - * A block device that advertized itself as zoned must have a - * report_zones method. If it does not have one defined, the device - * driver has a bug. So warn about that. - */ - if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones)) + if (!blk_queue_is_zoned(bdev_get_queue(bdev)) || + WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; - if (!*nr_zones || sector >= bdev->bd_part->nr_sects) { - *nr_zones = 0; + if (!nr_zones || sector >= capacity) return 0; - } - - nrz = min(*nr_zones, - __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector)); - ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector, - zones, &nrz); - if (ret) - return ret; - - for (i = 0; i < nrz; i++) { - if (!blkdev_report_zone(bdev, zones)) - break; - zones++; - } - *nr_zones = i; - - return 0; + return disk->fops->report_zones(disk, sector, nr_zones, cb, data); } EXPORT_SYMBOL_GPL(blkdev_report_zones); -/* - * Special case of zone reset operation to reset all zones in one command, - * useful for applications like mkfs. - */ -static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask) -{ - struct bio *bio = bio_alloc(gfp_mask, 0); - int ret; - - /* across the zones operations, don't need any sectors */ - bio_set_dev(bio, bdev); - bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0); - - ret = submit_bio_wait(bio); - bio_put(bio); - - return ret; -} - static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev, + sector_t sector, sector_t nr_sectors) { if (!blk_queue_zone_resetall(bdev_get_queue(bdev))) return false; - if (nr_sectors != part_nr_sects_read(bdev->bd_part)) - return false; /* - * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is - * the entire disk, that is, if the blocks device start offset is 0 and - * its capacity is the same as the entire disk. + * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors + * of the applicable zone range is the entire disk. */ - return get_start_sect(bdev) == 0 && - part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk); + return !sector && nr_sectors == get_capacity(bdev->bd_disk); } /** - * blkdev_reset_zones - Reset zones write pointer + * blkdev_zone_mgmt - Execute a zone management operation on a range of zones * @bdev: Target block device - * @sector: Start sector of the first zone to reset - * @nr_sectors: Number of sectors, at least the length of one zone + * @op: Operation to be performed on the zones + * @sector: Start sector of the first zone to operate on + * @nr_sectors: Number of sectors, should be at least the length of one zone and + * must be zone size aligned. * @gfp_mask: Memory allocation flags (for bio_alloc) * * Description: - * Reset the write pointer of the zones contained in the range + * Perform the specified operation on the range of zones specified by * @sector..@sector+@nr_sectors. Specifying the entire disk sector range * is valid, but the specified range should not contain conventional zones. + * The operation to execute on each zone can be a zone reset, open, close + * or finish request. */ -int blkdev_reset_zones(struct block_device *bdev, - sector_t sector, sector_t nr_sectors, - gfp_t gfp_mask) +int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, + sector_t sector, sector_t nr_sectors, + gfp_t gfp_mask) { struct request_queue *q = bdev_get_queue(bdev); - sector_t zone_sectors; + sector_t zone_sectors = blk_queue_zone_sectors(q); + sector_t capacity = get_capacity(bdev->bd_disk); sector_t end_sector = sector + nr_sectors; struct bio *bio = NULL; - struct blk_plug plug; int ret; if (!blk_queue_is_zoned(q)) @@ -267,45 +180,62 @@ int blkdev_reset_zones(struct block_device *bdev, if (bdev_read_only(bdev)) return -EPERM; - if (!nr_sectors || end_sector > bdev->bd_part->nr_sects) + if (!op_is_zone_mgmt(op)) + return -EOPNOTSUPP; + + if (!nr_sectors || end_sector > capacity) /* Out of range */ return -EINVAL; - if (blkdev_allow_reset_all_zones(bdev, nr_sectors)) - return __blkdev_reset_all_zones(bdev, gfp_mask); - /* Check alignment (handle eventual smaller last zone) */ - zone_sectors = blk_queue_zone_sectors(q); if (sector & (zone_sectors - 1)) return -EINVAL; - if ((nr_sectors & (zone_sectors - 1)) && - end_sector != bdev->bd_part->nr_sects) + if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity) return -EINVAL; - blk_start_plug(&plug); while (sector < end_sector) { - bio = blk_next_bio(bio, 0, gfp_mask); - bio->bi_iter.bi_sector = sector; bio_set_dev(bio, bdev); - bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0); + /* + * Special case for the zone reset operation that reset all + * zones, this is useful for applications like mkfs. + */ + if (op == REQ_OP_ZONE_RESET && + blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) { + bio->bi_opf = REQ_OP_ZONE_RESET_ALL; + break; + } + + bio->bi_opf = op; + bio->bi_iter.bi_sector = sector; sector += zone_sectors; /* This may take a while, so be nice to others */ cond_resched(); - } ret = submit_bio_wait(bio); bio_put(bio); - blk_finish_plug(&plug); - return ret; } -EXPORT_SYMBOL_GPL(blkdev_reset_zones); +EXPORT_SYMBOL_GPL(blkdev_zone_mgmt); + +struct zone_report_args { + struct blk_zone __user *zones; +}; + +static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct zone_report_args *args = data; + + if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone))) + return -EFAULT; + return 0; +} /* * BLKREPORTZONE ioctl processing. @@ -315,9 +245,9 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; + struct zone_report_args args; struct request_queue *q; struct blk_zone_report rep; - struct blk_zone *zones; int ret; if (!argp) @@ -339,44 +269,29 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, if (!rep.nr_zones) return -EINVAL; - rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones); - - zones = kvmalloc_array(rep.nr_zones, sizeof(struct blk_zone), - GFP_KERNEL | __GFP_ZERO); - if (!zones) - return -ENOMEM; - - ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones); - if (ret) - goto out; - - if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) { - ret = -EFAULT; - goto out; - } - - if (rep.nr_zones) { - if (copy_to_user(argp + sizeof(struct blk_zone_report), zones, - sizeof(struct blk_zone) * rep.nr_zones)) - ret = -EFAULT; - } - - out: - kvfree(zones); + args.zones = argp + sizeof(struct blk_zone_report); + ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones, + blkdev_copy_zone_to_user, &args); + if (ret < 0) + return ret; - return ret; + rep.nr_zones = ret; + if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) + return -EFAULT; + return 0; } /* - * BLKRESETZONE ioctl processing. + * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. */ -int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct request_queue *q; struct blk_zone_range zrange; + enum req_opf op; if (!argp) return -EINVAL; @@ -397,8 +312,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) return -EFAULT; - return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors, - GFP_KERNEL); + switch (cmd) { + case BLKRESETZONE: + op = REQ_OP_ZONE_RESET; + break; + case BLKOPENZONE: + op = REQ_OP_ZONE_OPEN; + break; + case BLKCLOSEZONE: + op = REQ_OP_ZONE_CLOSE; + break; + case BLKFINISHZONE: + op = REQ_OP_ZONE_FINISH; + break; + default: + return -ENOTTY; + } + + return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors, + GFP_KERNEL); } static inline unsigned long *blk_alloc_zone_bitmap(int node, @@ -408,37 +340,99 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node, GFP_NOIO, node); } +void blk_queue_free_zone_bitmaps(struct request_queue *q) +{ + kfree(q->seq_zones_bitmap); + q->seq_zones_bitmap = NULL; + kfree(q->seq_zones_wlock); + q->seq_zones_wlock = NULL; +} + +struct blk_revalidate_zone_args { + struct gendisk *disk; + unsigned long *seq_zones_bitmap; + unsigned long *seq_zones_wlock; + sector_t sector; +}; + /* - * Allocate an array of struct blk_zone to get nr_zones zone information. - * The allocated array may be smaller than nr_zones. + * Helper function to check the validity of zones of a zoned block device. */ -static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones) +static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, + void *data) { - struct blk_zone *zones; - size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES); + struct blk_revalidate_zone_args *args = data; + struct gendisk *disk = args->disk; + struct request_queue *q = disk->queue; + sector_t zone_sectors = blk_queue_zone_sectors(q); + sector_t capacity = get_capacity(disk); /* - * GFP_KERNEL here is meaningless as the caller task context has - * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones() - * with memalloc_noio_save(). + * All zones must have the same size, with the exception on an eventual + * smaller last zone. */ - zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL); - if (!zones) { - *nr_zones = 0; - return NULL; + if (zone->start + zone_sectors < capacity && + zone->len != zone_sectors) { + pr_warn("%s: Invalid zoned device with non constant zone size\n", + disk->disk_name); + return false; } - *nr_zones = nrz; + if (zone->start + zone->len >= capacity && + zone->len > zone_sectors) { + pr_warn("%s: Invalid zoned device with larger last zone size\n", + disk->disk_name); + return -ENODEV; + } + + /* Check for holes in the zone report */ + if (zone->start != args->sector) { + pr_warn("%s: Zone gap at sectors %llu..%llu\n", + disk->disk_name, args->sector, zone->start); + return -ENODEV; + } - return zones; + /* Check zone type */ + switch (zone->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: + break; + default: + pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n", + disk->disk_name, (int)zone->type, zone->start); + return -ENODEV; + } + + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, args->seq_zones_bitmap); + + args->sector += zone->len; + return 0; } -void blk_queue_free_zone_bitmaps(struct request_queue *q) +static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones, + struct blk_revalidate_zone_args *args) { - kfree(q->seq_zones_bitmap); - q->seq_zones_bitmap = NULL; - kfree(q->seq_zones_wlock); - q->seq_zones_wlock = NULL; + /* + * Ensure that all memory allocations in this context are done as + * if GFP_NOIO was specified. + */ + unsigned int noio_flag = memalloc_noio_save(); + struct request_queue *q = disk->queue; + int ret; + + args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->seq_zones_wlock) + return -ENOMEM; + args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->seq_zones_bitmap) + return -ENOMEM; + + ret = disk->fops->report_zones(disk, 0, nr_zones, + blk_revalidate_zone_cb, args); + memalloc_noio_restore(noio_flag); + return ret; } /** @@ -454,13 +448,12 @@ int blk_revalidate_disk_zones(struct gendisk *disk) { struct request_queue *q = disk->queue; unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk)); - unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; - unsigned int i, rep_nr_zones = 0, z = 0, nrz; - struct blk_zone *zones = NULL; - unsigned int noio_flag; - sector_t sector = 0; + struct blk_revalidate_zone_args args = { .disk = disk }; int ret = 0; + if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) + return -EIO; + /* * BIO based queues do not use a scheduler so only q->nr_zones * needs to be updated so that the sysfs exposed value is correct. @@ -470,78 +463,28 @@ int blk_revalidate_disk_zones(struct gendisk *disk) return 0; } - /* - * Ensure that all memory allocations in this context are done as - * if GFP_NOIO was specified. - */ - noio_flag = memalloc_noio_save(); - - if (!blk_queue_is_zoned(q) || !nr_zones) { - nr_zones = 0; - goto update; - } - - /* Allocate bitmaps */ - ret = -ENOMEM; - seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!seq_zones_wlock) - goto out; - seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!seq_zones_bitmap) - goto out; - - /* Get zone information and initialize seq_zones_bitmap */ - rep_nr_zones = nr_zones; - zones = blk_alloc_zones(&rep_nr_zones); - if (!zones) - goto out; - - while (z < nr_zones) { - nrz = min(nr_zones - z, rep_nr_zones); - ret = blk_report_zones(disk, sector, zones, &nrz); - if (ret) - goto out; - if (!nrz) - break; - for (i = 0; i < nrz; i++) { - if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(z, seq_zones_bitmap); - z++; - } - sector += nrz * blk_queue_zone_sectors(q); - } - - if (WARN_ON(z != nr_zones)) { - ret = -EIO; - goto out; - } + if (nr_zones) + ret = blk_update_zone_info(disk, nr_zones, &args); -update: /* * Install the new bitmaps, making sure the queue is stopped and * all I/Os are completed (i.e. a scheduler is not referencing the * bitmaps). */ blk_mq_freeze_queue(q); - q->nr_zones = nr_zones; - swap(q->seq_zones_wlock, seq_zones_wlock); - swap(q->seq_zones_bitmap, seq_zones_bitmap); - blk_mq_unfreeze_queue(q); - -out: - memalloc_noio_restore(noio_flag); - - kvfree(zones); - kfree(seq_zones_wlock); - kfree(seq_zones_bitmap); - - if (ret) { + if (ret >= 0) { + q->nr_zones = nr_zones; + swap(q->seq_zones_wlock, args.seq_zones_wlock); + swap(q->seq_zones_bitmap, args.seq_zones_bitmap); + ret = 0; + } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); - blk_mq_freeze_queue(q); blk_queue_free_zone_bitmaps(q); - blk_mq_unfreeze_queue(q); } + blk_mq_unfreeze_queue(q); + kfree(args.seq_zones_wlock); + kfree(args.seq_zones_bitmap); return ret; } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); diff --git a/block/blk.h b/block/blk.h index 47fba9362e60..2bea40180b6f 100644 --- a/block/blk.h +++ b/block/blk.h @@ -242,14 +242,11 @@ int blk_dev_init(void); * Contribute to IO statistics IFF: * * a) it's attached to a gendisk, and - * b) the queue had IO stats enabled when this request was started, and - * c) it's a file system request + * b) the queue had IO stats enabled when this request was started */ static inline bool blk_do_io_stat(struct request *rq) { - return rq->rq_disk && - (rq->rq_flags & RQF_IO_STAT) && - !blk_rq_is_passthrough(rq); + return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT); } static inline void req_set_nomerge(struct request_queue *q, struct request *req) diff --git a/block/elevator.c b/block/elevator.c index 076ba7308e65..4eab3d70e880 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -832,3 +832,12 @@ struct request *elv_rb_latter_request(struct request_queue *q, return NULL; } EXPORT_SYMBOL(elv_rb_latter_request); + +static int __init elevator_setup(char *str) +{ + pr_warn("Kernel parameter elevator= does not have any effect anymore.\n" + "Please use sysfs to set IO scheduler for individual devices.\n"); + return 1; +} + +__setup("elevator=", elevator_setup); diff --git a/block/genhd.c b/block/genhd.c index 26b31fcae217..ff6268970ddc 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1385,7 +1385,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) "%lu %lu %lu %u " "%lu %lu %lu %u " "%u %u %u " - "%lu %lu %lu %u\n", + "%lu %lu %lu %u " + "%lu %u" + "\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), part_stat_read(hd, ios[STAT_READ]), @@ -1402,7 +1404,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, ios[STAT_DISCARD]), part_stat_read(hd, merges[STAT_DISCARD]), part_stat_read(hd, sectors[STAT_DISCARD]), - (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD) + (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD), + part_stat_read(hd, ios[STAT_FLUSH]), + (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH) ); } disk_part_iter_exit(&piter); diff --git a/block/ioctl.c b/block/ioctl.c index 15a0eb80ada9..7ac8a66c9787 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -155,48 +155,21 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user } } -/* - * This is an exported API for the block driver, and will not - * acquire bd_mutex. This API should be used in case that - * caller has held bd_mutex already. - */ -int __blkdev_reread_part(struct block_device *bdev) +static int blkdev_reread_part(struct block_device *bdev) { - struct gendisk *disk = bdev->bd_disk; + int ret; - if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains) + if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - lockdep_assert_held(&bdev->bd_mutex); - - return rescan_partitions(disk, bdev); -} -EXPORT_SYMBOL(__blkdev_reread_part); - -/* - * This is an exported API for the block driver, and will - * try to acquire bd_mutex. If bd_mutex has been held already - * in current context, please call __blkdev_reread_part(). - * - * Make sure the held locks in current context aren't required - * in open()/close() handler and I/O path for avoiding ABBA deadlock: - * - bd_mutex is held before calling block driver's open/close - * handler - * - reading partition table may submit I/O to the block device - */ -int blkdev_reread_part(struct block_device *bdev) -{ - int res; - mutex_lock(&bdev->bd_mutex); - res = __blkdev_reread_part(bdev); + ret = bdev_disk_changed(bdev, false); mutex_unlock(&bdev->bd_mutex); - return res; + return ret; } -EXPORT_SYMBOL(blkdev_reread_part); static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, unsigned long arg, unsigned long flags) @@ -532,7 +505,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKREPORTZONE: return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); case BLKRESETZONE: - return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg); + case BLKOPENZONE: + case BLKCLOSEZONE: + case BLKFINISHZONE: + return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg); case BLKGETZONESZ: return put_uint(arg, bdev_zone_sectors(bdev)); case BLKGETNRZONES: diff --git a/block/opal_proto.h b/block/opal_proto.h index 5532412d567c..325cbba2465f 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -76,7 +76,6 @@ enum opal_response_token { * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00 * Section: 6.3 Assigned UIDs */ -#define OPAL_UID_LENGTH 8 #define OPAL_METHOD_LENGTH 8 #define OPAL_MSID_KEYLEN 15 #define OPAL_UID_LENGTH_HALF 4 @@ -108,6 +107,7 @@ enum opal_uid { OPAL_C_PIN_TABLE, OPAL_LOCKING_INFO_TABLE, OPAL_ENTERPRISE_LOCKING_INFO_TABLE, + OPAL_DATASTORE, /* C_PIN_TABLE object ID's */ OPAL_C_PIN_MSID, OPAL_C_PIN_SID, @@ -205,6 +205,10 @@ enum opal_lockingstate { OPAL_LOCKING_LOCKED = 0x03, }; +enum opal_parameter { + OPAL_SUM_SET_LIST = 0x060000, +}; + /* Packets derived from: * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00 * Secion: 3.2.3 ComPackets, Packets & Subpackets diff --git a/block/partition-generic.c b/block/partition-generic.c index aee643ce13d1..1d20c9cf213f 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -127,7 +127,8 @@ ssize_t part_stat_show(struct device *dev, "%8lu %8lu %8llu %8u " "%8lu %8lu %8llu %8u " "%8u %8u %8u " - "%8lu %8lu %8llu %8u" + "%8lu %8lu %8llu %8u " + "%8lu %8u" "\n", part_stat_read(p, ios[STAT_READ]), part_stat_read(p, merges[STAT_READ]), @@ -143,7 +144,9 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, ios[STAT_DISCARD]), part_stat_read(p, merges[STAT_DISCARD]), (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]), - (unsigned int)part_stat_read_msecs(p, STAT_DISCARD)); + (unsigned int)part_stat_read_msecs(p, STAT_DISCARD), + part_stat_read(p, ios[STAT_FLUSH]), + (unsigned int)part_stat_read_msecs(p, STAT_FLUSH)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, @@ -439,12 +442,14 @@ static bool disk_unlock_native_capacity(struct gendisk *disk) } } -static int drop_partitions(struct gendisk *disk, struct block_device *bdev) +int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev) { struct disk_part_iter piter; struct hd_struct *part; int res; + if (!disk_part_scan_enabled(disk)) + return 0; if (bdev->bd_part_count || bdev->bd_super) return -EBUSY; res = invalidate_partition(disk, 0); @@ -459,204 +464,124 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev) return 0; } -static bool part_zone_aligned(struct gendisk *disk, - struct block_device *bdev, - sector_t from, sector_t size) +static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, + struct parsed_partitions *state, int p) { - unsigned int zone_sectors = bdev_zone_sectors(bdev); + sector_t size = state->parts[p].size; + sector_t from = state->parts[p].from; + struct hd_struct *part; - /* - * If this function is called, then the disk is a zoned block device - * (host-aware or host-managed). This can be detected even if the - * zoned block device support is disabled (CONFIG_BLK_DEV_ZONED not - * set). In this case, however, only host-aware devices will be seen - * as a block device is not created for host-managed devices. Without - * zoned block device support, host-aware drives can still be used as - * regular block devices (no zone operation) and their zone size will - * be reported as 0. Allow this case. - */ - if (!zone_sectors) + if (!size) return true; - /* - * Check partition start and size alignement. If the drive has a - * smaller last runt zone, ignore it and allow the partition to - * use it. Check the zone size too: it should be a power of 2 number - * of sectors. - */ - if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) { - u32 rem; - - div_u64_rem(from, zone_sectors, &rem); - if (rem) + if (from >= get_capacity(disk)) { + printk(KERN_WARNING + "%s: p%d start %llu is beyond EOD, ", + disk->disk_name, p, (unsigned long long) from); + if (disk_unlock_native_capacity(disk)) return false; - if ((from + size) < get_capacity(disk)) { - div_u64_rem(size, zone_sectors, &rem); - if (rem) - return false; - } + return true; + } - } else { + if (from + size > get_capacity(disk)) { + printk(KERN_WARNING + "%s: p%d size %llu extends beyond EOD, ", + disk->disk_name, p, (unsigned long long) size); - if (from & (zone_sectors - 1)) - return false; - if ((from + size) < get_capacity(disk) && - (size & (zone_sectors - 1))) + if (disk_unlock_native_capacity(disk)) return false; + /* + * We can not ignore partitions of broken tables created by for + * example camera firmware, but we limit them to the end of the + * disk to avoid creating invalid block devices. + */ + size = get_capacity(disk) - from; + } + + part = add_partition(disk, p, from, size, state->parts[p].flags, + &state->parts[p].info); + if (IS_ERR(part)) { + printk(KERN_ERR " %s: p%d could not be added: %ld\n", + disk->disk_name, p, -PTR_ERR(part)); + return true; } +#ifdef CONFIG_BLK_DEV_MD + if (state->parts[p].flags & ADDPART_FLAG_RAID) + md_autodetect_dev(part_to_dev(part)->devt); +#endif return true; } -int rescan_partitions(struct gendisk *disk, struct block_device *bdev) +int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) { - struct parsed_partitions *state = NULL; - struct hd_struct *part; - int p, highest, res; -rescan: - if (state && !IS_ERR(state)) { - free_partitions(state); - state = NULL; - } + struct parsed_partitions *state; + int ret = -EAGAIN, p, highest; - res = drop_partitions(disk, bdev); - if (res) - return res; + if (!disk_part_scan_enabled(disk)) + return 0; - if (disk->fops->revalidate_disk) - disk->fops->revalidate_disk(disk); - check_disk_size_change(disk, bdev, true); - bdev->bd_invalidated = 0; - if (!get_capacity(disk) || !(state = check_partition(disk, bdev))) + state = check_partition(disk, bdev); + if (!state) return 0; if (IS_ERR(state)) { /* - * I/O error reading the partition table. If any - * partition code tried to read beyond EOD, retry - * after unlocking native capacity. + * I/O error reading the partition table. If we tried to read + * beyond EOD, retry after unlocking the native capacity. */ if (PTR_ERR(state) == -ENOSPC) { printk(KERN_WARNING "%s: partition table beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) - goto rescan; + return -EAGAIN; } return -EIO; } + /* - * If any partition code tried to read beyond EOD, try - * unlocking native capacity even if partition table is - * successfully read as we could be missing some partitions. + * Partitions are not supported on zoned block devices. + */ + if (bdev_is_zoned(bdev)) { + pr_warn("%s: ignoring partition table on zoned block device\n", + disk->disk_name); + ret = 0; + goto out_free_state; + } + + /* + * If we read beyond EOD, try unlocking native capacity even if the + * partition table was successfully read as we could be missing some + * partitions. */ if (state->access_beyond_eod) { printk(KERN_WARNING "%s: partition table partially beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) - goto rescan; + goto out_free_state; } /* tell userspace that the media / partition table may have changed */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - /* Detect the highest partition number and preallocate - * disk->part_tbl. This is an optimization and not strictly - * necessary. + /* + * Detect the highest partition number and preallocate disk->part_tbl. + * This is an optimization and not strictly necessary. */ for (p = 1, highest = 0; p < state->limit; p++) if (state->parts[p].size) highest = p; - disk_expand_part_tbl(disk, highest); - /* add partitions */ - for (p = 1; p < state->limit; p++) { - sector_t size, from; - - size = state->parts[p].size; - if (!size) - continue; - - from = state->parts[p].from; - if (from >= get_capacity(disk)) { - printk(KERN_WARNING - "%s: p%d start %llu is beyond EOD, ", - disk->disk_name, p, (unsigned long long) from); - if (disk_unlock_native_capacity(disk)) - goto rescan; - continue; - } - - if (from + size > get_capacity(disk)) { - printk(KERN_WARNING - "%s: p%d size %llu extends beyond EOD, ", - disk->disk_name, p, (unsigned long long) size); - - if (disk_unlock_native_capacity(disk)) { - /* free state and restart */ - goto rescan; - } else { - /* - * we can not ignore partitions of broken tables - * created by for example camera firmware, but - * we limit them to the end of the disk to avoid - * creating invalid block devices - */ - size = get_capacity(disk) - from; - } - } - - /* - * On a zoned block device, partitions should be aligned on the - * device zone size (i.e. zone boundary crossing not allowed). - * Otherwise, resetting the write pointer of the last zone of - * one partition may impact the following partition. - */ - if (bdev_is_zoned(bdev) && - !part_zone_aligned(disk, bdev, from, size)) { - printk(KERN_WARNING - "%s: p%d start %llu+%llu is not zone aligned\n", - disk->disk_name, p, (unsigned long long) from, - (unsigned long long) size); - continue; - } + for (p = 1; p < state->limit; p++) + if (!blk_add_partition(disk, bdev, state, p)) + goto out_free_state; - part = add_partition(disk, p, from, size, - state->parts[p].flags, - &state->parts[p].info); - if (IS_ERR(part)) { - printk(KERN_ERR " %s: p%d could not be added: %ld\n", - disk->disk_name, p, -PTR_ERR(part)); - continue; - } -#ifdef CONFIG_BLK_DEV_MD - if (state->parts[p].flags & ADDPART_FLAG_RAID) - md_autodetect_dev(part_to_dev(part)->devt); -#endif - } + ret = 0; +out_free_state: free_partitions(state); - return 0; -} - -int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) -{ - int res; - - if (!bdev->bd_invalidated) - return 0; - - res = drop_partitions(disk, bdev); - if (res) - return res; - - set_capacity(disk, 0); - check_disk_size_change(disk, bdev, false); - bdev->bd_invalidated = 0; - /* tell userspace that the media / partition table may have changed */ - kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - - return 0; + return ret; } unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) diff --git a/block/sed-opal.c b/block/sed-opal.c index b4c761973ac1..880cc57a5f6b 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -149,6 +149,8 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = { { 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 }, [OPAL_ENTERPRISE_LOCKING_INFO_TABLE] = { 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 }, + [OPAL_DATASTORE] = + { 0x00, 0x00, 0x10, 0x01, 0x00, 0x00, 0x00, 0x00 }, /* C_PIN_TABLE object ID's */ [OPAL_C_PIN_MSID] = @@ -1139,11 +1141,11 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table, * * the result is provided in dev->resp->tok[4] */ -static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table, +static int generic_get_table_info(struct opal_dev *dev, const u8 *table_uid, u64 column) { u8 uid[OPAL_UID_LENGTH]; - const unsigned int half = OPAL_UID_LENGTH/2; + const unsigned int half = OPAL_UID_LENGTH_HALF; /* sed-opal UIDs can be split in two halves: * first: actual table index @@ -1152,7 +1154,7 @@ static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table, * first part of the target table as relative index into that table */ memcpy(uid, opaluid[OPAL_TABLE_TABLE], half); - memcpy(uid+half, opaluid[table], half); + memcpy(uid + half, table_uid, half); return generic_get_column(dev, uid, column); } @@ -1221,6 +1223,75 @@ static int get_active_key(struct opal_dev *dev, void *data) return get_active_key_cont(dev); } +static int generic_table_write_data(struct opal_dev *dev, const u64 data, + u64 offset, u64 size, const u8 *uid) +{ + const u8 __user *src = (u8 __user *)(uintptr_t)data; + u8 *dst; + u64 len; + size_t off = 0; + int err; + + /* do we fit in the available space? */ + err = generic_get_table_info(dev, uid, OPAL_TABLE_ROWS); + if (err) { + pr_debug("Couldn't get the table size\n"); + return err; + } + + len = response_get_u64(&dev->parsed, 4); + if (size > len || offset > len - size) { + pr_debug("Does not fit in the table (%llu vs. %llu)\n", + offset + size, len); + return -ENOSPC; + } + + /* do the actual transmission(s) */ + while (off < size) { + err = cmd_start(dev, uid, opalmethod[OPAL_SET]); + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_WHERE); + add_token_u64(&err, dev, offset + off); + add_token_u8(&err, dev, OPAL_ENDNAME); + + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_VALUES); + + /* + * The bytestring header is either 1 or 2 bytes, so assume 2. + * There also needs to be enough space to accommodate the + * trailing OPAL_ENDNAME (1 byte) and tokens added by + * cmd_finalize. + */ + len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED), + (size_t)(size - off)); + pr_debug("Write bytes %zu+%llu/%llu\n", off, len, size); + + dst = add_bytestring_header(&err, dev, len); + if (!dst) + break; + + if (copy_from_user(dst, src + off, len)) { + err = -EFAULT; + break; + } + + dev->pos += len; + + add_token_u8(&err, dev, OPAL_ENDNAME); + if (err) + break; + + err = finalize_and_send(dev, parse_and_check_status); + if (err) + break; + + off += len; + } + + return err; +} + static int generic_lr_enable_disable(struct opal_dev *dev, u8 *uid, bool rle, bool wle, bool rl, bool wl) @@ -1583,68 +1654,9 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data) static int write_shadow_mbr(struct opal_dev *dev, void *data) { struct opal_shadow_mbr *shadow = data; - const u8 __user *src; - u8 *dst; - size_t off = 0; - u64 len; - int err = 0; - - /* do we fit in the available shadow mbr space? */ - err = generic_get_table_info(dev, OPAL_MBR, OPAL_TABLE_ROWS); - if (err) { - pr_debug("MBR: could not get shadow size\n"); - return err; - } - - len = response_get_u64(&dev->parsed, 4); - if (shadow->size > len || shadow->offset > len - shadow->size) { - pr_debug("MBR: does not fit in shadow (%llu vs. %llu)\n", - shadow->offset + shadow->size, len); - return -ENOSPC; - } - - /* do the actual transmission(s) */ - src = (u8 __user *)(uintptr_t)shadow->data; - while (off < shadow->size) { - err = cmd_start(dev, opaluid[OPAL_MBR], opalmethod[OPAL_SET]); - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, OPAL_WHERE); - add_token_u64(&err, dev, shadow->offset + off); - add_token_u8(&err, dev, OPAL_ENDNAME); - - add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, OPAL_VALUES); - - /* - * The bytestring header is either 1 or 2 bytes, so assume 2. - * There also needs to be enough space to accommodate the - * trailing OPAL_ENDNAME (1 byte) and tokens added by - * cmd_finalize. - */ - len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED), - (size_t)(shadow->size - off)); - pr_debug("MBR: write bytes %zu+%llu/%llu\n", - off, len, shadow->size); - - dst = add_bytestring_header(&err, dev, len); - if (!dst) - break; - if (copy_from_user(dst, src + off, len)) - err = -EFAULT; - dev->pos += len; - - add_token_u8(&err, dev, OPAL_ENDNAME); - if (err) - break; - - err = finalize_and_send(dev, parse_and_check_status); - if (err) - break; - - off += len; - } - return err; + return generic_table_write_data(dev, shadow->data, shadow->offset, + shadow->size, opaluid[OPAL_MBR]); } static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid, @@ -1874,7 +1886,6 @@ static int activate_lsp(struct opal_dev *dev, void *data) { struct opal_lr_act *opal_act = data; u8 user_lr[OPAL_UID_LENGTH]; - u8 uint_3 = 0x83; int err, i; err = cmd_start(dev, opaluid[OPAL_LOCKINGSP_UID], @@ -1887,10 +1898,7 @@ static int activate_lsp(struct opal_dev *dev, void *data) return err; add_token_u8(&err, dev, OPAL_STARTNAME); - add_token_u8(&err, dev, uint_3); - add_token_u8(&err, dev, 6); - add_token_u8(&err, dev, 0); - add_token_u8(&err, dev, 0); + add_token_u64(&err, dev, OPAL_SUM_SET_LIST); add_token_u8(&err, dev, OPAL_STARTLIST); add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH); @@ -1957,6 +1965,113 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data) return 0; } +static int write_table_data(struct opal_dev *dev, void *data) +{ + struct opal_read_write_table *write_tbl = data; + + return generic_table_write_data(dev, write_tbl->data, write_tbl->offset, + write_tbl->size, write_tbl->table_uid); +} + +static int read_table_data_cont(struct opal_dev *dev) +{ + int err; + const char *data_read; + + err = parse_and_check_status(dev); + if (err) + return err; + + dev->prev_d_len = response_get_string(&dev->parsed, 1, &data_read); + dev->prev_data = (void *)data_read; + if (!dev->prev_data) { + pr_debug("%s: Couldn't read data from the table.\n", __func__); + return OPAL_INVAL_PARAM; + } + + return 0; +} + +/* + * IO_BUFFER_LENGTH = 2048 + * sizeof(header) = 56 + * No. of Token Bytes in the Response = 11 + * MAX size of data that can be carried in response buffer + * at a time is : 2048 - (56 + 11) = 1981 = 0x7BD. + */ +#define OPAL_MAX_READ_TABLE (0x7BD) + +static int read_table_data(struct opal_dev *dev, void *data) +{ + struct opal_read_write_table *read_tbl = data; + int err; + size_t off = 0, max_read_size = OPAL_MAX_READ_TABLE; + u64 table_len, len; + u64 offset = read_tbl->offset, read_size = read_tbl->size - 1; + u8 __user *dst; + + err = generic_get_table_info(dev, read_tbl->table_uid, OPAL_TABLE_ROWS); + if (err) { + pr_debug("Couldn't get the table size\n"); + return err; + } + + table_len = response_get_u64(&dev->parsed, 4); + + /* Check if the user is trying to read from the table limits */ + if (read_size > table_len || offset > table_len - read_size) { + pr_debug("Read size exceeds the Table size limits (%llu vs. %llu)\n", + offset + read_size, table_len); + return -EINVAL; + } + + while (off < read_size) { + err = cmd_start(dev, read_tbl->table_uid, opalmethod[OPAL_GET]); + + add_token_u8(&err, dev, OPAL_STARTLIST); + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_STARTROW); + add_token_u64(&err, dev, offset + off); /* start row value */ + add_token_u8(&err, dev, OPAL_ENDNAME); + + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_ENDROW); + + len = min(max_read_size, (size_t)(read_size - off)); + add_token_u64(&err, dev, offset + off + len); /* end row value + */ + add_token_u8(&err, dev, OPAL_ENDNAME); + add_token_u8(&err, dev, OPAL_ENDLIST); + + if (err) { + pr_debug("Error building read table data command.\n"); + break; + } + + err = finalize_and_send(dev, read_table_data_cont); + if (err) + break; + + /* len+1: This includes the NULL terminator at the end*/ + if (dev->prev_d_len > len + 1) { + err = -EOVERFLOW; + break; + } + + dst = (u8 __user *)(uintptr_t)read_tbl->data; + if (copy_to_user(dst + off, dev->prev_data, dev->prev_d_len)) { + pr_debug("Error copying data to userspace\n"); + err = -EFAULT; + break; + } + dev->prev_data = NULL; + + off += len; + } + + return err; +} + static int end_opal_session(struct opal_dev *dev, void *data) { int err = 0; @@ -2443,6 +2558,68 @@ bool opal_unlock_from_suspend(struct opal_dev *dev) } EXPORT_SYMBOL(opal_unlock_from_suspend); +static int opal_read_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + const struct opal_step read_table_steps[] = { + { start_admin1LSP_opal_session, &rw_tbl->key }, + { read_table_data, rw_tbl }, + { end_opal_session, } + }; + int ret = 0; + + if (!rw_tbl->size) + return ret; + + return execute_steps(dev, read_table_steps, + ARRAY_SIZE(read_table_steps)); +} + +static int opal_write_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + const struct opal_step write_table_steps[] = { + { start_admin1LSP_opal_session, &rw_tbl->key }, + { write_table_data, rw_tbl }, + { end_opal_session, } + }; + int ret = 0; + + if (!rw_tbl->size) + return ret; + + return execute_steps(dev, write_table_steps, + ARRAY_SIZE(write_table_steps)); +} + +static int opal_generic_read_write_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + int ret, bit_set; + + mutex_lock(&dev->dev_lock); + setup_opal_dev(dev); + + bit_set = fls64(rw_tbl->flags) - 1; + switch (bit_set) { + case OPAL_READ_TABLE: + ret = opal_read_table(dev, rw_tbl); + break; + case OPAL_WRITE_TABLE: + ret = opal_write_table(dev, rw_tbl); + break; + default: + pr_debug("Invalid bit set in the flag (%016llx).\n", + rw_tbl->flags); + ret = -EINVAL; + break; + } + + mutex_unlock(&dev->dev_lock); + + return ret; +} + int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) { void *p; @@ -2505,6 +2682,9 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) case IOC_OPAL_PSID_REVERT_TPR: ret = opal_reverttper(dev, p, true); break; + case IOC_OPAL_GENERIC_TABLE_RW: + ret = opal_generic_read_write_table(dev, p); + break; default: break; } diff --git a/block/t10-pi.c b/block/t10-pi.c index 9803c7e0376e..f4907d941f03 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -235,16 +235,12 @@ static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter) return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION); } -/** - * Type 3 does not have a reference tag so no remapping is required. - */ +/* Type 3 does not have a reference tag so no remapping is required. */ static void t10_pi_type3_prepare(struct request *rq) { } -/** - * Type 3 does not have a reference tag so no remapping is required. - */ +/* Type 3 does not have a reference tag so no remapping is required. */ static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes) { } diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c index 76d2ce3a1b5b..d16d893bd195 100644 --- a/crypto/asymmetric_keys/asym_tpm.c +++ b/crypto/asymmetric_keys/asym_tpm.c @@ -13,7 +13,7 @@ #include <crypto/sha.h> #include <asm/unaligned.h> #include <keys/asymmetric-subtype.h> -#include <keys/trusted.h> +#include <keys/trusted_tpm.h> #include <crypto/asym_tpm_subtype.h> #include <crypto/public_key.h> @@ -21,10 +21,6 @@ #define TPM_ORD_LOADKEY2 65 #define TPM_ORD_UNBIND 30 #define TPM_ORD_SIGN 60 -#define TPM_LOADKEY2_SIZE 59 -#define TPM_FLUSHSPECIFIC_SIZE 18 -#define TPM_UNBIND_SIZE 63 -#define TPM_SIGN_SIZE 63 #define TPM_RT_KEY 0x00000001 @@ -68,16 +64,13 @@ static int tpm_loadkey2(struct tpm_buf *tb, return ret; /* build the request buffer */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_LOADKEY2_SIZE + keybloblen); - store32(tb, TPM_ORD_LOADKEY2); - store32(tb, keyhandle); - storebytes(tb, keyblob, keybloblen); - store32(tb, authhandle); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_LOADKEY2); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append(tb, keyblob, keybloblen); + tpm_buf_append_u32(tb, authhandle); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -101,12 +94,9 @@ static int tpm_loadkey2(struct tpm_buf *tb, */ static int tpm_flushspecific(struct tpm_buf *tb, uint32_t handle) { - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_COMMAND); - store32(tb, TPM_FLUSHSPECIFIC_SIZE); - store32(tb, TPM_ORD_FLUSHSPECIFIC); - store32(tb, handle); - store32(tb, TPM_RT_KEY); + tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_FLUSHSPECIFIC); + tpm_buf_append_u32(tb, handle); + tpm_buf_append_u32(tb, TPM_RT_KEY); return trusted_tpm_send(tb->data, MAX_BUF_SIZE); } @@ -155,17 +145,14 @@ static int tpm_unbind(struct tpm_buf *tb, return ret; /* build the request buffer */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_UNBIND_SIZE + bloblen); - store32(tb, TPM_ORD_UNBIND); - store32(tb, keyhandle); - store32(tb, bloblen); - storebytes(tb, blob, bloblen); - store32(tb, authhandle); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_UNBIND); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append_u32(tb, bloblen); + tpm_buf_append(tb, blob, bloblen); + tpm_buf_append_u32(tb, authhandle); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -241,17 +228,14 @@ static int tpm_sign(struct tpm_buf *tb, return ret; /* build the request buffer */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_SIGN_SIZE + bloblen); - store32(tb, TPM_ORD_SIGN); - store32(tb, keyhandle); - store32(tb, bloblen); - storebytes(tb, blob, bloblen); - store32(tb, authhandle); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SIGN); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append_u32(tb, bloblen); + tpm_buf_append(tb, blob, bloblen); + tpm_buf_append_u32(tb, authhandle); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -519,7 +503,7 @@ static int tpm_key_decrypt(struct tpm_key *tk, struct kernel_pkey_params *params, const void *in, void *out) { - struct tpm_buf *tb; + struct tpm_buf tb; uint32_t keyhandle; uint8_t srkauth[SHA1_DIGEST_SIZE]; uint8_t keyauth[SHA1_DIGEST_SIZE]; @@ -533,14 +517,14 @@ static int tpm_key_decrypt(struct tpm_key *tk, if (strcmp(params->encoding, "pkcs1")) return -ENOPKG; - tb = kzalloc(sizeof(*tb), GFP_KERNEL); - if (!tb) - return -ENOMEM; + r = tpm_buf_init(&tb, 0, 0); + if (r) + return r; /* TODO: Handle a non-all zero SRK authorization */ memset(srkauth, 0, sizeof(srkauth)); - r = tpm_loadkey2(tb, SRKHANDLE, srkauth, + r = tpm_loadkey2(&tb, SRKHANDLE, srkauth, tk->blob, tk->blob_len, &keyhandle); if (r < 0) { pr_devel("loadkey2 failed (%d)\n", r); @@ -550,16 +534,16 @@ static int tpm_key_decrypt(struct tpm_key *tk, /* TODO: Handle a non-all zero key authorization */ memset(keyauth, 0, sizeof(keyauth)); - r = tpm_unbind(tb, keyhandle, keyauth, + r = tpm_unbind(&tb, keyhandle, keyauth, in, params->in_len, out, params->out_len); if (r < 0) pr_devel("tpm_unbind failed (%d)\n", r); - if (tpm_flushspecific(tb, keyhandle) < 0) + if (tpm_flushspecific(&tb, keyhandle) < 0) pr_devel("flushspecific failed (%d)\n", r); error: - kzfree(tb); + tpm_buf_destroy(&tb); pr_devel("<==%s() = %d\n", __func__, r); return r; } @@ -643,7 +627,7 @@ static int tpm_key_sign(struct tpm_key *tk, struct kernel_pkey_params *params, const void *in, void *out) { - struct tpm_buf *tb; + struct tpm_buf tb; uint32_t keyhandle; uint8_t srkauth[SHA1_DIGEST_SIZE]; uint8_t keyauth[SHA1_DIGEST_SIZE]; @@ -681,15 +665,14 @@ static int tpm_key_sign(struct tpm_key *tk, goto error_free_asn1_wrapped; } - r = -ENOMEM; - tb = kzalloc(sizeof(*tb), GFP_KERNEL); - if (!tb) + r = tpm_buf_init(&tb, 0, 0); + if (r) goto error_free_asn1_wrapped; /* TODO: Handle a non-all zero SRK authorization */ memset(srkauth, 0, sizeof(srkauth)); - r = tpm_loadkey2(tb, SRKHANDLE, srkauth, + r = tpm_loadkey2(&tb, SRKHANDLE, srkauth, tk->blob, tk->blob_len, &keyhandle); if (r < 0) { pr_devel("loadkey2 failed (%d)\n", r); @@ -699,15 +682,15 @@ static int tpm_key_sign(struct tpm_key *tk, /* TODO: Handle a non-all zero key authorization */ memset(keyauth, 0, sizeof(keyauth)); - r = tpm_sign(tb, keyhandle, keyauth, in, in_len, out, params->out_len); + r = tpm_sign(&tb, keyhandle, keyauth, in, in_len, out, params->out_len); if (r < 0) pr_devel("tpm_sign failed (%d)\n", r); - if (tpm_flushspecific(tb, keyhandle) < 0) + if (tpm_flushspecific(&tb, keyhandle) < 0) pr_devel("flushspecific failed (%d)\n", r); error_free_tb: - kzfree(tb); + tpm_buf_destroy(&tb); error_free_asn1_wrapped: kfree(asn1_wrapped); pr_devel("<==%s() = %d\n", __func__, r); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 1413324982f0..14e68f202f81 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1322,7 +1322,7 @@ static ssize_t scrub_show(struct device *dev, nfit_device_lock(dev); nd_desc = dev_get_drvdata(dev); if (!nd_desc) { - device_unlock(dev); + nfit_device_unlock(dev); return rc; } acpi_desc = to_acpi_desc(nd_desc); diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index 08da9c29f1e9..62114a03a51a 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -290,14 +290,13 @@ static int acpi_processor_notifier(struct notifier_block *nb, unsigned long event, void *data) { struct cpufreq_policy *policy = data; - int cpu = policy->cpu; if (event == CPUFREQ_CREATE_POLICY) { - acpi_thermal_cpufreq_init(cpu); - acpi_processor_ppc_init(cpu); + acpi_thermal_cpufreq_init(policy); + acpi_processor_ppc_init(policy); } else if (event == CPUFREQ_REMOVE_POLICY) { - acpi_processor_ppc_exit(cpu); - acpi_thermal_cpufreq_exit(cpu); + acpi_processor_ppc_exit(policy); + acpi_thermal_cpufreq_exit(policy); } return 0; diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 930a49fa4dfc..5909e8fa4013 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -81,10 +81,10 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr) pr->performance_platform_limit = (int)ppc; if (ppc >= pr->performance->state_count || - unlikely(!dev_pm_qos_request_active(&pr->perflib_req))) + unlikely(!freq_qos_request_active(&pr->perflib_req))) return 0; - ret = dev_pm_qos_update_request(&pr->perflib_req, + ret = freq_qos_update_request(&pr->perflib_req, pr->performance->states[ppc].core_frequency * 1000); if (ret < 0) { pr_warn("Failed to update perflib freq constraint: CPU%d (%d)\n", @@ -157,28 +157,36 @@ void acpi_processor_ignore_ppc_init(void) ignore_ppc = 0; } -void acpi_processor_ppc_init(int cpu) +void acpi_processor_ppc_init(struct cpufreq_policy *policy) { - struct acpi_processor *pr = per_cpu(processors, cpu); - int ret; + unsigned int cpu; - if (!pr) - return; + for_each_cpu(cpu, policy->related_cpus) { + struct acpi_processor *pr = per_cpu(processors, cpu); + int ret; + + if (!pr) + continue; - ret = dev_pm_qos_add_request(get_cpu_device(cpu), - &pr->perflib_req, DEV_PM_QOS_MAX_FREQUENCY, - INT_MAX); - if (ret < 0) - pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu, - ret); + ret = freq_qos_add_request(&policy->constraints, + &pr->perflib_req, + FREQ_QOS_MAX, INT_MAX); + if (ret < 0) + pr_err("Failed to add freq constraint for CPU%d (%d)\n", + cpu, ret); + } } -void acpi_processor_ppc_exit(int cpu) +void acpi_processor_ppc_exit(struct cpufreq_policy *policy) { - struct acpi_processor *pr = per_cpu(processors, cpu); + unsigned int cpu; - if (pr) - dev_pm_qos_remove_request(&pr->perflib_req); + for_each_cpu(cpu, policy->related_cpus) { + struct acpi_processor *pr = per_cpu(processors, cpu); + + if (pr) + freq_qos_remove_request(&pr->perflib_req); + } } static int acpi_processor_get_performance_control(struct acpi_processor *pr) diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c index 8227c7dd75b1..41feb88ee92d 100644 --- a/drivers/acpi/processor_thermal.c +++ b/drivers/acpi/processor_thermal.c @@ -105,7 +105,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state) pr = per_cpu(processors, i); - if (unlikely(!dev_pm_qos_request_active(&pr->thermal_req))) + if (unlikely(!freq_qos_request_active(&pr->thermal_req))) continue; policy = cpufreq_cpu_get(i); @@ -116,7 +116,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state) cpufreq_cpu_put(policy); - ret = dev_pm_qos_update_request(&pr->thermal_req, max_freq); + ret = freq_qos_update_request(&pr->thermal_req, max_freq); if (ret < 0) { pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n", pr->id, ret); @@ -125,28 +125,36 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state) return 0; } -void acpi_thermal_cpufreq_init(int cpu) +void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy) { - struct acpi_processor *pr = per_cpu(processors, cpu); - int ret; + unsigned int cpu; - if (!pr) - return; - - ret = dev_pm_qos_add_request(get_cpu_device(cpu), - &pr->thermal_req, DEV_PM_QOS_MAX_FREQUENCY, - INT_MAX); - if (ret < 0) - pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu, - ret); + for_each_cpu(cpu, policy->related_cpus) { + struct acpi_processor *pr = per_cpu(processors, cpu); + int ret; + + if (!pr) + continue; + + ret = freq_qos_add_request(&policy->constraints, + &pr->thermal_req, + FREQ_QOS_MAX, INT_MAX); + if (ret < 0) + pr_err("Failed to add freq constraint for CPU%d (%d)\n", + cpu, ret); + } } -void acpi_thermal_cpufreq_exit(int cpu) +void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy) { - struct acpi_processor *pr = per_cpu(processors, cpu); + unsigned int cpu; + + for_each_cpu(cpu, policy->related_cpus) { + struct acpi_processor *pr = per_cpu(processors, policy->cpu); - if (pr) - dev_pm_qos_remove_request(&pr->thermal_req); + if (pr) + freq_qos_remove_request(&pr->thermal_req); + } } #else /* ! CONFIG_CPU_FREQ */ static int cpufreq_get_max_state(unsigned int cpu) diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index f39f075abff9..fe1523664816 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -409,9 +409,11 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent) */ rstc = of_reset_control_array_get_optional_shared(dev->dev.of_node); if (IS_ERR(rstc)) { - if (PTR_ERR(rstc) != -EPROBE_DEFER) - dev_err(&dev->dev, "Can't get amba reset!\n"); - return PTR_ERR(rstc); + ret = PTR_ERR(rstc); + if (ret != -EPROBE_DEFER) + dev_err(&dev->dev, "can't get reset: %d\n", + ret); + goto err_reset; } reset_control_deassert(rstc); reset_control_put(rstc); @@ -472,6 +474,12 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent) release_resource(&dev->res); err_out: return ret; + + err_reset: + amba_put_disable_pclk(dev); + iounmap(tmp); + dev_pm_domain_detach(&dev->dev, true); + goto err_release; } /* diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 5b9ac2122e89..265d9dd46a5e 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -97,10 +97,6 @@ DEFINE_SHOW_ATTRIBUTE(proc); #define SZ_1K 0x400 #endif -#ifndef SZ_4M -#define SZ_4M 0x400000 -#endif - #define FORBIDDEN_MMAP_FLAGS (VM_WRITE) enum { @@ -5177,9 +5173,6 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) if (proc->tsk != current->group_leader) return -EINVAL; - if ((vma->vm_end - vma->vm_start) > SZ_4M) - vma->vm_end = vma->vm_start + SZ_4M; - binder_debug(BINDER_DEBUG_OPEN_CLOSE, "%s: %d %lx-%lx (%ld K) vma %lx pagep %lx\n", __func__, proc->pid, vma->vm_start, vma->vm_end, diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index d42a8b2f636a..eb76a823fbb2 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -22,6 +22,7 @@ #include <asm/cacheflush.h> #include <linux/uaccess.h> #include <linux/highmem.h> +#include <linux/sizes.h> #include "binder_alloc.h" #include "binder_trace.h" @@ -689,7 +690,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, alloc->buffer = (void __user *)vma->vm_start; mutex_unlock(&binder_alloc_mmap_lock); - alloc->pages = kcalloc((vma->vm_end - vma->vm_start) / PAGE_SIZE, + alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start, + SZ_4M); + alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE, sizeof(alloc->pages[0]), GFP_KERNEL); if (alloc->pages == NULL) { @@ -697,7 +700,6 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, failure_string = "alloc page array"; goto err_alloc_pages_failed; } - alloc->buffer_size = vma->vm_end - vma->vm_start; buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); if (!buffer) { diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index 753985c01517..46dc54d18f0b 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -56,7 +56,7 @@ struct acard_sg { __le32 size; /* bit 31 (EOT) max==0x10000 (64k) */ }; -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc); static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int acard_ahci_port_start(struct ata_port *ap); static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); @@ -210,7 +210,7 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl) return si; } -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -248,6 +248,8 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 05c2b32dcc4d..ec6c64fce74a 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -56,6 +56,7 @@ enum board_ids { board_ahci_yes_fbs, /* board IDs for specific chipsets in alphabetical order */ + board_ahci_al, board_ahci_avn, board_ahci_mcp65, board_ahci_mcp77, @@ -167,6 +168,13 @@ static const struct ata_port_info ahci_port_info[] = { .port_ops = &ahci_ops, }, /* by chipsets */ + [board_ahci_al] = { + AHCI_HFLAGS (AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_MSI), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_avn] = { .flags = AHCI_FLAG_COMMON, .pio_mask = ATA_PIO4, @@ -415,6 +423,11 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(ATI, 0x4394), board_ahci_sb700 }, /* ATI SB700/800 */ { PCI_VDEVICE(ATI, 0x4395), board_ahci_sb700 }, /* ATI SB700/800 */ + /* Amazon's Annapurna Labs support */ + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031), + .class = PCI_CLASS_STORAGE_SATA_AHCI, + .class_mask = 0xffffff, + board_ahci_al }, /* AMD */ { PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */ { PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */ diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c index e3163dae5e85..cb55ebc1725b 100644 --- a/drivers/ata/ahci_tegra.c +++ b/drivers/ata/ahci_tegra.c @@ -483,7 +483,6 @@ static int tegra_ahci_probe(struct platform_device *pdev) struct tegra_ahci_priv *tegra; struct resource *res; int ret; - unsigned int i; hpriv = ahci_platform_get_resources(pdev, 0); if (IS_ERR(hpriv)) @@ -543,8 +542,9 @@ static int tegra_ahci_probe(struct platform_device *pdev) if (!tegra->supplies) return -ENOMEM; - for (i = 0; i < tegra->soc->num_supplies; i++) - tegra->supplies[i].supply = tegra->soc->supply_names[i]; + regulator_bulk_set_supply_names(tegra->supplies, + tegra->soc->supply_names, + tegra->soc->num_supplies); ret = devm_regulator_bulk_get(&pdev->dev, tegra->soc->num_supplies, diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index e4da725381d3..3ca7720e7d8f 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -841,6 +841,12 @@ static int piix_broken_suspend(void) }, }, { + .ident = "TECRA M3", + .matches = { + DMI_MATCH(DMI_OEM_STRING, "Tecra M3,"), + }, + }, + { .ident = "TECRA M4", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), @@ -955,18 +961,10 @@ static int piix_broken_suspend(void) { } /* terminate list */ }; - static const char *oemstrs[] = { - "Tecra M3,", - }; - int i; if (dmi_check_system(sysids)) return 1; - for (i = 0; i < ARRAY_SIZE(oemstrs); i++) - if (dmi_find_device(DMI_DEV_TYPE_OEM_STRING, oemstrs[i], NULL)) - return 1; - /* TECRA M4 sometimes forgets its identify and reports bogus * DMI information. As the bogus information is a bit * generic, match as many entries as possible. This manual diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index bff369d9a1a7..ea5bf5f4cbed 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -57,7 +57,7 @@ static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int ahci_port_start(struct ata_port *ap); static void ahci_port_stop(struct ata_port *ap); -static void ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc); static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc); static void ahci_freeze(struct ata_port *ap); static void ahci_thaw(struct ata_port *ap); @@ -1624,7 +1624,7 @@ static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc) return sata_pmp_qc_defer_cmd_switch(qc); } -static void ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -1660,6 +1660,8 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static void ahci_fbs_dec_intr(struct ata_port *ap) diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index e742780950de..8befce036af8 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -153,17 +153,13 @@ int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv) { int rc, i; - if (hpriv->ahci_regulator) { - rc = regulator_enable(hpriv->ahci_regulator); - if (rc) - return rc; - } + rc = regulator_enable(hpriv->ahci_regulator); + if (rc) + return rc; - if (hpriv->phy_regulator) { - rc = regulator_enable(hpriv->phy_regulator); - if (rc) - goto disable_ahci_pwrs; - } + rc = regulator_enable(hpriv->phy_regulator); + if (rc) + goto disable_ahci_pwrs; for (i = 0; i < hpriv->nports; i++) { if (!hpriv->target_pwrs[i]) @@ -181,11 +177,9 @@ disable_target_pwrs: if (hpriv->target_pwrs[i]) regulator_disable(hpriv->target_pwrs[i]); - if (hpriv->phy_regulator) - regulator_disable(hpriv->phy_regulator); + regulator_disable(hpriv->phy_regulator); disable_ahci_pwrs: - if (hpriv->ahci_regulator) - regulator_disable(hpriv->ahci_regulator); + regulator_disable(hpriv->ahci_regulator); return rc; } EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators); @@ -207,10 +201,8 @@ void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv) regulator_disable(hpriv->target_pwrs[i]); } - if (hpriv->ahci_regulator) - regulator_disable(hpriv->ahci_regulator); - if (hpriv->phy_regulator) - regulator_disable(hpriv->phy_regulator); + regulator_disable(hpriv->ahci_regulator); + regulator_disable(hpriv->phy_regulator); } EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators); /** @@ -359,7 +351,7 @@ static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port, struct regulator *target_pwr; int rc = 0; - target_pwr = regulator_get_optional(dev, "target"); + target_pwr = regulator_get(dev, "target"); if (!IS_ERR(target_pwr)) hpriv->target_pwrs[port] = target_pwr; @@ -436,16 +428,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, hpriv->clks[i] = clk; } - hpriv->ahci_regulator = devm_regulator_get_optional(dev, "ahci"); + hpriv->ahci_regulator = devm_regulator_get(dev, "ahci"); if (IS_ERR(hpriv->ahci_regulator)) { rc = PTR_ERR(hpriv->ahci_regulator); - if (rc == -EPROBE_DEFER) + if (rc != 0) goto err_out; - rc = 0; - hpriv->ahci_regulator = NULL; } - hpriv->phy_regulator = devm_regulator_get_optional(dev, "phy"); + hpriv->phy_regulator = devm_regulator_get(dev, "phy"); if (IS_ERR(hpriv->phy_regulator)) { rc = PTR_ERR(hpriv->phy_regulator); if (rc == -EPROBE_DEFER) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 28c492be0a57..e9017c570bc5 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4980,7 +4980,10 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc) return ATA_DEFER_LINK; } -void ata_noop_qc_prep(struct ata_queued_cmd *qc) { } +enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc) +{ + return AC_ERR_OK; +} /** * ata_sg_init - Associate command with scatter-gather table. @@ -5443,7 +5446,9 @@ void ata_qc_issue(struct ata_queued_cmd *qc) return; } - ap->ops->qc_prep(qc); + qc->err_mask |= ap->ops->qc_prep(qc); + if (unlikely(qc->err_mask)) + goto err; trace_ata_qc_issue(qc); qc->err_mask |= ap->ops->qc_issue(qc); if (unlikely(qc->err_mask)) @@ -6708,6 +6713,9 @@ void ata_host_detach(struct ata_host *host) { int i; + /* Ensure ata_port probe has completed */ + async_synchronize_full(); + for (i = 0; i < host->n_ports; i++) ata_port_detach(host->ports[i]); diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 4ed682da52ae..038db94216a9 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -2679,12 +2679,14 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc) * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); @@ -2697,12 +2699,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg_dumb(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep); diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c index 3aa006c5ed0c..6bd2228bb6ff 100644 --- a/drivers/ata/pata_artop.c +++ b/drivers/ata/pata_artop.c @@ -100,7 +100,7 @@ static void artop6210_load_piomode(struct ata_port *ap, struct ata_device *adev, { struct pci_dev *pdev = to_pci_dev(ap->host->dev); int dn = adev->devno + 2 * ap->port_no; - const u16 timing[2][5] = { + static const u16 timing[2][5] = { { 0x0000, 0x000A, 0x0008, 0x0303, 0x0301 }, { 0x0700, 0x070A, 0x0708, 0x0403, 0x0401 } @@ -154,7 +154,7 @@ static void artop6260_load_piomode (struct ata_port *ap, struct ata_device *adev { struct pci_dev *pdev = to_pci_dev(ap->host->dev); int dn = adev->devno + 2 * ap->port_no; - const u8 timing[2][5] = { + static const u8 timing[2][5] = { { 0x00, 0x0A, 0x08, 0x33, 0x31 }, { 0x70, 0x7A, 0x78, 0x43, 0x41 } diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 57f2ec71cfc3..1bfd0154dad5 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -510,7 +510,7 @@ static int pata_macio_cable_detect(struct ata_port *ap) return ATA_CBL_PATA40; } -static void pata_macio_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) { unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE); struct ata_port *ap = qc->ap; @@ -523,7 +523,7 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) __func__, qc, qc->flags, write, qc->dev->devno); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; table = (struct dbdma_cmd *) priv->dma_table_cpu; @@ -568,6 +568,8 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) table->command = cpu_to_le16(DBDMA_STOP); dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi); + + return AC_ERR_OK; } diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c index 4afcb8e63e21..41430f79663c 100644 --- a/drivers/ata/pata_pxa.c +++ b/drivers/ata/pata_pxa.c @@ -44,25 +44,27 @@ static void pxa_ata_dma_irq(void *d) /* * Prepare taskfile for submission. */ -static void pxa_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc) { struct pata_pxa_data *pd = qc->ap->private_data; struct dma_async_tx_descriptor *tx; enum dma_transfer_direction dir; if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM); tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir, DMA_PREP_INTERRUPT); if (!tx) { ata_dev_err(qc->dev, "prep_slave_sg() failed\n"); - return; + return AC_ERR_OK; } tx->callback = pxa_ata_dma_irq; tx->callback_param = pd; pd->dma_cookie = dmaengine_submit(tx); + + return AC_ERR_OK; } /* diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c index cb490531b62e..5db55e1e2a61 100644 --- a/drivers/ata/pdc_adma.c +++ b/drivers/ata/pdc_adma.c @@ -116,7 +116,7 @@ static int adma_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int adma_port_start(struct ata_port *ap); static void adma_port_stop(struct ata_port *ap); -static void adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int adma_qc_issue(struct ata_queued_cmd *qc); static int adma_check_atapi_dma(struct ata_queued_cmd *qc); static void adma_freeze(struct ata_port *ap); @@ -295,7 +295,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc) return i; } -static void adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc) { struct adma_port_priv *pp = qc->ap->private_data; u8 *buf = pp->pkt; @@ -306,7 +306,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) adma_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; buf[i++] = 0; /* Response flags */ buf[i++] = 0; /* reserved */ @@ -371,6 +371,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) printk("%s\n", obuf); } #endif + return AC_ERR_OK; } static inline void adma_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 8e9cb198fcd1..9239615d8a04 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -502,7 +502,7 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, return num_prde; } -static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sata_fsl_port_priv *pp = ap->private_data; @@ -548,6 +548,8 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n", desc_info, ttl_dwords, num_prde); + + return AC_ERR_OK; } static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index 7f99e23bff88..a6b76cc12a66 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -478,7 +478,7 @@ static void inic_fill_sg(struct inic_prd *prd, struct ata_queued_cmd *qc) prd[-1].flags |= PRD_END; } -static void inic_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc) { struct inic_port_priv *pp = qc->ap->private_data; struct inic_pkt *pkt = pp->pkt; @@ -538,6 +538,8 @@ static void inic_qc_prep(struct ata_queued_cmd *qc) inic_fill_sg(prd, qc); pp->cpb_tbl[0] = pp->pkt_dma; + + return AC_ERR_OK; } static unsigned int inic_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index ad385a113391..277f11909fc1 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -592,8 +592,8 @@ static int mv5_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val) static int mv_port_start(struct ata_port *ap); static void mv_port_stop(struct ata_port *ap); static int mv_qc_defer(struct ata_queued_cmd *qc); -static void mv_qc_prep(struct ata_queued_cmd *qc); -static void mv_qc_prep_iie(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc); static unsigned int mv_qc_issue(struct ata_queued_cmd *qc); static int mv_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); @@ -2031,7 +2031,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2043,15 +2043,15 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) switch (tf->protocol) { case ATA_PROT_DMA: if (tf->command == ATA_CMD_DSM) - return; + return AC_ERR_OK; /* fall-thru */ case ATA_PROT_NCQ: break; /* continue below */ case ATA_PROT_PIO: mv_rw_multi_errata_sata24(qc); - return; + return AC_ERR_OK; default: - return; + return AC_ERR_OK; } /* Fill in command request block @@ -2098,12 +2098,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none * of which are defined/used by Linux. If we get here, this * driver needs work. - * - * FIXME: modify libata to give qc_prep a return value and - * return error here. */ - BUG_ON(tf->command); - break; + ata_port_err(ap, "%s: unsupported command: %.2x\n", __func__, + tf->command); + return AC_ERR_INVALID; } mv_crqb_pack_cmd(cw++, tf->nsect, ATA_REG_NSECT, 0); mv_crqb_pack_cmd(cw++, tf->hob_lbal, ATA_REG_LBAL, 0); @@ -2116,8 +2114,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1); /* last */ if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** @@ -2132,7 +2132,7 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep_iie(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2143,9 +2143,9 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) if ((tf->protocol != ATA_PROT_DMA) && (tf->protocol != ATA_PROT_NCQ)) - return; + return AC_ERR_OK; if (tf->command == ATA_CMD_DSM) - return; /* use bmdma for this */ + return AC_ERR_OK; /* use bmdma for this */ /* Fill in Gen IIE command request block */ if (!(tf->flags & ATA_TFLAG_WRITE)) @@ -2186,8 +2186,10 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) ); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 56946012d113..65ec8dff1c51 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -297,7 +297,7 @@ static void nv_ck804_freeze(struct ata_port *ap); static void nv_ck804_thaw(struct ata_port *ap); static int nv_adma_slave_config(struct scsi_device *sdev); static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc); -static void nv_adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc); static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance); static void nv_adma_irq_clear(struct ata_port *ap); @@ -319,7 +319,7 @@ static void nv_mcp55_freeze(struct ata_port *ap); static void nv_swncq_error_handler(struct ata_port *ap); static int nv_swncq_slave_config(struct scsi_device *sdev); static int nv_swncq_port_start(struct ata_port *ap); -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc); static void nv_swncq_fill_sg(struct ata_queued_cmd *qc); static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc); static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis); @@ -1344,7 +1344,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc) return 1; } -static void nv_adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc) { struct nv_adma_port_priv *pp = qc->ap->private_data; struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag]; @@ -1356,7 +1356,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) (qc->flags & ATA_QCFLAG_DMAMAP)); nv_adma_register_mode(qc->ap); ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } cpb->resp_flags = NV_CPB_RESP_DONE; @@ -1388,6 +1388,8 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) cpb->ctl_flags = ctl_flags; wmb(); cpb->resp_flags = 0; + + return AC_ERR_OK; } static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc) @@ -1950,17 +1952,19 @@ static int nv_swncq_port_start(struct ata_port *ap) return 0; } -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc) { if (qc->tf.protocol != ATA_PROT_NCQ) { ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; nv_swncq_fill_sg(qc); + + return AC_ERR_OK; } static void nv_swncq_fill_sg(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 5fd464765ddc..c451d7d1c817 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -139,7 +139,7 @@ static int pdc_sata_scr_write(struct ata_link *link, unsigned int sc_reg, u32 va static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int pdc_common_port_start(struct ata_port *ap); static int pdc_sata_port_start(struct ata_port *ap); -static void pdc_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static int pdc_check_atapi_dma(struct ata_queued_cmd *qc); @@ -633,7 +633,7 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc) prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void pdc_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc) { struct pdc_port_priv *pp = qc->ap->private_data; unsigned int i; @@ -665,6 +665,8 @@ static void pdc_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static int pdc_is_sataii_tx4(unsigned long flags) diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c index c53c5a47204d..ef00ab644afb 100644 --- a/drivers/ata/sata_qstor.c +++ b/drivers/ata/sata_qstor.c @@ -100,7 +100,7 @@ static int qs_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int qs_port_start(struct ata_port *ap); static void qs_host_stop(struct ata_host *host); -static void qs_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc); static unsigned int qs_qc_issue(struct ata_queued_cmd *qc); static int qs_check_atapi_dma(struct ata_queued_cmd *qc); static void qs_freeze(struct ata_port *ap); @@ -260,7 +260,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc) return si; } -static void qs_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc) { struct qs_port_priv *pp = qc->ap->private_data; u8 dflags = QS_DF_PORD, *buf = pp->pkt; @@ -272,7 +272,7 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) qs_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; nelem = qs_fill_sg(qc); @@ -295,6 +295,8 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) /* frame information structure (FIS) */ ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]); + + return AC_ERR_OK; } static inline void qs_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 3495e1733a8e..980aacdbcf3b 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -550,12 +550,14 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc) prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND); } -static void sata_rcar_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sata_rcar_bmdma_fill_sg(qc); + + return AC_ERR_OK; } static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index e6fbae2f645a..75321f1ceba5 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -103,7 +103,7 @@ static void sil_dev_config(struct ata_device *dev); static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val); static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed); -static void sil_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc); static void sil_bmdma_setup(struct ata_queued_cmd *qc); static void sil_bmdma_start(struct ata_queued_cmd *qc); static void sil_bmdma_stop(struct ata_queued_cmd *qc); @@ -317,12 +317,14 @@ static void sil_fill_sg(struct ata_queued_cmd *qc) last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void sil_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sil_fill_sg(qc); + + return AC_ERR_OK; } static unsigned char sil_get_device_cache_line(struct pci_dev *pdev) diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 7bef82de53ca..560070d4f1d0 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -326,7 +326,7 @@ static void sil24_dev_config(struct ata_device *dev); static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val); static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val); static int sil24_qc_defer(struct ata_queued_cmd *qc); -static void sil24_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc); static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc); static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc); static void sil24_pmp_attach(struct ata_port *ap); @@ -830,7 +830,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) return ata_std_qc_defer(qc); } -static void sil24_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sil24_port_priv *pp = ap->private_data; @@ -874,6 +874,8 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc) if (qc->flags & ATA_QCFLAG_DMAMAP) sil24_fill_sg(qc, sge); + + return AC_ERR_OK; } static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 2277ba0c9c7f..2c7b30c5ea3d 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -202,7 +202,7 @@ static void pdc_error_handler(struct ata_port *ap); static void pdc_freeze(struct ata_port *ap); static void pdc_thaw(struct ata_port *ap); static int pdc_port_start(struct ata_port *ap); -static void pdc20621_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static unsigned int pdc20621_dimm_init(struct ata_host *host); @@ -530,7 +530,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc) VPRINTK("ata pkt buf ofs %u, mmio copied\n", i); } -static void pdc20621_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc) { switch (qc->tf.protocol) { case ATA_PROT_DMA: @@ -542,6 +542,8 @@ static void pdc20621_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static void __pdc20621_push_hdma(struct ata_queued_cmd *qc, diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index cc37511de866..6265871a4af2 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -554,12 +554,27 @@ ssize_t __weak cpu_show_mds(struct device *dev, return sprintf(buf, "Not affected\n"); } +ssize_t __weak cpu_show_tsx_async_abort(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_itlb_multihit(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL); static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL); static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL); +static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL); +static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -568,6 +583,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_spec_store_bypass.attr, &dev_attr_l1tf.attr, &dev_attr_mds.attr, + &dev_attr_tsx_async_abort.attr, + &dev_attr_itlb_multihit.attr, NULL }; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 55907c27075b..84c4e1f72cbd 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -872,3 +872,39 @@ int walk_memory_blocks(unsigned long start, unsigned long size, } return ret; } + +struct for_each_memory_block_cb_data { + walk_memory_blocks_func_t func; + void *arg; +}; + +static int for_each_memory_block_cb(struct device *dev, void *data) +{ + struct memory_block *mem = to_memory_block(dev); + struct for_each_memory_block_cb_data *cb_data = data; + + return cb_data->func(mem, cb_data->arg); +} + +/** + * for_each_memory_block - walk through all present memory blocks + * + * @arg: argument passed to func + * @func: callback for each memory block walked + * + * This function walks through all present memory blocks, calling func on + * each memory block. + * + * In case func() returns an error, walking is aborted and the error is + * returned. + */ +int for_each_memory_block(void *arg, walk_memory_blocks_func_t func) +{ + struct for_each_memory_block_cb_data cb_data = { + .func = func, + .arg = arg, + }; + + return bus_for_each_dev(&memory_subsys, NULL, &cb_data, + for_each_memory_block_cb); +} diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 6c90fd7e2ff8..350dcafd751f 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -115,20 +115,10 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) spin_lock_irqsave(&dev->power.lock, flags); - switch (type) { - case DEV_PM_QOS_RESUME_LATENCY: + if (type == DEV_PM_QOS_RESUME_LATENCY) { ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); - break; - case DEV_PM_QOS_MIN_FREQUENCY: - ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE - : pm_qos_read_value(&qos->min_frequency); - break; - case DEV_PM_QOS_MAX_FREQUENCY: - ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE - : pm_qos_read_value(&qos->max_frequency); - break; - default: + } else { WARN_ON(1); ret = 0; } @@ -169,14 +159,6 @@ static int apply_constraint(struct dev_pm_qos_request *req, req->dev->power.set_latency_tolerance(req->dev, value); } break; - case DEV_PM_QOS_MIN_FREQUENCY: - ret = pm_qos_update_target(&qos->min_frequency, - &req->data.pnode, action, value); - break; - case DEV_PM_QOS_MAX_FREQUENCY: - ret = pm_qos_update_target(&qos->max_frequency, - &req->data.pnode, action, value); - break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); @@ -227,24 +209,6 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; - c = &qos->min_frequency; - plist_head_init(&c->list); - c->target_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; - c->default_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; - c->no_constraint_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; - c->type = PM_QOS_MAX; - c->notifiers = ++n; - BLOCKING_INIT_NOTIFIER_HEAD(n); - - c = &qos->max_frequency; - plist_head_init(&c->list); - c->target_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; - c->default_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; - c->no_constraint_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; - c->type = PM_QOS_MIN; - c->notifiers = ++n; - BLOCKING_INIT_NOTIFIER_HEAD(n); - INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); @@ -305,18 +269,6 @@ void dev_pm_qos_constraints_destroy(struct device *dev) memset(req, 0, sizeof(*req)); } - c = &qos->min_frequency; - plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { - apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); - memset(req, 0, sizeof(*req)); - } - - c = &qos->max_frequency; - plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { - apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); - memset(req, 0, sizeof(*req)); - } - f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); @@ -428,8 +380,6 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, switch(req->type) { case DEV_PM_QOS_RESUME_LATENCY: case DEV_PM_QOS_LATENCY_TOLERANCE: - case DEV_PM_QOS_MIN_FREQUENCY: - case DEV_PM_QOS_MAX_FREQUENCY: curr_value = req->data.pnode.prio; break; case DEV_PM_QOS_FLAGS: @@ -557,14 +507,6 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; - case DEV_PM_QOS_MIN_FREQUENCY: - ret = blocking_notifier_chain_register(dev->power.qos->min_frequency.notifiers, - notifier); - break; - case DEV_PM_QOS_MAX_FREQUENCY: - ret = blocking_notifier_chain_register(dev->power.qos->max_frequency.notifiers, - notifier); - break; default: WARN_ON(1); ret = -EINVAL; @@ -604,14 +546,6 @@ int dev_pm_qos_remove_notifier(struct device *dev, ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; - case DEV_PM_QOS_MIN_FREQUENCY: - ret = blocking_notifier_chain_unregister(dev->power.qos->min_frequency.notifiers, - notifier); - break; - case DEV_PM_QOS_MAX_FREQUENCY: - ret = blocking_notifier_chain_unregister(dev->power.qos->max_frequency.notifiers, - notifier); - break; default: WARN_ON(1); ret = -EINVAL; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 5b248763a672..a18155cdce41 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -786,7 +786,6 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm if (nc->tentative && connection->agreed_pro_version < 92) { rcu_read_unlock(); - mutex_unlock(&sock->mutex); drbd_err(connection, "--dry-run is not supported by peer"); return -EOPNOTSUPP; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f6f77eaa7217..739b372a5112 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -417,18 +417,20 @@ out_free_page: return ret; } -static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos) +static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, + int mode) { /* - * We use punch hole to reclaim the free space used by the - * image a.k.a. discard. However we do not support discard if - * encryption is enabled, because it may give an attacker - * useful information. + * We use fallocate to manipulate the space mappings used by the image + * a.k.a. discard/zerorange. However we do not support this if + * encryption is enabled, because it may give an attacker useful + * information. */ struct file *file = lo->lo_backing_file; - int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE; int ret; + mode |= FALLOC_FL_KEEP_SIZE; + if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) { ret = -EOPNOTSUPP; goto out; @@ -596,9 +598,17 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); - case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - return lo_discard(lo, rq, pos); + /* + * If the caller doesn't want deallocation, call zeroout to + * write zeroes the range. Otherwise, punch them out. + */ + return lo_fallocate(lo, rq, pos, + (rq->cmd_flags & REQ_NOUNMAP) ? + FALLOC_FL_ZERO_RANGE : + FALLOC_FL_PUNCH_HOLE); + case REQ_OP_DISCARD: + return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: if (lo->transfer) return lo_write_transfer(lo, rq, pos); @@ -630,7 +640,9 @@ static void loop_reread_partitions(struct loop_device *lo, { int rc; - rc = blkdev_reread_part(bdev); + mutex_lock(&bdev->bd_mutex); + rc = bdev_disk_changed(bdev, false); + mutex_unlock(&bdev->bd_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); @@ -1154,10 +1166,11 @@ out_unlock: * must be at least one and it can only become zero when the * current holder is released. */ - if (release) - err = __blkdev_reread_part(bdev); - else - err = blkdev_reread_part(bdev); + if (!release) + mutex_lock(&bdev->bd_mutex); + err = bdev_disk_changed(bdev, false); + if (!release) + mutex_unlock(&bdev->bd_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo_number, err); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 964f78cfffa0..f6bafa9a68b9 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -129,7 +129,7 @@ struct mtip_compat_ide_task_request_s { /* * This function check_for_surprise_removal is called * while card is removed from the system and it will - * read the vendor id from the configration space + * read the vendor id from the configuration space * * @pdev Pointer to the pci_dev structure. * diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 478aa86fc1f2..57532465fb83 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -385,17 +385,16 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, struct nbd_device *nbd = cmd->nbd; struct nbd_config *config; + if (!mutex_trylock(&cmd->lock)) + return BLK_EH_RESET_TIMER; + if (!refcount_inc_not_zero(&nbd->config_refs)) { cmd->status = BLK_STS_TIMEOUT; + mutex_unlock(&cmd->lock); goto done; } config = nbd->config; - if (!mutex_trylock(&cmd->lock)) { - nbd_config_put(nbd); - return BLK_EH_RESET_TIMER; - } - if (config->num_connections > 1) { dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out, retrying (%d/%d alive)\n", @@ -711,6 +710,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) ret = -ENOENT; goto out; } + if (cmd->status != BLK_STS_OK) { + dev_err(disk_to_dev(nbd->disk), "Command already handled %p\n", + req); + ret = -ENOENT; + goto out; + } if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", req); @@ -792,7 +797,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); + mutex_lock(&cmd->lock); cmd->status = BLK_STS_IOERR; + mutex_unlock(&cmd->lock); + blk_mq_complete_request(req); return true; } @@ -972,6 +980,26 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, return ret; } +static struct socket *nbd_get_socket(struct nbd_device *nbd, unsigned long fd, + int *err) +{ + struct socket *sock; + + *err = 0; + sock = sockfd_lookup(fd, err); + if (!sock) + return NULL; + + if (sock->ops->shutdown == sock_no_shutdown) { + dev_err(disk_to_dev(nbd->disk), "Unsupported socket: shutdown callout must be supported.\n"); + *err = -EINVAL; + sockfd_put(sock); + return NULL; + } + + return sock; +} + static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, bool netlink) { @@ -981,7 +1009,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, struct nbd_sock *nsock; int err; - sock = sockfd_lookup(arg, &err); + sock = nbd_get_socket(nbd, arg, &err); if (!sock) return err; @@ -1004,14 +1032,15 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, sockfd_put(sock); return -ENOMEM; } + + config->socks = socks; + nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL); if (!nsock) { sockfd_put(sock); return -ENOMEM; } - config->socks = socks; - nsock->fallback_index = -1; nsock->dead = false; mutex_init(&nsock->tx_lock); @@ -1033,7 +1062,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) int i; int err; - sock = sockfd_lookup(arg, &err); + sock = nbd_get_socket(nbd, arg, &err); if (!sock) return err; diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index a235c45e22a7..bc837862b767 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -91,11 +91,13 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); +int null_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, sector_t sector, sector_t nr_sectors); +size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, unsigned int len); #else static inline int null_zone_init(struct nullb_device *dev) { @@ -103,17 +105,18 @@ static inline int null_zone_init(struct nullb_device *dev) return -EINVAL; } static inline void null_zone_exit(struct nullb_device *dev) {} -static inline int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, - unsigned int *nr_zones) -{ - return -EOPNOTSUPP; -} static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, sector_t sector, sector_t nr_sectors) { return BLK_STS_NOTSUPP; } +static inline size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, + unsigned int len) +{ + return len; +} +#define null_report_zones NULL #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* __NULL_BLK_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 0e7da5015ccd..795fda576824 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -227,7 +227,7 @@ static ssize_t nullb_device_uint_attr_store(unsigned int *val, int result; result = kstrtouint(page, 0, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -241,7 +241,7 @@ static ssize_t nullb_device_ulong_attr_store(unsigned long *val, unsigned long tmp; result = kstrtoul(page, 0, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -255,7 +255,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, int result; result = kstrtobool(page, &tmp); - if (result) + if (result < 0) return result; *val = tmp; @@ -263,7 +263,7 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, } /* The following macro should only be used with TYPE = {uint, ulong, bool}. */ -#define NULLB_DEVICE_ATTR(NAME, TYPE) \ +#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY) \ static ssize_t \ nullb_device_##NAME##_show(struct config_item *item, char *page) \ { \ @@ -274,31 +274,57 @@ static ssize_t \ nullb_device_##NAME##_store(struct config_item *item, const char *page, \ size_t count) \ { \ - if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags)) \ - return -EBUSY; \ - return nullb_device_##TYPE##_attr_store( \ - &to_nullb_device(item)->NAME, page, count); \ + int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY; \ + struct nullb_device *dev = to_nullb_device(item); \ + TYPE new_value; \ + int ret; \ + \ + ret = nullb_device_##TYPE##_attr_store(&new_value, page, count); \ + if (ret < 0) \ + return ret; \ + if (apply_fn) \ + ret = apply_fn(dev, new_value); \ + else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) \ + ret = -EBUSY; \ + if (ret < 0) \ + return ret; \ + dev->NAME = new_value; \ + return count; \ } \ CONFIGFS_ATTR(nullb_device_, NAME); -NULLB_DEVICE_ATTR(size, ulong); -NULLB_DEVICE_ATTR(completion_nsec, ulong); -NULLB_DEVICE_ATTR(submit_queues, uint); -NULLB_DEVICE_ATTR(home_node, uint); -NULLB_DEVICE_ATTR(queue_mode, uint); -NULLB_DEVICE_ATTR(blocksize, uint); -NULLB_DEVICE_ATTR(irqmode, uint); -NULLB_DEVICE_ATTR(hw_queue_depth, uint); -NULLB_DEVICE_ATTR(index, uint); -NULLB_DEVICE_ATTR(blocking, bool); -NULLB_DEVICE_ATTR(use_per_node_hctx, bool); -NULLB_DEVICE_ATTR(memory_backed, bool); -NULLB_DEVICE_ATTR(discard, bool); -NULLB_DEVICE_ATTR(mbps, uint); -NULLB_DEVICE_ATTR(cache_size, ulong); -NULLB_DEVICE_ATTR(zoned, bool); -NULLB_DEVICE_ATTR(zone_size, ulong); -NULLB_DEVICE_ATTR(zone_nr_conv, uint); +static int nullb_apply_submit_queues(struct nullb_device *dev, + unsigned int submit_queues) +{ + struct nullb *nullb = dev->nullb; + struct blk_mq_tag_set *set; + + if (!nullb) + return 0; + + set = nullb->tag_set; + blk_mq_update_nr_hw_queues(set, submit_queues); + return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM; +} + +NULLB_DEVICE_ATTR(size, ulong, NULL); +NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL); +NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues); +NULLB_DEVICE_ATTR(home_node, uint, NULL); +NULLB_DEVICE_ATTR(queue_mode, uint, NULL); +NULLB_DEVICE_ATTR(blocksize, uint, NULL); +NULLB_DEVICE_ATTR(irqmode, uint, NULL); +NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL); +NULLB_DEVICE_ATTR(index, uint, NULL); +NULLB_DEVICE_ATTR(blocking, bool, NULL); +NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL); +NULLB_DEVICE_ATTR(memory_backed, bool, NULL); +NULLB_DEVICE_ATTR(discard, bool, NULL); +NULLB_DEVICE_ATTR(mbps, uint, NULL); +NULLB_DEVICE_ATTR(cache_size, ulong, NULL); +NULLB_DEVICE_ATTR(zoned, bool, NULL); +NULLB_DEVICE_ATTR(zone_size, ulong, NULL); +NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL); static ssize_t nullb_device_power_show(struct config_item *item, char *page) { @@ -467,7 +493,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item) static ssize_t memb_group_features_show(struct config_item *item, char *page) { - return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n"); + return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n"); } CONFIGFS_ATTR_RO(memb_group_, features); @@ -996,6 +1022,16 @@ next: return 0; } +static void nullb_fill_pattern(struct nullb *nullb, struct page *page, + unsigned int len, unsigned int off) +{ + void *dst; + + dst = kmap_atomic(page); + memset(dst + off, 0xFF, len); + kunmap_atomic(dst); +} + static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n) { size_t temp; @@ -1036,10 +1072,24 @@ static int null_transfer(struct nullb *nullb, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector, bool is_fua) { + struct nullb_device *dev = nullb->dev; + unsigned int valid_len = len; int err = 0; if (!is_write) { - err = copy_from_nullb(nullb, page, off, sector, len); + if (dev->zoned) + valid_len = null_zone_valid_read_len(nullb, + sector, len); + + if (valid_len) { + err = copy_from_nullb(nullb, page, off, + sector, valid_len); + off += valid_len; + len -= valid_len; + } + + if (len) + nullb_fill_pattern(nullb, page, len, off); flush_dcache_page(page); } else { flush_dcache_page(page); @@ -1418,20 +1468,9 @@ static void null_config_discard(struct nullb *nullb) blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q); } -static int null_open(struct block_device *bdev, fmode_t mode) -{ - return 0; -} - -static void null_release(struct gendisk *disk, fmode_t mode) -{ -} - -static const struct block_device_operations null_fops = { - .owner = THIS_MODULE, - .open = null_open, - .release = null_release, - .report_zones = null_zone_report, +static const struct block_device_operations null_ops = { + .owner = THIS_MODULE, + .report_zones = null_report_zones, }; static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) @@ -1532,7 +1571,7 @@ static int null_gendisk_register(struct nullb *nullb) disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO; disk->major = null_major; disk->first_minor = nullb->index; - disk->fops = &null_fops; + disk->fops = &null_ops; disk->private_data = nullb; disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 3d7fdea872f8..d4d88b581822 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -66,22 +66,53 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +int null_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data) { struct nullb *nullb = disk->private_data; struct nullb_device *dev = nullb->dev; - unsigned int zno, nrz = 0; - - zno = null_zone_no(dev, sector); - if (zno < dev->nr_zones) { - nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno); - memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone)); + unsigned int first_zone, i; + struct blk_zone zone; + int error; + + first_zone = null_zone_no(dev, sector); + if (first_zone >= dev->nr_zones) + return 0; + + nr_zones = min(nr_zones, dev->nr_zones - first_zone); + for (i = 0; i < nr_zones; i++) { + /* + * Stacked DM target drivers will remap the zone information by + * modifying the zone information passed to the report callback. + * So use a local copy to avoid corruption of the device zone + * array. + */ + memcpy(&zone, &dev->zones[first_zone + i], + sizeof(struct blk_zone)); + error = cb(&zone, i, data); + if (error) + return error; } - *nr_zones = nrz; + return nr_zones; +} - return 0; +size_t null_zone_valid_read_len(struct nullb *nullb, + sector_t sector, unsigned int len) +{ + struct nullb_device *dev = nullb->dev; + struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)]; + unsigned int nr_sectors = len >> SECTOR_SHIFT; + + /* Read must be below the write pointer position */ + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL || + sector + nr_sectors <= zone->wp) + return len; + + if (sector > zone->wp) + return 0; + + return (zone->wp - sector) << SECTOR_SHIFT; } static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, @@ -118,14 +149,14 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, return BLK_STS_OK; } -static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector) +static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, + sector_t sector) { struct nullb_device *dev = cmd->nq->dev; - unsigned int zno = null_zone_no(dev, sector); - struct blk_zone *zone = &dev->zones[zno]; + struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)]; size_t i; - switch (req_op(cmd->rq)) { + switch (op) { case REQ_OP_ZONE_RESET_ALL: for (i = 0; i < dev->nr_zones; i++) { if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL) @@ -141,6 +172,29 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector) zone->cond = BLK_ZONE_COND_EMPTY; zone->wp = zone->start; break; + case REQ_OP_ZONE_OPEN: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + if (zone->cond == BLK_ZONE_COND_FULL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_EXP_OPEN; + break; + case REQ_OP_ZONE_CLOSE: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + if (zone->cond == BLK_ZONE_COND_FULL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_CLOSED; + break; + case REQ_OP_ZONE_FINISH: + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return BLK_STS_IOERR; + + zone->cond = BLK_ZONE_COND_FULL; + zone->wp = zone->start + zone->len; + break; default: return BLK_STS_NOTSUPP; } @@ -155,7 +209,10 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, return null_zone_write(cmd, sector, nr_sectors); case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: - return null_zone_reset(cmd, sector); + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return null_zone_mgmt(cmd, op, sector); default: return BLK_STS_OK; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 39136675dae5..13527a0b4e44 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2087,7 +2087,7 @@ static int rbd_object_map_update_finish(struct rbd_obj_request *obj_req, struct rbd_device *rbd_dev = obj_req->img_request->rbd_dev; struct ceph_osd_data *osd_data; u64 objno; - u8 state, new_state, current_state; + u8 state, new_state, uninitialized_var(current_state); bool has_current_state; void *p; diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index 76b73ddf8fd7..10f6368117d8 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -1000,8 +1000,10 @@ static void rsxx_pci_remove(struct pci_dev *dev) cancel_work_sync(&card->event_work); + destroy_workqueue(card->event_wq); rsxx_destroy_dev(card); rsxx_dma_destroy(card); + destroy_workqueue(card->creg_ctrl.creg_wq); spin_lock_irqsave(&card->irq_lock, flags); rsxx_disable_ier_and_isr(card, CR_INTR_ALL); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index ad50efb470aa..2b6670daf7fc 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -74,6 +74,7 @@ static const char * const clock_names[SYSC_MAX_CLOCKS] = { * @clk_disable_quirk: module specific clock disable quirk * @reset_done_quirk: module specific reset done quirk * @module_enable_quirk: module specific enable quirk + * @module_disable_quirk: module specific disable quirk */ struct sysc { struct device *dev; @@ -100,6 +101,7 @@ struct sysc { void (*clk_disable_quirk)(struct sysc *sysc); void (*reset_done_quirk)(struct sysc *sysc); void (*module_enable_quirk)(struct sysc *sysc); + void (*module_disable_quirk)(struct sysc *sysc); }; static void sysc_parse_dts_quirks(struct sysc *ddata, struct device_node *np, @@ -959,6 +961,9 @@ static int sysc_disable_module(struct device *dev) if (ddata->offsets[SYSC_SYSCONFIG] == -ENODEV) return 0; + if (ddata->module_disable_quirk) + ddata->module_disable_quirk(ddata); + regbits = ddata->cap->regbits; reg = sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]); @@ -1248,6 +1253,9 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_MODULE_QUIRK_SGX), SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0, SYSC_MODULE_QUIRK_WDT), + /* Watchdog on am3 and am4 */ + SYSC_QUIRK("wdt", 0x44e35000, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0, + SYSC_MODULE_QUIRK_WDT | SYSC_QUIRK_SWSUP_SIDLE), #ifdef DEBUG SYSC_QUIRK("adc", 0, 0, 0x10, -1, 0x47300001, 0xffffffff, 0), @@ -1440,14 +1448,14 @@ static void sysc_reset_done_quirk_wdt(struct sysc *ddata) !(val & 0x10), 100, MAX_MODULE_SOFTRESET_WAIT); if (error) - dev_warn(ddata->dev, "wdt disable spr failed\n"); + dev_warn(ddata->dev, "wdt disable step1 failed\n"); - sysc_write(ddata, wps, 0x5555); + sysc_write(ddata, spr, 0x5555); error = readl_poll_timeout(ddata->module_va + wps, val, !(val & 0x10), 100, MAX_MODULE_SOFTRESET_WAIT); if (error) - dev_warn(ddata->dev, "wdt disable wps failed\n"); + dev_warn(ddata->dev, "wdt disable step2 failed\n"); } static void sysc_init_module_quirks(struct sysc *ddata) @@ -1471,8 +1479,10 @@ static void sysc_init_module_quirks(struct sysc *ddata) if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_SGX) ddata->module_enable_quirk = sysc_module_enable_quirk_sgx; - if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_WDT) + if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_WDT) { ddata->reset_done_quirk = sysc_reset_done_quirk_wdt; + ddata->module_disable_quirk = sysc_reset_done_quirk_wdt; + } } static int sysc_clockdomain_init(struct sysc *ddata) diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 80b850ef1bf6..8d53b8ef545c 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -13,7 +13,6 @@ #include <linux/delay.h> #include <linux/device.h> #include <linux/err.h> -#include <linux/freezer.h> #include <linux/fs.h> #include <linux/hw_random.h> #include <linux/kernel.h> @@ -422,9 +421,7 @@ static int hwrng_fillfn(void *unused) { long rc; - set_freezable(); - - while (!kthread_freezable_should_stop(NULL)) { + while (!kthread_should_stop()) { struct hwrng *rng; rng = get_current_rng(); diff --git a/drivers/char/random.c b/drivers/char/random.c index de434feb873a..01b8868b9bed 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -327,7 +327,6 @@ #include <linux/percpu.h> #include <linux/cryptohash.h> #include <linux/fips.h> -#include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/workqueue.h> #include <linux/irq.h> @@ -2500,8 +2499,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count, * We'll be woken up again once below random_write_wakeup_thresh, * or when the calling thread is about to terminate. */ - wait_event_freezable(random_write_wait, - kthread_should_stop() || + wait_event_interruptible(random_write_wait, kthread_should_stop() || ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits); mix_pool_bytes(poolp, buffer, count); credit_entropy_bits(poolp, entropy); diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index 9c37047f4b56..aacdeed93320 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -67,6 +67,13 @@ config TCG_TIS_SPI within Linux. To compile this driver as a module, choose M here; the module will be called tpm_tis_spi. +config TCG_TIS_SPI_CR50 + bool "Cr50 SPI Interface" + depends on TCG_TIS_SPI + help + If you have a H1 secure module running Cr50 firmware on SPI bus, + say Yes and it will be accessible from within Linux. + config TCG_TIS_I2C_ATMEL tristate "TPM Interface Specification 1.2 Interface (I2C - Atmel)" depends on I2C diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile index c354cdff9c62..5a0d99d4fec0 100644 --- a/drivers/char/tpm/Makefile +++ b/drivers/char/tpm/Makefile @@ -21,7 +21,9 @@ tpm-$(CONFIG_EFI) += eventlog/efi.o tpm-$(CONFIG_OF) += eventlog/of.o obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o obj-$(CONFIG_TCG_TIS) += tpm_tis.o -obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o +obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o +tpm_tis_spi_mod-y := tpm_tis_spi.o +tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index d7a3888ad80f..a438b1206fcb 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/spinlock.h> +#include <linux/suspend.h> #include <linux/freezer.h> #include <linux/tpm_eventlog.h> @@ -394,7 +395,11 @@ int tpm_pm_suspend(struct device *dev) return -ENODEV; if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED) - return 0; + goto suspended; + + if ((chip->flags & TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED) && + !pm_suspend_via_firmware()) + goto suspended; if (!tpm_chip_start(chip)) { if (chip->flags & TPM_CHIP_FLAG_TPM2) @@ -405,6 +410,7 @@ int tpm_pm_suspend(struct device *dev) tpm_chip_stop(chip); } +suspended: return rc; } EXPORT_SYMBOL_GPL(tpm_pm_suspend); @@ -453,62 +459,6 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max) } EXPORT_SYMBOL_GPL(tpm_get_random); -/** - * tpm_seal_trusted() - seal a trusted key payload - * @chip: a &struct tpm_chip instance, %NULL for the default chip - * @options: authentication values and other options - * @payload: the key data in clear and encrypted form - * - * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in - * the keyring subsystem. - * - * Return: same as with tpm_transmit_cmd() - */ -int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - int rc; - - chip = tpm_find_get_ops(chip); - if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2)) - return -ENODEV; - - rc = tpm2_seal_trusted(chip, payload, options); - - tpm_put_ops(chip); - return rc; -} -EXPORT_SYMBOL_GPL(tpm_seal_trusted); - -/** - * tpm_unseal_trusted() - unseal a trusted key - * @chip: a &struct tpm_chip instance, %NULL for the default chip - * @options: authentication values and other options - * @payload: the key data in clear and encrypted form - * - * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in - * the keyring subsystem. - * - * Return: same as with tpm_transmit_cmd() - */ -int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - int rc; - - chip = tpm_find_get_ops(chip); - if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2)) - return -ENODEV; - - rc = tpm2_unseal_trusted(chip, payload, options); - - tpm_put_ops(chip); - - return rc; -} -EXPORT_SYMBOL_GPL(tpm_unseal_trusted); - static int __init tpm_init(void) { int rc; diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index edfa89160010..3b53b3e5ec3e 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -217,6 +217,7 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tpm_chip *chip = to_tpm_chip(dev); + struct tpm1_version *version; ssize_t rc = 0; char *str = buf; cap_t cap; @@ -232,31 +233,31 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr, str += sprintf(str, "Manufacturer: 0x%x\n", be32_to_cpu(cap.manufacturer_id)); - /* Try to get a TPM version 1.2 TPM_CAP_VERSION_INFO */ - rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap, + /* TPM 1.2 */ + if (!tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap, "attempting to determine the 1.2 version", - sizeof(cap.tpm_version_1_2)); - if (!rc) { - str += sprintf(str, - "TCG version: %d.%d\nFirmware version: %d.%d\n", - cap.tpm_version_1_2.Major, - cap.tpm_version_1_2.Minor, - cap.tpm_version_1_2.revMajor, - cap.tpm_version_1_2.revMinor); - } else { - /* Otherwise just use TPM_STRUCT_VER */ - if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap, - "attempting to determine the 1.1 version", - sizeof(cap.tpm_version))) - goto out_ops; - str += sprintf(str, - "TCG version: %d.%d\nFirmware version: %d.%d\n", - cap.tpm_version.Major, - cap.tpm_version.Minor, - cap.tpm_version.revMajor, - cap.tpm_version.revMinor); + sizeof(cap.version2))) { + version = &cap.version2.version; + goto out_print; } + + /* TPM 1.1 */ + if (tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap, + "attempting to determine the 1.1 version", + sizeof(cap.version1))) { + goto out_ops; + } + + version = &cap.version1; + +out_print: + str += sprintf(str, + "TCG version: %d.%d\nFirmware version: %d.%d\n", + version->major, version->minor, + version->rev_major, version->rev_minor); + rc = str - buf; + out_ops: tpm_put_ops(chip); return rc; diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index a7fea3e0ca86..b9e1547be6b5 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -25,7 +25,6 @@ #include <linux/platform_device.h> #include <linux/io.h> #include <linux/tpm.h> -#include <linux/highmem.h> #include <linux/tpm_eventlog.h> #ifdef CONFIG_X86 @@ -58,123 +57,6 @@ enum tpm_addr { #define TPM_ERR_DISABLED 0x7 #define TPM_ERR_INVALID_POSTINIT 38 -#define TPM_HEADER_SIZE 10 - -enum tpm2_const { - TPM2_PLATFORM_PCR = 24, - TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), -}; - -enum tpm2_timeouts { - TPM2_TIMEOUT_A = 750, - TPM2_TIMEOUT_B = 2000, - TPM2_TIMEOUT_C = 200, - TPM2_TIMEOUT_D = 30, - TPM2_DURATION_SHORT = 20, - TPM2_DURATION_MEDIUM = 750, - TPM2_DURATION_LONG = 2000, - TPM2_DURATION_LONG_LONG = 300000, - TPM2_DURATION_DEFAULT = 120000, -}; - -enum tpm2_structures { - TPM2_ST_NO_SESSIONS = 0x8001, - TPM2_ST_SESSIONS = 0x8002, -}; - -/* Indicates from what layer of the software stack the error comes from */ -#define TSS2_RC_LAYER_SHIFT 16 -#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) - -enum tpm2_return_codes { - TPM2_RC_SUCCESS = 0x0000, - TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ - TPM2_RC_HANDLE = 0x008B, - TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ - TPM2_RC_FAILURE = 0x0101, - TPM2_RC_DISABLED = 0x0120, - TPM2_RC_COMMAND_CODE = 0x0143, - TPM2_RC_TESTING = 0x090A, /* RC_WARN */ - TPM2_RC_REFERENCE_H0 = 0x0910, - TPM2_RC_RETRY = 0x0922, -}; - -enum tpm2_command_codes { - TPM2_CC_FIRST = 0x011F, - TPM2_CC_HIERARCHY_CONTROL = 0x0121, - TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, - TPM2_CC_CREATE_PRIMARY = 0x0131, - TPM2_CC_SEQUENCE_COMPLETE = 0x013E, - TPM2_CC_SELF_TEST = 0x0143, - TPM2_CC_STARTUP = 0x0144, - TPM2_CC_SHUTDOWN = 0x0145, - TPM2_CC_NV_READ = 0x014E, - TPM2_CC_CREATE = 0x0153, - TPM2_CC_LOAD = 0x0157, - TPM2_CC_SEQUENCE_UPDATE = 0x015C, - TPM2_CC_UNSEAL = 0x015E, - TPM2_CC_CONTEXT_LOAD = 0x0161, - TPM2_CC_CONTEXT_SAVE = 0x0162, - TPM2_CC_FLUSH_CONTEXT = 0x0165, - TPM2_CC_VERIFY_SIGNATURE = 0x0177, - TPM2_CC_GET_CAPABILITY = 0x017A, - TPM2_CC_GET_RANDOM = 0x017B, - TPM2_CC_PCR_READ = 0x017E, - TPM2_CC_PCR_EXTEND = 0x0182, - TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, - TPM2_CC_HASH_SEQUENCE_START = 0x0186, - TPM2_CC_CREATE_LOADED = 0x0191, - TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ -}; - -enum tpm2_permanent_handles { - TPM2_RS_PW = 0x40000009, -}; - -enum tpm2_capabilities { - TPM2_CAP_HANDLES = 1, - TPM2_CAP_COMMANDS = 2, - TPM2_CAP_PCRS = 5, - TPM2_CAP_TPM_PROPERTIES = 6, -}; - -enum tpm2_properties { - TPM_PT_TOTAL_COMMANDS = 0x0129, -}; - -enum tpm2_startup_types { - TPM2_SU_CLEAR = 0x0000, - TPM2_SU_STATE = 0x0001, -}; - -enum tpm2_cc_attrs { - TPM2_CC_ATTR_CHANDLES = 25, - TPM2_CC_ATTR_RHANDLE = 28, -}; - -#define TPM_VID_INTEL 0x8086 -#define TPM_VID_WINBOND 0x1050 -#define TPM_VID_STM 0x104A - -enum tpm_chip_flags { - TPM_CHIP_FLAG_TPM2 = BIT(1), - TPM_CHIP_FLAG_IRQ = BIT(2), - TPM_CHIP_FLAG_VIRTUAL = BIT(3), - TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), - TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), -}; - -#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) - -struct tpm_header { - __be16 tag; - __be32 length; - union { - __be32 ordinal; - __be32 return_code; - }; -} __packed; - #define TPM_TAG_RQU_COMMAND 193 struct stclear_flags_t { @@ -186,19 +68,16 @@ struct stclear_flags_t { u8 bGlobalLock; } __packed; -struct tpm_version_t { - u8 Major; - u8 Minor; - u8 revMajor; - u8 revMinor; +struct tpm1_version { + u8 major; + u8 minor; + u8 rev_major; + u8 rev_minor; } __packed; -struct tpm_version_1_2_t { - __be16 tag; - u8 Major; - u8 Minor; - u8 revMajor; - u8 revMinor; +struct tpm1_version2 { + __be16 tag; + struct tpm1_version version; } __packed; struct timeout_t { @@ -243,8 +122,8 @@ typedef union { struct stclear_flags_t stclear_flags; __u8 owned; __be32 num_pcrs; - struct tpm_version_t tpm_version; - struct tpm_version_1_2_t tpm_version_1_2; + struct tpm1_version version1; + struct tpm1_version2 version2; __be32 manufacturer_id; struct timeout_t timeout; struct duration_t duration; @@ -274,102 +153,6 @@ enum tpm_sub_capabilities { * compiler warnings about stack frame size. */ #define TPM_MAX_RNG_DATA 128 -/* A string buffer type for constructing TPM commands. This is based on the - * ideas of string buffer code in security/keys/trusted.h but is heap based - * in order to keep the stack usage minimal. - */ - -enum tpm_buf_flags { - TPM_BUF_OVERFLOW = BIT(0), -}; - -struct tpm_buf { - struct page *data_page; - unsigned int flags; - u8 *data; -}; - -static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - head->tag = cpu_to_be16(tag); - head->length = cpu_to_be32(sizeof(*head)); - head->ordinal = cpu_to_be32(ordinal); -} - -static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - buf->data_page = alloc_page(GFP_HIGHUSER); - if (!buf->data_page) - return -ENOMEM; - - buf->flags = 0; - buf->data = kmap(buf->data_page); - tpm_buf_reset(buf, tag, ordinal); - return 0; -} - -static inline void tpm_buf_destroy(struct tpm_buf *buf) -{ - kunmap(buf->data_page); - __free_page(buf->data_page); -} - -static inline u32 tpm_buf_length(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be32_to_cpu(head->length); -} - -static inline u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -static inline void tpm_buf_append(struct tpm_buf *buf, - const unsigned char *new_data, - unsigned int new_len) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - u32 len = tpm_buf_length(buf); - - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_OVERFLOW) - return; - - if ((len + new_len) > PAGE_SIZE) { - WARN(1, "tpm_buf: overflow\n"); - buf->flags |= TPM_BUF_OVERFLOW; - return; - } - - memcpy(&buf->data[len], new_data, new_len); - head->length = cpu_to_be32(len + new_len); -} - -static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) -{ - tpm_buf_append(buf, &value, 1); -} - -static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) -{ - __be16 value2 = cpu_to_be16(value); - - tpm_buf_append(buf, (u8 *) &value2, 2); -} - -static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) -{ - __be32 value2 = cpu_to_be32(value); - - tpm_buf_append(buf, (u8 *) &value2, 4); -} - extern struct class *tpm_class; extern struct class *tpmrm_class; extern dev_t tpm_devt; @@ -429,11 +212,6 @@ static inline void tpm_add_ppi(struct tpm_chip *chip) } #endif -static inline u32 tpm2_rc_value(u32 rc) -{ - return (rc & BIT(7)) ? rc & 0xff : rc; -} - int tpm2_get_timeouts(struct tpm_chip *chip); int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest, u16 *digest_size_ptr); @@ -441,12 +219,6 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max); void tpm2_flush_context(struct tpm_chip *chip, u32 handle); -int tpm2_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); -int tpm2_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc); diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index 149e953ca369..ca7158fa6e6c 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -343,6 +343,7 @@ int tpm1_get_timeouts(struct tpm_chip *chip) { cap_t cap; unsigned long timeout_old[4], timeout_chip[4], timeout_eff[4]; + unsigned long durations[3]; ssize_t rc; rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, NULL, @@ -427,6 +428,20 @@ int tpm1_get_timeouts(struct tpm_chip *chip) usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_long)); chip->duration[TPM_LONG_LONG] = 0; /* not used under 1.2 */ + /* + * Provide the ability for vendor overrides of duration values in case + * of misreporting. + */ + if (chip->ops->update_durations) + chip->ops->update_durations(chip, durations); + + if (chip->duration_adjusted) { + dev_info(&chip->dev, HW_ERR "Adjusting reported durations."); + chip->duration[TPM_SHORT] = durations[0]; + chip->duration[TPM_MEDIUM] = durations[1]; + chip->duration[TPM_LONG] = durations[2]; + } + /* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above * value wrong and apparently reports msecs rather than usecs. So we * fix up the resulting too-small TPM_SHORT value to make things work. diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index ba9acae83bff..fdb457704aa7 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -13,20 +13,6 @@ #include "tpm.h" #include <crypto/hash_info.h> -#include <keys/trusted-type.h> - -enum tpm2_object_attributes { - TPM2_OA_USER_WITH_AUTH = BIT(6), -}; - -enum tpm2_session_attributes { - TPM2_SA_CONTINUE_SESSION = BIT(0), -}; - -struct tpm2_hash { - unsigned int crypto_id; - unsigned int tpm_id; -}; static struct tpm2_hash tpm2_hash_map[] = { {HASH_ALGO_SHA1, TPM_ALG_SHA1}, @@ -377,299 +363,6 @@ void tpm2_flush_context(struct tpm_chip *chip, u32 handle) tpm_buf_destroy(&buf); } -/** - * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. - * - * @buf: an allocated tpm_buf instance - * @session_handle: session handle - * @nonce: the session nonce, may be NULL if not used - * @nonce_len: the session nonce length, may be 0 if not used - * @attributes: the session attributes - * @hmac: the session HMAC or password, may be NULL if not used - * @hmac_len: the session HMAC or password length, maybe 0 if not used - */ -static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle, - const u8 *nonce, u16 nonce_len, - u8 attributes, - const u8 *hmac, u16 hmac_len) -{ - tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len); - tpm_buf_append_u32(buf, session_handle); - tpm_buf_append_u16(buf, nonce_len); - - if (nonce && nonce_len) - tpm_buf_append(buf, nonce, nonce_len); - - tpm_buf_append_u8(buf, attributes); - tpm_buf_append_u16(buf, hmac_len); - - if (hmac && hmac_len) - tpm_buf_append(buf, hmac, hmac_len); -} - -/** - * tpm2_seal_trusted() - seal the payload of a trusted key - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * - * Return: < 0 on error and 0 on success. - */ -int tpm2_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - unsigned int blob_len; - struct tpm_buf buf; - u32 hash; - int i; - int rc; - - for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) { - if (options->hash == tpm2_hash_map[i].crypto_id) { - hash = tpm2_hash_map[i].tpm_id; - break; - } - } - - if (i == ARRAY_SIZE(tpm2_hash_map)) - return -EINVAL; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, options->keyhandle); - tpm2_buf_append_auth(&buf, TPM2_RS_PW, - NULL /* nonce */, 0, - 0 /* session_attributes */, - options->keyauth /* hmac */, - TPM_DIGEST_SIZE); - - /* sensitive */ - tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); - - tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); - tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); - tpm_buf_append_u16(&buf, payload->key_len + 1); - tpm_buf_append(&buf, payload->key, payload->key_len); - tpm_buf_append_u8(&buf, payload->migratable); - - /* public */ - tpm_buf_append_u16(&buf, 14 + options->policydigest_len); - tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH); - tpm_buf_append_u16(&buf, hash); - - /* policy */ - if (options->policydigest_len) { - tpm_buf_append_u32(&buf, 0); - tpm_buf_append_u16(&buf, options->policydigest_len); - tpm_buf_append(&buf, options->policydigest, - options->policydigest_len); - } else { - tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH); - tpm_buf_append_u16(&buf, 0); - } - - /* public parameters */ - tpm_buf_append_u16(&buf, TPM_ALG_NULL); - tpm_buf_append_u16(&buf, 0); - - /* outside info */ - tpm_buf_append_u16(&buf, 0); - - /* creation PCR */ - tpm_buf_append_u32(&buf, 0); - - if (buf.flags & TPM_BUF_OVERFLOW) { - rc = -E2BIG; - goto out; - } - - rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data"); - if (rc) - goto out; - - blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]); - if (blob_len > MAX_BLOB_SIZE) { - rc = -E2BIG; - goto out; - } - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) { - rc = -EFAULT; - goto out; - } - - memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len); - payload->blob_len = blob_len; - -out: - tpm_buf_destroy(&buf); - - if (rc > 0) { - if (tpm2_rc_value(rc) == TPM2_RC_HASH) - rc = -EINVAL; - else - rc = -EPERM; - } - - return rc; -} - -/** - * tpm2_load_cmd() - execute a TPM2_Load command - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * @blob_handle: returned blob handle - * - * Return: 0 on success. - * -E2BIG on wrong payload size. - * -EPERM on tpm error status. - * < 0 error from tpm_transmit_cmd. - */ -static int tpm2_load_cmd(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options, - u32 *blob_handle) -{ - struct tpm_buf buf; - unsigned int private_len; - unsigned int public_len; - unsigned int blob_len; - int rc; - - private_len = be16_to_cpup((__be16 *) &payload->blob[0]); - if (private_len > (payload->blob_len - 2)) - return -E2BIG; - - public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]); - blob_len = private_len + public_len + 4; - if (blob_len > payload->blob_len) - return -E2BIG; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, options->keyhandle); - tpm2_buf_append_auth(&buf, TPM2_RS_PW, - NULL /* nonce */, 0, - 0 /* session_attributes */, - options->keyauth /* hmac */, - TPM_DIGEST_SIZE); - - tpm_buf_append(&buf, payload->blob, blob_len); - - if (buf.flags & TPM_BUF_OVERFLOW) { - rc = -E2BIG; - goto out; - } - - rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob"); - if (!rc) - *blob_handle = be32_to_cpup( - (__be32 *) &buf.data[TPM_HEADER_SIZE]); - -out: - tpm_buf_destroy(&buf); - - if (rc > 0) - rc = -EPERM; - - return rc; -} - -/** - * tpm2_unseal_cmd() - execute a TPM2_Unload command - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * @blob_handle: blob handle - * - * Return: 0 on success - * -EPERM on tpm error status - * < 0 error from tpm_transmit_cmd - */ -static int tpm2_unseal_cmd(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options, - u32 blob_handle) -{ - struct tpm_buf buf; - u16 data_len; - u8 *data; - int rc; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, blob_handle); - tpm2_buf_append_auth(&buf, - options->policyhandle ? - options->policyhandle : TPM2_RS_PW, - NULL /* nonce */, 0, - TPM2_SA_CONTINUE_SESSION, - options->blobauth /* hmac */, - TPM_DIGEST_SIZE); - - rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing"); - if (rc > 0) - rc = -EPERM; - - if (!rc) { - data_len = be16_to_cpup( - (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); - if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { - rc = -EFAULT; - goto out; - } - - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) { - rc = -EFAULT; - goto out; - } - data = &buf.data[TPM_HEADER_SIZE + 6]; - - memcpy(payload->key, data, data_len - 1); - payload->key_len = data_len - 1; - payload->migratable = data[data_len - 1]; - } - -out: - tpm_buf_destroy(&buf); - return rc; -} - -/** - * tpm2_unseal_trusted() - unseal the payload of a trusted key - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * - * Return: Same as with tpm_transmit_cmd. - */ -int tpm2_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - u32 blob_handle; - int rc; - - rc = tpm2_load_cmd(chip, payload, options, &blob_handle); - if (rc) - return rc; - - rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); - tpm2_flush_context(chip, blob_handle); - return rc; -} - struct tpm2_get_cap_out { u8 more_data; __be32 subcap_id; @@ -939,6 +632,10 @@ static int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) chip->cc_attrs_tbl = devm_kcalloc(&chip->dev, 4, nr_commands, GFP_KERNEL); + if (!chip->cc_attrs_tbl) { + rc = -ENOMEM; + goto out; + } rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY); if (rc) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index e59f1f91d7f3..a9dcf31eadd2 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -22,6 +22,7 @@ #include "tpm.h" #define ACPI_SIG_TPM2 "TPM2" +#define TPM_CRB_MAX_RESOURCES 3 static const guid_t crb_acpi_start_guid = GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714, @@ -91,7 +92,6 @@ enum crb_status { struct crb_priv { u32 sm; const char *hid; - void __iomem *iobase; struct crb_regs_head __iomem *regs_h; struct crb_regs_tail __iomem *regs_t; u8 __iomem *cmd; @@ -434,21 +434,27 @@ static const struct tpm_class_ops tpm_crb = { static int crb_check_resource(struct acpi_resource *ares, void *data) { - struct resource *io_res = data; + struct resource *iores_array = data; struct resource_win win; struct resource *res = &(win.res); + int i; if (acpi_dev_resource_memory(ares, res) || acpi_dev_resource_address_space(ares, &win)) { - *io_res = *res; - io_res->name = NULL; + for (i = 0; i < TPM_CRB_MAX_RESOURCES + 1; ++i) { + if (resource_type(iores_array + i) != IORESOURCE_MEM) { + iores_array[i] = *res; + iores_array[i].name = NULL; + break; + } + } } return 1; } -static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, - struct resource *io_res, u64 start, u32 size) +static void __iomem *crb_map_res(struct device *dev, struct resource *iores, + void __iomem **iobase_ptr, u64 start, u32 size) { struct resource new_res = { .start = start, @@ -460,10 +466,16 @@ static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, if (start != new_res.start) return (void __iomem *) ERR_PTR(-EINVAL); - if (!resource_contains(io_res, &new_res)) + if (!iores) return devm_ioremap_resource(dev, &new_res); - return priv->iobase + (new_res.start - io_res->start); + if (!*iobase_ptr) { + *iobase_ptr = devm_ioremap_resource(dev, iores); + if (IS_ERR(*iobase_ptr)) + return *iobase_ptr; + } + + return *iobase_ptr + (new_res.start - iores->start); } /* @@ -490,9 +502,13 @@ static u64 crb_fixup_cmd_size(struct device *dev, struct resource *io_res, static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, struct acpi_table_tpm2 *buf) { - struct list_head resources; - struct resource io_res; + struct list_head acpi_resource_list; + struct resource iores_array[TPM_CRB_MAX_RESOURCES + 1] = { {0} }; + void __iomem *iobase_array[TPM_CRB_MAX_RESOURCES] = {NULL}; struct device *dev = &device->dev; + struct resource *iores; + void __iomem **iobase_ptr; + int i; u32 pa_high, pa_low; u64 cmd_pa; u32 cmd_size; @@ -501,21 +517,41 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, u32 rsp_size; int ret; - INIT_LIST_HEAD(&resources); - ret = acpi_dev_get_resources(device, &resources, crb_check_resource, - &io_res); + INIT_LIST_HEAD(&acpi_resource_list); + ret = acpi_dev_get_resources(device, &acpi_resource_list, + crb_check_resource, iores_array); if (ret < 0) return ret; - acpi_dev_free_resource_list(&resources); + acpi_dev_free_resource_list(&acpi_resource_list); - if (resource_type(&io_res) != IORESOURCE_MEM) { + if (resource_type(iores_array) != IORESOURCE_MEM) { dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n"); return -EINVAL; + } else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) == + IORESOURCE_MEM) { + dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n"); + memset(iores_array + TPM_CRB_MAX_RESOURCES, + 0, sizeof(*iores_array)); + iores_array[TPM_CRB_MAX_RESOURCES].flags = 0; } - priv->iobase = devm_ioremap_resource(dev, &io_res); - if (IS_ERR(priv->iobase)) - return PTR_ERR(priv->iobase); + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (buf->control_address >= iores_array[i].start && + buf->control_address + sizeof(struct crb_regs_tail) - 1 <= + iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + priv->regs_t = crb_map_res(dev, iores, iobase_ptr, buf->control_address, + sizeof(struct crb_regs_tail)); + + if (IS_ERR(priv->regs_t)) + return PTR_ERR(priv->regs_t); /* The ACPI IO region starts at the head area and continues to include * the control area, as one nice sane region except for some older @@ -523,9 +559,10 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, */ if ((priv->sm == ACPI_TPM2_COMMAND_BUFFER) || (priv->sm == ACPI_TPM2_MEMORY_MAPPED)) { - if (buf->control_address == io_res.start + + if (iores && + buf->control_address == iores->start + sizeof(*priv->regs_h)) - priv->regs_h = priv->iobase; + priv->regs_h = *iobase_ptr; else dev_warn(dev, FW_BUG "Bad ACPI memory layout"); } @@ -534,13 +571,6 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, if (ret) return ret; - priv->regs_t = crb_map_res(dev, priv, &io_res, buf->control_address, - sizeof(struct crb_regs_tail)); - if (IS_ERR(priv->regs_t)) { - ret = PTR_ERR(priv->regs_t); - goto out_relinquish_locality; - } - /* * PTT HW bug w/a: wake up the device to access * possibly not retained registers. @@ -552,13 +582,26 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, pa_high = ioread32(&priv->regs_t->ctrl_cmd_pa_high); pa_low = ioread32(&priv->regs_t->ctrl_cmd_pa_low); cmd_pa = ((u64)pa_high << 32) | pa_low; - cmd_size = crb_fixup_cmd_size(dev, &io_res, cmd_pa, - ioread32(&priv->regs_t->ctrl_cmd_size)); + cmd_size = ioread32(&priv->regs_t->ctrl_cmd_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; iores_array[i].end; ++i) { + if (cmd_pa >= iores_array[i].start && + cmd_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + cmd_size = crb_fixup_cmd_size(dev, iores, cmd_pa, cmd_size); dev_dbg(dev, "cmd_hi = %X cmd_low = %X cmd_size %X\n", pa_high, pa_low, cmd_size); - priv->cmd = crb_map_res(dev, priv, &io_res, cmd_pa, cmd_size); + priv->cmd = crb_map_res(dev, iores, iobase_ptr, cmd_pa, cmd_size); if (IS_ERR(priv->cmd)) { ret = PTR_ERR(priv->cmd); goto out; @@ -566,11 +609,25 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, memcpy_fromio(&__rsp_pa, &priv->regs_t->ctrl_rsp_pa, 8); rsp_pa = le64_to_cpu(__rsp_pa); - rsp_size = crb_fixup_cmd_size(dev, &io_res, rsp_pa, - ioread32(&priv->regs_t->ctrl_rsp_size)); + rsp_size = ioread32(&priv->regs_t->ctrl_rsp_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (rsp_pa >= iores_array[i].start && + rsp_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + rsp_size = crb_fixup_cmd_size(dev, iores, rsp_pa, rsp_size); if (cmd_pa != rsp_pa) { - priv->rsp = crb_map_res(dev, priv, &io_res, rsp_pa, rsp_size); + priv->rsp = crb_map_res(dev, iores, iobase_ptr, + rsp_pa, rsp_size); ret = PTR_ERR_OR_ZERO(priv->rsp); goto out; } diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index e4fdde93ed4c..e7df342a317d 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -286,7 +286,7 @@ static int tpm_tis_plat_probe(struct platform_device *pdev) } tpm_info.res = *res; - tpm_info.irq = platform_get_irq(pdev, 0); + tpm_info.irq = platform_get_irq_optional(pdev, 0); if (tpm_info.irq <= 0) { if (pdev != force_pdev) tpm_info.irq = -1; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 270f43acbb77..8af2cee1a762 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -506,6 +506,84 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) return rc; } +struct tis_vendor_durations_override { + u32 did_vid; + struct tpm1_version version; + unsigned long durations[3]; +}; + +static const struct tis_vendor_durations_override vendor_dur_overrides[] = { + /* STMicroelectronics 0x104a */ + { 0x0000104a, + { 1, 2, 8, 28 }, + { (2 * 60 * HZ), (2 * 60 * HZ), (2 * 60 * HZ) } }, +}; + +static void tpm_tis_update_durations(struct tpm_chip *chip, + unsigned long *duration_cap) +{ + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); + struct tpm1_version *version; + u32 did_vid; + int i, rc; + cap_t cap; + + chip->duration_adjusted = false; + + if (chip->ops->clk_enable != NULL) + chip->ops->clk_enable(chip, true); + + rc = tpm_tis_read32(priv, TPM_DID_VID(0), &did_vid); + if (rc < 0) { + dev_warn(&chip->dev, "%s: failed to read did_vid. %d\n", + __func__, rc); + goto out; + } + + /* Try to get a TPM version 1.2 or 1.1 TPM_CAP_VERSION_INFO */ + rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap, + "attempting to determine the 1.2 version", + sizeof(cap.version2)); + if (!rc) { + version = &cap.version2.version; + } else { + rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap, + "attempting to determine the 1.1 version", + sizeof(cap.version1)); + + if (rc) + goto out; + + version = &cap.version1; + } + + for (i = 0; i != ARRAY_SIZE(vendor_dur_overrides); i++) { + if (vendor_dur_overrides[i].did_vid != did_vid) + continue; + + if ((version->major == + vendor_dur_overrides[i].version.major) && + (version->minor == + vendor_dur_overrides[i].version.minor) && + (version->rev_major == + vendor_dur_overrides[i].version.rev_major) && + (version->rev_minor == + vendor_dur_overrides[i].version.rev_minor)) { + + memcpy(duration_cap, + vendor_dur_overrides[i].durations, + sizeof(vendor_dur_overrides[i].durations)); + + chip->duration_adjusted = true; + goto out; + } + } + +out: + if (chip->ops->clk_enable != NULL) + chip->ops->clk_enable(chip, false); +} + struct tis_vendor_timeout_override { u32 did_vid; unsigned long timeout_us[4]; @@ -842,6 +920,7 @@ static const struct tpm_class_ops tpm_tis = { .send = tpm_tis_send, .cancel = tpm_tis_ready, .update_timeouts = tpm_tis_update_timeouts, + .update_durations = tpm_tis_update_durations, .req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_canceled = tpm_tis_req_canceled, diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi.c index 19513e622053..d1754fd6c573 100644 --- a/drivers/char/tpm/tpm_tis_spi.c +++ b/drivers/char/tpm/tpm_tis_spi.c @@ -20,42 +20,64 @@ * Dorn and Kyleen Hall and Jarko Sakkinnen. */ +#include <linux/acpi.h> +#include <linux/completion.h> #include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/slab.h> -#include <linux/interrupt.h> -#include <linux/wait.h> -#include <linux/acpi.h> -#include <linux/freezer.h> +#include <linux/of_device.h> #include <linux/spi/spi.h> -#include <linux/gpio.h> -#include <linux/of_irq.h> -#include <linux/of_gpio.h> #include <linux/tpm.h> + #include "tpm.h" #include "tpm_tis_core.h" +#include "tpm_tis_spi.h" #define MAX_SPI_FRAMESIZE 64 -struct tpm_tis_spi_phy { - struct tpm_tis_data priv; - struct spi_device *spi_device; - u8 *iobuf; -}; - -static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data) +/* + * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short, + * keep trying to read from the device until MISO goes high indicating the + * wait state has ended. + * + * [1] https://trustedcomputinggroup.org/resource/pc-client-platform-tpm-profile-ptp-specification/ + */ +static int tpm_tis_spi_flow_control(struct tpm_tis_spi_phy *phy, + struct spi_transfer *spi_xfer) { - return container_of(data, struct tpm_tis_spi_phy, priv); + struct spi_message m; + int ret, i; + + if ((phy->iobuf[3] & 0x01) == 0) { + // handle SPI wait states + phy->iobuf[0] = 0; + + for (i = 0; i < TPM_RETRY; i++) { + spi_xfer->len = 1; + spi_message_init(&m); + spi_message_add_tail(spi_xfer, &m); + ret = spi_sync_locked(phy->spi_device, &m); + if (ret < 0) + return ret; + if (phy->iobuf[0] & 0x01) + break; + } + + if (i == TPM_RETRY) + return -ETIMEDOUT; + } + + return 0; } -static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, - u8 *in, const u8 *out) +int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, + u8 *in, const u8 *out) { struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); int ret = 0; - int i; struct spi_message m; struct spi_transfer spi_xfer; u8 transfer_len; @@ -82,26 +104,9 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, if (ret < 0) goto exit; - if ((phy->iobuf[3] & 0x01) == 0) { - // handle SPI wait states - phy->iobuf[0] = 0; - - for (i = 0; i < TPM_RETRY; i++) { - spi_xfer.len = 1; - spi_message_init(&m); - spi_message_add_tail(&spi_xfer, &m); - ret = spi_sync_locked(phy->spi_device, &m); - if (ret < 0) - goto exit; - if (phy->iobuf[0] & 0x01) - break; - } - - if (i == TPM_RETRY) { - ret = -ETIMEDOUT; - goto exit; - } - } + ret = phy->flow_control(phy, &spi_xfer); + if (ret < 0) + goto exit; spi_xfer.cs_change = 0; spi_xfer.len = transfer_len; @@ -117,6 +122,7 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, spi_message_init(&m); spi_message_add_tail(&spi_xfer, &m); + reinit_completion(&phy->ready); ret = spi_sync_locked(phy->spi_device, &m); if (ret < 0) goto exit; @@ -146,7 +152,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr, return tpm_tis_spi_transfer(data, addr, len, NULL, value); } -static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result) +int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result) { __le16 result_le; int rc; @@ -159,7 +165,7 @@ static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result) return rc; } -static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result) +int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result) { __le32 result_le; int rc; @@ -172,7 +178,7 @@ static int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result) return rc; } -static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value) +int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value) { __le32 value_le; int rc; @@ -184,6 +190,18 @@ static int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value) return rc; } +int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, + int irq, const struct tpm_tis_phy_ops *phy_ops) +{ + phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); + if (!phy->iobuf) + return -ENOMEM; + + phy->spi_device = spi; + + return tpm_tis_core_init(&spi->dev, &phy->priv, irq, phy_ops, NULL); +} + static const struct tpm_tis_phy_ops tpm_spi_phy_ops = { .read_bytes = tpm_tis_spi_read_bytes, .write_bytes = tpm_tis_spi_write_bytes, @@ -202,11 +220,7 @@ static int tpm_tis_spi_probe(struct spi_device *dev) if (!phy) return -ENOMEM; - phy->spi_device = dev; - - phy->iobuf = devm_kmalloc(&dev->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); - if (!phy->iobuf) - return -ENOMEM; + phy->flow_control = tpm_tis_spi_flow_control; /* If the SPI device has an IRQ then use that */ if (dev->irq > 0) @@ -214,11 +228,27 @@ static int tpm_tis_spi_probe(struct spi_device *dev) else irq = -1; - return tpm_tis_core_init(&dev->dev, &phy->priv, irq, &tpm_spi_phy_ops, - NULL); + init_completion(&phy->ready); + return tpm_tis_spi_init(dev, phy, irq, &tpm_spi_phy_ops); +} + +typedef int (*tpm_tis_spi_probe_func)(struct spi_device *); + +static int tpm_tis_spi_driver_probe(struct spi_device *spi) +{ + const struct spi_device_id *spi_dev_id = spi_get_device_id(spi); + tpm_tis_spi_probe_func probe_func; + + probe_func = of_device_get_match_data(&spi->dev); + if (!probe_func && spi_dev_id) + probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data; + if (!probe_func) + return -ENODEV; + + return probe_func(spi); } -static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume); +static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_spi_resume); static int tpm_tis_spi_remove(struct spi_device *dev) { @@ -230,15 +260,17 @@ static int tpm_tis_spi_remove(struct spi_device *dev) } static const struct spi_device_id tpm_tis_spi_id[] = { - {"tpm_tis_spi", 0}, + { "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe }, + { "cr50", (unsigned long)cr50_spi_probe }, {} }; MODULE_DEVICE_TABLE(spi, tpm_tis_spi_id); static const struct of_device_id of_tis_spi_match[] = { - { .compatible = "st,st33htpm-spi", }, - { .compatible = "infineon,slb9670", }, - { .compatible = "tcg,tpm_tis-spi", }, + { .compatible = "st,st33htpm-spi", .data = tpm_tis_spi_probe }, + { .compatible = "infineon,slb9670", .data = tpm_tis_spi_probe }, + { .compatible = "tcg,tpm_tis-spi", .data = tpm_tis_spi_probe }, + { .compatible = "google,cr50", .data = cr50_spi_probe }, {} }; MODULE_DEVICE_TABLE(of, of_tis_spi_match); @@ -251,13 +283,12 @@ MODULE_DEVICE_TABLE(acpi, acpi_tis_spi_match); static struct spi_driver tpm_tis_spi_driver = { .driver = { - .owner = THIS_MODULE, .name = "tpm_tis_spi", .pm = &tpm_tis_pm, .of_match_table = of_match_ptr(of_tis_spi_match), .acpi_match_table = ACPI_PTR(acpi_tis_spi_match), }, - .probe = tpm_tis_spi_probe, + .probe = tpm_tis_spi_driver_probe, .remove = tpm_tis_spi_remove, .id_table = tpm_tis_spi_id, }; diff --git a/drivers/char/tpm/tpm_tis_spi.h b/drivers/char/tpm/tpm_tis_spi.h new file mode 100644 index 000000000000..bba73979c368 --- /dev/null +++ b/drivers/char/tpm/tpm_tis_spi.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 Infineon Technologies AG + * Copyright (C) 2016 STMicroelectronics SAS + */ + +#ifndef TPM_TIS_SPI_H +#define TPM_TIS_SPI_H + +#include "tpm_tis_core.h" + +struct tpm_tis_spi_phy { + struct tpm_tis_data priv; + struct spi_device *spi_device; + int (*flow_control)(struct tpm_tis_spi_phy *phy, + struct spi_transfer *xfer); + struct completion ready; + unsigned long wake_after; + + u8 *iobuf; +}; + +static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data) +{ + return container_of(data, struct tpm_tis_spi_phy, priv); +} + +extern int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, + int irq, const struct tpm_tis_phy_ops *phy_ops); + +extern int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, + u8 *in, const u8 *out); + +extern int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result); +extern int tpm_tis_spi_read32(struct tpm_tis_data *data, u32 addr, u32 *result); +extern int tpm_tis_spi_write32(struct tpm_tis_data *data, u32 addr, u32 value); + +#ifdef CONFIG_TCG_TIS_SPI_CR50 +extern int cr50_spi_probe(struct spi_device *spi); +#else +static inline int cr50_spi_probe(struct spi_device *spi) +{ + return -ENODEV; +} +#endif + +#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_TCG_TIS_SPI_CR50) +extern int tpm_tis_spi_resume(struct device *dev); +#else +#define tpm_tis_spi_resume NULL +#endif + +#endif diff --git a/drivers/char/tpm/tpm_tis_spi_cr50.c b/drivers/char/tpm/tpm_tis_spi_cr50.c new file mode 100644 index 000000000000..37d72e818335 --- /dev/null +++ b/drivers/char/tpm/tpm_tis_spi_cr50.c @@ -0,0 +1,322 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2016 Google, Inc + * + * This device driver implements a TCG PTP FIFO interface over SPI for chips + * with Cr50 firmware. + * It is based on tpm_tis_spi driver by Peter Huewe and Christophe Ricard. + */ + +#include <linux/completion.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/pm.h> +#include <linux/spi/spi.h> +#include <linux/wait.h> + +#include "tpm_tis_core.h" +#include "tpm_tis_spi.h" + +/* + * Cr50 timing constants: + * - can go to sleep not earlier than after CR50_SLEEP_DELAY_MSEC. + * - needs up to CR50_WAKE_START_DELAY_USEC to wake after sleep. + * - requires waiting for "ready" IRQ, if supported; or waiting for at least + * CR50_NOIRQ_ACCESS_DELAY_MSEC between transactions, if IRQ is not supported. + * - waits for up to CR50_FLOW_CONTROL for flow control 'ready' indication. + */ +#define CR50_SLEEP_DELAY_MSEC 1000 +#define CR50_WAKE_START_DELAY_USEC 1000 +#define CR50_NOIRQ_ACCESS_DELAY msecs_to_jiffies(2) +#define CR50_READY_IRQ_TIMEOUT msecs_to_jiffies(TPM2_TIMEOUT_A) +#define CR50_FLOW_CONTROL msecs_to_jiffies(TPM2_TIMEOUT_A) +#define MAX_IRQ_CONFIRMATION_ATTEMPTS 3 + +#define TPM_CR50_FW_VER(l) (0x0f90 | ((l) << 12)) +#define TPM_CR50_MAX_FW_VER_LEN 64 + +struct cr50_spi_phy { + struct tpm_tis_spi_phy spi_phy; + + struct mutex time_track_mutex; + unsigned long last_access; + + unsigned long access_delay; + + unsigned int irq_confirmation_attempt; + bool irq_needs_confirmation; + bool irq_confirmed; +}; + +static inline struct cr50_spi_phy *to_cr50_spi_phy(struct tpm_tis_spi_phy *phy) +{ + return container_of(phy, struct cr50_spi_phy, spi_phy); +} + +/* + * The cr50 interrupt handler just signals waiting threads that the + * interrupt was asserted. It does not do any processing triggered + * by interrupts but is instead used to avoid fixed delays. + */ +static irqreturn_t cr50_spi_irq_handler(int dummy, void *dev_id) +{ + struct cr50_spi_phy *cr50_phy = dev_id; + + cr50_phy->irq_confirmed = true; + complete(&cr50_phy->spi_phy.ready); + + return IRQ_HANDLED; +} + +/* + * Cr50 needs to have at least some delay between consecutive + * transactions. Make sure we wait. + */ +static void cr50_ensure_access_delay(struct cr50_spi_phy *phy) +{ + unsigned long allowed_access = phy->last_access + phy->access_delay; + unsigned long time_now = jiffies; + struct device *dev = &phy->spi_phy.spi_device->dev; + + /* + * Note: There is a small chance, if Cr50 is not accessed in a few days, + * that time_in_range will not provide the correct result after the wrap + * around for jiffies. In this case, we'll have an unneeded short delay, + * which is fine. + */ + if (time_in_range_open(time_now, phy->last_access, allowed_access)) { + unsigned long remaining, timeout = allowed_access - time_now; + + remaining = wait_for_completion_timeout(&phy->spi_phy.ready, + timeout); + if (!remaining && phy->irq_confirmed) + dev_warn(dev, "Timeout waiting for TPM ready IRQ\n"); + } + + if (phy->irq_needs_confirmation) { + unsigned int attempt = ++phy->irq_confirmation_attempt; + + if (phy->irq_confirmed) { + phy->irq_needs_confirmation = false; + phy->access_delay = CR50_READY_IRQ_TIMEOUT; + dev_info(dev, "TPM ready IRQ confirmed on attempt %u\n", + attempt); + } else if (attempt > MAX_IRQ_CONFIRMATION_ATTEMPTS) { + phy->irq_needs_confirmation = false; + dev_warn(dev, "IRQ not confirmed - will use delays\n"); + } + } +} + +/* + * Cr50 might go to sleep if there is no SPI activity for some time and + * miss the first few bits/bytes on the bus. In such case, wake it up + * by asserting CS and give it time to start up. + */ +static bool cr50_needs_waking(struct cr50_spi_phy *phy) +{ + /* + * Note: There is a small chance, if Cr50 is not accessed in a few days, + * that time_in_range will not provide the correct result after the wrap + * around for jiffies. In this case, we'll probably timeout or read + * incorrect value from TPM_STS and just retry the operation. + */ + return !time_in_range_open(jiffies, phy->last_access, + phy->spi_phy.wake_after); +} + +static void cr50_wake_if_needed(struct cr50_spi_phy *cr50_phy) +{ + struct tpm_tis_spi_phy *phy = &cr50_phy->spi_phy; + + if (cr50_needs_waking(cr50_phy)) { + /* Assert CS, wait 1 msec, deassert CS */ + struct spi_transfer spi_cs_wake = { .delay_usecs = 1000 }; + + spi_sync_transfer(phy->spi_device, &spi_cs_wake, 1); + /* Wait for it to fully wake */ + usleep_range(CR50_WAKE_START_DELAY_USEC, + CR50_WAKE_START_DELAY_USEC * 2); + } + + /* Reset the time when we need to wake Cr50 again */ + phy->wake_after = jiffies + msecs_to_jiffies(CR50_SLEEP_DELAY_MSEC); +} + +/* + * Flow control: clock the bus and wait for cr50 to set LSB before + * sending/receiving data. TCG PTP spec allows it to happen during + * the last byte of header, but cr50 never does that in practice, + * and earlier versions had a bug when it was set too early, so don't + * check for it during header transfer. + */ +static int cr50_spi_flow_control(struct tpm_tis_spi_phy *phy, + struct spi_transfer *spi_xfer) +{ + struct device *dev = &phy->spi_device->dev; + unsigned long timeout = jiffies + CR50_FLOW_CONTROL; + struct spi_message m; + int ret; + + spi_xfer->len = 1; + + do { + spi_message_init(&m); + spi_message_add_tail(spi_xfer, &m); + ret = spi_sync_locked(phy->spi_device, &m); + if (ret < 0) + return ret; + + if (time_after(jiffies, timeout)) { + dev_warn(dev, "Timeout during flow control\n"); + return -EBUSY; + } + } while (!(phy->iobuf[0] & 0x01)); + + return 0; +} + +static int tpm_tis_spi_cr50_transfer(struct tpm_tis_data *data, u32 addr, u16 len, + u8 *in, const u8 *out) +{ + struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); + struct cr50_spi_phy *cr50_phy = to_cr50_spi_phy(phy); + int ret; + + mutex_lock(&cr50_phy->time_track_mutex); + /* + * Do this outside of spi_bus_lock in case cr50 is not the + * only device on that spi bus. + */ + cr50_ensure_access_delay(cr50_phy); + cr50_wake_if_needed(cr50_phy); + + ret = tpm_tis_spi_transfer(data, addr, len, in, out); + + cr50_phy->last_access = jiffies; + mutex_unlock(&cr50_phy->time_track_mutex); + + return ret; +} + +static int tpm_tis_spi_cr50_read_bytes(struct tpm_tis_data *data, u32 addr, + u16 len, u8 *result) +{ + return tpm_tis_spi_cr50_transfer(data, addr, len, result, NULL); +} + +static int tpm_tis_spi_cr50_write_bytes(struct tpm_tis_data *data, u32 addr, + u16 len, const u8 *value) +{ + return tpm_tis_spi_cr50_transfer(data, addr, len, NULL, value); +} + +static const struct tpm_tis_phy_ops tpm_spi_cr50_phy_ops = { + .read_bytes = tpm_tis_spi_cr50_read_bytes, + .write_bytes = tpm_tis_spi_cr50_write_bytes, + .read16 = tpm_tis_spi_read16, + .read32 = tpm_tis_spi_read32, + .write32 = tpm_tis_spi_write32, +}; + +static void cr50_print_fw_version(struct tpm_tis_data *data) +{ + struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); + int i, len = 0; + char fw_ver[TPM_CR50_MAX_FW_VER_LEN + 1]; + char fw_ver_block[4]; + + /* + * Write anything to TPM_CR50_FW_VER to start from the beginning + * of the version string + */ + tpm_tis_write8(data, TPM_CR50_FW_VER(data->locality), 0); + + /* Read the string, 4 bytes at a time, until we get '\0' */ + do { + tpm_tis_read_bytes(data, TPM_CR50_FW_VER(data->locality), 4, + fw_ver_block); + for (i = 0; i < 4 && fw_ver_block[i]; ++len, ++i) + fw_ver[len] = fw_ver_block[i]; + } while (i == 4 && len < TPM_CR50_MAX_FW_VER_LEN); + fw_ver[len] = '\0'; + + dev_info(&phy->spi_device->dev, "Cr50 firmware version: %s\n", fw_ver); +} + +int cr50_spi_probe(struct spi_device *spi) +{ + struct tpm_tis_spi_phy *phy; + struct cr50_spi_phy *cr50_phy; + int ret; + struct tpm_chip *chip; + + cr50_phy = devm_kzalloc(&spi->dev, sizeof(*cr50_phy), GFP_KERNEL); + if (!cr50_phy) + return -ENOMEM; + + phy = &cr50_phy->spi_phy; + phy->flow_control = cr50_spi_flow_control; + phy->wake_after = jiffies; + init_completion(&phy->ready); + + cr50_phy->access_delay = CR50_NOIRQ_ACCESS_DELAY; + cr50_phy->last_access = jiffies; + mutex_init(&cr50_phy->time_track_mutex); + + if (spi->irq > 0) { + ret = devm_request_irq(&spi->dev, spi->irq, + cr50_spi_irq_handler, + IRQF_TRIGGER_RISING | IRQF_ONESHOT, + "cr50_spi", cr50_phy); + if (ret < 0) { + if (ret == -EPROBE_DEFER) + return ret; + dev_warn(&spi->dev, "Requesting IRQ %d failed: %d\n", + spi->irq, ret); + /* + * This is not fatal, the driver will fall back to + * delays automatically, since ready will never + * be completed without a registered irq handler. + * So, just fall through. + */ + } else { + /* + * IRQ requested, let's verify that it is actually + * triggered, before relying on it. + */ + cr50_phy->irq_needs_confirmation = true; + } + } else { + dev_warn(&spi->dev, + "No IRQ - will use delays between transactions.\n"); + } + + ret = tpm_tis_spi_init(spi, phy, -1, &tpm_spi_cr50_phy_ops); + if (ret) + return ret; + + cr50_print_fw_version(&phy->priv); + + chip = dev_get_drvdata(&spi->dev); + chip->flags |= TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED; + + return 0; +} + +#ifdef CONFIG_PM_SLEEP +int tpm_tis_spi_resume(struct device *dev) +{ + struct tpm_chip *chip = dev_get_drvdata(dev); + struct tpm_tis_data *data = dev_get_drvdata(&chip->dev); + struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data); + /* + * Jiffies not increased during suspend, so we need to reset + * the time to wake Cr50 after resume. + */ + phy->wake_after = jiffies; + + return tpm_tis_resume(dev); +} +#endif diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 7270e7b69262..3259426f01dc 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1325,24 +1325,24 @@ static void set_console_size(struct port *port, u16 rows, u16 cols) port->cons.ws.ws_col = cols; } -static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock) +static int fill_queue(struct virtqueue *vq, spinlock_t *lock) { struct port_buffer *buf; - unsigned int nr_added_bufs; + int nr_added_bufs; int ret; nr_added_bufs = 0; do { buf = alloc_buf(vq->vdev, PAGE_SIZE, 0); if (!buf) - break; + return -ENOMEM; spin_lock_irq(lock); ret = add_inbuf(vq, buf); if (ret < 0) { spin_unlock_irq(lock); free_buf(buf, true); - break; + return ret; } nr_added_bufs++; spin_unlock_irq(lock); @@ -1362,7 +1362,6 @@ static int add_port(struct ports_device *portdev, u32 id) char debugfs_name[16]; struct port *port; dev_t devt; - unsigned int nr_added_bufs; int err; port = kmalloc(sizeof(*port), GFP_KERNEL); @@ -1421,11 +1420,13 @@ static int add_port(struct ports_device *portdev, u32 id) spin_lock_init(&port->outvq_lock); init_waitqueue_head(&port->waitqueue); - /* Fill the in_vq with buffers so the host can send us data. */ - nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock); - if (!nr_added_bufs) { + /* We can safely ignore ENOSPC because it means + * the queue already has buffers. Buffers are removed + * only by virtcons_remove(), not by unplug_port() + */ + err = fill_queue(port->in_vq, &port->inbuf_lock); + if (err < 0 && err != -ENOSPC) { dev_err(port->dev, "Error allocating inbufs\n"); - err = -ENOMEM; goto free_device; } @@ -2059,14 +2060,11 @@ static int virtcons_probe(struct virtio_device *vdev) INIT_WORK(&portdev->control_work, &control_work_handler); if (multiport) { - unsigned int nr_added_bufs; - spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); - nr_added_bufs = fill_queue(portdev->c_ivq, - &portdev->c_ivq_lock); - if (!nr_added_bufs) { + err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); + if (err < 0) { dev_err(&vdev->dev, "Error allocating buffers for control queue\n"); /* @@ -2077,7 +2075,7 @@ static int virtcons_probe(struct virtio_device *vdev) VIRTIO_CONSOLE_DEVICE_READY, 0); /* Device was functional: we need full cleanup. */ virtcons_remove(vdev); - return -ENOMEM; + return err; } } else { /* diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c index 87083b3a2769..37c22667e831 100644 --- a/drivers/clk/at91/clk-main.c +++ b/drivers/clk/at91/clk-main.c @@ -297,7 +297,10 @@ static int clk_main_probe_frequency(struct regmap *regmap) regmap_read(regmap, AT91_CKGR_MCFR, &mcfr); if (mcfr & AT91_PMC_MAINRDY) return 0; - usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT); + if (system_state < SYSTEM_RUNNING) + udelay(MAINF_LOOP_MIN_WAIT); + else + usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT); } while (time_before(prep_time, timeout)); return -ETIMEDOUT; diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c index 9790ddfa5b3c..86238d5ecb4d 100644 --- a/drivers/clk/at91/sam9x60.c +++ b/drivers/clk/at91/sam9x60.c @@ -43,6 +43,7 @@ static const struct clk_pll_characteristics upll_characteristics = { }; static const struct clk_programmable_layout sam9x60_programmable_layout = { + .pres_mask = 0xff, .pres_shift = 8, .css_mask = 0x1f, .have_slck_mck = 0, diff --git a/drivers/clk/at91/sckc.c b/drivers/clk/at91/sckc.c index 9bfe9a28294a..fac0ca56d42d 100644 --- a/drivers/clk/at91/sckc.c +++ b/drivers/clk/at91/sckc.c @@ -76,7 +76,10 @@ static int clk_slow_osc_prepare(struct clk_hw *hw) writel(tmp | osc->bits->cr_osc32en, sckcr); - usleep_range(osc->startup_usec, osc->startup_usec + 1); + if (system_state < SYSTEM_RUNNING) + udelay(osc->startup_usec); + else + usleep_range(osc->startup_usec, osc->startup_usec + 1); return 0; } @@ -187,7 +190,10 @@ static int clk_slow_rc_osc_prepare(struct clk_hw *hw) writel(readl(sckcr) | osc->bits->cr_rcen, sckcr); - usleep_range(osc->startup_usec, osc->startup_usec + 1); + if (system_state < SYSTEM_RUNNING) + udelay(osc->startup_usec); + else + usleep_range(osc->startup_usec, osc->startup_usec + 1); return 0; } @@ -288,7 +294,10 @@ static int clk_sam9x5_slow_set_parent(struct clk_hw *hw, u8 index) writel(tmp, sckcr); - usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1); + if (system_state < SYSTEM_RUNNING) + udelay(SLOWCK_SW_TIME_USEC); + else + usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1); return 0; } @@ -533,7 +542,10 @@ static int clk_sama5d4_slow_osc_prepare(struct clk_hw *hw) return 0; } - usleep_range(osc->startup_usec, osc->startup_usec + 1); + if (system_state < SYSTEM_RUNNING) + udelay(osc->startup_usec); + else + usleep_range(osc->startup_usec, osc->startup_usec + 1); osc->prepared = true; return 0; diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c index 1c1bb39bb04e..b1318e6b655b 100644 --- a/drivers/clk/clk-ast2600.c +++ b/drivers/clk/clk-ast2600.c @@ -266,10 +266,11 @@ static int aspeed_g6_clk_enable(struct clk_hw *hw) /* Enable clock */ if (gate->flags & CLK_GATE_SET_TO_DISABLE) { - regmap_write(gate->map, get_clock_reg(gate), clk); - } else { - /* Use set to clear register */ + /* Clock is clear to enable, so use set to clear register */ regmap_write(gate->map, get_clock_reg(gate) + 0x04, clk); + } else { + /* Clock is set to enable, so use write to set register */ + regmap_write(gate->map, get_clock_reg(gate), clk); } if (gate->reset_idx >= 0) { diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c index 067ab876911d..172589e94f60 100644 --- a/drivers/clk/imx/clk-imx8mm.c +++ b/drivers/clk/imx/clk-imx8mm.c @@ -638,7 +638,7 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) clks[IMX8MM_CLK_A53_DIV], clks[IMX8MM_CLK_A53_SRC], clks[IMX8MM_ARM_PLL_OUT], - clks[IMX8MM_CLK_24M]); + clks[IMX8MM_SYS_PLL1_800M]); imx_check_clocks(clks, ARRAY_SIZE(clks)); diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index 47a4b44ba3cb..58b5acee3830 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -610,7 +610,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) clks[IMX8MN_CLK_A53_DIV], clks[IMX8MN_CLK_A53_SRC], clks[IMX8MN_ARM_PLL_OUT], - clks[IMX8MN_CLK_24M]); + clks[IMX8MN_SYS_PLL1_800M]); imx_check_clocks(clks, ARRAY_SIZE(clks)); diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c index ea4c791f106d..b3af61cc6fb9 100644 --- a/drivers/clk/meson/g12a.c +++ b/drivers/clk/meson/g12a.c @@ -343,6 +343,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x3, .shift = 0, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk_dyn0_sel", @@ -353,8 +354,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = { { .hw = &g12a_fclk_div3.hw }, }, .num_parents = 3, - /* This sub-tree is used a parking clock */ - .flags = CLK_SET_RATE_NO_REPARENT, + .flags = CLK_SET_RATE_PARENT, }, }; @@ -410,6 +410,7 @@ static struct clk_regmap g12a_cpu_clk_postmux0 = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 2, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk_dyn0", @@ -466,6 +467,7 @@ static struct clk_regmap g12a_cpu_clk_dyn = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 10, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk_dyn", @@ -485,6 +487,7 @@ static struct clk_regmap g12a_cpu_clk = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 11, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk", @@ -504,6 +507,7 @@ static struct clk_regmap g12b_cpu_clk = { .offset = HHI_SYS_CPU_CLK_CNTL0, .mask = 0x1, .shift = 11, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpu_clk", @@ -523,6 +527,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x3, .shift = 0, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk_dyn0_sel", @@ -533,6 +538,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = { { .hw = &g12a_fclk_div3.hw }, }, .num_parents = 3, + .flags = CLK_SET_RATE_PARENT, }, }; @@ -567,6 +573,7 @@ static struct clk_regmap g12b_cpub_clk_postmux0 = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x1, .shift = 2, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk_dyn0", @@ -644,6 +651,7 @@ static struct clk_regmap g12b_cpub_clk_dyn = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x1, .shift = 10, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk_dyn", @@ -663,6 +671,7 @@ static struct clk_regmap g12b_cpub_clk = { .offset = HHI_SYS_CPUB_CLK_CNTL, .mask = 0x1, .shift = 11, + .flags = CLK_MUX_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "cpub_clk", diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 7cfb998eeb3e..1f9c056e684c 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -935,6 +935,7 @@ static struct clk_regmap gxbb_sar_adc_clk_div = { &gxbb_sar_adc_clk_sel.hw }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, }, }; diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c index 7670cc596c74..31466cd1842f 100644 --- a/drivers/clk/samsung/clk-exynos5420.c +++ b/drivers/clk/samsung/clk-exynos5420.c @@ -165,12 +165,18 @@ static const unsigned long exynos5x_clk_regs[] __initconst = { GATE_BUS_CPU, GATE_SCLK_CPU, CLKOUT_CMU_CPU, + CPLL_CON0, + DPLL_CON0, EPLL_CON0, EPLL_CON1, EPLL_CON2, RPLL_CON0, RPLL_CON1, RPLL_CON2, + IPLL_CON0, + SPLL_CON0, + VPLL_CON0, + MPLL_CON0, SRC_TOP0, SRC_TOP1, SRC_TOP2, @@ -1172,8 +1178,6 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = { GATE(CLK_SCLK_ISP_SENSOR2, "sclk_isp_sensor2", "dout_isp_sensor2", GATE_TOP_SCLK_ISP, 12, CLK_SET_RATE_PARENT, 0), - GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0), - /* CDREX */ GATE(CLK_CLKM_PHY0, "clkm_phy0", "dout_sclk_cdrex", GATE_BUS_CDREX0, 0, 0, 0), @@ -1248,6 +1252,15 @@ static struct exynos5_subcmu_reg_dump exynos5x_gsc_suspend_regs[] = { { DIV2_RATIO0, 0, 0x30 }, /* DIV dout_gscl_blk_300 */ }; +static const struct samsung_gate_clock exynos5x_g3d_gate_clks[] __initconst = { + GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0), +}; + +static struct exynos5_subcmu_reg_dump exynos5x_g3d_suspend_regs[] = { + { GATE_IP_G3D, 0x3ff, 0x3ff }, /* G3D gates */ + { SRC_TOP5, 0, BIT(16) }, /* MUX mout_user_aclk_g3d */ +}; + static const struct samsung_div_clock exynos5x_mfc_div_clks[] __initconst = { DIV(0, "dout_mfc_blk", "mout_user_aclk333", DIV4_RATIO, 0, 2), }; @@ -1320,6 +1333,14 @@ static const struct exynos5_subcmu_info exynos5x_gsc_subcmu = { .pd_name = "GSC", }; +static const struct exynos5_subcmu_info exynos5x_g3d_subcmu = { + .gate_clks = exynos5x_g3d_gate_clks, + .nr_gate_clks = ARRAY_SIZE(exynos5x_g3d_gate_clks), + .suspend_regs = exynos5x_g3d_suspend_regs, + .nr_suspend_regs = ARRAY_SIZE(exynos5x_g3d_suspend_regs), + .pd_name = "G3D", +}; + static const struct exynos5_subcmu_info exynos5x_mfc_subcmu = { .div_clks = exynos5x_mfc_div_clks, .nr_div_clks = ARRAY_SIZE(exynos5x_mfc_div_clks), @@ -1351,6 +1372,7 @@ static const struct exynos5_subcmu_info exynos5800_mau_subcmu = { static const struct exynos5_subcmu_info *exynos5x_subcmus[] = { &exynos5x_disp_subcmu, &exynos5x_gsc_subcmu, + &exynos5x_g3d_subcmu, &exynos5x_mfc_subcmu, &exynos5x_mscl_subcmu, }; @@ -1358,6 +1380,7 @@ static const struct exynos5_subcmu_info *exynos5x_subcmus[] = { static const struct exynos5_subcmu_info *exynos5800_subcmus[] = { &exynos5x_disp_subcmu, &exynos5x_gsc_subcmu, + &exynos5x_g3d_subcmu, &exynos5x_mfc_subcmu, &exynos5x_mscl_subcmu, &exynos5800_mau_subcmu, diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c index 7824c2ba3d8e..4b1aa9382ad2 100644 --- a/drivers/clk/samsung/clk-exynos5433.c +++ b/drivers/clk/samsung/clk-exynos5433.c @@ -13,6 +13,7 @@ #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/slab.h> #include <dt-bindings/clock/exynos5433.h> @@ -5584,6 +5585,8 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev) data->clk_save = samsung_clk_alloc_reg_dump(info->clk_regs, info->nr_clk_regs); + if (!data->clk_save) + return -ENOMEM; data->nr_clk_save = info->nr_clk_regs; data->clk_suspend = info->suspend_regs; data->nr_clk_suspend = info->nr_suspend_regs; @@ -5592,12 +5595,19 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev) if (data->nr_pclks > 0) { data->pclks = devm_kcalloc(dev, sizeof(struct clk *), data->nr_pclks, GFP_KERNEL); - + if (!data->pclks) { + kfree(data->clk_save); + return -ENOMEM; + } for (i = 0; i < data->nr_pclks; i++) { struct clk *clk = of_clk_get(dev->of_node, i); - if (IS_ERR(clk)) + if (IS_ERR(clk)) { + kfree(data->clk_save); + while (--i >= 0) + clk_put(data->pclks[i]); return PTR_ERR(clk); + } data->pclks[i] = clk; } } diff --git a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c index dcac1391767f..ef29582676f6 100644 --- a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c +++ b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c @@ -1224,7 +1224,7 @@ static int sun9i_a80_ccu_probe(struct platform_device *pdev) /* Enforce d1 = 0, d2 = 0 for Audio PLL */ val = readl(reg + SUN9I_A80_PLL_AUDIO_REG); - val &= (BIT(16) & BIT(18)); + val &= ~(BIT(16) | BIT(18)); writel(val, reg + SUN9I_A80_PLL_AUDIO_REG); /* Enforce P = 1 for both CPU cluster PLLs */ diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c index d3a43381a792..27201fd26e44 100644 --- a/drivers/clk/sunxi/clk-sunxi.c +++ b/drivers/clk/sunxi/clk-sunxi.c @@ -1080,8 +1080,8 @@ static struct clk ** __init sunxi_divs_clk_setup(struct device_node *node, rate_hw, rate_ops, gate_hw, &clk_gate_ops, clkflags | - data->div[i].critical ? - CLK_IS_CRITICAL : 0); + (data->div[i].critical ? + CLK_IS_CRITICAL : 0)); WARN_ON(IS_ERR(clk_data->clks[i])); } diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c index a01ca9395179..f65e16c4f3c4 100644 --- a/drivers/clk/ti/clk-dra7-atl.c +++ b/drivers/clk/ti/clk-dra7-atl.c @@ -174,7 +174,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node) struct clk_init_data init = { NULL }; const char **parent_names = NULL; struct clk *clk; - int ret; clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL); if (!clk_hw) { @@ -207,11 +206,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node) clk = ti_clk_register(NULL, &clk_hw->hw, node->name); if (!IS_ERR(clk)) { - ret = ti_clk_add_alias(NULL, clk, node->name); - if (ret) { - clk_unregister(clk); - goto cleanup; - } of_clk_add_provider(node, of_clk_src_simple_get, clk); kfree(parent_names); return; diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index 975995eea15c..b0c0690a5a12 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -100,11 +100,12 @@ static bool _omap4_is_timeout(union omap4_timeout *time, u32 timeout) * can be from a timer that requires pm_runtime access, which * will eventually bring us here with timekeeping_suspended, * during both suspend entry and resume paths. This happens - * at least on am43xx platform. + * at least on am43xx platform. Account for flakeyness + * with udelay() by multiplying the timeout value by 2. */ if (unlikely(_early_timeout || timekeeping_suspended)) { if (time->cycles++ < timeout) { - udelay(1); + udelay(1 * 2); return false; } } else { diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index 354b27d14a19..62812f80b5cc 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -328,12 +328,13 @@ static int sh_mtu2_register(struct sh_mtu2_channel *ch, const char *name) return 0; } +static const unsigned int sh_mtu2_channel_offsets[] = { + 0x300, 0x380, 0x000, +}; + static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index, struct sh_mtu2_device *mtu) { - static const unsigned int channel_offsets[] = { - 0x300, 0x380, 0x000, - }; char name[6]; int irq; int ret; @@ -356,7 +357,7 @@ static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index, return ret; } - ch->base = mtu->mapbase + channel_offsets[index]; + ch->base = mtu->mapbase + sh_mtu2_channel_offsets[index]; ch->index = index; return sh_mtu2_register(ch, dev_name(&mtu->pdev->dev)); @@ -408,7 +409,12 @@ static int sh_mtu2_setup(struct sh_mtu2_device *mtu, } /* Allocate and setup the channels. */ - mtu->num_channels = 3; + ret = platform_irq_count(pdev); + if (ret < 0) + goto err_unmap; + + mtu->num_channels = min_t(unsigned int, ret, + ARRAY_SIZE(sh_mtu2_channel_offsets)); mtu->channels = kcalloc(mtu->num_channels, sizeof(*mtu->channels), GFP_KERNEL); diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c index a562f491b0f8..9318edcd8963 100644 --- a/drivers/clocksource/timer-mediatek.c +++ b/drivers/clocksource/timer-mediatek.c @@ -268,15 +268,12 @@ static int __init mtk_syst_init(struct device_node *node) ret = timer_of_init(node, &to); if (ret) - goto err; + return ret; clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), TIMER_SYNC_TICKS, 0xffffffff); return 0; -err: - timer_of_cleanup(&to); - return ret; } static int __init mtk_gpt_init(struct device_node *node) @@ -293,7 +290,7 @@ static int __init mtk_gpt_init(struct device_node *node) ret = timer_of_init(node, &to); if (ret) - goto err; + return ret; /* Configure clock source */ mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN); @@ -311,9 +308,6 @@ static int __init mtk_gpt_init(struct device_node *node) mtk_gpt_enable_irq(&to, TIMER_CLK_EVT); return 0; -err: - timer_of_cleanup(&to); - return ret; } TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init); TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index bffc11b87247..48a224a6b178 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -720,7 +720,7 @@ static ssize_t store_##file_name \ if (ret != 1) \ return -EINVAL; \ \ - ret = dev_pm_qos_update_request(policy->object##_freq_req, val);\ + ret = freq_qos_update_request(policy->object##_freq_req, val);\ return ret >= 0 ? count : ret; \ } @@ -1202,19 +1202,21 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) goto err_free_real_cpus; } + freq_constraints_init(&policy->constraints); + policy->nb_min.notifier_call = cpufreq_notifier_min; policy->nb_max.notifier_call = cpufreq_notifier_max; - ret = dev_pm_qos_add_notifier(dev, &policy->nb_min, - DEV_PM_QOS_MIN_FREQUENCY); + ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MIN, + &policy->nb_min); if (ret) { dev_err(dev, "Failed to register MIN QoS notifier: %d (%*pbl)\n", ret, cpumask_pr_args(policy->cpus)); goto err_kobj_remove; } - ret = dev_pm_qos_add_notifier(dev, &policy->nb_max, - DEV_PM_QOS_MAX_FREQUENCY); + ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MAX, + &policy->nb_max); if (ret) { dev_err(dev, "Failed to register MAX QoS notifier: %d (%*pbl)\n", ret, cpumask_pr_args(policy->cpus)); @@ -1232,8 +1234,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) return policy; err_min_qos_notifier: - dev_pm_qos_remove_notifier(dev, &policy->nb_min, - DEV_PM_QOS_MIN_FREQUENCY); + freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN, + &policy->nb_min); err_kobj_remove: cpufreq_policy_put_kobj(policy); err_free_real_cpus: @@ -1250,7 +1252,6 @@ err_free_policy: static void cpufreq_policy_free(struct cpufreq_policy *policy) { - struct device *dev = get_cpu_device(policy->cpu); unsigned long flags; int cpu; @@ -1262,10 +1263,13 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) per_cpu(cpufreq_cpu_data, cpu) = NULL; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - dev_pm_qos_remove_notifier(dev, &policy->nb_max, - DEV_PM_QOS_MAX_FREQUENCY); - dev_pm_qos_remove_notifier(dev, &policy->nb_min, - DEV_PM_QOS_MIN_FREQUENCY); + freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MAX, + &policy->nb_max); + freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN, + &policy->nb_min); + + /* Cancel any pending policy->update work before freeing the policy. */ + cancel_work_sync(&policy->update); if (policy->max_freq_req) { /* @@ -1274,10 +1278,10 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) */ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_REMOVE_POLICY, policy); - dev_pm_qos_remove_request(policy->max_freq_req); + freq_qos_remove_request(policy->max_freq_req); } - dev_pm_qos_remove_request(policy->min_freq_req); + freq_qos_remove_request(policy->min_freq_req); kfree(policy->min_freq_req); cpufreq_policy_put_kobj(policy); @@ -1357,8 +1361,6 @@ static int cpufreq_online(unsigned int cpu) cpumask_and(policy->cpus, policy->cpus, cpu_online_mask); if (new_policy) { - struct device *dev = get_cpu_device(cpu); - for_each_cpu(j, policy->related_cpus) { per_cpu(cpufreq_cpu_data, j) = policy; add_cpu_dev_symlink(policy, j); @@ -1369,36 +1371,31 @@ static int cpufreq_online(unsigned int cpu) if (!policy->min_freq_req) goto out_destroy_policy; - ret = dev_pm_qos_add_request(dev, policy->min_freq_req, - DEV_PM_QOS_MIN_FREQUENCY, - policy->min); + ret = freq_qos_add_request(&policy->constraints, + policy->min_freq_req, FREQ_QOS_MIN, + policy->min); if (ret < 0) { /* - * So we don't call dev_pm_qos_remove_request() for an + * So we don't call freq_qos_remove_request() for an * uninitialized request. */ kfree(policy->min_freq_req); policy->min_freq_req = NULL; - - dev_err(dev, "Failed to add min-freq constraint (%d)\n", - ret); goto out_destroy_policy; } /* * This must be initialized right here to avoid calling - * dev_pm_qos_remove_request() on uninitialized request in case + * freq_qos_remove_request() on uninitialized request in case * of errors. */ policy->max_freq_req = policy->min_freq_req + 1; - ret = dev_pm_qos_add_request(dev, policy->max_freq_req, - DEV_PM_QOS_MAX_FREQUENCY, - policy->max); + ret = freq_qos_add_request(&policy->constraints, + policy->max_freq_req, FREQ_QOS_MAX, + policy->max); if (ret < 0) { policy->max_freq_req = NULL; - dev_err(dev, "Failed to add max-freq constraint (%d)\n", - ret); goto out_destroy_policy; } @@ -2374,7 +2371,6 @@ int cpufreq_set_policy(struct cpufreq_policy *policy, struct cpufreq_policy *new_policy) { struct cpufreq_governor *old_gov; - struct device *cpu_dev = get_cpu_device(policy->cpu); int ret; pr_debug("setting new policy for CPU %u: %u - %u kHz\n", @@ -2386,8 +2382,8 @@ int cpufreq_set_policy(struct cpufreq_policy *policy, * PM QoS framework collects all the requests from users and provide us * the final aggregated value here. */ - new_policy->min = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MIN_FREQUENCY); - new_policy->max = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MAX_FREQUENCY); + new_policy->min = freq_qos_read_value(&policy->constraints, FREQ_QOS_MIN); + new_policy->max = freq_qos_read_value(&policy->constraints, FREQ_QOS_MAX); /* verify the cpu speed can be set within this limit */ ret = cpufreq_driver->verify(new_policy); @@ -2518,7 +2514,7 @@ static int cpufreq_boost_set_sw(int state) break; } - ret = dev_pm_qos_update_request(policy->max_freq_req, policy->max); + ret = freq_qos_update_request(policy->max_freq_req, policy->max); if (ret < 0) break; } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 9f02de9a1b47..8ab31702cf6a 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -847,11 +847,9 @@ static void intel_pstate_hwp_force_min_perf(int cpu) value |= HWP_MAX_PERF(min_perf); value |= HWP_MIN_PERF(min_perf); - /* Set EPP/EPB to min */ + /* Set EPP to min */ if (boot_cpu_has(X86_FEATURE_HWP_EPP)) value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE); - else - intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE); wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } @@ -1088,10 +1086,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, static struct cpufreq_driver intel_pstate; -static void update_qos_request(enum dev_pm_qos_req_type type) +static void update_qos_request(enum freq_qos_req_type type) { int max_state, turbo_max, freq, i, perf_pct; - struct dev_pm_qos_request *req; + struct freq_qos_request *req; struct cpufreq_policy *policy; for_each_possible_cpu(i) { @@ -1112,7 +1110,7 @@ static void update_qos_request(enum dev_pm_qos_req_type type) else turbo_max = cpu->pstate.turbo_pstate; - if (type == DEV_PM_QOS_MIN_FREQUENCY) { + if (type == FREQ_QOS_MIN) { perf_pct = global.min_perf_pct; } else { req++; @@ -1122,7 +1120,7 @@ static void update_qos_request(enum dev_pm_qos_req_type type) freq = DIV_ROUND_UP(turbo_max * perf_pct, 100); freq *= cpu->pstate.scaling; - if (dev_pm_qos_update_request(req, freq) < 0) + if (freq_qos_update_request(req, freq) < 0) pr_warn("Failed to update freq constraint: CPU%d\n", i); } } @@ -1153,7 +1151,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b, if (intel_pstate_driver == &intel_pstate) intel_pstate_update_policies(); else - update_qos_request(DEV_PM_QOS_MAX_FREQUENCY); + update_qos_request(FREQ_QOS_MAX); mutex_unlock(&intel_pstate_driver_lock); @@ -1187,7 +1185,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b, if (intel_pstate_driver == &intel_pstate) intel_pstate_update_policies(); else - update_qos_request(DEV_PM_QOS_MIN_FREQUENCY); + update_qos_request(FREQ_QOS_MIN); mutex_unlock(&intel_pstate_driver_lock); @@ -2381,7 +2379,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) { int max_state, turbo_max, min_freq, max_freq, ret; - struct dev_pm_qos_request *req; + struct freq_qos_request *req; struct cpudata *cpu; struct device *dev; @@ -2416,15 +2414,15 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) max_freq = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100); max_freq *= cpu->pstate.scaling; - ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_MIN_FREQUENCY, - min_freq); + ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MIN, + min_freq); if (ret < 0) { dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret); goto free_req; } - ret = dev_pm_qos_add_request(dev, req + 1, DEV_PM_QOS_MAX_FREQUENCY, - max_freq); + ret = freq_qos_add_request(&policy->constraints, req + 1, FREQ_QOS_MAX, + max_freq); if (ret < 0) { dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret); goto remove_min_req; @@ -2435,7 +2433,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) return 0; remove_min_req: - dev_pm_qos_remove_request(req); + freq_qos_remove_request(req); free_req: kfree(req); pstate_exit: @@ -2446,12 +2444,12 @@ pstate_exit: static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy) { - struct dev_pm_qos_request *req; + struct freq_qos_request *req; req = policy->driver_data; - dev_pm_qos_remove_request(req + 1); - dev_pm_qos_remove_request(req); + freq_qos_remove_request(req + 1); + freq_qos_remove_request(req); kfree(req); return intel_pstate_cpu_exit(policy); diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c index bc9dd30395c4..037fe23bc6ed 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c @@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(cbe_cpufreq_set_pmode_pmi); static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg) { struct cpufreq_policy *policy; - struct dev_pm_qos_request *req; + struct freq_qos_request *req; u8 node, slow_mode; int cpu, ret; @@ -86,7 +86,7 @@ static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg) req = policy->driver_data; - ret = dev_pm_qos_update_request(req, + ret = freq_qos_update_request(req, policy->freq_table[slow_mode].frequency); if (ret < 0) pr_warn("Failed to update freq constraint: %d\n", ret); @@ -103,7 +103,7 @@ static struct pmi_handler cbe_pmi_handler = { void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy) { - struct dev_pm_qos_request *req; + struct freq_qos_request *req; int ret; if (!cbe_cpufreq_has_pmi) @@ -113,9 +113,8 @@ void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy) if (!req) return; - ret = dev_pm_qos_add_request(get_cpu_device(policy->cpu), req, - DEV_PM_QOS_MAX_FREQUENCY, - policy->freq_table[0].frequency); + ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MAX, + policy->freq_table[0].frequency); if (ret < 0) { pr_err("Failed to add freq constraint (%d)\n", ret); kfree(req); @@ -128,10 +127,10 @@ EXPORT_SYMBOL_GPL(cbe_cpufreq_pmi_policy_init); void cbe_cpufreq_pmi_policy_exit(struct cpufreq_policy *policy) { - struct dev_pm_qos_request *req = policy->driver_data; + struct freq_qos_request *req = policy->driver_data; if (cbe_cpufreq_has_pmi) { - dev_pm_qos_remove_request(req); + freq_qos_remove_request(req); kfree(req); } } diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c index 932390b028f1..b0ce9bc78113 100644 --- a/drivers/cpuidle/cpuidle-haltpoll.c +++ b/drivers/cpuidle/cpuidle-haltpoll.c @@ -95,6 +95,10 @@ static int __init haltpoll_init(void) int ret; struct cpuidle_driver *drv = &haltpoll_driver; + /* Do not load haltpoll if idle= is passed */ + if (boot_option_idle_override != IDLE_NO_OVERRIDE) + return -ENODEV; + cpuidle_poll_state_init(drv); if (!kvm_para_available() || diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c index 774d991d7cca..aca75237bbcf 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/crypto/chelsio/chtls/chtls_cm.c @@ -1297,7 +1297,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) tp->write_seq = snd_isn; tp->snd_nxt = snd_isn; tp->snd_una = snd_isn; - inet_sk(sk)->inet_id = tp->write_seq ^ jiffies; + inet_sk(sk)->inet_id = prandom_u32(); assign_rxopt(sk, opt); if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index 0891ab829b1b..98bc5a4cd5e7 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -1702,7 +1702,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return peekmsg(sk, msg, len, nonblock, flags); if (sk_can_busy_loop(sk) && - skb_queue_empty(&sk->sk_receive_queue) && + skb_queue_empty_lockless(&sk->sk_receive_queue) && sk->sk_state == TCP_ESTABLISHED) sk_busy_loop(sk, nonblock); diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 9ba74ab7e912..c27e206a764c 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1707,6 +1707,14 @@ static void sdma_add_scripts(struct sdma_engine *sdma, if (!sdma->script_number) sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1; + if (sdma->script_number > sizeof(struct sdma_script_start_addrs) + / sizeof(s32)) { + dev_err(sdma->dev, + "SDMA script number %d not match with firmware.\n", + sdma->script_number); + return; + } + for (i = 0; i < sdma->script_number; i++) if (addr_arr[i] > 0) saddr_arr[i] = addr_arr[i]; diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index 8e90a405939d..ef73f65224b1 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -694,6 +694,25 @@ static int bam_dma_terminate_all(struct dma_chan *chan) /* remove all transactions, including active transaction */ spin_lock_irqsave(&bchan->vc.lock, flag); + /* + * If we have transactions queued, then some might be committed to the + * hardware in the desc fifo. The only way to reset the desc fifo is + * to do a hardware reset (either by pipe or the entire block). + * bam_chan_init_hw() will trigger a pipe reset, and also reinit the + * pipe. If the pipe is left disabled (default state after pipe reset) + * and is accessed by a connected hardware engine, a fatal error in + * the BAM will occur. There is a small window where this could happen + * with bam_chan_init_hw(), but it is assumed that the caller has + * stopped activity on any attached hardware engine. Make sure to do + * this first so that the BAM hardware doesn't cause memory corruption + * by accessing freed resources. + */ + if (!list_empty(&bchan->desc_list)) { + async_desc = list_first_entry(&bchan->desc_list, + struct bam_async_desc, desc_node); + bam_chan_init_hw(bchan, async_desc->dir); + } + list_for_each_entry_safe(async_desc, tmp, &bchan->desc_list, desc_node) { list_add(&async_desc->vd.node, &bchan->vc.desc_issued); diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c index 525dc7338fe3..8546ad034720 100644 --- a/drivers/dma/sprd-dma.c +++ b/drivers/dma/sprd-dma.c @@ -134,6 +134,10 @@ #define SPRD_DMA_SRC_TRSF_STEP_OFFSET 0 #define SPRD_DMA_TRSF_STEP_MASK GENMASK(15, 0) +/* SPRD DMA_SRC_BLK_STEP register definition */ +#define SPRD_DMA_LLIST_HIGH_MASK GENMASK(31, 28) +#define SPRD_DMA_LLIST_HIGH_SHIFT 28 + /* define DMA channel mode & trigger mode mask */ #define SPRD_DMA_CHN_MODE_MASK GENMASK(7, 0) #define SPRD_DMA_TRG_MODE_MASK GENMASK(7, 0) @@ -208,6 +212,7 @@ struct sprd_dma_dev { struct sprd_dma_chn channels[0]; }; +static void sprd_dma_free_desc(struct virt_dma_desc *vd); static bool sprd_dma_filter_fn(struct dma_chan *chan, void *param); static struct of_dma_filter_info sprd_dma_info = { .filter_fn = sprd_dma_filter_fn, @@ -609,12 +614,19 @@ static int sprd_dma_alloc_chan_resources(struct dma_chan *chan) static void sprd_dma_free_chan_resources(struct dma_chan *chan) { struct sprd_dma_chn *schan = to_sprd_dma_chan(chan); + struct virt_dma_desc *cur_vd = NULL; unsigned long flags; spin_lock_irqsave(&schan->vc.lock, flags); + if (schan->cur_desc) + cur_vd = &schan->cur_desc->vd; + sprd_dma_stop(schan); spin_unlock_irqrestore(&schan->vc.lock, flags); + if (cur_vd) + sprd_dma_free_desc(cur_vd); + vchan_free_chan_resources(&schan->vc); pm_runtime_put(chan->device->dev); } @@ -717,6 +729,7 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, u32 int_mode = flags & SPRD_DMA_INT_MASK; int src_datawidth, dst_datawidth, src_step, dst_step; u32 temp, fix_mode = 0, fix_en = 0; + phys_addr_t llist_ptr; if (dir == DMA_MEM_TO_DEV) { src_step = sprd_dma_get_step(slave_cfg->src_addr_width); @@ -814,13 +827,16 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, * Set the link-list pointer point to next link-list * configuration's physical address. */ - hw->llist_ptr = schan->linklist.phy_addr + temp; + llist_ptr = schan->linklist.phy_addr + temp; + hw->llist_ptr = lower_32_bits(llist_ptr); + hw->src_blk_step = (upper_32_bits(llist_ptr) << SPRD_DMA_LLIST_HIGH_SHIFT) & + SPRD_DMA_LLIST_HIGH_MASK; } else { hw->llist_ptr = 0; + hw->src_blk_step = 0; } hw->frg_step = 0; - hw->src_blk_step = 0; hw->des_blk_step = 0; return 0; } @@ -1023,15 +1039,22 @@ static int sprd_dma_resume(struct dma_chan *chan) static int sprd_dma_terminate_all(struct dma_chan *chan) { struct sprd_dma_chn *schan = to_sprd_dma_chan(chan); + struct virt_dma_desc *cur_vd = NULL; unsigned long flags; LIST_HEAD(head); spin_lock_irqsave(&schan->vc.lock, flags); + if (schan->cur_desc) + cur_vd = &schan->cur_desc->vd; + sprd_dma_stop(schan); vchan_get_all_descriptors(&schan->vc, &head); spin_unlock_irqrestore(&schan->vc.lock, flags); + if (cur_vd) + sprd_dma_free_desc(cur_vd); + vchan_dma_desc_free_list(&schan->vc, &head); return 0; } diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index 5f8adf5c1f20..6e1268552f74 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -40,6 +40,7 @@ #define ADMA_CH_CONFIG_MAX_BURST_SIZE 16 #define ADMA_CH_CONFIG_WEIGHT_FOR_WRR(val) ((val) & 0xf) #define ADMA_CH_CONFIG_MAX_BUFS 8 +#define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs) (reqs << 4) #define ADMA_CH_FIFO_CTRL 0x2c #define TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(val) (((val) & 0xf) << 8) @@ -77,6 +78,7 @@ struct tegra_adma; * @ch_req_tx_shift: Register offset for AHUB transmit channel select. * @ch_req_rx_shift: Register offset for AHUB receive channel select. * @ch_base_offset: Register offset of DMA channel registers. + * @has_outstanding_reqs: If DMA channel can have outstanding requests. * @ch_fifo_ctrl: Default value for channel FIFO CTRL register. * @ch_req_mask: Mask for Tx or Rx channel select. * @ch_req_max: Maximum number of Tx or Rx channels available. @@ -95,6 +97,7 @@ struct tegra_adma_chip_data { unsigned int ch_req_max; unsigned int ch_reg_size; unsigned int nr_channels; + bool has_outstanding_reqs; }; /* @@ -594,6 +597,8 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc, ADMA_CH_CTRL_FLOWCTRL_EN; ch_regs->config |= cdata->adma_get_burst_config(burst_size); ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1); + if (cdata->has_outstanding_reqs) + ch_regs->config |= TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8); ch_regs->fifo_ctrl = cdata->ch_fifo_ctrl; ch_regs->tc = desc->period_len & ADMA_CH_TC_COUNT_MASK; @@ -778,6 +783,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = { .ch_req_tx_shift = 28, .ch_req_rx_shift = 24, .ch_base_offset = 0, + .has_outstanding_reqs = false, .ch_fifo_ctrl = TEGRA210_FIFO_CTRL_DEFAULT, .ch_req_mask = 0xf, .ch_req_max = 10, @@ -792,6 +798,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = { .ch_req_tx_shift = 27, .ch_req_rx_shift = 22, .ch_base_offset = 0x10000, + .has_outstanding_reqs = true, .ch_fifo_ctrl = TEGRA186_FIFO_CTRL_DEFAULT, .ch_req_mask = 0x1f, .ch_req_max = 20, diff --git a/drivers/dma/ti/cppi41.c b/drivers/dma/ti/cppi41.c index 2f946f55076c..8c2f7ebe998c 100644 --- a/drivers/dma/ti/cppi41.c +++ b/drivers/dma/ti/cppi41.c @@ -586,9 +586,22 @@ static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg( enum dma_transfer_direction dir, unsigned long tx_flags, void *context) { struct cppi41_channel *c = to_cpp41_chan(chan); + struct dma_async_tx_descriptor *txd = NULL; + struct cppi41_dd *cdd = c->cdd; struct cppi41_desc *d; struct scatterlist *sg; unsigned int i; + int error; + + error = pm_runtime_get(cdd->ddev.dev); + if (error < 0) { + pm_runtime_put_noidle(cdd->ddev.dev); + + return NULL; + } + + if (cdd->is_suspended) + goto err_out_not_ready; d = c->desc; for_each_sg(sgl, sg, sg_len, i) { @@ -611,7 +624,13 @@ static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg( d++; } - return &c->txd; + txd = &c->txd; + +err_out_not_ready: + pm_runtime_mark_last_busy(cdd->ddev.dev); + pm_runtime_put_autosuspend(cdd->ddev.dev); + + return txd; } static void cppi41_compute_td_desc(struct cppi41_desc *d) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index e7dc3c4dc8e0..5d56f1e4d332 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -68,6 +68,9 @@ #define XILINX_DMA_DMACR_CIRC_EN BIT(1) #define XILINX_DMA_DMACR_RUNSTOP BIT(0) #define XILINX_DMA_DMACR_FSYNCSRC_MASK GENMASK(6, 5) +#define XILINX_DMA_DMACR_DELAY_MASK GENMASK(31, 24) +#define XILINX_DMA_DMACR_FRAME_COUNT_MASK GENMASK(23, 16) +#define XILINX_DMA_DMACR_MASTER_MASK GENMASK(11, 8) #define XILINX_DMA_REG_DMASR 0x0004 #define XILINX_DMA_DMASR_EOL_LATE_ERR BIT(15) @@ -1354,7 +1357,8 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan) node); hw = &segment->hw; - xilinx_write(chan, XILINX_DMA_REG_SRCDSTADDR, hw->buf_addr); + xilinx_write(chan, XILINX_DMA_REG_SRCDSTADDR, + xilinx_prep_dma_addr_t(hw->buf_addr)); /* Start the transfer */ dma_ctrl_write(chan, XILINX_DMA_REG_BTT, @@ -2117,8 +2121,10 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan, chan->config.gen_lock = cfg->gen_lock; chan->config.master = cfg->master; + dmacr &= ~XILINX_DMA_DMACR_GENLOCK_EN; if (cfg->gen_lock && chan->genlock) { dmacr |= XILINX_DMA_DMACR_GENLOCK_EN; + dmacr &= ~XILINX_DMA_DMACR_MASTER_MASK; dmacr |= cfg->master << XILINX_DMA_DMACR_MASTER_SHIFT; } @@ -2134,11 +2140,13 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan, chan->config.delay = cfg->delay; if (cfg->coalesc <= XILINX_DMA_DMACR_FRAME_COUNT_MAX) { + dmacr &= ~XILINX_DMA_DMACR_FRAME_COUNT_MASK; dmacr |= cfg->coalesc << XILINX_DMA_DMACR_FRAME_COUNT_SHIFT; chan->config.coalesc = cfg->coalesc; } if (cfg->delay <= XILINX_DMA_DMACR_DELAY_MAX) { + dmacr &= ~XILINX_DMA_DMACR_DELAY_MASK; dmacr |= cfg->delay << XILINX_DMA_DMACR_DELAY_SHIFT; chan->config.delay = cfg->delay; } diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index d413a0bdc9ad..0bb62857ffb2 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -553,7 +553,11 @@ void ghes_edac_unregister(struct ghes *ghes) if (!ghes_pvt) return; + if (atomic_dec_return(&ghes_init)) + return; + mci = ghes_pvt->mci; + ghes_pvt = NULL; edac_mc_del_mc(mci->pdev); edac_mc_free(mci); } diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 178ee8106828..b248870a9806 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -182,6 +182,7 @@ config RESET_ATTACK_MITIGATION config EFI_RCI2_TABLE bool "EFI Runtime Configuration Interface Table Version 2 Support" + depends on X86 || COMPILE_TEST help Displays the content of the Runtime Configuration Interface Table version 2 on Dell EMC PowerEdge systems as a binary diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 69f00f7453a3..e98bbf8e56d9 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -554,7 +554,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, sizeof(*seed) + size); if (seed != NULL) { pr_notice("seeding entropy pool\n"); - add_device_randomness(seed->bits, seed->size); + add_bootloader_randomness(seed->bits, seed->size); early_memunmap(seed, sizeof(*seed) + size); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 0460c7581220..ee0661ddb25b 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -52,6 +52,7 @@ lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o string.o random.o \ lib-$(CONFIG_ARM) += arm32-stub.o lib-$(CONFIG_ARM64) += arm64-stub.o +CFLAGS_arm32-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) CFLAGS_arm64-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) # diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c index e8f7aefb6813..41213bf5fcf5 100644 --- a/drivers/firmware/efi/libstub/arm32-stub.c +++ b/drivers/firmware/efi/libstub/arm32-stub.c @@ -195,6 +195,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table, unsigned long dram_base, efi_loaded_image_t *image) { + unsigned long kernel_base; efi_status_t status; /* @@ -204,9 +205,18 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table, * loaded. These assumptions are made by the decompressor, * before any memory map is available. */ - dram_base = round_up(dram_base, SZ_128M); + kernel_base = round_up(dram_base, SZ_128M); - status = reserve_kernel_base(sys_table, dram_base, reserve_addr, + /* + * Note that some platforms (notably, the Raspberry Pi 2) put + * spin-tables and other pieces of firmware at the base of RAM, + * abusing the fact that the window of TEXT_OFFSET bytes at the + * base of the kernel image is only partially used at the moment. + * (Up to 5 pages are used for the swapper page tables) + */ + kernel_base += TEXT_OFFSET - 5 * PAGE_SIZE; + + status = reserve_kernel_base(sys_table, kernel_base, reserve_addr, reserve_size); if (status != EFI_SUCCESS) { pr_efi_err(sys_table, "Unable to allocate memory for uncompressed kernel.\n"); @@ -220,7 +230,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table, *image_size = image->image_size; status = efi_relocate_kernel(sys_table, image_addr, *image_size, *image_size, - dram_base + MAX_UNCOMP_KERNEL_SIZE, 0); + kernel_base + MAX_UNCOMP_KERNEL_SIZE, 0, 0); if (status != EFI_SUCCESS) { pr_efi_err(sys_table, "Failed to relocate kernel.\n"); efi_free(sys_table, *reserve_size, *reserve_addr); diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 3caae7f2cf56..35dbc2791c97 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -260,11 +260,11 @@ fail: } /* - * Allocate at the lowest possible address. + * Allocate at the lowest possible address that is not below 'min'. */ -efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, - unsigned long size, unsigned long align, - unsigned long *addr) +efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr, unsigned long min) { unsigned long map_size, desc_size, buff_size; efi_memory_desc_t *map; @@ -311,13 +311,8 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, start = desc->phys_addr; end = start + desc->num_pages * EFI_PAGE_SIZE; - /* - * Don't allocate at 0x0. It will confuse code that - * checks pointers against NULL. Skip the first 8 - * bytes so we start at a nice even number. - */ - if (start == 0x0) - start += 8; + if (start < min) + start = min; start = round_up(start, align); if ((start + size) > end) @@ -698,7 +693,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, unsigned long image_size, unsigned long alloc_size, unsigned long preferred_addr, - unsigned long alignment) + unsigned long alignment, + unsigned long min_addr) { unsigned long cur_image_addr; unsigned long new_addr = 0; @@ -731,8 +727,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, * possible. */ if (status != EFI_SUCCESS) { - status = efi_low_alloc(sys_table_arg, alloc_size, alignment, - &new_addr); + status = efi_low_alloc_above(sys_table_arg, alloc_size, + alignment, &new_addr, min_addr); } if (status != EFI_SUCCESS) { pr_efi_err(sys_table_arg, "Failed to allocate usable memory for kernel.\n"); diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c index 877745c3aaf2..7baf48c01e72 100644 --- a/drivers/firmware/efi/test/efi_test.c +++ b/drivers/firmware/efi/test/efi_test.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/efi.h> +#include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> @@ -717,6 +718,13 @@ static long efi_test_ioctl(struct file *file, unsigned int cmd, static int efi_test_open(struct inode *inode, struct file *file) { + int ret = security_locked_down(LOCKDOWN_EFI_TEST); + + if (ret) + return ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; /* * nothing special to do here * We do accept multiple open files at the same time as we diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index ebd7977653a8..31f9f0e369b9 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -88,6 +88,7 @@ int __init efi_tpm_eventlog_init(void) if (tbl_size < 0) { pr_err(FW_BUG "Failed to parse event in TPM Final Events Log\n"); + ret = -EINVAL; goto out_calc; } diff --git a/drivers/gpio/gpio-bd70528.c b/drivers/gpio/gpio-bd70528.c index 0c1ead12d883..4ba4d4a67881 100644 --- a/drivers/gpio/gpio-bd70528.c +++ b/drivers/gpio/gpio-bd70528.c @@ -25,13 +25,13 @@ static int bd70528_set_debounce(struct bd70528_gpio *bdgpio, case 0: val = BD70528_DEBOUNCE_DISABLE; break; - case 1 ... 