diff options
342 files changed, 3458 insertions, 1523 deletions
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 8ebe46b1af39..5dfcc4592b23 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -112,6 +112,20 @@ used when printing stack backtraces. The specifier takes into consideration the effect of compiler optimisations which may occur when tail-calls are used and marked with the noreturn GCC attribute. +Probed Pointers from BPF / tracing +---------------------------------- + +:: + + %pks kernel string + %pus user string + +The ``k`` and ``u`` specifiers are used for printing prior probed memory from +either kernel memory (k) or user memory (u). The subsequent ``s`` specifier +results in printing a string. For direct use in regular vsnprintf() the (k) +and (u) annotation is ignored, however, when used out of BPF's bpf_trace_printk(), +for example, it reads the memory it is pointing to without faulting. + Kernel Pointers --------------- diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index dcc252634cf9..b6833c7bb474 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -28,3 +28,5 @@ KVM arm/index devices/index + + running-nested-guests diff --git a/Documentation/virt/kvm/running-nested-guests.rst b/Documentation/virt/kvm/running-nested-guests.rst new file mode 100644 index 000000000000..d0a1fc754c84 --- /dev/null +++ b/Documentation/virt/kvm/running-nested-guests.rst @@ -0,0 +1,276 @@ +============================== +Running nested guests with KVM +============================== + +A nested guest is the ability to run a guest inside another guest (it +can be KVM-based or a different hypervisor). The straightforward +example is a KVM guest that in turn runs on a KVM guest (the rest of +this document is built on this example):: + + .----------------. .----------------. + | | | | + | L2 | | L2 | + | (Nested Guest) | | (Nested Guest) | + | | | | + |----------------'--'----------------| + | | + | L1 (Guest Hypervisor) | + | KVM (/dev/kvm) | + | | + .------------------------------------------------------. + | L0 (Host Hypervisor) | + | KVM (/dev/kvm) | + |------------------------------------------------------| + | Hardware (with virtualization extensions) | + '------------------------------------------------------' + +Terminology: + +- L0 – level-0; the bare metal host, running KVM + +- L1 – level-1 guest; a VM running on L0; also called the "guest + hypervisor", as it itself is capable of running KVM. + +- L2 – level-2 guest; a VM running on L1, this is the "nested guest" + +.. note:: The above diagram is modelled after the x86 architecture; + s390x, ppc64 and other architectures are likely to have + a different design for nesting. + + For example, s390x always has an LPAR (LogicalPARtition) + hypervisor running on bare metal, adding another layer and + resulting in at least four levels in a nested setup — L0 (bare + metal, running the LPAR hypervisor), L1 (host hypervisor), L2 + (guest hypervisor), L3 (nested guest). + + This document will stick with the three-level terminology (L0, + L1, and L2) for all architectures; and will largely focus on + x86. + + +Use Cases +--------- + +There are several scenarios where nested KVM can be useful, to name a +few: + +- As a developer, you want to test your software on different operating + systems (OSes). Instead of renting multiple VMs from a Cloud + Provider, using nested KVM lets you rent a large enough "guest + hypervisor" (level-1 guest). This in turn allows you to create + multiple nested guests (level-2 guests), running different OSes, on + which you can develop and test your software. + +- Live migration of "guest hypervisors" and their nested guests, for + load balancing, disaster recovery, etc. + +- VM image creation tools (e.g. ``virt-install``, etc) often run + their own VM, and users expect these to work inside a VM. + +- Some OSes use virtualization internally for security (e.g. to let + applications run safely in isolation). + + +Enabling "nested" (x86) +----------------------- + +From Linux kernel v4.19 onwards, the ``nested`` KVM parameter is enabled +by default for Intel and AMD. (Though your Linux distribution might +override this default.) + +In case you are running a Linux kernel older than v4.19, to enable +nesting, set the ``nested`` KVM module parameter to ``Y`` or ``1``. To +persist this setting across reboots, you can add it in a config file, as +shown below: + +1. On the bare metal host (L0), list the kernel modules and ensure that + the KVM modules:: + + $ lsmod | grep -i kvm + kvm_intel 133627 0 + kvm 435079 1 kvm_intel + +2. Show information for ``kvm_intel`` module:: + + $ modinfo kvm_intel | grep -i nested + parm: nested:bool + +3. For the nested KVM configuration to persist across reboots, place the + below in ``/etc/modprobed/kvm_intel.conf`` (create the file if it + doesn't exist):: + + $ cat /etc/modprobe.d/kvm_intel.conf + options kvm-intel nested=y + +4. Unload and re-load the KVM Intel module:: + + $ sudo rmmod kvm-intel + $ sudo modprobe kvm-intel + +5. Verify if the ``nested`` parameter for KVM is enabled:: + + $ cat /sys/module/kvm_intel/parameters/nested + Y + +For AMD hosts, the process is the same as above, except that the module +name is ``kvm-amd``. + + +Additional nested-related kernel parameters (x86) +------------------------------------------------- + +If your hardware is sufficiently advanced (Intel Haswell processor or +higher, which has newer hardware virt extensions), the following +additional features will also be enabled by default: "Shadow VMCS +(Virtual Machine Control Structure)", APIC Virtualization on your bare +metal host (L0). Parameters for Intel hosts:: + + $ cat /sys/module/kvm_intel/parameters/enable_shadow_vmcs + Y + + $ cat /sys/module/kvm_intel/parameters/enable_apicv + Y + + $ cat /sys/module/kvm_intel/parameters/ept + Y + +.. note:: If you suspect your L2 (i.e. nested guest) is running slower, + ensure the above are enabled (particularly + ``enable_shadow_vmcs`` and ``ept``). + + +Starting a nested guest (x86) +----------------------------- + +Once your bare metal host (L0) is configured for nesting, you should be +able to start an L1 guest with:: + + $ qemu-kvm -cpu host [...] + +The above will pass through the host CPU's capabilities as-is to the +gues); or for better live migration compatibility, use a named CPU +model supported by QEMU. e.g.:: + + $ qemu-kvm -cpu Haswell-noTSX-IBRS,vmx=on + +then the guest hypervisor will subsequently be capable of running a +nested guest with accelerated KVM. + + +Enabling "nested" (s390x) +------------------------- + +1. On the host hypervisor (L0), enable the ``nested`` parameter on + s390x:: + + $ rmmod kvm + $ modprobe kvm nested=1 + +.. note:: On s390x, the kernel parameter ``hpage`` is mutually exclusive + with the ``nested`` paramter — i.e. to be able to enable + ``nested``, the ``hpage`` parameter *must* be disabled. + +2. The guest hypervisor (L1) must be provided with the ``sie`` CPU + feature — with QEMU, this can be done by using "host passthrough" + (via the command-line ``-cpu host``). + +3. Now the KVM module can be loaded in the L1 (guest hypervisor):: + + $ modprobe kvm + + +Live migration with nested KVM +------------------------------ + +Migrating an L1 guest, with a *live* nested guest in it, to another +bare metal host, works as of Linux kernel 5.3 and QEMU 4.2.0 for +Intel x86 systems, and even on older versions for s390x. + +On AMD systems, once an L1 guest has started an L2 guest, the L1 guest +should no longer be migrated or saved (refer to QEMU documentation on +"savevm"/"loadvm") until the L2 guest shuts down. Attempting to migrate +or save-and-load an L1 guest while an L2 guest is running will result in +undefined behavior. You might see a ``kernel BUG!`` entry in ``dmesg``, a +kernel 'oops', or an outright kernel panic. Such a migrated or loaded L1 +guest can no longer be considered stable or secure, and must be restarted. +Migrating an L1 guest merely configured to support nesting, while not +actually running L2 guests, is expected to function normally even on AMD +systems but may fail once guests are started. + +Migrating an L2 guest is always expected to succeed, so all the following +scenarios should work even on AMD systems: + +- Migrating a nested guest (L2) to another L1 guest on the *same* bare + metal host. + +- Migrating a nested guest (L2) to another L1 guest on a *different* + bare metal host. + +- Migrating a nested guest (L2) to a bare metal host. + +Reporting bugs from nested setups +----------------------------------- + +Debugging "nested" problems can involve sifting through log files across +L0, L1 and L2; this can result in tedious back-n-forth between the bug +reporter and the bug fixer. + +- Mention that you are in a "nested" setup. If you are running any kind + of "nesting" at all, say so. Unfortunately, this needs to be called + out because when reporting bugs, people tend to forget to even + *mention* that they're using nested virtualization. + +- Ensure you are actually running KVM on KVM. Sometimes people do not + have KVM enabled for their guest hypervisor (L1), which results in + them running with pure emulation or what QEMU calls it as "TCG", but + they think they're running nested KVM. Thus confusing "nested Virt" + (which could also mean, QEMU on KVM) with "nested KVM" (KVM on KVM). + +Information to collect (generic) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The following is not an exhaustive list, but a very good starting point: + + - Kernel, libvirt, and