15: + case 1 ... 15000: val = BD70528_DEBOUNCE_15MS; break; - case 16 ... 30: + case 15001 ... 30000: val = BD70528_DEBOUNCE_30MS; break; - case 31 ... 50: + case 30001 ... 50000: val = BD70528_DEBOUNCE_50MS; break; default: diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c index faf86ea9c51a..642c6321c22a 100644 --- a/drivers/gpio/gpio-max77620.c +++ b/drivers/gpio/gpio-max77620.c @@ -192,13 +192,13 @@ static int max77620_gpio_set_debounce(struct max77620_gpio *mgpio, case 0: val = MAX77620_CNFG_GPIO_DBNC_None; break; - case 1000 ... 8000: + case 1 ... 8000: val = MAX77620_CNFG_GPIO_DBNC_8ms; break; - case 9000 ... 16000: + case 8001 ... 16000: val = MAX77620_CNFG_GPIO_DBNC_16ms; break; - case 17000 ... 32000: + case 16001 ... 32000: val = MAX77620_CNFG_GPIO_DBNC_32ms; break; default: diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c index 2f1e9da81c1e..3302125e5265 100644 --- a/drivers/gpio/gpio-merrifield.c +++ b/drivers/gpio/gpio-merrifield.c @@ -362,9 +362,8 @@ static void mrfld_irq_handler(struct irq_desc *desc) chained_irq_exit(irqchip, desc); } -static int mrfld_irq_init_hw(struct gpio_chip *chip) +static void mrfld_irq_init_hw(struct mrfld_gpio *priv) { - struct mrfld_gpio *priv = gpiochip_get_data(chip); void __iomem *reg; unsigned int base; @@ -376,8 +375,6 @@ static int mrfld_irq_init_hw(struct gpio_chip *chip) reg = gpio_reg(&priv->chip, base, GFER); writel(0, reg); } - - return 0; } static const char *mrfld_gpio_get_pinctrl_dev_name(struct mrfld_gpio *priv) @@ -400,7 +397,6 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id { const struct mrfld_gpio_pinrange *range; const char *pinctrl_dev_name; - struct gpio_irq_chip *girq; struct mrfld_gpio *priv; u32 gpio_base, irq_base; void __iomem *base; @@ -448,21 +444,6 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id raw_spin_lock_init(&priv->lock); - girq = &priv->chip.irq; - girq->chip = &mrfld_irqchip; - girq->init_hw = mrfld_irq_init_hw; - girq->parent_handler = mrfld_irq_handler; - girq->num_parents = 1; - girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents, - sizeof(*girq->parents), - GFP_KERNEL); - if (!girq->parents) - return -ENOMEM; - girq->parents[0] = pdev->irq; - girq->first = irq_base; - girq->default_type = IRQ_TYPE_NONE; - girq->handler = handle_bad_irq; - pci_set_drvdata(pdev, priv); retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv); if (retval) { @@ -484,6 +465,18 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id } } + retval = gpiochip_irqchip_add(&priv->chip, &mrfld_irqchip, irq_base, + handle_bad_irq, IRQ_TYPE_NONE); + if (retval) { + dev_err(&pdev->dev, "could not connect irqchip to gpiochip\n"); + return retval; + } + + mrfld_irq_init_hw(priv); + + gpiochip_set_chained_irqchip(&priv->chip, &mrfld_irqchip, pdev->irq, + mrfld_irq_handler); + return 0; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 609ed16ae933..59ccfd24627d 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1304,11 +1304,28 @@ late_initcall_sync(acpi_gpio_handle_deferred_request_irqs); static const struct dmi_system_id run_edge_events_on_boot_blacklist[] = { { + /* + * The Minix Neo Z83-4 has a micro-USB-B id-pin handler for + * a non existing micro-USB-B connector which puts the HDMI + * DDC pins in GPIO mode, breaking HDMI support. + */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MINIX"), DMI_MATCH(DMI_PRODUCT_NAME, "Z83-4"), } }, + { + /* + * The Terra Pad 1061 has a micro-USB-B id-pin handler, which + * instead of controlling the actual micro-USB-B turns the 5V + * boost for its USB-A connector off. The actual micro-USB-B + * connector is wired for charging only. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Wortmann_AG"), + DMI_MATCH(DMI_PRODUCT_NAME, "TERRA_PAD_1061"), + } + }, {} /* Terminating entry */ }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 61e38e43ad1d..85b0515c0fdc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -140,7 +140,12 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp, return 0; error_free: - while (i--) { + for (i = 0; i < last_entry; ++i) { + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo); + + amdgpu_bo_unref(&bo); + } + for (i = first_userptr; i < num_entries; ++i) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo); amdgpu_bo_unref(&bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 2e53feed40e2..82823d9a8ba8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -536,7 +536,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p, list_for_each_entry(lobj, validated, tv.head) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(lobj->tv.bo); - bool binding_userptr = false; struct mm_struct *usermm; usermm = amdgpu_ttm_tt_get_usermm(bo->tbo.ttm); @@ -553,7 +552,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p, amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm, lobj->user_pages); - binding_userptr = true; } if (p->evictable == lobj) @@ -563,10 +561,8 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p, if (r) return r; - if (binding_userptr) { - kvfree(lobj->user_pages); - lobj->user_pages = NULL; - } + kvfree(lobj->user_pages); + lobj->user_pages = NULL; } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 6614d8a6f4c8..2cdaf3b2a721 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -604,8 +604,11 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr) continue; } - for (i = 0; i < num_entities; i++) + for (i = 0; i < num_entities; i++) { + mutex_lock(&ctx->adev->lock_reset); drm_sched_entity_fini(&ctx->entities[0][i].entity); + mutex_unlock(&ctx->adev->lock_reset); + } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5a1939dbd4e3..7a6c837c0a85 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2885,6 +2885,13 @@ fence_driver_init: DRM_INFO("amdgpu: acceleration disabled, skipping benchmarks\n"); } + /* + * Register gpu instance before amdgpu_device_enable_mgpu_fan_boost. + * Otherwise the mgpu fan boost feature will be skipped due to the + * gpu instance is counted less. + */ + amdgpu_register_gpu_instance(adev); + /* enable clockgating, etc. after ib tests, etc. since some blocks require * explicit gating rather than handling it automatically. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 1d4aaa9580f4..82efc1e22e61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -511,7 +511,7 @@ uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, * Also, don't allow GTT domain if the BO doens't have USWC falg set. */ if (adev->asic_type >= CHIP_CARRIZO && - adev->asic_type <= CHIP_RAVEN && + adev->asic_type < CHIP_RAVEN && (adev->flags & AMD_IS_APU) && (bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) && amdgpu_bo_support_uswc(bo_flags) && diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 2a00a36106b2..b19157b19fa0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1013,9 +1013,10 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, /* Navi14 */ - {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, + {0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, + {0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, + {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, /* Renoir */ {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 6ee4021910e2..6d19183b478b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -289,6 +289,7 @@ struct amdgpu_gfx { uint32_t mec2_feature_version; bool mec_fw_write_wait; bool me_fw_write_wait; + bool cp_fw_write_wait; struct amdgpu_ring gfx_ring[AMDGPU_MAX_GFX_RINGS]; unsigned num_gfx_rings; struct amdgpu_ring compute_ring[AMDGPU_MAX_COMPUTE_RINGS]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 9d76e0923a5a..96b2a31ccfed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -218,7 +218,7 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched); struct dma_fence *fence = NULL, *finished; struct amdgpu_job *job; - int r; + int r = 0; job = to_amdgpu_job(sched_job); finished = &job->base.s_fence->finished; @@ -243,6 +243,8 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) job->fence = dma_fence_get(fence); amdgpu_job_free_resources(job); + + fence = r ? ERR_PTR(r) : fence; return fence; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d55f5baa83d3..a73206784cba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -190,7 +190,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) pm_runtime_put_autosuspend(dev->dev); } - amdgpu_register_gpu_instance(adev); out: if (r) { /* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */ @@ -650,15 +649,19 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return -ENOMEM; alloc_size = info->read_mmr_reg.count * sizeof(*regs); - for (i = 0; i < info->read_mmr_reg.count; i++) + amdgpu_gfx_off_ctrl(adev, false); + for (i = 0; i < info->read_mmr_reg.count; i++) { if (amdgpu_asic_read_register(adev, se_num, sh_num, info->read_mmr_reg.dword_offset + i, ®s[i])) { DRM_DEBUG_KMS("unallowed offset %#x\n", info->read_mmr_reg.dword_offset + i); kfree(regs); + amdgpu_gfx_off_ctrl(adev, true); return -EFAULT; } + } + amdgpu_gfx_off_ctrl(adev, true); n = copy_to_user(out, regs, min(size, alloc_size)); kfree(regs); return n ? -EFAULT : 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 1fead0e8b890..7289e1b4fb60 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -453,7 +453,8 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, .interruptible = (bp->type != ttm_bo_type_kernel), .no_wait_gpu = false, .resv = bp->resv, - .flags = TTM_OPT_FLAG_ALLOW_RES_EVICT + .flags = bp->type != ttm_bo_type_kernel ? + TTM_OPT_FLAG_ALLOW_RES_EVICT : 0 }; struct amdgpu_bo *bo; unsigned long page_align, size = bp->size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 4d71537a960d..a46090071034 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -950,21 +950,7 @@ static void psp_print_fw_hdr(struct psp_context *psp, struct amdgpu_firmware_info *ucode) { struct amdgpu_device *adev = psp->adev; - const struct sdma_firmware_header_v1_0 *sdma_hdr = - (const struct sdma_firmware_header_v1_0 *) - adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data; - const struct gfx_firmware_header_v1_0 *ce_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; - const struct gfx_firmware_header_v1_0 *pfp_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; - const struct gfx_firmware_header_v1_0 *me_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; - const struct gfx_firmware_header_v1_0 *mec_hdr = - (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; - const struct rlc_firmware_header_v2_0 *rlc_hdr = - (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; - const struct smc_firmware_header_v1_0 *smc_hdr = - (const struct smc_firmware_header_v1_0 *)adev->pm.fw->data; + struct common_firmware_header *hdr; switch (ucode->ucode_id) { case AMDGPU_UCODE_ID_SDMA0: @@ -975,25 +961,33 @@ static void psp_print_fw_hdr(struct psp_context *psp, case AMDGPU_UCODE_ID_SDMA5: case AMDGPU_UCODE_ID_SDMA6: case AMDGPU_UCODE_ID_SDMA7: - amdgpu_ucode_print_sdma_hdr(&sdma_hdr->header); + hdr = (struct common_firmware_header *) + adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data; + amdgpu_ucode_print_sdma_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_CE: - amdgpu_ucode_print_gfx_hdr(&ce_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.ce_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_PFP: - amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.pfp_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_ME: - amdgpu_ucode_print_gfx_hdr(&me_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.me_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_CP_MEC1: - amdgpu_ucode_print_gfx_hdr(&mec_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.mec_fw->data; + amdgpu_ucode_print_gfx_hdr(hdr); break; case AMDGPU_UCODE_ID_RLC_G: - amdgpu_ucode_print_rlc_hdr(&rlc_hdr->header); + hdr = (struct common_firmware_header *)adev->gfx.rlc_fw->data; + amdgpu_ucode_print_rlc_hdr(hdr); break; case AMDGPU_UCODE_ID_SMC: - amdgpu_ucode_print_smc_hdr(&smc_hdr->header); + hdr = (struct common_firmware_header *)adev->pm.fw->data; + amdgpu_ucode_print_smc_hdr(hdr); break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index b70b3c45bb29..65044b1b3d4c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -429,13 +429,14 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp) * Open up a stream for HW test */ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, + struct amdgpu_bo *bo, struct dma_fence **fence) { const unsigned ib_size_dw = 1024; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; - uint64_t dummy; + uint64_t addr; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -444,7 +445,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; + addr = amdgpu_bo_gpu_offset(bo); /* stitch together an VCE create msg */ ib->length_dw = 0; @@ -476,8 +477,8 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, ib->ptr[ib->length_dw++] = 0x00000014; /* len */ ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */ - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; + ib->ptr[ib->length_dw++] = upper_32_bits(addr); + ib->ptr[ib->length_dw++] = addr; ib->ptr[ib->length_dw++] = 0x00000001; for (i = ib->length_dw; i < ib_size_dw; ++i) @@ -1110,13 +1111,20 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring) int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct dma_fence *fence = NULL; + struct amdgpu_bo *bo = NULL; long r; /* skip vce ring1/2 ib test for now, since it's not reliable */ if (ring != &ring->adev->vce.ring[0]) return 0; - r = amdgpu_vce_get_create_msg(ring, 1, NULL); + r = amdgpu_bo_create_reserved(ring->adev, 512, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &bo, NULL, NULL); + if (r) + return r; + + r = amdgpu_vce_get_create_msg(ring, 1, bo, NULL); if (r) goto error; @@ -1132,5 +1140,7 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout) error: dma_fence_put(fence); + amdgpu_bo_unreserve(bo); + amdgpu_bo_unref(&bo); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h index 30ea54dd9117..e802f7d9db0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h @@ -59,6 +59,7 @@ int amdgpu_vce_entity_init(struct amdgpu_device *adev); int amdgpu_vce_suspend(struct amdgpu_device *adev); int amdgpu_vce_resume(struct amdgpu_device *adev); int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, + struct amdgpu_bo *bo, struct dma_fence **fence); int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, bool direct, struct dma_fence **fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 7a6beb2e7c4e..3199e4a5ff12 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -569,13 +569,14 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring) } static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, - struct dma_fence **fence) + struct amdgpu_bo *bo, + struct dma_fence **fence) { const unsigned ib_size_dw = 16; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; - uint64_t dummy; + uint64_t addr; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -583,14 +584,14 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand return r; ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; + addr = amdgpu_bo_gpu_offset(bo); ib->length_dw = 0; ib->ptr[ib->length_dw++] = 0x00000018; ib->ptr[ib->length_dw++] = 0x00000001; /* session info */ ib->ptr[ib->length_dw++] = handle; - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; + ib->ptr[ib->length_dw++] = upper_32_bits(addr); + ib->ptr[ib->length_dw++] = addr; ib->ptr[ib->length_dw++] = 0x0000000b; ib->ptr[ib->length_dw++] = 0x00000014; @@ -621,13 +622,14 @@ err: } static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, - struct dma_fence **fence) + struct amdgpu_bo *bo, + struct dma_fence **fence) { const unsigned ib_size_dw = 16; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; - uint64_t dummy; + uint64_t addr; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -635,14 +637,14 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han return r; ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; + addr = amdgpu_bo_gpu_offset(bo); ib->length_dw = 0; ib->ptr[ib->length_dw++] = 0x00000018; ib->ptr[ib->length_dw++] = 0x00000001; ib->ptr[ib->length_dw++] = handle; - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; + ib->ptr[ib->length_dw++] = upper_32_bits(addr); + ib->ptr[ib->length_dw++] = addr; ib->ptr[ib->length_dw++] = 0x0000000b; ib->ptr[ib->length_dw++] = 0x00000014; @@ -675,13 +677,20 @@ err: int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct dma_fence *fence = NULL; + struct amdgpu_bo *bo = NULL; long r; - r = amdgpu_vcn_enc_get_create_msg(ring, 1, NULL); + r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &bo, NULL, NULL); + if (r) + return r; + + r = amdgpu_vcn_enc_get_create_msg(ring, 1, bo, NULL); if (r) goto error; - r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, &fence); + r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, bo, &fence); if (r) goto error; @@ -693,6 +702,8 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout) error: dma_fence_put(fence); + amdgpu_bo_unreserve(bo); + amdgpu_bo_unref(&bo); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 957811b73672..53090eae0082 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -93,7 +93,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_CPF_CLK_CTRL, 0xfcff8fff, 0xf8000100), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0x60000ff0, 0x60000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000000, 0x40000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100), @@ -140,7 +140,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x003c0014), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xf8ff0fff, 0x60000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000ff0, 0x40000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100), @@ -179,7 +179,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x003e001f, 0x003c0014), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0xc0000100), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0x0d000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xffffcfff, 0x60000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0xffff0fff, 0x40000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100), @@ -564,6 +564,32 @@ static void gfx_v10_0_free_microcode(struct amdgpu_device *adev) kfree(adev->gfx.rlc.register_list_format); } +static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev) +{ + adev->gfx.cp_fw_write_wait = false; + + switch (adev->asic_type) { + case CHIP_NAVI10: + case CHIP_NAVI12: + case CHIP_NAVI14: + if ((adev->gfx.me_fw_version >= 0x00000046) && + (adev->gfx.me_feature_version >= 27) && + (adev->gfx.pfp_fw_version >= 0x00000068) && + (adev->gfx.pfp_feature_version >= 27) && + (adev->gfx.mec_fw_version >= 0x0000005b) && + (adev->gfx.mec_feature_version >= 27)) + adev->gfx.cp_fw_write_wait = true; + break; + default: + break; + } + + if (adev->gfx.cp_fw_write_wait == false) + DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \ + GRBM requires 1-cycle delay in cp firmware\n"); +} + + static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev) { const struct rlc_firmware_header_v2_1 *rlc_hdr; @@ -832,6 +858,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) } } + gfx_v10_0_check_fw_write_wait(adev); out: if (err) { dev_err(adev->dev, @@ -4765,6 +4792,24 @@ static void gfx_v10_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, gfx_v10_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20); } +static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, + uint32_t reg0, uint32_t reg1, + uint32_t ref, uint32_t mask) +{ + int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX); + struct amdgpu_device *adev = ring->adev; + bool fw_version_ok = false; + + fw_version_ok = adev->gfx.cp_fw_write_wait; + + if (fw_version_ok) + gfx_v10_0_wait_reg_mem(ring, usepfp, 0, 1, reg0, reg1, + ref, mask, 0x20); + else + amdgpu_ring_emit_reg_write_reg_wait_helper(ring, reg0, reg1, + ref, mask); +} + static void gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, uint32_t me, uint32_t pipe, @@ -5155,6 +5200,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { .emit_tmz = gfx_v10_0_ring_emit_tmz, .emit_wreg = gfx_v10_0_ring_emit_wreg, .emit_reg_wait = gfx_v10_0_ring_emit_reg_wait, + .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait, }; static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = { @@ -5188,6 +5234,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = { .pad_ib = amdgpu_ring_generic_pad_ib, .emit_wreg = gfx_v10_0_ring_emit_wreg, .emit_reg_wait = gfx_v10_0_ring_emit_reg_wait, + .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait, }; static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { @@ -5218,6 +5265,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { .emit_rreg = gfx_v10_0_ring_emit_rreg, .emit_wreg = gfx_v10_0_ring_emit_wreg, .emit_reg_wait = gfx_v10_0_ring_emit_reg_wait, + .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait, }; static void gfx_v10_0_set_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index dcadc73bffd2..97cf0b536873 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -973,6 +973,13 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev) adev->gfx.me_fw_write_wait = false; adev->gfx.mec_fw_write_wait = false; + if ((adev->gfx.mec_fw_version < 0x000001a5) || + (adev->gfx.mec_feature_version < 46) || + (adev->gfx.pfp_fw_version < 0x000000b7) || + (adev->gfx.pfp_feature_version < 46)) + DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \ + GRBM requires 1-cycle delay in cp firmware\n"); + switch (adev->asic_type) { case CHIP_VEGA10: if ((adev->gfx.me_fw_version >= 0x0000009c) && @@ -1031,8 +1038,13 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) case CHIP_VEGA20: break; case CHIP_RAVEN: - if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) - &&((adev->gfx.rlc_fw_version != 106 && + /* Disable GFXOFF on original raven. There are combinations + * of sbios and platforms that are not stable. + */ + if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)) + adev->pm.pp_feature &= ~PP_GFXOFF_MASK; + else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) + &&((adev->gfx.rlc_fw_version != 106 && adev->gfx.rlc_fw_version < 531) || (adev->gfx.rlc_fw_version == 53815) || (adev->gfx.rlc_feature_version < 1) || @@ -1044,6 +1056,12 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) AMD_PG_SUPPORT_CP | AMD_PG_SUPPORT_RLC_SMU_HS; break; + case CHIP_RENOIR: + if (adev->pm.pp_feature & PP_GFXOFF_MASK) + adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG | + AMD_PG_SUPPORT_CP | + AMD_PG_SUPPORT_RLC_SMU_HS; + break; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c index 8b789f750b72..db10640a3b2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c @@ -151,6 +151,15 @@ static void gfxhub_v2_0_init_cache_regs(struct amdgpu_device *adev) WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL2, tmp); tmp = mmGCVM_L2_CNTL3_DEFAULT; + if (adev->gmc.translate_further) { + tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 12); + tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 9); + } else { + tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 9); + tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 6); + } WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL3, tmp); tmp = mmGCVM_L2_CNTL4_DEFAULT; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 241a4e57cf4a..5c7d5f73f54f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -309,6 +309,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, job->vm_pd_addr = amdgpu_gmc_pd_addr(adev->gart.bo); job->vm_needs_flush = true; + job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop; amdgpu_ring_pad_ib(ring, &job->ibs[0]); r = amdgpu_job_submit(job, &adev->mman.entity, AMDGPU_FENCE_OWNER_UNDEFINED, &fence); @@ -343,11 +344,9 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring, amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid), upper_32_bits(pd_addr)); - amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req); - - /* wait for the invalidate to complete */ - amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_ack + eng, - 1 << vmid, 1 << vmid); + amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng, + hub->vm_inv_eng0_ack + eng, + req, 1 << vmid); return pd_addr; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 3542c203c3c8..b39bea6f54e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -137,6 +137,15 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev) WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL2, tmp); tmp = mmMMVM_L2_CNTL3_DEFAULT; + if (adev->gmc.translate_further) { + tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 12); + tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 9); + } else { + tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 9); + tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 6); + } WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL3, tmp); tmp = mmMMVM_L2_CNTL4_DEFAULT; diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 0cf7ef44b4b5..9ed178fa241c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -219,6 +219,15 @@ static void mmhub_v9_4_init_cache_regs(struct amdgpu_device *adev, int hubid) hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp); tmp = mmVML2PF0_VM_L2_CNTL3_DEFAULT; + if (adev->gmc.translate_further) { + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 12); + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 9); + } else { + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 9); + tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, + L2_CACHE_BIGK_FRAGMENT_SIZE, 6); + } WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2PF0_VM_L2_CNTL3, hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 78452cf0115d..4554e72c8378 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -254,6 +254,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = { SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index f6e81680dd7e..8493bfbbc148 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1173,6 +1173,16 @@ static void sdma_v5_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); } +static void sdma_v5_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, + uint32_t reg0, uint32_t reg1, + uint32_t ref, uint32_t mask) +{ + amdgpu_ring_emit_wreg(ring, reg0, ref); + /* wait for a cycle to reset vm_inv_eng*_ack */ + amdgpu_ring_emit_reg_wait(ring, reg0, 0, 0); + amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask); +} + static int sdma_v5_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1588,7 +1598,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = { 6 + /* sdma_v5_0_ring_emit_pipeline_sync */ /* sdma_v5_0_ring_emit_vm_flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + - SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 + + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 * 2 + 10 + 10 + 10, /* sdma_v5_0_ring_emit_fence x3 for user fence, vm fence */ .emit_ib_size = 7 + 6, /* sdma_v5_0_ring_emit_ib */ .emit_ib = sdma_v5_0_ring_emit_ib, @@ -1602,6 +1612,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = { .pad_ib = sdma_v5_0_ring_pad_ib, .emit_wreg = sdma_v5_0_ring_emit_wreg, .emit_reg_wait = sdma_v5_0_ring_emit_reg_wait, + .emit_reg_write_reg_wait = sdma_v5_0_ring_emit_reg_write_reg_wait, .init_cond_exec = sdma_v5_0_ring_init_cond_exec, .patch_cond_exec = sdma_v5_0_ring_patch_cond_exec, .preempt_ib = sdma_v5_0_ring_preempt_ib, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index f8ab80c8801b..4ccfcdf8f16a 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1186,11 +1186,6 @@ static int soc15_common_early_init(void *handle) AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG; adev->external_rev_id = adev->rev_id + 0x91; - - if (adev->pm.pp_feature & PP_GFXOFF_MASK) - adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG | - AMD_PG_SUPPORT_CP | - AMD_PG_SUPPORT_RLC_SMU_HS; break; default: /* FIXME: not supported yet */ diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 670784a78512..217084d56ab8 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -206,13 +206,14 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring) * Open up a stream for HW test */ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, + struct amdgpu_bo *bo, struct dma_fence **fence) { const unsigned ib_size_dw = 16; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; - uint64_t dummy; + uint64_t addr; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -220,15 +221,15 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle return r; ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; + addr = amdgpu_bo_gpu_offset(bo); ib->length_dw = 0; ib->ptr[ib->length_dw++] = 0x00000018; ib->ptr[ib->length_dw++] = 0x00000001; /* session info */ ib->ptr[ib->length_dw++] = handle; ib->ptr[ib->length_dw++] = 0x00010000; - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; + ib->ptr[ib->length_dw++] = upper_32_bits(addr); + ib->ptr[ib->length_dw++] = addr; ib->ptr[ib->length_dw++] = 0x00000014; ib->ptr[ib->length_dw++] = 0x00000002; /* task info */ @@ -268,13 +269,14 @@ err: */ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, + struct amdgpu_bo *bo, struct dma_fence **fence) { const unsigned ib_size_dw = 16; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; - uint64_t dummy; + uint64_t addr; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -282,15 +284,15 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring, return r; ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; + addr = amdgpu_bo_gpu_offset(bo); ib->length_dw = 0; ib->ptr[ib->length_dw++] = 0x00000018; ib->ptr[ib->length_dw++] = 0x00000001; /* session info */ ib->ptr[ib->length_dw++] = handle; ib->ptr[ib->length_dw++] = 0x00010000; - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; + ib->ptr[ib->length_dw++] = upper_32_bits(addr); + ib->ptr[ib->length_dw++] = addr; ib->ptr[ib->length_dw++] = 0x00000014; ib->ptr[ib->length_dw++] = 0x00000002; /* task info */ @@ -327,13 +329,20 @@ err: static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct dma_fence *fence = NULL; + struct amdgpu_bo *bo = NULL; long r; - r = uvd_v6_0_enc_get_create_msg(ring, 1, NULL); + r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &bo, NULL, NULL); + if (r) + return r; + + r = uvd_v6_0_enc_get_create_msg(ring, 1, bo, NULL); if (r) goto error; - r = uvd_v6_0_enc_get_destroy_msg(ring, 1, &fence); + r = uvd_v6_0_enc_get_destroy_msg(ring, 1, bo, &fence); if (r) goto error; @@ -345,6 +354,8 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout) error: dma_fence_put(fence); + amdgpu_bo_unreserve(bo); + amdgpu_bo_unref(&bo); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 01f658fa72c6..0995378d8263 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -214,13 +214,14 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring) * Open up a stream for HW test */ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, + struct amdgpu_bo *bo, struct dma_fence **fence) { const unsigned ib_size_dw = 16; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; - uint64_t dummy; + uint64_t addr; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -228,15 +229,15 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle return r; ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; + addr = amdgpu_bo_gpu_offset(bo); ib->length_dw = 0; ib->ptr[ib->length_dw++] = 0x00000018; ib->ptr[ib->length_dw++] = 0x00000001; /* session info */ ib->ptr[ib->length_dw++] = handle; ib->ptr[ib->length_dw++] = 0x00000000; - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; + ib->ptr[ib->length_dw++] = upper_32_bits(addr); + ib->ptr[ib->length_dw++] = addr; ib->ptr[ib->length_dw++] = 0x00000014; ib->ptr[ib->length_dw++] = 0x00000002; /* task info */ @@ -275,13 +276,14 @@ err: * Close up a stream for HW test or if userspace failed to do so */ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, - struct dma_fence **fence) + struct amdgpu_bo *bo, + struct dma_fence **fence) { const unsigned ib_size_dw = 16; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; - uint64_t dummy; + uint64_t addr; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -289,15 +291,15 @@ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handl return r; ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; + addr = amdgpu_bo_gpu_offset(bo); ib->length_dw = 0; ib->ptr[ib->length_dw++] = 0x00000018; ib->ptr[ib->length_dw++] = 0x00000001; ib->ptr[ib->length_dw++] = handle; ib->ptr[ib->length_dw++] = 0x00000000; - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; + ib->ptr[ib->length_dw++] = upper_32_bits(addr); + ib->ptr[ib->length_dw++] = addr; ib->ptr[ib->length_dw++] = 0x00000014; ib->ptr[ib->length_dw++] = 0x00000002; @@ -334,13 +336,20 @@ err: static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct dma_fence *fence = NULL; + struct amdgpu_bo *bo = NULL; long r; - r = uvd_v7_0_enc_get_create_msg(ring, 1, NULL); + r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM, + &bo, NULL, NULL); + if (r) + return r; + + r = uvd_v7_0_enc_get_create_msg(ring, 1, bo, NULL); if (r) goto error; - r = uvd_v7_0_enc_get_destroy_msg(ring, 1, &fence); + r = uvd_v7_0_enc_get_destroy_msg(ring, 1, bo, &fence); if (r) goto error; @@ -352,6 +361,8 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout) error: dma_fence_put(fence); + amdgpu_bo_unreserve(bo); + amdgpu_bo_unref(&bo); return r; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index a52f0b13a2c8..4139f129eafb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -688,7 +688,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) */ if (adev->flags & AMD_IS_APU && adev->asic_type >= CHIP_CARRIZO && - adev->asic_type <= CHIP_RAVEN) + adev->asic_type < CHIP_RAVEN) init_data.flags.gpu_vm_support = true; if (amdgpu_dc_feature_mask & DC_FBC_MASK) diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile index 985633c08a26..26c6d735cdc7 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile +++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile @@ -24,15 +24,20 @@ # It calculates Bandwidth and Watermarks values for HW programming # -ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) - cc_stack_align := -mpreferred-stack-boundary=4 -else ifneq ($(call cc-option, -mstack-alignment=16),) - cc_stack_align := -mstack-alignment=16 -endif +calcs_ccflags := -mhard-float -msse -calcs_ccflags := -mhard-float -msse $(cc_stack_align) +ifdef CONFIG_CC_IS_GCC +ifeq ($(call cc-ifversion, -lt, 0701, y), y) +IS_OLD_GCC = 1 +endif +endif -ifdef CONFIG_CC_IS_CLANG +ifdef IS_OLD_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +calcs_ccflags += -mpreferred-stack-boundary=4 +else calcs_ccflags += -msse2 endif diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 5d1adeda4d90..4b8819c27fcd 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -580,6 +580,10 @@ static bool construct(struct dc *dc, #ifdef CONFIG_DRM_AMD_DC_DCN2_0 // Allocate memory for the vm_helper dc->vm_helper = kzalloc(sizeof(struct vm_helper), GFP_KERNEL); + if (!dc->vm_helper) { + dm_error("%s: failed to create dc->vm_helper\n", __func__); + goto fail; + } #endif memcpy(&dc->bb_overrides, &init_params->bb_overrides, sizeof(dc->bb_overrides)); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index 505967b48e14..51991bf26a93 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -374,6 +374,7 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor( enum display_dongle_type *dongle = &sink_cap->dongle_type; uint8_t type2_dongle_buf[DP_ADAPTOR_TYPE2_SIZE]; bool is_type2_dongle = false; + int retry_count = 2; struct dp_hdmi_dongle_signature_data *dongle_signature; /* Assume we have no valid DP passive dongle connected */ @@ -386,13 +387,24 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor( DP_HDMI_DONGLE_ADDRESS, type2_dongle_buf, sizeof(type2_dongle_buf))) { - *dongle = DISPLAY_DONGLE_DP_DVI_DONGLE; - sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK; + /* Passive HDMI dongles can sometimes fail here without retrying*/ + while (retry_count > 0) { + if (i2c_read(ddc, + DP_HDMI_DONGLE_ADDRESS, + type2_dongle_buf, + sizeof(type2_dongle_buf))) + break; + retry_count--; + } + if (retry_count == 0) { + *dongle = DISPLAY_DONGLE_DP_DVI_DONGLE; + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK; - CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf), - "DP-DVI passive dongle %dMhz: ", - DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000); - return; + CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf), + "DP-DVI passive dongle %dMhz: ", + DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000); + return; + } } /* Check if Type 2 dongle.*/ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 8f70295179ff..f25ac17f47fa 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -404,6 +404,9 @@ bool resource_are_streams_timing_synchronizable( if (stream1->view_format != stream2->view_format) return false; + if (stream1->ignore_msa_timing_param || stream2->ignore_msa_timing_param) + return false; + return true; } static bool is_dp_and_hdmi_sharable( @@ -1540,6 +1543,9 @@ bool dc_is_stream_unchanged( if (!are_stream_backends_same(old_stream, stream)) return false; + if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) + return false; + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c index 01c7e30b9ce1..bbd6e01b3eca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c @@ -393,6 +393,10 @@ bool cm_helper_translate_curve_to_hw_format( rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index]; rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index]; + rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red; + rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green; + rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue; + // All 3 color channels have same x corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2), dc_fixpt_from_int(region_start)); @@ -464,13 +468,6 @@ bool cm_helper_translate_curve_to_hw_format( i = 1; while (i != hw_points + 1) { - if (dc_fixpt_lt(rgb_plus_1->red, rgb->red)) - rgb_plus_1->red = rgb->red; - if (dc_fixpt_lt(rgb_plus_1->green, rgb->green)) - rgb_plus_1->green = rgb->green; - if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue)) - rgb_plus_1->blue = rgb->blue; - rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red); rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green); rgb->delta_blue = dc_fixpt_sub(rgb_plus_1->blue, rgb->blue); @@ -562,6 +559,10 @@ bool cm_helper_translate_curve_to_degamma_hw_format( rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index]; rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index]; + rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red; + rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green; + rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue; + corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2), dc_fixpt_from_int(region_start)); corner_points[0].green.x = corner_points[0].red.x; @@ -624,13 +625,6 @@ bool cm_helper_translate_curve_to_degamma_hw_format( i = 1; while (i != hw_points + 1) { - if (dc_fixpt_lt(rgb_plus_1->red, rgb->red)) - rgb_plus_1->red = rgb->red; - if (dc_fixpt_lt(rgb_plus_1->green, rgb->green)) - rgb_plus_1->green = rgb->green; - if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue)) - rgb_plus_1->blue = rgb->blue; - rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red); rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green); rgb->delta_blue = dc_fixpt_sub(rgb_plus_1->blue, rgb->blue); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile index ddb8d5649e79..63f3bddba7da 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile @@ -10,15 +10,20 @@ ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT DCN20 += dcn20_dsc.o endif -ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) - cc_stack_align := -mpreferred-stack-boundary=4 -else ifneq ($(call cc-option, -mstack-alignment=16),) - cc_stack_align := -mstack-alignment=16 -endif +CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse -CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse $(cc_stack_align) +ifdef CONFIG_CC_IS_GCC +ifeq ($(call cc-ifversion, -lt, 0701, y), y) +IS_OLD_GCC = 1 +endif +endif -ifdef CONFIG_CC_IS_CLANG +ifdef IS_OLD_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4 +else CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2 endif diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 5a2763daff4d..6b2f2f1a1c9c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -814,7 +814,7 @@ static const struct resource_caps res_cap_nv14 = { .num_audio = 6, .num_stream_encoder = 5, .num_pll = 5, - .num_dwb = 0, + .num_dwb = 1, .num_ddc = 5, }; @@ -1107,6 +1107,11 @@ struct stream_encoder *dcn20_stream_encoder_create( if (!enc1) return NULL; + if (ASICREV_IS_NAVI14_M(ctx->asic_id.hw_internal_rev)) { + if (eng_id >= ENGINE_ID_DIGD) + eng_id++; + } + dcn20_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id, &stream_enc_regs[eng_id], &se_shift, &se_mask); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile index ef673bffc241..ff50ae71fe27 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile @@ -3,15 +3,20 @@ DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o -ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) - cc_stack_align := -mpreferred-stack-boundary=4 -else ifneq ($(call cc-option, -mstack-alignment=16),) - cc_stack_align := -mstack-alignment=16 -endif +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align) +ifdef CONFIG_CC_IS_GCC +ifeq ($(call cc-ifversion, -lt, 0701, y), y) +IS_OLD_GCC = 1 +endif +endif -ifdef CONFIG_CC_IS_CLANG +ifdef IS_OLD_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4 +else CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2 endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 5b2a65b42403..8df251626e22 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -24,15 +24,20 @@ # It provides the general basic services required by other DAL # subcomponents. -ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) - cc_stack_align := -mpreferred-stack-boundary=4 -else ifneq ($(call cc-option, -mstack-alignment=16),) - cc_stack_align := -mstack-alignment=16 -endif +dml_ccflags := -mhard-float -msse -dml_ccflags := -mhard-float -msse $(cc_stack_align) +ifdef CONFIG_CC_IS_GCC +ifeq ($(call cc-ifversion, -lt, 0701, y), y) +IS_OLD_GCC = 1 +endif +endif -ifdef CONFIG_CC_IS_CLANG +ifdef IS_OLD_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +dml_ccflags += -mpreferred-stack-boundary=4 +else dml_ccflags += -msse2 endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c index 649883777f62..6c6c486b774a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c @@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer mode_lib->vba.MinActiveDRAMClockChangeMargin + mode_lib->vba.DRAMClockChangeLatency; - if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) { + if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) { + mode_lib->vba.DRAMClockChangeWatermark += 25; mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive; } else { if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) { diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile index b456cd23c6fa..970737217e53 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile @@ -1,15 +1,20 @@ # # Makefile for the 'dsc' sub-component of DAL. -ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) - cc_stack_align := -mpreferred-stack-boundary=4 -else ifneq ($(call cc-option, -mstack-alignment=16),) - cc_stack_align := -mstack-alignment=16 -endif +dsc_ccflags := -mhard-float -msse -dsc_ccflags := -mhard-float -msse $(cc_stack_align) +ifdef CONFIG_CC_IS_GCC +ifeq ($(call cc-ifversion, -lt, 0701, y), y) +IS_OLD_GCC = 1 +endif +endif -ifdef CONFIG_CC_IS_CLANG +ifdef IS_OLD_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +dsc_ccflags += -mpreferred-stack-boundary=4 +else dsc_ccflags += -msse2 endif diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 34f95e0e3ea4..203ce4b1028f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3478,18 +3478,31 @@ static int smu7_get_pp_table_entry(struct pp_hwmgr *hwmgr, static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query) { + struct amdgpu_device *adev = hwmgr->adev; int i; u32 tmp = 0; if (!query) return -EINVAL; - smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0); - tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0); - *query = tmp; + /* + * PPSMC_MSG_GetCurrPkgPwr is not supported on: + * - Hawaii + * - Bonaire + * - Fiji + * - Tonga + */ + if ((adev->asic_type != CHIP_HAWAII) && + (adev->asic_type != CHIP_BONAIRE) && + (adev->asic_type != CHIP_FIJI) && + (adev->asic_type != CHIP_TONGA)) { + smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0); + tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0); + *query = tmp; - if (tmp != 0) - return 0; + if (tmp != 0) + return 0; + } smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogStart); cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index d08493b67b67..beacfffbdc3e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -5098,9 +5098,7 @@ static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr, if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) { podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk; - for (i = 0; i < podn_vdd_dep->count - 1; i++) - od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc; - if (od_vddc_lookup_table->entries[i].us_vdd < podn_vdd_dep->entries[i].vddc) + for (i = 0; i < podn_vdd_dep->count; i++) od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc; } else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) { podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk; diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 0b461404af6b..328e258a6895 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -205,7 +205,7 @@ static struct smu_11_0_cmn2aisc_mapping navi10_workload_map[PP_SMC_POWER_PROFILE WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT), + WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; @@ -759,6 +759,12 @@ static int navi10_force_clk_levels(struct smu_context *smu, case SMU_UCLK: case SMU_DCEFCLK: case SMU_FCLK: + /* There is only 2 levels for fine grained DPM */ + if (navi10_is_support_fine_grained_dpm(smu, clk_type)) { + soft_max_level = (soft_max_level >= 1 ? 1 : 0); + soft_min_level = (soft_min_level >= 1 ? 1 : 0); + } + ret = smu_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq); if (ret) return size; diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index bbd8ebd58434..92c393f613d3 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -219,7 +219,7 @@ static struct smu_11_0_cmn2aisc_mapping vega20_workload_map[PP_SMC_POWER_PROFILE WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING, WORKLOAD_PPLIB_POWER_SAVING_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO, WORKLOAD_PPLIB_VIDEO_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR, WORKLOAD_PPLIB_VR_BIT), - WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_CUSTOM_BIT), + WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE, WORKLOAD_PPLIB_COMPUTE_BIT), WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index 8820ce15ce37..ae274902ff92 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -82,7 +82,8 @@ static void komeda_kms_commit_tail(struct drm_atomic_state *old_state) drm_atomic_helper_commit_modeset_disables(dev, old_state); - drm_atomic_helper_commit_planes(dev, old_state, 0); + drm_atomic_helper_commit_planes(dev, old_state, + DRM_PLANE_COMMIT_ACTIVE_ONLY); drm_atomic_helper_commit_modeset_enables(dev, old_state); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index ea26bc9c2d00..b848270e0a1f 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -564,8 +564,8 @@ komeda_splitter_validate(struct komeda_splitter *splitter, } if (!in_range(&splitter->vsize, dflow->in_h)) { - DRM_DEBUG_ATOMIC("split in_in: %d exceed the acceptable range.\n", - dflow->in_w); + DRM_DEBUG_ATOMIC("split in_h: %d exceeds the acceptable range.\n", + dflow->in_h); return -EINVAL; } diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 3ef2ac52ce94..2dd2cd87cdbb 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1581,8 +1581,11 @@ static void commit_tail(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; const struct drm_mode_config_helper_funcs *funcs; + struct drm_crtc_state *new_crtc_state; + struct drm_crtc *crtc; ktime_t start; s64 commit_time_ms; + unsigned int i, new_self_refresh_mask = 0; funcs = dev->mode_config.helper_private; @@ -1602,6 +1605,15 @@ static void commit_tail(struct drm_atomic_state *old_state) drm_atomic_helper_wait_for_dependencies(old_state); + /* + * We cannot safely access new_crtc_state after + * drm_atomic_helper_commit_hw_done() so figure out which crtc's have + * self-refresh active beforehand: + */ + for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i) + if (new_crtc_state->self_refresh_active) + new_self_refresh_mask |= BIT(i); + if (funcs && funcs->atomic_commit_tail) funcs->atomic_commit_tail(old_state); else @@ -1610,7 +1622,8 @@ static void commit_tail(struct drm_atomic_state *old_state) commit_time_ms = ktime_ms_delta(ktime_get(), start); if (commit_time_ms > 0) drm_self_refresh_helper_update_avg_times(old_state, - (unsigned long)commit_time_ms); + (unsigned long)commit_time_ms, + new_self_refresh_mask); drm_atomic_helper_commit_cleanup_done(old_state); diff --git a/drivers/gpu/drm/drm_self_refresh_helper.c b/drivers/gpu/drm/drm_self_refresh_helper.c index 68f4765a5896..dd33fec5aabd 100644 --- a/drivers/gpu/drm/drm_self_refresh_helper.c +++ b/drivers/gpu/drm/drm_self_refresh_helper.c @@ -133,29 +133,33 @@ out_drop_locks: * drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages * @state: the state which has just been applied to hardware * @commit_time_ms: the amount of time in ms that this commit took to complete + * @new_self_refresh_mask: bitmask of crtc's that have self_refresh_active in + * new state * * Called after &drm_mode_config_funcs.atomic_commit_tail, this function will * update the average entry/exit self refresh times on self refresh transitions. * These averages will be used when calculating how long to delay before * entering self refresh mode after activity. */ -void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, - unsigned int commit_time_ms) +void +drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, + unsigned int commit_time_ms, + unsigned int new_self_refresh_mask) { struct drm_crtc *crtc; - struct drm_crtc_state *old_crtc_state, *new_crtc_state; + struct drm_crtc_state *old_crtc_state; int i; - for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { + for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) { + bool new_self_refresh_active = new_self_refresh_mask & BIT(i); struct drm_self_refresh_data *sr_data = crtc->self_refresh_data; struct ewma_psr_time *time; if (old_crtc_state->self_refresh_active == - new_crtc_state->self_refresh_active) + new_self_refresh_active) continue; - if (new_crtc_state->self_refresh_active) + if (new_self_refresh_active) time = &sr_data->entry_avg_ms; else time = &sr_data->exit_avg_ms; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index 698db540972c..648cf0207309 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -180,6 +180,8 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit) etnaviv_cmdbuf_get_va(&submit->cmdbuf, &gpu->mmu_context->cmdbuf_mapping)); + mutex_unlock(&gpu->mmu_context->lock); + /* Reserve space for the bomap */ if (n_bomap_pages) { bomap_start = bomap = iter.data; @@ -221,8 +223,6 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit) obj->base.size); } - mutex_unlock(&gpu->mmu_context->lock); - etnaviv_core_dump_header(&iter, ETDUMP_BUF_END, iter.data); dev_coredumpv(gpu->dev, iter.start, iter.data - iter.start, GFP_KERNEL); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c index 043111a1d60c..f8bf488e9d71 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c @@ -155,9 +155,11 @@ static void etnaviv_iommuv2_dump(struct etnaviv_iommu_context *context, void *bu memcpy(buf, v2_context->mtlb_cpu, SZ_4K); buf += SZ_4K; - for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++, buf += SZ_4K) - if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT) + for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++) + if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT) { memcpy(buf, v2_context->stlb_cpu[i], SZ_4K); + buf += SZ_4K; + } } static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index 35ebae6a1be7..3607d348c298 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -328,12 +328,23 @@ etnaviv_iommu_context_init(struct etnaviv_iommu_global *global, ret = etnaviv_cmdbuf_suballoc_map(suballoc, ctx, &ctx->cmdbuf_mapping, global->memory_base); - if (ret) { - global->ops->free(ctx); - return NULL; + if (ret) + goto out_free; + + if (global->version == ETNAVIV_IOMMU_V1 && + ctx->cmdbuf_mapping.iova > 0x80000000) { + dev_err(global->dev, + "command buffer outside valid memory window\n"); + goto out_unmap; } return ctx; + +out_unmap: + etnaviv_cmdbuf_suballoc_unmap(ctx, &ctx->cmdbuf_mapping); +out_free: + global->ops->free(ctx); + return NULL; } void etnaviv_iommu_restore(struct etnaviv_gpu *gpu, diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index d3fb75bb9eb1..7cb2257bbb93 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -201,6 +201,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc) crtc_state->update_wm_post = false; crtc_state->fb_changed = false; crtc_state->fifo_changed = false; + crtc_state->preload_luts = false; crtc_state->wm.need_postvbl_update = false; crtc_state->fb_bits = 0; crtc_state->update_planes = 0; diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 71a0201437a9..aa1e2c670bc4 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -990,6 +990,55 @@ void intel_color_commit(const struct intel_crtc_state *crtc_state) dev_priv->display.color_commit(crtc_state); } +static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct intel_atomic_state *state = + to_intel_atomic_state(new_crtc_state->base.state); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + + return !old_crtc_state->base.gamma_lut && + !old_crtc_state->base.degamma_lut; +} + +static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct intel_atomic_state *state = + to_intel_atomic_state(new_crtc_state->base.state); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + + /* + * CGM_PIPE_MODE is itself single buffered. We'd have to + * somehow split it out from chv_load_luts() if we wanted + * the ability to preload the CGM LUTs/CSC without tearing. + */ + if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode) + return false; + + return !old_crtc_state->base.gamma_lut; +} + +static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct intel_atomic_state *state = + to_intel_atomic_state(new_crtc_state->base.state); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + + /* + * The hardware degamma is active whenever the pipe + * CSC is active. Thus even if the old state has no + * software degamma we need to avoid clobbering the + * linear hardware degamma mid scanout. + */ + return !old_crtc_state->csc_enable && + !old_crtc_state->base.gamma_lut; +} + int intel_color_check(struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); @@ -1133,6 +1182,8 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } @@ -1185,6 +1236,8 @@ static int chv_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = chv_can_preload_luts(crtc_state); + return 0; } @@ -1224,6 +1277,8 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } @@ -1281,6 +1336,8 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } @@ -1319,6 +1376,8 @@ static int glk_color_check(struct intel_crtc_state *crtc_state) if (ret) return ret; + crtc_state->preload_luts = glk_can_preload_luts(crtc_state); + return 0; } @@ -1368,6 +1427,8 @@ static int icl_color_check(struct intel_crtc_state *crtc_state) crtc_state->csc_mode = icl_csc_mode(crtc_state); + crtc_state->preload_luts = intel_can_preload_luts(crtc_state); + return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index e6e8d4a82044..0a08354a6183 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -864,6 +864,13 @@ load_detect: out: intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref); + + /* + * Make sure the refs for power wells enabled during detect are + * dropped to avoid a new detect cycle triggered by HPD polling. + */ + intel_display_power_flush_work(dev_priv); + return status; } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index aa54bb22796d..af50f05f4e9d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -2504,6 +2504,9 @@ u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, * the highest stride limits of them all. */ crtc = intel_get_crtc_for_pipe(dev_priv, PIPE_A); + if (!crtc) + return 0; + plane = to_intel_plane(crtc->base.primary); return plane->max_stride(plane, pixel_format, modifier, @@ -9315,7 +9318,6 @@ static bool wrpll_uses_pch_ssc(struct drm_i915_private *dev_priv, static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv) { struct intel_encoder *encoder; - bool pch_ssc_in_use = false; bool has_fdi = false; for_each_intel_encoder(&dev_priv->drm, encoder) { @@ -9343,22 +9345,24 @@ static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv) * clock hierarchy. That would also allow us to do * clock bending finally. */ + dev_priv->pch_ssc_use = 0; + if (spll_uses_pch_ssc(dev_priv)) { DRM_DEBUG_KMS("SPLL using PCH SSC\n"); - pch_ssc_in_use = true; + dev_priv->pch_ssc_use |= BIT(DPLL_ID_SPLL); } if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL1)) { DRM_DEBUG_KMS("WRPLL1 using PCH SSC\n"); - pch_ssc_in_use = true; + dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL1); } if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL2)) { DRM_DEBUG_KMS("WRPLL2 using PCH SSC\n"); - pch_ssc_in_use = true; + dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL2); } - if (pch_ssc_in_use) + if (dev_priv->pch_ssc_use) return; if (has_fdi) { @@ -13739,6 +13743,11 @@ static void intel_update_crtc(struct intel_crtc *crtc, /* vblanks work again, re-enable pipe CRC. */ intel_crtc_enable_pipe_crc(crtc); } else { + if (new_crtc_state->preload_luts && + (new_crtc_state->base.color_mgmt_changed || + new_crtc_state->update_pipe)) + intel_color_load_luts(new_crtc_state); + intel_pre_plane_update(old_crtc_state, new_crtc_state); if (new_crtc_state->update_pipe) @@ -14033,6 +14042,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { if (new_crtc_state->base.active && !needs_modeset(new_crtc_state) && + !new_crtc_state->preload_luts && (new_crtc_state->base.color_mgmt_changed || new_crtc_state->update_pipe)) intel_color_load_luts(new_crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 12099760d99e..c002f234ff31 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4896,6 +4896,9 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume) power_domains->initializing = true; + /* Must happen before power domain init on VLV/CHV */ + intel_update_rawclk(i915); + if (INTEL_GEN(i915) >= 11) { icl_display_core_init(i915, resume); } else if (IS_CANNONLAKE(i915)) { diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 449abaea619f..4075b0387c87 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -761,6 +761,7 @@ struct intel_crtc_state { bool update_wm_pre, update_wm_post; /* watermarks are updated */ bool fb_changed; /* fb on any of the planes is changed */ bool fifo_changed; /* FIFO split is changed */ + bool preload_luts; /* Pipe source size (ie. panel fitter input size) * All planes will be positioned inside this space, diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 57e9f0ba331b..9b15ac4f2fb6 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1256,6 +1256,9 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, u32 unused) { struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *i915 = + to_i915(intel_dig_port->base.base.dev); + enum phy phy = intel_port_to_phy(i915, intel_dig_port->base.port); u32 ret; ret = DP_AUX_CH_CTL_SEND_BUSY | @@ -1268,7 +1271,8 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) | DP_AUX_CH_CTL_SYNC_PULSE_SKL(32); - if (intel_dig_port->tc_mode == TC_PORT_TBT_ALT) + if (intel_phy_is_tc(i915, phy) && + intel_dig_port->tc_mode == TC_PORT_TBT_ALT) ret |= DP_AUX_CH_CTL_TBT_IO; return ret; @@ -5436,6 +5440,12 @@ out: if (status != connector_status_connected && !intel_dp->is_mst) intel_dp_unset_edid(intel_dp); + /* + * Make sure the refs for power wells enabled during detect are + * dropped to avoid a new detect cycle triggered by HPD polling. + */ + intel_display_power_flush_work(dev_priv); + return status; } diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index b8148f838354..d5a298c3c83b 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -525,16 +525,31 @@ static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv, val = I915_READ(WRPLL_CTL(id)); I915_WRITE(WRPLL_CTL(id), val & ~WRPLL_PLL_ENABLE); POSTING_READ(WRPLL_CTL(id)); + + /* + * Try to set up the PCH reference clock once all DPLLs + * that depend on it have been shut down. + */ + if (dev_priv->pch_ssc_use & BIT(id)) + intel_init_pch_refclk(dev_priv); } static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { + enum intel_dpll_id id = pll->info->id; u32 val; val = I915_READ(SPLL_CTL); I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE); POSTING_READ(SPLL_CTL); + + /* + * Try to set up the PCH reference clock once all DPLLs + * that depend on it have been shut down. + */ + if (dev_priv->pch_ssc_use & BIT(id)) + intel_init_pch_refclk(dev_priv); } static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h index e7588799fce5..104cf6d42333 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h @@ -147,11 +147,11 @@ enum intel_dpll_id { */ DPLL_ID_ICL_MGPLL4 = 6, /** - * @DPLL_ID_TGL_TCPLL5: TGL TC PLL port 5 (TC5) + * @DPLL_ID_TGL_MGPLL5: TGL TC PLL port 5 (TC5) */ DPLL_ID_TGL_MGPLL5 = 7, /** - * @DPLL_ID_TGL_TCPLL6: TGL TC PLL port 6 (TC6) + * @DPLL_ID_TGL_MGPLL6: TGL TC PLL port 6 (TC6) */ DPLL_ID_TGL_MGPLL6 = 8, }; diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index d59eee5c5d9c..b5c588e511dd 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -235,6 +235,11 @@ static int intelfb_create(struct drm_fb_helper *helper, info->apertures->ranges[0].base = ggtt->gmadr.start; info->apertures->ranges[0].size = ggtt->mappable_end; + /* Our framebuffer is the entirety of fbdev's system memory */ + info->fix.smem_start = + (unsigned long)(ggtt->gmadr.start + vma->node.start); + info->fix.smem_len = vma->node.size; + vaddr = i915_vma_pin_iomap(vma); if (IS_ERR(vaddr)) { DRM_ERROR("Failed to remap framebuffer into virtual memory\n"); @@ -244,10 +249,6 @@ static int intelfb_create(struct drm_fb_helper *helper, info->screen_base = vaddr; info->screen_size = vma->node.size; - /* Our framebuffer is the entirety of fbdev's system memory */ - info->fix.smem_start = (unsigned long)info->screen_base; - info->fix.smem_len = info->screen_size; - drm_fb_helper_fill_info(info, &ifbdev->helper, sizes); /* If the object is shmemfs backed, it will have given us zeroed pages. diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index e02f0faecf02..b030f7ae3302 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -2565,6 +2565,12 @@ out: if (status != connector_status_connected) cec_notifier_phys_addr_invalidate(intel_hdmi->cec_notifier); + /* + * Make sure the refs for power wells enabled during detect are + * dropped to avoid a new detect cycle triggered by HPD polling. + */ + intel_display_power_flush_work(dev_priv); + return status; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 1cdfe05514c3..e41fd94ae5a9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -319,6 +319,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx) free_engines(rcu_access_pointer(ctx->engines)); mutex_destroy(&ctx->engines_mutex); + kfree(ctx->jump_whitelist); + if (ctx->timeline) intel_timeline_put(ctx->timeline); @@ -441,6 +443,9 @@ __create_context(struct drm_i915_private *i915) for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++) ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES; + ctx->jump_whitelist = NULL; + ctx->jump_whitelist_cmds = 0; + return ctx; err_free: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index 260d59cc3de8..00537b9d7006 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -192,6 +192,13 @@ struct i915_gem_context { * per vm, which may be one per context or shared with the global GTT) */ struct radix_tree_root handles_vma; + + /** jump_whitelist: Bit array for tracking cmds during cmdparsing + * Guarded by struct_mutex + */ + unsigned long *jump_whitelist; + /** jump_whitelist_cmds: No of cmd slots available */ + u32 jump_whitelist_cmds; }; #endif /* __I915_GEM_CONTEXT_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index b5f6937369ea..e635e1e5f4d3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -296,7 +296,9 @@ static inline u64 gen8_noncanonical_addr(u64 address) static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) { - return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len; + return intel_engine_requires_cmd_parser(eb->engine) || + (intel_engine_using_cmd_parser(eb->engine) && + eb->args->batch_len); } static int eb_create(struct i915_execbuffer *eb) @@ -1955,40 +1957,94 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq) return 0; } -static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master) +static struct i915_vma * +shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = eb->i915; + struct i915_vma * const vma = *eb->vma; + struct i915_address_space *vm; + u64 flags; + + /* + * PPGTT backed shadow buffers must be mapped RO, to prevent + * post-scan tampering + */ + if (CMDPARSER_USES_GGTT(dev_priv)) { + flags = PIN_GLOBAL; + vm = &dev_priv->ggtt.vm; + } else if (vma->vm->has_read_only) { + flags = PIN_USER; + vm = vma->vm; + i915_gem_object_set_readonly(obj); + } else { + DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n"); + return ERR_PTR(-EINVAL); + } + + return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags); +} + +static struct i915_vma *eb_parse(struct i915_execbuffer *eb) { struct intel_engine_pool_node *pool; struct i915_vma *vma; + u64 batch_start; + u64 shadow_batch_start; int err; pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len); if (IS_ERR(pool)) return ERR_CAST(pool); - err = intel_engine_cmd_parser(eb->engine, + vma = shadow_batch_pin(eb, pool->obj); + if (IS_ERR(vma)) + goto err; + + batch_start = gen8_canonical_addr(eb->batch->node.start) + + eb->batch_start_offset; + + shadow_batch_start = gen8_canonical_addr(vma->node.start); + + err = intel_engine_cmd_parser(eb->gem_context, + eb->engine, eb->batch->obj, - pool->obj, + batch_start, eb->batch_start_offset, eb->batch_len, - is_master); + pool->obj, + shadow_batch_start); + if (err) { - if (err == -EACCES) /* unhandled chained batch */ + i915_vma_unpin(vma); + + /* + * Unsafe GGTT-backed buffers can still be submitted safely + * as non-secure. + * For PPGTT backing however, we have no choice but to forcibly + * reject unsafe buffers + */ + if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES)) + /* Execute original buffer non-secure */ vma = NULL; else vma = ERR_PTR(err); goto err; } - vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0); - if (IS_ERR(vma)) - goto err; - eb->vma[eb->buffer_count] = i915_vma_get(vma); eb->flags[eb->buffer_count] = __EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF; vma->exec_flags = &eb->flags[eb->buffer_count]; eb->buffer_count++; + eb->batch_start_offset = 0; + eb->batch = vma; + + if (CMDPARSER_USES_GGTT(eb->i915)) + eb->batch_flags |= I915_DISPATCH_SECURE; + + /* eb->batch_len unchanged */ + vma->private = pool; return vma; @@ -2421,6 +2477,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, struct drm_i915_gem_exec_object2 *exec, struct drm_syncobj **fences) { + struct drm_i915_private *i915 = to_i915(dev); struct i915_execbuffer eb; struct dma_fence *in_fence = NULL; struct dma_fence *exec_fence = NULL; @@ -2432,7 +2489,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS & ~__EXEC_OBJECT_UNKNOWN_FLAGS); - eb.i915 = to_i915(dev); + eb.i915 = i915; eb.file = file; eb.args = args; if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) @@ -2452,8 +2509,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { + if (INTEL_GEN(i915) >= 11) + return -ENODEV; + + /* Return -EPERM to trigger fallback code on old binaries. */ + if (!HAS_SECURE_BATCHES(i915)) + return -EPERM; + if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN)) - return -EPERM; + return -EPERM; eb.batch_flags |= I915_DISPATCH_SECURE; } @@ -2530,34 +2594,19 @@ i915_gem_do_execbuffer(struct drm_device *dev, goto err_vma; } + if (eb.batch_len == 0) + eb.batch_len = eb.batch->size - eb.batch_start_offset; + if (eb_use_cmdparser(&eb)) { struct i915_vma *vma; - vma = eb_parse(&eb, drm_is_current_master(file)); + vma = eb_parse(&eb); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err_vma; } - - if (vma) { - /* - * Batch parsed and accepted: - * - * Set the DISPATCH_SECURE bit to remove the NON_SECURE - * bit from MI_BATCH_BUFFER_START commands issued in - * the dispatch_execbuffer implementations. We - * specifically don't want that set on batches the - * command parser has accepted. - */ - eb.batch_flags |= I915_DISPATCH_SECURE; - eb.batch_start_offset = 0; - eb.batch = vma; - } } - if (eb.batch_len == 0) - eb.batch_len = eb.batch->size - eb.batch_start_offset; - /* * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure * batch" bit. Hence we need to pin secure batches into the global gtt. diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 6b3b50f0f6d9..abfbac49b8e8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -671,8 +671,28 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, obj->mm.dirty = false; for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) + if (obj->mm.dirty && trylock_page(page)) { + /* + * As this may not be anonymous memory (e.g. shmem) + * but exist on a real mapping, we have to lock + * the page in order to dirty it -- holding + * the page reference is not sufficient to + * prevent the inode from being truncated. + * Play safe and take the lock. + * + * However...! + * + * The mmu-notifier can be invalidated for a + * migrate_page, that is alreadying holding the lock + * on the page. Such a try_to_unmap() will result + * in us calling put_pages() and so recursively try + * to lock the page. We avoid that deadlock with + * a trylock_page() and in exchange we risk missing + * some page dirtying. + */ set_page_dirty(page); + unlock_page(page); + } mark_page_accessed(page); put_page(page); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_engine_pool.c index 4cd54c569911..379a91780bd4 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.c @@ -103,6 +103,8 @@ node_create(struct intel_engine_pool *pool, size_t sz) return ERR_CAST(obj); } + i915_gem_object_set_readonly(obj); + node->obj = obj; return node; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index a82cea95c2f2..9dd8c299cb2d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -475,12 +475,13 @@ struct intel_engine_cs { struct intel_engine_hangcheck hangcheck; -#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0) +#define I915_ENGINE_USING_CMD_PARSER BIT(0) #define I915_ENGINE_SUPPORTS_STATS BIT(1) #define I915_ENGINE_HAS_PREEMPTION BIT(2) #define I915_ENGINE_HAS_SEMAPHORES BIT(3) #define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4) #define I915_ENGINE_IS_VIRTUAL BIT(5) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7) unsigned int flags; /* @@ -541,9 +542,15 @@ struct intel_engine_cs { }; static inline bool -intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine) +intel_engine_using_cmd_parser(const struct intel_engine_cs *engine) { - return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER; + return engine->flags & I915_ENGINE_USING_CMD_PARSER; +} + +static inline bool +intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine) +{ + return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER; } static inline bool diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 1363e069ec83..fac75afed35b 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -38,6 +38,9 @@ static int __gt_unpark(struct intel_wakeref *wf) gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ); GEM_BUG_ON(!gt->awake); + if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL); + intel_enable_gt_powersave(i915); i915_update_gfx_val(i915); @@ -67,6 +70,11 @@ static int __gt_park(struct intel_wakeref *wf) if (INTEL_GEN(i915) >= 6) gen6_rps_idle(i915); + if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) { + i915_rc6_ctx_wa_check(i915); + intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL); + } + /* Everything switched off, flush any residual interrupt just in case */ intel_synchronize_irq(i915); diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 728704bbbe18..cea184a7dde9 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -199,14 +199,6 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = { MOCS_ENTRY(15, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \ L3_3_WB), \ - /* Bypass LLC - Uncached (EHL+) */ \ - MOCS_ENTRY(16, \ - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ - L3_1_UC), \ - /* Bypass LLC - L3 (Read-Only) (EHL+) */ \ - MOCS_ENTRY(17, \ - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ - L3_3_WB), \ /* Self-Snoop - L3 + LLC */ \ MOCS_ENTRY(18, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \ @@ -270,7 +262,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = { L3_1_UC), /* HW Special Case (Displayable) */ MOCS_ENTRY(61, - LE_1_UC | LE_TC_1_LLC | LE_SCF(1), + LE_1_UC | LE_TC_1_LLC, L3_3_WB), }; diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 13044c027f27..4bfaefdf548d 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -498,8 +498,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id) goto out_free_gem; } - i915_gem_object_put(obj); - ret = dma_buf_fd(dmabuf, DRM_CLOEXEC | DRM_RDWR); if (ret < 0) { gvt_vgpu_err("create dma-buf fd failed ret:%d\n", ret); @@ -524,6 +522,8 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id) file_count(dmabuf->file), kref_read(&obj->base.refcount)); + i915_gem_object_put(obj); + return dmabuf_fd; out_free_dmabuf: diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 24555102e198..f24096e27bef 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -53,13 +53,11 @@ * granting userspace undue privileges. There are three categories of privilege. * * First, commands which are explicitly defined as privileged or which should - * only be used by the kernel driver. The parser generally rejects such - * commands, though it may allow some from the drm master process. + * only be used by the kernel driver. The parser rejects such commands * * Second, commands which access registers. To support correct/enhanced * userspace functionality, particularly certain OpenGL extensions, the parser - * provides a whitelist of registers which userspace may safely access (for both - * normal and drm master processes). + * provides a whitelist of registers which userspace may safely access * * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc). * The parser always rejects such commands. @@ -84,9 +82,9 @@ * in the per-engine command tables. * * Other command table entries map fairly directly to high level categories - * mentioned above: rejected, master-only, register whitelist. The parser - * implements a number of checks, including the privileged memory checks, via a - * general bitmasking mechanism. + * mentioned above: rejected, register whitelist. The parser implements a number + * of checks, including the privileged memory checks, via a general bitmasking + * mechanism. */ /* @@ -104,8 +102,6 @@ struct drm_i915_cmd_descriptor { * CMD_DESC_REJECT: The command is never allowed * CMD_DESC_REGISTER: The command should be checked against the * register whitelist for the appropriate ring - * CMD_DESC_MASTER: The command is allowed if the submitting process - * is the DRM master */ u32 flags; #define CMD_DESC_FIXED (1<<0) @@ -113,7 +109,6 @@ struct drm_i915_cmd_descriptor { #define CMD_DESC_REJECT (1<<2) #define CMD_DESC_REGISTER (1<<3) #define CMD_DESC_BITMASK (1<<4) -#define CMD_DESC_MASTER (1<<5) /* * The command's unique identification bits and the bitmask to get them. @@ -194,7 +189,7 @@ struct drm_i915_cmd_table { #define CMD(op, opm, f, lm, fl, ...) \ { \ .flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \ - .cmd = { (op), ~0u << (opm) }, \ + .cmd = { (op & ~0u << (opm)), ~0u << (opm) }, \ .length = { (lm) }, \ __VA_ARGS__ \ } @@ -209,14 +204,13 @@ struct drm_i915_cmd_table { #define R CMD_DESC_REJECT #define W CMD_DESC_REGISTER #define B CMD_DESC_BITMASK -#define M CMD_DESC_MASTER /* Command Mask Fixed Len Action ---------------------------------------------------------- */ -static const struct drm_i915_cmd_descriptor common_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = { CMD( MI_NOOP, SMI, F, 1, S ), CMD( MI_USER_INTERRUPT, SMI, F, 1, R ), - CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, R ), CMD( MI_ARB_CHECK, SMI, F, 1, S ), CMD( MI_REPORT_HEAD, SMI, F, 1, S ), CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), @@ -246,7 +240,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ), }; -static const struct drm_i915_cmd_descriptor render_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = { CMD( MI_FLUSH, SMI, F, 1, S ), CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_PREDICATE, SMI, F, 1, S ), @@ -313,7 +307,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( MI_URB_ATOMIC_ALLOC, SMI, F, 1, S ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_RS_CONTEXT, SMI, F, 1, S ), - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), @@ -330,7 +324,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS, S3D, !F, 0x1FF, S ), }; -static const struct drm_i915_cmd_descriptor video_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -374,7 +368,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = { CMD( MFX_WAIT, SMFX, F, 1, S ), }; -static const struct drm_i915_cmd_descriptor vecs_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -412,7 +406,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = { }}, ), }; -static const struct drm_i915_cmd_descriptor blt_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = { CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B, .bits = {{ @@ -446,10 +440,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = { }; static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = { - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), }; +/* + * For Gen9 we can still rely on the h/w to enforce cmd security, and only + * need to re-enforce the register access checks. We therefore only need to + * teach the cmdparser how to find the end of each command, and identify + * register accesses. The table doesn't need to reject any commands, and so + * the only commands listed here are: + * 1) Those that touch registers + * 2) Those that do not have the default 8-bit length + * + * Note that the default MI length mask chosen for this table is 0xFF, not + * the 0x3F used on older devices. This is because the vast majority of MI + * cmds on Gen9 use a standard 8-bit Length field. + * All the Gen9 blitter instructions are standard 0xFF length mask, and + * none allow access to non-general registers, so in fact no BLT cmds are + * included in the table at all. + * + */ +static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = { + CMD( MI_NOOP, SMI, F, 1, S ), + CMD( MI_USER_INTERRUPT, SMI, F, 1, S ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, S ), + CMD( MI_FLUSH, SMI, F, 1, S ), + CMD( MI_ARB_CHECK, SMI, F, 1, S ), + CMD( MI_REPORT_HEAD, SMI, F, 1, S ), + CMD( MI_ARB_ON_OFF, SMI, F, 1, S ), + CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, S ), + CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), + CMD( MI_UPDATE_GTT, SMI, !F, 0x3FF, S ), + CMD( MI_STORE_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_FLUSH_DW, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), + + /* + * We allow BB_START but apply further checks. We just sanitize the + * basic fields here. + */ +#define MI_BB_START_OPERAND_MASK GENMASK(SMI-1, 0) +#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1) + CMD( MI_BATCH_BUFFER_START_GEN8, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_BB_START_OPERAND_MASK, + .expected = MI_BB_START_OPERAND_EXPECT, + }}, ), +}; + static const struct drm_i915_cmd_descriptor noop_desc = CMD(MI_NOOP, SMI, F, 1, S); @@ -463,40 +511,44 @@ static const struct drm_i915_cmd_descriptor noop_desc = #undef R #undef W #undef B -#undef M -static const struct drm_i915_cmd_table gen7_render_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table gen7_render_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, }; -static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, { hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) }, }; -static const struct drm_i915_cmd_table gen7_video_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { video_cmds, ARRAY_SIZE(video_cmds) }, +static const struct drm_i915_cmd_table gen7_video_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) }, }; -static const struct drm_i915_cmd_table hsw_vebox_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { vecs_cmds, ARRAY_SIZE(vecs_cmds) }, +static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) }, }; -static const struct drm_i915_cmd_table gen7_blt_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, }; -static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, { hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) }, }; +static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = { + { gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) }, +}; + + /* * Register whitelists, sorted by increasing register offset. */ @@ -612,17 +664,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = { REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), }; -static const struct drm_i915_reg_descriptor ivb_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)), -}; - -static const struct drm_i915_reg_descriptor hsw_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), +static const struct drm_i915_reg_descriptor gen9_blt_regs[] = { + REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE), + REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE), + REG32(BCS_SWCTRL), + REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), + REG64_IDX(BCS_GPR, 0), + REG64_IDX(BCS_GPR, 1), + REG64_IDX(BCS_GPR, 2), + REG64_IDX(BCS_GPR, 3), + REG64_IDX(BCS_GPR, 4), + REG64_IDX(BCS_GPR, 5), + REG64_IDX(BCS_GPR, 6), + REG64_IDX(BCS_GPR, 7), + REG64_IDX(BCS_GPR, 8), + REG64_IDX(BCS_GPR, 9), + REG64_IDX(BCS_GPR, 10), + REG64_IDX(BCS_GPR, 11), + REG64_IDX(BCS_GPR, 12), + REG64_IDX(BCS_GPR, 13), + REG64_IDX(BCS_GPR, 14), + REG64_IDX(BCS_GPR, 15), }; #undef REG64 @@ -631,28 +693,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = { struct drm_i915_reg_table { const struct drm_i915_reg_descriptor *regs; int num_regs; - bool master; }; static const struct drm_i915_reg_table ivb_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, }; static const struct drm_i915_reg_table ivb_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, }; static const struct drm_i915_reg_table hsw_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, + { hsw_render_regs, ARRAY_SIZE(hsw_render_regs) }, }; static const struct drm_i915_reg_table hsw_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, +}; + +static const struct drm_i915_reg_table gen9_blt_reg_tables[] = { + { gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) }, }; static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) @@ -710,6 +771,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header) return 0; } +static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header) +{ + u32 client = cmd_header >> INSTR_CLIENT_SHIFT; + + if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT) + return 0xFF; + + DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header); + return 0; +} + static bool validate_cmds_sorted(const struct intel_engine_cs *engine, const struct drm_i915_cmd_table *cmd_tables, int cmd_table_count) @@ -867,18 +939,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) int cmd_table_count; int ret; - if (!IS_GEN(engine->i915, 7)) + if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) && + engine->class == COPY_ENGINE_CLASS)) return; switch (engine->class) { case RENDER_CLASS: if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_render_ring_cmds; + cmd_tables = hsw_render_ring_cmd_table; cmd_table_count = - ARRAY_SIZE(hsw_render_ring_cmds); + ARRAY_SIZE(hsw_render_ring_cmd_table); } else { - cmd_tables = gen7_render_cmds; - cmd_table_count = ARRAY_SIZE(gen7_render_cmds); + cmd_tables = gen7_render_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table); } if (IS_HASWELL(engine->i915)) { @@ -888,36 +961,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) engine->reg_tables = ivb_render_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables); } - engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask; break; case VIDEO_DECODE_CLASS: - cmd_tables = gen7_video_cmds; - cmd_table_count = ARRAY_SIZE(gen7_video_cmds); + cmd_tables = gen7_video_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table); engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; case COPY_ENGINE_CLASS: - if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_blt_ring_cmds; - cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); + engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; + if (IS_GEN(engine->i915, 9)) { + cmd_tables = gen9_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table); + engine->get_cmd_length_mask = + gen9_blt_get_cmd_length_mask; + + /* BCS Engine unsafe without parser */ + engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER; + } else if (IS_HASWELL(engine->i915)) { + cmd_tables = hsw_blt_ring_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table); } else { - cmd_tables = gen7_blt_cmds; - cmd_table_count = ARRAY_SIZE(gen7_blt_cmds); + cmd_tables = gen7_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table); } - if (IS_HASWELL(engine->i915)) { + if (IS_GEN(engine->i915, 9)) { + engine->reg_tables = gen9_blt_reg_tables; + engine->reg_table_count = + ARRAY_SIZE(gen9_blt_reg_tables); + } else if (IS_HASWELL(engine->i915)) { engine->reg_tables = hsw_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables); } else { engine->reg_tables = ivb_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables); } - - engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; break; case VIDEO_ENHANCEMENT_CLASS: - cmd_tables = hsw_vebox_cmds; - cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds); + cmd_tables = hsw_vebox_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table); /* VECS can use the same length_mask function as VCS */ engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; @@ -943,7 +1026,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) return; } - engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER; + engine->flags |= I915_ENGINE_USING_CMD_PARSER; } /** @@ -955,7 +1038,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) */ void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine) { - if (!intel_engine_needs_cmd_parser(engine)) + if (!intel_engine_using_cmd_parser(engine)) return; fini_hash_table(engine); @@ -1029,22 +1112,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr) } static const struct drm_i915_reg_descriptor * -find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) +find_reg(const struct intel_engine_cs *engine, u32 addr) { const struct drm_i915_reg_table *table = engine->reg_tables; + const struct drm_i915_reg_descriptor *reg = NULL; int count = engine->reg_table_count; - for (; count > 0; ++table, --count) { - if (!table->master || is_master) { - const struct drm_i915_reg_descriptor *reg; + for (; !reg && (count > 0); ++table, --count) + reg = __find_reg(table->regs, table->num_regs, addr); - reg = __find_reg(table->regs, table->num_regs, addr); - if (reg != NULL) - return reg; - } - } - - return NULL; + return reg; } /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */ @@ -1128,8 +1205,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, - const u32 *cmd, u32 length, - const bool is_master) + const u32 *cmd, u32 length) { if (desc->flags & CMD_DESC_SKIP) return true; @@ -1139,12 +1215,6 @@ static bool check_cmd(const struct intel_engine_cs *engine, return false; } - if ((desc->flags & CMD_DESC_MASTER) && !is_master) { - DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n", - *cmd); - return false; - } - if (desc->flags & CMD_DESC_REGISTER) { /* * Get the distance between individual register offset @@ -1158,7 +1228,7 @@ static bool check_cmd(const struct intel_engine_cs *engine, offset += step) { const u32 reg_addr = cmd[offset] & desc->reg.mask; const struct drm_i915_reg_descriptor *reg = - find_reg(engine, is_master, reg_addr); + find_reg(engine, reg_addr); if (!reg) { DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n", @@ -1236,16 +1306,112 @@ static bool check_cmd(const struct intel_engine_cs *engine, return true; } +static int check_bbstart(const struct i915_gem_context *ctx, + u32 *cmd, u32 offset, u32 length, + u32 batch_len, + u64 batch_start, + u64 shadow_batch_start) +{ + u64 jump_offset, jump_target; + u32 target_cmd_offset, target_cmd_index; + + /* For igt compatibility on older platforms */ + if (CMDPARSER_USES_GGTT(ctx->i915)) { + DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n"); + return -EACCES; + } + + if (length != 3) { + DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n", + length); + return -EINVAL; + } + + jump_target = *(u64*)(cmd+1); + jump_offset = jump_target - batch_start; + + /* + * Any underflow of jump_target is guaranteed to be outside the range + * of a u32, so >= test catches both too large and too small + */ + if (jump_offset >= batch_len) { + DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n", + jump_target); + return -EINVAL; + } + + /* + * This cannot overflow a u32 because we already checked jump_offset + * is within the BB, and the batch_len is a u32 + */ + target_cmd_offset = lower_32_bits(jump_offset); + target_cmd_index = target_cmd_offset / sizeof(u32); + + *(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset; + + if (target_cmd_index == offset) + return 0; + + if (ctx->jump_whitelist_cmds <= target_cmd_index) { + DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n"); + return -EINVAL; + } else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) { + DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n", + jump_target); + return -EINVAL; + } + + return 0; +} + +static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len) +{ + const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32)); + const u32 exact_size = BITS_TO_LONGS(batch_cmds); + u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds)); + unsigned long *next_whitelist; + + if (CMDPARSER_USES_GGTT(ctx->i915)) + return; + + if (batch_cmds <= ctx->jump_whitelist_cmds) { + bitmap_zero(ctx->jump_whitelist, batch_cmds); + return; + } + +again: + next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL); + if (next_whitelist) { + kfree(ctx->jump_whitelist); + ctx->jump_whitelist = next_whitelist; + ctx->jump_whitelist_cmds = + next_size * BITS_PER_BYTE * sizeof(long); + return; + } + + if (next_size > exact_size) { + next_size = exact_size; + goto again; + } + + DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n"); + bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds); + + return; +} + #define LENGTH_BIAS 2 /** * i915_parse_cmds() - parse a submitted batch buffer for privilege violations + * @ctx: the context in which the batch is to execute * @engine: the engine on which the batch is to execute * @batch_obj: the batch buffer in question - * @shadow_batch_obj: copy of the batch buffer in question + * @batch_start: Canonical base address of batch * @batch_start_offset: byte offset in the batch at which execution starts * @batch_len: length of the commands in batch_obj - * @is_master: is the submitting process the drm master? + * @shadow_batch_obj: copy of the batch buffer in question + * @shadow_batch_start: Canonical base address of shadow_batch_obj * * Parses the specified batch buffer looking for privilege violations as * described in the overview. @@ -1253,14 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine, * Return: non-zero if the parser finds violations or otherwise fails; -EACCES * if the batch appears legal but should use hardware parsing */ -int intel_engine_cmd_parser(struct intel_engine_cs *engine, + +int intel_engine_cmd_parser(struct i915_gem_context *ctx, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 batch_start, u32 batch_start_offset, u32 batch_len, - bool is_master) + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start) { - u32 *cmd, *batch_end; + u32 *cmd, *batch_end, offset = 0; struct drm_i915_cmd_descriptor default_desc = noop_desc; const struct drm_i915_cmd_descriptor *desc = &default_desc; bool needs_clflush_after = false; @@ -1274,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, return PTR_ERR(cmd); } + init_whitelist(ctx, batch_len); + /* * We use the batch length as size because the shadow object is as * large or larger and copy_batch() will write MI_NOPs to the extra @@ -1283,31 +1454,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, do { u32 length; - if (*cmd == MI_BATCH_BUFFER_END) { - if (needs_clflush_after) { - void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping); - drm_clflush_virt_range(ptr, - (void *)(cmd + 1) - ptr); - } + if (*cmd == MI_BATCH_BUFFER_END) break; - } desc = find_cmd(engine, *cmd, desc, &default_desc); if (!desc) { DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n", *cmd); ret = -EINVAL; - break; - } - - /* - * If the batch buffer contains a chained batch, return an - * error that tells the caller to abort and dispatch the - * workload as a non-secure batch. - */ - if (desc->cmd.value == MI_BATCH_BUFFER_START) { - ret = -EACCES; - break; + goto err; } if (desc->flags & CMD_DESC_FIXED) @@ -1321,22 +1476,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, length, batch_end - cmd); ret = -EINVAL; - break; + goto err; } - if (!check_cmd(engine, desc, cmd, length, is_master)) { + if (!check_cmd(engine, desc, cmd, length)) { ret = -EACCES; + goto err; + } + + if (desc->cmd.value == MI_BATCH_BUFFER_START) { + ret = check_bbstart(ctx, cmd, offset, length, + batch_len, batch_start, + shadow_batch_start); + + if (ret) + goto err; break; } + if (ctx->jump_whitelist_cmds > offset) + set_bit(offset, ctx->jump_whitelist); + cmd += length; + offset += length; if (cmd >= batch_end) { DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); ret = -EINVAL; - break; + goto err; } } while (1); + if (needs_clflush_after) { + void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping); + + drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr); + } + +err: i915_gem_object_unpin_map(shadow_batch_obj); return ret; } @@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) /* If the command parser is not enabled, report 0 - unsupported */ for_each_uabi_engine(engine, dev_priv) { - if (intel_engine_needs_cmd_parser(engine)) { + if (intel_engine_using_cmd_parser(engine)) { active = true; break; } @@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) * the parser enabled. * 9. Don't whitelist or handle oacontrol specially, as ownership * for oacontrol state is moving to i915-perf. + * 10. Support for Gen9 BCS Parsing */ - return 9; + return 10; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index bb6f86c7067a..3d717e282908 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -364,9 +364,6 @@ static int i915_driver_modeset_probe(struct drm_device *dev) if (ret) goto cleanup_vga_client; - /* must happen before intel_power_domains_init_hw() on VLV/CHV */ - intel_update_rawclk(dev_priv); - intel_power_domains_init_hw(dev_priv, false); intel_csr_ucode_init(dev_priv); @@ -1850,6 +1847,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) i915_gem_suspend_late(dev_priv); + i915_rc6_ctx_wa_suspend(dev_priv); + intel_uncore_suspend(&dev_priv->uncore); intel_power_domains_suspend(dev_priv, @@ -2053,6 +2052,8 @@ static int i915_drm_resume_early(struct drm_device *dev) intel_power_domains_resume(dev_priv); + i915_rc6_ctx_wa_resume(dev_priv); + intel_gt_sanitize(&dev_priv->gt, true); enable_rpm_wakeref_asserts(&dev_priv->runtime_pm); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 772154e4073e..89b6112bd66b 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -593,6 +593,8 @@ struct intel_rps { struct intel_rc6 { bool enabled; + bool ctx_corrupted; + intel_wakeref_t ctx_corrupted_wakeref; u64 prev_hw_residency[4]; u64 cur_residency[4]; }; @@ -1723,6 +1725,8 @@ struct drm_i915_private { struct work_struct idle_work; } gem; + u8 pch_ssc_use; + /* For i945gm vblank irq vs. C3 workaround */ struct { struct work_struct work; @@ -2073,9 +2077,16 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define VEBOX_MASK(dev_priv) \ ENGINE_INSTANCES_MASK(dev_priv, VECS0, I915_MAX_VECS) +/* + * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution + * All later gens can run the final buffer from the ppgtt + */ +#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7) + #define HAS_LLC(dev_priv) (INTEL_INFO(dev_priv)->has_llc) #define HAS_SNOOP(dev_priv) (INTEL_INFO(dev_priv)->has_snoop) #define HAS_EDRAM(dev_priv) ((dev_priv)->edram_size_mb) +#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6) #define HAS_WT(dev_priv) ((IS_HASWELL(dev_priv) || \ IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv)) @@ -2108,10 +2119,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, /* Early gen2 have a totally busted CS tlb and require pinned batches. */ #define HAS_BROKEN_CS_TLB(dev_priv) (IS_I830(dev_priv) || IS_I845G(dev_priv)) +#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv) \ + (IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9)) + /* WaRsDisableCoarsePowerGating:skl,cnl */ #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \ - (IS_CANNONLAKE(dev_priv) || \ - IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv)) + (IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9)) #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4) #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \ @@ -2282,6 +2295,14 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj, unsigned long flags); #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0) +struct i915_vma * __must_check +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags); + void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv); static inline int __must_check @@ -2391,12 +2412,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); -int intel_engine_cmd_parser(struct intel_engine_cs *engine, +int intel_engine_cmd_parser(struct i915_gem_context *cxt, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 user_batch_start, u32 batch_start_offset, u32 batch_len, - bool is_master); + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start); /* intel_device_info.c */ static inline struct intel_device_info * diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index d0f94f239919..98305d987ac1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -964,6 +964,20 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct i915_address_space *vm = &dev_priv->ggtt.vm; + + return i915_gem_object_pin(obj, vm, view, size, alignment, + flags | PIN_GLOBAL); +} + +struct i915_vma * +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags) +{ + struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct i915_vma *vma; int ret; @@ -1038,7 +1052,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, return ERR_PTR(ret); } - ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL); + ret = i915_vma_pin(vma, size, alignment, flags); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 5d9101376a3d..9f1517af5b7f 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -62,7 +62,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, value = !!(i915->caps.scheduler & I915_SCHEDULER_CAP_SEMAPHORES); break; case I915_PARAM_HAS_SECURE_BATCHES: - value = capable(CAP_SYS_ADMIN); + value = HAS_SECURE_BATCHES(i915) && capable(CAP_SYS_ADMIN); break; case I915_PARAM_CMD_PARSER_VERSION: value = i915_cmd_parser_get_version(i915); diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 8e251e719390..212acaef581e 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -843,8 +843,8 @@ create_event_attributes(struct i915_pmu *pmu) const char *name; const char *unit; } events[] = { - __event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "MHz"), - __event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "MHz"), + __event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "M"), + __event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "M"), __event(I915_PMU_INTERRUPTS, "interrupts", NULL), __event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"), }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2abd199093c5..f8ee9aba3955 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -471,6 +471,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ECOCHK_PPGTT_WT_HSW (0x2 << 3) #define ECOCHK_PPGTT_WB_HSW (0x3 << 3) +#define GEN8_RC6_CTX_INFO _MMIO(0x8504) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1 << 13) #define ECOBITS_PPGTT_CACHE64B (3 << 8) @@ -555,6 +557,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) */ #define BCS_SWCTRL _MMIO(0x22200) +/* There are 16 GPR registers */ +#define BCS_GPR(n) _MMIO(0x22600 + (n) * 8) +#define BCS_GPR_UDW(n) _MMIO(0x22600 + (n) * 8 + 4) + #define GPGPU_THREADS_DISPATCHED _MMIO(0x2290) #define GPGPU_THREADS_DISPATCHED_UDW _MMIO(0x2290 + 4) #define HS_INVOCATION_COUNT _MMIO(0x2300) @@ -7211,6 +7217,10 @@ enum { #define TGL_DMC_DEBUG_DC5_COUNT _MMIO(0x101084) #define TGL_DMC_DEBUG_DC6_COUNT _MMIO(0x101088) +/* Display Internal Timeout Register */ +#define RM_TIMEOUT _MMIO(0x42060) +#define MMIO_TIMEOUT_US(us) ((us) << 0) + /* interrupts */ #define DE_MASTER_IRQ_CONTROL (1 << 31) #define DE_SPRITEB_FLIP_DONE (1 << 29) diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 7b84ebca2901..3eba8a2b39c2 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -177,9 +177,37 @@ static inline int rq_prio(const struct i915_request *rq) return rq->sched.attr.priority | __NO_PREEMPTION; } -static void kick_submission(struct intel_engine_cs *engine, int prio) +static inline bool need_preempt(int prio, int active) { - const struct i915_request *inflight = *engine->execlists.active; + /* + * Allow preemption of low -> normal -> high, but we do + * not allow low priority tasks to preempt other low priority + * tasks under the impression that latency for low priority + * tasks does not matter (as much as background throughput), + * so kiss. + */ + return prio >= max(I915_PRIORITY_NORMAL, active); +} + +static void kick_submission(struct intel_engine_cs *engine, + const struct i915_request *rq, + int prio) +{ + const struct i915_request *inflight; + + /* + * We only need to kick the tasklet once for the high priority + * new context we add into the queue. + */ + if (prio <= engine->execlists.queue_priority_hint) + return; + + rcu_read_lock(); + + /* Nothing currently active? We're overdue for a submission! */ + inflight = execlists_active(&engine->execlists); + if (!inflight) + goto unlock; /* * If we are already the currently executing context, don't @@ -188,10 +216,15 @@ static void kick_submission(struct intel_engine_cs *engine, int prio) * tasklet, i.e. we have not change the priority queue * sufficiently to oust the running context. */ - if (!inflight || !i915_scheduler_need_preempt(prio, rq_prio(inflight))) - return; + if (inflight->hw_context == rq->hw_context) + goto unlock; - tasklet_hi_schedule(&engine->execlists.tasklet); + engine->execlists.queue_priority_hint = prio; + if (need_preempt(prio, rq_prio(inflight))) + tasklet_hi_schedule(&engine->execlists.tasklet); + +unlock: + rcu_read_unlock(); } static void __i915_schedule(struct i915_sched_node *node, @@ -317,13 +350,8 @@ static void __i915_schedule(struct i915_sched_node *node, list_move_tail(&node->link, cache.priolist); } - if (prio <= engine->execlists.queue_priority_hint) - continue; - - engine->execlists.queue_priority_hint = prio; - /* Defer (tasklet) submission until after all of our updates. */ - kick_submission(engine, prio); + kick_submission(engine, node_to_request(node), prio); } spin_unlock(&engine->active.lock); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 75ee027abb80..2efe1d12d5a9 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -126,6 +126,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv) */ I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) | PWM1_GATING_DIS | PWM2_GATING_DIS); + + /* + * Lower the display internal timeout. + * This is needed to avoid any hard hangs when DSI port PLL + * is off and a MMIO access is attempted by any privilege + * application, using batch buffers or any other means. + */ + I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950)); } static void glk_init_clock_gating(struct drm_i915_private *dev_priv) @@ -8544,6 +8552,100 @@ static void intel_init_emon(struct drm_i915_private *dev_priv) dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK); } +static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv) +{ + return !I915_READ(GEN8_RC6_CTX_INFO); +} + +static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + DRM_INFO("RC6 context corrupted, disabling runtime power management\n"); + i915->gt_pm.rc6.ctx_corrupted = true; + i915->gt_pm.rc6.ctx_corrupted_wakeref = + intel_runtime_pm_get(&i915->runtime_pm); + } +} + +static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915) +{ + if (i915->gt_pm.rc6.ctx_corrupted) { + intel_runtime_pm_put(&i915->runtime_pm, + i915->gt_pm.rc6.ctx_corrupted_wakeref); + i915->gt_pm.rc6.ctx_corrupted = false; + } +} + +/** + * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to clean up the RC6 CTX WA before system suspend. + */ +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915) +{ + if (i915->gt_pm.rc6.ctx_corrupted) + intel_runtime_pm_put(&i915->runtime_pm, + i915->gt_pm.rc6.ctx_corrupted_wakeref); +} + +/** + * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to re-init the RC6 CTX WA after system resume. + */ +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915) +{ + if (!i915->gt_pm.rc6.ctx_corrupted) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + i915->gt_pm.rc6.ctx_corrupted_wakeref = + intel_runtime_pm_get(&i915->runtime_pm); + return; + } + + DRM_INFO("RC6 context restored, re-enabling runtime power management\n"); + i915->gt_pm.rc6.ctx_corrupted = false; +} + +static void intel_disable_rc6(struct drm_i915_private *dev_priv); + +/** + * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption + * @i915: i915 device + * + * Check if an RC6 CTX corruption has happened since the last check and if so + * disable RC6 and runtime power management. + * + * Return false if no context corruption has happened since the last call of + * this function, true otherwise. +*/ +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return false; + + if (i915->gt_pm.rc6.ctx_corrupted) + return false; + + if (!i915_rc6_ctx_corrupted(i915)) + return false; + + DRM_NOTE("RC6 context corruption, disabling runtime power management\n"); + + intel_disable_rc6(i915); + i915->gt_pm.rc6.ctx_corrupted = true; + i915->gt_pm.rc6.ctx_corrupted_wakeref = + intel_runtime_pm_get_noresume(&i915->runtime_pm); + + return true; +} + void intel_init_gt_powersave(struct drm_i915_private *dev_priv) { struct intel_rps *rps = &dev_priv->gt_pm.rps; @@ -8557,6 +8659,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv) pm_runtime_get(&dev_priv->drm.pdev->dev); } + i915_rc6_ctx_wa_init(dev_priv); + /* Initialize RPS limits (for userspace) */ if (IS_CHERRYVIEW(dev_priv)) cherryview_init_gt_powersave(dev_priv); @@ -8595,6 +8699,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv) if (IS_VALLEYVIEW(dev_priv)) valleyview_cleanup_gt_powersave(dev_priv); + i915_rc6_ctx_wa_cleanup(dev_priv); + if (!HAS_RC6(dev_priv)) pm_runtime_put(&dev_priv->drm.pdev->dev); } @@ -8623,7 +8729,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915) i915->gt_pm.llc_pstate.enabled = false; } -static void intel_disable_rc6(struct drm_i915_private *dev_priv) +static void __intel_disable_rc6(struct drm_i915_private *dev_priv) { lockdep_assert_held(&dev_priv->gt_pm.rps.lock); @@ -8642,6 +8748,15 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv) dev_priv->gt_pm.rc6.enabled = false; } +static void intel_disable_rc6(struct drm_i915_private *dev_priv) +{ + struct intel_rps *rps = &dev_priv->gt_pm.rps; + + mutex_lock(&rps->lock); + __intel_disable_rc6(dev_priv); + mutex_unlock(&rps->lock); +} + static void intel_disable_rps(struct drm_i915_private *dev_priv) { lockdep_assert_held(&dev_priv->gt_pm.rps.lock); @@ -8667,7 +8782,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv) { mutex_lock(&dev_priv->gt_pm.rps.lock); - intel_disable_rc6(dev_priv); + __intel_disable_rc6(dev_priv); intel_disable_rps(dev_priv); if (HAS_LLC(dev_priv)) intel_disable_llc_pstate(dev_priv); @@ -8694,6 +8809,9 @@ static void intel_enable_rc6(struct drm_i915_private *dev_priv) if (dev_priv->gt_pm.rc6.enabled) return; + if (dev_priv->gt_pm.rc6.ctx_corrupted) + return; + if (IS_CHERRYVIEW(dev_priv)) cherryview_enable_rc6(dev_priv); else if (IS_VALLEYVIEW(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h index e3573e1e16e3..0f7390c850ec 100644 --- a/drivers/gpu/drm/i915/intel_pm.h +++ b/drivers/gpu/drm/i915/intel_pm.h @@ -36,6 +36,9 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv); void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv); void intel_enable_gt_powersave(struct drm_i915_private *dev_priv); void intel_disable_gt_powersave(struct drm_i915_private *dev_priv); +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915); void gen6_rps_busy(struct drm_i915_private *dev_priv); void gen6_rps_idle(struct drm_i915_private *dev_priv); void gen6_rps_boost(struct i915_request *rq); diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index bc2ddeb55f5d..f21bc8a7ee3a 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -556,11 +556,11 @@ static int panfrost_probe(struct platform_device *pdev) return 0; err_out2: + pm_runtime_disable(pfdev->dev); panfrost_devfreq_fini(pfdev); err_out1: panfrost_device_fini(pfdev); err_out0: - pm_runtime_disable(pfdev->dev); drm_dev_put(ddev); return err; } diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index bdd990568476..a3ed64a1f15e 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -224,9 +224,9 @@ static size_t get_pgsize(u64 addr, size_t size) return SZ_2M; } -void panfrost_mmu_flush_range(struct panfrost_device *pfdev, - struct panfrost_mmu *mmu, - u64 iova, size_t size) +static void panfrost_mmu_flush_range(struct panfrost_device *pfdev, + struct panfrost_mmu *mmu, + u64 iova, size_t size) { if (mmu->as < 0) return; @@ -406,11 +406,11 @@ addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr) spin_lock(&pfdev->as_lock); list_for_each_entry(mmu, &pfdev->as_lru_list, list) { if (as == mmu->as) - break; + goto found_mmu; } - if (as != mmu->as) - goto out; + goto out; +found_mmu: priv = container_of(mmu, struct panfrost_file_priv, mmu); spin_lock(&priv->mm_lock); @@ -432,7 +432,8 @@ out: #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE) -int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr) +static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, + u64 addr) { int ret, i; struct panfrost_gem_object *bo; diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c index 83c57d325ca8..2dba192bf198 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c @@ -16,6 +16,7 @@ #include "panfrost_issues.h" #include "panfrost_job.h" #include "panfrost_mmu.h" +#include "panfrost_perfcnt.h" #include "panfrost_regs.h" #define COUNTERS_PER_BLOCK 64 diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 9e55076578c6..4528f4dc0b2d 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -379,11 +379,25 @@ radeon_pci_remove(struct pci_dev *pdev) static void radeon_pci_shutdown(struct pci_dev *pdev) { +#ifdef CONFIG_PPC64 + struct drm_device *ddev = pci_get_drvdata(pdev); +#endif + /* if we are running in a VM, make sure the device * torn down properly on reboot/shutdown */ if (radeon_device_is_virtual()) radeon_pci_remove(pdev); + +#ifdef CONFIG_PPC64 + /* Some adapters need to be suspended before a + * shutdown occurs in order to prevent an error + * during kexec. + * Make this power specific becauase it breaks + * some non-power boards. + */ + radeon_suspend_kms(ddev, true, true, false); +#endif } static int radeon_pmops_suspend(struct device *dev) diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 460fd98e40a7..a0b382a637a6 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -1958,6 +1958,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev) case 0x682C: si_pi->cac_weights = cac_weights_cape_verde_pro; si_pi->dte_data = dte_data_sun_xt; + update_dte_from_pl2 = true; break; case 0x6825: case 0x6827: diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 9a0ee74d82dc..f39b97ed4ade 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -479,6 +479,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) struct drm_sched_job *s_job, *tmp; uint64_t guilty_context; bool found_guilty = false; + struct dma_fence *fence; list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { struct drm_sched_fence *s_fence = s_job->s_fence; @@ -492,7 +493,16 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) dma_fence_set_error(&s_fence->finished, -ECANCELED); dma_fence_put(s_job->s_fence->parent); - s_job->s_fence->parent = sched->ops->run_job(s_job); + fence = sched->ops->run_job(s_job); + + if (IS_ERR_OR_NULL(fence)) { + s_job->s_fence->parent = NULL; + dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); + } else { + s_job->s_fence->parent = fence; + } + + } } EXPORT_SYMBOL(drm_sched_resubmit_jobs); @@ -720,7 +730,7 @@ static int drm_sched_main(void *param) fence = sched->ops->run_job(sched_job); drm_sched_fence_scheduled(s_fence); - if (fence) { + if (!IS_ERR_OR_NULL(fence)) { s_fence->parent = dma_fence_get(fence); r = dma_fence_add_callback(fence, &sched_job->cb, drm_sched_process_job); @@ -730,8 +740,11 @@ static int drm_sched_main(void *param) DRM_ERROR("fence add callback failed (%d)\n", r); dma_fence_put(fence); - } else + } else { + + dma_fence_set_error(&s_fence->finished, PTR_ERR(fence)); drm_sched_process_job(NULL, &sched_job->cb); + } wake_up(&sched->job_scheduled); } diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 04c721d0d3b9..b89439ed210d 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -488,7 +488,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, WARN_ON(!tcon->quirks->has_channel_0); - tcon->dclk_min_div = 6; + tcon->dclk_min_div = 1; tcon->dclk_max_div = 127; sun4i_tcon0_mode_set_common(tcon, mode); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 5d80507b539b..19c092d75266 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -557,13 +557,16 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, if (args->bcl_start != args->bcl_end) { bin = kcalloc(1, sizeof(*bin), GFP_KERNEL); - if (!bin) + if (!bin) { + v3d_job_put(&render->base); return -ENOMEM; + } ret = v3d_job_init(v3d, file_priv, &bin->base, v3d_job_free, args->in_sync_bcl); if (ret) { v3d_job_put(&render->base); + kfree(bin); return ret; } diff --git a/drivers/hid/hid-axff.c b/drivers/hid/hid-axff.c index 6654c1550e2e..fbe4e16ab029 100644 --- a/drivers/hid/hid-axff.c +++ b/drivers/hid/hid-axff.c @@ -63,13 +63,20 @@ static int axff_init(struct hid_device *hid) { struct axff_device *axff; struct hid_report *report; - struct hid_input *hidinput = list_first_entry(&hid->inputs, struct hid_input, list); + struct hid_input *hidinput; struct list_head *report_list =&hid->report_enum[HID_OUTPUT_REPORT].report_list; - struct input_dev *dev = hidinput->input; + struct input_dev *dev; int field_count = 0; int i, j; int error; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_first_entry(&hid->inputs, struct hid_input, list); + dev = hidinput->input; + if (list_empty(report_list)) { hid_err(hid, "no output reports found\n"); return -ENODEV; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3eaee2c37931..63fdbf09b044 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1139,6 +1139,7 @@ int hid_open_report(struct hid_device *device) __u8 *start; __u8 *buf; __u8 *end; + __u8 *next; int ret; static int (*dispatch_type[])(struct hid_parser *parser, struct hid_item *item) = { @@ -1192,7 +1193,8 @@ int hid_open_report(struct hid_device *device) device->collection_size = HID_DEFAULT_NUM_COLLECTIONS; ret = -EINVAL; - while ((start = fetch_item(start, end, &item)) != NULL) { + while ((next = fetch_item(start, end, &item)) != NULL) { + start = next; if (item.format != HID_ITEM_FORMAT_SHORT) { hid_err(device, "unexpected long global item\n"); @@ -1230,7 +1232,8 @@ int hid_open_report(struct hid_device *device) } } - hid_err(device, "item fetching failed at offset %d\n", (int)(end - start)); + hid_err(device, "item fetching failed at offset %u/%u\n", + size - (unsigned int)(end - start), size); err: kfree(parser->collection_stack); alloc_err: diff --git a/drivers/hid/hid-dr.c b/drivers/hid/hid-dr.c index 17e17f9a597b..947f19f8685f 100644 --- a/drivers/hid/hid-dr.c +++ b/drivers/hid/hid-dr.c @@ -75,13 +75,19 @@ static int drff_init(struct hid_device *hid) { struct drff_device *drff; struct hid_report *report; - struct hid_input *hidinput = list_first_entry(&hid->inputs, - struct hid_input, list); + struct hid_input *hidinput; struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; - struct input_dev *dev = hidinput->input; + struct input_dev *dev; int error; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_first_entry(&hid->inputs, struct hid_input, list); + dev = hidinput->input; + if (list_empty(report_list)) { hid_err(hid, "no output reports found\n"); return -ENODEV; diff --git a/drivers/hid/hid-emsff.c b/drivers/hid/hid-emsff.c index 7cd5651872d3..c34f2e5a049f 100644 --- a/drivers/hid/hid-emsff.c +++ b/drivers/hid/hid-emsff.c @@ -47,13 +47,19 @@ static int emsff_init(struct hid_device *hid) { struct emsff_device *emsff; struct hid_report *report; - struct hid_input *hidinput = list_first_entry(&hid->inputs, - struct hid_input, list); + struct hid_input *hidinput; struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; - struct input_dev *dev = hidinput->input; + struct input_dev *dev; int error; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_first_entry(&hid->inputs, struct hid_input, list); + dev = hidinput->input; + if (list_empty(report_list)) { hid_err(hid, "no output reports found\n"); return -ENODEV; diff --git a/drivers/hid/hid-gaff.c b/drivers/hid/hid-gaff.c index 0f95c96b70f8..ecbd3995a4eb 100644 --- a/drivers/hid/hid-gaff.c +++ b/drivers/hid/hid-gaff.c @@ -64,14 +64,20 @@ static int gaff_init(struct hid_device *hid) { struct gaff_device *gaff; struct hid_report *report; - struct hid_input *hidinput = list_entry(hid->inputs.next, - struct hid_input, list); + struct hid_input *hidinput; struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; struct list_head *report_ptr = report_list; - struct input_dev *dev = hidinput->input; + struct input_dev *dev; int error; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + if (list_empty(report_list)) { hid_err(hid, "no output reports found\n"); return -ENODEV; diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 84f8c127ebdc..d86a9189e88f 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -470,6 +470,10 @@ static const struct hid_device_id hammer_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WAND) }, diff --git a/drivers/hid/hid-holtekff.c b/drivers/hid/hid-holtekff.c index 10a720558830..8619b80c834c 100644 --- a/drivers/hid/hid-holtekff.c +++ b/drivers/hid/hid-holtekff.c @@ -124,13 +124,19 @@ static int holtekff_init(struct hid_device *hid) { struct holtekff_device *holtekff; struct hid_report *report; - struct hid_input *hidinput = list_entry(hid->inputs.next, - struct hid_input, list); + struct hid_input *hidinput; struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; - struct input_dev *dev = hidinput->input; + struct input_dev *dev; int error; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + if (list_empty(report_list)) { hid_err(hid, "no output report found\n"); return -ENODEV; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 76969a22b0f2..447e8db21174 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -476,6 +476,8 @@ #define USB_DEVICE_ID_GOOGLE_STAFF 0x502b #define USB_DEVICE_ID_GOOGLE_WAND 0x502d #define USB_DEVICE_ID_GOOGLE_WHISKERS 0x5030 +#define USB_DEVICE_ID_GOOGLE_MASTERBALL 0x503c +#define USB_DEVICE_ID_GOOGLE_MAGNEMITE 0x503d #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f diff --git a/drivers/hid/hid-lg2ff.c b/drivers/hid/hid-lg2ff.c index dd1a6c3a7de6..73d07e35f12a 100644 --- a/drivers/hid/hid-lg2ff.c +++ b/drivers/hid/hid-lg2ff.c @@ -50,11 +50,17 @@ int lg2ff_init(struct hid_device *hid) { struct lg2ff_device *lg2ff; struct hid_report *report; - struct hid_input *hidinput = list_entry(hid->inputs.next, - struct hid_input, list); - struct input_dev *dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *dev; int error; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + /* Check that the report looks ok */ report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7); if (!report) diff --git a/drivers/hid/hid-lg3ff.c b/drivers/hid/hid-lg3ff.c index 9ecb6fd06203..b7e1949f3cf7 100644 --- a/drivers/hid/hid-lg3ff.c +++ b/drivers/hid/hid-lg3ff.c @@ -117,12 +117,19 @@ static const signed short ff3_joystick_ac[] = { int lg3ff_init(struct hid_device *hid) { - struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); - struct input_dev *dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *dev; const signed short *ff_bits = ff3_joystick_ac; int error; int i; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + /* Check that the report looks ok */ if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 35)) return -ENODEV; diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c index 03f0220062ca..5e6a0cef2a06 100644 --- a/drivers/hid/hid-lg4ff.c +++ b/drivers/hid/hid-lg4ff.c @@ -1253,8 +1253,8 @@ static int lg4ff_handle_multimode_wheel(struct hid_device *hid, u16 *real_produc int lg4ff_init(struct hid_device *hid) { - struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); - struct input_dev *dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *dev; struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; struct hid_report *report = list_entry(report_list->next, struct hid_report, list); const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor); @@ -1266,6 +1266,13 @@ int lg4ff_init(struct hid_device *hid) int mmode_ret, mmode_idx = -1; u16 real_product_id; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + /* Check that the report looks ok */ if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7)) return -1; diff --git a/drivers/hid/hid-lgff.c b/drivers/hid/hid-lgff.c index c79a6ec43745..aed4ddc397a9 100644 --- a/drivers/hid/hid-lgff.c +++ b/drivers/hid/hid-lgff.c @@ -115,12 +115,19 @@ static void hid_lgff_set_autocenter(struct input_dev *dev, u16 magnitude) int lgff_init(struct hid_device* hid) { - struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); - struct input_dev *dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *dev; const signed short *ff_bits = ff_joystick; int error; int i; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + /* Check that the report looks ok */ if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7)) return -ENODEV; diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 0179f7ed77e5..8e91e2f06cb4 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -1669,6 +1669,7 @@ static void hidpp_touchpad_raw_xy_event(struct hidpp_device *hidpp_dev, #define HIDPP_FF_EFFECTID_NONE -1 #define HIDPP_FF_EFFECTID_AUTOCENTER -2 +#define HIDPP_AUTOCENTER_PARAMS_LENGTH 18 #define HIDPP_FF_MAX_PARAMS 20 #define HIDPP_FF_RESERVED_SLOTS 1 @@ -2009,7 +2010,7 @@ static int hidpp_ff_erase_effect(struct input_dev *dev, int effect_id) static void hidpp_ff_set_autocenter(struct input_dev *dev, u16 magnitude) { struct hidpp_ff_private_data *data = dev->ff->private; - u8 params[18]; + u8 params[HIDPP_AUTOCENTER_PARAMS_LENGTH]; dbg_hid("Setting autocenter to %d.\n", magnitude); @@ -2077,23 +2078,34 @@ static DEVICE_ATTR(range, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, hidpp static void hidpp_ff_destroy(struct ff_device *ff) { struct hidpp_ff_private_data *data = ff->private; + struct hid_device *hid = data->hidpp->hid_dev; + hid_info(hid, "Unloading HID++ force feedback.\n"); + + device_remove_file(&hid->dev, &dev_attr_range); + destroy_workqueue(data->wq); kfree(data->effect_ids); } -static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) +static int hidpp_ff_init(struct hidpp_device *hidpp, + struct hidpp_ff_private_data *data) { struct hid_device *hid = hidpp->hid_dev; - struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); - struct input_dev *dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *dev; const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor); const u16 bcdDevice = le16_to_cpu(udesc->bcdDevice); struct ff_device *ff; - struct hidpp_report response; - struct hidpp_ff_private_data *data; - int error, j, num_slots; + int error, j, num_slots = data->num_effects; u8 version; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + if (!dev) { hid_err(hid, "Struct input_dev not set!\n"); return -EINVAL; @@ -2109,27 +2121,17 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) for (j = 0; hidpp_ff_effects_v2[j] >= 0; j++) set_bit(hidpp_ff_effects_v2[j], dev->ffbit); - /* Read number of slots available in device */ - error = hidpp_send_fap_command_sync(hidpp, feature_index, - HIDPP_FF_GET_INFO, NULL, 0, &response); - if (error) { - if (error < 0) - return error; - hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n", - __func__, error); - return -EPROTO; - } - - num_slots = response.fap.params[0] - HIDPP_FF_RESERVED_SLOTS; - error = input_ff_create(dev, num_slots); if (error) { hid_err(dev, "Failed to create FF device!\n"); return error; } - - data = kzalloc(sizeof(*data), GFP_KERNEL); + /* + * Create a copy of passed data, so we can transfer memory + * ownership to FF core + */ + data = kmemdup(data, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->effect_ids = kcalloc(num_slots, sizeof(int), GFP_KERNEL); @@ -2145,10 +2147,7 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) } data->hidpp = hidpp; - data->feature_index = feature_index; data->version = version; - data->slot_autocenter = 0; - data->num_effects = num_slots; for (j = 0; j < num_slots; j++) data->effect_ids[j] = -1; @@ -2162,68 +2161,20 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) ff->set_autocenter = hidpp_ff_set_autocenter; ff->destroy = hidpp_ff_destroy; - - /* reset all forces */ - error = hidpp_send_fap_command_sync(hidpp, feature_index, - HIDPP_FF_RESET_ALL, NULL, 0, &response); - - /* Read current Range */ - error = hidpp_send_fap_command_sync(hidpp, feature_index, - HIDPP_FF_GET_APERTURE, NULL, 0, &response); - if (error) - hid_warn(hidpp->hid_dev, "Failed to read range from device!\n"); - data->range = error ? 900 : get_unaligned_be16(&response.fap.params[0]); - /* Create sysfs interface */ error = device_create_file(&(hidpp->hid_dev->dev), &dev_attr_range); if (error) hid_warn(hidpp->hid_dev, "Unable to create sysfs interface for \"range\", errno %d!\n", error); - /* Read the current gain values */ - error = hidpp_send_fap_command_sync(hidpp, feature_index, - HIDPP_FF_GET_GLOBAL_GAINS, NULL, 0, &response); - if (error) - hid_warn(hidpp->hid_dev, "Failed to read gain values from device!\n"); - data->gain = error ? 0xffff : get_unaligned_be16(&response.fap.params[0]); - /* ignore boost value at response.fap.params[2] */ - /* init the hardware command queue */ atomic_set(&data->workqueue_size, 0); - /* initialize with zero autocenter to get wheel in usable state */ - hidpp_ff_set_autocenter(dev, 0); - hid_info(hid, "Force feedback support loaded (firmware release %d).\n", version); return 0; } -static int hidpp_ff_deinit(struct hid_device *hid) -{ - struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); - struct input_dev *dev = hidinput->input; - struct hidpp_ff_private_data *data; - - if (!dev) { - hid_err(hid, "Struct input_dev not found!\n"); - return -EINVAL; - } - - hid_info(hid, "Unloading HID++ force feedback.\n"); - data = dev->ff->private; - if (!data) { - hid_err(hid, "Private data not found!\n"); - return -EINVAL; - } - - destroy_workqueue(data->wq); - device_remove_file(&hid->dev, &dev_attr_range); - - return 0; -} - - /* ************************************************************************** */ /* */ /* Device Support */ @@ -2725,24 +2676,93 @@ static int k400_connect(struct hid_device *hdev, bool connected) #define HIDPP_PAGE_G920_FORCE_FEEDBACK 0x8123 -static int g920_get_config(struct hidpp_device *hidpp) +static int g920_ff_set_autocenter(struct hidpp_device *hidpp, + struct hidpp_ff_private_data *data) { + struct hidpp_report response; + u8 params[HIDPP_AUTOCENTER_PARAMS_LENGTH] = { + [1] = HIDPP_FF_EFFECT_SPRING | HIDPP_FF_EFFECT_AUTOSTART, + }; + int ret; + + /* initialize with zero autocenter to get wheel in usable state */ + + dbg_hid("Setting autocenter to 0.\n"); + ret = hidpp_send_fap_command_sync(hidpp, data->feature_index, + HIDPP_FF_DOWNLOAD_EFFECT, + params, ARRAY_SIZE(params), + &response); + if (ret) + hid_warn(hidpp->hid_dev, "Failed to autocenter device!\n"); + else + data->slot_autocenter = response.fap.params[0]; + + return ret; +} + +static int g920_get_config(struct hidpp_device *hidpp, + struct hidpp_ff_private_data *data) +{ + struct hidpp_report response; u8 feature_type; - u8 feature_index; int ret; + memset(data, 0, sizeof(*data)); + /* Find feature and store for later use */ ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_G920_FORCE_FEEDBACK, - &feature_index, &feature_type); + &data->feature_index, &feature_type); if (ret) return ret; - ret = hidpp_ff_init(hidpp, feature_index); + /* Read number of slots available in device */ + ret = hidpp_send_fap_command_sync(hidpp, data->feature_index, + HIDPP_FF_GET_INFO, + NULL, 0, + &response); + if (ret) { + if (ret < 0) + return ret; + hid_err(hidpp->hid_dev, + "%s: received protocol error 0x%02x\n", __func__, ret); + return -EPROTO; + } + + data->num_effects = response.fap.params[0] - HIDPP_FF_RESERVED_SLOTS; + + /* reset all forces */ + ret = hidpp_send_fap_command_sync(hidpp, data->feature_index, + HIDPP_FF_RESET_ALL, + NULL, 0, + &response); if (ret) - hid_warn(hidpp->hid_dev, "Unable to initialize force feedback support, errno %d\n", - ret); + hid_warn(hidpp->hid_dev, "Failed to reset all forces!\n"); - return 0; + ret = hidpp_send_fap_command_sync(hidpp, data->feature_index, + HIDPP_FF_GET_APERTURE, + NULL, 0, + &response); + if (ret) { + hid_warn(hidpp->hid_dev, + "Failed to read range from device!\n"); + } + data->range = ret ? + 900 : get_unaligned_be16(&response.fap.params[0]); + + /* Read the current gain values */ + ret = hidpp_send_fap_command_sync(hidpp, data->feature_index, + HIDPP_FF_GET_GLOBAL_GAINS, + NULL, 0, + &response); + if (ret) + hid_warn(hidpp->hid_dev, + "Failed to read gain values from device!\n"); + data->gain = ret ? + 0xffff : get_unaligned_be16(&response.fap.params[0]); + + /* ignore boost value at response.fap.params[2] */ + + return g920_ff_set_autocenter(hidpp, data); } /* -------------------------------------------------------------------------- */ @@ -3458,34 +3478,45 @@ static int hidpp_get_report_length(struct hid_device *hdev, int id) return report->field[0]->report_count + 1; } -static bool hidpp_validate_report(struct hid_device *hdev, int id, - int expected_length, bool optional) +static bool hidpp_validate_device(struct hid_device *hdev) { - int report_length; + struct hidpp_device *hidpp = hid_get_drvdata(hdev); + int id, report_length, supported_reports = 0; - if (id >= HID_MAX_IDS || id < 0) { - hid_err(hdev, "invalid HID report id %u\n", id); - return false; + id = REPORT_ID_HIDPP_SHORT; + report_length = hidpp_get_report_length(hdev, id); + if (report_length) { + if (report_length < HIDPP_REPORT_SHORT_LENGTH) + goto bad_device; + + supported_reports++; } + id = REPORT_ID_HIDPP_LONG; report_length = hidpp_get_report_length(hdev, id); - if (!report_length) - return optional; + if (report_length) { + if (report_length < HIDPP_REPORT_LONG_LENGTH) + goto bad_device; - if (report_length < expected_length) { - hid_warn(hdev, "not enough values in hidpp report %d\n", id); - return false; + supported_reports++; } - return true; -} + id = REPORT_ID_HIDPP_VERY_LONG; + report_length = hidpp_get_report_length(hdev, id); + if (report_length) { + if (report_length < HIDPP_REPORT_LONG_LENGTH || + report_length > HIDPP_REPORT_VERY_LONG_MAX_LENGTH) + goto bad_device; -static bool hidpp_validate_device(struct hid_device *hdev) -{ - return hidpp_validate_report(hdev, REPORT_ID_HIDPP_SHORT, - HIDPP_REPORT_SHORT_LENGTH, false) && - hidpp_validate_report(hdev, REPORT_ID_HIDPP_LONG, - HIDPP_REPORT_LONG_LENGTH, true); + supported_reports++; + hidpp->very_long_report_length = report_length; + } + + return supported_reports; + +bad_device: + hid_warn(hdev, "not enough values in hidpp report %d\n", id); + return false; } static bool hidpp_application_equals(struct hid_device *hdev, @@ -3505,6 +3536,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) int ret; bool connected; unsigned int connect_mask = HID_CONNECT_DEFAULT; + struct hidpp_ff_private_data data; /* report_fixup needs drvdata to be set before we call hid_parse */ hidpp = devm_kzalloc(&hdev->dev, sizeof(*hidpp), GFP_KERNEL); @@ -3531,11 +3563,6 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) return hid_hw_start(hdev, HID_CONNECT_DEFAULT); } - hidpp->very_long_report_length = - hidpp_get_report_length(hdev, REPORT_ID_HIDPP_VERY_LONG); - if (hidpp->very_long_report_length > HIDPP_REPORT_VERY_LONG_MAX_LENGTH) - hidpp->very_long_report_length = HIDPP_REPORT_VERY_LONG_MAX_LENGTH; - if (id->group == HID_GROUP_LOGITECH_DJ_DEVICE) hidpp->quirks |= HIDPP_QUIRK_UNIFYING; @@ -3614,7 +3641,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret) goto hid_hw_init_fail; } else if (connected && (hidpp->quirks & HIDPP_QUIRK_CLASS_G920)) { - ret = g920_get_config(hidpp); + ret = g920_get_config(hidpp, &data); if (ret) goto hid_hw_init_fail; } @@ -3636,6 +3663,14 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) goto hid_hw_start_fail; } + if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) { + ret = hidpp_ff_init(hidpp, &data); + if (ret) + hid_warn(hidpp->hid_dev, + "Unable to initialize force feedback support, errno %d\n", + ret); + } + return ret; hid_hw_init_fail: @@ -3658,9 +3693,6 @@ static void hidpp_remove(struct hid_device *hdev) sysfs_remove_group(&hdev->dev.kobj, &ps_attribute_group); - if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) - hidpp_ff_deinit(hdev); - hid_hw_stop(hdev); cancel_work_sync(&hidpp->work); mutex_destroy(&hidpp->send_mutex); diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index 2cf83856f2e4..2d8b589201a4 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -328,11 +328,17 @@ static int ms_play_effect(struct input_dev *dev, void *data, static int ms_init_ff(struct hid_device *hdev) { - struct hid_input *hidinput = list_entry(hdev->inputs.next, - struct hid_input, list); - struct input_dev *input_dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *input_dev; struct ms_data *ms = hid_get_drvdata(hdev); + if (list_empty(&hdev->inputs)) { + hid_err(hdev, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hdev->inputs.next, struct hid_input, list); + input_dev = hidinput->input; + if (!(ms->quirks & MS_QUIRK_FF)) return 0; diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c index 5a3b3d974d84..2666af02d5c1 100644 --- a/drivers/hid/hid-prodikeys.c +++ b/drivers/hid/hid-prodikeys.c @@ -516,7 +516,7 @@ static void pcmidi_setup_extra_keys( MY PICTURES => KEY_WORDPROCESSOR MY MUSIC=> KEY_SPREADSHEET */ - unsigned int keys[] = { + static const unsigned int keys[] = { KEY_FN, KEY_MESSENGER, KEY_CALENDAR, KEY_ADDRESSBOOK, KEY_DOCUMENTS, @@ -532,7 +532,7 @@ static void pcmidi_setup_extra_keys( 0 }; - unsigned int *pkeys = &keys[0]; + const unsigned int *pkeys = &keys[0]; unsigned short i; if (pm->ifnum != 1) /* only set up ONCE for interace 1 */ diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 73c0f7a95e2d..4c6ed6ef31f1 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -2254,9 +2254,15 @@ static int sony_play_effect(struct input_dev *dev, void *data, static int sony_init_ff(struct sony_sc *sc) { - struct hid_input *hidinput = list_entry(sc->hdev->inputs.next, - struct hid_input, list); - struct input_dev *input_dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *input_dev; + + if (list_empty(&sc->hdev->inputs)) { + hid_err(sc->hdev, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(sc->hdev->inputs.next, struct hid_input, list); + input_dev = hidinput->input; input_set_capability(input_dev, EV_FF, FF_RUMBLE); return input_ff_create_memless(input_dev, NULL, sony_play_effect); diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c index bdfc5ff3b2c5..90acef304536 100644 --- a/drivers/hid/hid-tmff.c +++ b/drivers/hid/hid-tmff.c @@ -124,12 +124,18 @@ static int tmff_init(struct hid_device *hid, const signed short *ff_bits) struct tmff_device *tmff; struct hid_report *report; struct list_head *report_list; - struct hid_input *hidinput = list_entry(hid->inputs.next, - struct hid_input, list); - struct input_dev *input_dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *input_dev; int error; int i; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + input_dev = hidinput->input; + tmff = kzalloc(sizeof(struct tmff_device), GFP_KERNEL); if (!tmff) return -ENOMEM; diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c index f90959e94028..3abaca045869 100644 --- a/drivers/hid/hid-zpff.c +++ b/drivers/hid/hid-zpff.c @@ -54,11 +54,17 @@ static int zpff_init(struct hid_device *hid) { struct zpff_device *zpff; struct hid_report *report; - struct hid_input *hidinput = list_entry(hid->inputs.next, - struct hid_input, list); - struct input_dev *dev = hidinput->input; + struct hid_input *hidinput; + struct input_dev *dev; int i, error; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + hidinput = list_entry(hid->inputs.next, struct hid_input, list); + dev = hidinput->input; + for (i = 0; i < 4; i++) { report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1); if (!report) diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 2a7c6e33bb1c..04c088131e04 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -26,7 +26,6 @@ #include <linux/delay.h> #include <linux/slab.h> #include <linux/pm.h> -#include <linux/pm_runtime.h> #include <linux/device.h> #include <linux/wait.h> #include <linux/err.h> @@ -48,8 +47,6 @@ /* quirks to control the device */ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1) -#define I2C_HID_QUIRK_NO_RUNTIME_PM BIT(2) -#define I2C_HID_QUIRK_DELAY_AFTER_SLEEP BIT(3) #define I2C_HID_QUIRK_BOGUS_IRQ BIT(4) /* flags */ @@ -172,14 +169,7 @@ static const struct i2c_hid_quirks { { USB_VENDOR_ID_WEIDA, HID_ANY_ID, I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV }, { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, - I2C_HID_QUIRK_NO_IRQ_AFTER_RESET | - I2C_HID_QUIRK_NO_RUNTIME_PM }, - { I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_4B33, - I2C_HID_QUIRK_DELAY_AFTER_SLEEP }, - { USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_8001, - I2C_HID_QUIRK_NO_RUNTIME_PM }, - { I2C_VENDOR_ID_GOODIX, I2C_DEVICE_ID_GOODIX_01F0, - I2C_HID_QUIRK_NO_RUNTIME_PM }, + I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, { USB_VENDOR_ID_ELAN, HID_ANY_ID, I2C_HID_QUIRK_BOGUS_IRQ }, { 0, 0 } @@ -397,7 +387,6 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) { struct i2c_hid *ihid = i2c_get_clientdata(client); int ret; - unsigned long now, delay; i2c_hid_dbg(ihid, "%s\n", __func__); @@ -415,22 +404,9 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) goto set_pwr_exit; } - if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && - power_state == I2C_HID_PWR_ON) { - now = jiffies; - if (time_after(ihid->sleep_delay, now)) { - delay = jiffies_to_usecs(ihid->sleep_delay - now); - usleep_range(delay, delay + 1); - } - } - ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state, 0, NULL, 0, NULL, 0); - if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && - power_state == I2C_HID_PWR_SLEEP) - ihid->sleep_delay = jiffies + msecs_to_jiffies(20); - if (ret) dev_err(&client->dev, "failed to change power setting.\n"); @@ -471,8 +447,12 @@ static int i2c_hid_hwreset(struct i2c_client *client) if (ret) { dev_err(&client->dev, "failed to reset device.\n"); i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); + goto out_unlock; } + /* At least some SIS devices need this after reset */ + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); + out_unlock: mutex_unlock(&ihid->reset_lock); return ret; @@ -791,11 +771,6 @@ static int i2c_hid_open(struct hid_device *hid) { struct i2c_client *client = hid->driver_data; struct i2c_hid *ihid = i2c_get_clientdata(client); - int ret = 0; - - ret = pm_runtime_get_sync(&client->dev); - if (ret < 0) - return ret; set_bit(I2C_HID_STARTED, &ihid->flags); return 0; @@ -807,27 +782,6 @@ static void i2c_hid_close(struct hid_device *hid) struct i2c_hid *ihid = i2c_get_clientdata(client); clear_bit(I2C_HID_STARTED, &ihid->flags); - - /* Save some power */ - pm_runtime_put(&client->dev); -} - -static int i2c_hid_power(struct hid_device *hid, int lvl) -{ - struct i2c_client *client = hid->driver_data; - struct i2c_hid *ihid = i2c_get_clientdata(client); - - i2c_hid_dbg(ihid, "%s lvl:%d\n", __func__, lvl); - - switch (lvl) { - case PM_HINT_FULLON: - pm_runtime_get_sync(&client->dev); - break; - case PM_HINT_NORMAL: - pm_runtime_put(&client->dev); - break; - } - return 0; } struct hid_ll_driver i2c_hid_ll_driver = { @@ -836,7 +790,6 @@ struct hid_ll_driver i2c_hid_ll_driver = { .stop = i2c_hid_stop, .open = i2c_hid_open, .close = i2c_hid_close, - .power = i2c_hid_power, .output_report = i2c_hid_output_report, .raw_request = i2c_hid_raw_request, }; @@ -1104,9 +1057,6 @@ static int i2c_hid_probe(struct i2c_client *client, i2c_hid_acpi_fix_up_power(&client->dev); - pm_runtime_get_noresume(&client->dev); - pm_runtime_set_active(&client->dev); - pm_runtime_enable(&client->dev); device_enable_async_suspend(&client->dev); /* Make sure there is something at this address */ @@ -1114,16 +1064,16 @@ static int i2c_hid_probe(struct i2c_client *client, if (ret < 0) { dev_dbg(&client->dev, "nothing at this address: %d\n", ret); ret = -ENXIO; - goto err_pm; + goto err_regulator; } ret = i2c_hid_fetch_hid_descriptor(ihid); if (ret < 0) - goto err_pm; + goto err_regulator; ret = i2c_hid_init_irq(client); if (ret < 0) - goto err_pm; + goto err_regulator; hid = hid_allocate_device(); if (IS_ERR(hid)) { @@ -1154,9 +1104,6 @@ static int i2c_hid_probe(struct i2c_client *client, goto err_mem_free; } - if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM)) - pm_runtime_put(&client->dev); - return 0; err_mem_free: @@ -1165,10 +1112,6 @@ err_mem_free: err_irq: free_irq(client->irq, ihid); -err_pm: - pm_runtime_put_noidle(&client->dev); - pm_runtime_disable(&client->dev); - err_regulator: regulator_bulk_disable(ARRAY_SIZE(ihid->pdata.supplies), ihid->pdata.supplies); @@ -1181,12 +1124,6 @@ static int i2c_hid_remove(struct i2c_client *client) struct i2c_hid *ihid = i2c_get_clientdata(client); struct hid_device *hid; - if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM)) - pm_runtime_get_sync(&client->dev); - pm_runtime_disable(&client->dev); - pm_runtime_set_suspended(&client->dev); - pm_runtime_put_noidle(&client->dev); - hid = ihid->hid; hid_destroy_device(hid); @@ -1219,25 +1156,15 @@ static int i2c_hid_suspend(struct device *dev) int wake_status; if (hid->driver && hid->driver->suspend) { - /* - * Wake up the device so that IO issues in - * HID driver's suspend code can succeed. - */ - ret = pm_runtime_resume(dev); - if (ret < 0) - return ret; - ret = hid->driver->suspend(hid, PMSG_SUSPEND); if (ret < 0) return ret; } - if (!pm_runtime_suspended(dev)) { - /* Save some power */ - i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); + /* Save some power */ + i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); - disable_irq(client->irq); - } + disable_irq(client->irq); if (device_may_wakeup(&client->dev)) { wake_status = enable_irq_wake(client->irq); @@ -1279,11 +1206,6 @@ static int i2c_hid_resume(struct device *dev) wake_status); } - /* We'll resume to full power */ - pm_runtime_disable(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - enable_irq(client->irq); /* Instead of resetting device, simply powers the device on. This @@ -1304,30 +1226,8 @@ static int i2c_hid_resume(struct device *dev) } #endif -#ifdef CONFIG_PM -static int i2c_hid_runtime_suspend(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - - i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); - disable_irq(client->irq); - return 0; -} - -static int i2c_hid_runtime_resume(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - - enable_irq(client->irq); - i2c_hid_set_power(client, I2C_HID_PWR_ON); - return 0; -} -#endif - static const struct dev_pm_ops i2c_hid_pm = { SET_SYSTEM_SLEEP_PM_OPS(i2c_hid_suspend, i2c_hid_resume) - SET_RUNTIME_PM_OPS(i2c_hid_runtime_suspend, i2c_hid_runtime_resume, - NULL) }; static const struct i2c_device_id i2c_hid_id_table[] = { diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index 75078c83be1a..d31ea82b84c1 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -323,6 +323,25 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { .driver_data = (void *)&sipodev_desc }, { + /* + * There are at least 2 Primebook C11B versions, the older + * version has a product-name of "Primebook C11B", and a + * bios version / release / firmware revision of: + * V2.1.2 / 05/03/2018 / 18.2 + * The new version has "PRIMEBOOK C11B" as product-name and a + * bios version / release / firmware revision of: + * CFALKSW05_BIOS_V1.1.2 / 11/19/2018 / 19.2 + * Only the older version needs this quirk, note the newer + * version will not match as it has a different product-name. + */ + .ident = "Trekstor Primebook C11B", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Primebook C11B"), + }, + .driver_data = (void *)&sipodev_desc + }, + { .ident = "Direkt-Tek DTLAPY116-2", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), diff --git a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c index 1b0a0cc605e7..513d7a4a1b8a 100644 --- a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c +++ b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c @@ -84,7 +84,7 @@ int ishtp_cl_alloc_tx_ring(struct ishtp_cl *cl) return 0; out: dev_err(&cl->device->dev, "error in allocating Tx pool\n"); - ishtp_cl_free_rx_ring(cl); + ishtp_cl_free_tx_ring(cl); return -ENOMEM; } diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h index 4a7f8d363220..203d27d198b8 100644 --- a/drivers/hid/wacom.h +++ b/drivers/hid/wacom.h @@ -202,6 +202,21 @@ static inline void wacom_schedule_work(struct wacom_wac *wacom_wac, } } +/* + * Convert a signed 32-bit integer to an unsigned n-bit integer. Undoes + * the normally-helpful work of 'hid_snto32' for fields that use signed + * ranges for questionable reasons. + */ +static inline __u32 wacom_s32tou(s32 value, __u8 n) +{ + switch (n) { + case 8: return ((__u8)value); + case 16: return ((__u16)value); + case 32: return ((__u32)value); + } + return value & (1 << (n - 1)) ? value & (~(~0U << n)) : value; +} + extern const struct hid_device_id wacom_ids[]; void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 2b0a5b8ca6e6..ccb74529bc78 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2303,7 +2303,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field case HID_DG_TOOLSERIALNUMBER: if (value) { wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); - wacom_wac->serial[0] |= (__u32)value; + wacom_wac->serial[0] |= wacom_s32tou(value, field->report_size); } return; case HID_DG_TWIST: @@ -2319,15 +2319,17 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field return; case WACOM_HID_WD_SERIALHI: if (value) { + __u32 raw_value = wacom_s32tou(value, field->report_size); + wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF); - wacom_wac->serial[0] |= ((__u64)value) << 32; + wacom_wac->serial[0] |= ((__u64)raw_value) << 32; /* * Non-USI EMR devices may contain additional tool type * information here. See WACOM_HID_WD_TOOLTYPE case for * more details. */ if (value >> 20 == 1) { - wacom_wac->id[0] |= value & 0xFFFFF; + wacom_wac->id[0] |= raw_value & 0xFFFFF; } } return; @@ -2339,7 +2341,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field * bitwise OR so the complete value can be built * up over time :( */ - wacom_wac->id[0] |= value; + wacom_wac->id[0] |= wacom_s32tou(value, field->report_size); return; case WACOM_HID_WD_OFFSETLEFT: if (features->offset_left && value != features->offset_left) diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c index 0037e2bdacd6..8a51dcf055ea 100644 --- a/drivers/hwmon/ina3221.c +++ b/drivers/hwmon/ina3221.c @@ -170,7 +170,7 @@ static inline int ina3221_wait_for_data(struct ina3221_data *ina) /* Polling the CVRF bit to make sure read data is ready */ return regmap_field_read_poll_timeout(ina->fields[F_CVRF], - cvrf, cvrf, wait, 100000); + cvrf, cvrf, wait, wait * 2); } static int ina3221_read_value(struct ina3221_data *ina, unsigned int reg, diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index b26419dbe840..281c81edabc6 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -82,6 +82,10 @@ #define FANCTL1_FMR_REG 0x00 /* Bank 3; 1 reg per channel */ #define FANCTL1_OUT_REG 0x10 /* Bank 3; 1 reg per channel */ +#define VOLT_MONITOR_MODE 0x0 +#define THERMAL_DIODE_MODE 0x1 +#define THERMISTOR_MODE 0x3 + #define ENABLE_TSI BIT(1) static const unsigned short normal_i2c[] = { @@ -935,11 +939,16 @@ static int nct7904_probe(struct i2c_client *client, for (i = 0; i < 4; i++) { val = (ret >> (i * 2)) & 0x03; bit = (1 << i); - if (val == 0) { + if (val == VOLT_MONITOR_MODE) { data->tcpu_mask &= ~bit; + } else if (val == THERMAL_DIODE_MODE && i < 2) { + data->temp_mode |= bit; + data->vsen_mask &= ~(0x06 << (i * 2)); + } else if (val == THERMISTOR_MODE) { + data->vsen_mask &= ~(0x02 << (i * 2)); } else { - if (val == 0x1 || val == 0x2) - data->temp_mode |= bit; + /* Reserved */ + data->tcpu_mask &= ~bit; data->vsen_mask &= ~(0x06 << (i * 2)); } } diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c index fa9d34af87ac..f72803a02391 100644 --- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -626,6 +626,9 @@ static void intel_th_gth_switch(struct intel_th_device *thdev, if (!count) dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n"); + /* De-assert the trigger */ + iowrite32(0, gth->base + REG_CTS_CTL); + intel_th_gth_stop(gth, output, false); intel_th_gth_start(gth, output); } diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index fc9f15f36ad4..6d240dfae9d9 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -164,7 +164,7 @@ struct msc { }; static LIST_HEAD(msu_buffer_list); -static struct mutex msu_buffer_mutex; +static DEFINE_MUTEX(msu_buffer_mutex); /** * struct msu_buffer_entry - internal MSU buffer bookkeeping @@ -327,7 +327,7 @@ static size_t msc_win_total_sz(struct msc_window *win) struct msc_block_desc *bdesc = sg_virt(sg); if (msc_block_wrapped(bdesc)) - return win->nr_blocks << PAGE_SHIFT; + return (size_t)win->nr_blocks << PAGE_SHIFT; size += msc_total_sz(bdesc); if (msc_block_last_written(bdesc)) @@ -1848,9 +1848,14 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf, len = cp - buf; mode = kstrndup(buf, len, GFP_KERNEL); + if (!mode) + return -ENOMEM; + i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode); - if (i >= 0) + if (i >= 0) { + kfree(mode); goto found; + } /* Buffer sinks only work with a usable IRQ */ if (!msc->do_irq) { diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 91dfeba62485..03ca5b1bef9f 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -200,6 +200,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)&intel_th_2x, }, { + /* Comet Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x06a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { /* Ice Lake NNPI */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5), .driver_data = (kernel_ulong_t)&intel_th_2x, @@ -209,6 +214,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Jasper Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index fa66951b05d0..7b098ff5f5dd 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -108,6 +108,12 @@ #define ASPEED_I2CD_S_TX_CMD BIT(2) #define ASPEED_I2CD_M_TX_CMD BIT(1) #define ASPEED_I2CD_M_START_CMD BIT(0) +#define ASPEED_I2CD_MASTER_CMDS_MASK \ + (ASPEED_I2CD_M_STOP_CMD | \ + ASPEED_I2CD_M_S_RX_CMD_LAST | \ + ASPEED_I2CD_M_RX_CMD | \ + ASPEED_I2CD_M_TX_CMD | \ + ASPEED_I2CD_M_START_CMD) /* 0x18 : I2CD Slave Device Address Register */ #define ASPEED_I2CD_DEV_ADDR_MASK GENMASK(6, 0) @@ -336,18 +342,19 @@ static void aspeed_i2c_do_start(struct aspeed_i2c_bus *bus) struct i2c_msg *msg = &bus->msgs[bus->msgs_index]; u8 slave_addr = i2c_8bit_addr_from_msg(msg); - bus->master_state = ASPEED_I2C_MASTER_START; - #if IS_ENABLED(CONFIG_I2C_SLAVE) /* * If it's requested in the middle of a slave session, set the master * state to 'pending' then H/W will continue handling this master * command when the bus comes back to the idle state. */ - if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE) + if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE) { bus->master_state = ASPEED_I2C_MASTER_PENDING; + return; + } #endif /* CONFIG_I2C_SLAVE */ + bus->master_state = ASPEED_I2C_MASTER_START; bus->buf_index = 0; if (msg->flags & I2C_M_RD) { @@ -422,20 +429,6 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status) } } -#if IS_ENABLED(CONFIG_I2C_SLAVE) - /* - * A pending master command will be started by H/W when the bus comes - * back to idle state after completing a slave operation so change the - * master state from 'pending' to 'start' at here if slave is inactive. - */ - if (bus->master_state == ASPEED_I2C_MASTER_PENDING) { - if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE) - goto out_no_complete; - - bus->master_state = ASPEED_I2C_MASTER_START; - } -#endif /* CONFIG_I2C_SLAVE */ - /* Master is not currently active, irq was for someone else. */ if (bus->master_state == ASPEED_I2C_MASTER_INACTIVE || bus->master_state == ASPEED_I2C_MASTER_PENDING) @@ -462,11 +455,15 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status) #if IS_ENABLED(CONFIG_I2C_SLAVE) /* * If a peer master starts a xfer immediately after it queues a - * master command, change its state to 'pending' then H/W will - * continue the queued master xfer just after completing the - * slave mode session. + * master command, clear the queued master command and change + * its state to 'pending'. To simplify handling of pending + * cases, it uses S/W solution instead of H/W command queue + * handling. */ if (unlikely(irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH)) { + writel(readl(bus->base + ASPEED_I2C_CMD_REG) & + ~ASPEED_I2CD_MASTER_CMDS_MASK, + bus->base + ASPEED_I2C_CMD_REG); bus->master_state = ASPEED_I2C_MASTER_PENDING; dev_dbg(bus->dev, "master goes pending due to a slave start\n"); @@ -629,6 +626,14 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id) irq_handled |= aspeed_i2c_master_irq(bus, irq_remaining); } + + /* + * Start a pending master command at here if a slave operation is + * completed. + */ + if (bus->master_state == ASPEED_I2C_MASTER_PENDING && + bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE) + aspeed_i2c_do_start(bus); #else irq_handled = aspeed_i2c_master_irq(bus, irq_remaining); #endif /* CONFIG_I2C_SLAVE */ @@ -691,6 +696,15 @@ static int aspeed_i2c_master_xfer(struct i2c_adapter *adap, ASPEED_I2CD_BUS_BUSY_STS)) aspeed_i2c_recover_bus(bus); + /* + * If timed out and the state is still pending, drop the pending + * master command. + */ + spin_lock_irqsave(&bus->lock, flags); + if (bus->master_state == ASPEED_I2C_MASTER_PENDING) + bus->master_state = ASPEED_I2C_MASTER_INACTIVE; + spin_unlock_irqrestore(&bus->lock, flags); + return -ETIMEDOUT; } diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 29eae1bf4f86..2152ec5f535c 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -875,7 +875,7 @@ static irqreturn_t mtk_i2c_irq(int irqno, void *dev_id) static u32 mtk_i2c_functionality(struct i2c_adapter *adap) { - if (adap->quirks->flags & I2C_AQ_NO_ZERO_LEN) + if (i2c_check_quirks(adap, I2C_AQ_NO_ZERO_LEN)) return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK); else diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index d36cf08461f7..b24e7b937f21 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -305,7 +305,7 @@ struct stm32f7_i2c_dev { struct regmap *regmap; }; -/** +/* * All these values are coming from I2C Specification, Version 6.0, 4th of * April 2014. * @@ -1192,6 +1192,8 @@ static void stm32f7_i2c_slave_start(struct stm32f7_i2c_dev *i2c_dev) STM32F7_I2C_CR1_TXIE; stm32f7_i2c_set_bits(base + STM32F7_I2C_CR1, mask); + /* Write 1st data byte */ + writel_relaxed(value, base + STM32F7_I2C_TXDR); } else { /* Notify i2c slave that new write transfer is starting */ i2c_slave_event(slave, I2C_SLAVE_WRITE_REQUESTED, &value); @@ -1501,7 +1503,7 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data) void __iomem *base = i2c_dev->base; struct device *dev = i2c_dev->dev; struct stm32_i2c_dma *dma = i2c_dev->dma; - u32 mask, status; + u32 status; status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR); @@ -1526,12 +1528,15 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data) f7_msg->result = -EINVAL; } - /* Disable interrupts */ - if (stm32f7_i2c_is_slave_registered(i2c_dev)) - mask = STM32F7_I2C_XFER_IRQ_MASK; - else - mask = STM32F7_I2C_ALL_IRQ_MASK; - stm32f7_i2c_disable_irq(i2c_dev, mask); + if (!i2c_dev->slave_running) { + u32 mask; + /* Disable interrupts */ + if (stm32f7_i2c_is_slave_registered(i2c_dev)) + mask = STM32F7_I2C_XFER_IRQ_MASK; + else + mask = STM32F7_I2C_ALL_IRQ_MASK; + stm32f7_i2c_disable_irq(i2c_dev, mask); + } /* Disable dma */ if (i2c_dev->use_dma) { diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 9cb2aa1e20ef..62a1c92ab803 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -39,6 +39,7 @@ struct i2c_acpi_lookup { int index; u32 speed; u32 min_speed; + u32 force_speed; }; /** @@ -285,6 +286,19 @@ i2c_acpi_match_device(const struct acpi_device_id *matches, return acpi_match_device(matches, &client->dev); } +static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = { + /* + * These Silead touchscreen controllers only work at 400KHz, for + * some reason they do not work at 100KHz. On some devices the ACPI + * tables list another device at their bus as only being capable + * of 100KHz, testing has shown that these other devices work fine + * at 400KHz (as can be expected of any recent i2c hw) so we force + * the speed of the bus to 400 KHz if a Silead device is present. + */ + { "MSSL1680", 0 }, + {} +}; + static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level, void *data, void **return_value) { @@ -303,6 +317,9 @@ static acpi_status i2c_acpi_lookup_speed(acpi_handle handle, u32 level, if (lookup->speed <= lookup->min_speed) lookup->min_speed = lookup->speed; + if (acpi_match_device_ids(adev, i2c_acpi_force_400khz_device_ids) == 0) + lookup->force_speed = 400000; + return AE_OK; } @@ -340,7 +357,16 @@ u32 i2c_acpi_find_bus_speed(struct device *dev) return 0; } - return lookup.min_speed != UINT_MAX ? lookup.min_speed : 0; + if (lookup.force_speed) { + if (lookup.force_speed != lookup.min_speed) + dev_warn(dev, FW_BUG "DSDT uses known not-working I2C bus speed %d, forcing it to %d\n", + lookup.min_speed, lookup.force_speed); + return lookup.force_speed; + } else if (lookup.min_speed != UINT_MAX) { + return lookup.min_speed; + } else { + return 0; + } } EXPORT_SYMBOL_GPL(i2c_acpi_find_bus_speed); diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index 6f632d543fcc..7eb41990bd6d 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -245,14 +245,14 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action, } client = of_i2c_register_device(adap, rd->dn); - put_device(&adap->dev); - if (IS_ERR(client)) { dev_err(&adap->dev, "failed to create client for '%pOF'\n", rd->dn); + put_device(&adap->dev); of_node_clear_flag(rd->dn, OF_POPULATED); return notifier_from_errno(PTR_ERR(client)); } + put_device(&adap->dev); break; case OF_RECONFIG_CHANGE_REMOVE: /* already depopulated? */ diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 663f8a5012d6..73aee5949b6b 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -1399,7 +1399,7 @@ static int stm32_adc_dma_start(struct iio_dev *indio_dev) cookie = dmaengine_submit(desc); ret = dma_submit_error(cookie); if (ret) { - dmaengine_terminate_all(adc->dma_chan); + dmaengine_terminate_sync(adc->dma_chan); return ret; } @@ -1477,7 +1477,7 @@ static void __stm32_adc_buffer_predisable(struct iio_dev *indio_dev) stm32_adc_conv_irq_disable(adc); if (adc->dma_chan) - dmaengine_terminate_all(adc->dma_chan); + dmaengine_terminate_sync(adc->dma_chan); if (stm32_adc_set_trig(indio_dev, NULL)) dev_err(&indio_dev->dev, "Can't clear trigger\n"); diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index b99d73887c9f..8743b2f376e2 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -317,8 +317,11 @@ static int adis16480_set_freq(struct iio_dev *indio_dev, int val, int val2) struct adis16480 *st = iio_priv(indio_dev); unsigned int t, reg; + if (val < 0 || val2 < 0) + return -EINVAL; + t = val * 1000 + val2 / 1000; - if (t <= 0) + if (t == 0) return -EINVAL; /* diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index b17f060b52fc..868281b8adb0 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -114,54 +114,63 @@ static const struct inv_mpu6050_hw hw_info[] = { .name = "MPU6050", .reg = ®_set_6050, .config = &chip_config_6050, + .fifo_size = 1024, }, { .whoami = INV_MPU6500_WHOAMI_VALUE, .name = "MPU6500", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_MPU6515_WHOAMI_VALUE, .name = "MPU6515", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_MPU6000_WHOAMI_VALUE, .name = "MPU6000", .reg = ®_set_6050, .config = &chip_config_6050, + .fifo_size = 1024, }, { .whoami = INV_MPU9150_WHOAMI_VALUE, .name = "MPU9150", .reg = ®_set_6050, .config = &chip_config_6050, + .fifo_size = 1024, }, { .whoami = INV_MPU9250_WHOAMI_VALUE, .name = "MPU9250", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_MPU9255_WHOAMI_VALUE, .name = "MPU9255", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_ICM20608_WHOAMI_VALUE, .name = "ICM20608", .reg = ®_set_6500, .config = &chip_config_6050, + .fifo_size = 512, }, { .whoami = INV_ICM20602_WHOAMI_VALUE, .name = "ICM20602", .reg = ®_set_icm20602, .config = &chip_config_6050, + .fifo_size = 1008, }, }; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h index db1c6904388b..51235677c534 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h @@ -100,12 +100,14 @@ struct inv_mpu6050_chip_config { * @name: name of the chip. * @reg: register map of the chip. * @config: configuration of the chip. + * @fifo_size: size of the FIFO in bytes. */ struct inv_mpu6050_hw { u8 whoami; u8 *name; const struct inv_mpu6050_reg_map *reg; const struct inv_mpu6050_chip_config *config; + size_t fifo_size; }; /* diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 5f9a5de0bab4..72d8c5790076 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -180,9 +180,6 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) "failed to ack interrupt\n"); goto flush_fifo; } - /* handle fifo overflow by reseting fifo */ - if (int_status & INV_MPU6050_BIT_FIFO_OVERFLOW_INT) - goto flush_fifo; if (!(int_status & INV_MPU6050_BIT_RAW_DATA_RDY_INT)) { dev_warn(regmap_get_device(st->map), "spurious interrupt with status 0x%x\n", int_status); @@ -211,6 +208,18 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) if (result) goto end_session; fifo_count = get_unaligned_be16(&data[0]); + + /* + * Handle fifo overflow by resetting fifo. + * Reset if there is only 3 data set free remaining to mitigate + * possible delay between reading fifo count and fifo data. + */ + nb = 3 * bytes_per_datum; + if (fifo_count >= st->hw->fifo_size - nb) { + dev_warn(regmap_get_device(st->map), "fifo overflow reset\n"); + goto flush_fifo; + } + /* compute and process all complete datum */ nb = fifo_count / bytes_per_datum; inv_mpu6050_update_period(st, pf->timestamp, nb); diff --git a/drivers/iio/proximity/srf04.c b/drivers/iio/proximity/srf04.c index 8b50d56b0a03..01eb8cc63076 100644 --- a/drivers/iio/proximity/srf04.c +++ b/drivers/iio/proximity/srf04.c @@ -110,7 +110,7 @@ static int srf04_read(struct srf04_data *data) udelay(data->cfg->trigger_pulse_us); gpiod_set_value(data->gpiod_trig, 0); - /* it cannot take more than 20 ms */ + /* it should not take more than 20 ms until echo is rising */ ret = wait_for_completion_killable_timeout(&data->rising, HZ/50); if (ret < 0) { mutex_unlock(&data->lock); @@ -120,7 +120,8 @@ static int srf04_read(struct srf04_data *data) return -ETIMEDOUT; } - ret = wait_for_completion_killable_timeout(&data->falling, HZ/50); + /* it cannot take more than 50 ms until echo is falling */ + ret = wait_for_completion_killable_timeout(&data->falling, HZ/20); if (ret < 0) { mutex_unlock(&data->lock); return ret; @@ -135,19 +136,19 @@ static int srf04_read(struct srf04_data *data) dt_ns = ktime_to_ns(ktime_dt); /* - * measuring more than 3 meters is beyond the capabilities of - * the sensor + * measuring more than 6,45 meters is beyond the capabilities of + * the supported sensors * ==> filter out invalid results for not measuring echos of * another us sensor * * formula: - * distance 3 m - * time = ---------- = --------- = 9404389 ns - * speed 319 m/s + * distance 6,45 * 2 m + * time = ---------- = ------------ = 40438871 ns + * speed 319 m/s * * using a minimum speed at -20 °C of 319 m/s */ - if (dt_ns > 9404389) + if (dt_ns > 40438871) return -EIO; time_ns = dt_ns; @@ -159,20 +160,20 @@ static int srf04_read(struct srf04_data *data) * with Temp in °C * and speed in m/s * - * use 343 m/s as ultrasonic speed at 20 °C here in absence of the + * use 343,5 m/s as ultrasonic speed at 20 °C here in absence of the * temperature * * therefore: - * time 343 - * distance = ------ * ----- - * 10^6 2 + * time 343,5 time * 106 + * distance = ------ * ------- = ------------ + * 10^6 2 617176 * with time in ns * and distance in mm (one way) * - * because we limit to 3 meters the multiplication with 343 just + * because we limit to 6,45 meters the multiplication with 106 just * fits into 32 bit */ - distance_mm = time_ns * 343 / 2000000; + distance_mm = time_ns * 106 / 617176; return distance_mm; } diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 3a8b0911c3bc..9d07378b5b42 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -199,6 +199,7 @@ void ib_mad_cleanup(void); int ib_sa_init(void); void ib_sa_cleanup(void); +void rdma_nl_init(void); void rdma_nl_exit(void); int ib_nl_handle_resolve_resp(struct sk_buff *skb, diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 2dd2cfe9b561..50a92442c4f7 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2716,6 +2716,8 @@ static int __init ib_core_init(void) goto err_comp_unbound; } + rdma_nl_init(); + ret = addr_init(); if (ret) { pr_warn("Could't init IB address resolution\n"); diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 72141c5b7c95..ade71823370f 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -372,6 +372,7 @@ EXPORT_SYMBOL(iw_cm_disconnect); static void destroy_cm_id(struct iw_cm_id *cm_id) { struct iwcm_id_private *cm_id_priv; + struct ib_qp *qp; unsigned long flags; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); @@ -389,6 +390,9 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) set_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags); spin_lock_irqsave(&cm_id_priv->lock, flags); + qp = cm_id_priv->qp; + cm_id_priv->qp = NULL; + switch (cm_id_priv->state) { case IW_CM_STATE_LISTEN: cm_id_priv->state = IW_CM_STATE_DESTROYING; @@ -401,7 +405,7 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) cm_id_priv->state = IW_CM_STATE_DESTROYING; spin_unlock_irqrestore(&cm_id_priv->lock, flags); /* Abrupt close of the connection */ - (void)iwcm_modify_qp_err(cm_id_priv->qp); + (void)iwcm_modify_qp_err(qp); spin_lock_irqsave(&cm_id_priv->lock, flags); break; case IW_CM_STATE_IDLE: @@ -426,11 +430,9 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) BUG(); break; } - if (cm_id_priv->qp) { - cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp); - cm_id_priv->qp = NULL; - } spin_unlock_irqrestore(&cm_id_priv->lock, flags); + if (qp) + cm_id_priv->id.device->ops.iw_rem_ref(qp); if (cm_id->mapped) { iwpm_remove_mapinfo(&cm_id->local_addr, &cm_id->m_local_addr); @@ -671,11 +673,11 @@ int iw_cm_accept(struct iw_cm_id *cm_id, BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_RECV); cm_id_priv->state = IW_CM_STATE_IDLE; spin_lock_irqsave(&cm_id_priv->lock, flags); - if (cm_id_priv->qp) { - cm_id->device->ops.iw_rem_ref(qp); - cm_id_priv->qp = NULL; - } + qp = cm_id_priv->qp; + cm_id_priv->qp = NULL; spin_unlock_irqrestore(&cm_id_priv->lock, flags); + if (qp) + cm_id->device->ops.iw_rem_ref(qp); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); } @@ -696,7 +698,7 @@ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param) struct iwcm_id_private *cm_id_priv; int ret; unsigned long flags; - struct ib_qp *qp; + struct ib_qp *qp = NULL; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); @@ -730,13 +732,13 @@ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param) return 0; /* success */ spin_lock_irqsave(&cm_id_priv->lock, flags); - if (cm_id_priv->qp) { - cm_id->device->ops.iw_rem_ref(qp); - cm_id_priv->qp = NULL; - } + qp = cm_id_priv->qp; + cm_id_priv->qp = NULL; cm_id_priv->state = IW_CM_STATE_IDLE; err: spin_unlock_irqrestore(&cm_id_priv->lock, flags); + if (qp) + cm_id->device->ops.iw_rem_ref(qp); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); return ret; @@ -878,6 +880,7 @@ static int cm_conn_est_handler(struct iwcm_id_private *cm_id_priv, static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv, struct iw_cm_event *iw_event) { + struct ib_qp *qp = NULL; unsigned long flags; int ret; @@ -896,11 +899,13 @@ static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv, cm_id_priv->state = IW_CM_STATE_ESTABLISHED; } else { /* REJECTED or RESET */ - cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp); + qp = cm_id_priv->qp; cm_id_priv->qp = NULL; cm_id_priv->state = IW_CM_STATE_IDLE; } spin_unlock_irqrestore(&cm_id_priv->lock, flags); + if (qp) + cm_id_priv->id.device->ops.iw_rem_ref(qp); ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event); if (iw_event->private_data_len) @@ -942,21 +947,18 @@ static void cm_disconnect_handler(struct iwcm_id_private *cm_id_priv, static int cm_close_handler(struct iwcm_id_private *cm_id_priv, struct iw_cm_event *iw_event) { + struct ib_qp *qp; unsigned long flags; - int ret = 0; + int ret = 0, notify_event = 0; spin_lock_irqsave(&cm_id_priv->lock, flags); + qp = cm_id_priv->qp; + cm_id_priv->qp = NULL; - if (cm_id_priv->qp) { - cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp); - cm_id_priv->qp = NULL; - } switch (cm_id_priv->state) { case IW_CM_STATE_ESTABLISHED: case IW_CM_STATE_CLOSING: cm_id_priv->state = IW_CM_STATE_IDLE; - spin_unlock_irqrestore(&cm_id_priv->lock, flags); - ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event); - spin_lock_irqsave(&cm_id_priv->lock, flags); + notify_event = 1; break; case IW_CM_STATE_DESTROYING: break; @@ -965,6 +967,10 @@ static int cm_close_handler(struct iwcm_id_private *cm_id_priv, } spin_unlock_irqrestore(&cm_id_priv->lock, flags); + if (qp) + cm_id_priv->id.device->ops.iw_rem_ref(qp); + if (notify_event) + ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event); return ret; } diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index 81dbd5f41bed..8cd31ef25eff 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -42,9 +42,12 @@ #include <linux/module.h> #include "core_priv.h" -static DEFINE_MUTEX(rdma_nl_mutex); static struct { - const struct rdma_nl_cbs *cb_table; + const struct rdma_nl_cbs *cb_table; + /* Synchronizes between ongoing netlink commands and netlink client + * unregistration. + */ + struct rw_semaphore sem; } rdma_nl_types[RDMA_NL_NUM_CLIENTS]; bool rdma_nl_chk_listeners(unsigned int group) @@ -75,70 +78,53 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op) return (op < max_num_ops[type]) ? true : false; } -static bool -is_nl_valid(const struct sk_buff *skb, unsigned int type, unsigned int op) +static const struct rdma_nl_cbs * +get_cb_table(const struct sk_buff *skb, unsigned int type, unsigned int op) { const struct rdma_nl_cbs *cb_table; - if (!is_nl_msg_valid(type, op)) - return false; - /* * Currently only NLDEV client is supporting netlink commands in * non init_net net namespace. */ if (sock_net(skb->sk) != &init_net && type != RDMA_NL_NLDEV) - return false; + return NULL; - if (!rdma_nl_types[type].cb_table) { - mutex_unlock(&rdma_nl_mutex); - request_module("rdma-netlink-subsys-%d", type); - mutex_lock(&rdma_nl_mutex); - } + cb_table = READ_ONCE(rdma_nl_types[type].cb_table); + if (!cb_table) { + /* + * Didn't get valid reference of the table, attempt module + * load once. + */ + up_read(&rdma_nl_types[type].sem); - cb_table = rdma_nl_types[type].cb_table; + request_module("rdma-netlink-subsys-%d", type); + down_read(&rdma_nl_types[type].sem); + cb_table = READ_ONCE(rdma_nl_types[type].cb_table); + } if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit)) - return false; - return true; + return NULL; + return cb_table; } void rdma_nl_register(unsigned int index, const struct rdma_nl_cbs cb_table[]) { - mutex_lock(&rdma_nl_mutex); - if (!is_nl_msg_valid(index, 0)) { - /* - * All clients are not interesting in success/failure of - * this call. They want to see the print to error log and - * continue their initialization. Print warning for them, - * because it is programmer's error to be here. - */ - mutex_unlock(&rdma_nl_mutex); - WARN(true, - "The not-valid %u index was supplied to RDMA netlink\n", - index); + if (WARN_ON(!is_nl_msg_valid(index, 0)) || + WARN_ON(READ_ONCE(rdma_nl_types[index].cb_table))) return; - } - - if (rdma_nl_types[index].cb_table) { - mutex_unlock(&rdma_nl_mutex); - WARN(true, - "The %u index is already registered in RDMA netlink\n", - index); - return; - } - rdma_nl_types[index].cb_table = cb_table; - mutex_unlock(&rdma_nl_mutex); + /* Pairs with the READ_ONCE in is_nl_valid() */ + smp_store_release(&rdma_nl_types[index].cb_table, cb_table); } EXPORT_SYMBOL(rdma_nl_register); void rdma_nl_unregister(unsigned int index) { - mutex_lock(&rdma_nl_mutex); + down_write(&rdma_nl_types[index].sem); rdma_nl_types[index].cb_table = NULL; - mutex_unlock(&rdma_nl_mutex); + up_write(&rdma_nl_types[index].sem); } EXPORT_SYMBOL(rdma_nl_unregister); @@ -170,15 +156,21 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, unsigned int index = RDMA_NL_GET_CLIENT(type); unsigned int op = RDMA_NL_GET_OP(type); const struct rdma_nl_cbs *cb_table; + int err = -EINVAL; - if (!is_nl_valid(skb, index, op)) + if (!is_nl_msg_valid(index, op)) return -EINVAL; - cb_table = rdma_nl_types[index].cb_table; + down_read(&rdma_nl_types[index].sem); + cb_table = get_cb_table(skb, index, op); + if (!cb_table) + goto done; if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) && - !netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; + !netlink_capable(skb, CAP_NET_ADMIN)) { + err = -EPERM; + goto done; + } /* * LS responses overload the 0x100 (NLM_F_ROOT) flag. Don't @@ -186,8 +178,8 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, */ if (index == RDMA_NL_LS) { if (cb_table[op].doit) - return cb_table[op].doit(skb, nlh, extack); - return -EINVAL; + err = cb_table[op].doit(skb, nlh, extack); + goto done; } /* FIXME: Convert IWCM to properly handle doit callbacks */ if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_IWCM) { @@ -195,14 +187,15 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, .dump = cb_table[op].dump, }; if (c.dump) - return netlink_dump_start(skb->sk, skb, nlh, &c); - return -EINVAL; + err = netlink_dump_start(skb->sk, skb, nlh, &c); + goto done; } if (cb_table[op].doit) - return cb_table[op].doit(skb, nlh, extack); - - return 0; + err = cb_table[op].doit(skb, nlh, extack); +done: + up_read(&rdma_nl_types[index].sem); + return err; } /* @@ -263,9 +256,7 @@ skip: static void rdma_nl_rcv(struct sk_buff *skb) { - mutex_lock(&rdma_nl_mutex); rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg); - mutex_unlock(&rdma_nl_mutex); } int rdma_nl_unicast(struct net *net, struct sk_buff *skb, u32 pid) @@ -297,6 +288,14 @@ int rdma_nl_multicast(struct net *net, struct sk_buff *skb, } EXPORT_SYMBOL(rdma_nl_multicast); +void rdma_nl_init(void) +{ + int idx; + + for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++) + init_rwsem(&rdma_nl_types[idx].sem); +} + void rdma_nl_exit(void) { int idx; diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 65b36548bc17..c03af08b80e7 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -778,7 +778,7 @@ static int fill_res_counter_entry(struct sk_buff *msg, bool has_cap_net_admin, container_of(res, struct rdma_counter, res); if (port && port != counter->port) - return 0; + return -EAGAIN; /* Dump it even query failed */ rdma_counter_query_stats(counter); diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index 1e5aeb39f774..63f7f7db5902 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -98,7 +98,7 @@ ib_uverbs_init_udata_buf_or_null(struct ib_udata *udata, struct ib_uverbs_device { atomic_t refcount; - int num_comp_vectors; + u32 num_comp_vectors; struct completion comp; struct device dev; /* First group for device attributes, NULL terminated array */ diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index f974b6854224..35c2841a569e 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -662,16 +662,17 @@ static bool find_gid_index(const union ib_gid *gid, void *context) { struct find_gid_index_context *ctx = context; + u16 vlan_id = 0xffff; + int ret; if (ctx->gid_type != gid_attr->gid_type) return false; - if ((!!(ctx->vlan_id != 0xffff) == !is_vlan_dev(gid_attr->ndev)) || - (is_vlan_dev(gid_attr->ndev) && - vlan_dev_vlan_id(gid_attr->ndev) != ctx->vlan_id)) + ret = rdma_read_gid_l2_fields(gid_attr, &vlan_id, NULL); + if (ret) return false; - return true; + return ctx->vlan_id == vlan_id; } static const struct ib_gid_attr * diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index e87fc0408470..347dc242fb88 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -495,7 +495,6 @@ static int _put_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb) ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *))); release_ep_resources(ep); - kfree_skb(skb); return 0; } @@ -506,7 +505,6 @@ static int _put_pass_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb) ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *))); c4iw_put_ep(&ep->parent_ep->com); release_ep_resources(ep); - kfree_skb(skb); return 0; } @@ -2424,20 +2422,6 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, enum chip_type adapter_type = ep->com.dev->rdev.lldi.adapter_type; pr_debug("ep %p tid %u\n", ep, ep->hwtid); - - skb_get(skb); - rpl = cplhdr(skb); - if (!is_t4(adapter_type)) { - skb_trim(skb, roundup(sizeof(*rpl5), 16)); - rpl5 = (void *)rpl; - INIT_TP_WR(rpl5, ep->hwtid); - } else { - skb_trim(skb, sizeof(*rpl)); - INIT_TP_WR(rpl, ep->hwtid); - } - OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL, - ep->hwtid)); - cxgb_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx, enable_tcp_timestamps && req->tcpopt.tstamp, (ep->com.remote_addr.ss_family == AF_INET) ? 0 : 1); @@ -2483,6 +2467,20 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, if (tcph->ece && tcph->cwr) opt2 |= CCTRL_ECN_V(1); } + + skb_get(skb); + rpl = cplhdr(skb); + if (!is_t4(adapter_type)) { + skb_trim(skb, roundup(sizeof(*rpl5), 16)); + rpl5 = (void *)rpl; + INIT_TP_WR(rpl5, ep->hwtid); + } else { + skb_trim(skb, sizeof(*rpl)); + INIT_TP_WR(rpl, ep->hwtid); + } + OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL, + ep->hwtid)); + if (CHELSIO_CHIP_VERSION(adapter_type) > CHELSIO_T4) { u32 isn = (prandom_u32() & ~7UL) - 1; opt2 |= T5_OPT_2_VALID_F; diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 71cb9525c074..26b792bb1027 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1489,7 +1489,6 @@ static int __init hfi1_mod_init(void) goto bail_dev; } - hfi1_compute_tid_rdma_flow_wt(); /* * These must be called before the driver is registered with * the PCI subsystem. diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 61aa5504d7c3..61362bd6d3ce 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -319,7 +319,9 @@ int pcie_speeds(struct hfi1_devdata *dd) /* * bus->max_bus_speed is set from the bridge's linkcap Max Link Speed */ - if (parent && dd->pcidev->bus->max_bus_speed != PCIE_SPEED_8_0GT) { + if (parent && + (dd->pcidev->bus->max_bus_speed == PCIE_SPEED_2_5GT || + dd->pcidev->bus->max_bus_speed == PCIE_SPEED_5_0GT)) { dd_dev_info(dd, "Parent PCIe bridge does not support Gen3\n"); dd->link_gen3_capable = 0; } diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 513a8aac9ccd..1a3c647675a7 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -2209,15 +2209,15 @@ int do_rc_ack(struct rvt_qp *qp, u32 aeth, u32 psn, int opcode, if (qp->s_flags & RVT_S_WAIT_RNR) goto bail_stop; rdi = ib_to_rvt(qp->ibqp.device); - if (qp->s_rnr_retry == 0 && - !((rdi->post_parms[wqe->wr.opcode].flags & - RVT_OPERATION_IGN_RNR_CNT) && - qp->s_rnr_retry_cnt == 0)) { - status = IB_WC_RNR_RETRY_EXC_ERR; - goto class_b; + if (!(rdi->post_parms[wqe->wr.opcode].flags & + RVT_OPERATION_IGN_RNR_CNT)) { + if (qp->s_rnr_retry == 0) { + status = IB_WC_RNR_RETRY_EXC_ERR; + goto class_b; + } + if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0) + qp->s_rnr_retry--; } - if (qp->s_rnr_retry_cnt < 7 && qp->s_rnr_retry_cnt > 0) - qp->s_rnr_retry--; /* * The last valid PSN is the previous PSN. For TID RDMA WRITE diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 2ed7bfd5feea..c61b6022575e 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -65,6 +65,7 @@ #define SDMA_DESCQ_CNT 2048 #define SDMA_DESC_INTR 64 #define INVALID_TAIL 0xffff +#define SDMA_PAD max_t(size_t, MAX_16B_PADDING, sizeof(u32)) static uint sdma_descq_cnt = SDMA_DESCQ_CNT; module_param(sdma_descq_cnt, uint, S_IRUGO); @@ -1296,7 +1297,7 @@ void sdma_clean(struct hfi1_devdata *dd, size_t num_engines) struct sdma_engine *sde; if (dd->sdma_pad_dma) { - dma_free_coherent(&dd->pcidev->dev, 4, + dma_free_coherent(&dd->pcidev->dev, SDMA_PAD, (void *)dd->sdma_pad_dma, dd->sdma_pad_phys); dd->sdma_pad_dma = NULL; @@ -1491,7 +1492,7 @@ int sdma_init(struct hfi1_devdata *dd, u8 port) } /* Allocate memory for pad */ - dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, sizeof(u32), + dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, SDMA_PAD, &dd->sdma_pad_phys, GFP_KERNEL); if (!dd->sdma_pad_dma) { dd_dev_err(dd, "failed to allocate SendDMA pad memory\n"); diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index b4dcc4d29f84..e53f542b60af 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -107,8 +107,6 @@ static u32 mask_generation(u32 a) * C - Capcode */ -static u32 tid_rdma_flow_wt; - static void tid_rdma_trigger_resume(struct work_struct *work); static void hfi1_kern_exp_rcv_free_flows(struct tid_rdma_request *req); static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req, @@ -136,6 +134,26 @@ static void update_r_next_psn_fecn(struct hfi1_packet *packet, struct tid_rdma_flow *flow, bool fecn); +static void validate_r_tid_ack(struct hfi1_qp_priv *priv) +{ + if (priv->r_tid_ack == HFI1_QP_WQE_INVALID) + priv->r_tid_ack = priv->r_tid_tail; +} + +static void tid_rdma_schedule_ack(struct rvt_qp *qp) +{ + struct hfi1_qp_priv *priv = qp->priv; + + priv->s_flags |= RVT_S_ACK_PENDING; + hfi1_schedule_tid_send(qp); +} + +static void tid_rdma_trigger_ack(struct rvt_qp *qp) +{ + validate_r_tid_ack(qp->priv); + tid_rdma_schedule_ack(qp); +} + static u64 tid_rdma_opfn_encode(struct tid_rdma_params *p) { return @@ -2736,11 +2754,6 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd, diff = cmp_psn(psn, flow->flow_state.r_next_psn); if (diff > 0) { - if (!(qp->r_flags & RVT_R_RDMAR_SEQ)) - restart_tid_rdma_read_req(rcd, - qp, - wqe); - /* Drop the packet.*/ goto s_unlock; } else if (diff < 0) { @@ -3010,10 +3023,7 @@ nak_psn: qpriv->s_nak_state = IB_NAK_PSN_ERROR; /* We are NAK'ing the next expected PSN */ qpriv->s_nak_psn = mask_psn(flow->flow_state.r_next_psn); - qpriv->s_flags |= RVT_S_ACK_PENDING; - if (qpriv->r_tid_ack == HFI1_QP_WQE_INVALID) - qpriv->r_tid_ack = qpriv->r_tid_tail; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); } goto unlock; } @@ -3376,18 +3386,17 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe, return sizeof(ohdr->u.tid_rdma.w_req) / sizeof(u32); } -void hfi1_compute_tid_rdma_flow_wt(void) +static u32 hfi1_compute_tid_rdma_flow_wt(struct rvt_qp *qp) { /* * Heuristic for computing the RNR timeout when waiting on the flow * queue. Rather than a computationaly expensive exact estimate of when * a flow will be available, we assume that if a QP is at position N in * the flow queue it has to wait approximately (N + 1) * (number of - * segments between two sync points), assuming PMTU of 4K. The rationale - * for this is that flows are released and recycled at each sync point. + * segments between two sync points). The rationale for this is that + * flows are released and recycled at each sync point. */ - tid_rdma_flow_wt = MAX_TID_FLOW_PSN * enum_to_mtu(OPA_MTU_4096) / - TID_RDMA_MAX_SEGMENT_SIZE; + return (MAX_TID_FLOW_PSN * qp->pmtu) >> TID_RDMA_SEGMENT_SHIFT; } static u32 position_in_queue(struct hfi1_qp_priv *qpriv, @@ -3510,7 +3519,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx) if (qpriv->flow_state.index >= RXE_NUM_TID_FLOWS) { ret = hfi1_kern_setup_hw_flow(qpriv->rcd, qp); if (ret) { - to_seg = tid_rdma_flow_wt * + to_seg = hfi1_compute_tid_rdma_flow_wt(qp) * position_in_queue(qpriv, &rcd->flow_queue); break; @@ -3531,7 +3540,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx) /* * If overtaking req->acked_tail, send an RNR NAK. Because the * QP is not queued in this case, and the issue can only be - * caused due a delay in scheduling the second leg which we + * caused by a delay in scheduling the second leg which we * cannot estimate, we use a rather arbitrary RNR timeout of * (MAX_FLOWS / 2) segments */ @@ -3539,8 +3548,7 @@ static void hfi1_tid_write_alloc_resources(struct rvt_qp *qp, bool intr_ctx) MAX_FLOWS)) { ret = -EAGAIN; to_seg = MAX_FLOWS >> 1; - qpriv->s_flags |= RVT_S_ACK_PENDING; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); break; } @@ -4340,8 +4348,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet) trace_hfi1_tid_req_rcv_write_data(qp, 0, e->opcode, e->psn, e->lpsn, req); trace_hfi1_tid_write_rsp_rcv_data(qp); - if (priv->r_tid_ack == HFI1_QP_WQE_INVALID) - priv->r_tid_ack = priv->r_tid_tail; + validate_r_tid_ack(priv); if (opcode == TID_OP(WRITE_DATA_LAST)) { release_rdma_sge_mr(e); @@ -4380,8 +4387,7 @@ void hfi1_rc_rcv_tid_rdma_write_data(struct hfi1_packet *packet) } done: - priv->s_flags |= RVT_S_ACK_PENDING; - hfi1_schedule_tid_send(qp); + tid_rdma_schedule_ack(qp); exit: priv->r_next_psn_kdeth = flow->flow_state.r_next_psn; if (fecn) @@ -4393,10 +4399,7 @@ send_nak: if (!priv->s_nak_state) { priv->s_nak_state = IB_NAK_PSN_ERROR; priv->s_nak_psn = flow->flow_state.r_next_psn; - priv->s_flags |= RVT_S_ACK_PENDING; - if (priv->r_tid_ack == HFI1_QP_WQE_INVALID) - priv->r_tid_ack = priv->r_tid_tail; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); } goto done; } @@ -4944,8 +4947,7 @@ void hfi1_rc_rcv_tid_rdma_resync(struct hfi1_packet *packet) qpriv->resync = true; /* RESYNC request always gets a TID RDMA ACK. */ qpriv->s_nak_state = 0; - qpriv->s_flags |= RVT_S_ACK_PENDING; - hfi1_schedule_tid_send(qp); + tid_rdma_trigger_ack(qp); bail: if (fecn) qp->s_flags |= RVT_S_ECN; diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.h b/drivers/infiniband/hw/hfi1/tid_rdma.h index 1c536185261e..6e82df2190b7 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.h +++ b/drivers/infiniband/hw/hfi1/tid_rdma.h @@ -17,6 +17,7 @@ #define TID_RDMA_MIN_SEGMENT_SIZE BIT(18) /* 256 KiB (for now) */ #define TID_RDMA_MAX_SEGMENT_SIZE BIT(18) /* 256 KiB (for now) */ #define TID_RDMA_MAX_PAGES (BIT(18) >> PAGE_SHIFT) +#define TID_RDMA_SEGMENT_SHIFT 18 /* * Bit definitions for priv->s_flags. @@ -274,8 +275,6 @@ u32 hfi1_build_tid_rdma_write_req(struct rvt_qp *qp, struct rvt_swqe *wqe, struct ib_other_headers *ohdr, u32 *bth1, u32 *bth2, u32 *len); -void hfi1_compute_tid_rdma_flow_wt(void); - void hfi1_rc_rcv_tid_rdma_write_req(struct hfi1_packet *packet); u32 hfi1_build_tid_rdma_write_resp(struct rvt_qp *qp, struct rvt_ack_entry *e, diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 7bff0a1e713d..089e201d7550 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -147,9 +147,6 @@ static int pio_wait(struct rvt_qp *qp, /* Length of buffer to create verbs txreq cache name */ #define TXREQ_NAME_LEN 24 -/* 16B trailing buffer */ -static const u8 trail_buf[MAX_16B_PADDING]; - static uint wss_threshold = 80; module_param(wss_threshold, uint, S_IRUGO); MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy"); @@ -820,8 +817,8 @@ static int build_verbs_tx_desc( /* add icrc, lt byte, and padding to flit */ if (extra_bytes) - ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq, - (void *)trail_buf, extra_bytes); + ret = sdma_txadd_daddr(sde->dd, &tx->txreq, + sde->dd->sdma_pad_phys, extra_bytes); bail_txadd: return ret; @@ -1089,7 +1086,8 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps, } /* add icrc, lt byte, and padding to flit */ if (extra_bytes) - seg_pio_copy_mid(pbuf, trail_buf, extra_bytes); + seg_pio_copy_mid(pbuf, ppd->dd->sdma_pad_dma, + extra_bytes); seg_pio_copy_end(pbuf); } diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h index 86783276fb1f..3bb8f78fb7b0 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.h +++ b/drivers/infiniband/hw/hns/hns_roce_hem.h @@ -59,7 +59,7 @@ enum { #define HNS_ROCE_HEM_CHUNK_LEN \ ((256 - sizeof(struct list_head) - 2 * sizeof(int)) / \ - (sizeof(struct scatterlist))) + (sizeof(struct scatterlist) + sizeof(void *))) #define check_whether_bt_num_3(type, hop_num) \ (type < HEM_TYPE_MTT && hop_num == 2) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 7a89d669f8bf..e82567fcdeb7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -5389,9 +5389,9 @@ static void hns_roce_v2_free_eq(struct hns_roce_dev *hr_dev, return; } - if (eq->buf_list) - dma_free_coherent(hr_dev->dev, buf_chk_sz, - eq->buf_list->buf, eq->buf_list->map); + dma_free_coherent(hr_dev->dev, buf_chk_sz, eq->buf_list->buf, + eq->buf_list->map); + kfree(eq->buf_list); } static void hns_roce_config_eqc(struct hns_roce_dev *hr_dev, diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 9591457eb768..43ea2c13b212 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -376,7 +376,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq, srq->max = roundup_pow_of_two(srq_init_attr->attr.max_wr + 1); srq->max_gs = srq_init_attr->attr.max_sge; - srq_desc_size = max(16, 16 * srq->max_gs); + srq_desc_size = roundup_pow_of_two(max(16, 16 * srq->max_gs)); srq->wqe_shift = ilog2(srq_desc_size); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 630599311586..7019c12005f4 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1967,8 +1967,8 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw) int err; if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { - xa_erase(&dev->mdev->priv.mkey_table, - mlx5_base_mkey(mmw->mmkey.key)); + xa_erase_irq(&dev->mdev->priv.mkey_table, + mlx5_base_mkey(mmw->mmkey.key)); /* * pagefault_single_data_segment() may be accessing mmw under * SRCU if the user bound an ODP MR to this MW. diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 8937d72ddcf6..5fd071c05944 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -3249,10 +3249,12 @@ static int modify_raw_packet_qp_sq( } /* Only remove the old rate after new rate was set */ - if ((old_rl.rate && - !mlx5_rl_are_equal(&old_rl, &new_rl)) || - (new_state != MLX5_SQC_STATE_RDY)) + if ((old_rl.rate && !mlx5_rl_are_equal(&old_rl, &new_rl)) || + (new_state != MLX5_SQC_STATE_RDY)) { mlx5_rl_remove_rate(dev, &old_rl); + if (new_state != MLX5_SQC_STATE_RDY) + memset(&new_rl, 0, sizeof(new_rl)); + } ibqp->rl = new_rl; sq->state = new_state; diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 5136b835e1ba..dc71b6e16a07 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -76,7 +76,7 @@ static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str) struct qedr_dev *qedr = get_qedr_dev(ibdev); u32 fw_ver = (u32)qedr->attr.fw_ver; - snprintf(str, IB_FW_VERSION_NAME_MAX, "%d. %d. %d. %d", + snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d.%d", (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF, (fw_ver >> 8) & 0xFF, fw_ver & 0xFF); } diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c index 52d402f39df9..b4317480cee7 100644 --- a/drivers/infiniband/sw/siw/siw_qp.c +++ b/drivers/infiniband/sw/siw/siw_qp.c @@ -1312,6 +1312,7 @@ int siw_qp_add(struct siw_device *sdev, struct siw_qp *qp) void siw_free_qp(struct kref *ref) { struct siw_qp *found, *qp = container_of(ref, struct siw_qp, ref); + struct siw_base_qp *siw_base_qp = to_siw_base_qp(qp->ib_qp); struct siw_device *sdev = qp->sdev; unsigned long flags; @@ -1334,4 +1335,5 @@ void siw_free_qp(struct kref *ref) atomic_dec(&sdev->num_qp); siw_dbg_qp(qp, "free QP\n"); kfree_rcu(qp, rcu); + kfree(siw_base_qp); } diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 869e02b69a01..b18a677832e1 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -604,7 +604,6 @@ out: int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata) { struct siw_qp *qp = to_siw_qp(base_qp); - struct siw_base_qp *siw_base_qp = to_siw_base_qp(base_qp); struct siw_ucontext *uctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); @@ -641,7 +640,6 @@ int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata) qp->scq = qp->rcq = NULL; siw_qp_put(qp); - kfree(siw_base_qp); return 0; } diff --git a/drivers/input/ff-memless.c b/drivers/input/ff-memless.c index 1cb40c7475af..8229a9006917 100644 --- a/drivers/input/ff-memless.c +++ b/drivers/input/ff-memless.c @@ -489,6 +489,15 @@ static void ml_ff_destroy(struct ff_device *ff) { struct ml_device *ml = ff->private; + /* + * Even though we stop all playing effects when tearing down + * an input device (via input_device_flush() that calls into + * input_ff_flush() that stops and erases all effects), we + * do not actually stop the timer, and therefore we should + * do it here. + */ + del_timer_sync(&ml->timer); + kfree(ml->private); } diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c index f28a7158b2ef..bbf9ae9f3f0c 100644 --- a/drivers/input/rmi4/rmi_f11.c +++ b/drivers/input/rmi4/rmi_f11.c @@ -510,7 +510,6 @@ struct f11_data { struct rmi_2d_sensor_platform_data sensor_pdata; unsigned long *abs_mask; unsigned long *rel_mask; - unsigned long *result_bits; }; enum f11_finger_state { @@ -1057,7 +1056,7 @@ static int rmi_f11_initialize(struct rmi_function *fn) /* ** init instance data, fill in values and create any sysfs files */ - f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 3, + f11 = devm_kzalloc(&fn->dev, sizeof(struct f11_data) + mask_size * 2, GFP_KERNEL); if (!f11) return -ENOMEM; @@ -1076,8 +1075,6 @@ static int rmi_f11_initialize(struct rmi_function *fn) + sizeof(struct f11_data)); f11->rel_mask = (unsigned long *)((char *)f11 + sizeof(struct f11_data) + mask_size); - f11->result_bits = (unsigned long *)((char *)f11 - + sizeof(struct f11_data) + mask_size * 2); set_bit(fn->irq_pos, f11->abs_mask); set_bit(fn->irq_pos + 1, f11->rel_mask); @@ -1284,8 +1281,8 @@ static irqreturn_t rmi_f11_attention(int irq, void *ctx) valid_bytes = f11->sensor.attn_size; memcpy(f11->sensor.data_pkt, drvdata->attn_data.data, valid_bytes); - drvdata->attn_data.data += f11->sensor.attn_size; - drvdata->attn_data.size -= f11->sensor.attn_size; + drvdata->attn_data.data += valid_bytes; + drvdata->attn_data.size -= valid_bytes; } else { error = rmi_read_block(rmi_dev, data_base_addr, f11->sensor.data_pkt, diff --git a/drivers/input/rmi4/rmi_f12.c b/drivers/input/rmi4/rmi_f12.c index d20a5d6780d1..7e97944f7616 100644 --- a/drivers/input/rmi4/rmi_f12.c +++ b/drivers/input/rmi4/rmi_f12.c @@ -55,6 +55,9 @@ struct f12_data { const struct rmi_register_desc_item *data15; u16 data15_offset; + + unsigned long *abs_mask; + unsigned long *rel_mask; }; static int rmi_f12_read_sensor_tuning(struct f12_data *f12) @@ -209,8 +212,8 @@ static irqreturn_t rmi_f12_attention(int irq, void *ctx) valid_bytes = sensor->attn_size; memcpy(sensor->data_pkt, drvdata->attn_data.data, valid_bytes); - drvdata->attn_data.data += sensor->attn_size; - drvdata->attn_data.size -= sensor->attn_size; + drvdata->attn_data.data += valid_bytes; + drvdata->attn_data.size -= valid_bytes; } else { retval = rmi_read_block(rmi_dev, f12->data_addr, sensor->data_pkt, sensor->pkt_size); @@ -291,9 +294,18 @@ static int rmi_f12_write_control_regs(struct rmi_function *fn) static int rmi_f12_config(struct rmi_function *fn) { struct rmi_driver *drv = fn->rmi_dev->driver; + struct f12_data *f12 = dev_get_drvdata(&fn->dev); + struct rmi_2d_sensor *sensor; int ret; - drv->set_irq_bits(fn->rmi_dev, fn->irq_mask); + sensor = &f12->sensor; + + if (!sensor->report_abs) + drv->clear_irq_bits(fn->rmi_dev, f12->abs_mask); + else + drv->set_irq_bits(fn->rmi_dev, f12->abs_mask); + + drv->clear_irq_bits(fn->rmi_dev, f12->rel_mask); ret = rmi_f12_write_control_regs(fn); if (ret) @@ -315,9 +327,12 @@ static int rmi_f12_probe(struct rmi_function *fn) struct rmi_device_platform_data *pdata = rmi_get_platform_data(rmi_dev); struct rmi_driver_data *drvdata = dev_get_drvdata(&rmi_dev->dev); u16 data_offset = 0; + int mask_size; rmi_dbg(RMI_DEBUG_FN, &fn->dev, "%s\n", __func__); + mask_size = BITS_TO_LONGS(drvdata->irq_count) * sizeof(unsigned long); + ret = rmi_read(fn->rmi_dev, query_addr, &buf); if (ret < 0) { dev_err(&fn->dev, "Failed to read general info register: %d\n", @@ -332,10 +347,19 @@ static int rmi_f12_probe(struct rmi_function *fn) return -ENODEV; } - f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data), GFP_KERNEL); + f12 = devm_kzalloc(&fn->dev, sizeof(struct f12_data) + mask_size * 2, + GFP_KERNEL); if (!f12) return -ENOMEM; + f12->abs_mask = (unsigned long *)((char *)f12 + + sizeof(struct f12_data)); + f12->rel_mask = (unsigned long *)((char *)f12 + + sizeof(struct f12_data) + mask_size); + + set_bit(fn->irq_pos, f12->abs_mask); + set_bit(fn->irq_pos + 1, f12->rel_mask); + f12->has_dribble = !!(buf & BIT(3)); if (fn->dev.of_node) { diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c index 710b02595486..897105b9a98b 100644 --- a/drivers/input/rmi4/rmi_f54.c +++ b/drivers/input/rmi4/rmi_f54.c @@ -359,7 +359,7 @@ static const struct vb2_ops rmi_f54_queue_ops = { static const struct vb2_queue rmi_f54_queue = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, .io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ, - .buf_struct_size = sizeof(struct vb2_buffer), + .buf_struct_size = sizeof(struct vb2_v4l2_buffer), .ops = &rmi_f54_queue_ops, .mem_ops = &vb2_vmalloc_memops, .timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC, @@ -601,7 +601,7 @@ static int rmi_f54_config(struct rmi_function *fn) { struct rmi_driver *drv = fn->rmi_dev->driver; - drv->set_irq_bits(fn->rmi_dev, fn->irq_mask); + drv->clear_irq_bits(fn->rmi_dev, fn->irq_mask); return 0; } @@ -730,6 +730,7 @@ static void rmi_f54_remove(struct rmi_function *fn) video_unregister_device(&f54->vdev); v4l2_device_unregister(&f54->v4l2); + destroy_workqueue(f54->workqueue); } struct rmi_function_handler rmi_f54_handler = { diff --git a/drivers/input/touchscreen/cyttsp4_core.c b/drivers/input/touchscreen/cyttsp4_core.c index 4b22d49a0f49..6bcffc930384 100644 --- a/drivers/input/touchscreen/cyttsp4_core.c +++ b/drivers/input/touchscreen/cyttsp4_core.c @@ -1990,11 +1990,6 @@ static int cyttsp4_mt_probe(struct cyttsp4 *cd) /* get sysinfo */ md->si = &cd->sysinfo; - if (!md->si) { - dev_err(dev, "%s: Fail get sysinfo pointer from core p=%p\n", - __func__, md->si); - goto error_get_sysinfo; - } rc = cyttsp4_setup_input_device(cd); if (rc) @@ -2004,8 +1999,6 @@ static int cyttsp4_mt_probe(struct cyttsp4 *cd) error_init_input: input_free_device(md->input); -error_get_sysinfo: - input_set_drvdata(md->input, NULL); error_alloc_failed: dev_err(dev, "%s failed.\n", __func__); return rc; diff --git a/drivers/input/touchscreen/st1232.c b/drivers/input/touchscreen/st1232.c index 34923399ece4..1139714e72e2 100644 --- a/drivers/input/touchscreen/st1232.c +++ b/drivers/input/touchscreen/st1232.c @@ -81,8 +81,10 @@ static int st1232_ts_read_data(struct st1232_ts_data *ts) for (i = 0, y = 0; i < ts->chip_info->max_fingers; i++, y += 3) { finger[i].is_valid = buf[i + y] >> 7; if (finger[i].is_valid) { - finger[i].x = ((buf[i + y] & 0x0070) << 4) | buf[i + 1]; - finger[i].y = ((buf[i + y] & 0x0007) << 8) | buf[i + 2]; + finger[i].x = ((buf[i + y] & 0x0070) << 4) | + buf[i + y + 1]; + finger[i].y = ((buf[i + y] & 0x0007) << 8) | + buf[i + y + 2]; /* st1232 includes a z-axis / touch strength */ if (ts->chip_info->have_z) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 7b971228df38..c498796adc07 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -405,8 +405,12 @@ void icc_set_tag(struct icc_path *path, u32 tag) if (!path) return; + mutex_lock(&icc_lock); + for (i = 0; i < path->num_nodes; i++) path->reqs[i].tag = tag; + + mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_set_tag); diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c index 910081d6ddc0..b4966d8f3348 100644 --- a/drivers/interconnect/qcom/qcs404.c +++ b/drivers/interconnect/qcom/qcs404.c @@ -433,7 +433,8 @@ static int qnoc_probe(struct platform_device *pdev) if (!qp) return -ENOMEM; - data = devm_kcalloc(dev, num_nodes, sizeof(*node), GFP_KERNEL); + data = devm_kzalloc(dev, struct_size(data, nodes, num_nodes), + GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c index 57955596bb59..502a6c22b41e 100644 --- a/drivers/interconnect/qcom/sdm845.c +++ b/drivers/interconnect/qcom/sdm845.c @@ -790,7 +790,8 @@ static int qnoc_probe(struct platform_device *pdev) if (!qp) return -ENOMEM; - data = devm_kcalloc(&pdev->dev, num_nodes, sizeof(*node), GFP_KERNEL); + data = devm_kzalloc(&pdev->dev, struct_size(data, nodes, num_nodes), + GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/drivers/iommu/amd_iommu_quirks.c b/drivers/iommu/amd_iommu_quirks.c index c235f79b7a20..5120ce4fdce3 100644 --- a/drivers/iommu/amd_iommu_quirks.c +++ b/drivers/iommu/amd_iommu_quirks.c @@ -74,6 +74,19 @@ static const struct dmi_system_id ivrs_quirks[] __initconst = { .driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495], }, { + /* + * Acer Aspire A315-41 requires the very same workaround as + * Dell Latitude 5495 + */ + .callback = ivrs_ioapic_quirk_cb, + .ident = "Acer Aspire A315-41", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-41"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495], + }, + { .callback = ivrs_ioapic_quirk_cb, .ident = "Lenovo ideapad 330S-15ARR", .matches = { diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 3f974919d3bd..6db6d969e31c 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2794,7 +2794,7 @@ static int identity_mapping(struct device *dev) struct device_domain_info *info; info = dev->archdata.iommu; - if (info && info != DUMMY_DEVICE_DOMAIN_INFO) + if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO) return (info->domain == si_domain); return 0; @@ -3471,7 +3471,7 @@ static bool iommu_need_mapping(struct device *dev) if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask) dma_mask = dev->coherent_dma_mask; - if (dma_mask >= dma_get_required_mask(dev)) + if (dma_mask >= dma_direct_get_required_mask(dev)) return false; /* @@ -3775,6 +3775,13 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele return nelems; } +static u64 intel_get_required_mask(struct device *dev) +{ + if (!iommu_need_mapping(dev)) + return dma_direct_get_required_mask(dev); + return DMA_BIT_MASK(32); +} + static const struct dma_map_ops intel_dma_ops = { .alloc = intel_alloc_coherent, .free = intel_free_coherent, @@ -3787,6 +3794,7 @@ static const struct dma_map_ops intel_dma_ops = { .dma_supported = dma_direct_supported, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, + .get_required_mask = intel_get_required_mask, }; static void diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 237103465b82..2639fc718117 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -1105,10 +1105,8 @@ static int ipmmu_probe(struct platform_device *pdev) /* Root devices have mandatory IRQs */ if (ipmmu_is_root(mmu)) { irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(&pdev->dev, "no IRQ found\n"); + if (irq < 0) return irq; - } ret = devm_request_irq(&pdev->dev, irq, ipmmu_irq, 0, dev_name(&pdev->dev), mmu); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 62e54f1a248b..787e8eec9a7f 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -175,6 +175,22 @@ static DEFINE_IDA(its_vpeid_ida); #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K) +static u16 get_its_list(struct its_vm *vm) +{ + struct its_node *its; + unsigned long its_list = 0; + + list_for_each_entry(its, &its_nodes, entry) { + if (!its->is_v4) + continue; + + if (vm->vlpi_count[its->list_nr]) + __set_bit(its->list_nr, &its_list); + } + + return (u16)its_list; +} + static struct its_collection *dev_event_to_col(struct its_device *its_dev, u32 event) { @@ -976,17 +992,15 @@ static void its_send_vmapp(struct its_node *its, static void its_send_vmovp(struct its_vpe *vpe) { - struct its_cmd_desc desc; + struct its_cmd_desc desc = {}; struct its_node *its; unsigned long flags; int col_id = vpe->col_idx; desc.its_vmovp_cmd.vpe = vpe; - desc.its_vmovp_cmd.its_list = (u16)its_list_map; if (!its_list_map) { its = list_first_entry(&its_nodes, struct its_node, entry); - desc.its_vmovp_cmd.seq_num = 0; desc.its_vmovp_cmd.col = &its->collections[col_id]; its_send_single_vcommand(its, its_build_vmovp_cmd, &desc); return; @@ -1003,6 +1017,7 @@ static void its_send_vmovp(struct its_vpe *vpe) raw_spin_lock_irqsave(&vmovp_lock, flags); desc.its_vmovp_cmd.seq_num = vmovp_seq_num++; + desc.its_vmovp_cmd.its_list = get_its_list(vpe->its_vm); /* Emit VMOVPs */ list_for_each_entry(its, &its_nodes, entry) { diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index daefc52b0ec5..7d0a12fe2714 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -252,8 +252,8 @@ static int __init plic_init(struct device_node *node, continue; } - /* skip context holes */ - if (parent.args[0] == -1) + /* skip contexts other than supervisor external interrupt */ + if (parent.args[0] != IRQ_S_EXT) continue; hartid = plic_find_hart_id(parent.np); diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index c92b405b7646..ba8619524231 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -744,7 +744,7 @@ capi_poll(struct file *file, poll_table *wait) poll_wait(file, &(cdev->recvwait), wait); mask = EPOLLOUT | EPOLLWRNORM; - if (!skb_queue_empty(&cdev->recvqueue)) + if (!skb_queue_empty_lockless(&cdev->recvqueue)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/macintosh/windfarm_cpufreq_clamp.c b/drivers/macintosh/windfarm_cpufreq_clamp.c index 705c6200814b..7b726f00f183 100644 --- a/drivers/macintosh/windfarm_cpufreq_clamp.c +++ b/drivers/macintosh/windfarm_cpufreq_clamp.c @@ -18,7 +18,7 @@ static int clamped; static struct wf_control *clamp_control; -static struct dev_pm_qos_request qos_req; +static struct freq_qos_request qos_req; static unsigned int min_freq, max_freq; static int clamp_set(struct wf_control *ct, s32 value) @@ -35,7 +35,7 @@ static int clamp_set(struct wf_control *ct, s32 value) } clamped = value; - return dev_pm_qos_update_request(&qos_req, freq); + return freq_qos_update_request(&qos_req, freq); } static int clamp_get(struct wf_control *ct, s32 *value) @@ -77,38 +77,44 @@ static int __init wf_cpufreq_clamp_init(void) min_freq = policy->cpuinfo.min_freq; max_freq = policy->cpuinfo.max_freq; + + ret = freq_qos_add_request(&policy->constraints, &qos_req, FREQ_QOS_MAX, + max_freq); + cpufreq_cpu_put(policy); + if (ret < 0) { + pr_err("%s: Failed to add freq constraint (%d)\n", __func__, + ret); + return ret; + } + dev = get_cpu_device(0); if (unlikely(!dev)) { pr_warn("%s: No cpu device for cpu0\n", __func__); - return -ENODEV; + ret = -ENODEV; + goto fail; } clamp = kmalloc(sizeof(struct wf_control), GFP_KERNEL); - if (clamp == NULL) - return -ENOMEM; - - ret = dev_pm_qos_add_request(dev, &qos_req, DEV_PM_QOS_MAX_FREQUENCY, - max_freq); - if (ret < 0) { - pr_err("%s: Failed to add freq constraint (%d)\n", __func__, - ret); - goto free; + if (clamp == NULL) { + ret = -ENOMEM; + goto fail; } clamp->ops = &clamp_ops; clamp->name = "cpufreq-clamp"; ret = wf_register_control(clamp); if (ret) - goto fail; + goto free; + clamp_control = clamp; return 0; - fail: - dev_pm_qos_remove_request(&qos_req); free: kfree(clamp); + fail: + freq_qos_remove_request(&qos_req); return ret; } @@ -116,7 +122,7 @@ static void __exit wf_cpufreq_clamp_exit(void) { if (clamp_control) { wf_unregister_control(clamp_control); - dev_pm_qos_remove_request(&qos_req); + freq_qos_remove_request(&qos_req); } } diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index aa98953f4462..d6d5ab23c088 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -38,9 +38,9 @@ config MD_AUTODETECT default y ---help--- If you say Y here, then the kernel will try to autodetect raid - arrays as part of its boot process. + arrays as part of its boot process. - If you don't use raid and say Y, this autodetection can cause + If you don't use raid and say Y, this autodetection can cause a several-second delay in the boot time due to various synchronisation steps that are part of this step. @@ -290,7 +290,7 @@ config DM_SNAPSHOT depends on BLK_DEV_DM select DM_BUFIO ---help--- - Allow volume managers to take writable snapshots of a device. + Allow volume managers to take writable snapshots of a device. config DM_THIN_PROVISIONING tristate "Thin provisioning target" @@ -298,7 +298,7 @@ config DM_THIN_PROVISIONING select DM_PERSISTENT_DATA select DM_BIO_PRISON ---help--- - Provides thin provisioning and snapshots that share a data store. + Provides thin provisioning and snapshots that share a data store. config DM_CACHE tristate "Cache target (EXPERIMENTAL)" @@ -307,23 +307,23 @@ config DM_CACHE select DM_PERSISTENT_DATA select DM_BIO_PRISON ---help--- - dm-cache attempts to improve performance of a block device by - moving frequently used data to a smaller, higher performance - device. Different 'policy' plugins can be used to change the - algorithms used to select which blocks are promoted, demoted, - cleaned etc. It supports writeback and writethrough modes. + dm-cache attempts to improve performance of a block device by + moving frequently used data to a smaller, higher performance + device. Different 'policy' plugins can be used to change the + algorithms used to select which blocks are promoted, demoted, + cleaned etc. It supports writeback and writethrough modes. config DM_CACHE_SMQ tristate "Stochastic MQ Cache Policy (EXPERIMENTAL)" depends on DM_CACHE default y ---help--- - A cache policy that uses a multiqueue ordered by recent hits - to select which blocks should be promoted and demoted. - This is meant to be a general purpose policy. It prioritises - reads over writes. This SMQ policy (vs MQ) offers the promise - of less memory utilization, improved performance and increased - adaptability in the face of changing workloads. + A cache policy that uses a multiqueue ordered by recent hits + to select which blocks should be promoted and demoted. + This is meant to be a general purpose policy. It prioritises + reads over writes. This SMQ policy (vs MQ) offers the promise + of less memory utilization, improved performance and increased + adaptability in the face of changing workloads. config DM_WRITECACHE tristate "Writecache target" @@ -343,9 +343,9 @@ config DM_ERA select DM_PERSISTENT_DATA select DM_BIO_PRISON ---help--- - dm-era tracks which parts of a block device are written to - over time. Useful for maintaining cache coherency when using - vendor snapshots. + dm-era tracks which parts of a block device are written to + over time. Useful for maintaining cache coherency when using + vendor snapshots. config DM_CLONE tristate "Clone target (EXPERIMENTAL)" @@ -353,20 +353,20 @@ config DM_CLONE default n select DM_PERSISTENT_DATA ---help--- - dm-clone produces a one-to-one copy of an existing, read-only source - device into a writable destination device. The cloned device is - visible/mountable immediately and the copy of the source device to the - destination device happens in the background, in parallel with user - I/O. + dm-clone produces a one-to-one copy of an existing, read-only source + device into a writable destination device. The cloned device is + visible/mountable immediately and the copy of the source device to the + destination device happens in the background, in parallel with user + I/O. - If unsure, say N. + If unsure, say N. config DM_MIRROR tristate "Mirror target" depends on BLK_DEV_DM ---help--- - Allow volume managers to mirror logical volumes, also - needed for live data migration tools such as 'pvmove'. + Allow volume managers to mirror logical volumes, also + needed for live data migration tools such as 'pvmove'. config DM_LOG_USERSPACE tristate "Mirror userspace logging" @@ -483,7 +483,7 @@ config DM_FLAKEY tristate "Flakey target" depends on BLK_DEV_DM ---help--- - A target that intermittently fails I/O for debugging purposes. + A target that intermittently fails I/O for debugging purposes. config DM_VERITY tristate "Verity target support" diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile index d26b35195825..fd714628da6a 100644 --- a/drivers/md/bcache/Makefile +++ b/drivers/md/bcache/Makefile @@ -5,5 +5,3 @@ obj-$(CONFIG_BCACHE) += bcache.o bcache-y := alloc.o bset.o btree.o closure.o debug.o extents.o\ io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\ util.o writeback.o - -CFLAGS_request.o += -Iblock diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 6f776823b9ba..a1df0d95151c 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -377,7 +377,10 @@ retry_invalidate: if (!fifo_full(&ca->free_inc)) goto retry_invalidate; - bch_prio_write(ca); + if (bch_prio_write(ca, false) < 0) { + ca->invalidate_needs_gc = 1; + wake_up_gc(ca->set); + } } } out: diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 013e35a9e317..9198c1b480d9 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -582,6 +582,7 @@ struct cache_set { */ wait_queue_head_t btree_cache_wait; struct task_struct *btree_cache_alloc_lock; + spinlock_t btree_cannibalize_lock; /* * When we free a btree node, we increment the gen of the bucket the @@ -723,6 +724,7 @@ struct cache_set { unsigned int gc_always_rewrite:1; unsigned int shrinker_disabled:1; unsigned int copy_gc_enabled:1; + unsigned int idle_max_writeback_rate_enabled:1; #define BUCKET_HASH_BITS 12 struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; @@ -977,7 +979,7 @@ bool bch_cached_dev_error(struct cached_dev *dc); __printf(2, 3) bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...); -void bch_prio_write(struct cache *ca); +int bch_prio_write(struct cache *ca, bool wait); void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent); extern struct workqueue_struct *bcache_wq; diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 08768796b543..cffcdc9feefb 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -155,6 +155,7 @@ int __bch_keylist_realloc(struct keylist *l, unsigned int u64s) return 0; } +/* Pop the top key of keylist by pointing l->top to its previous key */ struct bkey *bch_keylist_pop(struct keylist *l) { struct bkey *k = l->keys; @@ -168,6 +169,7 @@ struct bkey *bch_keylist_pop(struct keylist *l) return l->top = k; } +/* Pop the bottom key of keylist and update l->top_p */ void bch_keylist_pop_front(struct keylist *l) { l->top_p -= bkey_u64s(l->keys); @@ -309,7 +311,6 @@ void bch_btree_keys_free(struct btree_keys *b) t->tree = NULL; t->data = NULL; } -EXPORT_SYMBOL(bch_btree_keys_free); int bch_btree_keys_alloc(struct btree_keys *b, unsigned int page_order, @@ -342,7 +343,6 @@ err: bch_btree_keys_free(b); return -ENOMEM; } -EXPORT_SYMBOL(bch_btree_keys_alloc); void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops, bool *expensive_debug_checks) @@ -361,7 +361,6 @@ void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops, * any more. */ } -EXPORT_SYMBOL(bch_btree_keys_init); /* Binary tree stuff for auxiliary search trees */ @@ -678,7 +677,6 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic) bch_bset_build_unwritten_tree(b); } -EXPORT_SYMBOL(bch_bset_init_next); /* * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to @@ -732,7 +730,6 @@ void bch_bset_build_written_tree(struct btree_keys *b) j = inorder_next(j, t->size)) make_bfloat(t, j); } -EXPORT_SYMBOL(bch_bset_build_written_tree); /* Insert */ @@ -780,7 +777,6 @@ fix_right: do { j = j * 2 + 1; } while (j < t->size); } -EXPORT_SYMBOL(bch_bset_fix_invalidated_key); static void bch_bset_fix_lookup_table(struct btree_keys *b, struct bset_tree *t, @@ -855,7 +851,6 @@ bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r) return b->ops->key_merge(b, l, r); } -EXPORT_SYMBOL(bch_bkey_try_merge); void bch_bset_insert(struct btree_keys *b, struct bkey *where, struct bkey *insert) @@ -875,7 +870,6 @@ void bch_bset_insert(struct btree_keys *b, struct bkey *where, bkey_copy(where, insert); bch_bset_fix_lookup_table(b, t, where); } -EXPORT_SYMBOL(bch_bset_insert); unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, struct bkey *replace_key) @@ -931,7 +925,6 @@ copy: bkey_copy(m, k); merged: return status; } -EXPORT_SYMBOL(bch_btree_insert_key); /* Lookup */ @@ -1077,7 +1070,6 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, return i.l; } -EXPORT_SYMBOL(__bch_bset_search); /* Btree iterator */ @@ -1132,7 +1124,6 @@ struct bkey *bch_btree_iter_init(struct btree_keys *b, { return __bch_btree_iter_init(b, iter, search, b->set); } -EXPORT_SYMBOL(bch_btree_iter_init); static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, btree_iter_cmp_fn *cmp) @@ -1165,7 +1156,6 @@ struct bkey *bch_btree_iter_next(struct btree_iter *iter) return __bch_btree_iter_next(iter, btree_iter_cmp); } -EXPORT_SYMBOL(bch_btree_iter_next); struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, struct btree_keys *b, ptr_filter_fn fn) @@ -1196,7 +1186,6 @@ int bch_bset_sort_state_init(struct bset_sort_state *state, return mempool_init_page_pool(&state->pool, 1, page_order); } -EXPORT_SYMBOL(bch_bset_sort_state_init); static void btree_mergesort(struct btree_keys *b, struct bset *out, struct btree_iter *iter, @@ -1313,7 +1302,6 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } -EXPORT_SYMBOL(bch_btree_sort_partial); void bch_btree_sort_and_fix_extents(struct btree_keys *b, struct btree_iter *iter, @@ -1366,7 +1354,6 @@ void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state) out: bch_bset_build_written_tree(b); } -EXPORT_SYMBOL(bch_btree_sort_lazy); void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *stats) { diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ba434d9ac720..14d6c33b0957 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -543,6 +543,11 @@ static void bch_btree_leaf_dirty(struct btree *b, atomic_t *journal_ref) set_btree_node_dirty(b); + /* + * w->journal is always the oldest journal pin of all bkeys + * in the leaf node, to make sure the oldest jset seq won't + * be increased before this btree node is flushed. + */ if (journal_ref) { if (w->journal && journal_pin_cmp(b->c, w->journal, journal_ref)) { @@ -723,6 +728,8 @@ static unsigned long bch_mca_scan(struct shrinker *shrink, * IO can always make forward progress: */ nr /= c->btree_pages; + if (nr == 0) + nr = 1; nr = min_t(unsigned long, nr, mca_can_free(c)); i = 0; @@ -884,15 +891,17 @@ out: static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op) { - struct task_struct *old; - - old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current); - if (old && old != current) { + spin_lock(&c->btree_cannibalize_lock); + if (likely(c->btree_cache_alloc_lock == NULL)) { + c->btree_cache_alloc_lock = current; + } else if (c->btree_cache_alloc_lock != current) { if (op) prepare_to_wait(&c->btree_cache_wait, &op->wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&c->btree_cannibalize_lock); return -EINTR; } + spin_unlock(&c->btree_cannibalize_lock); return 0; } @@ -927,10 +936,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, */ static void bch_cannibalize_unlock(struct cache_set *c) { + spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { c->btree_cache_alloc_lock = NULL; wake_up(&c->btree_cache_wait); } + spin_unlock(&c->btree_cannibalize_lock); } static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op, diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index c12cd809ab19..0164a1fe94a9 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -45,7 +45,6 @@ void closure_sub(struct closure *cl, int v) { closure_put_after_sub(cl, atomic_sub_return(v, &cl->remaining)); } -EXPORT_SYMBOL(closure_sub); /* * closure_put - decrement a closure's refcount @@ -54,7 +53,6 @@ void closure_put(struct closure *cl) { closure_put_after_sub(cl, atomic_dec_return(&cl->remaining)); } -EXPORT_SYMBOL(closure_put); /* * closure_wake_up - wake up all closures on a wait list, without memory barrier @@ -76,7 +74,6 @@ void __closure_wake_up(struct closure_waitlist *wait_list) closure_sub(cl, CLOSURE_WAITING + 1); } } -EXPORT_SYMBOL(__closure_wake_up); /** * closure_wait - add a closure to a waitlist @@ -96,7 +93,6 @@ bool closure_wait(struct closure_waitlist *waitlist, struct closure *cl) return true; } -EXPORT_SYMBOL(closure_wait); struct closure_syncer { struct task_struct *task; @@ -131,7 +127,6 @@ void __sched __closure_sync(struct closure *cl) __set_current_state(TASK_RUNNING); } -EXPORT_SYMBOL(__closure_sync); #ifdef CONFIG_BCACHE_CLOSURES_DEBUG @@ -149,7 +144,6 @@ void closure_debug_create(struct closure *cl) list_add(&cl->all, &closure_list); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL(closure_debug_create); void closure_debug_destroy(struct closure *cl) { @@ -162,7 +156,6 @@ void closure_debug_destroy(struct closure *cl) list_del(&cl->all); spin_unlock_irqrestore(&closure_list_lock, flags); } -EXPORT_SYMBOL(closure_debug_destroy); static struct dentry *closure_debug; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 41adcd1546f1..73478a91a342 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -62,18 +62,6 @@ static void bch_data_insert_keys(struct closure *cl) struct bkey *replace_key = op->replace ? &op->replace_key : NULL; int ret; - /* - * If we're looping, might already be waiting on - * another journal write - can't wait on more than one journal write at - * a time - * - * XXX: this looks wrong - */ -#if 0 - while (atomic_read(&s->cl.remaining) & CLOSURE_WAITING) - closure_sync(&s->cl); -#endif - if (!op->replace) journal_ref = bch_journal(op->c, &op->insert_keys, op->flush_journal ? cl : NULL); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 20ed838e9413..77e9869345e7 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -92,10 +92,11 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev, pr_debug("read sb version %llu, flags %llu, seq %llu, journal size %u", sb->version, sb->flags, sb->seq, sb->keys); - err = "Not a bcache superblock"; + err = "Not a bcache superblock (bad offset)"; if (sb->offset != SB_SECTOR) goto err; + err = "Not a bcache superblock (bad magic)"; if (memcmp(sb->magic, bcache_magic, 16)) goto err; @@ -529,12 +530,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op, closure_sync(cl); } -void bch_prio_write(struct cache *ca) +int bch_prio_write(struct cache *ca, bool wait) { int i; struct bucket *b; struct closure cl; + pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu", + fifo_used(&ca->free[RESERVE_PRIO]), + fifo_used(&ca->free[RESERVE_NONE]), + fifo_used(&ca->free_inc)); + + /* + * Pre-check if there are enough free buckets. In the non-blocking + * scenario it's better to fail early rather than starting to allocate + * buckets and do a cleanup later in case of failure. + */ + if (!wait) { + size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) + + fifo_used(&ca->free[RESERVE_NONE]); + if (prio_buckets(ca) > avail) + return -ENOMEM; + } + closure_init_stack(&cl); lockdep_assert_held(&ca->set->bucket_lock); @@ -544,9 +562,6 @@ void bch_prio_write(struct cache *ca) atomic_long_add(ca->sb.bucket_size * prio_buckets(ca), &ca->meta_sectors_written); - //pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free), - // fifo_used(&ca->free_inc), fifo_used(&ca->unused)); - for (i = prio_buckets(ca) - 1; i >= 0; --i) { long bucket; struct prio_set *p = ca->disk_buckets; @@ -564,7 +579,7 @@ void bch_prio_write(struct cache *ca) p->magic = pset_magic(&ca->sb); p->csum = bch_crc64(&p->magic, bucket_bytes(ca) - 8); - bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true); + bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait); BUG_ON(bucket == -1); mutex_unlock(&ca->set->bucket_lock); @@ -593,6 +608,7 @@ void bch_prio_write(struct cache *ca) ca->prio_last_buckets[i] = ca->prio_buckets[i]; } + return 0; } static void prio_read(struct cache *ca, uint64_t bucket) @@ -761,20 +777,28 @@ static inline int idx_to_first_minor(int idx) static void bcache_device_free(struct bcache_device *d) { + struct gendisk *disk = d->disk; + lockdep_assert_held(&bch_register_lock); - pr_info("%s stopped", d->disk->disk_name); + if (disk) + pr_info("%s stopped", disk->disk_name); + else + pr_err("bcache device (NULL gendisk) stopped"); if (d->c) bcache_device_detach(d); - if (d->disk && d->disk->flags & GENHD_FL_UP) - del_gendisk(d->disk); - if (d->disk && d->disk->queue) - blk_cleanup_queue(d->disk->queue); - if (d->disk) { + + if (disk) { + if (disk->flags & GENHD_FL_UP) + del_gendisk(disk); + + if (disk->queue) + blk_cleanup_queue(disk->queue); + ida_simple_remove(&bcache_device_idx, - first_minor_to_idx(d->disk->first_minor)); - put_disk(d->disk); + first_minor_to_idx(disk->first_minor)); + put_disk(disk); } bioset_exit(&d->bio_split); @@ -1769,6 +1793,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) sema_init(&c->sb_write_mutex, 1); mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); + spin_lock_init(&c->btree_cannibalize_lock); init_waitqueue_head(&c->bucket_wait); init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1); @@ -1809,6 +1834,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->congested_read_threshold_us = 2000; c->congested_write_threshold_us = 20000; c->error_limit = DEFAULT_IO_ERROR_LIMIT; + c->idle_max_writeback_rate_enabled = 1; WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags)); return c; @@ -1954,7 +1980,7 @@ static int run_cache_set(struct cache_set *c) mutex_lock(&c->bucket_lock); for_each_cache(ca, c, i) - bch_prio_write(ca); + bch_prio_write(ca, true); mutex_unlock(&c->bucket_lock); err = "cannot allocate new UUID bucket"; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 627dcea0f5b6..733e2ddf3c78 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -134,6 +134,7 @@ rw_attribute(expensive_debug_checks); rw_attribute(cache_replacement_policy); rw_attribute(btree_shrinker_disabled); rw_attribute(copy_gc_enabled); +rw_attribute(idle_max_writeback_rate); rw_attribute(gc_after_writeback); rw_attribute(size); @@ -747,6 +748,8 @@ SHOW(__bch_cache_set) sysfs_printf(gc_always_rewrite, "%i", c->gc_always_rewrite); sysfs_printf(btree_shrinker_disabled, "%i", c->shrinker_disabled); sysfs_printf(copy_gc_enabled, "%i", c->copy_gc_enabled); + sysfs_printf(idle_max_writeback_rate, "%i", + c->idle_max_writeback_rate_enabled); sysfs_printf(gc_after_writeback, "%i", c->gc_after_writeback); sysfs_printf(io_disable, "%i", test_bit(CACHE_SET_IO_DISABLE, &c->flags)); @@ -864,6 +867,9 @@ STORE(__bch_cache_set) sysfs_strtoul_bool(gc_always_rewrite, c->gc_always_rewrite); sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled); sysfs_strtoul_bool(copy_gc_enabled, c->copy_gc_enabled); + sysfs_strtoul_bool(idle_max_writeback_rate, + c->idle_max_writeback_rate_enabled); + /* * write gc_after_writeback here may overwrite an already set * BCH_DO_AUTO_GC, it doesn't matter because this flag will be @@ -954,6 +960,7 @@ static struct attribute *bch_cache_set_internal_files[] = { &sysfs_gc_always_rewrite, &sysfs_btree_shrinker_disabled, &sysfs_copy_gc_enabled, + &sysfs_idle_max_writeback_rate, &sysfs_gc_after_writeback, &sysfs_io_disable, &sysfs_cutoff_writeback, diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index d60268fe49e1..4a40f9eadeaf 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -122,6 +122,10 @@ static void __update_writeback_rate(struct cached_dev *dc) static bool set_at_max_writeback_rate(struct cache_set *c, struct cached_dev *dc) { + /* Don't sst max writeback rate if it is disabled */ + if (!c->idle_max_writeback_rate_enabled) + return false; + /* Don't set max writeback rate if gc is running */ if (!c->gc_mark_valid) return false; diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c index b5389890bbc3..1f8f98efd97a 100644 --- a/drivers/md/dm-bio-prison-v1.c +++ b/drivers/md/dm-bio-prison-v1.c @@ -150,11 +150,10 @@ static int bio_detain(struct dm_bio_prison *prison, struct dm_bio_prison_cell **cell_result) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __bio_detain(prison, key, inmate, cell_prealloc, cell_result); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -198,11 +197,9 @@ void dm_cell_release(struct dm_bio_prison *prison, struct dm_bio_prison_cell *cell, struct bio_list *bios) { - unsigned long flags; - - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); __cell_release(prison, cell, bios); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); } EXPORT_SYMBOL_GPL(dm_cell_release); @@ -250,12 +247,10 @@ void dm_cell_visit_release(struct dm_bio_prison *prison, void *context, struct dm_bio_prison_cell *cell) { - unsigned long flags; - - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); visit_fn(context, cell); rb_erase(&cell->node, &prison->cells); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); } EXPORT_SYMBOL_GPL(dm_cell_visit_release); @@ -275,11 +270,10 @@ int dm_cell_promote_or_release(struct dm_bio_prison *prison, struct dm_bio_prison_cell *cell) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __promote_or_release(prison, cell); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -379,10 +373,9 @@ EXPORT_SYMBOL_GPL(dm_deferred_entry_dec); int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work) { int r = 1; - unsigned long flags; unsigned next_entry; - spin_lock_irqsave(&ds->lock, flags); + spin_lock_irq(&ds->lock); if ((ds->sweeper == ds->current_entry) && !ds->entries[ds->current_entry].count) r = 0; @@ -392,7 +385,7 @@ int dm_deferred_set_add_work(struct dm_deferred_set *ds, struct list_head *work) if (!ds->entries[next_entry].count) ds->current_entry = next_entry; } - spin_unlock_irqrestore(&ds->lock, flags); + spin_unlock_irq(&ds->lock); return r; } diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c index b092cdc8e1ae..8ee019eda32d 100644 --- a/drivers/md/dm-bio-prison-v2.c +++ b/drivers/md/dm-bio-prison-v2.c @@ -177,11 +177,10 @@ bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 **cell_result) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __get(prison, key, lock_level, inmate, cell_prealloc, cell_result); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -261,11 +260,10 @@ int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 **cell_result) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __lock(prison, key, lock_level, cell_prealloc, cell_result); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -285,11 +283,9 @@ void dm_cell_quiesce_v2(struct dm_bio_prison_v2 *prison, struct dm_bio_prison_cell_v2 *cell, struct work_struct *continuation) { - unsigned long flags; - - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); __quiesce(prison, cell, continuation); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); } EXPORT_SYMBOL_GPL(dm_cell_quiesce_v2); @@ -309,11 +305,10 @@ int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison, unsigned new_lock_level) { int r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __promote(prison, cell, new_lock_level); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } @@ -342,11 +337,10 @@ bool dm_cell_unlock_v2(struct dm_bio_prison_v2 *prison, struct bio_list *bios) { bool r; - unsigned long flags; - spin_lock_irqsave(&prison->lock, flags); + spin_lock_irq(&prison->lock); r = __unlock(prison, cell, bios); - spin_unlock_irqrestore(&prison->lock, flags); + spin_unlock_irq(&prison->lock); return r; } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 8346e6d1816c..2d32821b3a5b 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -74,22 +74,19 @@ static bool __iot_idle_for(struct io_tracker *iot, unsigned long jifs) static bool iot_idle_for(struct io_tracker *iot, unsigned long jifs) { bool r; - unsigned long flags; - spin_lock_irqsave(&iot->lock, flags); + spin_lock_irq(&iot->lock); r = __iot_idle_for(iot, jifs); - spin_unlock_irqrestore(&iot->lock, flags); + spin_unlock_irq(&iot->lock); return r; } static void iot_io_begin(struct io_tracker *iot, sector_t len) { - unsigned long flags; - - spin_lock_irqsave(&iot->lock, flags); + spin_lock_irq(&iot->lock); iot->in_flight += len; - spin_unlock_irqrestore(&iot->lock, flags); + spin_unlock_irq(&iot->lock); } static void __iot_io_end(struct io_tracker *iot, sector_t len) @@ -172,7 +169,6 @@ static void __commit(struct work_struct *_ws) { struct batcher *b = container_of(_ws, struct batcher, commit_work); blk_status_t r; - unsigned long flags; struct list_head work_items; struct work_struct *ws, *tmp; struct continuation *k; @@ -186,12 +182,12 @@ static void __commit(struct work_struct *_ws) * We have to grab these before the commit_op to avoid a race * condition. */ - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); list_splice_init(&b->work_items, &work_items); bio_list_merge(&bios, &b->bios); bio_list_init(&b->bios); b->commit_scheduled = false; - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); r = b->commit_op(b->commit_context); @@ -238,13 +234,12 @@ static void async_commit(struct batcher *b) static void continue_after_commit(struct batcher *b, struct continuation *k) { - unsigned long flags; bool commit_scheduled; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); commit_scheduled = b->commit_scheduled; list_add_tail(&k->ws.entry, &b->work_items); - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (commit_scheduled) async_commit(b); @@ -255,13 +250,12 @@ static void continue_after_commit(struct batcher *b, struct continuation *k) */ static void issue_after_commit(struct batcher *b, struct bio *bio) { - unsigned long flags; bool commit_scheduled; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); commit_scheduled = b->commit_scheduled; bio_list_add(&b->bios, bio); - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (commit_scheduled) async_commit(b); @@ -273,12 +267,11 @@ static void issue_after_commit(struct batcher *b, struct bio *bio) static void schedule_commit(struct batcher *b) { bool immediate; - unsigned long flags; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); immediate = !list_empty(&b->work_items) || !bio_list_empty(&b->bios); b->commit_scheduled = true; - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (immediate) async_commit(b); @@ -630,23 +623,19 @@ static struct per_bio_data *init_per_bio_data(struct bio *bio) static void defer_bio(struct cache *cache, struct bio *bio) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_add(&cache->deferred_bios, bio); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); wake_deferred_bio_worker(cache); } static void defer_bios(struct cache *cache, struct bio_list *bios) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_merge(&cache->deferred_bios, bios); bio_list_init(bios); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); wake_deferred_bio_worker(cache); } @@ -756,33 +745,27 @@ static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock) static void set_discard(struct cache *cache, dm_dblock_t b) { - unsigned long flags; - BUG_ON(from_dblock(b) >= from_dblock(cache->discard_nr_blocks)); atomic_inc(&cache->stats.discard_count); - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); set_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static void clear_discard(struct cache *cache, dm_dblock_t b) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); clear_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static bool is_discarded(struct cache *cache, dm_dblock_t b) { int r; - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); r = test_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); return r; } @@ -790,12 +773,10 @@ static bool is_discarded(struct cache *cache, dm_dblock_t b) static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b) { int r; - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); r = test_bit(from_dblock(oblock_to_dblock(cache, b)), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); return r; } @@ -827,17 +808,16 @@ static void remap_to_cache(struct cache *cache, struct bio *bio, static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) { - unsigned long flags; struct per_bio_data *pb; - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); if (cache->need_tick_bio && !op_is_flush(bio->bi_opf) && bio_op(bio) != REQ_OP_DISCARD) { pb = get_per_bio_data(bio); pb->tick = true; cache->need_tick_bio = false; } - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, @@ -1889,17 +1869,16 @@ static void process_deferred_bios(struct work_struct *ws) { struct cache *cache = container_of(ws, struct cache, deferred_bio_worker); - unsigned long flags; bool commit_needed = false; struct bio_list bios; struct bio *bio; bio_list_init(&bios); - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_merge(&bios, &cache->deferred_bios); bio_list_init(&cache->deferred_bios); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); while ((bio = bio_list_pop(&bios))) { if (bio->bi_opf & REQ_PREFLUSH) diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index 6bc8c1d1c351..08c552e5e41b 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -712,7 +712,7 @@ static int __metadata_commit(struct dm_clone_metadata *cmd) static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) { int r; - unsigned long word, flags; + unsigned long word; word = 0; do { @@ -736,9 +736,9 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) return r; /* Update the changed flag */ - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); dmap->changed = 0; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); return 0; } @@ -746,7 +746,6 @@ static int __flush_dmap(struct dm_clone_metadata *cmd, struct dirty_map *dmap) int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) { int r = -EPERM; - unsigned long flags; struct dirty_map *dmap, *next_dmap; down_write(&cmd->lock); @@ -770,9 +769,9 @@ int dm_clone_metadata_commit(struct dm_clone_metadata *cmd) } /* Swap dirty bitmaps */ - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); cmd->current_dmap = next_dmap; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); /* * No one is accessing the old dirty bitmap anymore, so we can flush @@ -817,9 +816,9 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, { int r = 0; struct dirty_map *dmap; - unsigned long word, region_nr, flags; + unsigned long word, region_nr; - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); if (cmd->read_only) { r = -EPERM; @@ -836,7 +835,7 @@ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, } } out: - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); return r; } @@ -903,13 +902,11 @@ out: void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd) { - unsigned long flags; - down_write(&cmd->lock); - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); cmd->read_only = 1; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); if (!cmd->fail_io) dm_bm_set_read_only(cmd->bm); @@ -919,13 +916,11 @@ void dm_clone_metadata_set_read_only(struct dm_clone_metadata *cmd) void dm_clone_metadata_set_read_write(struct dm_clone_metadata *cmd) { - unsigned long flags; - down_write(&cmd->lock); - spin_lock_irqsave(&cmd->bitmap_lock, flags); + spin_lock_irq(&cmd->bitmap_lock); cmd->read_only = 0; - spin_unlock_irqrestore(&cmd->bitmap_lock, flags); + spin_unlock_irq(&cmd->bitmap_lock); if (!cmd->fail_io) dm_bm_set_read_write(cmd->bm); diff --git a/drivers/md/dm-clone-metadata.h b/drivers/md/dm-clone-metadata.h index 434bff08508b..3fe50a781c11 100644 --- a/drivers/md/dm-clone-metadata.h +++ b/drivers/md/dm-clone-metadata.h @@ -44,7 +44,9 @@ int dm_clone_set_region_hydrated(struct dm_clone_metadata *cmd, unsigned long re * @start: Starting region number * @nr_regions: Number of regions in the range * - * This function doesn't block, so it's safe to call it from interrupt context. + * This function doesn't block, but since it uses spin_lock_irq()/spin_unlock_irq() + * it's NOT safe to call it from any context where interrupts are disabled, e.g., + * from interrupt context. */ int dm_clone_cond_set_range(struct dm_clone_metadata *cmd, unsigned long start, unsigned long nr_regions); diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 4ca8f1977222..b3d89072d21c 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -332,8 +332,6 @@ static void submit_bios(struct bio_list *bios) */ static void issue_bio(struct clone *clone, struct bio *bio) { - unsigned long flags; - if (!bio_triggers_commit(clone, bio)) { generic_make_request(bio); return; @@ -352,9 +350,9 @@ static void issue_bio(struct clone *clone, struct bio *bio) * Batch together any bios that trigger commits and then issue a single * commit for them in process_deferred_flush_bios(). */ - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_add(&clone->deferred_flush_bios, bio); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); wake_worker(clone); } @@ -469,7 +467,7 @@ static void complete_discard_bio(struct clone *clone, struct bio *bio, bool succ static void process_discard_bio(struct clone *clone, struct bio *bio) { - unsigned long rs, re, flags; + unsigned long rs, re; bio_region_range(clone, bio, &rs, &re); BUG_ON(re > clone->nr_regions); @@ -501,9 +499,9 @@ static void process_discard_bio(struct clone *clone, struct bio *bio) /* * Defer discard processing. */ - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_add(&clone->deferred_discard_bios, bio); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); wake_worker(clone); } @@ -554,6 +552,12 @@ struct hash_table_bucket { #define bucket_unlock_irqrestore(bucket, flags) \ spin_unlock_irqrestore(&(bucket)->lock, flags) +#define bucket_lock_irq(bucket) \ + spin_lock_irq(&(bucket)->lock) + +#define bucket_unlock_irq(bucket) \ + spin_unlock_irq(&(bucket)->lock) + static int hash_table_init(struct clone *clone) { unsigned int i, sz; @@ -851,7 +855,6 @@ static void hydration_overwrite(struct dm_clone_region_hydration *hd, struct bio */ static void hydrate_bio_region(struct clone *clone, struct bio *bio) { - unsigned long flags; unsigned long region_nr; struct hash_table_bucket *bucket; struct dm_clone_region_hydration *hd, *hd2; @@ -859,19 +862,19 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) region_nr = bio_to_region(clone, bio); bucket = get_hash_table_bucket(clone, region_nr); - bucket_lock_irqsave(bucket, flags); + bucket_lock_irq(bucket); hd = __hash_find(bucket, region_nr); if (hd) { /* Someone else is hydrating the region */ bio_list_add(&hd->deferred_bios, bio); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); return; } if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) { /* The region has been hydrated */ - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); issue_bio(clone, bio); return; } @@ -880,16 +883,16 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) * We must allocate a hydration descriptor and start the hydration of * the corresponding region. */ - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); hd = alloc_hydration(clone); hydration_init(hd, region_nr); - bucket_lock_irqsave(bucket, flags); + bucket_lock_irq(bucket); /* Check if the region has been hydrated in the meantime. */ if (dm_clone_is_region_hydrated(clone->cmd, region_nr)) { - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); free_hydration(hd); issue_bio(clone, bio); return; @@ -899,7 +902,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) if (hd2 != hd) { /* Someone else started the region's hydration. */ bio_list_add(&hd2->deferred_bios, bio); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); free_hydration(hd); return; } @@ -911,7 +914,7 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) */ if (unlikely(get_clone_mode(clone) >= CM_READ_ONLY)) { hlist_del(&hd->h); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); free_hydration(hd); bio_io_error(bio); return; @@ -925,11 +928,11 @@ static void hydrate_bio_region(struct clone *clone, struct bio *bio) * to the destination device. */ if (is_overwrite_bio(clone, bio)) { - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); hydration_overwrite(hd, bio); } else { bio_list_add(&hd->deferred_bios, bio); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); hydration_copy(hd, 1); } } @@ -996,7 +999,6 @@ static unsigned long __start_next_hydration(struct clone *clone, unsigned long offset, struct batch_info *batch) { - unsigned long flags; struct hash_table_bucket *bucket; struct dm_clone_region_hydration *hd; unsigned long nr_regions = clone->nr_regions; @@ -1010,13 +1012,13 @@ static unsigned long __start_next_hydration(struct clone *clone, break; bucket = get_hash_table_bucket(clone, offset); - bucket_lock_irqsave(bucket, flags); + bucket_lock_irq(bucket); if (!dm_clone_is_region_hydrated(clone->cmd, offset) && !__hash_find(bucket, offset)) { hydration_init(hd, offset); __insert_region_hydration(bucket, hd); - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); /* Batch hydration */ __batch_hydration(batch, hd); @@ -1024,7 +1026,7 @@ static unsigned long __start_next_hydration(struct clone *clone, return (offset + 1); } - bucket_unlock_irqrestore(bucket, flags); + bucket_unlock_irq(bucket); } while (++offset < nr_regions); @@ -1140,13 +1142,13 @@ static void process_deferred_discards(struct clone *clone) int r = -EPERM; struct bio *bio; struct blk_plug plug; - unsigned long rs, re, flags; + unsigned long rs, re; struct bio_list discards = BIO_EMPTY_LIST; - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_merge(&discards, &clone->deferred_discard_bios); bio_list_init(&clone->deferred_discard_bios); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); if (bio_list_empty(&discards)) return; @@ -1176,13 +1178,12 @@ out: static void process_deferred_bios(struct clone *clone) { - unsigned long flags; struct bio_list bios = BIO_EMPTY_LIST; - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_merge(&bios, &clone->deferred_bios); bio_list_init(&clone->deferred_bios); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); if (bio_list_empty(&bios)) return; @@ -1193,7 +1194,6 @@ static void process_deferred_bios(struct clone *clone) static void process_deferred_flush_bios(struct clone *clone) { struct bio *bio; - unsigned long flags; struct bio_list bios = BIO_EMPTY_LIST; struct bio_list bio_completions = BIO_EMPTY_LIST; @@ -1201,13 +1201,13 @@ static void process_deferred_flush_bios(struct clone *clone) * If there are any deferred flush bios, we must commit the metadata * before issuing them or signaling their completion. */ - spin_lock_irqsave(&clone->lock, flags); + spin_lock_irq(&clone->lock); bio_list_merge(&bios, &clone->deferred_flush_bios); bio_list_init(&clone->deferred_flush_bios); bio_list_merge(&bio_completions, &clone->deferred_flush_completions); bio_list_init(&clone->deferred_flush_completions); - spin_unlock_irqrestore(&clone->lock, flags); + spin_unlock_irq(&clone->lock); if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_clone_changed_this_transaction(clone->cmd) && need_commit_due_to_time(clone))) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f87f6495652f..eb9782fc93fe 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2700,21 +2700,18 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, - 1, devname); + cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, + cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1, devname); else cc->crypt_queue = alloc_workqueue("kcryptd/%s", - WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus(), devname); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c index 8288887b7f94..eb37584427a4 100644 --- a/drivers/md/dm-dust.c +++ b/drivers/md/dm-dust.c @@ -17,6 +17,7 @@ struct badblock { struct rb_node node; sector_t bb; + unsigned char wr_fail_cnt; }; struct dust_device { @@ -101,7 +102,8 @@ static int dust_remove_block(struct dust_device *dd, unsigned long long block) return 0; } -static int dust_add_block(struct dust_device *dd, unsigned long long block) +static int dust_add_block(struct dust_device *dd, unsigned long long block, + unsigned char wr_fail_cnt) { struct badblock *bblock; unsigned long flags; @@ -115,6 +117,7 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block) spin_lock_irqsave(&dd->dust_lock, flags); bblock->bb = block; + bblock->wr_fail_cnt = wr_fail_cnt; if (!dust_rb_insert(&dd->badblocklist, bblock)) { if (!dd->quiet_mode) { DMERR("%s: block %llu already in badblocklist", @@ -126,8 +129,10 @@ static int dust_add_block(struct dust_device *dd, unsigned long long block) } dd->badblock_count++; - if (!dd->quiet_mode) - DMINFO("%s: badblock added at block %llu", __func__, block); + if (!dd->quiet_mode) { + DMINFO("%s: badblock added at block %llu with write fail count %hhu", + __func__, block, wr_fail_cnt); + } spin_unlock_irqrestore(&dd->dust_lock, flags); return 0; @@ -163,22 +168,27 @@ static int dust_map_read(struct dust_device *dd, sector_t thisblock, bool fail_read_on_bb) { unsigned long flags; - int ret = DM_MAPIO_REMAPPED; + int r = DM_MAPIO_REMAPPED; if (fail_read_on_bb) { thisblock >>= dd->sect_per_block_shift; spin_lock_irqsave(&dd->dust_lock, flags); - ret = __dust_map_read(dd, thisblock); + r = __dust_map_read(dd, thisblock); spin_unlock_irqrestore(&dd->dust_lock, flags); } - return ret; + return r; } -static void __dust_map_write(struct dust_device *dd, sector_t thisblock) +static int __dust_map_write(struct dust_device *dd, sector_t thisblock) { struct badblock *bblk = dust_rb_search(&dd->badblocklist, thisblock); + if (bblk && bblk->wr_fail_cnt > 0) { + bblk->wr_fail_cnt--; + return DM_MAPIO_KILL; + } + if (bblk) { rb_erase(&bblk->node, &dd->badblocklist); dd->badblock_count--; @@ -189,37 +199,40 @@ static void __dust_map_write(struct dust_device *dd, sector_t thisblock) (unsigned long long)thisblock); } } + + return DM_MAPIO_REMAPPED; } static int dust_map_write(struct dust_device *dd, sector_t thisblock, bool fail_read_on_bb) { unsigned long flags; + int ret = DM_MAPIO_REMAPPED; if (fail_read_on_bb) { thisblock >>= dd->sect_per_block_shift; spin_lock_irqsave(&dd->dust_lock, flags); - __dust_map_write(dd, thisblock); + ret = __dust_map_write(dd, thisblock); spin_unlock_irqrestore(&dd->dust_lock, flags); } - return DM_MAPIO_REMAPPED; + return ret; } static int dust_map(struct dm_target *ti, struct bio *bio) { struct dust_device *dd = ti->private; - int ret; + int r; bio_set_dev(bio, dd->dev->bdev); bio->bi_iter.bi_sector = dd->start + dm_target_offset(ti, bio->bi_iter.bi_sector); if (bio_data_dir(bio) == READ) - ret = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); + r = dust_map_read(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); else - ret = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); + r = dust_map_write(dd, bio->bi_iter.bi_sector, dd->fail_read_on_bb); - return ret; + return r; } static bool __dust_clear_badblocks(struct rb_root *tree, @@ -375,8 +388,10 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv, struct dust_device *dd = ti->private; sector_t size = i_size_read(dd->dev->bdev->bd_inode) >> SECTOR_SHIFT; bool invalid_msg = false; - int result = -EINVAL; + int r = -EINVAL; unsigned long long tmp, block; + unsigned char wr_fail_cnt; + unsigned int tmp_ui; unsigned long flags; char dummy; @@ -388,45 +403,69 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv, } else if (!strcasecmp(argv[0], "disable")) { DMINFO("disabling read failures on bad sectors"); dd->fail_read_on_bb = false; - result = 0; + r = 0; } else if (!strcasecmp(argv[0], "enable")) { DMINFO("enabling read failures on bad sectors"); dd->fail_read_on_bb = true; - result = 0; + r = 0; } else if (!strcasecmp(argv[0], "countbadblocks")) { spin_lock_irqsave(&dd->dust_lock, flags); DMINFO("countbadblocks: %llu badblock(s) found", dd->badblock_count); spin_unlock_irqrestore(&dd->dust_lock, flags); - result = 0; + r = 0; } else if (!strcasecmp(argv[0], "clearbadblocks")) { - result = dust_clear_badblocks(dd); + r = dust_clear_badblocks(dd); } else if (!strcasecmp(argv[0], "quiet")) { if (!dd->quiet_mode) dd->quiet_mode = true; else dd->quiet_mode = false; - result = 0; + r = 0; } else { invalid_msg = true; } } else if (argc == 2) { if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) - return result; + return r; block = tmp; sector_div(size, dd->sect_per_block); if (block > size) { DMERR("selected block value out of range"); - return result; + return r; } if (!strcasecmp(argv[0], "addbadblock")) - result = dust_add_block(dd, block); + r = dust_add_block(dd, block, 0); else if (!strcasecmp(argv[0], "removebadblock")) - result = dust_remove_block(dd, block); + r = dust_remove_block(dd, block); else if (!strcasecmp(argv[0], "queryblock")) - result = dust_query_block(dd, block); + r = dust_query_block(dd, block); + else + invalid_msg = true; + + } else if (argc == 3) { + if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) + return r; + + if (sscanf(argv[2], "%u%c", &tmp_ui, &dummy) != 1) + return r; + + block = tmp; + if (tmp_ui > 255) { + DMERR("selected write fail count out of range"); + return r; + } + wr_fail_cnt = tmp_ui; + sector_div(size, dd->sect_per_block); + if (block > size) { + DMERR("selected block value out of range"); + return r; + } + + if (!strcasecmp(argv[0], "addbadblock")) + r = dust_add_block(dd, block, wr_fail_cnt); else invalid_msg = true; @@ -436,7 +475,7 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv, if (invalid_msg) DMERR("unrecognized message '%s' received", argv[0]); - return result; + return r; } static void dust_status(struct dm_target *ti, status_type_t type, @@ -499,12 +538,12 @@ static struct target_type dust_target = { static int __init dm_dust_init(void) { - int result = dm_register_target(&dust_target); + int r = dm_register_target(&dust_target); - if (result < 0) - DMERR("dm_register_target failed %d", result); + if (r < 0) + DMERR("dm_register_target failed %d", r); - return result; + return r; } static void __exit dm_dust_exit(void) diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 2900fbde89b3..a2cc9e45cbba 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -280,7 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio) struct flakey_c *fc = ti->private; bio_set_dev(bio, fc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector); } @@ -322,8 +322,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); pb->bio_submitted = false; - /* Do not fail reset zone */ - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) goto map_bio; /* Are we alive ? */ @@ -384,7 +383,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - if (bio_op(bio) == REQ_OP_ZONE_RESET) + if (op_is_zone_mgmt(bio_op(bio))) return DM_ENDIO_DONE; if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { @@ -460,21 +459,15 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev } #ifdef CONFIG_BLK_DEV_ZONED -static int flakey_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +static int flakey_report_zones(struct dm_target *ti, + struct dm_report_zones_args *args, unsigned int nr_zones) { struct flakey_c *fc = ti->private; - int ret; + sector_t sector = flakey_map_sector(ti, args->next_sector); - /* Do report and remap it */ - ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector), - zones, nr_zones); - if (ret != 0) - return ret; - - if (*nr_zones) - dm_remap_zone_report(ti, fc->start, zones, nr_zones); - return 0; + args->start = fc->start; + return blkdev_report_zones(fc->dev->bdev, sector, nr_zones, + dm_report_zones_cb, args); } #endif diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index dab4446fe7d8..b225b3e445fa 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -53,6 +53,7 @@ #define SB_VERSION_1 1 #define SB_VERSION_2 2 #define SB_VERSION_3 3 +#define SB_VERSION_4 4 #define SB_SECTORS 8 #define MAX_SECTORS_PER_BLOCK 8 @@ -73,6 +74,7 @@ struct superblock { #define SB_FLAG_HAVE_JOURNAL_MAC 0x1 #define SB_FLAG_RECALCULATING 0x2 #define SB_FLAG_DIRTY_BITMAP 0x4 +#define SB_FLAG_FIXED_PADDING 0x8 #define JOURNAL_ENTRY_ROUNDUP 8 @@ -250,6 +252,7 @@ struct dm_integrity_c { bool journal_uptodate; bool just_formatted; bool recalculate_flag; + bool fix_padding; struct alg_spec internal_hash_alg; struct alg_spec journal_crypt_alg; @@ -463,7 +466,9 @@ static void wraparound_section(struct dm_integrity_c *ic, unsigned *sec_ptr) static void sb_set_version(struct dm_integrity_c *ic) { - if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP)) + if (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) + ic->sb->version = SB_VERSION_4; + else if (ic->mode == 'B' || ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP)) ic->sb->version = SB_VERSION_3; else if (ic->meta_dev || ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) ic->sb->version = SB_VERSION_2; @@ -2955,6 +2960,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, arg_count += !!ic->internal_hash_alg.alg_string; arg_count += !!ic->journal_crypt_alg.alg_string; arg_count += !!ic->journal_mac_alg.alg_string; + arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0; DMEMIT("%s %llu %u %c %u", ic->dev->name, (unsigned long long)ic->start, ic->tag_size, ic->mode, arg_count); if (ic->meta_dev) @@ -2974,6 +2980,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, DMEMIT(" sectors_per_bit:%llu", (unsigned long long)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit); DMEMIT(" bitmap_flush_interval:%u", jiffies_to_msecs(ic->bitmap_flush_interval)); } + if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0) + DMEMIT(" fix_padding"); #define EMIT_ALG(a, n) \ do { \ @@ -3042,8 +3050,14 @@ static int calculate_device_limits(struct dm_integrity_c *ic) if (!ic->meta_dev) { sector_t last_sector, last_area, last_offset; - ic->metadata_run = roundup((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block), - (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS)) >> SECTOR_SHIFT; + /* we have to maintain excessive padding for compatibility with existing volumes */ + __u64 metadata_run_padding = + ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING) ? + (__u64)(METADATA_PADDING_SECTORS << SECTOR_SHIFT) : + (__u64)(1 << SECTOR_SHIFT << METADATA_PADDING_SECTORS); + + ic->metadata_run = round_up((__u64)ic->tag_size << (ic->sb->log2_interleave_sectors - ic->sb->log2_sectors_per_block), + metadata_run_padding) >> SECTOR_SHIFT; if (!(ic->metadata_run & (ic->metadata_run - 1))) ic->log2_metadata_run = __ffs(ic->metadata_run); else @@ -3086,6 +3100,8 @@ static int initialize_superblock(struct dm_integrity_c *ic, unsigned journal_sec journal_sections = 1; if (!ic->meta_dev) { + if (ic->fix_padding) + ic->sb->flags |= cpu_to_le32(SB_FLAG_FIXED_PADDING); ic->sb->journal_sections = cpu_to_le32(journal_sections); if (!interleave_sectors) interleave_sectors = DEFAULT_INTERLEAVE_SECTORS; @@ -3725,6 +3741,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } else if (!strcmp(opt_string, "recalculate")) { ic->recalculate_flag = true; + } else if (!strcmp(opt_string, "fix_padding")) { + ic->fix_padding = true; } else { r = -EINVAL; ti->error = "Invalid argument"; @@ -3867,7 +3885,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) should_write_sb = true; } - if (!ic->sb->version || ic->sb->version > SB_VERSION_3) { + if (!ic->sb->version || ic->sb->version > SB_VERSION_4) { r = -EINVAL; ti->error = "Unknown version"; goto bad; @@ -4182,7 +4200,7 @@ static void dm_integrity_dtr(struct dm_target *ti) static struct target_type integrity_target = { .name = "integrity", - .version = {1, 3, 0}, + .version = {1, 4, 0}, .module = THIS_MODULE, .features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY, .ctr = dm_integrity_ctr, diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index ecefe6703736..8d07fdf63a47 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -90,7 +90,7 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio) struct linear_c *lc = ti->private; bio_set_dev(bio, lc->dev->bdev); - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) bio->bi_iter.bi_sector = linear_map_sector(ti, bio->bi_iter.bi_sector); } @@ -136,21 +136,15 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev } #ifdef CONFIG_BLK_DEV_ZONED -static int linear_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +static int linear_report_zones(struct dm_target *ti, + struct dm_report_zones_args *args, unsigned int nr_zones) { - struct linear_c *lc = (struct linear_c *) ti->private; - int ret; - - /* Do report and remap it */ - ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector), - zones, nr_zones); - if (ret != 0) - return ret; + struct linear_c *lc = ti->private; + sector_t sector = linear_map_sector(ti, args->next_sector); - if (*nr_zones) - dm_remap_zone_report(ti, lc->start, zones, nr_zones); - return 0; + args->start = lc->start; + return blkdev_report_zones(lc->dev->bdev, sector, nr_zones, + dm_report_zones_cb, args); } #endif diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index b0aa595e4375..c412eaa975fc 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -209,6 +209,7 @@ struct raid_dev { #define RT_FLAG_RS_SUSPENDED 5 #define RT_FLAG_RS_IN_SYNC 6 #define RT_FLAG_RS_RESYNCING 7 +#define RT_FLAG_RS_GROW 8 /* Array elements of 64 bit needed for rebuild/failed disk bits */ #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8) @@ -241,6 +242,9 @@ struct raid_set { struct raid_type *raid_type; struct dm_target_callbacks callbacks; + sector_t array_sectors; + sector_t dev_sectors; + /* Optional raid4/5/6 journal device */ struct journal_dev { struct dm_dev *dev; @@ -616,7 +620,6 @@ static int raid10_format_to_md_layout(struct raid_set *rs, } else if (algorithm == ALGORITHM_RAID10_FAR) { f = copies; - r = !RAID10_OFFSET; if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) r |= RAID10_USE_FAR_SETS; @@ -1615,13 +1618,12 @@ static int _check_data_dev_sectors(struct raid_set *rs) } /* Calculate the sectors per device and per array used for @rs */ -static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev) +static int rs_set_dev_and_array_sectors(struct raid_set *rs, sector_t sectors, bool use_mddev) { int delta_disks; unsigned int data_stripes; + sector_t array_sectors = sectors, dev_sectors = sectors; struct mddev *mddev = &rs->md; - struct md_rdev *rdev; - sector_t array_sectors = rs->ti->len, dev_sectors = rs->ti->len; if (use_mddev) { delta_disks = mddev->delta_disks; @@ -1656,12 +1658,9 @@ static int rs_set_dev_and_array_sectors(struct raid_set *rs, bool use_mddev) /* Striped layouts */ array_sectors = (data_stripes + delta_disks) * dev_sectors; - rdev_for_each(rdev, mddev) - if (!test_bit(Journal, &rdev->flags)) - rdev->sectors = dev_sectors; - mddev->array_sectors = array_sectors; mddev->dev_sectors = dev_sectors; + rs_set_rdev_sectors(rs); return _check_data_dev_sectors(rs); bad: @@ -1670,7 +1669,7 @@ bad: } /* Setup recovery on @rs */ -static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) +static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) { /* raid0 does not recover */ if (rs_is_raid0(rs)) @@ -1691,22 +1690,6 @@ static void __rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) ? MaxSector : dev_sectors; } -/* Setup recovery on @rs based on raid type, device size and 'nosync' flag */ -static void rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors) -{ - if (!dev_sectors) - /* New raid set or 'sync' flag provided */ - __rs_setup_recovery(rs, 0); - else if (dev_sectors == MaxSector) - /* Prevent recovery */ - __rs_setup_recovery(rs, MaxSector); - else if (__rdev_sectors(rs) < dev_sectors) - /* Grown raid set */ - __rs_setup_recovery(rs, __rdev_sectors(rs)); - else - __rs_setup_recovery(rs, MaxSector); -} - static void do_table_event(struct work_struct *ws) { struct raid_set *rs = container_of(ws, struct raid_set, md.event_work); @@ -2474,7 +2457,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) return -EINVAL; } - /* Enable bitmap creation for RAID levels != 0 */ + /* Enable bitmap creation on @rs unless no metadevs or raid0 or journaled raid4/5/6 set. */ mddev->bitmap_info.offset = (rt_is_raid0(rs->raid_type) || rs->journal_dev.dev) ? 0 : to_sector(4096); mddev->bitmap_info.default_offset = mddev->bitmap_info.offset; @@ -2911,7 +2894,7 @@ static int rs_setup_reshape(struct raid_set *rs) /* Remove disk(s) */ } else if (rs->delta_disks < 0) { - r = rs_set_dev_and_array_sectors(rs, true); + r = rs_set_dev_and_array_sectors(rs, rs->ti->len, true); mddev->reshape_backwards = 1; /* removing disk(s) -> backward reshape */ /* Change layout and/or chunk size */ @@ -3008,7 +2991,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) bool resize = false; struct raid_type *rt; unsigned int num_raid_params, num_raid_devs; - sector_t calculated_dev_sectors, rdev_sectors, reshape_sectors; + sector_t sb_array_sectors, rdev_sectors, reshape_sectors; struct raid_set *rs = NULL; const char *arg; struct rs_layout rs_layout; @@ -3067,11 +3050,13 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) * * Any existing superblock will overwrite the array and device sizes */ - r = rs_set_dev_and_array_sectors(rs, false); + r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false); if (r) goto bad; - calculated_dev_sectors = rs->md.dev_sectors; + /* Memorize just calculated, potentially larger sizes to grow the raid set in preresume */ + rs->array_sectors = rs->md.array_sectors; + rs->dev_sectors = rs->md.dev_sectors; /* * Backup any new raid set level, layout, ... @@ -3084,6 +3069,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) goto bad; + /* All in-core metadata now as of current superblocks after calling analyse_superblocks() */ + sb_array_sectors = rs->md.array_sectors; rdev_sectors = __rdev_sectors(rs); if (!rdev_sectors) { ti->error = "Invalid rdev size"; @@ -3093,8 +3080,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) reshape_sectors = _get_reshape_sectors(rs); - if (calculated_dev_sectors != rdev_sectors) - resize = calculated_dev_sectors != (reshape_sectors ? rdev_sectors - reshape_sectors : rdev_sectors); + if (rs->dev_sectors != rdev_sectors) { + resize = (rs->dev_sectors != rdev_sectors - reshape_sectors); + if (rs->dev_sectors > rdev_sectors - reshape_sectors) + set_bit(RT_FLAG_RS_GROW, &rs->runtime_flags); + } INIT_WORK(&rs->md.event_work, do_table_event); ti->private = rs; @@ -3121,13 +3111,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); rs_set_new(rs); } else if (rs_is_recovering(rs)) { - /* Rebuild particular devices */ - if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { - set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - rs_setup_recovery(rs, MaxSector); - } /* A recovering raid set may be resized */ - ; /* skip setup rs */ + goto size_check; } else if (rs_is_reshaping(rs)) { /* Have to reject size change request during reshape */ if (resize) { @@ -3171,6 +3156,9 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) rs_setup_recovery(rs, MaxSector); rs_set_new(rs); } else if (rs_reshape_requested(rs)) { + /* Only request grow on raid set size extensions, not on reshapes. */ + clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags); + /* * No need to check for 'ongoing' takeover here, because takeover * is an instant operation as oposed to an ongoing reshape. @@ -3201,13 +3189,31 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) } rs_set_cur(rs); } else { +size_check: /* May not set recovery when a device rebuild is requested */ if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { - rs_setup_recovery(rs, MaxSector); + clear_bit(RT_FLAG_RS_GROW, &rs->runtime_flags); set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - } else - rs_setup_recovery(rs, test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags) ? - 0 : (resize ? calculated_dev_sectors : MaxSector)); + rs_setup_recovery(rs, MaxSector); + } else if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) { + /* + * Set raid set to current size, i.e. size as of + * superblocks to grow to larger size in preresume. + */ + r = rs_set_dev_and_array_sectors(rs, sb_array_sectors, false); + if (r) + goto bad; + + rs_setup_recovery(rs, rs->md.recovery_cp < rs->md.dev_sectors ? rs->md.recovery_cp : rs->md.dev_sectors); + } else { + /* This is no size change or it is shrinking, update size and record in superblocks */ + r = rs_set_dev_and_array_sectors(rs, rs->ti->len, false); + if (r) + goto bad; + + if (sb_array_sectors > rs->array_sectors) + set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); + } rs_set_cur(rs); } @@ -3406,10 +3412,9 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev) /* Helper to return resync/reshape progress for @rs and runtime flags for raid set in sync / resynching */ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, - sector_t resync_max_sectors) + enum sync_state state, sector_t resync_max_sectors) { sector_t r; - enum sync_state state; struct mddev *mddev = &rs->md; clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); @@ -3420,8 +3425,6 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - state = decipher_sync_action(mddev, recovery); - if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery)) r = mddev->recovery_cp; else @@ -3439,18 +3442,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, /* * In case we are recovering, the array is not in sync * and health chars should show the recovering legs. + * + * Already retrieved recovery offset from curr_resync_completed above. */ ; - else if (state == st_resync) - /* - * If "resync" is occurring, the raid set - * is or may be out of sync hence the health - * characters shall be 'a'. - */ - set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - else if (state == st_reshape) + + else if (state == st_resync || state == st_reshape) /* - * If "reshape" is occurring, the raid set + * If "resync/reshape" is occurring, the raid set * is or may be out of sync hence the health * characters shall be 'a'. */ @@ -3464,22 +3463,22 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - else { - struct md_rdev *rdev; - + else if (test_bit(MD_RECOVERY_NEEDED, &recovery)) /* * We are idle and recovery is needed, prevent 'A' chars race * caused by components still set to in-sync by constructor. */ - if (test_bit(MD_RECOVERY_NEEDED, &recovery)) - set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); + set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); + else { /* - * The raid set may be doing an initial sync, or it may - * be rebuilding individual components. If all the - * devices are In_sync, then it is the raid set that is - * being initialized. + * We are idle and the raid set may be doing an initial + * sync, or it may be rebuilding individual components. + * If all the devices are In_sync, then it is the raid set + * that is being initialized. */ + struct md_rdev *rdev; + set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); rdev_for_each(rdev, mddev) if (!test_bit(Journal, &rdev->flags) && @@ -3512,7 +3511,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, unsigned int rebuild_disks; unsigned int write_mostly_params = 0; sector_t progress, resync_max_sectors, resync_mismatches; - const char *sync_action; + enum sync_state state; struct raid_type *rt; switch (type) { @@ -3526,14 +3525,14 @@ static void raid_status(struct dm_target *ti, status_type_t type, /* Access most recent mddev properties for status output */ smp_rmb(); - recovery = rs->md.recovery; /* Get sensible max sectors even if raid set not yet started */ resync_max_sectors = test_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags) ? mddev->resync_max_sectors : mddev->dev_sectors; - progress = rs_get_progress(rs, recovery, resync_max_sectors); + recovery = rs->md.recovery; + state = decipher_sync_action(mddev, recovery); + progress = rs_get_progress(rs, recovery, state, resync_max_sectors); resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ? atomic64_read(&mddev->resync_mismatches) : 0; - sync_action = sync_str(decipher_sync_action(&rs->md, recovery)); /* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */ for (i = 0; i < rs->raid_disks; i++) @@ -3561,7 +3560,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, * See Documentation/admin-guide/device-mapper/dm-raid.rst for * information on each of these states. */ - DMEMIT(" %s", sync_action); + DMEMIT(" %s", sync_str(state)); /* * v1.5.0+: @@ -3955,11 +3954,22 @@ static int raid_preresume(struct dm_target *ti) if (r) return r; - /* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */ - if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap && - mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) { - r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors, - to_bytes(rs->requested_bitmap_chunk_sectors), 0); + /* We are extending the raid set size, adjust mddev/md_rdev sizes and set capacity. */ + if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) { + mddev->array_sectors = rs->array_sectors; + mddev->dev_sectors = rs->dev_sectors; + rs_set_rdev_sectors(rs); + rs_set_capacity(rs); + } + + /* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) or grown device size */ + if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap && + (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags) || + (rs->requested_bitmap_chunk_sectors && + mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) { + int chunksize = to_bytes(rs->requested_bitmap_chunk_sectors) ?: mddev->bitmap_info.chunksize; + + r = md_bitmap_resize(mddev->bitmap, mddev->dev_sectors, chunksize, 0); if (r) DMERR("Failed to resize bitmap"); } @@ -3968,8 +3978,10 @@ static int raid_preresume(struct dm_target *ti) /* Be prepared for mddev_resume() in raid_resume() */ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) { - set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); mddev->resync_min = mddev->recovery_cp; + if (test_bit(RT_FLAG_RS_GROW, &rs->runtime_flags)) + mddev->resync_max_sectors = mddev->dev_sectors; } /* Check for any reshape request unless new raid set */ @@ -4017,7 +4029,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 14, 0}, + .version = {1, 15, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 8547d7594338..63bbcc20f49a 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -55,19 +55,6 @@ static void trigger_event(struct work_struct *work) dm_table_event(sc->ti->table); } -static inline struct stripe_c *alloc_context(unsigned int stripes) -{ - size_t len; - - if (dm_array_too_big(sizeof(struct stripe_c), sizeof(struct stripe), - stripes)) - return NULL; - - len = sizeof(struct stripe_c) + (sizeof(struct stripe) * stripes); - - return kmalloc(len, GFP_KERNEL); -} - /* * Parse a single <dev> <sector> pair */ @@ -142,7 +129,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) return -EINVAL; } - sc = alloc_context(stripes); + sc = kmalloc(struct_size(sc, stripe, stripes), GFP_KERNEL); if (!sc) { ti->error = "Memory allocation for striped context " "failed"; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 52e049554f5c..2ae0c1913766 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -918,21 +918,15 @@ bool dm_table_supports_dax(struct dm_table *t, static bool dm_table_does_not_support_partial_completion(struct dm_table *t); -struct verify_rq_based_data { - unsigned sq_count; - unsigned mq_count; -}; - -static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - struct verify_rq_based_data *v = data; + struct block_device *bdev = dev->bdev; + struct request_queue *q = bdev_get_queue(bdev); - if (queue_is_mq(q)) - v->mq_count++; - else - v->sq_count++; + /* request-based cannot stack on partitions! */ + if (bdev != bdev->bd_contains) + return false; return queue_is_mq(q); } @@ -941,7 +935,6 @@ static int dm_table_determine_type(struct dm_table *t) { unsigned i; unsigned bio_based = 0, request_based = 0, hybrid = 0; - struct verify_rq_based_data v = {.sq_count = 0, .mq_count = 0}; struct dm_target *tgt; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); @@ -1045,14 +1038,10 @@ verify_rq_based: /* Non-request-stackable devices can't be used for request-based dm */ if (!tgt->type->iterate_devices || - !tgt->type->iterate_devices(tgt, device_is_rq_based, &v)) { + !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) { DMERR("table load rejected: including non-request-stackable devices"); return -EINVAL; } - if (v.sq_count > 0) { - DMERR("table load rejected: not all devices are blk-mq request-stackable"); - return -EINVAL; - } return 0; } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index fcd887703f95..5a2c494cb552 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -609,13 +609,12 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, blk_status_t error) { struct bio_list bios; - unsigned long flags; bio_list_init(&bios); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); __merge_bio_list(&bios, master); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); error_bio_list(&bios, error); } @@ -623,15 +622,14 @@ static void error_thin_bio_list(struct thin_c *tc, struct bio_list *master, static void requeue_deferred_cells(struct thin_c *tc) { struct pool *pool = tc->pool; - unsigned long flags; struct list_head cells; struct dm_bio_prison_cell *cell, *tmp; INIT_LIST_HEAD(&cells); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_splice_init(&tc->deferred_cells, &cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); list_for_each_entry_safe(cell, tmp, &cells, user_list) cell_requeue(pool, cell); @@ -640,14 +638,13 @@ static void requeue_deferred_cells(struct thin_c *tc) static void requeue_io(struct thin_c *tc) { struct bio_list bios; - unsigned long flags; bio_list_init(&bios); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); __merge_bio_list(&bios, &tc->deferred_bio_list); __merge_bio_list(&bios, &tc->retry_on_resume_list); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); error_bio_list(&bios, BLK_STS_DM_REQUEUE); requeue_deferred_cells(tc); @@ -756,7 +753,6 @@ static void inc_all_io_entry(struct pool *pool, struct bio *bio) static void issue(struct thin_c *tc, struct bio *bio) { struct pool *pool = tc->pool; - unsigned long flags; if (!bio_triggers_commit(tc, bio)) { generic_make_request(bio); @@ -777,9 +773,9 @@ static void issue(struct thin_c *tc, struct bio *bio) * Batch together any bios that trigger commits and then issue a * single commit for them in process_deferred_bios(). */ - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_list_add(&pool->deferred_flush_bios, bio); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); } static void remap_to_origin_and_issue(struct thin_c *tc, struct bio *bio) @@ -886,12 +882,15 @@ static void cell_defer_no_holder(struct thin_c *tc, struct dm_bio_prison_cell *c { struct pool *pool = tc->pool; unsigned long flags; + int has_work; spin_lock_irqsave(&tc->lock, flags); cell_release_no_holder(pool, cell, &tc->deferred_bio_list); + has_work = !bio_list_empty(&tc->deferred_bio_list); spin_unlock_irqrestore(&tc->lock, flags); - wake_worker(pool); + if (has_work) + wake_worker(pool); } static void thin_defer_bio(struct thin_c *tc, struct bio *bio); @@ -960,7 +959,6 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m) static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) { struct pool *pool = tc->pool; - unsigned long flags; /* * If the bio has the REQ_FUA flag set we must commit the metadata @@ -985,9 +983,9 @@ static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) * Batch together any bios that trigger commits and then issue a * single commit for them in process_deferred_bios(). */ - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_list_add(&pool->deferred_flush_completions, bio); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); } static void process_prepared_mapping(struct dm_thin_new_mapping *m) @@ -1226,14 +1224,13 @@ static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m) static void process_prepared(struct pool *pool, struct list_head *head, process_mapping_fn *fn) { - unsigned long flags; struct list_head maps; struct dm_thin_new_mapping *m, *tmp; INIT_LIST_HEAD(&maps); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); list_splice_init(head, &maps); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); list_for_each_entry_safe(m, tmp, &maps, list) (*fn)(m); @@ -1510,14 +1507,12 @@ static int commit(struct pool *pool) static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks) { - unsigned long flags; - if (free_blocks <= pool->low_water_blocks && !pool->low_water_triggered) { DMWARN("%s: reached low water mark for data device: sending event.", dm_device_name(pool->pool_md)); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->low_water_triggered = true; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); dm_table_event(pool->ti->table); } } @@ -1593,11 +1588,10 @@ static void retry_on_resume(struct bio *bio) { struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook)); struct thin_c *tc = h->tc; - unsigned long flags; - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_add(&tc->retry_on_resume_list, bio); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); } static blk_status_t should_error_unserviceable_bio(struct pool *pool) @@ -2170,7 +2164,6 @@ static void __sort_thin_deferred_bios(struct thin_c *tc) static void process_thin_deferred_bios(struct thin_c *tc) { struct pool *pool = tc->pool; - unsigned long flags; struct bio *bio; struct bio_list bios; struct blk_plug plug; @@ -2184,10 +2177,10 @@ static void process_thin_deferred_bios(struct thin_c *tc) bio_list_init(&bios); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); if (bio_list_empty(&tc->deferred_bio_list)) { - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); return; } @@ -2196,7 +2189,7 @@ static void process_thin_deferred_bios(struct thin_c *tc) bio_list_merge(&bios, &tc->deferred_bio_list); bio_list_init(&tc->deferred_bio_list); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); blk_start_plug(&plug); while ((bio = bio_list_pop(&bios))) { @@ -2206,10 +2199,10 @@ static void process_thin_deferred_bios(struct thin_c *tc) * prepared mappings to process. */ if (ensure_next_mapping(pool)) { - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_add(&tc->deferred_bio_list, bio); bio_list_merge(&tc->deferred_bio_list, &bios); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); break; } @@ -2264,16 +2257,15 @@ static unsigned sort_cells(struct pool *pool, struct list_head *cells) static void process_thin_deferred_cells(struct thin_c *tc) { struct pool *pool = tc->pool; - unsigned long flags; struct list_head cells; struct dm_bio_prison_cell *cell; unsigned i, j, count; INIT_LIST_HEAD(&cells); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_splice_init(&tc->deferred_cells, &cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); if (list_empty(&cells)) return; @@ -2294,9 +2286,9 @@ static void process_thin_deferred_cells(struct thin_c *tc) for (j = i; j < count; j++) list_add(&pool->cell_sort_array[j]->user_list, &cells); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_splice(&cells, &tc->deferred_cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); return; } @@ -2349,7 +2341,6 @@ static struct thin_c *get_next_thin(struct pool *pool, struct thin_c *tc) static void process_deferred_bios(struct pool *pool) { - unsigned long flags; struct bio *bio; struct bio_list bios, bio_completions; struct thin_c *tc; @@ -2368,13 +2359,13 @@ static void process_deferred_bios(struct pool *pool) bio_list_init(&bios); bio_list_init(&bio_completions); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_list_merge(&bios, &pool->deferred_flush_bios); bio_list_init(&pool->deferred_flush_bios); bio_list_merge(&bio_completions, &pool->deferred_flush_completions); bio_list_init(&pool->deferred_flush_completions); - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool))) @@ -2657,12 +2648,11 @@ static void metadata_operation_failed(struct pool *pool, const char *op, int r) */ static void thin_defer_bio(struct thin_c *tc, struct bio *bio) { - unsigned long flags; struct pool *pool = tc->pool; - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_add(&tc->deferred_bio_list, bio); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); wake_worker(pool); } @@ -2678,13 +2668,12 @@ static void thin_defer_bio_with_throttle(struct thin_c *tc, struct bio *bio) static void thin_defer_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell) { - unsigned long flags; struct pool *pool = tc->pool; throttle_lock(&pool->throttle); - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); list_add_tail(&cell->user_list, &tc->deferred_cells); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); throttle_unlock(&pool->throttle); wake_worker(pool); @@ -2810,15 +2799,14 @@ static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits) static void requeue_bios(struct pool *pool) { - unsigned long flags; struct thin_c *tc; rcu_read_lock(); list_for_each_entry_rcu(tc, &pool->active_thins, list) { - spin_lock_irqsave(&tc->lock, flags); + spin_lock_irq(&tc->lock); bio_list_merge(&tc->deferred_bio_list, &tc->retry_on_resume_list); bio_list_init(&tc->retry_on_resume_list); - spin_unlock_irqrestore(&tc->lock, flags); + spin_unlock_irq(&tc->lock); } rcu_read_unlock(); } @@ -3412,15 +3400,14 @@ static int pool_map(struct dm_target *ti, struct bio *bio) int r; struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; /* * As this is a singleton target, ti->begin is always zero. */ - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); bio_set_dev(bio, pt->data_dev->bdev); r = DM_MAPIO_REMAPPED; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); return r; } @@ -3591,7 +3578,6 @@ static void pool_resume(struct dm_target *ti) { struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; /* * Must requeue active_thins' bios and then resume @@ -3600,10 +3586,10 @@ static void pool_resume(struct dm_target *ti) requeue_bios(pool); pool_resume_active_thins(pool); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->low_water_triggered = false; pool->suspended = false; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); do_waker(&pool->waker.work); } @@ -3612,11 +3598,10 @@ static void pool_presuspend(struct dm_target *ti) { struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->suspended = true; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); pool_suspend_active_thins(pool); } @@ -3625,13 +3610,12 @@ static void pool_presuspend_undo(struct dm_target *ti) { struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - unsigned long flags; pool_resume_active_thins(pool); - spin_lock_irqsave(&pool->lock, flags); + spin_lock_irq(&pool->lock); pool->suspended = false; - spin_unlock_irqrestore(&pool->lock, flags); + spin_unlock_irq(&pool->lock); } static void pool_postsuspend(struct dm_target *ti) @@ -4110,11 +4094,10 @@ static void thin_put(struct thin_c *tc) static void thin_dtr(struct dm_target *ti) { struct thin_c *tc = ti->private; - unsigned long flags; - spin_lock_irqsave(&tc->pool->lock, flags); + spin_lock_irq(&tc->pool->lock); list_del_rcu(&tc->list); - spin_unlock_irqrestore(&tc->pool->lock, flags); + spin_unlock_irq(&tc->pool->lock); synchronize_rcu(); thin_put(tc); @@ -4150,7 +4133,6 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) struct thin_c *tc; struct dm_dev *pool_dev, *origin_dev; struct mapped_device *pool_md; - unsigned long flags; mutex_lock(&dm_thin_pool_table.mutex); @@ -4244,9 +4226,9 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) mutex_unlock(&dm_thin_pool_table.mutex); - spin_lock_irqsave(&tc->pool->lock, flags); + spin_lock_irq(&tc->pool->lock); if (tc->pool->suspended) { - spin_unlock_irqrestore(&tc->pool->lock, flags); + spin_unlock_irq(&tc->pool->lock); mutex_lock(&dm_thin_pool_table.mutex); /* reacquire for __pool_dec */ ti->error = "Unable to activate thin device while pool is suspended"; r = -EINVAL; @@ -4255,7 +4237,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) refcount_set(&tc->refcount, 1); init_completion(&tc->can_destroy); list_add_tail_rcu(&tc->list, &tc->pool->active_thins); - spin_unlock_irqrestore(&tc->pool->lock, flags); + spin_unlock_irq(&tc->pool->lock); /* * This synchronize_rcu() call is needed here otherwise we risk a * wake_worker() call finding no bios to process (because the newly diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index d06b8aa41e26..7d727a72aa13 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1218,7 +1218,8 @@ bio_copy: } } while (bio->bi_iter.bi_size); - if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) + if (unlikely(bio->bi_opf & REQ_FUA || + wc->uncommitted_blocks >= wc->autocommit_blocks)) writecache_flush(wc); else writecache_schedule_autocommit(wc); @@ -1561,7 +1562,7 @@ static void writecache_writeback(struct work_struct *work) { struct dm_writecache *wc = container_of(work, struct dm_writecache, writeback_work); struct blk_plug plug; - struct wc_entry *f, *g, *e = NULL; + struct wc_entry *f, *uninitialized_var(g), *e = NULL; struct rb_node *node, *next_node; struct list_head skipped; struct writeback_list wbl; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 595a73110e17..22b3cb0050a7 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -554,6 +554,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { dmz_release_mblock(zmd, mblk); + dmz_check_bdev(zmd->dev); return ERR_PTR(-EIO); } @@ -625,6 +626,8 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, ret = submit_bio_wait(bio); bio_put(bio); + if (ret) + dmz_check_bdev(zmd->dev); return ret; } @@ -691,6 +694,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { clear_bit(DMZ_META_ERROR, &mblk->state); + dmz_check_bdev(zmd->dev); ret = -EIO; } nr_mblks_submitted--; @@ -768,7 +772,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) /* If there are no dirty metadata blocks, just flush the device cache */ if (list_empty(&write_list)) { ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO, NULL); - goto out; + goto err; } /* @@ -778,7 +782,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_log_dirty_mblocks(zmd, &write_list); if (ret) - goto out; + goto err; /* * The log is on disk. It is now safe to update in place @@ -786,11 +790,11 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ ret = dmz_write_dirty_mblocks(zmd, &write_list, zmd->mblk_primary); if (ret) - goto out; + goto err; ret = dmz_write_sb(zmd, zmd->mblk_primary); if (ret) - goto out; + goto err; while (!list_empty(&write_list)) { mblk = list_first_entry(&write_list, struct dmz_mblock, link); @@ -805,16 +809,20 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) zmd->sb_gen++; out: - if (ret && !list_empty(&write_list)) { - spin_lock(&zmd->mblk_lock); - list_splice(&write_list, &zmd->mblk_dirty_list); - spin_unlock(&zmd->mblk_lock); - } - dmz_unlock_flush(zmd); up_write(&zmd->mblk_sem); return ret; + +err: + if (!list_empty(&write_list)) { + spin_lock(&zmd->mblk_lock); + list_splice(&write_list, &zmd->mblk_dirty_list); + spin_unlock(&zmd->mblk_lock); + } + if (!dmz_check_bdev(zmd->dev)) + ret = -EIO; + goto out; } /* @@ -1080,9 +1088,10 @@ static int dmz_load_sb(struct dmz_metadata *zmd) /* * Initialize a zone descriptor. */ -static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone, - struct blk_zone *blkz) +static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data) { + struct dmz_metadata *zmd = data; + struct dm_zone *zone = &zmd->zones[idx]; struct dmz_dev *dev = zmd->dev; /* Ignore the eventual last runt (smaller) zone */ @@ -1096,26 +1105,29 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone, atomic_set(&zone->refcount, 0); zone->chunk = DMZ_MAP_UNMAPPED; - if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) { + switch (blkz->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: set_bit(DMZ_RND, &zone->flags); zmd->nr_rnd_zones++; - } else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ || - blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) { + break; + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: set_bit(DMZ_SEQ, &zone->flags); - } else + break; + default: return -ENXIO; - - if (blkz->cond == BLK_ZONE_COND_OFFLINE) - set_bit(DMZ_OFFLINE, &zone->flags); - else if (blkz->cond == BLK_ZONE_COND_READONLY) - set_bit(DMZ_READ_ONLY, &zone->flags); + } if (dmz_is_rnd(zone)) zone->wp_block = 0; else zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start); - if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) { + if (blkz->cond == BLK_ZONE_COND_OFFLINE) + set_bit(DMZ_OFFLINE, &zone->flags); + else if (blkz->cond == BLK_ZONE_COND_READONLY) + set_bit(DMZ_READ_ONLY, &zone->flags); + else { zmd->nr_useable_zones++; if (dmz_is_rnd(zone)) { zmd->nr_rnd_zones++; @@ -1139,23 +1151,13 @@ static void dmz_drop_zones(struct dmz_metadata *zmd) } /* - * The size of a zone report in number of zones. - * This results in 4096*64B=256KB report zones commands. - */ -#define DMZ_REPORT_NR_ZONES 4096 - -/* * Allocate and initialize zone descriptors using the zone * information from disk. */ static int dmz_init_zones(struct dmz_metadata *zmd) { struct dmz_dev *dev = zmd->dev; - struct dm_zone *zone; - struct blk_zone *blkz; - unsigned int nr_blkz; - sector_t sector = 0; - int i, ret = 0; + int ret; /* Init */ zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3; @@ -1169,54 +1171,38 @@ static int dmz_init_zones(struct dmz_metadata *zmd) dmz_dev_info(dev, "Using %zu B for zone information", sizeof(struct dm_zone) * dev->nr_zones); - /* Get zone information */ - nr_blkz = DMZ_REPORT_NR_ZONES; - blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL); - if (!blkz) { - ret = -ENOMEM; - goto out; - } - /* - * Get zone information and initialize zone descriptors. - * At the same time, determine where the super block - * should be: first block of the first randomly writable - * zone. + * Get zone information and initialize zone descriptors. At the same + * time, determine where the super block should be: first block of the + * first randomly writable zone. */ - zone = zmd->zones; - while (sector < dev->capacity) { - /* Get zone information */ - nr_blkz = DMZ_REPORT_NR_ZONES; - ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz); - if (ret) { - dmz_dev_err(dev, "Report zones failed %d", ret); - goto out; - } + ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone, + zmd); + if (ret < 0) { + dmz_drop_zones(zmd); + return ret; + } - if (!nr_blkz) - break; + return 0; +} - /* Process report */ - for (i = 0; i < nr_blkz; i++) { - ret = dmz_init_zone(zmd, zone, &blkz[i]); - if (ret) - goto out; - sector += dev->zone_nr_sectors; - zone++; - } - } +static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx, + void *data) +{ + struct dm_zone *zone = data; - /* The entire zone configuration of the disk should now be known */ - if (sector < dev->capacity) { - dmz_dev_err(dev, "Failed to get correct zone information"); - ret = -ENXIO; - } -out: - kfree(blkz); - if (ret) - dmz_drop_zones(zmd); + clear_bit(DMZ_OFFLINE, &zone->flags); + clear_bit(DMZ_READ_ONLY, &zone->flags); + if (blkz->cond == BLK_ZONE_COND_OFFLINE) + set_bit(DMZ_OFFLINE, &zone->flags); + else if (blkz->cond == BLK_ZONE_COND_READONLY) + set_bit(DMZ_READ_ONLY, &zone->flags); - return ret; + if (dmz_is_seq(zone)) + zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start); + else + zone->wp_block = 0; + return 0; } /* @@ -1224,9 +1210,7 @@ out: */ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) { - unsigned int nr_blkz = 1; unsigned int noio_flag; - struct blk_zone blkz; int ret; /* @@ -1236,29 +1220,19 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) * GFP_NOIO was specified. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), - &blkz, &nr_blkz); + ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1, + dmz_update_zone_cb, zone); memalloc_noio_restore(noio_flag); - if (!nr_blkz) + + if (ret == 0) ret = -EIO; - if (ret) { + if (ret < 0) { dmz_dev_err(zmd->dev, "Get zone %u report failed", dmz_id(zmd, zone)); + dmz_check_bdev(zmd->dev); return ret; } - clear_bit(DMZ_OFFLINE, &zone->flags); - clear_bit(DMZ_READ_ONLY, &zone->flags); - if (blkz.cond == BLK_ZONE_COND_OFFLINE) - set_bit(DMZ_OFFLINE, &zone->flags); - else if (blkz.cond == BLK_ZONE_COND_READONLY) - set_bit(DMZ_READ_ONLY, &zone->flags); - - if (dmz_is_seq(zone)) - zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start); - else - zone->wp_block = 0; - return 0; } @@ -1312,9 +1286,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone) if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) { struct dmz_dev *dev = zmd->dev; - ret = blkdev_reset_zones(dev->bdev, - dmz_start_sect(zmd, zone), - dev->zone_nr_sectors, GFP_NOIO); + ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET, + dmz_start_sect(zmd, zone), + dev->zone_nr_sectors, GFP_NOIO); if (ret) { dmz_dev_err(dev, "Reset zone %u failed %d", dmz_id(zmd, zone), ret); diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index d240d7ca8a8a..e7ace908a9b7 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -82,6 +82,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", dmz_id(zmd, zone), (unsigned long long)wp_block, (unsigned long long)block, nr_blocks, ret); + dmz_check_bdev(zrc->dev); return ret; } @@ -489,12 +490,7 @@ static void dmz_reclaim_work(struct work_struct *work) ret = dmz_do_reclaim(zrc); if (ret) { dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret); - if (ret == -EIO) - /* - * LLD might be performing some error handling sequence - * at the underlying device. To not interfere, do not - * attempt to schedule the next reclaim run immediately. - */ + if (!dmz_check_bdev(zrc->dev)) return; } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index d3bcc4197f5d..4574e0dedbd6 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -80,6 +80,8 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) bio->bi_status = status; + if (bio->bi_status != BLK_STS_OK) + bioctx->target->dev->flags |= DMZ_CHECK_BDEV; if (refcount_dec_and_test(&bioctx->ref)) { struct dm_zone *zone = bioctx->zone; @@ -565,32 +567,52 @@ out: } /* - * Check the backing device availability. If it's on the way out, + * Check if the backing device is being removed. If it's on the way out, * start failing I/O. Reclaim and metadata components also call this * function to cleanly abort operation in the event of such failure. */ bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev) { - struct gendisk *disk; + if (dmz_dev->flags & DMZ_BDEV_DYING) + return true; - if (!(dmz_dev->flags & DMZ_BDEV_DYING)) { - disk = dmz_dev->bdev->bd_disk; - if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { - dmz_dev_warn(dmz_dev, "Backing device queue dying"); - dmz_dev->flags |= DMZ_BDEV_DYING; - } else if (disk->fops->check_events) { - if (disk->fops->check_events(disk, 0) & - DISK_EVENT_MEDIA_CHANGE) { - dmz_dev_warn(dmz_dev, "Backing device offline"); - dmz_dev->flags |= DMZ_BDEV_DYING; - } - } + if (dmz_dev->flags & DMZ_CHECK_BDEV) + return !dmz_check_bdev(dmz_dev); + + if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) { + dmz_dev_warn(dmz_dev, "Backing device queue dying"); + dmz_dev->flags |= DMZ_BDEV_DYING; } return dmz_dev->flags & DMZ_BDEV_DYING; } /* + * Check the backing device availability. This detects such events as + * backing device going offline due to errors, media removals, etc. + * This check is less efficient than dmz_bdev_is_dying() and should + * only be performed as a part of error handling. + */ +bool dmz_check_bdev(struct dmz_dev *dmz_dev) +{ + struct gendisk *disk; + + dmz_dev->flags &= ~DMZ_CHECK_BDEV; + + if (dmz_bdev_is_dying(dmz_dev)) + return false; + + disk = dmz_dev->bdev->bd_disk; + if (disk->fops->check_events && + disk->fops->check_events(disk, 0) & DISK_EVENT_MEDIA_CHANGE) { + dmz_dev_warn(dmz_dev, "Backing device offline"); + dmz_dev->flags |= DMZ_BDEV_DYING; + } + + return !(dmz_dev->flags & DMZ_BDEV_DYING); +} + +/* * Process a new BIO. */ static int dmz_map(struct dm_target *ti, struct bio *bio) @@ -902,8 +924,8 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) { struct dmz_target *dmz = ti->private; - if (dmz_bdev_is_dying(dmz->dev)) - return -ENODEV; + if (!dmz_check_bdev(dmz->dev)) + return -EIO; *bdev = dmz->dev->bdev; diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h index d8e70b0ade35..5b5e493d479c 100644 --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -72,6 +72,7 @@ struct dmz_dev { /* Device flags. */ #define DMZ_BDEV_DYING (1 << 0) +#define DMZ_CHECK_BDEV (2 << 0) /* * Zone descriptor. @@ -255,5 +256,6 @@ void dmz_schedule_reclaim(struct dmz_reclaim *zrc); * Functions defined in dm-zoned-target.c */ bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev); +bool dmz_check_bdev(struct dmz_dev *dmz_dev); #endif /* DM_ZONED_H */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1a5e328c443a..e8f9661a10a1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -440,14 +440,48 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } +#ifdef CONFIG_BLK_DEV_ZONED +int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data) +{ + struct dm_report_zones_args *args = data; + sector_t sector_diff = args->tgt->begin - args->start; + + /* + * Ignore zones beyond the target range. + */ + if (zone->start >= args->start + args->tgt->len) + return 0; + + /* + * Remap the start sector and write pointer position of the zone + * to match its position in the target range. + */ + zone->start += sector_diff; + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { + if (zone->cond == BLK_ZONE_COND_FULL) + zone->wp = zone->start + zone->len; + else if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->wp = zone->start; + else + zone->wp += sector_diff; + } + + args->next_sector = zone->start + zone->len; + return args->orig_cb(zone, args->zone_idx++, args->orig_data); +} +EXPORT_SYMBOL_GPL(dm_report_zones_cb); + static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { -#ifdef CONFIG_BLK_DEV_ZONED struct mapped_device *md = disk->private_data; - struct dm_target *tgt; struct dm_table *map; int srcu_idx, ret; + struct dm_report_zones_args args = { + .next_sector = sector, + .orig_data = data, + .orig_cb = cb, + }; if (dm_suspended_md(md)) return -EAGAIN; @@ -456,38 +490,30 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, if (!map) return -EIO; - tgt = dm_table_find_target(map, sector); - if (!tgt) { - ret = -EIO; - goto out; - } + do { + struct dm_target *tgt; - /* - * If we are executing this, we already know that the block device - * is a zoned device and so each target should have support for that - * type of drive. A missing report_zones method means that the target - * driver has a problem. - */ - if (WARN_ON(!tgt->type->report_zones)) { - ret = -EIO; - goto out; - } + tgt = dm_table_find_target(map, args.next_sector); + if (WARN_ON_ONCE(!tgt->type->report_zones)) { + ret = -EIO; + goto out; + } - /* - * blkdev_report_zones() will loop and call this again to cover all the - * zones of the target, eventually moving on to the next target. - * So there is no need to loop here trying to fill the entire array - * of zones. - */ - ret = tgt->type->report_zones(tgt, sector, zones, nr_zones); + args.tgt = tgt; + ret = tgt->type->report_zones(tgt, &args, nr_zones); + if (ret < 0) + goto out; + } while (args.zone_idx < nr_zones && + args.next_sector < get_capacity(disk)); + ret = args.zone_idx; out: dm_put_live_table(md, srcu_idx); return ret; -#else - return -ENOTSUPP; -#endif } +#else +#define dm_blk_report_zones NULL +#endif /* CONFIG_BLK_DEV_ZONED */ static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) @@ -1174,7 +1200,8 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, /* * A target may call dm_accept_partial_bio only from the map routine. It is - * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET. + * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET, + * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH. * * dm_accept_partial_bio informs the dm that the target only wants to process * additional n_sectors sectors of the bio and the rest of the data should be @@ -1212,54 +1239,6 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) } EXPORT_SYMBOL_GPL(dm_accept_partial_bio); -/* - * The zone descriptors obtained with a zone report indicate - * zone positions within the underlying device of the target. The zone - * descriptors must be remapped to match their position within the dm device. - * The caller target should obtain the zones information using - * blkdev_report_zones() to ensure that remapping for partition offset is - * already handled. - */ -void dm_remap_zone_report(struct dm_target *ti, sector_t start, - struct blk_zone *zones, unsigned int *nr_zones) -{ -#ifdef CONFIG_BLK_DEV_ZONED - struct blk_zone *zone; - unsigned int nrz = *nr_zones; - int i; - - /* - * Remap the start sector and write pointer position of the zones in - * the array. Since we may have obtained from the target underlying - * device more zones that the target size, also adjust the number - * of zones. - */ - for (i = 0; i < nrz; i++) { - zone = zones + i; - if (zone->start >= start + ti->len) { - memset(zone, 0, sizeof(struct blk_zone) * (nrz - i)); - break; - } - - zone->start = zone->start + ti->begin - start; - if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) - continue; - - if (zone->cond == BLK_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; - else if (zone->cond == BLK_ZONE_COND_EMPTY) - zone->wp = zone->start; - else - zone->wp = zone->wp + ti->begin - start; - } - - *nr_zones = i; -#else /* !CONFIG_BLK_DEV_ZONED */ - *nr_zones = 0; -#endif -} -EXPORT_SYMBOL_GPL(dm_remap_zone_report); - static blk_qc_t __map_bio(struct dm_target_io *tio) { int r; @@ -1627,7 +1606,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, ci.sector_count = 0; error = __send_empty_flush(&ci); /* dec_pending submits any data associated with flush */ - } else if (bio_op(bio) == REQ_OP_ZONE_RESET) { + } else if (op_is_zone_mgmt(bio_op(bio))) { ci.bio = bio; ci.sector_count = 0; error = __split_and_process_non_flush(&ci); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index b092c7b5282f..3ad18246fcb3 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, memcpy(page_address(store.sb_page), page_address(bitmap->storage.sb_page), sizeof(bitmap_super_t)); + spin_lock_irq(&bitmap->counts.lock); md_bitmap_file_unmap(&bitmap->storage); bitmap->storage = store; @@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, blocks = min(old_counts.chunks << old_counts.chunkshift, chunks << chunkshift); - spin_lock_irq(&bitmap->counts.lock); /* For cluster raid, need to pre-allocate bitmap */ if (mddev_is_clustered(bitmap->mddev)) { unsigned long page; diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index c766c559d36d..26c75c0199fa 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio) sector_t start_sector, end_sector, data_offset; sector_t bio_sector = bio->bi_iter.bi_sector; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } tmp_dev = which_dev(mddev, bio_sector); start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 6780938d2991..152f9e65a226 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } mp_bh = mempool_alloc(&conf->pool, GFP_NOIO); diff --git a/drivers/md/md.c b/drivers/md/md.c index 1be7abeb24fd..805b33e27496 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws) } } -void md_flush_request(struct mddev *mddev, struct bio *bio) +/* + * Manages consolidation of flushes and submitting any flushes needed for + * a bio with REQ_PREFLUSH. Returns true if the bio is finished or is + * being finished in another context. Returns false if the flushing is + * complete but still needs the I/O portion of the bio to be processed. + */ +bool md_flush_request(struct mddev *mddev, struct bio *bio) { ktime_t start = ktime_get_boottime(); spin_lock_irq(&mddev->lock); @@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + return false; } } + return true; } EXPORT_SYMBOL(md_flush_request); @@ -1098,6 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; mdp_super_t *sb; int ret; + bool spare_disk = true; /* * Calculate the position of the superblock (512byte sectors), @@ -1148,8 +1156,18 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor else rdev->desc_nr = sb->this_disk.number; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == LEVEL_MULTIPATH || + (rdev->desc_nr >= 0 && + sb->disks[rdev->desc_nr].state & + ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))) + spare_disk = false; + if (!refdev) { - ret = 1; + if (!spare_disk) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; mdp_super_t *refsb = page_address(refdev->sb_page); @@ -1165,7 +1183,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor } ev1 = md_event(sb); ev2 = md_event(refsb); - if (ev1 > ev2) + + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -1525,6 +1544,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sector_t sectors; char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; int bmask; + bool spare_disk = true; /* * Calculate the position of the superblock in 512byte sectors. @@ -1658,8 +1678,19 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ sb->level != 0) return -EINVAL; + /* not spare disk, or LEVEL_MULTIPATH */ + if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) || + (rdev->desc_nr >= 0 && + rdev->desc_nr < le32_to_cpu(sb->max_dev) && + (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || + le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))) + spare_disk = false; + if (!refdev) { - ret = 1; + if (!spare_disk) + ret = 1; + else + ret = 0; } else { __u64 ev1, ev2; struct mdp_superblock_1 *refsb = page_address(refdev->sb_page); @@ -1676,7 +1707,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ ev1 = le64_to_cpu(sb->events); ev2 = le64_to_cpu(refsb->events); - if (ev1 > ev2) + if (!spare_disk && ev1 > ev2) ret = 1; else ret = 0; @@ -3597,7 +3628,7 @@ abort_free: * Check a full RAID array for plausibility */ -static void analyze_sbs(struct mddev *mddev) +static int analyze_sbs(struct mddev *mddev) { int i; struct md_rdev *rdev, *freshest, *tmp; @@ -3618,6 +3649,12 @@ static void analyze_sbs(struct mddev *mddev) md_kick_rdev_from_array(rdev); } + /* Cannot find a valid fresh disk */ + if (!freshest) { + pr_warn("md: cannot find a valid disk\n"); + return -EINVAL; + } + super_types[mddev->major_version]. validate_super(mddev, freshest); @@ -3652,6 +3689,8 @@ static void analyze_sbs(struct mddev *mddev) clear_bit(In_sync, &rdev->flags); } } + + return 0; } /* Read a fixed-point number. @@ -5570,7 +5609,9 @@ int md_run(struct mddev *mddev) if (!mddev->raid_disks) { if (!mddev->persistent) return -EINVAL; - analyze_sbs(mddev); + err = analyze_sbs(mddev); + if (err) + return -EINVAL; } if (mddev->level != LEVEL_NONE) diff --git a/drivers/md/md.h b/drivers/md/md.h index c5e3ff398b59..5f86f8adb0a4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -550,7 +550,7 @@ struct md_personality int level; struct list_head list; struct module *owner; - bool (*make_request)(struct mddev *mddev, struct bio *bio); + bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio); /* * start up works that do NOT require md_thread. tasks that * requires md_thread should go into start() @@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); extern int mddev_congested(struct mddev *mddev, int bits); -extern void md_flush_request(struct mddev *mddev, struct bio *bio); +extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); extern int md_super_wait(struct mddev *mddev); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 1e772287b1c8..b7c20979bd19 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) unsigned chunk_sects; unsigned sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) { raid0_handle_discard(mddev, bio); @@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) tmp_dev = map_sector(mddev, zone, sector, §or); break; default: - WARN("md/raid0:%s: Invalid layout\n", mdname(mddev)); + WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev)); bio_io_error(bio); return true; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0466ee2453b4..a409ab6f30bc 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -819,6 +819,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio) else generic_make_request(bio); bio = next; + cond_resched(); } } @@ -1567,10 +1568,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio) { sector_t sectors; - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } /* * There is a limit to the maximum size, but diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 299c7b1c9718..ec136e44aef7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -191,7 +191,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) out_free_pages: while (--j >= 0) - resync_free_pages(&rps[j * 2]); + resync_free_pages(&rps[j]); j = 0; out_free_bio: @@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) int chunk_sects = chunk_mask + 1; int sectors = bio_sectors(bio); - if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { - md_flush_request(mddev, bio); + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) return true; - } if (!md_write_start(mddev, bio)) return false; diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 18a4064a61a8..cab5b1352892 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1404,7 +1404,7 @@ int ppl_init_log(struct r5conf *conf) atomic64_set(&ppl_conf->seq, 0); INIT_LIST_HEAD(&ppl_conf->no_mem_stripes); spin_lock_init(&ppl_conf->no_mem_stripes_lock); - ppl_conf->write_hint = RWF_WRITE_LIFE_NOT_SET; + ppl_conf->write_hint = RWH_WRITE_LIFE_NOT_SET; if (!mddev->external) { ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid)); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 223e97ab27e6..f0fc538bfe59 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1134,7 +1134,7 @@ again: bi->bi_iter.bi_size = STRIPE_SIZE; bi->bi_write_hint = sh->dev[i].write_hint; if (!rrdev) - sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET; + sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -1187,7 +1187,7 @@ again: rbi->bi_io_vec[0].bv_offset = 0; rbi->bi_iter.bi_size = STRIPE_SIZE; rbi->bi_write_hint = sh->dev[i].write_hint; - sh->dev[i].write_hint = RWF_WRITE_LIFE_NOT_SET; + sh->dev[i].write_hint = RWH_WRITE_LIFE_NOT_SET; /* * If this is discard request, set bi_vcnt 0. We don't * want to confuse SCSI because SCSI will replace payload @@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (ret == 0) return true; if (ret == -ENODEV) { - md_flush_request(mddev, bi); - return true; + if (md_flush_request(mddev, bi)) + return true; } /* ret == -EAGAIN, fallback */ /* diff --git a/drivers/mfd/mt6397-core.c b/drivers/mfd/mt6397-core.c index 310dae26ddff..b2c325ead1c8 100644 --- a/drivers/mfd/mt6397-core.c +++ b/drivers/mfd/mt6397-core.c @@ -129,11 +129,27 @@ static int mt6397_irq_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(mt6397_pm_ops, mt6397_irq_suspend, mt6397_irq_resume); +struct chip_data { + u32 cid_addr; + u32 cid_shift; +}; + +static const struct chip_data mt6323_core = { + .cid_addr = MT6323_CID, + .cid_shift = 0, +}; + +static const struct chip_data mt6397_core = { + .cid_addr = MT6397_CID, + .cid_shift = 0, +}; + static int mt6397_probe(struct platform_device *pdev) { int ret; unsigned int id; struct mt6397_chip *pmic; + const struct chip_data *pmic_core; pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL); if (!pmic) @@ -149,28 +165,30 @@ static int mt6397_probe(struct platform_device *pdev) if (!pmic->regmap) return -ENODEV; - platform_set_drvdata(pdev, pmic); + pmic_core = of_device_get_match_data(&pdev->dev); + if (!pmic_core) + return -ENODEV; - ret = regmap_read(pmic->regmap, MT6397_CID, &id); + ret = regmap_read(pmic->regmap, pmic_core->cid_addr, &id); if (ret) { - dev_err(pmic->dev, "Failed to read chip id: %d\n", ret); + dev_err(&pdev->dev, "Failed to read chip id: %d\n", ret); return ret; } + pmic->chip_id = (id >> pmic_core->cid_shift) & 0xff; + + platform_set_drvdata(pdev, pmic); + pmic->irq = platform_get_irq(pdev, 0); if (pmic->irq <= 0) return pmic->irq; - switch (id & 0xff) { - case MT6323_CHIP_ID: - pmic->int_con[0] = MT6323_INT_CON0; - pmic->int_con[1] = MT6323_INT_CON1; - pmic->int_status[0] = MT6323_INT_STATUS0; - pmic->int_status[1] = MT6323_INT_STATUS1; - ret = mt6397_irq_init(pmic); - if (ret) - return ret; + ret = mt6397_irq_init(pmic); + if (ret) + return ret; + switch (pmic->chip_id) { + case MT6323_CHIP_ID: ret = devm_mfd_add_devices(&pdev->dev, -1, mt6323_devs, ARRAY_SIZE(mt6323_devs), NULL, 0, pmic->irq_domain); @@ -178,21 +196,13 @@ static int mt6397_probe(struct platform_device *pdev) case MT6391_CHIP_ID: case MT6397_CHIP_ID: - pmic->int_con[0] = MT6397_INT_CON0; - pmic->int_con[1] = MT6397_INT_CON1; - pmic->int_status[0] = MT6397_INT_STATUS0; - pmic->int_status[1] = MT6397_INT_STATUS1; - ret = mt6397_irq_init(pmic); - if (ret) - return ret; - ret = devm_mfd_add_devices(&pdev->dev, -1, mt6397_devs, ARRAY_SIZE(mt6397_devs), NULL, 0, pmic->irq_domain); break; default: - dev_err(&pdev->dev, "unsupported chip: %d\n", id); + dev_err(&pdev->dev, "unsupported chip: %d\n", pmic->chip_id); return -ENODEV; } @@ -205,9 +215,15 @@ static int mt6397_probe(struct platform_device *pdev) } static const struct of_device_id mt6397_of_match[] = { - { .compatible = "mediatek,mt6397" }, - { .compatible = "mediatek,mt6323" }, - { } + { + .compatible = "mediatek,mt6323", + .data = &mt6323_core, + }, { + .compatible = "mediatek,mt6397", + .data = &mt6397_core, + }, { + /* sentinel */ + } }; MODULE_DEVICE_TABLE(of, mt6397_of_match); diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c index f7bdae5354c3..5047f7343ffc 100644 --- a/drivers/mmc/host/cqhci.c +++ b/drivers/mmc/host/cqhci.c @@ -611,7 +611,8 @@ static int cqhci_request(struct mmc_host *mmc, struct mmc_request *mrq) cq_host->slot[tag].flags = 0; cq_host->qcnt += 1; - + /* Make sure descriptors are ready before ringing the doorbell */ + wmb(); cqhci_writel(cq_host, 1 << tag, CQHCI_TDBR); if (!(cqhci_readl(cq_host, CQHCI_TDBR) & (1 << tag))) pr_debug("%s: cqhci: doorbell not set for tag %d\n", diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c index 78e7e350655c..4031217d21c3 100644 --- a/drivers/mmc/host/mxs-mmc.c +++ b/drivers/mmc/host/mxs-mmc.c @@ -17,6 +17,7 @@ #include <linux/interrupt.h> #include <linux/dma-mapping.h> #include <linux/dmaengine.h> +#include <linux/dma/mxs-dma.h> #include <linux/highmem.h> #include <linux/clk.h> #include <linux/err.h> @@ -266,7 +267,7 @@ static void mxs_mmc_bc(struct mxs_mmc_host *host) ssp->ssp_pio_words[2] = cmd1; ssp->dma_dir = DMA_NONE; ssp->slave_dirn = DMA_TRANS_NONE; - desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK); + desc = mxs_mmc_prep_dma(host, MXS_DMA_CTRL_WAIT4END); if (!desc) goto out; @@ -311,7 +312,7 @@ static void mxs_mmc_ac(struct mxs_mmc_host *host) ssp->ssp_pio_words[2] = cmd1; ssp->dma_dir = DMA_NONE; ssp->slave_dirn = DMA_TRANS_NONE; - desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK); + desc = mxs_mmc_prep_dma(host, MXS_DMA_CTRL_WAIT4END); if (!desc) goto out; @@ -441,7 +442,7 @@ static void mxs_mmc_adtc(struct mxs_mmc_host *host) host->data = data; ssp->dma_dir = dma_data_dir; ssp->slave_dirn = slave_dirn; - desc = mxs_mmc_prep_dma(host, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); + desc = mxs_mmc_prep_dma(host, DMA_PREP_INTERRUPT | MXS_DMA_CTRL_WAIT4END); if (!desc) goto out; diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c index e7d1920729fb..0ae986c42bc8 100644 --- a/drivers/mmc/host/sdhci-of-at91.c +++ b/drivers/mmc/host/sdhci-of-at91.c @@ -358,7 +358,7 @@ static int sdhci_at91_probe(struct platform_device *pdev) pm_runtime_use_autosuspend(&pdev->dev); /* HS200 is broken at this moment */ - host->quirks2 = SDHCI_QUIRK2_BROKEN_HS200; + host->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200; ret = sdhci_add_host(host); if (ret) diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 41c2677c587f..083e7e053c95 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -372,7 +372,7 @@ static int sdhci_omap_execute_tuning(struct mmc_host *mmc, u32 opcode) * on temperature */ if (temperature < -20000) - phase_delay = min(max_window + 4 * max_len - 24, + phase_delay = min(max_window + 4 * (max_len - 1) - 24, max_window + DIV_ROUND_UP(13 * max_len, 16) * 4); else if (temperature < 20000) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 8c79bad2a9a5..4f2e6910c623 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -952,7 +952,7 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data) struct bond_vlan_tag *tags; if (is_vlan_dev(upper) && - bond->nest_level == vlan_get_encap_level(upper) - 1) { + bond->dev->lower_level == upper->lower_level - 1) { if (upper->addr_assign_type == NET_ADDR_STOLEN) { alb_send_lp_vid(slave, mac_addr, vlan_dev_vlan_proto(upper), diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 21d8fcc83c9c..62f65573eb04 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1733,8 +1733,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_upper_unlink; } - bond->nest_level = dev_get_nest_level(bond_dev) + 1; - /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ @@ -1816,7 +1814,8 @@ err_detach: slave_disable_netpoll(new_slave); err_close: - slave_dev->priv_flags &= ~IFF_BONDING; + if (!netif_is_bond_master(slave_dev)) + slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_restore_mac: @@ -1956,9 +1955,6 @@ static int __bond_release_one(struct net_device *bond_dev, if (!bond_has_slaves(bond)) { bond_set_carrier(bond); eth_hw_addr_random(bond_dev); - bond->nest_level = SINGLE_DEPTH_NESTING; - } else { - bond->nest_level = dev_get_nest_level(bond_dev) + 1; } unblock_netpoll_tx(); @@ -2017,7 +2013,8 @@ static int __bond_release_one(struct net_device *bond_dev, else dev_set_mtu(slave_dev, slave->original_mtu); - slave_dev->priv_flags &= ~IFF_BONDING; + if (!netif_is_bond_master(slave_dev)) + slave_dev->priv_flags &= ~IFF_BONDING; bond_free_slave(slave); @@ -2086,8 +2083,7 @@ static int bond_miimon_inspect(struct bonding *bond) ignore_updelay = !rcu_dereference(bond->curr_active_slave); bond_for_each_slave_rcu(bond, slave, iter) { - slave->new_link = BOND_LINK_NOCHANGE; - slave->link_new_state = slave->link; + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); link_state = bond_check_dev_link(bond, slave->dev, 0); @@ -2121,7 +2117,7 @@ static int bond_miimon_inspect(struct bonding *bond) } if (slave->delay <= 0) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; continue; } @@ -2158,7 +2154,7 @@ static int bond_miimon_inspect(struct bonding *bond) slave->delay = 0; if (slave->delay <= 0) { - slave->new_link = BOND_LINK_UP; + bond_propose_link_state(slave, BOND_LINK_UP); commit++; ignore_updelay = false; continue; @@ -2196,7 +2192,7 @@ static void bond_miimon_commit(struct bonding *bond) struct slave *slave, *primary; bond_for_each_slave(bond, slave, iter) { - switch (slave->new_link) { + switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: /* For 802.3ad mode, check current slave speed and * duplex again in case its port was disabled after @@ -2268,8 +2264,8 @@ static void bond_miimon_commit(struct bonding *bond) default: slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", - slave->new_link); - slave->new_link = BOND_LINK_NOCHANGE; + slave->link_new_state); + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); continue; } @@ -2677,13 +2673,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) bond_for_each_slave_rcu(bond, slave, iter) { unsigned long trans_start = dev_trans_start(slave->dev); - slave->new_link = BOND_LINK_NOCHANGE; + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, trans_start, 1) && bond_time_in_interval(bond, slave->last_rx, 1)) { - slave->new_link = BOND_LINK_UP; + bond_propose_link_state(slave, BOND_LINK_UP); slave_state_changed = 1; /* primary_slave has no meaning in round-robin @@ -2708,7 +2704,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) if (!bond_time_in_interval(bond, trans_start, 2) || !bond_time_in_interval(bond, slave->last_rx, 2)) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; if (slave->link_failure_count < UINT_MAX) @@ -2739,8 +2735,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) goto re_arm; bond_for_each_slave(bond, slave, iter) { - if (slave->new_link != BOND_LINK_NOCHANGE) - slave->link = slave->new_link; + if (slave->link_new_state != BOND_LINK_NOCHANGE) + slave->link = slave->link_new_state; } if (slave_state_changed) { @@ -2763,9 +2759,9 @@ re_arm: } /* Called to inspect slaves for active-backup mode ARP monitor link state - * changes. Sets new_link in slaves to specify what action should take - * place for the slave. Returns 0 if no changes are found, >0 if changes - * to link states must be committed. + * changes. Sets proposed link state in slaves to specify what action + * should take place for the slave. Returns 0 if no changes are found, >0 + * if changes to link states must be committed. * * Called with rcu_read_lock held. */ @@ -2777,12 +2773,12 @@ static int bond_ab_arp_inspect(struct bonding *bond) int commit = 0; bond_for_each_slave_rcu(bond, slave, iter) { - slave->new_link = BOND_LINK_NOCHANGE; + bond_propose_link_state(slave, BOND_LINK_NOCHANGE); last_rx = slave_last_rx(bond, slave); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_rx, 1)) { - slave->new_link = BOND_LINK_UP; + bond_propose_link_state(slave, BOND_LINK_UP); commit++; } continue; @@ -2810,7 +2806,7 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (!bond_is_active_slave(slave) && !rcu_access_pointer(bond->current_arp_slave) && !bond_time_in_interval(bond, last_rx, 3)) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } @@ -2823,7 +2819,7 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (bond_is_active_slave(slave) && (!bond_time_in_interval(bond, trans_start, 2) || !bond_time_in_interval(bond, last_rx, 2))) { - slave->new_link = BOND_LINK_DOWN; + bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } } @@ -2843,7 +2839,7 @@ static void bond_ab_arp_commit(struct bonding *bond) struct slave *slave; bond_for_each_slave(bond, slave, iter) { - switch (slave->new_link) { + switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: continue; @@ -2893,8 +2889,9 @@ static void bond_ab_arp_commit(struct bonding *bond) continue; default: - slave_err(bond->dev, slave->dev, "impossible: new_link %d on slave\n", - slave->new_link); + slave_err(bond->dev, slave->dev, + "impossible: link_new_state %d on slave\n", + slave->link_new_state); continue; } @@ -3442,13 +3439,6 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } -static int bond_get_nest_level(struct net_device *bond_dev) -{ - struct bonding *bond = netdev_priv(bond_dev); - - return bond->nest_level; -} - static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3457,7 +3447,7 @@ static void bond_get_stats(struct net_device *bond_dev, struct list_head *iter; struct slave *slave; - spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev)); + spin_lock(&bond->stats_lock); memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); @@ -4268,7 +4258,6 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, - .ndo_get_lock_subclass = bond_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, @@ -4296,7 +4285,6 @@ void bond_setup(struct net_device *bond_dev) struct bonding *bond = netdev_priv(bond_dev); spin_lock_init(&bond->mode_lock); - spin_lock_init(&bond->stats_lock); bond->params = bonding_defaults; /* Initialize pointers */ @@ -4365,6 +4353,7 @@ static void bond_uninit(struct net_device *bond_dev) list_del(&bond->bond_list); + lockdep_unregister_key(&bond->stats_lock_key); bond_debug_unregister(bond); } @@ -4768,8 +4757,9 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; - bond->nest_level = SINGLE_DEPTH_NESTING; - netdev_lockdep_set_classes(bond_dev); + spin_lock_init(&bond->stats_lock); + lockdep_register_key(&bond->stats_lock_key); + lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key); list_add_tail(&bond->bond_list, &bn->dev_list); diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 606b7d8ffe13..8e9f5620c9a2 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -52,6 +52,7 @@ #define CONTROL_EX_PDR BIT(8) /* control register */ +#define CONTROL_SWR BIT(15) #define CONTROL_TEST BIT(7) #define CONTROL_CCE BIT(6) #define CONTROL_DISABLE_AR BIT(5) @@ -97,6 +98,9 @@ #define BTR_TSEG2_SHIFT 12 #define BTR_TSEG2_MASK (0x7 << BTR_TSEG2_SHIFT) +/* interrupt register */ +#define INT_STS_PENDING 0x8000 + /* brp extension register */ #define BRP_EXT_BRPE_MASK 0x0f #define BRP_EXT_BRPE_SHIFT 0 @@ -569,6 +573,26 @@ static void c_can_configure_msg_objects(struct net_device *dev) IF_MCONT_RCV_EOB); } +static int c_can_software_reset(struct net_device *dev) +{ + struct c_can_priv *priv = netdev_priv(dev); + int retry = 0; + + if (priv->type != BOSCH_D_CAN) + return 0; + + priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_SWR | CONTROL_INIT); + while (priv->read_reg(priv, C_CAN_CTRL_REG) & CONTROL_SWR) { + msleep(20); + if (retry++ > 100) { + netdev_err(dev, "CCTRL: software reset failed\n"); + return -EIO; + } + } + + return 0; +} + /* * Configure C_CAN chip: * - enable/disable auto-retransmission @@ -578,6 +602,11 @@ static void c_can_configure_msg_objects(struct net_device *dev) static int c_can_chip_config(struct net_device *dev) { struct c_can_priv *priv = netdev_priv(dev); + int err; + + err = c_can_software_reset(dev); + if (err) + return err; /* enable automatic retransmission */ priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_ENABLE_AR); @@ -886,6 +915,9 @@ static int c_can_handle_state_change(struct net_device *dev, struct can_berr_counter bec; switch (error_type) { + case C_CAN_NO_ERROR: + priv->can.state = CAN_STATE_ERROR_ACTIVE; + break; case C_CAN_ERROR_WARNING: /* error warning state */ priv->can.can_stats.error_warning++; @@ -916,6 +948,13 @@ static int c_can_handle_state_change(struct net_device *dev, ERR_CNT_RP_SHIFT; switch (error_type) { + case C_CAN_NO_ERROR: + /* error warning state */ + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = CAN_ERR_CRTL_ACTIVE; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + break; case C_CAN_ERROR_WARNING: /* error warning state */ cf->can_id |= CAN_ERR_CRTL; @@ -1029,10 +1068,16 @@ static int c_can_poll(struct napi_struct *napi, int quota) u16 curr, last = priv->last_status; int work_done = 0; - priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG); - /* Ack status on C_CAN. D_CAN is self clearing */ - if (priv->type != BOSCH_D_CAN) - priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED); + /* Only read the status register if a status interrupt was pending */ + if (atomic_xchg(&priv->sie_pending, 0)) { + priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG); + /* Ack status on C_CAN. D_CAN is self clearing */ + if (priv->type != BOSCH_D_CAN) + priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED); + } else { + /* no change detected ... */ + curr = last; + } /* handle state changes */ if ((curr & STATUS_EWARN) && (!(last & STATUS_EWARN))) { @@ -1054,11 +1099,17 @@ static int c_can_poll(struct napi_struct *napi, int quota) /* handle bus recovery events */ if ((!(curr & STATUS_BOFF)) && (last & STATUS_BOFF)) { netdev_dbg(dev, "left bus off state\n"); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + work_done += c_can_handle_state_change(dev, C_CAN_ERROR_PASSIVE); } + if ((!(curr & STATUS_EPASS)) && (last & STATUS_EPASS)) { netdev_dbg(dev, "left error passive state\n"); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + work_done += c_can_handle_state_change(dev, C_CAN_ERROR_WARNING); + } + + if ((!(curr & STATUS_EWARN)) && (last & STATUS_EWARN)) { + netdev_dbg(dev, "left error warning state\n"); + work_done += c_can_handle_state_change(dev, C_CAN_NO_ERROR); } /* handle lec errors on the bus */ @@ -1083,10 +1134,16 @@ static irqreturn_t c_can_isr(int irq, void *dev_id) { struct net_device *dev = (struct net_device *)dev_id; struct c_can_priv *priv = netdev_priv(dev); + int reg_int; - if (!priv->read_reg(priv, C_CAN_INT_REG)) + reg_int = priv->read_reg(priv, C_CAN_INT_REG); + if (!reg_int) return IRQ_NONE; + /* save for later use */ + if (reg_int & INT_STS_PENDING) + atomic_set(&priv->sie_pending, 1); + /* disable all interrupts and schedule the NAPI */ c_can_irq_control(priv, false); napi_schedule(&priv->napi); diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h index 8acdc7fa4792..d5567a7c1c6d 100644 --- a/drivers/net/can/c_can/c_can.h +++ b/drivers/net/can/c_can/c_can.h @@ -198,6 +198,7 @@ struct c_can_priv { struct net_device *dev; struct device *device; atomic_t tx_active; + atomic_t sie_pending; unsigned long tx_dir; int last_status; u16 (*read_reg) (const struct c_can_priv *priv, enum reg index); diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index ac86be52b461..1c88c361938c 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -848,6 +848,7 @@ void of_can_transceiver(struct net_device *dev) return; ret = of_property_read_u32(dn, "max-bitrate", &priv->bitrate_max); + of_node_put(dn); if ((ret && ret != -EINVAL) || (!ret && !priv->bitrate_max)) netdev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit.\n"); } diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index dc5695dffc2e..57f9a2f51085 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -677,6 +677,7 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr) struct can_frame *cf; bool rx_errors = false, tx_errors = false; u32 timestamp; + int err; timestamp = priv->read(®s->timer) << 16; @@ -725,7 +726,9 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr) if (tx_errors) dev->stats.tx_errors++; - can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + if (err) + dev->stats.rx_fifo_errors++; } static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) @@ -738,6 +741,7 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) int flt; struct can_berr_counter bec; u32 timestamp; + int err; timestamp = priv->read(®s->timer) << 16; @@ -769,7 +773,9 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) if (unlikely(new_state == CAN_STATE_BUS_OFF)) can_bus_off(dev); - can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + if (err) + dev->stats.rx_fifo_errors++; } static inline struct flexcan_priv *rx_offload_to_priv(struct can_rx_offload *offload) @@ -1188,6 +1194,7 @@ static int flexcan_chip_start(struct net_device *dev) reg_mecr = priv->read(®s->mecr); reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS; priv->write(reg_mecr, ®s->mecr); + reg_mecr |= FLEXCAN_MECR_ECCDIS; reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK | FLEXCAN_MECR_FANCEI_MSK); priv->write(reg_mecr, ®s->mecr); diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index 6ac4c35f247a..38ea5e600fb8 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -107,7 +107,7 @@ static int m_can_plat_probe(struct platform_device *pdev) mcan_class->is_peripheral = false; - platform_set_drvdata(pdev, mcan_class->dev); + platform_set_drvdata(pdev, mcan_class->net); m_can_init_ram(mcan_class); @@ -166,8 +166,6 @@ static int __maybe_unused m_can_runtime_resume(struct device *dev) if (err) clk_disable_unprepare(mcan_class->hclk); - m_can_class_resume(dev); - return err; } diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index e6a668ee7730..84cae167e42f 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -107,37 +107,95 @@ static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b) return cb_b->timestamp - cb_a->timestamp; } -static struct sk_buff *can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n) +/** + * can_rx_offload_offload_one() - Read one CAN frame from HW + * @offload: pointer to rx_offload context + * @n: number of mailbox to read + * + * The task of this function is to read a CAN frame from mailbox @n + * from the device and return the mailbox's content as a struct + * sk_buff. + * + * If the struct can_rx_offload::skb_queue exceeds the maximal queue + * length (struct can_rx_offload::skb_queue_len_max) or no skb can be + * allocated, the mailbox contents is discarded by reading it into an + * overflow buffer. This way the mailbox is marked as free by the + * driver. + * + * Return: A pointer to skb containing the CAN frame on success. + * + * NULL if the mailbox @n is empty. + * + * ERR_PTR() in case of an error + */ +static struct sk_buff * +can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n) { - struct sk_buff *skb = NULL; + struct sk_buff *skb = NULL, *skb_error = NULL; struct can_rx_offload_cb *cb; struct can_frame *cf; int ret; - /* If queue is full or skb not available, read to discard mailbox */ - if (likely(skb_queue_len(&offload->skb_queue) <= - offload->skb_queue_len_max)) + if (likely(skb_queue_len(&offload->skb_queue) < + offload->skb_queue_len_max)) { skb = alloc_can_skb(offload->dev, &cf); + if (unlikely(!skb)) + skb_error = ERR_PTR(-ENOMEM); /* skb alloc failed */ + } else { + skb_error = ERR_PTR(-ENOBUFS); /* skb_queue is full */ + } - if (!skb) { + /* If queue is full or skb not available, drop by reading into + * overflow buffer. + */ + if (unlikely(skb_error)) { struct can_frame cf_overflow; u32 timestamp; ret = offload->mailbox_read(offload, &cf_overflow, ×tamp, n); - if (ret) - offload->dev->stats.rx_dropped++; - return NULL; + /* Mailbox was empty. */ + if (unlikely(!ret)) + return NULL; + + /* Mailbox has been read and we're dropping it or + * there was a problem reading the mailbox. + * + * Increment error counters in any case. + */ + offload->dev->stats.rx_dropped++; + offload->dev->stats.rx_fifo_errors++; + + /* There was a problem reading the mailbox, propagate + * error value. + */ + if (unlikely(ret < 0)) + return ERR_PTR(ret); + + return skb_error; } cb = can_rx_offload_get_cb(skb); ret = offload->mailbox_read(offload, cf, &cb->timestamp, n); - if (!ret) { + + /* Mailbox was empty. */ + if (unlikely(!ret)) { kfree_skb(skb); return NULL; } + /* There was a problem reading the mailbox, propagate error value. */ + if (unlikely(ret < 0)) { + kfree_skb(skb); + + offload->dev->stats.rx_dropped++; + offload->dev->stats.rx_fifo_errors++; + + return ERR_PTR(ret); + } + + /* Mailbox was read. */ return skb; } @@ -157,8 +215,8 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 pen continue; skb = can_rx_offload_offload_one(offload, i); - if (!skb) - break; + if (IS_ERR_OR_NULL(skb)) + continue; __skb_queue_add_sort(&skb_queue, skb, can_rx_offload_compare); } @@ -188,7 +246,13 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload) struct sk_buff *skb; int received = 0; - while ((skb = can_rx_offload_offload_one(offload, 0))) { + while (1) { + skb = can_rx_offload_offload_one(offload, 0); + if (IS_ERR(skb)) + continue; + if (!skb) + break; + skb_queue_tail(&offload->skb_queue, skb); received++; } @@ -207,8 +271,10 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, unsigned long flags; if (skb_queue_len(&offload->skb_queue) > - offload->skb_queue_len_max) - return -ENOMEM; + offload->skb_queue_len_max) { + kfree_skb(skb); + return -ENOBUFS; + } cb = can_rx_offload_get_cb(skb); cb->timestamp = timestamp; @@ -250,8 +316,10 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb) { if (skb_queue_len(&offload->skb_queue) > - offload->skb_queue_len_max) - return -ENOMEM; + offload->skb_queue_len_max) { + kfree_skb(skb); + return -ENOBUFS; + } skb_queue_tail(&offload->skb_queue, skb); can_rx_offload_schedule(offload); diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index bb6032211043..0a9f42e5fedf 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -617,6 +617,7 @@ err_free_chan: sl->tty = NULL; tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); + free_netdev(sl->dev); err_exit: rtnl_unlock(); diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index bee9f7b8dad6..bb20a9b75cc6 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -717,6 +717,7 @@ static void mcp251x_restart_work_handler(struct work_struct *ws) if (priv->after_suspend) { mcp251x_hw_reset(spi); mcp251x_setup(net, spi); + priv->force_quit = 0; if (priv->after_suspend & AFTER_SUSPEND_RESTART) { mcp251x_set_normal_mode(spi); } else if (priv->after_suspend & AFTER_SUSPEND_UP) { @@ -728,7 +729,6 @@ static void mcp251x_restart_work_handler(struct work_struct *ws) mcp251x_hw_sleep(spi); } priv->after_suspend = 0; - priv->force_quit = 0; } if (priv->restart_tx) { diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index f8b19eef5d26..31ad364a89bb 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -73,6 +73,7 @@ MODULE_VERSION(HECC_MODULE_VERSION); */ #define HECC_MAX_RX_MBOX (HECC_MAX_MAILBOXES - HECC_MAX_TX_MBOX) #define HECC_RX_FIRST_MBOX (HECC_MAX_MAILBOXES - 1) +#define HECC_RX_LAST_MBOX (HECC_MAX_TX_MBOX) /* TI HECC module registers */ #define HECC_CANME 0x0 /* Mailbox enable */ @@ -82,7 +83,7 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_CANTA 0x10 /* Transmission acknowledge */ #define HECC_CANAA 0x14 /* Abort acknowledge */ #define HECC_CANRMP 0x18 /* Receive message pending */ -#define HECC_CANRML 0x1C /* Remote message lost */ +#define HECC_CANRML 0x1C /* Receive message lost */ #define HECC_CANRFP 0x20 /* Remote frame pending */ #define HECC_CANGAM 0x24 /* SECC only:Global acceptance mask */ #define HECC_CANMC 0x28 /* Master control */ @@ -149,6 +150,8 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_BUS_ERROR (HECC_CANES_FE | HECC_CANES_BE |\ HECC_CANES_CRCE | HECC_CANES_SE |\ HECC_CANES_ACKE) +#define HECC_CANES_FLAGS (HECC_BUS_ERROR | HECC_CANES_BO |\ + HECC_CANES_EP | HECC_CANES_EW) #define HECC_CANMCF_RTR BIT(4) /* Remote transmit request */ @@ -382,8 +385,18 @@ static void ti_hecc_start(struct net_device *ndev) hecc_set_bit(priv, HECC_CANMIM, mbx_mask); } - /* Prevent message over-write & Enable interrupts */ - hecc_write(priv, HECC_CANOPC, HECC_SET_REG); + /* Enable tx interrupts */ + hecc_set_bit(priv, HECC_CANMIM, BIT(HECC_MAX_TX_MBOX) - 1); + + /* Prevent message over-write to create a rx fifo, but not for + * the lowest priority mailbox, since that allows detecting + * overflows instead of the hardware silently dropping the + * messages. + */ + mbx_mask = ~BIT(HECC_RX_LAST_MBOX); + hecc_write(priv, HECC_CANOPC, mbx_mask); + + /* Enable interrupts */ if (priv->use_hecc1int) { hecc_write(priv, HECC_CANMIL, HECC_SET_REG); hecc_write(priv, HECC_CANGIM, HECC_CANGIM_DEF_MASK | @@ -400,6 +413,9 @@ static void ti_hecc_stop(struct net_device *ndev) { struct ti_hecc_priv *priv = netdev_priv(ndev); + /* Disable the CPK; stop sending, erroring and acking */ + hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_CCR); + /* Disable interrupts and disable mailboxes */ hecc_write(priv, HECC_CANGIM, 0); hecc_write(priv, HECC_CANMIM, 0); @@ -508,8 +524,6 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev) hecc_set_bit(priv, HECC_CANME, mbx_mask); spin_unlock_irqrestore(&priv->mbx_lock, flags); - hecc_clear_bit(priv, HECC_CANMD, mbx_mask); - hecc_set_bit(priv, HECC_CANMIM, mbx_mask); hecc_write(priv, HECC_CANTRS, mbx_mask); return NETDEV_TX_OK; @@ -526,8 +540,10 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload, u32 *timestamp, unsigned int mbxno) { struct ti_hecc_priv *priv = rx_offload_to_priv(offload); - u32 data; + u32 data, mbx_mask; + int ret = 1; + mbx_mask = BIT(mbxno); data = hecc_read_mbx(priv, mbxno, HECC_CANMID); if (data & HECC_CANMID_IDE) cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG; @@ -548,7 +564,25 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload, *timestamp = hecc_read_stamp(priv, mbxno); - return 1; + /* Check for FIFO overrun. + * + * All but the last RX mailbox have activated overwrite + * protection. So skip check for overrun, if we're not + * handling the last RX mailbox. + * + * As the overwrite protection for the last RX mailbox is + * disabled, the CAN core might update while we're reading + * it. This means the skb might be inconsistent. + * + * Return an error to let rx-offload discard this CAN frame. + */ + if (unlikely(mbxno == HECC_RX_LAST_MBOX && + hecc_read(priv, HECC_CANRML) & mbx_mask)) + ret = -ENOBUFS; + + hecc_write(priv, HECC_CANRMP, mbx_mask); + + return ret; } static int ti_hecc_error(struct net_device *ndev, int int_status, @@ -558,92 +592,73 @@ static int ti_hecc_error(struct net_device *ndev, int int_status, struct can_frame *cf; struct sk_buff *skb; u32 timestamp; + int err; - /* propagate the error condition to the can stack */ - skb = alloc_can_err_skb(ndev, &cf); - if (!skb) { - if (printk_ratelimit()) - netdev_err(priv->ndev, - "%s: alloc_can_err_skb() failed\n", - __func__); - return -ENOMEM; - } - - if (int_status & HECC_CANGIF_WLIF) { /* warning level int */ - if ((int_status & HECC_CANGIF_BOIF) == 0) { - priv->can.state = CAN_STATE_ERROR_WARNING; - ++priv->can.can_stats.error_warning; - cf->can_id |= CAN_ERR_CRTL; - if (hecc_read(priv, HECC_CANTEC) > 96) - cf->data[1] |= CAN_ERR_CRTL_TX_WARNING; - if (hecc_read(priv, HECC_CANREC) > 96) - cf->data[1] |= CAN_ERR_CRTL_RX_WARNING; - } - hecc_set_bit(priv, HECC_CANES, HECC_CANES_EW); - netdev_dbg(priv->ndev, "Error Warning interrupt\n"); - hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR); - } - - if (int_status & HECC_CANGIF_EPIF) { /* error passive int */ - if ((int_status & HECC_CANGIF_BOIF) == 0) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - ++priv->can.can_stats.error_passive; - cf->can_id |= CAN_ERR_CRTL; - if (hecc_read(priv, HECC_CANTEC) > 127) - cf->data[1] |= CAN_ERR_CRTL_TX_PASSIVE; - if (hecc_read(priv, HECC_CANREC) > 127) - cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE; + if (err_status & HECC_BUS_ERROR) { + /* propagate the error condition to the can stack */ + skb = alloc_can_err_skb(ndev, &cf); + if (!skb) { + if (net_ratelimit()) + netdev_err(priv->ndev, + "%s: alloc_can_err_skb() failed\n", + __func__); + return -ENOMEM; } - hecc_set_bit(priv, HECC_CANES, HECC_CANES_EP); - netdev_dbg(priv->ndev, "Error passive interrupt\n"); - hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR); - } - - /* Need to check busoff condition in error status register too to - * ensure warning interrupts don't hog the system - */ - if ((int_status & HECC_CANGIF_BOIF) || (err_status & HECC_CANES_BO)) { - priv->can.state = CAN_STATE_BUS_OFF; - cf->can_id |= CAN_ERR_BUSOFF; - hecc_set_bit(priv, HECC_CANES, HECC_CANES_BO); - hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR); - /* Disable all interrupts in bus-off to avoid int hog */ - hecc_write(priv, HECC_CANGIM, 0); - ++priv->can.can_stats.bus_off; - can_bus_off(ndev); - } - if (err_status & HECC_BUS_ERROR) { ++priv->can.can_stats.bus_error; cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT; - if (err_status & HECC_CANES_FE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_FE); + if (err_status & HECC_CANES_FE) cf->data[2] |= CAN_ERR_PROT_FORM; - } - if (err_status & HECC_CANES_BE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_BE); + if (err_status & HECC_CANES_BE) cf->data[2] |= CAN_ERR_PROT_BIT; - } - if (err_status & HECC_CANES_SE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_SE); + if (err_status & HECC_CANES_SE) cf->data[2] |= CAN_ERR_PROT_STUFF; - } - if (err_status & HECC_CANES_CRCE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE); + if (err_status & HECC_CANES_CRCE) cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ; - } - if (err_status & HECC_CANES_ACKE) { - hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE); + if (err_status & HECC_CANES_ACKE) cf->data[3] = CAN_ERR_PROT_LOC_ACK; - } + + timestamp = hecc_read(priv, HECC_CANLNT); + err = can_rx_offload_queue_sorted(&priv->offload, skb, + timestamp); + if (err) + ndev->stats.rx_fifo_errors++; } - timestamp = hecc_read(priv, HECC_CANLNT); - can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + hecc_write(priv, HECC_CANES, HECC_CANES_FLAGS); return 0; } +static void ti_hecc_change_state(struct net_device *ndev, + enum can_state rx_state, + enum can_state tx_state) +{ + struct ti_hecc_priv *priv = netdev_priv(ndev); + struct can_frame *cf; + struct sk_buff *skb; + u32 timestamp; + int err; + + skb = alloc_can_err_skb(priv->ndev, &cf); + if (unlikely(!skb)) { + priv->can.state = max(tx_state, rx_state); + return; + } + + can_change_state(priv->ndev, cf, tx_state, rx_state); + + if (max(tx_state, rx_state) != CAN_STATE_BUS_OFF) { + cf->data[6] = hecc_read(priv, HECC_CANTEC); + cf->data[7] = hecc_read(priv, HECC_CANREC); + } + + timestamp = hecc_read(priv, HECC_CANLNT); + err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); + if (err) + ndev->stats.rx_fifo_errors++; +} + static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) { struct net_device *ndev = (struct net_device *)dev_id; @@ -651,6 +666,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) struct net_device_stats *stats = &ndev->stats; u32 mbxno, mbx_mask, int_status, err_status, stamp; unsigned long flags, rx_pending; + u32 handled = 0; int_status = hecc_read(priv, priv->use_hecc1int ? @@ -660,17 +676,66 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) return IRQ_NONE; err_status = hecc_read(priv, HECC_CANES); - if (err_status & (HECC_BUS_ERROR | HECC_CANES_BO | - HECC_CANES_EP | HECC_CANES_EW)) + if (unlikely(err_status & HECC_CANES_FLAGS)) ti_hecc_error(ndev, int_status, err_status); + if (unlikely(int_status & HECC_CANGIM_DEF_MASK)) { + enum can_state rx_state, tx_state; + u32 rec = hecc_read(priv, HECC_CANREC); + u32 tec = hecc_read(priv, HECC_CANTEC); + + if (int_status & HECC_CANGIF_WLIF) { + handled |= HECC_CANGIF_WLIF; + rx_state = rec >= tec ? CAN_STATE_ERROR_WARNING : 0; + tx_state = rec <= tec ? CAN_STATE_ERROR_WARNING : 0; + netdev_dbg(priv->ndev, "Error Warning interrupt\n"); + ti_hecc_change_state(ndev, rx_state, tx_state); + } + + if (int_status & HECC_CANGIF_EPIF) { + handled |= HECC_CANGIF_EPIF; + rx_state = rec >= tec ? CAN_STATE_ERROR_PASSIVE : 0; + tx_state = rec <= tec ? CAN_STATE_ERROR_PASSIVE : 0; + netdev_dbg(priv->ndev, "Error passive interrupt\n"); + ti_hecc_change_state(ndev, rx_state, tx_state); + } + + if (int_status & HECC_CANGIF_BOIF) { + handled |= HECC_CANGIF_BOIF; + rx_state = CAN_STATE_BUS_OFF; + tx_state = CAN_STATE_BUS_OFF; + netdev_dbg(priv->ndev, "Bus off interrupt\n"); + + /* Disable all interrupts */ + hecc_write(priv, HECC_CANGIM, 0); + can_bus_off(ndev); + ti_hecc_change_state(ndev, rx_state, tx_state); + } + } else if (unlikely(priv->can.state != CAN_STATE_ERROR_ACTIVE)) { + enum can_state new_state, tx_state, rx_state; + u32 rec = hecc_read(priv, HECC_CANREC); + u32 tec = hecc_read(priv, HECC_CANTEC); + + if (rec >= 128 || tec >= 128) + new_state = CAN_STATE_ERROR_PASSIVE; + else if (rec >= 96 || tec >= 96) + new_state = CAN_STATE_ERROR_WARNING; + else + new_state = CAN_STATE_ERROR_ACTIVE; + + if (new_state < priv->can.state) { + rx_state = rec >= tec ? new_state : 0; + tx_state = rec <= tec ? new_state : 0; + ti_hecc_change_state(ndev, rx_state, tx_state); + } + } + if (int_status & HECC_CANGIF_GMIF) { while (priv->tx_tail - priv->tx_head > 0) { mbxno = get_tx_tail_mb(priv); mbx_mask = BIT(mbxno); if (!(mbx_mask & hecc_read(priv, HECC_CANTA))) break; - hecc_clear_bit(priv, HECC_CANMIM, mbx_mask); hecc_write(priv, HECC_CANTA, mbx_mask); spin_lock_irqsave(&priv->mbx_lock, flags); hecc_clear_bit(priv, HECC_CANME, mbx_mask); @@ -695,16 +760,15 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) while ((rx_pending = hecc_read(priv, HECC_CANRMP))) { can_rx_offload_irq_offload_timestamp(&priv->offload, rx_pending); - hecc_write(priv, HECC_CANRMP, rx_pending); } } /* clear all interrupt conditions - read back to avoid spurious ints */ if (priv->use_hecc1int) { - hecc_write(priv, HECC_CANGIF1, HECC_SET_REG); + hecc_write(priv, HECC_CANGIF1, handled); int_status = hecc_read(priv, HECC_CANGIF1); } else { - hecc_write(priv, HECC_CANGIF0, HECC_SET_REG); + hecc_write(priv, HECC_CANGIF0, handled); int_status = hecc_read(priv, HECC_CANGIF0); } @@ -877,7 +941,7 @@ static int ti_hecc_probe(struct platform_device *pdev) priv->offload.mailbox_read = ti_hecc_mailbox_read; priv->offload.mb_first = HECC_RX_FIRST_MBOX; - priv->offload.mb_last = HECC_MAX_TX_MBOX; + priv->offload.mb_last = HECC_RX_LAST_MBOX; err = can_rx_offload_add_timestamp(ndev, &priv->offload); if (err) { dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n"); diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index bd6eb9967630..2f74f6704c12 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -623,6 +623,7 @@ static int gs_can_open(struct net_device *netdev) rc); usb_unanchor_urb(urb); + usb_free_urb(urb); break; } diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 19a702ac49e4..21faa2ec4632 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -876,9 +876,8 @@ static void mcba_usb_disconnect(struct usb_interface *intf) netdev_info(priv->netdev, "device disconnected\n"); unregister_candev(priv->netdev); - free_candev(priv->netdev); - mcba_urb_unlink(priv); + free_candev(priv->netdev); } static struct usb_driver mcba_usb_driver = { diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 617da295b6c1..d2539c95adb6 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -100,7 +100,7 @@ struct pcan_usb_msg_context { u8 *end; u8 rec_cnt; u8 rec_idx; - u8 rec_data_idx; + u8 rec_ts_idx; struct net_device *netdev; struct pcan_usb *pdev; }; @@ -436,8 +436,8 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, } if ((n & PCAN_USB_ERROR_BUS_LIGHT) == 0) { /* no error (back to active state) */ - mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE; - return 0; + new_state = CAN_STATE_ERROR_ACTIVE; + break; } break; @@ -460,9 +460,9 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, } if ((n & PCAN_USB_ERROR_BUS_HEAVY) == 0) { - /* no error (back to active state) */ - mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE; - return 0; + /* no error (back to warning state) */ + new_state = CAN_STATE_ERROR_WARNING; + break; } break; @@ -501,6 +501,11 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n, mc->pdev->dev.can.can_stats.error_warning++; break; + case CAN_STATE_ERROR_ACTIVE: + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = CAN_ERR_CRTL_ACTIVE; + break; + default: /* CAN_STATE_MAX (trick to handle other errors) */ cf->can_id |= CAN_ERR_CRTL; @@ -547,10 +552,15 @@ static int pcan_usb_decode_status(struct pcan_usb_msg_context *mc, mc->ptr += PCAN_USB_CMD_ARGS; if (status_len & PCAN_USB_STATUSLEN_TIMESTAMP) { - int err = pcan_usb_decode_ts(mc, !mc->rec_idx); + int err = pcan_usb_decode_ts(mc, !mc->rec_ts_idx); if (err) return err; + + /* Next packet in the buffer will have a timestamp on a single + * byte + */ + mc->rec_ts_idx++; } switch (f) { @@ -632,10 +642,13 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len) cf->can_dlc = get_can_dlc(rec_len); - /* first data packet timestamp is a word */ - if (pcan_usb_decode_ts(mc, !mc->rec_data_idx)) + /* Only first packet timestamp is a word */ + if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx)) goto decode_failed; + /* Next packet in the buffer will have a timestamp on a single byte */ + mc->rec_ts_idx++; + /* read data */ memset(cf->data, 0x0, sizeof(cf->data)); if (status_len & PCAN_USB_STATUSLEN_RTR) { @@ -688,7 +701,6 @@ static int pcan_usb_decode_msg(struct peak_usb_device *dev, u8 *ibuf, u32 lbuf) /* handle normal can frames here */ } else { err = pcan_usb_decode_data(&mc, sl); - mc.rec_data_idx++; } } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 65dce642b86b..0b7766b715fd 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -750,7 +750,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, dev = netdev_priv(netdev); /* allocate a buffer large enough to send commands */ - dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); + dev->cmd_buf = kzalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL); if (!dev->cmd_buf) { err = -ENOMEM; goto lbl_free_candev; diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index d596a2ad7f78..8fa224b28218 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -996,9 +996,8 @@ static void usb_8dev_disconnect(struct usb_interface *intf) netdev_info(priv->netdev, "device disconnected\n"); unregister_netdev(priv->netdev); - free_candev(priv->netdev); - unlink_all_urbs(priv); + free_candev(priv->netdev); } } diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 911b34316c9d..7c482b2d78d2 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -1599,7 +1599,6 @@ static const struct xcan_devtype_data xcan_zynq_data = { static const struct xcan_devtype_data xcan_axi_data = { .cantype = XAXI_CAN, - .flags = XCAN_FLAG_TXFEMP, .bittiming_const = &xcan_bittiming_const, .btr_ts2_shift = XCAN_BTR_TS2_SHIFT, .btr_sjw_shift = XCAN_BTR_SJW_SHIFT, diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 26509fa37a50..69fc13046ac7 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -37,22 +37,11 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) unsigned int i; u32 reg, offset; - if (priv->type == BCM7445_DEVICE_ID) - offset = CORE_STS_OVERRIDE_IMP; - else - offset = CORE_STS_OVERRIDE_IMP2; - /* Enable the port memories */ reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL); reg &= ~P_TXQ_PSM_VDD(port); core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL); - /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ - reg = core_readl(priv, CORE_IMP_CTL); - reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN); - reg &= ~(RX_DIS | TX_DIS); - core_writel(priv, reg, CORE_IMP_CTL); - /* Enable forwarding */ core_writel(priv, SW_FWDG_EN, CORE_SWMODE); @@ -71,10 +60,27 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) b53_brcm_hdr_setup(ds, port); - /* Force link status for IMP port */ - reg = core_readl(priv, offset); - reg |= (MII_SW_OR | LINK_STS); - core_writel(priv, reg, offset); + if (port == 8) { + if (priv->type == BCM7445_DEVICE_ID) + offset = CORE_STS_OVERRIDE_IMP; + else + offset = CORE_STS_OVERRIDE_IMP2; + + /* Force link status for IMP port */ + reg = core_readl(priv, offset); + reg |= (MII_SW_OR | LINK_STS); + core_writel(priv, reg, offset); + + /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ + reg = core_readl(priv, CORE_IMP_CTL); + reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN); + reg &= ~(RX_DIS | TX_DIS); + core_writel(priv, reg, CORE_IMP_CTL); + } else { + reg = core_readl(priv, CORE_G_PCTL_PORT(port)); + reg &= ~(RX_DIS | TX_DIS); + core_writel(priv, reg, CORE_G_PCTL_PORT(port)); + } } static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable) @@ -1209,10 +1215,10 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) struct bcm_sf2_priv *priv = platform_get_drvdata(pdev); priv->wol_ports_mask = 0; + /* Disable interrupts */ + bcm_sf2_intr_disable(priv); dsa_unregister_switch(priv->dev->ds); bcm_sf2_cfp_exit(priv->dev->ds); - /* Disable all ports and interrupts */ - bcm_sf2_sw_suspend(priv->dev->ds); bcm_sf2_mdio_unregister(priv); return 0; diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c index 073cbd0bb91b..d838c174dc0d 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.c +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -273,6 +273,19 @@ static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip, int pin; int err; + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests to enable time stamping on both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + pin = ptp_find_pin(chip->ptp_clock, PTP_PF_EXTTS, rq->extts.index); if (pin < 0) diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index f40b248f0b23..ffac0ea4e8d5 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -26,8 +26,8 @@ config NET_DSA_SJA1105_PTP config NET_DSA_SJA1105_TAS bool "Support for the Time-Aware Scheduler on NXP SJA1105" - depends on NET_DSA_SJA1105 - depends on NET_SCH_TAPRIO + depends on NET_DSA_SJA1105 && NET_SCH_TAPRIO + depends on NET_SCH_TAPRIO=y || NET_DSA_SJA1105=m help This enables support for the TTEthernet-based egress scheduling engine in the SJA1105 DSA driver, which is controlled using a diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index 42d2e1b02c44..664d664e0925 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -256,6 +256,9 @@ static int emac_rockchip_remove(struct platform_device *pdev) if (priv->regulator) regulator_disable(priv->regulator); + if (priv->soc_data->need_div_macclk) + clk_disable_unprepare(priv->macclk); + free_netdev(ndev); return err; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b4a8cf620a0c..04ec909e06df 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10382,7 +10382,8 @@ static void bnxt_cleanup_pci(struct bnxt *bp) { bnxt_unmap_bars(bp, bp->pdev); pci_release_regions(bp->pdev); - pci_disable_device(bp->pdev); + if (pci_is_enabled(bp->pdev)) + pci_disable_device(bp->pdev); } static void bnxt_init_dflt_coal(struct bnxt *bp) @@ -10669,14 +10670,11 @@ static void bnxt_fw_reset_task(struct work_struct *work) bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW; } /* fall through */ - case BNXT_FW_RESET_STATE_RESET_FW: { - u32 wait_dsecs = bp->fw_health->post_reset_wait_dsecs; - + case BNXT_FW_RESET_STATE_RESET_FW: bnxt_reset_all(bp); bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; - bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10); + bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10); return; - } case BNXT_FW_RESET_STATE_ENABLE_DEV: if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) && bp->fw_health) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index e664392dccc0..7151244f8c7d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -29,25 +29,20 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter, val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); health_status = val & 0xffff; - if (health_status == BNXT_FW_STATUS_HEALTHY) { - rc = devlink_fmsg_string_pair_put(fmsg, "FW status", - "Healthy;"); - if (rc) - return rc; - } else if (health_status < BNXT_FW_STATUS_HEALTHY) { - rc = devlink_fmsg_string_pair_put(fmsg, "FW status", - "Not yet completed initialization;"); + if (health_status < BNXT_FW_STATUS_HEALTHY) { + rc = devlink_fmsg_string_pair_put(fmsg, "Description", + "Not yet completed initialization"); if (rc) return rc; } else if (health_status > BNXT_FW_STATUS_HEALTHY) { - rc = devlink_fmsg_string_pair_put(fmsg, "FW status", - "Encountered fatal error and cannot recover;"); + rc = devlink_fmsg_string_pair_put(fmsg, "Description", + "Encountered fatal error and cannot recover"); if (rc) return rc; } if (val >> 16) { - rc = devlink_fmsg_u32_pair_put(fmsg, "Error", val >> 16); + rc = devlink_fmsg_u32_pair_put(fmsg, "Error code", val >> 16); if (rc) return rc; } @@ -215,25 +210,68 @@ enum bnxt_dl_param_id { static const struct bnxt_dl_nvm_param nvm_params[] = { {DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV, - BNXT_NVM_SHARED_CFG, 1}, + BNXT_NVM_SHARED_CFG, 1, 1}, {DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, NVM_OFF_IGNORE_ARI, - BNXT_NVM_SHARED_CFG, 1}, + BNXT_NVM_SHARED_CFG, 1, 1}, {DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, - NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10}, + NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10, 4}, {DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, - NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7}, + NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7, 4}, {BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK, - BNXT_NVM_SHARED_CFG, 1}, + BNXT_NVM_SHARED_CFG, 1, 1}, }; +union bnxt_nvm_data { + u8 val8; + __le32 val32; +}; + +static void bnxt_copy_to_nvm_data(union bnxt_nvm_data *dst, + union devlink_param_value *src, + int nvm_num_bits, int dl_num_bytes) +{ + u32 val32 = 0; + + if (nvm_num_bits == 1) { + dst->val8 = src->vbool; + return; + } + if (dl_num_bytes == 4) + val32 = src->vu32; + else if (dl_num_bytes == 2) + val32 = (u32)src->vu16; + else if (dl_num_bytes == 1) + val32 = (u32)src->vu8; + dst->val32 = cpu_to_le32(val32); +} + +static void bnxt_copy_from_nvm_data(union devlink_param_value *dst, + union bnxt_nvm_data *src, + int nvm_num_bits, int dl_num_bytes) +{ + u32 val32; + + if (nvm_num_bits == 1) { + dst->vbool = src->val8; + return; + } + val32 = le32_to_cpu(src->val32); + if (dl_num_bytes == 4) + dst->vu32 = val32; + else if (dl_num_bytes == 2) + dst->vu16 = (u16)val32; + else if (dl_num_bytes == 1) + dst->vu8 = (u8)val32; +} + static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, int msg_len, union devlink_param_value *val) { struct hwrm_nvm_get_variable_input *req = msg; - void *data_addr = NULL, *buf = NULL; struct bnxt_dl_nvm_param nvm_param; - int bytesize, idx = 0, rc, i; + union bnxt_nvm_data *data; dma_addr_t data_dma_addr; + int idx = 0, rc, i; /* Get/Set NVM CFG parameter is supported only on PFs */ if (BNXT_VF(bp)) @@ -254,47 +292,31 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG) idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID; - bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE; - switch (bytesize) { - case 1: - if (nvm_param.num_bits == 1) - buf = &val->vbool; - else - buf = &val->vu8; - break; - case 2: - buf = &val->vu16; - break; - case 4: - buf = &val->vu32; - break; - default: - return -EFAULT; - } - - data_addr = dma_alloc_coherent(&bp->pdev->dev, bytesize, - &data_dma_addr, GFP_KERNEL); - if (!data_addr) + data = dma_alloc_coherent(&bp->pdev->dev, sizeof(*data), + &data_dma_addr, GFP_KERNEL); + if (!data) return -ENOMEM; req->dest_data_addr = cpu_to_le64(data_dma_addr); - req->data_len = cpu_to_le16(nvm_param.num_bits); + req->data_len = cpu_to_le16(nvm_param.nvm_num_bits); req->option_num = cpu_to_le16(nvm_param.offset); req->index_0 = cpu_to_le16(idx); if (idx) req->dimensions = cpu_to_le16(1); if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) { - memcpy(data_addr, buf, bytesize); + bnxt_copy_to_nvm_data(data, val, nvm_param.nvm_num_bits, + nvm_param.dl_num_bytes); rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT); } else { rc = hwrm_send_message_silent(bp, msg, msg_len, HWRM_CMD_TIMEOUT); + if (!rc) + bnxt_copy_from_nvm_data(val, data, + nvm_param.nvm_num_bits, + nvm_param.dl_num_bytes); } - if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE)) - memcpy(buf, data_addr, bytesize); - - dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr); + dma_free_coherent(&bp->pdev->dev, sizeof(*data), data, data_dma_addr); if (rc == -EACCES) netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n"); return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index b97e0baeb42d..2f4fd0a7d04b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -52,7 +52,8 @@ struct bnxt_dl_nvm_param { u16 id; u16 offset; u16 dir_type; - u16 num_bits; + u16 nvm_num_bits; + u8 dl_num_bytes; }; void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 0f138280315a..1de51811fcb4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1996,8 +1996,6 @@ static void reset_umac(struct bcmgenet_priv *priv) /* issue soft reset with (rg)mii loopback to ensure a stable rxclk */ bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD); - udelay(2); - bcmgenet_umac_writel(priv, 0, UMAC_CMD); } static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) @@ -2614,8 +2612,10 @@ static void bcmgenet_irq_task(struct work_struct *work) spin_unlock_irq(&priv->lock); if (status & UMAC_IRQ_PHY_DET_R && - priv->dev->phydev->autoneg != AUTONEG_ENABLE) + priv->dev->phydev->autoneg != AUTONEG_ENABLE) { phy_init_hw(priv->dev->phydev); + genphy_config_aneg(priv->dev->phydev); + } /* Link UP/DOWN event */ if (status & UMAC_IRQ_LINK_EVENT) @@ -2879,12 +2879,6 @@ static int bcmgenet_open(struct net_device *dev) if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); - ret = bcmgenet_mii_connect(dev); - if (ret) { - netdev_err(dev, "failed to connect to PHY\n"); - goto err_clk_disable; - } - /* take MAC out of reset */ bcmgenet_umac_reset(priv); @@ -2894,12 +2888,6 @@ static int bcmgenet_open(struct net_device *dev) reg = bcmgenet_umac_readl(priv, UMAC_CMD); priv->crc_fwd_en = !!(reg & CMD_CRC_FWD); - ret = bcmgenet_mii_config(dev, true); - if (ret) { - netdev_err(dev, "unsupported PHY\n"); - goto err_disconnect_phy; - } - bcmgenet_set_hw_addr(priv, dev->dev_addr); if (priv->internal_phy) { @@ -2915,7 +2903,7 @@ static int bcmgenet_open(struct net_device *dev) ret = bcmgenet_init_dma(priv); if (ret) { netdev_err(dev, "failed to initialize DMA\n"); - goto err_disconnect_phy; + goto err_clk_disable; } /* Always enable ring 16 - descriptor ring */ @@ -2938,19 +2926,25 @@ static int bcmgenet_open(struct net_device *dev) goto err_irq0; } + ret = bcmgenet_mii_probe(dev); + if (ret) { + netdev_err(dev, "failed to connect to PHY\n"); + goto err_irq1; + } + bcmgenet_netif_start(dev); netif_tx_start_all_queues(dev); return 0; +err_irq1: + free_irq(priv->irq1, priv); err_irq0: free_irq(priv->irq0, priv); err_fini_dma: bcmgenet_dma_teardown(priv); bcmgenet_fini_dma(priv); -err_disconnect_phy: - phy_disconnect(dev->phydev); err_clk_disable: if (priv->internal_phy) bcmgenet_power_down(priv, GENET_POWER_PASSIVE); @@ -3631,8 +3625,6 @@ static int bcmgenet_resume(struct device *d) if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); - phy_init_hw(dev->phydev); - bcmgenet_umac_reset(priv); init_umac(priv); @@ -3641,7 +3633,10 @@ static int bcmgenet_resume(struct device *d) if (priv->wolopts) clk_disable_unprepare(priv->clk_wol); + phy_init_hw(dev->phydev); + /* Speed settings must be restored */ + genphy_config_aneg(dev->phydev); bcmgenet_mii_config(priv->dev, false); bcmgenet_set_hw_addr(priv, dev->dev_addr); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 7fbf573d8d52..dbc69d8fa05f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -720,8 +720,8 @@ GENET_IO_MACRO(rbuf, GENET_RBUF_OFF); /* MDIO routines */ int bcmgenet_mii_init(struct net_device *dev); -int bcmgenet_mii_connect(struct net_device *dev); int bcmgenet_mii_config(struct net_device *dev, bool init); +int bcmgenet_mii_probe(struct net_device *dev); void bcmgenet_mii_exit(struct net_device *dev); void bcmgenet_phy_power_set(struct net_device *dev, bool enable); void bcmgenet_mii_setup(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 17bb8d60a157..dbe18cdf6c1b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -173,46 +173,6 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) bcmgenet_fixed_phy_link_update); } -int bcmgenet_mii_connect(struct net_device *dev) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device_node *dn = priv->pdev->dev.of_node; - struct phy_device *phydev; - u32 phy_flags = 0; - int ret; - - /* Communicate the integrated PHY revision */ - if (priv->internal_phy) - phy_flags = priv->gphy_rev; - - /* Initialize link state variables that bcmgenet_mii_setup() uses */ - priv->old_link = -1; - priv->old_speed = -1; - priv->old_duplex = -1; - priv->old_pause = -1; - - if (dn) { - phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, - phy_flags, priv->phy_interface); - if (!phydev) { - pr_err("could not attach to PHY\n"); - return -ENODEV; - } - } else { - phydev = dev->phydev; - phydev->dev_flags = phy_flags; - - ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, - priv->phy_interface); - if (ret) { - pr_err("could not attach to PHY\n"); - return -ENODEV; - } - } - - return 0; -} - int bcmgenet_mii_config(struct net_device *dev, bool init) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -221,8 +181,38 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) const char *phy_name = NULL; u32 id_mode_dis = 0; u32 port_ctrl; + int bmcr = -1; + int ret; u32 reg; + /* MAC clocking workaround during reset of umac state machines */ + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + if (reg & CMD_SW_RESET) { + /* An MII PHY must be isolated to prevent TXC contention */ + if (priv->phy_interface == PHY_INTERFACE_MODE_MII) { + ret = phy_read(phydev, MII_BMCR); + if (ret >= 0) { + bmcr = ret; + ret = phy_write(phydev, MII_BMCR, + bmcr | BMCR_ISOLATE); + } + if (ret) { + netdev_err(dev, "failed to isolate PHY\n"); + return ret; + } + } + /* Switch MAC clocking to RGMII generated clock */ + bcmgenet_sys_writel(priv, PORT_MODE_EXT_GPHY, SYS_PORT_CTRL); + /* Ensure 5 clks with Rx disabled + * followed by 5 clks with Reset asserted + */ + udelay(4); + reg &= ~(CMD_SW_RESET | CMD_LCL_LOOP_EN); + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + /* Ensure 5 more clocks before Rx is enabled */ + udelay(2); + } + priv->ext_phy = !priv->internal_phy && (priv->phy_interface != PHY_INTERFACE_MODE_MOCA); @@ -254,6 +244,9 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) phy_set_max_speed(phydev, SPEED_100); bcmgenet_sys_writel(priv, PORT_MODE_EXT_EPHY, SYS_PORT_CTRL); + /* Restore the MII PHY after isolation */ + if (bmcr >= 0) + phy_write(phydev, MII_BMCR, bmcr); break; case PHY_INTERFACE_MODE_REVMII: @@ -306,21 +299,71 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } - if (init) { - linkmode_copy(phydev->advertising, phydev->supported); + if (init) + dev_info(kdev, "configuring instance for %s\n", phy_name); - /* The internal PHY has its link interrupts routed to the - * Ethernet MAC ISRs. On GENETv5 there is a hardware issue - * that prevents the signaling of link UP interrupts when - * the link operates at 10Mbps, so fallback to polling for - * those versions of GENET. - */ - if (priv->internal_phy && !GENET_IS_V5(priv)) - phydev->irq = PHY_IGNORE_INTERRUPT; + return 0; +} - dev_info(kdev, "configuring instance for %s\n", phy_name); +int bcmgenet_mii_probe(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; + struct phy_device *phydev; + u32 phy_flags = 0; + int ret; + + /* Communicate the integrated PHY revision */ + if (priv->internal_phy) + phy_flags = priv->gphy_rev; + + /* Initialize link state variables that bcmgenet_mii_setup() uses */ + priv->old_link = -1; + priv->old_speed = -1; + priv->old_duplex = -1; + priv->old_pause = -1; + + if (dn) { + phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, + phy_flags, priv->phy_interface); + if (!phydev) { + pr_err("could not attach to PHY\n"); + return -ENODEV; + } + } else { + phydev = dev->phydev; + phydev->dev_flags = phy_flags; + + ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, + priv->phy_interface); + if (ret) { + pr_err("could not attach to PHY\n"); + return -ENODEV; + } } + /* Configure port multiplexer based on what the probed PHY device since + * reading the 'max-speed' property determines the maximum supported + * PHY speed which is needed for bcmgenet_mii_config() to configure + * things appropriately. + */ + ret = bcmgenet_mii_config(dev, true); + if (ret) { + phy_disconnect(dev->phydev); + return ret; + } + + linkmode_copy(phydev->advertising, phydev->supported); + + /* The internal PHY has its link interrupts routed to the + * Ethernet MAC ISRs. On GENETv5 there is a hardware issue + * that prevents the signaling of link UP interrupts when + * the link operates at 10Mbps, so fallback to polling for + * those versions of GENET. + */ + if (priv->internal_phy && !GENET_IS_V5(priv)) + dev->phydev->irq = PHY_IGNORE_INTERRUPT; + return 0; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 77f3511b97de..ca3aa1250dd1 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6280,6 +6280,10 @@ static int tg3_ptp_enable(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + if (rq->perout.index != 0) return -EINVAL; diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 0e5de88fd6e8..cdd7e5da4a74 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1499,7 +1499,7 @@ static int octeon_mgmt_probe(struct platform_device *pdev) netdev->ethtool_ops = &octeon_mgmt_ethtool_ops; netdev->min_mtu = 64 - OCTEON_MGMT_RX_HEADROOM; - netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM; + netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM - VLAN_HLEN; mac = of_get_mac_address(pdev->dev.of_node); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c index a4dead4ab0ed..86b528d8364c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c @@ -695,10 +695,10 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld) lld->write_cmpl_support = adap->params.write_cmpl_support; } -static void uld_attach(struct adapter *adap, unsigned int uld) +static int uld_attach(struct adapter *adap, unsigned int uld) { - void *handle; struct cxgb4_lld_info lli; + void *handle; uld_init(adap, &lli); uld_queue_init(adap, uld, &lli); @@ -708,7 +708,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld) dev_warn(adap->pdev_dev, "could not attach to the %s driver, error %ld\n", adap->uld[uld].name, PTR_ERR(handle)); - return; + return PTR_ERR(handle); } adap->uld[uld].handle = handle; @@ -716,22 +716,22 @@ static void uld_attach(struct adapter *adap, unsigned int uld) if (adap->flags & CXGB4_FULL_INIT_DONE) adap->uld[uld].state_change(handle, CXGB4_STATE_UP); + + return 0; } -/** - * cxgb4_register_uld - register an upper-layer driver - * @type: the ULD type - * @p: the ULD methods +/* cxgb4_register_uld - register an upper-layer driver + * @type: the ULD type + * @p: the ULD methods * - * Registers an upper-layer driver with this driver and notifies the ULD - * about any presently available devices that support its type. Returns - * %-EBUSY if a ULD of the same type is already registered. + * Registers an upper-layer driver with this driver and notifies the ULD + * about any presently available devices that support its type. */ void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p) { - int ret = 0; struct adapter *adap; + int ret = 0; if (type >= CXGB4_ULD_MAX) return; @@ -763,8 +763,12 @@ void cxgb4_register_uld(enum cxgb4_uld type, if (ret) goto free_irq; adap->uld[type] = *p; - uld_attach(adap, type); + ret = uld_attach(adap, type); + if (ret) + goto free_txq; continue; +free_txq: + release_sge_txq_uld(adap, type); free_irq: if (adap->flags & CXGB4_FULL_INIT_DONE) quiesce_rx_uld(adap, type); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index b3da81e90132..928bfea5457b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -3791,15 +3791,11 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, * write the CIDX Updates into the Status Page at the end of the * TX Queue. */ - c.autoequiqe_to_viid = htonl((dbqt - ? FW_EQ_ETH_CMD_AUTOEQUIQE_F - : FW_EQ_ETH_CMD_AUTOEQUEQE_F) | + c.autoequiqe_to_viid = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F | FW_EQ_ETH_CMD_VIID_V(pi->viid)); c.fetchszm_to_iqid = - htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(dbqt - ? HOSTFCMODE_INGRESS_QUEUE_X - : HOSTFCMODE_STATUS_PAGE_X) | + htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) | FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) | FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid)); diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index f1a0c4dceda0..f37c9a08c4cf 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -763,6 +763,7 @@ static int ep93xx_eth_remove(struct platform_device *pdev) { struct net_device *dev; struct ep93xx_priv *ep; + struct resource *mem; dev = platform_get_drvdata(pdev); if (dev == NULL) @@ -778,8 +779,8 @@ static int ep93xx_eth_remove(struct platform_device *pdev) iounmap(ep->base_addr); if (ep->res != NULL) { - release_resource(ep->res); - kfree(ep->res); + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + release_mem_region(mem->start, resource_size(mem)); } free_netdev(dev); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index e736ce2c58ca..a8f4c69252ff 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2524,6 +2524,7 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev) struct gemini_ethernet_port *port = platform_get_drvdata(pdev); gemini_port_remove(port); + free_netdev(port->netdev); return 0; } diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h index 0b12f89bf89a..9fdf77d5eb37 100644 --- a/drivers/net/ethernet/cortina/gemini.h +++ b/drivers/net/ethernet/cortina/gemini.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* Register definitions for Gemini GMAC Ethernet device driver * * Copyright (C) 2006 Storlink, Corp. diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 9b7af94a40bb..96e9565f1e08 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -727,6 +727,18 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb, */ nfrags = skb_shinfo(skb)->nr_frags; + /* Setup HW checksumming */ + csum_vlan = 0; + if (skb->ip_summed == CHECKSUM_PARTIAL && + !ftgmac100_prep_tx_csum(skb, &csum_vlan)) + goto drop; + + /* Add VLAN tag */ + if (skb_vlan_tag_present(skb)) { + csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG; + csum_vlan |= skb_vlan_tag_get(skb) & 0xffff; + } + /* Get header len */ len = skb_headlen(skb); @@ -753,19 +765,6 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb, if (nfrags == 0) f_ctl_stat |= FTGMAC100_TXDES0_LTS; txdes->txdes3 = cpu_to_le32(map); - - /* Setup HW checksumming */ - csum_vlan = 0; - if (skb->ip_summed == CHECKSUM_PARTIAL && - !ftgmac100_prep_tx_csum(skb, &csum_vlan)) - goto drop; - - /* Add VLAN tag */ - if (skb_vlan_tag_present(skb)) { - csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG; - csum_vlan |= skb_vlan_tag_get(skb) & 0xffff; - } - txdes->txdes1 = cpu_to_le32(csum_vlan); /* Next descriptor */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 19379bae0144..bf5add954181 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -2232,8 +2232,16 @@ err_set_cdan: err_service_reg: free_channel(priv, channel); err_alloc_ch: - if (err == -EPROBE_DEFER) + if (err == -EPROBE_DEFER) { + for (i = 0; i < priv->num_channels; i++) { + channel = priv->channel[i]; + nctx = &channel->nctx; + dpaa2_io_service_deregister(channel->dpio, nctx, dev); + free_channel(priv, channel); + } + priv->num_channels = 0; return err; + } if (cpumask_empty(&priv->dpio_cpumask)) { dev_err(dev, "No cpu with an affine DPIO/DPCON\n"); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h index ff2e177395d4..df2458a5e9ef 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2018 NXP */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h index 720cd50f5895..4ac05bfef338 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2013-2016 Freescale Semiconductor Inc. * Copyright 2016-2018 NXP diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc.h b/drivers/net/ethernet/freescale/dpaa2/dprtc.h index be7914c1634d..311c184e1aef 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dprtc.h +++ b/drivers/net/ethernet/freescale/dpaa2/dprtc.