QEMU version from L0 + + - Kernel, libvirt and QEMU version from L1 + + - QEMU command-line of L1 -- when using libvirt, you'll find it here: + ``/var/log/libvirt/qemu/instance.log`` + + - QEMU command-line of L2 -- as above, when using libvirt, get the + complete libvirt-generated QEMU command-line + + - ``cat /sys/cpuinfo`` from L0 + + - ``cat /sys/cpuinfo`` from L1 + + - ``lscpu`` from L0 + + - ``lscpu`` from L1 + + - Full ``dmesg`` output from L0 + + - Full ``dmesg`` output from L1 + +x86-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Both the below commands, ``x86info`` and ``dmidecode``, should be +available on most Linux distributions with the same name: + + - Output of: ``x86info -a`` from L0 + + - Output of: ``x86info -a`` from L1 + + - Output of: ``dmidecode`` from L0 + + - Output of: ``dmidecode`` from L1 + +s390x-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Along with the earlier mentioned generic details, the below is +also recommended: + + - ``/proc/sysinfo`` from L1; this will also include the info from L0 diff --git a/MAINTAINERS b/MAINTAINERS index d853f70181a0..b7844f6cfa4a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3936,11 +3936,9 @@ F: arch/powerpc/platforms/cell/ CEPH COMMON CODE (LIBCEPH) M: Ilya Dryomov <idryomov@gmail.com> M: Jeff Layton <jlayton@kernel.org> -M: Sage Weil <sage@redhat.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: include/linux/ceph/ F: include/linux/crush/ @@ -3948,12 +3946,10 @@ F: net/ceph/ CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH) M: Jeff Layton <jlayton@kernel.org> -M: Sage Weil <sage@redhat.com> M: Ilya Dryomov <idryomov@gmail.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/filesystems/ceph.rst F: fs/ceph/ @@ -7119,9 +7115,10 @@ F: include/uapi/asm-generic/ GENERIC PHY FRAMEWORK M: Kishon Vijay Abraham I <kishon@ti.com> +M: Vinod Koul <vkoul@kernel.org> L: linux-kernel@vger.kernel.org S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kishon/linux-phy.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git F: Documentation/devicetree/bindings/phy/ F: drivers/phy/ F: include/linux/phy/ @@ -7746,11 +7743,6 @@ L: platform-driver-x86@vger.kernel.org S: Orphan F: drivers/platform/x86/tc1100-wmi.c -HP100: Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series -M: Jaroslav Kysela <perex@perex.cz> -S: Obsolete -F: drivers/staging/hp/hp100.* - HPET: High Precision Event Timers driver M: Clemens Ladisch <clemens@ladisch.de> S: Maintained @@ -11718,8 +11710,9 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> +M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org -S: Odd Fixes +S: Maintained W: http://www.linuxfoundation.org/en/Net Q: http://patchwork.ozlabs.org/project/netdev/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -14102,12 +14095,10 @@ F: drivers/media/radio/radio-tea5777.c RADOS BLOCK DEVICE (RBD) M: Ilya Dryomov <idryomov@gmail.com> -M: Sage Weil <sage@redhat.com> R: Dongsheng Yang <dongsheng.yang@easystack.cn> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/ABI/testing/sysfs-bus-rbd F: drivers/block/rbd.c @@ -14644,6 +14635,7 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> +M: Karsten Graul <kgraul@linux.ibm.com> M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -14654,6 +14646,7 @@ F: net/iucv/ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> +M: Karsten Graul <kgraul@linux.ibm.com> M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -729,10 +729,6 @@ else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os endif -ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED -KBUILD_CFLAGS += -Wno-maybe-uninitialized -endif - # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0) KBUILD_CFLAGS += $(call cc-option,-fno-allow-store-data-races) @@ -881,6 +877,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign # disable stringop warnings in gcc 8+ KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) +# We'll want to enable this eventually, but it's not going away for 5.7 at least +KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow) + +# Another good warning that we'll want to enable eventually +KBUILD_CFLAGS += $(call cc-disable-warning, restrict) + +# Enabled with W=2, disabled by default as noisy +KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 66a04f6f4775..c77c93c485a0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -12,6 +12,7 @@ config ARM select ARCH_HAS_KEEPINITRD select ARCH_HAS_KCOV select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL if ARM_LPAE select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig index 11e2211f9007..84a3b055f253 100644 --- a/arch/arm/configs/keystone_defconfig +++ b/arch/arm/configs/keystone_defconfig @@ -147,6 +147,7 @@ CONFIG_I2C_DAVINCI=y CONFIG_SPI=y CONFIG_SPI_DAVINCI=y CONFIG_SPI_SPIDEV=y +CONFIG_PTP_1588_CLOCK=y CONFIG_PINCTRL_SINGLE=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 3cc3ca5fa027..8b83d4a5d309 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -274,6 +274,7 @@ CONFIG_SPI_TI_QSPI=m CONFIG_HSI=m CONFIG_OMAP_SSI=m CONFIG_SSI_PROTOCOL=m +CONFIG_PTP_1588_CLOCK=y CONFIG_PINCTRL_SINGLE=y CONFIG_DEBUG_GPIO=y CONFIG_GPIO_SYSFS=y diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index e133da303a98..a9151884bc85 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -165,8 +165,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) preempt_enable(); #endif - if (!ret) - *oval = oldval; + /* + * Store unconditionally. If ret != 0 the extra store is the least + * of the worries but GCC cannot figure out that __futex_atomic_op() + * is either setting ret to -EFAULT or storing the old value in + * oldval which results in a uninitialized warning at the call site. + */ + *oval = oldval; return ret; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 40fb05d96c60..5d513f461957 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -20,6 +20,7 @@ config ARM64 select ARCH_HAS_KCOV select ARCH_HAS_KEEPINITRD select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 8e9c924423b4..a0b144cfaea7 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -177,6 +177,7 @@ void machine_kexec(struct kimage *kimage) * the offline CPUs. Therefore, we must use the __* variant here. */ __flush_icache_range((uintptr_t)reboot_code_buffer, + (uintptr_t)reboot_code_buffer + arm64_relocate_new_kernel_size); /* Flush the kimage list and its buffers. */ diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 23ebe51410f0..50a279d3ddd7 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + + if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { + int i; + + for (i = 0; i < 16; i++) + *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + } out: return err; } diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index d22d0534dd60..90186cf6473e 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -18,6 +18,7 @@ #define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x) #define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x) +#define CPU_SP_EL0_OFFSET (CPU_XREG_OFFSET(30) + 8) .text .pushsection .hyp.text, "ax" @@ -47,6 +48,16 @@ ldp x29, lr, [\ctxt, #CPU_XREG_OFFSET(29)] .endm +.macro save_sp_el0 ctxt, tmp + mrs \tmp, sp_el0 + str \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] +.endm + +.macro restore_sp_el0 ctxt, tmp + ldr \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] + msr sp_el0, \tmp +.endm + /* * u64 __guest_enter(struct kvm_vcpu *vcpu, * struct kvm_cpu_context *host_ctxt); @@ -60,6 +71,9 @@ SYM_FUNC_START(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Save the host's sp_el0 + save_sp_el0 x1, x2 + // Now the host state is stored if we have a pending RAS SError it must // affect the host. If any asynchronous exception is pending we defer // the guest entry. The DSB isn't necessary before v8.2 as any SError @@ -83,6 +97,9 @@ alternative_else_nop_endif // when this feature is enabled for kernel code. ptrauth_switch_to_guest x29, x0, x1, x2 + // Restore the guest's sp_el0 + restore_sp_el0 x29, x0 + // Restore guest regs x0-x17 ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] @@ -130,6 +147,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // Store the guest regs x18-x29, lr save_callee_saved_regs x1 + // Store the guest's sp_el0 + save_sp_el0 x1, x2 + get_host_ctxt x2, x3 // Macro ptrauth_switch_to_guest format: @@ -139,6 +159,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // when this feature is enabled for kernel code. ptrauth_switch_to_host x1, x2, x3, x4, x5 + // Restore the hosts's sp_el0 + restore_sp_el0 x2, x3 + // Now restore the host regs restore_callee_saved_regs x2 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index c2a13ab3c471..9c5cfb04170e 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -198,7 +198,6 @@ SYM_CODE_END(__hyp_panic) .macro invalid_vector label, target = __hyp_panic .align 2 SYM_CODE_START(\label) -\label: b \target SYM_CODE_END(\label) .endm diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 75b1925763f1..6d2df9fe0b5d 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -15,8 +15,9 @@ /* * Non-VHE: Both host and guest must save everything. * - * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate, - * which are handled as part of the el2 return state) on every switch. + * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and + * pstate, which are handled as part of the el2 return state) on every + * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two @@ -26,12 +27,6 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - ctxt->gp_regs.regs.sp = read_sysreg(sp_el0); } static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) @@ -99,12 +94,6 @@ NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - write_sysreg(ctxt->gp_regs.regs.sp, sp_el0); } static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index bbeb6a5a6ba6..0be3355e3499 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); + if (!pmdp) + return NULL; WARN_ON(addr & (sz - 1)); /* diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index e15166b0a16d..ad2f172c26a6 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -521,6 +521,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 74f82cf4f781..a31e1a41913a 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -54,7 +54,7 @@ config RISCV select GENERIC_ARCH_TOPOLOGY if SMP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MMIOWB - select ARCH_HAS_DEBUG_VIRTUAL + select ARCH_HAS_DEBUG_VIRTUAL if MMU select HAVE_EBPF_JIT if MMU select EDAC_SUPPORT select ARCH_HAS_GIGANTIC_PAGE @@ -136,6 +136,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y config SYS_SUPPORTS_HUGETLBFS + depends on MMU def_bool y config STACKTRACE_SUPPORT diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 216286db81c9..d646332e44f1 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -11,14 +11,15 @@ config SOC_SIFIVE This enables support for SiFive SoC platform hardware. config SOC_VIRT - bool "QEMU Virt Machine" - select POWER_RESET_SYSCON - select POWER_RESET_SYSCON_POWEROFF - select GOLDFISH - select RTC_DRV_GOLDFISH - select SIFIVE_PLIC - help - This enables support for QEMU Virt Machine. + bool "QEMU Virt Machine" + select POWER_RESET + select POWER_RESET_SYSCON + select POWER_RESET_SYSCON_POWEROFF + select GOLDFISH + select RTC_DRV_GOLDFISH if RTC_CLASS + select SIFIVE_PLIC + help + This enables support for QEMU Virt Machine. config SOC_KENDRYTE bool "Kendryte K210 SoC" diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 8e18d2c64399..cec462e198ce 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -51,13 +51,10 @@ #define CAUSE_IRQ_FLAG (_AC(1, UL) << (__riscv_xlen - 1)) /* Interrupt causes (minus the high bit) */ -#define IRQ_U_SOFT 0 #define IRQ_S_SOFT 1 #define IRQ_M_SOFT 3 -#define IRQ_U_TIMER 4 #define IRQ_S_TIMER 5 #define IRQ_M_TIMER 7 -#define IRQ_U_EXT 8 #define IRQ_S_EXT 9 #define IRQ_M_EXT 11 diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 1bb0cd04aec3..5ce50468aff1 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -8,6 +8,7 @@ #ifndef _ASM_RISCV_HWCAP_H #define _ASM_RISCV_HWCAP_H +#include <linux/bits.h> #include <uapi/asm/hwcap.h> #ifndef __ASSEMBLY__ @@ -22,6 +23,27 @@ enum { }; extern unsigned long elf_hwcap; + +#define RISCV_ISA_EXT_a ('a' - 'a') +#define RISCV_ISA_EXT_c ('c' - 'a') +#define RISCV_ISA_EXT_d ('d' - 'a') +#define RISCV_ISA_EXT_f ('f' - 'a') +#define RISCV_ISA_EXT_h ('h' - 'a') +#define RISCV_ISA_EXT_i ('i' - 'a') +#define RISCV_ISA_EXT_m ('m' - 'a') +#define RISCV_ISA_EXT_s ('s' - 'a') +#define RISCV_ISA_EXT_u ('u' - 'a') + +#define RISCV_ISA_EXT_MAX 64 + +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); + +#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext) + +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit); +#define riscv_isa_extension_available(isa_bitmap, ext) \ + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) + #endif #endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index a2c809df2733..56053c9838b2 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -16,6 +16,8 @@ #ifndef CONFIG_MMU #define pgprot_noncached(x) (x) +#define pgprot_writecombine(x) (x) +#define pgprot_device(x) (x) #endif /* CONFIG_MMU */ /* Generic IO read/write. These perform native-endian accesses. */ diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h index bb4091ff4a21..0b2333e71fdc 100644 --- a/arch/riscv/include/asm/mmiowb.h +++ b/arch/riscv/include/asm/mmiowb.h @@ -9,6 +9,7 @@ */ #define mmiowb() __asm__ __volatile__ ("fence o,w" : : : "memory"); +#include <linux/smp.h> #include <asm-generic/mmiowb.h> #endif /* _ASM_RISCV_MMIOWB_H */ diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h index 0234048b12bc..062efd3a1d5d 100644 --- a/arch/riscv/include/asm/perf_event.h +++ b/arch/riscv/include/asm/perf_event.h @@ -12,19 +12,14 @@ #include <linux/ptrace.h> #include <linux/interrupt.h> +#ifdef CONFIG_RISCV_BASE_PMU #define RISCV_BASE_COUNTERS 2 /* * The RISCV_MAX_COUNTERS parameter should be specified. */ -#ifdef CONFIG_RISCV_BASE_PMU #define RISCV_MAX_COUNTERS 2 -#endif - -#ifndef RISCV_MAX_COUNTERS -#error "Please provide a valid RISCV_MAX_COUNTERS for the PMU." -#endif /* * These are the indexes of bits in counteren register *minus* 1, @@ -82,6 +77,7 @@ struct riscv_pmu { int irq; }; +#endif #ifdef CONFIG_PERF_EVENTS #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs #endif diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 9c188ad2e52d..35b60035b6b0 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -470,12 +470,15 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #else /* CONFIG_MMU */ +#define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL #define VMALLOC_START 0 #define TASK_SIZE 0xffffffffUL +static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {} + #endif /* !CONFIG_MMU */ #define kern_addr_valid(addr) (1) /* FIXME */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index c38df4771c09..4c5bae7ca01c 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -22,14 +22,6 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif -#ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_ro(void); -void set_kernel_text_rw(void); -#else -static inline void set_kernel_text_ro(void) { } -static inline void set_kernel_text_rw(void) { } -#endif - int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 86c83081044f..d8bbd3207100 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_RISCV_BASE_PMU) += perf_event.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o obj-$(CONFIG_RISCV_SBI) += sbi.o diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c index c4c33bf02369..0ec22354018c 100644 --- a/arch/riscv/kernel/cpu_ops.c +++ b/arch/riscv/kernel/cpu_ops.c @@ -15,8 +15,8 @@ const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; -void *__cpu_up_stack_pointer[NR_CPUS]; -void *__cpu_up_task_pointer[NR_CPUS]; +void *__cpu_up_stack_pointer[NR_CPUS] __section(.data); +void *__cpu_up_task_pointer[NR_CPUS] __section(.data); extern const struct cpu_operations cpu_ops_sbi; extern const struct cpu_operations cpu_ops_spinwait; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index a5ad00043104..ac202f44a670 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -6,6 +6,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/bitmap.h> #include <linux/of.h> #include <asm/processor.h> #include <asm/hwcap.h> @@ -13,15 +14,57 @@ #include <asm/switch_to.h> unsigned long elf_hwcap __read_mostly; + +/* Host ISA bitmap */ +static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; + #ifdef CONFIG_FPU bool has_fpu __read_mostly; #endif +/** + * riscv_isa_extension_base() - Get base extension word + * + * @isa_bitmap: ISA bitmap to use + * Return: base extension word as unsigned long value + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap) +{ + if (!isa_bitmap) + return riscv_isa[0]; + return isa_bitmap[0]; +} +EXPORT_SYMBOL_GPL(riscv_isa_extension_base); + +/** + * __riscv_isa_extension_available() - Check whether given extension + * is available or not + * + * @isa_bitmap: ISA bitmap to use + * @bit: bit position of the desired extension + * Return: true or false + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) +{ + const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa; + + if (bit >= RISCV_ISA_EXT_MAX) + return false; + + return test_bit(bit, bmap) ? true : false; +} +EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); + void riscv_fill_hwcap(void) { struct device_node *node; const char *isa; - size_t i; + char print_str[BITS_PER_LONG + 1]; + size_t i, j, isa_len; static unsigned long isa2hwcap[256] = {0}; isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; @@ -33,8 +76,11 @@ void riscv_fill_hwcap(void) elf_hwcap = 0; + bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); + for_each_of_cpu_node(node) { unsigned long this_hwcap = 0; + unsigned long this_isa = 0; if (riscv_of_processor_hartid(node) < 0) continue; @@ -44,8 +90,24 @@ void riscv_fill_hwcap(void) continue; } - for (i = 0; i < strlen(isa); ++i) + i = 0; + isa_len = strlen(isa); +#if IS_ENABLED(CONFIG_32BIT) + if (!strncmp(isa, "rv32", 4)) + i += 4; +#elif IS_ENABLED(CONFIG_64BIT) + if (!strncmp(isa, "rv64", 4)) + i += 4; +#endif + for (; i < isa_len; ++i) { this_hwcap |= isa2hwcap[(unsigned char)(isa[i])]; + /* + * TODO: X, Y and Z extension parsing for Host ISA + * bitmap will be added in-future. + */ + if ('a' <= isa[i] && isa[i] < 'x') + this_isa |= (1UL << (isa[i] - 'a')); + } /* * All "okay" hart should have same isa. Set HWCAP based on @@ -56,6 +118,11 @@ void riscv_fill_hwcap(void) elf_hwcap &= this_hwcap; else elf_hwcap = this_hwcap; + + if (riscv_isa[0]) + riscv_isa[0] &= this_isa; + else + riscv_isa[0] = this_isa; } /* We don't support systems with F but without D, so mask those out @@ -65,7 +132,17 @@ void riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - pr_info("elf_hwcap is 0x%lx\n", elf_hwcap); + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (riscv_isa[0] & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ISA extensions %s\n", print_str); + + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (elf_hwcap & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ELF