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2013-2016 Freescale Semiconductor Inc. * Copyright 2016-2018 NXP diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d4d4c72adf49..4bb30761abfc 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3558,7 +3558,7 @@ fec_probe(struct platform_device *pdev) for (i = 0; i < irq_cnt; i++) { snprintf(irq_name, sizeof(irq_name), "int%d", i); - irq = platform_get_irq_byname(pdev, irq_name); + irq = platform_get_irq_byname_optional(pdev, irq_name); if (irq < 0) irq = platform_get_irq(pdev, i); if (irq < 0) { @@ -3636,6 +3636,11 @@ fec_drv_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); struct device_node *np = pdev->dev.of_node; + int ret; + + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) + return ret; cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -3643,13 +3648,17 @@ fec_drv_remove(struct platform_device *pdev) fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); - pm_runtime_put(&pdev->dev); - pm_runtime_disable(&pdev->dev); + if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); free_netdev(ndev); + clk_disable_unprepare(fep->clk_ahb); + clk_disable_unprepare(fep->clk_ipg); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; } diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 19e2365be7d8..945643c02615 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -600,9 +600,9 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep); - irq = platform_get_irq_byname(pdev, "pps"); + irq = platform_get_irq_byname_optional(pdev, "pps"); if (irq < 0) - irq = platform_get_irq(pdev, irq_idx); + irq = platform_get_irq_optional(pdev, irq_idx); /* Failure to get an irq is not fatal, * only the PTP_CLOCK_PPS clock events should stop */ diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 59564ac99d2a..edec61dfc868 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -289,6 +289,8 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD; page_info = &rx->data.page_info[idx]; + dma_sync_single_for_cpu(&priv->pdev->dev, rx->data.qpl->page_buses[idx], + PAGE_SIZE, DMA_FROM_DEVICE); /* gvnic can only receive into registered segments. If the buffer * can't be recycled, our only choice is to copy the data out of diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 778b87b5a06c..f4889431f9b7 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -390,7 +390,22 @@ static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc, seg_desc->seg.seg_addr = cpu_to_be64(addr); } -static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb) +static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses, + u64 iov_offset, u64 iov_len) +{ + u64 last_page = (iov_offset + iov_len - 1) / PAGE_SIZE; + u64 first_page = iov_offset / PAGE_SIZE; + dma_addr_t dma; + u64 page; + + for (page = first_page; page <= last_page; page++) { + dma = page_buses[page]; + dma_sync_single_for_device(dev, dma, PAGE_SIZE, DMA_TO_DEVICE); + } +} + +static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb, + struct device *dev) { int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset; union gve_tx_desc *pkt_desc, *seg_desc; @@ -432,6 +447,9 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb) skb_copy_bits(skb, 0, tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset, hlen); + gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses, + info->iov[hdr_nfrags - 1].iov_offset, + info->iov[hdr_nfrags - 1].iov_len); copy_offset = hlen; for (i = payload_iov; i < payload_nfrags + payload_iov; i++) { @@ -445,6 +463,9 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb) skb_copy_bits(skb, copy_offset, tx->tx_fifo.base + info->iov[i].iov_offset, info->iov[i].iov_len); + gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses, + info->iov[i].iov_offset, + info->iov[i].iov_len); copy_offset += info->iov[i].iov_len; } @@ -473,7 +494,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) gve_tx_put_doorbell(priv, tx->q_resources, tx->req); return NETDEV_TX_BUSY; } - nsegs = gve_tx_add_skb(tx, skb); + nsegs = gve_tx_add_skb(tx, skb, &priv->pdev->dev); netdev_tx_sent_queue(tx->netdev_txq, skb->len); skb_tx_timestamp(skb); diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index c84167447abe..4606a7e4a6d1 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -237,6 +237,7 @@ struct hip04_priv { dma_addr_t rx_phys[RX_DESC_NUM]; unsigned int rx_head; unsigned int rx_buf_size; + unsigned int rx_cnt_remaining; struct device_node *phy_node; struct phy_device *phy; @@ -575,7 +576,6 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) struct hip04_priv *priv = container_of(napi, struct hip04_priv, napi); struct net_device *ndev = priv->ndev; struct net_device_stats *stats = &ndev->stats; - unsigned int cnt = hip04_recv_cnt(priv); struct rx_desc *desc; struct sk_buff *skb; unsigned char *buf; @@ -588,8 +588,8 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) /* clean up tx descriptors */ tx_remaining = hip04_tx_reclaim(ndev, false); - - while (cnt && !last) { + priv->rx_cnt_remaining += hip04_recv_cnt(priv); + while (priv->rx_cnt_remaining && !last) { buf = priv->rx_buf[priv->rx_head]; skb = build_skb(buf, priv->rx_buf_size); if (unlikely(!skb)) { @@ -635,11 +635,13 @@ refill: hip04_set_recv_desc(priv, phys); priv->rx_head = RX_NEXT(priv->rx_head); - if (rx >= budget) + if (rx >= budget) { + --priv->rx_cnt_remaining; goto done; + } - if (--cnt == 0) - cnt = hip04_recv_cnt(priv); + if (--priv->rx_cnt_remaining == 0) + priv->rx_cnt_remaining += hip04_recv_cnt(priv); } if (!(priv->reg_inten & RCV_INT)) { @@ -724,6 +726,7 @@ static int hip04_mac_open(struct net_device *ndev) int i; priv->rx_head = 0; + priv->rx_cnt_remaining = 0; priv->tx_head = 0; priv->tx_tail = 0; hip04_reset_ppe(priv); @@ -1038,7 +1041,6 @@ static int hip04_remove(struct platform_device *pdev) hip04_free_ring(ndev, d); unregister_netdev(ndev); - free_irq(ndev->irq, ndev); of_node_put(priv->phy_node); cancel_work_sync(&priv->tx_timeout_task); free_netdev(ndev); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 6d0457eb4faa..08339278c722 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -199,7 +199,6 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags) ring->q = q; ring->flags = flags; - spin_lock_init(&ring->lock); ring->coal_param = q->handle->coal_param; assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index e9c67c06bfd2..6ab9458302e1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -274,9 +274,6 @@ struct hnae_ring { /* statistic */ struct ring_stats stats; - /* ring lock for poll one */ - spinlock_t lock; - dma_addr_t desc_dma_addr; u32 buf_size; /* size for hnae_desc->addr, preset by AE */ u16 desc_num; /* total number of desc */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index a48396dd4ebb..14ab20491fd0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -943,15 +943,6 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h) return u > c ? (h > c && h <= u) : (h > c || h <= u); } -/* netif_tx_lock will turn down the performance, set only when necessary */ -#ifdef CONFIG_NET_POLL_CONTROLLER -#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock) -#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock) -#else -#define NETIF_TX_LOCK(ring) -#define NETIF_TX_UNLOCK(ring) -#endif - /* reclaim all desc in one budget * return error or number of desc left */ @@ -965,21 +956,16 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, int head; int bytes, pkts; - NETIF_TX_LOCK(ring); - head = readl_relaxed(ring->io_base + RCB_REG_HEAD); rmb(); /* make sure head is ready before touch any data */ - if (is_ring_empty(ring) || head == ring->next_to_clean) { - NETIF_TX_UNLOCK(ring); + if (is_ring_empty(ring) || head == ring->next_to_clean) return 0; /* no data to poll */ - } if (!is_valid_clean_head(ring, head)) { netdev_err(ndev, "wrong head (%d, %d-%d)\n", head, ring->next_to_use, ring->next_to_clean); ring->stats.io_err_cnt++; - NETIF_TX_UNLOCK(ring); return -EIO; } @@ -994,8 +980,6 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, ring->stats.tx_pkts += pkts; ring->stats.tx_bytes += bytes; - NETIF_TX_UNLOCK(ring); - dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); netdev_tx_completed_queue(dev_queue, pkts, bytes); @@ -1055,16 +1039,12 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data) int head; int bytes, pkts; - NETIF_TX_LOCK(ring); - head = ring->next_to_use; /* ntu :soft setted ring position*/ bytes = 0; pkts = 0; while (head != ring->next_to_clean) hns_nic_reclaim_one_desc(ring, &bytes, &pkts); - NETIF_TX_UNLOCK(ring); - dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); netdev_tx_reset_queue(dev_queue); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 75ccc1e7076b..a0998937727d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HNAE3_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 2110fa3b4479..5d468ed404a6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HNS3_ENET_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 680c3508876d..52c9d204fe3d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -70,11 +70,6 @@ static const struct hns3_stats hns3_rxq_stats[] = { #define HNS3_NIC_LB_TEST_TX_CNT_ERR 2 #define HNS3_NIC_LB_TEST_RX_CNT_ERR 3 -struct hns3_link_mode_mapping { - u32 hns3_link_mode; - u32 ethtool_link_mode; -}; - static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) { struct hnae3_handle *h = hns3_get_handle(ndev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 4821fe08b5e4..1426eb5ddf3d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_CMD_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index c063301d6060..a1790af73096 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -124,7 +124,7 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets, if (ret) return ret; - for (i = 0; i < HNAE3_MAX_TC; i++) { + for (i = 0; i < hdev->tc_max; i++) { switch (ets->tc_tsa[i]) { case IEEE_8021QAZ_TSA_STRICT: if (hdev->tm_info.tc_info[i].tc_sch_mode != @@ -318,6 +318,7 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; u8 i, j, pfc_map, *prio_tc; + int ret; if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) @@ -347,7 +348,21 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) hclge_tm_pfc_info_update(hdev); - return hclge_pause_setup_hw(hdev, false); + ret = hclge_pause_setup_hw(hdev, false); + if (ret) + return ret; + + ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT); + if (ret) + return ret; + + ret = hclge_buffer_alloc(hdev); + if (ret) { + hclge_notify_client(hdev, HNAE3_UP_CLIENT); + return ret; + } + + return hclge_notify_client(hdev, HNAE3_UP_CLIENT); } /* DCBX configuration */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h index 278f21e02736..b04702e65689 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_DCB_H__ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e02e01bd9eff..c052bb33b3d3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3587,12 +3587,28 @@ static int hclge_set_rst_done(struct hclge_dev *hdev) { struct hclge_pf_rst_done_cmd *req; struct hclge_desc desc; + int ret; req = (struct hclge_pf_rst_done_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PF_RST_DONE, false); req->pf_rst_done |= HCLGE_PF_RESET_DONE_BIT; - return hclge_cmd_send(&hdev->hw, &desc, 1); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + /* To be compatible with the old firmware, which does not support + * command HCLGE_OPC_PF_RST_DONE, just print a warning and + * return success + */ + if (ret == -EOPNOTSUPP) { + dev_warn(&hdev->pdev->dev, + "current firmware does not support command(0x%x)!\n", + HCLGE_OPC_PF_RST_DONE); + return 0; + } else if (ret) { + dev_err(&hdev->pdev->dev, "assert PF reset done fail %d!\n", + ret); + } + + return ret; } static int hclge_reset_prepare_up(struct hclge_dev *hdev) @@ -6247,11 +6263,23 @@ static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, func_id = hclge_get_port_number(HOST_PORT, 0, vfid, 0); req = (struct hclge_mac_vlan_switch_cmd *)desc.data; + + /* read current config parameter */ hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_SWITCH_PARAM, - false); + true); req->roce_sel = HCLGE_MAC_VLAN_NIC_SEL; req->func_id = cpu_to_le32(func_id); - req->switch_param = switch_param; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "read mac vlan switch parameter fail, ret = %d\n", ret); + return ret; + } + + /* modify and write new config parameter */ + hclge_cmd_reuse_desc(&desc, false); + req->switch_param = (req->switch_param & param_mask) | switch_param; req->param_mask = param_mask; ret = hclge_cmd_send(&hdev->hw, &desc, 1); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index c3d56b872ed7..615cde1cbf0b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_MAIN_H @@ -166,7 +166,7 @@ enum HLCGE_PORT_TYPE { #define HCLGE_GLOBAL_RESET_BIT 0 #define HCLGE_CORE_RESET_BIT 1 #define HCLGE_IMP_RESET_BIT 2 -#define HCLGE_RESET_INT_M GENMASK(2, 0) +#define HCLGE_RESET_INT_M GENMASK(7, 5) #define HCLGE_FUN_RST_ING 0x20C00 #define HCLGE_FUN_RST_ING_B 0 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h index ef095d9c566f..dd9a1218a7b0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_MDIO_H diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 818610988d34..260f22d19d81 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright (c) 2016-2017 Hisilicon Limited. #ifndef __HCLGE_TM_H diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index f59d9a8e35e2..0686ded7ad3a 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2878,10 +2878,15 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter, if (test_bit(0, &adapter->resetting) && adapter->reset_reason == VNIC_RESET_MOBILITY) { - struct irq_desc *desc = irq_to_desc(scrq->irq); - struct irq_chip *chip = irq_desc_get_chip(desc); + u64 val = (0xff000000) | scrq->hw_irq; - chip->irq_eoi(&desc->irq_data); + rc = plpar_hcall_norets(H_EOI, val); + /* H_EOI would fail with rc = H_FUNCTION when running + * in XIVE mode which is expected, but not an error. + */ + if (rc && (rc != H_FUNCTION)) + dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n", + val, rc); } rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 71d3d8854d8f..be56e631d693 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -607,6 +607,7 @@ static int e1000_set_ringparam(struct net_device *netdev, for (i = 0; i < adapter->num_rx_queues; i++) rxdr[i].count = rxdr->count; + err = 0; if (netif_running(adapter->netdev)) { /* Try to get new resources before deleting old */ err = e1000_setup_all_rx_resources(adapter); @@ -627,14 +628,13 @@ static int e1000_set_ringparam(struct net_device *netdev, adapter->rx_ring = rxdr; adapter->tx_ring = txdr; err = e1000_up(adapter); - if (err) - goto err_setup; } kfree(tx_old); kfree(rx_old); clear_bit(__E1000_RESETTING, &adapter->flags); - return 0; + return err; + err_setup_tx: e1000_free_all_rx_resources(adapter); err_setup_rx: @@ -646,7 +646,6 @@ err_alloc_rx: err_alloc_tx: if (netif_running(adapter->netdev)) e1000_up(adapter); -err_setup: clear_bit(__E1000_RESETTING, &adapter->flags); return err; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 530613f31527..69a2daaca5c5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -20,6 +20,8 @@ /* API version 1.7 implements additional link and PHY-specific APIs */ #define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 +/* API version 1.9 for X722 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_X722 0x0009 /* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */ #define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006 diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index d37c6e0e5f08..7560f06768e0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1876,7 +1876,8 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE) hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU; - if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE && + hw->mac.type != I40E_MAC_X722) { __le32 tmp; memcpy(&tmp, resp->link_type, sizeof(tmp)); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index b1c3227ae4ab..d07e1a890428 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -157,11 +157,6 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) err = i40e_queue_pair_enable(vsi, qid); if (err) return err; - - /* Kick start the NAPI context so that receiving will start */ - err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX); - if (err) - return err; } return 0; @@ -694,8 +689,6 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) i40e_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -774,12 +767,8 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, i40e_update_tx_stats(tx_ring, completed_frames, total_bytes); out_xmit: - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { - if (tx_ring->next_to_clean == tx_ring->next_to_use) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); - else - xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); - } + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); xmit_done = i40e_xmit_zc(tx_ring, budget); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8f310e520b06..821987da5698 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -314,7 +314,7 @@ iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx) q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx), - q_vector->rx.current_itr); + q_vector->rx.current_itr >> 1); q_vector->rx.current_itr = q_vector->rx.target_itr; } @@ -340,7 +340,7 @@ iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx) q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx), - q_vector->tx.target_itr); + q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; } diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index fc624b73d05d..2fde9653a608 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -1036,7 +1036,7 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) struct ice_aqc_query_txsched_res_resp *buf; enum ice_status status = 0; __le16 max_sibl; - u8 i; + u16 i; if (hw->layer_info) return status; diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 3ec2ce0725d5..8a6ef3514129 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -466,7 +466,7 @@ static s32 igb_init_mac_params_82575(struct e1000_hw *hw) ? igb_setup_copper_link_82575 : igb_setup_serdes_link_82575; - if (mac->type == e1000_82580) { + if (mac->type == e1000_82580 || mac->type == e1000_i350) { switch (hw->device_id) { /* feature not supported on these id's */ case E1000_DEV_ID_DH89XXCC_SGMII: diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 105b0624081a..ed7e667d7eb2 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -753,7 +753,8 @@ u32 igb_rd32(struct e1000_hw *hw, u32 reg) struct net_device *netdev = igb->netdev; hw->hw_addr = NULL; netdev_err(netdev, "PCIe link lost\n"); - WARN(1, "igb: Failed to read reg 0x%x!\n", reg); + WARN(pci_device_is_present(igb->pdev), + "igb: Failed to read reg 0x%x!\n", reg); } return value; @@ -2064,7 +2065,8 @@ static void igb_check_swap_media(struct igb_adapter *adapter) if ((hw->phy.media_type == e1000_media_type_copper) && (!(connsw & E1000_CONNSW_AUTOSENSE_EN))) { swap_now = true; - } else if (!(connsw & E1000_CONNSW_SERDESD)) { + } else if ((hw->phy.media_type != e1000_media_type_copper) && + !(connsw & E1000_CONNSW_SERDESD)) { /* copper signal takes time to appear */ if (adapter->copper_tries < 4) { adapter->copper_tries++; @@ -2370,7 +2372,7 @@ void igb_reset(struct igb_adapter *adapter) adapter->ei.get_invariants(hw); adapter->flags &= ~IGB_FLAG_MEDIA_RESET; } - if ((mac->type == e1000_82575) && + if ((mac->type == e1000_82575 || mac->type == e1000_i350) && (adapter->flags & IGB_FLAG_MAS_ENABLE)) { igb_enable_mas(adapter); } @@ -5673,8 +5675,8 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, * should have been handled by the upper layers. */ if (tx_ring->launchtime_enable) { - ts = ns_to_timespec64(first->skb->tstamp); - first->skb->tstamp = 0; + ts = ktime_to_timespec64(first->skb->tstamp); + first->skb->tstamp = ktime_set(0, 0); context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32); } else { context_desc->seqnum_seed = 0; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index fd3071f55bd3..c39e921757ba 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -521,6 +521,19 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests failing to enable both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + if (on) { pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS, rq->extts.index); @@ -551,6 +564,10 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp, return 0; case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + if (on) { pin = ptp_find_pin(igb->ptp_clock, PTP_PF_PEROUT, rq->perout.index); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 63b62d74f961..24888676f69b 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -824,8 +824,8 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, * should have been handled by the upper layers. */ if (tx_ring->launchtime_enable) { - ts = ns_to_timespec64(first->skb->tstamp); - first->skb->tstamp = 0; + ts = ktime_to_timespec64(first->skb->tstamp); + first->skb->tstamp = ktime_set(0, 0); context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32); } else { context_desc->launch_time = 0; @@ -4047,7 +4047,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg) hw->hw_addr = NULL; netif_device_detach(netdev); netdev_err(netdev, "PCIe link lost, device now detached\n"); - WARN(1, "igc: Failed to read reg 0x%x!\n", reg); + WARN(pci_device_is_present(igc->pdev), + "igc: Failed to read reg 0x%x!\n", reg); } return value; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 1ce2397306b9..91b3780ddb04 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4310,7 +4310,6 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state)) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); - clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state); if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) continue; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 100ac89b345d..d6feaacfbf89 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -622,8 +622,6 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) if (tx_desc) { ixgbe_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -691,12 +689,8 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, if (xsk_frames) xsk_umem_complete_tx(umem, xsk_frames); - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { - if (tx_ring->next_to_clean == tx_ring->next_to_use) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); - else - xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); - } + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); } diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h index c8425d35c049..e47783ce77e0 100644 --- a/drivers/net/ethernet/marvell/mvneta_bm.h +++ b/drivers/net/ethernet/marvell/mvneta_bm.h @@ -160,16 +160,23 @@ static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv, (bm_pool->id << MVNETA_BM_POOL_ACCESS_OFFS)); } #else -void mvneta_bm_pool_destroy(struct mvneta_bm *priv, - struct mvneta_bm_pool *bm_pool, u8 port_map) {} -void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool, - u8 port_map) {} -int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf) { return 0; } -int mvneta_bm_pool_refill(struct mvneta_bm *priv, - struct mvneta_bm_pool *bm_pool) {return 0; } -struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id, - enum mvneta_bm_type type, u8 port_id, - int pkt_size) { return NULL; } +static inline void mvneta_bm_pool_destroy(struct mvneta_bm *priv, + struct mvneta_bm_pool *bm_pool, + u8 port_map) {} +static inline void mvneta_bm_bufs_free(struct mvneta_bm *priv, + struct mvneta_bm_pool *bm_pool, + u8 port_map) {} +static inline int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf) +{ return 0; } +static inline int mvneta_bm_pool_refill(struct mvneta_bm *priv, + struct mvneta_bm_pool *bm_pool) +{ return 0; } +static inline struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, + u8 pool_id, + enum mvneta_bm_type type, + u8 port_id, + int pkt_size) +{ return NULL; } static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool, @@ -178,7 +185,8 @@ static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv, static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool) { return 0; } -struct mvneta_bm *mvneta_bm_get(struct device_node *node) { return NULL; } -void mvneta_bm_put(struct mvneta_bm *priv) {} +static inline struct mvneta_bm *mvneta_bm_get(struct device_node *node) +{ return NULL; } +static inline void mvneta_bm_put(struct mvneta_bm *priv) {} #endif /* CONFIG_MVNETA_BM */ #endif diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 206dc5dc1df8..5c1f389e3320 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 CGX driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 CGX driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h index fb3ba4968a9b..473d9751601f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 CGX driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 CGX driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index e332e82fc066..413c3f254cf8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 76a4575d18ff..75439fce0505 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 8d6d90fdfb73..5d4df315a0e1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index b2ce957605bb..da649f6a5573 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index c9d60b0554c0..5222e4228905 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 09a8d61f3144..1ea92a2e7cfe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index f920dac74e6c..84a39063a8bb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 - * Marvell OcteonTx2 RVU Admin Function driver +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 RVU Admin Function driver * * Copyright (C) 2018 Marvell International Ltd. * diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index d8313e2ee600..a1202e53710c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1745,6 +1745,7 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, err = mlx4_en_get_flow(dev, cmd, cmd->fs.location); break; case ETHTOOL_GRXCLSRLALL: + cmd->data = MAX_NUM_OF_FS_RULES; while ((!err || err == -ENOENT) && priority < cmd->rule_cnt) { err = mlx4_en_get_flow(dev, cmd, i); if (!err) @@ -1811,6 +1812,7 @@ static int mlx4_en_set_channels(struct net_device *dev, struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_tx_count; int port_up = 0; int xdp_count; int err = 0; @@ -1825,13 +1827,12 @@ static int mlx4_en_set_channels(struct net_device *dev, mutex_lock(&mdev->state_lock); xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0; - if (channel->tx_count * priv->prof->num_up + xdp_count > - priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) { + total_tx_count = channel->tx_count * priv->prof->num_up + xdp_count; + if (total_tx_count > MAX_TX_RINGS) { err = -EINVAL; en_err(priv, "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", - channel->tx_count * priv->prof->num_up + xdp_count, - MAX_TX_RINGS); + total_tx_count, MAX_TX_RINGS); goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 40ec5acf79c0..70fd246840e2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -91,6 +91,7 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_count; int port_up = 0; int err = 0; @@ -104,6 +105,14 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) MLX4_EN_NUM_UP_HIGH; new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up * new_prof.num_up; + total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP]; + if (total_count > MAX_TX_RINGS) { + err = -EINVAL; + en_err(priv, + "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", + total_count, MAX_TX_RINGS); + goto out; + } err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index fce9b3a24347..d44ac666e730 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -514,8 +514,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_rq_desc_sz = dev_cap->max_rq_desc_sz; /* * Subtract 1 from the limit because we need to allocate a - * spare CQE so the HCA HW can tell the difference between an - * empty CQ and a full CQ. + * spare CQE to enable resizing the CQ. */ dev->caps.max_cqes = dev_cap->max_cq_sz - 1; dev->caps.reserved_cqs = dev_cap->reserved_cqs; @@ -4011,6 +4010,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_params_unregister; devlink_params_publish(devlink); + devlink_reload_enable(devlink); pci_save_state(pdev); return 0; @@ -4122,6 +4122,8 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; + devlink_reload_disable(devlink); + if (mlx4_is_slave(dev)) persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 4356f3a58002..1187ef1375e2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -471,12 +471,31 @@ void mlx4_init_quotas(struct mlx4_dev *dev) priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[pf]; } -static int get_max_gauranteed_vfs_counter(struct mlx4_dev *dev) +static int +mlx4_calc_res_counter_guaranteed(struct mlx4_dev *dev, + struct resource_allocator *res_alloc, + int vf) { - /* reduce the sink counter */ - return (dev->caps.max_counters - 1 - - (MLX4_PF_COUNTERS_PER_PORT * MLX4_MAX_PORTS)) - / MLX4_MAX_PORTS; + struct mlx4_active_ports actv_ports; + int ports, counters_guaranteed; + + /* For master, only allocate according to the number of phys ports */ + if (vf == mlx4_master_func_num(dev)) + return MLX4_PF_COUNTERS_PER_PORT * dev->caps.num_ports; + + /* calculate real number of ports for the VF */ + actv_ports = mlx4_get_active_ports(dev, vf); + ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports); + counters_guaranteed = ports * MLX4_VF_COUNTERS_PER_PORT; + + /* If we do not have enough counters for this VF, do not + * allocate any for it. '-1' to reduce the sink counter. + */ + if ((res_alloc->res_reserved + counters_guaranteed) > + (dev->caps.max_counters - 1)) + return 0; + + return counters_guaranteed; } int mlx4_init_resource_tracker(struct mlx4_dev *dev) @@ -484,7 +503,6 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); int i, j; int t; - int max_vfs_guarantee_counter = get_max_gauranteed_vfs_counter(dev); priv->mfunc.master.res_tracker.slave_list = kcalloc(dev->num_slaves, sizeof(struct slave_list), @@ -603,16 +621,8 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev) break; case RES_COUNTER: res_alloc->quota[t] = dev->caps.max_counters; - if (t == mlx4_master_func_num(dev)) - res_alloc->guaranteed[t] = - MLX4_PF_COUNTERS_PER_PORT * - MLX4_MAX_PORTS; - else if (t <= max_vfs_guarantee_counter) - res_alloc->guaranteed[t] = - MLX4_VF_COUNTERS_PER_PORT * - MLX4_MAX_PORTS; - else - res_alloc->guaranteed[t] = 0; + res_alloc->guaranteed[t] = + mlx4_calc_res_counter_guaranteed(dev, res_alloc, t); break; default: break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8d76452cacdc..f1a7bc46f1c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -345,7 +345,7 @@ struct mlx5e_tx_wqe_info { u8 num_wqebbs; u8 num_dma; #ifdef CONFIG_MLX5_EN_TLS - skb_frag_t *resync_dump_frag; + struct page *resync_dump_frag_page; #endif }; @@ -410,6 +410,7 @@ struct mlx5e_txqsq { struct device *pdev; __be32 mkey_be; unsigned long state; + unsigned int hw_mtu; struct hwtstamp_config *tstamp; struct mlx5_clock *clock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c index b3a249b2a482..ac44bbe95c5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c @@ -141,7 +141,7 @@ int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv) "Failed to create hv vhca stats agent, err = %ld\n", PTR_ERR(agent)); - kfree(priv->stats_agent.buf); + kvfree(priv->stats_agent.buf); return IS_ERR_OR_NULL(agent); } @@ -157,5 +157,5 @@ void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv) return; mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent); - kfree(priv->stats_agent.buf); + kvfree(priv->stats_agent.buf); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index f8ee18b4da6f..745ab6cd7c30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -97,15 +97,19 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, if (ret) return ret; - if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET) + if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET) { + ip_rt_put(rt); return -ENETUNREACH; + } #else return -EOPNOTSUPP; #endif ret = get_route_and_out_devs(priv, rt->dst.dev, route_dev, out_dev); - if (ret < 0) + if (ret < 0) { + ip_rt_put(rt); return ret; + } if (!(*out_ttl)) *out_ttl = ip4_dst_hoplimit(&rt->dst); @@ -149,8 +153,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, *out_ttl = ip6_dst_hoplimit(dst); ret = get_route_and_out_devs(priv, dst->dev, route_dev, out_dev); - if (ret < 0) + if (ret < 0) { + dst_release(dst); return ret; + } #else return -EOPNOTSUPP; #endif @@ -233,12 +239,15 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, if (max_encap_size < ipv4_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv4_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -349,12 +358,15 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, if (max_encap_size < ipv6_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv6_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 87be96747902..7c8796d9743f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -15,15 +15,14 @@ #else /* TLS offload requires additional stop_room for: * - a resync SKB. - * kTLS offload requires additional stop_room for: - * - static params WQE, - * - progress params WQE, and - * - resync DUMP per frag. + * kTLS offload requires fixed additional stop_room for: + * - a static params WQE, and a progress params WQE. + * The additional MTU-depending room for the resync DUMP WQEs + * will be calculated and added in runtime. */ #define MLX5E_SQ_TLS_ROOM \ (MLX5_SEND_WQE_MAX_WQEBBS + \ - MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS + \ - MAX_SKB_FRAGS * MLX5E_KTLS_MAX_DUMP_WQEBBS) + MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS) #endif #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start)) @@ -92,7 +91,7 @@ mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, struct mlx5_wq_cyc *wq, /* fill sq frag edge with nops to avoid wqe wrapping two pages */ for (; wi < edge_wi; wi++) { - wi->skb = NULL; + memset(wi, 0, sizeof(*wi)); wi->num_wqebbs = 1; mlx5e_post_nop(wq, sq->sqn, &sq->pc); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index d2ff74d52720..46725cd743a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -38,7 +38,7 @@ static int mlx5e_ktls_add(struct net_device *netdev, struct sock *sk, return -ENOMEM; tx_priv->expected_seq = start_offload_tcp_sn; - tx_priv->crypto_info = crypto_info; + tx_priv->crypto_info = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info; mlx5e_set_ktls_tx_priv_ctx(tls_ctx, tx_priv); /* tc and underlay_qpn values are not in use for tls tis */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h index b7298f9ee3d3..a3efa29a4629 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h @@ -21,7 +21,14 @@ MLX5_ST_SZ_BYTES(tls_progress_params)) #define MLX5E_KTLS_PROGRESS_WQEBBS \ (DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_BB)) -#define MLX5E_KTLS_MAX_DUMP_WQEBBS 2 + +struct mlx5e_dump_wqe { + struct mlx5_wqe_ctrl_seg ctrl; + struct mlx5_wqe_data_seg data; +}; + +#define MLX5E_KTLS_DUMP_WQEBBS \ + (DIV_ROUND_UP(sizeof(struct mlx5e_dump_wqe), MLX5_SEND_WQE_BB)) enum { MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD = 0, @@ -37,7 +44,7 @@ enum { struct mlx5e_ktls_offload_context_tx { struct tls_offload_context_tx *tx_ctx; - struct tls_crypto_info *crypto_info; + struct tls12_crypto_info_aes_gcm_128 crypto_info; u32 expected_seq; u32 tisn; u32 key_id; @@ -86,14 +93,28 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, struct mlx5e_tx_wqe **wqe, u16 *pi); void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq, struct mlx5e_tx_wqe_info *wi, - struct mlx5e_sq_dma *dma); - + u32 *dma_fifo_cc); +static inline u8 +mlx5e_ktls_dumps_num_wqebbs(struct mlx5e_txqsq *sq, unsigned int nfrags, + unsigned int sync_len) +{ + /* Given the MTU and sync_len, calculates an upper bound for the + * number of WQEBBs needed for the TX resync DUMP WQEs of a record. + */ + return MLX5E_KTLS_DUMP_WQEBBS * + (nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu)); +} #else static inline void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv) { } +static inline void +mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq, + struct mlx5e_tx_wqe_info *wi, + u32 *dma_fifo_cc) {} + #endif #endif /* __MLX5E_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index d195366461c9..778dab1af8fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -24,17 +24,12 @@ enum { static void fill_static_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx) { - struct tls_crypto_info *crypto_info = priv_tx->crypto_info; - struct tls12_crypto_info_aes_gcm_128 *info; + struct tls12_crypto_info_aes_gcm_128 *info = &priv_tx->crypto_info; char *initial_rn, *gcm_iv; u16 salt_sz, rec_seq_sz; char *salt, *rec_seq; u8 tls_version; - if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128)) - return; - - info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info; EXTRACT_INFO_FIELDS; gcm_iv = MLX5_ADDR_OF(tls_static_params, ctx, gcm_iv); @@ -108,16 +103,15 @@ build_progress_params(struct mlx5e_tx_wqe *wqe, u16 pc, u32 sqn, } static void tx_fill_wi(struct mlx5e_txqsq *sq, - u16 pi, u8 num_wqebbs, - skb_frag_t *resync_dump_frag, - u32 num_bytes) + u16 pi, u8 num_wqebbs, u32 num_bytes, + struct page *page) { struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi]; - wi->skb = NULL; - wi->num_wqebbs = num_wqebbs; - wi->resync_dump_frag = resync_dump_frag; - wi->num_bytes = num_bytes; + memset(wi, 0, sizeof(*wi)); + wi->num_wqebbs = num_wqebbs; + wi->num_bytes = num_bytes; + wi->resync_dump_frag_page = page; } void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx) @@ -145,7 +139,7 @@ post_static_params(struct mlx5e_txqsq *sq, umr_wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_STATIC_UMR_WQE_SZ, &pi); build_static_params(umr_wqe, sq->pc, sq->sqn, priv_tx, fence); - tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, NULL, 0); + tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, 0, NULL); sq->pc += MLX5E_KTLS_STATIC_WQEBBS; } @@ -159,7 +153,7 @@ post_progress_params(struct mlx5e_txqsq *sq, wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_PROGRESS_WQE_SZ, &pi); build_progress_params(wqe, sq->pc, sq->sqn, priv_tx, fence); - tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, NULL, 0); + tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, 0, NULL); sq->pc += MLX5E_KTLS_PROGRESS_WQEBBS; } @@ -169,6 +163,14 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq, bool skip_static_post, bool fence_first_post) { bool progress_fence = skip_static_post || !fence_first_post; + struct mlx5_wq_cyc *wq = &sq->wq; + u16 contig_wqebbs_room, pi; + + pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); + if (unlikely(contig_wqebbs_room < + MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS)) + mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); if (!skip_static_post) post_static_params(sq, priv_tx, fence_first_post); @@ -180,29 +182,36 @@ struct tx_sync_info { u64 rcd_sn; s32 sync_len; int nr_frags; - skb_frag_t *frags[MAX_SKB_FRAGS]; + skb_frag_t frags[MAX_SKB_FRAGS]; +}; + +enum mlx5e_ktls_sync_retval { + MLX5E_KTLS_SYNC_DONE, + MLX5E_KTLS_SYNC_FAIL, + MLX5E_KTLS_SYNC_SKIP_NO_DATA, }; -static bool tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, - u32 tcp_seq, struct tx_sync_info *info) +static enum mlx5e_ktls_sync_retval +tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, + u32 tcp_seq, struct tx_sync_info *info) { struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx; + enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE; struct tls_record_info *record; int remaining, i = 0; unsigned long flags; - bool ret = true; spin_lock_irqsave(&tx_ctx->lock, flags); record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn); if (unlikely(!record)) { - ret = false; + ret = MLX5E_KTLS_SYNC_FAIL; goto out; } if (unlikely(tcp_seq < tls_record_start_seq(record))) { - if (!tls_record_is_start_marker(record)) - ret = false; + ret = tls_record_is_start_marker(record) ? + MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL; goto out; } @@ -211,13 +220,13 @@ static bool tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, while (remaining > 0) { skb_frag_t *frag = &record->frags[i]; - __skb_frag_ref(frag); + get_page(skb_frag_page(frag)); remaining -= skb_frag_size(frag); - info->frags[i++] = frag; + info->frags[i++] = *frag; } /* reduce the part which will be sent with the original SKB */ if (remaining < 0) - skb_frag_size_add(info->frags[i - 1], remaining); + skb_frag_size_add(&info->frags[i - 1], remaining); info->nr_frags = i; out: spin_unlock_irqrestore(&tx_ctx->lock, flags); @@ -229,17 +238,12 @@ tx_post_resync_params(struct mlx5e_txqsq *sq, struct mlx5e_ktls_offload_context_tx *priv_tx, u64 rcd_sn) { - struct tls_crypto_info *crypto_info = priv_tx->crypto_info; - struct tls12_crypto_info_aes_gcm_128 *info; + struct tls12_crypto_info_aes_gcm_128 *info = &priv_tx->crypto_info; __be64 rn_be = cpu_to_be64(rcd_sn); bool skip_static_post; u16 rec_seq_sz; char *rec_seq; - if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128)) - return; - - info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info; rec_seq = info->rec_seq; rec_seq_sz = sizeof(info->rec_seq); @@ -250,11 +254,6 @@ tx_post_resync_params(struct mlx5e_txqsq *sq, mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, skip_static_post, true); } -struct mlx5e_dump_wqe { - struct mlx5_wqe_ctrl_seg ctrl; - struct mlx5_wqe_data_seg data; -}; - static int tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool first) { @@ -262,7 +261,6 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir struct mlx5_wqe_data_seg *dseg; struct mlx5e_dump_wqe *wqe; dma_addr_t dma_addr = 0; - u8 num_wqebbs; u16 ds_cnt; int fsz; u16 pi; @@ -270,7 +268,6 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi); ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; - num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); cseg = &wqe->ctrl; dseg = &wqe->data; @@ -291,24 +288,27 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir dseg->byte_count = cpu_to_be32(fsz); mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); - tx_fill_wi(sq, pi, num_wqebbs, frag, fsz); - sq->pc += num_wqebbs; - - WARN(num_wqebbs > MLX5E_KTLS_MAX_DUMP_WQEBBS, - "unexpected DUMP num_wqebbs, %d > %d", - num_wqebbs, MLX5E_KTLS_MAX_DUMP_WQEBBS); + tx_fill_wi(sq, pi, MLX5E_KTLS_DUMP_WQEBBS, fsz, skb_frag_page(frag)); + sq->pc += MLX5E_KTLS_DUMP_WQEBBS; return 0; } void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq, struct mlx5e_tx_wqe_info *wi, - struct mlx5e_sq_dma *dma) + u32 *dma_fifo_cc) { - struct mlx5e_sq_stats *stats = sq->stats; + struct mlx5e_sq_stats *stats; + struct mlx5e_sq_dma *dma; + + if (!wi->resync_dump_frag_page) + return; + + dma = mlx5e_dma_get(sq, (*dma_fifo_cc)++); + stats = sq->stats; mlx5e_tx_dma_unmap(sq->pdev, dma); - __skb_frag_unref(wi->resync_dump_frag); + put_page(wi->resync_dump_frag_page); stats->tls_dump_packets++; stats->tls_dump_bytes += wi->num_bytes; } @@ -318,25 +318,31 @@ static void tx_post_fence_nop(struct mlx5e_txqsq *sq) struct mlx5_wq_cyc *wq = &sq->wq; u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); - tx_fill_wi(sq, pi, 1, NULL, 0); + tx_fill_wi(sq, pi, 1, 0, NULL); mlx5e_post_nop_fence(wq, sq->sqn, &sq->pc); } -static struct sk_buff * +static enum mlx5e_ktls_sync_retval mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, struct mlx5e_txqsq *sq, - struct sk_buff *skb, + int datalen, u32 seq) { struct mlx5e_sq_stats *stats = sq->stats; struct mlx5_wq_cyc *wq = &sq->wq; + enum mlx5e_ktls_sync_retval ret; struct tx_sync_info info = {}; u16 contig_wqebbs_room, pi; u8 num_wqebbs; - int i; - - if (!tx_sync_info_get(priv_tx, seq, &info)) { + int i = 0; + + ret = tx_sync_info_get(priv_tx, seq, &info); + if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) { + if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) { + stats->tls_skip_no_sync_data++; + return MLX5E_KTLS_SYNC_SKIP_NO_DATA; + } /* We might get here if a retransmission reaches the driver * after the relevant record is acked. * It should be safe to drop the packet in this case @@ -346,13 +352,8 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, } if (unlikely(info.sync_len < 0)) { - u32 payload; - int headln; - - headln = skb_transport_offset(skb) + tcp_hdrlen(skb); - payload = skb->len - headln; - if (likely(payload <= -info.sync_len)) - return skb; + if (likely(datalen <= -info.sync_len)) + return MLX5E_KTLS_SYNC_DONE; stats->tls_drop_bypass_req++; goto err_out; @@ -360,30 +361,62 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, stats->tls_ooo++; - num_wqebbs = MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS + - (info.nr_frags ? info.nr_frags * MLX5E_KTLS_MAX_DUMP_WQEBBS : 1); + tx_post_resync_params(sq, priv_tx, info.rcd_sn); + + /* If no dump WQE was sent, we need to have a fence NOP WQE before the + * actual data xmit. + */ + if (!info.nr_frags) { + tx_post_fence_nop(sq); + return MLX5E_KTLS_SYNC_DONE; + } + + num_wqebbs = mlx5e_ktls_dumps_num_wqebbs(sq, info.nr_frags, info.sync_len); pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); + if (unlikely(contig_wqebbs_room < num_wqebbs)) mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); tx_post_resync_params(sq, priv_tx, info.rcd_sn); - for (i = 0; i < info.nr_frags; i++) - if (tx_post_resync_dump(sq, info.frags[i], priv_tx->tisn, !i)) - goto err_out; + for (; i < info.nr_frags; i++) { + unsigned int orig_fsz, frag_offset = 0, n = 0; + skb_frag_t *f = &info.frags[i]; - /* If no dump WQE was sent, we need to have a fence NOP WQE before the - * actual data xmit. - */ - if (!info.nr_frags) - tx_post_fence_nop(sq); + orig_fsz = skb_frag_size(f); - return skb; + do { + bool fence = !(i || frag_offset); + unsigned int fsz; + + n++; + fsz = min_t(unsigned int, sq->hw_mtu, orig_fsz - frag_offset); + skb_frag_size_set(f, fsz); + if (tx_post_resync_dump(sq, f, priv_tx->tisn, fence)) { + page_ref_add(skb_frag_page(f), n - 1); + goto err_out; + } + + skb_frag_off_add(f, fsz); + frag_offset += fsz; + } while (frag_offset < orig_fsz); + + page_ref_add(skb_frag_page(f), n - 1); + } + + return MLX5E_KTLS_SYNC_DONE; err_out: - dev_kfree_skb_any(skb); - return NULL; + for (; i < info.nr_frags; i++) + /* The put_page() here undoes the page ref obtained in tx_sync_info_get(). + * Page refs obtained for the DUMP WQEs above (by page_ref_add) will be + * released only upon their completions (or in mlx5e_free_txqsq_descs, + * if channel closes). + */ + put_page(skb_frag_page(&info.frags[i])); + + return MLX5E_KTLS_SYNC_FAIL; } struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, @@ -419,10 +452,15 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, seq = ntohl(tcp_hdr(skb)->seq); if (unlikely(priv_tx->expected_seq != seq)) { - skb = mlx5e_ktls_tx_handle_ooo(priv_tx, sq, skb, seq); - if (unlikely(!skb)) + enum mlx5e_ktls_sync_retval ret = + mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq); + + if (likely(ret == MLX5E_KTLS_SYNC_DONE)) + *wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi); + else if (ret == MLX5E_KTLS_SYNC_FAIL) + goto err_out; + else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */ goto out; - *wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi); } priv_tx->expected_seq = seq + datalen; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index c5a9c20d7f00..95601269fa2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -708,9 +708,9 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings, u32 eth_proto_cap, - u8 connector_type) + u8 connector_type, bool ext) { - if (!connector_type || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { + if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR) | MLX5E_PROT_MASK(MLX5E_10GBASE_SR) | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) @@ -842,9 +842,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = { [MLX5E_PORT_OTHER] = PORT_OTHER, }; -static u8 get_connector_port(u32 eth_proto, u8 connector_type) +static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext) { - if (connector_type && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) + if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) return ptys2connector_type[connector_type]; if (eth_proto & @@ -945,9 +945,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; link_ksettings->base.port = get_connector_port(eth_proto_oper, - connector_type); + connector_type, ext); ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin, - connector_type); + connector_type, ext); get_lp_advertising(mdev, eth_proto_lp, link_ksettings); if (an_status == MLX5_AN_COMPLETE) @@ -1021,7 +1021,7 @@ static bool ext_link_mode_requested(const unsigned long *adver) { #define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT; - __ETHTOOL_DECLARE_LINK_MODE_MASK(modes); + __ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = {0,}; bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size); return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 7569287f8f3c..2a56e66f58d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1128,6 +1128,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->txq_ix = txq_ix; sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; + sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; sq->stop_room = MLX5E_SQ_STOP_ROOM; INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); @@ -1135,10 +1136,14 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); +#ifdef CONFIG_MLX5_EN_TLS if (mlx5_accel_is_tls_device(c->priv->mdev)) { set_bit(MLX5E_SQ_STATE_TLS, &sq->state); - sq->stop_room += MLX5E_SQ_TLS_ROOM; + sq->stop_room += MLX5E_SQ_TLS_ROOM + + mlx5e_ktls_dumps_num_wqebbs(sq, MAX_SKB_FRAGS, + TLS_MAX_PAYLOAD_SIZE); } +#endif param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -1349,9 +1354,13 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) /* last doorbell out, godspeed .. */ if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) { u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + struct mlx5e_tx_wqe_info *wi; struct mlx5e_tx_wqe *nop; - sq->db.wqe_info[pi].skb = NULL; + wi = &sq->db.wqe_info[pi]; + + memset(wi, 0, sizeof(*wi)); + wi->num_wqebbs = 1; nop = mlx5e_post_nop(wq, sq->sqn, &sq->pc); mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nop->ctrl); } @@ -4243,9 +4252,12 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: + return features; case IPPROTO_IPIP: case IPPROTO_IPV6: - return features; + if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP)) + return features; + break; case IPPROTO_UDP: udph = udp_hdr(skb); port = be16_to_cpu(udph->dest); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 95892a3b63a1..cd9bb7c7b341 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -611,8 +611,8 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, mutex_lock(&esw->offloads.encap_tbl_lock); encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); - if (e->compl_result || (encap_connected == neigh_connected && - ether_addr_equal(e->h_dest, ha))) + if (e->compl_result < 0 || (encap_connected == neigh_connected && + ether_addr_equal(e->h_dest, ha))) goto unlock; mlx5e_take_all_encap_flows(e, &flow_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index d6a547238de0..82cffb3a9964 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1386,8 +1386,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return 0; - if (rq->cqd.left) + if (rq->cqd.left) { work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget); + if (rq->cqd.left || work_done >= budget) + goto out; + } cqe = mlx5_cqwq_get_cqe(cqwq); if (!cqe) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 840ec945ccba..bbff8d8ded76 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -35,6 +35,7 @@ #include <linux/udp.h> #include <net/udp.h> #include "en.h" +#include "en/port.h" enum { MLX5E_ST_LINK_STATE, @@ -80,22 +81,12 @@ static int mlx5e_test_link_state(struct mlx5e_priv *priv) static int mlx5e_test_link_speed(struct mlx5e_priv *priv) { - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - u32 eth_proto_oper; - int i; + u32 speed; if (!netif_carrier_ok(priv->netdev)) return 1; - if (mlx5_query_port_ptys(priv->mdev, out, sizeof(out), MLX5_PTYS_EN, 1)) - return 1; - - eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; i++) { - if (eth_proto_oper & MLX5E_PROT_MASK(i)) - return 0; - } - return 1; + return mlx5e_port_linkspeed(priv->mdev, &speed); } struct mlx5ehdr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index ac6fdcda7019..7e6ebd0505cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -52,11 +52,12 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_resync_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_skip_no_sync_data) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_no_sync_data) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_bypass_req) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) }, #endif { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) }, @@ -288,11 +289,12 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_tls_encrypted_bytes += sq_stats->tls_encrypted_bytes; s->tx_tls_ctx += sq_stats->tls_ctx; s->tx_tls_ooo += sq_stats->tls_ooo; + s->tx_tls_dump_bytes += sq_stats->tls_dump_bytes; + s->tx_tls_dump_packets += sq_stats->tls_dump_packets; s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes; + s->tx_tls_skip_no_sync_data += sq_stats->tls_skip_no_sync_data; s->tx_tls_drop_no_sync_data += sq_stats->tls_drop_no_sync_data; s->tx_tls_drop_bypass_req += sq_stats->tls_drop_bypass_req; - s->tx_tls_dump_bytes += sq_stats->tls_dump_bytes; - s->tx_tls_dump_packets += sq_stats->tls_dump_packets; #endif s->tx_cqes += sq_stats->cqes; } @@ -1472,10 +1474,12 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) }, - { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_no_sync_data) }, - { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_bypass_req) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_resync_bytes) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_skip_no_sync_data) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_no_sync_data) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_bypass_req) }, #endif { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 79f261bf86ac..869f3502f631 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -129,11 +129,12 @@ struct mlx5e_sw_stats { u64 tx_tls_encrypted_bytes; u64 tx_tls_ctx; u64 tx_tls_ooo; + u64 tx_tls_dump_packets; + u64 tx_tls_dump_bytes; u64 tx_tls_resync_bytes; + u64 tx_tls_skip_no_sync_data; u64 tx_tls_drop_no_sync_data; u64 tx_tls_drop_bypass_req; - u64 tx_tls_dump_packets; - u64 tx_tls_dump_bytes; #endif u64 rx_xsk_packets; @@ -273,11 +274,12 @@ struct mlx5e_sq_stats { u64 tls_encrypted_bytes; u64 tls_ctx; u64 tls_ooo; + u64 tls_dump_packets; + u64 tls_dump_bytes; u64 tls_resync_bytes; + u64 tls_skip_no_sync_data; u64 tls_drop_no_sync_data; u64 tls_drop_bypass_req; - u64 tls_dump_packets; - u64 tls_dump_bytes; #endif /* less likely accessed in data path */ u64 csum_none; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3e78a727f3e6..f90a9f8e0fc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1278,8 +1278,10 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_eswitch_del_vlan_action(esw, attr); for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) - if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) + if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) { mlx5e_detach_encap(priv, flow, out_index); + kfree(attr->parse_attr->tun_info[out_index]); + } kvfree(attr->parse_attr); if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) @@ -1559,6 +1561,7 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); } + kfree(e->tun_info); kfree(e->encap_header); kfree_rcu(e, rcu); } @@ -2972,6 +2975,13 @@ mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key, return NULL; } +static struct ip_tunnel_info *dup_tun_info(const struct ip_tunnel_info *tun_info) +{ + size_t tun_size = sizeof(*tun_info) + tun_info->options_len; + + return kmemdup(tun_info, tun_size, GFP_KERNEL); +} + static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct net_device *mirred_dev, @@ -3028,13 +3038,15 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, refcount_set(&e->refcnt, 1); init_completion(&e->res_ready); + tun_info = dup_tun_info(tun_info); + if (!tun_info) { + err = -ENOMEM; + goto out_err_init; + } e->tun_info = tun_info; err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack); - if (err) { - kfree(e); - e = NULL; - goto out_err; - } + if (err) + goto out_err_init; INIT_LIST_HEAD(&e->flows); hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); @@ -3075,6 +3087,12 @@ out_err: if (e) mlx5e_encap_put(priv, e); return err; + +out_err_init: + mutex_unlock(&esw->offloads.encap_tbl_lock); + kfree(tun_info); + kfree(e); + return err; } static int parse_tc_vlan_action(struct mlx5e_priv *priv, @@ -3160,7 +3178,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr, u32 *action) { - int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev); + int nest_level = attr->parse_attr->filter_dev->lower_level; struct flow_action_entry vlan_act = { .id = FLOW_ACTION_VLAN_POP, }; @@ -3250,7 +3268,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - if (netdev_port_same_parent_id(priv->netdev, out_dev)) { + if (encap) { + parse_attr->mirred_ifindex[attr->out_count] = + out_dev->ifindex; + parse_attr->tun_info[attr->out_count] = dup_tun_info(info); + if (!parse_attr->tun_info[attr->out_count]) + return -ENOMEM; + encap = false; + attr->dests[attr->out_count].flags |= + MLX5_ESW_DEST_ENCAP; + attr->out_count++; + /* attr->dests[].rep is resolved when we + * handle encap + */ + } else if (netdev_port_same_parent_id(priv->netdev, out_dev)) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); struct net_device *uplink_upper; @@ -3292,17 +3323,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, attr->dests[attr->out_count].rep = rpriv->rep; attr->dests[attr->out_count].mdev = out_priv->mdev; attr->out_count++; - } else if (encap) { - parse_attr->mirred_ifindex[attr->out_count] = - out_dev->ifindex; - parse_attr->tun_info[attr->out_count] = info; - encap = false; - attr->dests[attr->out_count].flags |= - MLX5_ESW_DEST_ENCAP; - attr->out_count++; - /* attr->dests[].rep is resolved when we - * handle encap - */ } else if (parse_attr->filter_dev != priv->netdev) { /* All mlx5 devices are called to configure * high level device filters. Therefore, the @@ -3980,9 +4000,8 @@ int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, struct tc_cls_matchall_offload *ma) { struct netlink_ext_ack *extack = ma->common.extack; - int prio = TC_H_MAJ(ma->common.prio) >> 16; - if (prio != 1) { + if (ma->common.prio != 1) { NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index d3a67a9b4eba..67dc4f0921b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -403,7 +403,10 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq, struct mlx5_err_cqe *err_cqe) { - u32 ci = mlx5_cqwq_get_ci(&sq->cq.wq); + struct mlx5_cqwq *wq = &sq->cq.wq; + u32 ci; + + ci = mlx5_cqwq_ctr2ix(wq, wq->cc - 1); netdev_err(sq->channel->netdev, "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n", @@ -479,14 +482,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) skb = wi->skb; if (unlikely(!skb)) { -#ifdef CONFIG_MLX5_EN_TLS - if (wi->resync_dump_frag) { - struct mlx5e_sq_dma *dma = - mlx5e_dma_get(sq, dma_fifo_cc++); - - mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, dma); - } -#endif + mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc); sqcc += wi->num_wqebbs; continue; } @@ -542,29 +538,38 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq) { struct mlx5e_tx_wqe_info *wi; struct sk_buff *skb; + u32 dma_fifo_cc; + u16 sqcc; u16 ci; int i; - while (sq->cc != sq->pc) { - ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc); + sqcc = sq->cc; + dma_fifo_cc = sq->dma_fifo_cc; + + while (sqcc != sq->pc) { + ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); wi = &sq->db.wqe_info[ci]; skb = wi->skb; - if (!skb) { /* nop */ - sq->cc++; + if (!skb) { + mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc); + sqcc += wi->num_wqebbs; continue; } for (i = 0; i < wi->num_dma; i++) { struct mlx5e_sq_dma *dma = - mlx5e_dma_get(sq, sq->dma_fifo_cc++); + mlx5e_dma_get(sq, dma_fifo_cc++); mlx5e_tx_dma_unmap(sq->pdev, dma); } dev_kfree_skb_any(skb); - sq->cc += wi->num_wqebbs; + sqcc += wi->num_wqebbs; } + + sq->dma_fifo_cc = dma_fifo_cc; + sq->cc = sqcc; } #ifdef CONFIG_MLX5_CORE_IPOIB diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 30aae76b6a1d..60fddf8afc99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2117,7 +2117,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, unlock: mutex_unlock(&esw->state_lock); - return 0; + return err; } int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 00d71db15f22..9004a07e457a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -285,7 +285,6 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, mlx5_eswitch_set_rule_source_port(esw, spec, attr); - spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; if (attr->outer_match_level != MLX5_MATCH_NONE) spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; @@ -1080,7 +1079,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) MLX5_CAP_GEN(dev, max_flow_counter_15_0); fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size); - esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(2^%d))\n", + esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(%d))\n", MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size), max_flow_counter, ESW_OFFLOADS_NUM_GROUPS, fdb_max); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 1d55a324a17e..366bda1bb1c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -177,22 +177,33 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src, memset(&src->vlan[1], 0, sizeof(src->vlan[1])); } +static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw, + const struct mlx5_flow_spec *spec) +{ + u32 port_mask, port_value; + + if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source)) + return spec->flow_context.flow_source == + MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + + port_mask = MLX5_GET(fte_match_param, spec->match_criteria, + misc_parameters.source_port); + port_value = MLX5_GET(fte_match_param, spec->match_value, + misc_parameters.source_port); + return (port_mask & port_value & 0xffff) == MLX5_VPORT_UPLINK; +} + bool mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, struct mlx5_flow_act *flow_act, struct mlx5_flow_spec *spec) { - u32 port_mask = MLX5_GET(fte_match_param, spec->match_criteria, - misc_parameters.source_port); - u32 port_value = MLX5_GET(fte_match_param, spec->match_value, - misc_parameters.source_port); - if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table)) return false; /* push vlan on RX */ return (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) && - ((port_mask & port_value) == MLX5_VPORT_UPLINK); + mlx5_eswitch_offload_is_uplink_port(esw, spec); } struct mlx5_flow_handle * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 4c50efe4e7f1..61021133029e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -464,8 +464,10 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) } err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); - if (err) + if (err) { + kvfree(in); goto err_cqwq; + } cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 579c306caa7b..3c816e81f8d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -507,7 +507,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(dest_format_struct, in_dests, destination_eswitch_owner_vhca_id, dst->dest_attr.vport.vhca_id); - if (extended_dest) { + if (extended_dest && + dst->dest_attr.vport.pkt_reformat) { MLX5_SET(dest_format_struct, in_dests, packet_reformat, !!(dst->dest_attr.vport.flags & diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3bbb49354829..791e14ac26f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -579,7 +579,7 @@ static void del_sw_flow_group(struct fs_node *node) rhashtable_destroy(&fg->ftes_hash); ida_destroy(&fg->fte_allocator); - if (ft->autogroup.active) + if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size) ft->autogroup.num_groups--; err = rhltable_remove(&ft->fgs_hash, &fg->hash, @@ -1126,6 +1126,8 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, ft->autogroup.active = true; ft->autogroup.required_groups = max_num_groups; + /* We save place for flow groups in addition to max types */ + ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1); return ft; } @@ -1328,8 +1330,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft return ERR_PTR(-ENOENT); if (ft->autogroup.num_groups < ft->autogroup.required_groups) - /* We save place for flow groups in addition to max types */ - group_size = ft->max_fte / (ft->autogroup.required_groups + 1); + group_size = ft->autogroup.group_size; /* ft->max_fte == ft->autogroup.max_types */ if (group_size == 0) @@ -1356,7 +1357,8 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft if (IS_ERR(fg)) goto out; - ft->autogroup.num_groups++; + if (group_size == ft->autogroup.group_size) + ft->autogroup.num_groups++; out: return fg; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 00717eba2256..c2621b911563 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -162,6 +162,7 @@ struct mlx5_flow_table { struct { bool active; unsigned int required_groups; + unsigned int group_size; unsigned int num_groups; } autogroup; /* Protect fwd_rules */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index d685122d9ff7..c07f3154437c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -572,7 +572,7 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, return -ENOMEM; err = mlx5_crdump_collect(dev, cr_data); if (err) - return err; + goto free_data; if (priv_ctx) { struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 0059b290e095..43f97601b500 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -236,6 +236,19 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp, if (!MLX5_PPS_CAP(mdev)) return -EOPNOTSUPP; + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests to enable time stamping on both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + if (rq->extts.index >= clock->ptp_info.n_pins) return -EINVAL; @@ -290,6 +303,10 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, if (!MLX5_PPS_CAP(mdev)) return -EOPNOTSUPP; + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + if (rq->perout.index >= clock->ptp_info.n_pins) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e47dd7c1b909..50ab88d80033 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1566,6 +1566,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF}, /* ConnectX-6 VF */ { PCI_VDEVICE(MELLANOX, 0x101d) }, /* ConnectX-6 Dx */ { PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */ + { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index b74b7d0f6590..004c56c2fc0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -1577,6 +1577,7 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action) break; case DR_ACTION_TYP_MODIFY_HDR: mlx5dr_icm_free_chunk(action->rewrite.chunk); + kfree(action->rewrite.data); refcount_dec(&action->rewrite.dmn->refcount); break; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index e8b656075c6f..bd1699e62142 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -595,6 +595,18 @@ static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule, } } +static u16 dr_get_bits_per_mask(u16 byte_mask) +{ + u16 bits = 0; + + while (byte_mask) { + byte_mask = byte_mask & (byte_mask - 1); + bits++; + } + + return bits; +} + static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, struct mlx5dr_domain *dmn, struct mlx5dr_domain_rx_tx *nic_dmn) @@ -607,6 +619,9 @@ static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, if (!ctrl->may_grow) return false; + if (dr_get_bits_per_mask(htbl->byte_mask) * BITS_PER_BYTE <= htbl->chunk_size) + return false; + if (ctrl->num_of_collisions >= ctrl->increase_threshold && (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold) return true; @@ -1096,6 +1111,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, if (htbl) mlx5dr_htbl_put(htbl); + kfree(hw_ste_arr); + return 0; free_ste: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 5df8436b2ae3..51803eef13dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -700,6 +700,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, unsigned int irqn; void *cqc, *in; __be64 *pas; + int vector; u32 i; cq = kzalloc(sizeof(*cq), GFP_KERNEL); @@ -728,7 +729,8 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + vector = smp_processor_id() % mlx5_comp_vectors_count(mdev); + err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); if (err) { kvfree(in); goto err_cqwq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 4efe1b0be4a8..3cbf74b44d1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -560,18 +560,6 @@ bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste) return !refcount_read(&ste->refcount); } -static u16 get_bits_per_mask(u16 byte_mask) -{ - u16 bits = 0; - - while (byte_mask) { - byte_mask = byte_mask & (byte_mask - 1); - bits++; - } - - return bits; -} - /* Init one ste as a pattern for ste data array */ void mlx5dr_ste_set_formatted_ste(u16 gvmi, struct mlx5dr_domain_rx_tx *nic_dmn, @@ -620,20 +608,12 @@ int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher, struct mlx5dr_ste_htbl *next_htbl; if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) { - u32 bits_in_mask; u8 next_lu_type; u16 byte_mask; next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type); byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask); - /* Don't allocate table more than required, - * the size of the table defined via the byte_mask, so no need - * to allocate more than that. - */ - bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE; - log_table_size = min(log_table_size, bits_in_mask); - next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, log_table_size, next_lu_type, @@ -671,7 +651,7 @@ static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl) htbl->ctrl.may_grow = true; - if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1) + if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask) htbl->ctrl.may_grow = false; /* Threshold is 50%, one is added to table of size 1 */ diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 67990406cba2..29e95d0a6ad1 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -66,6 +66,8 @@ retry: return err; if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) { + fsm_state_err = min_t(enum mlxfw_fsm_state_err, + fsm_state_err, MLXFW_FSM_STATE_ERR_MAX); pr_err("Firmware flash failed: %s\n", mlxfw_fsm_state_err_str[fsm_state_err]); NL_SET_ERR_MSG_MOD(extack, "Firmware flash failed"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 14dcc786926d..0a0884d86d44 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1186,9 +1186,12 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_thermal_init; - if (mlxsw_driver->params_register && !reload) + if (mlxsw_driver->params_register) devlink_params_publish(devlink); + if (!reload) + devlink_reload_enable(devlink); + return 0; err_thermal_init: @@ -1249,6 +1252,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); + if (!reload) + devlink_reload_disable(devlink); if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the @@ -1259,7 +1264,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, return; } - if (mlxsw_core->driver->params_unregister && !reload) + if (mlxsw_core->driver->params_unregister) devlink_params_unpublish(devlink); mlxsw_thermal_fini(mlxsw_core->thermal); mlxsw_hwmon_fini(mlxsw_core->hwmon); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a330b369e899..39d600c8b92d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -994,7 +994,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) if (d) return l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else - return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN; + return RT_TABLE_MAIN; } static struct mlxsw_sp_rif * @@ -1598,27 +1598,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_ipip_entry *ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); - enum mlxsw_sp_l3proto ul_proto; - union mlxsw_sp_l3addr saddr; - u32 ul_tb_id; if (!ipip_entry) return 0; - /* For flat configuration cases, moving overlay to a different VRF might - * cause local address conflict, and the conflicting tunnels need to be - * demoted. - */ - ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); - ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; - saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); - if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto, - saddr, ul_tb_id, - ipip_entry)) { - mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); - return 0; - } - return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, true, false, false, extack); } diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index 57b26c2acf87..e8fe9a90fe4f 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -429,6 +429,10 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, int pulse_width = 0; int perout_bit = 0; + /* Reject requests with unsupported flags */ + if (perout->flags) + return -EOPNOTSUPP; + if (!on) { lan743x_ptp_perout_off(adapter); return 0; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 4d1bce4389c7..672ea1342add 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -261,8 +261,15 @@ static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid, port->pvid = vid; /* Untagged egress vlan clasification */ - if (untagged) + if (untagged && port->vid != vid) { + if (port->vid) { + dev_err(ocelot->dev, + "Port already has a native VLAN: %d\n", + port->vid); + return -EBUSY; + } port->vid = vid; + } ocelot_vlan_port_apply(ocelot, port); @@ -934,7 +941,7 @@ end: static int ocelot_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { - return ocelot_vlan_vid_add(dev, vid, false, true); + return ocelot_vlan_vid_add(dev, vid, false, false); } static int ocelot_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, @@ -1673,9 +1680,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev, struct ocelot_port *ocelot_port = netdev_priv(dev); int err = 0; - if (!ocelot_netdevice_dev_check(dev)) - return 0; - switch (event) { case NETDEV_CHANGEUPPER: if (netif_is_bridge_master(info->upper_dev)) { @@ -1712,12 +1716,16 @@ static int ocelot_netdevice_event(struct notifier_block *unused, struct net_device *dev = netdev_notifier_info_to_dev(ptr); int ret = 0; + if (!ocelot_netdevice_dev_check(dev)) + return 0; + if (event == NETDEV_PRECHANGEUPPER && netif_is_lag_master(info->upper_dev)) { struct netdev_lag_upper_info *lag_upper_info = info->upper_info; struct netlink_ext_ack *extack; - if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { + if (lag_upper_info && + lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { extack = netdev_notifier_info_to_extack(&info->info); NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type"); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index e40773c01a44..06ac806052bc 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -523,7 +523,7 @@ void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset); #define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri)) #define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0) -void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 mask, +void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, u32 offset); #define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) #define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi)) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 1eef446036d6..79d72c88bbef 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -299,22 +299,6 @@ static void nfp_repr_clean(struct nfp_repr *repr) nfp_port_free(repr->port); } -static struct lock_class_key nfp_repr_netdev_xmit_lock_key; -static struct lock_class_key nfp_repr_netdev_addr_lock_key; - -static void nfp_repr_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &nfp_repr_netdev_xmit_lock_key); -} - -static void nfp_repr_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &nfp_repr_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, nfp_repr_set_lockdep_class_one, NULL); -} - int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, u32 cmsg_port_id, struct nfp_port *port, struct net_device *pf_netdev) @@ -324,8 +308,6 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, u32 repr_cap = nn->tlv_caps.repr_cap; int err; - nfp_repr_set_lockdep_class(netdev); - repr->port = port; repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL); if (!repr->dst) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 72107a0627a9..20faa8d24c9f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ +#include <linux/printk.h> +#include <linux/dynamic_debug.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 15e432386b35..aab311413412 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ +#include <linux/printk.h> +#include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/utsname.h> diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 2ce70097d018..38f7f40b3a4d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -67,10 +67,9 @@ #define QED_ROCE_QPS (8192) #define QED_ROCE_DPIS (8) #define QED_RDMA_SRQS QED_ROCE_QPS -#define QED_NVM_CFG_SET_FLAGS 0xE -#define QED_NVM_CFG_SET_PF_FLAGS 0x1E #define QED_NVM_CFG_GET_FLAGS 0xA #define QED_NVM_CFG_GET_PF_FLAGS 0x1A +#define QED_NVM_CFG_MAX_ATTRS 50 static char version[] = "QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n"; @@ -2255,6 +2254,7 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); u8 entity_id, len, buf[32]; + bool need_nvm_init = true; struct qed_ptt *ptt; u16 cfg_id, count; int rc = 0, i; @@ -2271,8 +2271,10 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) DP_VERBOSE(cdev, NETIF_MSG_DRV, "Read config ids: num_attrs = %0d\n", count); - /* NVM CFG ID attributes */ - for (i = 0; i < count; i++) { + /* NVM CFG ID attributes. Start loop index from 1 to avoid additional + * arithmetic operations in the implementation. + */ + for (i = 1; i <= count; i++) { cfg_id = *((u16 *)*data); *data += 2; entity_id = **data; @@ -2282,8 +2284,21 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) memcpy(buf, *data, len); *data += len; - flags = entity_id ? QED_NVM_CFG_SET_PF_FLAGS : - QED_NVM_CFG_SET_FLAGS; + flags = 0; + if (need_nvm_init) { + flags |= QED_NVM_CFG_OPTION_INIT; + need_nvm_init = false; + } + + /* Commit to flash and free the resources */ + if (!(i % QED_NVM_CFG_MAX_ATTRS) || i == count) { + flags |= QED_NVM_CFG_OPTION_COMMIT | + QED_NVM_CFG_OPTION_FREE; + need_nvm_init = true; + } + + if (entity_id) + flags |= QED_NVM_CFG_OPTION_ENTITY_SEL; DP_VERBOSE(cdev, NETIF_MSG_DRV, "cfg_id = %d entity = %d len = %d\n", cfg_id, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 78f77b712b10..dcb5c917f373 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -2005,7 +2005,7 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn, (qed_iov_validate_active_txq(p_hwfn, vf))) { vf->b_malicious = true; DP_NOTICE(p_hwfn, - "VF [%02x] - considered malicious; Unable to stop RX/TX queuess\n", + "VF [%02x] - considered malicious; Unable to stop RX/TX queues\n", vf->abs_vf_id); status = PFVF_STATUS_MALICIOUS; goto out; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 8d1c208f778f..a220cc7c947a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1208,8 +1208,16 @@ enum qede_remove_mode { static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) { struct net_device *ndev = pci_get_drvdata(pdev); - struct qede_dev *edev = netdev_priv(ndev); - struct qed_dev *cdev = edev->cdev; + struct qede_dev *edev; + struct qed_dev *cdev; + + if (!ndev) { + dev_info(&pdev->dev, "Device has already been removed\n"); + return; + } + + edev = netdev_priv(ndev); + cdev = edev->cdev; DP_INFO(edev, "Starting qede_remove\n"); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 5ecf61df78bd..baac016f3ec0 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -363,7 +363,7 @@ qcaspi_receive(struct qcaspi *qca) netdev_dbg(net_dev, "qcaspi_receive: SPI_REG_RDBUF_BYTE_AVA: Value: %08x\n", available); - if (available > QCASPI_HW_BUF_LEN) { + if (available > QCASPI_HW_BUF_LEN + QCASPI_HW_PKT_LEN) { /* This could only happen by interferences on the SPI line. * So retry later ... */ @@ -496,7 +496,6 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event) u16 signature = 0; u16 spi_config; u16 wrbuf_space = 0; - static u16 reset_count; if (event == QCASPI_EVENT_CPUON) { /* Read signature twice, if not valid @@ -549,13 +548,13 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event) qca->sync = QCASPI_SYNC_RESET; qca->stats.trig_reset++; - reset_count = 0; + qca->reset_count = 0; break; case QCASPI_SYNC_RESET: - reset_count++; + qca->reset_count++; netdev_dbg(qca->net_dev, "sync: waiting for CPU on, count %u.\n", - reset_count); - if (reset_count >= QCASPI_RESET_TIMEOUT) { + qca->reset_count); + if (qca->reset_count >= QCASPI_RESET_TIMEOUT) { /* reset did not seem to take place, try again */ qca->sync = QCASPI_SYNC_UNKNOWN; qca->stats.reset_timeout++; diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index eb9af45fcc5e..d13a67e20d65 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -94,6 +94,7 @@ struct qcaspi { unsigned int intr_req; unsigned int intr_svc; + u16 reset_count; #ifdef CONFIG_DEBUG_FS struct dentry *device_root; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 9c54b715228e..06de59521fc4 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -57,10 +57,10 @@ static int rmnet_unregister_real_device(struct net_device *real_dev, if (port->nr_rmnet_devs) return -EINVAL; - kfree(port); - netdev_rx_handler_unregister(real_dev); + kfree(port); + /* release reference on real_dev */ dev_put(real_dev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 350b0d949611..c33c438850cc 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -916,6 +916,9 @@ static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value) static int r8168g_mdio_read(struct rtl8169_private *tp, int reg) { + if (reg == 0x1f) + return tp->ocp_base == OCP_STD_PHY_BASE ? 0 : tp->ocp_base >> 4; + if (tp->ocp_base != OCP_STD_PHY_BASE) reg -= 0x10; @@ -1029,6 +1032,10 @@ static int r8168dp_2_mdio_read(struct rtl8169_private *tp, int reg) { int value; + /* Work around issue with chip reporting wrong PHY ID */ + if (reg == MII_PHYSID2) + return 0xc912; + r8168dp_2_mdio_start(tp); value = r8169_mdio_read(tp, reg); @@ -7172,8 +7179,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1; } - /* RTL8168e-vl has a HW issue with TSO */ - if (tp->mac_version == RTL_GIGA_MAC_VER_34) { + /* RTL8168e-vl and one RTL8168c variant are known to have a + * HW issue with TSO. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_34 || + tp->mac_version == RTL_GIGA_MAC_VER_22) { dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index a9c89d5d8898..9f88b5db4f89 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -955,6 +955,8 @@ enum RAVB_QUEUE { #define NUM_RX_QUEUE 2 #define NUM_TX_QUEUE 2 +#define RX_BUF_SZ (2048 - ETH_FCS_LEN + sizeof(__sum16)) + /* TX descriptors per packet */ #define NUM_TX_DESC_GEN2 2 #define NUM_TX_DESC_GEN3 1 @@ -1018,7 +1020,6 @@ struct ravb_private { u32 dirty_rx[NUM_RX_QUEUE]; /* Producer ring indices */ u32 cur_tx[NUM_TX_QUEUE]; u32 dirty_tx[NUM_TX_QUEUE]; - u32 rx_buf_sz; /* Based on MTU+slack. */ struct napi_struct napi[NUM_RX_QUEUE]; struct work_struct work; /* MII transceiver section. */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index de9aa8c47f1c..3f165c137236 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -230,7 +230,7 @@ static void ravb_ring_free(struct net_device *ndev, int q) le32_to_cpu(desc->dptr))) dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - priv->rx_buf_sz, + RX_BUF_SZ, DMA_FROM_DEVICE); } ring_size = sizeof(struct ravb_ex_rx_desc) * @@ -293,9 +293,9 @@ static void ravb_ring_format(struct net_device *ndev, int q) for (i = 0; i < priv->num_rx_ring[q]; i++) { /* RX descriptor */ rx_desc = &priv->rx_ring[q][i]; - rx_desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); + rx_desc->ds_cc = cpu_to_le16(RX_BUF_SZ); dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, - priv->rx_buf_sz, + RX_BUF_SZ, DMA_FROM_DEVICE); /* We just set the data size to 0 for a failed mapping which * should prevent DMA from happening... @@ -342,9 +342,6 @@ static int ravb_ring_init(struct net_device *ndev, int q) int ring_size; int i; - priv->rx_buf_sz = (ndev->mtu <= 1492 ? PKT_BUF_SZ : ndev->mtu) + - ETH_HLEN + VLAN_HLEN + sizeof(__sum16); - /* Allocate RX and TX skb rings */ priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q], sizeof(*priv->rx_skb[q]), GFP_KERNEL); @@ -354,7 +351,7 @@ static int ravb_ring_init(struct net_device *ndev, int q) goto error; for (i = 0; i < priv->num_rx_ring[q]; i++) { - skb = netdev_alloc_skb(ndev, priv->rx_buf_sz + RAVB_ALIGN - 1); + skb = netdev_alloc_skb(ndev, RX_BUF_SZ + RAVB_ALIGN - 1); if (!skb) goto error; ravb_set_buffer_align(skb); @@ -584,7 +581,7 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) skb = priv->rx_skb[q][entry]; priv->rx_skb[q][entry] = NULL; dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - priv->rx_buf_sz, + RX_BUF_SZ, DMA_FROM_DEVICE); get_ts &= (q == RAVB_NC) ? RAVB_RXTSTAMP_TYPE_V2_L2_EVENT : @@ -617,11 +614,11 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; desc = &priv->rx_ring[q][entry]; - desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); + desc->ds_cc = cpu_to_le16(RX_BUF_SZ); if (!priv->rx_skb[q][entry]) { skb = netdev_alloc_skb(ndev, - priv->rx_buf_sz + + RX_BUF_SZ + RAVB_ALIGN - 1); if (!skb) break; /* Better luck next round. */ @@ -1801,10 +1798,15 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) static int ravb_change_mtu(struct net_device *ndev, int new_mtu) { - if (netif_running(ndev)) - return -EBUSY; + struct ravb_private *priv = netdev_priv(ndev); ndev->mtu = new_mtu; + + if (netif_running(ndev)) { + synchronize_irq(priv->emac_irq); + ravb_emac_init(ndev); + } + netdev_update_features(ndev); return 0; diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index 9a42580693cb..6984bd5b7da9 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -182,6 +182,13 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp, struct net_device *ndev = priv->ndev; unsigned long flags; + /* Reject requests with unsupported flags */ + if (req->flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + if (req->index) return -EINVAL; @@ -211,6 +218,10 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp, unsigned long flags; int error = 0; + /* Reject requests with unsupported flags */ + if (req->flags) + return -EOPNOTSUPP; + if (req->index) return -EINVAL; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 02ed6d1b716c..af15a737c675 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1531,7 +1531,8 @@ void efx_ptp_remove(struct efx_nic *efx) (void)efx_ptp_disable(efx); cancel_work_sync(&efx->ptp_data->work); - cancel_work_sync(&efx->ptp_data->pps_work); + if (efx->ptp_data->pps_workwq) + cancel_work_sync(&efx->ptp_data->pps_work); skb_queue_purge(&efx->ptp_data->rxq); skb_queue_purge(&efx->ptp_data->txq); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index ddcc191febdb..6e47be63a43c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1226,7 +1226,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) dwmac_mux: sun8i_dwmac_unset_syscon(gmac); dwmac_exit: - sun8i_dwmac_exit(pdev, plat_dat->bsp_priv); + stmmac_pltfr_remove(pdev); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 5a7b0aca1d31..66e60c7e9850 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -432,7 +432,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw, * bits used depends on the hardware configuration * selected at core configuration time. */ - int bit_nr = bitrev32(~crc32_le(~0, ha->addr, + u32 bit_nr = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)) >> (32 - mcbitslog2); /* The most significant bit determines the register to * use (H/L) while the other 5 bits determine the bit diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index 775db776b3cc..23fecf68f781 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ // Copyright (c) 2017 Synopsys, Inc. and/or its affiliates. // stmmac Support for 5.xx Ethernet QoS cores diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 99037386080a..9d08a934fe4f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ /* * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates. * stmmac XGMAC definitions. diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 5031398e612c..070bd7d1ae4c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -224,6 +224,7 @@ static void dwxgmac2_config_cbs(struct mac_device_info *hw, writel(low_credit, ioaddr + XGMAC_MTL_TCx_LOCREDIT(queue)); value = readl(ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); + value &= ~XGMAC_TSA; value |= XGMAC_CC | XGMAC_CBS; writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); } @@ -463,7 +464,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw, value |= XGMAC_FILTER_HMC; netdev_for_each_mc_addr(ha, dev) { - int nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >> + u32 nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >> (32 - mcbitslog2)); mc_filter[nr >> 5] |= (1 << (nr & 0x1F)); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c index ae48154f933c..bd5838ce1e8a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c @@ -288,7 +288,8 @@ static int dwxgmac2_get_rx_hash(struct dma_desc *p, u32 *hash, static int dwxgmac2_get_rx_header_len(struct dma_desc *p, unsigned int *len) { - *len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL; + if (le32_to_cpu(p->des3) & XGMAC_RDES3_L34T) + *len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL; return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 965cbe3e6f51..f70ca5300b82 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -369,7 +369,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13; dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12; dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11; - dma_cap->av &= !(hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10; + dma_cap->av &= !((hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10); dma_cap->arpoffsel = (hw_cap & XGMAC_HWFEAT_ARPOFFSEL) >> 9; dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8; dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7; @@ -470,6 +470,7 @@ static void dwxgmac2_enable_tso(void __iomem *ioaddr, bool en, u32 chan) static void dwxgmac2_qmode(void __iomem *ioaddr, u32 channel, u8 qmode) { u32 value = readl(ioaddr + XGMAC_MTL_TXQ_OPMODE(channel)); + u32 flow = readl(ioaddr + XGMAC_RX_FLOW_CTRL); value &= ~XGMAC_TXQEN; if (qmode != MTL_QUEUE_AVB) { @@ -477,6 +478,7 @@ static void dwxgmac2_qmode(void __iomem *ioaddr, u32 channel, u8 qmode) writel(0, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(channel)); } else { value |= 0x1 << XGMAC_TXQEN_SHIFT; + writel(flow & (~XGMAC_RFE), ioaddr + XGMAC_RX_FLOW_CTRL); } writel(value, ioaddr + XGMAC_MTL_TXQ_OPMODE(channel)); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index ddb851d99618..9010d881b12e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ // Copyright (c) 2018 Synopsys, Inc. and/or its affiliates. // stmmac HW Interface Callbacks diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index a223584f5f9a..252cf48c5816 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -176,6 +176,7 @@ #define MMC_XGMAC_RX_PKT_SMD_ERR 0x22c #define MMC_XGMAC_RX_PKT_ASSEMBLY_OK 0x230 #define MMC_XGMAC_RX_FPE_FRAG 0x234 +#define MMC_XGMAC_RX_IPC_INTR_MASK 0x25c static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) { @@ -333,8 +334,9 @@ static void dwxgmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr) { - writel(MMC_DEFAULT_MASK, mmcaddr + MMC_RX_INTR_MASK); - writel(MMC_DEFAULT_MASK, mmcaddr + MMC_TX_INTR_MASK); + writel(0x0, mmcaddr + MMC_RX_INTR_MASK); + writel(0x0, mmcaddr + MMC_TX_INTR_MASK); + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_IPC_INTR_MASK); } static void dwxgmac_read_mmc_reg(void __iomem *addr, u32 reg, u32 *dest) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3dfd04e0506a..f826365c979d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2995,6 +2995,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } else { stmmac_set_desc_addr(priv, first, des); tmp_pay_len = pay_len; + des += proto_hdr_len; + pay_len = 0; } stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue); @@ -3022,6 +3024,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* Only the last descriptor gets to point to the skb. */ tx_q->tx_skbuff[tx_q->cur_tx] = skb; + /* Manage tx mitigation */ + tx_q->tx_count_frames += nfrags + 1; + if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && + !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en)) { + stmmac_tx_timer_arm(priv, queue); + } else { + desc = &tx_q->dma_tx[tx_q->cur_tx]; + tx_q->tx_count_frames = 0; + stmmac_set_tx_ic(priv, desc); + priv->xstats.tx_set_ic_bit++; + } + /* We've used all descriptors we need for this skb, however, * advance cur_tx so that it references a fresh descriptor. * ndo_start_xmit will fill this descriptor the next time it's @@ -3039,19 +3054,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_tso_frames++; priv->xstats.tx_tso_nfrags += nfrags; - /* Manage tx mitigation */ - tx_q->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && - !(priv->synopsys_id >= DWMAC_CORE_4_00 && - (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - priv->hwts_tx_en)) { - stmmac_tx_timer_arm(priv, queue); - } else { - tx_q->tx_count_frames = 0; - stmmac_set_tx_ic(priv, desc); - priv->xstats.tx_set_ic_bit++; - } - if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -3223,6 +3225,27 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Only the last descriptor gets to point to the skb. */ tx_q->tx_skbuff[entry] = skb; + /* According to the coalesce parameter the IC bit for the latest + * segment is reset and the timer re-started to clean the tx status. + * This approach takes care about the fragments: desc is the first + * element in case of no SG. + */ + tx_q->tx_count_frames += nfrags + 1; + if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && + !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en)) { + stmmac_tx_timer_arm(priv, queue); + } else { + if (likely(priv->extend_desc)) + desc = &tx_q->dma_etx[entry].basic; + else + desc = &tx_q->dma_tx[entry]; + + tx_q->tx_count_frames = 0; + stmmac_set_tx_ic(priv, desc); + priv->xstats.tx_set_ic_bit++; + } + /* We've used all descriptors we need for this skb, however, * advance cur_tx so that it references a fresh descriptor. * ndo_start_xmit will fill this descriptor the next time it's @@ -3258,23 +3281,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += skb->len; - /* According to the coalesce parameter the IC bit for the latest - * segment is reset and the timer re-started to clean the tx status. - * This approach takes care about the fragments: desc is the first - * element in case of no SG. - */ - tx_q->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && - !(priv->synopsys_id >= DWMAC_CORE_4_00 && - (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - priv->hwts_tx_en)) { - stmmac_tx_timer_arm(priv, queue); - } else { - tx_q->tx_count_frames = 0; - stmmac_set_tx_ic(priv, desc); - priv->xstats.tx_set_ic_bit++; - } - if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -3505,8 +3511,6 @@ read_again: if (unlikely(status & dma_own)) break; - count++; - rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE); next_entry = rx_q->cur_rx; @@ -3533,6 +3537,7 @@ read_again: goto read_again; if (unlikely(error)) { dev_kfree_skb(skb); + count++; continue; } @@ -3572,6 +3577,7 @@ read_again: skb = napi_alloc_skb(&ch->rx_napi, len); if (!skb) { priv->dev->stats.rx_dropped++; + count++; continue; } @@ -3637,6 +3643,7 @@ read_again: priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += len; + count++; } if (status & rx_not_ls) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index df638b18b72c..0989e2bb6ee3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -140,6 +140,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + cfg = &priv->pps[rq->perout.index]; cfg->start.tv_sec = rq->perout.start.sec; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index e4ac3c401432..ac3f658105c0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -6,7 +6,9 @@ * Author: Jose Abreu <joabreu@synopsys.com> */ +#include <linux/bitrev.h> #include <linux/completion.h> +#include <linux/crc32.h> #include <linux/ethtool.h> #include <linux/ip.h> #include <linux/phy.h> @@ -485,12 +487,48 @@ static int stmmac_filter_check(struct stmmac_priv *priv) return -EOPNOTSUPP; } +static bool stmmac_hash_check(struct stmmac_priv *priv, unsigned char *addr) +{ + int mc_offset = 32 - priv->hw->mcast_bits_log2; + struct netdev_hw_addr *ha; + u32 hash, hash_nr; + + /* First compute the hash for desired addr */ + hash = bitrev32(~crc32_le(~0, addr, 6)) >> mc_offset; + hash_nr = hash >> 5; + hash = 1 << (hash & 0x1f); + + /* Now, check if it collides with any existing one */ + netdev_for_each_mc_addr(ha, priv->dev) { + u32 nr = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)) >> mc_offset; + if (((nr >> 5) == hash_nr) && ((1 << (nr & 0x1f)) == hash)) + return false; + } + + /* No collisions, address is good to go */ + return true; +} + +static bool stmmac_perfect_check(struct stmmac_priv *priv, unsigned char *addr) +{ + struct netdev_hw_addr *ha; + + /* Check if it collides with any existing one */ + netdev_for_each_uc_addr(ha, priv->dev) { + if (!memcmp(ha->addr, addr, ETH_ALEN)) + return false; + } + + /* No collisions, address is good to go */ + return true; +} + static int stmmac_test_hfilt(struct stmmac_priv *priv) { - unsigned char gd_addr[ETH_ALEN] = {0x01, 0xee, 0xdd, 0xcc, 0xbb, 0xaa}; - unsigned char bd_addr[ETH_ALEN] = {0x01, 0x01, 0x02, 0x03, 0x04, 0x05}; + unsigned char gd_addr[ETH_ALEN] = {0xf1, 0xee, 0xdd, 0xcc, 0xbb, 0xaa}; + unsigned char bd_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; ret = stmmac_filter_check(priv); if (ret) @@ -499,6 +537,16 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv) if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) return -EOPNOTSUPP; + while (--tries) { + /* We only need to check the bd_addr for collisions */ + bd_addr[ETH_ALEN - 1] = tries; + if (stmmac_hash_check(priv, bd_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; + ret = dev_mc_add(priv->dev, gd_addr); if (ret) return ret; @@ -523,13 +571,25 @@ cleanup: static int stmmac_test_pfilt(struct stmmac_priv *priv) { - unsigned char gd_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77}; - unsigned char bd_addr[ETH_ALEN] = {0x08, 0x00, 0x22, 0x33, 0x44, 0x55}; + unsigned char gd_addr[ETH_ALEN] = {0xf0, 0x01, 0x44, 0x55, 0x66, 0x77}; + unsigned char bd_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; if (stmmac_filter_check(priv)) return -EOPNOTSUPP; + if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) + return -EOPNOTSUPP; + + while (--tries) { + /* We only need to check the bd_addr for collisions */ + bd_addr[ETH_ALEN - 1] = tries; + if (stmmac_perfect_check(priv, bd_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; ret = dev_uc_add(priv->dev, gd_addr); if (ret) @@ -553,39 +613,31 @@ cleanup: return ret; } -static int stmmac_dummy_sync(struct net_device *netdev, const u8 *addr) -{ - return 0; -} - -static void stmmac_test_set_rx_mode(struct net_device *netdev) -{ - /* As we are in test mode of ethtool we already own the rtnl lock - * so no address will change from user. We can just call the - * ndo_set_rx_mode() callback directly */ - if (netdev->netdev_ops->ndo_set_rx_mode) - netdev->netdev_ops->ndo_set_rx_mode(netdev); -} - static int stmmac_test_mcfilt(struct stmmac_priv *priv) { - unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77}; - unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77}; + unsigned char uc_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff}; + unsigned char mc_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; if (stmmac_filter_check(priv)) return -EOPNOTSUPP; - if (!priv->hw->multicast_filter_bins) + if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries) return -EOPNOTSUPP; - /* Remove all MC addresses */ - __dev_mc_unsync(priv->dev, NULL); - stmmac_test_set_rx_mode(priv->dev); + while (--tries) { + /* We only need to check the mc_addr for collisions */ + mc_addr[ETH_ALEN - 1] = tries; + if (stmmac_hash_check(priv, mc_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; ret = dev_uc_add(priv->dev, uc_addr); if (ret) - goto cleanup; + return ret; attr.dst = uc_addr; @@ -602,30 +654,34 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv) cleanup: dev_uc_del(priv->dev, uc_addr); - __dev_mc_sync(priv->dev, stmmac_dummy_sync, NULL); - stmmac_test_set_rx_mode(priv->dev); return ret; } static int stmmac_test_ucfilt(struct stmmac_priv *priv) { - unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77}; - unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77}; + unsigned char uc_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff}; + unsigned char mc_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff}; struct stmmac_packet_attrs attr = { }; - int ret; + int ret, tries = 256; if (stmmac_filter_check(priv)) return -EOPNOTSUPP; - if (!priv->hw->multicast_filter_bins) + if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins) return -EOPNOTSUPP; - /* Remove all UC addresses */ - __dev_uc_unsync(priv->dev, NULL); - stmmac_test_set_rx_mode(priv->dev); + while (--tries) { + /* We only need to check the uc_addr for collisions */ + uc_addr[ETH_ALEN - 1] = tries; + if (stmmac_perfect_check(priv, uc_addr)) + break; + } + + if (!tries) + return -EOPNOTSUPP; ret = dev_mc_add(priv->dev, mc_addr); if (ret) - goto cleanup; + return ret; attr.dst = mc_addr; @@ -642,8 +698,6 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv) cleanup: dev_mc_del(priv->dev, mc_addr); - __dev_uc_sync(priv->dev, stmmac_dummy_sync, NULL); - stmmac_test_set_rx_mode(priv->dev); return ret; } diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index bbbc1dcb6ab5..b517c1af9de0 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -1237,8 +1237,17 @@ static int fjes_probe(struct platform_device *plat_dev) adapter->open_guard = false; adapter->txrx_wq = alloc_workqueue(DRV_NAME "/txrx", WQ_MEM_RECLAIM, 0); + if (unlikely(!adapter->txrx_wq)) { + err = -ENOMEM; + goto err_free_netdev; + } + adapter->control_wq = alloc_workqueue(DRV_NAME "/control", WQ_MEM_RECLAIM, 0); + if (unlikely(!adapter->control_wq)) { + err = -ENOMEM; + goto err_free_txrx_wq; + } INIT_WORK(&adapter->tx_stall_task, fjes_tx_stall_task); INIT_WORK(&adapter->raise_intr_rxdata_task, @@ -1255,7 +1264,7 @@ static int fjes_probe(struct platform_device *plat_dev) hw->hw_res.irq = platform_get_irq(plat_dev, 0); err = fjes_hw_init(&adapter->hw); if (err) - goto err_free_netdev; + goto err_free_control_wq; /* setup MAC address (02:00:00:00:00:[epid])*/ netdev->dev_addr[0] = 2; @@ -1277,6 +1286,10 @@ static int fjes_probe(struct platform_device *plat_dev) err_hw_exit: fjes_hw_exit(&adapter->hw); +err_free_control_wq: + destroy_workqueue(adapter->control_wq); +err_free_txrx_wq: + destroy_workqueue(adapter->txrx_wq); err_free_netdev: free_netdev(netdev); err_out: diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index fbec711ff514..fbea6f232819 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -107,27 +107,6 @@ struct bpqdev { static LIST_HEAD(bpq_devices); -/* - * bpqether network devices are paired with ethernet devices below them, so - * form a special "super class" of normal ethernet devices; split their locks - * off into a separate class since they always nest. - */ -static struct lock_class_key bpq_netdev_xmit_lock_key; -static struct lock_class_key bpq_netdev_addr_lock_key; - -static void bpq_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &bpq_netdev_xmit_lock_key); -} - -static void bpq_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &bpq_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL); -} - /* ------------------------------------------------------------------------ */ @@ -498,7 +477,6 @@ static int bpq_new_device(struct net_device *edev) err = register_netdevice(ndev); if (err) goto error; - bpq_set_lockdep_class(ndev); /* List protected by RTNL */ list_add_rcu(&bpq->bpq_list, &bpq_devices); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 670ef682f268..fb547f37af1e 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -609,7 +609,8 @@ struct nvsp_5_send_indirect_table { /* The number of entries in the send indirection table */ u32 count; - /* The offset of the send indirection table from top of this struct. + /* The offset of the send indirection table from the beginning of + * struct nvsp_message. * The send indirection table tells which channel to put the send * traffic on. Each entry is a channel number. */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d22a36fc7a7c..eab83e71567a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1178,20 +1178,39 @@ static int netvsc_receive(struct net_device *ndev, } static void netvsc_send_table(struct net_device *ndev, - const struct nvsp_message *nvmsg) + struct netvsc_device *nvscdev, + const struct nvsp_message *nvmsg, + u32 msglen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - u32 count, *tab; + u32 count, offset, *tab; int i; count = nvmsg->msg.v5_msg.send_table.count; + offset = nvmsg->msg.v5_msg.send_table.offset; + if (count != VRSS_SEND_TAB_SIZE) { netdev_err(ndev, "Received wrong send-table size:%u\n", count); return; } - tab = (u32 *)((unsigned long)&nvmsg->msg.v5_msg.send_table + - nvmsg->msg.v5_msg.send_table.offset); + /* If negotiated version <= NVSP_PROTOCOL_VERSION_6, the offset may be + * wrong due to a host bug. So fix the offset here. + */ + if (nvscdev->nvsp_version <= NVSP_PROTOCOL_VERSION_6 && + msglen >= sizeof(struct nvsp_message_header) + + sizeof(union nvsp_6_message_uber) + count * sizeof(u32)) + offset = sizeof(struct nvsp_message_header) + + sizeof(union nvsp_6_message_uber); + + /* Boundary check for all versions */ + if (offset > msglen - count * sizeof(u32)) { + netdev_err(ndev, "Received send-table offset too big:%u\n", + offset); + return; + } + + tab = (void *)nvmsg + offset; for (i = 0; i < count; i++) net_device_ctx->tx_table[i] = tab[i]; @@ -1209,12 +1228,14 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc ? "added" : "removed"); } -static void netvsc_receive_inband(struct net_device *ndev, - const struct nvsp_message *nvmsg) +static void netvsc_receive_inband(struct net_device *ndev, + struct netvsc_device *nvscdev, + const struct nvsp_message *nvmsg, + u32 msglen) { switch (nvmsg->hdr.msg_type) { case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: - netvsc_send_table(ndev, nvmsg); + netvsc_send_table(ndev, nvscdev, nvmsg, msglen); break; case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: @@ -1232,6 +1253,7 @@ static int netvsc_process_raw_pkt(struct hv_device *device, { struct vmbus_channel *channel = nvchan->channel; const struct nvsp_message *nvmsg = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); trace_nvsp_recv(ndev, channel, nvmsg); @@ -1247,7 +1269,7 @@ static int netvsc_process_raw_pkt(struct hv_device *device, break; case VM_PKT_DATA_INBAND: - netvsc_receive_inband(ndev, nvmsg); + netvsc_receive_inband(ndev, net_device, nvmsg, msglen); break; default: diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 39dddcd8b3cb..963509add611 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -982,7 +982,7 @@ static int netvsc_attach(struct net_device *ndev, if (netif_running(ndev)) { ret = rndis_filter_open(nvdev); if (ret) - return ret; + goto err; rdev = nvdev->extension; if (!rdev->link_state) @@ -990,6 +990,13 @@ static int netvsc_attach(struct net_device *ndev, } return 0; + +err: + netif_device_detach(ndev); + + rndis_filter_device_remove(hdev, nvdev); + + return ret; } static int netvsc_set_channels(struct net_device *net, @@ -1807,8 +1814,10 @@ static int netvsc_set_features(struct net_device *ndev, ret = rndis_filter_set_offload_params(ndev, nvdev, &offloads); - if (ret) + if (ret) { features ^= NETIF_F_LRO; + ndev->features = features; + } syncvf: if (!vf_netdev) @@ -2335,8 +2344,6 @@ static int netvsc_probe(struct hv_device *dev, NETIF_F_HW_VLAN_CTAG_RX; net->vlan_features = net->features; - netdev_lockdep_set_classes(net); - /* MTU range: 68 - 1500 or 65521 */ net->min_mtu = NETVSC_MTU_MIN; if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 887bbba4631e..ba3dfac1d904 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -131,8 +131,6 @@ static int ipvlan_init(struct net_device *dev) dev->gso_max_segs = phy_dev->gso_max_segs; dev->hard_header_len = phy_dev->hard_header_len; - netdev_lockdep_set_classes(dev); - ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats); if (!ipvlan->pcpu_stats) return -ENOMEM; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index cb7637364b40..afd8b2a08245 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -267,7 +267,6 @@ struct macsec_dev { struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; - unsigned int nest_level; }; /** @@ -2750,7 +2749,6 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) -static struct lock_class_key macsec_netdev_addr_lock_key; static int macsec_dev_init(struct net_device *dev) { @@ -2958,11 +2956,6 @@ static int macsec_get_iflink(const struct net_device *dev) return macsec_priv(dev)->real_dev->ifindex; } -static int macsec_get_nest_level(struct net_device *dev) -{ - return macsec_priv(dev)->nest_level; -} - static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, @@ -2976,7 +2969,6 @@ static const struct net_device_ops macsec_netdev_ops = { .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, - .ndo_get_lock_subclass = macsec_get_nest_level, }; static const struct device_type macsec_type = { @@ -3001,12 +2993,10 @@ static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { static void macsec_free_netdev(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); - struct net_device *real_dev = macsec->real_dev; free_percpu(macsec->stats); free_percpu(macsec->secy.tx_sc.stats); - dev_put(real_dev); } static void macsec_setup(struct net_device *dev) @@ -3261,14 +3251,6 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (err < 0) return err; - dev_hold(real_dev); - - macsec->nest_level = dev_get_nest_level(real_dev) + 1; - netdev_lockdep_set_classes(dev); - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &macsec_netdev_addr_lock_key, - macsec_get_nest_level(dev)); - err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 940192c057b6..34fc59bd1e20 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -852,8 +852,6 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) * "super class" of normal network devices; split their locks off into a * separate class since they always nest. */ -static struct lock_class_key macvlan_netdev_addr_lock_key; - #define ALWAYS_ON_OFFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL) @@ -869,19 +867,6 @@ static struct lock_class_key macvlan_netdev_addr_lock_key; #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) -static int macvlan_get_nest_level(struct net_device *dev) -{ - return ((struct macvlan_dev *)netdev_priv(dev))->nest_level; -} - -static void macvlan_set_lockdep_class(struct net_device *dev) -{ - netdev_lockdep_set_classes(dev); - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &macvlan_netdev_addr_lock_key, - macvlan_get_nest_level(dev)); -} - static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -900,8 +885,6 @@ static int macvlan_init(struct net_device *dev) dev->gso_max_segs = lowerdev->gso_max_segs; dev->hard_header_len = lowerdev->hard_header_len; - macvlan_set_lockdep_class(dev); - vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; @@ -1161,7 +1144,6 @@ static const struct net_device_ops macvlan_netdev_ops = { .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, - .ndo_get_lock_subclass = macvlan_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macvlan_dev_poll_controller, .ndo_netpoll_setup = macvlan_dev_netpoll_setup, @@ -1445,7 +1427,6 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; - vlan->nest_level = dev_get_nest_level(lowerdev) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 56576d4f34a5..44c2d857a7fa 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -708,6 +708,7 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) goto err_debugfs_exit; devlink_params_publish(devlink); + devlink_reload_enable(devlink); return nsim_dev; err_debugfs_exit: @@ -732,6 +733,7 @@ static void nsim_dev_destroy(struct nsim_dev *nsim_dev) { struct devlink *devlink = priv_to_devlink(nsim_dev); + devlink_reload_disable(devlink); nsim_bpf_dev_exit(nsim_dev); nsim_dev_debugfs_exit(nsim_dev); nsim_dev_traps_exit(devlink); @@ -806,9 +808,11 @@ static void nsim_dev_port_del_all(struct nsim_dev *nsim_dev) { struct nsim_dev_port *nsim_dev_port, *tmp; + mutex_lock(&nsim_dev->port_list_lock); list_for_each_entry_safe(nsim_dev_port, tmp, &nsim_dev->port_list, list) __nsim_dev_port_del(nsim_dev_port); + mutex_unlock(&nsim_dev->port_list_lock); } int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) @@ -822,14 +826,17 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) return PTR_ERR(nsim_dev); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); + mutex_lock(&nsim_dev->port_list_lock); for (i = 0; i < nsim_bus_dev->port_count; i++) { err = __nsim_dev_port_add(nsim_dev, i); if (err) goto err_port_del_all; } + mutex_unlock(&nsim_dev->port_list_lock); return 0; err_port_del_all: + mutex_unlock(&nsim_dev->port_list_lock); nsim_dev_port_del_all(nsim_dev); nsim_dev_destroy(nsim_dev); return err; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 6580094161a9..8f241b57fcf6 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -469,6 +469,19 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: + /* Reject requests with unsupported flags */ + if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* Reject requests to enable time stamping on both edges. */ + if ((rq->extts.flags & PTP_STRICT_FLAGS) && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) == PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + index = rq->extts.index; if (index >= N_EXT_TS) return -EINVAL; @@ -491,6 +504,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp, return 0; case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; if (rq->perout.index >= N_PER_OUT) return -EINVAL; return periodic_output(clock, rq, on, rq->perout.index); diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/phy/mdio-sun4i.c index 58d6504495e0..f798de3276dc 100644 --- a/drivers/net/phy/mdio-sun4i.c +++ b/drivers/net/phy/mdio-sun4i.c @@ -145,8 +145,11 @@ err_out_free_mdiobus: static int sun4i_mdio_remove(struct platform_device *pdev) { struct mii_bus *bus = platform_get_drvdata(pdev); + struct sun4i_mdio_data *data = bus->priv; mdiobus_unregister(bus); + if (data->regulator) + regulator_disable(data->regulator); mdiobus_free(bus); return 0; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 2e29ab841b4d..dbacb0031877 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -64,11 +64,12 @@ static int mdiobus_register_reset(struct mdio_device *mdiodev) if (mdiodev->dev.of_node) reset = devm_reset_control_get_exclusive(&mdiodev->dev, "phy"); - if (PTR_ERR(reset) == -ENOENT || - PTR_ERR(reset) == -ENOTSUPP) - reset = NULL; - else if (IS_ERR(reset)) - return PTR_ERR(reset); + if (IS_ERR(reset)) { + if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP) + reset = NULL; + else + return PTR_ERR(reset); + } mdiodev->reset_ctrl = reset; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 20e2ebe458f2..536236fdb232 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -87,8 +87,24 @@ struct phylink { phylink_printk(KERN_WARNING, pl, fmt, ##__VA_ARGS__) #define phylink_info(pl, fmt, ...) \ phylink_printk(KERN_INFO, pl, fmt, ##__VA_ARGS__) +#if defined(CONFIG_DYNAMIC_DEBUG) #define phylink_dbg(pl, fmt, ...) \ +do { \ + if ((pl)->config->type == PHYLINK_NETDEV) \ + netdev_dbg((pl)->netdev, fmt, ##__VA_ARGS__); \ + else if ((pl)->config->type == PHYLINK_DEV) \ + dev_dbg((pl)->dev, fmt, ##__VA_ARGS__); \ +} while (0) +#elif defined(DEBUG) +#define phylink_dbg(pl, fmt, ...) \ phylink_printk(KERN_DEBUG, pl, fmt, ##__VA_ARGS__) +#else +#define phylink_dbg(pl, fmt, ...) \ +({ \ + if (0) \ + phylink_printk(KERN_DEBUG, pl, fmt, ##__VA_ARGS__); \ +}) +#endif /** * phylink_set_port_modes() - set the port type modes in the ethtool mask @@ -585,6 +601,8 @@ static int phylink_register_sfp(struct phylink *pl, * Create a new phylink instance, and parse the link parameters found in @np. * This will parse in-band modes, fixed-link or SFP configuration. * + * Note: the rtnl lock must not be held when calling this function. + * * Returns a pointer to a &struct phylink, or an error-pointer value. Users * must use IS_ERR() to check for errors from this function. */ @@ -662,6 +680,8 @@ EXPORT_SYMBOL_GPL(phylink_create); * * Destroy a phylink instance. Any PHY that has been attached must have been * cleaned up via phylink_disconnect_phy() prior to calling this function. + * + * Note: the rtnl lock must not be held when calling this function. */ void phylink_destroy(struct phylink *pl) { @@ -1238,7 +1258,13 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, pl->link_config.duplex = our_kset.base.duplex; pl->link_config.an_enabled = our_kset.base.autoneg != AUTONEG_DISABLE; - if (!test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) { + /* If we have a PHY, phylib will call our link state function if the + * mode has changed, which will trigger a resolve and update the MAC + * configuration. For a fixed link, this isn't able to change any + * parameters, which just leaves inband mode. + */ + if (pl->link_an_mode == MLO_AN_INBAND && + !test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) { phylink_mac_config(pl, &pl->link_config); phylink_mac_an_restart(pl); } @@ -1318,15 +1344,16 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, if (pause->tx_pause) config->pause |= MLO_PAUSE_TX; - if (!test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) { + /* If we have a PHY, phylib will call our link state function if the + * mode has changed, which will trigger a resolve and update the MAC + * configuration. + */ + if (pl->phydev) { + phy_set_asym_pause(pl->phydev, pause->rx_pause, + pause->tx_pause); + } else if (!test_bit(PHYLINK_DISABLE_STOPPED, + &pl->phylink_disable_state)) { switch (pl->link_an_mode) { - case MLO_AN_PHY: - /* Silently mark the carrier down, and then trigger a resolve */ - if (pl->netdev) - netif_carrier_off(pl->netdev); - phylink_run_resolve(pl); - break; - case MLO_AN_FIXED: /* Should we allow fixed links to change against the config? */ phylink_resolve_flow(pl, config); diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index dc3d92d340c4..b73298250793 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -327,6 +327,7 @@ static struct phy_driver smsc_phy_driver[] = { .name = "SMSC LAN8740", /* PHY_BASIC_FEATURES */ + .flags = PHY_RST_AFTER_CLK_EN, .probe = smsc_phy_probe, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 9a1b006904a7..61824bbb5588 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1324,8 +1324,6 @@ static int ppp_dev_init(struct net_device *dev) { struct ppp *ppp; - netdev_lockdep_set_classes(dev); - ppp = netdev_priv(dev); /* Let the netdevice take a reference on the ppp file. This ensures * that ppp_destroy_interface() won't run before the device gets diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index cac64b96d545..4d479e3c817d 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -855,6 +855,7 @@ err_free_chan: sl->tty = NULL; tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); + free_netdev(sl->dev); err_exit: rtnl_unlock(); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index e8089def5a46..8156b33ee3e7 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1615,7 +1615,6 @@ static int team_init(struct net_device *dev) int err; team->dev = dev; - mutex_init(&team->lock); team_set_no_mode(team); team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); @@ -1642,7 +1641,8 @@ static int team_init(struct net_device *dev) goto err_options_register; netif_carrier_off(dev); - netdev_lockdep_set_classes(dev); + lockdep_register_key(&team->team_lock_key); + __mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key); return 0; @@ -1673,6 +1673,7 @@ static void team_uninit(struct net_device *dev) team_queue_override_fini(team); mutex_unlock(&team->lock); netdev_change_features(dev); + lockdep_unregister_key(&team->team_lock_key); } static void team_destructor(struct net_device *dev) @@ -1976,8 +1977,15 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev) err = team_port_del(team, port_dev); mutex_unlock(&team->lock); - if (!err) - netdev_change_features(dev); + if (err) + return err; + + if (netif_is_team_master(port_dev)) { + lockdep_unregister_key(&team->team_lock_key); + lockdep_register_key(&team->team_lock_key); + lockdep_set_class(&team->lock, &team->team_lock_key); + } + netdev_change_features(dev); return err; } diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 011bd4cb546e..af3994e0853b 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -196,7 +196,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) /* Get the MAC address */ ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); - if (ret < 0) { + if (ret < ETH_ALEN) { netdev_err(dev->net, "Failed to read MAC address: %d\n", ret); goto free; } diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 32f53de5b1fe..fe630438f67b 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -787,6 +787,13 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* ThinkPad USB-C Dock Gen 2 (based on Realtek RTL8153) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa387, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* NVIDIA Tegra USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */ { USB_DEVICE_AND_INTERFACE_INFO(NVIDIA_VENDOR_ID, 0x09ff, USB_CLASS_COMM, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 00cab3f43a4c..c2c82e6391b4 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -578,8 +578,8 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size) /* read current mtu value from device */ err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE, USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE, - 0, iface_no, &max_datagram_size, 2); - if (err < 0) { + 0, iface_no, &max_datagram_size, sizeof(max_datagram_size)); + if (err != sizeof(max_datagram_size)) { dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n"); goto out; } @@ -590,7 +590,7 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size) max_datagram_size = cpu_to_le16(ctx->max_datagram_size); err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE, USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE, - 0, iface_no, &max_datagram_size, 2); + 0, iface_no, &max_datagram_size, sizeof(max_datagram_size)); if (err < 0) dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n"); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 62948098191f..f24a1b0b801f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1264,8 +1264,11 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb) netif_dbg(dev, link, dev->net, "PHY INTR: 0x%08x\n", intdata); lan78xx_defer_kevent(dev, EVENT_LINK_RESET); - if (dev->domain_data.phyirq > 0) + if (dev->domain_data.phyirq > 0) { + local_irq_disable(); generic_handle_irq(dev->domain_data.phyirq); + local_irq_enable(); + } } else netdev_warn(dev->net, "unexpected interrupt: 0x%08x\n", intdata); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 596428ec71df..4196c0e32740 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1362,6 +1362,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ @@ -1370,6 +1371,8 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ + {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ + {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index cee9fef925cd..b2507c59ba8b 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4283,10 +4283,10 @@ static int rtl8152_close(struct net_device *netdev) unregister_pm_notifier(&tp->pm_notifier); #endif tasklet_disable(&tp->tx_tl); - napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); + napi_disable(&tp->napi); netif_stop_queue(netdev); res = usb_autopm_get_interface(tp->intf); @@ -4552,10 +4552,10 @@ static int rtl8152_pre_reset(struct usb_interface *intf) netif_stop_queue(netdev); tasklet_disable(&tp->tx_tl); - napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); + napi_disable(&tp->napi); if (netif_carrier_ok(netdev)) { mutex_lock(&tp->control); tp->rtl_ops.disable(tp); @@ -4673,7 +4673,7 @@ static int rtl8152_system_resume(struct r8152 *tp) netif_device_attach(netdev); - if (netif_running(netdev) && netdev->flags & IFF_UP) { + if (netif_running(netdev) && (netdev->flags & IFF_UP)) { tp->rtl_ops.up(tp); netif_carrier_off(netdev); set_bit(WORK_ENABLE, &tp->flags); @@ -5244,9 +5244,15 @@ static int rtl8152_set_tunable(struct net_device *netdev, } if (tp->rx_copybreak != val) { - napi_disable(&tp->napi); - tp->rx_copybreak = val; - napi_enable(&tp->napi); + if (netdev->flags & IFF_UP) { + mutex_lock(&tp->control); + napi_disable(&tp->napi); + tp->rx_copybreak = val; + napi_enable(&tp->napi); + mutex_unlock(&tp->control); + } else { + tp->rx_copybreak = val; + } } break; default: @@ -5274,9 +5280,15 @@ static int rtl8152_set_ringparam(struct net_device *netdev, return -EINVAL; if (tp->rx_pending != ring->rx_pending) { - napi_disable(&tp->napi); - tp->rx_pending = ring->rx_pending; - napi_enable(&tp->napi); + if (netdev->flags & IFF_UP) { + mutex_lock(&tp->control); + napi_disable(&tp->napi); + tp->rx_pending = ring->rx_pending; + napi_enable(&tp->napi); + mutex_unlock(&tp->control); + } else { + tp->rx_pending = ring->rx_pending; + } } return 0; @@ -5755,6 +5767,7 @@ static const struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x720c)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7214)}, + {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0xa387)}, {REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)}, {REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff)}, {REALTEK_USB_DEVICE(VENDOR_ID_TPLINK, 0x0601)}, diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index ee52bde058df..b8228f50bc94 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -865,7 +865,6 @@ static int vrf_dev_init(struct net_device *dev) /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; - netdev_lockdep_set_classes(dev); return 0; out_rth: diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 3d9bcc957f7d..8869154fad88 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2487,9 +2487,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; - if (info->options_len && - info->key.tun_flags & TUNNEL_VXLAN_OPT) + if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + if (info->options_len < sizeof(*md)) + goto drop; md = ip_tunnel_info_opts(info); + } ttl = info->key.ttl; tos = info->key.tos; label = info->key.label; @@ -3566,10 +3568,13 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); + struct net_device *remote_dev = NULL; struct vxlan_fdb *f = NULL; bool unregister = false; + struct vxlan_rdst *dst; int err; + dst = &vxlan->default_dst; err = vxlan_dev_configure(net, dev, conf, false, extack); if (err) return err; @@ -3577,14 +3582,14 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, dev->ethtool_ops = &vxlan_ethtool_ops; /* create an fdb entry for a valid default destination */ - if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) { + if (!vxlan_addr_any(&dst->remote_ip)) { err = vxlan_fdb_create(vxlan, all_zeros_mac, - &vxlan->default_dst.remote_ip, + &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, vxlan->cfg.dst_port, - vxlan->default_dst.remote_vni, - vxlan->default_dst.remote_vni, - vxlan->default_dst.remote_ifindex, + dst->remote_vni, + dst->remote_vni, + dst->remote_ifindex, NTF_SELF, &f); if (err) return err; @@ -3595,26 +3600,41 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, goto errout; unregister = true; + if (dst->remote_ifindex) { + remote_dev = __dev_get_by_index(net, dst->remote_ifindex); + if (!remote_dev) + goto errout; + + err = netdev_upper_dev_link(remote_dev, dev, extack); + if (err) + goto errout; + } + err = rtnl_configure_link(dev, NULL); if (err) - goto errout; + goto unlink; if (f) { - vxlan_fdb_insert(vxlan, all_zeros_mac, - vxlan->default_dst.remote_vni, f); + vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f); /* notify default fdb entry */ err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, true, extack); if (err) { vxlan_fdb_destroy(vxlan, f, false, false); + if (remote_dev) + netdev_upper_dev_unlink(remote_dev, dev); goto unregister; } } list_add(&vxlan->next, &vn->vxlan_list); + if (remote_dev) + dst->remote_dev = remote_dev; return 0; - +unlink: + if (remote_dev) + netdev_upper_dev_unlink(remote_dev, dev); errout: /* unregister_netdevice() destroys the default FDB entry with deletion * notification. But the addition notification was not sent yet, so @@ -3932,11 +3952,12 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev; struct vxlan_config conf; + struct vxlan_rdst *dst; int err; + dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) return err; @@ -3946,6 +3967,14 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (err) return err; + if (dst->remote_dev == lowerdev) + lowerdev = NULL; + + err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, + extack); + if (err) + return err; + /* handle default dst entry */ if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); @@ -3962,6 +3991,8 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], NTF_SELF, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); + netdev_adjacent_change_abort(dst->remote_dev, + lowerdev, dev); return err; } } @@ -3979,6 +4010,11 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); + netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); + if (lowerdev && lowerdev != dst->remote_dev) { + dst->remote_dev = lowerdev; + netdev_update_lockdep_key(lowerdev); + } vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); return 0; } @@ -3991,6 +4027,8 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head) list_del(&vxlan->next); unregister_netdevice_queue(dev, head); + if (vxlan->default_dst.remote_dev) + netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); } static size_t vxlan_get_size(const struct net_device *dev) diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/net/wimax/i2400m/op-rfkill.c index 8efb493ceec2..5c79f052cad2 100644 --- a/drivers/net/wimax/i2400m/op-rfkill.c +++ b/drivers/net/wimax/i2400m/op-rfkill.c @@ -127,12 +127,12 @@ int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev, "%d\n", result); result = 0; error_cmd: - kfree(cmd); kfree_skb(ack_skb); error_msg_to_dev: error_alloc: d_fnend(4, dev, "(wimax_dev %p state %d) = %d\n", wimax_dev, state, result); + kfree(cmd); return result; } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h index 39c64850cb6f..c0750ced5ac2 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h @@ -520,7 +520,7 @@ struct iwl_scan_dwell { } __packed; /** - * struct iwl_scan_config + * struct iwl_scan_config_v1 * @flags: enum scan_config_flags * @tx_chains: valid_tx antenna - ANT_* definitions * @rx_chains: valid_rx antenna - ANT_* definitions @@ -552,7 +552,7 @@ struct iwl_scan_config_v1 { #define SCAN_LB_LMAC_IDX 0 #define SCAN_HB_LMAC_IDX 1 -struct iwl_scan_config { +struct iwl_scan_config_v2 { __le32 flags; __le32 tx_chains; __le32 rx_chains; @@ -564,6 +564,24 @@ struct iwl_scan_config { u8 bcast_sta_id; u8 channel_flags; u8 channel_array[]; +} __packed; /* SCAN_CONFIG_DB_CMD_API_S_2 */ + +/** + * struct iwl_scan_config + * @enable_cam_mode: whether to enable CAM mode. + * @enable_promiscouos_mode: whether to enable promiscouos mode + * @bcast_sta_id: the index of the station in the fw + * @reserved: reserved + * @tx_chains: valid_tx antenna - ANT_* definitions + * @rx_chains: valid_rx antenna - ANT_* definitions + */ +struct iwl_scan_config { + u8 enable_cam_mode; + u8 enable_promiscouos_mode; + u8 bcast_sta_id; + u8 reserved; + __le32 tx_chains; + __le32 rx_chains; } __packed; /* SCAN_CONFIG_DB_CMD_API_S_3 */ /** diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index 423cc0cf8e78..0d5bc4ce5c07 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -288,6 +288,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t; * STA_CONTEXT_DOT11AX_API_S * @IWL_UCODE_TLV_CAPA_SAR_TABLE_VER: This ucode supports different sar * version tables. + * @IWL_UCODE_TLV_API_REDUCED_SCAN_CONFIG: This ucode supports v3 of + * SCAN_CONFIG_DB_CMD_API_S. * * @NUM_IWL_UCODE_TLV_API: number of bits used */ @@ -321,6 +323,7 @@ enum iwl_ucode_tlv_api { IWL_UCODE_TLV_API_WOWLAN_TCP_SYN_WAKE = (__force iwl_ucode_tlv_api_t)53, IWL_UCODE_TLV_API_FTM_RTT_ACCURACY = (__force iwl_ucode_tlv_api_t)54, IWL_UCODE_TLV_API_SAR_TABLE_VER = (__force iwl_ucode_tlv_api_t)55, + IWL_UCODE_TLV_API_REDUCED_SCAN_CONFIG = (__force iwl_ucode_tlv_api_t)56, IWL_UCODE_TLV_API_ADWELL_HB_DEF_N_AP = (__force iwl_ucode_tlv_api_t)57, IWL_UCODE_TLV_API_SCAN_EXT_CHAN_VER = (__force iwl_ucode_tlv_api_t)58, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index cb4c5514a556..695bbaa86273 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -279,6 +279,7 @@ * Indicates MAC is entering a power-saving sleep power-down. * Not a good time to access device-internal resources. */ +#define CSR_GP_CNTRL_REG_FLAG_INIT_DONE (0x00000004) #define CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP (0x00000010) #define CSR_GP_CNTRL_REG_FLAG_XTAL_ON (0x00000400) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h index f47e0f97acf8..23c25a7665f2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h @@ -449,6 +449,11 @@ enum { #define PERSISTENCE_BIT BIT(12) #define PREG_WFPM_ACCESS BIT(12) +#define HPM_HIPM_GEN_CFG 0xA03458 +#define HPM_HIPM_GEN_CFG_CR_PG_EN BIT(0) +#define HPM_HIPM_GEN_CFG_CR_SLP_EN BIT(1) +#define HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE BIT(10) + #define UREG_DOORBELL_TO_ISR6 0xA05C04 #define UREG_DOORBELL_TO_ISR6_NMI_BIT BIT(0) #define UREG_DOORBELL_TO_ISR6_SUSPEND BIT(18) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 843d00bf2bd5..5ca50f39a023 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1405,6 +1405,12 @@ static inline bool iwl_mvm_is_scan_ext_chan_supported(struct iwl_mvm *mvm) IWL_UCODE_TLV_API_SCAN_EXT_CHAN_VER); } +static inline bool iwl_mvm_is_reduced_config_scan_supported(struct iwl_mvm *mvm) +{ + return fw_has_api(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_API_REDUCED_SCAN_CONFIG); +} + static inline bool iwl_mvm_has_new_rx_stats_api(struct iwl_mvm *mvm) { return fw_has_api(&mvm->fw->ucode_capa, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index f6b3045badbd..fcafa22ec6ce 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1137,11 +1137,11 @@ static void iwl_mvm_fill_scan_config_v1(struct iwl_mvm *mvm, void *config, iwl_mvm_fill_channels(mvm, cfg->channel_array, max_channels); } -static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config, - u32 flags, u8 channel_flags, - u32 max_channels) +static void iwl_mvm_fill_scan_config_v2(struct iwl_mvm *mvm, void *config, + u32 flags, u8 channel_flags, + u32 max_channels) { - struct iwl_scan_config *cfg = config; + struct iwl_scan_config_v2 *cfg = config; cfg->flags = cpu_to_le32(flags); cfg->tx_chains = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm)); @@ -1185,7 +1185,7 @@ static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config, iwl_mvm_fill_channels(mvm, cfg->channel_array, max_channels); } -int iwl_mvm_config_scan(struct iwl_mvm *mvm) +static int iwl_mvm_legacy_config_scan(struct iwl_mvm *mvm) { void *cfg; int ret, cmd_size; @@ -1217,7 +1217,7 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm) } if (iwl_mvm_cdb_scan_api(mvm)) - cmd_size = sizeof(struct iwl_scan_config); + cmd_size = sizeof(struct iwl_scan_config_v2); else cmd_size = sizeof(struct iwl_scan_config_v1); cmd_size += num_channels; @@ -1254,8 +1254,8 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm) flags |= (iwl_mvm_is_scan_fragmented(hb_type)) ? SCAN_CONFIG_FLAG_SET_LMAC2_FRAGMENTED : SCAN_CONFIG_FLAG_CLEAR_LMAC2_FRAGMENTED; - iwl_mvm_fill_scan_config(mvm, cfg, flags, channel_flags, - num_channels); + iwl_mvm_fill_scan_config_v2(mvm, cfg, flags, channel_flags, + num_channels); } else { iwl_mvm_fill_scan_config_v1(mvm, cfg, flags, channel_flags, num_channels); @@ -1277,6 +1277,30 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm) return ret; } +int iwl_mvm_config_scan(struct iwl_mvm *mvm) +{ + struct iwl_scan_config cfg; + struct iwl_host_cmd cmd = { + .id = iwl_cmd_id(SCAN_CFG_CMD, IWL_ALWAYS_LONG_GROUP, 0), + .len[0] = sizeof(cfg), + .data[0] = &cfg, + .dataflags[0] = IWL_HCMD_DFL_NOCOPY, + }; + + if (!iwl_mvm_is_reduced_config_scan_supported(mvm)) + return iwl_mvm_legacy_config_scan(mvm); + + memset(&cfg, 0, sizeof(cfg)); + + cfg.bcast_sta_id = mvm->aux_sta.sta_id; + cfg.tx_chains = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm)); + cfg.rx_chains = cpu_to_le32(iwl_mvm_scan_rx_ant(mvm)); + + IWL_DEBUG_SCAN(mvm, "Sending UMAC scan config\n"); + + return iwl_mvm_send_cmd(mvm, &cmd); +} + static int iwl_mvm_scan_uid_by_status(struct iwl_mvm *mvm, int status) { int i; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 0bedba4c61f2..b3768d5d852a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1482,6 +1482,13 @@ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm, mvm_sta->sta_id, i); txq_id = iwl_mvm_tvqm_enable_txq(mvm, mvm_sta->sta_id, i, wdg); + /* + * on failures, just set it to IWL_MVM_INVALID_QUEUE + * to try again later, we have no other good way of + * failing here + */ + if (txq_id < 0) + txq_id = IWL_MVM_INVALID_QUEUE; tid_data->txq_id = txq_id; /* @@ -1950,30 +1957,73 @@ void iwl_mvm_dealloc_int_sta(struct iwl_mvm *mvm, struct iwl_mvm_int_sta *sta) sta->sta_id = IWL_MVM_INVALID_STA; } -static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 *queue, +static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 queue, u8 sta_id, u8 fifo) { unsigned int wdg_timeout = iwlmvm_mod_params.tfd_q_hang_detect ? mvm->trans->trans_cfg->base_params->wd_timeout : IWL_WATCHDOG_DISABLED; + struct iwl_trans_txq_scd_cfg cfg = { + .fifo = fifo, + .sta_id = sta_id, + .tid = IWL_MAX_TID_COUNT, + .aggregate = false, + .frame_limit = IWL_FRAME_LIMIT, + }; + + WARN_ON(iwl_mvm_has_new_tx_api(mvm)); + + iwl_mvm_enable_txq(mvm, NULL, queue, 0, &cfg, wdg_timeout); +} + +static int iwl_mvm_enable_aux_snif_queue_tvqm(struct iwl_mvm *mvm, u8 sta_id) +{ + unsigned int wdg_timeout = iwlmvm_mod_params.tfd_q_hang_detect ? + mvm->trans->trans_cfg->base_params->wd_timeout : + IWL_WATCHDOG_DISABLED; + + WARN_ON(!iwl_mvm_has_new_tx_api(mvm)); + + return iwl_mvm_tvqm_enable_txq(mvm, sta_id, IWL_MAX_TID_COUNT, + wdg_timeout); +} +static int iwl_mvm_add_int_sta_with_queue(struct iwl_mvm *mvm, int macidx, + int maccolor, + struct iwl_mvm_int_sta *sta, + u16 *queue, int fifo) +{ + int ret; + + /* Map queue to fifo - needs to happen before adding station */ + if (!iwl_mvm_has_new_tx_api(mvm)) + iwl_mvm_enable_aux_snif_queue(mvm, *queue, sta->sta_id, fifo); + + ret = iwl_mvm_add_int_sta_common(mvm, sta, NULL, macidx, maccolor); + if (ret) { + if (!iwl_mvm_has_new_tx_api(mvm)) + iwl_mvm_disable_txq(mvm, NULL, *queue, + IWL_MAX_TID_COUNT, 0); + return ret; + } + + /* + * For 22000 firmware and on we cannot add queue to a station unknown + * to firmware so enable queue here - after the station was added + */ if (iwl_mvm_has_new_tx_api(mvm)) { - int tvqm_queue = - iwl_mvm_tvqm_enable_txq(mvm, sta_id, - IWL_MAX_TID_COUNT, - wdg_timeout); - *queue = tvqm_queue; - } else { - struct iwl_trans_txq_scd_cfg cfg = { - .fifo = fifo, - .sta_id = sta_id, - .tid = IWL_MAX_TID_COUNT, - .aggregate = false, - .frame_limit = IWL_FRAME_LIMIT, - }; + int txq; - iwl_mvm_enable_txq(mvm, NULL, *queue, 0, &cfg, wdg_timeout); + txq = iwl_mvm_enable_aux_snif_queue_tvqm(mvm, sta->sta_id); + if (txq < 0) { + iwl_mvm_rm_sta_common(mvm, sta->sta_id); + return txq; + } + + *queue = txq; } + + return 0; } int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm) @@ -1989,59 +2039,26 @@ int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm) if (ret) return ret; - /* Map Aux queue to fifo - needs to happen before adding Aux station */ - if (!iwl_mvm_has_new_tx_api(mvm)) - iwl_mvm_enable_aux_snif_queue(mvm, &mvm->aux_queue, - mvm->aux_sta.sta_id, - IWL_MVM_TX_FIFO_MCAST); - - ret = iwl_mvm_add_int_sta_common(mvm, &mvm->aux_sta, NULL, - MAC_INDEX_AUX, 0); + ret = iwl_mvm_add_int_sta_with_queue(mvm, MAC_INDEX_AUX, 0, + &mvm->aux_sta, &mvm->aux_queue, + IWL_MVM_TX_FIFO_MCAST); if (ret) { iwl_mvm_dealloc_int_sta(mvm, &mvm->aux_sta); return ret; } - /* - * For 22000 firmware and on we cannot add queue to a station unknown - * to firmware so enable queue here - after the station was added - */ - if (iwl_mvm_has_new_tx_api(mvm)) - iwl_mvm_enable_aux_snif_queue(mvm, &mvm->aux_queue, - mvm->aux_sta.sta_id, - IWL_MVM_TX_FIFO_MCAST); - return 0; } int iwl_mvm_add_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - int ret; lockdep_assert_held(&mvm->mutex); - /* Map snif queue to fifo - must happen before adding snif station */ - if (!iwl_mvm_has_new_tx_api(mvm)) - iwl_mvm_enable_aux_snif_queue(mvm, &mvm->snif_queue, - mvm->snif_sta.sta_id, + return iwl_mvm_add_int_sta_with_queue(mvm, mvmvif->id, mvmvif->color, + &mvm->snif_sta, &mvm->snif_queue, IWL_MVM_TX_FIFO_BE); - - ret = iwl_mvm_add_int_sta_common(mvm, &mvm->snif_sta, vif->addr, - mvmvif->id, 0); - if (ret) - return ret; - - /* - * For 22000 firmware and on we cannot add queue to a station unknown - * to firmware so enable queue here - after the station was added - */ - if (iwl_mvm_has_new_tx_api(mvm)) - iwl_mvm_enable_aux_snif_queue(mvm, &mvm->snif_queue, - mvm->snif_sta.sta_id, - IWL_MVM_TX_FIFO_BE); - - return 0; } int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) @@ -2133,6 +2150,10 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) queue = iwl_mvm_tvqm_enable_txq(mvm, bsta->sta_id, IWL_MAX_TID_COUNT, wdg_timeout); + if (queue < 0) { + iwl_mvm_rm_sta_common(mvm, bsta->sta_id); + return queue; + } if (vif->type == NL80211_IFTYPE_AP || vif->type == NL80211_IFTYPE_ADHOC) @@ -2307,10 +2328,8 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) } ret = iwl_mvm_add_int_sta_common(mvm, msta, maddr, mvmvif->id, mvmvif->color); - if (ret) { - iwl_mvm_dealloc_int_sta(mvm, msta); - return ret; - } + if (ret) + goto err; /* * Enable cab queue after the ADD_STA command is sent. @@ -2323,6 +2342,10 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) int queue = iwl_mvm_tvqm_enable_txq(mvm, msta->sta_id, 0, timeout); + if (queue < 0) { + ret = queue; + goto err; + } mvmvif->cab_queue = queue; } else if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE)) @@ -2330,6 +2353,9 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) timeout); return 0; +err: + iwl_mvm_dealloc_int_sta(mvm, msta); + return ret; } static int __iwl_mvm_remove_sta_key(struct iwl_mvm *mvm, u8 sta_id, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 6f4bb7ce71a5..040cec17d3ad 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -573,20 +573,20 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x0034, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0038, iwl9560_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x003C, iwl9560_2ac_160_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x0060, iwl9460_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x0064, iwl9460_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x00A0, iwl9460_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x00A4, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0060, iwl9461_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x0064, iwl9461_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x00A0, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x00A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x0210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0214, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0230, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0234, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0238, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x023C, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x0260, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0260, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x0264, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2526, 0x02A0, iwl9460_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x02A4, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x02A0, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x02A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1030, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1210, iwl9260_2ac_cfg)}, @@ -603,7 +603,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x401C, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4030, iwl9560_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x6010, iwl9260_2ac_160_cfg)}, @@ -618,60 +618,61 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x271B, 0x0210, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0214, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x271C, 0x0214, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0034, iwl9560_2ac_160_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0038, iwl9560_2ac_160_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x003C, iwl9560_2ac_160_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0060, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x0064, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x00A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x00A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x0230, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0234, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0238, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x023C, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0260, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x0264, iwl9461_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x02A0, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x02A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x1010, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_160_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x4034, iwl9560_2ac_160_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x40A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x4234, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x42A4, iwl9462_2ac_cfg_soc)}, - - {IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + + {IWL_PCI_DEVICE(0x2720, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, + + {IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9460_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x31DC, 0x0030, iwl9560_2ac_160_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x0034, iwl9560_2ac_cfg_shared_clk)}, @@ -1067,11 +1068,7 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(iwl_trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) && - ((cfg != &iwl_ax200_cfg_cc && - cfg != &killer1650x_2ax_cfg && - cfg != &killer1650w_2ax_cfg && - cfg != &iwl_ax201_cfg_quz_hr) || - iwl_trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) { + iwl_trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) { u32 hw_status; hw_status = iwl_read_prph(iwl_trans, UMAG_GEN_HW_STATUS); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index df8455f14e4d..ca3bb4d65b00 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -57,6 +57,24 @@ #include "internal.h" #include "fw/dbg.h" +static int iwl_pcie_gen2_force_power_gating(struct iwl_trans *trans) +{ + iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); + udelay(20); + iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_PG_EN | + HPM_HIPM_GEN_CFG_CR_SLP_EN); + udelay(20); + iwl_clear_bits_prph(trans, HPM_HIPM_GEN_CFG, + HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE); + + iwl_trans_sw_reset(trans); + iwl_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE); + + return 0; +} + /* * Start up NIC's basic functionality after it has been reset * (e.g. after platform boot, or shutdown via iwl_pcie_apm_stop()) @@ -92,6 +110,13 @@ int iwl_pcie_gen2_apm_init(struct iwl_trans *trans) iwl_pcie_apm_config(trans); + if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 && + trans->cfg->integrated) { + ret = iwl_pcie_gen2_force_power_gating(trans); + if (ret) + return ret; + } + ret = iwl_finish_nic_init(trans, trans->trans_cfg); if (ret) return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 8894027429d6..d80f71f82a6d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -251,27 +251,23 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room; unsigned int mss = skb_shinfo(skb)->gso_size; - u16 length, iv_len, amsdu_pad; + u16 length, amsdu_pad; u8 *start_hdr; struct iwl_tso_hdr_page *hdr_page; struct page **page_ptr; struct tso_t tso; - /* if the packet is protected, then it must be CCMP or GCMP */ - iv_len = ieee80211_has_protected(hdr->frame_control) ? - IEEE80211_CCMP_HDR_LEN : 0; - trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr, start_len, 0); ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb); snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb); - total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len - iv_len; + total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len; amsdu_pad = 0; /* total amount of header we may need for this A-MSDU */ hdr_room = DIV_ROUND_UP(total_len, mss) * - (3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len; + (3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)); /* Our device supports 9 segments at most, it will fit in 1 page */ hdr_page = get_page_hdr(trans, hdr_room); @@ -282,14 +278,12 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, start_hdr = hdr_page->pos; page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs); *page_ptr = hdr_page->page; - memcpy(hdr_page->pos, skb->data + hdr_len, iv_len); - hdr_page->pos += iv_len; /* - * Pull the ieee80211 header + IV to be able to use TSO core, + * Pull the ieee80211 header to be able to use TSO core, * we will restore it for the tx_status flow. */ - skb_pull(skb, hdr_len + iv_len); + skb_pull(skb, hdr_len); /* * Remove the length of all the headers that we don't actually @@ -364,8 +358,8 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, } } - /* re -add the WiFi header and IV */ - skb_push(skb, hdr_len + iv_len); + /* re -add the WiFi header */ + skb_push(skb, hdr_len); return 0; diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c index 158a3d762e55..e323e9a5999f 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_hw.c +++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c @@ -3041,30 +3041,6 @@ static void prism2_clear_set_tim_queue(local_info_t *local) } } - -/* - * HostAP uses two layers of net devices, where the inner - * layer gets called all the time from the outer layer. - * This is a natural nesting, which needs a split lock type. - */ -static struct lock_class_key hostap_netdev_xmit_lock_key; -static struct lock_class_key hostap_netdev_addr_lock_key; - -static void prism2_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &hostap_netdev_xmit_lock_key); -} - -static void prism2_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, - &hostap_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, prism2_set_lockdep_class_one, NULL); -} - static struct net_device * prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx, struct device *sdev) @@ -3223,7 +3199,6 @@ while (0) if (ret >= 0) ret = register_netdevice(dev); - prism2_set_lockdep_class(dev); rtnl_unlock(); if (ret < 0) { printk(KERN_WARNING "%s: register netdevice failed!\n", diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile index 4d03596e891f..d7a1ddc9e407 100644 --- a/drivers/net/wireless/mediatek/mt76/Makefile +++ b/drivers/net/wireless/mediatek/mt76/Makefile @@ -8,6 +8,8 @@ mt76-y := \ mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o \ tx.o agg-rx.o mcu.o +mt76-$(CONFIG_PCI) += pci.o + mt76-usb-y := usb.o usb_trace.o CFLAGS_trace.o := -I$(src) diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index c747eb24581c..8f69d00bd940 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -53,8 +53,10 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q, u32 ctrl; int i, idx = -1; - if (txwi) + if (txwi) { q->entry[q->head].txwi = DMA_DUMMY_DATA; + q->entry[q->head].skip_buf0 = true; + } for (i = 0; i < nbufs; i += 2, buf += 2) { u32 buf0 = buf[0].addr, buf1 = 0; @@ -97,7 +99,7 @@ mt76_dma_tx_cleanup_idx(struct mt76_dev *dev, struct mt76_queue *q, int idx, __le32 __ctrl = READ_ONCE(q->desc[idx].ctrl); u32 ctrl = le32_to_cpu(__ctrl); - if (!e->txwi || !e->skb) { + if (!e->skip_buf0) { __le32 addr = READ_ONCE(q->desc[idx].buf0); u32 len = FIELD_GET(MT_DMA_CTL_SD_LEN0, ctrl); diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 570c159515a0..8aec7ccf2d79 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -93,8 +93,9 @@ struct mt76_queue_entry { struct urb *urb; }; enum mt76_txq_id qid; - bool schedule; - bool done; + bool skip_buf0:1; + bool schedule:1; + bool done:1; }; struct mt76_queue_regs { @@ -578,6 +579,7 @@ bool __mt76_poll_msec(struct mt76_dev *dev, u32 offset, u32 mask, u32 val, #define mt76_poll_msec(dev, ...) __mt76_poll_msec(&((dev)->mt76), __VA_ARGS__) void mt76_mmio_init(struct mt76_dev *dev, void __iomem *regs); +void mt76_pci_disable_aspm(struct pci_dev *pdev); static inline u16 mt76_chip(struct mt76_dev *dev) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c index 73c3104f8858..cf611d1b817c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c @@ -81,6 +81,8 @@ mt76pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* RG_SSUSB_CDR_BR_PE1D = 0x3 */ mt76_rmw_field(dev, 0x15c58, 0x3 << 6, 0x3); + mt76_pci_disable_aspm(pdev); + return 0; error: diff --git a/drivers/net/wireless/mediatek/mt76/pci.c b/drivers/net/wireless/mediatek/mt76/pci.c new file mode 100644 index 000000000000..04c5a692bc85 --- /dev/null +++ b/drivers/net/wireless/mediatek/mt76/pci.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (C) 2019 Lorenzo Bianconi <lorenzo@kernel.org> + */ + +#include <linux/pci.h> + +void mt76_pci_disable_aspm(struct pci_dev *pdev) +{ + struct pci_dev *parent = pdev->bus->self; + u16 aspm_conf, parent_aspm_conf = 0; + + pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &aspm_conf); + aspm_conf &= PCI_EXP_LNKCTL_ASPMC; + if (parent) { + pcie_capability_read_word(parent, PCI_EXP_LNKCTL, + &parent_aspm_conf); + parent_aspm_conf &= PCI_EXP_LNKCTL_ASPMC; + } + + if (!aspm_conf && (!parent || !parent_aspm_conf)) { + /* aspm already disabled */ + return; + } + + dev_info(&pdev->dev, "disabling ASPM %s %s\n", + (aspm_conf & PCI_EXP_LNKCTL_ASPM_L0S) ? "L0s" : "", + (aspm_conf & PCI_EXP_LNKCTL_ASPM_L1) ? "L1" : ""); + + if (IS_ENABLED(CONFIG_PCIEASPM)) { + int err; + + err = pci_disable_link_state(pdev, aspm_conf); + if (!err) + return; + } + + /* both device and parent should have the same ASPM setting. + * disable ASPM in downstream component first and then upstream. + */ + pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, aspm_conf); + if (parent) + pcie_capability_clear_word(parent, PCI_EXP_LNKCTL, + aspm_conf); +} +EXPORT_SYMBOL_GPL(mt76_pci_disable_aspm); diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index 6087ec7a90a6..f88d26535978 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -822,7 +822,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw) hdr = rtl_get_hdr(skb); fc = rtl_get_fc(skb); - if (!stats.crc && !stats.hwerror) { + if (!stats.crc && !stats.hwerror && (skb->len > FCS_LEN)) { memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status)); @@ -859,6 +859,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw) _rtl_pci_rx_to_mac80211(hw, skb, rx_status); } } else { + /* drop packets with errors or those too short */ dev_kfree_skb_any(skb); } new_trx_end: diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c index 70f04c2f5b17..fff8dda14023 100644 --- a/drivers/net/wireless/realtek/rtlwifi/ps.c +++ b/drivers/net/wireless/realtek/rtlwifi/ps.c @@ -754,6 +754,9 @@ static void rtl_p2p_noa_ie(struct ieee80211_hw *hw, void *data, return; } else { noa_num = (noa_len - 2) / 13; + if (noa_num > P2P_MAX_NOA_NUM) + noa_num = P2P_MAX_NOA_NUM; + } noa_index = ie[3]; if (rtlpriv->psc.p2p_ps_info.p2p_ps_mode == @@ -848,6 +851,9 @@ static void rtl_p2p_action_ie(struct ieee80211_hw *hw, void *data, return; } else { noa_num = (noa_len - 2) / 13; + if (noa_num > P2P_MAX_NOA_NUM) + noa_num = P2P_MAX_NOA_NUM; + } noa_index = ie[3]; if (rtlpriv->psc.p2p_ps_info.p2p_ps_mode == diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index be92e1220284..7997cc6de334 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -548,6 +548,7 @@ static int virt_wifi_newlink(struct net *src_net, struct net_device *dev, priv->is_connected = false; priv->is_up = false; INIT_DELAYED_WORK(&priv->connect, virt_wifi_connect_complete); + __module_get(THIS_MODULE); return 0; unregister_netdev: @@ -578,6 +579,7 @@ static void virt_wifi_dellink(struct net_device *dev, netdev_upper_dev_unlink(priv->lowerdev, dev); unregister_netdevice_queue(dev, head); + module_put(THIS_MODULE); /* Deleting the wiphy is handled in the module destructor. */ } @@ -590,6 +592,42 @@ static struct rtnl_link_ops virt_wifi_link_ops = { .priv_size = sizeof(struct virt_wifi_netdev_priv), }; +static bool netif_is_virt_wifi_dev(const struct net_device *dev) +{ + return rcu_access_pointer(dev->rx_handler) == virt_wifi_rx_handler; +} + +static int virt_wifi_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *lower_dev = netdev_notifier_info_to_dev(ptr); + struct virt_wifi_netdev_priv *priv; + struct net_device *upper_dev; + LIST_HEAD(list_kill); + + if (!netif_is_virt_wifi_dev(lower_dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_UNREGISTER: + priv = rtnl_dereference(lower_dev->rx_handler_data); + if (!priv) + return NOTIFY_DONE; + + upper_dev = priv->upperdev; + + upper_dev->rtnl_link_ops->dellink(upper_dev, &list_kill); + unregister_netdevice_many(&list_kill); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block virt_wifi_notifier = { + .notifier_call = virt_wifi_event, +}; + /* Acquires and releases the rtnl lock. */ static int __init virt_wifi_init_module(void) { @@ -598,14 +636,25 @@ static int __init virt_wifi_init_module(void) /* Guaranteed to be locallly-administered and not multicast. */ eth_random_addr(fake_router_bssid); + err = register_netdevice_notifier(&virt_wifi_notifier); + if (err) + return err; + + err = -ENOMEM; common_wiphy = virt_wifi_make_wiphy(); if (!common_wiphy) - return -ENOMEM; + goto notifier; err = rtnl_link_register(&virt_wifi_link_ops); if (err) - virt_wifi_destroy_wiphy(common_wiphy); + goto destroy_wiphy; + return 0; + +destroy_wiphy: + virt_wifi_destroy_wiphy(common_wiphy); +notifier: + unregister_netdevice_notifier(&virt_wifi_notifier); return err; } @@ -615,6 +664,7 @@ static void __exit virt_wifi_cleanup_module(void) /* Will delete any devices that depend on the wiphy. */ rtnl_link_unregister(&virt_wifi_link_ops); virt_wifi_destroy_wiphy(common_wiphy); + unregister_netdevice_notifier(&virt_wifi_notifier); } module_init(virt_wifi_init_module); diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 1cd113c8d7cb..ad0abb1f0bae 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -259,7 +259,7 @@ static void fdp_nci_i2c_read_device_properties(struct device *dev, *fw_vsc_cfg, len); if (r) { - devm_kfree(dev, fw_vsc_cfg); + devm_kfree(dev, *fw_vsc_cfg); goto vsc_read_err; } } else { diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 307bd2afbe05..4d1909aecd6c 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -220,8 +220,10 @@ static irqreturn_t nxp_nci_i2c_irq_thread_fn(int irq, void *phy_id) if (r == -EREMOTEIO) { phy->hard_fault = r; - skb = NULL; - } else if (r < 0) { + if (info->mode == NXP_NCI_MODE_FW) + nxp_nci_fw_recv_frame(phy->ndev, NULL); + } + if (r < 0) { nfc_err(&client->dev, "Read failed with error %d\n", r); goto exit_irq_handled; } diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 145ddf3f0a45..604dba4f18af 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -783,7 +783,7 @@ static int port100_send_frame_async(struct port100 *dev, struct sk_buff *out, rc = port100_submit_urb_for_ack(dev, GFP_KERNEL); if (rc) - usb_unlink_urb(dev->out_urb); + usb_kill_urb(dev->out_urb); exit: mutex_unlock(&dev->out_urb_lock); diff --git a/drivers/nfc/st21nfca/core.c b/drivers/nfc/st21nfca/core.c index f9ac176cf257..2ce17932a073 100644 --- a/drivers/nfc/st21nfca/core.c +++ b/drivers/nfc/st21nfca/core.c @@ -708,6 +708,7 @@ static int st21nfca_hci_complete_target_discovered(struct nfc_hci_dev *hdev, NFC_PROTO_FELICA_MASK; } else { kfree_skb(nfcid_skb); + nfcid_skb = NULL; /* P2P in type A */ r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_F_GATE, ST21NFCA_RF_READER_F_NFCID1, diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 2b36f052bfb9..c6439638a419 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -23,6 +23,16 @@ config NVME_MULTIPATH /dev/nvmeXnY device will show up for each NVMe namespaces, even if it is accessible through multiple controllers. +config NVME_HWMON + bool "NVMe hardware monitoring" + depends on (NVME_CORE=y && HWMON=y) || (NVME_CORE=m && HWMON) + help + This provides support for NVMe hardware monitoring. If enabled, + a hardware monitoring device will be created for each NVMe drive + in the system. + + If unsure, say N. + config NVME_FABRICS tristate diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index 8a4b671c5f0c..fc7b26be692d 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -14,6 +14,7 @@ nvme-core-$(CONFIG_TRACING) += trace.o nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o nvme-core-$(CONFIG_NVM) += lightnvm.o nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS) += fault_inject.o +nvme-core-$(CONFIG_NVME_HWMON) += hwmon.o nvme-y += pci.o diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fa7ba09dca77..8e8527408db3 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -283,6 +283,8 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(req); + nvme_cleanup_cmd(req); + if (nvme_req(req)->ctrl->kas) nvme_req(req)->ctrl->comp_seen = true; @@ -313,7 +315,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) if (blk_mq_request_completed(req)) return true; - nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; + nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(req); return true; } @@ -611,8 +613,14 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, struct nvme_dsm_range *range; struct bio *bio; - range = kmalloc_array(segments, sizeof(*range), - GFP_ATOMIC | __GFP_NOWARN); + /* + * Some devices do not consider the DSM 'Number of Ranges' field when + * determining how much data to DMA. Always allocate memory for maximum + * number of segments to prevent device reading beyond end of buffer. + */ + static const size_t alloc_size = sizeof(*range) * NVME_DSM_MAX_RANGES; + + range = kzalloc(alloc_size, GFP_ATOMIC | __GFP_NOWARN); if (!range) { /* * If we fail allocation our range, fallback to the controller @@ -626,7 +634,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, } __rq_for_each_bio(bio, req) { - u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector); + u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector); u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; if (n < segments) { @@ -652,7 +660,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, req->special_vec.bv_page = virt_to_page(range); req->special_vec.bv_offset = offset_in_page(range); - req->special_vec.bv_len = sizeof(*range) * segments; + req->special_vec.bv_len = alloc_size; req->rq_flags |= RQF_SPECIAL_PAYLOAD; return BLK_STS_OK; @@ -667,7 +675,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes; cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id); cmnd->write_zeroes.slba = - cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); + cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->write_zeroes.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); cmnd->write_zeroes.control = 0; @@ -691,7 +699,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read); cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id); - cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); + cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) @@ -1647,7 +1655,7 @@ static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type) static void nvme_set_chunk_size(struct nvme_ns *ns) { - u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9)); + u32 chunk_size = nvme_lba_to_sect(ns, ns->noiob); blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size)); } @@ -1684,8 +1692,7 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) { - u32 max_sectors; - unsigned short bs = 1 << ns->lba_shift; + u64 max_blocks; if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) || (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES)) @@ -1701,11 +1708,12 @@ static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) * nvme_init_identify() if available. */ if (ns->ctrl->max_hw_sectors == UINT_MAX) - max_sectors = ((u32)(USHRT_MAX + 1) * bs) >> 9; + max_blocks = (u64)USHRT_MAX + 1; else - max_sectors = ((u32)(ns->ctrl->max_hw_sectors + 1) * bs) >> 9; + max_blocks = ns->ctrl->max_hw_sectors + 1; - blk_queue_max_write_zeroes_sectors(disk->queue, max_sectors); + blk_queue_max_write_zeroes_sectors(disk->queue, + nvme_lba_to_sect(ns, max_blocks)); } static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, @@ -1748,7 +1756,7 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) static void nvme_update_disk_info(struct gendisk *disk, struct nvme_ns *ns, struct nvme_id_ns *id) { - sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9); + sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze)); unsigned short bs = 1 << ns->lba_shift; u32 atomic_bs, phys_bs, io_opt; @@ -2796,6 +2804,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->oncs = le16_to_cpu(id->oncs); ctrl->mtfa = le16_to_cpu(id->mtfa); ctrl->oaes = le32_to_cpu(id->oaes); + ctrl->wctemp = le16_to_cpu(id->wctemp); + ctrl->cctemp = le16_to_cpu(id->cctemp); + atomic_set(&ctrl->abort_limit, id->acl + 1); ctrl->vwc = id->vwc; if (id->mdts) @@ -2895,6 +2906,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret < 0) return ret; + if (!ctrl->identified) + nvme_hwmon_init(ctrl); + ctrl->identified = true; return 0; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 265f89e11d8b..679a721ae229 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1224,7 +1224,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, lsreq->rqstlen = sizeof(*assoc_rqst); lsreq->rspaddr = assoc_acc; lsreq->rsplen = sizeof(*assoc_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req(ctrl->rport, lsop); if (ret) @@ -1264,7 +1264,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, if (fcret) { ret = -EBADF; dev_err(ctrl->dev, - "q %d connect failed: %s\n", + "q %d Create Association LS failed: %s\n", queue->qnum, validation_errors[fcret]); } else { ctrl->association_id = @@ -1332,7 +1332,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, lsreq->rqstlen = sizeof(*conn_rqst); lsreq->rspaddr = conn_acc; lsreq->rsplen = sizeof(*conn_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req(ctrl->rport, lsop); if (ret) @@ -1363,7 +1363,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (fcret) { ret = -EBADF; dev_err(ctrl->dev, - "q %d connect failed: %s\n", + "q %d Create I/O Connection LS failed: %s\n", queue->qnum, validation_errors[fcret]); } else { queue->connection_id = @@ -1376,7 +1376,7 @@ out_free_buffer: out_no_memory: if (ret) dev_err(ctrl->dev, - "queue %d connect command failed (%d).\n", + "queue %d connect I/O queue failed (%d).\n", queue->qnum, ret); return ret; } @@ -1413,8 +1413,8 @@ nvme_fc_disconnect_assoc_done(struct nvmefc_ls_req *lsreq, int status) static void nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) { - struct fcnvme_ls_disconnect_rqst *discon_rqst; - struct fcnvme_ls_disconnect_acc *discon_acc; + struct fcnvme_ls_disconnect_assoc_rqst *discon_rqst; + struct fcnvme_ls_disconnect_assoc_acc *discon_acc; struct nvmefc_ls_req_op *lsop; struct nvmefc_ls_req *lsreq; int ret; @@ -1430,11 +1430,11 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) lsreq = &lsop->ls_req; lsreq->private = (void *)&lsop[1]; - discon_rqst = (struct fcnvme_ls_disconnect_rqst *) + discon_rqst = (struct fcnvme_ls_disconnect_assoc_rqst *) (lsreq->private + ctrl->lport->ops->lsrqst_priv_sz); - discon_acc = (struct fcnvme_ls_disconnect_acc *)&discon_rqst[1]; + discon_acc = (struct fcnvme_ls_disconnect_assoc_acc *)&discon_rqst[1]; - discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT; + discon_rqst->w0.ls_cmd = FCNVME_LS_DISCONNECT_ASSOC; discon_rqst->desc_list_len = cpu_to_be32( sizeof(struct fcnvme_lsdesc_assoc_id) + sizeof(struct fcnvme_lsdesc_disconn_cmd)); @@ -1451,22 +1451,17 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) discon_rqst->discon_cmd.desc_len = fcnvme_lsdesc_len( sizeof(struct fcnvme_lsdesc_disconn_cmd)); - discon_rqst->discon_cmd.scope = FCNVME_DISCONN_ASSOCIATION; - discon_rqst->discon_cmd.id = cpu_to_be64(ctrl->association_id); lsreq->rqstaddr = discon_rqst; lsreq->rqstlen = sizeof(*discon_rqst); lsreq->rspaddr = discon_acc; lsreq->rsplen = sizeof(*discon_acc); - lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC; + lsreq->timeout = NVME_FC_LS_TIMEOUT_SEC; ret = nvme_fc_send_ls_req_async(ctrl->rport, lsop, nvme_fc_disconnect_assoc_done); if (ret) kfree(lsop); - - /* only meaningful part to terminating the association */ - ctrl->association_id = 0; } @@ -1662,7 +1657,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) (freq->rcv_rsplen / 4) || be32_to_cpu(op->rsp_iu.xfrd_len) != freq->transferred_length || - op->rsp_iu.status_code || + op->rsp_iu.ersp_result || sqe->common.command_id != cqe->command_id)) { status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1); dev_info(ctrl->ctrl.device, @@ -1672,7 +1667,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) ctrl->cnum, be16_to_cpu(op->rsp_iu.iu_len), be32_to_cpu(op->rsp_iu.xfrd_len), freq->transferred_length, - op->rsp_iu.status_code, + op->rsp_iu.ersp_result, sqe->common.command_id, cqe->command_id); goto done; @@ -1731,9 +1726,14 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl, op->rq = rq; op->rqno = rqno; - cmdiu->scsi_id = NVME_CMD_SCSI_ID; + cmdiu->format_id = NVME_CMD_FORMAT_ID; cmdiu->fc_id = NVME_CMD_FC_ID; cmdiu->iu_len = cpu_to_be16(sizeof(*cmdiu) / sizeof(u32)); + if (queue->qnum) + cmdiu->rsv_cat = fccmnd_set_cat_css(0, + (NVME_CC_CSS_NVM >> NVME_CC_CSS_SHIFT)); + else + cmdiu->rsv_cat = fccmnd_set_cat_admin(0); op->fcp_req.cmddma = fc_dma_map_single(ctrl->lport->dev, &op->cmd_iu, sizeof(op->cmd_iu), DMA_TO_DEVICE); @@ -2173,8 +2173,6 @@ nvme_fc_unmap_data(struct nvme_fc_ctrl *ctrl, struct request *rq, fc_dma_unmap_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents, rq_dma_dir(rq)); - nvme_cleanup_cmd(rq); - sg_free_table_chained(&freq->sg_table, SG_CHUNK_SIZE); freq->sg_cnt = 0; @@ -2305,6 +2303,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (!(op->flags & FCOP_FLAGS_AEN)) nvme_fc_unmap_data(ctrl, op->rq, op); + nvme_cleanup_cmd(op->rq); nvme_fc_ctrl_put(ctrl); if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE && @@ -2695,7 +2694,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) /* warn if maxcmd is lower than queue_size */ dev_warn(ctrl->ctrl.device, "queue_size %zu > ctrl maxcmd %u, reducing " - "to queue_size\n", + "to maxcmd\n", opts->queue_size, ctrl->ctrl.maxcmd); opts->queue_size = ctrl->ctrl.maxcmd; } @@ -2703,7 +2702,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (opts->queue_size > ctrl->ctrl.sqsize + 1) { /* warn if sqsize is lower than queue_size */ dev_warn(ctrl->ctrl.device, - "queue_size %zu > ctrl sqsize %u, clamping down\n", + "queue_size %zu > ctrl sqsize %u, reducing " + "to sqsize\n", opts->queue_size, ctrl->ctrl.sqsize + 1); opts->queue_size = ctrl->ctrl.sqsize + 1; } @@ -2739,6 +2739,7 @@ out_term_aen_ops: out_disconnect_admin_queue: /* send a Disconnect(association) LS to fc-nvme target */ nvme_fc_xmt_disconnect_assoc(ctrl); + ctrl->association_id = 0; out_delete_hw_queue: __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); out_free_queue: @@ -2830,6 +2831,8 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) if (ctrl->association_id) nvme_fc_xmt_disconnect_assoc(ctrl); + ctrl->association_id = 0; + if (ctrl->ctrl.tagset) { nvme_fc_delete_hw_io_queues(ctrl); nvme_fc_free_io_queues(ctrl); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c new file mode 100644 index 000000000000..a5af21f5d370 --- /dev/null +++ b/drivers/nvme/host/hwmon.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVM Express hardware monitoring support + * Copyright (c) 2019, Guenter Roeck + */ + +#include <linux/hwmon.h> +#include <asm/unaligned.h> + +#include "nvme.h" + +/* These macros should be moved to linux/temperature.h */ +#define MILLICELSIUS_TO_KELVIN(t) DIV_ROUND_CLOSEST((t) + 273150, 1000) +#define KELVIN_TO_MILLICELSIUS(t) ((t) * 1000L - 273150) + +struct nvme_hwmon_data { + struct nvme_ctrl *ctrl; + struct nvme_smart_log log; + struct mutex read_lock; +}; + +static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, + long *temp) +{ + unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT; + u32 status; + int ret; + + if (under) + threshold |= NVME_TEMP_THRESH_TYPE_UNDER; + + ret = nvme_get_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0, + &status); + if (ret > 0) + return -EIO; + if (ret < 0) + return ret; + *temp = KELVIN_TO_MILLICELSIUS(status & NVME_TEMP_THRESH_MASK); + + return 0; +} + +static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, + long temp) +{ + unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT; + int ret; + + temp = MILLICELSIUS_TO_KELVIN(temp); + threshold |= clamp_val(temp, 0, NVME_TEMP_THRESH_MASK); + + if (under) + threshold |= NVME_TEMP_THRESH_TYPE_UNDER; + + ret = nvme_set_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0, + NULL); + if (ret > 0) + return -EIO; + + return ret; +} + +static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) +{ + int ret; + + ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, + &data->log, sizeof(data->log), 0); + + return ret <= 0 ? ret : -EIO; +} + +static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct nvme_hwmon_data *data = dev_get_drvdata(dev); + struct nvme_smart_log *log = &data->log; + int temp; + int err; + + /* + * First handle attributes which don't require us to read + * the smart log. + */ + switch (attr) { + case hwmon_temp_max: + return nvme_get_temp_thresh(data->ctrl, channel, false, val); + case hwmon_temp_min: + return nvme_get_temp_thresh(data->ctrl, channel, true, val); + case hwmon_temp_crit: + *val = KELVIN_TO_MILLICELSIUS(data->ctrl->cctemp); + return 0; + default: + break; + } + + mutex_lock(&data->read_lock); + err = nvme_hwmon_get_smart_log(data); + if (err) + goto unlock; + + switch (attr) { + case hwmon_temp_input: + if (!channel) + temp = get_unaligned_le16(log->temperature); + else + temp = le16_to_cpu(log->temp_sensor[channel - 1]); + *val = KELVIN_TO_MILLICELSIUS(temp); + break; + case hwmon_temp_alarm: + *val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE); + break; + default: + err = -EOPNOTSUPP; + break; + } +unlock: + mutex_unlock(&data->read_lock); + return err; +} + +static int nvme_hwmon_write(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long val) +{ + struct nvme_hwmon_data *data = dev_get_drvdata(dev); + + switch (attr) { + case hwmon_temp_max: + return nvme_set_temp_thresh(data->ctrl, channel, false, val); + case hwmon_temp_min: + return nvme_set_temp_thresh(data->ctrl, channel, true, val); + default: + break; + } + + return -EOPNOTSUPP; +} + +static const char * const nvme_hwmon_sensor_names[] = { + "Composite", + "Sensor 1", + "Sensor 2", + "Sensor 3", + "Sensor 4", + "Sensor 5", + "Sensor 6", + "Sensor 7", + "Sensor 8", +}; + +static int nvme_hwmon_read_string(struct device *dev, + enum hwmon_sensor_types type, u32 attr, + int channel, const char **str) +{ + *str = nvme_hwmon_sensor_names[channel]; + return 0; +} + +static umode_t nvme_hwmon_is_visible(const void *_data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + const struct nvme_hwmon_data *data = _data; + + switch (attr) { + case hwmon_temp_crit: + if (!channel && data->ctrl->cctemp) + return 0444; + break; + case hwmon_temp_max: + case hwmon_temp_min: + if ((!channel && data->ctrl->wctemp) || + (channel && data->log.temp_sensor[channel - 1])) { + if (data->ctrl->quirks & + NVME_QUIRK_NO_TEMP_THRESH_CHANGE) + return 0444; + return 0644; + } + break; + case hwmon_temp_alarm: + if (!channel) + return 0444; + break; + case hwmon_temp_input: + case hwmon_temp_label: + if (!channel || data->log.temp_sensor[channel - 1]) + return 0444; + break; + default: + break; + } + return 0; +} + +static const struct hwmon_channel_info *nvme_hwmon_info[] = { + HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ), + HWMON_CHANNEL_INFO(temp, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_CRIT | HWMON_T_LABEL | HWMON_T_ALARM, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL), + NULL +}; + +static const struct hwmon_ops nvme_hwmon_ops = { + .is_visible = nvme_hwmon_is_visible, + .read = nvme_hwmon_read, + .read_string = nvme_hwmon_read_string, + .write = nvme_hwmon_write, +}; + +static const struct hwmon_chip_info nvme_hwmon_chip_info = { + .ops = &nvme_hwmon_ops, + .info = nvme_hwmon_info, +}; + +void nvme_hwmon_init(struct nvme_ctrl *ctrl) +{ + struct device *dev = ctrl->dev; + struct nvme_hwmon_data *data; + struct device *hwmon; + int err; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return; + + data->ctrl = ctrl; + mutex_init(&data->read_lock); + + err = nvme_hwmon_get_smart_log(data); + if (err) { + dev_warn(dev, "Failed to read smart log (error %d)\n", err); + devm_kfree(dev, data); + return; + } + + hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data, + &nvme_hwmon_chip_info, + NULL); + if (IS_ERR(hwmon)) { + dev_warn(dev, "Failed to instantiate hwmon device\n"); + devm_kfree(dev, data); + } +} diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 30de7efef003..797c18337d96 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -95,6 +95,7 @@ void nvme_failover_req(struct request *req) } break; case NVME_SC_HOST_PATH_ERROR: + case NVME_SC_HOST_ABORTED_CMD: /* * Temporary transport disruption in talking to the controller. * Try to send on a new path. @@ -158,9 +159,11 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) struct nvme_ns *ns; mutex_lock(&ctrl->scan_lock); + down_read(&ctrl->namespaces_rwsem); list_for_each_entry(ns, &ctrl->namespaces, list) if (nvme_mpath_clear_current_path(ns)) kblockd_schedule_work(&ns->head->requeue_work); + up_read(&ctrl->namespaces_rwsem); mutex_unlock(&ctrl->scan_lock); } @@ -444,8 +447,14 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) { struct nvme_ana_group_desc *desc = base + offset; - u32 nr_nsids = le32_to_cpu(desc->nnsids); - size_t nsid_buf_size = nr_nsids * sizeof(__le32); + u32 nr_nsids; + size_t nsid_buf_size; + + if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc))) + return -EINVAL; + + nr_nsids = le32_to_cpu(desc->nnsids); + nsid_buf_size = nr_nsids * sizeof(__le32); if (WARN_ON_ONCE(desc->grpid == 0)) return -EINVAL; @@ -465,8 +474,6 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, return error; offset += nsid_buf_size; - if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc))) - return -EINVAL; } return 0; @@ -522,14 +529,13 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl, return 0; } -static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only) +static int nvme_read_ana_log(struct nvme_ctrl *ctrl) { u32 nr_change_groups = 0; int error; mutex_lock(&ctrl->ana_lock); - error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, - groups_only ? NVME_ANA_LOG_RGO : 0, + error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0, ctrl->ana_log_buf, ctrl->ana_log_size, 0); if (error) { dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error); @@ -565,7 +571,7 @@ static void nvme_ana_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work); - nvme_read_ana_log(ctrl, false); + nvme_read_ana_log(ctrl); } static void nvme_anatt_timeout(struct timer_list *t) @@ -715,7 +721,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) goto out; } - error = nvme_read_ana_log(ctrl, true); + error = nvme_read_ana_log(ctrl); if (error) goto out_free_ana_log_buf; return 0; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 22e8401352c2..3b9cbe0668fa 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -115,6 +115,11 @@ enum nvme_quirks { * Prevent tag overlap between queues */ NVME_QUIRK_SHARED_TAGS = (1 << 13), + + /* + * Don't change the value of the temperature threshold feature + */ + NVME_QUIRK_NO_TEMP_THRESH_CHANGE = (1 << 14), }; /* @@ -231,6 +236,8 @@ struct nvme_ctrl { u16 kas; u8 npss; u8 apsta; + u16 wctemp; + u16 cctemp; u32 oaes; u32 aen_result; u32 ctratt; @@ -419,9 +426,20 @@ static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl) return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); } -static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) +/* + * Convert a 512B sector number to a device logical block number. + */ +static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector) +{ + return sector >> (ns->lba_shift - SECTOR_SHIFT); +} + +/* + * Convert a device logical block number to a 512B sector number. + */ +static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba) { - return (sector >> (ns->lba_shift - 9)); + return lba << (ns->lba_shift - SECTOR_SHIFT); } static inline void nvme_end_request(struct request *req, __le16 status, @@ -446,6 +464,11 @@ static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl) put_device(ctrl->device); } +static inline bool nvme_is_aen_req(u16 qid, __u16 command_id) +{ + return !qid && command_id >= NVME_AQ_BLK_MQ_DEPTH; +} + void nvme_complete_rq(struct request *req); bool nvme_cancel_request(struct request *req, void *data, bool reserved); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, @@ -652,4 +675,10 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) return dev_to_disk(dev)->private_data; } +#ifdef CONFIG_NVME_HWMON +void nvme_hwmon_init(struct nvme_ctrl *ctrl); +#else +static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { } +#endif + #endif /* _NVME_H */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 869f462e6b6e..dcaad5831cee 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -925,7 +925,6 @@ static void nvme_pci_complete_rq(struct request *req) struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_dev *dev = iod->nvmeq->dev; - nvme_cleanup_cmd(req); if (blk_integrity_rq(req)) dma_unmap_page(dev->dev, iod->meta_dma, rq_integrity_vec(req)->bv_len, rq_data_dir(req)); @@ -968,8 +967,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvmeq->qid == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { + if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) { nvme_complete_async_event(&nvmeq->dev->ctrl, cqe->status, &cqe->result); return; @@ -2982,7 +2980,7 @@ static int nvme_suspend(struct device *dev) /* * Clearing npss forces a controller reset on resume. The - * correct value will be resdicovered then. + * correct value will be rediscovered then. */ ret = nvme_disable_prepare_reset(ndev, true); ctrl->npss = 0; @@ -3082,7 +3080,8 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_DEALLOCATE_ZEROES, }, { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | - NVME_QUIRK_MEDIUM_PRIO_SQ }, + NVME_QUIRK_MEDIUM_PRIO_SQ | + NVME_QUIRK_NO_TEMP_THRESH_CHANGE }, { PCI_VDEVICE(INTEL, 0xf1a6), /* Intel 760p/Pro 7600p */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f19a28b4e997..dce59459ed41 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1160,8 +1160,6 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, } ib_dma_unmap_sg(ibdev, req->sg_table.sgl, req->nents, rq_dma_dir(rq)); - - nvme_cleanup_cmd(rq); sg_free_table_chained(&req->sg_table, SG_CHUNK_SIZE); } @@ -1501,8 +1499,8 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_rdma_queue_idx(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + if (unlikely(nvme_is_aen_req(nvme_rdma_queue_idx(queue), + cqe->command_id))) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else @@ -1768,7 +1766,6 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, if (unlikely(err < 0)) { dev_err(queue->ctrl->ctrl.device, "Failed to map data (%d)\n", err); - nvme_cleanup_cmd(rq); goto err; } @@ -1779,18 +1776,19 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge, req->mr ? &req->reg_wr.wr : NULL); - if (unlikely(err)) { - nvme_rdma_unmap_data(queue, rq); - goto err; - } + if (unlikely(err)) + goto err_unmap; return BLK_STS_OK; +err_unmap: + nvme_rdma_unmap_data(queue, rq); err: if (err == -ENOMEM || err == -EAGAIN) ret = BLK_STS_RESOURCE; else ret = BLK_STS_IOERR; + nvme_cleanup_cmd(rq); unmap_qe: ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command), DMA_TO_DEVICE); @@ -2133,8 +2131,16 @@ err_unreg_client: static void __exit nvme_rdma_cleanup_module(void) { + struct nvme_rdma_ctrl *ctrl; + nvmf_unregister_transport(&nvme_rdma_transport); ib_unregister_client(&nvme_rdma_ib_client); + + mutex_lock(&nvme_rdma_ctrl_mutex); + list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) + nvme_delete_ctrl(&ctrl->ctrl); + mutex_unlock(&nvme_rdma_ctrl_mutex); + flush_workqueue(nvme_delete_wq); } module_init(nvme_rdma_init_module); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 770dbcbc999e..6d43b23a0fc8 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -491,8 +491,8 @@ static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_tcp_queue_id(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) + if (unlikely(nvme_is_aen_req(nvme_tcp_queue_id(queue), + cqe->command_id))) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else @@ -2219,7 +2219,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx) struct nvme_tcp_queue *queue = hctx->driver_data; struct sock *sk = queue->sock->sk; - if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue)) + if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue)) sk_busy_loop(sk, true); nvme_tcp_try_recv(queue); return queue->nr_cqe; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 831a062d27cb..56c21b501185 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -31,7 +31,7 @@ u64 nvmet_get_log_page_offset(struct nvme_command *cmd) static void nvmet_execute_get_log_page_noop(struct nvmet_req *req) { - nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len)); + nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->transfer_len)); } static void nvmet_execute_get_log_page_error(struct nvmet_req *req) @@ -134,7 +134,7 @@ static void nvmet_execute_get_log_page_smart(struct nvmet_req *req) u16 status = NVME_SC_INTERNAL; unsigned long flags; - if (req->data_len != sizeof(*log)) + if (req->transfer_len != sizeof(*log)) goto out; log = kzalloc(sizeof(*log), GFP_KERNEL); @@ -196,7 +196,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req) u16 status = NVME_SC_INTERNAL; size_t len; - if (req->data_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32)) + if (req->transfer_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32)) goto out; mutex_lock(&ctrl->lock); @@ -206,7 +206,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req) len = ctrl->nr_changed_ns * sizeof(__le32); status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len); if (!status) - status = nvmet_zero_sgl(req, len, req->data_len - len); + status = nvmet_zero_sgl(req, len, req->transfer_len - len); ctrl->nr_changed_ns = 0; nvmet_clear_aen_bit(req, NVME_AEN_BIT_NS_ATTR); mutex_unlock(&ctrl->lock); @@ -282,6 +282,36 @@ out: nvmet_req_complete(req, status); } +static void nvmet_execute_get_log_page(struct nvmet_req *req) +{ + if (!nvmet_check_data_len(req, nvmet_get_log_page_len(req->cmd))) + return; + + switch (req->cmd->get_log_page.lid) { + case NVME_LOG_ERROR: + return nvmet_execute_get_log_page_error(req); + case NVME_LOG_SMART: + return nvmet_execute_get_log_page_smart(req); + case NVME_LOG_FW_SLOT: + /* + * We only support a single firmware slot which always is + * active, so we can zero out the whole firmware slot log and + * still claim to fully implement this mandatory log page. + */ + return nvmet_execute_get_log_page_noop(req); + case NVME_LOG_CHANGED_NS: + return nvmet_execute_get_log_changed_ns(req); + case NVME_LOG_CMD_EFFECTS: + return nvmet_execute_get_log_cmd_effects_ns(req); + case NVME_LOG_ANA: + return nvmet_execute_get_log_page_ana(req); + } + pr_err("unhandled lid %d on qid %d\n", + req->cmd->get_log_page.lid, req->sq->qid); + req->error_loc = offsetof(struct nvme_get_log_page_command, lid); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); +} + static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -565,6 +595,28 @@ out: nvmet_req_complete(req, status); } +static void nvmet_execute_identify(struct nvmet_req *req) +{ + if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE)) + return; + + switch (req->cmd->identify.cns) { + case NVME_ID_CNS_NS: + return nvmet_execute_identify_ns(req); + case NVME_ID_CNS_CTRL: + return nvmet_execute_identify_ctrl(req); + case NVME_ID_CNS_NS_ACTIVE_LIST: + return nvmet_execute_identify_nslist(req); + case NVME_ID_CNS_NS_DESC_LIST: + return nvmet_execute_identify_desclist(req); + } + + pr_err("unhandled identify cns %d on qid %d\n", + req->cmd->identify.cns, req->sq->qid); + req->error_loc = offsetof(struct nvme_identify, cns); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); +} + /* * A "minimum viable" abort implementation: the command is mandatory in the * spec, but we are not required to do any useful work. We couldn't really @@ -574,6 +626,8 @@ out: */ static void nvmet_execute_abort(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; nvmet_set_result(req, 1); nvmet_req_complete(req, 0); } @@ -658,6 +712,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_NUM_QUEUES: nvmet_set_result(req, @@ -721,6 +778,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { /* * These features are mandatory in the spec, but we don't @@ -785,6 +845,9 @@ void nvmet_execute_async_event(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; + if (!nvmet_check_data_len(req, 0)) + return; + mutex_lock(&ctrl->lock); if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) { mutex_unlock(&ctrl->lock); @@ -801,6 +864,9 @@ void nvmet_execute_keep_alive(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; + if (!nvmet_check_data_len(req, 0)) + return; + pr_debug("ctrl %d update keep-alive timer for %d secs\n", ctrl->cntlid, ctrl->kato); @@ -813,77 +879,36 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) struct nvme_command *cmd = req->cmd; u16 ret; + if (nvme_is_fabrics(cmd)) + return nvmet_parse_fabrics_cmd(req); + if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) + return nvmet_parse_discovery_cmd(req); + ret = nvmet_check_ctrl_status(req, cmd); if (unlikely(ret)) return ret; switch (cmd->common.opcode) { case nvme_admin_get_log_page: - req->data_len = nvmet_get_log_page_len(cmd); - - switch (cmd->get_log_page.lid) { - case NVME_LOG_ERROR: - req->execute = nvmet_execute_get_log_page_error; - return 0; - case NVME_LOG_SMART: - req->execute = nvmet_execute_get_log_page_smart; - return 0; - case NVME_LOG_FW_SLOT: - /* - * We only support a single firmware slot which always - * is active, so we can zero out the whole firmware slot - * log and still claim to fully implement this mandatory - * log page. - */ - req->execute = nvmet_execute_get_log_page_noop; - return 0; - case NVME_LOG_CHANGED_NS: - req->execute = nvmet_execute_get_log_changed_ns; - return 0; - case NVME_LOG_CMD_EFFECTS: - req->execute = nvmet_execute_get_log_cmd_effects_ns; - return 0; - case NVME_LOG_ANA: - req->execute = nvmet_execute_get_log_page_ana; - return 0; - } - break; + req->execute = nvmet_execute_get_log_page; + return 0; case nvme_admin_identify: - req->data_len = NVME_IDENTIFY_DATA_SIZE; - switch (cmd->identify.cns) { - case NVME_ID_CNS_NS: - req->execute = nvmet_execute_identify_ns; - return 0; - case NVME_ID_CNS_CTRL: - req->execute = nvmet_execute_identify_ctrl; - return 0; - case NVME_ID_CNS_NS_ACTIVE_LIST: - req->execute = nvmet_execute_identify_nslist; - return 0; - case NVME_ID_CNS_NS_DESC_LIST: - req->execute = nvmet_execute_identify_desclist; - return 0; - } - break; + req->execute = nvmet_execute_identify; + return 0; case nvme_admin_abort_cmd: req->execute = nvmet_execute_abort; - req->data_len = 0; return 0; case nvme_admin_set_features: req->execute = nvmet_execute_set_features; - req->data_len = 0; return 0; case nvme_admin_get_features: req->execute = nvmet_execute_get_features; - req->data_len = 0; return 0; case nvme_admin_async_event: req->execute = nvmet_execute_async_event; - req->data_len = 0; return 0; case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; - req->data_len = 0; return 0; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 3a67e244e568..28438b833c1b 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -892,14 +892,10 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, } if (unlikely(!req->sq->ctrl)) - /* will return an error for any Non-connect command: */ + /* will return an error for any non-connect command: */ status = nvmet_parse_connect_cmd(req); else if (likely(req->sq->qid != 0)) status = nvmet_parse_io_cmd(req); - else if (nvme_is_fabrics(req->cmd)) - status = nvmet_parse_fabrics_cmd(req); - else if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) - status = nvmet_parse_discovery_cmd(req); else status = nvmet_parse_admin_cmd(req); @@ -930,15 +926,17 @@ void nvmet_req_uninit(struct nvmet_req *req) } EXPORT_SYMBOL_GPL(nvmet_req_uninit); -void nvmet_req_execute(struct nvmet_req *req) +bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len) { - if (unlikely(req->data_len != req->transfer_len)) { + if (unlikely(data_len != req->transfer_len)) { req->error_loc = offsetof(struct nvme_common_command, dptr); nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); - } else - req->execute(req); + return false; + } + + return true; } -EXPORT_SYMBOL_GPL(nvmet_req_execute); +EXPORT_SYMBOL_GPL(nvmet_check_data_len); int nvmet_req_alloc_sgl(struct nvmet_req *req) { @@ -966,7 +964,7 @@ int nvmet_req_alloc_sgl(struct nvmet_req *req) } req->sg = sgl_alloc(req->transfer_len, GFP_KERNEL, &req->sg_cnt); - if (!req->sg) + if (unlikely(!req->sg)) return -ENOMEM; return 0; diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 3764a8900850..0c2274b21e15 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -157,7 +157,7 @@ static size_t discovery_log_entries(struct nvmet_req *req) return entries; } -static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) +static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) { const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry); struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -171,6 +171,16 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) u16 status = 0; void *buffer; + if (!nvmet_check_data_len(req, data_len)) + return; + + if (req->cmd->get_log_page.lid != NVME_LOG_DISC) { + req->error_loc = + offsetof(struct nvme_get_log_page_command, lid); + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + goto out; + } + /* Spec requires dword aligned offsets */ if (offset & 0x3) { status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; @@ -227,20 +237,35 @@ out: nvmet_req_complete(req, status); } -static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req) +static void nvmet_execute_disc_identify(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; + const char model[] = "Linux"; u16 status = 0; + if (!nvmet_check_data_len(req, NVME_IDENTIFY_DATA_SIZE)) + return; + + if (req->cmd->identify.cns != NVME_ID_CNS_CTRL) { + req->error_loc = offsetof(struct nvme_identify, cns); + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + goto out; + } + id = kzalloc(sizeof(*id), GFP_KERNEL); if (!id) { status = NVME_SC_INTERNAL; goto out; } + memset(id->sn, ' ', sizeof(id->sn)); + bin2hex(id->sn, &ctrl->subsys->serial, + min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2)); memset(id->fr, ' ', sizeof(id->fr)); - strncpy((char *)id->fr, UTS_RELEASE, sizeof(id->fr)); + memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' '); + memcpy_and_pad(id->fr, sizeof(id->fr), + UTS_RELEASE, strlen(UTS_RELEASE), ' '); /* no limit on data transfer sizes for now */ id->mdts = 0; @@ -273,6 +298,9 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_KATO: stat = nvmet_set_feat_kato(req); @@ -296,6 +324,9 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req) u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 stat = 0; + if (!nvmet_check_data_len(req, 0)) + return; + switch (cdw10 & 0xff) { case NVME_FEAT_KATO: nvmet_get_feat_kato(req); @@ -328,47 +359,22 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) switch (cmd->common.opcode) { case nvme_admin_set_features: req->execute = nvmet_execute_disc_set_features; - req->data_len = 0; return 0; case nvme_admin_get_features: req->execute = nvmet_execute_disc_get_features; - req->data_len = 0; return 0; case nvme_admin_async_event: req->execute = nvmet_execute_async_event; - req->data_len = 0; return 0; case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; - req->data_len = 0; return 0; case nvme_admin_get_log_page: - req->data_len = nvmet_get_log_page_len(cmd); - - switch (cmd->get_log_page.lid) { - case NVME_LOG_DISC: - req->execute = nvmet_execute_get_disc_log_page; - return 0; - default: - pr_err("unsupported get_log_page lid %d\n", - cmd->get_log_page.lid); - req->error_loc = - offsetof(struct nvme_get_log_page_command, lid); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; - } + req->execute = nvmet_execute_disc_get_log_page; + return 0; case nvme_admin_identify: - req->data_len = NVME_IDENTIFY_DATA_SIZE; - switch (cmd->identify.cns) { - case NVME_ID_CNS_CTRL: - req->execute = - nvmet_execute_identify_disc_ctrl; - return 0; - default: - pr_err("unsupported identify cns %d\n", - cmd->identify.cns); - req->error_loc = offsetof(struct nvme_identify, cns); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; - } + req->execute = nvmet_execute_disc_identify; + return 0; default: pr_err("unhandled cmd %d\n", cmd->common.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index d16b55ffe79f..f7297473d9eb 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -12,6 +12,9 @@ static void nvmet_execute_prop_set(struct nvmet_req *req) u64 val = le64_to_cpu(req->cmd->prop_set.value); u16 status = 0; + if (!nvmet_check_data_len(req, 0)) + return; + if (req->cmd->prop_set.attrib & 1) { req->error_loc = offsetof(struct nvmf_property_set_command, attrib); @@ -38,6 +41,9 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) u16 status = 0; u64 val = 0; + if (!nvmet_check_data_len(req, 0)) + return; + if (req->cmd->prop_get.attrib & 1) { switch (le32_to_cpu(req->cmd->prop_get.offset)) { case NVME_REG_CAP: @@ -82,11 +88,9 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) switch (cmd->fabrics.fctype) { case nvme_fabrics_type_property_set: - req->data_len = 0; req->execute = nvmet_execute_prop_set; break; case nvme_fabrics_type_property_get: - req->data_len = 0; req->execute = nvmet_execute_prop_get; break; default: @@ -147,6 +151,9 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) struct nvmet_ctrl *ctrl = NULL; u16 status = 0; + if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data))) + return; + d = kmalloc(sizeof(*d), GFP_KERNEL); if (!d) { status = NVME_SC_INTERNAL; @@ -211,6 +218,9 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) u16 qid = le16_to_cpu(c->qid); u16 status = 0; + if (!nvmet_check_data_len(req, sizeof(struct nvmf_connect_data))) + return; + d = kmalloc(sizeof(*d), GFP_KERNEL); if (!d) { status = NVME_SC_INTERNAL; @@ -281,7 +291,6 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } - req->data_len = sizeof(struct nvmf_connect_data); if (cmd->connect.qid == 0) req->execute = nvmet_execute_admin_connect; else diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index ce8d819f86cc..a0db6371b43e 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1495,20 +1495,20 @@ static void nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_ls_iod *iod) { - struct fcnvme_ls_disconnect_rqst *rqst = - (struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf; - struct fcnvme_ls_disconnect_acc *acc = - (struct fcnvme_ls_disconnect_acc *)iod->rspbuf; + struct fcnvme_ls_disconnect_assoc_rqst *rqst = + (struct fcnvme_ls_disconnect_assoc_rqst *)iod->rqstbuf; + struct fcnvme_ls_disconnect_assoc_acc *acc = + (struct fcnvme_ls_disconnect_assoc_acc *)iod->rspbuf; struct nvmet_fc_tgt_assoc *assoc; int ret = 0; memset(acc, 0, sizeof(*acc)); - if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_rqst)) + if (iod->rqstdatalen < sizeof(struct fcnvme_ls_disconnect_assoc_rqst)) ret = VERR_DISCONN_LEN; else if (rqst->desc_list_len != fcnvme_lsdesc_len( - sizeof(struct fcnvme_ls_disconnect_rqst))) + sizeof(struct fcnvme_ls_disconnect_assoc_rqst))) ret = VERR_DISCONN_RQST_LEN; else if (rqst->associd.desc_tag != cpu_to_be32(FCNVME_LSDESC_ASSOC_ID)) ret = VERR_ASSOC_ID; @@ -1523,8 +1523,11 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, fcnvme_lsdesc_len( sizeof(struct fcnvme_lsdesc_disconn_cmd))) ret = VERR_DISCONN_CMD_LEN; - else if ((rqst->discon_cmd.scope != FCNVME_DISCONN_ASSOCIATION) && - (rqst->discon_cmd.scope != FCNVME_DISCONN_CONNECTION)) + /* + * As the standard changed on the LS, check if old format and scope + * something other than Association (e.g. 0). + */ + else if (rqst->discon_cmd.rsvd8[0]) ret = VERR_DISCONN_SCOPE; else { /* match an active association */ @@ -1556,8 +1559,8 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, nvmet_fc_format_rsp_hdr(acc, FCNVME_LS_ACC, fcnvme_lsdesc_len( - sizeof(struct fcnvme_ls_disconnect_acc)), - FCNVME_LS_DISCONNECT); + sizeof(struct fcnvme_ls_disconnect_assoc_acc)), + FCNVME_LS_DISCONNECT_ASSOC); /* release get taken in nvmet_fc_find_target_assoc */ nvmet_fc_tgt_a_put(iod->assoc); @@ -1632,7 +1635,7 @@ nvmet_fc_handle_ls_rqst(struct nvmet_fc_tgtport *tgtport, /* Creates an IO Queue/Connection */ nvmet_fc_ls_create_connection(tgtport, iod); break; - case FCNVME_LS_DISCONNECT: + case FCNVME_LS_DISCONNECT_ASSOC: /* Terminate a Queue/Connection or the Association */ nvmet_fc_ls_disconnect(tgtport, iod); break; @@ -2015,7 +2018,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) } /* data transfer complete, resume with nvmet layer */ - nvmet_req_execute(&fod->req); + fod->req.execute(&fod->req); break; case NVMET_FCOP_READDATA: @@ -2231,7 +2234,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, * can invoke the nvmet_layer now. If read data, cmd completion will * push the data */ - nvmet_req_execute(&fod->req); + fod->req.execute(&fod->req); return; transport_error: @@ -2299,7 +2302,7 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port, /* validate iu, so the connection id can be used to find the queue */ if ((cmdiubuf_len != sizeof(*cmdiu)) || - (cmdiu->scsi_id != NVME_CMD_SCSI_ID) || + (cmdiu->format_id != NVME_CMD_FORMAT_ID) || (cmdiu->fc_id != NVME_CMD_FC_ID) || (be16_to_cpu(cmdiu->iu_len) != (sizeof(*cmdiu)/4))) return -EIO; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 32008d85172b..b6fca0e421ef 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -147,8 +147,12 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) int sg_cnt = req->sg_cnt; struct bio *bio; struct scatterlist *sg; + struct blk_plug plug; sector_t sector; - int op, op_flags = 0, i; + int op, i; + + if (!nvmet_check_data_len(req, nvmet_rw_len(req))) + return; if (!req->sg_cnt) { nvmet_req_complete(req, 0); @@ -156,21 +160,20 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) } if (req->cmd->rw.opcode == nvme_cmd_write) { - op = REQ_OP_WRITE; - op_flags = REQ_SYNC | REQ_IDLE; + op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA)) - op_flags |= REQ_FUA; + op |= REQ_FUA; } else { op = REQ_OP_READ; } if (is_pci_p2pdma_page(sg_page(req->sg))) - op_flags |= REQ_NOMERGE; + op |= REQ_NOMERGE; sector = le64_to_cpu(req->cmd->rw.slba); sector <<= (req->ns->blksize_shift - 9); - if (req->data_len <= NVMET_MAX_INLINE_DATA_LEN) { + if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { bio = &req->b.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { @@ -180,8 +183,9 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) bio->bi_iter.bi_sector = sector; bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; - bio_set_op_attrs(bio, op, op_flags); + bio->bi_opf = op; + blk_start_plug(&plug); for_each_sg(req->sg, sg, req->sg_cnt, i) { while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset) != sg->length) { @@ -190,7 +194,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES)); bio_set_dev(bio, req->ns->bdev); bio->bi_iter.bi_sector = sector; - bio_set_op_attrs(bio, op, op_flags); + bio->bi_opf = op; bio_chain(bio, prev); submit_bio(prev); @@ -201,12 +205,16 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) } submit_bio(bio); + blk_finish_plug(&plug); } static void nvmet_bdev_execute_flush(struct nvmet_req *req) { struct bio *bio = &req->b.inline_bio; + if (!nvmet_check_data_len(req, 0)) + return; + bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); bio_set_dev(bio, req->ns->bdev); bio->bi_private = req; @@ -261,12 +269,10 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req) if (bio) { bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; - if (status) { - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); - } else { + if (status) + bio_io_error(bio); + else submit_bio(bio); - } } else { nvmet_req_complete(req, status); } @@ -274,6 +280,9 @@ static void nvmet_bdev_execute_discard(struct nvmet_req *req) static void nvmet_bdev_execute_dsm(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, nvmet_dsm_len(req))) + return; + switch (le32_to_cpu(req->cmd->dsm.attributes)) { case NVME_DSMGMT_AD: nvmet_bdev_execute_discard(req); @@ -295,6 +304,9 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) sector_t nr_sector; int ret; + if (!nvmet_check_data_len(req, 0)) + return; + sector = le64_to_cpu(write_zeroes->slba) << (req->ns->blksize_shift - 9); nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) << @@ -319,20 +331,15 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req) case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_bdev_execute_rw; - req->data_len = nvmet_rw_len(req); return 0; case nvme_cmd_flush: req->execute = nvmet_bdev_execute_flush; - req->data_len = 0; return 0; case nvme_cmd_dsm: req->execute = nvmet_bdev_execute_dsm; - req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) * - sizeof(struct nvme_dsm_range); return 0; case nvme_cmd_write_zeroes: req->execute = nvmet_bdev_execute_write_zeroes; - req->data_len = 0; return 0; default: pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode, diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 05453f5d1448..caebfce06605 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -126,7 +126,7 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) mempool_free(req->f.bvec, req->ns->bvec_pool); } - if (unlikely(ret != req->data_len)) + if (unlikely(ret != req->transfer_len)) status = errno_to_nvme_status(req, ret); nvmet_req_complete(req, status); } @@ -146,7 +146,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) is_sync = true; pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift; - if (unlikely(pos + req->data_len > req->ns->size)) { + if (unlikely(pos + req->transfer_len > req->ns->size)) { nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC)); return true; } @@ -173,7 +173,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) nr_bvec--; } - if (WARN_ON_ONCE(total_len != req->data_len)) { + if (WARN_ON_ONCE(total_len != req->transfer_len)) { ret = -EIO; goto complete; } @@ -232,6 +232,9 @@ static void nvmet_file_execute_rw(struct nvmet_req *req) { ssize_t nr_bvec = req->sg_cnt; + if (!nvmet_check_data_len(req, nvmet_rw_len(req))) + return; + if (!req->sg_cnt || !nr_bvec) { nvmet_req_complete(req, 0); return; @@ -273,6 +276,8 @@ static void nvmet_file_flush_work(struct work_struct *w) static void nvmet_file_execute_flush(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; INIT_WORK(&req->f.work, nvmet_file_flush_work); schedule_work(&req->f.work); } @@ -331,6 +336,8 @@ static void nvmet_file_dsm_work(struct work_struct *w) static void nvmet_file_execute_dsm(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, nvmet_dsm_len(req))) + return; INIT_WORK(&req->f.work, nvmet_file_dsm_work); schedule_work(&req->f.work); } @@ -359,6 +366,8 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w) static void nvmet_file_execute_write_zeroes(struct nvmet_req *req) { + if (!nvmet_check_data_len(req, 0)) + return; INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work); schedule_work(&req->f.work); } @@ -371,20 +380,15 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req) case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_file_execute_rw; - req->data_len = nvmet_rw_len(req); return 0; case nvme_cmd_flush: req->execute = nvmet_file_execute_flush; - req->data_len = 0; return 0; case nvme_cmd_dsm: req->execute = nvmet_file_execute_dsm; - req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) * - sizeof(struct nvme_dsm_range); return 0; case nvme_cmd_write_zeroes: req->execute = nvmet_file_execute_write_zeroes; - req->data_len = 0; return 0; default: pr_err("unhandled cmd for file ns %d on qid %d\n", diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 11f5aea97d1b..a758bb3d5dd4 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -76,7 +76,6 @@ static void nvme_loop_complete_rq(struct request *req) { struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); - nvme_cleanup_cmd(req); sg_free_table_chained(&iod->sg_table, SG_CHUNK_SIZE); nvme_complete_rq(req); } @@ -102,8 +101,8 @@ static void nvme_loop_queue_response(struct nvmet_req *req) * aborts. We don't even bother to allocate a struct request * for them but rather special case them here. */ - if (unlikely(nvme_loop_queue_idx(queue) == 0 && - cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { + if (unlikely(nvme_is_aen_req(nvme_loop_queue_idx(queue), + cqe->command_id))) { nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); } else { @@ -126,7 +125,7 @@ static void nvme_loop_execute_work(struct work_struct *work) struct nvme_loop_iod *iod = container_of(work, struct nvme_loop_iod, work); - nvmet_req_execute(&iod->req); + iod->req.execute(&iod->req); } static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index c51f8dd01dc4..46df45e837c9 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -304,8 +304,6 @@ struct nvmet_req { } f; }; int sg_cnt; - /* data length as parsed from the command: */ - size_t data_len; /* data length as parsed from the SGL descriptor: */ size_t transfer_len; @@ -375,7 +373,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req); bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops); void nvmet_req_uninit(struct nvmet_req *req); -void nvmet_req_execute(struct nvmet_req *req); +bool nvmet_check_data_len(struct nvmet_req *req, size_t data_len); void nvmet_req_complete(struct nvmet_req *req, u16 status); int nvmet_req_alloc_sgl(struct nvmet_req *req); void nvmet_req_free_sgl(struct nvmet_req *req); @@ -495,6 +493,12 @@ static inline u32 nvmet_rw_len(struct nvmet_req *req) req->ns->blksize_shift; } +static inline u32 nvmet_dsm_len(struct nvmet_req *req) +{ + return (le32_to_cpu(req->cmd->dsm.nr) + 1) * + sizeof(struct nvme_dsm_range); +} + u16 errno_to_nvme_status(struct nvmet_req *req, int errno); /* Convert a 32-bit number to a 16-bit 0's based number */ diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 36d906a7f70d..37d262a65877 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -603,7 +603,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc) return; } - nvmet_req_execute(&rsp->req); + rsp->req.execute(&rsp->req); } static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len, @@ -672,13 +672,13 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp, return 0; ret = nvmet_req_alloc_sgl(&rsp->req); - if (ret < 0) + if (unlikely(ret < 0)) goto error_out; ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, 0, addr, key, nvmet_data_dir(&rsp->req)); - if (ret < 0) + if (unlikely(ret < 0)) goto error_out; rsp->n_rdma += ret; @@ -746,7 +746,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp) queue->cm_id->port_num, &rsp->read_cqe, NULL)) nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR); } else { - nvmet_req_execute(&rsp->req); + rsp->req.execute(&rsp->req); } return true; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index d535080b781f..af674fc0bb1e 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -320,7 +320,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl; u32 len = le32_to_cpu(sgl->length); - if (!cmd->req.data_len) + if (!len) return 0; if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) | @@ -813,13 +813,11 @@ free_crypto: static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd, struct nvmet_req *req) { + size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); int ret; - /* recover the expected data transfer length */ - req->data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); - if (!nvme_is_write(cmd->req.cmd) || - req->data_len > cmd->req.port->inline_data_size) { + data_len > cmd->req.port->inline_data_size) { nvmet_prepare_receive_pdu(queue); return; } @@ -932,7 +930,7 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) goto out; } - nvmet_req_execute(&queue->cmd->req); + queue->cmd->req.execute(&queue->cmd->req); out: nvmet_prepare_receive_pdu(queue); return ret; @@ -1052,7 +1050,7 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) nvmet_tcp_prep_recv_ddgst(cmd); return 0; } - nvmet_req_execute(&cmd->req); + cmd->req.execute(&cmd->req); } nvmet_prepare_receive_pdu(queue); @@ -1092,7 +1090,7 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) && cmd->rbytes_done == cmd->req.transfer_len) - nvmet_req_execute(&cmd->req); + cmd->req.execute(&cmd->req); ret = 0; out: nvmet_prepare_receive_pdu(queue); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 7989703b883c..6bd610ee2cd7 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -324,8 +324,10 @@ int of_reserved_mem_device_init_by_idx(struct device *dev, if (!target) return -ENODEV; - if (!of_device_is_available(target)) + if (!of_device_is_available(target)) { + of_node_put(target); return 0; + } rmem = __find_rmem(target); of_node_put(target); diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 480a21e2ed39..92e895d86458 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -1207,6 +1207,7 @@ static int __init unittest_data_add(void) of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node); if (!unittest_data_node) { pr_warn("%s: No tree to attach; not running tests\n", __func__); + kfree(unittest_data); return -ENODATA; } diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 3b7ffd0234e9..9ff0538ee83a 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1626,12 +1626,6 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev, goto free_regulators; } - ret = regulator_enable(reg); - if (ret < 0) { - regulator_put(reg); - goto free_regulators; - } - opp_table->regulators[i] = reg; } @@ -1645,10 +1639,8 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev, return opp_table; free_regulators: - while (i--) { - regulator_disable(opp_table->regulators[i]); - regulator_put(opp_table->regulators[i]); - } + while (i != 0) + regulator_put(opp_table->regulators[--i]); kfree(opp_table->regulators); opp_table->regulators = NULL; @@ -1674,10 +1666,8 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table) /* Make sure there are no concurrent readers while updating opp_table */ WARN_ON(!list_empty(&opp_table->opp_list)); - for (i = opp_table->regulator_count - 1; i >= 0; i--) { - regulator_disable(opp_table->regulators[i]); + for (i = opp_table->regulator_count - 1; i >= 0; i--) regulator_put(opp_table->regulators[i]); - } _free_set_opp_data(opp_table); diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 1813f5ad5fa2..1cbb58240b80 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -77,8 +77,6 @@ static struct dev_pm_opp *_find_opp_of_np(struct opp_table *opp_table, { struct dev_pm_opp *opp; - lockdep_assert_held(&opp_table_lock); - mutex_lock(&opp_table->lock); list_for_each_entry(opp, &opp_table->opp_list, node) { @@ -665,6 +663,13 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table) return 0; } + /* + * Re-initialize list_kref every time we add static OPPs to the OPP + * table as the reference count may be 0 after the last tie static OPPs + * were removed. + */ + kref_init(&opp_table->list_kref); + /* We have opp-table node now, iterate over it and add OPPs */ for_each_available_child_of_node(opp_table->np, np) { opp = _opp_add_static_v2(opp_table, dev, np); diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index 648ddb7f038a..c6800d220920 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -87,7 +87,7 @@ FUNC_GROUP_DECL(MACLINK3, L23); #define K25 7 SIG_EXPR_LIST_DECL_SESG(K25, MACLINK4, MACLINK4, SIG_DESC_SET(SCU410, 7)); -SIG_EXPR_LIST_DECL_SESG(K25, SDA14, SDA14, SIG_DESC_SET(SCU4B0, 7)); +SIG_EXPR_LIST_DECL_SESG(K25, SDA14, I2C14, SIG_DESC_SET(SCU4B0, 7)); PIN_DECL_2(K25, GPIOA7, MACLINK4, SDA14); FUNC_GROUP_DECL(MACLINK4, K25); @@ -1262,13 +1262,13 @@ GROUP_DECL(SPI1, AB11, AC11, AA11); #define AD11 206 SIG_EXPR_LIST_DECL_SEMG(AD11, SPI1DQ2, QSPI1, SPI1, SIG_DESC_SET(SCU438, 14)); SIG_EXPR_LIST_DECL_SEMG(AD11, TXD13, UART13G1, UART13, - SIG_DESC_SET(SCU438, 14)); + SIG_DESC_CLEAR(SCU4B8, 2), SIG_DESC_SET(SCU4D8, 14)); PIN_DECL_2(AD11, GPIOZ6, SPI1DQ2, TXD13); #define AF10 207 SIG_EXPR_LIST_DECL_SEMG(AF10, SPI1DQ3, QSPI1, SPI1, SIG_DESC_SET(SCU438, 15)); SIG_EXPR_LIST_DECL_SEMG(AF10, RXD13, UART13G1, UART13, - SIG_DESC_SET(SCU438, 15)); + SIG_DESC_CLEAR(SCU4B8, 3), SIG_DESC_SET(SCU4D8, 15)); PIN_DECL_2(AF10, GPIOZ7, SPI1DQ3, RXD13); GROUP_DECL(QSPI1, AB11, AC11, AA11, AD11, AF10); @@ -1440,91 +1440,85 @@ FUNC_GROUP_DECL(RGMII2, D4, C2, C1, D3, E4, F5, D2, E3, D1, F4, E2, E1); FUNC_GROUP_DECL(RMII2, D4, C2, C1, D3, D2, D1, F4, E2, E1); #define AB4 232 -SIG_EXPR_LIST_DECL_SESG(AB4, SD3CLK, SD3, SIG_DESC_SET(SCU400, 24)); -PIN_DECL_1(AB4, GPIO18D0, SD3CLK); +SIG_EXPR_LIST_DECL_SEMG(AB4, EMMCCLK, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 24)); +PIN_DECL_1(AB4, GPIO18D0, EMMCCLK); #define AA4 233 -SIG_EXPR_LIST_DECL_SESG(AA4, SD3CMD, SD3, SIG_DESC_SET(SCU400, 25)); -PIN_DECL_1(AA4, GPIO18D1, SD3CMD); +SIG_EXPR_LIST_DECL_SEMG(AA4, EMMCCMD, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 25)); +PIN_DECL_1(AA4, GPIO18D1, EMMCCMD); #define AC4 234 -SIG_EXPR_LIST_DECL_SESG(AC4, SD3DAT0, SD3, SIG_DESC_SET(SCU400, 26)); -PIN_DECL_1(AC4, GPIO18D2, SD3DAT0); +SIG_EXPR_LIST_DECL_SEMG(AC4, EMMCDAT0, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 26)); +PIN_DECL_1(AC4, GPIO18D2, EMMCDAT0); #define AA5 235 -SIG_EXPR_LIST_DECL_SESG(AA5, SD3DAT1, SD3, SIG_DESC_SET(SCU400, 27)); -PIN_DECL_1(AA5, GPIO18D3, SD3DAT1); +SIG_EXPR_LIST_DECL_SEMG(AA5, EMMCDAT1, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 27)); +PIN_DECL_1(AA5, GPIO18D3, EMMCDAT1); #define Y5 236 -SIG_EXPR_LIST_DECL_SESG(Y5, SD3DAT2, SD3, SIG_DESC_SET(SCU400, 28)); -PIN_DECL_1(Y5, GPIO18D4, SD3DAT2); +SIG_EXPR_LIST_DECL_SEMG(Y5, EMMCDAT2, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 28)); +PIN_DECL_1(Y5, GPIO18D4, EMMCDAT2); #define AB5 237 -SIG_EXPR_LIST_DECL_SESG(AB5, SD3DAT3, SD3, SIG_DESC_SET(SCU400, 29)); -PIN_DECL_1(AB5, GPIO18D5, SD3DAT3); +SIG_EXPR_LIST_DECL_SEMG(AB5, EMMCDAT3, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 29)); +PIN_DECL_1(AB5, GPIO18D5, EMMCDAT3); #define AB6 238 -SIG_EXPR_LIST_DECL_SESG(AB6, SD3CD, SD3, SIG_DESC_SET(SCU400, 30)); -PIN_DECL_1(AB6, GPIO18D6, SD3CD); +SIG_EXPR_LIST_DECL_SEMG(AB6, EMMCCD, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 30)); +PIN_DECL_1(AB6, GPIO18D6, EMMCCD); #define AC5 239 -SIG_EXPR_LIST_DECL_SESG(AC5, SD3WP, SD3, SIG_DESC_SET(SCU400, 31)); -PIN_DECL_1(AC5, GPIO18D7, SD3WP); +SIG_EXPR_LIST_DECL_SEMG(AC5, EMMCWP, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 31)); +PIN_DECL_1(AC5, GPIO18D7, EMMCWP); -FUNC_GROUP_DECL(SD3, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5); +GROUP_DECL(EMMCG1, AB4, AA4, AC4, AB6, AC5); +GROUP_DECL(EMMCG4, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5); #define Y1 240 SIG_EXPR_LIST_DECL_SEMG(Y1, FWSPIDCS, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y1, VBCS, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y1, SD3DAT4, SD3DAT4, SIG_DESC_SET(SCU404, 0)); -PIN_DECL_3(Y1, GPIO18E0, FWSPIDCS, VBCS, SD3DAT4); -FUNC_GROUP_DECL(SD3DAT4, Y1); +SIG_EXPR_LIST_DECL_SEMG(Y1, EMMCDAT4, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 0)); +PIN_DECL_3(Y1, GPIO18E0, FWSPIDCS, VBCS, EMMCDAT4); #define Y2 241 SIG_EXPR_LIST_DECL_SEMG(Y2, FWSPIDCK, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y2, VBCK, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y2, SD3DAT5, SD3DAT5, SIG_DESC_SET(SCU404, 1)); -PIN_DECL_3(Y2, GPIO18E1, FWSPIDCK, VBCK, SD3DAT5); -FUNC_GROUP_DECL(SD3DAT5, Y2); +SIG_EXPR_LIST_DECL_SEMG(Y2, EMMCDAT5, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 1)); +PIN_DECL_3(Y2, GPIO18E1, FWSPIDCK, VBCK, EMMCDAT5); #define Y3 242 SIG_EXPR_LIST_DECL_SEMG(Y3, FWSPIDMOSI, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y3, VBMOSI, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y3, SD3DAT6, SD3DAT6, SIG_DESC_SET(SCU404, 2)); -PIN_DECL_3(Y3, GPIO18E2, FWSPIDMOSI, VBMOSI, SD3DAT6); -FUNC_GROUP_DECL(SD3DAT6, Y3); +SIG_EXPR_LIST_DECL_SEMG(Y3, EMMCDAT6, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 2)); +PIN_DECL_3(Y3, GPIO18E2, FWSPIDMOSI, VBMOSI, EMMCDAT6); #define Y4 243 SIG_EXPR_LIST_DECL_SEMG(Y4, FWSPIDMISO, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3)); SIG_EXPR_LIST_DECL_SESG(Y4, VBMISO, VB, SIG_DESC_SET(SCU500, 5)); -SIG_EXPR_LIST_DECL_SESG(Y4, SD3DAT7, SD3DAT7, SIG_DESC_SET(SCU404, 3)); -PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, SD3DAT7); -FUNC_GROUP_DECL(SD3DAT7, Y4); +SIG_EXPR_LIST_DECL_SEMG(Y4, EMMCDAT7, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 3)); +PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, EMMCDAT7); GROUP_DECL(FWSPID, Y1, Y2, Y3, Y4); GROUP_DECL(FWQSPID, Y1, Y2, Y3, Y4, AE12, AF12); +GROUP_DECL(EMMCG8, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5, Y1, Y2, Y3, Y4); FUNC_DECL_2(FWSPID, FWSPID, FWQSPID); FUNC_GROUP_DECL(VB, Y1, Y2, Y3, Y4); - +FUNC_DECL_3(EMMC, EMMCG1, EMMCG4, EMMCG8); /* * FIXME: Confirm bits and priorities are the right way around for the * following 4 pins */ #define AF25 244 -SIG_EXPR_LIST_DECL_SEMG(AF25, I3C3SCL, I3C3, I3C3, SIG_DESC_SET(SCU438, 20), - SIG_DESC_SET(SCU4D8, 20)); -SIG_EXPR_LIST_DECL_SESG(AF25, FSI1CLK, FSI1, SIG_DESC_CLEAR(SCU438, 20), - SIG_DESC_SET(SCU4D8, 20)); +SIG_EXPR_LIST_DECL_SEMG(AF25, I3C3SCL, I3C3, I3C3, SIG_DESC_SET(SCU438, 20)); +SIG_EXPR_LIST_DECL_SESG(AF25, FSI1CLK, FSI1, SIG_DESC_SET(SCU4D8, 20)); PIN_DECL_(AF25, SIG_EXPR_LIST_PTR(AF25, I3C3SCL), SIG_EXPR_LIST_PTR(AF25, FSI1CLK)); #define AE26 245 -SIG_EXPR_LIST_DECL_SEMG(AE26, I3C3SDA, I3C3, I3C3, SIG_DESC_SET(SCU438, 21), - SIG_DESC_SET(SCU4D8, 21)); -SIG_EXPR_LIST_DECL_SESG(AE26, FSI1DATA, FSI1, SIG_DESC_CLEAR(SCU438, 21), - SIG_DESC_SET(SCU4D8, 21)); +SIG_EXPR_LIST_DECL_SEMG(AE26, I3C3SDA, I3C3, I3C3, SIG_DESC_SET(SCU438, 21)); +SIG_EXPR_LIST_DECL_SESG(AE26, FSI1DATA, FSI1, SIG_DESC_SET(SCU4D8, 21)); PIN_DECL_(AE26, SIG_EXPR_LIST_PTR(AE26, I3C3SDA), SIG_EXPR_LIST_PTR(AE26, FSI1DATA)); @@ -1533,18 +1527,14 @@ FUNC_DECL_2(I3C3, HVI3C3, I3C3); FUNC_GROUP_DECL(FSI1, AF25, AE26); #define AE25 246 -SIG_EXPR_LIST_DECL_SEMG(AE25, I3C4SCL, I3C4, I3C4, SIG_DESC_SET(SCU438, 22), - SIG_DESC_SET(SCU4D8, 22)); -SIG_EXPR_LIST_DECL_SESG(AE25, FSI2CLK, FSI2, SIG_DESC_CLEAR(SCU438, 22), - SIG_DESC_SET(SCU4D8, 22)); +SIG_EXPR_LIST_DECL_SEMG(AE25, I3C4SCL, I3C4, I3C4, SIG_DESC_SET(SCU438, 22)); +SIG_EXPR_LIST_DECL_SESG(AE25, FSI2CLK, FSI2, SIG_DESC_SET(SCU4D8, 22)); PIN_DECL_(AE25, SIG_EXPR_LIST_PTR(AE25, I3C4SCL), SIG_EXPR_LIST_PTR(AE25, FSI2CLK)); #define AF24 247 -SIG_EXPR_LIST_DECL_SEMG(AF24, I3C4SDA, I3C4, I3C4, SIG_DESC_SET(SCU438, 23), - SIG_DESC_SET(SCU4D8, 23)); -SIG_EXPR_LIST_DECL_SESG(AF24, FSI2DATA, FSI2, SIG_DESC_CLEAR(SCU438, 23), - SIG_DESC_SET(SCU4D8, 23)); +SIG_EXPR_LIST_DECL_SEMG(AF24, I3C4SDA, I3C4, I3C4, SIG_DESC_SET(SCU438, 23)); +SIG_EXPR_LIST_DECL_SESG(AF24, FSI2DATA, FSI2, SIG_DESC_SET(SCU4D8, 23)); PIN_DECL_(AF24, SIG_EXPR_LIST_PTR(AF24, I3C4SDA), SIG_EXPR_LIST_PTR(AF24, FSI2DATA)); @@ -1574,6 +1564,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(A3), ASPEED_PINCTRL_PIN(AA11), ASPEED_PINCTRL_PIN(AA12), + ASPEED_PINCTRL_PIN(AA16), + ASPEED_PINCTRL_PIN(AA17), ASPEED_PINCTRL_PIN(AA23), ASPEED_PINCTRL_PIN(AA24), ASPEED_PINCTRL_PIN(AA25), @@ -1585,6 +1577,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AB11), ASPEED_PINCTRL_PIN(AB12), ASPEED_PINCTRL_PIN(AB15), + ASPEED_PINCTRL_PIN(AB16), + ASPEED_PINCTRL_PIN(AB17), ASPEED_PINCTRL_PIN(AB18), ASPEED_PINCTRL_PIN(AB19), ASPEED_PINCTRL_PIN(AB22), @@ -1602,6 +1596,7 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AC11), ASPEED_PINCTRL_PIN(AC12), ASPEED_PINCTRL_PIN(AC15), + ASPEED_PINCTRL_PIN(AC16), ASPEED_PINCTRL_PIN(AC17), ASPEED_PINCTRL_PIN(AC18), ASPEED_PINCTRL_PIN(AC19), @@ -1619,6 +1614,7 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AD12), ASPEED_PINCTRL_PIN(AD14), ASPEED_PINCTRL_PIN(AD15), + ASPEED_PINCTRL_PIN(AD16), ASPEED_PINCTRL_PIN(AD19), ASPEED_PINCTRL_PIN(AD20), ASPEED_PINCTRL_PIN(AD22), @@ -1634,8 +1630,11 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AE12), ASPEED_PINCTRL_PIN(AE14), ASPEED_PINCTRL_PIN(AE15), + ASPEED_PINCTRL_PIN(AE16), ASPEED_PINCTRL_PIN(AE18), ASPEED_PINCTRL_PIN(AE19), + ASPEED_PINCTRL_PIN(AE25), + ASPEED_PINCTRL_PIN(AE26), ASPEED_PINCTRL_PIN(AE7), ASPEED_PINCTRL_PIN(AE8), ASPEED_PINCTRL_PIN(AF10), @@ -1643,6 +1642,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(AF12), ASPEED_PINCTRL_PIN(AF14), ASPEED_PINCTRL_PIN(AF15), + ASPEED_PINCTRL_PIN(AF24), + ASPEED_PINCTRL_PIN(AF25), ASPEED_PINCTRL_PIN(AF7), ASPEED_PINCTRL_PIN(AF8), ASPEED_PINCTRL_PIN(AF9), @@ -1792,17 +1793,6 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = { ASPEED_PINCTRL_PIN(Y3), ASPEED_PINCTRL_PIN(Y4), ASPEED_PINCTRL_PIN(Y5), - ASPEED_PINCTRL_PIN(AB16), - ASPEED_PINCTRL_PIN(AA17), - ASPEED_PINCTRL_PIN(AB17), - ASPEED_PINCTRL_PIN(AE16), - ASPEED_PINCTRL_PIN(AC16), - ASPEED_PINCTRL_PIN(AA16), - ASPEED_PINCTRL_PIN(AD16), - ASPEED_PINCTRL_PIN(AF25), - ASPEED_PINCTRL_PIN(AE26), - ASPEED_PINCTRL_PIN(AE25), - ASPEED_PINCTRL_PIN(AF24), }; static const struct aspeed_pin_group aspeed_g6_groups[] = { @@ -1976,11 +1966,9 @@ static const struct aspeed_pin_group aspeed_g6_groups[] = { ASPEED_PINCTRL_GROUP(SALT9G1), ASPEED_PINCTRL_GROUP(SD1), ASPEED_PINCTRL_GROUP(SD2), - ASPEED_PINCTRL_GROUP(SD3), - ASPEED_PINCTRL_GROUP(SD3DAT4), - ASPEED_PINCTRL_GROUP(SD3DAT5), - ASPEED_PINCTRL_GROUP(SD3DAT6), - ASPEED_PINCTRL_GROUP(SD3DAT7), + ASPEED_PINCTRL_GROUP(EMMCG1), + ASPEED_PINCTRL_GROUP(EMMCG4), + ASPEED_PINCTRL_GROUP(EMMCG8), ASPEED_PINCTRL_GROUP(SGPM1), ASPEED_PINCTRL_GROUP(SGPS1), ASPEED_PINCTRL_GROUP(SIOONCTRL), @@ -2059,6 +2047,7 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = { ASPEED_PINCTRL_FUNC(ADC8), ASPEED_PINCTRL_FUNC(ADC9), ASPEED_PINCTRL_FUNC(BMCINT), + ASPEED_PINCTRL_FUNC(EMMC), ASPEED_PINCTRL_FUNC(ESPI), ASPEED_PINCTRL_FUNC(ESPIALT), ASPEED_PINCTRL_FUNC(FSI1), @@ -2191,11 +2180,6 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = { ASPEED_PINCTRL_FUNC(SALT9), ASPEED_PINCTRL_FUNC(SD1), ASPEED_PINCTRL_FUNC(SD2), - ASPEED_PINCTRL_FUNC(SD3), - ASPEED_PINCTRL_FUNC(SD3DAT4), - ASPEED_PINCTRL_FUNC(SD3DAT5), - ASPEED_PINCTRL_FUNC(SD3DAT6), - ASPEED_PINCTRL_FUNC(SD3DAT7), ASPEED_PINCTRL_FUNC(SGPM1), ASPEED_PINCTRL_FUNC(SGPS1), ASPEED_PINCTRL_FUNC(SIOONCTRL), diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h index a2c0d52e4f7b..140c5ce9fbc1 100644 --- a/drivers/pinctrl/aspeed/pinmux-aspeed.h +++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h @@ -508,7 +508,7 @@ struct aspeed_pin_desc { * @idx: The bit index in the register */ #define SIG_DESC_SET(reg, idx) SIG_DESC_IP_BIT(ASPEED_IP_SCU, reg, idx, 1) -#define SIG_DESC_CLEAR(reg, idx) SIG_DESC_IP_BIT(ASPEED_IP_SCU, reg, idx, 0) +#define SIG_DESC_CLEAR(reg, idx) { ASPEED_IP_SCU, reg, BIT_MASK(idx), 0, 0 } #define SIG_DESC_LIST_SYM(sig, group) sig_descs_ ## sig ## _ ## group #define SIG_DESC_LIST_DECL(sig, group, ...) \ @@ -738,6 +738,7 @@ struct aspeed_pin_desc { static const char *FUNC_SYM(func)[] = { __VA_ARGS__ } #define FUNC_DECL_2(func, one, two) FUNC_DECL_(func, #one, #two) +#define FUNC_DECL_3(func, one, two, three) FUNC_DECL_(func, #one, #two, #three) #define FUNC_GROUP_DECL(func, ...) \ GROUP_DECL(func, __VA_ARGS__); \ diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c index 6f7d3a2f2e97..42f7ab383ad9 100644 --- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c @@ -1,14 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2014-2017 Broadcom - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ /* @@ -853,7 +845,7 @@ static int iproc_gpio_probe(struct platform_device *pdev) /* optional GPIO interrupt support */ irq = platform_get_irq(pdev, 0); - if (irq) { + if (irq > 0) { struct irq_chip *irqc; struct gpio_irq_chip *girq; diff --git a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c index 2bf6af7df7d9..9fabc451550e 100644 --- a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c +++ b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c @@ -640,8 +640,8 @@ static int ns2_pinmux_enable(struct pinctrl_dev *pctrl_dev, const struct ns2_pin_function *func; const struct ns2_pin_group *grp; - if (grp_select > pinctrl->num_groups || - func_select > pinctrl->num_functions) + if (grp_select >= pinctrl->num_groups || + func_select >= pinctrl->num_functions) return -EINVAL; func = &pinctrl->functions[func_select]; diff --git a/drivers/pinctrl/berlin/pinctrl-as370.c b/drivers/pinctrl/berlin/pinctrl-as370.c index 44f8ccdbeeff..9dfdc275ee33 100644 --- a/drivers/pinctrl/berlin/pinctrl-as370.c +++ b/drivers/pinctrl/berlin/pinctrl-as370.c @@ -43,7 +43,7 @@ static const struct berlin_desc_group as370_soc_pinctrl_groups[] = { BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO5 */ BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO3 */ BERLIN_PINCTRL_FUNCTION(0x2, "pwm"), /* PWM5 */ - BERLIN_PINCTRL_FUNCTION(0x3, "spififib"), /* SPDIFIB */ + BERLIN_PINCTRL_FUNCTION(0x3, "spdifib"), /* SPDIFIB */ BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */ BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG5 */ BERLIN_PINCTRL_GROUP("I2S1_MCLK", 0x0, 0x3, 0x12, diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index aae51c507f59..2c419fa5d1c1 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -147,6 +147,7 @@ struct chv_pin_context { * @pctldesc: Pin controller description * @pctldev: Pointer to the pin controller device * @chip: GPIO chip in this pin controller + * @irqchip: IRQ chip in this pin controller * @regs: MMIO registers * @intr_lines: Stores mapping between 16 HW interrupt wires and GPIO * offset (in GPIO number space) @@ -162,6 +163,7 @@ struct chv_pinctrl { struct pinctrl_desc pctldesc; struct pinctrl_dev *pctldev; struct gpio_chip chip; + struct irq_chip irqchip; void __iomem *regs; unsigned intr_lines[16]; const struct chv_community *community; @@ -1466,16 +1468,6 @@ static int chv_gpio_irq_type(struct irq_data *d, unsigned int type) return 0; } -static struct irq_chip chv_gpio_irqchip = { - .name = "chv-gpio", - .irq_startup = chv_gpio_irq_startup, - .irq_ack = chv_gpio_irq_ack, - .irq_mask = chv_gpio_irq_mask, - .irq_unmask = chv_gpio_irq_unmask, - .irq_set_type = chv_gpio_irq_type, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - static void chv_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); @@ -1513,7 +1505,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1521,7 +1512,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1529,7 +1519,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Cyan"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1537,7 +1526,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Celes"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, {} @@ -1563,7 +1551,7 @@ static void chv_init_irq_valid_mask(struct gpio_chip *chip, intsel >>= CHV_PADCTRL0_INTSEL_SHIFT; if (intsel >= community->nirqs) - clear_bit(i, valid_mask); + clear_bit(desc->number, valid_mask); } } @@ -1629,7 +1617,15 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) } } - ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0, + pctrl->irqchip.name = "chv-gpio"; + pctrl->irqchip.irq_startup = chv_gpio_irq_startup; + pctrl->irqchip.irq_ack = chv_gpio_irq_ack; + pctrl->irqchip.irq_mask = chv_gpio_irq_mask; + pctrl->irqchip.irq_unmask = chv_gpio_irq_unmask; + pctrl->irqchip.irq_set_type = chv_gpio_irq_type; + pctrl->irqchip.flags = IRQCHIP_SKIP_SET_WAKE; + + ret = gpiochip_irqchip_add(chip, &pctrl->irqchip, 0, handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add IRQ chip\n"); @@ -1646,7 +1642,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) } } - gpiochip_set_chained_irqchip(chip, &chv_gpio_irqchip, irq, + gpiochip_set_chained_irqchip(chip, &pctrl->irqchip, irq, chv_gpio_irq_handler); return 0; } diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 1f13bcd0e4e1..83981ad66a71 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -52,6 +52,7 @@ #define PADCFG0_GPIROUTNMI BIT(17) #define PADCFG0_PMODE_SHIFT 10 #define PADCFG0_PMODE_MASK GENMASK(13, 10) +#define PADCFG0_PMODE_GPIO 0 #define PADCFG0_GPIORXDIS BIT(9) #define PADCFG0_GPIOTXDIS BIT(8) #define PADCFG0_GPIORXSTATE BIT(1) @@ -96,6 +97,7 @@ struct intel_pinctrl_context { * @pctldesc: Pin controller description * @pctldev: Pointer to the pin controller device * @chip: GPIO chip in this pin controller + * @irqchip: IRQ chip in this pin controller * @soc: SoC/PCH specific pin configuration data * @communities: All communities in this pin controller * @ncommunities: Number of communities in this pin controller @@ -108,6 +110,7 @@ struct intel_pinctrl { struct pinctrl_desc pctldesc; struct pinctrl_dev *pctldev; struct gpio_chip chip; + struct irq_chip irqchip; const struct intel_pinctrl_soc_data *soc; struct intel_community *communities; size_t ncommunities; @@ -330,7 +333,7 @@ static void intel_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s, cfg1 = readl(intel_get_padcfg(pctrl, pin, PADCFG1)); mode = (cfg0 & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT; - if (!mode) + if (mode == PADCFG0_PMODE_GPIO) seq_puts(s, "GPIO "); else seq_printf(s, "mode %d ", mode); @@ -456,6 +459,11 @@ static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input) writel(value, padcfg0); } +static int intel_gpio_get_gpio_mode(void __iomem *padcfg0) +{ + return (readl(padcfg0) & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT; +} + static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) { u32 value; @@ -489,7 +497,20 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, } padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0); + + /* + * If pin is already configured in GPIO mode, we assume that + * firmware provides correct settings. In such case we avoid + * potential glitches on the pin. Otherwise, for the pin in + * alternative mode, consumer has to supply respective flags. + */ + if (intel_gpio_get_gpio_mode(padcfg0) == PADCFG0_PMODE_GPIO) { + raw_spin_unlock_irqrestore(&pctrl->lock, flags); + return 0; + } + intel_gpio_set_gpio_mode(padcfg0); + /* Disable TX buffer and enable RX (this will be input) */ __intel_gpio_set_direction(padcfg0, true); @@ -1139,16 +1160,6 @@ static irqreturn_t intel_gpio_irq(int irq, void *data) return ret; } -static struct irq_chip intel_gpio_irqchip = { - .name = "intel-gpio", - .irq_ack = intel_gpio_irq_ack, - .irq_mask = intel_gpio_irq_mask, - .irq_unmask = intel_gpio_irq_unmask, - .irq_set_type = intel_gpio_irq_type, - .irq_set_wake = intel_gpio_irq_wake, - .flags = IRQCHIP_MASK_ON_SUSPEND, -}; - static int intel_gpio_add_pin_ranges(struct intel_pinctrl *pctrl, const struct intel_community *community) { @@ -1198,12 +1209,22 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq) pctrl->chip = intel_gpio_chip; + /* Setup GPIO chip */ pctrl->chip.ngpio = intel_gpio_ngpio(pctrl); pctrl->chip.label = dev_name(pctrl->dev); pctrl->chip.parent = pctrl->dev; pctrl->chip.base = -1; pctrl->irq = irq; + /* Setup IRQ chip */ + pctrl->irqchip.name = dev_name(pctrl->dev); + pctrl->irqchip.irq_ack = intel_gpio_irq_ack; + pctrl->irqchip.irq_mask = intel_gpio_irq_mask; + pctrl->irqchip.irq_unmask = intel_gpio_irq_unmask; + pctrl->irqchip.irq_set_type = intel_gpio_irq_type; + pctrl->irqchip.irq_set_wake = intel_gpio_irq_wake; + pctrl->irqchip.flags = IRQCHIP_MASK_ON_SUSPEND; + ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl); if (ret) { dev_err(pctrl->dev, "failed to register gpiochip\n"); @@ -1233,15 +1254,14 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq) return ret; } - ret = gpiochip_irqchip_add(&pctrl->chip, &intel_gpio_irqchip, 0, + ret = gpiochip_irqchip_add(&pctrl->chip, &pctrl->irqchip, 0, handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add irqchip\n"); return ret; } - gpiochip_set_chained_irqchip(&pctrl->chip, &intel_gpio_irqchip, irq, - NULL); + gpiochip_set_chained_irqchip(&pctrl->chip, &pctrl->irqchip, irq, NULL); return 0; } diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index 6462d3ca7ceb..f2f5fcd9a237 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -183,10 +183,10 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = { PIN_GRP_EXTRA("uart2", 9, 2, BIT(1) | BIT(13) | BIT(14) | BIT(19), BIT(1) | BIT(13) | BIT(14), BIT(1) | BIT(19), 18, 2, "gpio", "uart"), - PIN_GRP_GPIO("led0_od", 11, 1, BIT(20), "led"), - PIN_GRP_GPIO("led1_od", 12, 1, BIT(21), "led"), - PIN_GRP_GPIO("led2_od", 13, 1, BIT(22), "led"), - PIN_GRP_GPIO("led3_od", 14, 1, BIT(23), "led"), + PIN_GRP_GPIO_2("led0_od", 11, 1, BIT(20), BIT(20), 0, "led"), + PIN_GRP_GPIO_2("led1_od", 12, 1, BIT(21), BIT(21), 0, "led"), + PIN_GRP_GPIO_2("led2_od", 13, 1, BIT(22), BIT(22), 0, "led"), + PIN_GRP_GPIO_2("led3_od", 14, 1, BIT(23), BIT(23), 0, "led"), }; @@ -221,11 +221,11 @@ static const struct armada_37xx_pin_data armada_37xx_pin_sb = { }; static inline void armada_37xx_update_reg(unsigned int *reg, - unsigned int offset) + unsigned int *offset) { /* We never have more than 2 registers */ - if (offset >= GPIO_PER_REG) { - offset -= GPIO_PER_REG; + if (*offset >= GPIO_PER_REG) { + *offset -= GPIO_PER_REG; *reg += sizeof(u32); } } @@ -376,7 +376,7 @@ static inline void armada_37xx_irq_update_reg(unsigned int *reg, { int offset = irqd_to_hwirq(d); - armada_37xx_update_reg(reg, offset); + armada_37xx_update_reg(reg, &offset); } static int armada_37xx_gpio_direction_input(struct gpio_chip *chip, @@ -386,7 +386,7 @@ static int armada_37xx_gpio_direction_input(struct gpio_chip *chip, unsigned int reg = OUTPUT_EN; unsigned int mask; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); return regmap_update_bits(info->regmap, reg, mask, 0); @@ -399,7 +399,7 @@ static int armada_37xx_gpio_get_direction(struct gpio_chip *chip, unsigned int reg = OUTPUT_EN; unsigned int val, mask; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); regmap_read(info->regmap, reg, &val); @@ -413,7 +413,7 @@ static int armada_37xx_gpio_direction_output(struct gpio_chip *chip, unsigned int reg = OUTPUT_EN; unsigned int mask, val, ret; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); ret = regmap_update_bits(info->regmap, reg, mask, mask); @@ -434,7 +434,7 @@ static int armada_37xx_gpio_get(struct gpio_chip *chip, unsigned int offset) unsigned int reg = INPUT_VAL; unsigned int val, mask; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); regmap_read(info->regmap, reg, &val); @@ -449,7 +449,7 @@ static void armada_37xx_gpio_set(struct gpio_chip *chip, unsigned int offset, unsigned int reg = OUTPUT_VAL; unsigned int mask, val; - armada_37xx_update_reg(®, offset); + armada_37xx_update_reg(®, &offset); mask = BIT(offset); val = value ? mask : 0; diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c index 974973777395..ccdf0bb21414 100644 --- a/drivers/pinctrl/pinctrl-stmfx.c +++ b/drivers/pinctrl/pinctrl-stmfx.c @@ -585,19 +585,6 @@ static int stmfx_pinctrl_gpio_function_enable(struct stmfx_pinctrl *pctl) return stmfx_function_enable(pctl->stmfx, func); } -static int stmfx_pinctrl_gpio_init_valid_mask(struct gpio_chip *gc, - unsigned long *valid_mask, - unsigned int ngpios) -{ - struct stmfx_pinctrl *pctl = gpiochip_get_data(gc); - u32 n; - - for_each_clear_bit(n, &pctl->gpio_valid_mask, ngpios) - clear_bit(n, valid_mask); - - return 0; -} - static int stmfx_pinctrl_probe(struct platform_device *pdev) { struct stmfx *stmfx = dev_get_drvdata(pdev->dev.parent); @@ -660,7 +647,6 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) pctl->gpio_chip.ngpio = pctl->pctl_desc.npins; pctl->gpio_chip.can_sleep = true; pctl->gpio_chip.of_node = np; - pctl->gpio_chip.init_valid_mask = stmfx_pinctrl_gpio_init_valid_mask; ret = devm_gpiochip_add_data(pctl->dev, &pctl->gpio_chip, pctl); if (ret) { @@ -705,7 +691,7 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) static int stmfx_pinctrl_remove(struct platform_device *pdev) { - struct stmfx *stmfx = dev_get_platdata(&pdev->dev); + struct stmfx *stmfx = dev_get_drvdata(pdev->dev.parent); return stmfx_function_disable(stmfx, STMFX_FUNC_GPIO | diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 67d0199840fd..9d72ab593f13 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -149,11 +149,21 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg) err = -EFAULT; break; } - if (((req.extts.flags & ~PTP_EXTTS_VALID_FLAGS) || - req.extts.rsv[0] || req.extts.rsv[1]) && - cmd == PTP_EXTTS_REQUEST2) { - err = -EINVAL; - break; + if (cmd == PTP_EXTTS_REQUEST2) { + /* Tell the drivers to check the flags carefully. */ + req.extts.flags |= PTP_STRICT_FLAGS; + /* Make sure no reserved bit is set. */ + if ((req.extts.flags & ~PTP_EXTTS_VALID_FLAGS) || + req.extts.rsv[0] || req.extts.rsv[1]) { + err = -EINVAL; + break; + } + /* Ensure one of the rising/falling edge bits is set. */ + if ((req.extts.flags & PTP_ENABLE_FEATURE) && + (req.extts.flags & PTP_EXTTS_EDGES) == 0) { + err = -EINVAL; + break; + } } else if (cmd == PTP_EXTTS_REQUEST) { req.extts.flags &= PTP_EXTTS_V1_VALID_FLAGS; req.extts.rsv[0] = 0; diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 6ad51aa60c03..f877e77d9184 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -472,14 +472,7 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) if (err) return err; - /* - * .apply might have to round some values in *state, if possible - * read the actually implemented value back. - */ - if (chip->ops->get_state) - chip->ops->get_state(chip, pwm, &pwm->state); - else - pwm->state = *state; + pwm->state = *state; } else { /* * FIXME: restore the initial state in case of error. diff --git a/drivers/pwm/pwm-bcm-iproc.c b/drivers/pwm/pwm-bcm-iproc.c index 56c38cfae92c..1f829edd8ee7 100644 --- a/drivers/pwm/pwm-bcm-iproc.c +++ b/drivers/pwm/pwm-bcm-iproc.c @@ -187,6 +187,7 @@ static int iproc_pwmc_apply(struct pwm_chip *chip, struct pwm_device *pwm, static const struct pwm_ops iproc_pwm_ops = { .apply = iproc_pwmc_apply, .get_state = iproc_pwmc_get_state, + .owner = THIS_MODULE, }; static int iproc_pwmc_probe(struct platform_device *pdev) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index afe94470b67f..a46be221dbdc 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5053,6 +5053,19 @@ regulator_register(const struct regulator_desc *regulator_desc, init_data = regulator_of_get_init_data(dev, regulator_desc, config, &rdev->dev.of_node); + + /* + * Sometimes not all resources are probed already so we need to take + * that into account. This happens most the time if the ena_gpiod comes + * from a gpio extender or something else. + */ + if (PTR_ERR(init_data) == -EPROBE_DEFER) { + kfree(config); + kfree(rdev); + ret = -EPROBE_DEFER; + goto rinse; + } + /* * We need to keep track of any GPIO descriptor coming from the * device tree until we have handled it over to the core. If the diff --git a/drivers/regulator/da9062-regulator.c b/drivers/regulator/da9062-regulator.c index 56f3f72d7707..710e67081d53 100644 --- a/drivers/regulator/da9062-regulator.c +++ b/drivers/regulator/da9062-regulator.c @@ -136,7 +136,6 @@ static int da9062_buck_set_mode(struct regulator_dev *rdev, unsigned mode) static unsigned da9062_buck_get_mode(struct regulator_dev *rdev) { struct da9062_regulator *regl = rdev_get_drvdata(rdev); - struct regmap_field *field; unsigned int val, mode = 0; int ret; @@ -158,18 +157,7 @@ static unsigned da9062_buck_get_mode(struct regulator_dev *rdev) return REGULATOR_MODE_NORMAL; } - /* Detect current regulator state */ - ret = regmap_field_read(regl->suspend, &val); - if (ret < 0) - return 0; - - /* Read regulator mode from proper register, depending on state */ - if (val) - field = regl->suspend_sleep; - else - field = regl->sleep; - - ret = regmap_field_read(field, &val); + ret = regmap_field_read(regl->sleep, &val); if (ret < 0) return 0; @@ -208,21 +196,9 @@ static int da9062_ldo_set_mode(struct regulator_dev *rdev, unsigned mode) static unsigned da9062_ldo_get_mode(struct regulator_dev *rdev) { struct da9062_regulator *regl = rdev_get_drvdata(rdev); - struct regmap_field *field; int ret, val; - /* Detect current regulator state */ - ret = regmap_field_read(regl->suspend, &val); - if (ret < 0) - return 0; - - /* Read regulator mode from proper register, depending on state */ - if (val) - field = regl->suspend_sleep; - else - field = regl->sleep; - - ret = regmap_field_read(field, &val); + ret = regmap_field_read(regl->sleep, &val); if (ret < 0) return 0; @@ -408,10 +384,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = { __builtin_ffs((int)DA9062AA_BUCK1_MODE_MASK) - 1, sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_BUCK1_MODE_MASK)) - 1), - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VBUCK1_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_BUCK1_CONT, + __builtin_ffs((int)DA9062AA_BUCK1_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VBUCK1_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_BUCK1_CONF_MASK) - 1), }, { .desc.id = DA9061_ID_BUCK2, @@ -444,10 +420,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = { __builtin_ffs((int)DA9062AA_BUCK3_MODE_MASK) - 1, sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_BUCK3_MODE_MASK)) - 1), - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VBUCK3_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_BUCK3_CONT, + __builtin_ffs((int)DA9062AA_BUCK3_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VBUCK3_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_BUCK3_CONF_MASK) - 1), }, { .desc.id = DA9061_ID_BUCK3, @@ -480,10 +456,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = { __builtin_ffs((int)DA9062AA_BUCK4_MODE_MASK) - 1, sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_BUCK4_MODE_MASK)) - 1), - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VBUCK4_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_BUCK4_CONT, + __builtin_ffs((int)DA9062AA_BUCK4_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VBUCK4_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_BUCK4_CONF_MASK) - 1), }, { .desc.id = DA9061_ID_LDO1, @@ -509,10 +485,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO1_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO1_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO1_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO1_CONT, + __builtin_ffs((int)DA9062AA_LDO1_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO1_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO1_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO1_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - @@ -542,10 +518,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO2_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO2_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO2_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO2_CONT, + __builtin_ffs((int)DA9062AA_LDO2_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO2_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO2_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO2_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - @@ -575,10 +551,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO3_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO3_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO3_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO3_CONT, + __builtin_ffs((int)DA9062AA_LDO3_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO3_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO3_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO3_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - @@ -608,10 +584,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO4_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO4_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO4_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO4_CONT, + __builtin_ffs((int)DA9062AA_LDO4_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO4_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO4_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO4_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - @@ -652,10 +628,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { __builtin_ffs((int)DA9062AA_BUCK1_MODE_MASK) - 1, sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_BUCK1_MODE_MASK)) - 1), - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VBUCK1_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_BUCK1_CONT, + __builtin_ffs((int)DA9062AA_BUCK1_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VBUCK1_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_BUCK1_CONF_MASK) - 1), }, { .desc.id = DA9062_ID_BUCK2, @@ -688,10 +664,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { __builtin_ffs((int)DA9062AA_BUCK2_MODE_MASK) - 1, sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_BUCK2_MODE_MASK)) - 1), - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VBUCK2_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_BUCK2_CONT, + __builtin_ffs((int)DA9062AA_BUCK2_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VBUCK2_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_BUCK2_CONF_MASK) - 1), }, { .desc.id = DA9062_ID_BUCK3, @@ -724,10 +700,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { __builtin_ffs((int)DA9062AA_BUCK3_MODE_MASK) - 1, sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_BUCK3_MODE_MASK)) - 1), - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VBUCK3_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_BUCK3_CONT, + __builtin_ffs((int)DA9062AA_BUCK3_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VBUCK3_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_BUCK3_CONF_MASK) - 1), }, { .desc.id = DA9062_ID_BUCK4, @@ -760,10 +736,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { __builtin_ffs((int)DA9062AA_BUCK4_MODE_MASK) - 1, sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_BUCK4_MODE_MASK)) - 1), - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VBUCK4_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_BUCK4_CONT, + __builtin_ffs((int)DA9062AA_BUCK4_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VBUCK4_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_BUCK4_CONF_MASK) - 1), }, { .desc.id = DA9062_ID_LDO1, @@ -789,10 +765,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO1_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO1_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO1_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO1_CONT, + __builtin_ffs((int)DA9062AA_LDO1_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO1_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO1_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO1_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - @@ -822,10 +798,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO2_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO2_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO2_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO2_CONT, + __builtin_ffs((int)DA9062AA_LDO2_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO2_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO2_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO2_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - @@ -855,10 +831,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO3_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO3_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO3_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO3_CONT, + __builtin_ffs((int)DA9062AA_LDO3_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO3_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO3_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO3_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - @@ -888,10 +864,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = { sizeof(unsigned int) * 8 - __builtin_clz((DA9062AA_LDO4_SL_B_MASK)) - 1), .suspend_vsel_reg = DA9062AA_VLDO4_B, - .suspend = REG_FIELD(DA9062AA_DVC_1, - __builtin_ffs((int)DA9062AA_VLDO4_SEL_MASK) - 1, + .suspend = REG_FIELD(DA9062AA_LDO4_CONT, + __builtin_ffs((int)DA9062AA_LDO4_CONF_MASK) - 1, sizeof(unsigned int) * 8 - - __builtin_clz((DA9062AA_VLDO4_SEL_MASK)) - 1), + __builtin_clz(DA9062AA_LDO4_CONF_MASK) - 1), .oc_event = REG_FIELD(DA9062AA_STATUS_D, __builtin_ffs((int)DA9062AA_LDO4_ILIM_MASK) - 1, sizeof(unsigned int) * 8 - diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index d90a6fd8cbc7..f81533070058 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -144,8 +144,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct fixed_voltage_config *config; struct fixed_voltage_data *drvdata; - const struct fixed_dev_type *drvtype = - of_match_device(dev->driver->of_match_table, dev)->data; + const struct fixed_dev_type *drvtype = of_device_get_match_data(dev); struct regulator_config cfg = { }; enum gpiod_flags gflags; int ret; @@ -177,7 +176,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) drvdata->desc.type = REGULATOR_VOLTAGE; drvdata->desc.owner = THIS_MODULE; - if (drvtype->has_enable_clock) { + if (drvtype && drvtype->has_enable_clock) { drvdata->desc.ops = &fixed_voltage_clkenabled_ops; drvdata->enable_clock = devm_clk_get(dev, NULL); diff --git a/drivers/regulator/lochnagar-regulator.c b/drivers/regulator/lochnagar-regulator.c index ff97cc50f2eb..9b05e03ba830 100644 --- a/drivers/regulator/lochnagar-regulator.c +++ b/drivers/regulator/lochnagar-regulator.c @@ -210,6 +210,7 @@ static const struct regulator_desc lochnagar_regulators[] = { .enable_time = 3000, .ramp_delay = 1000, + .off_on_delay = 15000, .owner = THIS_MODULE, }, diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index afefb29ce1b0..87637eb6bcbc 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -231,12 +231,12 @@ static int of_get_regulation_constraints(struct device *dev, "regulator-off-in-suspend")) suspend_state->enabled = DISABLE_IN_SUSPEND; - if (!of_property_read_u32(np, "regulator-suspend-min-microvolt", - &pval)) + if (!of_property_read_u32(suspend_np, + "regulator-suspend-min-microvolt", &pval)) suspend_state->min_uV = pval; - if (!of_property_read_u32(np, "regulator-suspend-max-microvolt", - &pval)) + if (!of_property_read_u32(suspend_np, + "regulator-suspend-max-microvolt", &pval)) suspend_state->max_uV = pval; if (!of_property_read_u32(suspend_np, @@ -445,11 +445,20 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev, goto error; } - if (desc->of_parse_cb && desc->of_parse_cb(child, desc, config)) { - dev_err(dev, - "driver callback failed to parse DT for regulator %pOFn\n", - child); - goto error; + if (desc->of_parse_cb) { + int ret; + + ret = desc->of_parse_cb(child, desc, config); + if (ret) { + if (ret == -EPROBE_DEFER) { + of_node_put(child); + return ERR_PTR(-EPROBE_DEFER); + } + dev_err(dev, + "driver callback failed to parse DT for regulator %pOFn\n", + child); + goto error; + } } *node = child; diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index df5df1c495ad..689537927f6f 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -788,7 +788,13 @@ static int pfuze100_regulator_probe(struct i2c_client *client, /* SW2~SW4 high bit check and modify the voltage value table */ if (i >= sw_check_start && i <= sw_check_end) { - regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val); + ret = regmap_read(pfuze_chip->regmap, + desc->vsel_reg, &val); + if (ret) { + dev_err(&client->dev, "Fails to read from the register.\n"); + return ret; + } + if (val & sw_hi) { if (pfuze_chip->chip_id == PFUZE3000 || pfuze_chip->chip_id == PFUZE3001) { diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index db6c085da65e..0246b6f99fb5 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -735,8 +735,8 @@ static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = { static const struct rpmh_vreg_hw_data pmic5_bob = { .regulator_type = VRM, .ops = &rpmh_regulator_vrm_bypass_ops, - .voltage_range = REGULATOR_LINEAR_RANGE(300000, 0, 135, 32000), - .n_voltages = 136, + .voltage_range = REGULATOR_LINEAR_RANGE(3000000, 0, 31, 32000), + .n_voltages = 32, .pmic_mode_map = pmic_mode_map_pmic5_bob, .of_map_mode = rpmh_regulator_pmic4_bob_of_map_mode, }; diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c index cced1ffb896c..89b9314d64c9 100644 --- a/drivers/regulator/ti-abb-regulator.c +++ b/drivers/regulator/ti-abb-regulator.c @@ -173,19 +173,14 @@ static int ti_abb_wait_txdone(struct device *dev, struct ti_abb *abb) while (timeout++ <= abb->settling_time) { status = ti_abb_check_txdone(abb); if (status) - break; + return 0; udelay(1); } - if (timeout > abb->settling_time) { - dev_warn_ratelimited(dev, - "%s:TRANXDONE timeout(%duS) int=0x%08x\n", - __func__, timeout, readl(abb->int_base)); - return -ETIMEDOUT; - } - - return 0; + dev_warn_ratelimited(dev, "%s:TRANXDONE timeout(%duS) int=0x%08x\n", + __func__, timeout, readl(abb->int_base)); + return -ETIMEDOUT; } /** @@ -205,19 +200,14 @@ static int ti_abb_clear_all_txdone(struct device *dev, const struct ti_abb *abb) status = ti_abb_check_txdone(abb); if (!status) - break; + return 0; udelay(1); } - if (timeout > abb->settling_time) { - dev_warn_ratelimited(dev, - "%s:TRANXDONE timeout(%duS) int=0x%08x\n", - __func__, timeout, readl(abb->int_base)); - return -ETIMEDOUT; - } - - return 0; + dev_warn_ratelimited(dev, "%s:TRANXDONE timeout(%duS) int=0x%08x\n", + __func__, timeout, readl(abb->int_base)); + return -ETIMEDOUT; } /** diff --git a/drivers/reset/core.c b/drivers/reset/core.c index 213ff40dda11..3c9a64c1b7a8 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -76,7 +76,6 @@ static const char *rcdev_name(struct reset_controller_dev *rcdev) * of_reset_simple_xlate - translate reset_spec to the reset line number * @rcdev: a pointer to the reset controller device * @reset_spec: reset line specifier as found in the device tree - * @flags: a flags pointer to fill in (optional) * * This simple translation function should be used for reset controllers * with 1:1 mapping, where reset lines can be indexed by number without gaps. @@ -748,6 +747,7 @@ static void reset_control_array_put(struct reset_control_array *resets) for (i = 0; i < resets->num_rstcs; i++) __reset_control_put_internal(resets->rstc[i]); mutex_unlock(&reset_list_mutex); + kfree(resets); } /** @@ -825,9 +825,10 @@ int __device_reset(struct device *dev, bool optional) } EXPORT_SYMBOL_GPL(__device_reset); -/** +/* * APIs to manage an array of reset controls. */ + /** * of_reset_control_get_count - Count number of resets available with a device * diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 5542d9eadfe0..7d079154f849 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -116,7 +116,9 @@ int dasd_scan_partitions(struct dasd_block *block) return -ENODEV; } - rc = blkdev_reread_part(bdev); + mutex_lock(&bdev->bd_mutex); + rc = bdev_disk_changed(bdev, false); + mutex_unlock(&bdev->bd_mutex); if (rc) DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, rc %d", rc); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 45bdb47f84c1..9157e728a362 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -522,8 +522,7 @@ static int zcrypt_release(struct inode *inode, struct file *filp) if (filp->f_inode->i_cdev == &zcrypt_cdev) { struct zcdn_device *zcdndev; - if (mutex_lock_interruptible(&ap_perms_mutex)) - return -ERESTARTSYS; + mutex_lock(&ap_perms_mutex); zcdndev = find_zcdndev_by_devt(filp->f_inode->i_rdev); mutex_unlock(&ap_perms_mutex); if (zcdndev) { diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index e4b55f9aa062..65e31df37b1f 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -839,6 +839,7 @@ struct qeth_card { struct service_level qeth_service_level; struct qdio_ssqd_desc ssqd; debug_info_t *debug; + struct mutex sbp_lock; struct mutex conf_mutex; struct mutex discipline_mutex; struct napi_struct napi; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index dda274351c21..83794d7494d4 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -901,30 +901,30 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev, CCW_DEVID(cdev), dstat, cstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 64, 1); - return 1; + return -EIO; } if (dstat & DEV_STAT_UNIT_CHECK) { if (sense[SENSE_RESETTING_EVENT_BYTE] & SENSE_RESETTING_EVENT_FLAG) { QETH_CARD_TEXT(card, 2, "REVIND"); - return 1; + return -EIO; } if (sense[SENSE_COMMAND_REJECT_BYTE] & SENSE_COMMAND_REJECT_FLAG) { QETH_CARD_TEXT(card, 2, "CMDREJi"); - return 1; + return -EIO; } if ((sense[2] == 0xaf) && (sense[3] == 0xfe)) { QETH_CARD_TEXT(card, 2, "AFFE"); - return 1; + return -EIO; } if ((!sense[0]) && (!sense[1]) && (!sense[2]) && (!sense[3])) { QETH_CARD_TEXT(card, 2, "ZEROSEN"); return 0; } QETH_CARD_TEXT(card, 2, "DGENCHK"); - return 1; + return -EIO; } return 0; } diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index bd8143e51747..4bccdce19b5a 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -467,10 +467,14 @@ static void qeth_l2_set_promisc_mode(struct qeth_card *card) if (card->info.promisc_mode == enable) return; - if (qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE)) + if (qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE)) { qeth_setadp_promisc_mode(card, enable); - else if (card->options.sbp.reflect_promisc) - qeth_l2_promisc_to_bridge(card, enable); + } else { + mutex_lock(&card->sbp_lock); + if (card->options.sbp.reflect_promisc) + qeth_l2_promisc_to_bridge(card, enable); + mutex_unlock(&card->sbp_lock); + } } /* New MAC address is added to the hash table and marked to be written on card @@ -631,6 +635,7 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev) int rc; qeth_l2_vnicc_set_defaults(card); + mutex_init(&card->sbp_lock); if (gdev->dev.type == &qeth_generic_devtype) { rc = qeth_l2_create_device_attributes(&gdev->dev); @@ -804,10 +809,12 @@ static int qeth_l2_set_online(struct ccwgroup_device *gdev) } else card->info.hwtrap = 0; + mutex_lock(&card->sbp_lock); qeth_bridgeport_query_support(card); if (card->options.sbp.supported_funcs) dev_info(&card->gdev->dev, "The device represents a Bridge Capable Port\n"); + mutex_unlock(&card->sbp_lock); qeth_l2_register_dev_addr(card); @@ -1162,9 +1169,9 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) /* Role should not change by itself, but if it did, */ /* information from the hardware is authoritative. */ - mutex_lock(&data->card->conf_mutex); + mutex_lock(&data->card->sbp_lock); data->card->options.sbp.role = entry->role; - mutex_unlock(&data->card->conf_mutex); + mutex_unlock(&data->card->sbp_lock); snprintf(env_locrem, sizeof(env_locrem), "BRIDGEPORT=statechange"); snprintf(env_role, sizeof(env_role), "ROLE=%s", @@ -1230,9 +1237,9 @@ static void qeth_bridge_host_event_worker(struct work_struct *work) : (data->hostevs.lost_event_mask == 0x02) ? "Bridge port state change" : "Unknown reason"); - mutex_lock(&data->card->conf_mutex); + mutex_lock(&data->card->sbp_lock); data->card->options.sbp.hostnotification = 0; - mutex_unlock(&data->card->conf_mutex); + mutex_unlock(&data->card->sbp_lock); qeth_bridge_emit_host_event(data->card, anev_abort, 0, NULL, NULL); } else diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index f2c3b127b1e4..e2bcb26105a3 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -24,6 +24,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, if (qeth_l2_vnicc_is_in_use(card)) return sprintf(buf, "n/a (VNIC characteristics)\n"); + mutex_lock(&card->sbp_lock); if (qeth_card_hw_is_reachable(card) && card->options.sbp.supported_funcs) rc = qeth_bridgeport_query_ports(card, @@ -57,6 +58,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, else rc = sprintf(buf, "%s\n", word); } + mutex_unlock(&card->sbp_lock); return rc; } @@ -91,6 +93,7 @@ static ssize_t qeth_bridge_port_role_store(struct device *dev, return -EINVAL; mutex_lock(&card->conf_mutex); + mutex_lock(&card->sbp_lock); if (qeth_l2_vnicc_is_in_use(card)) rc = -EBUSY; @@ -104,6 +107,7 @@ static ssize_t qeth_bridge_port_role_store(struct device *dev, } else card->options.sbp.role = role; + mutex_unlock(&card->sbp_lock); mutex_unlock(&card->conf_mutex); return rc ? rc : count; @@ -158,6 +162,7 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, return rc; mutex_lock(&card->conf_mutex); + mutex_lock(&card->sbp_lock); if (qeth_l2_vnicc_is_in_use(card)) rc = -EBUSY; @@ -168,6 +173,7 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, } else card->options.sbp.hostnotification = enable; + mutex_unlock(&card->sbp_lock); mutex_unlock(&card->conf_mutex); return rc ? rc : count; @@ -223,6 +229,7 @@ static ssize_t qeth_bridgeport_reflect_store(struct device *dev, return -EINVAL; mutex_lock(&card->conf_mutex); + mutex_lock(&card->sbp_lock); if (qeth_l2_vnicc_is_in_use(card)) rc = -EBUSY; @@ -234,6 +241,7 @@ static ssize_t qeth_bridgeport_reflect_store(struct device *dev, rc = 0; } + mutex_unlock(&card->sbp_lock); mutex_unlock(&card->conf_mutex); return rc ? rc : count; @@ -269,6 +277,8 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) return; if (!card->options.sbp.supported_funcs) return; + + mutex_lock(&card->sbp_lock); if (card->options.sbp.role != QETH_SBP_ROLE_NONE) { /* Conditional to avoid spurious error messages */ qeth_bridgeport_setrole(card, card->options.sbp.role); @@ -280,8 +290,10 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) rc = qeth_bridgeport_an_set(card, 1); if (rc) card->options.sbp.hostnotification = 0; - } else + } else { qeth_bridgeport_an_set(card, 0); + } + mutex_unlock(&card->sbp_lock); } /* VNIC CHARS support */ diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 1b92f3c19ff3..90cf4691b8c3 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -898,7 +898,7 @@ config SCSI_SNI_53C710 config 53C700_LE_ON_BE bool - depends on SCSI_LASI700 + depends on SCSI_LASI700 || SCSI_SNI_53C710 default y config SCSI_STEX diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c index 5f8153c37f77..76751d6c7f0d 100644 --- a/drivers/scsi/ch.c +++ b/drivers/scsi/ch.c @@ -579,7 +579,6 @@ ch_release(struct inode *inode, struct file *file) scsi_changer *ch = file->private_data; scsi_device_put(ch->device); - ch->device = NULL; file->private_data = NULL; kref_put(&ch->ref, ch_destroy); return 0; diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 4971104b1817..f32da0ca529e 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -512,6 +512,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) unsigned int tpg_desc_tbl_off; unsigned char orig_transition_tmo; unsigned long flags; + bool transitioning_sense = false; if (!pg->expiry) { unsigned long transition_tmo = ALUA_FAILOVER_TIMEOUT * HZ; @@ -572,13 +573,19 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) goto retry; } /* - * Retry on ALUA state transition or if any - * UNIT ATTENTION occurred. + * If the array returns with 'ALUA state transition' + * sense code here it cannot return RTPG data during + * transition. So set the state to 'transitioning' directly. */ if (sense_hdr.sense_key == NOT_READY && - sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a) - err = SCSI_DH_RETRY; - else if (sense_hdr.sense_key == UNIT_ATTENTION) + sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a) { + transitioning_sense = true; + goto skip_rtpg; + } + /* + * Retry on any other UNIT ATTENTION occurred. + */ + if (sense_hdr.sense_key == UNIT_ATTENTION) err = SCSI_DH_RETRY; if (err == SCSI_DH_RETRY && pg->expiry != 0 && time_before(jiffies, pg->expiry)) { @@ -666,7 +673,11 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) off = 8 + (desc[7] * 4); } + skip_rtpg: spin_lock_irqsave(&pg->lock, flags); + if (transitioning_sense) + pg->state = SCSI_ACCESS_STATE_TRANSITIONING; + sdev_printk(KERN_INFO, sdev, "%s: port group %02x state %c %s supports %c%c%c%c%c%c%c\n", ALUA_DH_NAME, pg->group_id, print_alua_state(pg->state), diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index ac39ed79ccaa..216e557f703e 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -5477,6 +5477,8 @@ static int hpsa_ciss_submit(struct ctlr_info *h, return SCSI_MLQUEUE_HOST_BUSY; } + c->device = dev; + enqueue_cmd_and_start_io(h, c); /* the cmd'll come back via intr handler in complete_scsi_command() */ return 0; @@ -5548,6 +5550,7 @@ static int hpsa_ioaccel_submit(struct ctlr_info *h, hpsa_cmd_init(h, c->cmdindex, c); c->cmd_type = CMD_SCSI; c->scsi_cmd = cmd; + c->device = dev; rc = hpsa_scsi_ioaccel_raid_map(h, c); if (rc < 0) /* scsi_dma_map failed. */ rc = SCSI_MLQUEUE_HOST_BUSY; @@ -5555,6 +5558,7 @@ static int hpsa_ioaccel_submit(struct ctlr_info *h, hpsa_cmd_init(h, c->cmdindex, c); c->cmd_type = CMD_SCSI; c->scsi_cmd = cmd; + c->device = dev; rc = hpsa_scsi_ioaccel_direct_map(h, c); if (rc < 0) /* scsi_dma_map failed. */ rc = SCSI_MLQUEUE_HOST_BUSY; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index e91377a4cafe..e8813d26e594 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -9055,7 +9055,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) } } -#if defined(BUILD_NVME) /* Clear NVME stats */ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) { for (idx = 0; idx < phba->cfg_hdw_queue; idx++) { @@ -9063,7 +9062,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) sizeof(phba->sli4_hba.hdwq[idx].nvme_cstat)); } } -#endif /* Clear SCSI stats */ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) { diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index f4b879d25fe9..fc6e4546d738 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -851,9 +851,9 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) if (!(vport->fc_flag & FC_PT2PT)) { /* Check config parameter use-adisc or FCP-2 */ - if ((vport->cfg_use_adisc && (vport->fc_flag & FC_RSCN_MODE)) || + if (vport->cfg_use_adisc && ((vport->fc_flag & FC_RSCN_MODE) || ((ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) && - (ndlp->nlp_type & NLP_FCP_TARGET))) { + (ndlp->nlp_type & NLP_FCP_TARGET)))) { spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= NLP_NPR_ADISC; spin_unlock_irq(shost->host_lock); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index fe1097666de4..6822cd9ff8f1 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -528,7 +528,6 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba, list_del_init(&psb->list); psb->exch_busy = 0; psb->status = IOSTAT_SUCCESS; -#ifdef BUILD_NVME if (psb->cur_iocbq.iocb_flag == LPFC_IO_NVME) { qp->abts_nvme_io_bufs--; spin_unlock(&qp->abts_io_buf_list_lock); @@ -536,7 +535,6 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba, lpfc_sli4_nvme_xri_aborted(phba, axri, psb); return; } -#endif qp->abts_scsi_io_bufs--; spin_unlock(&qp->abts_io_buf_list_lock); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index a0c6945b8139..614f78dddafe 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -7866,7 +7866,7 @@ lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba) if (sli4_hba->hdwq) { for (eqidx = 0; eqidx < phba->cfg_irq_chann; eqidx++) { eq = phba->sli4_hba.hba_eq_hdl[eqidx].eq; - if (eq->queue_id == sli4_hba->mbx_cq->assoc_qid) { + if (eq && eq->queue_id == sli4_hba->mbx_cq->assoc_qid) { fpeq = eq; break; } diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 30bafd9d21e9..7259bce85e0e 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -440,9 +440,6 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj, valid = 0; if (ha->optrom_size == OPTROM_SIZE_2300 && start == 0) valid = 1; - else if (start == (ha->flt_region_boot * 4) || - start == (ha->flt_region_fw * 4)) - valid = 1; else if (IS_QLA24XX_TYPE(ha) || IS_QLA25XX(ha)) valid = 1; if (!valid) { @@ -489,8 +486,10 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj, "Writing flash region -- 0x%x/0x%x.\n", ha->optrom_region_start, ha->optrom_region_size); - ha->isp_ops->write_optrom(vha, ha->optrom_buffer, + rval = ha->isp_ops->write_optrom(vha, ha->optrom_buffer, ha->optrom_region_start, ha->optrom_region_size); + if (rval) + rval = -EIO; break; default: rval = -EINVAL; diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 28d587a89ba6..99f0a1a08143 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -253,7 +253,7 @@ qla2x00_process_els(struct bsg_job *bsg_job) srb_t *sp; const char *type; int req_sg_cnt, rsp_sg_cnt; - int rval = (DRIVER_ERROR << 16); + int rval = (DID_ERROR << 16); uint16_t nextlid = 0; if (bsg_request->msgcode == FC_BSG_RPT_ELS) { @@ -432,7 +432,7 @@ qla2x00_process_ct(struct bsg_job *bsg_job) struct Scsi_Host *host = fc_bsg_to_shost(bsg_job); scsi_qla_host_t *vha = shost_priv(host); struct qla_hw_data *ha = vha->hw; - int rval = (DRIVER_ERROR << 16); + int rval = (DID_ERROR << 16); int req_sg_cnt, rsp_sg_cnt; uint16_t loop_id; struct fc_port *fcport; @@ -1950,7 +1950,7 @@ qlafx00_mgmt_cmd(struct bsg_job *bsg_job) struct Scsi_Host *host = fc_bsg_to_shost(bsg_job); scsi_qla_host_t *vha = shost_priv(host); struct qla_hw_data *ha = vha->hw; - int rval = (DRIVER_ERROR << 16); + int rval = (DID_ERROR << 16); struct qla_mt_iocb_rqst_fx00 *piocb_rqst; srb_t *sp; int req_sg_cnt = 0, rsp_sg_cnt = 0; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 1cc6913f76c4..4a1f21c11758 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -702,6 +702,7 @@ qla2x00_execute_fw(scsi_qla_host_t *vha, uint32_t risc_addr) mcp->mb[2] = LSW(risc_addr); mcp->mb[3] = 0; mcp->mb[4] = 0; + mcp->mb[11] = 0; ha->flags.using_lr_setting = 0; if (IS_QLA25XX(ha) || IS_QLA81XX(ha) || IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) { @@ -746,7 +747,7 @@ qla2x00_execute_fw(scsi_qla_host_t *vha, uint32_t risc_addr) if (ha->flags.exchoffld_enabled) mcp->mb[4] |= ENABLE_EXCHANGE_OFFLD; - mcp->out_mb |= MBX_4|MBX_3|MBX_2|MBX_1; + mcp->out_mb |= MBX_4 | MBX_3 | MBX_2 | MBX_1 | MBX_11; mcp->in_mb |= MBX_3 | MBX_2 | MBX_1; } else { mcp->mb[1] = LSW(risc_addr); diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index 6afad68e5ba2..238240984bc1 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -76,9 +76,11 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha) * ensures no active vp_list traversal while the vport is removed * from the queue) */ - for (i = 0; i < 10 && atomic_read(&vha->vref_count); i++) - wait_event_timeout(vha->vref_waitq, - atomic_read(&vha->vref_count), HZ); + for (i = 0; i < 10; i++) { + if (wait_event_timeout(vha->vref_waitq, + !atomic_read(&vha->vref_count), HZ) > 0) + break; + } spin_lock_irqsave(&ha->vport_slock, flags); if (atomic_read(&vha->vref_count)) { diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 3568031c6504..726ad4cbf4a6 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1119,9 +1119,11 @@ qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) qla2x00_mark_all_devices_lost(vha, 0); - for (i = 0; i < 10; i++) - wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), - HZ); + for (i = 0; i < 10; i++) { + if (wait_event_timeout(vha->fcport_waitQ, + test_fcport_count(vha), HZ) > 0) + break; + } flush_workqueue(vha->hw->wq); } @@ -3224,6 +3226,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) req->req_q_in, req->req_q_out, rsp->rsp_q_in, rsp->rsp_q_out); ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0); + if (unlikely(!ha->wq)) { + ret = -ENOMEM; + goto probe_failed; + } if (ha->isp_ops->initialize_adapter(base_vha)) { ql_log(ql_log_fatal, base_vha, 0x00d6, @@ -3531,6 +3537,10 @@ qla2x00_shutdown(struct pci_dev *pdev) qla2x00_try_to_stop_firmware(vha); } + /* Disable timer */ + if (vha->timer_active) + qla2x00_stop_timer(vha); + /* Turn adapter off line */ vha->flags.online = 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 5447738906ac..91c007d26c1e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1883,7 +1883,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost) { unsigned int cmd_size, sgl_size; - sgl_size = scsi_mq_inline_sgl_size(shost); + sgl_size = max_t(unsigned int, sizeof(struct scatterlist), + scsi_mq_inline_sgl_size(shost)); cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size; if (scsi_host_get_prot(shost)) cmd_size += sizeof(struct scsi_data_buffer) + diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 64c96c7828ee..6d7362e7367e 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -730,6 +730,14 @@ sdev_store_delete(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct kernfs_node *kn; + struct scsi_device *sdev = to_scsi_device(dev); + + /* + * We need to try to get module, avoiding the module been removed + * during delete. + */ + if (scsi_device_get(sdev)) + return -ENODEV; kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); WARN_ON_ONCE(!kn); @@ -744,9 +752,10 @@ sdev_store_delete(struct device *dev, struct device_attribute *attr, * state into SDEV_DEL. */ device_remove_file(dev, attr); - scsi_remove_device(to_scsi_device(dev)); + scsi_remove_device(sdev); if (kn) sysfs_unbreak_active_protection(kn); + scsi_device_put(sdev); return count; }; static DEVICE_ATTR(delete, S_IWUSR, NULL, sdev_store_delete); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 03163ac5fe95..470ee6dc3f7e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1166,11 +1166,12 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) sector_t lba = sectors_to_logical(sdp, blk_rq_pos(rq)); sector_t threshold; unsigned int nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); - bool dif, dix; unsigned int mask = logical_to_sectors(sdp, 1) - 1; bool write = rq_data_dir(rq) == WRITE; unsigned char protect, fua; blk_status_t ret; + unsigned int dif; + bool dix; ret = scsi_init_io(cmd); if (ret != BLK_STS_OK) @@ -1290,9 +1291,17 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd) case REQ_OP_WRITE: return sd_setup_read_write_cmnd(cmd); case REQ_OP_ZONE_RESET: - return sd_zbc_setup_reset_cmnd(cmd, false); + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, + false); case REQ_OP_ZONE_RESET_ALL: - return sd_zbc_setup_reset_cmnd(cmd, true); + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, + true); + case REQ_OP_ZONE_OPEN: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_OPEN_ZONE, false); + case REQ_OP_ZONE_CLOSE: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_CLOSE_ZONE, false); + case REQ_OP_ZONE_FINISH: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_FINISH_ZONE, false); default: WARN_ON_ONCE(1); return BLK_STS_NOTSUPP; @@ -1960,6 +1969,9 @@ static int sd_done(struct scsi_cmnd *SCpnt) case REQ_OP_WRITE_SAME: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: if (!result) { good_bytes = blk_rq_bytes(req); scsi_set_resid(SCpnt, 0); diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 1eab779f812b..42fd3f00e4a5 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -209,11 +209,12 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp) extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); extern void sd_zbc_print_zones(struct scsi_disk *sdkp); -extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all); +blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, + unsigned char op, bool all); extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); -extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); +int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); #else /* CONFIG_BLK_DEV_ZONED */ @@ -225,8 +226,9 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {} -static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, - bool all) +static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, + unsigned char op, + bool all) { return BLK_STS_TARGET; } diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index de4019dc0f0b..0e5ede48f045 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -19,34 +19,27 @@ #include "sd.h" -/** - * sd_zbc_parse_report - Convert a zone descriptor to a struct blk_zone, - * @sdkp: The disk the report originated from - * @buf: Address of the report zone descriptor - * @zone: the destination zone structure - * - * All LBA sized values are converted to 512B sectors unit. - */ -static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, - struct blk_zone *zone) +static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, + unsigned int idx, report_zones_cb cb, void *data) { struct scsi_device *sdp = sdkp->device; + struct blk_zone zone = { 0 }; - memset(zone, 0, sizeof(struct blk_zone)); - - zone->type = buf[0] & 0x0f; - zone->cond = (buf[1] >> 4) & 0xf; + zone.type = buf[0] & 0x0f; + zone.cond = (buf[1] >> 4) & 0xf; if (buf[1] & 0x01) - zone->reset = 1; + zone.reset = 1; if (buf[1] & 0x02) - zone->non_seq = 1; - - zone->len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8])); - zone->start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16])); - zone->wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24])); - if (zone->type != ZBC_ZONE_TYPE_CONV && - zone->cond == ZBC_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; + zone.non_seq = 1; + + zone.len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8])); + zone.start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16])); + zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24])); + if (zone.type != ZBC_ZONE_TYPE_CONV && + zone.cond == ZBC_ZONE_COND_FULL) + zone.wp = zone.start + zone.len; + + return cb(&zone, idx, data); } /** @@ -104,11 +97,6 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf, return 0; } -/* - * Maximum number of zones to get with one report zones command. - */ -#define SD_ZBC_REPORT_MAX_ZONES 8192U - /** * Allocate a buffer for report zones reply. * @sdkp: The target disk @@ -138,82 +126,94 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, * sure that the allocated buffer can always be mapped by limiting the * number of pages allocated to the HBA max segments limit. */ - nr_zones = min(nr_zones, SD_ZBC_REPORT_MAX_ZONES); - bufsize = roundup((nr_zones + 1) * 64, 512); + nr_zones = min(nr_zones, sdkp->nr_zones); + bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE); bufsize = min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT); bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT); - buf = vzalloc(bufsize); - if (buf) - *buflen = bufsize; + while (bufsize >= SECTOR_SIZE) { + buf = __vmalloc(bufsize, + GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY, + PAGE_KERNEL); + if (buf) { + *buflen = bufsize; + return buf; + } + bufsize >>= 1; + } - return buf; + return NULL; } /** - * sd_zbc_report_zones - Disk report zones operation. - * @disk: The target disk - * @sector: Start 512B sector of the report - * @zones: Array of zone descriptors - * @nr_zones: Number of descriptors in the array - * - * Execute a report zones command on the target disk. + * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors. + * @sdkp: The target disk */ +static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp) +{ + return logical_to_sectors(sdkp->device, sdkp->zone_blocks); +} + int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { struct scsi_disk *sdkp = scsi_disk(disk); - unsigned int i, nrz = *nr_zones; + unsigned int nr, i; unsigned char *buf; - size_t buflen = 0, offset = 0; - int ret = 0; + size_t offset, buflen = 0; + int zone_idx = 0; + int ret; if (!sd_is_zoned(sdkp)) /* Not a zoned device */ return -EOPNOTSUPP; - buf = sd_zbc_alloc_report_buffer(sdkp, nrz, &buflen); + buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen); if (!buf) return -ENOMEM; - ret = sd_zbc_do_report_zones(sdkp, buf, buflen, - sectors_to_logical(sdkp->device, sector), true); - if (ret) - goto out; + while (zone_idx < nr_zones && sector < get_capacity(disk)) { + ret = sd_zbc_do_report_zones(sdkp, buf, buflen, + sectors_to_logical(sdkp->device, sector), true); + if (ret) + goto out; + + offset = 0; + nr = min(nr_zones, get_unaligned_be32(&buf[0]) / 64); + if (!nr) + break; + + for (i = 0; i < nr && zone_idx < nr_zones; i++) { + offset += 64; + ret = sd_zbc_parse_report(sdkp, buf + offset, zone_idx, + cb, data); + if (ret) + goto out; + zone_idx++; + } - nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64); - for (i = 0; i < nrz; i++) { - offset += 64; - sd_zbc_parse_report(sdkp, buf + offset, zones); - zones++; + sector += sd_zbc_zone_sectors(sdkp) * i; } - *nr_zones = nrz; - + ret = zone_idx; out: kvfree(buf); - return ret; } /** - * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors. - * @sdkp: The target disk - */ -static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp) -{ - return logical_to_sectors(sdkp->device, sdkp->zone_blocks); -} - -/** - * sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command. + * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations + * can be RESET WRITE POINTER, OPEN, CLOSE or FINISH. * @cmd: the command to setup - * @all: Reset all zones control. + * @op: Operation to be performed + * @all: All zones control * - * Called from sd_init_command() for a REQ_OP_ZONE_RESET request. + * Called from sd_init_command() for REQ_OP_ZONE_RESET, REQ_OP_ZONE_RESET_ALL, + * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE or REQ_OP_ZONE_FINISH requests. */ -blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all) +blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, + unsigned char op, bool all) { struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); @@ -234,7 +234,7 @@ blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all) cmd->cmd_len = 16; memset(cmd->cmnd, 0, cmd->cmd_len); cmd->cmnd[0] = ZBC_OUT; - cmd->cmnd[1] = ZO_RESET_WRITE_POINTER; + cmd->cmnd[1] = op; if (all) cmd->cmnd[14] = 0x1; else @@ -263,25 +263,16 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, int result = cmd->result; struct request *rq = cmd->request; - switch (req_op(rq)) { - case REQ_OP_ZONE_RESET: - case REQ_OP_ZONE_RESET_ALL: - - if (result && - sshdr->sense_key == ILLEGAL_REQUEST && - sshdr->asc == 0x24) - /* - * INVALID FIELD IN CDB error: reset of a conventional - * zone was attempted. Nothing to worry about, so be - * quiet about the error. - */ - rq->rq_flags |= RQF_QUIET; - break; - - case REQ_OP_WRITE: - case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE_SAME: - break; + if (op_is_zone_mgmt(req_op(rq)) && + result && + sshdr->sense_key == ILLEGAL_REQUEST && + sshdr->asc == 0x24) { + /* + * INVALID FIELD IN CDB error: a zone management command was + * attempted on a conventional zone. Nothing to worry about, + * so be quiet about the error. + */ + rq->rq_flags |= RQF_QUIET; } } @@ -344,32 +335,18 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp, * Returns the zone size in number of blocks upon success or an error code * upon failure. */ -static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks) +static int sd_zbc_check_zones(struct scsi_disk *sdkp, unsigned char *buf, + u32 *zblocks) { - size_t bufsize, buflen; - unsigned int noio_flag; u64 zone_blocks = 0; - sector_t max_lba, block = 0; - unsigned char *buf; + sector_t max_lba; unsigned char *rec; int ret; - u8 same; - - /* Do all memory allocations as if GFP_NOIO was specified */ - noio_flag = memalloc_noio_save(); - - /* Get a buffer */ - buf = sd_zbc_alloc_report_buffer(sdkp, SD_ZBC_REPORT_MAX_ZONES, - &bufsize); - if (!buf) { - ret = -ENOMEM; - goto out; - } - /* Do a report zone to get max_lba and the same field */ - ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, 0, false); + /* Do a report zone to get max_lba and the size of the first zone */ + ret = sd_zbc_do_report_zones(sdkp, buf, SD_BUF_SIZE, 0, false); if (ret) - goto out_free; + return ret; if (sdkp->rc_basis == 0) { /* The max_lba field is the capacity of this device */ @@ -384,82 +361,27 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks) } } - /* - * Check same field: for any value other than 0, we know that all zones - * have the same size. - */ - same = buf[4] & 0x0f; - if (same > 0) { - rec = &buf[64]; - zone_blocks = get_unaligned_be64(&rec[8]); - goto out; - } - - /* - * Check the size of all zones: all zones must be of - * equal size, except the last zone which can be smaller - * than other zones. - */ - do { - - /* Parse REPORT ZONES header */ - buflen = min_t(size_t, get_unaligned_be32(&buf[0]) + 64, - bufsize); - rec = buf + 64; - - /* Parse zone descriptors */ - while (rec < buf + buflen) { - u64 this_zone_blocks = get_unaligned_be64(&rec[8]); - - if (zone_blocks == 0) { - zone_blocks = this_zone_blocks; - } else if (this_zone_blocks != zone_blocks && - (block + this_zone_blocks < sdkp->capacity - || this_zone_blocks > zone_blocks)) { - zone_blocks = 0; - goto out; - } - block += this_zone_blocks; - rec += 64; - } - - if (block < sdkp->capacity) { - ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, block, - true); - if (ret) - goto out_free; - } - - } while (block < sdkp->capacity); - -out: - if (!zone_blocks) { - if (sdkp->first_scan) - sd_printk(KERN_NOTICE, sdkp, - "Devices with non constant zone " - "size are not supported\n"); - ret = -ENODEV; - } else if (!is_power_of_2(zone_blocks)) { + /* Parse REPORT ZONES header */ + rec = buf + 64; + zone_blocks = get_unaligned_be64(&rec[8]); + if (!zone_blocks || !is_power_of_2(zone_blocks)) { if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Devices with non power of 2 zone " "size are not supported\n"); - ret = -ENODEV; - } else if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) { + return -ENODEV; + } + + if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) { if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Zone size too large\n"); - ret = -EFBIG; - } else { - *zblocks = zone_blocks; - ret = 0; + return -EFBIG; } -out_free: - memalloc_noio_restore(noio_flag); - kvfree(buf); + *zblocks = zone_blocks; - return ret; + return 0; } int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) @@ -485,7 +407,7 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) * Check zone size: only devices with a constant zone size (except * an eventual last runt zone) that is a power of 2 are supported. */ - ret = sd_zbc_check_zones(sdkp, &zone_blocks); + ret = sd_zbc_check_zones(sdkp, buf, &zone_blocks); if (ret != 0) goto err; diff --git a/drivers/scsi/sni_53c710.c b/drivers/scsi/sni_53c710.c index aef4881d8e21..a85d52b5dc32 100644 --- a/drivers/scsi/sni_53c710.c +++ b/drivers/scsi/sni_53c710.c @@ -66,10 +66,8 @@ static int snirm710_probe(struct platform_device *dev) base = res->start; hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL); - if (!hostdata) { - dev_printk(KERN_ERR, dev, "Failed to allocate host data\n"); + if (!hostdata) return -ENOMEM; - } hostdata->dev = &dev->dev; dma_set_mask(&dev->dev, DMA_BIT_MASK(32)); diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c index a9344eb4e047..dc2f6d2b46ed 100644 --- a/drivers/scsi/ufs/ufs_bsg.c +++ b/drivers/scsi/ufs/ufs_bsg.c @@ -98,6 +98,8 @@ static int ufs_bsg_request(struct bsg_job *job) bsg_reply->reply_payload_rcv_len = 0; + pm_runtime_get_sync(hba->dev); + msgcode = bsg_request->msgcode; switch (msgcode) { case UPIU_TRANSACTION_QUERY_REQ: @@ -135,6 +137,8 @@ static int ufs_bsg_request(struct bsg_job *job) break; } + pm_runtime_put_sync(hba->dev); + if (!desc_buff) goto out; diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index d9231bd3c691..98b9d9a902ae 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -249,13 +249,13 @@ static struct genpd_power_state imx6_pm_domain_pu_state = { }; static struct imx_pm_domain imx_gpc_domains[] = { - [GPC_PGC_DOMAIN_ARM] { + [GPC_PGC_DOMAIN_ARM] = { .base = { .name = "ARM", .flags = GENPD_FLAG_ALWAYS_ON, }, }, - [GPC_PGC_DOMAIN_PU] { + [GPC_PGC_DOMAIN_PU] = { .base = { .name = "PU", .power_off = imx6_pm_domain_power_off, @@ -266,7 +266,7 @@ static struct imx_pm_domain imx_gpc_domains[] = { .reg_offs = 0x260, .cntr_pdn_bit = 0, }, - [GPC_PGC_DOMAIN_DISPLAY] { + [GPC_PGC_DOMAIN_DISPLAY] = { .base = { .name = "DISPLAY", .power_off = imx6_pm_domain_power_off, @@ -275,7 +275,7 @@ static struct imx_pm_domain imx_gpc_domains[] = { .reg_offs = 0x240, .cntr_pdn_bit = 4, }, - [GPC_PGC_DOMAIN_PCI] { + [GPC_PGC_DOMAIN_PCI] = { .base = { .name = "PCI", .power_off = imx6_pm_domain_power_off, diff --git a/drivers/soc/imx/soc-imx-scu.c b/drivers/soc/imx/soc-imx-scu.c index 50831ebf126a..c68882eb80f7 100644 --- a/drivers/soc/imx/soc-imx-scu.c +++ b/drivers/soc/imx/soc-imx-scu.c @@ -46,7 +46,7 @@ static ssize_t soc_uid_show(struct device *dev, hdr->func = IMX_SC_MISC_FUNC_UNIQUE_ID; hdr->size = 1; - ret = imx_scu_call_rpc(soc_ipc_handle, &msg, false); + ret = imx_scu_call_rpc(soc_ipc_handle, &msg, true); if (ret) { pr_err("%s: get soc uid failed, ret %d\n", __func__, ret); return ret; diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig index f518273cfbe3..c8c80df090d1 100644 --- a/drivers/soundwire/Kconfig +++ b/drivers/soundwire/Kconfig @@ -5,6 +5,7 @@ menuconfig SOUNDWIRE tristate "SoundWire support" + depends on ACPI || OF help SoundWire is a 2-Pin interface with data and clock line ratified by the MIPI Alliance. SoundWire is used for transporting data diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index f1e38a293967..13c54eac0cc3 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -900,7 +900,7 @@ static int intel_register_dai(struct sdw_intel *sdw) /* Create PCM DAIs */ stream = &cdns->pcm; - ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, stream->num_in, + ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, cdns->pcm.num_in, off, stream->num_ch_in, true); if (ret) return ret; @@ -931,7 +931,7 @@ static int intel_register_dai(struct sdw_intel *sdw) if (ret) return ret; - off += cdns->pdm.num_bd; + off += cdns->pdm.num_out; ret = intel_create_dai(cdns, dais, INTEL_PDI_BD, cdns->pdm.num_bd, off, stream->num_ch_bd, false); if (ret) diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c index 48a63ca130d2..6473fa602f82 100644 --- a/drivers/soundwire/slave.c +++ b/drivers/soundwire/slave.c @@ -128,7 +128,8 @@ int sdw_of_find_slaves(struct sdw_bus *bus) struct device_node *node; for_each_child_of_node(bus->dev->of_node, node) { - int link_id, sdw_version, ret, len; + int link_id, ret, len; + unsigned int sdw_version; const char *compat = NULL; struct sdw_slave_id id; const __be32 *addr; diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c index eee1998c4b18..fac38c842ac5 100644 --- a/drivers/staging/wlan-ng/cfg80211.c +++ b/drivers/staging/wlan-ng/cfg80211.c @@ -469,10 +469,8 @@ static int prism2_connect(struct wiphy *wiphy, struct net_device *dev, /* Set the encryption - we only support wep */ if (is_wep) { if (sme->key) { - if (sme->key_idx >= NUM_WEPKEYS) { - err = -EINVAL; - goto exit; - } + if (sme->key_idx >= NUM_WEPKEYS) + return -EINVAL; result = prism2_domibset_uint32(wlandev, DIDMIB_DOT11SMT_PRIVACYTABLE_WEPDEFAULTKEYID, diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index c70caf4ea490..a2b5c796bbc4 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -1831,7 +1831,7 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb) while (credits) { struct sk_buff *p = cxgbit_sock_peek_wr(csk); - const u32 csum = (__force u32)p->csum; + u32 csum; if (unlikely(!p)) { pr_err("csk 0x%p,%u, cr %u,%u+%u, empty.\n", @@ -1840,6 +1840,7 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb) break; } + csum = (__force u32)p->csum; if (unlikely(credits < csum)) { pr_warn("csk 0x%p,%u, cr %u,%u+%u, < %u.\n", csk, csk->tid, diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 04bf2acd3800..2d19f0e332b0 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1075,27 +1075,6 @@ passthrough_parse_cdb(struct se_cmd *cmd, unsigned int size; /* - * Clear a lun set in the cdb if the initiator talking to use spoke - * and old standards version, as we can't assume the underlying device - * won't choke up on it. - */ - switch (cdb[0]) { - case READ_10: /* SBC - RDProtect */ - case READ_12: /* SBC - RDProtect */ - case READ_16: /* SBC - RDProtect */ - case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */ - case VERIFY: /* SBC - VRProtect */ - case VERIFY_16: /* SBC - VRProtect */ - case WRITE_VERIFY: /* SBC - VRProtect */ - case WRITE_VERIFY_12: /* SBC - VRProtect */ - case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */ - break; - default: - cdb[1] &= 0x1f; /* clear logical unit number */ - break; - } - - /* * For REPORT LUNS we always need to emulate the response, for everything * else, pass it up. */ diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 391f39776c6a..6b9865c786ba 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -88,7 +88,7 @@ struct cpufreq_cooling_device { struct cpufreq_policy *policy; struct list_head node; struct time_in_idle *idle_time; - struct dev_pm_qos_request qos_req; + struct freq_qos_request qos_req; }; static DEFINE_IDA(cpufreq_ida); @@ -331,7 +331,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, cpufreq_cdev->cpufreq_state = state; - return dev_pm_qos_update_request(&cpufreq_cdev->qos_req, + return freq_qos_update_request(&cpufreq_cdev->qos_req, cpufreq_cdev->freq_table[state].frequency); } @@ -615,9 +615,9 @@ __cpufreq_cooling_register(struct device_node *np, cooling_ops = &cpufreq_cooling_ops; } - ret = dev_pm_qos_add_request(dev, &cpufreq_cdev->qos_req, - DEV_PM_QOS_MAX_FREQUENCY, - cpufreq_cdev->freq_table[0].frequency); + ret = freq_qos_add_request(&policy->constraints, + &cpufreq_cdev->qos_req, FREQ_QOS_MAX, + cpufreq_cdev->freq_table[0].frequency); if (ret < 0) { pr_err("%s: Failed to add freq constraint (%d)\n", __func__, ret); @@ -637,7 +637,7 @@ __cpufreq_cooling_register(struct device_node *np, return cdev; remove_qos_req: - dev_pm_qos_remove_request(&cpufreq_cdev->qos_req); + freq_qos_remove_request(&cpufreq_cdev->qos_req); remove_ida: ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); free_table: @@ -736,7 +736,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) mutex_unlock(&cooling_list_lock); thermal_cooling_device_unregister(cdev); - dev_pm_qos_remove_request(&cpufreq_cdev->qos_req); + freq_qos_remove_request(&cpufreq_cdev->qos_req); ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); kfree(cpufreq_cdev->idle_time); kfree(cpufreq_cdev->freq_table); diff --git a/drivers/thunderbolt/nhi_ops.c b/drivers/thunderbolt/nhi_ops.c index 61cd09cef943..6795851aac95 100644 --- a/drivers/thunderbolt/nhi_ops.c +++ b/drivers/thunderbolt/nhi_ops.c @@ -80,7 +80,6 @@ static void icl_nhi_lc_mailbox_cmd(struct tb_nhi *nhi, enum icl_lc_mailbox_cmd c { u32 data; - pci_read_config_dword(nhi->pdev, VS_CAP_19, &data); data = (cmd << VS_CAP_19_CMD_SHIFT) & VS_CAP_19_CMD_MASK; pci_write_config_dword(nhi->pdev, VS_CAP_19, data | VS_CAP_19_VALID); } diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 410bf1bceeee..5ea8db667e83 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -896,12 +896,13 @@ int tb_dp_port_set_hops(struct tb_port *port, unsigned int video, */ bool tb_dp_port_is_enabled(struct tb_port *port) { - u32 data; + u32 data[2]; - if (tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1)) + if (tb_port_read(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data))) return false; - return !!(data & (TB_DP_VIDEO_EN | TB_DP_AUX_EN)); + return !!(data[0] & (TB_DP_VIDEO_EN | TB_DP_AUX_EN)); } /** @@ -914,19 +915,21 @@ bool tb_dp_port_is_enabled(struct tb_port *port) */ int tb_dp_port_enable(struct tb_port *port, bool enable) { - u32 data; + u32 data[2]; int ret; - ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1); + ret = tb_port_read(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data)); if (ret) return ret; if (enable) - data |= TB_DP_VIDEO_EN | TB_DP_AUX_EN; + data[0] |= TB_DP_VIDEO_EN | TB_DP_AUX_EN; else - data &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN); + data[0] &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN); - return tb_port_write(port, &data, TB_CFG_PORT, port->cap_adap, 1); + return tb_port_write(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data)); } /* switch utility functions */ @@ -1031,13 +1034,6 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val) if (sw->authorized) goto unlock; - /* - * Make sure there is no PCIe rescan ongoing when a new PCIe - * tunnel is created. Otherwise the PCIe rescan code might find - * the new tunnel too early. - */ - pci_lock_rescan_remove(); - switch (val) { /* Approve switch */ case 1: @@ -1057,8 +1053,6 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val) break; } - pci_unlock_rescan_remove(); - if (!ret) { sw->authorized = val; /* Notify status change to the userspace */ diff --git a/drivers/tty/serial/8250/8250_men_mcb.c b/drivers/tty/serial/8250/8250_men_mcb.c index 02c5aff58a74..8df89e9cd254 100644 --- a/drivers/tty/serial/8250/8250_men_mcb.c +++ b/drivers/tty/serial/8250/8250_men_mcb.c @@ -72,8 +72,8 @@ static int serial_8250_men_mcb_probe(struct mcb_device *mdev, { struct serial_8250_men_mcb_data *data; struct resource *mem; - unsigned int num_ports; - unsigned int i; + int num_ports; + int i; void __iomem *membase; mem = mcb_get_resource(mdev, IORESOURCE_MEM); @@ -88,7 +88,7 @@ static int serial_8250_men_mcb_probe(struct mcb_device *mdev, dev_dbg(&mdev->dev, "found a 16z%03u with %u ports\n", mdev->id, num_ports); - if (num_ports == 0 || num_ports > 4) { + if (num_ports <= 0 || num_ports > 4) { dev_err(&mdev->dev, "unexpected number of ports: %u\n", num_ports); return -ENODEV; @@ -133,7 +133,7 @@ static int serial_8250_men_mcb_probe(struct mcb_device *mdev, static void serial_8250_men_mcb_remove(struct mcb_device *mdev) { - unsigned int num_ports, i; + int num_ports, i; struct serial_8250_men_mcb_data *data = mcb_get_drvdata(mdev); if (!data) diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 1109dc5a4c39..c2123ef8d8a3 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -166,7 +166,6 @@ static int cdns3_core_init_role(struct cdns3 *cdns) goto err; switch (cdns->dr_mode) { - case USB_DR_MODE_UNKNOWN: case USB_DR_MODE_OTG: ret = cdns3_hw_role_switch(cdns); if (ret) @@ -182,6 +181,9 @@ static int cdns3_core_init_role(struct cdns3 *cdns) if (ret) goto err; break; + default: + ret = -EINVAL; + goto err; } return ret; diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 2ca280f4c054..4c1e75509303 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -1145,6 +1145,14 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, request = cdns3_next_request(&priv_ep->pending_req_list); priv_req = to_cdns3_request(request); + trb = priv_ep->trb_pool + priv_ep->dequeue; + + /* Request was dequeued and TRB was changed to TRB_LINK. */ + if (TRB_FIELD_TO_TYPE(trb->control) == TRB_LINK) { + trace_cdns3_complete_trb(priv_ep, trb); + cdns3_move_deq_to_next_trb(priv_req); + } + /* Re-select endpoint. It could be changed by other CPU during * handling usb_gadget_giveback_request. */ @@ -2067,6 +2075,7 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep, struct usb_request *req, *req_temp; struct cdns3_request *priv_req; struct cdns3_trb *link_trb; + u8 req_on_hw_ring = 0; unsigned long flags; int ret = 0; @@ -2083,8 +2092,10 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep, list_for_each_entry_safe(req, req_temp, &priv_ep->pending_req_list, list) { - if (request == req) + if (request == req) { + req_on_hw_ring = 1; goto found; + } } list_for_each_entry_safe(req, req_temp, &priv_ep->deferred_req_list, @@ -2096,27 +2107,21 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep, goto not_found; found: - - if (priv_ep->wa1_trb == priv_req->trb) - cdns3_wa1_restore_cycle_bit(priv_ep); - link_trb = priv_req->trb; - cdns3_move_deq_to_next_trb(priv_req); - cdns3_gadget_giveback(priv_ep, priv_req, -ECONNRESET); - - /* Update ring */ - request = cdns3_next_request(&priv_ep->deferred_req_list); - if (request) { - priv_req = to_cdns3_request(request); + /* Update ring only if removed request is on pending_req_list list */ + if (req_on_hw_ring) { link_trb->buffer = TRB_BUFFER(priv_ep->trb_pool_dma + (priv_req->start_trb * TRB_SIZE)); link_trb->control = (link_trb->control & TRB_CYCLE) | - TRB_TYPE(TRB_LINK) | TRB_CHAIN | TRB_TOGGLE; - } else { - priv_ep->flags |= EP_UPDATE_EP_TRBADDR; + TRB_TYPE(TRB_LINK) | TRB_CHAIN; + + if (priv_ep->wa1_trb == priv_req->trb) + cdns3_wa1_restore_cycle_bit(priv_ep); } + cdns3_gadget_giveback(priv_ep, priv_req, -ECONNRESET); + not_found: spin_unlock_irqrestore(&priv_dev->lock, flags); return ret; @@ -2324,8 +2329,6 @@ static void cdns3_gadget_config(struct cdns3_device *priv_dev) writel(USB_CONF_CLK2OFFDS | USB_CONF_L1DS, ®s->usb_conf); cdns3_configure_dmult(priv_dev, NULL); - - cdns3_gadget_pullup(&priv_dev->gadget, 1); } /** @@ -2340,9 +2343,35 @@ static int cdns3_gadget_udc_start(struct usb_gadget *gadget, { struct cdns3_device *priv_dev = gadget_to_cdns3_device(gadget); unsigned long flags; + enum usb_device_speed max_speed = driver->max_speed; spin_lock_irqsave(&priv_dev->lock, flags); priv_dev->gadget_driver = driver; + + /* limit speed if necessary */ + max_speed = min(driver->max_speed, gadget->max_speed); + + switch (max_speed) { + case USB_SPEED_FULL: + writel(USB_CONF_SFORCE_FS, &priv_dev->regs->usb_conf); + writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf); + break; + case USB_SPEED_HIGH: + writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf); + break; + case USB_SPEED_SUPER: + break; + default: + dev_err(priv_dev->dev, + "invalid maximum_speed parameter %d\n", + max_speed); + /* fall through */ + case USB_SPEED_UNKNOWN: + /* default to superspeed */ + max_speed = USB_SPEED_SUPER; + break; + } + cdns3_gadget_config(priv_dev); spin_unlock_irqrestore(&priv_dev->lock, flags); return 0; @@ -2376,6 +2405,8 @@ static int cdns3_gadget_udc_stop(struct usb_gadget *gadget) writel(EP_CMD_EPRST, &priv_dev->regs->ep_cmd); readl_poll_timeout_atomic(&priv_dev->regs->ep_cmd, val, !(val & EP_CMD_EPRST), 1, 100); + + priv_ep->flags &= ~EP_CLAIMED; } /* disable interrupt for device */ @@ -2570,12 +2601,7 @@ static int cdns3_gadget_start(struct cdns3 *cdns) /* Check the maximum_speed parameter */ switch (max_speed) { case USB_SPEED_FULL: - writel(USB_CONF_SFORCE_FS, &priv_dev->regs->usb_conf); - writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf); - break; case USB_SPEED_HIGH: - writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf); - break; case USB_SPEED_SUPER: break; default: @@ -2708,8 +2734,6 @@ static int cdns3_gadget_suspend(struct cdns3 *cdns, bool do_wakeup) /* disable interrupt for device */ writel(0, &priv_dev->regs->usb_ien); - cdns3_gadget_pullup(&priv_dev->gadget, 0); - return 0; } diff --git a/drivers/usb/cdns3/host-export.h b/drivers/usb/cdns3/host-export.h index b498a170b7e8..ae11810f8826 100644 --- a/drivers/usb/cdns3/host-export.h +++ b/drivers/usb/cdns3/host-export.h @@ -12,7 +12,6 @@ #ifdef CONFIG_USB_CDNS3_HOST int cdns3_host_init(struct cdns3 *cdns); -void cdns3_host_exit(struct cdns3 *cdns); #else diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c index 2733a8f71fcd..ad788bf3fe4f 100644 --- a/drivers/usb/cdns3/host.c +++ b/drivers/usb/cdns3/host.c @@ -12,6 +12,7 @@ #include <linux/platform_device.h> #include "core.h" #include "drd.h" +#include "host-export.h" static int __cdns3_host_init(struct cdns3 *cdns) { diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index fb8bd60c83f4..0d8e3f3804a3 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -445,6 +445,7 @@ static void usblp_cleanup(struct usblp *usblp) kfree(usblp->readbuf); kfree(usblp->device_id_string); kfree(usblp->statusbuf); + usb_put_intf(usblp->intf); kfree(usblp); } @@ -1113,7 +1114,7 @@ static int usblp_probe(struct usb_interface *intf, init_waitqueue_head(&usblp->wwait); init_usb_anchor(&usblp->urbs); usblp->ifnum = intf->cur_altsetting->desc.bInterfaceNumber; - usblp->intf = intf; + usblp->intf = usb_get_intf(intf); /* Malloc device ID string buffer to the largest expected length, * since we can re-query it on an ioctl and a dynamic string @@ -1198,6 +1199,7 @@ abort: kfree(usblp->readbuf); kfree(usblp->statusbuf); kfree(usblp->device_id_string); + usb_put_intf(usblp->intf); kfree(usblp); abort_ret: return retval; diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 151a74a54386..1ac1095bfeac 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -348,6 +348,11 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, /* Validate the wMaxPacketSize field */ maxp = usb_endpoint_maxp(&endpoint->desc); + if (maxp == 0) { + dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has wMaxPacketSize 0, skipping\n", + cfgno, inum, asnum, d->bEndpointAddress); + goto skip_to_next_endpoint_or_interface_descriptor; + } /* Find the highest legal maxpacket size for this endpoint */ i = 0; /* additional transactions per microframe */ diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig index 89abc6078703..556a876c7896 100644 --- a/drivers/usb/dwc3/Kconfig +++ b/drivers/usb/dwc3/Kconfig @@ -102,6 +102,7 @@ config USB_DWC3_MESON_G12A depends on ARCH_MESON || COMPILE_TEST default USB_DWC3 select USB_ROLE_SWITCH + select REGMAP_MMIO help Support USB2/3 functionality in Amlogic G12A platforms. Say 'Y' or 'M' if you have one such device. diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 999ce5e84d3c..97d6ae3c4df2 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -312,8 +312,7 @@ static void dwc3_frame_length_adjustment(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_GFLADJ); dft = reg & DWC3_GFLADJ_30MHZ_MASK; - if (!dev_WARN_ONCE(dwc->dev, dft == dwc->fladj, - "request value same as default, ignoring\n")) { + if (dft != dwc->fladj) { reg &= ~DWC3_GFLADJ_30MHZ_MASK; reg |= DWC3_GFLADJ_30MHZ_SDBND_SEL | dwc->fladj; dwc3_writel(dwc->regs, DWC3_GFLADJ, reg); diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 5e8e18222f92..023f0357efd7 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -258,7 +258,7 @@ static int dwc3_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) ret = platform_device_add_properties(dwc->dwc3, p); if (ret < 0) - return ret; + goto err; ret = dwc3_pci_quirks(dwc); if (ret) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 86dc1db788a9..a9aba716bf80 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -707,6 +707,12 @@ static void dwc3_remove_requests(struct dwc3 *dwc, struct dwc3_ep *dep) dwc3_gadget_giveback(dep, req, -ESHUTDOWN); } + + while (!list_empty(&dep->cancelled_list)) { + req = next_request(&dep->cancelled_list); + + dwc3_gadget_giveback(dep, req, -ESHUTDOWN); + } } /** diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d516e8d6cd7f..5ec54b69c29c 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2170,14 +2170,18 @@ void composite_dev_cleanup(struct usb_composite_dev *cdev) usb_ep_dequeue(cdev->gadget->ep0, cdev->os_desc_req); kfree(cdev->os_desc_req->buf); + cdev->os_desc_req->buf = NULL; usb_ep_free_request(cdev->gadget->ep0, cdev->os_desc_req); + cdev->os_desc_req = NULL; } if (cdev->req) { if (cdev->setup_pending) usb_ep_dequeue(cdev->gadget->ep0, cdev->req); kfree(cdev->req->buf); + cdev->req->buf = NULL; usb_ep_free_request(cdev->gadget->ep0, cdev->req); + cdev->req = NULL; } cdev->next_string_id = 0; device_remove_file(&cdev->gadget->dev, &dev_attr_suspended); diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 025129942894..33852c2b29d1 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -61,6 +61,8 @@ struct gadget_info { bool use_os_desc; char b_vendor_code; char qw_sign[OS_STRING_QW_SIGN_LEN]; + spinlock_t spinlock; + bool unbind; }; static inline struct gadget_info *to_gadget_info(struct config_item *item) @@ -1244,6 +1246,7 @@ static int configfs_composite_bind(struct usb_gadget *gadget, int ret; /* the gi->lock is hold by the caller */ + gi->unbind = 0; cdev->gadget = gadget; set_gadget_data(gadget, cdev); ret = composite_dev_prepare(composite, cdev); @@ -1376,31 +1379,128 @@ static void configfs_composite_unbind(struct usb_gadget *gadget) { struct usb_composite_dev *cdev; struct gadget_info *gi; + unsigned long flags; /* the gi->lock is hold by the caller */ cdev = get_gadget_data(gadget); gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + gi->unbind = 1; + spin_unlock_irqrestore(&gi->spinlock, flags); kfree(otg_desc[0]); otg_desc[0] = NULL; purge_configs_funcs(gi); composite_dev_cleanup(cdev); usb_ep_autoconfig_reset(cdev->gadget); + spin_lock_irqsave(&gi->spinlock, flags); cdev->gadget = NULL; set_gadget_data(gadget, NULL); + spin_unlock_irqrestore(&gi->spinlock, flags); +} + +static int configfs_composite_setup(struct usb_gadget *gadget, + const struct usb_ctrlrequest *ctrl) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + int ret; + + cdev = get_gadget_data(gadget); + if (!cdev) + return 0; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return 0; + } + + ret = composite_setup(gadget, ctrl); + spin_unlock_irqrestore(&gi->spinlock, flags); + return ret; +} + +static void configfs_composite_disconnect(struct usb_gadget *gadget) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + + cdev = get_gadget_data(gadget); + if (!cdev) + return; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return; + } + + composite_disconnect(gadget); + spin_unlock_irqrestore(&gi->spinlock, flags); +} + +static void configfs_composite_suspend(struct usb_gadget *gadget) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + + cdev = get_gadget_data(gadget); + if (!cdev) + return; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return; + } + + composite_suspend(gadget); + spin_unlock_irqrestore(&gi->spinlock, flags); +} + +static void configfs_composite_resume(struct usb_gadget *gadget) +{ + struct usb_composite_dev *cdev; + struct gadget_info *gi; + unsigned long flags; + + cdev = get_gadget_data(gadget); + if (!cdev) + return; + + gi = container_of(cdev, struct gadget_info, cdev); + spin_lock_irqsave(&gi->spinlock, flags); + cdev = get_gadget_data(gadget); + if (!cdev || gi->unbind) { + spin_unlock_irqrestore(&gi->spinlock, flags); + return; + } + + composite_resume(gadget); + spin_unlock_irqrestore(&gi->spinlock, flags); } static const struct usb_gadget_driver configfs_driver_template = { .bind = configfs_composite_bind, .unbind = configfs_composite_unbind, - .setup = composite_setup, - .reset = composite_disconnect, - .disconnect = composite_disconnect, + .setup = configfs_composite_setup, + .reset = configfs_composite_disconnect, + .disconnect = configfs_composite_disconnect, - .suspend = composite_suspend, - .resume = composite_resume, + .suspend = configfs_composite_suspend, + .resume = configfs_composite_resume, .max_speed = USB_SPEED_SUPER, .driver = { diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 86ffc8307864..1d0d8952a74b 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -449,9 +449,11 @@ static void submit_request(struct usba_ep *ep, struct usba_request *req) next_fifo_transaction(ep, req); if (req->last_transaction) { usba_ep_writel(ep, CTL_DIS, USBA_TX_PK_RDY); - usba_ep_writel(ep, CTL_ENB, USBA_TX_COMPLETE); + if (ep_is_control(ep)) + usba_ep_writel(ep, CTL_ENB, USBA_TX_COMPLETE); } else { - usba_ep_writel(ep, CTL_DIS, USBA_TX_COMPLETE); + if (ep_is_control(ep)) + usba_ep_writel(ep, CTL_DIS, USBA_TX_COMPLETE); usba_ep_writel(ep, CTL_ENB, USBA_TX_PK_RDY); } } diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 92af8dc98c3d..51fa614b4079 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -98,6 +98,17 @@ int usb_ep_enable(struct usb_ep *ep) if (ep->enabled) goto out; + /* UDC drivers can't handle endpoints with maxpacket size 0 */ + if (usb_endpoint_maxp(ep->desc) == 0) { + /* + * We should log an error message here, but we can't call + * dev_err() because there's no way to find the gadget + * given only ep. + */ + ret = -EINVAL; + goto out; + } + ret = ep->ops->enable(ep, ep->desc); if (ret) goto out; diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index 20141c3096f6..9a05863b2876 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -2576,7 +2576,7 @@ static int fsl_udc_remove(struct platform_device *pdev) dma_pool_destroy(udc_controller->td_pool); free_irq(udc_controller->irq, udc_controller); iounmap(dr_regs); - if (pdata->operating_mode == FSL_USB2_DR_DEVICE) + if (res && (pdata->operating_mode == FSL_USB2_DR_DEVICE)) release_mem_region(res->start, resource_size(res)); /* free udc --wait for the release() finished */ diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c index 2b1f3cc7819b..bf6c81e2f8cc 100644 --- a/drivers/usb/gadget/udc/lpc32xx_udc.c +++ b/drivers/usb/gadget/udc/lpc32xx_udc.c @@ -1177,11 +1177,11 @@ static void udc_pop_fifo(struct lpc32xx_udc *udc, u8 *data, u32 bytes) tmp = readl(USBD_RXDATA(udc->udp_baseaddr)); bl = bytes - n; - if (bl > 3) - bl = 3; + if (bl > 4) + bl = 4; for (i = 0; i < bl; i++) - data[n + i] = (u8) ((tmp >> (n * 8)) & 0xFF); + data[n + i] = (u8) ((tmp >> (i * 8)) & 0xFF); } break; diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index e098f16c01cb..33703140233a 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -1544,10 +1544,10 @@ static void usb3_set_device_address(struct renesas_usb3 *usb3, u16 addr) static bool usb3_std_req_set_address(struct renesas_usb3 *usb3, struct usb_ctrlrequest *ctrl) { - if (ctrl->wValue >= 128) + if (le16_to_cpu(ctrl->wValue) >= 128) return true; /* stall */ - usb3_set_device_address(usb3, ctrl->wValue); + usb3_set_device_address(usb3, le16_to_cpu(ctrl->wValue)); usb3_set_p0_con_for_no_data(usb3); return false; @@ -1582,6 +1582,7 @@ static bool usb3_std_req_get_status(struct renesas_usb3 *usb3, struct renesas_usb3_ep *usb3_ep; int num; u16 status = 0; + __le16 tx_data; switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: @@ -1604,10 +1605,10 @@ static bool usb3_std_req_get_status(struct renesas_usb3 *usb3, } if (!stall) { - status = cpu_to_le16(status); + tx_data = cpu_to_le16(status); dev_dbg(usb3_to_dev(usb3), "get_status: req = %p\n", usb_req_to_usb3_req(usb3->ep0_req)); - usb3_pipe0_internal_xfer(usb3, &status, sizeof(status), + usb3_pipe0_internal_xfer(usb3, &tx_data, sizeof(tx_data), usb3_pipe0_get_status_completion); } @@ -1772,7 +1773,7 @@ static bool usb3_std_req_set_sel(struct renesas_usb3 *usb3, static bool usb3_std_req_set_configuration(struct renesas_usb3 *usb3, struct usb_ctrlrequest *ctrl) { - if (ctrl->wValue > 0) + if (le16_to_cpu(ctrl->wValue) > 0) usb3_set_bit(usb3, USB_COM_CON_CONF, USB3_USB_COM_CON); else usb3_clear_bit(usb3, USB_COM_CON_CONF, USB3_USB_COM_CON); diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index 7ba6afc7ef23..76c3f29562d2 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -202,10 +202,10 @@ static void xhci_ring_dump_segment(struct seq_file *s, trb = &seg->trbs[i]; dma = seg->dma + i * sizeof(*trb); seq_printf(s, "%pad: %s\n", &dma, - xhci_decode_trb(trb->generic.field[0], - trb->generic.field[1], - trb->generic.field[2], - trb->generic.field[3])); + xhci_decode_trb(le32_to_cpu(trb->generic.field[0]), + le32_to_cpu(trb->generic.field[1]), + le32_to_cpu(trb->generic.field[2]), + le32_to_cpu(trb->generic.field[3]))); } } @@ -263,10 +263,10 @@ static int xhci_slot_context_show(struct seq_file *s, void *unused) xhci = hcd_to_xhci(bus_to_hcd(dev->udev->bus)); slot_ctx = xhci_get_slot_ctx(xhci, dev->out_ctx); seq_printf(s, "%pad: %s\n", &dev->out_ctx->dma, - xhci_decode_slot_context(slot_ctx->dev_info, - slot_ctx->dev_info2, - slot_ctx->tt_info, - slot_ctx->dev_state)); + xhci_decode_slot_context(le32_to_cpu(slot_ctx->dev_info), + le32_to_cpu(slot_ctx->dev_info2), + le32_to_cpu(slot_ctx->tt_info), + le32_to_cpu(slot_ctx->dev_state))); return 0; } @@ -286,10 +286,10 @@ static int xhci_endpoint_context_show(struct seq_file *s, void *unused) ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, dci); dma = dev->out_ctx->dma + dci * CTX_SIZE(xhci->hcc_params); seq_printf(s, "%pad: %s\n", &dma, - xhci_decode_ep_context(ep_ctx->ep_info, - ep_ctx->ep_info2, - ep_ctx->deq, - ep_ctx->tx_info)); + xhci_decode_ep_context(le32_to_cpu(ep_ctx->ep_info), + le32_to_cpu(ep_ctx->ep_info2), + le64_to_cpu(ep_ctx->deq), + le32_to_cpu(ep_ctx->tx_info))); } return 0; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 85ceb43e3405..e7aab31fd9a5 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3330,6 +3330,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, if (xhci_urb_suitable_for_idt(urb)) { memcpy(&send_addr, urb->transfer_buffer, trb_buff_len); + le64_to_cpus(&send_addr); field |= TRB_IDT; } } @@ -3475,6 +3476,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags, if (xhci_urb_suitable_for_idt(urb)) { memcpy(&addr, urb->transfer_buffer, urb->transfer_buffer_length); + le64_to_cpus(&addr); field |= TRB_IDT; } else { addr = (u64) urb->transfer_dma; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 517ec3206f6e..6c17e3fe181a 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3071,6 +3071,48 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index, } } +static void xhci_endpoint_disable(struct usb_hcd *hcd, + struct usb_host_endpoint *host_ep) +{ + struct xhci_hcd *xhci; + struct xhci_virt_device *vdev; + struct xhci_virt_ep *ep; + struct usb_device *udev; + unsigned long flags; + unsigned int ep_index; + + xhci = hcd_to_xhci(hcd); +rescan: + spin_lock_irqsave(&xhci->lock, flags); + + udev = (struct usb_device *)host_ep->hcpriv; + if (!udev || !udev->slot_id) + goto done; + + vdev = xhci->devs[udev->slot_id]; + if (!vdev) + goto done; + + ep_index = xhci_get_endpoint_index(&host_ep->desc); + ep = &vdev->eps[ep_index]; + if (!ep) + goto done; + + /* wait for hub_tt_work to finish clearing hub TT */ + if (ep->ep_state & EP_CLEARING_TT) { + spin_unlock_irqrestore(&xhci->lock, flags); + schedule_timeout_uninterruptible(1); + goto rescan; + } + + if (ep->ep_state) + xhci_dbg(xhci, "endpoint disable with ep_state 0x%x\n", + ep->ep_state); +done: + host_ep->hcpriv = NULL; + spin_unlock_irqrestore(&xhci->lock, flags); +} + /* * Called after usb core issues a clear halt control message. * The host side of the halt should already be cleared by a reset endpoint @@ -5238,20 +5280,13 @@ static void xhci_clear_tt_buffer_complete(struct usb_hcd *hcd, unsigned int ep_index; unsigned long flags; - /* - * udev might be NULL if tt buffer is cleared during a failed device - * enumeration due to a halted control endpoint. Usb core might - * have allocated a new udev for the next enumeration attempt. - */ - xhci = hcd_to_xhci(hcd); + + spin_lock_irqsave(&xhci->lock, flags); udev = (struct usb_device *)ep->hcpriv; - if (!udev) - return; slot_id = udev->slot_id; ep_index = xhci_get_endpoint_index(&ep->desc); - spin_lock_irqsave(&xhci->lock, flags); xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_CLEARING_TT; xhci_ring_doorbell_for_active_rings(xhci, slot_id, ep_index); spin_unlock_irqrestore(&xhci->lock, flags); @@ -5288,6 +5323,7 @@ static const struct hc_driver xhci_hc_driver = { .free_streams = xhci_free_streams, .add_endpoint = xhci_add_endpoint, .drop_endpoint = xhci_drop_endpoint, + .endpoint_disable = xhci_endpoint_disable, .endpoint_reset = xhci_endpoint_reset, .check_bandwidth = xhci_check_bandwidth, .reset_bandwidth = xhci_reset_bandwidth, diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index f3108d85e768..8f86b4ebca89 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -380,10 +380,7 @@ static int ld_usb_release(struct inode *inode, struct file *file) goto exit; } - if (mutex_lock_interruptible(&dev->mutex)) { - retval = -ERESTARTSYS; - goto exit; - } + mutex_lock(&dev->mutex); if (dev->open_count != 1) { retval = -ENODEV; @@ -467,7 +464,7 @@ static ssize_t ld_usb_read(struct file *file, char __user *buffer, size_t count, /* wait for data */ spin_lock_irq(&dev->rbsl); - if (dev->ring_head == dev->ring_tail) { + while (dev->ring_head == dev->ring_tail) { dev->interrupt_in_done = 0; spin_unlock_irq(&dev->rbsl); if (file->f_flags & O_NONBLOCK) { @@ -477,15 +474,20 @@ static ssize_t ld_usb_read(struct file *file, char __user *buffer, size_t count, retval = wait_event_interruptible(dev->read_wait, dev->interrupt_in_done); if (retval < 0) goto unlock_exit; - } else { - spin_unlock_irq(&dev->rbsl); + + spin_lock_irq(&dev->rbsl); } + spin_unlock_irq(&dev->rbsl); /* actual_buffer contains actual_length + interrupt_in_buffer */ actual_buffer = (size_t *)(dev->ring_buffer + dev->ring_tail * (sizeof(size_t)+dev->interrupt_in_endpoint_size)); + if (*actual_buffer > dev->interrupt_in_endpoint_size) { + retval = -EIO; + goto unlock_exit; + } bytes_to_read = min(count, *actual_buffer); if (bytes_to_read < *actual_buffer) - dev_warn(&dev->intf->dev, "Read buffer overflow, %zd bytes dropped\n", + dev_warn(&dev->intf->dev, "Read buffer overflow, %zu bytes dropped\n", *actual_buffer-bytes_to_read); /* copy one interrupt_in_buffer from ring_buffer into userspace */ @@ -493,11 +495,11 @@ static ssize_t ld_usb_read(struct file *file, char __user *buffer, size_t count, retval = -EFAULT; goto unlock_exit; } - dev->ring_tail = (dev->ring_tail+1) % ring_buffer_size; - retval = bytes_to_read; spin_lock_irq(&dev->rbsl); + dev->ring_tail = (dev->ring_tail + 1) % ring_buffer_size; + if (dev->buffer_overflow) { dev->buffer_overflow = 0; spin_unlock_irq(&dev->rbsl); @@ -560,8 +562,9 @@ static ssize_t ld_usb_write(struct file *file, const char __user *buffer, /* write the data into interrupt_out_buffer from userspace */ bytes_to_write = min(count, write_buffer_size*dev->interrupt_out_endpoint_size); if (bytes_to_write < count) - dev_warn(&dev->intf->dev, "Write buffer overflow, %zd bytes dropped\n", count-bytes_to_write); - dev_dbg(&dev->intf->dev, "%s: count = %zd, bytes_to_write = %zd\n", + dev_warn(&dev->intf->dev, "Write buffer overflow, %zu bytes dropped\n", + count - bytes_to_write); + dev_dbg(&dev->intf->dev, "%s: count = %zu, bytes_to_write = %zu\n", __func__, count, bytes_to_write); if (copy_from_user(dev->interrupt_out_buffer, buffer, bytes_to_write)) { @@ -578,7 +581,7 @@ static ssize_t ld_usb_write(struct file *file, const char __user *buffer, 1 << 8, 0, dev->interrupt_out_buffer, bytes_to_write, - USB_CTRL_SET_TIMEOUT * HZ); + USB_CTRL_SET_TIMEOUT); if (retval < 0) dev_err(&dev->intf->dev, "Couldn't submit HID_REQ_SET_REPORT %d\n", @@ -693,10 +696,9 @@ static int ld_usb_probe(struct usb_interface *intf, const struct usb_device_id * dev_warn(&intf->dev, "Interrupt out endpoint not found (using control endpoint instead)\n"); dev->interrupt_in_endpoint_size = usb_endpoint_maxp(dev->interrupt_in_endpoint); - dev->ring_buffer = - kmalloc_array(ring_buffer_size, - sizeof(size_t) + dev->interrupt_in_endpoint_size, - GFP_KERNEL); + dev->ring_buffer = kcalloc(ring_buffer_size, + sizeof(size_t) + dev->interrupt_in_endpoint_size, + GFP_KERNEL); if (!dev->ring_buffer) goto error; dev->interrupt_in_buffer = kmalloc(dev->interrupt_in_endpoint_size, GFP_KERNEL); diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c index 9d4c52a7ebe0..23061f1526b4 100644 --- a/drivers/usb/misc/legousbtower.c +++ b/drivers/usb/misc/legousbtower.c @@ -419,10 +419,7 @@ static int tower_release (struct inode *inode, struct file *file) goto exit; } - if (mutex_lock_interruptible(&dev->lock)) { - retval = -ERESTARTSYS; - goto exit; - } + mutex_lock(&dev->lock); if (dev->open_count != 1) { dev_dbg(&dev->udev->dev, "%s: device not opened exactly once\n", @@ -881,7 +878,7 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device get_version_reply, sizeof(*get_version_reply), 1000); - if (result < sizeof(*get_version_reply)) { + if (result != sizeof(*get_version_reply)) { if (result >= 0) result = -EIO; dev_err(idev, "get version request failed: %d\n", result); diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c index c3d5c1206eec..9dd02160cca9 100644 --- a/drivers/usb/mtu3/mtu3_core.c +++ b/drivers/usb/mtu3/mtu3_core.c @@ -16,6 +16,7 @@ #include <linux/platform_device.h> #include "mtu3.h" +#include "mtu3_dr.h" #include "mtu3_debug.h" #include "mtu3_trace.h" diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index 4c3de777ef6c..a3c30b609433 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -162,17 +162,17 @@ void usbhs_usbreq_get_val(struct usbhs_priv *priv, struct usb_ctrlrequest *req) req->bRequest = (val >> 8) & 0xFF; req->bRequestType = (val >> 0) & 0xFF; - req->wValue = usbhs_read(priv, USBVAL); - req->wIndex = usbhs_read(priv, USBINDX); - req->wLength = usbhs_read(priv, USBLENG); + req->wValue = cpu_to_le16(usbhs_read(priv, USBVAL)); + req->wIndex = cpu_to_le16(usbhs_read(priv, USBINDX)); + req->wLength = cpu_to_le16(usbhs_read(priv, USBLENG)); } void usbhs_usbreq_set_val(struct usbhs_priv *priv, struct usb_ctrlrequest *req) { usbhs_write(priv, USBREQ, (req->bRequest << 8) | req->bRequestType); - usbhs_write(priv, USBVAL, req->wValue); - usbhs_write(priv, USBINDX, req->wIndex); - usbhs_write(priv, USBLENG, req->wLength); + usbhs_write(priv, USBVAL, le16_to_cpu(req->wValue)); + usbhs_write(priv, USBINDX, le16_to_cpu(req->wIndex)); + usbhs_write(priv, USBLENG, le16_to_cpu(req->wLength)); usbhs_bset(priv, DCPCTR, SUREQ, SUREQ); } diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index e5ef56991dba..cd38d74b3223 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -265,7 +265,7 @@ static int usbhsg_recip_handler_std_set_device(struct usbhs_priv *priv, case USB_DEVICE_TEST_MODE: usbhsg_recip_handler_std_control_done(priv, uep, ctrl); udelay(100); - usbhs_sys_set_test_mode(priv, le16_to_cpu(ctrl->wIndex >> 8)); + usbhs_sys_set_test_mode(priv, le16_to_cpu(ctrl->wIndex) >> 8); break; default: usbhsg_recip_handler_std_control_done(priv, uep, ctrl); @@ -315,7 +315,7 @@ static void __usbhsg_recip_send_status(struct usbhsg_gpriv *gpriv, struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(dcp); struct device *dev = usbhsg_gpriv_to_dev(gpriv); struct usb_request *req; - unsigned short *buf; + __le16 *buf; /* alloc new usb_request for recip */ req = usb_ep_alloc_request(&dcp->ep, GFP_ATOMIC); diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index dd0ad67aa71e..ef23acc9b9ce 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -776,7 +776,6 @@ static void ti_close(struct usb_serial_port *port) struct ti_port *tport; int port_number; int status; - int do_unlock; unsigned long flags; tdev = usb_get_serial_data(port->serial); @@ -800,16 +799,13 @@ static void ti_close(struct usb_serial_port *port) "%s - cannot send close port command, %d\n" , __func__, status); - /* if mutex_lock is interrupted, continue anyway */ - do_unlock = !mutex_lock_interruptible(&tdev->td_open_close_lock); - --tport->tp_tdev->td_open_port_count; - if (tport->tp_tdev->td_open_port_count <= 0) { + mutex_lock(&tdev->td_open_close_lock); + --tdev->td_open_port_count; + if (tdev->td_open_port_count == 0) { /* last port is closed, shut down interrupt urb */ usb_kill_urb(port->serial->port[0]->interrupt_in_urb); - tport->tp_tdev->td_open_port_count = 0; } - if (do_unlock) - mutex_unlock(&tdev->td_open_close_lock); + mutex_unlock(&tdev->td_open_close_lock); } diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c index 79314d8c94a4..ca3bd58f2025 100644 --- a/drivers/usb/serial/whiteheat.c +++ b/drivers/usb/serial/whiteheat.c @@ -559,6 +559,10 @@ static int firm_send_command(struct usb_serial_port *port, __u8 command, command_port = port->serial->port[COMMAND_PORT]; command_info = usb_get_serial_port_data(command_port); + + if (command_port->bulk_out_size < datasize + 1) + return -EIO; + mutex_lock(&command_info->mutex); command_info->command_finished = false; @@ -632,6 +636,7 @@ static void firm_setup_port(struct tty_struct *tty) struct device *dev = &port->dev; struct whiteheat_port_settings port_settings; unsigned int cflag = tty->termios.c_cflag; + speed_t baud; port_settings.port = port->port_number + 1; @@ -692,11 +697,13 @@ static void firm_setup_port(struct tty_struct *tty) dev_dbg(dev, "%s - XON = %2x, XOFF = %2x\n", __func__, port_settings.xon, port_settings.xoff); /* get the baud rate wanted */ - port_settings.baud = tty_get_baud_rate(tty); - dev_dbg(dev, "%s - baud rate = %d\n", __func__, port_settings.baud); + baud = tty_get_baud_rate(tty); + port_settings.baud = cpu_to_le32(baud); + dev_dbg(dev, "%s - baud rate = %u\n", __func__, baud); /* fixme: should set validated settings */ - tty_encode_baud_rate(tty, port_settings.baud, port_settings.baud); + tty_encode_baud_rate(tty, baud, baud); + /* handle any settings that aren't specified in the tty structure */ port_settings.lloop = 0; diff --git a/drivers/usb/serial/whiteheat.h b/drivers/usb/serial/whiteheat.h index 00398149cd8d..269e727a92f9 100644 --- a/drivers/usb/serial/whiteheat.h +++ b/drivers/usb/serial/whiteheat.h @@ -87,7 +87,7 @@ struct whiteheat_simple { struct whiteheat_port_settings { __u8 port; /* port number (1 to N) */ - __u32 baud; /* any value 7 - 460800, firmware calculates + __le32 baud; /* any value 7 - 460800, firmware calculates best fit; arrives little endian */ __u8 bits; /* 5, 6, 7, or 8 */ __u8 stop; /* 1 or 2, default 1 (2 = 1.5 if bits = 5) */ diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 6737fab94959..54a3c8195c96 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -68,7 +68,6 @@ static const char* host_info(struct Scsi_Host *host) static int slave_alloc (struct scsi_device *sdev) { struct us_data *us = host_to_us(sdev->host); - int maxp; /* * Set the INQUIRY transfer length to 36. We don't use any of @@ -78,15 +77,6 @@ static int slave_alloc (struct scsi_device *sdev) sdev->inquiry_len = 36; /* - * USB has unusual scatter-gather requirements: the length of each - * scatterlist element except the last must be divisible by the - * Bulk maxpacket value. Fortunately this value is always a - * power of 2. Inform the block layer about this requirement. - */ - maxp = usb_maxpacket(us->pusb_dev, us->recv_bulk_pipe, 0); - blk_queue_virt_boundary(sdev->request_queue, maxp - 1); - - /* * Some host controllers may have alignment requirements. * We'll play it safe by requiring 512-byte alignment always. */ diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index bf80d6f81f58..34538253f12c 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -789,30 +789,10 @@ static int uas_slave_alloc(struct scsi_device *sdev) { struct uas_dev_info *devinfo = (struct uas_dev_info *)sdev->host->hostdata; - int maxp; sdev->hostdata = devinfo; /* - * We have two requirements here. We must satisfy the requirements - * of the physical HC and the demands of the protocol, as we - * definitely want no additional memory allocation in this path - * ruling out using bounce buffers. - * - * For a transmission on USB to continue we must never send - * a package that is smaller than maxpacket. Hence the length of each - * scatterlist element except the last must be divisible by the - * Bulk maxpacket value. - * If the HC does not ensure that through SG, - * the upper layer must do that. We must assume nothing - * about the capabilities off the HC, so we use the most - * pessimistic requirement. - */ - - maxp = usb_maxpacket(devinfo->udev, devinfo->data_in_pipe, 0); - blk_queue_virt_boundary(sdev->request_queue, maxp - 1); - - /* * The protocol has no requirements on alignment in the strict sense. * Controllers may or may not have alignment restrictions. * As this is not exported, we use an extremely conservative guess. diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c index c3803785f6ef..0ae40a13a9fe 100644 --- a/drivers/usb/usbip/vhci_tx.c +++ b/drivers/usb/usbip/vhci_tx.c @@ -147,7 +147,10 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev) } kfree(iov); + /* This is only for isochronous case */ kfree(iso_buffer); + iso_buffer = NULL; + usbip_dbg_vhci_tx("send txdata\n"); total_size += txsize; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 96fddc1dafc3..d864277ea16f 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1658,7 +1658,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, struct bus_type *bus = NULL; int ret; bool resv_msi, msi_remap; - phys_addr_t resv_msi_base; + phys_addr_t resv_msi_base = 0; struct iommu_domain_geometry geo; LIST_HEAD(iova_copy); LIST_HEAD(group_resv_regions); diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 08ad0d1f0476..a0a2d74967ef 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -852,6 +852,12 @@ static inline int xfer_kern(void *src, void *dst, size_t len) return 0; } +static inline int kern_xfer(void *dst, void *src, size_t len) +{ + memcpy(dst, src, len); + return 0; +} + /** * vringh_init_kern - initialize a vringh for a kernelspace vring. * @vrh: the vringh to initialize. @@ -958,7 +964,7 @@ EXPORT_SYMBOL(vringh_iov_pull_kern); ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov, const void *src, size_t len) { - return vringh_iov_xfer(wiov, (void *)src, len, xfer_kern); + return vringh_iov_xfer(wiov, (void *)src, len, kern_xfer); } EXPORT_SYMBOL(vringh_iov_push_kern); diff --git a/drivers/video/fbdev/c2p_core.h b/drivers/video/fbdev/c2p_core.h index e1035a865fb9..45a6d895a7d7 100644 --- a/drivers/video/fbdev/c2p_core.h +++ b/drivers/video/fbdev/c2p_core.h @@ -29,7 +29,7 @@ static inline void _transp(u32 d[], unsigned int i1, unsigned int i2, extern void c2p_unsupported(void); -static inline u32 get_mask(unsigned int n) +static __always_inline u32 get_mask(unsigned int n) { switch (n) { case 1: @@ -57,7 +57,7 @@ static inline u32 get_mask(unsigned int n) * Transpose operations on 8 32-bit words */ -static inline void transp8(u32 d[], unsigned int n, unsigned int m) +static __always_inline void transp8(u32 d[], unsigned int n, unsigned int m) { u32 mask = get_mask(n); @@ -99,7 +99,7 @@ static inline void transp8(u32 d[], unsigned int n, unsigned int m) * Transpose operations on 4 32-bit words */ -static inline void transp4(u32 d[], unsigned int n, unsigned int m) +static __always_inline void transp4(u32 d[], unsigned int n, unsigned int m) { u32 mask = get_mask(n); @@ -126,7 +126,7 @@ static inline void transp4(u32 d[], unsigned int n, unsigned int m) * Transpose operations on 4 32-bit words (reverse order) */ -static inline void transp4x(u32 d[], unsigned int n, unsigned int m) +static __always_inline void transp4x(u32 d[], unsigned int n, unsigned int m) { u32 mask = get_mask(n); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 226fbb995fb0..e05679c478e2 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -772,6 +772,13 @@ static unsigned long shrink_free_pages(struct virtio_balloon *vb, return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER; } +static unsigned long leak_balloon_pages(struct virtio_balloon *vb, + unsigned long pages_to_free) +{ + return leak_balloon(vb, pages_to_free * VIRTIO_BALLOON_PAGES_PER_PAGE) / + VIRTIO_BALLOON_PAGES_PER_PAGE; +} + static unsigned long shrink_balloon_pages(struct virtio_balloon *vb, unsigned long pages_to_free) { @@ -782,11 +789,10 @@ static unsigned long shrink_balloon_pages(struct virtio_balloon *vb, * VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it * multiple times to deflate pages till reaching pages_to_free. */ - while (vb->num_pages && pages_to_free) { - pages_freed += leak_balloon(vb, pages_to_free) / - VIRTIO_BALLOON_PAGES_PER_PAGE; - pages_to_free -= pages_freed; - } + while (vb->num_pages && pages_freed < pages_to_free) + pages_freed += leak_balloon_pages(vb, + pages_to_free - pages_freed); + update_balloon_size(vb); return pages_freed; @@ -799,7 +805,7 @@ static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker, struct virtio_balloon *vb = container_of(shrinker, struct virtio_balloon, shrinker); - pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE; + pages_to_free = sc->nr_to_scan; if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) pages_freed = shrink_free_pages(vb, pages_to_free); @@ -820,7 +826,7 @@ static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker, unsigned long count; count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE; - count += vb->num_free_page_blocks >> VIRTIO_BALLOON_FREE_PAGE_ORDER; + count += vb->num_free_page_blocks << VIRTIO_BALLOON_FREE_PAGE_ORDER; return count; } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index bdc08244a648..867c7ebd3f10 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -583,7 +583,7 @@ unmap_release: kfree(desc); END_USE(vq); - return -EIO; + return -ENOMEM; } static bool virtqueue_kick_prepare_split(struct virtqueue *_vq) @@ -1085,7 +1085,7 @@ unmap_release: kfree(desc); END_USE(vq); - return -EIO; + return -ENOMEM; } static inline int virtqueue_add_packed(struct virtqueue *_vq, @@ -1499,9 +1499,6 @@ static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq) * counter first before updating event flags. */ virtio_wmb(vq->weak_barriers); - } else { - used_idx = vq->last_used_idx; - wrap_counter = vq->packed.used_wrap_counter; } if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) { @@ -1518,7 +1515,9 @@ static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq) */ virtio_mb(vq->weak_barriers); - if (is_used_desc_packed(vq, used_idx, wrap_counter)) { + if (is_used_desc_packed(vq, + vq->last_used_idx, + vq->packed.used_wrap_counter)) { END_USE(vq); return false; } diff --git a/drivers/watchdog/bd70528_wdt.c b/drivers/watchdog/bd70528_wdt.c index b0152fef4fc7..bc60e036627a 100644 --- a/drivers/watchdog/bd70528_wdt.c +++ b/drivers/watchdog/bd70528_wdt.c @@ -288,3 +288,4 @@ module_platform_driver(bd70528_wdt); MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>"); MODULE_DESCRIPTION("BD70528 watchdog driver"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:bd70528-wdt"); diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index 9393be584e72..808eeb4779e4 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -26,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/timer.h> +#include <linux/compat.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/io.h> @@ -473,6 +474,11 @@ static long cpwd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; } +static long cpwd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return cpwd_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} + static ssize_t cpwd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -497,7 +503,7 @@ static ssize_t cpwd_read(struct file *file, char __user *buffer, static const struct file_operations cpwd_fops = { .owner = THIS_MODULE, .unlocked_ioctl = cpwd_ioctl, - .compat_ioctl = compat_ptr_ioctl, + .compat_ioctl = cpwd_compat_ioctl, .open = cpwd_open, .write = cpwd_write, .read = cpwd_read, diff --git a/drivers/watchdog/imx_sc_wdt.c b/drivers/watchdog/imx_sc_wdt.c index 7ea5cf54e94a..8ed89f032ebf 100644 --- a/drivers/watchdog/imx_sc_wdt.c +++ b/drivers/watchdog/imx_sc_wdt.c @@ -99,8 +99,14 @@ static int imx_sc_wdt_set_pretimeout(struct watchdog_device *wdog, { struct arm_smccc_res res; + /* + * SCU firmware calculates pretimeout based on current time + * stamp instead of watchdog timeout stamp, need to convert + * the pretimeout to SCU firmware's timeout value. + */ arm_smccc_smc(IMX_SIP_TIMER, IMX_SIP_TIMER_SET_PRETIME_WDOG, - pretimeout * 1000, 0, 0, 0, 0, 0, &res); + (wdog->timeout - pretimeout) * 1000, 0, 0, 0, + 0, 0, &res); if (res.a0) return -EACCES; diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c index d17c1a6ed723..5a9ca10fbcfa 100644 --- a/drivers/watchdog/meson_gxbb_wdt.c +++ b/drivers/watchdog/meson_gxbb_wdt.c @@ -89,8 +89,8 @@ static unsigned int meson_gxbb_wdt_get_timeleft(struct watchdog_device *wdt_dev) reg = readl(data->reg_base + GXBB_WDT_TCNT_REG); - return ((reg >> GXBB_WDT_TCNT_CNT_SHIFT) - - (reg & GXBB_WDT_TCNT_SETUP_MASK)) / 1000; + return ((reg & GXBB_WDT_TCNT_SETUP_MASK) - + (reg >> GXBB_WDT_TCNT_CNT_SHIFT)) / 1000; } static const struct watchdog_ops meson_gxbb_wdt_ops = { diff --git a/drivers/watchdog/pm8916_wdt.c b/drivers/watchdog/pm8916_wdt.c index 2d3652004e39..1213179f863c 100644 --- a/drivers/watchdog/pm8916_wdt.c +++ b/drivers/watchdog/pm8916_wdt.c @@ -163,9 +163,17 @@ static int pm8916_wdt_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq > 0) { - if (devm_request_irq(dev, irq, pm8916_wdt_isr, 0, "pm8916_wdt", - wdt)) - irq = 0; + err = devm_request_irq(dev, irq, pm8916_wdt_isr, 0, + "pm8916_wdt", wdt); + if (err) + return err; + + wdt->wdev.info = &pm8916_wdt_pt_ident; + } else { + if (irq == -EPROBE_DEFER) + return -EPROBE_DEFER; + + wdt->wdev.info = &pm8916_wdt_ident; } /* Configure watchdog to hard-reset mode */ @@ -177,7 +185,6 @@ static int pm8916_wdt_probe(struct platform_device *pdev) return err; } - wdt->wdev.info = (irq > 0) ? &pm8916_wdt_pt_ident : &pm8916_wdt_ident, wdt->wdev.ops = &pm8916_wdt_ops, wdt->wdev.parent = dev; wdt->wdev.min_timeout = PM8916_WDT_MIN_TIMEOUT; diff --git a/fs/Kconfig b/fs/Kconfig index 2501e6f1f965..7b623e9fc1b0 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -322,4 +322,7 @@ source "fs/nls/Kconfig" source "fs/dlm/Kconfig" source "fs/unicode/Kconfig" +config IO_WQ + bool + endmenu diff --git a/fs/Makefile b/fs/Makefile index 14231b4cf383..1148c555c4d3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o obj-$(CONFIG_IO_URING) += io_uring.o +obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 6cdd7047c809..2dca8df1a18d 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -312,7 +312,6 @@ void afs_break_callbacks(struct afs_server *server, size_t count, _enter("%p,%zu,", server, count); ASSERT(server != NULL); - ASSERTCMP(count, <=, AFSCBMAX); /* TODO: Sort the callback break list by volume ID */ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index cc12772d0a4d..497f979018c2 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -803,7 +803,12 @@ success: continue; if (cookie->inodes[i]) { - afs_vnode_commit_status(&fc, AFS_FS_I(cookie->inodes[i]), + struct afs_vnode *iv = AFS_FS_I(cookie->inodes[i]); + + if (test_bit(AFS_VNODE_UNSET, &iv->flags)) + continue; + + afs_vnode_commit_status(&fc, iv, scb->cb_break, NULL, scb); continue; } diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 0e5269374ac1..61498d9f06ef 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -637,6 +637,7 @@ long afs_wait_for_call_to_complete(struct afs_call *call, call->need_attention = false; __set_current_state(TASK_RUNNING); afs_deliver_to_call(call); + timeout = rtt2; continue; } diff --git a/fs/afs/super.c b/fs/afs/super.c index f18911e8d770..488641b1a418 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -435,6 +435,7 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) /* fill in the superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; if (!as->dyn_root) @@ -2179,7 +2179,7 @@ SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, #ifdef CONFIG_COMPAT struct __compat_aio_sigset { - compat_sigset_t __user *sigmask; + compat_uptr_t sigmask; compat_size_t sigsetsize; }; @@ -2193,7 +2193,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, struct old_timespec32 __user *, timeout, const struct __compat_aio_sigset __user *, usig) { - struct __compat_aio_sigset ksig = { NULL, }; + struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; @@ -2204,7 +2204,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; - ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize); + ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; @@ -2228,7 +2228,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, struct __kernel_timespec __user *, timeout, const struct __compat_aio_sigset __user *, usig) { - struct __compat_aio_sigset ksig = { NULL, }; + struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; @@ -2239,7 +2239,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; - ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize); + ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index 2866fabf497f..91f5787dae7c 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -459,9 +459,10 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb, */ how &= ~AUTOFS_EXP_LEAVES; found = should_expire(expired, mnt, timeout, how); - if (!found || found != expired) - /* Something has changed, continue */ + if (found != expired) { // something has changed, continue + dput(found); goto next; + } if (expired != dentry) dput(dentry); diff --git a/fs/block_dev.c b/fs/block_dev.c index 9c073dbdc1b0..ee63c2732fa2 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1403,11 +1403,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty) "resized disk %s\n", bdev->bd_disk ? bdev->bd_disk->disk_name : ""); } - - if (!bdev->bd_disk) - return; - if (disk_part_scan_enabled(bdev->bd_disk)) - bdev->bd_invalidated = 1; + bdev->bd_invalidated = 1; } /** @@ -1420,8 +1416,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty) * and adjusts it if it differs. When shrinking the bdev size, its all caches * are freed. */ -void check_disk_size_change(struct gendisk *disk, struct block_device *bdev, - bool verbose) +static void check_disk_size_change(struct gendisk *disk, + struct block_device *bdev, bool verbose) { loff_t disk_size, bdev_size; @@ -1437,6 +1433,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev, if (bdev_size > disk_size) flush_disk(bdev, false); } + bdev->bd_invalidated = 0; } /** @@ -1466,7 +1463,6 @@ int revalidate_disk(struct gendisk *disk) mutex_lock(&bdev->bd_mutex); check_disk_size_change(disk, bdev, ret == 0); - bdev->bd_invalidated = 0; mutex_unlock(&bdev->bd_mutex); bdput(bdev); } @@ -1512,6 +1508,45 @@ EXPORT_SYMBOL(bd_set_size); static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); +int bdev_disk_changed(struct block_device *bdev, bool invalidate) +{ + struct gendisk *disk = bdev->bd_disk; + int ret; + + lockdep_assert_held(&bdev->bd_mutex); + +rescan: + ret = blk_drop_partitions(disk, bdev); + if (ret) + return ret; + + if (invalidate) + set_capacity(disk, 0); + else if (disk->fops->revalidate_disk) + disk->fops->revalidate_disk(disk); + + check_disk_size_change(disk, bdev, !invalidate); + + if (get_capacity(disk)) { + ret = blk_add_partitions(disk, bdev); + if (ret == -EAGAIN) + goto rescan; + } else { + /* + * Tell userspace that the media / partition table may have + * changed. + */ + kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); + } + + return ret; +} +/* + * Only exported for for loop and dasd for historic reasons. Don't use in new + * code! + */ +EXPORT_SYMBOL_GPL(bdev_disk_changed); + /* * bd_mutex locking: * @@ -1594,12 +1629,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) * The latter is necessary to prevent ghost * partitions on a removed medium. */ - if (bdev->bd_invalidated) { - if (!ret) - rescan_partitions(disk, bdev); - else if (ret == -ENOMEDIUM) - invalidate_partitions(disk, bdev); - } + if (bdev->bd_invalidated && + (!ret || ret == -ENOMEDIUM)) + bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_clear; @@ -1632,12 +1664,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ - if (bdev->bd_invalidated) { - if (!ret) - rescan_partitions(bdev->bd_disk, bdev); - else if (ret == -ENOMEDIUM) - invalidate_partitions(bdev->bd_disk, bdev); - } + if (bdev->bd_invalidated && + (!ret || ret == -ENOMEDIUM)) + bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) goto out_unlock_bdev; } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index bf7e3f23bba7..670700cb1110 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1761,6 +1761,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) btrfs_err(info, "bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", cache->key.objectid); + btrfs_put_block_group(cache); ret = -EINVAL; goto error; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 19d669d12ca1..fe2b8765d9e6 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -734,8 +734,6 @@ struct btrfs_fs_info { struct btrfs_workqueue *fixup_workers; struct btrfs_workqueue *delayed_workers; - /* the extent workers do delayed refs on the extent allocation tree */ - struct btrfs_workqueue *extent_workers; struct task_struct *transaction_kthread; struct task_struct *cleaner_kthread; u32 thread_pool_size; @@ -2489,8 +2487,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, int nitems, bool use_global_rsv); void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); -void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes, - bool qgroup_free); +void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes); int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes); u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index d949d7d2abed..db9f2c58eb4a 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -381,7 +381,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) out_qgroup: btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve); out_fail: - btrfs_inode_rsv_release(inode, true); if (delalloc_lock) mutex_unlock(&inode->delalloc_mutex); return ret; @@ -418,7 +417,6 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, * btrfs_delalloc_release_extents - release our outstanding_extents * @inode: the inode to balance the reservation for. * @num_bytes: the number of bytes we originally reserved with - * @qgroup_free: do we need to free qgroup meta reservation or convert them. * * When we reserve space we increase outstanding_extents for the extents we may * add. Once we've set the range as delalloc or created our ordered extents we @@ -426,8 +424,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, * temporarily tracked outstanding_extents. This _must_ be used in conjunction * with btrfs_delalloc_reserve_metadata. */ -void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes, - bool qgroup_free) +void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; unsigned num_extents; @@ -441,7 +438,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes, if (btrfs_is_testing(fs_info)) return; - btrfs_inode_rsv_release(inode, qgroup_free); + btrfs_inode_rsv_release(inode, true); } /** diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 044981cf6df9..402b61bf345c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2008,7 +2008,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) btrfs_destroy_workqueue(fs_info->readahead_workers); btrfs_destroy_workqueue(fs_info->flush_workers); btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); - btrfs_destroy_workqueue(fs_info->extent_workers); /* * Now that all other work queues are destroyed, we can safely destroy * the queues used for metadata I/O, since tasks from those other work @@ -2214,10 +2213,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, max_active, 2); fs_info->qgroup_rescan_workers = btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0); - fs_info->extent_workers = - btrfs_alloc_workqueue(fs_info, "extent-refs", flags, - min_t(u64, fs_devices->num_devices, - max_active), 8); if (!(fs_info->workers && fs_info->delalloc_workers && fs_info->submit_workers && fs_info->flush_workers && @@ -2228,7 +2223,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info, fs_info->endio_freespace_worker && fs_info->rmw_workers && fs_info->caching_workers && fs_info->readahead_workers && fs_info->fixup_workers && fs_info->delayed_workers && - fs_info->extent_workers && fs_info->qgroup_rescan_workers)) { return -ENOMEM; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 27e5b269e729..435a502a3226 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1692,7 +1692,7 @@ again: force_page_uptodate); if (ret) { btrfs_delalloc_release_extents(BTRFS_I(inode), - reserve_bytes, true); + reserve_bytes); break; } @@ -1704,7 +1704,7 @@ again: if (extents_locked == -EAGAIN) goto again; btrfs_delalloc_release_extents(BTRFS_I(inode), - reserve_bytes, true); + reserve_bytes); ret = extents_locked; break; } @@ -1772,8 +1772,7 @@ again: else free_extent_state(cached_state); - btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes, - true); + btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); if (ret) { btrfs_drop_pages(pages, num_pages); break; @@ -2068,25 +2067,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct btrfs_trans_handle *trans; struct btrfs_log_ctx ctx; int ret = 0, err; - u64 len; - /* - * If the inode needs a full sync, make sure we use a full range to - * avoid log tree corruption, due to hole detection racing with ordered - * extent completion for adjacent ranges, and assertion failures during - * hole detection. - */ - if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags)) { - start = 0; - end = LLONG_MAX; - } - - /* - * The range length can be represented by u64, we have to do the typecasts - * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync() - */ - len = (u64)end - (u64)start + 1; trace_btrfs_sync_file(file, datasync); btrfs_init_log_ctx(&ctx, inode); @@ -2113,6 +2094,19 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* + * If the inode needs a full sync, make sure we use a full range to + * avoid log tree corruption, due to hole detection racing with ordered + * extent completion for adjacent ranges, and assertion failures during + * hole detection. Do this while holding the inode lock, to avoid races + * with other tasks. + */ + if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags)) { + start = 0; + end = LLONG_MAX; + } + + /* * Before we acquired the inode's lock, someone may have dirtied more * pages in the target range. We need to make sure that writeback for * any such pages does not start while we are logging the inode, because @@ -2139,8 +2133,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) /* * We have to do this here to avoid the priority inversion of waiting on * IO of a lower priority task while holding a transaction open. + * + * Also, the range length can be represented by u64, we have to do the + * typecasts to avoid signed overflow if it's [0, LLONG_MAX]. */ - ret = btrfs_wait_ordered_range(inode, start, len); + ret = btrfs_wait_ordered_range(inode, start, (u64)end - (u64)start + 1); if (ret) { up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 63cad7865d75..37345fb6191d 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -501,13 +501,13 @@ again: ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc); btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true); goto out_put; } ret = btrfs_write_out_ino_cache(root, trans, path, inode); - btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, false); + btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc); out_put: iput(inode); out_release: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0f2754eaa05b..015910079e73 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -474,6 +474,7 @@ static noinline int compress_file_range(struct async_chunk *async_chunk) u64 start = async_chunk->start; u64 end = async_chunk->end; u64 actual_end; + u64 i_size; int ret = 0; struct page **pages = NULL; unsigned long nr_pages; @@ -488,7 +489,19 @@ static noinline int compress_file_range(struct async_chunk *async_chunk) inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1, SZ_16K); - actual_end = min_t(u64, i_size_read(inode), end + 1); + /* + * We need to save i_size before now because it could change in between + * us evaluating the size and assigning it. This is because we lock and + * unlock the page in truncate and fallocate, and then modify the i_size + * later on. + * + * The barriers are to emulate READ_ONCE, remove that once i_size_read + * does that for us. + */ + barrier(); + i_size = i_size_read(inode); + barrier(); + actual_end = min_t(u64, i_size, end + 1); again: will_compress = 0; nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1; @@ -2206,7 +2219,7 @@ again: ClearPageChecked(page); set_page_dirty(page); - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, false); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); out: unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, &cached_state); @@ -4951,7 +4964,7 @@ again: if (!page) { btrfs_delalloc_release_space(inode, data_reserved, block_start, blocksize, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); ret = -ENOMEM; goto out; } @@ -5018,7 +5031,7 @@ out_unlock: if (ret) btrfs_delalloc_release_space(inode, data_reserved, block_start, blocksize, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, (ret != 0)); + btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); unlock_page(page); put_page(page); out: @@ -8709,7 +8722,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } else if (ret >= 0 && (size_t)ret < count) btrfs_delalloc_release_space(inode, data_reserved, offset, count - (size_t)ret, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), count, false); + btrfs_delalloc_release_extents(BTRFS_I(inode), count); } out: if (wakeup) @@ -9059,7 +9072,7 @@ again: unlock_extent_cached(io_tree, page_start, page_end, &cached_state); if (!ret2) { - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); sb_end_pagefault(inode->i_sb); extent_changeset_free(data_reserved); return VM_FAULT_LOCKED; @@ -9068,7 +9081,7 @@ again: out_unlock: unlock_page(page); out: - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0)); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); btrfs_delalloc_release_space(inode, data_reserved, page_start, reserved_space, (ret != 0)); out_noreserve: @@ -9731,6 +9744,18 @@ out_fail: commit_transaction = true; } if (commit_transaction) { + /* + * We may have set commit_transaction when logging the new name + * in the destination root, in which case we left the source + * root context in the list of log contextes. So make sure we + * remove it to avoid invalid memory accesses, since the context + * was allocated in our stack frame. + */ + if (sync_log_root) { + mutex_lock(&root->log_mutex); + list_del_init(&ctx_root.list); + mutex_unlock(&root->log_mutex); + } ret = btrfs_commit_transaction(trans); } else { int ret2; @@ -9744,6 +9769,9 @@ out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); + ASSERT(list_empty(&ctx_root.list)); + ASSERT(list_empty(&ctx_dest.list)); + return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index de730e56d3f5..23272d9154f3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1360,8 +1360,7 @@ again: unlock_page(pages[i]); put_page(pages[i]); } - btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT, - false); + btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return i_done; out: @@ -1372,8 +1371,7 @@ out: btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT, - true); + btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return ret; @@ -4197,9 +4195,6 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root, u64 transid; int ret; - btrfs_warn(root->fs_info, - "START_SYNC ioctl is deprecated and will be removed in kernel 5.7"); - trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT) @@ -4227,9 +4222,6 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info, { u64 transid; - btrfs_warn(fs_info, - "WAIT_SYNC ioctl is deprecated and will be removed in kernel 5.7"); - if (argp) { if (copy_from_user(&transid, argp, sizeof(transid))) return -EFAULT; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c4bb69941c77..3ad151655eb8 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3629,7 +3629,7 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, return 0; BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); - trace_qgroup_meta_reserve(root, type, (s64)num_bytes); + trace_qgroup_meta_reserve(root, (s64)num_bytes, type); ret = qgroup_reserve(root, num_bytes, enforce, type); if (ret < 0) return ret; @@ -3676,7 +3676,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, */ num_bytes = sub_root_meta_rsv(root, num_bytes, type); BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); - trace_qgroup_meta_reserve(root, type, -(s64)num_bytes); + trace_qgroup_meta_reserve(root, -(s64)num_bytes, type); btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid, num_bytes, type); } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 00504657b602..5cd42b66818c 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3277,6 +3277,8 @@ static int relocate_file_extent_cluster(struct inode *inode, if (!page) { btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), + PAGE_SIZE); ret = -ENOMEM; goto out; } @@ -3297,7 +3299,7 @@ static int relocate_file_extent_cluster(struct inode *inode, btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE, true); btrfs_delalloc_release_extents(BTRFS_I(inode), - PAGE_SIZE, true); + PAGE_SIZE); ret = -EIO; goto out; } @@ -3326,7 +3328,7 @@ static int relocate_file_extent_cluster(struct inode *inode, btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE, true); btrfs_delalloc_release_extents(BTRFS_I(inode), - PAGE_SIZE, true); + PAGE_SIZE); clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, @@ -3342,8 +3344,7 @@ static int relocate_file_extent_cluster(struct inode *inode, put_page(page); index++; - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, - false); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); balance_dirty_pages_ratelimited(inode->i_mapping); btrfs_throttle(fs_info); } diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 98dc092a905e..e8a4b0ebe97f 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -893,6 +893,15 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, while (ticket->bytes > 0 && ticket->error == 0) { ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE); if (ret) { + /* + * Delete us from the list. After we unlock the space + * info, we don't want the async reclaim job to reserve + * space for this ticket. If that would happen, then the + * ticket's task would not known that space was reserved + * despite getting an error, resulting in a space leak + * (bytes_may_use counter of our space_info). + */ + list_del_init(&ticket->list); ticket->error = -EINTR; break; } @@ -945,12 +954,24 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, spin_lock(&space_info->lock); ret = ticket->error; if (ticket->bytes || ticket->error) { + /* + * Need to delete here for priority tickets. For regular tickets + * either the async reclaim job deletes the ticket from the list + * or we delete it ourselves at wait_reserve_ticket(). + */ list_del_init(&ticket->list); if (!ret) ret = -ENOSPC; } spin_unlock(&space_info->lock); ASSERT(list_empty(&ticket->list)); + /* + * Check that we can't have an error set if the reservation succeeded, + * as that would confuse tasks and lead them to error out without + * releasing reserved space (if an error happens the expectation is that + * space wasn't reserved at all). + */ + ASSERT(!(ticket->bytes == 0 && ticket->error)); return ret; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 43e488f5d063..076d5b8014fb 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -686,9 +686,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot, static int check_dev_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { - struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_dev_item *ditem; - u64 max_devid = max(BTRFS_MAX_DEVS(fs_info), BTRFS_MAX_DEVS_SYS_CHUNK); if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) { dev_item_err(leaf, slot, @@ -696,12 +694,6 @@ static int check_dev_item(struct extent_buffer *leaf, key->objectid, BTRFS_DEV_ITEMS_OBJECTID); return -EUCLEAN; } - if (key->offset > max_devid) { - dev_item_err(leaf, slot, - "invalid devid: has=%llu expect=[0, %llu]", - key->offset, max_devid); - return -EUCLEAN; - } ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); if (btrfs_device_id(leaf, ditem) != key->offset) { dev_item_err(leaf, slot, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bdfe4493e43a..e04409f85063 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4967,6 +4967,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, } else if (type & BTRFS_BLOCK_GROUP_SYSTEM) { max_stripe_size = SZ_32M; max_chunk_size = 2 * max_stripe_size; + devs_max = min_t(int, devs_max, BTRFS_MAX_DEVS_SYS_CHUNK); } else { btrfs_err(info, "invalid chunk type 0x%llx requested", type); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index d3b9c9d5c1bd..f5a38910a82b 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1058,6 +1058,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode); + /* remove from inode's cap rbtree, and clear auth cap */ + rb_erase(&cap->ci_node, &ci->i_caps); + if (ci->i_auth_cap == cap) + ci->i_auth_cap = NULL; + /* remove from session list */ spin_lock(&session->s_cap_lock); if (session->s_cap_iterator == cap) { @@ -1091,11 +1096,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) spin_unlock(&session->s_cap_lock); - /* remove from inode list */ - rb_erase(&cap->ci_node, &ci->i_caps); - if (ci->i_auth_cap == cap) - ci->i_auth_cap = NULL; - if (removed) ceph_put_cap(mdsc, cap); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4ca0b8ff9a72..d17a789fd856 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1553,36 +1553,37 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) { int valid = 0; struct dentry *parent; - struct inode *dir; + struct inode *dir, *inode; if (flags & LOOKUP_RCU) { parent = READ_ONCE(dentry->d_parent); dir = d_inode_rcu(parent); if (!dir) return -ECHILD; + inode = d_inode_rcu(dentry); } else { parent = dget_parent(dentry); dir = d_inode(parent); + inode = d_inode(dentry); } dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry, - dentry, d_inode(dentry), ceph_dentry(dentry)->offset); + dentry, inode, ceph_dentry(dentry)->offset); /* always trust cached snapped dentries, snapdir dentry */ if (ceph_snap(dir) != CEPH_NOSNAP) { dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry, - dentry, d_inode(dentry)); + dentry, inode); valid = 1; - } else if (d_really_is_positive(dentry) && - ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) { + } else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) { valid = 1; } else { valid = dentry_lease_is_valid(dentry, flags); if (valid == -ECHILD) return valid; if (valid || dir_lease_is_valid(dir, dentry)) { - if (d_really_is_positive(dentry)) - valid = ceph_is_any_caps(d_inode(dentry)); + if (inode) + valid = ceph_is_any_caps(inode); else valid = 1; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d277f71abe0b..8de633964dc3 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -462,6 +462,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, err = ceph_security_init_secctx(dentry, mode, &as_ctx); if (err < 0) goto out_ctx; + } else if (!d_in_lookup(dentry)) { + /* If it's not being looked up, it's negative */ + return -ENOENT; } /* do the open */ @@ -750,6 +753,9 @@ static void ceph_aio_complete(struct inode *inode, if (!atomic_dec_and_test(&aio_req->pending_reqs)) return; + if (aio_req->iocb->ki_flags & IOCB_DIRECT) + inode_dio_end(inode); + ret = aio_req->error; if (!ret) ret = aio_req->total_len; @@ -1088,6 +1094,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, CEPH_CAP_FILE_RD); list_splice(&aio_req->osd_reqs, &osd_reqs); + inode_dio_begin(inode); while (!list_empty(&osd_reqs)) { req = list_first_entry(&osd_reqs, struct ceph_osd_request, @@ -1261,14 +1268,24 @@ again: dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode); + if (iocb->ki_flags & IOCB_DIRECT) + ceph_start_io_direct(inode); + else + ceph_start_io_read(inode); + if (fi->fmode & CEPH_FILE_MODE_LAZY) want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO; else want = CEPH_CAP_FILE_CACHE; ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1, &got, &pinned_page); - if (ret < 0) + if (ret < 0) { + if (iocb->ki_flags & IOCB_DIRECT) + ceph_end_io_direct(inode); + else + ceph_end_io_read(inode); return ret; + } if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 || (iocb->ki_flags & IOCB_DIRECT) || @@ -1280,16 +1297,12 @@ again: if (ci->i_inline_version == CEPH_INLINE_NONE) { if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) { - ceph_start_io_direct(inode); ret = ceph_direct_read_write(iocb, to, NULL, NULL); - ceph_end_io_direct(inode); if (ret >= 0 && ret < len) retry_op = CHECK_EOF; } else { - ceph_start_io_read(inode); ret = ceph_sync_read(iocb, to, &retry_op); - ceph_end_io_read(inode); } } else { retry_op = READ_INLINE; @@ -1300,11 +1313,10 @@ again: inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, ceph_cap_string(got)); ceph_add_rw_context(fi, &rw_ctx); - ceph_start_io_read(inode); ret = generic_file_read_iter(iocb, to); - ceph_end_io_read(inode); ceph_del_rw_context(fi, &rw_ctx); } + dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n", inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret); if (pinned_page) { @@ -1312,6 +1324,12 @@ again: pinned_page = NULL; } ceph_put_cap_refs(ci, got); + + if (iocb->ki_flags & IOCB_DIRECT) + ceph_end_io_direct(inode); + else + ceph_end_io_read(inode); + if (retry_op > HAVE_RETRIED && ret >= 0) { int statret; struct page *page = NULL; @@ -1956,10 +1974,18 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, if (ceph_test_mount_opt(src_fsc, NOCOPYFROM)) return -EOPNOTSUPP; + /* + * Striped file layouts require that we copy partial objects, but the + * OSD copy-from operation only supports full-object copies. Limit + * this to non-striped file layouts for now. + */ if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) || - (src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) || - (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) + (src_ci->i_layout.stripe_count != 1) || + (dst_ci->i_layout.stripe_count != 1) || + (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) { + dout("Invalid src/dst files layout\n"); return -EOPNOTSUPP; + } if (len < src_ci->i_layout.object_size) return -EOPNOTSUPP; /* no remote copy will be done */ diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9f135624ae47..c07407586ce8 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1434,6 +1434,7 @@ retry_lookup: dout(" final dn %p\n", dn); } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP || req->r_op == CEPH_MDS_OP_MKSNAP) && + test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) && !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) { struct inode *dir = req->r_parent; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index edfd643a8205..b47f43fc2d68 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -268,6 +268,7 @@ static int parse_fsopt_token(char *c, void *private) } break; case Opt_fscache_uniq: +#ifdef CONFIG_CEPH_FSCACHE kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = kstrndup(argstr[0].from, argstr[0].to-argstr[0].from, @@ -276,7 +277,10 @@ static int parse_fsopt_token(char *c, void *private) return -ENOMEM; fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; break; - /* misc */ +#else + pr_err("fscache support is disabled\n"); + return -EINVAL; +#endif case Opt_wsize: if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE) return -EINVAL; @@ -353,10 +357,15 @@ static int parse_fsopt_token(char *c, void *private) fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; case Opt_fscache: +#ifdef CONFIG_CEPH_FSCACHE fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = NULL; break; +#else + pr_err("fscache support is disabled\n"); + return -EINVAL; +#endif case Opt_nofscache: fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c049c7b3aa87..1a135d1b85bd 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -169,7 +169,13 @@ cifs_read_super(struct super_block *sb) else sb->s_maxbytes = MAX_NON_LFS; - /* Some very old servers like DOS and OS/2 used 2 second granularity */ + /* + * Some very old servers like DOS and OS/2 used 2 second granularity + * (while all current servers use 100ns granularity - see MS-DTYP) + * but 1 second is the maximum allowed granularity for the VFS + * so for old servers set time granularity to 1 second while for + * everything else (current servers) set it to 100ns. + */ if ((tcon->ses->server->vals->protocol_id == SMB10_PROT_ID) && ((tcon->ses->capabilities & tcon->ses->server->vals->cap_nt_find) == 0) && diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 50dfd9049370..d78bfcc19156 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1391,6 +1391,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file); struct cifsInodeInfo { bool can_cache_brlcks; struct list_head llist; /* locks helb by this inode */ + /* + * NOTE: Some code paths call down_read(lock_sem) twice, so + * we must always use use cifs_down_write() instead of down_write() + * for this semaphore to avoid deadlocks. + */ struct rw_semaphore lock_sem; /* protect the fields above */ /* BB add in lists for dirty pages i.e. write caching info for oplock */ struct list_head openFileList; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index e53e9f62b87b..fe597d3d5208 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -170,6 +170,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile); +extern void cifs_down_write(struct rw_semaphore *sem); extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a64dfa95a925..ccaa8bad336f 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -564,9 +564,11 @@ cifs_reconnect(struct TCP_Server_Info *server) spin_lock(&GlobalMid_Lock); list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { mid_entry = list_entry(tmp, struct mid_q_entry, qhead); + kref_get(&mid_entry->refcount); if (mid_entry->mid_state == MID_REQUEST_SUBMITTED) mid_entry->mid_state = MID_RETRY_NEEDED; list_move(&mid_entry->qhead, &retry_list); + mid_entry->mid_flags |= MID_DELETED; } spin_unlock(&GlobalMid_Lock); mutex_unlock(&server->srv_mutex); @@ -576,6 +578,7 @@ cifs_reconnect(struct TCP_Server_Info *server) mid_entry = list_entry(tmp, struct mid_q_entry, qhead); list_del_init(&mid_entry->qhead); mid_entry->callback(mid_entry); + cifs_mid_q_entry_release(mid_entry); } if (cifs_rdma_enabled(server)) { @@ -895,8 +898,10 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) if (mid->mid_flags & MID_DELETED) printk_once(KERN_WARNING "trying to dequeue a deleted mid\n"); - else + else { list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } spin_unlock(&GlobalMid_Lock); } @@ -966,8 +971,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { mid_entry = list_entry(tmp, struct mid_q_entry, qhead); cifs_dbg(FYI, "Clearing mid 0x%llx\n", mid_entry->mid); + kref_get(&mid_entry->refcount); mid_entry->mid_state = MID_SHUTDOWN; list_move(&mid_entry->qhead, &dispose_list); + mid_entry->mid_flags |= MID_DELETED; } spin_unlock(&GlobalMid_Lock); @@ -977,6 +984,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) cifs_dbg(FYI, "Callback mid 0x%llx\n", mid_entry->mid); list_del_init(&mid_entry->qhead); mid_entry->callback(mid_entry); + cifs_mid_q_entry_release(mid_entry); } /* 1/8th of sec is more than enough time for them to exit */ msleep(125); @@ -3882,8 +3890,12 @@ generic_ip_connect(struct TCP_Server_Info *server) rc = socket->ops->connect(socket, saddr, slen, server->noblockcnt ? O_NONBLOCK : 0); - - if (rc == -EINPROGRESS) + /* + * When mounting SMB root file systems, we do not want to block in + * connect. Otherwise bail out and then let cifs_reconnect() perform + * reconnect failover - if possible. + */ + if (server->noblockcnt && rc == -EINPROGRESS) rc = 0; if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 5ad15de2bb4f..fa7b0fa72bb3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -281,6 +281,13 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode) return has_locks; } +void +cifs_down_write(struct rw_semaphore *sem) +{ + while (!down_write_trylock(sem)) + msleep(10); +} + struct cifsFileInfo * cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock) @@ -306,7 +313,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, INIT_LIST_HEAD(&fdlocks->locks); fdlocks->cfile = cfile; cfile->llist = fdlocks; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_add(&fdlocks->llist, &cinode->llist); up_write(&cinode->lock_sem); @@ -405,10 +412,11 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) bool oplock_break_cancelled; spin_lock(&tcon->open_file_lock); - + spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); + spin_unlock(&cifsi->open_file_lock); spin_unlock(&tcon->open_file_lock); return; } @@ -421,9 +429,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) cifs_add_pending_open_locked(&fid, cifs_file->tlink, &open); /* remove it from the lists */ - spin_lock(&cifsi->open_file_lock); list_del(&cifs_file->flist); - spin_unlock(&cifsi->open_file_lock); list_del(&cifs_file->tlist); atomic_dec(&tcon->num_local_opens); @@ -440,6 +446,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) cifs_set_oplock_level(cifsi, 0); } + spin_unlock(&cifsi->open_file_lock); spin_unlock(&tcon->open_file_lock); oplock_break_cancelled = wait_oplock_handler ? @@ -464,7 +471,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) * Delete any outstanding lock records. We'll lose them when the file * is closed anyway. */ - down_write(&cifsi->lock_sem); + cifs_down_write(&cifsi->lock_sem); list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) { list_del(&li->llist); cifs_del_lock_waiters(li); @@ -1027,7 +1034,7 @@ static void cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock) { struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry)); - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_add_tail(&lock->llist, &cfile->llist->locks); up_write(&cinode->lock_sem); } @@ -1049,7 +1056,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock, try_again: exist = false; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length, lock->type, lock->flags, &conf_lock, @@ -1072,7 +1079,7 @@ try_again: (lock->blist.next == &lock->blist)); if (!rc) goto try_again; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_del_init(&lock->blist); } @@ -1125,7 +1132,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock) return rc; try_again: - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); if (!cinode->can_cache_brlcks) { up_write(&cinode->lock_sem); return rc; @@ -1331,7 +1338,7 @@ cifs_push_locks(struct cifsFileInfo *cfile) int rc = 0; /* we are going to update can_cache_brlcks here - need a write access */ - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); if (!cinode->can_cache_brlcks) { up_write(&cinode->lock_sem); return rc; @@ -1522,7 +1529,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, if (!buf) return -ENOMEM; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); for (i = 0; i < 2; i++) { cur = buf; num = 0; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 5dcc95b38310..df9377828e2f 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2475,9 +2475,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid); cifsFileInfo_put(wfile); if (rc) - return rc; + goto cifs_setattr_exit; } else if (rc != -EBADF) - return rc; + goto cifs_setattr_exit; else rc = 0; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index b7421a096319..514810694c0f 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -171,6 +171,9 @@ cifs_get_next_mid(struct TCP_Server_Info *server) /* we do not want to loop forever */ last_mid = cur_mid; cur_mid++; + /* avoid 0xFFFF MID */ + if (cur_mid == 0xffff) + cur_mid++; /* * This nested loop looks more expensive than it is. diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index e6a1fc72018f..8b0b512c5792 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -145,7 +145,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, cur = buf; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) { if (flock->fl_start > li->offset || (flock->fl_start + length) < diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 4c0922596467..cd55af9b7cc5 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4084,6 +4084,7 @@ free_pages: kfree(dw->ppages); cifs_small_buf_release(dw->buf); + kfree(dw); } @@ -4157,7 +4158,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, dw->server = server; dw->ppages = pages; dw->len = len; - queue_work(cifsiod_wq, &dw->decrypt); + queue_work(decrypt_wq, &dw->decrypt); *num_mids = 0; /* worker thread takes care of finding mid */ return -1; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index ea735d59c36e..0abfde6d0b05 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -838,6 +838,7 @@ struct create_durable_handle_reconnect_v2 { struct create_context ccontext; __u8 Name[8]; struct durable_reconnect_context_v2 dcontext; + __u8 Pad[4]; } __packed; /* See MS-SMB2 2.2.13.2.5 */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 308ad0f495e1..ca3de62688d6 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -86,22 +86,8 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) static void _cifs_mid_q_entry_release(struct kref *refcount) { - struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry, - refcount); - - mempool_free(mid, cifs_mid_poolp); -} - -void cifs_mid_q_entry_release(struct mid_q_entry *midEntry) -{ - spin_lock(&GlobalMid_Lock); - kref_put(&midEntry->refcount, _cifs_mid_q_entry_release); - spin_unlock(&GlobalMid_Lock); -} - -void -DeleteMidQEntry(struct mid_q_entry *midEntry) -{ + struct mid_q_entry *midEntry = + container_of(refcount, struct mid_q_entry, refcount); #ifdef CONFIG_CIFS_STATS2 __le16 command = midEntry->server->vals->lock_cmd; __u16 smb_cmd = le16_to_cpu(midEntry->command); @@ -166,6 +152,19 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) } } #endif + + mempool_free(midEntry, cifs_mid_poolp); +} + +void cifs_mid_q_entry_release(struct mid_q_entry *midEntry) +{ + spin_lock(&GlobalMid_Lock); + kref_put(&midEntry->refcount, _cifs_mid_q_entry_release); + spin_unlock(&GlobalMid_Lock); +} + +void DeleteMidQEntry(struct mid_q_entry *midEntry) +{ cifs_mid_q_entry_release(midEntry); } @@ -173,8 +172,10 @@ void cifs_delete_mid(struct mid_q_entry *mid) { spin_lock(&GlobalMid_Lock); - list_del_init(&mid->qhead); - mid->mid_flags |= MID_DELETED; + if (!(mid->mid_flags & MID_DELETED)) { + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } spin_unlock(&GlobalMid_Lock); DeleteMidQEntry(mid); @@ -872,7 +873,10 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) rc = -EHOSTDOWN; break; default: - list_del_init(&mid->qhead); + if (!(mid->mid_flags & MID_DELETED)) { + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n", __func__, mid->mid, mid->mid_state); rc = -EIO; diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index dc5dbf6a81d7..cb61467478ca 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -101,7 +101,7 @@ static int create_link(struct config_item *parent_item, } target_sd->s_links++; spin_unlock(&configfs_dirent_lock); - ret = configfs_get_target_path(item, item, body); + ret = configfs_get_target_path(parent_item, item, body); if (!ret) ret = configfs_create_link(target_sd, parent_item->ci_dentry, dentry, body); diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index d12ea28836a5..2f04024c3588 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -958,8 +958,8 @@ static int cramfs_get_tree(struct fs_context *fc) if (IS_ENABLED(CONFIG_CRAMFS_MTD)) { ret = get_tree_mtd(fc, cramfs_mtd_fill_super); - if (ret < 0) - return ret; + if (!ret) + return 0; } if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV)) ret = get_tree_bdev(fc, cramfs_blkdev_fill_super); @@ -220,10 +220,11 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order) for (;;) { entry = xas_find_conflict(xas); + if (!entry || WARN_ON_ONCE(!xa_is_value(entry))) + return entry; if (dax_entry_order(entry) < order) return XA_RETRY_ENTRY; - if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) || - !dax_is_locked(entry)) + if (!dax_is_locked(entry)) return entry; wq = dax_entry_waitqueue(xas, entry, &ewait.key); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 18426f4855f1..e23752d9a79f 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -128,13 +128,20 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, struct inode *inode) { struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); - struct inode *lower_dir_inode = ecryptfs_inode_to_lower(dir); struct dentry *lower_dir_dentry; + struct inode *lower_dir_inode; int rc; - dget(lower_dentry); - lower_dir_dentry = lock_parent(lower_dentry); - rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL); + lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent); + lower_dir_inode = d_inode(lower_dir_dentry); + inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT); + dget(lower_dentry); // don't even try to make the lower negative + if (lower_dentry->d_parent != lower_dir_dentry) + rc = -EINVAL; + else if (d_unhashed(lower_dentry)) + rc = -EINVAL; + else + rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL); if (rc) { printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc); goto out_unlock; @@ -142,10 +149,11 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry, fsstack_copy_attr_times(dir, lower_dir_inode); set_nlink(inode, ecryptfs_inode_to_lower(inode)->i_nlink); inode->i_ctime = dir->i_ctime; - d_drop(dentry); out_unlock: - unlock_dir(lower_dir_dentry); dput(lower_dentry); + inode_unlock(lower_dir_inode); + if (!rc) + d_drop(dentry); return rc; } @@ -311,9 +319,9 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode) static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, struct dentry *lower_dentry) { - struct inode *inode, *lower_inode = d_inode(lower_dentry); + struct path *path = ecryptfs_dentry_to_lower_path(dentry->d_parent); + struct inode *inode, *lower_inode; struct ecryptfs_dentry_info *dentry_info; - struct vfsmount *lower_mnt; int rc = 0; dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL); @@ -322,16 +330,23 @@ static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, return ERR_PTR(-ENOMEM); } - lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent)); fsstack_copy_attr_atime(d_inode(dentry->d_parent), - d_inode(lower_dentry->d_parent)); + d_inode(path->dentry)); BUG_ON(!d_count(lower_dentry)); ecryptfs_set_dentry_private(dentry, dentry_info); - dentry_info->lower_path.mnt = lower_mnt; + dentry_info->lower_path.mnt = mntget(path->mnt); dentry_info->lower_path.dentry = lower_dentry; - if (d_really_is_negative(lower_dentry)) { + /* + * negative dentry can go positive under us here - its parent is not + * locked. That's OK and that could happen just as we return from + * ecryptfs_lookup() anyway. Just need to be careful and fetch + * ->d_inode only once - it's not stable here. + */ + lower_inode = READ_ONCE(lower_dentry->d_inode); + + if (!lower_inode) { /* We want to add because we couldn't find in lower */ d_add(dentry, NULL); return NULL; @@ -512,22 +527,30 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) { struct dentry *lower_dentry; struct dentry *lower_dir_dentry; + struct inode *lower_dir_inode; int rc; lower_dentry = ecryptfs_dentry_to_lower(dentry); - dget(dentry); - lower_dir_dentry = lock_parent(lower_dentry); - dget(lower_dentry); - rc = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry); - dput(lower_dentry); - if (!rc && d_really_is_positive(dentry)) + lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent); + lower_dir_inode = d_inode(lower_dir_dentry); + + inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT); + dget(lower_dentry); // don't even try to make the lower negative + if (lower_dentry->d_parent != lower_dir_dentry) + rc = -EINVAL; + else if (d_unhashed(lower_dentry)) + rc = -EINVAL; + else + rc = vfs_rmdir(lower_dir_inode, lower_dentry); + if (!rc) { clear_nlink(d_inode(dentry)); - fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry)); - set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink); - unlock_dir(lower_dir_dentry); + fsstack_copy_attr_times(dir, lower_dir_inode); + set_nlink(dir, lower_dir_inode->i_nlink); + } + dput(lower_dentry); + inode_unlock(lower_dir_inode); if (!rc) d_drop(dentry); - dput(dentry); return rc; } @@ -565,20 +588,22 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct dentry *lower_new_dentry; struct dentry *lower_old_dir_dentry; struct dentry *lower_new_dir_dentry; - struct dentry *trap = NULL; + struct dentry *trap; struct inode *target_inode; if (flags) return -EINVAL; + lower_old_dir_dentry = ecryptfs_dentry_to_lower(old_dentry->d_parent); + lower_new_dir_dentry = ecryptfs_dentry_to_lower(new_dentry->d_parent); + lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry); lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry); - dget(lower_old_dentry); - dget(lower_new_dentry); - lower_old_dir_dentry = dget_parent(lower_old_dentry); - lower_new_dir_dentry = dget_parent(lower_new_dentry); + target_inode = d_inode(new_dentry); + trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + dget(lower_new_dentry); rc = -EINVAL; if (lower_old_dentry->d_parent != lower_old_dir_dentry) goto out_lock; @@ -606,11 +631,8 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dir != old_dir) fsstack_copy_attr_all(old_dir, d_inode(lower_old_dir_dentry)); out_lock: - unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); - dput(lower_new_dir_dentry); - dput(lower_old_dir_dentry); dput(lower_new_dentry); - dput(lower_old_dentry); + unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); return rc; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 09bc68708d28..2dd55b172d57 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -519,26 +519,33 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, * inode is actually connected to the parent. */ err = exportfs_get_name(mnt, target_dir, nbuf, result); - if (!err) { - inode_lock(target_dir->d_inode); - nresult = lookup_one_len(nbuf, target_dir, - strlen(nbuf)); - inode_unlock(target_dir->d_inode); - if (!IS_ERR(nresult)) { - if (nresult->d_inode) { - dput(result); - result = nresult; - } else - dput(nresult); - } + if (err) { + dput(target_dir); + goto err_result; } + inode_lock(target_dir->d_inode); + nresult = lookup_one_len(nbuf, target_dir, strlen(nbuf)); + if (!IS_ERR(nresult)) { + if (unlikely(nresult->d_inode != result->d_inode)) { + dput(nresult); + nresult = ERR_PTR(-ESTALE); + } + } + inode_unlock(target_dir->d_inode); /* * At this point we are done with the parent, but it's pinned * by the child dentry anyway. */ dput(target_dir); + if (IS_ERR(nresult)) { + err = PTR_ERR(nresult); + goto err_result; + } + dput(result); + result = nresult; + /* * And finally make sure the dentry is actually acceptable * to NFSD. diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 808709581481..2c997f94a3b2 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1771,7 +1771,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, return -EIO; } trace_f2fs_issue_reset_zone(bdev, blkstart); - return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS); + return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, + sector, nr_sects, GFP_NOFS); } /* For conventional zones, use regular discard if supported */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1443cee15863..95761740cf1f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2857,15 +2857,21 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) } #ifdef CONFIG_BLK_DEV_ZONED +static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct f2fs_dev_info *dev = data; + + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, dev->blkz_seq); + return 0; +} + static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) { struct block_device *bdev = FDEV(devi).bdev; sector_t nr_sectors = bdev->bd_part->nr_sects; - sector_t sector = 0; - struct blk_zone *zones; - unsigned int i, nr_zones; - unsigned int n = 0; - int err = -EIO; + int ret; if (!f2fs_sb_has_blkzoned(sbi)) return 0; @@ -2890,38 +2896,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (!FDEV(devi).blkz_seq) return -ENOMEM; -#define F2FS_REPORT_NR_ZONES 4096 - - zones = f2fs_kzalloc(sbi, - array_size(F2FS_REPORT_NR_ZONES, - sizeof(struct blk_zone)), - GFP_KERNEL); - if (!zones) - return -ENOMEM; - /* Get block zones type */ - while (zones && sector < nr_sectors) { - - nr_zones = F2FS_REPORT_NR_ZONES; - err = blkdev_report_zones(bdev, sector, zones, &nr_zones); - if (err) - break; - if (!nr_zones) { - err = -EIO; - break; - } - - for (i = 0; i < nr_zones; i++) { - if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(n, FDEV(devi).blkz_seq); - sector += zones[i].len; - n++; - } - } - - kvfree(zones); + ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb, + &FDEV(devi)); + if (ret < 0) + return ret; - return err; + return 0; } #endif diff --git a/fs/fcntl.c b/fs/fcntl.c index 3d40771e8e7c..41b6438bd2d9 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -261,7 +261,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) static bool rw_hint_valid(enum rw_hint hint) { switch (hint) { - case RWF_WRITE_LIFE_NOT_SET: + case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: diff --git a/fs/file.c b/fs/file.c index 3da91a112bab..b241ea7f1aa4 100644 --- a/fs/file.c +++ b/fs/file.c @@ -795,7 +795,7 @@ unsigned long __fdget_pos(unsigned int fd) unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file && !(file->f_mode & FMODE_STREAM)) { if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8461a6322039..335607b8c5c0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -576,10 +576,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, spin_unlock(&inode->i_lock); /* - * A dying wb indicates that the memcg-blkcg mapping has changed - * and a new wb is already serving the memcg. Switch immediately. + * A dying wb indicates that either the blkcg associated with the + * memcg changed or the associated memcg is dying. In the first + * case, a replacement wb should already be available and we should + * refresh the wb immediately. In the second case, trying to + * refresh will keep failing. */ - if (unlikely(wb_dying(wbc->wb))) + if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index 6419a2b3510d..3e8cebfb59b7 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_FUSE_FS) += fuse.o obj-$(CONFIG_CUSE) += cuse.o -obj-$(CONFIG_VIRTIO_FS) += virtio_fs.o +obj-$(CONFIG_VIRTIO_FS) += virtiofs.o fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o +virtiofs-y += virtio_fs.o diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index dadd617d826c..ed1abc9e33cf 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -276,10 +276,12 @@ static void flush_bg_queue(struct fuse_conn *fc) void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req) { struct fuse_iqueue *fiq = &fc->iq; - bool async = req->args->end; + bool async; if (test_and_set_bit(FR_FINISHED, &req->flags)) goto put_request; + + async = req->args->end; /* * test_and_set_bit() implies smp_mb() between bit * changing and below intr_entry check. Pairs with diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d572c900bb0f..54d638f9ba1c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -405,7 +405,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, else fuse_invalidate_entry_cache(entry); - fuse_advise_use_readdirplus(dir); + if (inode) + fuse_advise_use_readdirplus(dir); return newent; out_iput: @@ -1521,6 +1522,19 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, is_truncate = true; } + /* Flush dirty data/metadata before non-truncate SETATTR */ + if (is_wb && S_ISREG(inode->i_mode) && + attr->ia_valid & + (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME_SET | + ATTR_TIMES_SET)) { + err = write_inode_now(inode, true); + if (err) + return err; + + fuse_set_nowrite(inode); + fuse_release_nowrite(inode); + } + if (is_truncate) { fuse_set_nowrite(inode); set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 0f0225686aee..db48a5cf8620 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -217,7 +217,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) { struct fuse_conn *fc = get_fuse_conn(inode); int err; - bool lock_inode = (file->f_flags & O_TRUNC) && + bool is_wb_truncate = (file->f_flags & O_TRUNC) && fc->atomic_o_trunc && fc->writeback_cache; @@ -225,16 +225,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) if (err) return err; - if (lock_inode) + if (is_wb_truncate) { inode_lock(inode); + fuse_set_nowrite(inode); + } err = fuse_do_open(fc, get_node_id(inode), file, isdir); if (!err) fuse_finish_open(inode, file); - if (lock_inode) + if (is_wb_truncate) { + fuse_release_nowrite(inode); inode_unlock(inode); + } return err; } @@ -1997,7 +2001,7 @@ static int fuse_writepages_fill(struct page *page, if (!data->ff) { err = -EIO; - data->ff = fuse_write_file_get(fc, get_fuse_inode(inode)); + data->ff = fuse_write_file_get(fc, fi); if (!data->ff) goto out_unlock; } @@ -2042,8 +2046,6 @@ static int fuse_writepages_fill(struct page *page, * under writeback, so we can release the page lock. */ if (data->wpa == NULL) { - struct fuse_inode *fi = get_fuse_inode(inode); - err = -ENOMEM; wpa = fuse_writepage_args_alloc(); if (!wpa) { diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 956aeaf961ae..d148188cfca4 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -479,6 +479,7 @@ struct fuse_fs_context { bool destroy:1; bool no_control:1; bool no_force_umount:1; + bool no_mount_options:1; unsigned int max_read; unsigned int blksize; const char *subtype; @@ -713,6 +714,9 @@ struct fuse_conn { /** Do not allow MNT_FORCE umount */ unsigned int no_force_umount:1; + /* Do not show mount options */ + unsigned int no_mount_options:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e040e2a2b621..16aec32f7f3d 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -558,6 +558,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root) struct super_block *sb = root->d_sb; struct fuse_conn *fc = get_fuse_conn_super(sb); + if (fc->no_mount_options) + return 0; + seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id)); seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id)); if (fc->default_permissions) @@ -1180,6 +1183,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx) fc->destroy = ctx->destroy; fc->no_control = ctx->no_control; fc->no_force_umount = ctx->no_force_umount; + fc->no_mount_options = ctx->no_mount_options; err = -ENOMEM; root = fuse_get_root_inode(sb, ctx->rootmode); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 6af3f131e468..a5c86048b96e 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -30,6 +30,7 @@ struct virtio_fs_vq { struct virtqueue *vq; /* protected by ->lock */ struct work_struct done_work; struct list_head queued_reqs; + struct list_head end_reqs; /* End these requests */ struct delayed_work dispatch_work; struct fuse_dev *fud; bool connected; @@ -54,6 +55,9 @@ struct virtio_fs_forget { struct list_head list; }; +static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, + struct fuse_req *req, bool in_flight); + static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq) { struct virtio_fs *fs = vq->vdev->priv; @@ -66,6 +70,19 @@ static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq) return &vq_to_fsvq(vq)->fud->pq; } +/* Should be called with fsvq->lock held. */ +static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq) +{ + fsvq->in_flight++; +} + +/* Should be called with fsvq->lock held. */ +static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq) +{ + WARN_ON(fsvq->in_flight <= 0); + fsvq->in_flight--; +} + static void release_virtio_fs_obj(struct kref *ref) { struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount); @@ -109,22 +126,6 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq) flush_delayed_work(&fsvq->dispatch_work); } -static inline void drain_hiprio_queued_reqs(struct virtio_fs_vq *fsvq) -{ - struct virtio_fs_forget *forget; - - spin_lock(&fsvq->lock); - while (1) { - forget = list_first_entry_or_null(&fsvq->queued_reqs, - struct virtio_fs_forget, list); - if (!forget) - break; - list_del(&forget->list); - kfree(forget); - } - spin_unlock(&fsvq->lock); -} - static void virtio_fs_drain_all_queues(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; @@ -132,9 +133,6 @@ static void virtio_fs_drain_all_queues(struct virtio_fs *fs) for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; - if (i == VQ_HIPRIO) - drain_hiprio_queued_reqs(fsvq); - virtio_fs_drain_queue(fsvq); } } @@ -253,14 +251,66 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work) while ((req = virtqueue_get_buf(vq, &len)) != NULL) { kfree(req); - fsvq->in_flight--; + dec_in_flight_req(fsvq); } } while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq))); spin_unlock(&fsvq->lock); } -static void virtio_fs_dummy_dispatch_work(struct work_struct *work) +static void virtio_fs_request_dispatch_work(struct work_struct *work) { + struct fuse_req *req; + struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, + dispatch_work.work); + struct fuse_conn *fc = fsvq->fud->fc; + int ret; + + pr_debug("virtio-fs: worker %s called.\n", __func__); + while (1) { + spin_lock(&fsvq->lock); + req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req, + list); + if (!req) { + spin_unlock(&fsvq->lock); + break; + } + + list_del_init(&req->list); + spin_unlock(&fsvq->lock); + fuse_request_end(fc, req); + } + + /* Dispatch pending requests */ + while (1) { + spin_lock(&fsvq->lock); + req = list_first_entry_or_null(&fsvq->queued_reqs, + struct fuse_req, list); + if (!req) { + spin_unlock(&fsvq->lock); + return; + } + list_del_init(&req->list); + spin_unlock(&fsvq->lock); + + ret = virtio_fs_enqueue_req(fsvq, req, true); + if (ret < 0) { + if (ret == -ENOMEM || ret == -ENOSPC) { + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->queued_reqs); + schedule_delayed_work(&fsvq->dispatch_work, + msecs_to_jiffies(1)); + spin_unlock(&fsvq->lock); + return; + } + req->out.h.error = ret; + spin_lock(&fsvq->lock); + dec_in_flight_req(fsvq); + spin_unlock(&fsvq->lock); + pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", + ret); + fuse_request_end(fc, req); + } + } } static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) @@ -286,6 +336,7 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) list_del(&forget->list); if (!fsvq->connected) { + dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); kfree(forget); continue; @@ -307,13 +358,13 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) } else { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n", ret); + dec_in_flight_req(fsvq); kfree(forget); } spin_unlock(&fsvq->lock); return; } - fsvq->in_flight++; notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); @@ -452,7 +503,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work) fuse_request_end(fc, req); spin_lock(&fsvq->lock); - fsvq->in_flight--; + dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); } } @@ -502,6 +553,7 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev, names[VQ_HIPRIO] = fs->vqs[VQ_HIPRIO].name; INIT_WORK(&fs->vqs[VQ_HIPRIO].done_work, virtio_fs_hiprio_done_work); INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].queued_reqs); + INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].end_reqs); INIT_DELAYED_WORK(&fs->vqs[VQ_HIPRIO].dispatch_work, virtio_fs_hiprio_dispatch_work); spin_lock_init(&fs->vqs[VQ_HIPRIO].lock); @@ -511,8 +563,9 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev, spin_lock_init(&fs->vqs[i].lock); INIT_WORK(&fs->vqs[i].done_work, virtio_fs_requests_done_work); INIT_DELAYED_WORK(&fs->vqs[i].dispatch_work, - virtio_fs_dummy_dispatch_work); + virtio_fs_request_dispatch_work); INIT_LIST_HEAD(&fs->vqs[i].queued_reqs); + INIT_LIST_HEAD(&fs->vqs[i].end_reqs); snprintf(fs->vqs[i].name, sizeof(fs->vqs[i].name), "requests.%u", i - VQ_REQUEST); callbacks[i] = virtio_fs_vq_done; @@ -708,6 +761,7 @@ __releases(fiq->lock) list_add_tail(&forget->list, &fsvq->queued_reqs); schedule_delayed_work(&fsvq->dispatch_work, msecs_to_jiffies(1)); + inc_in_flight_req(fsvq); } else { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n", ret); @@ -717,7 +771,7 @@ __releases(fiq->lock) goto out; } - fsvq->in_flight++; + inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); @@ -819,7 +873,7 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg, /* Add a request to a virtqueue and kick the device */ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, - struct fuse_req *req) + struct fuse_req *req, bool in_flight) { /* requests need at least 4 elements */ struct scatterlist *stack_sgs[6]; @@ -835,6 +889,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, unsigned int i; int ret; bool notify; + struct fuse_pqueue *fpq; /* Does the sglist fit on the stack? */ total_sgs = sg_count_fuse_req(req); @@ -889,7 +944,17 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, goto out; } - fsvq->in_flight++; + /* Request successfully sent. */ + fpq = &fsvq->fud->pq; + spin_lock(&fpq->lock); + list_add_tail(&req->list, fpq->processing); + spin_unlock(&fpq->lock); + set_bit(FR_SENT, &req->flags); + /* matches barrier in request_wait_answer() */ + smp_mb__after_atomic(); + + if (!in_flight) + inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); @@ -915,9 +980,8 @@ __releases(fiq->lock) { unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */ struct virtio_fs *fs; - struct fuse_conn *fc; struct fuse_req *req; - struct fuse_pqueue *fpq; + struct virtio_fs_vq *fsvq; int ret; WARN_ON(list_empty(&fiq->pending)); @@ -928,44 +992,36 @@ __releases(fiq->lock) spin_unlock(&fiq->lock); fs = fiq->priv; - fc = fs->vqs[queue_id].fud->fc; pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n", __func__, req->in.h.opcode, req->in.h.unique, req->in.h.nodeid, req->in.h.len, fuse_len_args(req->args->out_numargs, req->args->out_args)); - fpq = &fs->vqs[queue_id].fud->pq; - spin_lock(&fpq->lock); - if (!fpq->connected) { - spin_unlock(&fpq->lock); - req->out.h.error = -ENODEV; - pr_err("virtio-fs: %s disconnected\n", __func__); - fuse_request_end(fc, req); - return; - } - list_add_tail(&req->list, fpq->processing); - spin_unlock(&fpq->lock); - set_bit(FR_SENT, &req->flags); - /* matches barrier in request_wait_answer() */ - smp_mb__after_atomic(); - -retry: - ret = virtio_fs_enqueue_req(&fs->vqs[queue_id], req); + fsvq = &fs->vqs[queue_id]; + ret = virtio_fs_enqueue_req(fsvq, req, false); if (ret < 0) { if (ret == -ENOMEM || ret == -ENOSPC) { - /* Virtqueue full. Retry submission */ - /* TODO use completion instead of timeout */ - usleep_range(20, 30); - goto retry; + /* + * Virtqueue full. Retry submission from worker + * context as we might be holding fc->bg_lock. + */ + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->queued_reqs); + inc_in_flight_req(fsvq); + schedule_delayed_work(&fsvq->dispatch_work, + msecs_to_jiffies(1)); + spin_unlock(&fsvq->lock); + return; } req->out.h.error = ret; pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret); - spin_lock(&fpq->lock); - clear_bit(FR_SENT, &req->flags); - list_del_init(&req->list); - spin_unlock(&fpq->lock); - fuse_request_end(fc, req); + + /* Can't end request in submission context. Use a worker */ + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->end_reqs); + schedule_delayed_work(&fsvq->dispatch_work, 0); + spin_unlock(&fsvq->lock); return; } } @@ -992,6 +1048,7 @@ static int virtio_fs_fill_super(struct super_block *sb) .destroy = true, .no_control = true, .no_force_umount = true, + .no_mount_options = true, }; mutex_lock(&virtio_fs_mutex); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 681b44682b0d..18daf494abab 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1540,17 +1540,23 @@ static int gfs2_init_fs_context(struct fs_context *fc) { struct gfs2_args *args; - args = kzalloc(sizeof(*args), GFP_KERNEL); + args = kmalloc(sizeof(*args), GFP_KERNEL); if (args == NULL) return -ENOMEM; - args->ar_quota = GFS2_QUOTA_DEFAULT; - args->ar_data = GFS2_DATA_DEFAULT; - args->ar_commit = 30; - args->ar_statfs_quantum = 30; - args->ar_quota_quantum = 60; - args->ar_errors = GFS2_ERRORS_DEFAULT; + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { + struct gfs2_sbd *sdp = fc->root->d_sb->s_fs_info; + *args = sdp->sd_args; + } else { + memset(args, 0, sizeof(*args)); + args->ar_quota = GFS2_QUOTA_DEFAULT; + args->ar_data = GFS2_DATA_DEFAULT; + args->ar_commit = 30; + args->ar_statfs_quantum = 30; + args->ar_quota_quantum = 60; + args->ar_errors = GFS2_ERRORS_DEFAULT; + } fc->fs_private = args; fc->ops = &gfs2_context_ops; return 0; @@ -1600,6 +1606,7 @@ static int gfs2_meta_get_tree(struct fs_context *fc) } static const struct fs_context_operations gfs2_meta_context_ops = { + .free = gfs2_fc_free, .get_tree = gfs2_meta_get_tree, }; diff --git a/fs/io-wq.c b/fs/io-wq.c new file mode 100644 index 000000000000..9174007ce107 --- /dev/null +++ b/fs/io-wq.c @@ -0,0 +1,1065 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic worker thread pool for io_uring + * + * Copyright (C) 2019 Jens Axboe + * + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/sched/signal.h> +#include <linux/mm.h> +#include <linux/mmu_context.h> +#include <linux/sched/mm.h> +#include <linux/percpu.h> +#include <linux/slab.h> +#include <linux/kthread.h> +#include <linux/rculist_nulls.h> + +#include "io-wq.h" + +#define WORKER_IDLE_TIMEOUT (5 * HZ) + +enum { + IO_WORKER_F_UP = 1, /* up and active */ + IO_WORKER_F_RUNNING = 2, /* account as running */ + IO_WORKER_F_FREE = 4, /* worker on free list */ + IO_WORKER_F_EXITING = 8, /* worker exiting */ + IO_WORKER_F_FIXED = 16, /* static idle worker */ + IO_WORKER_F_BOUND = 32, /* is doing bounded work */ +}; + +enum { + IO_WQ_BIT_EXIT = 0, /* wq exiting */ + IO_WQ_BIT_CANCEL = 1, /* cancel work on list */ +}; + +enum { + IO_WQE_FLAG_STALLED = 1, /* stalled on hash */ +}; + +/* + * One for each thread in a wqe pool + */ +struct io_worker { + refcount_t ref; + unsigned flags; + struct hlist_nulls_node nulls_node; + struct list_head all_list; + struct task_struct *task; + wait_queue_head_t wait; + struct io_wqe *wqe; + + struct io_wq_work *cur_work; + spinlock_t lock; + + struct rcu_head rcu; + struct mm_struct *mm; + struct files_struct *restore_files; +}; + +#if BITS_PER_LONG == 64 +#define IO_WQ_HASH_ORDER 6 +#else +#define IO_WQ_HASH_ORDER 5 +#endif + +struct io_wqe_acct { + unsigned nr_workers; + unsigned max_workers; + atomic_t nr_running; +}; + +enum { + IO_WQ_ACCT_BOUND, + IO_WQ_ACCT_UNBOUND, +}; + +/* + * Per-node worker thread pool + */ +struct io_wqe { + struct { + spinlock_t lock; + struct list_head work_list; + unsigned long hash_map; + unsigned flags; + } ____cacheline_aligned_in_smp; + + int node; + struct io_wqe_acct acct[2]; + + struct hlist_nulls_head free_list; + struct hlist_nulls_head busy_list; + struct list_head all_list; + + struct io_wq *wq; +}; + +/* + * Per io_wq state + */ +struct io_wq { + struct io_wqe **wqes; + unsigned long state; + unsigned nr_wqes; + + get_work_fn *get_work; + put_work_fn *put_work; + + struct task_struct *manager; + struct user_struct *user; + struct mm_struct *mm; + refcount_t refs; + struct completion done; +}; + +static bool io_worker_get(struct io_worker *worker) +{ + return refcount_inc_not_zero(&worker->ref); +} + +static void io_worker_release(struct io_worker *worker) +{ + if (refcount_dec_and_test(&worker->ref)) + wake_up_process(worker->task); +} + +/* + * Note: drops the wqe->lock if returning true! The caller must re-acquire + * the lock in that case. Some callers need to restart handling if this + * happens, so we can't just re-acquire the lock on behalf of the caller. + */ +static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) +{ + bool dropped_lock = false; + + if (current->files != worker->restore_files) { + __acquire(&wqe->lock); + spin_unlock_irq(&wqe->lock); + dropped_lock = true; + + task_lock(current); + current->files = worker->restore_files; + task_unlock(current); + } + + /* + * If we have an active mm, we need to drop the wq lock before unusing + * it. If we do, return true and let the caller retry the idle loop. + */ + if (worker->mm) { + if (!dropped_lock) { + __acquire(&wqe->lock); + spin_unlock_irq(&wqe->lock); + dropped_lock = true; + } + __set_current_state(TASK_RUNNING); + set_fs(KERNEL_DS); + unuse_mm(worker->mm); + mmput(worker->mm); + worker->mm = NULL; + } + + return dropped_lock; +} + +static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, + struct io_wq_work *work) +{ + if (work->flags & IO_WQ_WORK_UNBOUND) + return &wqe->acct[IO_WQ_ACCT_UNBOUND]; + + return &wqe->acct[IO_WQ_ACCT_BOUND]; +} + +static inline struct io_wqe_acct *io_wqe_get_acct(struct io_wqe *wqe, + struct io_worker *worker) +{ + if (worker->flags & IO_WORKER_F_BOUND) + return &wqe->acct[IO_WQ_ACCT_BOUND]; + + return &wqe->acct[IO_WQ_ACCT_UNBOUND]; +} + +static void io_worker_exit(struct io_worker *worker) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); + unsigned nr_workers; + + /* + * If we're not at zero, someone else is holding a brief reference + * to the worker. Wait for that to go away. + */ + set_current_state(TASK_INTERRUPTIBLE); + if (!refcount_dec_and_test(&worker->ref)) + schedule(); + __set_current_state(TASK_RUNNING); + + preempt_disable(); + current->flags &= ~PF_IO_WORKER; + if (worker->flags & IO_WORKER_F_RUNNING) + atomic_dec(&acct->nr_running); + if (!(worker->flags & IO_WORKER_F_BOUND)) + atomic_dec(&wqe->wq->user->processes); + worker->flags = 0; + preempt_enable(); + + spin_lock_irq(&wqe->lock); + hlist_nulls_del_rcu(&worker->nulls_node); + list_del_rcu(&worker->all_list); + if (__io_worker_unuse(wqe, worker)) { + __release(&wqe->lock); + spin_lock_irq(&wqe->lock); + } + acct->nr_workers--; + nr_workers = wqe->acct[IO_WQ_ACCT_BOUND].nr_workers + + wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers; + spin_unlock_irq(&wqe->lock); + + /* all workers gone, wq exit can proceed */ + if (!nr_workers && refcount_dec_and_test(&wqe->wq->refs)) + complete(&wqe->wq->done); + + kfree_rcu(worker, rcu); +} + +static inline bool io_wqe_run_queue(struct io_wqe *wqe) + __must_hold(wqe->lock) +{ + if (!list_empty(&wqe->work_list) && !(wqe->flags & IO_WQE_FLAG_STALLED)) + return true; + return false; +} + +/* + * Check head of free list for an available worker. If one isn't available, + * caller must wake up the wq manager to create one. + */ +static bool io_wqe_activate_free_worker(struct io_wqe *wqe) + __must_hold(RCU) +{ + struct hlist_nulls_node *n; + struct io_worker *worker; + + n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list)); + if (is_a_nulls(n)) + return false; + + worker = hlist_nulls_entry(n, struct io_worker, nulls_node); + if (io_worker_get(worker)) { + wake_up(&worker->wait); + io_worker_release(worker); + return true; + } + + return false; +} + +/* + * We need a worker. If we find a free one, we're good. If not, and we're + * below the max number of workers, wake up the manager to create one. + */ +static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) +{ + bool ret; + + /* + * Most likely an attempt to queue unbounded work on an io_wq that + * wasn't setup with any unbounded workers. + */ + WARN_ON_ONCE(!acct->max_workers); + + rcu_read_lock(); + ret = io_wqe_activate_free_worker(wqe); + rcu_read_unlock(); + + if (!ret && acct->nr_workers < acct->max_workers) + wake_up_process(wqe->wq->manager); +} + +static void io_wqe_inc_running(struct io_wqe *wqe, struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); + + atomic_inc(&acct->nr_running); +} + +static void io_wqe_dec_running(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); + + if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe)) + io_wqe_wake_worker(wqe, acct); +} + +static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) +{ + allow_kernel_signal(SIGINT); + + current->flags |= PF_IO_WORKER; + + worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + worker->restore_files = current->files; + io_wqe_inc_running(wqe, worker); +} + +/* + * Worker will start processing some work. Move it to the busy list, if + * it's currently on the freelist + */ +static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, + struct io_wq_work *work) + __must_hold(wqe->lock) +{ + bool worker_bound, work_bound; + + if (worker->flags & IO_WORKER_F_FREE) { + worker->flags &= ~IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->busy_list); + } + + /* + * If worker is moving from bound to unbound (or vice versa), then + * ensure we update the running accounting. + */ + worker_bound = (worker->flags & IO_WORKER_F_BOUND) != 0; + work_bound = (work->flags & IO_WQ_WORK_UNBOUND) == 0; + if (worker_bound != work_bound) { + io_wqe_dec_running(wqe, worker); + if (work_bound) { + worker->flags |= IO_WORKER_F_BOUND; + wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers--; + wqe->acct[IO_WQ_ACCT_BOUND].nr_workers++; + atomic_dec(&wqe->wq->user->processes); + } else { + worker->flags &= ~IO_WORKER_F_BOUND; + wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers++; + wqe->acct[IO_WQ_ACCT_BOUND].nr_workers--; + atomic_inc(&wqe->wq->user->processes); + } + io_wqe_inc_running(wqe, worker); + } +} + +/* + * No work, worker going to sleep. Move to freelist, and unuse mm if we + * have one attached. Dropping the mm may potentially sleep, so we drop + * the lock in that case and return success. Since the caller has to + * retry the loop in that case (we changed task state), we don't regrab + * the lock if we return success. + */ +static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + if (!(worker->flags & IO_WORKER_F_FREE)) { + worker->flags |= IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + } + + return __io_worker_unuse(wqe, worker); +} + +static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash) + __must_hold(wqe->lock) +{ + struct io_wq_work *work; + + list_for_each_entry(work, &wqe->work_list, list) { + /* not hashed, can run anytime */ + if (!(work->flags & IO_WQ_WORK_HASHED)) { + list_del(&work->list); + return work; + } + + /* hashed, can run if not already running */ + *hash = work->flags >> IO_WQ_HASH_SHIFT; + if (!(wqe->hash_map & BIT_ULL(*hash))) { + wqe->hash_map |= BIT_ULL(*hash); + list_del(&work->list); + return work; + } + } + + return NULL; +} + +static void io_worker_handle_work(struct io_worker *worker) + __releases(wqe->lock) +{ + struct io_wq_work *work, *old_work = NULL, *put_work = NULL; + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + do { + unsigned hash = -1U; + + /* + * If we got some work, mark us as busy. If we didn't, but + * the list isn't empty, it means we stalled on hashed work. + * Mark us stalled so we don't keep looking for work when we + * can't make progress, any work completion or insertion will + * clear the stalled flag. + */ + work = io_get_next_work(wqe, &hash); + if (work) + __io_worker_busy(wqe, worker, work); + else if (!list_empty(&wqe->work_list)) + wqe->flags |= IO_WQE_FLAG_STALLED; + + spin_unlock_irq(&wqe->lock); + if (put_work && wq->put_work) + wq->put_work(old_work); + if (!work) + break; +next: + /* flush any pending signals before assigning new work */ + if (signal_pending(current)) + flush_signals(current); + + spin_lock_irq(&worker->lock); + worker->cur_work = work; + spin_unlock_irq(&worker->lock); + + if ((work->flags & IO_WQ_WORK_NEEDS_FILES) && + current->files != work->files) { + task_lock(current); + current->files = work->files; + task_unlock(current); + } + if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm && + wq->mm && mmget_not_zero(wq->mm)) { + use_mm(wq->mm); + set_fs(USER_DS); + worker->mm = wq->mm; + } + if (test_bit(IO_WQ_BIT_CANCEL, &wq->state)) + work->flags |= IO_WQ_WORK_CANCEL; + if (worker->mm) + work->flags |= IO_WQ_WORK_HAS_MM; + + if (wq->get_work && !(work->flags & IO_WQ_WORK_INTERNAL)) { + put_work = work; + wq->get_work(work); + } + + old_work = work; + work->func(&work); + + spin_lock_irq(&worker->lock); + worker->cur_work = NULL; + spin_unlock_irq(&worker->lock); + + spin_lock_irq(&wqe->lock); + + if (hash != -1U) { + wqe->hash_map &= ~BIT_ULL(hash); + wqe->flags &= ~IO_WQE_FLAG_STALLED; + } + if (work && work != old_work) { + spin_unlock_irq(&wqe->lock); + + if (put_work && wq->put_work) { + wq->put_work(put_work); + put_work = NULL; + } + + /* dependent work not hashed */ + hash = -1U; + goto next; + } + } while (1); +} + +static int io_wqe_worker(void *data) +{ + struct io_worker *worker = data; + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + DEFINE_WAIT(wait); + + io_worker_start(wqe, worker); + + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + prepare_to_wait(&worker->wait, &wait, TASK_INTERRUPTIBLE); + + spin_lock_irq(&wqe->lock); + if (io_wqe_run_queue(wqe)) { + __set_current_state(TASK_RUNNING); + io_worker_handle_work(worker); + continue; + } + /* drops the lock on success, retry */ + if (__io_worker_idle(wqe, worker)) { + __release(&wqe->lock); + continue; + } + spin_unlock_irq(&wqe->lock); + if (signal_pending(current)) + flush_signals(current); + if (schedule_timeout(WORKER_IDLE_TIMEOUT)) + continue; + /* timed out, exit unless we're the fixed worker */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || + !(worker->flags & IO_WORKER_F_FIXED)) + break; + } + + finish_wait(&worker->wait, &wait); + + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + spin_lock_irq(&wqe->lock); + if (!list_empty(&wqe->work_list)) + io_worker_handle_work(worker); + else + spin_unlock_irq(&wqe->lock); + } + + io_worker_exit(worker); + return 0; +} + +/* + * Called when a worker is scheduled in. Mark us as currently running. + */ +void io_wq_worker_running(struct task_struct *tsk) +{ + struct io_worker *worker = kthread_data(tsk); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (worker->flags & IO_WORKER_F_RUNNING) + return; + worker->flags |= IO_WORKER_F_RUNNING; + io_wqe_inc_running(wqe, worker); +} + +/* + * Called when worker is going to sleep. If there are no workers currently + * running and we have work pending, wake up a free one or have the manager + * set one up. + */ +void io_wq_worker_sleeping(struct task_struct *tsk) +{ + struct io_worker *worker = kthread_data(tsk); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (!(worker->flags & IO_WORKER_F_RUNNING)) + return; + + worker->flags &= ~IO_WORKER_F_RUNNING; + + spin_lock_irq(&wqe->lock); + io_wqe_dec_running(wqe, worker); + spin_unlock_irq(&wqe->lock); +} + +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +{ + struct io_wqe_acct *acct =&wqe->acct[index]; + struct io_worker *worker; + + worker = kcalloc_node(1, sizeof(*worker), GFP_KERNEL, wqe->node); + if (!worker) + return; + + refcount_set(&worker->ref, 1); + worker->nulls_node.pprev = NULL; + init_waitqueue_head(&worker->wait); + worker->wqe = wqe; + spin_lock_init(&worker->lock); + + worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node, + "io_wqe_worker-%d/%d", index, wqe->node); + if (IS_ERR(worker->task)) { + kfree(worker); + return; + } + + spin_lock_irq(&wqe->lock); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + list_add_tail_rcu(&worker->all_list, &wqe->all_list); + worker->flags |= IO_WORKER_F_FREE; + if (index == IO_WQ_ACCT_BOUND) + worker->flags |= IO_WORKER_F_BOUND; + if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND)) + worker->flags |= IO_WORKER_F_FIXED; + acct->nr_workers++; + spin_unlock_irq(&wqe->lock); + + if (index == IO_WQ_ACCT_UNBOUND) + atomic_inc(&wq->user->processes); + + wake_up_process(worker->task); +} + +static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index) + __must_hold(wqe->lock) +{ + struct io_wqe_acct *acct = &wqe->acct[index]; + + /* always ensure we have one bounded worker */ + if (index == IO_WQ_ACCT_BOUND && !acct->nr_workers) + return true; + /* if we have available workers or no work, no need */ + if (!hlist_nulls_empty(&wqe->free_list) || !io_wqe_run_queue(wqe)) + return false; + return acct->nr_workers < acct->max_workers; +} + +/* + * Manager thread. Tasked with creating new workers, if we need them. + */ +static int io_wq_manager(void *data) +{ + struct io_wq *wq = data; + + while (!kthread_should_stop()) { + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + bool fork_worker[2] = { false, false }; + + spin_lock_irq(&wqe->lock); + if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND)) + fork_worker[IO_WQ_ACCT_BOUND] = true; + if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND)) + fork_worker[IO_WQ_ACCT_UNBOUND] = true; + spin_unlock_irq(&wqe->lock); + if (fork_worker[IO_WQ_ACCT_BOUND]) + create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND); + if (fork_worker[IO_WQ_ACCT_UNBOUND]) + create_io_worker(wq, wqe, IO_WQ_ACCT_UNBOUND); + } + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ); + } + + return 0; +} + +static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct, + struct io_wq_work *work) +{ + bool free_worker; + + if (!(work->flags & IO_WQ_WORK_UNBOUND)) + return true; + if (atomic_read(&acct->nr_running)) + return true; + + rcu_read_lock(); + free_worker = !hlist_nulls_empty(&wqe->free_list); + rcu_read_unlock(); + if (free_worker) + return true; + + if (atomic_read(&wqe->wq->user->processes) >= acct->max_workers && + !(capable(CAP_SYS_RESOURCE) || capable(CAP_SYS_ADMIN))) + return false; + + return true; +} + +static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned long flags; + + /* + * Do early check to see if we need a new unbound worker, and if we do, + * if we're allowed to do so. This isn't 100% accurate as there's a + * gap between this check and incrementing the value, but that's OK. + * It's close enough to not be an issue, fork() has the same delay. + */ + if (unlikely(!io_wq_can_queue(wqe, acct, work))) { + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + return; + } + + spin_lock_irqsave(&wqe->lock, flags); + list_add_tail(&work->list, &wqe->work_list); + wqe->flags &= ~IO_WQE_FLAG_STALLED; + spin_unlock_irqrestore(&wqe->lock, flags); + + if (!atomic_read(&acct->nr_running)) + io_wqe_wake_worker(wqe, acct); +} + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + + io_wqe_enqueue(wqe, work); +} + +/* + * Enqueue work, hashed by some key. Work items that hash to the same value + * will not be done in parallel. Used to limit concurrent writes, generally + * hashed by inode. + */ +void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + unsigned bit; + + + bit = hash_ptr(val, IO_WQ_HASH_ORDER); + work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); + io_wqe_enqueue(wqe, work); +} + +static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) +{ + send_sig(SIGINT, worker->task, 1); + return false; +} + +/* + * Iterate the passed in list and call the specific function for each + * worker that isn't exiting + */ +static bool io_wq_for_each_worker(struct io_wqe *wqe, + bool (*func)(struct io_worker *, void *), + void *data) +{ + struct io_worker *worker; + bool ret = false; + + list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { + if (io_worker_get(worker)) { + ret = func(worker, data); + io_worker_release(worker); + if (ret) + break; + } + } + + return ret; +} + +void io_wq_cancel_all(struct io_wq *wq) +{ + int i; + + set_bit(IO_WQ_BIT_CANCEL, &wq->state); + + /* + * Browse both lists, as there's a gap between handing work off + * to a worker and the worker putting itself on the busy_list + */ + rcu_read_lock(); + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL); + } + rcu_read_unlock(); +} + +struct io_cb_cancel_data { + struct io_wqe *wqe; + work_cancel_fn *cancel; + void *caller_data; +}; + +static bool io_work_cancel(struct io_worker *worker, void *cancel_data) +{ + struct io_cb_cancel_data *data = cancel_data; + unsigned long flags; + bool ret = false; + + /* + * Hold the lock to avoid ->cur_work going out of scope, caller + * may dereference the passed in work. + */ + spin_lock_irqsave(&worker->lock, flags); + if (worker->cur_work && + data->cancel(worker->cur_work, data->caller_data)) { + send_sig(SIGINT, worker->task, 1); + ret = true; + } + spin_unlock_irqrestore(&worker->lock, flags); + + return ret; +} + +static enum io_wq_cancel io_wqe_cancel_cb_work(struct io_wqe *wqe, + work_cancel_fn *cancel, + void *cancel_data) +{ + struct io_cb_cancel_data data = { + .wqe = wqe, + .cancel = cancel, + .caller_data = cancel_data, + }; + struct io_wq_work *work; + unsigned long flags; + bool found = false; + + spin_lock_irqsave(&wqe->lock, flags); + list_for_each_entry(work, &wqe->work_list, list) { + if (cancel(work, cancel_data)) { + list_del(&work->list); + found = true; + break; + } + } + spin_unlock_irqrestore(&wqe->lock, flags); + + if (found) { + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + return IO_WQ_CANCEL_OK; + } + + rcu_read_lock(); + found = io_wq_for_each_worker(wqe, io_work_cancel, &data); + rcu_read_unlock(); + return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND; +} + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data) +{ + enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + ret = io_wqe_cancel_cb_work(wqe, cancel, data); + if (ret != IO_WQ_CANCEL_NOTFOUND) + break; + } + + return ret; +} + +static bool io_wq_worker_cancel(struct io_worker *worker, void *data) +{ + struct io_wq_work *work = data; + unsigned long flags; + bool ret = false; + + if (worker->cur_work != work) + return false; + + spin_lock_irqsave(&worker->lock, flags); + if (worker->cur_work == work) { + send_sig(SIGINT, worker->task, 1); + ret = true; + } + spin_unlock_irqrestore(&worker->lock, flags); + + return ret; +} + +static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, + struct io_wq_work *cwork) +{ + struct io_wq_work *work; + unsigned long flags; + bool found = false; + + cwork->flags |= IO_WQ_WORK_CANCEL; + + /* + * First check pending list, if we're lucky we can just remove it + * from there. CANCEL_OK means that the work is returned as-new, + * no completion will be posted for it. + */ + spin_lock_irqsave(&wqe->lock, flags); + list_for_each_entry(work, &wqe->work_list, list) { + if (work == cwork) { + list_del(&work->list); + found = true; + break; + } + } + spin_unlock_irqrestore(&wqe->lock, flags); + + if (found) { + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + return IO_WQ_CANCEL_OK; + } + + /* + * Now check if a free (going busy) or busy worker has the work + * currently running. If we find it there, we'll return CANCEL_RUNNING + * as an indication that we attempte to signal cancellation. The + * completion will run normally in this case. + */ + rcu_read_lock(); + found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, cwork); + rcu_read_unlock(); + return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND; +} + +enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork) +{ + enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + ret = io_wqe_cancel_work(wqe, cwork); + if (ret != IO_WQ_CANCEL_NOTFOUND) + break; + } + + return ret; +} + +struct io_wq_flush_data { + struct io_wq_work work; + struct completion done; +}; + +static void io_wq_flush_func(struct io_wq_work **workptr) +{ + struct io_wq_work *work = *workptr; + struct io_wq_flush_data *data; + + data = container_of(work, struct io_wq_flush_data, work); + complete(&data->done); +} + +/* + * Doesn't wait for previously queued work to finish. When this completes, + * it just means that previously queued work was started. + */ +void io_wq_flush(struct io_wq *wq) +{ + struct io_wq_flush_data data; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + init_completion(&data.done); + INIT_IO_WORK(&data.work, io_wq_flush_func); + data.work.flags |= IO_WQ_WORK_INTERNAL; + io_wqe_enqueue(wqe, &data.work); + wait_for_completion(&data.done); + } +} + +struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm, + struct user_struct *user, get_work_fn *get_work, + put_work_fn *put_work) +{ + int ret = -ENOMEM, i, node; + struct io_wq *wq; + + wq = kcalloc(1, sizeof(*wq), GFP_KERNEL); + if (!wq) + return ERR_PTR(-ENOMEM); + + wq->nr_wqes = num_online_nodes(); + wq->wqes = kcalloc(wq->nr_wqes, sizeof(struct io_wqe *), GFP_KERNEL); + if (!wq->wqes) { + kfree(wq); + return ERR_PTR(-ENOMEM); + } + + wq->get_work = get_work; + wq->put_work = put_work; + + /* caller must already hold a reference to this */ + wq->user = user; + + i = 0; + refcount_set(&wq->refs, wq->nr_wqes); + for_each_online_node(node) { + struct io_wqe *wqe; + + wqe = kcalloc_node(1, sizeof(struct io_wqe), GFP_KERNEL, node); + if (!wqe) + break; + wq->wqes[i] = wqe; + wqe->node = node; + wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; + atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0); + if (user) { + wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers = + task_rlimit(current, RLIMIT_NPROC); + } + atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0); + wqe->node = node; + wqe->wq = wq; + spin_lock_init(&wqe->lock); + INIT_LIST_HEAD(&wqe->work_list); + INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); + INIT_HLIST_NULLS_HEAD(&wqe->busy_list, 1); + INIT_LIST_HEAD(&wqe->all_list); + + i++; + } + + init_completion(&wq->done); + + if (i != wq->nr_wqes) + goto err; + + /* caller must have already done mmgrab() on this mm */ + wq->mm = mm; + + wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager"); + if (!IS_ERR(wq->manager)) { + wake_up_process(wq->manager); + return wq; + } + + ret = PTR_ERR(wq->manager); + wq->manager = NULL; +err: + complete(&wq->done); + io_wq_destroy(wq); + return ERR_PTR(ret); +} + +static bool io_wq_worker_wake(struct io_worker *worker, void *data) +{ + wake_up_process(worker->task); + return false; +} + +void io_wq_destroy(struct io_wq *wq) +{ + int i; + + if (wq->manager) { + set_bit(IO_WQ_BIT_EXIT, &wq->state); + kthread_stop(wq->manager); + } + + rcu_read_lock(); + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + if (!wqe) + continue; + io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL); + } + rcu_read_unlock(); + + wait_for_completion(&wq->done); + + for (i = 0; i < wq->nr_wqes; i++) + kfree(wq->wqes[i]); + kfree(wq->wqes); + kfree(wq); +} diff --git a/fs/io-wq.h b/fs/io-wq.h new file mode 100644 index 000000000000..4b29f922f80c --- /dev/null +++ b/fs/io-wq.h @@ -0,0 +1,74 @@ +#ifndef INTERNAL_IO_WQ_H +#define INTERNAL_IO_WQ_H + +struct io_wq; + +enum { + IO_WQ_WORK_CANCEL = 1, + IO_WQ_WORK_HAS_MM = 2, + IO_WQ_WORK_HASHED = 4, + IO_WQ_WORK_NEEDS_USER = 8, + IO_WQ_WORK_NEEDS_FILES = 16, + IO_WQ_WORK_UNBOUND = 32, + IO_WQ_WORK_INTERNAL = 64, + + IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ +}; + +enum io_wq_cancel { + IO_WQ_CANCEL_OK, /* cancelled before started */ + IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */ + IO_WQ_CANCEL_NOTFOUND, /* work not found */ +}; + +struct io_wq_work { + struct list_head list; + void (*func)(struct io_wq_work **); + unsigned flags; + struct files_struct *files; +}; + +#define INIT_IO_WORK(work, _func) \ + do { \ + (work)->func = _func; \ + (work)->flags = 0; \ + (work)->files = NULL; \ + } while (0) \ + +typedef void (get_work_fn)(struct io_wq_work *); +typedef void (put_work_fn)(struct io_wq_work *); + +struct io_wq *io_wq_create(unsigned bounded, struct mm_struct *mm, + struct user_struct *user, + get_work_fn *get_work, put_work_fn *put_work); +void io_wq_destroy(struct io_wq *wq); + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); +void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val); +void io_wq_flush(struct io_wq *wq); + +void io_wq_cancel_all(struct io_wq *wq); +enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork); + +typedef bool (work_cancel_fn)(struct io_wq_work *, void *); + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data); + +#if defined(CONFIG_IO_WQ) +extern void io_wq_worker_sleeping(struct task_struct *); +extern void io_wq_worker_running(struct task_struct *); +#else +static inline void io_wq_worker_sleeping(struct task_struct *tsk) +{ +} +static inline void io_wq_worker_running(struct task_struct *tsk) +{ +} +#endif + +static inline bool io_wq_current_is_worker(void) +{ + return in_task() && (current->flags & PF_IO_WORKER); +} +#endif diff --git a/fs/io_uring.c b/fs/io_uring.c index 67dbe0201e0d..4c030a92de79 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -56,7 +56,6 @@ #include <linux/mmu_context.h> #include <linux/percpu.h> #include <linux/slab.h> -#include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/blkdev.h> #include <linux/bvec.h> @@ -71,12 +70,24 @@ #include <linux/sizes.h> #include <linux/hugetlb.h> +#define CREATE_TRACE_POINTS +#include <trace/events/io_uring.h> + #include <uapi/linux/io_uring.h> #include "internal.h" +#include "io-wq.h" #define IORING_MAX_ENTRIES 32768 -#define IORING_MAX_FIXED_FILES 1024 +#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) + +/* + * Shift of 9 is 512 entries, or exactly one page on 64-bit archs + */ +#define IORING_FILE_TABLE_SHIFT 9 +#define IORING_MAX_FILES_TABLE (1U << IORING_FILE_TABLE_SHIFT) +#define IORING_FILE_TABLE_MASK (IORING_MAX_FILES_TABLE - 1) +#define IORING_MAX_FIXED_FILES (64 * IORING_MAX_FILES_TABLE) struct io_uring { u32 head ____cacheline_aligned_in_smp; @@ -161,14 +172,8 @@ struct io_mapped_ubuf { unsigned int nr_bvecs; }; -struct async_list { - spinlock_t lock; - atomic_t cnt; - struct list_head list; - - struct file *file; - off_t io_start; - size_t io_len; +struct fixed_file_table { + struct file **files; }; struct io_ring_ctx { @@ -180,6 +185,7 @@ struct io_ring_ctx { unsigned int flags; bool compat; bool account_mem; + bool cq_overflow_flushed; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -197,37 +203,31 @@ struct io_ring_ctx { unsigned sq_entries; unsigned sq_mask; unsigned sq_thread_idle; + unsigned cached_sq_dropped; + atomic_t cached_cq_overflow; struct io_uring_sqe *sq_sqes; struct list_head defer_list; struct list_head timeout_list; + struct list_head cq_overflow_list; + + wait_queue_head_t inflight_wait; } ____cacheline_aligned_in_smp; + struct io_rings *rings; + /* IO offload */ - struct workqueue_struct *sqo_wq[2]; + struct io_wq *io_wq; struct task_struct *sqo_thread; /* if using sq thread polling */ struct mm_struct *sqo_mm; wait_queue_head_t sqo_wait; - struct completion sqo_thread_started; - - struct { - unsigned cached_cq_tail; - unsigned cq_entries; - unsigned cq_mask; - struct wait_queue_head cq_wait; - struct fasync_struct *cq_fasync; - struct eventfd_ctx *cq_ev_fd; - atomic_t cq_timeouts; - } ____cacheline_aligned_in_smp; - - struct io_rings *rings; /* * If used, fixed file set. Writers must ensure that ->refs is dead, * readers must ensure that ->refs is alive as long as the file* is * used. Only updated through io_uring_register(2). */ - struct file **user_files; + struct fixed_file_table *file_table; unsigned nr_user_files; /* if used, fixed mapped user buffers */ @@ -236,7 +236,25 @@ struct io_ring_ctx { struct user_struct *user; - struct completion ctx_done; + /* 0 is for ctx quiesce/reinit/free, 1 is for sqo_thread started */ + struct completion *completions; + + /* if all else fails... */ + struct io_kiocb *fallback_req; + +#if defined(CONFIG_UNIX) + struct socket *ring_sock; +#endif + + struct { + unsigned cached_cq_tail; + unsigned cq_entries; + unsigned cq_mask; + atomic_t cq_timeouts; + struct wait_queue_head cq_wait; + struct fasync_struct *cq_fasync; + struct eventfd_ctx *cq_ev_fd; + } ____cacheline_aligned_in_smp; struct { struct mutex uring_lock; @@ -253,22 +271,20 @@ struct io_ring_ctx { * manipulate the list, hence no extra locking is needed there. */ struct list_head poll_list; - struct list_head cancel_list; - } ____cacheline_aligned_in_smp; - - struct async_list pending_async[2]; + struct rb_root cancel_tree; -#if defined(CONFIG_UNIX) - struct socket *ring_sock; -#endif + spinlock_t inflight_lock; + struct list_head inflight_list; + } ____cacheline_aligned_in_smp; }; struct sqe_submit { const struct io_uring_sqe *sqe; - unsigned short index; + struct file *ring_file; + int ring_fd; u32 sequence; bool has_user; - bool needs_lock; + bool in_async; bool needs_fixed_file; }; @@ -307,7 +323,10 @@ struct io_kiocb { struct sqe_submit submit; struct io_ring_ctx *ctx; - struct list_head list; + union { + struct list_head list; + struct rb_node rb_node; + }; struct list_head link_list; unsigned int flags; refcount_t refs; @@ -318,17 +337,22 @@ struct io_kiocb { #define REQ_F_IO_DRAIN 16 /* drain existing IO first */ #define REQ_F_IO_DRAINED 32 /* drain done */ #define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_LINK_DONE 128 /* linked sqes done */ +#define REQ_F_LINK_TIMEOUT 128 /* has linked timeout */ #define REQ_F_FAIL_LINK 256 /* fail rest of links */ #define REQ_F_SHADOW_DRAIN 512 /* link-drain shadow req */ #define REQ_F_TIMEOUT 1024 /* timeout request */ #define REQ_F_ISREG 2048 /* regular file */ #define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */ +#define REQ_F_TIMEOUT_NOSEQ 8192 /* no timeout sequence */ +#define REQ_F_INFLIGHT 16384 /* on inflight list */ +#define REQ_F_COMP_LOCKED 32768 /* completion under lock */ u64 user_data; u32 result; u32 sequence; - struct work_struct work; + struct list_head inflight_entry; + + struct io_wq_work work; }; #define IO_PLUG_THRESHOLD 2 @@ -354,10 +378,11 @@ struct io_submit_state { unsigned int ios_left; }; -static void io_sq_wq_submit_work(struct work_struct *work); -static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, - long res); +static void io_wq_submit_work(struct io_wq_work **workptr); +static void io_cqring_fill_event(struct io_kiocb *req, long res); static void __io_free_req(struct io_kiocb *req); +static void io_put_req(struct io_kiocb *req); +static void io_double_put_req(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -380,56 +405,67 @@ static void io_ring_ctx_ref_free(struct percpu_ref *ref) { struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); - complete(&ctx->ctx_done); + complete(&ctx->completions[0]); } static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; - int i; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; + ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL); + if (!ctx->fallback_req) + goto err; + + ctx->completions = kmalloc(2 * sizeof(struct completion), GFP_KERNEL); + if (!ctx->completions) + goto err; + if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { - kfree(ctx); - return NULL; - } + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) + goto err; ctx->flags = p->flags; init_waitqueue_head(&ctx->cq_wait); - init_completion(&ctx->ctx_done); - init_completion(&ctx->sqo_thread_started); + INIT_LIST_HEAD(&ctx->cq_overflow_list); + init_completion(&ctx->completions[0]); + init_completion(&ctx->completions[1]); mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->wait); - for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) { - spin_lock_init(&ctx->pending_async[i].lock); - INIT_LIST_HEAD(&ctx->pending_async[i].list); - atomic_set(&ctx->pending_async[i].cnt, 0); - } spin_lock_init(&ctx->completion_lock); INIT_LIST_HEAD(&ctx->poll_list); - INIT_LIST_HEAD(&ctx->cancel_list); + ctx->cancel_tree = RB_ROOT; INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); + init_waitqueue_head(&ctx->inflight_wait); + spin_lock_init(&ctx->inflight_lock); + INIT_LIST_HEAD(&ctx->inflight_list); return ctx; +err: + if (ctx->fallback_req) + kmem_cache_free(req_cachep, ctx->fallback_req); + kfree(ctx->completions); + kfree(ctx); + return NULL; } -static inline bool __io_sequence_defer(struct io_ring_ctx *ctx, - struct io_kiocb *req) +static inline bool __req_need_defer(struct io_kiocb *req) { - return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped; + struct io_ring_ctx *ctx = req->ctx; + + return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped + + atomic_read(&ctx->cached_cq_overflow); } -static inline bool io_sequence_defer(struct io_ring_ctx *ctx, - struct io_kiocb *req) +static inline bool req_need_defer(struct io_kiocb *req) { - if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) - return false; + if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN) + return __req_need_defer(req); - return __io_sequence_defer(ctx, req); + return false; } static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) @@ -437,7 +473,7 @@ static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) struct io_kiocb *req; req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list); - if (req && !io_sequence_defer(ctx, req)) { + if (req && !req_need_defer(req)) { list_del_init(&req->list); return req; } @@ -450,9 +486,13 @@ static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx) struct io_kiocb *req; req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list); - if (req && !__io_sequence_defer(ctx, req)) { - list_del_init(&req->list); - return req; + if (req) { + if (req->flags & REQ_F_TIMEOUT_NOSEQ) + return NULL; + if (!__req_need_defer(req)) { + list_del_init(&req->list); + return req; + } } return NULL; @@ -473,21 +513,59 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx) } } -static inline void io_queue_async_work(struct io_ring_ctx *ctx, - struct io_kiocb *req) +static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) { - int rw = 0; + u8 opcode = READ_ONCE(sqe->opcode); + + return !(opcode == IORING_OP_READ_FIXED || + opcode == IORING_OP_WRITE_FIXED); +} + +static inline bool io_prep_async_work(struct io_kiocb *req) +{ + bool do_hashed = false; if (req->submit.sqe) { switch (req->submit.sqe->opcode) { case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: - rw = !(req->rw.ki_flags & IOCB_DIRECT); + do_hashed = true; + /* fall-through */ + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_SENDMSG: + case IORING_OP_RECVMSG: + case IORING_OP_ACCEPT: + case IORING_OP_POLL_ADD: + /* + * We know REQ_F_ISREG is not set on some of these + * opcodes, but this enables us to keep the check in + * just one place. + */ + if (!(req->flags & REQ_F_ISREG)) + req->work.flags |= IO_WQ_WORK_UNBOUND; break; } + if (io_sqe_needs_user(req->submit.sqe)) + req->work.flags |= IO_WQ_WORK_NEEDS_USER; } - queue_work(ctx->sqo_wq[rw], &req->work); + return do_hashed; +} + +static inline void io_queue_async_work(struct io_kiocb *req) +{ + bool do_hashed = io_prep_async_work(req); + struct io_ring_ctx *ctx = req->ctx; + + trace_io_uring_queue_async_work(ctx, do_hashed, req, &req->work, + req->flags); + if (!do_hashed) { + io_wq_enqueue(ctx->io_wq, &req->work); + } else { + io_wq_enqueue_hashed(ctx->io_wq, &req->work, + file_inode(req->file)); + } } static void io_kill_timeout(struct io_kiocb *req) @@ -497,9 +575,9 @@ static void io_kill_timeout(struct io_kiocb *req) ret = hrtimer_try_to_cancel(&req->timeout.timer); if (ret != -1) { atomic_inc(&req->ctx->cq_timeouts); - list_del(&req->list); - io_cqring_fill_event(req->ctx, req->user_data, 0); - __io_free_req(req); + list_del_init(&req->list); + io_cqring_fill_event(req, 0); + io_put_req(req); } } @@ -529,7 +607,7 @@ static void io_commit_cqring(struct io_ring_ctx *ctx) continue; } req->flags |= REQ_F_IO_DRAINED; - io_queue_async_work(ctx, req); + io_queue_async_work(req); } } @@ -551,10 +629,73 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) return &rings->cqes[tail & ctx->cq_mask]; } -static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, - long res) +static void io_cqring_ev_posted(struct io_ring_ctx *ctx) { + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); + if (waitqueue_active(&ctx->sqo_wait)) + wake_up(&ctx->sqo_wait); + if (ctx->cq_ev_fd) + eventfd_signal(ctx->cq_ev_fd, 1); +} + +static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) +{ + struct io_rings *rings = ctx->rings; struct io_uring_cqe *cqe; + struct io_kiocb *req; + unsigned long flags; + LIST_HEAD(list); + + if (!force) { + if (list_empty_careful(&ctx->cq_overflow_list)) + return; + if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) == + rings->cq_ring_entries)) + return; + } + + spin_lock_irqsave(&ctx->completion_lock, flags); + + /* if force is set, the ring is going away. always drop after that */ + if (force) + ctx->cq_overflow_flushed = true; + + while (!list_empty(&ctx->cq_overflow_list)) { + cqe = io_get_cqring(ctx); + if (!cqe && !force) + break; + + req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb, + list); + list_move(&req->list, &list); + if (cqe) { + WRITE_ONCE(cqe->user_data, req->user_data); + WRITE_ONCE(cqe->res, req->result); + WRITE_ONCE(cqe->flags, 0); + } else { + WRITE_ONCE(ctx->rings->cq_overflow, + atomic_inc_return(&ctx->cached_cq_overflow)); + } + } + + io_commit_cqring(ctx); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + io_cqring_ev_posted(ctx); + + while (!list_empty(&list)) { + req = list_first_entry(&list, struct io_kiocb, list); + list_del(&req->list); + io_put_req(req); + } +} + +static void io_cqring_fill_event(struct io_kiocb *req, long res) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_cqe *cqe; + + trace_io_uring_complete(ctx, req->user_data, res); /* * If we can't get a cq entry, userspace overflowed the @@ -562,40 +703,50 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, * the ring. */ cqe = io_get_cqring(ctx); - if (cqe) { - WRITE_ONCE(cqe->user_data, ki_user_data); + if (likely(cqe)) { + WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, 0); + } else if (ctx->cq_overflow_flushed) { + WRITE_ONCE(ctx->rings->cq_overflow, + atomic_inc_return(&ctx->cached_cq_overflow)); } else { - unsigned overflow = READ_ONCE(ctx->rings->cq_overflow); - - WRITE_ONCE(ctx->rings->cq_overflow, overflow + 1); + refcount_inc(&req->refs); + req->result = res; + list_add_tail(&req->list, &ctx->cq_overflow_list); } } -static void io_cqring_ev_posted(struct io_ring_ctx *ctx) -{ - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); - if (waitqueue_active(&ctx->sqo_wait)) - wake_up(&ctx->sqo_wait); - if (ctx->cq_ev_fd) - eventfd_signal(ctx->cq_ev_fd, 1); -} - -static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data, - long res) +static void io_cqring_add_event(struct io_kiocb *req, long res) { + struct io_ring_ctx *ctx = req->ctx; unsigned long flags; spin_lock_irqsave(&ctx->completion_lock, flags); - io_cqring_fill_event(ctx, user_data, res); + io_cqring_fill_event(req, res); io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); } +static inline bool io_is_fallback_req(struct io_kiocb *req) +{ + return req == (struct io_kiocb *) + ((unsigned long) req->ctx->fallback_req & ~1UL); +} + +static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx) +{ + struct io_kiocb *req; + + req = ctx->fallback_req; + if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req)) + return req; + + return NULL; +} + static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, struct io_submit_state *state) { @@ -608,7 +759,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, if (!state) { req = kmem_cache_alloc(req_cachep, gfp); if (unlikely(!req)) - goto out; + goto fallback; } else if (!state->free_reqs) { size_t sz; int ret; @@ -623,7 +774,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, if (unlikely(ret <= 0)) { state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); if (!state->reqs[0]) - goto out; + goto fallback; ret = 1; } state->free_reqs = ret - 1; @@ -635,14 +786,19 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, state->cur_req++; } +got_it: req->file = NULL; req->ctx = ctx; req->flags = 0; /* one is dropped after submission, the other at completion */ refcount_set(&req->refs, 2); req->result = 0; + INIT_IO_WORK(&req->work, io_wq_submit_work); return req; -out: +fallback: + req = io_get_fallback_req(ctx); + if (req) + goto got_it; percpu_ref_put(&ctx->refs); return NULL; } @@ -658,15 +814,48 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr) static void __io_free_req(struct io_kiocb *req) { + struct io_ring_ctx *ctx = req->ctx; + if (req->file && !(req->flags & REQ_F_FIXED_FILE)) fput(req->file); - percpu_ref_put(&req->ctx->refs); - kmem_cache_free(req_cachep, req); + if (req->flags & REQ_F_INFLIGHT) { + unsigned long flags; + + spin_lock_irqsave(&ctx->inflight_lock, flags); + list_del(&req->inflight_entry); + if (waitqueue_active(&ctx->inflight_wait)) + wake_up(&ctx->inflight_wait); + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + } + percpu_ref_put(&ctx->refs); + if (likely(!io_is_fallback_req(req))) + kmem_cache_free(req_cachep, req); + else + clear_bit_unlock(0, (unsigned long *) ctx->fallback_req); } -static void io_req_link_next(struct io_kiocb *req) +static bool io_link_cancel_timeout(struct io_kiocb *req) { + struct io_ring_ctx *ctx = req->ctx; + int ret; + + ret = hrtimer_try_to_cancel(&req->timeout.timer); + if (ret != -1) { + io_cqring_fill_event(req, -ECANCELED); + io_commit_cqring(ctx); + req->flags &= ~REQ_F_LINK; + io_put_req(req); + return true; + } + + return false; +} + +static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr) +{ + struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *nxt; + bool wake_ev = false; /* * The list should never be empty when we are called here. But could @@ -674,18 +863,35 @@ static void io_req_link_next(struct io_kiocb *req) * safe side. */ nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list); - if (nxt) { - list_del(&nxt->list); + while (nxt) { + list_del_init(&nxt->list); if (!list_empty(&req->link_list)) { INIT_LIST_HEAD(&nxt->link_list); list_splice(&req->link_list, &nxt->link_list); nxt->flags |= REQ_F_LINK; } - nxt->flags |= REQ_F_LINK_DONE; - INIT_WORK(&nxt->work, io_sq_wq_submit_work); - io_queue_async_work(req->ctx, nxt); + /* + * If we're in async work, we can continue processing the chain + * in this context instead of having to queue up new async work. + */ + if (req->flags & REQ_F_LINK_TIMEOUT) { + wake_ev = io_link_cancel_timeout(nxt); + + /* we dropped this link, get next */ + nxt = list_first_entry_or_null(&req->link_list, + struct io_kiocb, list); + } else if (nxtptr && io_wq_current_is_worker()) { + *nxtptr = nxt; + break; + } else { + io_queue_async_work(nxt); + break; + } } + + if (wake_ev) + io_cqring_ev_posted(ctx); } /* @@ -693,48 +899,131 @@ static void io_req_link_next(struct io_kiocb *req) */ static void io_fail_links(struct io_kiocb *req) { + struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link; + unsigned long flags; + + spin_lock_irqsave(&ctx->completion_lock, flags); while (!list_empty(&req->link_list)) { link = list_first_entry(&req->link_list, struct io_kiocb, list); - list_del(&link->list); + list_del_init(&link->list); - io_cqring_add_event(req->ctx, link->user_data, -ECANCELED); - __io_free_req(link); + trace_io_uring_fail_link(req, link); + + if ((req->flags & REQ_F_LINK_TIMEOUT) && + link->submit.sqe->opcode == IORING_OP_LINK_TIMEOUT) { + io_link_cancel_timeout(link); + } else { + io_cqring_fill_event(link, -ECANCELED); + io_double_put_req(link); + } } + + io_commit_cqring(ctx); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + io_cqring_ev_posted(ctx); } -static void io_free_req(struct io_kiocb *req) +static void io_free_req_find_next(struct io_kiocb *req, struct io_kiocb **nxt) { + if (likely(!(req->flags & REQ_F_LINK))) { + __io_free_req(req); + return; + } + /* * If LINK is set, we have dependent requests in this chain. If we * didn't fail this request, queue the first one up, moving any other * dependencies to the next request. In case of failure, fail the rest * of the chain. */ - if (req->flags & REQ_F_LINK) { - if (req->flags & REQ_F_FAIL_LINK) - io_fail_links(req); - else - io_req_link_next(req); + if (req->flags & REQ_F_FAIL_LINK) { + io_fail_links(req); + } else if ((req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_COMP_LOCKED)) == + REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + /* + * If this is a timeout link, we could be racing with the + * timeout timer. Grab the completion lock for this case to + * protect against that. + */ + spin_lock_irqsave(&ctx->completion_lock, flags); + io_req_link_next(req, nxt); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + } else { + io_req_link_next(req, nxt); } __io_free_req(req); } +static void io_free_req(struct io_kiocb *req) +{ + io_free_req_find_next(req, NULL); +} + +/* + * Drop reference to request, return next in chain (if there is one) if this + * was the last reference to this request. + */ +static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr) +{ + struct io_kiocb *nxt = NULL; + + if (refcount_dec_and_test(&req->refs)) + io_free_req_find_next(req, &nxt); + + if (nxt) { + if (nxtptr) + *nxtptr = nxt; + else + io_queue_async_work(nxt); + } +} + static void io_put_req(struct io_kiocb *req) { if (refcount_dec_and_test(&req->refs)) io_free_req(req); } -static unsigned io_cqring_events(struct io_rings *rings) +static void io_double_put_req(struct io_kiocb *req) { + /* drop both submit and complete references */ + if (refcount_sub_and_test(2, &req->refs)) + __io_free_req(req); +} + +static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush) +{ + struct io_rings *rings = ctx->rings; + + /* + * noflush == true is from the waitqueue handler, just ensure we wake + * up the task, and the next invocation will flush the entries. We + * cannot safely to it from here. + */ + if (noflush && !list_empty(&ctx->cq_overflow_list)) + return -1U; + + io_cqring_overflow_flush(ctx, false); + /* See comment at the top of this file */ smp_rmb(); return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head); } +static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + + /* make sure SQ entry isn't read before tail */ + return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; +} + /* * Find and free completed poll iocbs */ @@ -750,7 +1039,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, list); list_del(&req->list); - io_cqring_fill_event(ctx, req->user_data, req->result); + io_cqring_fill_event(req, req->result); (*nr_events)++; if (refcount_dec_and_test(&req->refs)) { @@ -759,8 +1048,8 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, * completions for those, only batch free for fixed * file and non-linked commands. */ - if ((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) == - REQ_F_FIXED_FILE) { + if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) == + REQ_F_FIXED_FILE) && !io_is_fallback_req(req)) { reqs[to_free++] = req; if (to_free == ARRAY_SIZE(reqs)) io_free_req_many(ctx, reqs, &to_free); @@ -864,19 +1153,11 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, - long min) +static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) { - int iters, ret = 0; + int iters = 0, ret = 0; - /* - * We disallow the app entering submit/complete with polling, but we - * still need to lock the ring to prevent racing with polled issue - * that got punted to a workqueue. - */ - mutex_lock(&ctx->uring_lock); - - iters = 0; do { int tmin = 0; @@ -885,7 +1166,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ - if (io_cqring_events(ctx->rings)) + if (io_cqring_events(ctx, false)) break; /* @@ -912,6 +1193,21 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, ret = 0; } while (min && !*nr_events && !need_resched()); + return ret; +} + +static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, + long min) +{ + int ret; + + /* + * We disallow the app entering submit/complete with polling, but we + * still need to lock the ring to prevent racing with polled issue + * that got punted to a workqueue. + */ + mutex_lock(&ctx->uring_lock); + ret = __io_iopoll_check(ctx, nr_events, min); mutex_unlock(&ctx->uring_lock); return ret; } @@ -930,7 +1226,7 @@ static void kiocb_end_write(struct io_kiocb *req) file_end_write(req->file); } -static void io_complete_rw(struct kiocb *kiocb, long res, long res2) +static void io_complete_rw_common(struct kiocb *kiocb, long res) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); @@ -939,10 +1235,28 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) if ((req->flags & REQ_F_LINK) && res != req->result) req->flags |= REQ_F_FAIL_LINK; - io_cqring_add_event(req->ctx, req->user_data, res); + io_cqring_add_event(req, res); +} + +static void io_complete_rw(struct kiocb *kiocb, long res, long res2) +{ + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + + io_complete_rw_common(kiocb, res); io_put_req(req); } +static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) +{ + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *nxt = NULL; + + io_complete_rw_common(kiocb, res); + io_put_req_find_next(req, &nxt); + + return nxt; +} + static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); @@ -1050,10 +1364,9 @@ static bool io_file_supports_async(struct file *file) return false; } -static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock) +static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) { - const struct io_uring_sqe *sqe = s->sqe; + const struct io_uring_sqe *sqe = req->submit.sqe; struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw; unsigned ioprio; @@ -1107,6 +1420,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, kiocb->ki_flags |= IOCB_HIPRI; kiocb->ki_complete = io_complete_rw_iopoll; + req->result = 0; } else { if (kiocb->ki_flags & IOCB_HIPRI) return -EINVAL; @@ -1136,6 +1450,15 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } +static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt, + bool in_async) +{ + if (in_async && ret >= 0 && nxt && kiocb->ki_complete == io_complete_rw) + *nxt = __io_complete_rw(kiocb, ret); + else + io_rw_done(kiocb, ret); +} + static int io_import_fixed(struct io_ring_ctx *ctx, int rw, const struct io_uring_sqe *sqe, struct iov_iter *iter) @@ -1207,7 +1530,7 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, } } - return 0; + return len; } static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, @@ -1247,65 +1570,6 @@ static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter); } -static inline bool io_should_merge(struct async_list *al, struct kiocb *kiocb) -{ - if (al->file == kiocb->ki_filp) { - off_t start, end; - - /* - * Allow merging if we're anywhere in the range of the same - * page. Generally this happens for sub-page reads or writes, - * and it's beneficial to allow the first worker to bring the - * page in and the piggy backed work can then work on the - * cached page. - */ - start = al->io_start & PAGE_MASK; - end = (al->io_start + al->io_len + PAGE_SIZE - 1) & PAGE_MASK; - if (kiocb->ki_pos >= start && kiocb->ki_pos <= end) - return true; - } - - al->file = NULL; - return false; -} - -/* - * Make a note of the last file/offset/direction we punted to async - * context. We'll use this information to see if we can piggy back a - * sequential request onto the previous one, if it's still hasn't been - * completed by the async worker. - */ -static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) -{ - struct async_list *async_list = &req->ctx->pending_async[rw]; - struct kiocb *kiocb = &req->rw; - struct file *filp = kiocb->ki_filp; - - if (io_should_merge(async_list, kiocb)) { - unsigned long max_bytes; - - /* Use 8x RA size as a decent limiter for both reads/writes */ - max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3); - if (!max_bytes) - max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3); - - /* If max len are exceeded, reset the state */ - if (async_list->io_len + len <= max_bytes) { - req->flags |= REQ_F_SEQ_PREV; - async_list->io_len += len; - } else { - async_list->file = NULL; - } - } - - /* New file? Reset state. */ - if (async_list->file != filp) { - async_list->io_start = kiocb->ki_pos; - async_list->io_len = len; - async_list->file = filp; - } -} - /* * For files that don't have ->read_iter() and ->write_iter(), handle them * by looping over ->read() or ->write() manually. @@ -1351,7 +1615,7 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, return ret; } -static int io_read(struct io_kiocb *req, const struct sqe_submit *s, +static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; @@ -1361,7 +1625,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; ssize_t read_size, ret; - ret = io_prep_rw(req, s, force_nonblock); + ret = io_prep_rw(req, force_nonblock); if (ret) return ret; file = kiocb->ki_filp; @@ -1369,7 +1633,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; - ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, READ, &req->submit, &iovec, &iter); if (ret < 0) return ret; @@ -1400,23 +1664,16 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, ret2 > 0 && ret2 < read_size) ret2 = -EAGAIN; /* Catch -EAGAIN return for forced non-blocking submission */ - if (!force_nonblock || ret2 != -EAGAIN) { - io_rw_done(kiocb, ret2); - } else { - /* - * If ->needs_lock is true, we're already in async - * context. - */ - if (!s->needs_lock) - io_async_list_note(READ, req, iov_count); + if (!force_nonblock || ret2 != -EAGAIN) + kiocb_done(kiocb, ret2, nxt, req->submit.in_async); + else ret = -EAGAIN; - } } kfree(iovec); return ret; } -static int io_write(struct io_kiocb *req, const struct sqe_submit *s, +static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; @@ -1426,7 +1683,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; ssize_t ret; - ret = io_prep_rw(req, s, force_nonblock); + ret = io_prep_rw(req, force_nonblock); if (ret) return ret; @@ -1434,7 +1691,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_WRITE))) return -EBADF; - ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, WRITE, &req->submit, &iovec, &iter); if (ret < 0) return ret; @@ -1444,12 +1701,8 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, iov_count = iov_iter_count(&iter); ret = -EAGAIN; - if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) { - /* If ->needs_lock is true, we're already in async context. */ - if (!s->needs_lock) - io_async_list_note(WRITE, req, iov_count); + if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) goto out_free; - } ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); if (!ret) { @@ -1474,17 +1727,10 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, ret2 = call_write_iter(file, kiocb, &iter); else ret2 = loop_rw_iter(WRITE, file, kiocb, &iter); - if (!force_nonblock || ret2 != -EAGAIN) { - io_rw_done(kiocb, ret2); - } else { - /* - * If ->needs_lock is true, we're already in async - * context. - */ - if (!s->needs_lock) - io_async_list_note(WRITE, req, iov_count); + if (!force_nonblock || ret2 != -EAGAIN) + kiocb_done(kiocb, ret2, nxt, req->submit.in_async); + else ret = -EAGAIN; - } } out_free: kfree(iovec); @@ -1494,15 +1740,14 @@ out_free: /* * IORING_OP_NOP just posts a completion event, nothing else. */ -static int io_nop(struct io_kiocb *req, u64 user_data) +static int io_nop(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - long err = 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - io_cqring_add_event(ctx, user_data, err); + io_cqring_add_event(req, 0); io_put_req(req); return 0; } @@ -1523,7 +1768,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) } static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock) + struct io_kiocb **nxt, bool force_nonblock) { loff_t sqe_off = READ_ONCE(sqe->off); loff_t sqe_len = READ_ONCE(sqe->len); @@ -1549,8 +1794,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; - io_cqring_add_event(req->ctx, sqe->user_data, ret); - io_put_req(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); return 0; } @@ -1572,6 +1817,7 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_sync_file_range(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) { loff_t sqe_off; @@ -1595,14 +1841,14 @@ static int io_sync_file_range(struct io_kiocb *req, if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; - io_cqring_add_event(req->ctx, sqe->user_data, ret); - io_put_req(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); return 0; } #if defined(CONFIG_NET) static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock, + struct io_kiocb **nxt, bool force_nonblock, long (*fn)(struct socket *, struct user_msghdr __user *, unsigned int)) { @@ -1631,32 +1877,80 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, return ret; } - io_cqring_add_event(req->ctx, sqe->user_data, ret); - io_put_req(req); + io_cqring_add_event(req, ret); + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_put_req_find_next(req, nxt); return 0; } #endif static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock) + struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, force_nonblock, __sys_sendmsg_sock); + return io_send_recvmsg(req, sqe, nxt, force_nonblock, + __sys_sendmsg_sock); #else return -EOPNOTSUPP; #endif } static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - bool force_nonblock) + struct io_kiocb **nxt, bool force_nonblock) +{ +#if defined(CONFIG_NET) + return io_send_recvmsg(req, sqe, nxt, force_nonblock, + __sys_recvmsg_sock); +#else + return -EOPNOTSUPP; +#endif +} + +static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, force_nonblock, __sys_recvmsg_sock); + struct sockaddr __user *addr; + int __user *addr_len; + unsigned file_flags; + int flags, ret; + + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) + return -EINVAL; + + addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); + addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2); + flags = READ_ONCE(sqe->accept_flags); + file_flags = force_nonblock ? O_NONBLOCK : 0; + + ret = __sys_accept4_file(req->file, file_flags, addr, addr_len, flags); + if (ret == -EAGAIN && force_nonblock) { + req->work.flags |= IO_WQ_WORK_NEEDS_FILES; + return -EAGAIN; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); + return 0; #else return -EOPNOTSUPP; #endif } +static inline void io_poll_remove_req(struct io_kiocb *req) +{ + if (!RB_EMPTY_NODE(&req->rb_node)) { + rb_erase(&req->rb_node, &req->ctx->cancel_tree); + RB_CLEAR_NODE(&req->rb_node); + } +} + static void io_poll_remove_one(struct io_kiocb *req) { struct io_poll_iocb *poll = &req->poll; @@ -1665,25 +1959,47 @@ static void io_poll_remove_one(struct io_kiocb *req) WRITE_ONCE(poll->canceled, true); if (!list_empty(&poll->wait.entry)) { list_del_init(&poll->wait.entry); - io_queue_async_work(req->ctx, req); + io_queue_async_work(req); } spin_unlock(&poll->head->lock); - - list_del_init(&req->list); + io_poll_remove_req(req); } static void io_poll_remove_all(struct io_ring_ctx *ctx) { + struct rb_node *node; struct io_kiocb *req; spin_lock_irq(&ctx->completion_lock); - while (!list_empty(&ctx->cancel_list)) { - req = list_first_entry(&ctx->cancel_list, struct io_kiocb,list); + while ((node = rb_first(&ctx->cancel_tree)) != NULL) { + req = rb_entry(node, struct io_kiocb, rb_node); io_poll_remove_one(req); } spin_unlock_irq(&ctx->completion_lock); } +static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) +{ + struct rb_node *p, *parent = NULL; + struct io_kiocb *req; + + p = ctx->cancel_tree.rb_node; + while (p) { + parent = p; + req = rb_entry(parent, struct io_kiocb, rb_node); + if (sqe_addr < req->user_data) { + p = p->rb_left; + } else if (sqe_addr > req->user_data) { + p = p->rb_right; + } else { + io_poll_remove_one(req); + return 0; + } + } + + return -ENOENT; +} + /* * Find a running poll command that matches one specified in sqe->addr, * and remove it if found. @@ -1691,8 +2007,7 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx) static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *poll_req, *next; - int ret = -ENOENT; + int ret; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; @@ -1701,36 +2016,38 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EINVAL; spin_lock_irq(&ctx->completion_lock); - list_for_each_entry_safe(poll_req, next, &ctx->cancel_list, list) { - if (READ_ONCE(sqe->addr) == poll_req->user_data) { - io_poll_remove_one(poll_req); - ret = 0; - break; - } - } + ret = io_poll_cancel(ctx, READ_ONCE(sqe->addr)); spin_unlock_irq(&ctx->completion_lock); - io_cqring_add_event(req->ctx, sqe->user_data, ret); + io_cqring_add_event(req, ret); + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; io_put_req(req); return 0; } -static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req, - __poll_t mask) +static void io_poll_complete(struct io_kiocb *req, __poll_t mask) { + struct io_ring_ctx *ctx = req->ctx; + req->poll.done = true; - io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask)); + io_cqring_fill_event(req, mangle_poll(mask)); io_commit_cqring(ctx); } -static void io_poll_complete_work(struct work_struct *work) +static void io_poll_complete_work(struct io_wq_work **workptr) { + struct io_wq_work *work = *workptr; struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_poll_iocb *poll = &req->poll; struct poll_table_struct pt = { ._key = poll->events }; struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *nxt = NULL; __poll_t mask = 0; + if (work->flags & IO_WQ_WORK_CANCEL) + WRITE_ONCE(poll->canceled, true); + if (!READ_ONCE(poll->canceled)) mask = vfs_poll(poll->file, &pt) & poll->events; @@ -1747,12 +2064,15 @@ static void io_poll_complete_work(struct work_struct *work) spin_unlock_irq(&ctx->completion_lock); return; } - list_del_init(&req->list); - io_poll_complete(ctx, req, mask); + io_poll_remove_req(req); + io_poll_complete(req, mask); spin_unlock_irq(&ctx->completion_lock); io_cqring_ev_posted(ctx); - io_put_req(req); + + io_put_req_find_next(req, &nxt); + if (nxt) + *workptr = &nxt->work; } static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, @@ -1771,15 +2091,22 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del_init(&poll->wait.entry); + /* + * Run completion inline if we can. We're using trylock here because + * we are violating the completion_lock -> poll wq lock ordering. + * If we have a link timeout we're going to need the completion_lock + * for finalizing the request, mark us as having grabbed that already. + */ if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) { - list_del(&req->list); - io_poll_complete(ctx, req, mask); + io_poll_remove_req(req); + io_poll_complete(req, mask); + req->flags |= REQ_F_COMP_LOCKED; + io_put_req(req); spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); - io_put_req(req); } else { - io_queue_async_work(ctx, req); + io_queue_async_work(req); } return 1; @@ -1806,7 +2133,27 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, add_wait_queue(head, &pt->req->poll.wait); } -static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static void io_poll_req_insert(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct rb_node **p = &ctx->cancel_tree.rb_node; + struct rb_node *parent = NULL; + struct io_kiocb *tmp; + + while (*p) { + parent = *p; + tmp = rb_entry(parent, struct io_kiocb, rb_node); + if (req->user_data < tmp->user_data) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&req->rb_node, parent, p); + rb_insert_color(&req->rb_node, &ctx->cancel_tree); +} + +static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt) { struct io_poll_iocb *poll = &req->poll; struct io_ring_ctx *ctx = req->ctx; @@ -1823,9 +2170,10 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EBADF; req->submit.sqe = NULL; - INIT_WORK(&req->work, io_poll_complete_work); + INIT_IO_WORK(&req->work, io_poll_complete_work); events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; + RB_CLEAR_NODE(&req->rb_node); poll->head = NULL; poll->done = false; @@ -1858,18 +2206,18 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) else if (cancel) WRITE_ONCE(poll->canceled, true); else if (!poll->done) /* actually waiting for an event */ - list_add_tail(&req->list, &ctx->cancel_list); + io_poll_req_insert(req); spin_unlock(&poll->head->lock); } if (mask) { /* no async, we'd stolen it */ ipt.error = 0; - io_poll_complete(ctx, req, mask); + io_poll_complete(req, mask); } spin_unlock_irq(&ctx->completion_lock); if (mask) { io_cqring_ev_posted(ctx); - io_put_req(req); + io_put_req_find_next(req, nxt); } return ipt.error; } @@ -1885,46 +2233,137 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) atomic_inc(&ctx->cq_timeouts); spin_lock_irqsave(&ctx->completion_lock, flags); - list_del(&req->list); + /* + * We could be racing with timeout deletion. If the list is empty, + * then timeout lookup already found it and will be handling it. + */ + if (!list_empty(&req->list)) { + struct io_kiocb *prev; - io_cqring_fill_event(ctx, req->user_data, -ETIME); + /* + * Adjust the reqs sequence before the current one because it + * will consume a slot in the cq_ring and the the cq_tail + * pointer will be increased, otherwise other timeout reqs may + * return in advance without waiting for enough wait_nr. + */ + prev = req; + list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list) + prev->sequence++; + list_del_init(&req->list); + } + + io_cqring_fill_event(req, -ETIME); io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); - + if (req->flags & REQ_F_LINK) + req->flags |= REQ_F_FAIL_LINK; io_put_req(req); return HRTIMER_NORESTART; } +static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) +{ + struct io_kiocb *req; + int ret = -ENOENT; + + list_for_each_entry(req, &ctx->timeout_list, list) { + if (user_data == req->user_data) { + list_del_init(&req->list); + ret = 0; + break; + } + } + + if (ret == -ENOENT) + return ret; + + ret = hrtimer_try_to_cancel(&req->timeout.timer); + if (ret == -1) + return -EALREADY; + + io_cqring_fill_event(req, -ECANCELED); + io_put_req(req); + return 0; +} + +/* + * Remove or update an existing timeout command + */ +static int io_timeout_remove(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_ring_ctx *ctx = req->ctx; + unsigned flags; + int ret; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) + return -EINVAL; + flags = READ_ONCE(sqe->timeout_flags); + if (flags) + return -EINVAL; + + spin_lock_irq(&ctx->completion_lock); + ret = io_timeout_cancel(ctx, READ_ONCE(sqe->addr)); + + io_cqring_fill_event(req, ret); + io_commit_cqring(ctx); + spin_unlock_irq(&ctx->completion_lock); + io_cqring_ev_posted(ctx); + if (ret < 0 && req->flags & REQ_F_LINK) + req->flags |= REQ_F_FAIL_LINK; + io_put_req(req); + return 0; +} + static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) { unsigned count; struct io_ring_ctx *ctx = req->ctx; struct list_head *entry; + enum hrtimer_mode mode; struct timespec64 ts; + unsigned span = 0; + unsigned flags; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags || - sqe->len != 1) + if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len != 1) + return -EINVAL; + flags = READ_ONCE(sqe->timeout_flags); + if (flags & ~IORING_TIMEOUT_ABS) return -EINVAL; if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; + if (flags & IORING_TIMEOUT_ABS) + mode = HRTIMER_MODE_ABS; + else + mode = HRTIMER_MODE_REL; + + hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, mode); + req->flags |= REQ_F_TIMEOUT; + /* * sqe->off holds how many events that need to occur for this - * timeout event to be satisfied. + * timeout event to be satisfied. If it isn't set, then this is + * a pure timeout request, sequence isn't used. */ count = READ_ONCE(sqe->off); - if (!count) - count = 1; + if (!count) { + req->flags |= REQ_F_TIMEOUT_NOSEQ; + spin_lock_irq(&ctx->completion_lock); + entry = ctx->timeout_list.prev; + goto add; + } req->sequence = ctx->cached_sq_head + count - 1; /* reuse it to store the count */ req->submit.sequence = count; - req->flags |= REQ_F_TIMEOUT; /* * Insertion sort, ensuring the first entry in the list is always @@ -1936,6 +2375,9 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) unsigned nxt_sq_head; long long tmp, tmp_nxt; + if (nxt->flags & REQ_F_TIMEOUT_NOSEQ) + continue; + /* * Since cached_sq_head + count - 1 can overflow, use type long * long to store it. @@ -1951,25 +2393,105 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (ctx->cached_sq_head < nxt_sq_head) tmp += UINT_MAX; - if (tmp >= tmp_nxt) + if (tmp > tmp_nxt) break; + + /* + * Sequence of reqs after the insert one and itself should + * be adjusted because each timeout req consumes a slot. + */ + span++; + nxt->sequence++; } + req->sequence -= span; +add: list_add(&req->list, entry); + req->timeout.timer.function = io_timeout_fn; + hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts), mode); spin_unlock_irq(&ctx->completion_lock); + return 0; +} - hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - req->timeout.timer.function = io_timeout_fn; - hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts), - HRTIMER_MODE_REL); +static bool io_cancel_cb(struct io_wq_work *work, void *data) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + return req->user_data == (unsigned long) data; +} + +static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr) +{ + enum io_wq_cancel cancel_ret; + int ret = 0; + + cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr); + switch (cancel_ret) { + case IO_WQ_CANCEL_OK: + ret = 0; + break; + case IO_WQ_CANCEL_RUNNING: + ret = -EALREADY; + break; + case IO_WQ_CANCEL_NOTFOUND: + ret = -ENOENT; + break; + } + + return ret; +} + +static void io_async_find_and_cancel(struct io_ring_ctx *ctx, + struct io_kiocb *req, __u64 sqe_addr, + struct io_kiocb **nxt) +{ + unsigned long flags; + int ret; + + ret = io_async_cancel_one(ctx, (void *) (unsigned long) sqe_addr); + if (ret != -ENOENT) { + spin_lock_irqsave(&ctx->completion_lock, flags); + goto done; + } + + spin_lock_irqsave(&ctx->completion_lock, flags); + ret = io_timeout_cancel(ctx, sqe_addr); + if (ret != -ENOENT) + goto done; + ret = io_poll_cancel(ctx, sqe_addr); +done: + io_cqring_fill_event(req, ret); + io_commit_cqring(ctx); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + io_cqring_ev_posted(ctx); + + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_put_req_find_next(req, nxt); +} + +static int io_async_cancel(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->flags || sqe->ioprio || sqe->off || sqe->len || + sqe->cancel_flags) + return -EINVAL; + + io_async_find_and_cancel(ctx, req, READ_ONCE(sqe->addr), NULL); return 0; } -static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_req_defer(struct io_kiocb *req) { + const struct io_uring_sqe *sqe = req->submit.sqe; struct io_uring_sqe *sqe_copy; + struct io_ring_ctx *ctx = req->ctx; - if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) + /* Still need defer if there is pending req in defer list. */ + if (!req_need_defer(req) && list_empty(&ctx->defer_list)) return 0; sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL); @@ -1977,7 +2499,7 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, return -EAGAIN; spin_lock_irq(&ctx->completion_lock); - if (!io_sequence_defer(ctx, req) && list_empty(&ctx->defer_list)) { + if (!req_need_defer(req) && list_empty(&ctx->defer_list)) { spin_unlock_irq(&ctx->completion_lock); kfree(sqe_copy); return 0; @@ -1986,64 +2508,70 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, memcpy(sqe_copy, sqe, sizeof(*sqe_copy)); req->submit.sqe = sqe_copy; - INIT_WORK(&req->work, io_sq_wq_submit_work); + trace_io_uring_defer(ctx, req, false); list_add_tail(&req->list, &ctx->defer_list); spin_unlock_irq(&ctx->completion_lock); return -EIOCBQUEUED; } -static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct sqe_submit *s, bool force_nonblock) +static int __io_submit_sqe(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { int ret, opcode; - - req->user_data = READ_ONCE(s->sqe->user_data); - - if (unlikely(s->index >= ctx->sq_entries)) - return -EINVAL; + struct sqe_submit *s = &req->submit; + struct io_ring_ctx *ctx = req->ctx; opcode = READ_ONCE(s->sqe->opcode); switch (opcode) { case IORING_OP_NOP: - ret = io_nop(req, req->user_data); + ret = io_nop(req); break; case IORING_OP_READV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_read(req, s, force_nonblock); + ret = io_read(req, nxt, force_nonblock); break; case IORING_OP_WRITEV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_write(req, s, force_nonblock); + ret = io_write(req, nxt, force_nonblock); break; case IORING_OP_READ_FIXED: - ret = io_read(req, s, force_nonblock); + ret = io_read(req, nxt, force_nonblock); break; case IORING_OP_WRITE_FIXED: - ret = io_write(req, s, force_nonblock); + ret = io_write(req, nxt, force_nonblock); break; case IORING_OP_FSYNC: - ret = io_fsync(req, s->sqe, force_nonblock); + ret = io_fsync(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_POLL_ADD: - ret = io_poll_add(req, s->sqe); + ret = io_poll_add(req, s->sqe, nxt); break; case IORING_OP_POLL_REMOVE: ret = io_poll_remove(req, s->sqe); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, s->sqe, force_nonblock); + ret = io_sync_file_range(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_SENDMSG: - ret = io_sendmsg(req, s->sqe, force_nonblock); + ret = io_sendmsg(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_RECVMSG: - ret = io_recvmsg(req, s->sqe, force_nonblock); + ret = io_recvmsg(req, s->sqe, nxt, force_nonblock); break; case IORING_OP_TIMEOUT: ret = io_timeout(req, s->sqe); break; + case IORING_OP_TIMEOUT_REMOVE: + ret = io_timeout_remove(req, s->sqe); + break; + case IORING_OP_ACCEPT: + ret = io_accept(req, s->sqe, nxt, force_nonblock); + break; + case IORING_OP_ASYNC_CANCEL: + ret = io_async_cancel(req, s->sqe, nxt); + break; default: ret = -EINVAL; break; @@ -2057,187 +2585,65 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return -EAGAIN; /* workqueue context doesn't hold uring_lock, grab it now */ - if (s->needs_lock) + if (s->in_async) mutex_lock(&ctx->uring_lock); io_iopoll_req_issued(req); - if (s->needs_lock) + if (s->in_async) mutex_unlock(&ctx->uring_lock); } return 0; } -static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx, - const struct io_uring_sqe *sqe) -{ - switch (sqe->opcode) { - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - return &ctx->pending_async[READ]; - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: - return &ctx->pending_async[WRITE]; - default: - return NULL; - } -} - -static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) -{ - u8 opcode = READ_ONCE(sqe->opcode); - - return !(opcode == IORING_OP_READ_FIXED || - opcode == IORING_OP_WRITE_FIXED); -} - -static void io_sq_wq_submit_work(struct work_struct *work) +static void io_wq_submit_work(struct io_wq_work **workptr) { + struct io_wq_work *work = *workptr; struct io_kiocb *req = container_of(work, struct io_kiocb, work); - struct io_ring_ctx *ctx = req->ctx; - struct mm_struct *cur_mm = NULL; - struct async_list *async_list; - LIST_HEAD(req_list); - mm_segment_t old_fs; - int ret; + struct sqe_submit *s = &req->submit; + const struct io_uring_sqe *sqe = s->sqe; + struct io_kiocb *nxt = NULL; + int ret = 0; - async_list = io_async_list_from_sqe(ctx, req->submit.sqe); -restart: - do { - struct sqe_submit *s = &req->submit; - const struct io_uring_sqe *sqe = s->sqe; - unsigned int flags = req->flags; + /* Ensure we clear previously set non-block flag */ + req->rw.ki_flags &= ~IOCB_NOWAIT; - /* Ensure we clear previously set non-block flag */ - req->rw.ki_flags &= ~IOCB_NOWAIT; + if (work->flags & IO_WQ_WORK_CANCEL) + ret = -ECANCELED; - ret = 0; - if (io_sqe_needs_user(sqe) && !cur_mm) { - if (!mmget_not_zero(ctx->sqo_mm)) { - ret = -EFAULT; - } else { - cur_mm = ctx->sqo_mm; - use_mm(cur_mm); - old_fs = get_fs(); - set_fs(USER_DS); - } - } + if (!ret) { + s->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0; + s->in_async = true; + do { + ret = __io_submit_sqe(req, &nxt, false); + /* + * We can get EAGAIN for polled IO even though we're + * forcing a sync submission from here, since we can't + * wait for request slots on the block side. + */ + if (ret != -EAGAIN) + break; + cond_resched(); + } while (1); + } - if (!ret) { - s->has_user = cur_mm != NULL; - s->needs_lock = true; - do { - ret = __io_submit_sqe(ctx, req, s, false); - /* - * We can get EAGAIN for polled IO even though - * we're forcing a sync submission from here, - * since we can't wait for request slots on the - * block side. - */ - if (ret != -EAGAIN) - break; - cond_resched(); - } while (1); - } + /* drop submission reference */ + io_put_req(req); - /* drop submission reference */ + if (ret) { + if (req->flags & REQ_F_LINK) + req->flags |= REQ_F_FAIL_LINK; + io_cqring_add_event(req, ret); io_put_req(req); - - if (ret) { - io_cqring_add_event(ctx, sqe->user_data, ret); - io_put_req(req); - } - - /* async context always use a copy of the sqe */ - kfree(sqe); - - /* req from defer and link list needn't decrease async cnt */ - if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) - goto out; - - if (!async_list) - break; - if (!list_empty(&req_list)) { - req = list_first_entry(&req_list, struct io_kiocb, - list); - list_del(&req->list); - continue; - } - if (list_empty(&async_list->list)) - break; - - req = NULL; - spin_lock(&async_list->lock); - if (list_empty(&async_list->list)) { - spin_unlock(&async_list->lock); - break; - } - list_splice_init(&async_list->list, &req_list); - spin_unlock(&async_list->lock); - - req = list_first_entry(&req_list, struct io_kiocb, list); - list_del(&req->list); - } while (req); - - /* - * Rare case of racing with a submitter. If we find the count has - * dropped to zero AND we have pending work items, then restart - * the processing. This is a tiny race window. - */ - if (async_list) { - ret = atomic_dec_return(&async_list->cnt); - while (!ret && !list_empty(&async_list->list)) { - spin_lock(&async_list->lock); - atomic_inc(&async_list->cnt); - list_splice_init(&async_list->list, &req_list); - spin_unlock(&async_list->lock); - - if (!list_empty(&req_list)) { - req = list_first_entry(&req_list, - struct io_kiocb, list); - list_del(&req->list); - goto restart; - } - ret = atomic_dec_return(&async_list->cnt); - } } -out: - if (cur_mm) { - set_fs(old_fs); - unuse_mm(cur_mm); - mmput(cur_mm); - } -} + /* async context always use a copy of the sqe */ + kfree(sqe); -/* - * See if we can piggy back onto previously submitted work, that is still - * running. We currently only allow this if the new request is sequential - * to the previous one we punted. - */ -static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) -{ - bool ret; - - if (!list) - return false; - if (!(req->flags & REQ_F_SEQ_PREV)) - return false; - if (!atomic_read(&list->cnt)) - return false; - - ret = true; - spin_lock(&list->lock); - list_add_tail(&req->list, &list->list); - /* - * Ensure we see a simultaneous modification from io_sq_wq_submit_work() - */ - smp_mb(); - if (!atomic_read(&list->cnt)) { - list_del_init(&req->list); - ret = false; + /* if a dependent link is ready, pass it back */ + if (!ret && nxt) { + io_prep_async_work(nxt); + *workptr = &nxt->work; } - spin_unlock(&list->lock); - return ret; } static bool io_op_needs_file(const struct io_uring_sqe *sqe) @@ -2247,15 +2653,29 @@ static bool io_op_needs_file(const struct io_uring_sqe *sqe) switch (op) { case IORING_OP_NOP: case IORING_OP_POLL_REMOVE: + case IORING_OP_TIMEOUT: + case IORING_OP_TIMEOUT_REMOVE: + case IORING_OP_ASYNC_CANCEL: + case IORING_OP_LINK_TIMEOUT: return false; default: return true; } } -static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, - struct io_submit_state *state, struct io_kiocb *req) +static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, + int index) { + struct fixed_file_table *table; + + table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT]; + return table->files[index & IORING_FILE_TABLE_MASK]; +} + +static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req) +{ + struct sqe_submit *s = &req->submit; + struct io_ring_ctx *ctx = req->ctx; unsigned flags; int fd; @@ -2275,14 +2695,18 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, return 0; if (flags & IOSQE_FIXED_FILE) { - if (unlikely(!ctx->user_files || + if (unlikely(!ctx->file_table || (unsigned) fd >= ctx->nr_user_files)) return -EBADF; - req->file = ctx->user_files[fd]; + fd = array_index_nospec(fd, ctx->nr_user_files); + req->file = io_file_from_index(ctx, fd); + if (!req->file) + return -EBADF; req->flags |= REQ_F_FIXED_FILE; } else { if (s->needs_fixed_file) return -EBADF; + trace_io_uring_file_get(ctx, fd); req->file = io_file_get(state, fd); if (unlikely(!req->file)) return -EBADF; @@ -2291,12 +2715,146 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, return 0; } -static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s, bool force_nonblock) +static int io_grab_files(struct io_kiocb *req) { + int ret = -EBADF; + struct io_ring_ctx *ctx = req->ctx; + + rcu_read_lock(); + spin_lock_irq(&ctx->inflight_lock); + /* + * We use the f_ops->flush() handler to ensure that we can flush + * out work accessing these files if the fd is closed. Check if + * the fd has changed since we started down this path, and disallow + * this operation if it has. + */ + if (fcheck(req->submit.ring_fd) == req->submit.ring_file) { + list_add(&req->inflight_entry, &ctx->inflight_list); + req->flags |= REQ_F_INFLIGHT; + req->work.files = current->files; + ret = 0; + } + spin_unlock_irq(&ctx->inflight_lock); + rcu_read_unlock(); + + return ret; +} + +static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) +{ + struct io_kiocb *req = container_of(timer, struct io_kiocb, + timeout.timer); + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *prev = NULL; + unsigned long flags; + + spin_lock_irqsave(&ctx->completion_lock, flags); + + /* + * We don't expect the list to be empty, that will only happen if we + * race with the completion of the linked work. + */ + if (!list_empty(&req->list)) { + prev = list_entry(req->list.prev, struct io_kiocb, link_list); + if (refcount_inc_not_zero(&prev->refs)) + list_del_init(&req->list); + else + prev = NULL; + } + + spin_unlock_irqrestore(&ctx->completion_lock, flags); + + if (prev) { + io_async_find_and_cancel(ctx, req, prev->user_data, NULL); + io_put_req(prev); + } else { + io_cqring_add_event(req, -ETIME); + io_put_req(req); + } + return HRTIMER_NORESTART; +} + +static void io_queue_linked_timeout(struct io_kiocb *req, struct timespec64 *ts, + enum hrtimer_mode *mode) +{ + struct io_ring_ctx *ctx = req->ctx; + + /* + * If the list is now empty, then our linked request finished before + * we got a chance to setup the timer + */ + spin_lock_irq(&ctx->completion_lock); + if (!list_empty(&req->list)) { + req->timeout.timer.function = io_link_timeout_fn; + hrtimer_start(&req->timeout.timer, timespec64_to_ktime(*ts), + *mode); + } + spin_unlock_irq(&ctx->completion_lock); + + /* drop submission reference */ + io_put_req(req); +} + +static int io_validate_link_timeout(const struct io_uring_sqe *sqe, + struct timespec64 *ts) +{ + if (sqe->ioprio || sqe->buf_index || sqe->len != 1 || sqe->off) + return -EINVAL; + if (sqe->timeout_flags & ~IORING_TIMEOUT_ABS) + return -EINVAL; + if (get_timespec64(ts, u64_to_user_ptr(sqe->addr))) + return -EFAULT; + + return 0; +} + +static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req, + struct timespec64 *ts, + enum hrtimer_mode *mode) +{ + struct io_kiocb *nxt; int ret; - ret = __io_submit_sqe(ctx, req, s, force_nonblock); + if (!(req->flags & REQ_F_LINK)) + return NULL; + + nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, list); + if (!nxt || nxt->submit.sqe->opcode != IORING_OP_LINK_TIMEOUT) + return NULL; + + ret = io_validate_link_timeout(nxt->submit.sqe, ts); + if (ret) { + list_del_init(&nxt->list); + io_cqring_add_event(nxt, ret); + io_double_put_req(nxt); + return ERR_PTR(-ECANCELED); + } + + if (nxt->submit.sqe->timeout_flags & IORING_TIMEOUT_ABS) + *mode = HRTIMER_MODE_ABS; + else + *mode = HRTIMER_MODE_REL; + + req->flags |= REQ_F_LINK_TIMEOUT; + hrtimer_init(&nxt->timeout.timer, CLOCK_MONOTONIC, *mode); + return nxt; +} + +static int __io_queue_sqe(struct io_kiocb *req) +{ + enum hrtimer_mode mode; + struct io_kiocb *nxt; + struct timespec64 ts; + int ret; + + nxt = io_prep_linked_timeout(req, &ts, &mode); + if (IS_ERR(nxt)) { + ret = PTR_ERR(nxt); + nxt = NULL; + goto err; + } + + ret = __io_submit_sqe(req, NULL, true); /* * We async punt it if the file wasn't marked NOWAIT, or if the file @@ -2304,36 +2862,47 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, */ if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) || (req->flags & REQ_F_MUST_PUNT))) { + struct sqe_submit *s = &req->submit; struct io_uring_sqe *sqe_copy; sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL); if (sqe_copy) { - struct async_list *list; - s->sqe = sqe_copy; - memcpy(&req->submit, s, sizeof(*s)); - list = io_async_list_from_sqe(ctx, s->sqe); - if (!io_add_to_prev_work(list, req)) { - if (list) - atomic_inc(&list->cnt); - INIT_WORK(&req->work, io_sq_wq_submit_work); - io_queue_async_work(ctx, req); + if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) { + ret = io_grab_files(req); + if (ret) { + kfree(sqe_copy); + goto err; + } } /* * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ + io_queue_async_work(req); + + if (nxt) + io_queue_linked_timeout(nxt, &ts, &mode); + return 0; } } +err: /* drop submission reference */ io_put_req(req); + if (nxt) { + if (!ret) + io_queue_linked_timeout(nxt, &ts, &mode); + else + io_put_req(nxt); + } + /* and drop final reference, if we failed */ if (ret) { - io_cqring_add_event(ctx, req->user_data, ret); + io_cqring_add_event(req, ret); if (req->flags & REQ_F_LINK) req->flags |= REQ_F_FAIL_LINK; io_put_req(req); @@ -2342,32 +2911,30 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return ret; } -static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s, bool force_nonblock) +static int io_queue_sqe(struct io_kiocb *req) { int ret; - ret = io_req_defer(ctx, req, s->sqe); + ret = io_req_defer(req); if (ret) { if (ret != -EIOCBQUEUED) { - io_free_req(req); - io_cqring_add_event(ctx, s->sqe->user_data, ret); + io_cqring_add_event(req, ret); + io_double_put_req(req); } return 0; } - return __io_queue_sqe(ctx, req, s, force_nonblock); + return __io_queue_sqe(req); } -static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, - struct sqe_submit *s, struct io_kiocb *shadow, - bool force_nonblock) +static int io_queue_link_head(struct io_kiocb *req, struct io_kiocb *shadow) { int ret; int need_submit = false; + struct io_ring_ctx *ctx = req->ctx; if (!shadow) - return io_queue_sqe(ctx, req, s, force_nonblock); + return io_queue_sqe(req); /* * Mark the first IO in link list as DRAIN, let all the following @@ -2375,11 +2942,12 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, * list. */ req->flags |= REQ_F_IO_DRAIN; - ret = io_req_defer(ctx, req, s->sqe); + ret = io_req_defer(req); if (ret) { if (ret != -EIOCBQUEUED) { - io_free_req(req); - io_cqring_add_event(ctx, s->sqe->user_data, ret); + io_cqring_add_event(req, ret); + io_double_put_req(req); + __io_free_req(shadow); return 0; } } else { @@ -2392,43 +2960,39 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, /* Insert shadow req to defer_list, blocking next IOs */ spin_lock_irq(&ctx->completion_lock); + trace_io_uring_defer(ctx, shadow, true); list_add_tail(&shadow->list, &ctx->defer_list); spin_unlock_irq(&ctx->completion_lock); if (need_submit) - return __io_queue_sqe(ctx, req, s, force_nonblock); + return __io_queue_sqe(req); return 0; } #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK) -static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, - struct io_submit_state *state, struct io_kiocb **link, - bool force_nonblock) +static void io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state, + struct io_kiocb **link) { struct io_uring_sqe *sqe_copy; - struct io_kiocb *req; + struct sqe_submit *s = &req->submit; + struct io_ring_ctx *ctx = req->ctx; int ret; + req->user_data = s->sqe->user_data; + /* enforce forwards compatibility on users */ if (unlikely(s->sqe->flags & ~SQE_VALID_FLAGS)) { ret = -EINVAL; - goto err; - } - - req = io_get_req(ctx, state); - if (unlikely(!req)) { - ret = -EAGAIN; - goto err; + goto err_req; } - ret = io_req_set_file(ctx, s, state, req); + ret = io_req_set_file(state, req); if (unlikely(ret)) { err_req: - io_free_req(req); -err: - io_cqring_add_event(ctx, s->sqe->user_data, ret); + io_cqring_add_event(req, ret); + io_double_put_req(req); return; } @@ -2449,16 +3013,19 @@ err: } s->sqe = sqe_copy; - memcpy(&req->submit, s, sizeof(*s)); + trace_io_uring_link(ctx, req, prev); list_add_tail(&req->list, &prev->link_list); } else if (s->sqe->flags & IOSQE_IO_LINK) { req->flags |= REQ_F_LINK; - memcpy(&req->submit, s, sizeof(*s)); INIT_LIST_HEAD(&req->link_list); *link = req; + } else if (READ_ONCE(s->sqe->opcode) == IORING_OP_LINK_TIMEOUT) { + /* Only valid as a linked SQE */ + ret = -EINVAL; + goto err_req; } else { - io_queue_sqe(ctx, req, s, force_nonblock); + io_queue_sqe(req); } } @@ -2529,7 +3096,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) head = READ_ONCE(sq_array[head & ctx->sq_mask]); if (head < ctx->sq_entries) { - s->index = head; + s->ring_file = NULL; s->sqe = &ctx->sq_sqes[head]; s->sequence = ctx->cached_sq_head; ctx->cached_sq_head++; @@ -2538,18 +3105,25 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) /* drop invalid entries */ ctx->cached_sq_head++; - rings->sq_dropped++; + ctx->cached_sq_dropped++; + WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped); return false; } -static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, - unsigned int nr, bool has_user, bool mm_fault) +static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, + struct file *ring_file, int ring_fd, + struct mm_struct **mm, bool async) { struct io_submit_state state, *statep = NULL; struct io_kiocb *link = NULL; struct io_kiocb *shadow_req = NULL; - bool prev_was_link = false; int i, submitted = 0; + bool mm_fault = false; + + if (!list_empty(&ctx->cq_overflow_list)) { + io_cqring_overflow_flush(ctx, false); + return -EBUSY; + } if (nr > IO_PLUG_THRESHOLD) { io_submit_state_start(&state, ctx, nr); @@ -2557,19 +3131,31 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, } for (i = 0; i < nr; i++) { - /* - * If previous wasn't linked and we have a linked command, - * that's the end of the chain. Submit the previous link. - */ - if (!prev_was_link && link) { - io_queue_link_head(ctx, link, &link->submit, shadow_req, - true); - link = NULL; - shadow_req = NULL; + struct io_kiocb *req; + unsigned int sqe_flags; + + req = io_get_req(ctx, statep); + if (unlikely(!req)) { + if (!submitted) + submitted = -EAGAIN; + break; + } + if (!io_get_sqring(ctx, &req->submit)) { + __io_free_req(req); + break; + } + + if (io_sqe_needs_user(req->submit.sqe) && !*mm) { + mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm); + if (!mm_fault) { + use_mm(ctx->sqo_mm); + *mm = ctx->sqo_mm; + } } - prev_was_link = (sqes[i].sqe->flags & IOSQE_IO_LINK) != 0; - if (link && (sqes[i].sqe->flags & IOSQE_IO_DRAIN)) { + sqe_flags = req->submit.sqe->flags; + + if (link && (sqe_flags & IOSQE_IO_DRAIN)) { if (!shadow_req) { shadow_req = io_get_req(ctx, NULL); if (unlikely(!shadow_req)) @@ -2577,55 +3163,79 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN); refcount_dec(&shadow_req->refs); } - shadow_req->sequence = sqes[i].sequence; + shadow_req->sequence = req->submit.sequence; } out: - if (unlikely(mm_fault)) { - io_cqring_add_event(ctx, sqes[i].sqe->user_data, - -EFAULT); - } else { - sqes[i].has_user = has_user; - sqes[i].needs_lock = true; - sqes[i].needs_fixed_file = true; - io_submit_sqe(ctx, &sqes[i], statep, &link, true); - submitted++; + req->submit.ring_file = ring_file; + req->submit.ring_fd = ring_fd; + req->submit.has_user = *mm != NULL; + req->submit.in_async = async; + req->submit.needs_fixed_file = async; + trace_io_uring_submit_sqe(ctx, req->submit.sqe->user_data, + true, async); + io_submit_sqe(req, statep, &link); + submitted++; + + /* + * If previous wasn't linked and we have a linked command, + * that's the end of the chain. Submit the previous link. + */ + if (!(sqe_flags & IOSQE_IO_LINK) && link) { + io_queue_link_head(link, shadow_req); + link = NULL; + shadow_req = NULL; } } if (link) - io_queue_link_head(ctx, link, &link->submit, shadow_req, true); + io_queue_link_head(link, shadow_req); if (statep) io_submit_state_end(&state); + /* Commit SQ ring head once we've consumed and submitted all SQEs */ + io_commit_sqring(ctx); + return submitted; } static int io_sq_thread(void *data) { - struct sqe_submit sqes[IO_IOPOLL_BATCH]; struct io_ring_ctx *ctx = data; struct mm_struct *cur_mm = NULL; mm_segment_t old_fs; DEFINE_WAIT(wait); unsigned inflight; unsigned long timeout; + int ret; - complete(&ctx->sqo_thread_started); + complete(&ctx->completions[1]); old_fs = get_fs(); set_fs(USER_DS); - timeout = inflight = 0; + ret = timeout = inflight = 0; while (!kthread_should_park()) { - bool all_fixed, mm_fault = false; - int i; + unsigned int to_submit; if (inflight) { unsigned nr_events = 0; if (ctx->flags & IORING_SETUP_IOPOLL) { - io_iopoll_check(ctx, &nr_events, 0); + /* + * inflight is the count of the maximum possible + * entries we submitted, but it can be smaller + * if we dropped some of them. If we don't have + * poll entries available, then we know that we + * have nothing left to poll for. Reset the + * inflight count to zero in that case. + */ + mutex_lock(&ctx->uring_lock); + if (!list_empty(&ctx->poll_list)) + __io_iopoll_check(ctx, &nr_events, 0); + else + inflight = 0; + mutex_unlock(&ctx->uring_lock); } else { /* * Normal IO, just pretend everything completed. @@ -2639,13 +3249,22 @@ static int io_sq_thread(void *data) timeout = jiffies + ctx->sq_thread_idle; } - if (!io_get_sqring(ctx, &sqes[0])) { + to_submit = io_sqring_entries(ctx); + + /* + * If submit got -EBUSY, flag us as needing the application + * to enter the kernel to reap and flush events. + */ + if (!to_submit || ret == -EBUSY) { /* * We're polling. If we're within the defined idle * period, then let us spin without work before going - * to sleep. + * to sleep. The exception is if we got EBUSY doing + * more IO, we should wait for the application to + * reap events and wake us up. */ - if (inflight || !time_after(jiffies, timeout)) { + if (inflight || + (!time_after(jiffies, timeout) && ret != -EBUSY)) { cond_resched(); continue; } @@ -2670,7 +3289,8 @@ static int io_sq_thread(void *data) /* make sure to read SQ tail after writing flags */ smp_mb(); - if (!io_get_sqring(ctx, &sqes[0])) { + to_submit = io_sqring_entries(ctx); + if (!to_submit || ret == -EBUSY) { if (kthread_should_park()) { finish_wait(&ctx->sqo_wait, &wait); break; @@ -2688,31 +3308,10 @@ static int io_sq_thread(void *data) ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; } - i = 0; - all_fixed = true; - do { - if (all_fixed && io_sqe_needs_user(sqes[i].sqe)) - all_fixed = false; - - i++; - if (i == ARRAY_SIZE(sqes)) - break; - } while (io_get_sqring(ctx, &sqes[i])); - - /* Unless all new commands are FIXED regions, grab mm */ - if (!all_fixed && !cur_mm) { - mm_fault = !mmget_not_zero(ctx->sqo_mm); - if (!mm_fault) { - use_mm(ctx->sqo_mm); - cur_mm = ctx->sqo_mm; - } - } - - inflight += io_submit_sqes(ctx, sqes, i, cur_mm != NULL, - mm_fault); - - /* Commit SQ ring head once we've consumed all SQEs */ - io_commit_sqring(ctx); + to_submit = min(to_submit, ctx->sq_entries); + ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true); + if (ret > 0) + inflight += ret; } set_fs(old_fs); @@ -2726,79 +3325,6 @@ static int io_sq_thread(void *data) return 0; } -static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit, - bool block_for_last) -{ - struct io_submit_state state, *statep = NULL; - struct io_kiocb *link = NULL; - struct io_kiocb *shadow_req = NULL; - bool prev_was_link = false; - int i, submit = 0; - - if (to_submit > IO_PLUG_THRESHOLD) { - io_submit_state_start(&state, ctx, to_submit); - statep = &state; - } - - for (i = 0; i < to_submit; i++) { - bool force_nonblock = true; - struct sqe_submit s; - - if (!io_get_sqring(ctx, &s)) - break; - - /* - * If previous wasn't linked and we have a linked command, - * that's the end of the chain. Submit the previous link. - */ - if (!prev_was_link && link) { - io_queue_link_head(ctx, link, &link->submit, shadow_req, - force_nonblock); - link = NULL; - shadow_req = NULL; - } - prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0; - - if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) { - if (!shadow_req) { - shadow_req = io_get_req(ctx, NULL); - if (unlikely(!shadow_req)) - goto out; - shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN); - refcount_dec(&shadow_req->refs); - } - shadow_req->sequence = s.sequence; - } - -out: - s.has_user = true; - s.needs_lock = false; - s.needs_fixed_file = false; - submit++; - - /* - * The caller will block for events after submit, submit the - * last IO non-blocking. This is either the only IO it's - * submitting, or it already submitted the previous ones. This - * improves performance by avoiding an async punt that we don't - * need to do. - */ - if (block_for_last && submit == to_submit) - force_nonblock = false; - - io_submit_sqe(ctx, &s, statep, &link, force_nonblock); - } - io_commit_sqring(ctx); - - if (link) - io_queue_link_head(ctx, link, &link->submit, shadow_req, - !block_for_last); - if (statep) - io_submit_state_end(statep); - - return submit; -} - struct io_wait_queue { struct wait_queue_entry wq; struct io_ring_ctx *ctx; @@ -2806,7 +3332,7 @@ struct io_wait_queue { unsigned nr_timeouts; }; -static inline bool io_should_wake(struct io_wait_queue *iowq) +static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) { struct io_ring_ctx *ctx = iowq->ctx; @@ -2815,7 +3341,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq) * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ - return io_cqring_events(ctx->rings) >= iowq->to_wait || + return io_cqring_events(ctx, noflush) >= iowq->to_wait || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } @@ -2825,7 +3351,8 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq); - if (!io_should_wake(iowq)) + /* use noflush == true, as we can't safely rely on locking context */ + if (!io_should_wake(iowq, true)) return -1; return autoremove_wake_function(curr, mode, wake_flags, key); @@ -2848,9 +3375,9 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, .to_wait = min_events, }; struct io_rings *rings = ctx->rings; - int ret; + int ret = 0; - if (io_cqring_events(rings) >= min_events) + if (io_cqring_events(ctx, false) >= min_events) return 0; if (sig) { @@ -2866,24 +3393,22 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } - ret = 0; iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); + trace_io_uring_cqring_wait(ctx, min_events); do { prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, TASK_INTERRUPTIBLE); - if (io_should_wake(&iowq)) + if (io_should_wake(&iowq, false)) break; schedule(); if (signal_pending(current)) { - ret = -ERESTARTSYS; + ret = -EINTR; break; } } while (1); finish_wait(&ctx->wait, &iowq.wq); - restore_saved_sigmask_unless(ret == -ERESTARTSYS); - if (ret == -ERESTARTSYS) - ret = -EINTR; + restore_saved_sigmask_unless(ret == -EINTR); return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } @@ -2901,19 +3426,29 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) #else int i; - for (i = 0; i < ctx->nr_user_files; i++) - fput(ctx->user_files[i]); + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file; + + file = io_file_from_index(ctx, i); + if (file) + fput(file); + } #endif } static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { - if (!ctx->user_files) + unsigned nr_tables, i; + + if (!ctx->file_table) return -ENXIO; __io_sqe_files_unregister(ctx); - kfree(ctx->user_files); - ctx->user_files = NULL; + nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); + for (i = 0; i < nr_tables; i++) + kfree(ctx->file_table[i].files); + kfree(ctx->file_table); + ctx->file_table = NULL; ctx->nr_user_files = 0; return 0; } @@ -2921,7 +3456,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) static void io_sq_thread_stop(struct io_ring_ctx *ctx) { if (ctx->sqo_thread) { - wait_for_completion(&ctx->sqo_thread_started); + wait_for_completion(&ctx->completions[1]); /* * The park is a bit of a work-around, without it we get * warning spews on shutdown with SQPOLL set and affinity @@ -2935,15 +3470,11 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx) static void io_finish_async(struct io_ring_ctx *ctx) { - int i; - io_sq_thread_stop(ctx); - for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) { - if (ctx->sqo_wq[i]) { - destroy_workqueue(ctx->sqo_wq[i]); - ctx->sqo_wq[i] = NULL; - } + if (ctx->io_wq) { + io_wq_destroy(ctx->io_wq); + ctx->io_wq = NULL; } } @@ -2951,11 +3482,9 @@ static void io_finish_async(struct io_ring_ctx *ctx) static void io_destruct_skb(struct sk_buff *skb) { struct io_ring_ctx *ctx = skb->sk->sk_user_data; - int i; - for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) - if (ctx->sqo_wq[i]) - flush_workqueue(ctx->sqo_wq[i]); + if (ctx->io_wq) + io_wq_flush(ctx->io_wq); unix_destruct_scm(skb); } @@ -2970,7 +3499,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) struct sock *sk = ctx->ring_sock->sk; struct scm_fp_list *fpl; struct sk_buff *skb; - int i; + int i, nr_files; if (!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { unsigned long inflight = ctx->user->unix_inflight + nr; @@ -2990,21 +3519,33 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) } skb->sk = sk; - skb->destructor = io_destruct_skb; + nr_files = 0; fpl->user = get_uid(ctx->user); for (i = 0; i < nr; i++) { - fpl->fp[i] = get_file(ctx->user_files[i + offset]); - unix_inflight(fpl->user, fpl->fp[i]); + struct file *file = io_file_from_index(ctx, i + offset); + + if (!file) + continue; + fpl->fp[nr_files] = get_file(file); + unix_inflight(fpl->user, fpl->fp[nr_files]); + nr_files++; } - fpl->max = fpl->count = nr; - UNIXCB(skb).fp = fpl; - refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_queue_head(&sk->sk_receive_queue, skb); + if (nr_files) { + fpl->max = SCM_MAX_FD; + fpl->count = nr_files; + UNIXCB(skb).fp = fpl; + skb->destructor = io_destruct_skb; + refcount_add(skb->truesize, &sk->sk_wmem_alloc); + skb_queue_head(&sk->sk_receive_queue, skb); - for (i = 0; i < nr; i++) - fput(fpl->fp[i]); + for (i = 0; i < nr_files; i++) + fput(fpl->fp[i]); + } else { + kfree_skb(skb); + kfree(fpl); + } return 0; } @@ -3035,7 +3576,10 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) return 0; while (total < ctx->nr_user_files) { - fput(ctx->user_files[total]); + struct file *file = io_file_from_index(ctx, total); + + if (file) + fput(file); total++; } @@ -3048,33 +3592,79 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) } #endif +static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables, + unsigned nr_files) +{ + int i; + + for (i = 0; i < nr_tables; i++) { + struct fixed_file_table *table = &ctx->file_table[i]; + unsigned this_files; + + this_files = min(nr_files, IORING_MAX_FILES_TABLE); + table->files = kcalloc(this_files, sizeof(struct file *), + GFP_KERNEL); + if (!table->files) + break; + nr_files -= this_files; + } + + if (i == nr_tables) + return 0; + + for (i = 0; i < nr_tables; i++) { + struct fixed_file_table *table = &ctx->file_table[i]; + kfree(table->files); + } + return 1; +} + static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { __s32 __user *fds = (__s32 __user *) arg; + unsigned nr_tables; int fd, ret = 0; unsigned i; - if (ctx->user_files) + if (ctx->file_table) return -EBUSY; if (!nr_args) return -EINVAL; if (nr_args > IORING_MAX_FIXED_FILES) return -EMFILE; - ctx->user_files = kcalloc(nr_args, sizeof(struct file *), GFP_KERNEL); - if (!ctx->user_files) + nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE); + ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table), + GFP_KERNEL); + if (!ctx->file_table) return -ENOMEM; - for (i = 0; i < nr_args; i++) { + if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) { + kfree(ctx->file_table); + ctx->file_table = NULL; + return -ENOMEM; + } + + for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { + struct fixed_file_table *table; + unsigned index; + ret = -EFAULT; if (copy_from_user(&fd, &fds[i], sizeof(fd))) break; + /* allow sparse sets */ + if (fd == -1) { + ret = 0; + continue; + } - ctx->user_files[i] = fget(fd); + table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT]; + index = i & IORING_FILE_TABLE_MASK; + table->files[index] = fget(fd); ret = -EBADF; - if (!ctx->user_files[i]) + if (!table->files[index]) break; /* * Don't allow io_uring instances to be registered. If UNIX @@ -3083,20 +3673,26 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, * handle it just fine, but there's still no point in allowing * a ring fd as it doesn't support regular read/write anyway. */ - if (ctx->user_files[i]->f_op == &io_uring_fops) { - fput(ctx->user_files[i]); + if (table->files[index]->f_op == &io_uring_fops) { + fput(table->files[index]); break; } - ctx->nr_user_files++; ret = 0; } if (ret) { - for (i = 0; i < ctx->nr_user_files; i++) - fput(ctx->user_files[i]); + for (i = 0; i < ctx->nr_user_files; i++) { + struct file *file; + + file = io_file_from_index(ctx, i); + if (file) + fput(file); + } + for (i = 0; i < nr_tables; i++) + kfree(ctx->file_table[i].files); - kfree(ctx->user_files); - ctx->user_files = NULL; + kfree(ctx->file_table); + ctx->file_table = NULL; ctx->nr_user_files = 0; return ret; } @@ -3108,9 +3704,201 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return ret; } +static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index) +{ +#if defined(CONFIG_UNIX) + struct file *file = io_file_from_index(ctx, index); + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff_head list, *head = &sock->sk_receive_queue; + struct sk_buff *skb; + int i; + + __skb_queue_head_init(&list); + + /* + * Find the skb that holds this file in its SCM_RIGHTS. When found, + * remove this entry and rearrange the file array. + */ + skb = skb_dequeue(head); + while (skb) { + struct scm_fp_list *fp; + + fp = UNIXCB(skb).fp; + for (i = 0; i < fp->count; i++) { + int left; + + if (fp->fp[i] != file) + continue; + + unix_notinflight(fp->user, fp->fp[i]); + left = fp->count - 1 - i; + if (left) { + memmove(&fp->fp[i], &fp->fp[i + 1], + left * sizeof(struct file *)); + } + fp->count--; + if (!fp->count) { + kfree_skb(skb); + skb = NULL; + } else { + __skb_queue_tail(&list, skb); + } + fput(file); + file = NULL; + break; + } + + if (!file) + break; + + __skb_queue_tail(&list, skb); + + skb = skb_dequeue(head); + } + + if (skb_peek(&list)) { + spin_lock_irq(&head->lock); + while ((skb = __skb_dequeue(&list)) != NULL) + __skb_queue_tail(head, skb); + spin_unlock_irq(&head->lock); + } +#else + fput(io_file_from_index(ctx, index)); +#endif +} + +static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, + int index) +{ +#if defined(CONFIG_UNIX) + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff_head *head = &sock->sk_receive_queue; + struct sk_buff *skb; + + /* + * See if we can merge this file into an existing skb SCM_RIGHTS + * file set. If there's no room, fall back to allocating a new skb + * and filling it in. + */ + spin_lock_irq(&head->lock); + skb = skb_peek(head); + if (skb) { + struct scm_fp_list *fpl = UNIXCB(skb).fp; + + if (fpl->count < SCM_MAX_FD) { + __skb_unlink(skb, head); + spin_unlock_irq(&head->lock); + fpl->fp[fpl->count] = get_file(file); + unix_inflight(fpl->user, fpl->fp[fpl->count]); + fpl->count++; + spin_lock_irq(&head->lock); + __skb_queue_head(head, skb); + } else { + skb = NULL; + } + } + spin_unlock_irq(&head->lock); + + if (skb) { + fput(file); + return 0; + } + + return __io_sqe_files_scm(ctx, 1, index); +#else + return 0; +#endif +} + +static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_files_update up; + __s32 __user *fds; + int fd, i, err; + __u32 done; + + if (!ctx->file_table) + return -ENXIO; + if (!nr_args) + return -EINVAL; + if (copy_from_user(&up, arg, sizeof(up))) + return -EFAULT; + if (check_add_overflow(up.offset, nr_args, &done)) + return -EOVERFLOW; + if (done > ctx->nr_user_files) + return -EINVAL; + + done = 0; + fds = (__s32 __user *) up.fds; + while (nr_args) { + struct fixed_file_table *table; + unsigned index; + + err = 0; + if (copy_from_user(&fd, &fds[done], sizeof(fd))) { + err = -EFAULT; + break; + } + i = array_index_nospec(up.offset, ctx->nr_user_files); + table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT]; + index = i & IORING_FILE_TABLE_MASK; + if (table->files[index]) { + io_sqe_file_unregister(ctx, i); + table->files[index] = NULL; + } + if (fd != -1) { + struct file *file; + + file = fget(fd); + if (!file) { + err = -EBADF; + break; + } + /* + * Don't allow io_uring instances to be registered. If + * UNIX isn't enabled, then this causes a reference + * cycle and this instance can never get freed. If UNIX + * is enabled we'll handle it just fine, but there's + * still no point in allowing a ring fd as it doesn't + * support regular read/write anyway. + */ + if (file->f_op == &io_uring_fops) { + fput(file); + err = -EBADF; + break; + } + table->files[index] = file; + err = io_sqe_file_register(ctx, file, i); + if (err) + break; + } + nr_args--; + done++; + up.offset++; + } + + return done ? done : err; +} + +static void io_put_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + io_put_req(req); +} + +static void io_get_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + refcount_inc(&req->refs); +} + static int io_sq_offload_start(struct io_ring_ctx *ctx, struct io_uring_params *p) { + unsigned concurrency; int ret; init_waitqueue_head(&ctx->sqo_wait); @@ -3154,26 +3942,13 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, goto err; } - /* Do QD, or 2 * CPUS, whatever is smallest */ - ctx->sqo_wq[0] = alloc_workqueue("io_ring-wq", - WQ_UNBOUND | WQ_FREEZABLE, - min(ctx->sq_entries - 1, 2 * num_online_cpus())); - if (!ctx->sqo_wq[0]) { - ret = -ENOMEM; - goto err; - } - - /* - * This is for buffered writes, where we want to limit the parallelism - * due to file locking in file systems. As "normal" buffered writes - * should parellelize on writeout quite nicely, limit us to having 2 - * pending. This avoids massive contention on the inode when doing - * buffered async writes. - */ - ctx->sqo_wq[1] = alloc_workqueue("io_ring-write-wq", - WQ_UNBOUND | WQ_FREEZABLE, 2); - if (!ctx->sqo_wq[1]) { - ret = -ENOMEM; + /* Do QD, or 4 * CPUS, whatever is smallest */ + concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); + ctx->io_wq = io_wq_create(concurrency, ctx->sqo_mm, ctx->user, + io_get_work, io_put_work); + if (IS_ERR(ctx->io_wq)) { + ret = PTR_ERR(ctx->io_wq); + ctx->io_wq = NULL; goto err; } @@ -3519,6 +4294,8 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_unaccount_mem(ctx->user, ring_pages(ctx->sq_entries, ctx->cq_entries)); free_uid(ctx->user); + kfree(ctx->completions); + kmem_cache_free(req_cachep, ctx->fallback_req); kfree(ctx); } @@ -3557,8 +4334,15 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_kill_timeouts(ctx); io_poll_remove_all(ctx); + + if (ctx->io_wq) + io_wq_cancel_all(ctx->io_wq); + io_iopoll_reap_events(ctx); - wait_for_completion(&ctx->ctx_done); + /* if we failed setting up the ctx, we might not have any rings */ + if (ctx->rings) + io_cqring_overflow_flush(ctx, true); + wait_for_completion(&ctx->completions[0]); io_ring_ctx_free(ctx); } @@ -3571,6 +4355,53 @@ static int io_uring_release(struct inode *inode, struct file *file) return 0; } +static void io_uring_cancel_files(struct io_ring_ctx *ctx, + struct files_struct *files) +{ + struct io_kiocb *req; + DEFINE_WAIT(wait); + + while (!list_empty_careful(&ctx->inflight_list)) { + struct io_kiocb *cancel_req = NULL; + + spin_lock_irq(&ctx->inflight_lock); + list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { + if (req->work.files != files) + continue; + /* req is being completed, ignore */ + if (!refcount_inc_not_zero(&req->refs)) + continue; + cancel_req = req; + break; + } + if (cancel_req) + prepare_to_wait(&ctx->inflight_wait, &wait, + TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&ctx->inflight_lock); + + /* We need to keep going until we don't find a matching req */ + if (!cancel_req) + break; + + io_wq_cancel_work(ctx->io_wq, &cancel_req->work); + io_put_req(cancel_req); + schedule(); + } + finish_wait(&ctx->inflight_wait, &wait); +} + +static int io_uring_flush(struct file *file, void *data) +{ + struct io_ring_ctx *ctx = file->private_data; + + io_uring_cancel_files(ctx, data); + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) { + io_cqring_overflow_flush(ctx, true); + io_wq_cancel_all(ctx->io_wq); + } + return 0; +} + static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) { loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT; @@ -3632,25 +4463,20 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, */ ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { + if (!list_empty_careful(&ctx->cq_overflow_list)) + io_cqring_overflow_flush(ctx, false); if (flags & IORING_ENTER_SQ_WAKEUP) wake_up(&ctx->sqo_wait); submitted = to_submit; } else if (to_submit) { - bool block_for_last = false; + struct mm_struct *cur_mm; to_submit = min(to_submit, ctx->sq_entries); - - /* - * Allow last submission to block in a series, IFF the caller - * asked to wait for events and we don't currently have - * enough. This potentially avoids an async punt. - */ - if (to_submit == min_complete && - io_cqring_events(ctx->rings) < min_complete) - block_for_last = true; - mutex_lock(&ctx->uring_lock); - submitted = io_ring_submit(ctx, to_submit, block_for_last); + /* already have mm, so io_submit_sqes() won't try to grab it */ + cur_mm = ctx->sqo_mm; + submitted = io_submit_sqes(ctx, to_submit, f.file, fd, + &cur_mm, false); mutex_unlock(&ctx->uring_lock); } if (flags & IORING_ENTER_GETEVENTS) { @@ -3673,6 +4499,7 @@ out_fput: static const struct file_operations io_uring_fops = { .release = io_uring_release, + .flush = io_uring_flush, .mmap = io_uring_mmap, .poll = io_uring_poll, .fasync = io_uring_fasync, @@ -3772,10 +4599,23 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) * Use twice as many entries for the CQ ring. It's possible for the * application to drive a higher depth than the size of the SQ ring, * since the sqes are only used at submission time. This allows for - * some flexibility in overcommitting a bit. + * some flexibility in overcommitting a bit. If the application has + * set IORING_SETUP_CQSIZE, it will have passed in the desired number + * of CQ ring entries manually. */ p->sq_entries = roundup_pow_of_two(entries); - p->cq_entries = 2 * p->sq_entries; + if (p->flags & IORING_SETUP_CQSIZE) { + /* + * If IORING_SETUP_CQSIZE is set, we do the same roundup + * to a power-of-two, if it isn't already. We do NOT impose + * any cq vs sq ring sizing. + */ + if (p->cq_entries < p->sq_entries || p->cq_entries > IORING_MAX_CQ_ENTRIES) + return -EINVAL; + p->cq_entries = roundup_pow_of_two(p->cq_entries); + } else { + p->cq_entries = 2 * p->sq_entries; + } user = get_uid(current_user()); account_mem = !capable(CAP_IPC_LOCK); @@ -3809,10 +4649,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret) goto err; - ret = io_uring_get_fd(ctx); - if (ret < 0) - goto err; - memset(&p->sq_off, 0, sizeof(p->sq_off)); p->sq_off.head = offsetof(struct io_rings, sq.head); p->sq_off.tail = offsetof(struct io_rings, sq.tail); @@ -3830,7 +4666,16 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); - p->features = IORING_FEAT_SINGLE_MMAP; + /* + * Install ring fd as the very last thing, so we don't risk someone + * having closed it before we finish setup + */ + ret = io_uring_get_fd(ctx); + if (ret < 0) + goto err; + + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP; + trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: io_ring_ctx_wait_and_kill(ctx); @@ -3856,7 +4701,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) } if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | - IORING_SETUP_SQ_AFF)) + IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE)) return -EINVAL; ret = io_uring_create(entries, &p); @@ -3900,7 +4745,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, * no new references will come in after we've killed the percpu ref. */ mutex_unlock(&ctx->uring_lock); - wait_for_completion(&ctx->ctx_done); + wait_for_completion(&ctx->completions[0]); mutex_lock(&ctx->uring_lock); switch (opcode) { @@ -3922,6 +4767,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_sqe_files_unregister(ctx); break; + case IORING_REGISTER_FILES_UPDATE: + ret = io_sqe_files_update(ctx, arg, nr_args); + break; case IORING_REGISTER_EVENTFD: ret = -EINVAL; if (nr_args != 1) @@ -3940,7 +4788,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, } /* bring the ctx back to life */ - reinit_completion(&ctx->ctx_done); + reinit_completion(&ctx->completions[0]); percpu_ref_reinit(&ctx->refs); return ret; } @@ -3965,6 +4813,8 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, mutex_lock(&ctx->uring_lock); ret = __io_uring_register(ctx, opcode, arg, nr_args); mutex_unlock(&ctx->uring_lock); + trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, + ctx->cq_ev_fd != NULL, ret); out_fput: fdput(f); return ret; diff --git a/fs/namespace.c b/fs/namespace.c index fe0e9e1410fe..2adfe7b166a3 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2478,8 +2478,10 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount * time64_to_tm(sb->s_time_max, 0, &tm); - pr_warn("Mounted %s file system at %s supports timestamps until %04ld (0x%llx)\n", - sb->s_type->name, mntpath, + pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n", + sb->s_type->name, + is_mounted(mnt) ? "remounted" : "mounted", + mntpath, tm.tm_year+1900, (unsigned long long)sb->s_time_max); free_page((unsigned long)buf); @@ -2764,14 +2766,11 @@ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, if (IS_ERR(mnt)) return PTR_ERR(mnt); - error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags); - if (error < 0) { - mntput(mnt); - return error; - } - mnt_warn_timestamp_expiry(mountpoint, mnt); + error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags); + if (error < 0) + mntput(mnt); return error; } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 071b90a45933..af549d70ec50 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -53,6 +53,16 @@ nfs4_is_valid_delegation(const struct nfs_delegation *delegation, return false; } +struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode) +{ + struct nfs_delegation *delegation; + + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (nfs4_is_valid_delegation(delegation, 0)) + return delegation; + return NULL; +} + static int nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark) { @@ -1181,7 +1191,7 @@ bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode) if (delegation != NULL && nfs4_stateid_match_other(dst, &delegation->stateid)) { dst->seqid = delegation->stateid.seqid; - return ret; + ret = true; } rcu_read_unlock(); out: diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 9eb87ae4c982..8b14d441e699 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -68,6 +68,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred); bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode); +struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode); void nfs_mark_delegation_referenced(struct nfs_delegation *delegation); int nfs4_have_delegation(struct inode *inode, fmode_t flags); int nfs4_check_delegation(struct inode *inode, fmode_t flags); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ab8ca20fd579..caacf5e7f5e1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1440,8 +1440,6 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode, return 0; if ((delegation->type & fmode) != fmode) return 0; - if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) - return 0; switch (claim) { case NFS4_OPEN_CLAIM_NULL: case NFS4_OPEN_CLAIM_FH: @@ -1810,7 +1808,6 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) { struct nfs4_state *state = opendata->state; - struct nfs_inode *nfsi = NFS_I(state->inode); struct nfs_delegation *delegation; int open_mode = opendata->o_arg.open_flags; fmode_t fmode = opendata->o_arg.fmode; @@ -1827,7 +1824,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) } spin_unlock(&state->owner->so_lock); rcu_read_lock(); - delegation = rcu_dereference(nfsi->delegation); + delegation = nfs4_get_valid_delegation(state->inode); if (!can_open_delegated(delegation, fmode, claim)) { rcu_read_unlock(); break; @@ -2371,7 +2368,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) data->o_arg.open_flags, claim)) goto out_no_action; rcu_read_lock(); - delegation = rcu_dereference(NFS_I(data->state->inode)->delegation); + delegation = nfs4_get_valid_delegation(data->state->inode); if (can_open_delegated(delegation, data->o_arg.fmode, claim)) goto unlock_no_action; rcu_read_unlock(); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 53939bf9d7d2..9876db52913a 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2098,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) return 0; } -static int ocfs2_prepare_inode_for_refcount(struct inode *inode, - struct file *file, - loff_t pos, size_t count, - int *meta_level) +static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, + struct buffer_head **di_bh, + int meta_level, + int overwrite_io, + int write_sem, + int wait) { - int ret; - struct buffer_head *di_bh = NULL; - u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; - u32 clusters = - ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos; + int ret = 0; - ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (ret) { - mlog_errno(ret); + if (wait) + ret = ocfs2_inode_lock(inode, NULL, meta_level); + else + ret = ocfs2_try_inode_lock(inode, + overwrite_io ? NULL : di_bh, meta_level); + if (ret < 0) goto out; + + if (wait) { + if (write_sem) + down_write(&OCFS2_I(inode)->ip_alloc_sem); + else + down_read(&OCFS2_I(inode)->ip_alloc_sem); + } else { + if (write_sem) + ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem); + else + ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem); + + if (!ret) { + ret = -EAGAIN; + goto out_unlock; + } } - *meta_level = 1; + return ret; - ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); - if (ret) - mlog_errno(ret); +out_unlock: + brelse(*di_bh); + ocfs2_inode_unlock(inode, meta_level); out: - brelse(di_bh); return ret; } +static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode, + struct buffer_head **di_bh, + int meta_level, + int write_sem) +{ + if (write_sem) + up_write(&OCFS2_I(inode)->ip_alloc_sem); + else + up_read(&OCFS2_I(inode)->ip_alloc_sem); + + brelse(*di_bh); + *di_bh = NULL; + + if (meta_level >= 0) + ocfs2_inode_unlock(inode, meta_level); +} + static int ocfs2_prepare_inode_for_write(struct file *file, loff_t pos, size_t count, int wait) { int ret = 0, meta_level = 0, overwrite_io = 0; + int write_sem = 0; struct dentry *dentry = file->f_path.dentry; struct inode *inode = d_inode(dentry); struct buffer_head *di_bh = NULL; + u32 cpos; + u32 clusters; /* * We start with a read level meta lock and only jump to an ex * if we need to make modifications here. */ for(;;) { - if (wait) - ret = ocfs2_inode_lock(inode, NULL, meta_level); - else - ret = ocfs2_try_inode_lock(inode, - overwrite_io ? NULL : &di_bh, meta_level); + ret = ocfs2_inode_lock_for_extent_tree(inode, + &di_bh, + meta_level, + overwrite_io, + write_sem, + wait); if (ret < 0) { - meta_level = -1; if (ret != -EAGAIN) mlog_errno(ret); goto out; @@ -2156,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file, */ if (!wait && !overwrite_io) { overwrite_io = 1; - if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { - ret = -EAGAIN; - goto out_unlock; - } ret = ocfs2_overwrite_io(inode, di_bh, pos, count); - brelse(di_bh); - di_bh = NULL; - up_read(&OCFS2_I(inode)->ip_alloc_sem); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); @@ -2183,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file, * set inode->i_size at the end of a write. */ if (should_remove_suid(dentry)) { if (meta_level == 0) { - ocfs2_inode_unlock(inode, meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); meta_level = 1; continue; } @@ -2197,18 +2229,32 @@ static int ocfs2_prepare_inode_for_write(struct file *file, ret = ocfs2_check_range_for_refcount(inode, pos, count); if (ret == 1) { - ocfs2_inode_unlock(inode, meta_level); - meta_level = -1; - - ret = ocfs2_prepare_inode_for_refcount(inode, - file, - pos, - count, - &meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); + ret = ocfs2_inode_lock_for_extent_tree(inode, + &di_bh, + meta_level, + overwrite_io, + 1, + wait); + write_sem = 1; + if (ret < 0) { + if (ret != -EAGAIN) + mlog_errno(ret); + goto out; + } + + cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; + clusters = + ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos; + ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); } if (ret < 0) { - mlog_errno(ret); + if (ret != -EAGAIN) + mlog_errno(ret); goto out_unlock; } @@ -2219,10 +2265,10 @@ out_unlock: trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno, pos, count, wait); - brelse(di_bh); - - if (meta_level >= 0) - ocfs2_inode_unlock(inode, meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); out: return ret; diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index d8507972ee13..90c830e3758e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1490,6 +1490,18 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc, return loc->xl_ops->xlo_check_space(loc, xi); } +static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash) +{ + loc->xl_ops->xlo_add_entry(loc, name_hash); + loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash); + /* + * We can't leave the new entry's xe_name_offset at zero or + * add_namevalue() will go nuts. We set it to the size of our + * storage so that it can never be less than any other entry. + */ + loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size); +} + static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc, struct ocfs2_xattr_info *xi) { @@ -2121,31 +2133,29 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc, if (rc) goto out; - if (!loc->xl_entry) { - rc = -EINVAL; - goto out; - } - - if (ocfs2_xa_can_reuse_entry(loc, xi)) { - orig_value_size = loc->xl_entry->xe_value_size; - rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); - if (rc) - goto out; - goto alloc_value; - } + if (loc->xl_entry) { + if (ocfs2_xa_can_reuse_entry(loc, xi)) { + orig_value_size = loc->xl_entry->xe_value_size; + rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); + if (rc) + goto out; + goto alloc_value; + } - if (!ocfs2_xattr_is_local(loc->xl_entry)) { - orig_clusters = ocfs2_xa_value_clusters(loc); - rc = ocfs2_xa_value_truncate(loc, 0, ctxt); - if (rc) { - mlog_errno(rc); - ocfs2_xa_cleanup_value_truncate(loc, - "overwriting", - orig_clusters); - goto out; + if (!ocfs2_xattr_is_local(loc->xl_entry)) { + orig_clusters = ocfs2_xa_value_clusters(loc); + rc = ocfs2_xa_value_truncate(loc, 0, ctxt); + if (rc) { + mlog_errno(rc); + ocfs2_xa_cleanup_value_truncate(loc, + "overwriting", + orig_clusters); + goto out; + } } - } - ocfs2_xa_wipe_namevalue(loc); + ocfs2_xa_wipe_namevalue(loc); + } else + ocfs2_xa_add_entry(loc, name_hash); /* * If we get here, we have a blank entry. Fill it. We grow our diff --git a/fs/open.c b/fs/open.c index b62f5c0923a8..5c68282ea79e 100644 --- a/fs/open.c +++ b/fs/open.c @@ -771,10 +771,6 @@ static int do_dentry_open(struct file *f, f->f_mode |= FMODE_WRITER; } - /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) - f->f_mode |= FMODE_ATOMIC_POS; - f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; @@ -1256,7 +1252,7 @@ EXPORT_SYMBOL(nonseekable_open); */ int stream_open(struct inode *inode, struct file *filp) { - filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); filp->f_mode |= FMODE_STREAM; return 0; } diff --git a/fs/pipe.c b/fs/pipe.c index 8a2ab2f974bd..a9149199e0e7 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -793,6 +793,8 @@ int create_pipe_files(struct file **res, int flags) } res[0]->private_data = inode->i_pipe; res[1] = f; + stream_open(inode, res[0]); + stream_open(inode, res[1]); return 0; } @@ -931,9 +933,9 @@ static int fifo_open(struct inode *inode, struct file *filp) __pipe_lock(pipe); /* We can only do regular read/write on fifos */ - filp->f_mode &= (FMODE_READ | FMODE_WRITE); + stream_open(inode, filp); - switch (filp->f_mode) { + switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY diff --git a/include/Kbuild b/include/Kbuild index ffba79483cc5..95508049ee51 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -65,7 +65,6 @@ header-test- += keys/asymmetric-subtype.h header-test- += keys/asymmetric-type.h header-test- += keys/big_key-type.h header-test- += keys/request_key_auth-type.h -header-test- += keys/trusted.h header-test- += kvm/arm_arch_timer.h header-test- += kvm/arm_pmu.h header-test-$(CONFIG_ARM) += kvm/arm_psci.h @@ -1028,6 +1027,7 @@ header-test- += trace/events/fsi_master_gpio.h header-test- += trace/events/huge_memory.h header-test- += trace/events/ib_mad.h header-test- += trace/events/ib_umad.h +header-test- += trace/events/io_uring.h header-test- += trace/events/iscsi.h header-test- += trace/events/jbd2.h header-test- += trace/events/kvm.h diff --git a/include/acpi/processor.h b/include/acpi/processor.h index f936033cb9e6..47805172e73d 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -232,8 +232,8 @@ struct acpi_processor { struct acpi_processor_limit limit; struct thermal_cooling_device *cdev; struct device *dev; /* Processor device. */ - struct dev_pm_qos_request perflib_req; - struct dev_pm_qos_request thermal_req; + struct freq_qos_request perflib_req; + struct freq_qos_request thermal_req; }; struct acpi_processor_errata { @@ -302,8 +302,8 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx #ifdef CONFIG_CPU_FREQ extern bool acpi_processor_cpufreq_init; void acpi_processor_ignore_ppc_init(void); -void acpi_processor_ppc_init(int cpu); -void acpi_processor_ppc_exit(int cpu); +void acpi_processor_ppc_init(struct cpufreq_policy *policy); +void acpi_processor_ppc_exit(struct cpufreq_policy *policy); void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag); extern int acpi_processor_get_bios_limit(int cpu, unsigned int *limit); #else @@ -311,11 +311,11 @@ static inline void acpi_processor_ignore_ppc_init(void) { return; } -static inline void acpi_processor_ppc_init(int cpu) +static inline void acpi_processor_ppc_init(struct cpufreq_policy *policy) { return; } -static inline void acpi_processor_ppc_exit(int cpu) +static inline void acpi_processor_ppc_exit(struct cpufreq_policy *policy) { return; } @@ -431,14 +431,14 @@ static inline int acpi_processor_hotplug(struct acpi_processor *pr) int acpi_processor_get_limit_info(struct acpi_processor *pr); extern const struct thermal_cooling_device_ops processor_cooling_ops; #if defined(CONFIG_ACPI_CPU_FREQ_PSS) & defined(CONFIG_CPU_FREQ) -void acpi_thermal_cpufreq_init(int cpu); -void acpi_thermal_cpufreq_exit(int cpu); +void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy); +void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy); #else -static inline void acpi_thermal_cpufreq_init(int cpu) +static inline void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy) { return; } -static inline void acpi_thermal_cpufreq_exit(int cpu) +static inline void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy) { return; } diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h index e94b19782c92..ce4103208619 100644 --- a/include/asm-generic/vdso/vsyscall.h +++ b/include/asm-generic/vdso/vsyscall.h @@ -25,13 +25,6 @@ static __always_inline int __arch_get_clock_mode(struct timekeeper *tk) } #endif /* __arch_get_clock_mode */ -#ifndef __arch_use_vsyscall -static __always_inline int __arch_use_vsyscall(struct vdso_data *vdata) -{ - return 1; -} -#endif /* __arch_use_vsyscall */ - #ifndef __arch_update_vsyscall static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk) diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 01f514521687..7865e6b5d36c 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -44,7 +44,20 @@ struct drm_gem_shmem_object { */ unsigned int pages_use_count; + /** + * @madv: State for madvise + * + * 0 is active/inuse. + * A negative value is the object is purged. + * Positive values are driver specific and not used by the helpers. + */ int madv; + + /** + * @madv_list: List entry for madvise tracking + * + * Typically used by drivers to track purgeable objects + */ struct list_head madv_list; /** diff --git a/include/drm/drm_self_refresh_helper.h b/include/drm/drm_self_refresh_helper.h index 5b79d253fb46..520235c20708 100644 --- a/include/drm/drm_self_refresh_helper.h +++ b/include/drm/drm_self_refresh_helper.h @@ -13,7 +13,8 @@ struct drm_crtc; void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state); void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state, - unsigned int commit_time_ms); + unsigned int commit_time_ms, + unsigned int new_self_refresh_mask); int drm_self_refresh_helper_init(struct drm_crtc *crtc); void drm_self_refresh_helper_cleanup(struct drm_crtc *crtc); diff --git a/include/keys/trusted.h b/include/keys/trusted_tpm.h index 0071298b9b28..a56d8e1298f2 100644 --- a/include/keys/trusted.h +++ b/include/keys/trusted_tpm.h @@ -1,14 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __TRUSTED_KEY_H -#define __TRUSTED_KEY_H +#ifndef __TRUSTED_TPM_H +#define __TRUSTED_TPM_H + +#include <keys/trusted-type.h> +#include <linux/tpm_command.h> /* implementation specific TPM constants */ #define MAX_BUF_SIZE 1024 #define TPM_GETRANDOM_SIZE 14 -#define TPM_OSAP_SIZE 36 -#define TPM_OIAP_SIZE 10 -#define TPM_SEAL_SIZE 87 -#define TPM_UNSEAL_SIZE 104 #define TPM_SIZE_OFFSET 2 #define TPM_RETURN_OFFSET 6 #define TPM_DATA_OFFSET 10 @@ -17,13 +16,6 @@ #define LOAD32N(buffer, offset) (*(uint32_t *)&buffer[offset]) #define LOAD16(buffer, offset) (ntohs(*(uint16_t *)&buffer[offset])) -struct tpm_buf { - int len; - unsigned char data[MAX_BUF_SIZE]; -}; - -#define INIT_BUF(tb) (tb->len = 0) - struct osapsess { uint32_t handle; unsigned char secret[SHA1_DIGEST_SIZE]; @@ -48,6 +40,13 @@ int TSS_checkhmac1(unsigned char *buffer, int trusted_tpm_send(unsigned char *cmd, size_t buflen); int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce); +int tpm2_seal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options); +int tpm2_unseal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options); + #define TPM_DEBUG 0 #if TPM_DEBUG @@ -109,28 +108,4 @@ static inline void dump_tpm_buf(unsigned char *buf) { } #endif - -static inline void store8(struct tpm_buf *buf, const unsigned char value) -{ - buf->data[buf->len++] = value; -} - -static inline void store16(struct tpm_buf *buf, const uint16_t value) -{ - *(uint16_t *) & buf->data[buf->len] = htons(value); - buf->len += sizeof value; -} - -static inline void store32(struct tpm_buf *buf, const uint32_t value) -{ - *(uint32_t *) & buf->data[buf->len] = htonl(value); - buf->len += sizeof value; -} - -static inline void storebytes(struct tpm_buf *buf, const unsigned char *in, - const int len) -{ - memcpy(buf->data + buf->len, in, len); - buf->len += len; -} #endif diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index bed9e43f9426..19394c77ed99 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -15,7 +15,9 @@ */ #include <linux/cgroup.h> +#include <linux/percpu.h> #include <linux/percpu_counter.h> +#include <linux/u64_stats_sync.h> #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> @@ -31,15 +33,12 @@ #ifdef CONFIG_BLK_CGROUP -enum blkg_rwstat_type { - BLKG_RWSTAT_READ, - BLKG_RWSTAT_WRITE, - BLKG_RWSTAT_SYNC, - BLKG_RWSTAT_ASYNC, - BLKG_RWSTAT_DISCARD, +enum blkg_iostat_type { + BLKG_IOSTAT_READ, + BLKG_IOSTAT_WRITE, + BLKG_IOSTAT_DISCARD, - BLKG_RWSTAT_NR, - BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, + BLKG_IOSTAT_NR, }; struct blkcg_gq; @@ -61,17 +60,15 @@ struct blkcg { #endif }; -/* - * blkg_[rw]stat->aux_cnt is excluded for local stats but included for - * recursive. Used to carry stats of dead children. - */ -struct blkg_rwstat { - struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; - atomic64_t aux_cnt[BLKG_RWSTAT_NR]; +struct blkg_iostat { + u64 bytes[BLKG_IOSTAT_NR]; + u64 ios[BLKG_IOSTAT_NR]; }; -struct blkg_rwstat_sample { - u64 cnt[BLKG_RWSTAT_NR]; +struct blkg_iostat_set { + struct u64_stats_sync sync; + struct blkg_iostat cur; + struct blkg_iostat last; }; /* @@ -127,8 +124,8 @@ struct blkcg_gq { /* is this blkg online? protected by both blkcg and q locks */ bool online; - struct blkg_rwstat stat_bytes; - struct blkg_rwstat stat_ios; + struct blkg_iostat_set __percpu *iostat_cpu; + struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; @@ -202,13 +199,6 @@ int blkcg_activate_policy(struct request_queue *q, void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol); -static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, - unsigned int idx) -{ - return atomic64_read(&rwstat->aux_cnt[idx]) + - percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); -} - const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, @@ -216,17 +206,6 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); -u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - const struct blkg_rwstat_sample *rwstat); -u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - int off); -int blkg_print_stat_bytes(struct seq_file *sf, void *v); -int blkg_print_stat_ios(struct seq_file *sf, void *v); -int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v); -int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v); - -void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, - int off, struct blkg_rwstat_sample *sum); struct blkg_conf_ctx { struct gendisk *disk; @@ -578,128 +557,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) -{ - int i, ret; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) { - ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); - if (ret) { - while (--i >= 0) - percpu_counter_destroy(&rwstat->cpu_cnt[i]); - return ret; - } - atomic64_set(&rwstat->aux_cnt[i], 0); - } - return 0; -} - -static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - percpu_counter_destroy(&rwstat->cpu_cnt[i]); -} - -/** - * blkg_rwstat_add - add a value to a blkg_rwstat - * @rwstat: target blkg_rwstat - * @op: REQ_OP and flags - * @val: value to add - * - * Add @val to @rwstat. The counters are chosen according to @rw. The - * caller is responsible for synchronizing calls to this function. - */ -static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, - unsigned int op, uint64_t val) -{ - struct percpu_counter *cnt; - - if (op_is_discard(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; - else if (op_is_write(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; - - percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); - - if (op_is_sync(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - - percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); -} - -/** - * blkg_rwstat_read - read the current values of a blkg_rwstat - * @rwstat: blkg_rwstat to read - * - * Read the current snapshot of @rwstat and return it in the aux counts. - */ -static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, - struct blkg_rwstat_sample *result) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - result->cnt[i] = - percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); -} - -/** - * blkg_rwstat_total - read the total count of a blkg_rwstat - * @rwstat: blkg_rwstat to read - * - * Return the total count of @rwstat regardless of the IO direction. This - * function can be called without synchronization and takes care of u64 - * atomicity. - */ -static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) -{ - struct blkg_rwstat_sample tmp = { }; - - blkg_rwstat_read(rwstat, &tmp); - return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; -} - -/** - * blkg_rwstat_reset - reset a blkg_rwstat - * @rwstat: blkg_rwstat to reset - */ -static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) { - percpu_counter_set(&rwstat->cpu_cnt[i], 0); - atomic64_set(&rwstat->aux_cnt[i], 0); - } -} - -/** - * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count - * @to: the destination blkg_rwstat - * @from: the source - * - * Add @from's count including the aux one to @to's aux count. - */ -static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, - struct blkg_rwstat *from) -{ - u64 sum[BLKG_RWSTAT_NR]; - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]), - &to->aux_cnt[i]); -} - #ifdef CONFIG_BLK_DEV_THROTTLING extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio); @@ -745,15 +602,33 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + struct blkg_iostat_set *bis; + int rwd, cpu; + + if (op_is_discard(bio->bi_opf)) + rwd = BLKG_IOSTAT_DISCARD; + else if (op_is_write(bio->bi_opf)) + rwd = BLKG_IOSTAT_WRITE; + else + rwd = BLKG_IOSTAT_READ; + + cpu = get_cpu(); + bis = per_cpu_ptr(blkg->iostat_cpu, cpu); + u64_stats_update_begin(&bis->sync); + /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the * size of the bio. */ if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, - bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); + bis->cur.bytes[rwd] += bio->bi_iter.bi_size; + bis->cur.ios[rwd]++; + + u64_stats_update_end(&bis->sync); + if (cgroup_subsys_on_dfl(io_cgrp_subsys)) + cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); + put_cpu(); } blkcg_bio_issue_init(bio); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 0bf056de5cc3..11cfd6470b1a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -10,103 +10,239 @@ struct blk_mq_tags; struct blk_flush_queue; /** - * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device + * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware + * block device */ struct blk_mq_hw_ctx { struct { + /** @lock: Protects the dispatch list. */ spinlock_t lock; + /** + * @dispatch: Used for requests that are ready to be + * dispatched to the hardware but for some reason (e.g. lack of + * resources) could not be sent to the hardware. As soon as the + * driver can send new requests, requests at this list will + * be sent first for a fairer dispatch. + */ struct list_head dispatch; - unsigned long state; /* BLK_MQ_S_* flags */ + /** + * @state: BLK_MQ_S_* flags. Defines the state of the hw + * queue (active, scheduled to restart, stopped). + */ + unsigned long state; } ____cacheline_aligned_in_smp; + /** + * @run_work: Used for scheduling a hardware queue run at a later time. + */ struct delayed_work run_work; + /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; + /** + * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU + * selection from @cpumask. + */ int next_cpu; + /** + * @next_cpu_batch: Counter of how many works left in the batch before + * changing to the next CPU. + */ int next_cpu_batch; - unsigned long flags; /* BLK_MQ_F_* flags */ + /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ + unsigned long flags; + /** + * @sched_data: Pointer owned by the IO scheduler attached to a request + * queue. It's up to the IO scheduler how to use this pointer. + */ void *sched_data; + /** + * @queue: Pointer to the request queue that owns this hardware context. + */ struct request_queue *queue; + /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; + /** + * @driver_data: Pointer to data owned by the block driver that created + * this hctx + */ void *driver_data; + /** + * @ctx_map: Bitmap for each software queue. If bit is on, there is a + * pending request in that software queue. + */ struct sbitmap ctx_map; + /** + * @dispatch_from: Software queue to be used when no scheduler was + * selected. + */ struct blk_mq_ctx *dispatch_from; + /** + * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to + * decide if the hw_queue is busy using Exponential Weighted Moving + * Average algorithm. + */ unsigned int dispatch_busy; + /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; + /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; + /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; + /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; + /** + * @dispatch_wait: Waitqueue to put requests when there is no tag + * available at the moment, to wait for another try in the future. + */ wait_queue_entry_t dispatch_wait; + + /** + * @wait_index: Index of next available dispatch_wait queue to insert + * requests. + */ atomic_t wait_index; + /** + * @tags: Tags owned by the block driver. A tag at this set is only + * assigned when a request is dispatched from a hardware queue. + */ struct blk_mq_tags *tags; + /** + * @sched_tags: Tags owned by I/O scheduler. If there is an I/O + * scheduler associated with a request queue, a tag is assigned when + * that request is allocated. Else, this member is not used. + */ struct blk_mq_tags *sched_tags; + /** @queued: Number of queued requests. */ unsigned long queued; + /** @run: Number of dispatched requests. */ unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 + /** @dispatched: Number of dispatch requests by queue. */ unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; + /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; + /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; + /** + * @nr_active: Number of active requests. Only used when a tag set is + * shared across request queues. + */ atomic_t nr_active; + /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; + /** @kobj: Kernel object for sysfs. */ struct kobject kobj; + /** @poll_considered: Count times blk_poll() was called. */ unsigned long poll_considered; + /** @poll_invoked: Count how many requests blk_poll() polled. */ unsigned long poll_invoked; + /** @poll_success: Count how many polled requests were completed. */ unsigned long poll_success; #ifdef CONFIG_BLK_DEBUG_FS + /** + * @debugfs_dir: debugfs directory for this hardware queue. Named + * as cpu<cpu_number>. + */ struct dentry *debugfs_dir; + /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif + /** @hctx_list: List of all hardware queues. */ struct list_head hctx_list; - /* Must be the last member - see also blk_mq_hw_ctx_size(). */ + /** + * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is + * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also + * blk_mq_hw_ctx_size(). + */ struct srcu_struct srcu[0]; }; +/** + * struct blk_mq_queue_map - Map software queues to hardware queues + * @mq_map: CPU ID to hardware queue index map. This is an array + * with nr_cpu_ids elements. Each element has a value in the range + * [@queue_offset, @queue_offset + @nr_queues). + * @nr_queues: Number of hardware queues to map CPU IDs onto. + * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe + * driver to map each hardware queue type (enum hctx_type) onto a distinct + * set of hardware queues. + */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; +/** + * enum hctx_type - Type of hardware queue + * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. + * @HCTX_TYPE_READ: Just for READ I/O. + * @HCTX_TYPE_POLL: Polled I/O of any kind. + * @HCTX_MAX_TYPES: Number of types of hctx. + */ enum hctx_type { - HCTX_TYPE_DEFAULT, /* all I/O not otherwise accounted for */ - HCTX_TYPE_READ, /* just for READ I/O */ - HCTX_TYPE_POLL, /* polled I/O of any kind */ + HCTX_TYPE_DEFAULT, + HCTX_TYPE_READ, + HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; +/** + * struct blk_mq_tag_set - tag set that can be shared between request queues + * @map: One or more ctx -> hctx mappings. One map exists for each + * hardware queue type (enum hctx_type) that the driver wishes + * to support. There are no restrictions on maps being of the + * same size, and it's perfectly legal to share maps between + * types. + * @nr_maps: Number of elements in the @map array. A number in the range + * [1, HCTX_MAX_TYPES]. + * @ops: Pointers to functions that implement block driver behavior. + * @nr_hw_queues: Number of hardware queues supported by the block driver that + * owns this data structure. + * @queue_depth: Number of tags per hardware queue, reserved tags included. + * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag + * allocations. + * @cmd_size: Number of additional bytes to allocate per request. The block + * driver owns these additional bytes. + * @numa_node: NUMA node the storage adapter has been connected to. + * @timeout: Request processing timeout in jiffies. + * @flags: Zero or more BLK_MQ_F_* flags. + * @driver_data: Pointer to data owned by the block driver that created this + * tag set. + * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues + * elements. + * @tag_list_lock: Serializes tag_list accesses. + * @tag_list: List of the request queues that use this tag set. See also + * request_queue.tag_set_list. + */ struct blk_mq_tag_set { - /* - * map[] holds ctx -> hctx mappings, one map exists for each type - * that the driver wishes to support. There are no restrictions - * on maps being of the same size, and it's perfectly legal to - * share maps between types. - */ struct blk_mq_queue_map map[HCTX_MAX_TYPES]; - unsigned int nr_maps; /* nr entries in map[] */ + unsigned int nr_maps; const struct blk_mq_ops *ops; - unsigned int nr_hw_queues; /* nr hw queues across maps */ - unsigned int queue_depth; /* max hw supported */ + unsigned int nr_hw_queues; + unsigned int queue_depth; unsigned int reserved_tags; - unsigned int cmd_size; /* per-request extra data */ + unsigned int cmd_size; int numa_node; unsigned int timeout; - unsigned int flags; /* BLK_MQ_F_* */ + unsigned int flags; void *driver_data; struct blk_mq_tags **tags; @@ -115,6 +251,12 @@ struct blk_mq_tag_set { struct list_head tag_list; }; +/** + * struct blk_mq_queue_data - Data about a request inserted in a queue + * + * @rq: Request pointer. + * @last: If it is the last request in the queue. + */ struct blk_mq_queue_data { struct request *rq; bool last; @@ -142,81 +284,101 @@ typedef bool (busy_fn)(struct request_queue *); typedef void (complete_fn)(struct request *); typedef void (cleanup_rq_fn)(struct request *); - +/** + * struct blk_mq_ops - Callback functions that implements block driver + * behaviour. + */ struct blk_mq_ops { - /* - * Queue request + /** + * @queue_rq: Queue a new request from block IO. */ queue_rq_fn *queue_rq; - /* - * If a driver uses bd->last to judge when to submit requests to - * hardware, it must define this function. In case of errors that - * make us stop issuing further requests, this hook serves the + /** + * @commit_rqs: If a driver uses bd->last to judge when to submit + * requests to hardware, it must define this function. In case of errors + * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ commit_rqs_fn *commit_rqs; - /* - * Reserve budget before queue request, once .queue_rq is + /** + * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ get_budget_fn *get_budget; + /** + * @put_budget: Release the reserved budget. + */ put_budget_fn *put_budget; - /* - * Called on request timeout + /** + * @timeout: Called on request timeout. */ timeout_fn *timeout; - /* - * Called to poll for completion of a specific tag. + /** + * @poll: Called to poll for completion of a specific tag. */ poll_fn *poll; + /** + * @complete: Mark the request as complete. + */ complete_fn *complete; - /* - * Called when the block layer side of a hardware queue has been - * set up, allowing the driver to allocate/init matching structures. - * Ditto for exit/teardown. + /** + * @init_hctx: Called when the block layer side of a hardware queue has + * been set up, allowing the driver to allocate/init matching + * structures. */ init_hctx_fn *init_hctx; + /** + * @exit_hctx: Ditto for exit/teardown. + */ exit_hctx_fn *exit_hctx; - /* - * Called for every command allocated by the block layer to allow - * the driver to set up driver specific data. + /** + * @init_request: Called for every command allocated by the block layer + * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. - * - * Ditto for exit/teardown. */ init_request_fn *init_request; + /** + * @exit_request: Ditto for exit/teardown. + */ exit_request_fn *exit_request; - /* Called from inside blk_get_request() */ + + /** + * @initialize_rq_fn: Called from inside blk_get_request(). + */ void (*initialize_rq_fn)(struct request *rq); - /* - * Called before freeing one request which isn't completed yet, - * and usually for freeing the driver private data + /** + * @cleanup_rq: Called before freeing one request which isn't completed + * yet, and usually for freeing the driver private data. */ cleanup_rq_fn *cleanup_rq; - /* - * If set, returns whether or not this queue currently is busy + /** + * @busy: If set, returns whether or not this queue currently is busy. */ busy_fn *busy; + /** + * @map_queues: This allows drivers specify their own queue mapping by + * overriding the setup-time function that builds the mq_map. + */ map_queues_fn *map_queues; #ifdef CONFIG_BLK_DEBUG_FS - /* - * Used by the debugfs implementation to show driver-specific + /** + * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); @@ -262,7 +424,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_free_request(struct request *rq); -bool blk_mq_can_queue(struct blk_mq_hw_ctx *); bool blk_mq_queue_inflight(struct request_queue *q); @@ -301,9 +462,25 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } +/** + * blk_mq_rq_state() - read the current MQ_RQ_* state of a request + * @rq: target request. + */ +static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) +{ + return READ_ONCE(rq->state); +} + +static inline int blk_mq_request_started(struct request *rq) +{ + return blk_mq_rq_state(rq) != MQ_RQ_IDLE; +} + +static inline int blk_mq_request_completed(struct request *rq) +{ + return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; +} -int blk_mq_request_started(struct request *rq); -int blk_mq_request_completed(struct request *rq); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); @@ -324,7 +501,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); @@ -343,14 +520,29 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); -/* +/** + * blk_mq_rq_from_pdu - cast a PDU to a request + * @pdu: the PDU (Protocol Data Unit) to be casted + * + * Return: request + * * Driver command data is immediately after the request. So subtract request - * size to get back to the original request, add request size to get the PDU. + * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } + +/** + * blk_mq_rq_to_pdu - cast a request to a PDU + * @rq: the request to be casted + * + * Return: pointer to the PDU + * + * Driver command data is immediately after the request. So add request to get + * the PDU. + */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d688b96d1d63..70254ae11769 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -153,10 +153,10 @@ struct bio { unsigned short bi_write_hint; blk_status_t bi_status; u8 bi_partno; + atomic_t __bi_remaining; struct bvec_iter bi_iter; - atomic_t __bi_remaining; bio_end_io_t *bi_end_io; void *bi_private; @@ -290,6 +290,12 @@ enum req_opf { REQ_OP_ZONE_RESET_ALL = 8, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, + /* Open a zone */ + REQ_OP_ZONE_OPEN = 10, + /* Close a zone */ + REQ_OP_ZONE_CLOSE = 11, + /* Transition a zone to full */ + REQ_OP_ZONE_FINISH = 12, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, @@ -371,6 +377,7 @@ enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, + STAT_FLUSH, NR_STAT_GROUPS }; @@ -417,6 +424,25 @@ static inline bool op_is_discard(unsigned int op) return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } +/* + * Check if a bio or request operation is a zone management operation, with + * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case + * due to its different handling in the block layer and device response in + * case of command failure. + */ +static inline bool op_is_zone_mgmt(enum req_opf op) +{ + switch (op & REQ_OP_MASK) { + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return true; + default: + return false; + } +} + static inline int op_stat_group(unsigned int op) { if (op_is_discard(op)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3ea78b0c91c..397bb9bc230b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -349,25 +349,25 @@ struct queue_limits { enum blk_zoned_model zoned; }; +typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, + void *data); + #ifdef CONFIG_BLK_DEV_ZONED -/* - * Maximum number of zones to report with a single report zones command. - */ -#define BLK_ZONED_REPORT_MAX_ZONES 8192U +#define BLK_ALL_ZONES ((unsigned int)-1) +int blkdev_report_zones(struct block_device *bdev, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); extern unsigned int blkdev_nr_zones(struct block_device *bdev); -extern int blkdev_report_zones(struct block_device *bdev, - sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones); -extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, - sector_t nr_sectors, gfp_t gfp_mask); +extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, + sector_t sectors, sector_t nr_sectors, + gfp_t gfp_mask); extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); -extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); +extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ @@ -388,9 +388,9 @@ static inline int blkdev_report_zones_ioctl(struct block_device *bdev, return -ENOTTY; } -static inline int blkdev_reset_zones_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) +static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) { return -ENOTTY; } @@ -411,7 +411,6 @@ struct request_queue { /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; - unsigned int nr_queues; unsigned int queue_depth; @@ -1709,7 +1708,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); + unsigned int nr_zones, report_zones_cb cb, void *data); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5b9d22338606..3bf3835d0e86 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -656,11 +656,11 @@ void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size); +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size); void bpf_map_charge_finish(struct bpf_map_memory *mem); void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src); -void *bpf_map_area_alloc(size_t size, int numa_node); +void *bpf_map_area_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 8339071ab08b..e20a0cd09ba5 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -65,5 +65,6 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); +void can_sock_destruct(struct sock *sk); #endif /* !_CAN_CORE_H */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d0633ebdaa9c..bc6c879bd110 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -59,6 +59,11 @@ extern ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_tsx_async_abort(struct device *dev, + struct device_attribute *attr, + char *buf); +extern ssize_t cpu_show_itlb_multihit(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -213,28 +218,7 @@ static inline int cpuhp_smt_enable(void) { return 0; } static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; } #endif -/* - * These are used for a global "mitigations=" cmdline option for toggling - * optional CPU mitigations. - */ -enum cpu_mitigations { - CPU_MITIGATIONS_OFF, - CPU_MITIGATIONS_AUTO, - CPU_MITIGATIONS_AUTO_NOSMT, -}; - -extern enum cpu_mitigations cpu_mitigations; - -/* mitigations=off */ -static inline bool cpu_mitigations_off(void) -{ - return cpu_mitigations == CPU_MITIGATIONS_OFF; -} - -/* mitigations=auto,nosmt */ -static inline bool cpu_mitigations_auto_nosmt(void) -{ - return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; -} +extern bool cpu_mitigations_off(void); +extern bool cpu_mitigations_auto_nosmt(void); #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c57e88e85c41..92d5fdc8154e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -13,6 +13,7 @@ #include <linux/completion.h> #include <linux/kobject.h> #include <linux/notifier.h> +#include <linux/pm_qos.h> #include <linux/spinlock.h> #include <linux/sysfs.h> @@ -76,8 +77,10 @@ struct cpufreq_policy { struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ - struct dev_pm_qos_request *min_freq_req; - struct dev_pm_qos_request *max_freq_req; + struct freq_constraints constraints; + struct freq_qos_request *min_freq_req; + struct freq_qos_request *max_freq_req; + struct cpufreq_frequency_table *freq_table; enum cpufreq_table_sorting freq_table_sorted; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 399ad8632356..475668c69dbc 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -17,6 +17,7 @@ struct dm_dev; struct dm_target; struct dm_table; +struct dm_report_zones_args; struct mapped_device; struct bio_vec; @@ -93,9 +94,9 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); -typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, - struct blk_zone *zones, - unsigned int *nr_zones); +typedef int (*dm_report_zones_fn) (struct dm_target *ti, + struct dm_report_zones_args *args, + unsigned int nr_zones); /* * These iteration functions are typically used to check (and combine) @@ -422,10 +423,23 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_remap_zone_report(struct dm_target *ti, sector_t start, - struct blk_zone *zones, unsigned int *nr_zones); union map_info *dm_get_rq_mapinfo(struct request *rq); +#ifdef CONFIG_BLK_DEV_ZONED +struct dm_report_zones_args { + struct dm_target *tgt; + sector_t next_sector; + + void *orig_data; + report_zones_cb orig_cb; + unsigned int zone_idx; + + /* must be filled by ->report_zones before calling dm_report_zones_cb */ + sector_t start; +}; +int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data); +#endif /* CONFIG_BLK_DEV_ZONED */ + /* * Device mapper functions to parse and create devices specified by the * parameter "dm-mod.create=" @@ -594,9 +608,6 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); */ #define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz)) -#define dm_array_too_big(fixed, obj, num) \ - ((num) > (UINT_MAX - (fixed)) / (obj)) - /* * Sector offset taken relative to the start of the target instead of * relative to the start of the device. diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 6c809440f319..4cf02ecd67de 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -204,6 +204,12 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) #define dynamic_dev_dbg(dev, fmt, ...) \ do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) +#define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ + groupsize, buf, len, ascii) \ + do { if (0) \ + print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii); \ + } while (0) #endif #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index bd3837022307..d87acf62958e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1579,9 +1579,22 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, struct efi_boot_memmap *map); +efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr, unsigned long min); + +static inline efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, - unsigned long *addr); + unsigned long *addr) +{ + /* + * Don't allocate at 0x0. It will confuse code that + * checks pointers against NULL. Skip the first 8 + * bytes so we start at a nice even number. + */ + return efi_low_alloc_above(sys_table_arg, size, align, addr, 0x8); +} efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, @@ -1592,7 +1605,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, unsigned long image_size, unsigned long alloc_size, unsigned long preferred_addr, - unsigned long alignment); + unsigned long alignment, + unsigned long min_addr); efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, efi_loaded_image_t *image, diff --git a/include/linux/export.h b/include/linux/export.h index 621158ecd2e2..941d075f03d6 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -18,8 +18,6 @@ extern struct module __this_module; #define THIS_MODULE ((struct module *)0) #endif -#define NS_SEPARATOR "." - #ifdef CONFIG_MODVERSIONS /* Mark the CRC weak since genksyms apparently decides not to * generate a checksums for some symbols */ @@ -48,11 +46,11 @@ extern struct module __this_module; * absolute relocations that require runtime processing on relocatable * kernels. */ -#define __KSYMTAB_ENTRY_NS(sym, sec, ns) \ +#define __KSYMTAB_ENTRY_NS(sym, sec) \ __ADDRESSABLE(sym) \ asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ " .balign 4 \n" \ - "__ksymtab_" #ns NS_SEPARATOR #sym ": \n" \ + "__ksymtab_" #sym ": \n" \ " .long " #sym "- . \n" \ " .long __kstrtab_" #sym "- . \n" \ " .long __kstrtabns_" #sym "- . \n" \ @@ -74,16 +72,14 @@ struct kernel_symbol { int namespace_offset; }; #else -#define __KSYMTAB_ENTRY_NS(sym, sec, ns) \ - static const struct kernel_symbol __ksymtab_##sym##__##ns \ - asm("__ksymtab_" #ns NS_SEPARATOR #sym) \ +#define __KSYMTAB_ENTRY_NS(sym, sec) \ + static const struct kernel_symbol __ksymtab_##sym \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ = { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym } #define __KSYMTAB_ENTRY(sym, sec) \ static const struct kernel_symbol __ksymtab_##sym \ - asm("__ksymtab_" #sym) \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ = { (unsigned long)&sym, __kstrtab_##sym, NULL } @@ -115,7 +111,7 @@ struct kernel_symbol { static const char __kstrtabns_##sym[] \ __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ = #ns; \ - __KSYMTAB_ENTRY_NS(sym, sec, ns) + __KSYMTAB_ENTRY_NS(sym, sec) #define ___EXPORT_SYMBOL(sym, sec) \ ___export_symbol_common(sym, sec); \ diff --git a/include/linux/filter.h b/include/linux/filter.h index 2ce57645f3cd..0367a75f873b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1099,7 +1099,6 @@ static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) #endif /* CONFIG_BPF_JIT */ -void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp); void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..dde6dc4492a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -148,8 +148,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) -/* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ @@ -2632,8 +2630,6 @@ extern void bd_finish_claiming(struct block_device *bdev, extern void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); -extern int __blkdev_reread_part(struct block_device *bdev); -extern int blkdev_reread_part(struct block_device *bdev); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); @@ -2703,8 +2699,6 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK -extern void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev, bool verbose); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); extern int __invalidate_device(struct block_device *, bool); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8b5330dd5ac0..8bb63027e4d6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -621,9 +621,10 @@ extern void blk_invalidate_devt(dev_t devt); extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); +int bdev_disk_changed(struct block_device *bdev, bool invalidate); +int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); +int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev); extern int disk_expand_part_tbl(struct gendisk *disk, int target); -extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); -extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev); extern struct hd_struct * __must_check add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fb07b503dc45..61f2f6ff9467 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -325,6 +325,29 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } +/** + * gfpflags_normal_context - is gfp_flags a normal sleepable context? + * @gfp_flags: gfp_flags to test + * + * Test whether @gfp_flags indicates that the allocation is from the + * %current context and allowed to sleep. + * + * An allocation being allowed to block doesn't mean it owns the %current + * context. When direct reclaim path tries to allocate memory, the + * allocation context is nested inside whatever %current was doing at the + * time of the original allocation. The nested allocation may be allowed + * to block but modifying anything %current owns can corrupt the outer + * context's expectations. + * + * %true result from this function indicates that the allocation context + * can sleep and use anything that's associated with %current. + */ +static inline bool gfpflags_normal_context(const gfp_t gfp_flags) +{ + return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == + __GFP_DIRECT_RECLAIM; +} + #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else diff --git a/include/linux/idr.h b/include/linux/idr.h index 4ec8986e5dfb..ac6e946b6767 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -185,7 +185,7 @@ static inline void idr_preload_end(void) * is convenient for a "not found" value. */ #define idr_for_each_entry(idr, entry, id) \ - for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) + for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U) /** * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 2e55e4cdbd8a..a367ead4bf4b 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -29,7 +29,6 @@ struct macvlan_dev { netdev_features_t set_features; enum macvlan_mode mode; u16 flags; - int nest_level; unsigned int macaddr_count; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 06faa066496f..ec7e4bd07f82 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -223,6 +223,7 @@ struct team { atomic_t count_pending; struct delayed_work dw; } mcast_rejoin; + struct lock_class_key team_lock_key; long mode_priv[TEAM_MODE_PRIV_LONGS]; }; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 244278d5c222..b05e855f1ddd 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -182,7 +182,6 @@ struct vlan_dev_priv { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif - unsigned int nest_level; }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) @@ -221,11 +220,6 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG_ON(!is_vlan_dev(dev)); - return vlan_dev_priv(dev)->nest_level; -} #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, @@ -295,11 +289,6 @@ static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG(); - return 0; -} #endif /** diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ed11ef594378..6d8bf4bdf240 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -336,7 +336,8 @@ enum { #define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) #define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16) #define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) -#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) +#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ + ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_IOTLB_SIZE 1 #define QI_DEV_IOTLB_MAX_INVS 32 @@ -360,7 +361,8 @@ enum { #define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) -#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) +#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ + ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_EIOTLB_MAX_INVS 32 /* Page group response descriptor QW0 */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 719fc3e15ea4..d41c521a39da 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -966,6 +966,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); +bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -1382,4 +1383,10 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ +typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data); + +int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, + uintptr_t data, const char *name, + struct task_struct **thread_ptr); + #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index 207e7ee764ce..d3bbfddf616a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -484,6 +484,7 @@ enum hsm_task_states { }; enum ata_completion_errors { + AC_ERR_OK = 0, /* no error */ AC_ERR_DEV = (1 << 0), /* device reported error */ AC_ERR_HSM = (1 << 1), /* host state machine violation */ AC_ERR_TIMEOUT = (1 << 2), /* timeout */ @@ -891,9 +892,9 @@ struct ata_port_operations { /* * Command execution */ - int (*qc_defer)(struct ata_queued_cmd *qc); - int (*check_atapi_dma)(struct ata_queued_cmd *qc); - void (*qc_prep)(struct ata_queued_cmd *qc); + int (*qc_defer)(struct ata_queued_cmd *qc); + int (*check_atapi_dma)(struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc); unsigned int (*qc_issue)(struct ata_queued_cmd *qc); bool (*qc_fill_rtf)(struct ata_queued_cmd *qc); @@ -1161,7 +1162,7 @@ extern int ata_xfer_mode2shift(unsigned long xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -extern void ata_noop_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); @@ -1893,9 +1894,9 @@ extern const struct ata_port_operations ata_bmdma_port_ops; .sg_tablesize = LIBATA_MAX_PRD, \ .dma_boundary = ATA_DMA_BOUNDARY -extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); -extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance); diff --git a/include/linux/memory.h b/include/linux/memory.h index 0ebb105eb261..4c75dae8dd29 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -119,6 +119,7 @@ extern struct memory_block *find_memory_block(struct mem_section *); typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); +extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT) #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 138c50d5a353..0836fe232f97 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1545,9 +1545,8 @@ struct mlx5_ifc_extended_dest_format_bits { }; union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits { - struct mlx5_ifc_dest_format_struct_bits dest_format_struct; + struct mlx5_ifc_extended_dest_format_bits extended_dest_format; struct mlx5_ifc_flow_counter_list_bits flow_counter_list; - u8 reserved_at_0[0x40]; }; struct mlx5_ifc_fte_match_param_bits { diff --git a/include/linux/mm.h b/include/linux/mm.h index cc292273e6ba..a2adf95b3f9c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -695,11 +695,6 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2222fa795284..270aa8fd2800 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -221,6 +221,11 @@ struct page { #endif } _struct_page_alignment; +static inline atomic_t *compound_mapcount_ptr(struct page *page) +{ + return &page[1].compound_mapcount; +} + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9eda1c31d1f7..c20f190b4c18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -925,6 +925,7 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1421,7 +1422,6 @@ struct net_device_ops { void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); @@ -1649,6 +1649,8 @@ enum netdev_priv_flags { * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length + * @upper_level: Maximum depth level of upper devices. + * @lower_level: Maximum depth level of lower devices. * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address @@ -1758,9 +1760,13 @@ enum netdev_priv_flags { * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. - * - * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount + * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock + spinlock + * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount + * @qdisc_xmit_lock_key: lockdep class annotating + * netdev_queue->_xmit_lock spinlock + * @addr_list_lock_key: lockdep class annotating + * net_device->addr_list_lock spinlock * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -1875,6 +1881,8 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; unsigned char addr_len; + unsigned char upper_level; + unsigned char lower_level; unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; @@ -2045,8 +2053,10 @@ struct net_device { #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; - struct lock_class_key *qdisc_tx_busylock; - struct lock_class_key *qdisc_running_key; + struct lock_class_key qdisc_tx_busylock_key; + struct lock_class_key qdisc_running_key; + struct lock_class_key qdisc_xmit_lock_key; + struct lock_class_key addr_list_lock_key; bool proto_down; unsigned wol_enabled:1; }; @@ -2124,23 +2134,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } -#define netdev_lockdep_set_classes(dev) \ -{ \ - static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_running_key; \ - static struct lock_class_key qdisc_xmit_lock_key; \ - static struct lock_class_key dev_addr_list_lock_key; \ - unsigned int i; \ - \ - (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - (dev)->qdisc_running_key = &qdisc_running_key; \ - lockdep_set_class(&(dev)->addr_list_lock, \ - &dev_addr_list_lock_key); \ - for (i = 0; i < (dev)->num_tx_queues; i++) \ - lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ - &qdisc_xmit_lock_key); \ -} - u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, @@ -3139,6 +3132,7 @@ static inline void netif_stop_queue(struct net_device *dev) } void netif_tx_stop_all_queues(struct net_device *dev); +void netdev_update_lockdep_key(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { @@ -4056,16 +4050,6 @@ static inline void netif_addr_lock(struct net_device *dev) spin_lock(&dev->addr_list_lock); } -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - int subclass = SINGLE_DEPTH_NESTING; - - if (dev->netdev_ops->ndo_get_lock_subclass) - subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); - - spin_lock_nested(&dev->addr_list_lock, subclass); -} - static inline void netif_addr_lock_bh(struct net_device *dev) { spin_lock_bh(&dev->addr_list_lock); @@ -4329,6 +4313,16 @@ int netdev_master_upper_dev_link(struct net_device *dev, struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack); +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); @@ -4340,7 +4334,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index 067c9fea64fe..e8c30b39bb27 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -4,33 +4,60 @@ */ /* - * This file contains definitions relative to FC-NVME r1.14 (16-020vB). - * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. + * This file contains definitions relative to FC-NVME-2 r1.06 + * (T11-2019-00210-v001). */ #ifndef _NVME_FC_H #define _NVME_FC_H 1 +#include <uapi/scsi/fc/fc_fs.h> -#define NVME_CMD_SCSI_ID 0xFD +#define NVME_CMD_FORMAT_ID 0xFD #define NVME_CMD_FC_ID FC_TYPE_NVME /* FC-NVME Cmd IU Flags */ -#define FCNVME_CMD_FLAGS_DIRMASK 0x03 -#define FCNVME_CMD_FLAGS_WRITE 0x01 -#define FCNVME_CMD_FLAGS_READ 0x02 +enum { + FCNVME_CMD_FLAGS_DIRMASK = 0x03, + FCNVME_CMD_FLAGS_WRITE = (1 << 0), + FCNVME_CMD_FLAGS_READ = (1 << 1), + + FCNVME_CMD_FLAGS_PICWP = (1 << 2), +}; + +enum { + FCNVME_CMD_CAT_MASK = 0x0F, + FCNVME_CMD_CAT_ADMINQ = 0x01, + FCNVME_CMD_CAT_CSSMASK = 0x07, + FCNVME_CMD_CAT_CSSFLAG = 0x08, +}; + +static inline __u8 fccmnd_set_cat_admin(__u8 rsv_cat) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_ADMINQ; +} + +static inline __u8 fccmnd_set_cat_css(__u8 rsv_cat, __u8 css) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_CSSFLAG | + (css & FCNVME_CMD_CAT_CSSMASK); +} struct nvme_fc_cmd_iu { - __u8 scsi_id; + __u8 format_id; __u8 fc_id; __be16 iu_len; - __u8 rsvd4[3]; + __u8 rsvd4[2]; + __u8 rsv_cat; __u8 flags; __be64 connection_id; __be32 csn; __be32 data_len; struct nvme_command sqe; - __be32 rsvd88[2]; + __u8 dps; + __u8 lbads; + __be16 ms; + __be32 rsvd92; }; #define NVME_FC_SIZEOF_ZEROS_RSP 12 @@ -38,11 +65,12 @@ struct nvme_fc_cmd_iu { enum { FCNVME_SC_SUCCESS = 0, FCNVME_SC_INVALID_FIELD = 1, - FCNVME_SC_INVALID_CONNID = 2, + /* reserved 2 */ + FCNVME_SC_ILL_CONN_PARAMS = 3, }; struct nvme_fc_ersp_iu { - __u8 status_code; + __u8 ersp_result; __u8 rsvd1; __be16 iu_len; __be32 rsn; @@ -53,14 +81,44 @@ struct nvme_fc_ersp_iu { }; -/* FC-NVME Link Services */ +#define FCNVME_NVME_SR_OPCODE 0x01 + +struct nvme_fc_nvme_sr_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 retry_rctl; + __be32 rsvd4; +}; + + +enum { + FCNVME_SRSTAT_ACC = 0x0, + FCNVME_SRSTAT_INV_FCID = 0x1, + /* reserved 0x2 */ + FCNVME_SRSTAT_LOGICAL_ERR = 0x3, + FCNVME_SRSTAT_INV_QUALIF = 0x4, + FCNVME_SRSTAT_UNABL2PERFORM = 0x9, +}; + +struct nvme_fc_nvme_sr_rsp_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 status; + __be32 rsvd4; +}; + + +/* FC-NVME Link Services - LS cmd values (w0 bits 31:24) */ enum { FCNVME_LS_RSVD = 0, FCNVME_LS_RJT = 1, FCNVME_LS_ACC = 2, - FCNVME_LS_CREATE_ASSOCIATION = 3, - FCNVME_LS_CREATE_CONNECTION = 4, - FCNVME_LS_DISCONNECT = 5, + FCNVME_LS_CREATE_ASSOCIATION = 3, /* Create Association */ + FCNVME_LS_CREATE_CONNECTION = 4, /* Create I/O Connection */ + FCNVME_LS_DISCONNECT_ASSOC = 5, /* Disconnect Association */ + FCNVME_LS_DISCONNECT_CONN = 6, /* Disconnect Connection */ }; /* FC-NVME Link Service Descriptors */ @@ -117,14 +175,17 @@ enum fcnvme_ls_rjt_reason { FCNVME_RJT_RC_UNSUP = 0x0b, /* command not supported */ - FCNVME_RJT_RC_INPROG = 0x0e, - /* command already in progress */ - FCNVME_RJT_RC_INV_ASSOC = 0x40, - /* Invalid Association ID*/ + /* Invalid Association ID */ FCNVME_RJT_RC_INV_CONN = 0x41, - /* Invalid Connection ID*/ + /* Invalid Connection ID */ + + FCNVME_RJT_RC_INV_PARAM = 0x42, + /* Invalid Parameters */ + + FCNVME_RJT_RC_INSUF_RES = 0x43, + /* Insufficient Resources */ FCNVME_RJT_RC_VENDOR = 0xff, /* vendor specific error */ @@ -138,14 +199,32 @@ enum fcnvme_ls_rjt_explan { FCNVME_RJT_EXP_OXID_RXID = 0x17, /* invalid OX_ID-RX_ID combination */ - FCNVME_RJT_EXP_INSUF_RES = 0x29, - /* insufficient resources */ - FCNVME_RJT_EXP_UNAB_DATA = 0x2a, /* unable to supply requested data */ FCNVME_RJT_EXP_INV_LEN = 0x2d, /* Invalid payload length */ + + FCNVME_RJT_EXP_INV_ERSP_RAT = 0x40, + /* Invalid NVMe_ERSP Ratio */ + + FCNVME_RJT_EXP_INV_CTLR_ID = 0x41, + /* Invalid Controller ID */ + + FCNVME_RJT_EXP_INV_QUEUE_ID = 0x42, + /* Invalid Queue ID */ + + FCNVME_RJT_EXP_INV_SQSIZE = 0x43, + /* Invalid Submission Queue Size */ + + FCNVME_RJT_EXP_INV_HOSTID = 0x44, + /* Invalid HOST ID */ + + FCNVME_RJT_EXP_INV_HOSTNQN = 0x45, + /* Invalid HOSTNQN */ + + FCNVME_RJT_EXP_INV_SUBNQN = 0x46, + /* Invalid SUBNQN */ }; /* FCNVME_LSDESC_RJT */ @@ -209,21 +288,11 @@ struct fcnvme_lsdesc_cr_conn_cmd { __be32 rsvd52; }; -/* Disconnect Scope Values */ -enum { - FCNVME_DISCONN_ASSOCIATION = 0, - FCNVME_DISCONN_CONNECTION = 1, -}; - /* FCNVME_LSDESC_DISCONN_CMD */ struct fcnvme_lsdesc_disconn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ __be32 desc_len; - u8 rsvd8[3]; - /* note: scope is really a 1 bit field */ - u8 scope; /* FCNVME_DISCONN_xxx */ - __be32 rsvd12; - __be64 id; + __be32 rsvd8[4]; }; /* FCNVME_LSDESC_CONN_ID */ @@ -242,9 +311,14 @@ struct fcnvme_lsdesc_assoc_id { /* r_ctl values */ enum { - FCNVME_RS_RCTL_DATA = 1, - FCNVME_RS_RCTL_XFER_RDY = 5, - FCNVME_RS_RCTL_RSP = 8, + FCNVME_RS_RCTL_CMND = 0x6, + FCNVME_RS_RCTL_DATA = 0x1, + FCNVME_RS_RCTL_CONF = 0x3, + FCNVME_RS_RCTL_SR = 0x9, + FCNVME_RS_RCTL_XFER_RDY = 0x5, + FCNVME_RS_RCTL_RSP = 0x7, + FCNVME_RS_RCTL_ERSP = 0x8, + FCNVME_RS_RCTL_SR_RSP = 0xA, }; @@ -264,7 +338,10 @@ struct fcnvme_ls_acc_hdr { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_rqst rqst; - /* Followed by cmd-specific ACC descriptors, see next definitions */ + /* + * Followed by cmd-specific ACCEPT descriptors, see xxx_acc + * definitions below + */ }; /* FCNVME_LS_CREATE_ASSOCIATION */ @@ -302,25 +379,39 @@ struct fcnvme_ls_cr_conn_acc { struct fcnvme_lsdesc_conn_id connectid; }; -/* FCNVME_LS_DISCONNECT */ -struct fcnvme_ls_disconnect_rqst { +/* FCNVME_LS_DISCONNECT_ASSOC */ +struct fcnvme_ls_disconnect_assoc_rqst { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_assoc_id associd; struct fcnvme_lsdesc_disconn_cmd discon_cmd; }; -struct fcnvme_ls_disconnect_acc { +struct fcnvme_ls_disconnect_assoc_acc { + struct fcnvme_ls_acc_hdr hdr; +}; + + +/* FCNVME_LS_DISCONNECT_CONN */ +struct fcnvme_ls_disconnect_conn_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_disconn_cmd connectid; +}; + +struct fcnvme_ls_disconnect_conn_acc { struct fcnvme_ls_acc_hdr hdr; }; /* - * Yet to be defined in FC-NVME: + * Default R_A_TOV is pulled in from fc_fs.h but needs conversion + * from ms to seconds for our use. */ -#define NVME_FC_CONNECT_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_LS_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_TGTOP_TIMEOUT_SEC 2 /* 2 seconds */ +#define FC_TWO_TIMES_R_A_TOV (2 * (FC_DEF_R_A_TOV / 1000)) +#define NVME_FC_LS_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV +#define NVME_FC_TGTOP_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV /* * TRADDR string must be of form "nn-<16hexdigits>:pn-<16hexdigits>" @@ -328,6 +419,7 @@ struct fcnvme_ls_disconnect_acc { * infront of the <16hexdigits>. Without is considered the "min" string * and with is considered the "max" string. The hexdigits may be upper * or lower case. + * Note: FC-NVME-2 standard requires a "0x" prefix. */ #define NVME_FC_TRADDR_NNLEN 3 /* "?n-" */ #define NVME_FC_TRADDR_OXNNLEN 5 /* "?n-0x" */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f61d6906e59d..3d5189f46cb1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,8 +107,22 @@ enum { NVME_REG_AQA = 0x0024, /* Admin Queue Attributes */ NVME_REG_ASQ = 0x0028, /* Admin SQ Base Address */ NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ - NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ + NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_BPINFO = 0x0040, /* Boot Partition Information */ + NVME_REG_BPRSEL = 0x0044, /* Boot Partition Read Select */ + NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer + * Location + */ + NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ + NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ + NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ + NVME_REG_PMREBS = 0x0e0c, /* Persistent Memory Region Elasticity + * Buffer Size + */ + NVME_REG_PMRSWTP = 0x0e10, /* Persistent Memory Region Sustained + * Write Throughput + */ NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; @@ -295,6 +309,14 @@ enum { NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, + NVME_CTRL_CTRATT_128_ID = 1 << 0, + NVME_CTRL_CTRATT_NON_OP_PSP = 1 << 1, + NVME_CTRL_CTRATT_NVM_SETS = 1 << 2, + NVME_CTRL_CTRATT_READ_RECV_LVLS = 1 << 3, + NVME_CTRL_CTRATT_ENDURANCE_GROUPS = 1 << 4, + NVME_CTRL_CTRATT_PREDICTABLE_LAT = 1 << 5, + NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY = 1 << 7, + NVME_CTRL_CTRATT_UUID_LIST = 1 << 9, }; struct nvme_lbaf { @@ -352,6 +374,9 @@ enum { NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, NVME_ID_CNS_CTRL_LIST = 0x13, + NVME_ID_CNS_SCNDRY_CTRL_LIST = 0x15, + NVME_ID_CNS_NS_GRANULARITY = 0x16, + NVME_ID_CNS_UUID_LIST = 0x17, }; enum { @@ -409,7 +434,8 @@ struct nvme_smart_log { __u8 avail_spare; __u8 spare_thresh; __u8 percent_used; - __u8 rsvd6[26]; + __u8 endu_grp_crit_warn_sumry; + __u8 rsvd7[25]; __u8 data_units_read[16]; __u8 data_units_written[16]; __u8 host_reads[16]; @@ -423,7 +449,11 @@ struct nvme_smart_log { __le32 warning_temp_time; __le32 critical_comp_time; __le16 temp_sensor[8]; - __u8 rsvd216[296]; + __le32 thm_temp1_trans_count; + __le32 thm_temp2_trans_count; + __le32 thm_temp1_total_time; + __le32 thm_temp2_total_time; + __u8 rsvd232[280]; }; struct nvme_fw_slot_info_log { @@ -440,6 +470,7 @@ enum { NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, + NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, }; struct nvme_effects_log { @@ -563,6 +594,7 @@ enum nvme_opcode { nvme_cmd_compare = 0x05, nvme_cmd_write_zeroes = 0x08, nvme_cmd_dsm = 0x09, + nvme_cmd_verify = 0x0c, nvme_cmd_resv_register = 0x0d, nvme_cmd_resv_report = 0x0e, nvme_cmd_resv_acquire = 0x11, @@ -772,6 +804,12 @@ struct nvme_write_zeroes_cmd { /* Features */ +enum { + NVME_TEMP_THRESH_MASK = 0xffff, + NVME_TEMP_THRESH_SELECT_SHIFT = 16, + NVME_TEMP_THRESH_TYPE_UNDER = 0x100000, +}; + struct nvme_feat_auto_pst { __le64 entries[32]; }; @@ -806,10 +844,14 @@ enum nvme_admin_opcode { nvme_admin_ns_mgmt = 0x0d, nvme_admin_activate_fw = 0x10, nvme_admin_download_fw = 0x11, + nvme_admin_dev_self_test = 0x14, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, nvme_admin_directive_send = 0x19, nvme_admin_directive_recv = 0x1a, + nvme_admin_virtual_mgmt = 0x1c, + nvme_admin_nvme_mi_send = 0x1d, + nvme_admin_nvme_mi_recv = 0x1e, nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, @@ -873,6 +915,7 @@ enum { NVME_FEAT_PLM_CONFIG = 0x13, NVME_FEAT_PLM_WINDOW = 0x14, NVME_FEAT_HOST_BEHAVIOR = 0x16, + NVME_FEAT_SANITIZE = 0x17, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, @@ -883,6 +926,10 @@ enum { NVME_LOG_FW_SLOT = 0x03, NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, + NVME_LOG_DEVICE_SELF_TEST = 0x06, + NVME_LOG_TELEMETRY_HOST = 0x07, + NVME_LOG_TELEMETRY_CTRL = 0x08, + NVME_LOG_ENDURANCE_GROUP = 0x09, NVME_LOG_ANA = 0x0c, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, @@ -1290,7 +1337,11 @@ enum { NVME_SC_SGL_INVALID_OFFSET = 0x16, NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_SANITIZE_FAILED = 0x1C, + NVME_SC_SANITIZE_IN_PROGRESS = 0x1D, + NVME_SC_NS_WRITE_PROTECTED = 0x20, + NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, @@ -1328,6 +1379,8 @@ enum { NVME_SC_NS_NOT_ATTACHED = 0x11a, NVME_SC_THIN_PROV_NOT_SUPP = 0x11b, NVME_SC_CTRL_LIST_INVALID = 0x11c, + NVME_SC_BP_WRITE_PROHIBITED = 0x11e, + NVME_SC_PMR_SAN_PROHIBITED = 0x123, /* * I/O Command Set Specific - NVM commands: @@ -1368,6 +1421,7 @@ enum { NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, NVME_SC_HOST_PATH_ERROR = 0x370, + NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, NVME_SC_DNR = 0x4000, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f91cb8898ff0..1bf83c8fcaa7 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -622,12 +622,28 @@ static inline int PageTransCompound(struct page *page) * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * MMU notifier, otherwise it may result in page->_mapcount check false * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so comparing subpage's _mapcount to + * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; + struct page *head; + + if (!PageTransCompound(page)) + return 0; + + if (PageAnon(page)) + return atomic_read(&page->_mapcount) < 0; + + head = compound_head(page); + /* File THP is PMD mapped and not PTE mapped */ + return atomic_read(&page->_mapcount) == + atomic_read(compound_mapcount_ptr(head)); } /* diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 61448c19a132..68ccc5b1913b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -292,7 +292,7 @@ struct pmu { * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported - * -EACCESS -- @event is for this PMU, @event is valid, but no privilidges + * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * diff --git a/include/linux/platform_data/dma-imx-sdma.h b/include/linux/platform_data/dma-imx-sdma.h index 6eaa53cef0bd..30e676b36b24 100644 --- a/include/linux/platform_data/dma-imx-sdma.h +++ b/include/linux/platform_data/dma-imx-sdma.h @@ -51,7 +51,10 @@ struct sdma_script_start_addrs { /* End of v2 array */ s32 zcanfd_2_mcu_addr; s32 zqspi_2_mcu_addr; + s32 mcu_2_ecspi_addr; /* End of v3 array */ + s32 mcu_2_zqspi_addr; + /* End of v4 array */ }; /** diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 222c3e01397c..ebf5ef17cc2a 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -34,8 +34,6 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 -#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 -#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE (-1) #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -54,8 +52,6 @@ struct pm_qos_flags_request { enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, - DEV_PM_QOS_MIN_FREQUENCY, - DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; @@ -97,14 +93,10 @@ struct pm_qos_flags { struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; - struct pm_qos_constraints min_frequency; - struct pm_qos_constraints max_frequency; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; struct dev_pm_qos_request *flags_req; - struct dev_pm_qos_request *min_frequency_req; - struct dev_pm_qos_request *max_frequency_req; }; /* Action requested to pm_qos_update_target */ @@ -199,10 +191,6 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; - case DEV_PM_QOS_MIN_FREQUENCY: - return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; - case DEV_PM_QOS_MAX_FREQUENCY: - return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; @@ -267,4 +255,48 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) } #endif +#define FREQ_QOS_MIN_DEFAULT_VALUE 0 +#define FREQ_QOS_MAX_DEFAULT_VALUE (-1) + +enum freq_qos_req_type { + FREQ_QOS_MIN = 1, + FREQ_QOS_MAX, +}; + +struct freq_constraints { + struct pm_qos_constraints min_freq; + struct blocking_notifier_head min_freq_notifiers; + struct pm_qos_constraints max_freq; + struct blocking_notifier_head max_freq_notifiers; +}; + +struct freq_qos_request { + enum freq_qos_req_type type; + struct plist_node pnode; + struct freq_constraints *qos; +}; + +static inline int freq_qos_request_active(struct freq_qos_request *req) +{ + return !IS_ERR_OR_NULL(req->qos); +} + +void freq_constraints_init(struct freq_constraints *qos); + +s32 freq_qos_read_value(struct freq_constraints *qos, + enum freq_qos_req_type type); + +int freq_qos_add_request(struct freq_constraints *qos, + struct freq_qos_request *req, + enum freq_qos_req_type type, s32 value); +int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); +int freq_qos_remove_request(struct freq_qos_request *req); + +int freq_qos_add_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier); +int freq_qos_remove_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier); + #endif diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index b5116013f27e..63e62372443a 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -316,24 +316,6 @@ radix_tree_iter_lookup(const struct radix_tree_root *root, } /** - * radix_tree_iter_find - find a present entry - * @root: radix tree root - * @iter: iterator state - * @index: start location - * - * This function returns the slot containing the entry with the lowest index - * which is at least @index. If @index is larger than any present entry, this - * function returns NULL. The @iter is updated to describe the entry found. - */ -static inline void __rcu ** -radix_tree_iter_find(const struct radix_tree_root *root, - struct radix_tree_iter *iter, unsigned long index) -{ - radix_tree_iter_init(iter, index); - return radix_tree_next_chunk(root, iter, 0); -} - -/** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index 9326d671b6e6..eaae6b4e9f24 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -7,7 +7,7 @@ struct reset_controller_dev; /** - * struct reset_control_ops + * struct reset_control_ops - reset controller driver callbacks * * @reset: for self-deasserting resets, does all necessary * things to reset the device @@ -33,7 +33,7 @@ struct of_phandle_args; * @provider: name of the reset controller device controlling this reset line * @index: ID of the reset controller in the reset controller device * @dev_id: name of the device associated with this reset line - * @con_id name of the reset line (can be NULL) + * @con_id: name of the reset line (can be NULL) */ struct reset_control_lookup { struct list_head list; diff --git a/include/linux/reset.h b/include/linux/reset.h index e7793fc0fa93..eb597e8aa430 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -143,7 +143,7 @@ static inline int device_reset_optional(struct device *dev) * If this function is called more than once for the same reset_control it will * return -EBUSY. * - * See reset_control_get_shared for details on shared references to + * See reset_control_get_shared() for details on shared references to * reset-controls. * * Use of id names is optional. diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index a986ac12a848..e40d019c3d9d 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -216,15 +216,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, */ bool sbitmap_any_bit_set(const struct sbitmap *sb); -/** - * sbitmap_any_bit_clear() - Check for an unset bit in a &struct - * sbitmap. - * @sb: Bitmap to check. - * - * Return: true if any bit in the bitmap is clear, false otherwise. - */ -bool sbitmap_any_bit_clear(const struct sbitmap *sb); - #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..6666e25606b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ extern struct pid *cad_pid; #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ +#define PF_IO_WORKER 0x20000000 /* Task is an IO worker */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/security.h b/include/linux/security.h index a8d59d612d27..9df7547afc0c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -105,6 +105,7 @@ enum lockdown_reason { LOCKDOWN_NONE, LOCKDOWN_MODULE_SIGNATURE, LOCKDOWN_DEV_MEM, + LOCKDOWN_EFI_TEST, LOCKDOWN_KEXEC, LOCKDOWN_HIBERNATION, LOCKDOWN_PCI_ACCESS, diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 53c28d750a45..1ac0d712a9c3 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -42,6 +42,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_PSID_REVERT_TPR: case IOC_OPAL_MBR_DONE: case IOC_OPAL_WRITE_SHADOW_MBR: + case IOC_OPAL_GENERIC_TABLE_RW: return true; } return false; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7914fdaf4226..8688f7adfda7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1354,7 +1354,8 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 return skb->hash; } -__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); +__u32 skb_get_hash_perturb(const struct sk_buff *skb, + const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { @@ -1495,6 +1496,19 @@ static inline int skb_queue_empty(const struct sk_buff_head *list) } /** + * skb_queue_empty_lockless - check if a queue is empty + * @list: queue head + * + * Returns true if the queue is empty, false otherwise. + * This variant can be used in lockless contexts. + */ +static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) +{ + return READ_ONCE(list->next) == (const struct sk_buff *) list; +} + + +/** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer @@ -1847,9 +1861,11 @@ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { - newsk->next = next; - newsk->prev = prev; - next->prev = prev->next = newsk; + /* see skb_queue_empty_lockless() for the opposite READ_ONCE() */ + WRITE_ONCE(newsk->next, next); + WRITE_ONCE(newsk->prev, prev); + WRITE_ONCE(next->prev, newsk); + WRITE_ONCE(prev->next, newsk); list->qlen++; } @@ -1860,11 +1876,11 @@ static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *first = list->next; struct sk_buff *last = list->prev; - first->prev = prev; - prev->next = first; + WRITE_ONCE(first->prev, prev); + WRITE_ONCE(prev->next, first); - last->next = next; - next->prev = last; + WRITE_ONCE(last->next, next); + WRITE_ONCE(next->prev, last); } /** @@ -2005,8 +2021,8 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; - next->prev = prev; - prev->next = next; + WRITE_ONCE(next->prev, prev); + WRITE_ONCE(prev->next, next); } /** @@ -4153,12 +4169,18 @@ static inline void skb_ext_reset(struct sk_buff *skb) skb->active_extensions = 0; } } + +static inline bool skb_has_extensions(struct sk_buff *skb) +{ + return unlikely(skb->active_extensions); +} #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} +static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e4b3fb4bb77c..ce7055259877 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -139,6 +139,11 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) } } +static inline u32 sk_msg_iter_dist(u32 start, u32 end) +{ + return end >= start ? end - start : end + (MAX_MSG_FRAGS - start); +} + #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ @@ -198,9 +203,7 @@ static inline u32 sk_msg_elem_used(const struct sk_msg *msg) if (sk_msg_full(msg)) return MAX_MSG_FRAGS; - return msg->sg.end >= msg->sg.start ? - msg->sg.end - msg->sg.start : - msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); + return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) diff --git a/include/linux/socket.h b/include/linux/socket.h index fc0bed59fc84..09c32a21555b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -263,7 +263,7 @@ struct ucred { #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ -#define SOMAXCONN 128 +#define SOMAXCONN 4096 /* Flags we can use with send/ and recv. Added those for 1003.1g not all are supported yet @@ -392,6 +392,9 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); +extern int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 87d27e13d885..d796058cdff2 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -64,6 +64,11 @@ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt, return 0; } +static inline void xprt_destroy_backchannel(struct rpc_xprt *xprt, + unsigned int max_reqs) +{ +} + static inline bool svc_is_backchannel(const struct svc_rqst *rqstp) { return false; diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 5420817ed317..fa7ee503fb76 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -196,9 +196,9 @@ struct bin_attribute { .size = _size, \ } -#define __BIN_ATTR_WO(_name) { \ +#define __BIN_ATTR_WO(_name, _size) { \ .attr = { .name = __stringify(_name), .mode = 0200 }, \ - .store = _name##_store, \ + .write = _name##_write, \ .size = _size, \ } diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 53c0ea9ec9df..0d6e949ba315 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -21,6 +21,7 @@ #include <linux/acpi.h> #include <linux/cdev.h> #include <linux/fs.h> +#include <linux/highmem.h> #include <crypto/hash_info.h> #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ @@ -67,6 +68,8 @@ struct tpm_class_ops { u8 (*status) (struct tpm_chip *chip); void (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); + void (*update_durations)(struct tpm_chip *chip, + unsigned long *duration_cap); int (*go_idle)(struct tpm_chip *chip); int (*cmd_ready)(struct tpm_chip *chip); int (*request_locality)(struct tpm_chip *chip, int loc); @@ -161,6 +164,235 @@ struct tpm_chip { int locality; }; +#define TPM_HEADER_SIZE 10 + +enum tpm2_const { + TPM2_PLATFORM_PCR = 24, + TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), +}; + +enum tpm2_timeouts { + TPM2_TIMEOUT_A = 750, + TPM2_TIMEOUT_B = 2000, + TPM2_TIMEOUT_C = 200, + TPM2_TIMEOUT_D = 30, + TPM2_DURATION_SHORT = 20, + TPM2_DURATION_MEDIUM = 750, + TPM2_DURATION_LONG = 2000, + TPM2_DURATION_LONG_LONG = 300000, + TPM2_DURATION_DEFAULT = 120000, +}; + +enum tpm2_structures { + TPM2_ST_NO_SESSIONS = 0x8001, + TPM2_ST_SESSIONS = 0x8002, +}; + +/* Indicates from what layer of the software stack the error comes from */ +#define TSS2_RC_LAYER_SHIFT 16 +#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) + +enum tpm2_return_codes { + TPM2_RC_SUCCESS = 0x0000, + TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ + TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ + TPM2_RC_FAILURE = 0x0101, + TPM2_RC_DISABLED = 0x0120, + TPM2_RC_COMMAND_CODE = 0x0143, + TPM2_RC_TESTING = 0x090A, /* RC_WARN */ + TPM2_RC_REFERENCE_H0 = 0x0910, + TPM2_RC_RETRY = 0x0922, +}; + +enum tpm2_command_codes { + TPM2_CC_FIRST = 0x011F, + TPM2_CC_HIERARCHY_CONTROL = 0x0121, + TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, + TPM2_CC_CREATE_PRIMARY = 0x0131, + TPM2_CC_SEQUENCE_COMPLETE = 0x013E, + TPM2_CC_SELF_TEST = 0x0143, + TPM2_CC_STARTUP = 0x0144, + TPM2_CC_SHUTDOWN = 0x0145, + TPM2_CC_NV_READ = 0x014E, + TPM2_CC_CREATE = 0x0153, + TPM2_CC_LOAD = 0x0157, + TPM2_CC_SEQUENCE_UPDATE = 0x015C, + TPM2_CC_UNSEAL = 0x015E, + TPM2_CC_CONTEXT_LOAD = 0x0161, + TPM2_CC_CONTEXT_SAVE = 0x0162, + TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_VERIFY_SIGNATURE = 0x0177, + TPM2_CC_GET_CAPABILITY = 0x017A, + TPM2_CC_GET_RANDOM = 0x017B, + TPM2_CC_PCR_READ = 0x017E, + TPM2_CC_PCR_EXTEND = 0x0182, + TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, + TPM2_CC_HASH_SEQUENCE_START = 0x0186, + TPM2_CC_CREATE_LOADED = 0x0191, + TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ +}; + +enum tpm2_permanent_handles { + TPM2_RS_PW = 0x40000009, +}; + +enum tpm2_capabilities { + TPM2_CAP_HANDLES = 1, + TPM2_CAP_COMMANDS = 2, + TPM2_CAP_PCRS = 5, + TPM2_CAP_TPM_PROPERTIES = 6, +}; + +enum tpm2_properties { + TPM_PT_TOTAL_COMMANDS = 0x0129, +}; + +enum tpm2_startup_types { + TPM2_SU_CLEAR = 0x0000, + TPM2_SU_STATE = 0x0001, +}; + +enum tpm2_cc_attrs { + TPM2_CC_ATTR_CHANDLES = 25, + TPM2_CC_ATTR_RHANDLE = 28, +}; + +#define TPM_VID_INTEL 0x8086 +#define TPM_VID_WINBOND 0x1050 +#define TPM_VID_STM 0x104A + +enum tpm_chip_flags { + TPM_CHIP_FLAG_TPM2 = BIT(1), + TPM_CHIP_FLAG_IRQ = BIT(2), + TPM_CHIP_FLAG_VIRTUAL = BIT(3), + TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), + TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), + TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), +}; + +#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) + +struct tpm_header { + __be16 tag; + __be32 length; + union { + __be32 ordinal; + __be32 return_code; + }; +} __packed; + +/* A string buffer type for constructing TPM commands. This is based on the + * ideas of string buffer code in security/keys/trusted.h but is heap based + * in order to keep the stack usage minimal. + */ + +enum tpm_buf_flags { + TPM_BUF_OVERFLOW = BIT(0), +}; + +struct tpm_buf { + unsigned int flags; + u8 *data; +}; + +enum tpm2_object_attributes { + TPM2_OA_USER_WITH_AUTH = BIT(6), +}; + +enum tpm2_session_attributes { + TPM2_SA_CONTINUE_SESSION = BIT(0), +}; + +struct tpm2_hash { + unsigned int crypto_id; + unsigned int tpm_id; +}; + +static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + head->tag = cpu_to_be16(tag); + head->length = cpu_to_be32(sizeof(*head)); + head->ordinal = cpu_to_be32(ordinal); +} + +static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + buf->data = (u8 *)__get_free_page(GFP_KERNEL); + if (!buf->data) + return -ENOMEM; + + buf->flags = 0; + tpm_buf_reset(buf, tag, ordinal); + return 0; +} + +static inline void tpm_buf_destroy(struct tpm_buf *buf) +{ + free_page((unsigned long)buf->data); +} + +static inline u32 tpm_buf_length(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be32_to_cpu(head->length); +} + +static inline u16 tpm_buf_tag(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be16_to_cpu(head->tag); +} + +static inline void tpm_buf_append(struct tpm_buf *buf, + const unsigned char *new_data, + unsigned int new_len) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + u32 len = tpm_buf_length(buf); + + /* Return silently if overflow has already happened. */ + if (buf->flags & TPM_BUF_OVERFLOW) + return; + + if ((len + new_len) > PAGE_SIZE) { + WARN(1, "tpm_buf: overflow\n"); + buf->flags |= TPM_BUF_OVERFLOW; + return; + } + + memcpy(&buf->data[len], new_data, new_len); + head->length = cpu_to_be32(len + new_len); +} + +static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) +{ + tpm_buf_append(buf, &value, 1); +} + +static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) +{ + __be16 value2 = cpu_to_be16(value); + + tpm_buf_append(buf, (u8 *) &value2, 2); +} + +static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) +{ + __be32 value2 = cpu_to_be32(value); + + tpm_buf_append(buf, (u8 *) &value2, 4); +} + +static inline u32 tpm2_rc_value(u32 rc) +{ + return (rc & BIT(7)) ? rc & 0xff : rc; +} + #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); @@ -170,12 +402,6 @@ extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); -extern int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); -extern int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); extern struct tpm_chip *tpm_default_chip(void); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) @@ -204,18 +430,6 @@ static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) return -ENODEV; } -static inline int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} -static inline int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} static inline struct tpm_chip *tpm_default_chip(void) { return NULL; diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 4c7781f4b29b..07875ccc7bb5 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,7 +48,6 @@ struct virtio_vsock_sock { struct virtio_vsock_pkt { struct virtio_vsock_hdr hdr; - struct work_struct work; struct list_head list; /* socket refcnt not held, only use for cancellation */ struct vsock_sock *vsk; diff --git a/include/net/bonding.h b/include/net/bonding.h index f7fe45689142..3d56b026bb9e 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -159,7 +159,6 @@ struct slave { unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 link_new_state; /* one of BOND_LINK_XXXX */ - s8 new_link; u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ @@ -203,7 +202,6 @@ struct bonding { struct slave __rcu *primary_slave; struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ bool force_primary; - u32 nest_level; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); @@ -239,6 +237,7 @@ struct bonding { struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; + struct lock_class_key stats_lock_key; }; #define bond_slave_get_rcu(dev) \ @@ -549,7 +548,7 @@ static inline void bond_propose_link_state(struct slave *slave, int state) static inline void bond_commit_link_state(struct slave *slave, bool notify) { - if (slave->link == slave->link_new_state) + if (slave->link_new_state == BOND_LINK_NOCHANGE) return; slave->link = slave->link_new_state; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 127a5c4e3699..86e028388bad 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -122,7 +122,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL - sk->sk_napi_id = skb->napi_id; + WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif sk_rx_queue_set(sk, skb); } @@ -132,8 +132,8 @@ static inline void sk_mark_napi_id_once(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL - if (!sk->sk_napi_id) - sk->sk_napi_id = skb->napi_id; + if (!READ_ONCE(sk->sk_napi_id)) + WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif } diff --git a/include/net/devlink.h b/include/net/devlink.h index 23e4b65ec9df..2116c88663a1 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -38,7 +38,8 @@ struct devlink { struct device *dev; possible_net_t _net; struct mutex lock; - bool reload_failed; + u8 reload_failed:1, + reload_enabled:1; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -774,6 +775,8 @@ struct ib_device; struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); +void devlink_reload_enable(struct devlink *devlink); +void devlink_reload_disable(struct devlink *devlink); void devlink_free(struct devlink *devlink); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 90bd210be060..5cd12276ae21 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/in6.h> +#include <linux/siphash.h> #include <uapi/linux/if_ether.h> /** @@ -276,7 +277,7 @@ struct flow_keys_basic { struct flow_keys { struct flow_dissector_key_control control; #define FLOW_KEYS_HASH_START_FIELD basic - struct flow_dissector_key_basic basic; + struct flow_dissector_key_basic basic __aligned(SIPHASH_ALIGNMENT); struct flow_dissector_key_tags tags; struct flow_dissector_key_vlan vlan; struct flow_dissector_key_vlan cvlan; diff --git a/include/net/fq.h b/include/net/fq.h index d126b5d20261..2ad85e683041 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -69,7 +69,7 @@ struct fq { struct list_head backlogs; spinlock_t lock; u32 flows_cnt; - u32 perturbation; + siphash_key_t perturbation; u32 limit; u32 memory_limit; u32 memory_usage; diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index be40a4b327e3..38a9a3d1222b 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -108,7 +108,7 @@ begin: static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb) { - u32 hash = skb_get_hash_perturb(skb, fq->perturbation); + u32 hash = skb_get_hash_perturb(skb, &fq->perturbation); return reciprocal_scale(hash, fq->flows_cnt); } @@ -308,12 +308,12 @@ static int fq_init(struct fq *fq, int flows_cnt) INIT_LIST_HEAD(&fq->backlogs); spin_lock_init(&fq->lock); fq->flows_cnt = max_t(u32, flows_cnt, 1); - fq->perturbation = prandom_u32(); + get_random_bytes(&fq->perturbation, sizeof(fq->perturbation)); fq->quantum = 300; fq->limit = 8192; fq->memory_limit = 16 << 20; /* 16 MBytes */ - fq->flows = kcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); + fq->flows = kvcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); if (!fq->flows) return -ENOMEM; @@ -331,7 +331,7 @@ static void fq_reset(struct fq *fq, for (i = 0; i < fq->flows_cnt; i++) fq_flow_reset(fq, &fq->flows[i], free_func); - kfree(fq->flows); + kvfree(fq->flows); fq->flows = NULL; } diff --git a/include/net/hwbm.h b/include/net/hwbm.h index 81643cf8a1c4..c81444611a22 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -21,9 +21,13 @@ void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf); int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp); int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num); #else -void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {} -int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; } -int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num) +static inline void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {} + +static inline int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) +{ return 0; } + +static inline int hwbm_pool_add(struct hwbm_pool *bm_pool, + unsigned int buf_num) { return 0; } #endif /* CONFIG_HWBM */ #endif /* _HWBM_H */ diff --git a/include/net/ip.h b/include/net/ip.h index 95bb77f95bcc..a2c61c36dc4a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -185,7 +185,7 @@ static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter) } struct ip_frag_state { - struct iphdr *iph; + bool DF; unsigned int hlen; unsigned int ll_rs; unsigned int mtu; @@ -196,7 +196,7 @@ struct ip_frag_state { }; void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, - unsigned int mtu, struct ip_frag_state *state); + unsigned int mtu, bool DF, struct ip_frag_state *state); struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state); diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3759167f91f5..078887c8c586 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -889,6 +889,7 @@ struct netns_ipvs { struct delayed_work defense_work; /* Work handler */ int drop_rate; int drop_counter; + int old_secure_tcp; atomic_t dropentry; /* locks in ctl.c */ spinlock_t dropentry_lock; /* drop entry handling */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 50a67bd6a434..b8452cc0e059 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -439,8 +439,8 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { unsigned long now = jiffies; - if (neigh->used != now) - neigh->used = now; + if (READ_ONCE(neigh->used) != now) + WRITE_ONCE(neigh->used, now); if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE))) return __neigh_event_send(neigh, skb); return 0; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 4c2cd9378699..c7e15a213ef2 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -342,7 +342,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet) #define __net_initconst __initconst #endif -int peernet2id_alloc(struct net *net, struct net *peer); +int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp); int peernet2id(struct net *net, struct net *peer); bool peernet_has_id(struct net *net, struct net *peer); struct net *get_net_ns_by_id(struct net *net, int id); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 001d294edf57..2d0275f13bbf 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -820,7 +820,8 @@ struct nft_expr_ops { */ struct nft_expr { const struct nft_expr_ops *ops; - unsigned char data[]; + unsigned char data[] + __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_expr_priv(const struct nft_expr *expr) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 637548d54b3e..d80acda231ae 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -15,6 +15,7 @@ #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/atomic.h> +#include <linux/hashtable.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> #include <net/flow_offload.h> @@ -362,6 +363,7 @@ struct tcf_proto { bool deleting; refcount_t refcnt; struct rcu_head rcu; + struct hlist_node destroy_ht_node; }; struct qdisc_skb_cb { @@ -414,6 +416,8 @@ struct tcf_block { struct list_head filter_chain_list; } chain0; struct rcu_head rcu; + DECLARE_HASHTABLE(proto_destroy_ht, 7); + struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */ }; #ifdef CONFIG_PROVE_LOCKING diff --git a/include/net/sock.h b/include/net/sock.h index f69b58bff7e5..718e62fbe869 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -954,8 +954,8 @@ static inline void sk_incoming_cpu_update(struct sock *sk) { int cpu = raw_smp_processor_id(); - if (unlikely(sk->sk_incoming_cpu != cpu)) - sk->sk_incoming_cpu = cpu; + if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu)) + WRITE_ONCE(sk->sk_incoming_cpu, cpu); } static inline void sock_rps_record_flow_hash(__u32 hash) @@ -2242,12 +2242,17 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * sk_page_frag - return an appropriate page_frag * @sk: socket * - * If socket allocation mode allows current thread to sleep, it means its - * safe to use the per task page_frag instead of the per socket one. + * Use the per task page_frag instead of the per socket one for + * optimization when we know that we're in the normal context and owns + * everything that's associated with %current. + * + * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest + * inside other socket operations and end up recursing into sk_page_frag() + * while it's already in use. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (gfpflags_allow_blocking(sk->sk_allocation)) + if (gfpflags_normal_context(sk->sk_allocation)) return ¤t->task_frag; return &sk->sk_frag; @@ -2337,7 +2342,7 @@ static inline ktime_t sock_read_timestamp(struct sock *sk) return kt; #else - return sk->sk_stamp; + return READ_ONCE(sk->sk_stamp); #endif } @@ -2348,7 +2353,7 @@ static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else - sk->sk_stamp = kt; + WRITE_ONCE(sk->sk_stamp, kt); #endif } diff --git a/include/net/tls.h b/include/net/tls.h index c664e6dba0d1..f4ad831eaa02 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -40,6 +40,7 @@ #include <linux/socket.h> #include <linux/tcp.h> #include <linux/skmsg.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> @@ -269,6 +270,10 @@ struct tls_context { bool in_tcp_sendpages; bool pending_open_record_frags; + + struct mutex tx_lock; /* protects partially_sent_* fields and + * per-type TX fields + */ unsigned long flags; /* cache cold stuff */ @@ -351,6 +356,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int tls_sw_sendpage_locked(struct sock *sk, struct page *page, + int offset, size_t size, int flags); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 335283dbe9b3..373aadcfea21 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -197,6 +197,7 @@ struct vxlan_rdst { u8 offloaded:1; __be32 remote_vni; u32 remote_ifindex; + struct net_device *remote_dev; struct list_head list; struct rcu_head rcu; struct dst_cache dst_cache; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 6a47ba85c54c..e7e733add99f 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -366,7 +366,7 @@ struct ib_tm_caps { struct ib_cq_init_attr { unsigned int cqe; - int comp_vector; + u32 comp_vector; u32 flags; }; diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 985a5f583de4..31f76b6abf71 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -135,9 +135,9 @@ int asoc_simple_init_priv(struct asoc_simple_priv *priv, struct link_info *li); #ifdef DEBUG -inline void asoc_simple_debug_dai(struct asoc_simple_priv *priv, - char *name, - struct asoc_simple_dai *dai) +static inline void asoc_simple_debug_dai(struct asoc_simple_priv *priv, + char *name, + struct asoc_simple_dai *dai) { struct device *dev = simple_priv_to_dev(priv); @@ -167,7 +167,7 @@ inline void asoc_simple_debug_dai(struct asoc_simple_priv *priv, dev_dbg(dev, "%s clk %luHz\n", name, clk_get_rate(dai->clk)); } -inline void asoc_simple_debug_info(struct asoc_simple_priv *priv) +static inline void asoc_simple_debug_info(struct asoc_simple_priv *priv) { struct snd_soc_card *card = simple_priv_to_card(priv); struct device *dev = simple_priv_to_dev(priv); diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 5df604de4f11..75ae1899452b 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1688,6 +1688,7 @@ TRACE_EVENT(qgroup_update_reserve, __entry->qgid = qgroup->qgroupid; __entry->cur_reserved = qgroup->rsv.values[type]; __entry->diff = diff; + __entry->type = type; ), TP_printk_btrfs("qgid=%llu type=%s cur_reserved=%llu diff=%lld", @@ -1710,6 +1711,7 @@ TRACE_EVENT(qgroup_meta_reserve, TP_fast_assign_btrfs(root->fs_info, __entry->refroot = root->root_key.objectid; __entry->diff = diff; + __entry->type = type; ), TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld", @@ -1726,7 +1728,6 @@ TRACE_EVENT(qgroup_meta_convert, TP_STRUCT__entry_btrfs( __field( u64, refroot ) __field( s64, diff ) - __field( int, type ) ), TP_fast_assign_btrfs(root->fs_info, diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h new file mode 100644 index 000000000000..72a4d0174b02 --- /dev/null +++ b/include/trace/events/io_uring.h @@ -0,0 +1,358 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM io_uring + +#if !defined(_TRACE_IO_URING_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IO_URING_H + +#include <linux/tracepoint.h> + +struct io_wq_work; + +/** + * io_uring_create - called after a new io_uring context was prepared + * + * @fd: corresponding file descriptor + * @ctx: pointer to a ring context structure + * @sq_entries: actual SQ size + * @cq_entries: actual CQ size + * @flags: SQ ring flags, provided to io_uring_setup(2) + * + * Allows to trace io_uring creation and provide pointer to a context, that can + * be used later to find correlated events. + */ +TRACE_EVENT(io_uring_create, + + TP_PROTO(int fd, void *ctx, u32 sq_entries, u32 cq_entries, u32 flags), + + TP_ARGS(fd, ctx, sq_entries, cq_entries, flags), + + TP_STRUCT__entry ( + __field( int, fd ) + __field( void *, ctx ) + __field( u32, sq_entries ) + __field( u32, cq_entries ) + __field( u32, flags ) + ), + + TP_fast_assign( + __entry->fd = fd; + __entry->ctx = ctx; + __entry->sq_entries = sq_entries; + __entry->cq_entries = cq_entries; + __entry->flags = flags; + ), + + TP_printk("ring %p, fd %d sq size %d, cq size %d, flags %d", + __entry->ctx, __entry->fd, __entry->sq_entries, + __entry->cq_entries, __entry->flags) +); + +/** + * io_uring_register - called after a buffer/file/eventfd was succesfully + * registered for a ring + * + * @ctx: pointer to a ring context structure + * @opcode: describes which operation to perform + * @nr_user_files: number of registered files + * @nr_user_bufs: number of registered buffers + * @cq_ev_fd: whether eventfs registered or not + * @ret: return code + * + * Allows to trace fixed files/buffers/eventfds, that could be registered to + * avoid an overhead of getting references to them for every operation. This + * event, together with io_uring_file_get, can provide a full picture of how + * much overhead one can reduce via fixing. + */ +TRACE_EVENT(io_uring_register, + + TP_PROTO(void *ctx, unsigned opcode, unsigned nr_files, + unsigned nr_bufs, bool eventfd, long ret), + + TP_ARGS(ctx, opcode, nr_files, nr_bufs, eventfd, ret), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned, opcode ) + __field( unsigned, nr_files ) + __field( unsigned, nr_bufs ) + __field( bool, eventfd ) + __field( long, ret ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->opcode = opcode; + __entry->nr_files = nr_files; + __entry->nr_bufs = nr_bufs; + __entry->eventfd = eventfd; + __entry->ret = ret; + ), + + TP_printk("ring %p, opcode %d, nr_user_files %d, nr_user_bufs %d, " + "eventfd %d, ret %ld", + __entry->ctx, __entry->opcode, __entry->nr_files, + __entry->nr_bufs, __entry->eventfd, __entry->ret) +); + +/** + * io_uring_file_get - called before getting references to an SQE file + * + * @ctx: pointer to a ring context structure + * @fd: SQE file descriptor + * + * Allows to trace out how often an SQE file reference is obtained, which can + * help figuring out if it makes sense to use fixed files, or check that fixed + * files are used correctly. + */ +TRACE_EVENT(io_uring_file_get, + + TP_PROTO(void *ctx, int fd), + + TP_ARGS(ctx, fd), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( int, fd ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->fd = fd; + ), + + TP_printk("ring %p, fd %d", __entry->ctx, __entry->fd) +); + +/** + * io_uring_queue_async_work - called before submitting a new async work + * + * @ctx: pointer to a ring context structure + * @hashed: type of workqueue, hashed or normal + * @req: pointer to a submitted request + * @work: pointer to a submitted io_wq_work + * + * Allows to trace asynchronous work submission. + */ +TRACE_EVENT(io_uring_queue_async_work, + + TP_PROTO(void *ctx, int rw, void * req, struct io_wq_work *work, + unsigned int flags), + + TP_ARGS(ctx, rw, req, work, flags), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( int, rw ) + __field( void *, req ) + __field( struct io_wq_work *, work ) + __field( unsigned int, flags ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->rw = rw; + __entry->req = req; + __entry->work = work; + __entry->flags = flags; + ), + + TP_printk("ring %p, request %p, flags %d, %s queue, work %p", + __entry->ctx, __entry->req, __entry->flags, + __entry->rw ? "hashed" : "normal", __entry->work) +); + +/** + * io_uring_defer_list - called before the io_uring work added into defer_list + * + * @ctx: pointer to a ring context structure + * @req: pointer to a deferred request + * @shadow: whether request is shadow or not + * + * Allows to track deferred requests, to get an insight about what requests are + * not started immediately. + */ +TRACE_EVENT(io_uring_defer, + + TP_PROTO(void *ctx, void *req, bool shadow), + + TP_ARGS(ctx, req, shadow), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( void *, req ) + __field( bool, shadow ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->req = req; + __entry->shadow = shadow; + ), + + TP_printk("ring %p, request %p%s", __entry->ctx, __entry->req, + __entry->shadow ? ", shadow": "") +); + +/** + * io_uring_link - called before the io_uring request added into link_list of + * another request + * + * @ctx: pointer to a ring context structure + * @req: pointer to a linked request + * @target_req: pointer to a previous request, that would contain @req + * + * Allows to track linked requests, to understand dependencies between requests + * and how does it influence their execution flow. + */ +TRACE_EVENT(io_uring_link, + + TP_PROTO(void *ctx, void *req, void *target_req), + + TP_ARGS(ctx, req, target_req), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( void *, req ) + __field( void *, target_req ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->req = req; + __entry->target_req = target_req; + ), + + TP_printk("ring %p, request %p linked after %p", + __entry->ctx, __entry->req, __entry->target_req) +); + +/** + * io_uring_cqring_wait - called before start waiting for an available CQE + * + * @ctx: pointer to a ring context structure + * @min_events: minimal number of events to wait for + * + * Allows to track waiting for CQE, so that we can e.g. troubleshoot + * situations, when an application wants to wait for an event, that never + * comes. + */ +TRACE_EVENT(io_uring_cqring_wait, + + TP_PROTO(void *ctx, int min_events), + + TP_ARGS(ctx, min_events), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( int, min_events ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->min_events = min_events; + ), + + TP_printk("ring %p, min_events %d", __entry->ctx, __entry->min_events) +); + +/** + * io_uring_fail_link - called before failing a linked request + * + * @req: request, which links were cancelled + * @link: cancelled link + * + * Allows to track linked requests cancellation, to see not only that some work + * was cancelled, but also which request was the reason. + */ +TRACE_EVENT(io_uring_fail_link, + + TP_PROTO(void *req, void *link), + + TP_ARGS(req, link), + + TP_STRUCT__entry ( + __field( void *, req ) + __field( void *, link ) + ), + + TP_fast_assign( + __entry->req = req; + __entry->link = link; + ), + + TP_printk("request %p, link %p", __entry->req, __entry->link) +); + +/** + * io_uring_complete - called when completing an SQE + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: result of the request + * + */ +TRACE_EVENT(io_uring_complete, + + TP_PROTO(void *ctx, u64 user_data, long res), + + TP_ARGS(ctx, user_data, res), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( u64, user_data ) + __field( long, res ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + ), + + TP_printk("ring %p, user_data 0x%llx, result %ld", + __entry->ctx, (unsigned long long)__entry->user_data, + __entry->res) +); + + +/** + * io_uring_submit_sqe - called before submitting one SQE + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @force_nonblock: whether a context blocking or not + * @sq_thread: true if sq_thread has submitted this SQE + * + * Allows to track SQE submitting, to understand what was the source of it, SQ + * thread or io_uring_enter call. + */ +TRACE_EVENT(io_uring_submit_sqe, + + TP_PROTO(void *ctx, u64 user_data, bool force_nonblock, bool sq_thread), + + TP_ARGS(ctx, user_data, force_nonblock, sq_thread), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( u64, user_data ) + __field( bool, force_nonblock ) + __field( bool, sq_thread ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->force_nonblock = force_nonblock; + __entry->sq_thread = sq_thread; + ), + + TP_printk("ring %p, user data 0x%llx, non block %d, sq_thread %d", + __entry->ctx, (unsigned long long) __entry->user_data, + __entry->force_nonblock, __entry->sq_thread) +); + +#endif /* _TRACE_IO_URING_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 2bc9960a31aa..cf97f6339acb 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -86,7 +86,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s\n", + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->state)) diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index b048694070e2..37342a13c9cb 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -33,7 +33,8 @@ TRACE_EVENT(wbt_stat, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->rmean = stat[0].mean; __entry->rmin = stat[0].min; __entry->rmax = stat[0].max; @@ -67,7 +68,8 @@ TRACE_EVENT(wbt_lat, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->lat = div_u64(lat, 1000); ), @@ -103,7 +105,8 @@ TRACE_EVENT(wbt_step, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->msg = msg; __entry->step = step; __entry->window = div_u64(window, 1000); @@ -138,7 +141,8 @@ TRACE_EVENT(wbt_timer, ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + strlcpy(__entry->name, dev_name(bdi->dev), + ARRAY_SIZE(__entry->name)); __entry->status = status; __entry->step = step; __entry->inflight = inflight; diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 498eec813494..0cdef67135f0 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -120,9 +120,11 @@ struct blk_zone_report { }; /** - * struct blk_zone_range - BLKRESETZONE ioctl request - * @sector: starting sector of the first zone to issue reset write pointer - * @nr_sectors: Total number of sectors of 1 or more zones to reset + * struct blk_zone_range - BLKRESETZONE/BLKOPENZONE/ + * BLKCLOSEZONE/BLKFINISHZONE ioctl + * requests + * @sector: Starting sector of the first zone to operate on. + * @nr_sectors: Total number of sectors of all zones to operate on. */ struct blk_zone_range { __u64 sector; @@ -139,10 +141,19 @@ struct blk_zone_range { * sector range. The sector range must be zone aligned. * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors. * @BLKGETNRZONES: Get the total number of zones of the device. + * @BLKOPENZONE: Open the zones in the specified sector range. + * The 512 B sector range must be zone aligned. + * @BLKCLOSEZONE: Close the zones in the specified sector range. + * The 512 B sector range must be zone aligned. + * @BLKFINISHZONE: Mark the zones as full in the specified sector range. + * The 512 B sector range must be zone aligned. */ #define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) #define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) #define BLKGETZONESZ _IOR(0x12, 132, __u32) #define BLKGETNRZONES _IOR(0x12, 133, __u32) +#define BLKOPENZONE _IOW(0x12, 134, struct blk_zone_range) +#define BLKCLOSEZONE _IOW(0x12, 135, struct blk_zone_range) +#define BLKFINISHZONE _IOW(0x12, 136, struct blk_zone_range) #endif /* _UAPI_BLKZONED_H */ diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index 1e988fdeba34..6a6d2c7655ff 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can.h * diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index 0fb328d93148..dd2b925b09ac 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/bcm.h * diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h index bfc4b5d22a5e..34633283de64 100644 --- a/include/uapi/linux/can/error.h +++ b/include/uapi/linux/can/error.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/error.h * diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h index 3aea5388c8e4..c2190bbe21d8 100644 --- a/include/uapi/linux/can/gw.h +++ b/include/uapi/linux/can/gw.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/gw.h * diff --git a/include/uapi/linux/can/j1939.h b/include/uapi/linux/can/j1939.h index c32325342d30..df6e821075c1 100644 --- a/include/uapi/linux/can/j1939.h +++ b/include/uapi/linux/can/j1939.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * j1939.h * diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 1bc70d3a4d39..6f598b73839e 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * linux/can/netlink.h * diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h index be3b36e7ff61..6a11d308eb5c 100644 --- a/include/uapi/linux/can/raw.h +++ b/include/uapi/linux/can/raw.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/raw.h * diff --git a/include/uapi/linux/can/vxcan.h b/include/uapi/linux/can/vxcan.h index 066812d118a2..4fa9d8777a07 100644 --- a/include/uapi/linux/can/vxcan.h +++ b/include/uapi/linux/can/vxcan.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ #ifndef _UAPI_CAN_VXCAN_H #define _UAPI_CAN_VXCAN_H diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 580b7a2e40e1..a8a2174db030 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -421,6 +421,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_FAILED, /* u8 0 or 1 */ + DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, /* u64 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 1d338357df8a..1f97b33c840e 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -58,7 +58,7 @@ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be * used to clear any hints previously set. */ -#define RWF_WRITE_LIFE_NOT_SET 0 +#define RWH_WRITE_LIFE_NOT_SET 0 #define RWH_WRITE_LIFE_NONE 1 #define RWH_WRITE_LIFE_SHORT 2 #define RWH_WRITE_LIFE_MEDIUM 3 @@ -66,6 +66,13 @@ #define RWH_WRITE_LIFE_EXTREME 5 /* + * The originally introduced spelling is remained from the first + * versions of the patch set that introduced the feature, see commit + * v4.13-rc1~212^2~51. + */ +#define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET + +/* * Types of directory notifications that may be requested. */ #define DN_ACCESS 0x00000001 /* File accessed */ diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 802b0377a49e..373cada89815 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -38,6 +38,43 @@ * * Protocol changelog: * + * 7.1: + * - add the following messages: + * FUSE_SETATTR, FUSE_SYMLINK, FUSE_MKNOD, FUSE_MKDIR, FUSE_UNLINK, + * FUSE_RMDIR, FUSE_RENAME, FUSE_LINK, FUSE_OPEN, FUSE_READ, FUSE_WRITE, + * FUSE_RELEASE, FUSE_FSYNC, FUSE_FLUSH, FUSE_SETXATTR, FUSE_GETXATTR, + * FUSE_LISTXATTR, FUSE_REMOVEXATTR, FUSE_OPENDIR, FUSE_READDIR, + * FUSE_RELEASEDIR + * - add padding to messages to accommodate 32-bit servers on 64-bit kernels + * + * 7.2: + * - add FOPEN_DIRECT_IO and FOPEN_KEEP_CACHE flags + * - add FUSE_FSYNCDIR message + * + * 7.3: + * - add FUSE_ACCESS message + * - add FUSE_CREATE message + * - add filehandle to fuse_setattr_in + * + * 7.4: + * - add frsize to fuse_kstatfs + * - clean up request size limit checking + * + * 7.5: + * - add flags and max_write to fuse_init_out + * + * 7.6: + * - add max_readahead to fuse_init_in and fuse_init_out + * + * 7.7: + * - add FUSE_INTERRUPT message + * - add POSIX file lock support + * + * 7.8: + * - add lock_owner and flags fields to fuse_release_in + * - add FUSE_BMAP message + * - add FUSE_DESTROY message + * * 7.9: * - new fuse_getattr_in input argument of GETATTR * - add lk_flags in fuse_lk_in diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ea57526a5b89..2a1569211d87 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -19,7 +19,10 @@ struct io_uring_sqe { __u8 flags; /* IOSQE_ flags */ __u16 ioprio; /* ioprio for the request */ __s32 fd; /* file descriptor to do IO on */ - __u64 off; /* offset into file */ + union { + __u64 off; /* offset into file */ + __u64 addr2; + }; __u64 addr; /* pointer to buffer or iovecs */ __u32 len; /* buffer size or number of iovecs */ union { @@ -29,6 +32,8 @@ struct io_uring_sqe { __u32 sync_range_flags; __u32 msg_flags; __u32 timeout_flags; + __u32 accept_flags; + __u32 cancel_flags; }; __u64 user_data; /* data to be passed back at completion time */ union { @@ -50,6 +55,7 @@ struct io_uring_sqe { #define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */ #define IORING_SETUP_SQPOLL (1U << 1) /* SQ poll thread */ #define IORING_SETUP_SQ_AFF (1U << 2) /* sq_thread_cpu is valid */ +#define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */ #define IORING_OP_NOP 0 #define IORING_OP_READV 1 @@ -63,6 +69,10 @@ struct io_uring_sqe { #define IORING_OP_SENDMSG 9 #define IORING_OP_RECVMSG 10 #define IORING_OP_TIMEOUT 11 +#define IORING_OP_TIMEOUT_REMOVE 12 +#define IORING_OP_ACCEPT 13 +#define IORING_OP_ASYNC_CANCEL 14 +#define IORING_OP_LINK_TIMEOUT 15 /* * sqe->fsync_flags @@ -70,6 +80,11 @@ struct io_uring_sqe { #define IORING_FSYNC_DATASYNC (1U << 0) /* + * sqe->timeout_flags + */ +#define IORING_TIMEOUT_ABS (1U << 0) + +/* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { @@ -140,6 +155,7 @@ struct io_uring_params { * io_uring_params->features flags */ #define IORING_FEAT_SINGLE_MMAP (1U << 0) +#define IORING_FEAT_NODROP (1U << 1) /* * io_uring_register(2) opcodes and arguments @@ -150,5 +166,11 @@ struct io_uring_params { #define IORING_UNREGISTER_FILES 3 #define IORING_REGISTER_EVENTFD 4 #define IORING_UNREGISTER_EVENTFD 5 +#define IORING_REGISTER_FILES_UPDATE 6 + +struct io_uring_files_update { + __u32 offset; + __s32 *fds; +}; #endif diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index e168dc59e9a0..d99b5a772698 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -63,6 +63,7 @@ struct nvme_passthru_cmd64 { __u32 cdw14; __u32 cdw15; __u32 timeout_ms; + __u32 rsvd2; __u64 result; }; diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index 59e89a1bc3bb..9dc9d0079e98 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -31,13 +31,16 @@ #define PTP_ENABLE_FEATURE (1<<0) #define PTP_RISING_EDGE (1<<1) #define PTP_FALLING_EDGE (1<<2) +#define PTP_STRICT_FLAGS (1<<3) +#define PTP_EXTTS_EDGES (PTP_RISING_EDGE | PTP_FALLING_EDGE) /* * flag fields valid for the new PTP_EXTTS_REQUEST2 ioctl. */ #define PTP_EXTTS_VALID_FLAGS (PTP_ENABLE_FEATURE | \ PTP_RISING_EDGE | \ - PTP_FALLING_EDGE) + PTP_FALLING_EDGE | \ + PTP_STRICT_FLAGS) /* * flag fields valid for the original PTP_EXTTS_REQUEST ioctl. diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index 99335e1f4a27..25b4fa00bad1 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -51,6 +51,10 @@ * sent when the child exits. * @stack: Specify the location of the stack for the * child process. + * Note, @stack is expected to point to the + * lowest address. The stack direction will be + * determined by the kernel and set up + * appropriately based on @stack_size. * @stack_size: The size of the stack for the child process. * @tls: If CLONE_SETTLS is set, the tls descriptor * is set to tls. diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index c6d035fa1b6c..6f5af1a84213 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -113,6 +113,25 @@ struct opal_shadow_mbr { __u64 size; }; +/* Opal table operations */ +enum opal_table_ops { + OPAL_READ_TABLE, + OPAL_WRITE_TABLE, +}; + +#define OPAL_UID_LENGTH 8 +struct opal_read_write_table { + struct opal_key key; + const __u64 data; + const __u8 table_uid[OPAL_UID_LENGTH]; + __u64 offset; + __u64 size; +#define OPAL_TABLE_READ (1 << OPAL_READ_TABLE) +#define OPAL_TABLE_WRITE (1 << OPAL_WRITE_TABLE) + __u64 flags; + __u64 priv; +}; + #define IOC_OPAL_SAVE _IOW('p', 220, struct opal_lock_unlock) #define IOC_OPAL_LOCK_UNLOCK _IOW('p', 221, struct opal_lock_unlock) #define IOC_OPAL_TAKE_OWNERSHIP _IOW('p', 222, struct opal_key) @@ -128,5 +147,6 @@ struct opal_shadow_mbr { #define IOC_OPAL_PSID_REVERT_TPR _IOW('p', 232, struct opal_key) #define IOC_OPAL_MBR_DONE _IOW('p', 233, struct opal_mbr_done) #define IOC_OPAL_WRITE_SHADOW_MBR _IOW('p', 234, struct opal_shadow_mbr) +#define IOC_OPAL_GENERIC_TABLE_RW _IOW('p', 235, struct opal_read_write_table) #endif /* _UAPI_SED_OPAL_H */ diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..4d8d145c41d2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1548,6 +1548,7 @@ config AIO config IO_URING bool "Enable IO uring support" if EXPERT select ANON_INODES + select IO_WQ default y help This option enables support for the io_uring interface, enabling diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 1f31c2f1e6fc..4508d5e0cf69 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -351,12 +351,12 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent) struct dentry *d = kern_path_locked(watch->path, parent); if (IS_ERR(d)) return PTR_ERR(d); - inode_unlock(d_backing_inode(parent->dentry)); if (d_is_positive(d)) { /* update watch filter fields */ watch->dev = d->d_sb->s_dev; watch->ino = d_backing_inode(d)->i_ino; } + inode_unlock(d_backing_inode(parent->dentry)); dput(d); return 0; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ddd8addcdb5c..a3eaf08e7dd3 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1311,12 +1311,12 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type, return false; switch (off) { - case offsetof(struct bpf_sysctl, write): + case bpf_ctx_range(struct bpf_sysctl, write): if (type != BPF_READ) return false; bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); - case offsetof(struct bpf_sysctl, file_pos): + case bpf_ctx_range(struct bpf_sysctl, file_pos): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 66088a9e9b9e..ef0e1e3e66f4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -502,7 +502,7 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false)); } -void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) +static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d27f3b60ff6d..3867864cdc2f 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -128,7 +128,7 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) if (!dtab->n_buckets) /* Overflow check */ return -EINVAL; - cost += sizeof(struct hlist_head) * dtab->n_buckets; + cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets; } /* if map size is larger than memlock limit, reject it */ @@ -719,6 +719,32 @@ const struct bpf_map_ops dev_map_hash_ops = { .map_check_btf = map_check_no_btf, }; +static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, + struct net_device *netdev) +{ + unsigned long flags; + u32 i; + + spin_lock_irqsave(&dtab->index_lock, flags); + for (i = 0; i < dtab->n_buckets; i++) { + struct bpf_dtab_netdev *dev; + struct hlist_head *head; + struct hlist_node *next; + + head = dev_map_index_hash(dtab, i); + + hlist_for_each_entry_safe(dev, next, head, index_hlist) { + if (netdev != dev->dev) + continue; + + dtab->items--; + hlist_del_rcu(&dev->index_hlist); + call_rcu(&dev->rcu, __dev_map_entry_free); + } + } + spin_unlock_irqrestore(&dtab->index_lock, flags); +} + static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { @@ -735,6 +761,11 @@ static int dev_map_notification(struct notifier_block *notifier, */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { + if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dev_map_hash_remove_netdev(dtab, netdev); + continue; + } + for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index ba635209ae9a..5b9da0954a27 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -678,8 +678,10 @@ bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv) down_write(&bpf_devs_lock); if (!offdevs_inited) { err = rhashtable_init(&offdevs, &offdevs_params); - if (err) + if (err) { + up_write(&bpf_devs_lock); return ERR_PTR(err); + } offdevs_inited = true; } up_write(&bpf_devs_lock); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 82eabd4e38ad..ace1cfaa24b6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -126,7 +126,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -void *bpf_map_area_alloc(size_t size, int numa_node) +void *bpf_map_area_alloc(u64 size, int numa_node) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, @@ -141,6 +141,9 @@ void *bpf_map_area_alloc(size_t size, int numa_node) const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; + if (size >= SIZE_MAX) + return NULL; + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, numa_node); @@ -197,7 +200,7 @@ static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) atomic_long_sub(pages, &user->locked_vm); } -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size) +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) { u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; struct user_struct *user; @@ -1326,24 +1329,32 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); + kvfree(aux->func_info); free_used_maps(aux); bpf_prog_uncharge_memlock(aux->prog); security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } +static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) +{ + bpf_prog_kallsyms_del_all(prog); + btf_put(prog->aux->btf); + bpf_prog_free_linfo(prog); + + if (deferred) + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); + else + __bpf_prog_put_rcu(&prog->aux->rcu); +} + static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); - bpf_prog_kallsyms_del_all(prog); - btf_put(prog->aux->btf); - kvfree(prog->aux->func_info); - bpf_prog_free_linfo(prog); - - call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); + __bpf_prog_put_noref(prog, true); } } @@ -1741,11 +1752,12 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) return err; free_used_maps: - bpf_prog_free_linfo(prog); - kvfree(prog->aux->func_info); - btf_put(prog->aux->btf); - bpf_prog_kallsyms_del_subprogs(prog); - free_used_maps(prog->aux); + /* In case we have subprogs, we need to wait for a grace + * period before we can tear down JIT memory since symbols + * are already exposed under kallsyms. + */ + __bpf_prog_put_noref(prog, prog->aux->func_cnt); + return err; free_prog: bpf_prog_uncharge_memlock(prog); free_prog_sec: diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 080561bb8a4b..ef4242e5d4bc 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2119,11 +2119,12 @@ int cgroup_do_get_tree(struct fs_context *fc) nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); - fc->root = nsdentry; if (IS_ERR(nsdentry)) { - ret = PTR_ERR(nsdentry); deactivate_locked_super(sb); + ret = PTR_ERR(nsdentry); + nsdentry = NULL; } + fc->root = nsdentry; } if (!ctx->kfc.new_sb_created) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c52bc91f882b..c87ee6412b36 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -798,7 +798,8 @@ static int generate_sched_domains(cpumask_var_t **domains, cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) continue; - if (is_sched_load_balance(cp)) + if (is_sched_load_balance(cp) && + !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree if not a partition root */ diff --git a/kernel/cpu.c b/kernel/cpu.c index fc28e17940e0..e2cad3ee2ead 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2373,7 +2373,18 @@ void __init boot_cpu_hotplug_init(void) this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } -enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; +/* + * These are used for a global "mitigations=" cmdline option for toggling + * optional CPU mitigations. + */ +enum cpu_mitigations { + CPU_MITIGATIONS_OFF, + CPU_MITIGATIONS_AUTO, + CPU_MITIGATIONS_AUTO_NOSMT, +}; + +static enum cpu_mitigations cpu_mitigations __ro_after_init = + CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { @@ -2390,3 +2401,17 @@ static int __init mitigations_parse_cmdline(char *arg) return 0; } early_param("mitigations", mitigations_parse_cmdline); + +/* mitigations=off */ +bool cpu_mitigations_off(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_OFF; +} +EXPORT_SYMBOL_GPL(cpu_mitigations_off); + +/* mitigations=auto,nosmt */ +bool cpu_mitigations_auto_nosmt(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; +} +EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); diff --git a/kernel/events/core.c b/kernel/events/core.c index 9ec0b0bfddbd..00a014670ed0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1031,7 +1031,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, { } -void +static inline void perf_cgroup_switch(struct task_struct *task, struct task_struct *next) { } @@ -5607,8 +5607,10 @@ static void perf_mmap_close(struct vm_area_struct *vma) perf_pmu_output_stop(event); /* now it's safe to free the pages */ - atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); - atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm); + if (!rb->aux_mmap_locked) + atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); + else + atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm); /* this has to be the last one */ rb_free_aux(rb); @@ -6947,7 +6949,7 @@ static void __perf_event_output_stop(struct perf_event *event, void *data) static int __perf_pmu_output_stop(void *info) { struct perf_event *event = info; - struct pmu *pmu = event->pmu; + struct pmu *pmu = event->ctx->pmu; struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); struct remote_output ro = { .rb = event->rb, @@ -10533,6 +10535,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, goto err_ns; } + /* + * Disallow uncore-cgroup events, they don't make sense as the cgroup will + * be different on other CPUs in the uncore mask. + */ + if (pmu->task_ctx_nr == perf_invalid_context && cgroup_fd != -1) { + err = -EINVAL; + goto err_pmu; + } + if (event->attr.aux_output && !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) { err = -EOPNOTSUPP; @@ -10633,7 +10644,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, attr->size = size; - if (attr->__reserved_1) + if (attr->__reserved_1 || attr->__reserved_2) return -EINVAL; if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) @@ -11321,8 +11332,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, int err; /* - * Get the target context (task or percpu): + * Grouping is not supported for kernel events, neither is 'AUX', + * make sure the caller's intentions are adjusted. */ + if (attr->aux_output) + return ERR_PTR(-EINVAL); event = perf_event_alloc(attr, cpu, task, NULL, NULL, overflow_handler, context, -1); @@ -11334,6 +11348,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, /* Mark owner so we could distinguish it from user events. */ event->owner = TASK_TOMBSTONE; + /* + * Get the target context (task or percpu): + */ ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); @@ -11785,7 +11802,7 @@ inherit_event(struct perf_event *parent_event, GFP_KERNEL); if (!child_ctx->task_ctx_data) { free_event(child_event); - return NULL; + return ERR_PTR(-ENOMEM); } } @@ -11888,7 +11905,7 @@ static int inherit_group(struct perf_event *parent_event, if (IS_ERR(child_ctr)) return PTR_ERR(child_ctr); - if (sub->aux_event == parent_event && + if (sub->aux_event == parent_event && child_ctr && !perf_get_aux_event(child_ctr, leader)) return -EINVAL; } diff --git a/kernel/fork.c b/kernel/fork.c index bcdf53125210..13b38794efb5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1708,11 +1708,11 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) /* * Poll support for process exit notification. */ -static unsigned int pidfd_poll(struct file *file, struct poll_table_struct *pts) +static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct task_struct *task; struct pid *pid = file->private_data; - int poll_flags = 0; + __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); @@ -1724,7 +1724,7 @@ static unsigned int pidfd_poll(struct file *file, struct poll_table_struct *pts) * group, then poll(2) should block, similar to the wait(2) family. */ if (!task || (task->exit_state && thread_group_empty(task))) - poll_flags = POLLIN | POLLRDNORM; + poll_flags = EPOLLIN | EPOLLRDNORM; rcu_read_unlock(); return poll_flags; @@ -2561,7 +2561,35 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, return 0; } -static bool clone3_args_valid(const struct kernel_clone_args *kargs) +/** + * clone3_stack_valid - check and prepare stack + * @kargs: kernel clone args + * + * Verify that the stack arguments userspace gave us are sane. + * In addition, set the stack direction for userspace since it's easy for us to + * determine. + */ +static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) +{ + if (kargs->stack == 0) { + if (kargs->stack_size > 0) + return false; + } else { + if (kargs->stack_size == 0) + return false; + + if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) + return false; + +#if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64) + kargs->stack += kargs->stack_size; +#endif + } + + return true; +} + +static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* * All lower bits of the flag word are taken. @@ -2581,6 +2609,9 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs) kargs->exit_signal) return false; + if (!clone3_stack_valid(kargs)) + return false; + return true; } diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 132672b74e4b..dd822fd8a7d5 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops); * @type: Type of irqchip_fwnode. See linux/irqdomain.h * @name: Optional user provided domain name * @id: Optional user provided id if name != NULL - * @data: Optional user-provided data + * @pa: Optional user-provided physical address * * Allocate a struct irqchip_fwid, and return a poiner to the embedded * fwnode_handle (or NULL on failure). diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 9568a2fe7c11..a45cba7df0ae 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -650,3 +650,249 @@ static int __init pm_qos_power_init(void) } late_initcall(pm_qos_power_init); + +/* Definitions related to the frequency QoS below. */ + +/** + * freq_constraints_init - Initialize frequency QoS constraints. + * @qos: Frequency QoS constraints to initialize. + */ +void freq_constraints_init(struct freq_constraints *qos) +{ + struct pm_qos_constraints *c; + + c = &qos->min_freq; + plist_head_init(&c->list); + c->target_value = FREQ_QOS_MIN_DEFAULT_VALUE; + c->default_value = FREQ_QOS_MIN_DEFAULT_VALUE; + c->no_constraint_value = FREQ_QOS_MIN_DEFAULT_VALUE; + c->type = PM_QOS_MAX; + c->notifiers = &qos->min_freq_notifiers; + BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers); + + c = &qos->max_freq; + plist_head_init(&c->list); + c->target_value = FREQ_QOS_MAX_DEFAULT_VALUE; + c->default_value = FREQ_QOS_MAX_DEFAULT_VALUE; + c->no_constraint_value = FREQ_QOS_MAX_DEFAULT_VALUE; + c->type = PM_QOS_MIN; + c->notifiers = &qos->max_freq_notifiers; + BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers); +} + +/** + * freq_qos_read_value - Get frequency QoS constraint for a given list. + * @qos: Constraints to evaluate. + * @type: QoS request type. + */ +s32 freq_qos_read_value(struct freq_constraints *qos, + enum freq_qos_req_type type) +{ + s32 ret; + + switch (type) { + case FREQ_QOS_MIN: + ret = IS_ERR_OR_NULL(qos) ? + FREQ_QOS_MIN_DEFAULT_VALUE : + pm_qos_read_value(&qos->min_freq); + break; + case FREQ_QOS_MAX: + ret = IS_ERR_OR_NULL(qos) ? + FREQ_QOS_MAX_DEFAULT_VALUE : + pm_qos_read_value(&qos->max_freq); + break; + default: + WARN_ON(1); + ret = 0; + } + + return ret; +} + +/** + * freq_qos_apply - Add/modify/remove frequency QoS request. + * @req: Constraint request to apply. + * @action: Action to perform (add/update/remove). + * @value: Value to assign to the QoS request. + */ +static int freq_qos_apply(struct freq_qos_request *req, + enum pm_qos_req_action action, s32 value) +{ + int ret; + + switch(req->type) { + case FREQ_QOS_MIN: + ret = pm_qos_update_target(&req->qos->min_freq, &req->pnode, + action, value); + break; + case FREQ_QOS_MAX: + ret = pm_qos_update_target(&req->qos->max_freq, &req->pnode, + action, value); + break; + default: + ret = -EINVAL; + } + + return ret; +} + +/** + * freq_qos_add_request - Insert new frequency QoS request into a given list. + * @qos: Constraints to update. + * @req: Preallocated request object. + * @type: Request type. + * @value: Request value. + * + * Insert a new entry into the @qos list of requests, recompute the effective + * QoS constraint value for that list and initialize the @req object. The + * caller needs to save that object for later use in updates and removal. + * + * Return 1 if the effective constraint value has changed, 0 if the effective + * constraint value has not changed, or a negative error code on failures. + */ +int freq_qos_add_request(struct freq_constraints *qos, + struct freq_qos_request *req, + enum freq_qos_req_type type, s32 value) +{ + int ret; + + if (IS_ERR_OR_NULL(qos) || !req) + return -EINVAL; + + if (WARN(freq_qos_request_active(req), + "%s() called for active request\n", __func__)) + return -EINVAL; + + req->qos = qos; + req->type = type; + ret = freq_qos_apply(req, PM_QOS_ADD_REQ, value); + if (ret < 0) { + req->qos = NULL; + req->type = 0; + } + + return ret; +} +EXPORT_SYMBOL_GPL(freq_qos_add_request); + +/** + * freq_qos_update_request - Modify existing frequency QoS request. + * @req: Request to modify. + * @new_value: New request value. + * + * Update an existing frequency QoS request along with the effective constraint + * value for the list of requests it belongs to. + * + * Return 1 if the effective constraint value has changed, 0 if the effective + * constraint value has not changed, or a negative error code on failures. + */ +int freq_qos_update_request(struct freq_qos_request *req, s32 new_value) +{ + if (!req) + return -EINVAL; + + if (WARN(!freq_qos_request_active(req), + "%s() called for unknown object\n", __func__)) + return -EINVAL; + + if (req->pnode.prio == new_value) + return 0; + + return freq_qos_apply(req, PM_QOS_UPDATE_REQ, new_value); +} +EXPORT_SYMBOL_GPL(freq_qos_update_request); + +/** + * freq_qos_remove_request - Remove frequency QoS request from its list. + * @req: Request to remove. + * + * Remove the given frequency QoS request from the list of constraints it + * belongs to and recompute the effective constraint value for that list. + * + * Return 1 if the effective constraint value has changed, 0 if the effective + * constraint value has not changed, or a negative error code on failures. + */ +int freq_qos_remove_request(struct freq_qos_request *req) +{ + int ret; + + if (!req) + return -EINVAL; + + if (WARN(!freq_qos_request_active(req), + "%s() called for unknown object\n", __func__)) + return -EINVAL; + + ret = freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); + req->qos = NULL; + req->type = 0; + + return ret; +} +EXPORT_SYMBOL_GPL(freq_qos_remove_request); + +/** + * freq_qos_add_notifier - Add frequency QoS change notifier. + * @qos: List of requests to add the notifier to. + * @type: Request type. + * @notifier: Notifier block to add. + */ +int freq_qos_add_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier) +{ + int ret; + + if (IS_ERR_OR_NULL(qos) || !notifier) + return -EINVAL; + + switch (type) { + case FREQ_QOS_MIN: + ret = blocking_notifier_chain_register(qos->min_freq.notifiers, + notifier); + break; + case FREQ_QOS_MAX: + ret = blocking_notifier_chain_register(qos->max_freq.notifiers, + notifier); + break; + default: + WARN_ON(1); + ret = -EINVAL; + } + + return ret; +} +EXPORT_SYMBOL_GPL(freq_qos_add_notifier); + +/** + * freq_qos_remove_notifier - Remove frequency QoS change notifier. + * @qos: List of requests to remove the notifier from. + * @type: Request type. + * @notifier: Notifier block to remove. + */ +int freq_qos_remove_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier) +{ + int ret; + + if (IS_ERR_OR_NULL(qos) || !notifier) + return -EINVAL; + + switch (type) { + case FREQ_QOS_MIN: + ret = blocking_notifier_chain_unregister(qos->min_freq.notifiers, + notifier); + break; + case FREQ_QOS_MAX: + ret = blocking_notifier_chain_unregister(qos->max_freq.notifiers, + notifier); + break; + default: + WARN_ON(1); + ret = -EINVAL; + } + + return ret; +} +EXPORT_SYMBOL_GPL(freq_qos_remove_notifier); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index dd05a378631a..80b60ca7767f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -16,6 +16,7 @@ #include <asm/tlb.h> #include "../workqueue_internal.h" +#include "../../fs/io-wq.h" #include "../smpboot.h" #include "pelt.h" @@ -1065,7 +1066,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) * affecting a valid clamp bucket, the next time it's enqueued, * it will already see the updated clamp bucket value. */ - if (!p->uclamp[clamp_id].active) { + if (p->uclamp[clamp_id].active) { uclamp_rq_dec_id(rq, p, clamp_id); uclamp_rq_inc_id(rq, p, clamp_id); } @@ -1073,6 +1074,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) task_rq_unlock(rq, p, &rf); } +#ifdef CONFIG_UCLAMP_TASK_GROUP static inline void uclamp_update_active_tasks(struct cgroup_subsys_state *css, unsigned int clamps) @@ -1091,7 +1093,6 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css, css_task_iter_end(&it); } -#ifdef CONFIG_UCLAMP_TASK_GROUP static void cpu_util_update_eff(struct cgroup_subsys_state *css); static void uclamp_update_root_tg(void) { @@ -3929,13 +3930,22 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } restart: +#ifdef CONFIG_SMP /* - * Ensure that we put DL/RT tasks before the pick loop, such that they - * can PULL higher prio tasks when we lower the RQ 'priority'. + * We must do the balancing pass before put_next_task(), such + * that when we release the rq->lock the task is in the same + * state as before we took rq->lock. + * + * We can terminate the balance pass as soon as we know there is + * a runnable task of @class priority or higher. */ - prev->sched_class->put_prev_task(rq, prev, rf); - if (!rq->nr_running) - newidle_balance(rq, rf); + for_class_range(class, prev->sched_class, &idle_sched_class) { + if (class->balance(rq, prev, rf)) + break; + } +#endif + + put_prev_task(rq, prev); for_each_class(class) { p = class->pick_next_task(rq, NULL, NULL); @@ -4103,9 +4113,12 @@ static inline void sched_submit_work(struct task_struct *tsk) * we disable preemption to avoid it calling schedule() again * in the possible wakeup of a kworker. */ - if (tsk->flags & PF_WQ_WORKER) { + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { preempt_disable(); - wq_worker_sleeping(tsk); + if (tsk->flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + else + io_wq_worker_sleeping(tsk); preempt_enable_no_resched(); } @@ -4122,8 +4135,12 @@ static inline void sched_submit_work(struct task_struct *tsk) static void sched_update_worker(struct task_struct *tsk) { - if (tsk->flags & PF_WQ_WORKER) - wq_worker_running(tsk); + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); + else + io_wq_worker_running(tsk); + } } asmlinkage __visible void __sched schedule(void) @@ -6010,10 +6027,11 @@ void init_idle(struct task_struct *idle, int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; + __sched_fork(0, idle); + raw_spin_lock_irqsave(&idle->pi_lock, flags); raw_spin_lock(&rq->lock); - __sched_fork(0, idle); idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); idle->flags |= PF_IDLE; @@ -6201,7 +6219,7 @@ static struct task_struct *__pick_migrate_task(struct rq *rq) for_each_class(class) { next = class->pick_next_task(rq, NULL, NULL); if (next) { - next->sched_class->put_prev_task(rq, next, NULL); + next->sched_class->put_prev_task(rq, next); return next; } } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 2dc48720f189..a8a08030a8f7 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1691,6 +1691,22 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) resched_curr(rq); } +static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +{ + if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_dl_task(rq); + rq_repin_lock(rq, rf); + } + + return sched_stop_runnable(rq) || sched_dl_runnable(rq); +} #endif /* CONFIG_SMP */ /* @@ -1758,45 +1774,28 @@ static struct task_struct * pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct sched_dl_entity *dl_se; + struct dl_rq *dl_rq = &rq->dl; struct task_struct *p; - struct dl_rq *dl_rq; WARN_ON_ONCE(prev || rf); - dl_rq = &rq->dl; - - if (unlikely(!dl_rq->dl_nr_running)) + if (!sched_dl_runnable(rq)) return NULL; dl_se = pick_next_dl_entity(rq, dl_rq); BUG_ON(!dl_se); - p = dl_task_of(dl_se); - set_next_task_dl(rq, p); - return p; } -static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); - - if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we've - * not yet started the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_dl_task(rq); - rq_repin_lock(rq, rf); - } } /* @@ -2442,6 +2441,7 @@ const struct sched_class dl_sched_class = { .set_next_task = set_next_task_dl, #ifdef CONFIG_SMP + .balance = balance_dl, .select_task_rq = select_task_rq_dl, .migrate_task_rq = migrate_task_rq_dl, .set_cpus_allowed = set_cpus_allowed_dl, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 682a754ea3e1..69a81a5709ff 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6570,6 +6570,15 @@ static void task_dead_fair(struct task_struct *p) { remove_entity_load_avg(&p->se); } + +static int +balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + if (rq->nr_running) + return 1; + + return newidle_balance(rq, rf) != 0; +} #endif /* CONFIG_SMP */ static unsigned long wakeup_gran(struct sched_entity *se) @@ -6746,7 +6755,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf int new_tasks; again: - if (!cfs_rq->nr_running) + if (!sched_fair_runnable(rq)) goto idle; #ifdef CONFIG_FAIR_GROUP_SCHED @@ -6884,7 +6893,7 @@ idle: /* * Account for a descheduled task: */ -static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) { struct sched_entity *se = &prev->se; struct cfs_rq *cfs_rq; @@ -7539,6 +7548,19 @@ static void update_blocked_averages(int cpu) update_rq_clock(rq); /* + * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure + * that RT, DL and IRQ signals have been updated before updating CFS. + */ + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); + update_irq_load_avg(rq, 0); + + /* Don't need periodic decay once load/util_avg are null */ + if (others_have_blocked(rq)) + done = false; + + /* * Iterates the task_group tree in a bottom up fashion, see * list_add_leaf_cfs_rq() for details. */ @@ -7565,14 +7587,6 @@ static void update_blocked_averages(int cpu) done = false; } - curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); - update_irq_load_avg(rq, 0); - /* Don't need periodic decay once load/util_avg are null */ - if (others_have_blocked(rq)) - done = false; - update_blocked_load_status(rq, !done); rq_unlock_irqrestore(rq, &rf); } @@ -7633,12 +7647,18 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); + /* + * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure + * that RT, DL and IRQ signals have been updated before updating CFS. + */ curr_class = rq->curr->sched_class; update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); + + update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); + update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq)); rq_unlock_irqrestore(rq, &rf); } @@ -10414,11 +10434,11 @@ const struct sched_class fair_sched_class = { .check_preempt_curr = check_preempt_wakeup, .pick_next_task = pick_next_task_fair, - .put_prev_task = put_prev_task_fair, .set_next_task = set_next_task_fair, #ifdef CONFIG_SMP + .balance = balance_fair, .select_task_rq = select_task_rq_fair, .migrate_task_rq = migrate_task_rq_fair, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8dad5aa600ea..f65ef1e2f204 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -365,6 +365,12 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } + +static int +balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + return WARN_ON_ONCE(1); +} #endif /* @@ -375,7 +381,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl resched_curr(rq); } -static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { } @@ -460,6 +466,7 @@ const struct sched_class idle_sched_class = { .set_next_task = set_next_task_idle, #ifdef CONFIG_SMP + .balance = balance_idle, .select_task_rq = select_task_rq_idle, .set_cpus_allowed = set_cpus_allowed_common, #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index ebaa4e619684..9b8adc01be3d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1469,6 +1469,22 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) resched_curr(rq); } +static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +{ + if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_rt_task(rq); + rq_repin_lock(rq, rf); + } + + return sched_stop_runnable(rq) || sched_dl_runnable(rq) || sched_rt_runnable(rq); +} #endif /* CONFIG_SMP */ /* @@ -1552,21 +1568,18 @@ static struct task_struct * pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *p; - struct rt_rq *rt_rq = &rq->rt; WARN_ON_ONCE(prev || rf); - if (!rt_rq->rt_queued) + if (!sched_rt_runnable(rq)) return NULL; p = _pick_next_task_rt(rq); - set_next_task_rt(rq, p); - return p; } -static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) +static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); @@ -1578,18 +1591,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_fla */ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); - - if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we've - * not yet started the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_rt_task(rq); - rq_repin_lock(rq, rf); - } } #ifdef CONFIG_SMP @@ -2366,8 +2367,8 @@ const struct sched_class rt_sched_class = { .set_next_task = set_next_task_rt, #ifdef CONFIG_SMP + .balance = balance_rt, .select_task_rq = select_task_rq_rt, - .set_cpus_allowed = set_cpus_allowed_common, .rq_online = rq_online_rt, .rq_offline = rq_offline_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0db2c1b3361e..c8870c5bd7df 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1727,10 +1727,11 @@ struct sched_class { struct task_struct * (*pick_next_task)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); - void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf); + void (*put_prev_task)(struct rq *rq, struct task_struct *p); void (*set_next_task)(struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP + int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); void (*migrate_task_rq)(struct task_struct *p, int new_cpu); @@ -1773,7 +1774,7 @@ struct sched_class { static inline void put_prev_task(struct rq *rq, struct task_struct *prev) { WARN_ON_ONCE(rq->curr != prev); - prev->sched_class->put_prev_task(rq, prev, NULL); + prev->sched_class->put_prev_task(rq, prev); } static inline void set_next_task(struct rq *rq, struct task_struct *next) @@ -1787,8 +1788,12 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next) #else #define sched_class_highest (&dl_sched_class) #endif + +#define for_class_range(class, _from, _to) \ + for (class = (_from); class != (_to); class = class->next) + #define for_each_class(class) \ - for (class = sched_class_highest; class; class = class->next) + for_class_range(class, sched_class_highest, NULL) extern const struct sched_class stop_sched_class; extern const struct sched_class dl_sched_class; @@ -1796,6 +1801,25 @@ extern const struct sched_class rt_sched_class; extern const struct sched_class fair_sched_class; extern const struct sched_class idle_sched_class; +static inline bool sched_stop_runnable(struct rq *rq) +{ + return rq->stop && task_on_rq_queued(rq->stop); +} + +static inline bool sched_dl_runnable(struct rq *rq) +{ + return rq->dl.dl_nr_running > 0; +} + +static inline bool sched_rt_runnable(struct rq *rq) +{ + return rq->rt.rt_queued > 0; +} + +static inline bool sched_fair_runnable(struct rq *rq) +{ + return rq->cfs.nr_running > 0; +} #ifdef CONFIG_SMP diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 7e1cee4e65b2..c0640739e05e 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -15,6 +15,12 @@ select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } + +static int +balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + return sched_stop_runnable(rq); +} #endif /* CONFIG_SMP */ static void @@ -31,16 +37,13 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop) static struct task_struct * pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { - struct task_struct *stop = rq->stop; - WARN_ON_ONCE(prev || rf); - if (!stop || !task_on_rq_queued(stop)) + if (!sched_stop_runnable(rq)) return NULL; - set_next_task_stop(rq, stop); - - return stop; + set_next_task_stop(rq, rq->stop); + return rq->stop; } static void @@ -60,7 +63,7 @@ static void yield_task_stop(struct rq *rq) BUG(); /* the stop task should never yield, its pointless. */ } -static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) { struct task_struct *curr = rq->curr; u64 delta_exec; @@ -129,6 +132,7 @@ const struct sched_class stop_sched_class = { .set_next_task = set_next_task_stop, #ifdef CONFIG_SMP + .balance = balance_stop, .select_task_rq = select_task_rq_stop, .set_cpus_allowed = set_cpus_allowed_common, #endif diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index b5667a273bf6..49b835f1305f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1948,7 +1948,7 @@ next_level: static int build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) { - enum s_alloc alloc_state; + enum s_alloc alloc_state = sa_none; struct sched_domain *sd; struct s_data d; struct rq *rq = NULL; @@ -1956,6 +1956,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att struct sched_domain_topology_level *tl_asym; bool has_asym = false; + if (WARN_ON(cpumask_empty(cpu_map))) + goto error; + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); if (alloc_state != sa_rootdomain) goto error; @@ -2026,7 +2029,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att rcu_read_unlock(); if (has_asym) - static_branch_enable_cpuslocked(&sched_asym_cpucapacity); + static_branch_inc_cpuslocked(&sched_asym_cpucapacity); if (rq && sched_debug_enabled) { pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n", @@ -2121,8 +2124,12 @@ int sched_init_domains(const struct cpumask *cpu_map) */ static void detach_destroy_domains(const struct cpumask *cpu_map) { + unsigned int cpu = cpumask_any(cpu_map); int i; + if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu))) + static_branch_dec_cpuslocked(&sched_asym_cpucapacity); + rcu_read_lock(); for_each_cpu(i, cpu_map) cpu_attach_domain(NULL, &def_root_domain, i); diff --git a/kernel/signal.c b/kernel/signal.c index c4da1ef56fdf..bcd46f547db3 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2205,8 +2205,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t */ preempt_disable(); read_unlock(&tasklist_lock); - preempt_enable_no_resched(); cgroup_enter_frozen(); + preempt_enable_no_resched(); freezable_schedule(); cgroup_leave_frozen(true); } else { diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 6d1f68b7e528..c9ea7eb2cb1a 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -141,7 +141,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store, struct stacktrace_cookie c = { .store = store, .size = size, - .skip = skipnr + 1, + /* skip this function if they are tracing us */ + .skip = skipnr + !!(current == tsk), }; if (!try_get_task_stack(tsk)) @@ -298,7 +299,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *task, struct stack_trace trace = { .entries = store, .max_entries = size, - .skip = skipnr + 1, + /* skip this function if they are tracing us */ + .skip = skipnr + !!(current == task), }; save_stack_trace_tsk(task, &trace); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 65eb796610dc..069ca78fb0bf 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -771,7 +771,7 @@ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, /* fill PPS status fields */ pps_fill_timex(txc); - txc->time.tv_sec = (time_t)ts->tv_sec; + txc->time.tv_sec = ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(time_status & STA_NANO)) txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 92a431981b1c..42d512fcfda2 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -266,7 +266,7 @@ static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, /** * thread_group_sample_cputime - Sample cputime for a given task * @tsk: Task for which cputime needs to be started - * @iimes: Storage for time samples + * @samples: Storage for time samples * * Called from sys_getitimer() to calculate the expiry time of an active * timer. That means group cputime accounting is already active. Called @@ -1038,12 +1038,12 @@ unlock: * member of @pct->bases[CLK].nextevt. False otherwise */ static inline bool -task_cputimers_expired(const u64 *sample, struct posix_cputimers *pct) +task_cputimers_expired(const u64 *samples, struct posix_cputimers *pct) { int i; for (i = 0; i < CPUCLOCK_MAX; i++) { - if (sample[i] >= pct->bases[i].nextevt) + if (samples[i] >= pct->bases[i].nextevt) return true; } return false; diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 142b07619918..dbd69052eaa6 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -17,6 +17,8 @@ #include <linux/seqlock.h> #include <linux/bitops.h> +#include "timekeeping.h" + /** * struct clock_read_data - data required to read from sched_clock() * diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 4bc37ac3bb05..5ee0f7709410 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -110,8 +110,7 @@ void update_vsyscall(struct timekeeper *tk) nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); - if (__arch_use_vsyscall(vdata)) - update_vdso_data(vdata, tk); + update_vdso_data(vdata, tk); __arch_update_vsyscall(vdata, tk); @@ -124,10 +123,8 @@ void update_vsyscall_tz(void) { struct vdso_data *vdata = __arch_get_k_vdso_data(); - if (__arch_use_vsyscall(vdata)) { - vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest; - vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime; - } + vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest; + vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime; __arch_sync_vdso_data(vdata); } diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0892e38ed6fb..a9dfa04ffa44 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -272,9 +272,11 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe) goto out; } + mutex_lock(&event_mutex); ret = perf_trace_event_init(tp_event, p_event); if (ret) destroy_local_trace_kprobe(tp_event); + mutex_unlock(&event_mutex); out: kfree(func); return ret; @@ -282,8 +284,10 @@ out: void perf_kprobe_destroy(struct perf_event *p_event) { + mutex_lock(&event_mutex); perf_trace_event_close(p_event); perf_trace_event_unreg(p_event); + mutex_unlock(&event_mutex); destroy_local_trace_kprobe(p_event->tp_event); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 57648c5aa679..7482a1466ebf 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -679,6 +679,8 @@ static bool synth_field_signed(char *type) { if (str_has_prefix(type, "u")) return false; + if (strcmp(type, "gfp_t") == 0) + return false; return true; } diff --git a/lib/Kconfig b/lib/Kconfig index 183f92a297ca..3321d04dfa5a 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -447,7 +447,6 @@ config ASSOCIATIVE_ARRAY config HAS_IOMEM bool depends on !NO_IOMEM - select GENERIC_IO default y config HAS_IOPORT_MAP diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 5cff72f18c4a..33ffbf308853 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -106,7 +106,12 @@ retry: was_locked = 1; } else { local_irq_restore(flags); - cpu_relax(); + /* + * Wait for the lock to release before jumping to + * atomic_cmpxchg() in order to mitigate the thundering herd + * problem. + */ + do { cpu_relax(); } while (atomic_read(&dump_lock) != -1); goto retry; } diff --git a/lib/idr.c b/lib/idr.c index 66a374892482..c2cf2c52bbde 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -215,7 +215,7 @@ int idr_for_each(const struct idr *idr, EXPORT_SYMBOL(idr_for_each); /** - * idr_get_next() - Find next populated entry. + * idr_get_next_ul() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * @@ -224,7 +224,7 @@ EXPORT_SYMBOL(idr_for_each); * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ -void *idr_get_next(struct idr *idr, int *nextid) +void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; @@ -245,18 +245,14 @@ void *idr_get_next(struct idr *idr, int *nextid) } if (!slot) return NULL; - id = iter.index + base; - - if (WARN_ON_ONCE(id > INT_MAX)) - return NULL; - *nextid = id; + *nextid = iter.index + base; return entry; } -EXPORT_SYMBOL(idr_get_next); +EXPORT_SYMBOL(idr_get_next_ul); /** - * idr_get_next_ul() - Find next populated entry. + * idr_get_next() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * @@ -265,22 +261,17 @@ EXPORT_SYMBOL(idr_get_next); * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ -void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) +void *idr_get_next(struct idr *idr, int *nextid) { - struct radix_tree_iter iter; - void __rcu **slot; - unsigned long base = idr->idr_base; unsigned long id = *nextid; + void *entry = idr_get_next_ul(idr, &id); - id = (id < base) ? 0 : id - base; - slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); - if (!slot) + if (WARN_ON_ONCE(id > INT_MAX)) return NULL; - - *nextid = iter.index + base; - return rcu_dereference_raw(*slot); + *nextid = id; + return entry; } -EXPORT_SYMBOL(idr_get_next_ul); +EXPORT_SYMBOL(idr_get_next); /** * idr_replace() - replace pointer for given ID. diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 18c1dfbb1765..c8fa1d274530 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1529,7 +1529,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root, offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); - if (start > max) + if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 969e5400a615..33feec8989f1 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -236,23 +236,6 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb) } EXPORT_SYMBOL_GPL(sbitmap_any_bit_set); -bool sbitmap_any_bit_clear(const struct sbitmap *sb) -{ - unsigned int i; - - for (i = 0; i < sb->map_nr; i++) { - const struct sbitmap_word *word = &sb->map[i]; - unsigned long mask = word->word & ~word->cleared; - unsigned long ret; - - ret = find_first_zero_bit(&mask, word->depth); - if (ret < word->depth) - return true; - } - return false; -} -EXPORT_SYMBOL_GPL(sbitmap_any_bit_clear); - static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set) { unsigned int i, weight = 0; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 9d631a7b6a70..7df4f7f395bf 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1110,6 +1110,28 @@ static noinline void check_find_entry(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_move_tiny(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + XA_BUG_ON(xa, !xa_empty(xa)); + rcu_read_lock(); + XA_BUG_ON(xa, xas_next(&xas) != NULL); + XA_BUG_ON(xa, xas_next(&xas) != NULL); + rcu_read_unlock(); + xa_store_index(xa, 0, GFP_KERNEL); + rcu_read_lock(); + xas_set(&xas, 0); + XA_BUG_ON(xa, xas_next(&xas) != xa_mk_index(0)); + XA_BUG_ON(xa, xas_next(&xas) != NULL); + xas_set(&xas, 0); + XA_BUG_ON(xa, xas_prev(&xas) != xa_mk_index(0)); + XA_BUG_ON(xa, xas_prev(&xas) != NULL); + rcu_read_unlock(); + xa_erase_index(xa, 0); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_move_small(struct xarray *xa, unsigned long idx) { XA_STATE(xas, xa, 0); @@ -1217,6 +1239,8 @@ static noinline void check_move(struct xarray *xa) xa_destroy(xa); + check_move_tiny(xa); + for (i = 0; i < 16; i++) check_move_small(xa, 1UL << i); diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index e630e7ff57f1..45f57fd2db64 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -214,9 +214,10 @@ int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res) return -1; } - res->tv_sec = 0; - res->tv_nsec = ns; - + if (likely(res)) { + res->tv_sec = 0; + res->tv_nsec = ns; + } return 0; } @@ -245,7 +246,7 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) ret = clock_getres_fallback(clock, &ts); #endif - if (likely(!ret)) { + if (likely(!ret && res)) { res->tv_sec = ts.tv_sec; res->tv_nsec = ts.tv_nsec; } diff --git a/lib/xarray.c b/lib/xarray.c index 446b956c9188..1237c213f52b 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -994,6 +994,8 @@ void *__xas_prev(struct xa_state *xas) if (!xas_frozen(xas->xa_node)) xas->xa_index--; + if (!xas->xa_node) + return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); @@ -1031,6 +1033,8 @@ void *__xas_next(struct xa_state *xas) if (!xas_frozen(xas->xa_node)) xas->xa_index++; + if (!xas->xa_node) + return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index 08c3c8049998..156f26fdc4c9 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -1146,6 +1146,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) if (DEC_IS_DYNALLOC(s->dict.mode)) { if (s->dict.allocated < s->dict.size) { + s->dict.allocated = s->dict.size; vfree(s->dict.buf); s->dict.buf = vmalloc(s->dict.size); if (s->dict.buf == NULL) { diff --git a/mm/debug.c b/mm/debug.c index 8345bb6e4769..0461df1207cb 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -67,28 +67,31 @@ void __dump_page(struct page *page, const char *reason) */ mapcount = PageSlab(page) ? 0 : page_mapcount(page); - pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx", - page, page_ref_count(page), mapcount, - page->mapping, page_to_pgoff(page)); if (PageCompound(page)) - pr_cont(" compound_mapcount: %d", compound_mapcount(page)); - pr_cont("\n"); - if (PageAnon(page)) - pr_warn("anon "); - else if (PageKsm(page)) - pr_warn("ksm "); + pr_warn("page:%px refcount:%d mapcount:%d mapping:%px " + "index:%#lx compound_mapcount: %d\n", + page, page_ref_count(page), mapcount, + page->mapping, page_to_pgoff(page), + compound_mapcount(page)); + else + pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx\n", + page, page_ref_count(page), mapcount, + page->mapping, page_to_pgoff(page)); + if (PageKsm(page)) + pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags); + else if (PageAnon(page)) + pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags); else if (mapping) { - pr_warn("%ps ", mapping->a_ops); if (mapping->host && mapping->host->i_dentry.first) { struct dentry *dentry; dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias); - pr_warn("name:\"%pd\" ", dentry); - } + pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry); + } else + pr_warn("%ps\n", mapping->a_ops); + pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags); } BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); - pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags); - hex_only: print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index f1930fa0b445..2ac38bdc18a1 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -196,7 +196,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); - if (!css_tryget_online(&h_cg->css)) { + if (!css_tryget(&h_cg->css)) { rcu_read_unlock(); goto again; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 0a1b4b484ac5..a8a57bebb5fa 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1028,12 +1028,13 @@ static void collapse_huge_page(struct mm_struct *mm, anon_vma_lock_write(vma->anon_vma); - pte = pte_offset_map(pmd, address); - pte_ptl = pte_lockptr(mm, pmd); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); + + pte = pte_offset_map(pmd, address); + pte_ptl = pte_lockptr(mm, pmd); + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * After this gup_fast can't run anymore. This also removes @@ -1601,17 +1602,6 @@ static void collapse_file(struct mm_struct *mm, result = SCAN_FAIL; goto xa_unlocked; } - } else if (!PageUptodate(page)) { - xas_unlock_irq(&xas); - wait_on_page_locked(page); - if (!trylock_page(page)) { - result = SCAN_PAGE_LOCK; - goto xa_unlocked; - } - get_page(page); - } else if (PageDirty(page)) { - result = SCAN_FAIL; - goto xa_locked; } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); @@ -1626,7 +1616,12 @@ static void collapse_file(struct mm_struct *mm, * without racing with truncate. */ VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageUptodate(page), page); + + /* make sure the page is up to date */ + if (unlikely(!PageUptodate(page))) { + result = SCAN_FAIL; + goto out_unlock; + } /* * If file was truncated then extended, or hole-punched, before @@ -1642,6 +1637,16 @@ static void collapse_file(struct mm_struct *mm, goto out_unlock; } + if (!is_shmem && PageDirty(page)) { + /* + * khugepaged only works on read-only fd, so this + * page is dirty because it hasn't been flushed + * since first write. + */ + result = SCAN_FAIL; + goto out_unlock; + } + if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; @@ -885,13 +885,13 @@ static int remove_stable_node(struct stable_node *stable_node) return 0; } - if (WARN_ON_ONCE(page_mapped(page))) { - /* - * This should not happen: but if it does, just refuse to let - * merge_across_nodes be switched - there is no need to panic. - */ - err = -EBUSY; - } else { + /* + * Page could be still mapped if this races with __mmput() running in + * between ksm_exit() and exit_mmap(). Just refuse to let + * merge_across_nodes/max_page_sharing be switched. + */ + err = -EBUSY; + if (!page_mapped(page)) { /* * The stable node did not yet appear stale to get_ksm_page(), * since that allows for an unmapped ksm page to be recognized diff --git a/mm/madvise.c b/mm/madvise.c index 2be9f3fdb05e..94c343b4c968 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -363,8 +363,12 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, ClearPageReferenced(page); test_and_clear_page_young(page); if (pageout) { - if (!isolate_lru_page(page)) - list_add(&page->lru, &page_list); + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } } else deactivate_page(page); huge_unlock: @@ -441,8 +445,12 @@ regular_page: ClearPageReferenced(page); test_and_clear_page_young(page); if (pageout) { - if (!isolate_lru_page(page)) - list_add(&page->lru, &page_list); + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } } else deactivate_page(page); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 363106578876..46ad252e6d6a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -484,7 +484,7 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - if (PageHead(page) && PageSlab(page)) + if (PageSlab(page) && !PageTail(page)) memcg = memcg_from_slab_page(page); else memcg = READ_ONCE(page->mem_cgroup); @@ -960,7 +960,7 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (unlikely(!memcg)) memcg = root_mem_cgroup; } - } while (!css_tryget_online(&memcg->css)); + } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; } @@ -2535,6 +2535,15 @@ retry: } /* + * Memcg doesn't have a dedicated reserve for atomic + * allocations. But like the global atomic pool, we need to + * put the burden of reclaim on regular allocation requests + * and let these go through as privileged allocations. + */ + if (gfp_mask & __GFP_ATOMIC) + goto force; + + /* * Unlike in global OOM situations, memcg is not in a physical * memory shortage. Allow dying and OOM-killed tasks to * bypass the last charges so that they can exit quickly and @@ -5014,12 +5023,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - /* - * Flush percpu vmstats and vmevents to guarantee the value correctness - * on parent's and all ancestor levels. - */ - memcg_flush_percpu_vmstats(memcg, false); - memcg_flush_percpu_vmevents(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->vmstats_percpu); @@ -5030,6 +5033,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) static void mem_cgroup_free(struct mem_cgroup *memcg) { memcg_wb_domain_exit(memcg); + /* + * Flush percpu vmstats and vmevents to guarantee the value correctness + * on parent's and all ancestor levels. + */ + memcg_flush_percpu_vmstats(memcg, false); + memcg_flush_percpu_vmevents(memcg); __mem_cgroup_free(memcg); } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index df570e5c71cc..f307bd82d750 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -331,7 +331,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long end_pfn) { for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(start_pfn))) + if (unlikely(!pfn_to_online_page(start_pfn))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) @@ -356,7 +356,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) @@ -415,7 +415,7 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, */ pfn = zone_start_pfn; for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (page_zone(pfn_to_page(pfn)) != zone) @@ -447,6 +447,14 @@ static void update_pgdat_span(struct pglist_data *pgdat) zone->spanned_pages; /* No need to lock the zones, they can't change. */ + if (!zone->spanned_pages) + continue; + if (!node_end_pfn) { + node_start_pfn = zone->zone_start_pfn; + node_end_pfn = zone_end_pfn; + continue; + } + if (zone_end_pfn > node_end_pfn) node_end_pfn = zone_end_pfn; if (zone->zone_start_pfn < node_start_pfn) @@ -463,6 +471,16 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; +#ifdef CONFIG_ZONE_DEVICE + /* + * Zone shrinking code cannot properly deal with ZONE_DEVICE. So + * we will not try to shrink the zones - which is okay as + * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. + */ + if (zone_idx(zone) == ZONE_DEVICE) + return; +#endif + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); @@ -1638,6 +1656,18 @@ static int check_cpu_on_node(pg_data_t *pgdat) return 0; } +static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg) +{ + int nid = *(int *)arg; + + /* + * If a memory block belongs to multiple nodes, the stored nid is not + * reliable. However, such blocks are always online (e.g., cannot get + * offlined) and, therefore, are still spanned by the node. + */ + return mem->nid == nid ? -EEXIST : 0; +} + /** * try_offline_node * @nid: the node ID @@ -1650,25 +1680,24 @@ static int check_cpu_on_node(pg_data_t *pgdat) void try_offline_node(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - unsigned long start_pfn = pgdat->node_start_pfn; - unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; - unsigned long pfn; - - for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - unsigned long section_nr = pfn_to_section_nr(pfn); - - if (!present_section_nr(section_nr)) - continue; + int rc; - if (pfn_to_nid(pfn) != nid) - continue; + /* + * If the node still spans pages (especially ZONE_DEVICE), don't + * offline it. A node spans memory after move_pfn_range_to_zone(), + * e.g., after the memory block was onlined. + */ + if (pgdat->node_spanned_pages) + return; - /* - * some memory sections of this node are not removed, and we - * can't offline node now. - */ + /* + * Especially offline memory blocks might not be spanned by the + * node. They will get spanned by the node once they get onlined. + * However, they link to the node in sysfs and can get onlined later. + */ + rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb); + if (rc) return; - } if (check_cpu_on_node(pgdat)) return; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4ae967bcf954..e08c94170ae4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -672,7 +672,9 @@ static const struct mm_walk_ops queue_pages_walk_ops = { * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 0 - queue pages successfully or no misplaced page. - * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified. + * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or + * memory range specified by nodemask and maxnode points outside + * your accessible address space (-EFAULT) */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, @@ -1286,7 +1288,7 @@ static long do_mbind(unsigned long start, unsigned long len, flags | MPOL_MF_INVERT, &pagelist); if (ret < 0) { - err = -EIO; + err = ret; goto up_out; } @@ -1305,10 +1307,12 @@ static long do_mbind(unsigned long start, unsigned long len, if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; - } else - putback_movable_pages(&pagelist); - + } else { up_out: + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); + } + up_write(&mm->mmap_sem); mpol_out: mpol_put(new); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 7fde88695f35..9a889e456168 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -180,7 +180,7 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) mn->ops->invalidate_range_start, _ret, !mmu_notifier_range_blockable(range) ? "non-" : ""); WARN_ON(mmu_notifier_range_blockable(range) || - ret != -EAGAIN); + _ret != -EAGAIN); ret = _ret; } } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ecc3dbad606b..f391c0c4ed1d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1948,6 +1948,14 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* + * The number of managed pages has changed due to the initialisation + * so the pcpu batch and high limits needs to be updated or the limits + * will be artificially small. + */ + for_each_populated_zone(zone) + zone_pcp_update(zone); + + /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -3720,10 +3728,6 @@ try_this_zone: static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) { unsigned int filter = SHOW_MEM_FILTER_NODES; - static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1); - - if (!__ratelimit(&show_mem_rs)) - return; /* * This documents exceptions given to allocations in certain @@ -3744,8 +3748,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) { struct va_format vaf; va_list args; - static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); + static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) return; @@ -8514,7 +8517,6 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) WARN(count != 0, "%d pages are still in use!\n", count); } -#ifdef CONFIG_MEMORY_HOTPLUG /* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalulated. @@ -8528,7 +8530,6 @@ void __meminit zone_pcp_update(struct zone *zone) per_cpu_ptr(zone->pageset, cpu)); mutex_unlock(&pcp_batch_high_lock); } -#endif void zone_pcp_reset(struct zone *zone) { diff --git a/mm/page_io.c b/mm/page_io.c index 24ee600f9131..60a66a58b9bf 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -73,6 +73,7 @@ static void swap_slot_free_notify(struct page *page) { struct swap_info_struct *sis; struct gendisk *disk; + swp_entry_t entry; /* * There is no guarantee that the page is in swap cache - the software @@ -104,11 +105,10 @@ static void swap_slot_free_notify(struct page *page) * we again wish to reclaim it. */ disk = sis->bdev->bd_disk; - if (disk->fops->swap_slot_free_notify) { - swp_entry_t entry; + entry.val = page_private(page); + if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) { unsigned long offset; - entry.val = page_private(page); offset = swp_offset(entry); SetPageDirty(page); diff --git a/mm/slab.h b/mm/slab.h index 68e455f2b698..b2b01694dc43 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -323,8 +323,8 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) * Expects a pointer to a slab page. Please note, that PageSlab() check * isn't sufficient, as it returns true also for tail compound slab pages, * which do not have slab_cache pointer set. - * So this function assumes that the page can pass PageHead() and PageSlab() - * checks. + * So this function assumes that the page can pass PageSlab() && !PageTail() + * check. * * The kmem_cache can be reparented asynchronously. The caller must ensure * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex. diff --git a/mm/slub.c b/mm/slub.c index b25c807a111f..e72e802fc569 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1433,12 +1433,15 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; - if (slab_want_init_on_free(s)) { - void *p = NULL; + /* Head and tail of the reconstructed freelist */ + *head = NULL; + *tail = NULL; - do { - object = next; - next = get_freepointer(s, object); + do { + object = next; + next = get_freepointer(s, object); + + if (slab_want_init_on_free(s)) { /* * Clear the object and the metadata, but don't touch * the redzone. @@ -1448,29 +1451,8 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, : 0; memset((char *)object + s->inuse, 0, s->size - s->inuse - rsize); - set_freepointer(s, object, p); - p = object; - } while (object != old_tail); - } - -/* - * Compiler cannot detect this function can be removed if slab_free_hook() - * evaluates to nothing. Thus, catch all relevant config debug options here. - */ -#if defined(CONFIG_LOCKDEP) || \ - defined(CONFIG_DEBUG_KMEMLEAK) || \ - defined(CONFIG_DEBUG_OBJECTS_FREE) || \ - defined(CONFIG_KASAN) - next = *head; - - /* Head and tail of the reconstructed freelist */ - *head = NULL; - *tail = NULL; - - do { - object = next; - next = get_freepointer(s, object); + } /* If object's reuse doesn't have to be delayed */ if (!slab_free_hook(s, object)) { /* Move object to the new freelist */ @@ -1485,9 +1467,6 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, *tail = NULL; return *head != NULL; -#else - return true; -#endif } static void *setup_object(struct kmem_cache *s, struct page *page, diff --git a/mm/vmstat.c b/mm/vmstat.c index 6afc892a148a..a8222041bd44 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1383,12 +1383,29 @@ static void pagetypeinfo_showfree_print(struct seq_file *m, unsigned long freecount = 0; struct free_area *area; struct list_head *curr; + bool overflow = false; area = &(zone->free_area[order]); - list_for_each(curr, &area->free_list[mtype]) - freecount++; - seq_printf(m, "%6lu ", freecount); + list_for_each(curr, &area->free_list[mtype]) { + /* + * Cap the free_list iteration because it might + * be really large and we are under a spinlock + * so a long time spent here could trigger a + * hard lockup detector. Anyway this is a + * debugging tool so knowing there is a handful + * of pages of this order should be more than + * sufficient. + */ + if (++freecount >= 100000) { + overflow = true; + break; + } + } + seq_printf(m, "%s%6lu ", overflow ? ">" : "", freecount); + spin_unlock_irq(&zone->lock); + cond_resched(); + spin_lock_irq(&zone->lock); } seq_putc(m, '\n'); } @@ -1972,7 +1989,7 @@ void __init init_mm_internals(void) #endif #ifdef CONFIG_PROC_FS proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); - proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op); + proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); proc_create_seq("vmstat", 0444, NULL, &vmstat_op); proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op); #endif diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 54728d2eda18..d4bcfd8f95bf 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -172,7 +172,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 93eadf179123..e5bff5cc6f97 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -489,36 +489,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } -/* - * vlan network devices have devices nesting below it, and are a special - * "super class" of normal network devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key vlan_netdev_xmit_lock_key; -static struct lock_class_key vlan_netdev_addr_lock_key; - -static void vlan_dev_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_subclass) -{ - lockdep_set_class_and_subclass(&txq->_xmit_lock, - &vlan_netdev_xmit_lock_key, - *(int *)_subclass); -} - -static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) -{ - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &vlan_netdev_addr_lock_key, - subclass); - netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); -} - -static int vlan_dev_get_lock_subclass(struct net_device *dev) -{ - return vlan_dev_priv(dev)->nest_level; -} - static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .parse = eth_header_parse, @@ -609,8 +579,6 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev)); - vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) return -ENOMEM; @@ -812,7 +780,6 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, - .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, .ndo_get_iflink = vlan_dev_get_iflink, }; diff --git a/net/atm/clip.c b/net/atm/clip.c index a7972da7235d..294cb9efe3d3 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -89,7 +89,7 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc) struct clip_vcc **walk; if (!entry) { - pr_crit("!clip_vcc->entry (clip_vcc %p)\n", clip_vcc); + pr_err("!clip_vcc->entry (clip_vcc %p)\n", clip_vcc); return; } netif_tx_lock_bh(entry->neigh->dev); /* block clip_start_xmit() */ @@ -109,10 +109,10 @@ static void unlink_clip_vcc(struct clip_vcc *clip_vcc) error = neigh_update(entry->neigh, NULL, NUD_NONE, NEIGH_UPDATE_F_ADMIN, 0); if (error) - pr_crit("neigh_update failed with %d\n", error); + pr_err("neigh_update failed with %d\n", error); goto out; } - pr_crit("ATMARP: failed (entry %p, vcc 0x%p)\n", entry, clip_vcc); + pr_err("ATMARP: failed (entry %p, vcc 0x%p)\n", entry, clip_vcc); out: netif_tx_unlock_bh(entry->neigh->dev); } diff --git a/net/atm/common.c b/net/atm/common.c index b7528e77997c..0ce530af534d 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -668,7 +668,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* writable? */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index d78938e3e008..5b0b20e6da95 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -22,6 +22,8 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/pkt_sched.h> @@ -193,14 +195,18 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) unsigned char *ogm_buff; u32 random_seqno; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); atomic_set(&hard_iface->bat_iv.ogm_seqno, random_seqno); hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN; ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC); - if (!ogm_buff) + if (!ogm_buff) { + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); return -ENOMEM; + } hard_iface->bat_iv.ogm_buff = ogm_buff; @@ -212,35 +218,59 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->reserved = 0; batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE; + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); + return 0; } static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) { + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + kfree(hard_iface->bat_iv.ogm_buff); hard_iface->bat_iv.ogm_buff = NULL; + + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; ether_addr_copy(batadv_ogm_packet->orig, hard_iface->net_dev->dev_addr); ether_addr_copy(batadv_ogm_packet->prev_sender, hard_iface->net_dev->dev_addr); + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; batadv_ogm_packet->ttl = BATADV_TTL; + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } /* when do we schedule our own ogm to be sent */ @@ -742,7 +772,11 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) } } -static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +/** + * batadv_iv_ogm_schedule_buff() - schedule submission of hardif ogm buffer + * @hard_iface: interface whose ogm buffer should be transmitted + */ +static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff; @@ -753,9 +787,7 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) u16 tvlv_len = 0; unsigned long send_time; - if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || - hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) - return; + lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); /* the interface gets activated here to avoid race conditions between * the moment of activating the interface in @@ -823,6 +855,17 @@ out: batadv_hardif_put(primary_if); } +static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +{ + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) + return; + + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + batadv_iv_ogm_schedule_buff(hard_iface); + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); +} + /** * batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over iterface * @orig_node: originator which reproadcasted the OGMs directly diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index dc4f7430cb5a..8033f24f506c 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -18,6 +18,7 @@ #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/rculist.h> @@ -256,14 +257,12 @@ static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, } /** - * batadv_v_ogm_send() - periodic worker broadcasting the own OGM - * @work: work queue item + * batadv_v_ogm_send_softif() - periodic worker broadcasting the own OGM + * @bat_priv: the bat priv with all the soft interface information */ -static void batadv_v_ogm_send(struct work_struct *work) +static void batadv_v_ogm_send_softif(struct batadv_priv *bat_priv) { struct batadv_hard_iface *hard_iface; - struct batadv_priv_bat_v *bat_v; - struct batadv_priv *bat_priv; struct batadv_ogm2_packet *ogm_packet; struct sk_buff *skb, *skb_tmp; unsigned char *ogm_buff; @@ -271,8 +270,7 @@ static void batadv_v_ogm_send(struct work_struct *work) u16 tvlv_len = 0; int ret; - bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work); - bat_priv = container_of(bat_v, struct batadv_priv, bat_v); + lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; @@ -364,6 +362,23 @@ out: } /** + * batadv_v_ogm_send() - periodic worker broadcasting the own OGM + * @work: work queue item + */ +static void batadv_v_ogm_send(struct work_struct *work) +{ + struct batadv_priv_bat_v *bat_v; + struct batadv_priv *bat_priv; + + bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work); + bat_priv = container_of(bat_v, struct batadv_priv, bat_v); + + mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); + batadv_v_ogm_send_softif(bat_priv); + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); +} + +/** * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface * @work: work queue item * @@ -424,11 +439,15 @@ void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface) struct batadv_priv *bat_priv = netdev_priv(primary_iface->soft_iface); struct batadv_ogm2_packet *ogm_packet; + mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); if (!bat_priv->bat_v.ogm_buff) - return; + goto unlock; ogm_packet = (struct batadv_ogm2_packet *)bat_priv->bat_v.ogm_buff; ether_addr_copy(ogm_packet->orig, primary_iface->net_dev->dev_addr); + +unlock: + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } /** @@ -1050,6 +1069,8 @@ int batadv_v_ogm_init(struct batadv_priv *bat_priv) atomic_set(&bat_priv->bat_v.ogm_seqno, random_seqno); INIT_DELAYED_WORK(&bat_priv->bat_v.ogm_wq, batadv_v_ogm_send); + mutex_init(&bat_priv->bat_v.ogm_buff_mutex); + return 0; } @@ -1061,7 +1082,11 @@ void batadv_v_ogm_free(struct batadv_priv *bat_priv) { cancel_delayed_work_sync(&bat_priv->bat_v.ogm_wq); + mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); + kfree(bat_priv->bat_v.ogm_buff); bat_priv->bat_v.ogm_buff = NULL; bat_priv->bat_v.ogm_buff_len = 0; + + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index c90e47342bb0..afb52282d5bd 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -18,6 +18,7 @@ #include <linux/kref.h> #include <linux/limits.h> #include <linux/list.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> @@ -929,6 +930,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) INIT_LIST_HEAD(&hard_iface->list); INIT_HLIST_HEAD(&hard_iface->neigh_list); + mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); spin_lock_init(&hard_iface->neigh_list_lock); kref_init(&hard_iface->refcount); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 9cbed6f5a85a..5ee8e9a100f9 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -740,36 +740,6 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto, return 0; } -/* batman-adv network devices have devices nesting below it and are a special - * "super class" of normal network devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key batadv_netdev_xmit_lock_key; -static struct lock_class_key batadv_netdev_addr_lock_key; - -/** - * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue - * @dev: device which owns the tx queue - * @txq: tx queue to modify - * @_unused: always NULL - */ -static void batadv_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &batadv_netdev_xmit_lock_key); -} - -/** - * batadv_set_lockdep_class() - Set txq and addr_list lockdep class - * @dev: network device to modify - */ -static void batadv_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL); -} - /** * batadv_softif_init_late() - late stage initialization of soft interface * @dev: registered network device to modify @@ -783,8 +753,6 @@ static int batadv_softif_init_late(struct net_device *dev) int ret; size_t cnt_len = sizeof(u64) * BATADV_CNT_NUM; - batadv_set_lockdep_class(dev); - bat_priv = netdev_priv(dev); bat_priv->soft_iface = dev; diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index be7c02aa91e2..4d7f1baee7b7 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -17,6 +17,7 @@ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/kref.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/sched.h> /* for linux/wait.h */ @@ -81,6 +82,9 @@ struct batadv_hard_iface_bat_iv { /** @ogm_seqno: OGM sequence number - used to identify each OGM */ atomic_t ogm_seqno; + + /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ + struct mutex ogm_buff_mutex; }; /** @@ -1539,6 +1543,9 @@ struct batadv_priv_bat_v { /** @ogm_seqno: OGM sequence number - used to identify each OGM */ atomic_t ogm_seqno; + /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ + struct mutex ogm_buff_mutex; + /** @ogm_wq: workqueue used to schedule OGM transmissions */ struct delayed_work ogm_wq; }; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index bb55d92691b0..4febc82a7c76 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -571,15 +571,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) return err < 0 ? NET_XMIT_DROP : err; } -static int bt_dev_init(struct net_device *dev) -{ - netdev_lockdep_set_classes(dev); - - return 0; -} - static const struct net_device_ops netdev_ops = { - .ndo_init = bt_dev_init, .ndo_start_xmit = bt_xmit, }; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 94ddf19998c7..5f508c50649d 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -460,7 +460,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, if (sk->sk_state == BT_LISTEN) return bt_accept_poll(sk); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); @@ -470,7 +470,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == BT_CLOSED) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 681b72862c16..e804a3016902 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -24,8 +24,6 @@ const struct nf_br_ops __rcu *nf_br_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_br_ops); -static struct lock_class_key bridge_netdev_addr_lock_key; - /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -108,11 +106,6 @@ out: return NETDEV_TX_OK; } -static void br_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); -} - static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -150,7 +143,6 @@ static int br_dev_init(struct net_device *dev) br_mdb_hash_fini(br); br_fdb_hash_fini(br); } - br_set_lockdep_class(dev); return err; } diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index ed91ea31978a..12a4f4d93681 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -20,7 +20,6 @@ static unsigned int ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - struct net_device *dev; if (skb_ensure_writable(skb, ETH_ALEN)) return EBT_DROP; @@ -33,10 +32,22 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) else skb->pkt_type = PACKET_MULTICAST; } else { - if (xt_hooknum(par) != NF_BR_BROUTING) - dev = br_port_get_rcu(xt_in(par))->br->dev; - else + const struct net_device *dev; + + switch (xt_hooknum(par)) { + case NF_BR_BROUTING: dev = xt_in(par); + break; + case NF_BR_PRE_ROUTING: + dev = br_port_get_rcu(xt_in(par))->br->dev; + break; + default: + dev = NULL; + break; + } + + if (!dev) /* NF_BR_LOCAL_OUT */ + return info->target; if (ether_addr_equal(info->mac, dev->dev_addr)) skb->pkt_type = PACKET_HOST; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 506d6141e44e..809673222382 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -95,7 +95,7 @@ slow_path: * This may also be a clone skbuff, we could preserve the geometry for * the copies but probably not worth the effort. */ - ip_frag_init(skb, hlen, ll_rs, frag_max_size, &state); + ip_frag_init(skb, hlen, ll_rs, frag_max_size, false, &state); while (state.left > 0) { struct sk_buff *skb2; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 13ea920600ae..ef14da50a981 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -953,7 +953,7 @@ static __poll_t caif_poll(struct file *file, mask |= EPOLLRDHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/can/af_can.c b/net/can/af_can.c index 5518a7d9eed9..128d37a4c2e0 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -86,11 +86,12 @@ static atomic_t skbcounter = ATOMIC_INIT(0); /* af_can socket functions */ -static void can_sock_destruct(struct sock *sk) +void can_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_error_queue); } +EXPORT_SYMBOL(can_sock_destruct); static const struct can_proto *can_get_proto(int protocol) { diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index def2f813ffce..137054bff9ec 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -51,6 +51,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) if (!skb) return; + j1939_priv_get(priv); can_skb_set_owner(skb, iskb->sk); /* get a pointer to the header of the skb @@ -104,6 +105,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) j1939_simple_recv(priv, skb); j1939_sk_recv(priv, skb); done: + j1939_priv_put(priv); kfree_skb(skb); } @@ -150,6 +152,10 @@ static void __j1939_priv_release(struct kref *kref) netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv); + WARN_ON_ONCE(!list_empty(&priv->active_session_list)); + WARN_ON_ONCE(!list_empty(&priv->ecus)); + WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); + dev_put(ndev); kfree(priv); } @@ -207,6 +213,9 @@ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { struct can_ml_priv *can_ml_priv = ndev->ml_priv; + if (!can_ml_priv) + return NULL; + return can_ml_priv->j1939_priv; } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 37c1040bcb9c..de09b0a65791 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -78,7 +78,6 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) { jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - jsk->priv = priv; spin_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); @@ -91,7 +90,6 @@ static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) list_del_init(&jsk->list); spin_unlock_bh(&priv->j1939_socks_lock); - jsk->priv = NULL; j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; } @@ -349,6 +347,34 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) spin_unlock_bh(&priv->j1939_socks_lock); } +static void j1939_sk_sock_destruct(struct sock *sk) +{ + struct j1939_sock *jsk = j1939_sk(sk); + + /* This function will be call by the generic networking code, when then + * the socket is ultimately closed (sk->sk_destruct). + * + * The race between + * - processing a received CAN frame + * (can_receive -> j1939_can_recv) + * and accessing j1939_priv + * ... and ... + * - closing a socket + * (j1939_can_rx_unregister -> can_rx_unregister) + * and calling the final j1939_priv_put() + * + * is avoided by calling the final j1939_priv_put() from this + * RCU deferred cleanup call. + */ + if (jsk->priv) { + j1939_priv_put(jsk->priv); + jsk->priv = NULL; + } + + /* call generic CAN sock destruct */ + can_sock_destruct(sk); +} + static int j1939_sk_init(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); @@ -371,6 +397,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + sk->sk_destruct = j1939_sk_sock_destruct; return 0; } @@ -443,6 +470,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) } jsk->ifindex = addr->can_ifindex; + + /* the corresponding j1939_priv_put() is called via + * sk->sk_destruct, which points to j1939_sk_sock_destruct() + */ + j1939_priv_get(priv); + jsk->priv = priv; } /* set default transmit pgn */ @@ -560,8 +593,8 @@ static int j1939_sk_release(struct socket *sock) if (!sk) return 0; - jsk = j1939_sk(sk); lock_sock(sk); + jsk = j1939_sk(sk); if (jsk->state & J1939_SOCK_BOUND) { struct j1939_priv *priv = jsk->priv; @@ -580,6 +613,7 @@ static int j1939_sk_release(struct socket *sock) j1939_netdev_stop(priv); } + kfree(jsk->filters); sock_orphan(sk); sock->sk = NULL; @@ -909,8 +943,10 @@ void j1939_sk_errqueue(struct j1939_session *session, memset(serr, 0, sizeof(*serr)); switch (type) { case J1939_ERRQUEUE_ACK: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) { + kfree_skb(skb); return; + } serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; @@ -918,8 +954,10 @@ void j1939_sk_errqueue(struct j1939_session *session, state = "ACK"; break; case J1939_ERRQUEUE_SCHED: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) { + kfree_skb(skb); return; + } serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; @@ -1054,51 +1092,72 @@ static int j1939_sk_sendmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct j1939_sock *jsk = j1939_sk(sk); - struct j1939_priv *priv = jsk->priv; + struct j1939_priv *priv; int ifindex; int ret; + lock_sock(sock->sk); /* various socket state tests */ - if (!(jsk->state & J1939_SOCK_BOUND)) - return -EBADFD; + if (!(jsk->state & J1939_SOCK_BOUND)) { + ret = -EBADFD; + goto sendmsg_done; + } + priv = jsk->priv; ifindex = jsk->ifindex; - if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) + if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) { /* no source address assigned yet */ - return -EBADFD; + ret = -EBADFD; + goto sendmsg_done; + } /* deal with provided destination address info */ if (msg->msg_name) { struct sockaddr_can *addr = msg->msg_name; - if (msg->msg_namelen < J1939_MIN_NAMELEN) - return -EINVAL; + if (msg->msg_namelen < J1939_MIN_NAMELEN) { + ret = -EINVAL; + goto sendmsg_done; + } - if (addr->can_family != AF_CAN) - return -EINVAL; + if (addr->can_family != AF_CAN) { + ret = -EINVAL; + goto sendmsg_done; + } - if (addr->can_ifindex && addr->can_ifindex != ifindex) - return -EBADFD; + if (addr->can_ifindex && addr->can_ifindex != ifindex) { + ret = -EBADFD; + goto sendmsg_done; + } if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) && - !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) - return -EINVAL; + !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) { + ret = -EINVAL; + goto sendmsg_done; + } if (!addr->can_addr.j1939.name && addr->can_addr.j1939.addr == J1939_NO_ADDR && - !sock_flag(sk, SOCK_BROADCAST)) + !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ - return -EACCES; + ret = -EACCES; + goto sendmsg_done; + } } else { if (!jsk->addr.dst_name && jsk->addr.da == J1939_NO_ADDR && - !sock_flag(sk, SOCK_BROADCAST)) + !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ - return -EACCES; + ret = -EACCES; + goto sendmsg_done; + } } ret = j1939_sk_send_loop(priv, sk, msg, size); +sendmsg_done: + release_sock(sock->sk); + return ret; } diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fe000ea757ea..9f99af5b0b11 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -255,6 +255,7 @@ static void __j1939_session_drop(struct j1939_session *session) return; j1939_sock_pending_del(session->sk); + sock_put(session->sk); } static void j1939_session_destroy(struct j1939_session *session) @@ -266,6 +267,9 @@ static void j1939_session_destroy(struct j1939_session *session) netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + WARN_ON_ONCE(!list_empty(&session->sk_session_queue_entry)); + WARN_ON_ONCE(!list_empty(&session->active_session_list_entry)); + skb_queue_purge(&session->skb_queue); __j1939_session_drop(session); j1939_priv_put(session->priv); @@ -1042,12 +1046,13 @@ j1939_session_deactivate_activate_next(struct j1939_session *session) j1939_sk_queue_activate_next(session); } -static void j1939_session_cancel(struct j1939_session *session, +static void __j1939_session_cancel(struct j1939_session *session, enum j1939_xtp_abort err) { struct j1939_priv *priv = session->priv; WARN_ON_ONCE(!err); + lockdep_assert_held(&session->priv->active_session_list_lock); session->err = j1939_xtp_abort_to_errno(priv, err); /* do not send aborts on incoming broadcasts */ @@ -1062,6 +1067,20 @@ static void j1939_session_cancel(struct j1939_session *session, j1939_sk_send_loop_abort(session->sk, session->err); } +static void j1939_session_cancel(struct j1939_session *session, + enum j1939_xtp_abort err) +{ + j1939_session_list_lock(session->priv); + + if (session->state >= J1939_SESSION_ACTIVE && + session->state < J1939_SESSION_WAITING_ABORT) { + j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); + __j1939_session_cancel(session, err); + } + + j1939_session_list_unlock(session->priv); +} + static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) { struct j1939_session *session = @@ -1108,8 +1127,6 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) netdev_alert(priv->ndev, "%s: 0x%p: tx aborted with unknown reason: %i\n", __func__, session, ret); if (session->skcb.addr.type != J1939_SIMPLE) { - j1939_tp_set_rxtimeout(session, - J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_OTHER); } else { session->err = ret; @@ -1169,7 +1186,7 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer) hrtimer_start(&session->rxtimer, ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS), HRTIMER_MODE_REL_SOFT); - j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); + __j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); } j1939_session_list_unlock(session->priv); } @@ -1273,9 +1290,27 @@ j1939_xtp_rx_abort(struct j1939_priv *priv, struct sk_buff *skb, static void j1939_xtp_rx_eoma_one(struct j1939_session *session, struct sk_buff *skb) { + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + const u8 *dat; + int len; + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) return; + dat = skb->data; + + if (skcb->addr.type == J1939_ETP) + len = j1939_etp_ctl_to_size(dat); + else + len = j1939_tp_ctl_to_size(dat); + + if (session->total_message_size != len) { + netdev_warn_once(session->priv->ndev, + "%s: 0x%p: Incorrect size. Expected: %i; got: %i.\n", + __func__, session, session->total_message_size, + len); + } + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); session->pkt.tx_acked = session->pkt.total; @@ -1357,7 +1392,6 @@ j1939_xtp_rx_cts_one(struct j1939_session *session, struct sk_buff *skb) out_session_cancel: j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, err); } @@ -1432,7 +1466,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, skcb = j1939_skb_to_cb(skb); memcpy(skcb, rel_skcb, sizeof(*skcb)); - session = j1939_session_new(priv, skb, skb->len); + session = j1939_session_new(priv, skb, size); if (!session) { kfree_skb(skb); return NULL; @@ -1554,7 +1588,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, /* RTS on active session */ j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); } @@ -1565,7 +1598,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, session->last_cmd); j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); return -EBUSY; @@ -1767,7 +1799,6 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, out_session_cancel: j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); j1939_session_put(session); } @@ -1848,6 +1879,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv, return ERR_PTR(-ENOMEM); /* skb is recounted in j1939_session_new() */ + sock_hold(skb->sk); session->sk = skb->sk; session->transmission = true; session->pkt.total = (size + 6) / 7; @@ -2010,7 +2042,11 @@ int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk) &priv->active_session_list, active_session_list_entry) { if (!sk || sk == session->sk) { - j1939_session_timers_cancel(session); + if (hrtimer_try_to_cancel(&session->txtimer) == 1) + j1939_session_put(session); + if (hrtimer_try_to_cancel(&session->rxtimer) == 1) + j1939_session_put(session); + session->err = ESHUTDOWN; j1939_session_deactivate_locked(session); } diff --git a/net/core/datagram.c b/net/core/datagram.c index c210fc116103..da3c24ed129c 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -97,7 +97,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, if (error) goto out_err; - if (sk->sk_receive_queue.prev != skb) + if (READ_ONCE(sk->sk_receive_queue.prev) != skb) goto out; /* Socket shut down? */ @@ -278,7 +278,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (sk->sk_receive_queue.prev != *last); + } while (READ_ONCE(sk->sk_receive_queue.prev) != *last); error = -EAGAIN; @@ -767,7 +767,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); @@ -777,7 +777,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ diff --git a/net/core/dev.c b/net/core/dev.c index bf3ed413abaf..99ac84ff398f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,6 +146,7 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 +#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -276,88 +277,6 @@ static RAW_NOTIFIER_HEAD(netdev_chain); DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); -#ifdef CONFIG_LOCKDEP -/* - * register_netdevice() inits txq->_xmit_lock and sets lockdep class - * according to dev->type - */ -static const unsigned short netdev_lock_type[] = { - ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, - ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, - ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, - ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, - ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, - ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, - ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, - ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, - ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, - ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, - ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, - ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, - ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, - ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, - ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; - -static const char *const netdev_lock_name[] = { - "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", - "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", - "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", - "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", - "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", - "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", - "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", - "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", - "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", - "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", - "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", - "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; - -static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; -static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; - -static inline unsigned short netdev_lock_pos(unsigned short dev_type) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) - if (netdev_lock_type[i] == dev_type) - return i; - /* the last key is used by default */ - return ARRAY_SIZE(netdev_lock_type) - 1; -} - -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ - int i; - - i = netdev_lock_pos(dev_type); - lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], - netdev_lock_name[i]); -} - -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ - int i; - - i = netdev_lock_pos(dev->type); - lockdep_set_class_and_name(&dev->addr_list_lock, - &netdev_addr_lock_key[i], - netdev_lock_name[i]); -} -#else -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ -} -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ -} -#endif - /******************************************************************************* * * Protocol management and registration routines @@ -6489,6 +6408,9 @@ struct netdev_adjacent { /* upper master flag, there can only be one master device per list */ bool master; + /* lookup ignore flag */ + bool ignore; + /* counter for the number of times this device was added to us */ u16 ref_nr; @@ -6511,7 +6433,7 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, return NULL; } -static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data) +static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) { struct net_device *dev = data; @@ -6532,7 +6454,7 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -6550,7 +6472,7 @@ EXPORT_SYMBOL(netdev_has_upper_dev); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { - return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); @@ -6594,6 +6516,22 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get); +static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_adjacent *upper; + + ASSERT_RTNL(); + + if (list_empty(&dev->adj_list.upper)) + return NULL; + + upper = list_first_entry(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (likely(upper->master) && !upper->ignore) + return upper->dev; + return NULL; +} + /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device @@ -6644,6 +6582,23 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); +static struct net_device *__netdev_next_upper_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) +{ + struct netdev_adjacent *upper; + + upper = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + *ignore = upper->ignore; + + return upper->dev; +} + static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { @@ -6661,34 +6616,111 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, return upper->dev; } +static int __netdev_walk_all_upper_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + bool ignore; + + now = dev; + iter = &dev->adj_list.upper; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = __netdev_next_upper_dev(now, &iter, &ignore); + if (!udev) + break; + if (ignore) + continue; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *udev; - struct list_head *iter; - int ret; + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.upper, - udev = netdev_next_upper_dev_rcu(dev, &iter); - udev; - udev = netdev_next_upper_dev_rcu(dev, &iter)) { - /* first is the upper device itself */ - ret = fn(udev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.upper; - /* then look at all of its upper devices */ - ret = netdev_walk_all_upper_dev_rcu(udev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = netdev_next_upper_dev_rcu(now, &iter); + if (!udev) + break; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); +static bool __netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + ASSERT_RTNL(); + + return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, + upper_dev); +} + /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list @@ -6785,34 +6817,119 @@ static struct net_device *netdev_next_lower_dev(struct net_device *dev, return lower->dev; } +static struct net_device *__netdev_next_lower_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + *ignore = lower->ignore; + + return lower->dev; +} + int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *ldev; - struct list_head *iter; - int ret; + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev(dev, &iter); - ldev; - ldev = netdev_next_lower_dev(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.lower; - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev(ldev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); +static int __netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + bool ignore; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = __netdev_next_lower_dev(now, &iter, &ignore); + if (!ldev) + break; + if (ignore) + continue; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { @@ -6827,28 +6944,99 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } -int netdev_walk_all_lower_dev_rcu(struct net_device *dev, - int (*fn)(struct net_device *dev, - void *data), - void *data) +static u8 __netdev_upper_depth(struct net_device *dev) +{ + struct net_device *udev; + struct list_head *iter; + u8 max_depth = 0; + bool ignore; + + for (iter = &dev->adj_list.upper, + udev = __netdev_next_upper_dev(dev, &iter, &ignore); + udev; + udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { + if (ignore) + continue; + if (max_depth < udev->upper_level) + max_depth = udev->upper_level; + } + + return max_depth; +} + +static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; - int ret; + u8 max_depth = 0; + bool ignore; for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev_rcu(dev, &iter); + ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; - ldev = netdev_next_lower_dev_rcu(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { + if (ignore) + continue; + if (max_depth < ldev->lower_level) + max_depth = ldev->lower_level; + } - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data); - if (ret) - return ret; + return max_depth; +} + +static int __netdev_update_upper_level(struct net_device *dev, void *data) +{ + dev->upper_level = __netdev_upper_depth(dev) + 1; + return 0; +} + +static int __netdev_update_lower_level(struct net_device *dev, void *data) +{ + dev->lower_level = __netdev_lower_depth(dev) + 1; + return 0; +} + +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; @@ -6952,6 +7140,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->master = master; adj->ref_nr = 1; adj->private = private; + adj->ignore = false; dev_hold(adj_dev); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", @@ -7102,14 +7291,17 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (netdev_has_upper_dev(upper_dev, dev)) + if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; + if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) + return -EMLINK; + if (!master) { - if (netdev_has_upper_dev(dev, upper_dev)) + if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { - master_dev = netdev_master_upper_dev_get(dev); + master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } @@ -7131,6 +7323,13 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) goto rollback; + __netdev_update_upper_level(dev, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); + return 0; rollback: @@ -7213,9 +7412,96 @@ void netdev_upper_dev_unlink(struct net_device *dev, call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); + + __netdev_update_upper_level(dev, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); } EXPORT_SYMBOL(netdev_upper_dev_unlink); +static void __netdev_adjacent_dev_set(struct net_device *upper_dev, + struct net_device *lower_dev, + bool val) +{ + struct netdev_adjacent *adj; + + adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); + if (adj) + adj->ignore = val; + + adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); + if (adj) + adj->ignore = val; +} + +static void netdev_adjacent_dev_disable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, true); +} + +static void netdev_adjacent_dev_enable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, false); +} + +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack) +{ + int err; + + if (!new_dev) + return 0; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_disable(dev, old_dev); + + err = netdev_upper_dev_link(new_dev, dev, extack); + if (err) { + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + return err; + } + + return 0; +} +EXPORT_SYMBOL(netdev_adjacent_change_prepare); + +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev || !old_dev) + return; + + if (new_dev == old_dev) + return; + + netdev_adjacent_dev_enable(dev, old_dev); + netdev_upper_dev_unlink(old_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_commit); + +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev) + return; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + + netdev_upper_dev_unlink(new_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_abort); + /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device @@ -7329,25 +7615,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev) -{ - struct net_device *lower = NULL; - struct list_head *iter; - int max_nest = -1; - int nest; - - ASSERT_RTNL(); - - netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower); - if (max_nest < nest) - max_nest = nest; - } - - return max_nest + 1; -} -EXPORT_SYMBOL(dev_get_nest_level); - /** * netdev_lower_change - Dispatch event about lower device state change * @lower_dev: device @@ -8154,7 +8421,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, return -EINVAL; } - if (prog->aux->id == prog_id) { + /* prog->aux->id may be 0 for orphaned device-bound progs */ + if (prog->aux->id && prog->aux->id == prog_id) { bpf_prog_put(prog); return 0; } @@ -8619,7 +8887,7 @@ static void netdev_init_one_queue(struct net_device *dev, { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; @@ -8666,6 +8934,43 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); +static void netdev_register_lockdep_key(struct net_device *dev) +{ + lockdep_register_key(&dev->qdisc_tx_busylock_key); + lockdep_register_key(&dev->qdisc_running_key); + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); +} + +static void netdev_unregister_lockdep_key(struct net_device *dev) +{ + lockdep_unregister_key(&dev->qdisc_tx_busylock_key); + lockdep_unregister_key(&dev->qdisc_running_key); + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); +} + +void netdev_update_lockdep_key(struct net_device *dev) +{ + struct netdev_queue *queue; + int i; + + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); + + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); + + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); + for (i = 0; i < dev->num_tx_queues; i++) { + queue = netdev_get_tx_queue(dev, i); + + lockdep_set_class(&queue->_xmit_lock, + &dev->qdisc_xmit_lock_key); + } +} +EXPORT_SYMBOL(netdev_update_lockdep_key); + /** * register_netdevice - register a network device * @dev: device to register @@ -8700,7 +9005,7 @@ int register_netdevice(struct net_device *dev) BUG_ON(!net); spin_lock_init(&dev->addr_list_lock); - netdev_set_addr_lockdep_class(dev); + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) @@ -9210,8 +9515,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); + netdev_register_lockdep_key(dev); + dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->upper_level = 1; + dev->lower_level = 1; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); @@ -9292,6 +9601,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; + netdev_unregister_lockdep_key(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); @@ -9460,7 +9771,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); - new_nsid = peernet2id_alloc(dev_net(dev), net); + new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); /* If there is an ifindex conflict assign a new one */ if (__dev_get_by_index(net, dev->ifindex)) new_ifindex = dev_new_index(net); diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 6393ba930097..2f949b5a1eb9 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/core/devlink.c b/net/core/devlink.c index f80151eeaf51..93905dc7c179 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2699,7 +2699,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) struct devlink *devlink = info->user_ptr[0]; int err; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink) || !devlink->reload_enabled) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -4618,6 +4618,7 @@ struct devlink_health_reporter { bool auto_recover; u8 health_state; u64 dump_ts; + u64 dump_real_ts; u64 error_count; u64 recovery_count; u64 last_recovery_ts; @@ -4790,6 +4791,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, goto dump_err; reporter->dump_ts = jiffies; + reporter->dump_real_ts = ktime_get_real_ns(); return 0; @@ -4952,6 +4954,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg, jiffies_to_msecs(reporter->dump_ts), DEVLINK_ATTR_PAD)) goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, + reporter->dump_real_ts, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; nla_nest_end(msg, reporter_attr); genlmsg_end(msg, hdr); @@ -6196,6 +6202,8 @@ EXPORT_SYMBOL_GPL(devlink_register); void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); + WARN_ON(devlink_reload_supported(devlink) && + devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); mutex_unlock(&devlink_mutex); @@ -6203,6 +6211,41 @@ void devlink_unregister(struct devlink *devlink) EXPORT_SYMBOL_GPL(devlink_unregister); /** + * devlink_reload_enable - Enable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at end of device initialization + * process when reload operation is supported. + */ +void devlink_reload_enable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink->reload_enabled = true; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_enable); + +/** + * devlink_reload_disable - Disable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at the beginning of device cleanup + * process when reload operation is supported. + */ +void devlink_reload_disable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + /* Mutex is taken which ensures that no reload operation is in + * progress while setting up forbidded flag. + */ + devlink->reload_enabled = false; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_disable); + +/** * devlink_free - Free devlink instance resources * * @devlink: devlink diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c763106c73fc..cd9bc67381b2 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1396,11 +1396,13 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr) static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + struct ethtool_wolinfo wol; if (!dev->ethtool_ops->get_wol) return -EOPNOTSUPP; + memset(&wol, 0, sizeof(struct ethtool_wolinfo)); + wol.cmd = ETHTOOL_GWOL; dev->ethtool_ops->get_wol(dev, &wol); if (copy_to_user(useraddr, &wol, sizeof(wol))) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7c09d87d3269..68eda10d0680 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1350,30 +1350,21 @@ out_bad: } EXPORT_SYMBOL(__skb_flow_dissect); -static u32 hashrnd __read_mostly; +static siphash_key_t hashrnd __read_mostly; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } -static __always_inline u32 __flow_hash_words(const u32 *words, u32 length, - u32 keyval) +static const void *flow_keys_hash_start(const struct flow_keys *flow) { - return jhash2(words, length, keyval); -} - -static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow) -{ - const void *p = flow; - - BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32)); - return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET); + BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); + return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); - BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); BUILD_BUG_ON(offsetof(typeof(*flow), addrs) != sizeof(*flow) - sizeof(flow->addrs)); @@ -1388,7 +1379,7 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow) diff -= sizeof(flow->addrs.tipckey); break; } - return (sizeof(*flow) - diff) / sizeof(u32); + return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) @@ -1454,14 +1445,15 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) } } -static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) +static inline u32 __flow_hash_from_keys(struct flow_keys *keys, + const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); - hash = __flow_hash_words(flow_keys_hash_start(keys), - flow_keys_hash_length(keys), keyval); + hash = siphash(flow_keys_hash_start(keys), + flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; @@ -1471,12 +1463,13 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); - return __flow_hash_from_keys(keys, hashrnd); + return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); static inline u32 ___skb_get_hash(const struct sk_buff *skb, - struct flow_keys *keys, u32 keyval) + struct flow_keys *keys, + const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); @@ -1524,7 +1517,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb) &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); - return __flow_hash_from_keys(&keys, hashrnd); + return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); @@ -1544,13 +1537,14 @@ void __skb_get_hash(struct sk_buff *skb) __flow_hash_secret_init(); - hash = ___skb_get_hash(skb, &keys, hashrnd); + hash = ___skb_get_hash(skb, &keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); -__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) +__u32 skb_get_hash_perturb(const struct sk_buff *skb, + const siphash_key_t *perturb) { struct flow_keys keys; diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index f93785e5833c..74cfb8b5ab33 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -88,11 +88,16 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb) int err = -EINVAL; if (skb->protocol == htons(ETH_P_IP)) { + struct net_device *dev = skb_dst(skb)->dev; struct iphdr *iph = ip_hdr(skb); + dev_hold(dev); + skb_dst_drop(skb); err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, skb_dst(skb)->dev); + iph->tos, dev); + dev_put(dev); } else if (skb->protocol == htons(ETH_P_IPV6)) { + skb_dst_drop(skb); err = ipv6_stub->ipv6_route_input(skb); } else { err = -EAFNOSUPPORT; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 865ba6ca16eb..ae3bcb1540ec 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -923,21 +923,23 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) - return error; + goto err; dev_hold(queue->dev); if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); - if (error) { - kobject_put(kobj); - return error; - } + if (error) + goto err; } kobject_uevent(kobj, KOBJ_ADD); return error; + +err: + kobject_put(kobj); + return error; } #endif /* CONFIG_SYSFS */ @@ -1461,21 +1463,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) - return error; + goto err; dev_hold(queue->dev); #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); - if (error) { - kobject_put(kobj); - return error; - } + if (error) + goto err; #endif kobject_uevent(kobj, KOBJ_ADD); - return 0; + +err: + kobject_put(kobj); + return error; } #endif /* CONFIG_SYSFS */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6d3e4821b02d..39402840025e 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -246,11 +246,11 @@ static int __peernet2id(struct net *net, struct net *peer) } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, - struct nlmsghdr *nlh); + struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ -int peernet2id_alloc(struct net *net, struct net *peer) +int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { bool alloc = false, alive = false; int id; @@ -269,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer) id = __peernet2id_alloc(net, peer, &alloc); spin_unlock_bh(&net->nsid_lock); if (alloc && id >= 0) - rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL); + rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); if (alive) put_net(peer); return id; @@ -479,6 +479,7 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) { put_userns: + key_remove_domain(net->key_domain); put_user_ns(user_ns); net_drop_ns(net); dec_ucounts: @@ -533,7 +534,8 @@ static void unhash_nsid(struct net *net, struct net *last) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) - rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL); + rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, + GFP_KERNEL); if (tmp == last) break; } @@ -766,7 +768,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, - nlh); + nlh, GFP_KERNEL); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; @@ -1054,7 +1056,7 @@ end: } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, - struct nlmsghdr *nlh) + struct nlmsghdr *nlh, gfp_t gfp) { struct net_fill_args fillargs = { .portid = portid, @@ -1065,7 +1067,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct sk_buff *msg; int err = -ENOMEM; - msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); + msg = nlmsg_new(rtnl_net_get_size(), gfp); if (!msg) goto out; @@ -1073,7 +1075,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, if (err < 0) goto err_out; - rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, 0); + rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp); return; err_out: diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee6460f8275..e4ec575c1fba 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1523,7 +1523,7 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, static int rtnl_fill_link_netnsid(struct sk_buff *skb, const struct net_device *dev, - struct net *src_net) + struct net *src_net, gfp_t gfp) { bool put_iflink = false; @@ -1531,7 +1531,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); if (!net_eq(dev_net(dev), link_net)) { - int id = peernet2id_alloc(src_net, link_net); + int id = peernet2id_alloc(src_net, link_net, gfp); if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) return -EMSGSIZE; @@ -1589,7 +1589,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, u32 event, int *new_nsid, int new_ifindex, - int tgt_netnsid) + int tgt_netnsid, gfp_t gfp) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1681,7 +1681,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } - if (rtnl_fill_link_netnsid(skb, dev, src_net)) + if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp)) goto nla_put_failure; if (new_nsid && @@ -2001,7 +2001,7 @@ walk_entries: NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, 0, flags, ext_filter_mask, 0, NULL, 0, - netnsid); + netnsid, GFP_KERNEL); if (err < 0) { if (likely(skb->len)) @@ -2195,6 +2195,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_MAC]) { struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); + if (ivm->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_mac) err = ops->ndo_set_vf_mac(dev, ivm->vf, @@ -2206,6 +2208,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_VLAN]) { struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + if (ivv->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, @@ -2238,6 +2242,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (len == 0) return -EINVAL; + if (ivvl[0]->vf >= INT_MAX) + return -EINVAL; err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) @@ -2248,6 +2254,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); struct ifla_vf_info ivf; + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_get_vf_config) err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf); @@ -2266,6 +2274,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_RATE]) { struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_rate) err = ops->ndo_set_vf_rate(dev, ivt->vf, @@ -2278,6 +2288,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_SPOOFCHK]) { struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + if (ivs->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_spoofchk) err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, @@ -2289,6 +2301,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_LINK_STATE]) { struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]); + if (ivl->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_link_state) err = ops->ndo_set_vf_link_state(dev, ivl->vf, @@ -2302,6 +2316,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]); + if (ivrssq_en->vf >= INT_MAX) + return -EINVAL; if (ops->ndo_set_vf_rss_query_en) err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf, ivrssq_en->setting); @@ -2312,6 +2328,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_TRUST]) { struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_trust) err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting); @@ -2322,15 +2340,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_IB_NODE_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; - return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID); } if (tb[IFLA_VF_IB_PORT_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; @@ -2355,6 +2376,7 @@ static int do_set_master(struct net_device *dev, int ifindex, err = ops->ndo_del_slave(upper_dev, dev); if (err) return err; + netdev_update_lockdep_key(dev); } else { return -EOPNOTSUPP; } @@ -3359,7 +3381,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, err = rtnl_fill_ifinfo(nskb, dev, net, RTM_NEWLINK, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, ext_filter_mask, - 0, NULL, 0, netnsid); + 0, NULL, 0, netnsid, GFP_KERNEL); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -3471,7 +3493,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, 0, 0, change, 0, 0, event, - new_nsid, new_ifindex, -1); + new_nsid, new_ifindex, -1, flags); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -3916,7 +3938,7 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state || ndm->ndm_flags || ndm->ndm_type) { - NL_SET_ERR_MSG(extack, "Invalid values in header for fbd dump request"); + NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request"); return -EINVAL; } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index cf390e0aa73d..ad31e4e53d0a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -270,18 +270,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len) msg->sg.data[i].length -= trim; sk_mem_uncharge(sk, trim); + /* Adjust copybreak if it falls into the trimmed part of last buf */ + if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length) + msg->sg.copybreak = msg->sg.data[i].length; out: - /* If we trim data before curr pointer update copybreak and current - * so that any future copy operations start at new copy location. + sk_msg_iter_var_next(i); + msg->sg.end = i; + + /* If we trim data a full sg elem before curr pointer update + * copybreak and current so that any future copy operations + * start at new copy location. * However trimed data that has not yet been used in a copy op * does not require an update. */ - if (msg->sg.curr >= i) { + if (!msg->sg.size) { + msg->sg.curr = msg->sg.start; + msg->sg.copybreak = 0; + } else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >= + sk_msg_iter_dist(msg->sg.start, msg->sg.end)) { + sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } - sk_msg_iter_var_next(i); - msg->sg.end = i; } EXPORT_SYMBOL_GPL(sk_msg_trim); diff --git a/net/core/sock.c b/net/core/sock.c index a515392ba84b..ac78a570e43a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1127,7 +1127,7 @@ set_rcvbuf: break; } case SO_INCOMING_CPU: - sk->sk_incoming_cpu = val; + WRITE_ONCE(sk->sk_incoming_cpu, val); break; case SO_CNX_ADVICE: @@ -1476,7 +1476,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_INCOMING_CPU: - v.val = sk->sk_incoming_cpu; + v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: @@ -3600,7 +3600,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; - return !skb_queue_empty(&sk->sk_receive_queue) || + return !skb_queue_empty_lockless(&sk->sk_receive_queue) || sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d9b4200ed12d..d19557c6d04b 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -117,7 +117,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = dp->dccps_iss ^ jiffies; + inet->inet_id = prandom_u32(); err = dccp_connect(sk); rt = NULL; @@ -416,7 +416,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = jiffies; + newinet->inet_id = prandom_u32(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 0ea75286abf4..3349ea81f901 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1205,7 +1205,7 @@ static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wai struct dn_scp *scp = DN_SK(sk); __poll_t mask = datagram_poll(file, sock, wait); - if (!skb_queue_empty(&scp->other_receive_queue)) + if (!skb_queue_empty_lockless(&scp->other_receive_queue)) mask |= EPOLLRDBAND; return mask; diff --git a/net/dsa/master.c b/net/dsa/master.c index a8e52c9967f4..3255dfc97f86 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -310,8 +310,6 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } -static struct lock_class_key dsa_master_addr_list_lock_key; - int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -325,9 +323,6 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; - lockdep_set_class(&dev->addr_list_lock, - &dsa_master_addr_list_lock_key); - ret = dsa_master_ethtool_setup(dev); if (ret) return ret; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 75d58229a4bd..028e65f4b5ba 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1341,15 +1341,6 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } -static struct lock_class_key dsa_slave_netdev_xmit_lock_key; -static void dsa_slave_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &dsa_slave_netdev_xmit_lock_key); -} - int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); @@ -1433,9 +1424,6 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->max_mtu = ETH_MAX_MTU; SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); - netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, - NULL); - SET_NETDEV_DEV(slave_dev, port->ds->dev); slave_dev->dev.of_node = port->dn; slave_dev->vlan_features = master->vlan_features; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 9c1cc2482b68..9e5a883a9f0c 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -106,7 +106,7 @@ static int dsa_8021q_restore_pvid(struct dsa_switch *ds, int port) slave = ds->ports[port].slave; err = br_vlan_get_pvid(slave, &pvid); - if (err < 0) + if (!pvid || err < 0) /* There is no pvid on the bridge for this port, which is * perfectly valid. Nothing to restore, bye-bye! */ diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 3297e7fa9945..c0b107cdd715 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -58,13 +58,6 @@ static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; -static int lowpan_dev_init(struct net_device *ldev) -{ - netdev_lockdep_set_classes(ldev); - - return 0; -} - static int lowpan_open(struct net_device *dev) { if (!open_count) @@ -96,7 +89,6 @@ static int lowpan_get_iflink(const struct net_device *dev) } static const struct net_device_ops lowpan_netdev_ops = { - .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 9a0fe0c2fa02..4a8550c49202 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns(sk, true); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = jiffies; + inet->inet_id = prandom_u32(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index dde77f72e03e..71c78d223dfd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1148,7 +1148,7 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || - prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32) + (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0913a090b2bf..f1888c683426 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1814,8 +1814,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); - int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 97824864e40d..83fb00153018 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -240,7 +240,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score = sk->sk_family == PF_INET ? 2 : 1; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 52690bb3e40f..10636fb6093e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -509,9 +509,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto err_free_skb; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto err_free_skb; + md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 814b9b8882a0..3d8baaaf7086 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -645,11 +645,12 @@ void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, - unsigned int ll_rs, unsigned int mtu, + unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); + state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; @@ -668,9 +669,6 @@ static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; - if (IPCB(from)->flags & IPSKB_FRAG_PMTU) - state->iph->frag_off |= htons(IP_DF); - /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE @@ -738,6 +736,8 @@ struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); + if (state->DF) + iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the @@ -883,7 +883,8 @@ slow_path: * Fragment the datagram. */ - ip_frag_init(skb, hlen, ll_rs, mtu, &state); + ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, + &state); /* * Keep copying data until we run out. diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 716d5472c022..58007439cffd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2289,7 +2289,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_unlock(); return -ENODEV; } - skb2 = skb_clone(skb, GFP_ATOMIC); + + skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { read_unlock(&mrt_lock); rcu_read_unlock(); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 59ded25acd04..0902cb32bbad 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1037,7 +1037,7 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_fib_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, #endif { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 42187a3b82f4..d8876f0e9672 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -584,7 +584,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; @@ -1964,7 +1964,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); - if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && + if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && (sk->sk_state == TCP_ESTABLISHED)) sk_busy_loop(sk, nonblock); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6be568334848..67b2dc7a1727 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -303,7 +303,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr); } - inet->inet_id = tp->write_seq ^ jiffies; + inet->inet_id = prandom_u32(); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -1450,7 +1450,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = newtp->write_seq ^ jiffies; + newinet->inet_id = prandom_u32(); if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); @@ -2681,7 +2681,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; - net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); + net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 14bc654b6842..447defbfccdd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -388,7 +388,7 @@ static int compute_score(struct sock *sk, struct net *net, return -1; score += 4; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } @@ -1297,6 +1297,27 @@ out: #define UDP_SKB_IS_STATELESS 0x80000000 +/* all head states (dst, sk, nf conntrack) except skb extensions are + * cleared by udp_rcv(). + * + * We need to preserve secpath, if present, to eventually process + * IP_CMSG_PASSSEC at recvmsg() time. + * + * Other extensions can be cleared. + */ +static bool udp_try_make_stateless(struct sk_buff *skb) +{ + if (!skb_has_extensions(skb)) + return true; + + if (!secpath_exists(skb)) { + skb_ext_reset(skb); + return true; + } + + return false; +} + static void udp_set_dev_scratch(struct sk_buff *skb) { struct udp_dev_scratch *scratch = udp_skb_scratch(skb); @@ -1308,14 +1329,24 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif - /* all head states execept sp (dst, sk, nf) are always cleared by - * udp_rcv() and we need to preserve secpath, if present, to eventually - * process IP_CMSG_PASSSEC at recvmsg() time - */ - if (likely(!skb_sec_path(skb))) + if (udp_try_make_stateless(skb)) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } +static void udp_skb_csum_unnecessary_set(struct sk_buff *skb) +{ + /* We come here after udp_lib_checksum_complete() returned 0. + * This means that __skb_checksum_complete() might have + * set skb->csum_valid to 1. + * On 64bit platforms, we can set csum_unnecessary + * to true, but only if the skb is not shared. + */ +#if BITS_PER_LONG == 64 + if (!skb_shared(skb)) + udp_skb_scratch(skb)->csum_unnecessary = true; +#endif +} + static int udp_skb_truesize(struct sk_buff *skb) { return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; @@ -1550,10 +1581,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk, *total += skb->truesize; kfree_skb(skb); } else { - /* the csum related bits could be changed, refresh - * the scratch area - */ - udp_set_dev_scratch(skb); + udp_skb_csum_unnecessary_set(skb); break; } } @@ -1577,7 +1605,7 @@ static int first_packet_length(struct sock *sk) spin_lock_bh(&rcvq->lock); skb = __first_packet_length(sk, rcvq, &total); - if (!skb && !skb_queue_empty(sk_queue)) { + if (!skb && !skb_queue_empty_lockless(sk_queue)) { spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, rcvq); spin_unlock(&sk_queue->lock); @@ -1650,7 +1678,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, return skb; } - if (skb_queue_empty(sk_queue)) { + if (skb_queue_empty_lockless(sk_queue)) { spin_unlock_bh(&queue->lock); goto busy_check; } @@ -1676,7 +1704,7 @@ busy_check: break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (!skb_queue_empty(sk_queue)); + } while (!skb_queue_empty_lockless(sk_queue)); /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && @@ -2712,7 +2740,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; - if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) + if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 783f3c1466da..2fc079284ca4 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -7,6 +7,7 @@ #include <linux/export.h> #include <net/ipv6.h> #include <net/ipv6_stubs.h> +#include <net/addrconf.h> #include <net/ip.h> /* if ipv6 module registers this function is used by xfrm to force all diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index cf60fae9533b..fbe9d4295eac 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -105,7 +105,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score = 1; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 787d9f2a6e99..923034c52ce4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -980,9 +980,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, dsfield = key->tos; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto tx_err; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto tx_err; + md = ip_tunnel_info_opts(tun_info); tun_id = tunnel_id_to_key32(key->tun_id); if (md->version == 1) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 264c292e7dcc..79fc012dd2ca 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -363,8 +363,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; case IPV6_TRANSPARENT: - if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) && - !ns_capable(net->user_ns, CAP_NET_RAW)) { + if (valbool && !ns_capable(net->user_ns, CAP_NET_RAW) && + !ns_capable(net->user_ns, CAP_NET_ADMIN)) { retv = -EPERM; break; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a63ff85fe141..3f83ea851ebf 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -621,6 +621,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; + unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; @@ -633,12 +634,13 @@ static void rt6_probe(struct fib6_nh *fib6_nh) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - if (fib6_nh->fib_nh_gw_family) + if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock_bh(); + last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { @@ -654,13 +656,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh) __neigh_set_probe_once(neigh); } write_unlock(&neigh->lock); - } else if (time_after(jiffies, fib6_nh->last_probe + + } else if (time_after(jiffies, last_probe + idev->cnf.rtr_probe_interval)) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } - if (work) { - fib6_nh->last_probe = jiffies; + if (!work || cmpxchg(&fib6_nh->last_probe, + last_probe, jiffies) != last_probe) { + kfree(work); + } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; dev_hold(dev); @@ -3383,6 +3387,9 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, int err; fib6_nh->fib_nh_family = AF_INET6; +#ifdef CONFIG_IPV6_ROUTER_PREF + fib6_nh->last_probe = jiffies; +#endif err = -ENODEV; if (cfg->fc_ifindex) { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 9d4f75e0d33a..e70567446f28 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -81,6 +81,11 @@ static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb) if (!pskb_may_pull(skb, srhoff + len)) return NULL; + /* note that pskb_may_pull may change pointers in header; + * for this reason it is necessary to reload them when needed. + */ + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + if (!seg6_validate_srh(srh, len)) return NULL; @@ -336,6 +341,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (!ipv6_addr_any(&slwt->nh6)) nhaddr = &slwt->nh6; + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + seg6_lookup_nexthop(skb, nhaddr, 0); return dst_input(skb); @@ -365,6 +372,8 @@ static int input_action_end_dx4(struct sk_buff *skb, skb_dst_drop(skb); + skb_set_transport_header(skb, sizeof(struct iphdr)); + err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev); if (err) goto drop; @@ -385,6 +394,8 @@ static int input_action_end_dt6(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + seg6_lookup_nexthop(skb, NULL, slwt->table); return dst_input(skb); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6324d3a8cb53..9fec580c968e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -135,7 +135,7 @@ static int compute_score(struct sock *sk, struct net *net, return -1; score++; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index fd5ac2788e45..d3b520b9b2c9 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -56,7 +56,6 @@ static int l2tp_eth_dev_init(struct net_device *dev) { eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); - netdev_lockdep_set_classes(dev); return 0; } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index aba094b4ccfc..2d05c4cfaf6d 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1292,8 +1292,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_remove_interfaces(local); fail_rate: rtnl_unlock(); - ieee80211_led_exit(local); fail_flows: + ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: wiphy_unregister(local->hw.wiphy); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index bd11fef2139f..8d3a2389b055 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2457,7 +2457,8 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta) { struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta); - if (time_after(stats->last_rx, sta->status_stats.last_ack)) + if (!sta->status_stats.last_ack || + time_after(stats->last_rx, sta->status_stats.last_ack)) return stats->last_rx; return sta->status_stats.last_ack; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e64d5f9a89dd..d73d1828216a 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -296,7 +296,8 @@ ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4))) return -IPSET_ERR_PROTOCOL; @@ -314,7 +315,8 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6))) return -IPSET_ERR_PROTOCOL; @@ -934,7 +936,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Without holding any locks, create private part. */ if (attr[IPSET_ATTR_DATA] && - nla_parse_nested_deprecated(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy, NULL)) { + nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], + set->type->create_policy, NULL)) { ret = -IPSET_ERR_PROTOCOL; goto put_out; } @@ -1281,6 +1284,14 @@ dump_attrs(struct nlmsghdr *nlh) } } +static const struct nla_policy +ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_FLAGS] = { .type = NLA_U32 }, +}; + static int dump_init(struct netlink_callback *cb, struct ip_set_net *inst) { @@ -1292,9 +1303,9 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst) ip_set_id_t index; int ret; - ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, attr, - nlh->nlmsg_len - min_len, - ip_set_setname_policy, NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, + nlh->nlmsg_len - min_len, + ip_set_dump_policy, NULL); if (ret) return ret; @@ -1543,9 +1554,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, memcpy(&errmsg->msg, nlh, nlh->nlmsg_len); cmdattr = (void *)&errmsg->msg + min_len; - ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, cmdattr, - nlh->nlmsg_len - min_len, - ip_set_adt_policy, NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr, + nlh->nlmsg_len - min_len, ip_set_adt_policy, + NULL); if (ret) { nlmsg_free(skb2); @@ -1596,7 +1607,9 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, use_lineno = !!attr[IPSET_ATTR_LINENO]; if (attr[IPSET_ATTR_DATA]) { - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, + attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, adt, flags, use_lineno); @@ -1606,7 +1619,8 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) { if (nla_type(nla) != IPSET_ATTR_DATA || !flag_nested(nla) || - nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL)) + nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, adt, flags, use_lineno); @@ -1655,7 +1669,8 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, if (!set) return -ENOENT; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; rcu_read_lock_bh(); @@ -1961,7 +1976,7 @@ static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { [IPSET_CMD_LIST] = { .call = ip_set_dump, .attr_count = IPSET_ATTR_CMD_MAX, - .policy = ip_set_setname_policy, + .policy = ip_set_dump_policy, }, [IPSET_CMD_SAVE] = { .call = ip_set_dump, @@ -2069,8 +2084,9 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } req_version->version = IPSET_PROTOCOL; - ret = copy_to_user(user, req_version, - sizeof(struct ip_set_req_version)); + if (copy_to_user(user, req_version, + sizeof(struct ip_set_req_version))) + ret = -EFAULT; goto done; } case IP_SET_OP_GET_BYNAME: { @@ -2129,7 +2145,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } /* end of switch(op) */ copy: - ret = copy_to_user(user, data, copylen); + if (copy_to_user(user, data, copylen)) + ret = -EFAULT; done: vfree(data); diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index 24d8f4df4230..4ce563eb927d 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -209,7 +209,7 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb, (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c259cbc3ef45..3d932de0ad29 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -368,6 +368,7 @@ static struct ip_set_type hash_net_type __read_mostly = { [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index a3ae69bfee66..4398322fad59 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -476,6 +476,7 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 4515056ef1c2..f9b16f2b2219 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -193,21 +193,29 @@ struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app * mutex_lock(&__ip_vs_app_mutex); + /* increase the module use count */ + if (!ip_vs_use_count_inc()) { + err = -ENOENT; + goto out_unlock; + } + list_for_each_entry(a, &ipvs->app_list, a_list) { if (!strcmp(app->name, a->name)) { err = -EEXIST; + /* decrease the module use count */ + ip_vs_use_count_dec(); goto out_unlock; } } a = kmemdup(app, sizeof(*app), GFP_KERNEL); if (!a) { err = -ENOMEM; + /* decrease the module use count */ + ip_vs_use_count_dec(); goto out_unlock; } INIT_LIST_HEAD(&a->incs_list); list_add(&a->a_list, &ipvs->app_list); - /* increase the module use count */ - ip_vs_use_count_inc(); out_unlock: mutex_unlock(&__ip_vs_app_mutex); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 8b48e7ce1c2c..3cccc88ef817 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -93,7 +93,6 @@ static bool __ip_vs_addr_is_local_v6(struct net *net, static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; - static int old_secure_tcp = 0; int availmem; int nomem; int to_change = -1; @@ -174,35 +173,35 @@ static void update_defense_level(struct netns_ipvs *ipvs) spin_lock(&ipvs->securetcp_lock); switch (ipvs->sysctl_secure_tcp) { case 0: - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; break; case 1: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; ipvs->sysctl_secure_tcp = 2; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; } break; case 2: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; ipvs->sysctl_secure_tcp = 1; } break; case 3: - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; break; } - old_secure_tcp = ipvs->sysctl_secure_tcp; + ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp; if (to_change >= 0) ip_vs_protocol_timeout_change(ipvs, ipvs->sysctl_secure_tcp > 1); @@ -1275,7 +1274,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_service *svc = NULL; /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOPROTOOPT; /* Lookup the scheduler by 'u->sched_name' */ if (strcmp(u->sched_name, "none")) { @@ -2435,9 +2435,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (copy_from_user(arg, user, len) != 0) return -EFAULT; - /* increase the module use count */ - ip_vs_use_count_inc(); - /* Handle daemons since they have another lock */ if (cmd == IP_VS_SO_SET_STARTDAEMON || cmd == IP_VS_SO_SET_STOPDAEMON) { @@ -2450,13 +2447,13 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) ret = -EINVAL; if (strscpy(cfg.mcast_ifn, dm->mcast_ifn, sizeof(cfg.mcast_ifn)) <= 0) - goto out_dec; + return ret; cfg.syncid = dm->syncid; ret = start_sync_thread(ipvs, &cfg, dm->state); } else { ret = stop_sync_thread(ipvs, dm->state); } - goto out_dec; + return ret; } mutex_lock(&__ip_vs_mutex); @@ -2551,10 +2548,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) out_unlock: mutex_unlock(&__ip_vs_mutex); - out_dec: - /* decrease the module use count */ - ip_vs_use_count_dec(); - return ret; } diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c index 8e104dff7abc..166c669f0763 100644 --- a/net/netfilter/ipvs/ip_vs_pe.c +++ b/net/netfilter/ipvs/ip_vs_pe.c @@ -68,7 +68,8 @@ int register_ip_vs_pe(struct ip_vs_pe *pe) struct ip_vs_pe *tmp; /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOENT; mutex_lock(&ip_vs_pe_mutex); /* Make sure that the pe with this name doesn't exist diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 2f9d5cd5daee..d4903723be7e 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -179,7 +179,8 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) } /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOENT; mutex_lock(&ip_vs_sched_mutex); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index a4a78c4b06de..8dc892a9dc91 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1762,6 +1762,10 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + /* increase the module use count */ + if (!ip_vs_use_count_inc()) + return -ENOPROTOOPT; + /* Do not hold one mutex and then to block on another */ for (;;) { rtnl_lock(); @@ -1892,9 +1896,6 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); - /* increase the module use count */ - ip_vs_use_count_inc(); - return 0; out: @@ -1924,11 +1925,17 @@ out: } kfree(ti); } + + /* decrease the module use count */ + ip_vs_use_count_dec(); return result; out_early: mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); + + /* decrease the module use count */ + ip_vs_use_count_dec(); return result; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 132f5228b431..128245efe84a 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -202,6 +202,8 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; + flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, nf_flow_offload_rhash_params); @@ -218,7 +220,6 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d481f9baca2f..712a428509ad 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1922,6 +1922,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + flags |= chain->flags & NFT_BASE_CHAIN; return nf_tables_updchain(&ctx, genmask, policy, flags); } @@ -5143,9 +5144,6 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, struct nft_trans *trans; int err; - if (!obj->ops->update) - return -EOPNOTSUPP; - trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) @@ -6499,7 +6497,8 @@ static void nft_obj_commit_update(struct nft_trans *trans) obj = nft_trans_obj(trans); newobj = nft_trans_obj_newobj(trans); - obj->ops->update(obj, newobj); + if (obj->ops->update) + obj->ops->update(obj, newobj); kfree(newobj); } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index e546f759b7a7..e25dab8128db 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -334,7 +334,8 @@ int nft_flow_rule_offload_commit(struct net *net) switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) || + nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); @@ -347,7 +348,7 @@ int nft_flow_rule_offload_commit(struct net *net) policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(trans->ctx.chain, &policy, - FLOW_BLOCK_BIND); + FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 974300178fa9..02afa752dd2e 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -134,12 +134,13 @@ static int nft_bitwise_offload(struct nft_offload_ctx *ctx, const struct nft_expr *expr) { const struct nft_bitwise *priv = nft_expr_priv(expr); + struct nft_offload_reg *reg = &ctx->regs[priv->dreg]; if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) || - priv->sreg != priv->dreg) + priv->sreg != priv->dreg || priv->len != reg->len) return -EOPNOTSUPP; - memcpy(&ctx->regs[priv->dreg].mask, &priv->mask, sizeof(priv->mask)); + memcpy(®->mask, &priv->mask, sizeof(priv->mask)); return 0; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index bd173b1824c6..0744b2bb46da 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -116,7 +116,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, u8 *mask = (u8 *)&flow->match.mask; u8 *key = (u8 *)&flow->match.key; - if (priv->op != NFT_CMP_EQ) + if (priv->op != NFT_CMP_EQ || reg->len != priv->len) return -EOPNOTSUPP; memcpy(key + reg->offset, &priv->data, priv->len); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 22a80eb60222..5cb2d8908d2a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -161,13 +161,21 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ethhdr, h_source): + if (priv->len != ETH_ALEN) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, src, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_dest): + if (priv->len != ETH_ALEN) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, dst, ETH_ALEN, reg); break; + default: + return -EOPNOTSUPP; } return 0; @@ -181,14 +189,23 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct iphdr, saddr): + if (priv->len != sizeof(struct in_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src, sizeof(struct in_addr), reg); break; case offsetof(struct iphdr, daddr): + if (priv->len != sizeof(struct in_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst, sizeof(struct in_addr), reg); break; case offsetof(struct iphdr, protocol): + if (priv->len != sizeof(__u8)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, sizeof(__u8), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT); @@ -208,14 +225,23 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ipv6hdr, saddr): + if (priv->len != sizeof(struct in6_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src, sizeof(struct in6_addr), reg); break; case offsetof(struct ipv6hdr, daddr): + if (priv->len != sizeof(struct in6_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst, sizeof(struct in6_addr), reg); break; case offsetof(struct ipv6hdr, nexthdr): + if (priv->len != sizeof(__u8)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, sizeof(__u8), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT); @@ -255,10 +281,16 @@ static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct tcphdr, source): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct tcphdr, dest): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, sizeof(__be16), reg); break; @@ -277,10 +309,16 @@ static int nft_payload_offload_udp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct udphdr, source): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct udphdr, dest): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, sizeof(__be16), reg); break; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index c4f54ad2b98a..58d5373c513c 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -64,28 +64,6 @@ static DEFINE_SPINLOCK(nr_list_lock); static const struct proto_ops nr_proto_ops; /* - * NETROM network devices are virtual network devices encapsulating NETROM - * frames into AX.25 which will be sent through an AX.25 device, so form a - * special "super class" of normal net devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key nr_netdev_xmit_lock_key; -static struct lock_class_key nr_netdev_addr_lock_key; - -static void nr_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &nr_netdev_xmit_lock_key); -} - -static void nr_set_lockdep_key(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL); -} - -/* * Socket removal during an interrupt is now safe. */ static void nr_remove_socket(struct sock *sk) @@ -1414,7 +1392,6 @@ static int __init nr_proto_init(void) free_netdev(dev); goto fail; } - nr_set_lockdep_key(dev); dev_nr[i] = dev; } diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index ccdd790e163a..28604414dec1 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -554,11 +554,11 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock, if (sk->sk_state == LLCP_LISTEN) return llcp_accept_poll(sk); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == LLCP_CLOSED) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 17e6ca62f1be..afde0d763039 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1099,7 +1099,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } @@ -1159,7 +1158,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f30e406fbec5..d8c364d637b1 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1881,7 +1881,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, struct net *net, u32 portid, u32 seq, - u32 flags, u8 cmd) + u32 flags, u8 cmd, gfp_t gfp) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; @@ -1902,7 +1902,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, goto nla_put_failure; if (!net_eq(net, dev_net(vport->dev))) { - int id = peernet2id_alloc(net, dev_net(vport->dev)); + int id = peernet2id_alloc(net, dev_net(vport->dev), gfp); if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) goto nla_put_failure; @@ -1943,11 +1943,12 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, struct sk_buff *skb; int retval; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd, + GFP_KERNEL); BUG_ON(retval < 0); return skb; @@ -2089,7 +2090,7 @@ restart: err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_NEW); + OVS_VPORT_CMD_NEW, GFP_KERNEL); new_headroom = netdev_get_fwd_headroom(vport->dev); @@ -2150,7 +2151,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_SET); + OVS_VPORT_CMD_SET, GFP_KERNEL); BUG_ON(err < 0); ovs_unlock(); @@ -2190,7 +2191,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_DEL); + OVS_VPORT_CMD_DEL, GFP_KERNEL); BUG_ON(err < 0); /* the vport deletion may trigger dp headroom update */ @@ -2237,7 +2238,7 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_GET); + OVS_VPORT_CMD_GET, GFP_ATOMIC); BUG_ON(err < 0); rcu_read_unlock(); @@ -2273,7 +2274,8 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - OVS_VPORT_CMD_GET) < 0) + OVS_VPORT_CMD_GET, + GFP_ATOMIC) < 0) goto out; j++; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 21c90d3a7ebf..58a7b8312c28 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -137,7 +137,7 @@ static void do_setup(struct net_device *netdev) netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH | IFF_NO_QUEUE; netdev->needs_free_netdev = true; - netdev->priv_destructor = internal_dev_destructor; + netdev->priv_destructor = NULL; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; @@ -159,7 +159,6 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) struct internal_dev *internal_dev; struct net_device *dev; int err; - bool free_vport = true; vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms); if (IS_ERR(vport)) { @@ -190,10 +189,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) rtnl_lock(); err = register_netdevice(vport->dev); - if (err) { - free_vport = false; + if (err) goto error_unlock; - } + vport->dev->priv_destructor = internal_dev_destructor; dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); @@ -207,8 +205,7 @@ error_unlock: error_free_netdev: free_netdev(dev); error_free_vport: - if (free_vport) - ovs_vport_free(vport); + ovs_vport_free(vport); error: return ERR_PTR(err); } diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 96ea9f254ae9..76d499f6af9a 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -338,9 +338,9 @@ static __poll_t pn_socket_poll(struct file *file, struct socket *sock, if (sk->sk_state == TCP_CLOSE) return EPOLLERR; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; - if (!skb_queue_empty(&pn->ctrlreq_queue)) + if (!skb_queue_empty_lockless(&pn->ctrlreq_queue)) mask |= EPOLLPRI; if (!mask && sk->sk_state == TCP_CLOSE_WAIT) return EPOLLHUP; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 233f1368162b..18c6fac6ead9 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -450,6 +450,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) struct ib_qp_init_attr attr; struct ib_cq_init_attr cq_attr = {}; struct rds_ib_device *rds_ibdev; + unsigned long max_wrs; int ret, fr_queue_space; /* @@ -469,10 +470,15 @@ static int rds_ib_setup_qp(struct rds_connection *conn) /* add the conn now so that connection establishment has the dev */ rds_ib_add_conn(rds_ibdev, conn); - if (rds_ibdev->max_wrs < ic->i_send_ring.w_nr + 1) - rds_ib_ring_resize(&ic->i_send_ring, rds_ibdev->max_wrs - 1); - if (rds_ibdev->max_wrs < ic->i_recv_ring.w_nr + 1) - rds_ib_ring_resize(&ic->i_recv_ring, rds_ibdev->max_wrs - 1); + max_wrs = rds_ibdev->max_wrs < rds_ib_sysctl_max_send_wr + 1 ? + rds_ibdev->max_wrs - 1 : rds_ib_sysctl_max_send_wr; + if (ic->i_send_ring.w_nr != max_wrs) + rds_ib_ring_resize(&ic->i_send_ring, max_wrs); + + max_wrs = rds_ibdev->max_wrs < rds_ib_sysctl_max_recv_wr + 1 ? + rds_ibdev->max_wrs - 1 : rds_ib_sysctl_max_recv_wr; + if (ic->i_recv_ring.w_nr != max_wrs) + rds_ib_ring_resize(&ic->i_recv_ring, max_wrs); /* Protection domain and memory range */ ic->i_pd = rds_ibdev->pd; @@ -1099,8 +1105,9 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp) ic->i_flowctl = 0; atomic_set(&ic->i_credits, 0); - rds_ib_ring_init(&ic->i_send_ring, rds_ib_sysctl_max_send_wr); - rds_ib_ring_init(&ic->i_recv_ring, rds_ib_sysctl_max_recv_wr); + /* Re-init rings, but retain sizes. */ + rds_ib_ring_init(&ic->i_send_ring, ic->i_send_ring.w_nr); + rds_ib_ring_init(&ic->i_recv_ring, ic->i_recv_ring.w_nr); if (ic->i_ibinc) { rds_inc_put(&ic->i_ibinc->ii_inc); @@ -1147,8 +1154,8 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) * rds_ib_conn_shutdown() waits for these to be emptied so they * must be initialized before it can be called. */ - rds_ib_ring_init(&ic->i_send_ring, rds_ib_sysctl_max_send_wr); - rds_ib_ring_init(&ic->i_recv_ring, rds_ib_sysctl_max_recv_wr); + rds_ib_ring_init(&ic->i_send_ring, 0); + rds_ib_ring_init(&ic->i_recv_ring, 0); ic->conn = conn; conn->c_transport_data = ic; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index f0e9ccf472a9..6a0df7c8a939 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -65,28 +65,6 @@ static const struct proto_ops rose_proto_ops; ax25_address rose_callsign; /* - * ROSE network devices are virtual network devices encapsulating ROSE - * frames into AX.25 which will be sent through an AX.25 device, so form a - * special "super class" of normal net devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key rose_netdev_xmit_lock_key; -static struct lock_class_key rose_netdev_addr_lock_key; - -static void rose_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &rose_netdev_xmit_lock_key); -} - -static void rose_set_lockdep_key(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL); -} - -/* * Convert a ROSE address into text. */ char *rose2asc(char *buf, const rose_address *addr) @@ -1533,7 +1511,6 @@ static int __init rose_proto_init(void) free_netdev(dev); goto fail; } - rose_set_lockdep_key(dev); dev_rose[i] = dev; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ecc17dabec8f..7c7d10f2e0c1 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -601,6 +601,7 @@ struct rxrpc_call { int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ + bool rx_pkt_last; /* Current recvmsg packet is last */ /* Rx/Tx circular buffer, depending on phase. * diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a4090797c9b2..8578c39ec839 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -267,11 +267,13 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, */ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, u8 *_annotation, - unsigned int *_offset, unsigned int *_len) + unsigned int *_offset, unsigned int *_len, + bool *_last) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len; + bool last = false; int ret; u8 annotation = *_annotation; u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; @@ -281,6 +283,8 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, len = skb->len - offset; if (subpacket < sp->nr_subpackets - 1) len = RXRPC_JUMBO_DATALEN; + else if (sp->rx_flags & RXRPC_SKB_INCL_LAST) + last = true; if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { ret = rxrpc_verify_packet(call, skb, annotation, offset, len); @@ -291,6 +295,7 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, *_offset = offset; *_len = len; + *_last = last; call->security->locate_data(call, skb, _offset, _len); return 0; } @@ -309,7 +314,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; size_t remain; - bool last; + bool rx_pkt_last; unsigned int rx_pkt_offset, rx_pkt_len; int ix, copy, ret = -EAGAIN, ret2; @@ -319,6 +324,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; + rx_pkt_last = call->rx_pkt_last; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { seq = call->rx_hard_ack; @@ -329,6 +335,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, /* Barriers against rxrpc_input_data(). */ hard_ack = call->rx_hard_ack; seq = hard_ack + 1; + while (top = smp_load_acquire(&call->rx_top), before_eq(seq, top) ) { @@ -356,7 +363,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (rx_pkt_offset == 0) { ret2 = rxrpc_locate_data(call, skb, &call->rxtx_annotations[ix], - &rx_pkt_offset, &rx_pkt_len); + &rx_pkt_offset, &rx_pkt_len, + &rx_pkt_last); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq, rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { @@ -396,13 +404,12 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } /* The whole packet has been transferred. */ - last = sp->hdr.flags & RXRPC_LAST_PACKET; if (!(flags & MSG_PEEK)) rxrpc_rotate_rx_window(call); rx_pkt_offset = 0; rx_pkt_len = 0; - if (last) { + if (rx_pkt_last) { ASSERTCMP(seq, ==, READ_ONCE(call->rx_top)); ret = 1; goto out; @@ -415,6 +422,7 @@ out: if (!(flags & MSG_PEEK)) { call->rx_pkt_offset = rx_pkt_offset; call->rx_pkt_len = rx_pkt_len; + call->rx_pkt_last = rx_pkt_last; } done: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index cdfaa79382a2..b5bc631b96b7 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -43,7 +43,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, int err = -EINVAL; int rem; - if (!nla || !n) + if (!nla) return NULL; keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL); @@ -170,6 +170,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(pattr); + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); + return -EINVAL; + } ksize = parm->nkeys * sizeof(struct tc_pedit_key); if (nla_len(pattr) < sizeof(*parm) + ksize) { NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); @@ -183,12 +187,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - if (!parm->nkeys) { - tcf_idr_cleanup(tn, index); - NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); - ret = -EINVAL; - goto out_free; - } ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 2f83a79f76aa..d55669e14741 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -135,6 +135,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; + if (opts_len > IP_TUNNEL_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -EINVAL; + } if (dst) { dst_len -= opt_len; dst += opt_len; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8717c0b26c90..20d60b8fcb70 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -47,6 +48,62 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +static u32 destroy_obj_hashfn(const struct tcf_proto *tp) +{ + return jhash_3words(tp->chain->index, tp->prio, + (__force __u32)tp->protocol, 0); +} + +static void tcf_proto_signal_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node, + destroy_obj_hashfn(tp)); + mutex_unlock(&block->proto_destroy_lock); +} + +static bool tcf_proto_cmp(const struct tcf_proto *tp1, + const struct tcf_proto *tp2) +{ + return tp1->chain->index == tp2->chain->index && + tp1->prio == tp2->prio && + tp1->protocol == tp2->protocol; +} + +static bool tcf_proto_exists_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + u32 hash = destroy_obj_hashfn(tp); + struct tcf_proto *iter; + bool found = false; + + rcu_read_lock(); + hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter, + destroy_ht_node, hash) { + if (tcf_proto_cmp(tp, iter)) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; +} + +static void +tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + if (hash_hashed(&tp->destroy_ht_node)) + hash_del_rcu(&tp->destroy_ht_node); + mutex_unlock(&block->proto_destroy_lock); +} + /* Find classifier type by string name */ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) @@ -234,9 +291,11 @@ static void tcf_proto_get(struct tcf_proto *tp) static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) + bool sig_destroy, struct netlink_ext_ack *extack) { tp->ops->destroy(tp, rtnl_held, extack); + if (sig_destroy) + tcf_proto_signal_destroyed(tp->chain, tp); tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); @@ -246,7 +305,7 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { if (refcount_dec_and_test(&tp->refcnt)) - tcf_proto_destroy(tp, rtnl_held, extack); + tcf_proto_destroy(tp, rtnl_held, true, extack); } static int walker_check_empty(struct tcf_proto *tp, void *fh, @@ -370,6 +429,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain) static void tcf_block_destroy(struct tcf_block *block) { mutex_destroy(&block->lock); + mutex_destroy(&block->proto_destroy_lock); kfree_rcu(block, rcu); } @@ -545,6 +605,12 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_dereference(chain->filter_chain, chain); + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_signal_destroying(chain, tp); + tp = tp_next; + } + tp = tcf_chain_dereference(chain->filter_chain, chain); RCU_INIT_POINTER(chain->filter_chain, NULL); tcf_chain0_head_change(chain, NULL); chain->flushing = true; @@ -844,6 +910,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + mutex_init(&block->proto_destroy_lock); init_rwsem(&block->cb_lock); flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); @@ -1621,6 +1688,12 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_lock(&chain->filter_chain_lock); + if (tcf_proto_exists_destroying(chain, tp_new)) { + mutex_unlock(&chain->filter_chain_lock); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + return ERR_PTR(-EAGAIN); + } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); if (!tp) @@ -1628,10 +1701,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_unlock(&chain->filter_chain_lock); if (tp) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = tp; } else if (err) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = ERR_PTR(err); } @@ -1669,6 +1742,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, return; } + tcf_proto_signal_destroying(chain, tp); next = tcf_chain_dereference(chain_info.next, chain); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); @@ -2188,6 +2262,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -EINVAL; goto errout_locked; } else if (t->tcm_handle == 0) { + tcf_proto_signal_destroying(chain, tp); tcf_chain_tp_remove(chain, &chain_info, tp); mutex_unlock(&chain->filter_chain_lock); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index bf10bdaf5012..8229ed4a67be 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -162,16 +162,20 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, cls_bpf.name = obj->bpf_name; cls_bpf.exts_integrated = obj->exts_integrated; - if (oldprog) + if (oldprog && prog) err = tc_setup_cb_replace(block, tp, TC_SETUP_CLSBPF, &cls_bpf, skip_sw, &oldprog->gen_flags, &oldprog->in_hw_count, &prog->gen_flags, &prog->in_hw_count, true); - else + else if (prog) err = tc_setup_cb_add(block, tp, TC_SETUP_CLSBPF, &cls_bpf, skip_sw, &prog->gen_flags, &prog->in_hw_count, true); + else + err = tc_setup_cb_destroy(block, tp, TC_SETUP_CLSBPF, &cls_bpf, + skip_sw, &oldprog->gen_flags, + &oldprog->in_hw_count, true); if (prog && err) { cls_bpf_offload_cmd(tp, oldprog, prog, extack); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 17bd8f539bc7..8769b4b8807d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -799,9 +799,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { }; EXPORT_SYMBOL(pfifo_fast_ops); -static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; - struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) @@ -854,17 +851,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, } spin_lock_init(&sch->busylock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); sch->ops = ops; sch->flags = ops->static_flags; @@ -875,6 +864,12 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, dev_hold(dev); refcount_set(&sch->refcnt, 1); + if (sch != &noop_qdisc) { + lockdep_set_class(&sch->busylock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->seqlock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->running, &dev->qdisc_running_key); + } + return sch; errout1: kfree(p); @@ -1043,6 +1038,8 @@ static void attach_one_default_qdisc(struct net_device *dev, if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; + else if(dev->type == ARPHRD_CAN) + ops = &pfifo_fast_ops; qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); if (!qdisc) { diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 23cd1c873a2c..be35f03b657b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -5,11 +5,11 @@ * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com> */ -#include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> +#include <linux/siphash.h> #include <net/pkt_sched.h> #include <net/sock.h> @@ -126,7 +126,7 @@ struct wdrr_bucket { struct hhf_sched_data { struct wdrr_bucket buckets[WDRR_BUCKET_CNT]; - u32 perturbation; /* hash perturbation */ + siphash_key_t perturbation; /* hash perturbation */ u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ u32 drop_overlimit; /* number of times max qdisc packet * limit was hit @@ -264,7 +264,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) } /* Get hashed flow-id of the skb. */ - hash = skb_get_hash_perturb(skb, q->perturbation); + hash = skb_get_hash_perturb(skb, &q->perturbation); /* Check if this packet belongs to an already established HH flow. */ flow_pos = hash & HHF_BIT_MASK; @@ -582,7 +582,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, sch->limit = 1000; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index d448fe3068e5..4074c50ac3d7 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -18,7 +18,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/random.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <net/ip.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -45,7 +45,7 @@ struct sfb_bucket { * (Section 4.4 of SFB reference : moving hash functions) */ struct sfb_bins { - u32 perturbation; /* jhash perturbation */ + siphash_key_t perturbation; /* siphash key */ struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; }; @@ -217,7 +217,8 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = prandom_u32(); + get_random_bytes(&q->bins[slot].perturbation, + sizeof(q->bins[slot].perturbation)); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -314,9 +315,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If using external classifiers, get result and record it. */ if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; - sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation); } else { - sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation); + sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation); } @@ -352,7 +353,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Inelastic flow */ if (q->double_buffering) { sfbhash = skb_get_hash_perturb(skb, - q->bins[slot].perturbation); + &q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 68404a9d2ce4..c787d4d46017 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/netlink.h> @@ -117,7 +117,7 @@ struct sfq_sched_data { u8 headdrop; u8 maxdepth; /* limit of packets per flow */ - u32 perturbation; + siphash_key_t perturbation; u8 cur_depth; /* depth of longest slot */ u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ @@ -157,7 +157,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index static unsigned int sfq_hash(const struct sfq_sched_data *q, const struct sk_buff *skb) { - return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1); + return skb_get_hash_perturb(skb, &q->perturbation) & (q->divisor - 1); } static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, @@ -607,9 +607,11 @@ static void sfq_perturbation(struct timer_list *t) struct sfq_sched_data *q = from_timer(q, t, perturb_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + siphash_key_t nkey; + get_random_bytes(&nkey, sizeof(nkey)); spin_lock(root_lock); - q->perturbation = prandom_u32(); + q->perturbation = nkey; if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); @@ -688,7 +690,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) del_timer(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); } sch_tree_unlock(sch); kfree(p); @@ -745,7 +747,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt, q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); if (opt) { int err = sfq_change(sch, opt); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 6719a65169d4..c609373c8661 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -922,7 +922,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, } /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { + for (i = 0; i <= TC_BITMASK; i++) { if (qopt->prio_tc_map[i] >= qopt->num_tc) { NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); return -EINVAL; @@ -1152,7 +1152,7 @@ EXPORT_SYMBOL_GPL(taprio_offload_free); * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). * This is left as TODO. */ -void taprio_offload_config_changed(struct taprio_sched *q) +static void taprio_offload_config_changed(struct taprio_sched *q) { struct sched_gate_list *oper, *admin; @@ -1224,8 +1224,6 @@ static int taprio_enable_offload(struct net_device *dev, goto done; } - taprio_offload_config_changed(q); - done: taprio_offload_free(offload); @@ -1349,6 +1347,26 @@ out: return err; } +static int taprio_mqprio_cmp(const struct net_device *dev, + const struct tc_mqprio_qopt *mqprio) +{ + int i; + + if (!mqprio || mqprio->num_tc != dev->num_tc) + return -1; + + for (i = 0; i < mqprio->num_tc; i++) + if (dev->tc_to_txq[i].count != mqprio->count[i] || + dev->tc_to_txq[i].offset != mqprio->offset[i]) + return -1; + + for (i = 0; i <= TC_BITMASK; i++) + if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i]) + return -1; + + return 0; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1400,6 +1418,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, admin = rcu_dereference(q->admin_sched); rcu_read_unlock(); + /* no changes - no new mqprio settings */ + if (!taprio_mqprio_cmp(dev, mqprio)) + mqprio = NULL; + if (mqprio && (oper || admin)) { NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported"); err = -ENOTSUPP; @@ -1457,7 +1479,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, mqprio->offset[i]); /* Always use supplied priority mappings */ - for (i = 0; i < TC_BITMASK + 1; i++) + for (i = 0; i <= TC_BITMASK; i++) netdev_set_prio_tc_map(dev, i, mqprio->prio_tc_map[i]); } @@ -1505,6 +1527,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, call_rcu(&admin->rcu, taprio_free_sched_cb); spin_unlock_irqrestore(&q->current_entry_lock, flags); + + if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) + taprio_offload_config_changed(q); } new_admin = NULL; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 5ca0ec0e823c..ffd3262b7a41 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8476,7 +8476,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) mask = 0; /* Is there any exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -8485,7 +8485,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= EPOLLHUP; /* Is it readable? Reconsider this code with TCP-style support. */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* The association is either gone or not ready. */ @@ -8871,7 +8871,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, if (sk_can_busy_loop(sk)) { sk_busy_loop(sk, noblock); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) continue; } @@ -9306,7 +9306,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = asoc->next_tsn ^ jiffies; + newinet->inet_id = prandom_u32(); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5b932583e407..737b49909a7a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -123,6 +123,12 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_restore_fallback_changes(struct smc_sock *smc) +{ + smc->clcsock->file->private_data = smc->sk.sk_socket; + smc->clcsock->file = NULL; +} + static int __smc_release(struct smc_sock *smc) { struct sock *sk = &smc->sk; @@ -141,6 +147,7 @@ static int __smc_release(struct smc_sock *smc) } sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); + smc_restore_fallback_changes(smc); } sk->sk_prot->unhash(sk); @@ -700,8 +707,6 @@ static int __smc_connect(struct smc_sock *smc) int smc_type; int rc = 0; - sock_hold(&smc->sk); /* sock put in passive closing */ - if (smc->use_fallback) return smc_connect_fallback(smc, smc->fallback_rsn); @@ -791,6 +796,7 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = EPIPE; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); + sock_put(&smc->sk); /* passive closing */ goto out; } @@ -846,6 +852,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, rc = kernel_connect(smc->clcsock, addr, alen, flags); if (rc && rc != -EINPROGRESS) goto out; + + sock_hold(&smc->sk); /* sock put in passive closing */ if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1291,8 +1299,8 @@ static void smc_listen_work(struct work_struct *work) /* check if RDMA is available */ if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */ /* prepare RDMA check */ - memset(&ini, 0, sizeof(ini)); ini.is_smcd = false; + ini.ism_dev = NULL; ini.ib_lcl = &pclc->lcl; rc = smc_find_rdma_device(new_smc, &ini); if (rc) { @@ -1724,7 +1732,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 88556f0251ab..2ba97ff325a5 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -561,7 +561,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) } rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index bab2da8cf17a..571e6d84da3b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -376,8 +376,6 @@ static int smc_pnet_fill_entry(struct net *net, return 0; error: - if (pnetelem->ndev) - dev_put(pnetelem->ndev); return rc; } @@ -718,7 +716,7 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) int i, nest_lvl; rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; diff --git a/net/socket.c b/net/socket.c index 6a9ab7a8b1d2..17bc1eee198a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -404,6 +404,7 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) sock->file = file; file->private_data = sock; + stream_open(SOCK_INODE(sock), file); return file; } EXPORT_SYMBOL(sock_alloc_file); @@ -1690,24 +1691,13 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -/* - * For accept, we attempt to create a new socket, set up the link - * with the client, wake up the client, then return the new - * connected fd. We collect the address of the connector in kernel - * space and move it to user at the very end. This is unclean because - * we open the socket then return an error. - * - * 1003.1g adds the ability to recvmsg() to query connection pending - * status to recvmsg. We need to add that support in a way thats - * clean when we restructure accept also. - */ - -int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags) +int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd, fput_needed; + int err, len, newfd; struct sockaddr_storage address; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) @@ -1716,14 +1706,14 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - sock = sockfd_lookup_light(fd, &err, &fput_needed); + sock = sock_from_file(file, &err); if (!sock) goto out; err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out_put; + goto out; newsock->type = sock->type; newsock->ops = sock->ops; @@ -1738,20 +1728,21 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); - goto out_put; + goto out; } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) { err = PTR_ERR(newfile); put_unused_fd(newfd); - goto out_put; + goto out; } err = security_socket_accept(sock, newsock); if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); + err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags, + false); if (err < 0) goto out_fd; @@ -1772,15 +1763,42 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, fd_install(newfd, newfile); err = newfd; - -out_put: - fput_light(sock->file, fput_needed); out: return err; out_fd: fput(newfile); put_unused_fd(newfd); - goto out_put; + goto out; + +} + +/* + * For accept, we attempt to create a new socket, set up the link + * with the client, wake up the client, then return the new + * connected fd. We collect the address of the connector in kernel + * space and move it to user at the very end. This is unclean because + * we open the socket then return an error. + * + * 1003.1g adds the ability to recvmsg() to query connection pending + * status to recvmsg. We need to add that support in a way thats + * clean when we restructure accept also. + */ + +int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) +{ + int ret = -EBADF; + struct fd f; + + f = fdget(fd); + if (f.file) { + ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, + upeer_addrlen, flags); + if (f.flags) + fput(f.file); + } + + return ret; } SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 339e8c077c2d..195b40c5dae4 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -220,7 +220,7 @@ void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs) goto out; spin_lock_bh(&xprt->bc_pa_lock); - xprt->bc_alloc_max -= max_reqs; + xprt->bc_alloc_max -= min(max_reqs, xprt->bc_alloc_max); list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) { dprintk("RPC: req=%p\n", req); list_del(&req->rq_bc_pa_list); @@ -307,8 +307,8 @@ void xprt_free_bc_rqst(struct rpc_rqst *req) */ dprintk("RPC: Last session removed req=%p\n", req); xprt_free_allocation(req); - return; } + xprt_put(xprt); } /* @@ -339,7 +339,7 @@ found: spin_unlock(&xprt->bc_pa_lock); if (new) { if (req != new) - xprt_free_bc_rqst(new); + xprt_free_allocation(new); break; } else if (req) break; @@ -368,6 +368,7 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); dprintk("RPC: add callback request to list\n"); + xprt_get(xprt); spin_lock(&bc_serv->sv_cb_lock); list_add(&req->rq_bc_list, &bc_serv->sv_cb_list); wake_up(&bc_serv->sv_cb_waitq); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8a45b3ccc313..41df4c507193 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1943,6 +1943,11 @@ static void xprt_destroy_cb(struct work_struct *work) rpc_destroy_wait_queue(&xprt->backlog); kfree(xprt->servername); /* + * Destroy any existing back channel + */ + xprt_destroy_backchannel(xprt, UINT_MAX); + + /* * Tear down transport state and free the rpc_xprt */ xprt->ops->destroy(xprt); diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 50e075fcdd8f..b458bf53ca69 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -163,6 +163,7 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst) spin_lock(&xprt->bc_pa_lock); list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list); spin_unlock(&xprt->bc_pa_lock); + xprt_put(xprt); } static struct rpc_rqst *rpcrdma_bc_rqst_get(struct rpcrdma_xprt *r_xprt) @@ -259,6 +260,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, /* Queue rqst for ULP's callback service */ bc_serv = xprt->bc_serv; + xprt_get(xprt); spin_lock(&bc_serv->sv_cb_lock); list_add(&rqst->rq_bc_list, &bc_serv->sv_cb_list); spin_unlock(&bc_serv->sv_cb_lock); diff --git a/net/tipc/core.c b/net/tipc/core.c index 23cb379a93d6..8f35060a24e1 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -34,8 +34,6 @@ * POSSIBILITY OF SUCH DAMAGE. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include "core.h" #include "name_table.h" #include "subscr.h" diff --git a/net/tipc/core.h b/net/tipc/core.h index 60d829581068..3042f654e0af 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -60,6 +60,12 @@ #include <linux/rhashtable.h> #include <net/genetlink.h> +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + struct tipc_node; struct tipc_bearer; struct tipc_bc_base; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f8bbc4aab213..4b92b196cfa6 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -740,7 +740,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, /* fall through */ case TIPC_LISTEN: case TIPC_CONNECTING: - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) revents |= EPOLLIN | EPOLLRDNORM; break; case TIPC_OPEN: @@ -748,7 +748,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, revents |= EPOLLOUT; if (!tipc_sk_type_connectionless(sk)) break; - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) break; revents |= EPOLLIN | EPOLLRDNORM; break; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index f959487c5cd1..683d00837693 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -523,8 +523,10 @@ last_record: int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; + struct tls_context *tls_ctx = tls_get_ctx(sk); int rc; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (unlikely(msg->msg_controllen)) { @@ -538,12 +540,14 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; char *kaddr = kmap(page); struct kvec iov; @@ -552,6 +556,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, if (flags & MSG_SENDPAGE_NOTLAST) flags |= MSG_MORE; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (flags & MSG_OOB) { @@ -568,6 +573,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } @@ -623,9 +629,11 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) void tls_device_write_space(struct sock *sk, struct tls_context *ctx) { - if (!sk->sk_write_pending && tls_is_partially_sent_record(ctx)) { + if (tls_is_partially_sent_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; + WARN_ON_ONCE(sk->sk_write_pending); + sk->sk_allocation = GFP_ATOMIC; tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL | diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index ac88877dcade..f874cc0da45d 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -267,6 +267,7 @@ void tls_ctx_free(struct sock *sk, struct tls_context *ctx) memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + mutex_destroy(&ctx->tx_lock); if (sk) kfree_rcu(ctx, rcu); @@ -612,6 +613,7 @@ static struct tls_context *create_ctx(struct sock *sk) if (!ctx) return NULL; + mutex_init(&ctx->tx_lock); rcu_assign_pointer(icsk->icsk_ulp_data, ctx); ctx->sk_proto = sk->sk_prot; return ctx; @@ -906,6 +908,7 @@ static int __init tls_register(void) { tls_sw_proto_ops = inet_stream_ops; tls_sw_proto_ops.splice_read = tls_sw_splice_read; + tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked, tls_device_init(); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index c2b5e0d2ba1a..319735d5c084 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -897,15 +897,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) return -ENOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto send_end; - } - if (unlikely(msg->msg_controllen)) { ret = tls_proccess_cmsg(sk, msg, &record_type); if (ret) { @@ -1091,6 +1085,7 @@ send_end: ret = sk_stream_error(sk, msg->msg_flags, ret); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return copied ? copied : ret; } @@ -1114,13 +1109,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto sendpage_end; - } - /* Call the sk_stream functions to manage the sndbuf mem. */ while (size > 0) { size_t copy, required_size; @@ -1216,18 +1204,32 @@ sendpage_end: return copied ? copied : ret; } +int tls_sw_sendpage_locked(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY | + MSG_NO_SHARED_FRAGS)) + return -ENOTSUPP; + + return tls_sw_do_sendpage(sk, page, offset, size, flags); +} + int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); int ret; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) return -ENOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); ret = tls_sw_do_sendpage(sk, page, offset, size, flags); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return ret; } @@ -2170,9 +2172,11 @@ static void tx_work_handler(struct work_struct *work) if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) return; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); } void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) @@ -2180,12 +2184,9 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx); /* Schedule the transmission if tx list is ready */ - if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) { - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, - &tx_ctx->tx_bitmask)) - schedule_delayed_work(&tx_ctx->tx_work.work, 0); - } + if (is_tx_ready(tx_ctx) && + !test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) + schedule_delayed_work(&tx_ctx->tx_work.work, 0); } void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 67e87db5877f..0d8da809bea2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2599,7 +2599,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -2628,7 +2628,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); @@ -2638,7 +2638,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 2ab43b2bba31..582a3e4dfce2 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -870,7 +870,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, * the queue and write as long as the socket isn't shutdown for * sending. */ - if (!skb_queue_empty(&sk->sk_receive_queue) || + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) { mask |= EPOLLIN | EPOLLRDNORM; } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 481f7f8a1655..fb2060dffb0a 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -947,9 +947,11 @@ virtio_transport_recv_connected(struct sock *sk, if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) vsk->peer_shutdown |= SEND_SHUTDOWN; if (vsk->peer_shutdown == SHUTDOWN_MASK && - vsock_stream_has_data(vsk) <= 0) { - sock_set_flag(sk, SOCK_DONE); - sk->sk_state = TCP_CLOSING; + vsock_stream_has_data(vsk) <= 0 && + !sock_flag(sk, SOCK_DONE)) { + (void)virtio_transport_reset(vsk, NULL); + + virtio_transport_do_close(vsk, true); } if (le32_to_cpu(pkt->hdr.flags)) sk->sk_state_change(sk); diff --git a/net/wireless/chan.c b/net/wireless/chan.c index e851cafd8e2f..fcac5c6366e1 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -204,6 +204,11 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) return false; } + /* channel 14 is only for IEEE 802.11b */ + if (chandef->center_freq1 == 2484 && + chandef->width != NL80211_CHAN_WIDTH_20_NOHT) + return false; + if (cfg80211_chandef_is_edmg(chandef) && !cfg80211_edmg_chandef_valid(chandef)) return false; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4453dd375de9..7b72286922f7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -393,7 +393,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MNTR_FLAGS] = { /* NLA_NESTED can't be empty */ }, [NL80211_ATTR_MESH_ID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_MESH_ID_LEN }, - [NL80211_ATTR_MPATH_NEXT_HOP] = { .type = NLA_U32 }, + [NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT, [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, [NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED }, diff --git a/net/wireless/util.c b/net/wireless/util.c index 419eb12c1e93..5b4ed5bbc542 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1559,7 +1559,8 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, } if (freq == 2484) { - if (chandef->width > NL80211_CHAN_WIDTH_40) + /* channel 14 is only for IEEE 802.11b */ + if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT) return false; *op_class = 82; /* channel 14 */ diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 16d5f353163a..3049af269fbf 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -27,6 +27,9 @@ void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; + if (!xs->tx) + return; + spin_lock_irqsave(&umem->xsk_list_lock, flags); list_add_rcu(&xs->list, &umem->xsk_list); spin_unlock_irqrestore(&umem->xsk_list_lock, flags); @@ -36,6 +39,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; + if (!xs->tx) + return; + spin_lock_irqsave(&umem->xsk_list_lock, flags); list_del_rcu(&xs->list); spin_unlock_irqrestore(&umem->xsk_list_lock, flags); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 9b599ed66d97..2c86a2fc3915 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -480,6 +480,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); + + if (encap_type == -1) + dev_put(skb->dev); goto drop; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index c6f3c4a1bd99..f3423562d933 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -495,6 +495,8 @@ static void ___xfrm_state_destroy(struct xfrm_state *x) x->type->destructor(x); xfrm_put_type(x->type); } + if (x->xfrag.page) + put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 1d9be26b4edd..42b571cde177 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -176,6 +176,7 @@ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf +KBUILD_HOSTCFLAGS += -DHAVE_ATTR_TEST=0 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 7b7c2fafbc68..be984aa29b75 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -99,7 +99,8 @@ lx-symbols command.""" attrs[n]['name'].string(): attrs[n]['address'] for n in range(int(sect_attrs['nsections']))} args = [] - for section_name in [".data", ".data..read_mostly", ".rodata", ".bss"]: + for section_name in [".data", ".data..read_mostly", ".rodata", ".bss", + ".text", ".text.hot", ".text.unlikely"]: address = section_name_to_address.get(section_name) if address: args.append(" -s {name} {addr}".format( diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 936d3ad23c83..d2a30a7b3f07 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -348,26 +348,38 @@ static enum export export_from_sec(struct elf_info *elf, unsigned int sec) return export_unknown; } -static char *sym_extract_namespace(const char **symname) +static const char *namespace_from_kstrtabns(struct elf_info *info, + Elf_Sym *kstrtabns) { - char *namespace = NULL; - char *ns_separator; + char *value = info->ksymtab_strings + kstrtabns->st_value; + return value[0] ? value : NULL; +} + +static void sym_update_namespace(const char *symname, const char *namespace) +{ + struct symbol *s = find_symbol(symname); - ns_separator = strchr(*symname, '.'); - if (ns_separator) { - namespace = NOFAIL(strndup(*symname, ns_separator - *symname)); - *symname = ns_separator + 1; + /* + * That symbol should have been created earlier and thus this is + * actually an assertion. + */ + if (!s) { + merror("Could not update namespace(%s) for symbol %s\n", + namespace, symname); + return; } - return namespace; + free(s->namespace); + s->namespace = + namespace && namespace[0] ? NOFAIL(strdup(namespace)) : NULL; } /** * Add an exported symbol - it may have already been added without a * CRC, in this case just update the CRC **/ -static struct symbol *sym_add_exported(const char *name, const char *namespace, - struct module *mod, enum export export) +static struct symbol *sym_add_exported(const char *name, struct module *mod, + enum export export) { struct symbol *s = find_symbol(name); @@ -383,8 +395,6 @@ static struct symbol *sym_add_exported(const char *name, const char *namespace, s->module = mod; } } - free(s->namespace); - s->namespace = namespace ? strdup(namespace) : NULL; s->preloaded = 0; s->vmlinux = is_vmlinux(mod->name); s->kernel = 0; @@ -583,6 +593,10 @@ static int parse_elf(struct elf_info *info, const char *filename) info->export_unused_gpl_sec = i; else if (strcmp(secname, "__ksymtab_gpl_future") == 0) info->export_gpl_future_sec = i; + else if (strcmp(secname, "__ksymtab_strings") == 0) + info->ksymtab_strings = (void *)hdr + + sechdrs[i].sh_offset - + sechdrs[i].sh_addr; if (sechdrs[i].sh_type == SHT_SYMTAB) { unsigned int sh_link_idx; @@ -672,7 +686,6 @@ static void handle_modversions(struct module *mod, struct elf_info *info, enum export export; bool is_crc = false; const char *name; - char *namespace; if ((!is_vmlinux(mod->name) || mod->is_dot_o) && strstarts(symname, "__ksymtab")) @@ -745,9 +758,7 @@ static void handle_modversions(struct module *mod, struct elf_info *info, /* All exported symbols */ if (strstarts(symname, "__ksymtab_")) { name = symname + strlen("__ksymtab_"); - namespace = sym_extract_namespace(&name); - sym_add_exported(name, namespace, mod, export); - free(namespace); + sym_add_exported(name, mod, export); } if (strcmp(symname, "init_module") == 0) mod->has_init = 1; @@ -2043,6 +2054,16 @@ static void read_symbols(const char *modname) handle_moddevtable(mod, &info, sym, symname); } + /* Apply symbol namespaces from __kstrtabns_<symbol> entries. */ + for (sym = info.symtab_start; sym < info.symtab_stop; sym++) { + symname = remove_dot(info.strtab + sym->st_name); + + if (strstarts(symname, "__kstrtabns_")) + sym_update_namespace(symname + strlen("__kstrtabns_"), + namespace_from_kstrtabns(&info, + sym)); + } + // check for static EXPORT_SYMBOL_* functions && global vars for (sym = info.symtab_start; sym < info.symtab_stop; sym++) { unsigned char bind = ELF_ST_BIND(sym->st_info); @@ -2196,7 +2217,7 @@ static int check_exports(struct module *mod) else basename = mod->name; - if (exp->namespace && exp->namespace[0]) { + if (exp->namespace) { add_namespace(&mod->required_namespaces, exp->namespace); @@ -2454,12 +2475,12 @@ static void read_dump(const char *fname, unsigned int kernel) mod = new_module(modname); mod->skip = 1; } - s = sym_add_exported(symname, namespace, mod, - export_no(export)); + s = sym_add_exported(symname, mod, export_no(export)); s->kernel = kernel; s->preloaded = 1; s->is_static = 0; sym_update_crc(symname, mod, crc, export_no(export)); + sym_update_namespace(symname, namespace); } release_file(file, size); return; diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 92a926d375d2..ad271bc6c313 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -143,6 +143,7 @@ struct elf_info { Elf_Section export_gpl_sec; Elf_Section export_unused_gpl_sec; Elf_Section export_gpl_future_sec; + char *ksymtab_strings; char *strtab; char *modinfo; unsigned int modinfo_len; diff --git a/scripts/nsdeps b/scripts/nsdeps index 3754dac13b31..04cea0921673 100644 --- a/scripts/nsdeps +++ b/scripts/nsdeps @@ -31,12 +31,12 @@ generate_deps() { local mod_file=`echo $@ | sed -e 's/\.ko/\.mod/'` local ns_deps_file=`echo $@ | sed -e 's/\.ko/\.ns_deps/'` if [ ! -f "$ns_deps_file" ]; then return; fi - local mod_source_files=`cat $mod_file | sed -n 1p \ + local mod_source_files="`cat $mod_file | sed -n 1p \ | sed -e 's/\.o/\.c/g' \ - | sed "s/[^ ]* */${srctree}\/&/g"` + | sed "s|[^ ]* *|${srctree}/&|g"`" for ns in `cat $ns_deps_file`; do echo "Adding namespace $ns to module $mod_name (if needed)." - generate_deps_for_ns $ns $mod_source_files + generate_deps_for_ns $ns "$mod_source_files" # sort the imports for source_file in $mod_source_files; do sed '/MODULE_IMPORT_NS/Q' $source_file > ${source_file}.tmp diff --git a/scripts/tools-support-relr.sh b/scripts/tools-support-relr.sh index 97a2c844a95e..45e8aa360b45 100755 --- a/scripts/tools-support-relr.sh +++ b/scripts/tools-support-relr.sh @@ -4,13 +4,13 @@ tmp_file=$(mktemp) trap "rm -f $tmp_file.o $tmp_file $tmp_file.bin" EXIT -cat << "END" | "$CC" -c -x c - -o $tmp_file.o >/dev/null 2>&1 +cat << "END" | $CC -c -x c - -o $tmp_file.o >/dev/null 2>&1 void *p = &p; END -"$LD" $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr -o $tmp_file +$LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr -o $tmp_file # Despite printing an error message, GNU nm still exits with exit code 0 if it # sees a relr section. So we need to check that nothing is printed to stderr. -test -z "$("$NM" $tmp_file 2>&1 >/dev/null)" +test -z "$($NM $tmp_file 2>&1 >/dev/null)" -"$OBJCOPY" -O binary $tmp_file $tmp_file.bin +$OBJCOPY -O binary $tmp_file $tmp_file.bin diff --git a/security/keys/Makefile b/security/keys/Makefile index 9cef54064f60..074f27538f55 100644 --- a/security/keys/Makefile +++ b/security/keys/Makefile @@ -28,5 +28,5 @@ obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += keyctl_pkey.o # Key types # obj-$(CONFIG_BIG_KEYS) += big_key.o -obj-$(CONFIG_TRUSTED_KEYS) += trusted.o +obj-$(CONFIG_TRUSTED_KEYS) += trusted-keys/ obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/ diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile new file mode 100644 index 000000000000..7b73cebbb378 --- /dev/null +++ b/security/keys/trusted-keys/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for trusted keys +# + +obj-$(CONFIG_TRUSTED_KEYS) += trusted.o +trusted-y += trusted_tpm1.o +trusted-y += trusted_tpm2.o diff --git a/security/keys/trusted.c b/security/keys/trusted-keys/trusted_tpm1.c index 1fbd77816610..d2c5ec1e040b 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -27,7 +27,7 @@ #include <linux/tpm.h> #include <linux/tpm_command.h> -#include <keys/trusted.h> +#include <keys/trusted_tpm.h> static const char hmac_alg[] = "hmac(sha1)"; static const char hash_alg[] = "sha1"; @@ -406,13 +406,10 @@ static int osap(struct tpm_buf *tb, struct osapsess *s, if (ret != TPM_NONCE_SIZE) return ret; - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_COMMAND); - store32(tb, TPM_OSAP_SIZE); - store32(tb, TPM_ORD_OSAP); - store16(tb, type); - store32(tb, handle); - storebytes(tb, ononce, TPM_NONCE_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OSAP); + tpm_buf_append_u16(tb, type); + tpm_buf_append_u32(tb, handle); + tpm_buf_append(tb, ononce, TPM_NONCE_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) @@ -437,10 +434,7 @@ int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) if (!chip) return -ENODEV; - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_COMMAND); - store32(tb, TPM_OIAP_SIZE); - store32(tb, TPM_ORD_OIAP); + tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OIAP); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) return ret; @@ -535,20 +529,17 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype, goto out; /* build and send the TPM request packet */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); - store32(tb, TPM_SEAL_SIZE + pcrinfosize + datalen); - store32(tb, TPM_ORD_SEAL); - store32(tb, keyhandle); - storebytes(tb, td->encauth, SHA1_DIGEST_SIZE); - store32(tb, pcrinfosize); - storebytes(tb, pcrinfo, pcrinfosize); - store32(tb, datalen); - storebytes(tb, data, datalen); - store32(tb, sess.handle); - storebytes(tb, td->nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, td->pubauth, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SEAL); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append(tb, td->encauth, SHA1_DIGEST_SIZE); + tpm_buf_append_u32(tb, pcrinfosize); + tpm_buf_append(tb, pcrinfo, pcrinfosize); + tpm_buf_append_u32(tb, datalen); + tpm_buf_append(tb, data, datalen); + tpm_buf_append_u32(tb, sess.handle); + tpm_buf_append(tb, td->nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, td->pubauth, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) @@ -594,7 +585,6 @@ static int tpm_unseal(struct tpm_buf *tb, uint32_t authhandle2 = 0; unsigned char cont = 0; uint32_t ordinal; - uint32_t keyhndl; int ret; /* sessions for unsealing key and data */ @@ -610,7 +600,6 @@ static int tpm_unseal(struct tpm_buf *tb, } ordinal = htonl(TPM_ORD_UNSEAL); - keyhndl = htonl(SRKHANDLE); ret = tpm_get_random(chip, nonceodd, TPM_NONCE_SIZE); if (ret != TPM_NONCE_SIZE) { pr_info("trusted_key: tpm_get_random failed (%d)\n", ret); @@ -628,20 +617,17 @@ static int tpm_unseal(struct tpm_buf *tb, return ret; /* build and send TPM request packet */ - INIT_BUF(tb); - store16(tb, TPM_TAG_RQU_AUTH2_COMMAND); - store32(tb, TPM_UNSEAL_SIZE + bloblen); - store32(tb, TPM_ORD_UNSEAL); - store32(tb, keyhandle); - storebytes(tb, blob, bloblen); - store32(tb, authhandle1); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata1, SHA1_DIGEST_SIZE); - store32(tb, authhandle2); - storebytes(tb, nonceodd, TPM_NONCE_SIZE); - store8(tb, cont); - storebytes(tb, authdata2, SHA1_DIGEST_SIZE); + tpm_buf_reset(tb, TPM_TAG_RQU_AUTH2_COMMAND, TPM_ORD_UNSEAL); + tpm_buf_append_u32(tb, keyhandle); + tpm_buf_append(tb, blob, bloblen); + tpm_buf_append_u32(tb, authhandle1); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata1, SHA1_DIGEST_SIZE); + tpm_buf_append_u32(tb, authhandle2); + tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE); + tpm_buf_append_u8(tb, cont); + tpm_buf_append(tb, authdata2, SHA1_DIGEST_SIZE); ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { @@ -670,23 +656,23 @@ static int tpm_unseal(struct tpm_buf *tb, static int key_seal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf *tb; + struct tpm_buf tb; int ret; - tb = kzalloc(sizeof *tb, GFP_KERNEL); - if (!tb) - return -ENOMEM; + ret = tpm_buf_init(&tb, 0, 0); + if (ret) + return ret; /* include migratable flag at end of sealed key */ p->key[p->key_len] = p->migratable; - ret = tpm_seal(tb, o->keytype, o->keyhandle, o->keyauth, + ret = tpm_seal(&tb, o->keytype, o->keyhandle, o->keyauth, p->key, p->key_len + 1, p->blob, &p->blob_len, o->blobauth, o->pcrinfo, o->pcrinfo_len); if (ret < 0) pr_info("trusted_key: srkseal failed (%d)\n", ret); - kzfree(tb); + tpm_buf_destroy(&tb); return ret; } @@ -696,14 +682,14 @@ static int key_seal(struct trusted_key_payload *p, static int key_unseal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf *tb; + struct tpm_buf tb; int ret; - tb = kzalloc(sizeof *tb, GFP_KERNEL); - if (!tb) - return -ENOMEM; + ret = tpm_buf_init(&tb, 0, 0); + if (ret) + return ret; - ret = tpm_unseal(tb, o->keyhandle, o->keyauth, p->blob, p->blob_len, + ret = tpm_unseal(&tb, o->keyhandle, o->keyauth, p->blob, p->blob_len, o->blobauth, p->key, &p->key_len); if (ret < 0) pr_info("trusted_key: srkunseal failed (%d)\n", ret); @@ -711,7 +697,7 @@ static int key_unseal(struct trusted_key_payload *p, /* pull migratable flag out of sealed key */ p->migratable = p->key[--p->key_len]; - kzfree(tb); + tpm_buf_destroy(&tb); return ret; } @@ -1016,7 +1002,7 @@ static int trusted_instantiate(struct key *key, switch (key_cmd) { case Opt_load: if (tpm2) - ret = tpm_unseal_trusted(chip, payload, options); + ret = tpm2_unseal_trusted(chip, payload, options); else ret = key_unseal(payload, options); dump_payload(payload); @@ -1032,7 +1018,7 @@ static int trusted_instantiate(struct key *key, goto out; } if (tpm2) - ret = tpm_seal_trusted(chip, payload, options); + ret = tpm2_seal_trusted(chip, payload, options); else ret = key_seal(payload, options); if (ret < 0) diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c new file mode 100644 index 000000000000..a9810ac2776f --- /dev/null +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2004 IBM Corporation + * Copyright (C) 2014 Intel Corporation + */ + +#include <linux/string.h> +#include <linux/err.h> +#include <linux/tpm.h> +#include <linux/tpm_command.h> + +#include <keys/trusted-type.h> +#include <keys/trusted_tpm.h> + +static struct tpm2_hash tpm2_hash_map[] = { + {HASH_ALGO_SHA1, TPM_ALG_SHA1}, + {HASH_ALGO_SHA256, TPM_ALG_SHA256}, + {HASH_ALGO_SHA384, TPM_ALG_SHA384}, + {HASH_ALGO_SHA512, TPM_ALG_SHA512}, + {HASH_ALGO_SM3_256, TPM_ALG_SM3_256}, +}; + +/** + * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. + * + * @buf: an allocated tpm_buf instance + * @session_handle: session handle + * @nonce: the session nonce, may be NULL if not used + * @nonce_len: the session nonce length, may be 0 if not used + * @attributes: the session attributes + * @hmac: the session HMAC or password, may be NULL if not used + * @hmac_len: the session HMAC or password length, maybe 0 if not used + */ +static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle, + const u8 *nonce, u16 nonce_len, + u8 attributes, + const u8 *hmac, u16 hmac_len) +{ + tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len); + tpm_buf_append_u32(buf, session_handle); + tpm_buf_append_u16(buf, nonce_len); + + if (nonce && nonce_len) + tpm_buf_append(buf, nonce, nonce_len); + + tpm_buf_append_u8(buf, attributes); + tpm_buf_append_u16(buf, hmac_len); + + if (hmac && hmac_len) + tpm_buf_append(buf, hmac, hmac_len); +} + +/** + * tpm2_seal_trusted() - seal the payload of a trusted key + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * + * Return: < 0 on error and 0 on success. + */ +int tpm2_seal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + unsigned int blob_len; + struct tpm_buf buf; + u32 hash; + int i; + int rc; + + for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) { + if (options->hash == tpm2_hash_map[i].crypto_id) { + hash = tpm2_hash_map[i].tpm_id; + break; + } + } + + if (i == ARRAY_SIZE(tpm2_hash_map)) + return -EINVAL; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, options->keyhandle); + tpm2_buf_append_auth(&buf, TPM2_RS_PW, + NULL /* nonce */, 0, + 0 /* session_attributes */, + options->keyauth /* hmac */, + TPM_DIGEST_SIZE); + + /* sensitive */ + tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); + + tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); + tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); + tpm_buf_append_u16(&buf, payload->key_len + 1); + tpm_buf_append(&buf, payload->key, payload->key_len); + tpm_buf_append_u8(&buf, payload->migratable); + + /* public */ + tpm_buf_append_u16(&buf, 14 + options->policydigest_len); + tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH); + tpm_buf_append_u16(&buf, hash); + + /* policy */ + if (options->policydigest_len) { + tpm_buf_append_u32(&buf, 0); + tpm_buf_append_u16(&buf, options->policydigest_len); + tpm_buf_append(&buf, options->policydigest, + options->policydigest_len); + } else { + tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH); + tpm_buf_append_u16(&buf, 0); + } + + /* public parameters */ + tpm_buf_append_u16(&buf, TPM_ALG_NULL); + tpm_buf_append_u16(&buf, 0); + + /* outside info */ + tpm_buf_append_u16(&buf, 0); + + /* creation PCR */ + tpm_buf_append_u32(&buf, 0); + + if (buf.flags & TPM_BUF_OVERFLOW) { + rc = -E2BIG; + goto out; + } + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (rc) + goto out; + + blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]); + if (blob_len > MAX_BLOB_SIZE) { + rc = -E2BIG; + goto out; + } + if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) { + rc = -EFAULT; + goto out; + } + + memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len); + payload->blob_len = blob_len; + +out: + tpm_buf_destroy(&buf); + + if (rc > 0) { + if (tpm2_rc_value(rc) == TPM2_RC_HASH) + rc = -EINVAL; + else + rc = -EPERM; + } + + return rc; +} + +/** + * tpm2_load_cmd() - execute a TPM2_Load command + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * @blob_handle: returned blob handle + * + * Return: 0 on success. + * -E2BIG on wrong payload size. + * -EPERM on tpm error status. + * < 0 error from tpm_send. + */ +static int tpm2_load_cmd(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options, + u32 *blob_handle) +{ + struct tpm_buf buf; + unsigned int private_len; + unsigned int public_len; + unsigned int blob_len; + int rc; + + private_len = be16_to_cpup((__be16 *) &payload->blob[0]); + if (private_len > (payload->blob_len - 2)) + return -E2BIG; + + public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]); + blob_len = private_len + public_len + 4; + if (blob_len > payload->blob_len) + return -E2BIG; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, options->keyhandle); + tpm2_buf_append_auth(&buf, TPM2_RS_PW, + NULL /* nonce */, 0, + 0 /* session_attributes */, + options->keyauth /* hmac */, + TPM_DIGEST_SIZE); + + tpm_buf_append(&buf, payload->blob, blob_len); + + if (buf.flags & TPM_BUF_OVERFLOW) { + rc = -E2BIG; + goto out; + } + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (!rc) + *blob_handle = be32_to_cpup( + (__be32 *) &buf.data[TPM_HEADER_SIZE]); + +out: + tpm_buf_destroy(&buf); + + if (rc > 0) + rc = -EPERM; + + return rc; +} + +/** + * tpm2_unseal_cmd() - execute a TPM2_Unload command + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * @blob_handle: blob handle + * + * Return: 0 on success + * -EPERM on tpm error status + * < 0 error from tpm_send + */ +static int tpm2_unseal_cmd(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options, + u32 blob_handle) +{ + struct tpm_buf buf; + u16 data_len; + u8 *data; + int rc; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, blob_handle); + tpm2_buf_append_auth(&buf, + options->policyhandle ? + options->policyhandle : TPM2_RS_PW, + NULL /* nonce */, 0, + TPM2_SA_CONTINUE_SESSION, + options->blobauth /* hmac */, + TPM_DIGEST_SIZE); + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (rc > 0) + rc = -EPERM; + + if (!rc) { + data_len = be16_to_cpup( + (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); + if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { + rc = -EFAULT; + goto out; + } + + if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) { + rc = -EFAULT; + goto out; + } + data = &buf.data[TPM_HEADER_SIZE + 6]; + + memcpy(payload->key, data, data_len - 1); + payload->key_len = data_len - 1; + payload->migratable = data[data_len - 1]; + } + +out: + tpm_buf_destroy(&buf); + return rc; +} + +/** + * tpm2_unseal_trusted() - unseal the payload of a trusted key + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * + * Return: Same as with tpm_send. + */ +int tpm2_unseal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + u32 blob_handle; + int rc; + + rc = tpm2_load_cmd(chip, payload, options, &blob_handle); + if (rc) + return rc; + + rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); + + return rc; +} diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c index 8a10b43daf74..40b790536def 100644 --- a/security/lockdown/lockdown.c +++ b/security/lockdown/lockdown.c @@ -20,6 +20,7 @@ static const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", + [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 41905afada63..f34ce564d92c 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -528,7 +528,7 @@ static int snd_compress_check_input(struct snd_compr_params *params) { /* first let's check the buffer parameter's */ if (params->buffer.fragment_size == 0 || - params->buffer.fragments > INT_MAX / params->buffer.fragment_size || + params->buffer.fragments > U32_MAX / params->buffer.fragment_size || params->buffer.fragments == 0) return -EINVAL; diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index d80041ea4e01..2236b5e0c1f2 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1782,11 +1782,14 @@ void snd_pcm_period_elapsed(struct snd_pcm_substream *substream) struct snd_pcm_runtime *runtime; unsigned long flags; - if (PCM_RUNTIME_CHECK(substream)) + if (snd_BUG_ON(!substream)) return; - runtime = substream->runtime; snd_pcm_stream_lock_irqsave(substream, flags); + if (PCM_RUNTIME_CHECK(substream)) + goto _unlock; + runtime = substream->runtime; + if (!snd_pcm_running(substream) || snd_pcm_update_hw_ptr0(substream, 1) < 0) goto _end; @@ -1797,6 +1800,7 @@ void snd_pcm_period_elapsed(struct snd_pcm_substream *substream) #endif _end: kill_fasync(&runtime->fasync, SIGIO, POLL_IN); + _unlock: snd_pcm_stream_unlock_irqrestore(substream, flags); } EXPORT_SYMBOL(snd_pcm_period_elapsed); diff --git a/sound/core/timer.c b/sound/core/timer.c index 5c9fbf3f4340..59ae21b0bb93 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -226,7 +226,8 @@ static int snd_timer_check_master(struct snd_timer_instance *master) return 0; } -static int snd_timer_close_locked(struct snd_timer_instance *timeri); +static int snd_timer_close_locked(struct snd_timer_instance *timeri, + struct device **card_devp_to_put); /* * open a timer instance @@ -238,6 +239,7 @@ int snd_timer_open(struct snd_timer_instance **ti, { struct snd_timer *timer; struct snd_timer_instance *timeri = NULL; + struct device *card_dev_to_put = NULL; int err; mutex_lock(®ister_mutex); @@ -261,7 +263,7 @@ int snd_timer_open(struct snd_timer_instance **ti, list_add_tail(&timeri->open_list, &snd_timer_slave_list); err = snd_timer_check_slave(timeri); if (err < 0) { - snd_timer_close_locked(timeri); + snd_timer_close_locked(timeri, &card_dev_to_put); timeri = NULL; } goto unlock; @@ -282,11 +284,11 @@ int snd_timer_open(struct snd_timer_instance **ti, goto unlock; } if (!list_empty(&timer->open_list_head)) { - timeri = list_entry(timer->open_list_head.next, + struct snd_timer_instance *t = + list_entry(timer->open_list_head.next, struct snd_timer_instance, open_list); - if (timeri->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { + if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { err = -EBUSY; - timeri = NULL; goto unlock; } } @@ -313,7 +315,7 @@ int snd_timer_open(struct snd_timer_instance **ti, timeri = NULL; if (timer->card) - put_device(&timer->card->card_dev); + card_dev_to_put = &timer->card->card_dev; module_put(timer->module); goto unlock; } @@ -323,12 +325,15 @@ int snd_timer_open(struct snd_timer_instance **ti, timer->num_instances++; err = snd_timer_check_master(timeri); if (err < 0) { - snd_timer_close_locked(timeri); + snd_timer_close_locked(timeri, &card_dev_to_put); timeri = NULL; } unlock: mutex_unlock(®ister_mutex); + /* put_device() is called after unlock for avoiding deadlock */ + if (card_dev_to_put) + put_device(card_dev_to_put); *ti = timeri; return err; } @@ -338,7 +343,8 @@ EXPORT_SYMBOL(snd_timer_open); * close a timer instance * call this with register_mutex down. */ -static int snd_timer_close_locked(struct snd_timer_instance *timeri) +static int snd_timer_close_locked(struct snd_timer_instance *timeri, + struct device **card_devp_to_put) { struct snd_timer *timer = timeri->timer; struct snd_timer_instance *slave, *tmp; @@ -395,7 +401,7 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri) timer->hw.close(timer); /* release a card refcount for safe disconnection */ if (timer->card) - put_device(&timer->card->card_dev); + *card_devp_to_put = &timer->card->card_dev; module_put(timer->module); } @@ -407,14 +413,18 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri) */ int snd_timer_close(struct snd_timer_instance *timeri) { + struct device *card_dev_to_put = NULL; int err; if (snd_BUG_ON(!timeri)) return -ENXIO; mutex_lock(®ister_mutex); - err = snd_timer_close_locked(timeri); + err = snd_timer_close_locked(timeri, &card_dev_to_put); mutex_unlock(®ister_mutex); + /* put_device() is called after unlock for avoiding deadlock */ + if (card_dev_to_put) + put_device(card_dev_to_put); return err; } EXPORT_SYMBOL(snd_timer_close); diff --git a/sound/firewire/bebob/bebob_focusrite.c b/sound/firewire/bebob/bebob_focusrite.c index 32b864bee25f..06d6a37cd853 100644 --- a/sound/firewire/bebob/bebob_focusrite.c +++ b/sound/firewire/bebob/bebob_focusrite.c @@ -27,6 +27,8 @@ #define SAFFIRE_CLOCK_SOURCE_SPDIF 1 /* clock sources as returned from register of Saffire Pro 10 and 26 */ +#define SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK 0x000000ff +#define SAFFIREPRO_CLOCK_SOURCE_DETECT_MASK 0x0000ff00 #define SAFFIREPRO_CLOCK_SOURCE_INTERNAL 0 #define SAFFIREPRO_CLOCK_SOURCE_SKIP 1 /* never used on hardware */ #define SAFFIREPRO_CLOCK_SOURCE_SPDIF 2 @@ -189,6 +191,7 @@ saffirepro_both_clk_src_get(struct snd_bebob *bebob, unsigned int *id) map = saffirepro_clk_maps[1]; /* In a case that this driver cannot handle the value of register. */ + value &= SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK; if (value >= SAFFIREPRO_CLOCK_SOURCE_COUNT || map[value] < 0) { err = -EIO; goto end; diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c index 73fee991bd75..6c1497d9f52b 100644 --- a/sound/firewire/bebob/bebob_stream.c +++ b/sound/firewire/bebob/bebob_stream.c @@ -252,8 +252,7 @@ end: return err; } -static unsigned int -map_data_channels(struct snd_bebob *bebob, struct amdtp_stream *s) +static int map_data_channels(struct snd_bebob *bebob, struct amdtp_stream *s) { unsigned int sec, sections, ch, channels; unsigned int pcm, midi, location; diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index d3999e7b0705..7e7be8e4dcf9 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -447,8 +447,6 @@ static void azx_int_disable(struct hdac_bus *bus) list_for_each_entry(azx_dev, &bus->stream_list, list) snd_hdac_stream_updateb(azx_dev, SD_CTL, SD_INT_MASK, 0); - synchronize_irq(bus->irq); - /* disable SIE for all streams */ snd_hdac_chip_writeb(bus, INTCTL, 0); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 240f4ca76391..c52419376c74 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1348,9 +1348,9 @@ static int azx_free(struct azx *chip) } if (bus->chip_init) { - azx_stop_chip(chip); azx_clear_irq_pending(chip); azx_stop_all_streams(chip); + azx_stop_chip(chip); } if (bus->irq >= 0) @@ -2396,9 +2396,18 @@ static const struct pci_device_id azx_ids[] = { /* CometLake-H */ { PCI_DEVICE(0x8086, 0x06C8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* CometLake-S */ + { PCI_DEVICE(0x8086, 0xa3f0), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Icelake */ { PCI_DEVICE(0x8086, 0x34c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Jasperlake */ + { PCI_DEVICE(0x8086, 0x38c8), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Tigerlake */ + { PCI_DEVICE(0x8086, 0xa0c8), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Elkhart Lake */ { PCI_DEVICE(0x8086, 0x4b55), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 6d1fb7c11f17..b7a1abb3e231 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -7604,7 +7604,7 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work_sync(&spec->unsol_hp_work); + cancel_delayed_work(&spec->unsol_hp_work); schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 795cbda32cbb..78bd2e3722c7 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -46,10 +46,12 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); ((codec)->core.vendor_id == 0x80862800)) #define is_cannonlake(codec) ((codec)->core.vendor_id == 0x8086280c) #define is_icelake(codec) ((codec)->core.vendor_id == 0x8086280f) +#define is_tigerlake(codec) ((codec)->core.vendor_id == 0x80862812) #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \ || is_skylake(codec) || is_broxton(codec) \ || is_kabylake(codec) || is_geminilake(codec) \ - || is_cannonlake(codec) || is_icelake(codec)) + || is_cannonlake(codec) || is_icelake(codec) \ + || is_tigerlake(codec)) #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882) #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883) #define is_valleyview_plus(codec) (is_valleyview(codec) || is_cherryview(codec)) @@ -145,6 +147,7 @@ struct hdmi_spec { struct snd_array pins; /* struct hdmi_spec_per_pin */ struct hdmi_pcm pcm_rec[16]; struct mutex pcm_lock; + struct mutex bind_lock; /* for audio component binding */ /* pcm_bitmap means which pcms have been assigned to pins*/ unsigned long pcm_bitmap; int pcm_used; /* counter of pcm_rec[] */ @@ -2258,7 +2261,7 @@ static int generic_hdmi_init(struct hda_codec *codec) struct hdmi_spec *spec = codec->spec; int pin_idx; - mutex_lock(&spec->pcm_lock); + mutex_lock(&spec->bind_lock); spec->use_jack_detect = !codec->jackpoll_interval; for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) { struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx); @@ -2275,7 +2278,7 @@ static int generic_hdmi_init(struct hda_codec *codec) snd_hda_jack_detect_enable_callback(codec, pin_nid, jack_callback); } - mutex_unlock(&spec->pcm_lock); + mutex_unlock(&spec->bind_lock); return 0; } @@ -2382,6 +2385,7 @@ static int alloc_generic_hdmi(struct hda_codec *codec) spec->ops = generic_standard_hdmi_ops; spec->dev_num = 1; /* initialize to 1 */ mutex_init(&spec->pcm_lock); + mutex_init(&spec->bind_lock); snd_hdac_register_chmap_ops(&codec->core, &spec->chmap); spec->chmap.ops.get_chmap = hdmi_get_chmap; @@ -2451,7 +2455,7 @@ static void generic_acomp_notifier_set(struct drm_audio_component *acomp, int i; spec = container_of(acomp->audio_ops, struct hdmi_spec, drm_audio_ops); - mutex_lock(&spec->pcm_lock); + mutex_lock(&spec->bind_lock); spec->use_acomp_notifier = use_acomp; spec->codec->relaxed_resume = use_acomp; /* reprogram each jack detection logic depending on the notifier */ @@ -2461,7 +2465,7 @@ static void generic_acomp_notifier_set(struct drm_audio_component *acomp, get_pin(spec, i)->pin_nid, use_acomp); } - mutex_unlock(&spec->pcm_lock); + mutex_unlock(&spec->bind_lock); } /* enable / disable the notifier via master bind / unbind */ @@ -2849,6 +2853,18 @@ static int patch_i915_icl_hdmi(struct hda_codec *codec) return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map)); } +static int patch_i915_tgl_hdmi(struct hda_codec *codec) +{ + /* + * pin to port mapping table where the value indicate the pin number and + * the index indicate the port number with 1 base. + */ + static const int map[] = {0x4, 0x6, 0x8, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf}; + + return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map)); +} + + /* Intel Baytrail and Braswell; with eld notifier */ static int patch_i915_byt_hdmi(struct hda_codec *codec) { @@ -4151,6 +4167,7 @@ HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), +HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index ce4f11659765..80f66ba85f87 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -393,6 +393,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0700: case 0x10ec0701: case 0x10ec0703: + case 0x10ec0711: alc_update_coef_idx(codec, 0x10, 1<<15, 0); break; case 0x10ec0662: @@ -408,6 +409,9 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0672: alc_update_coef_idx(codec, 0xd, 0, 1<<14); /* EAPD Ctrl */ break; + case 0x10ec0623: + alc_update_coef_idx(codec, 0x19, 1<<13, 0); + break; case 0x10ec0668: alc_update_coef_idx(codec, 0x7, 3<<13, 0); break; @@ -2919,6 +2923,7 @@ enum { ALC269_TYPE_ALC225, ALC269_TYPE_ALC294, ALC269_TYPE_ALC300, + ALC269_TYPE_ALC623, ALC269_TYPE_ALC700, }; @@ -2954,6 +2959,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec) case ALC269_TYPE_ALC225: case ALC269_TYPE_ALC294: case ALC269_TYPE_ALC300: + case ALC269_TYPE_ALC623: case ALC269_TYPE_ALC700: ssids = alc269_ssids; break; @@ -7215,6 +7221,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -8016,9 +8024,13 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC300; spec->gen.mixer_nid = 0; /* no loopback on ALC300 */ break; + case 0x10ec0623: + spec->codec_variant = ALC269_TYPE_ALC623; + break; case 0x10ec0700: case 0x10ec0701: case 0x10ec0703: + case 0x10ec0711: spec->codec_variant = ALC269_TYPE_ALC700; spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x4a, 1 << 15, 0); /* Combo jack auto trigger control */ @@ -9216,6 +9228,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0298, "ALC298", patch_alc269), HDA_CODEC_ENTRY(0x10ec0299, "ALC299", patch_alc269), HDA_CODEC_ENTRY(0x10ec0300, "ALC300", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0623, "ALC623", patch_alc269), HDA_CODEC_REV_ENTRY(0x10ec0861, 0x100340, "ALC660", patch_alc861), HDA_CODEC_ENTRY(0x10ec0660, "ALC660-VD", patch_alc861vd), HDA_CODEC_ENTRY(0x10ec0861, "ALC861", patch_alc861), @@ -9233,6 +9246,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0700, "ALC700", patch_alc269), HDA_CODEC_ENTRY(0x10ec0701, "ALC701", patch_alc269), HDA_CODEC_ENTRY(0x10ec0703, "ALC703", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0711, "ALC711", patch_alc269), HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc662), HDA_CODEC_ENTRY(0x10ec0880, "ALC880", patch_alc880), HDA_CODEC_ENTRY(0x10ec0882, "ALC882", patch_alc882), diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index 91242b6f8ea7..4570f662fb48 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -410,8 +410,8 @@ static void hdac_hda_codec_remove(struct snd_soc_component *component) return; } - snd_hdac_ext_bus_link_put(hdev->bus, hlink); pm_runtime_disable(&hdev->dev); + snd_hdac_ext_bus_link_put(hdev->bus, hlink); } static const struct snd_soc_dapm_route hdac_hda_dapm_routes[] = { diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index b5fd8f08726e..f8b5b960e597 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -274,7 +274,7 @@ struct hdmi_codec_priv { uint8_t eld[MAX_ELD_BYTES]; struct snd_pcm_chmap *chmap_info; unsigned int chmap_idx; - struct mutex lock; + unsigned long busy; struct snd_soc_jack *jack; unsigned int jack_status; }; @@ -390,8 +390,8 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream, struct hdmi_codec_priv *hcp = snd_soc_dai_get_drvdata(dai); int ret = 0; - ret = mutex_trylock(&hcp->lock); - if (!ret) { + ret = test_and_set_bit(0, &hcp->busy); + if (ret) { dev_err(dai->dev, "Only one simultaneous stream supported!\n"); return -EINVAL; } @@ -419,7 +419,7 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream, err: /* Release the exclusive lock on error */ - mutex_unlock(&hcp->lock); + clear_bit(0, &hcp->busy); return ret; } @@ -431,7 +431,7 @@ static void hdmi_codec_shutdown(struct snd_pcm_substream *substream, hcp->chmap_idx = HDMI_CODEC_CHMAP_IDX_UNKNOWN; hcp->hcd.ops->audio_shutdown(dai->dev->parent, hcp->hcd.data); - mutex_unlock(&hcp->lock); + clear_bit(0, &hcp->busy); } static int hdmi_codec_hw_params(struct snd_pcm_substream *substream, @@ -811,8 +811,6 @@ static int hdmi_codec_probe(struct platform_device *pdev) return -ENOMEM; hcp->hcd = *hcd; - mutex_init(&hcp->lock); - daidrv = devm_kcalloc(dev, dai_count, sizeof(*daidrv), GFP_KERNEL); if (!daidrv) return -ENOMEM; diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c index e609abcf3220..cae1def8902d 100644 --- a/sound/soc/codecs/max98373.c +++ b/sound/soc/codecs/max98373.c @@ -901,16 +901,20 @@ static void max98373_slot_config(struct i2c_client *i2c, max98373->i_slot = value & 0xF; else max98373->i_slot = 1; - - max98373->reset_gpio = of_get_named_gpio(dev->of_node, + if (dev->of_node) { + max98373->reset_gpio = of_get_named_gpio(dev->of_node, "maxim,reset-gpio", 0); - if (!gpio_is_valid(max98373->reset_gpio)) { - dev_err(dev, "Looking up %s property in node %s failed %d\n", - "maxim,reset-gpio", dev->of_node->full_name, - max98373->reset_gpio); + if (!gpio_is_valid(max98373->reset_gpio)) { + dev_err(dev, "Looking up %s property in node %s failed %d\n", + "maxim,reset-gpio", dev->of_node->full_name, + max98373->reset_gpio); + } else { + dev_dbg(dev, "maxim,reset-gpio=%d", + max98373->reset_gpio); + } } else { - dev_dbg(dev, "maxim,reset-gpio=%d", - max98373->reset_gpio); + /* this makes reset_gpio as invalid */ + max98373->reset_gpio = -1; } if (!device_property_read_u32(dev, "maxim,spkfb-slot-no", &value)) @@ -956,11 +960,11 @@ static int max98373_i2c_probe(struct i2c_client *i2c, /* Power on device */ if (gpio_is_valid(max98373->reset_gpio)) { - ret = gpio_request(max98373->reset_gpio, "MAX98373_RESET"); + ret = devm_gpio_request(&i2c->dev, max98373->reset_gpio, + "MAX98373_RESET"); if (ret) { dev_err(&i2c->dev, "%s: Failed to request gpio %d\n", __func__, max98373->reset_gpio); - gpio_free(max98373->reset_gpio); return -EINVAL; } gpio_direction_output(max98373->reset_gpio, 0); diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c index 667e9f73aba3..e3d311fb510e 100644 --- a/sound/soc/codecs/msm8916-wcd-analog.c +++ b/sound/soc/codecs/msm8916-wcd-analog.c @@ -306,7 +306,7 @@ struct pm8916_wcd_analog_priv { }; static const char *const adc2_mux_text[] = { "ZERO", "INP2", "INP3" }; -static const char *const rdac2_mux_text[] = { "ZERO", "RX2", "RX1" }; +static const char *const rdac2_mux_text[] = { "RX1", "RX2" }; static const char *const hph_text[] = { "ZERO", "Switch", }; static const struct soc_enum hph_enum = SOC_ENUM_SINGLE_VIRT( @@ -321,7 +321,7 @@ static const struct soc_enum adc2_enum = SOC_ENUM_SINGLE_VIRT( /* RDAC2 MUX */ static const struct soc_enum rdac2_mux_enum = SOC_ENUM_SINGLE( - CDC_D_CDC_CONN_HPHR_DAC_CTL, 0, 3, rdac2_mux_text); + CDC_D_CDC_CONN_HPHR_DAC_CTL, 0, 2, rdac2_mux_text); static const struct snd_kcontrol_new spkr_switch[] = { SOC_DAPM_SINGLE("Switch", CDC_A_SPKR_DAC_CTL, 7, 1, 0) diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c index 9fa5d44fdc79..58b2468fb2a7 100644 --- a/sound/soc/codecs/msm8916-wcd-digital.c +++ b/sound/soc/codecs/msm8916-wcd-digital.c @@ -243,6 +243,10 @@ static const char *const rx_mix1_text[] = { "ZERO", "IIR1", "IIR2", "RX1", "RX2", "RX3" }; +static const char * const rx_mix2_text[] = { + "ZERO", "IIR1", "IIR2" +}; + static const char *const dec_mux_text[] = { "ZERO", "ADC1", "ADC2", "ADC3", "DMIC1", "DMIC2" }; @@ -270,6 +274,16 @@ static const struct soc_enum rx3_mix1_inp_enum[] = { SOC_ENUM_SINGLE(LPASS_CDC_CONN_RX3_B2_CTL, 0, 6, rx_mix1_text), }; +/* RX1 MIX2 */ +static const struct soc_enum rx_mix2_inp1_chain_enum = + SOC_ENUM_SINGLE(LPASS_CDC_CONN_RX1_B3_CTL, + 0, 3, rx_mix2_text); + +/* RX2 MIX2 */ +static const struct soc_enum rx2_mix2_inp1_chain_enum = + SOC_ENUM_SINGLE(LPASS_CDC_CONN_RX2_B3_CTL, + 0, 3, rx_mix2_text); + /* DEC */ static const struct soc_enum dec1_mux_enum = SOC_ENUM_SINGLE( LPASS_CDC_CONN_TX_B1_CTL, 0, 6, dec_mux_text); @@ -309,6 +323,10 @@ static const struct snd_kcontrol_new rx3_mix1_inp2_mux = SOC_DAPM_ENUM( "RX3 MIX1 INP2 Mux", rx3_mix1_inp_enum[1]); static const struct snd_kcontrol_new rx3_mix1_inp3_mux = SOC_DAPM_ENUM( "RX3 MIX1 INP3 Mux", rx3_mix1_inp_enum[2]); +static const struct snd_kcontrol_new rx1_mix2_inp1_mux = SOC_DAPM_ENUM( + "RX1 MIX2 INP1 Mux", rx_mix2_inp1_chain_enum); +static const struct snd_kcontrol_new rx2_mix2_inp1_mux = SOC_DAPM_ENUM( + "RX2 MIX2 INP1 Mux", rx2_mix2_inp1_chain_enum); /* Digital Gain control -38.4 dB to +38.4 dB in 0.3 dB steps */ static const DECLARE_TLV_DB_SCALE(digital_gain, -3840, 30, 0); @@ -740,6 +758,10 @@ static const struct snd_soc_dapm_widget msm8916_wcd_digital_dapm_widgets[] = { &rx3_mix1_inp2_mux), SND_SOC_DAPM_MUX("RX3 MIX1 INP3", SND_SOC_NOPM, 0, 0, &rx3_mix1_inp3_mux), + SND_SOC_DAPM_MUX("RX1 MIX2 INP1", SND_SOC_NOPM, 0, 0, + &rx1_mix2_inp1_mux), + SND_SOC_DAPM_MUX("RX2 MIX2 INP1", SND_SOC_NOPM, 0, 0, + &rx2_mix2_inp1_mux), SND_SOC_DAPM_MUX("CIC1 MUX", SND_SOC_NOPM, 0, 0, &cic1_mux), SND_SOC_DAPM_MUX("CIC2 MUX", SND_SOC_NOPM, 0, 0, &cic2_mux), diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c index 762595de956c..c506c9305043 100644 --- a/sound/soc/codecs/rt5651.c +++ b/sound/soc/codecs/rt5651.c @@ -1770,6 +1770,9 @@ static int rt5651_detect_headset(struct snd_soc_component *component) static bool rt5651_support_button_press(struct rt5651_priv *rt5651) { + if (!rt5651->hp_jack) + return false; + /* Button press support only works with internal jack-detection */ return (rt5651->hp_jack->status & SND_JACK_MICROPHONE) && rt5651->gpiod_hp_det == NULL; diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 1ef470700ed5..c50b75ce82e0 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -995,6 +995,16 @@ static int rt5682_set_jack_detect(struct snd_soc_component *component, { struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); + rt5682->hs_jack = hs_jack; + + if (!hs_jack) { + regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2, + RT5682_JD1_EN_MASK, RT5682_JD1_DIS); + regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL, + RT5682_POW_JDH | RT5682_POW_JDL, 0); + return 0; + } + switch (rt5682->pdata.jd_src) { case RT5682_JD1: snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_2, @@ -1032,8 +1042,6 @@ static int rt5682_set_jack_detect(struct snd_soc_component *component, break; } - rt5682->hs_jack = hs_jack; - return 0; } diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index c3d06e8bc54f..d5fb7f5dd551 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -533,13 +533,10 @@ static SOC_ENUM_SINGLE_DECL(dac_osr, static SOC_ENUM_SINGLE_DECL(adc_osr, WM8994_OVERSAMPLING, 1, osr_text); -static const struct snd_kcontrol_new wm8994_snd_controls[] = { +static const struct snd_kcontrol_new wm8994_common_snd_controls[] = { SOC_DOUBLE_R_TLV("AIF1ADC1 Volume", WM8994_AIF1_ADC1_LEFT_VOLUME, WM8994_AIF1_ADC1_RIGHT_VOLUME, 1, 119, 0, digital_tlv), -SOC_DOUBLE_R_TLV("AIF1ADC2 Volume", WM8994_AIF1_ADC2_LEFT_VOLUME, - WM8994_AIF1_ADC2_RIGHT_VOLUME, - 1, 119, 0, digital_tlv), SOC_DOUBLE_R_TLV("AIF2ADC Volume", WM8994_AIF2_ADC_LEFT_VOLUME, WM8994_AIF2_ADC_RIGHT_VOLUME, 1, 119, 0, digital_tlv), @@ -556,8 +553,6 @@ SOC_ENUM("AIF2DACR Source", aif2dacr_src), SOC_DOUBLE_R_TLV("AIF1DAC1 Volume", WM8994_AIF1_DAC1_LEFT_VOLUME, WM8994_AIF1_DAC1_RIGHT_VOLUME, 1, 96, 0, digital_tlv), -SOC_DOUBLE_R_TLV("AIF1DAC2 Volume", WM8994_AIF1_DAC2_LEFT_VOLUME, - WM8994_AIF1_DAC2_RIGHT_VOLUME, 1, 96, 0, digital_tlv), SOC_DOUBLE_R_TLV("AIF2DAC Volume", WM8994_AIF2_DAC_LEFT_VOLUME, WM8994_AIF2_DAC_RIGHT_VOLUME, 1, 96, 0, digital_tlv), @@ -565,17 +560,12 @@ SOC_SINGLE_TLV("AIF1 Boost Volume", WM8994_AIF1_CONTROL_2, 10, 3, 0, aif_tlv), SOC_SINGLE_TLV("AIF2 Boost Volume", WM8994_AIF2_CONTROL_2, 10, 3, 0, aif_tlv), SOC_SINGLE("AIF1DAC1 EQ Switch", WM8994_AIF1_DAC1_EQ_GAINS_1, 0, 1, 0), -SOC_SINGLE("AIF1DAC2 EQ Switch", WM8994_AIF1_DAC2_EQ_GAINS_1, 0, 1, 0), SOC_SINGLE("AIF2 EQ Switch", WM8994_AIF2_EQ_GAINS_1, 0, 1, 0), WM8994_DRC_SWITCH("AIF1DAC1 DRC Switch", WM8994_AIF1_DRC1_1, 2), WM8994_DRC_SWITCH("AIF1ADC1L DRC Switch", WM8994_AIF1_DRC1_1, 1), WM8994_DRC_SWITCH("AIF1ADC1R DRC Switch", WM8994_AIF1_DRC1_1, 0), -WM8994_DRC_SWITCH("AIF1DAC2 DRC Switch", WM8994_AIF1_DRC2_1, 2), -WM8994_DRC_SWITCH("AIF1ADC2L DRC Switch", WM8994_AIF1_DRC2_1, 1), -WM8994_DRC_SWITCH("AIF1ADC2R DRC Switch", WM8994_AIF1_DRC2_1, 0), - WM8994_DRC_SWITCH("AIF2DAC DRC Switch", WM8994_AIF2_DRC_1, 2), WM8994_DRC_SWITCH("AIF2ADCL DRC Switch", WM8994_AIF2_DRC_1, 1), WM8994_DRC_SWITCH("AIF2ADCR DRC Switch", WM8994_AIF2_DRC_1, 0), @@ -594,9 +584,6 @@ SOC_SINGLE("Sidetone HPF Switch", WM8994_SIDETONE, 6, 1, 0), SOC_ENUM("AIF1ADC1 HPF Mode", aif1adc1_hpf), SOC_DOUBLE("AIF1ADC1 HPF Switch", WM8994_AIF1_ADC1_FILTERS, 12, 11, 1, 0), -SOC_ENUM("AIF1ADC2 HPF Mode", aif1adc2_hpf), -SOC_DOUBLE("AIF1ADC2 HPF Switch", WM8994_AIF1_ADC2_FILTERS, 12, 11, 1, 0), - SOC_ENUM("AIF2ADC HPF Mode", aif2adc_hpf), SOC_DOUBLE("AIF2ADC HPF Switch", WM8994_AIF2_ADC_FILTERS, 12, 11, 1, 0), @@ -637,6 +624,24 @@ SOC_SINGLE("AIF2DAC 3D Stereo Switch", WM8994_AIF2_DAC_FILTERS_2, 8, 1, 0), }; +/* Controls not available on WM1811 */ +static const struct snd_kcontrol_new wm8994_snd_controls[] = { +SOC_DOUBLE_R_TLV("AIF1ADC2 Volume", WM8994_AIF1_ADC2_LEFT_VOLUME, + WM8994_AIF1_ADC2_RIGHT_VOLUME, + 1, 119, 0, digital_tlv), +SOC_DOUBLE_R_TLV("AIF1DAC2 Volume", WM8994_AIF1_DAC2_LEFT_VOLUME, + WM8994_AIF1_DAC2_RIGHT_VOLUME, 1, 96, 0, digital_tlv), + +SOC_SINGLE("AIF1DAC2 EQ Switch", WM8994_AIF1_DAC2_EQ_GAINS_1, 0, 1, 0), + +WM8994_DRC_SWITCH("AIF1DAC2 DRC Switch", WM8994_AIF1_DRC2_1, 2), +WM8994_DRC_SWITCH("AIF1ADC2L DRC Switch", WM8994_AIF1_DRC2_1, 1), +WM8994_DRC_SWITCH("AIF1ADC2R DRC Switch", WM8994_AIF1_DRC2_1, 0), + +SOC_ENUM("AIF1ADC2 HPF Mode", aif1adc2_hpf), +SOC_DOUBLE("AIF1ADC2 HPF Switch", WM8994_AIF1_ADC2_FILTERS, 12, 11, 1, 0), +}; + static const struct snd_kcontrol_new wm8994_eq_controls[] = { SOC_SINGLE_TLV("AIF1DAC1 EQ1 Volume", WM8994_AIF1_DAC1_EQ_GAINS_1, 11, 31, 0, eq_tlv), @@ -4258,13 +4263,15 @@ static int wm8994_component_probe(struct snd_soc_component *component) wm8994_handle_pdata(wm8994); wm_hubs_add_analogue_controls(component); - snd_soc_add_component_controls(component, wm8994_snd_controls, - ARRAY_SIZE(wm8994_snd_controls)); + snd_soc_add_component_controls(component, wm8994_common_snd_controls, + ARRAY_SIZE(wm8994_common_snd_controls)); snd_soc_dapm_new_controls(dapm, wm8994_dapm_widgets, ARRAY_SIZE(wm8994_dapm_widgets)); switch (control->type) { case WM8994: + snd_soc_add_component_controls(component, wm8994_snd_controls, + ARRAY_SIZE(wm8994_snd_controls)); snd_soc_dapm_new_controls(dapm, wm8994_specific_dapm_widgets, ARRAY_SIZE(wm8994_specific_dapm_widgets)); if (control->revision < 4) { @@ -4284,8 +4291,10 @@ static int wm8994_component_probe(struct snd_soc_component *component) } break; case WM8958: + snd_soc_add_component_controls(component, wm8994_snd_controls, + ARRAY_SIZE(wm8994_snd_controls)); snd_soc_add_component_controls(component, wm8958_snd_controls, - ARRAY_SIZE(wm8958_snd_controls)); + ARRAY_SIZE(wm8958_snd_controls)); snd_soc_dapm_new_controls(dapm, wm8958_dapm_widgets, ARRAY_SIZE(wm8958_dapm_widgets)); if (control->revision < 1) { diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index ae28d9907c30..9b8bb7bbe945 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1259,8 +1259,7 @@ static unsigned int wmfw_convert_flags(unsigned int in, unsigned int len) } if (in) { - if (in & WMFW_CTL_FLAG_READABLE) - out |= rd; + out |= rd; if (in & WMFW_CTL_FLAG_WRITEABLE) out |= wr; if (in & WMFW_CTL_FLAG_VOLATILE) @@ -3697,11 +3696,16 @@ static int wm_adsp_buffer_parse_legacy(struct wm_adsp *dsp) u32 xmalg, addr, magic; int i, ret; + alg_region = wm_adsp_find_alg_region(dsp, WMFW_ADSP2_XM, dsp->fw_id); + if (!alg_region) { + adsp_err(dsp, "No algorithm region found\n"); + return -EINVAL; + } + buf = wm_adsp_buffer_alloc(dsp); if (!buf) return -ENOMEM; - alg_region = wm_adsp_find_alg_region(dsp, WMFW_ADSP2_XM, dsp->fw_id); xmalg = dsp->ops->sys_config_size / sizeof(__be32); addr = alg_region->base + xmalg + ALG_XM_FIELD(magic); diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index a437567b8cee..4f6e58c3954a 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -308,6 +308,9 @@ static const struct snd_soc_dapm_widget sof_widgets[] = { SND_SOC_DAPM_HP("Headphone Jack", NULL), SND_SOC_DAPM_MIC("Headset Mic", NULL), SND_SOC_DAPM_SPK("Spk", NULL), +}; + +static const struct snd_soc_dapm_widget dmic_widgets[] = { SND_SOC_DAPM_MIC("SoC DMIC", NULL), }; @@ -318,10 +321,6 @@ static const struct snd_soc_dapm_route sof_map[] = { /* other jacks */ { "IN1P", NULL, "Headset Mic" }, - - /* digital mics */ - {"DMic", NULL, "SoC DMIC"}, - }; static const struct snd_soc_dapm_route speaker_map[] = { @@ -329,6 +328,11 @@ static const struct snd_soc_dapm_route speaker_map[] = { { "Spk", NULL, "Speaker" }, }; +static const struct snd_soc_dapm_route dmic_map[] = { + /* digital mics */ + {"DMic", NULL, "SoC DMIC"}, +}; + static int speaker_codec_init(struct snd_soc_pcm_runtime *rtd) { struct snd_soc_card *card = rtd->card; @@ -342,6 +346,28 @@ static int speaker_codec_init(struct snd_soc_pcm_runtime *rtd) return ret; } +static int dmic_init(struct snd_soc_pcm_runtime *rtd) +{ + struct snd_soc_card *card = rtd->card; + int ret; + + ret = snd_soc_dapm_new_controls(&card->dapm, dmic_widgets, + ARRAY_SIZE(dmic_widgets)); + if (ret) { + dev_err(card->dev, "DMic widget addition failed: %d\n", ret); + /* Don't need to add routes if widget addition failed */ + return ret; + } + + ret = snd_soc_dapm_add_routes(&card->dapm, dmic_map, + ARRAY_SIZE(dmic_map)); + + if (ret) + dev_err(card->dev, "DMic map addition failed: %d\n", ret); + + return ret; +} + /* sof audio machine driver for rt5682 codec */ static struct snd_soc_card sof_audio_card_rt5682 = { .name = "sof_rt5682", @@ -445,6 +471,7 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].name = "dmic01"; links[id].cpus = &cpus[id]; links[id].cpus->dai_name = "DMIC01 Pin"; + links[id].init = dmic_init; if (dmic_be_num > 1) { /* set up 2 BE links at most */ links[id + 1].name = "dmic16k"; @@ -576,6 +603,15 @@ static int sof_audio_probe(struct platform_device *pdev) /* need to get main clock from pmc */ if (sof_rt5682_quirk & SOF_RT5682_MCLK_BYTCHT_EN) { ctx->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3"); + if (IS_ERR(ctx->mclk)) { + ret = PTR_ERR(ctx->mclk); + + dev_err(&pdev->dev, + "Failed to get MCLK from pmc_plt_clk_3: %d\n", + ret); + return ret; + } + ret = clk_prepare_enable(ctx->mclk); if (ret < 0) { dev_err(&pdev->dev, @@ -621,8 +657,24 @@ static int sof_audio_probe(struct platform_device *pdev) &sof_audio_card_rt5682); } +static int sof_rt5682_remove(struct platform_device *pdev) +{ + struct snd_soc_card *card = platform_get_drvdata(pdev); + struct snd_soc_component *component = NULL; + + for_each_card_components(card, component) { + if (!strcmp(component->name, rt5682_component[0].name)) { + snd_soc_component_set_jack(component, NULL, NULL); + break; + } + } + + return 0; +} + static struct platform_driver sof_audio = { .probe = sof_audio_probe, + .remove = sof_rt5682_remove, .driver = { .name = "sof_rt5682", .pm = &snd_soc_pm_ops, diff --git a/sound/soc/kirkwood/kirkwood-i2s.c b/sound/soc/kirkwood/kirkwood-i2s.c index 61226fefe1c4..2a4ffe945177 100644 --- a/sound/soc/kirkwood/kirkwood-i2s.c +++ b/sound/soc/kirkwood/kirkwood-i2s.c @@ -555,10 +555,6 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev) return PTR_ERR(priv->clk); } - err = clk_prepare_enable(priv->clk); - if (err < 0) - return err; - priv->extclk = devm_clk_get(&pdev->dev, "extclk"); if (IS_ERR(priv->extclk)) { if (PTR_ERR(priv->extclk) == -EPROBE_DEFER) @@ -574,6 +570,10 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev) } } + err = clk_prepare_enable(priv->clk); + if (err < 0) + return err; + /* Some sensible defaults - this reflects the powerup values */ priv->ctl_play = KIRKWOOD_PLAYCTL_SIZE_24; priv->ctl_rec = KIRKWOOD_RECCTL_SIZE_24; @@ -587,7 +587,7 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev) priv->ctl_rec |= KIRKWOOD_RECCTL_BURST_128; } - err = devm_snd_soc_register_component(&pdev->dev, &kirkwood_soc_component, + err = snd_soc_register_component(&pdev->dev, &kirkwood_soc_component, soc_dai, 2); if (err) { dev_err(&pdev->dev, "snd_soc_register_component failed\n"); @@ -610,6 +610,7 @@ static int kirkwood_i2s_dev_remove(struct platform_device *pdev) { struct kirkwood_dma_data *priv = dev_get_drvdata(&pdev->dev); + snd_soc_unregister_component(&pdev->dev); if (!IS_ERR(priv->extclk)) clk_disable_unprepare(priv->extclk); clk_disable_unprepare(priv->clk); diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c index af2d5a6124c8..61c984f10d8e 100644 --- a/sound/soc/rockchip/rockchip_i2s.c +++ b/sound/soc/rockchip/rockchip_i2s.c @@ -677,7 +677,7 @@ static int rockchip_i2s_probe(struct platform_device *pdev) ret = rockchip_pcm_platform_register(&pdev->dev); if (ret) { dev_err(&pdev->dev, "Could not register PCM\n"); - return ret; + goto err_suspend; } return 0; diff --git a/sound/soc/rockchip/rockchip_max98090.c b/sound/soc/rockchip/rockchip_max98090.c index 0097df1fae66..e80b09143b63 100644 --- a/sound/soc/rockchip/rockchip_max98090.c +++ b/sound/soc/rockchip/rockchip_max98090.c @@ -66,10 +66,13 @@ static int rk_jack_event(struct notifier_block *nb, unsigned long event, struct snd_soc_jack *jack = (struct snd_soc_jack *)data; struct snd_soc_dapm_context *dapm = &jack->card->dapm; - if (event & SND_JACK_MICROPHONE) + if (event & SND_JACK_MICROPHONE) { snd_soc_dapm_force_enable_pin(dapm, "MICBIAS"); - else + snd_soc_dapm_force_enable_pin(dapm, "SHDN"); + } else { snd_soc_dapm_disable_pin(dapm, "MICBIAS"); + snd_soc_dapm_disable_pin(dapm, "SHDN"); + } snd_soc_dapm_sync(dapm); diff --git a/sound/soc/samsung/arndale_rt5631.c b/sound/soc/samsung/arndale_rt5631.c index c213913eb984..fd8c6642fb0d 100644 --- a/sound/soc/samsung/arndale_rt5631.c +++ b/sound/soc/samsung/arndale_rt5631.c @@ -5,6 +5,7 @@ // Author: Claude <claude@insginal.co.kr> #include <linux/module.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/clk.h> @@ -74,6 +75,17 @@ static struct snd_soc_card arndale_rt5631 = { .num_links = ARRAY_SIZE(arndale_rt5631_dai), }; +static void arndale_put_of_nodes(struct snd_soc_card *card) +{ + struct snd_soc_dai_link *dai_link; + int i; + + for_each_card_prelinks(card, i, dai_link) { + of_node_put(dai_link->cpus->of_node); + of_node_put(dai_link->codecs->of_node); + } +} + static int arndale_audio_probe(struct platform_device *pdev) { int n, ret; @@ -103,18 +115,31 @@ static int arndale_audio_probe(struct platform_device *pdev) if (!arndale_rt5631_dai[0].codecs->of_node) { dev_err(&pdev->dev, "Property 'samsung,audio-codec' missing or invalid\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_of_nodes; } } ret = devm_snd_soc_register_card(card->dev, card); + if (ret) { + dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret); + goto err_put_of_nodes; + } + return 0; - if (ret) - dev_err(&pdev->dev, "snd_soc_register_card() failed:%d\n", ret); - +err_put_of_nodes: + arndale_put_of_nodes(card); return ret; } +static int arndale_audio_remove(struct platform_device *pdev) +{ + struct snd_soc_card *card = platform_get_drvdata(pdev); + + arndale_put_of_nodes(card); + return 0; +} + static const struct of_device_id samsung_arndale_rt5631_of_match[] __maybe_unused = { { .compatible = "samsung,arndale-rt5631", }, { .compatible = "samsung,arndale-alc5631", }, @@ -129,6 +154,7 @@ static struct platform_driver arndale_audio_driver = { .of_match_table = of_match_ptr(samsung_arndale_rt5631_of_match), }, .probe = arndale_audio_probe, + .remove = arndale_audio_remove, }; module_platform_driver(arndale_audio_driver); diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index bda5b958d0dc..e9596c2096cd 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -761,6 +761,7 @@ static int rsnd_soc_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) } /* set format */ + rdai->bit_clk_inv = 0; switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: rdai->sys_delay = 0; diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index 0324a5c39619..28f65eba2bb4 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -508,10 +508,10 @@ static struct rsnd_mod_ops rsnd_dmapp_ops = { #define RDMA_SSI_I_N(addr, i) (addr ##_reg - 0x00300000 + (0x40 * i) + 0x8) #define RDMA_SSI_O_N(addr, i) (addr ##_reg - 0x00300000 + (0x40 * i) + 0xc) -#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400)) +#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4))) #define RDMA_SSIU_O_N(addr, i, j) RDMA_SSIU_I_N(addr, i, j) -#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400)) +#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4))) #define RDMA_SSIU_O_P(addr, i, j) RDMA_SSIU_I_P(addr, i, j) #define RDMA_SRC_I_N(addr, i) (addr ##_reg - 0x00500000 + (0x400 * i)) diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index e163dde5eab1..b600d3eaaf5c 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1070,7 +1070,7 @@ static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd) return ret; } - snd_soc_dai_trigger(cpu_dai, substream, cmd); + ret = snd_soc_dai_trigger(cpu_dai, substream, cmd); if (ret < 0) return ret; @@ -1097,7 +1097,7 @@ static int soc_pcm_bespoke_trigger(struct snd_pcm_substream *substream, return ret; } - snd_soc_dai_bespoke_trigger(cpu_dai, substream, cmd); + ret = snd_soc_dai_bespoke_trigger(cpu_dai, substream, cmd); if (ret < 0) return ret; @@ -1146,6 +1146,7 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, { struct snd_soc_dpcm *dpcm; unsigned long flags; + char *name; /* only add new dpcms */ for_each_dpcm_be(fe, stream, dpcm) { @@ -1171,9 +1172,15 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, stream ? "<-" : "->", be->dai_link->name); #ifdef CONFIG_DEBUG_FS - dpcm->debugfs_state = debugfs_create_dir(be->dai_link->name, - fe->debugfs_dpcm_root); - debugfs_create_u32("state", 0644, dpcm->debugfs_state, &dpcm->state); + name = kasprintf(GFP_KERNEL, "%s:%s", be->dai_link->name, + stream ? "capture" : "playback"); + if (name) { + dpcm->debugfs_state = debugfs_create_dir(name, + fe->debugfs_dpcm_root); + debugfs_create_u32("state", 0644, dpcm->debugfs_state, + &dpcm->state); + kfree(name); + } #endif return 1; } diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index aa9a1fca46fa..0fd032914a31 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1582,7 +1582,7 @@ static int soc_tplg_dapm_widget_create(struct soc_tplg *tplg, /* map user to kernel widget ID */ template.id = get_widget_id(le32_to_cpu(w->id)); - if (template.id < 0) + if ((int)template.id < 0) return template.id; /* strings are allocated here, but used and freed by the widget */ diff --git a/sound/soc/sof/control.c b/sound/soc/sof/control.c index a4983f90ff5b..2b8711eda362 100644 --- a/sound/soc/sof/control.c +++ b/sound/soc/sof/control.c @@ -60,13 +60,16 @@ int snd_sof_volume_put(struct snd_kcontrol *kcontrol, struct snd_sof_dev *sdev = scontrol->sdev; struct sof_ipc_ctrl_data *cdata = scontrol->control_data; unsigned int i, channels = scontrol->num_channels; + bool change = false; + u32 value; /* update each channel */ for (i = 0; i < channels; i++) { - cdata->chanv[i].value = - mixer_to_ipc(ucontrol->value.integer.value[i], + value = mixer_to_ipc(ucontrol->value.integer.value[i], scontrol->volume_table, sm->max + 1); + change = change || (value != cdata->chanv[i].value); cdata->chanv[i].channel = i; + cdata->chanv[i].value = value; } /* notify DSP of mixer updates */ @@ -76,8 +79,7 @@ int snd_sof_volume_put(struct snd_kcontrol *kcontrol, SOF_CTRL_TYPE_VALUE_CHAN_GET, SOF_CTRL_CMD_VOLUME, true); - - return 0; + return change; } int snd_sof_switch_get(struct snd_kcontrol *kcontrol, @@ -105,11 +107,15 @@ int snd_sof_switch_put(struct snd_kcontrol *kcontrol, struct snd_sof_dev *sdev = scontrol->sdev; struct sof_ipc_ctrl_data *cdata = scontrol->control_data; unsigned int i, channels = scontrol->num_channels; + bool change = false; + u32 value; /* update each channel */ for (i = 0; i < channels; i++) { - cdata->chanv[i].value = ucontrol->value.integer.value[i]; + value = ucontrol->value.integer.value[i]; + change = change || (value != cdata->chanv[i].value); cdata->chanv[i].channel = i; + cdata->chanv[i].value = value; } /* notify DSP of mixer updates */ @@ -120,7 +126,7 @@ int snd_sof_switch_put(struct snd_kcontrol *kcontrol, SOF_CTRL_CMD_SWITCH, true); - return 0; + return change; } int snd_sof_enum_get(struct snd_kcontrol *kcontrol, @@ -148,11 +154,15 @@ int snd_sof_enum_put(struct snd_kcontrol *kcontrol, struct snd_sof_dev *sdev = scontrol->sdev; struct sof_ipc_ctrl_data *cdata = scontrol->control_data; unsigned int i, channels = scontrol->num_channels; + bool change = false; + u32 value; /* update each channel */ for (i = 0; i < channels; i++) { - cdata->chanv[i].value = ucontrol->value.enumerated.item[i]; + value = ucontrol->value.enumerated.item[i]; + change = change || (value != cdata->chanv[i].value); cdata->chanv[i].channel = i; + cdata->chanv[i].value = value; } /* notify DSP of enum updates */ @@ -163,7 +173,7 @@ int snd_sof_enum_put(struct snd_kcontrol *kcontrol, SOF_CTRL_CMD_ENUM, true); - return 0; + return change; } int snd_sof_bytes_get(struct snd_kcontrol *kcontrol, diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index 54cd431faab7..5529e8eeca46 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -152,8 +152,10 @@ static ssize_t sof_dfsentry_write(struct file *file, const char __user *buffer, */ dentry = file->f_path.dentry; if (strcmp(dentry->d_name.name, "ipc_flood_count") && - strcmp(dentry->d_name.name, "ipc_flood_duration_ms")) - return -EINVAL; + strcmp(dentry->d_name.name, "ipc_flood_duration_ms")) { + ret = -EINVAL; + goto out; + } if (!strcmp(dentry->d_name.name, "ipc_flood_duration_ms")) flood_duration_test = true; diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index 479ba249e219..d62f51d33be1 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -273,6 +273,16 @@ config SND_SOC_SOF_HDA_AUDIO_CODEC Say Y if you want to enable HDAudio codecs with SOF. If unsure select "N". +config SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1 + bool "SOF enable DMI Link L1" + help + This option enables DMI L1 for both playback and capture + and disables known workarounds for specific HDaudio platforms. + Only use to look into power optimizations on platforms not + affected by DMI L1 issues. This option is not recommended. + Say Y if you want to enable DMI Link L1 + If unsure, select "N". + endif ## SND_SOC_SOF_HDA_COMMON config SND_SOC_SOF_HDA_LINK_BASELINE diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c index e282179263e8..80e2826fb447 100644 --- a/sound/soc/sof/intel/bdw.c +++ b/sound/soc/sof/intel/bdw.c @@ -37,6 +37,7 @@ #define MBOX_SIZE 0x1000 #define MBOX_DUMP_SIZE 0x30 #define EXCEPT_OFFSET 0x800 +#define EXCEPT_MAX_HDR_SIZE 0x400 /* DSP peripherals */ #define DMAC0_OFFSET 0xFE000 @@ -228,6 +229,11 @@ static void bdw_get_registers(struct snd_sof_dev *sdev, /* note: variable AR register array is not read */ /* then get panic info */ + if (xoops->arch_hdr.totalsize > EXCEPT_MAX_HDR_SIZE) { + dev_err(sdev->dev, "invalid header size 0x%x. FW oops is bogus\n", + xoops->arch_hdr.totalsize); + return; + } offset += xoops->arch_hdr.totalsize; sof_mailbox_read(sdev, offset, panic_info, sizeof(*panic_info)); @@ -451,6 +457,7 @@ static int bdw_probe(struct snd_sof_dev *sdev) /* TODO: add offsets */ sdev->mmio_bar = BDW_DSP_BAR; sdev->mailbox_bar = BDW_DSP_BAR; + sdev->dsp_oops_offset = MBOX_OFFSET; /* PCI base */ mmio = platform_get_resource(pdev, IORESOURCE_MEM, diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c index 5e7a6aaa627a..a1e514f71739 100644 --- a/sound/soc/sof/intel/byt.c +++ b/sound/soc/sof/intel/byt.c @@ -28,6 +28,7 @@ #define MBOX_OFFSET 0x144000 #define MBOX_SIZE 0x1000 #define EXCEPT_OFFSET 0x800 +#define EXCEPT_MAX_HDR_SIZE 0x400 /* DSP peripherals */ #define DMAC0_OFFSET 0x098000 @@ -126,6 +127,11 @@ static void byt_get_registers(struct snd_sof_dev *sdev, /* note: variable AR register array is not read */ /* then get panic info */ + if (xoops->arch_hdr.totalsize > EXCEPT_MAX_HDR_SIZE) { + dev_err(sdev->dev, "invalid header size 0x%x. FW oops is bogus\n", + xoops->arch_hdr.totalsize); + return; + } offset += xoops->arch_hdr.totalsize; sof_mailbox_read(sdev, offset, panic_info, sizeof(*panic_info)); diff --git a/sound/soc/sof/intel/hda-ctrl.c b/sound/soc/sof/intel/hda-ctrl.c index bc41028a7a01..df1909e1d950 100644 --- a/sound/soc/sof/intel/hda-ctrl.c +++ b/sound/soc/sof/intel/hda-ctrl.c @@ -139,20 +139,16 @@ void hda_dsp_ctrl_misc_clock_gating(struct snd_sof_dev *sdev, bool enable) */ int hda_dsp_ctrl_clock_power_gating(struct snd_sof_dev *sdev, bool enable) { -#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) - struct hdac_bus *bus = sof_to_bus(sdev); -#endif u32 val; /* enable/disable audio dsp clock gating */ val = enable ? PCI_CGCTL_ADSPDCGE : 0; snd_sof_pci_update_bits(sdev, PCI_CGCTL, PCI_CGCTL_ADSPDCGE, val); -#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) - /* enable/disable L1 support */ - val = enable ? SOF_HDA_VS_EM2_L1SEN : 0; - snd_hdac_chip_updatel(bus, VS_EM2, SOF_HDA_VS_EM2_L1SEN, val); -#endif + /* enable/disable DMI Link L1 support */ + val = enable ? HDA_VS_INTEL_EM2_L1SEN : 0; + snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, HDA_VS_INTEL_EM2, + HDA_VS_INTEL_EM2_L1SEN, val); /* enable/disable audio dsp power gating */ val = enable ? 0 : PCI_PGCTL_ADSPPGD; diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c index 6427f0b3a2f1..65c2af3fcaab 100644 --- a/sound/soc/sof/intel/hda-loader.c +++ b/sound/soc/sof/intel/hda-loader.c @@ -44,6 +44,7 @@ static int cl_stream_prepare(struct snd_sof_dev *sdev, unsigned int format, return -ENODEV; } hstream = &dsp_stream->hstream; + hstream->substream = NULL; /* allocate DMA buffer */ ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV_SG, &pci->dev, size, dmab); diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index ad8d41f22e92..0c11fceb28a7 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -185,6 +185,17 @@ hda_dsp_stream_get(struct snd_sof_dev *sdev, int direction) direction == SNDRV_PCM_STREAM_PLAYBACK ? "playback" : "capture"); + /* + * Disable DMI Link L1 entry when capture stream is opened. + * Workaround to address a known issue with host DMA that results + * in xruns during pause/release in capture scenarios. + */ + if (!IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1)) + if (stream && direction == SNDRV_PCM_STREAM_CAPTURE) + snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, + HDA_VS_INTEL_EM2, + HDA_VS_INTEL_EM2_L1SEN, 0); + return stream; } @@ -193,23 +204,43 @@ int hda_dsp_stream_put(struct snd_sof_dev *sdev, int direction, int stream_tag) { struct hdac_bus *bus = sof_to_bus(sdev); struct hdac_stream *s; + bool active_capture_stream = false; + bool found = false; spin_lock_irq(&bus->reg_lock); - /* find used stream */ + /* + * close stream matching the stream tag + * and check if there are any open capture streams. + */ list_for_each_entry(s, &bus->stream_list, list) { - if (s->direction == direction && - s->opened && s->stream_tag == stream_tag) { + if (!s->opened) + continue; + + if (s->direction == direction && s->stream_tag == stream_tag) { s->opened = false; - spin_unlock_irq(&bus->reg_lock); - return 0; + found = true; + } else if (s->direction == SNDRV_PCM_STREAM_CAPTURE) { + active_capture_stream = true; } } spin_unlock_irq(&bus->reg_lock); - dev_dbg(sdev->dev, "stream_tag %d not opened!\n", stream_tag); - return -ENODEV; + /* Enable DMI L1 entry if there are no capture streams open */ + if (!IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1)) + if (!active_capture_stream) + snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, + HDA_VS_INTEL_EM2, + HDA_VS_INTEL_EM2_L1SEN, + HDA_VS_INTEL_EM2_L1SEN); + + if (!found) { + dev_dbg(sdev->dev, "stream_tag %d not opened!\n", stream_tag); + return -ENODEV; + } + + return 0; } int hda_dsp_stream_trigger(struct snd_sof_dev *sdev, diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index c72e9a09eee1..06e84679087b 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -35,6 +35,8 @@ #define IS_CFL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa348) #define IS_CNL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9dc8) +#define EXCEPT_MAX_HDR_SIZE 0x400 + /* * Debug */ @@ -131,6 +133,11 @@ static void hda_dsp_get_registers(struct snd_sof_dev *sdev, /* note: variable AR register array is not read */ /* then get panic info */ + if (xoops->arch_hdr.totalsize > EXCEPT_MAX_HDR_SIZE) { + dev_err(sdev->dev, "invalid header size 0x%x. FW oops is bogus\n", + xoops->arch_hdr.totalsize); + return; + } offset += xoops->arch_hdr.totalsize; sof_block_read(sdev, sdev->mmio_bar, offset, panic_info, sizeof(*panic_info)); diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h index 5591841a1b6f..23e430d3e056 100644 --- a/sound/soc/sof/intel/hda.h +++ b/sound/soc/sof/intel/hda.h @@ -39,7 +39,6 @@ #define SOF_HDA_WAKESTS 0x0E #define SOF_HDA_WAKESTS_INT_MASK ((1 << 8) - 1) #define SOF_HDA_RIRBSTS 0x5d -#define SOF_HDA_VS_EM2_L1SEN BIT(13) /* SOF_HDA_GCTL register bist */ #define SOF_HDA_GCTL_RESET BIT(0) @@ -228,6 +227,10 @@ #define HDA_DSP_REG_HIPCIE (HDA_DSP_IPC_BASE + 0x0C) #define HDA_DSP_REG_HIPCCTL (HDA_DSP_IPC_BASE + 0x10) +/* Intel Vendor Specific Registers */ +#define HDA_VS_INTEL_EM2 0x1030 +#define HDA_VS_INTEL_EM2_L1SEN BIT(13) + /* HIPCI */ #define HDA_DSP_REG_HIPCI_BUSY BIT(31) #define HDA_DSP_REG_HIPCI_MSG_MASK 0x7FFFFFFF diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c index b2f359d2f7e5..086eeeab8679 100644 --- a/sound/soc/sof/ipc.c +++ b/sound/soc/sof/ipc.c @@ -572,8 +572,10 @@ static int sof_set_get_large_ctrl_data(struct snd_sof_dev *sdev, else err = sof_get_ctrl_copy_params(cdata->type, partdata, cdata, sparams); - if (err < 0) + if (err < 0) { + kfree(partdata); return err; + } msg_bytes = sparams->msg_bytes; pl_size = sparams->pl_size; diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index d7f32745fefe..9a9a381a908d 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -546,10 +546,10 @@ int snd_sof_run_firmware(struct snd_sof_dev *sdev) msecs_to_jiffies(sdev->boot_timeout)); if (ret == 0) { dev_err(sdev->dev, "error: firmware boot failure\n"); - /* after this point FW_READY msg should be ignored */ - sdev->boot_complete = true; snd_sof_dsp_dbg_dump(sdev, SOF_DBG_REGS | SOF_DBG_MBOX | SOF_DBG_TEXT | SOF_DBG_PCI); + /* after this point FW_READY msg should be ignored */ + sdev->boot_complete = true; return -EIO; } diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index e3f6a6dc0f36..2b876d497447 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -244,7 +244,7 @@ static int sof_pcm_hw_free(struct snd_pcm_substream *substream) snd_soc_rtdcom_lookup(rtd, DRV_NAME); struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component); struct snd_sof_pcm *spcm; - int ret; + int ret, err = 0; /* nothing to do for BE */ if (rtd->dai_link->no_pcm) @@ -254,26 +254,26 @@ static int sof_pcm_hw_free(struct snd_pcm_substream *substream) if (!spcm) return -EINVAL; - if (!spcm->prepared[substream->stream]) - return 0; - dev_dbg(sdev->dev, "pcm: free stream %d dir %d\n", spcm->pcm.pcm_id, substream->stream); - ret = sof_pcm_dsp_pcm_free(substream, sdev, spcm); + if (spcm->prepared[substream->stream]) { + ret = sof_pcm_dsp_pcm_free(substream, sdev, spcm); + if (ret < 0) + err = ret; + } snd_pcm_lib_free_pages(substream); cancel_work_sync(&spcm->stream[substream->stream].period_elapsed_work); - if (ret < 0) - return ret; - ret = snd_sof_pcm_platform_hw_free(sdev, substream); - if (ret < 0) + if (ret < 0) { dev_err(sdev->dev, "error: platform hw free failed\n"); + err = ret; + } - return ret; + return err; } static int sof_pcm_prepare(struct snd_pcm_substream *substream) @@ -323,6 +323,7 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd) struct sof_ipc_stream stream; struct sof_ipc_reply reply; bool reset_hw_params = false; + bool ipc_first = false; int ret; /* nothing to do for BE */ @@ -343,6 +344,7 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd) switch (cmd) { case SNDRV_PCM_TRIGGER_PAUSE_PUSH: stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_PAUSE; + ipc_first = true; break; case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_RELEASE; @@ -363,6 +365,7 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd) case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_STOP; + ipc_first = true; reset_hw_params = true; break; default: @@ -370,12 +373,22 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd) return -EINVAL; } - snd_sof_pcm_platform_trigger(sdev, substream, cmd); + /* + * DMA and IPC sequence is different for start and stop. Need to send + * STOP IPC before stop DMA + */ + if (!ipc_first) + snd_sof_pcm_platform_trigger(sdev, substream, cmd); /* send IPC to the DSP */ ret = sof_ipc_tx_message(sdev->ipc, stream.hdr.cmd, &stream, sizeof(stream), &reply, sizeof(reply)); + /* need to STOP DMA even if STOP IPC failed */ + if (ipc_first) + snd_sof_pcm_platform_trigger(sdev, substream, cmd); + + /* free PCM if reset_hw_params is set and the STOP IPC is successful */ if (!ret && reset_hw_params) ret = sof_pcm_dsp_pcm_free(substream, sdev, spcm); diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index fc85efbad378..4452594c2e17 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -543,15 +543,16 @@ static int sof_control_load_bytes(struct snd_soc_component *scomp, struct soc_bytes_ext *sbe = (struct soc_bytes_ext *)kc->private_value; int max_size = sbe->max; - if (le32_to_cpu(control->priv.size) > max_size) { + /* init the get/put bytes data */ + scontrol->size = sizeof(struct sof_ipc_ctrl_data) + + le32_to_cpu(control->priv.size); + + if (scontrol->size > max_size) { dev_err(sdev->dev, "err: bytes data size %d exceeds max %d.\n", - control->priv.size, max_size); + scontrol->size, max_size); return -EINVAL; } - /* init the get/put bytes data */ - scontrol->size = sizeof(struct sof_ipc_ctrl_data) + - le32_to_cpu(control->priv.size); scontrol->control_data = kzalloc(max_size, GFP_KERNEL); cdata = scontrol->control_data; if (!scontrol->control_data) @@ -920,7 +921,9 @@ static void sof_parse_word_tokens(struct snd_soc_component *scomp, for (j = 0; j < count; j++) { /* match token type */ if (!(tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_WORD || - tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_SHORT)) + tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_SHORT || + tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_BYTE || + tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_BOOL)) continue; /* match token id */ diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index d7501f88aaa6..48e629ac2d88 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -505,10 +505,20 @@ static int stm32_sai_set_sysclk(struct snd_soc_dai *cpu_dai, if (dir == SND_SOC_CLOCK_OUT && sai->sai_mclk) { ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV, - (unsigned int)~SAI_XCR1_NODIV); + freq ? 0 : SAI_XCR1_NODIV); if (ret < 0) return ret; + /* Assume shutdown if requested frequency is 0Hz */ + if (!freq) { + /* Release mclk rate only if rate was actually set */ + if (sai->mclk_rate) { + clk_rate_exclusive_put(sai->sai_mclk); + sai->mclk_rate = 0; + } + return 0; + } + /* If master clock is used, set parent clock now */ ret = stm32_sai_set_parent_clock(sai, freq); if (ret) @@ -1093,15 +1103,6 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream, regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0); - regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV, - SAI_XCR1_NODIV); - - /* Release mclk rate only if rate was actually set */ - if (sai->mclk_rate) { - clk_rate_exclusive_put(sai->sai_mclk); - sai->mclk_rate = 0; - } - clk_disable_unprepare(sai->sai_ck); spin_lock_irqsave(&sai->irq_lock, flags); @@ -1217,6 +1218,16 @@ static int stm32_sai_pcm_process_spdif(struct snd_pcm_substream *substream, return 0; } +/* No support of mmap in S/PDIF mode */ +static const struct snd_pcm_hardware stm32_sai_pcm_hw_spdif = { + .info = SNDRV_PCM_INFO_INTERLEAVED, + .buffer_bytes_max = 8 * PAGE_SIZE, + .period_bytes_min = 1024, + .period_bytes_max = PAGE_SIZE, + .periods_min = 2, + .periods_max = 8, +}; + static const struct snd_pcm_hardware stm32_sai_pcm_hw = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP, .buffer_bytes_max = 8 * PAGE_SIZE, @@ -1269,7 +1280,7 @@ static const struct snd_dmaengine_pcm_config stm32_sai_pcm_config = { }; static const struct snd_dmaengine_pcm_config stm32_sai_pcm_config_spdif = { - .pcm_hardware = &stm32_sai_pcm_hw, + .pcm_hardware = &stm32_sai_pcm_hw_spdif, .prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config, .process = stm32_sai_pcm_process_spdif, }; diff --git a/sound/soc/ti/sdma-pcm.c b/sound/soc/ti/sdma-pcm.c index a236350beb10..2b0bc234e1b6 100644 --- a/sound/soc/ti/sdma-pcm.c +++ b/sound/soc/ti/sdma-pcm.c @@ -62,7 +62,7 @@ int sdma_pcm_platform_register(struct device *dev, config->chan_names[0] = txdmachan; config->chan_names[1] = rxdmachan; - return devm_snd_dmaengine_pcm_register(dev, config, 0); + return devm_snd_dmaengine_pcm_register(dev, config, flags); } EXPORT_SYMBOL_GPL(sdma_pcm_platform_register); diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index a2ab8e8d3a93..4a9a2f6ef5a4 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -388,6 +388,9 @@ static void snd_complete_urb(struct urb *urb) } prepare_outbound_urb(ep, ctx); + /* can be stopped during prepare callback */ + if (unlikely(!test_bit(EP_FLAG_RUNNING, &ep->flags))) + goto exit_clear; } else { retire_inbound_urb(ep, ctx); /* can be stopped during retire callback */ diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 3fd1d1749edf..45eee5cc312e 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1229,7 +1229,8 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, if (cval->min + cval->res < cval->max) { int last_valid_res = cval->res; int saved, test, check; - get_cur_mix_raw(cval, minchn, &saved); + if (get_cur_mix_raw(cval, minchn, &saved) < 0) + goto no_res_check; for (;;) { test = saved; if (test < cval->max) @@ -1249,6 +1250,7 @@ static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval, snd_usb_set_cur_mix_value(cval, minchn, 0, saved); } +no_res_check: cval->initialized = 1; } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index fbfde996fee7..349e1e52996d 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -248,8 +248,8 @@ static int create_yamaha_midi_quirk(struct snd_usb_audio *chip, NULL, USB_MS_MIDI_OUT_JACK); if (!injd && !outjd) return -ENODEV; - if (!(injd && snd_usb_validate_midi_desc(injd)) || - !(outjd && snd_usb_validate_midi_desc(outjd))) + if ((injd && !snd_usb_validate_midi_desc(injd)) || + (outjd && !snd_usb_validate_midi_desc(outjd))) return -ENODEV; if (injd && (injd->bLength < 5 || (injd->bJackType != USB_MS_EMBEDDED && @@ -1657,6 +1657,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case 0x23ba: /* Playback Designs */ case 0x25ce: /* Mytek devices */ case 0x278b: /* Rotel? */ + case 0x292b: /* Gustard/Ess based devices */ case 0x2ab6: /* T+A devices */ case 0x3842: /* EVGA */ case 0xc502: /* HiBy devices */ diff --git a/sound/usb/validate.c b/sound/usb/validate.c index 3c8f73a0eb12..389e8657434a 100644 --- a/sound/usb/validate.c +++ b/sound/usb/validate.c @@ -75,15 +75,15 @@ static bool validate_processing_unit(const void *p, if (d->bLength < sizeof(*d)) return false; - len = d->bLength < sizeof(*d) + d->bNrInPins; + len = sizeof(*d) + d->bNrInPins; if (d->bLength < len) return false; switch (v->protocol) { case UAC_VERSION_1: default: - /* bNrChannels, wChannelConfig, iChannelNames, bControlSize */ - len += 1 + 2 + 1 + 1; - if (d->bLength < len) /* bControlSize */ + /* bNrChannels, wChannelConfig, iChannelNames */ + len += 1 + 2 + 1; + if (d->bLength < len + 1) /* bControlSize */ return false; m = hdr[len]; len += 1 + m + 1; /* bControlSize, bmControls, iProcessing */ diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index a9731f8a480f..2e8a30f06c74 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -75,6 +75,7 @@ #define SVM_EXIT_MWAIT 0x08b #define SVM_EXIT_MWAIT_COND 0x08c #define SVM_EXIT_XSETBV 0x08d +#define SVM_EXIT_RDPRU 0x08e #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index f01950aa7fae..3eb8411ab60e 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -86,6 +86,8 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 +#define EXIT_REASON_UMWAIT 67 +#define EXIT_REASON_TPAUSE 68 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -144,7 +146,9 @@ { EXIT_REASON_RDSEED, "RDSEED" }, \ { EXIT_REASON_PML_FULL, "PML_FULL" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" } + { EXIT_REASON_XRSTORS, "XRSTORS" }, \ + { EXIT_REASON_UMWAIT, "UMWAIT" }, \ + { EXIT_REASON_TPAUSE, "TPAUSE" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 diff --git a/tools/gpio/Build b/tools/gpio/Build index 620c1937d957..4141f35837db 100644 --- a/tools/gpio/Build +++ b/tools/gpio/Build @@ -1,3 +1,4 @@ +gpio-utils-y += gpio-utils.o lsgpio-y += lsgpio.o gpio-utils.o gpio-hammer-y += gpio-hammer.o gpio-utils.o gpio-event-mon-y += gpio-event-mon.o gpio-utils.o diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index 6ecdd1067826..6080de58861f 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -3,7 +3,11 @@ include ../scripts/Makefile.include bindir ?= /usr/bin -ifeq ($(srctree),) +# This will work when gpio is built in tools env. where srctree +# isn't set and when invoked from selftests build, where srctree +# is set to ".". building_out_of_srctree is undefined for in srctree +# builds +ifndef building_out_of_srctree srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif @@ -31,11 +35,15 @@ $(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h prepare: $(OUTPUT)include/linux/gpio.h +GPIO_UTILS_IN := $(output)gpio-utils-in.o +$(GPIO_UTILS_IN): prepare FORCE + $(Q)$(MAKE) $(build)=gpio-utils + # # lsgpio # LSGPIO_IN := $(OUTPUT)lsgpio-in.o -$(LSGPIO_IN): prepare FORCE +$(LSGPIO_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=lsgpio $(OUTPUT)lsgpio: $(LSGPIO_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ @@ -44,7 +52,7 @@ $(OUTPUT)lsgpio: $(LSGPIO_IN) # gpio-hammer # GPIO_HAMMER_IN := $(OUTPUT)gpio-hammer-in.o -$(GPIO_HAMMER_IN): prepare FORCE +$(GPIO_HAMMER_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=gpio-hammer $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ @@ -53,7 +61,7 @@ $(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN) # gpio-event-mon # GPIO_EVENT_MON_IN := $(OUTPUT)gpio-event-mon-in.o -$(GPIO_EVENT_MON_IN): prepare FORCE +$(GPIO_EVENT_MON_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(Q)$(MAKE) $(build)=gpio-event-mon $(OUTPUT)gpio-event-mon: $(GPIO_EVENT_MON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 1d338357df8a..1f97b33c840e 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -58,7 +58,7 @@ * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be * used to clear any hints previously set. */ -#define RWF_WRITE_LIFE_NOT_SET 0 +#define RWH_WRITE_LIFE_NOT_SET 0 #define RWH_WRITE_LIFE_NONE 1 #define RWH_WRITE_LIFE_SHORT 2 #define RWH_WRITE_LIFE_MEDIUM 3 @@ -66,6 +66,13 @@ #define RWH_WRITE_LIFE_EXTREME 5 /* + * The originally introduced spelling is remained from the first + * versions of the patch set that introduced the feature, see commit + * v4.13-rc1~212^2~51. + */ +#define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET + +/* * Types of directory notifications that may be requested. */ #define DN_ACCESS 0x00000001 /* File accessed */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 233efbb1c81c..52641d8ca9e8 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -999,6 +999,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_PTRAUTH_GENERIC 172 #define KVM_CAP_PMU_EVENT_FILTER 173 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174 +#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175 #ifdef KVM_CAP_IRQ_ROUTING @@ -1145,6 +1146,7 @@ struct kvm_dirty_tlb { #define KVM_REG_S390 0x5000000000000000ULL #define KVM_REG_ARM64 0x6000000000000000ULL #define KVM_REG_MIPS 0x7000000000000000ULL +#define KVM_REG_RISCV 0x8000000000000000ULL #define KVM_REG_SIZE_SHIFT 52 #define KVM_REG_SIZE_MASK 0x00f0000000000000ULL diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index b3105ac1381a..99335e1f4a27 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -33,8 +33,31 @@ #define CLONE_NEWNET 0x40000000 /* New network namespace */ #define CLONE_IO 0x80000000 /* Clone io context */ -/* - * Arguments for the clone3 syscall +#ifndef __ASSEMBLY__ +/** + * struct clone_args - arguments for the clone3 syscall + * @flags: Flags for the new process as listed above. + * All flags are valid except for CSIGNAL and + * CLONE_DETACHED. + * @pidfd: If CLONE_PIDFD is set, a pidfd will be + * returned in this argument. + * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the + * child process will be returned in the child's + * memory. + * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of + * the child process will be returned in the + * parent's memory. + * @exit_signal: The exit_signal the parent process will be + * sent when the child exits. + * @stack: Specify the location of the stack for the + * child process. + * @stack_size: The size of the stack for the child process. + * @tls: If CLONE_SETTLS is set, the tls descriptor + * is set to tls. + * + * The structure is versioned by size and thus extensible. + * New struct members must go at the end of the struct and + * must be properly 64bit aligned. */ struct clone_args { __aligned_u64 flags; @@ -46,6 +69,9 @@ struct clone_args { __aligned_u64 stack_size; __aligned_u64 tls; }; +#endif + +#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ /* * Scheduling policies diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 3542b6ab9813..e69f44941aad 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2635,6 +2635,7 @@ static int build_cl_output(char *cl_sort, bool no_source) bool add_sym = false; bool add_dso = false; bool add_src = false; + int ret = 0; if (!buf) return -ENOMEM; @@ -2653,7 +2654,8 @@ static int build_cl_output(char *cl_sort, bool no_source) add_dso = true; } else if (strcmp(tok, "offset")) { pr_err("unrecognized sort token: %s\n", tok); - return -EINVAL; + ret = -EINVAL; + goto err; } } @@ -2676,13 +2678,15 @@ static int build_cl_output(char *cl_sort, bool no_source) add_sym ? "symbol," : "", add_dso ? "dso," : "", add_src ? "cl_srcline," : "", - "node") < 0) - return -ENOMEM; + "node") < 0) { + ret = -ENOMEM; + goto err; + } c2c.show_src = add_src; - +err: free(buf); - return 0; + return ret; } static int setup_coalesce(const char *coalesce, bool no_source) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 1e61e353f579..9661671cc26e 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -691,6 +691,7 @@ static char *compact_gfp_flags(char *gfp_flags) new = realloc(new_flags, len + strlen(cpt) + 2); if (new == NULL) { free(new_flags); + free(orig_flags); return NULL; } diff --git a/tools/perf/jvmti/Build b/tools/perf/jvmti/Build index 1e148bbdf820..202cadaaf097 100644 --- a/tools/perf/jvmti/Build +++ b/tools/perf/jvmti/Build @@ -2,7 +2,7 @@ jvmti-y += libjvmti.o jvmti-y += jvmti_agent.o # For strlcpy -jvmti-y += libstring.o +jvmti-y += libstring.o libctype.o CFLAGS_jvmti = -fPIC -DPIC -I$(JDIR)/include -I$(JDIR)/include/linux CFLAGS_REMOVE_jvmti = -Wmissing-declarations @@ -15,3 +15,7 @@ CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PE $(OUTPUT)jvmti/libstring.o: ../lib/string.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) + +$(OUTPUT)jvmti/libctype.o: ../lib/ctype.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index 63e4349a772a..15e458e150bd 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -15,7 +15,9 @@ void test_attr__init(void); void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, int fd, int group_fd, unsigned long flags); -#define HAVE_ATTR_TEST +#ifndef HAVE_ATTR_TEST +#define HAVE_ATTR_TEST 1 +#endif static inline int sys_perf_event_open(struct perf_event_attr *attr, @@ -27,7 +29,7 @@ sys_perf_event_open(struct perf_event_attr *attr, fd = syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); -#ifdef HAVE_ATTR_TEST +#if HAVE_ATTR_TEST if (unlikely(test_attr__enabled)) test_attr__open(attr, pid, cpu, fd, group_fd, flags); #endif diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 4036c7f7b0fb..e42bf572358c 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1758,7 +1758,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id); if (!info_node) { - return SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; + ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; goto out; } info_linear = info_node->info_linear; diff --git a/tools/perf/util/copyfile.c b/tools/perf/util/copyfile.c index 3fa0db136667..47e03de7c235 100644 --- a/tools/perf/util/copyfile.c +++ b/tools/perf/util/copyfile.c @@ -101,14 +101,16 @@ static int copyfile_mode_ns(const char *from, const char *to, mode_t mode, if (tofd < 0) goto out; - if (fchmod(tofd, mode)) - goto out_close_to; - if (st.st_size == 0) { /* /proc? do it slowly... */ err = slow_copyfile(from, tmp, nsi); + if (!err && fchmod(tofd, mode)) + err = -1; goto out_close_to; } + if (fchmod(tofd, mode)) + goto out_close_to; + nsinfo__mountns_enter(nsi, &nsc); fromfd = open(from, O_RDONLY); nsinfo__mountns_exit(&nsc); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d277a98e62df..de79c735e441 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1659,7 +1659,7 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, is_open = false; if (c2->leader == leader) { if (is_open) - perf_evsel__close(&evsel->core); + perf_evsel__close(&c2->core); c2->leader = c2; c2->core.nr_members = 0; } diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 86d9396cb131..becc2d109423 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1296,8 +1296,10 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) continue; if (WARN_ONCE(cnt >= size, - "failed to write MEM_TOPOLOGY, way too many nodes\n")) + "failed to write MEM_TOPOLOGY, way too many nodes\n")) { + closedir(dir); return -1; + } ret = memory_node__read(&nodes[cnt++], idx); } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 679a1d75090c..7b6eaf5e0bda 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1625,7 +1625,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) +static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { struct hists *hists = a->hists; struct perf_hpp_fmt *fmt; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 15961854ba67..741f040648b5 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -539,10 +539,11 @@ static int perl_stop_script(void) static int perl_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.pl", outfile); @@ -603,8 +604,11 @@ sub print_backtrace\n\ }\n\n\ "); + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); - while ((event = trace_find_next_event(pevent, event))) { + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 5d341efc3237..93c03b39cd9c 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1687,10 +1687,11 @@ static int python_stop_script(void) static int python_generate_script(struct tep_handle *pevent, const char *outfile) { + int i, not_first, count, nr_events; + struct tep_event **all_events; struct tep_event *event = NULL; struct tep_format_field *f; char fname[PATH_MAX]; - int not_first, count; FILE *ofp; sprintf(fname, "%s.py", outfile); @@ -1735,7 +1736,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint(\"in trace_end\")\n\n"); - while ((event = trace_find_next_event(pevent, event))) { + nr_events = tep_get_events_count(pevent); + all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID); + + for (i = 0; all_events && i < nr_events; i++) { + event = all_events[i]; fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 5d6bfc70b210..9634f0ae57be 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -173,37 +173,6 @@ int parse_event_file(struct tep_handle *pevent, return tep_parse_event(pevent, buf, size, sys); } -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event) -{ - static int idx; - int events_count; - struct tep_event *all_events; - - all_events = tep_get_first_event(pevent); - events_count = tep_get_events_count(pevent); - if (!pevent || !all_events || events_count < 1) - return NULL; - - if (!event) { - idx = 0; - return all_events; - } - - if (idx < events_count && event == (all_events + idx)) { - idx++; - if (idx == events_count) - return NULL; - return (all_events + idx); - } - - for (idx = 1; idx < events_count; idx++) { - if (event == (all_events + (idx - 1))) - return (all_events + idx); - } - return NULL; -} - struct flag { const char *name; unsigned long long value; diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 2e158387b3d7..72fdf2a3577c 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -47,8 +47,6 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); -struct tep_event *trace_find_next_event(struct tep_handle *pevent, - struct tep_event *event); unsigned long long read_size(struct tep_event *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 5eda6e19c947..ae56c766eda1 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -154,8 +154,10 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) continue; - if (!match_pat(d->d_name, pat)) - return -2; + if (!match_pat(d->d_name, pat)) { + ret = -2; + break; + } scnprintf(namebuf, sizeof(namebuf), "%s/%s", path, d->d_name); diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 15a666329a34..1afa22c88e42 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -22,6 +22,7 @@ import os import pprint import random import re +import stat import string import struct import subprocess @@ -311,7 +312,11 @@ class DebugfsDir: for f in out.split(): if f == "ports": continue + p = os.path.join(path, f) + if not os.stat(p).st_mode & stat.S_IRUSR: + continue + if os.path.isfile(p): _, out = cmd('cat %s/%s' % (path, f)) dfs[f] = out.strip() diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index a320e3844b17..7c6e5b173f33 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -161,9 +161,14 @@ static struct sysctl_test tests[] = { .descr = "ctx:file_pos sysctl:read read ok narrow", .insns = { /* If (file_pos == X) */ +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, file_pos)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2), +#else + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sysctl, file_pos) + 3), +#endif + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 4, 2), /* return ALLOW; */ BPF_MOV64_IMM(BPF_REG_0, 1), @@ -176,6 +181,7 @@ static struct sysctl_test tests[] = { .attach_type = BPF_CGROUP_SYSCTL, .sysctl = "kernel/ostype", .open_flags = O_RDONLY, + .seek = 4, .result = SUCCESS, }, { diff --git a/tools/testing/selftests/bpf/test_tc_edt.sh b/tools/testing/selftests/bpf/test_tc_edt.sh index f38567ef694b..daa7d1b8d309 100755 --- a/tools/testing/selftests/bpf/test_tc_edt.sh +++ b/tools/testing/selftests/bpf/test_tc_edt.sh @@ -59,7 +59,7 @@ ip netns exec ${NS_SRC} tc filter add dev veth_src egress \ # start the listener ip netns exec ${NS_DST} bash -c \ - "nc -4 -l -s ${IP_DST} -p 9000 >/dev/null &" + "nc -4 -l -p 9000 >/dev/null &" declare -i NC_PID=$! sleep 1 diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index ae6146ec5afd..4632f51af7ab 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -112,14 +112,16 @@ sanitization_single_dev_mcast_group_test() RET=0 ip link add dev br0 type bridge mcast_snooping 0 + ip link add name dummy1 up type dummy ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ ttl 20 tos inherit local 198.51.100.1 dstport 4789 \ - dev $swp2 group 239.0.0.1 + dev dummy1 group 239.0.0.1 sanitization_single_dev_test_fail ip link del dev vxlan0 + ip link del dev dummy1 ip link del dev br0 log_test "vxlan device with a multicast group" @@ -181,13 +183,15 @@ sanitization_single_dev_local_interface_test() RET=0 ip link add dev br0 type bridge mcast_snooping 0 + ip link add name dummy1 up type dummy ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev $swp2 + ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev dummy1 sanitization_single_dev_test_fail ip link del dev vxlan0 + ip link del dev dummy1 ip link del dev br0 log_test "vxlan device with local interface" diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index b35da375530a..409c1fa75e03 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,4 +1,5 @@ /s390x/sync_regs_test +/s390x/memop /x86_64/cr4_cpuid_sync_test /x86_64/evmcs_test /x86_64/hyperv_cpuid @@ -9,6 +10,7 @@ /x86_64/state_test /x86_64/sync_regs_test /x86_64/vmx_close_while_nested_test +/x86_64/vmx_dirty_log_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test /clear_dirty_log_test diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 6ae5a47fe067..f52e0ba84fed 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -580,6 +580,8 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx); void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); bool load_vmcs(struct vmx_pages *vmx); +void nested_vmx_check_supported(void); + void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot); void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index 4911fc77d0f6..d1cf9f6e0e6b 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -55,7 +55,7 @@ static void test_dump_stack(void) #pragma GCC diagnostic pop } -static pid_t gettid(void) +static pid_t _gettid(void) { return syscall(SYS_gettid); } @@ -72,7 +72,7 @@ test_assert(bool exp, const char *exp_str, fprintf(stderr, "==== Test Assertion Failure ====\n" " %s:%u: %s\n" " pid=%d tid=%d - %s\n", - file, line, exp_str, getpid(), gettid(), + file, line, exp_str, getpid(), _gettid(), strerror(errno)); test_dump_stack(); if (fmt) { diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index fab8f6b0bf52..f6ec97b7eaef 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -376,6 +376,16 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp) init_vmcs_guest_state(guest_rip, guest_rsp); } +void nested_vmx_check_supported(void) +{ + struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + + if (!(entry->ecx & CPUID_VMX)) { + fprintf(stderr, "nested VMX not enabled, skipping test\n"); + exit(KSFT_SKIP); + } +} + void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot) { diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index 11c2a70a7b87..5c8224256294 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -22,18 +22,19 @@ #define VCPU_ID 5 +#define UCALL_PIO_PORT ((uint16_t)0x1000) + +/* + * ucall is embedded here to protect against compiler reshuffling registers + * before calling a function. In this test we only need to get KVM_EXIT_IO + * vmexit and preserve RBX, no additional information is needed. + */ void guest_code(void) { - /* - * use a callee-save register, otherwise the compiler - * saves it around the call to GUEST_SYNC. - */ - register u32 stage asm("rbx"); - for (;;) { - GUEST_SYNC(0); - stage++; - asm volatile ("" : : "r" (stage)); - } + asm volatile("1: in %[port], %%al\n" + "add $0x1, %%rbx\n" + "jmp 1b" + : : [port] "d" (UCALL_PIO_PORT) : "rax", "rbx"); } static void compare_regs(struct kvm_regs *left, struct kvm_regs *right) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index 3b0ffe01dacd..5dfb53546a26 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -53,12 +53,8 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - if (!(entry->ecx & CPUID_VMX)) { - fprintf(stderr, "nested VMX not enabled, skipping test\n"); - exit(KSFT_SKIP); - } + nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 0bca1cfe2c1e..a223a6401258 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -78,6 +78,8 @@ int main(int argc, char *argv[]) struct ucall uc; bool done = false; + nested_vmx_check_supported(); + /* Create VM */ vm = vm_create_default(VCPU_ID, 0, l1_guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 853e370e8a39..9ef7fab39d48 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -224,7 +224,6 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; struct kvm_nested_state state; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); @@ -237,10 +236,7 @@ int main(int argc, char *argv[]) * AMD currently does not implement set_nested_state, so for now we * just early out. */ - if (!(entry->ecx & CPUID_VMX)) { - fprintf(stderr, "nested VMX not enabled, skipping test\n"); - exit(KSFT_SKIP); - } + nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, 0); @@ -271,12 +267,7 @@ int main(int argc, char *argv[]) state.flags = KVM_STATE_NESTED_RUN_PENDING; test_nested_state_expect_einval(vm, &state); - /* - * TODO: When SVM support is added for KVM_SET_NESTED_STATE - * add tests here to support it like VMX. - */ - if (entry->ecx & CPUID_VMX) - test_vmx_nested_state(vm); + test_vmx_nested_state(vm); kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index f36c10eba71e..5590fd2bcf87 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -128,12 +128,8 @@ static void report(int64_t val) int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva; - struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); - if (!(entry->ecx & CPUID_VMX)) { - fprintf(stderr, "nested VMX not enabled, skipping test\n"); - exit(KSFT_SKIP); - } + nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index c4ba0ff4a53f..76c1897e6352 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1438,6 +1438,27 @@ ipv4_addr_metric_test() fi log_test $rc 0 "Prefix route with metric on link up" + # explicitly check for metric changes on edge scenarios + run_cmd "$IP addr flush dev dummy2" + run_cmd "$IP addr add dev dummy2 172.16.104.0/24 metric 259" + run_cmd "$IP addr change dev dummy2 172.16.104.0/24 metric 260" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.0 metric 260" + rc=$? + fi + log_test $rc 0 "Modify metric of .0/24 address" + + run_cmd "$IP addr flush dev dummy2" + run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260" + run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261" + rc=$? + fi + log_test $rc 0 "Modify metric of address with peer route" + $IP li del dummy1 $IP li del dummy2 cleanup diff --git a/tools/testing/selftests/net/l2tp.sh b/tools/testing/selftests/net/l2tp.sh index 5782433886fc..5782433886fc 100644..100755 --- a/tools/testing/selftests/net/l2tp.sh +++ b/tools/testing/selftests/net/l2tp.sh diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c index fe3230c55986..fb7a59ed759e 100644 --- a/tools/testing/selftests/net/reuseport_dualstack.c +++ b/tools/testing/selftests/net/reuseport_dualstack.c @@ -129,7 +129,7 @@ static void test(int *rcv_fds, int count, int proto) { struct epoll_event ev; int epfd, i, test_fd; - uint16_t test_family; + int test_family; socklen_t len; epfd = epoll_create(1); @@ -146,6 +146,7 @@ static void test(int *rcv_fds, int count, int proto) send_from_v4(proto); test_fd = receive_once(epfd, proto); + len = sizeof(test_family); if (getsockopt(test_fd, SOL_SOCKET, SO_DOMAIN, &test_family, &len)) error(1, errno, "failed to read socket domain"); if (test_family != AF_INET) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 4c285b6e1db8..1c8f194d6556 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -898,6 +898,114 @@ TEST_F(tls, nonblocking) } } +static void +test_mutliproc(struct __test_metadata *_metadata, struct _test_data_tls *self, + bool sendpg, unsigned int n_readers, unsigned int n_writers) +{ + const unsigned int n_children = n_readers + n_writers; + const size_t data = 6 * 1000 * 1000; + const size_t file_sz = data / 100; + size_t read_bias, write_bias; + int i, fd, child_id; + char buf[file_sz]; + pid_t pid; + + /* Only allow multiples for simplicity */ + ASSERT_EQ(!(n_readers % n_writers) || !(n_writers % n_readers), true); + read_bias = n_writers / n_readers ?: 1; + write_bias = n_readers / n_writers ?: 1; + + /* prep a file to send */ + fd = open("/tmp/", O_TMPFILE | O_RDWR, 0600); + ASSERT_GE(fd, 0); + + memset(buf, 0xac, file_sz); + ASSERT_EQ(write(fd, buf, file_sz), file_sz); + + /* spawn children */ + for (child_id = 0; child_id < n_children; child_id++) { + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) + break; + } + + /* parent waits for all children */ + if (pid) { + for (i = 0; i < n_children; i++) { + int status; + + wait(&status); + EXPECT_EQ(status, 0); + } + + return; + } + + /* Split threads for reading and writing */ + if (child_id < n_readers) { + size_t left = data * read_bias; + char rb[8001]; + + while (left) { + int res; + + res = recv(self->cfd, rb, + left > sizeof(rb) ? sizeof(rb) : left, 0); + + EXPECT_GE(res, 0); + left -= res; + } + } else { + size_t left = data * write_bias; + + while (left) { + int res; + + ASSERT_EQ(lseek(fd, 0, SEEK_SET), 0); + if (sendpg) + res = sendfile(self->fd, fd, NULL, + left > file_sz ? file_sz : left); + else + res = send(self->fd, buf, + left > file_sz ? file_sz : left, 0); + + EXPECT_GE(res, 0); + left -= res; + } + } +} + +TEST_F(tls, mutliproc_even) +{ + test_mutliproc(_metadata, self, false, 6, 6); +} + +TEST_F(tls, mutliproc_readers) +{ + test_mutliproc(_metadata, self, false, 4, 12); +} + +TEST_F(tls, mutliproc_writers) +{ + test_mutliproc(_metadata, self, false, 10, 2); +} + +TEST_F(tls, mutliproc_sendpage_even) +{ + test_mutliproc(_metadata, self, true, 6, 6); +} + +TEST_F(tls, mutliproc_sendpage_readers) +{ + test_mutliproc(_metadata, self, true, 4, 12); +} + +TEST_F(tls, mutliproc_sendpage_writers) +{ + test_mutliproc(_metadata, self, true, 10, 2); +} + TEST_F(tls, control_msg) { if (self->notls) diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index bd4a7247b44f..c0dd10257df5 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -44,6 +44,46 @@ static int clock_adjtime(clockid_t id, struct timex *tx) } #endif +static void show_flag_test(int rq_index, unsigned int flags, int err) +{ + printf("PTP_EXTTS_REQUEST%c flags 0x%08x : (%d) %s\n", + rq_index ? '1' + rq_index : ' ', + flags, err, strerror(errno)); + /* sigh, uClibc ... */ + errno = 0; +} + +static void do_flag_test(int fd, unsigned int index) +{ + struct ptp_extts_request extts_request; + unsigned long request[2] = { + PTP_EXTTS_REQUEST, + PTP_EXTTS_REQUEST2, + }; + unsigned int enable_flags[5] = { + PTP_ENABLE_FEATURE, + PTP_ENABLE_FEATURE | PTP_RISING_EDGE, + PTP_ENABLE_FEATURE | PTP_FALLING_EDGE, + PTP_ENABLE_FEATURE | PTP_RISING_EDGE | PTP_FALLING_EDGE, + PTP_ENABLE_FEATURE | (PTP_EXTTS_VALID_FLAGS + 1), + }; + int err, i, j; + + memset(&extts_request, 0, sizeof(extts_request)); + extts_request.index = index; + + for (i = 0; i < 2; i++) { + for (j = 0; j < 5; j++) { + extts_request.flags = enable_flags[j]; + err = ioctl(fd, request[i], &extts_request); + show_flag_test(i, extts_request.flags, err); + + extts_request.flags = 0; + err = ioctl(fd, request[i], &extts_request); + } + } +} + static clockid_t get_clockid(int fd) { #define CLOCKFD 3 @@ -96,7 +136,8 @@ static void usage(char *progname) " -s set the ptp clock time from the system time\n" " -S set the system time from the ptp clock time\n" " -t val shift the ptp clock time by 'val' seconds\n" - " -T val set the ptp clock time to 'val' seconds\n", + " -T val set the ptp clock time to 'val' seconds\n" + " -z test combinations of rising/falling external time stamp flags\n", progname); } @@ -122,6 +163,7 @@ int main(int argc, char *argv[]) int adjtime = 0; int capabilities = 0; int extts = 0; + int flagtest = 0; int gettime = 0; int index = 0; int list_pins = 0; @@ -138,7 +180,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:v"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghi:k:lL:p:P:sSt:T:z"))) { switch (c) { case 'c': capabilities = 1; @@ -191,6 +233,9 @@ int main(int argc, char *argv[]) settime = 3; seconds = atoi(optarg); break; + case 'z': + flagtest = 1; + break; case 'h': usage(progname); return 0; @@ -322,6 +367,10 @@ int main(int argc, char *argv[]) } } + if (flagtest) { + do_flag_test(fd, index); + } + if (list_pins) { int n_pins = 0; if (ioctl(fd, PTP_CLOCK_GETCAPS, &caps)) { diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index cb3fc09645c4..485cf06ef013 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -71,7 +71,7 @@ int main(int argc, char **argv) flags |= MAP_SHARED; break; case 'H': - flags |= MAP_HUGETLB; + flags |= (MAP_HUGETLB | MAP_ANONYMOUS); break; default: return -1; diff --git a/tools/usb/usbip/libsrc/usbip_device_driver.c b/tools/usb/usbip/libsrc/usbip_device_driver.c index 051d7d3f443b..927a151fa9aa 100644 --- a/tools/usb/usbip/libsrc/usbip_device_driver.c +++ b/tools/usb/usbip/libsrc/usbip_device_driver.c @@ -69,7 +69,7 @@ int read_usb_vudc_device(struct udev_device *sdev, struct usbip_usb_device *dev) FILE *fd = NULL; struct udev_device *plat; const char *speed; - int ret = 0; + size_t ret; plat = udev_device_get_parent(sdev); path = udev_device_get_syspath(plat); @@ -79,8 +79,10 @@ int read_usb_vudc_device(struct udev_device *sdev, struct usbip_usb_device *dev) if (!fd) return -1; ret = fread((char *) &descr, sizeof(descr), 1, fd); - if (ret < 0) + if (ret != 1) { + err("Cannot read vudc device descr file: %s", strerror(errno)); goto err; + } fclose(fd); copy_descr_attr(dev, &descr, bDeviceClass); diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c index 362a01886bab..8731dfeced8b 100644 --- a/virt/kvm/arm/pmu.c +++ b/virt/kvm/arm/pmu.c @@ -8,6 +8,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> +#include <linux/perf/arm_pmu.h> #include <linux/uaccess.h> #include <asm/kvm_emulate.h> #include <kvm/arm_pmu.h> @@ -146,8 +147,7 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) if (kvm_pmu_pmc_is_chained(pmc) && kvm_pmu_idx_is_high_counter(select_idx)) counter = upper_32_bits(counter); - - else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx)) + else if (select_idx != ARMV8_PMU_CYCLE_IDX) counter = lower_32_bits(counter); return counter; @@ -193,7 +193,7 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) */ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc) { - u64 counter, reg; + u64 counter, reg, val; pmc = kvm_pmu_get_canonical_pmc(pmc); if (!pmc->perf_event) @@ -201,16 +201,19 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc) counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); - if (kvm_pmu_pmc_is_chained(pmc)) { - reg = PMEVCNTR0_EL0 + pmc->idx; - __vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter); - __vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter); + if (pmc->idx == ARMV8_PMU_CYCLE_IDX) { + reg = PMCCNTR_EL0; + val = counter; } else { - reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX) - ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx; - __vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter); + reg = PMEVCNTR0_EL0 + pmc->idx; + val = lower_32_bits(counter); } + __vcpu_sys_reg(vcpu, reg) = val; + + if (kvm_pmu_pmc_is_chained(pmc)) + __vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter); + kvm_pmu_release_perf_event(pmc); } @@ -440,8 +443,25 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); int idx = pmc->idx; + u64 period; + + cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE); + + /* + * Reset the sample period to the architectural limit, + * i.e. the point where the counter overflows. + */ + period = -(local64_read(&perf_event->count)); + + if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) + period &= GENMASK(31, 0); + + local64_set(&perf_event->hw.period_left, 0); + perf_event->attr.sample_period = period; + perf_event->hw.sample_period = period; __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx); @@ -449,6 +469,8 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); } + + cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD); } /** @@ -567,12 +589,12 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx) * high counter. */ attr.sample_period = (-counter) & GENMASK(63, 0); + if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1)) + attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED; + event = perf_event_create_kernel_counter(&attr, -1, current, kvm_pmu_perf_overflow, pmc + 1); - - if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1)) - attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED; } else { /* The initial sample period (overflow count) of an event. */ if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fd68fbe0a75d..13efc291b1c7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -50,6 +50,7 @@ #include <linux/bsearch.h> #include <linux/io.h> #include <linux/lockdep.h> +#include <linux/kthread.h> #include <asm/processor.h> #include <asm/ioctl.h> @@ -121,9 +122,22 @@ static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #define KVM_COMPAT(c) .compat_ioctl = (c) #else +/* + * For architectures that don't implement a compat infrastructure, + * adopt a double line of defense: + * - Prevent a compat task from opening /dev/kvm + * - If the open has been done by a 64bit task, and the KVM fd + * passed to a compat task, let the ioctls fail. + */ static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { return -EINVAL; } -#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl + +static int kvm_no_compat_open(struct inode *inode, struct file *file) +{ + return is_compat_task() ? -ENODEV : 0; +} +#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ + .open = kvm_no_compat_open #endif static int hardware_enable_all(void); static void hardware_disable_all(void); @@ -149,10 +163,30 @@ __weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, return 0; } +bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) +{ + /* + * The metadata used by is_zone_device_page() to determine whether or + * not a page is ZONE_DEVICE is guaranteed to be valid if and only if + * the device has been pinned, e.g. by get_user_pages(). WARN if the + * page_count() is zero to help detect bad usage of this helper. + */ + if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn)))) + return false; + + return is_zone_device_page(pfn_to_page(pfn)); +} + bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { + /* + * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting + * perspective they are "normal" pages, albeit with slightly different + * usage rules. + */ if (pfn_valid(pfn)) - return PageReserved(pfn_to_page(pfn)); + return PageReserved(pfn_to_page(pfn)) && + !kvm_is_zone_device_pfn(pfn); return true; } @@ -625,10 +659,28 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) return 0; } +/* + * Called after the VM is otherwise initialized, but just before adding it to + * the vm_list. + */ +int __weak kvm_arch_post_init_vm(struct kvm *kvm) +{ + return 0; +} + +/* + * Called just after removing the VM from the vm_list, but before doing any + * other destruction. + */ +void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ +} + static struct kvm *kvm_create_vm(unsigned long type) { - int r, i; struct kvm *kvm = kvm_arch_alloc_vm(); + int r = -ENOMEM; + int i; if (!kvm) return ERR_PTR(-ENOMEM); @@ -640,46 +692,51 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); - refcount_set(&kvm->users_count, 1); INIT_LIST_HEAD(&kvm->devices); - r = kvm_arch_init_vm(kvm, type); - if (r) - goto out_err_no_disable; - - r = hardware_enable_all(); - if (r) - goto out_err_no_disable; - -#ifdef CONFIG_HAVE_KVM_IRQFD - INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); -#endif - BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); - r = -ENOMEM; + if (init_srcu_struct(&kvm->srcu)) + goto out_err_no_srcu; + if (init_srcu_struct(&kvm->irq_srcu)) + goto out_err_no_irq_srcu; + + refcount_set(&kvm->users_count, 1); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_memslots *slots = kvm_alloc_memslots(); + if (!slots) - goto out_err_no_srcu; + goto out_err_no_arch_destroy_vm; /* Generations must be different for each address space. */ slots->generation = i; rcu_assign_pointer(kvm->memslots[i], slots); } - if (init_srcu_struct(&kvm->srcu)) - goto out_err_no_srcu; - if (init_srcu_struct(&kvm->irq_srcu)) - goto out_err_no_irq_srcu; for (i = 0; i < KVM_NR_BUSES; i++) { rcu_assign_pointer(kvm->buses[i], kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT)); if (!kvm->buses[i]) - goto out_err; + goto out_err_no_arch_destroy_vm; } + r = kvm_arch_init_vm(kvm, type); + if (r) + goto out_err_no_arch_destroy_vm; + + r = hardware_enable_all(); + if (r) + goto out_err_no_disable; + +#ifdef CONFIG_HAVE_KVM_IRQFD + INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); +#endif + r = kvm_init_mmu_notifier(kvm); if (r) + goto out_err_no_mmu_notifier; + + r = kvm_arch_post_init_vm(kvm); + if (r) goto out_err; mutex_lock(&kvm_lock); @@ -691,17 +748,24 @@ static struct kvm *kvm_create_vm(unsigned long type) return kvm; out_err: - cleanup_srcu_struct(&kvm->irq_srcu); -out_err_no_irq_srcu: - cleanup_srcu_struct(&kvm->srcu); -out_err_no_srcu: +#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) + if (kvm->mmu_notifier.ops) + mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); +#endif +out_err_no_mmu_notifier: hardware_disable_all(); out_err_no_disable: - refcount_set(&kvm->users_count, 0); + kvm_arch_destroy_vm(kvm); +out_err_no_arch_destroy_vm: + WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); + cleanup_srcu_struct(&kvm->irq_srcu); +out_err_no_irq_srcu: + cleanup_srcu_struct(&kvm->srcu); +out_err_no_srcu: kvm_arch_free_vm(kvm); mmdrop(current->mm); return ERR_PTR(r); @@ -733,6 +797,8 @@ static void kvm_destroy_vm(struct kvm *kvm) mutex_lock(&kvm_lock); list_del(&kvm->vm_list); mutex_unlock(&kvm_lock); + kvm_arch_pre_destroy_vm(kvm); + kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { struct kvm_io_bus *bus = kvm_get_bus(kvm, i); @@ -1853,7 +1919,7 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); void kvm_set_pfn_dirty(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn)) { + if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) { struct page *page = pfn_to_page(pfn); SetPageDirty(page); @@ -1863,7 +1929,7 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); void kvm_set_pfn_accessed(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn)) + if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) mark_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); @@ -2360,20 +2426,23 @@ out: kvm_arch_vcpu_unblocking(vcpu); block_ns = ktime_to_ns(cur) - ktime_to_ns(start); - if (!vcpu_valid_wakeup(vcpu)) - shrink_halt_poll_ns(vcpu); - else if (halt_poll_ns) { - if (block_ns <= vcpu->halt_poll_ns) - ; - /* we had a long block, shrink polling */ - else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + if (!kvm_arch_no_poll(vcpu)) { + if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); - /* we had a short halt and our poll time is too small */ - else if (vcpu->halt_poll_ns < halt_poll_ns && - block_ns < halt_poll_ns) - grow_halt_poll_ns(vcpu); - } else - vcpu->halt_poll_ns = 0; + } else if (halt_poll_ns) { + if (block_ns <= vcpu->halt_poll_ns) + ; + /* we had a long block, shrink polling */ + else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + shrink_halt_poll_ns(vcpu); + /* we had a short halt and our poll time is too small */ + else if (vcpu->halt_poll_ns < halt_poll_ns && + block_ns < halt_poll_ns) + grow_halt_poll_ns(vcpu); + } else { + vcpu->halt_poll_ns = 0; + } + } trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu)); kvm_arch_vcpu_block_finish(vcpu); @@ -4364,3 +4433,86 @@ void kvm_exit(void) kvm_vfio_ops_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); + +struct kvm_vm_worker_thread_context { + struct kvm *kvm; + struct task_struct *parent; + struct completion init_done; + kvm_vm_thread_fn_t thread_fn; + uintptr_t data; + int err; +}; + +static int kvm_vm_worker_thread(void *context) +{ + /* + * The init_context is allocated on the stack of the parent thread, so + * we have to locally copy anything that is needed beyond initialization + */ + struct kvm_vm_worker_thread_context *init_context = context; + struct kvm *kvm = init_context->kvm; + kvm_vm_thread_fn_t thread_fn = init_context->thread_fn; + uintptr_t data = init_context->data; + int err; + + err = kthread_park(current); + /* kthread_park(current) is never supposed to return an error */ + WARN_ON(err != 0); + if (err) + goto init_complete; + + err = cgroup_attach_task_all(init_context->parent, current); + if (err) { + kvm_err("%s: cgroup_attach_task_all failed with err %d\n", + __func__, err); + goto init_complete; + } + + set_user_nice(current, task_nice(init_context->parent)); + +init_complete: + init_context->err = err; + complete(&init_context->init_done); + init_context = NULL; + + if (err) + return err; + + /* Wait to be woken up by the spawner before proceeding. */ + kthread_parkme(); + + if (!kthread_should_stop()) + err = thread_fn(kvm, data); + + return err; +} + +int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, + uintptr_t data, const char *name, + struct task_struct **thread_ptr) +{ + struct kvm_vm_worker_thread_context init_context = {}; + struct task_struct *thread; + + *thread_ptr = NULL; + init_context.kvm = kvm; + init_context.parent = current; + init_context.thread_fn = thread_fn; + init_context.data = data; + init_completion(&init_context.init_done); + + thread = kthread_run(kvm_vm_worker_thread, &init_context, + "%s-%d", name, task_pid_nr(current)); + if (IS_ERR(thread)) + return PTR_ERR(thread); + + /* kthread_run is never supposed to return NULL */ + WARN_ON(thread == NULL); + + wait_for_completion(&init_context.init_done); + + if (!init_context.err) + *thread_ptr = thread; + + return init_context.err; +} |