capabilities %s\n", print_str); #ifdef CONFIG_FPU if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)) diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c index 91626d9ae5f2..c835f0362d94 100644 --- a/arch/riscv/kernel/perf_event.c +++ b/arch/riscv/kernel/perf_event.c @@ -147,7 +147,7 @@ static int riscv_map_hw_event(u64 config) return riscv_pmu->hw_events[config]; } -int riscv_map_cache_decode(u64 config, unsigned int *type, +static int riscv_map_cache_decode(u64 config, unsigned int *type, unsigned int *op, unsigned int *result) { return -ENOENT; @@ -342,7 +342,7 @@ static void riscv_pmu_del(struct perf_event *event, int flags) static DEFINE_MUTEX(pmc_reserve_mutex); -irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev) +static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev) { return IRQ_NONE; } @@ -361,7 +361,7 @@ static int reserve_pmc_hardware(void) return err; } -void release_pmc_hardware(void) +static void release_pmc_hardware(void) { mutex_lock(&pmc_reserve_mutex); if (riscv_pmu->irq >= 0) @@ -464,7 +464,7 @@ static const struct of_device_id riscv_pmu_of_ids[] = { { /* sentinel value */ } }; -int __init init_hw_perf_events(void) +static int __init init_hw_perf_events(void) { struct device_node *node = of_find_node_by_type(NULL, "pmu"); const struct of_device_id *of_id; diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index e0a6293093f1..a65a8fa0c22d 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -10,6 +10,7 @@ #include <linux/cpu.h> #include <linux/interrupt.h> +#include <linux/module.h> #include <linux/profile.h> #include <linux/smp.h> #include <linux/sched.h> @@ -63,6 +64,7 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out) for_each_cpu(cpu, in) cpumask_set_cpu(cpuid_to_hartid_map(cpu), out); } +EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask); bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 6c854875ac74..837b9b38f825 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -65,7 +65,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, #else /* !CONFIG_FRAME_POINTER */ -static void notrace walk_stackframe(struct task_struct *task, +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) { unsigned long sp, pc; diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index a4ee3a0e7d20..4c8b2a4a6a70 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -12,7 +12,7 @@ vdso-syms += getcpu vdso-syms += flush_icache # Files to link into the vdso -obj-vdso = $(patsubst %, %.o, $(vdso-syms)) +obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o # Build rules targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S new file mode 100644 index 000000000000..2a956c942211 --- /dev/null +++ b/arch/riscv/kernel/vdso/note.S @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/elfnote.h> +#include <linux/version.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b55be44ff9bd..27a334106708 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -150,7 +150,8 @@ void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = max_pfn; #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); @@ -501,22 +502,6 @@ static inline void setup_vm_final(void) #endif /* CONFIG_MMU */ #ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_rw(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_rw(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - void mark_rodata_ro(void) { unsigned long text_start = (unsigned long)_text; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5dcf9ff12828..d05bb040fd42 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -545,6 +545,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_AIS: case KVM_CAP_S390_AIS_MIGRATION: case KVM_CAP_S390_VCPU_RESETS: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_S390_HPAGE_1M: diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 69a824f9ef0b..893893642415 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu) * available for the guest are AQIC and TAPQ with the t bit set * since we do not set IC.3 (FIII) we currently will only intercept * the AQIC function code. + * Note: running nested under z/VM can result in intercepts for other + * function codes, e.g. PQAP(QCI). We do not support this and bail out. */ reg0 = vcpu->run->s.regs.gprs[0]; fc = (reg0 >> 24) & 0xff; - if (WARN_ON_ONCE(fc != 0x03)) + if (fc != 0x03) return -EOPNOTSUPP; /* PQAP instruction is allowed for guest kernel only */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1197b5596d5a..2d3f963fd6f1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -68,6 +68,7 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 0789e13ece90..1c7f13bb6728 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 0e9504fabe52..3063aa9090f9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -258,6 +257,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -279,8 +279,7 @@ SYM_CODE_END(entry_SYSCALL_64) * %rdi: prev task * %rsi: next task */ -SYM_CODE_START(__switch_to_asm) - UNWIND_HINT_FUNC +SYM_FUNC_START(__switch_to_asm) /* * Save callee-saved registers * This must match the order in inactive_task_frame @@ -321,7 +320,7 @@ SYM_CODE_START(__switch_to_asm) popq %rbp jmp __switch_to -SYM_CODE_END(__switch_to_asm) +SYM_FUNC_END(__switch_to_asm) /* * A newly forked process directly context switches into this address. @@ -512,7 +511,7 @@ SYM_CODE_END(spurious_entries_start) * +----------------------------------------------------+ */ SYM_CODE_START(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -544,9 +543,9 @@ SYM_CODE_START(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -637,6 +636,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1739,7 +1739,7 @@ SYM_CODE_START(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 85be2f506272..84b9449be080 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -56,16 +56,23 @@ struct dyn_arch_ftrace { #ifndef __ASSEMBLY__ +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +extern void set_ftrace_ops_ro(void); +#else +static inline void set_ftrace_ops_ro(void) { } +#endif + #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { /* * Compare the symbol name with the system call name. Skip the - * "__x64_sys", "__ia32_sys" or simple "sys" prefix. + * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix. */ return !strcmp(sym + 3, name + 3) || (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) || - (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)); + (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) || + (!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3)); } #ifndef COMPILE_OFFSETS diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 42a2d0d3984a..0dea9f122bb9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 81b9c63dae1b..e53dda210cd7 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -546,7 +544,7 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -556,7 +554,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -568,7 +566,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -581,7 +579,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), @@ -603,18 +601,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -626,11 +625,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " "please update microcode to version: 0x%x (or later)\n", rev); + return false; } /* @@ -2092,7 +2092,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_debug("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 87b97897a881..460ae7f66818 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -183,7 +183,8 @@ recursion_check: */ if (visit_mask) { if (*visit_mask & (1UL << info->type)) { - printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); + if (task == current) + printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); goto unknown; } *visit_mask |= 1UL << info->type; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 37a0aeaf89e7..b0e641793be4 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -407,7 +407,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) set_vm_flush_reset_perms(trampoline); - set_memory_ro((unsigned long)trampoline, npages); + if (likely(system_state != SYSTEM_BOOTING)) + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -415,6 +416,32 @@ fail: return 0; } +void set_ftrace_ops_ro(void) +{ + struct ftrace_ops *ops; + unsigned long start_offset; + unsigned long end_offset; + unsigned long npages; + unsigned long size; + + do_for_each_ftrace_op(ops, ftrace_ops_list) { + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + continue; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + start_offset = (unsigned long)ftrace_regs_caller; + end_offset = (unsigned long)ftrace_regs_caller_end; + } else { + start_offset = (unsigned long)ftrace_caller; + end_offset = (unsigned long)ftrace_epilogue; + } + size = end_offset - start_offset; + size = size + RET_SIZE + sizeof(void *); + npages = DIV_ROUND_UP(size, PAGE_SIZE); + set_memory_ro((unsigned long)ops->trampoline, npages); + } while_for_each_ftrace_op(ops); +} + static unsigned long calc_trampoline_call_offset(bool save_regs) { unsigned long start_offset; diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index a224b5ab103f..54226110bc7f 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -344,6 +344,9 @@ bad_address: if (IS_ENABLED(CONFIG_X86_32)) goto the_end; + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index e9cc182aa97e..5b0bd8581fe6 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -8,19 +8,21 @@ #include <asm/orc_lookup.h> #define orc_warn(fmt, ...) \ - printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) + +#define orc_warn_current(args...) \ +({ \ + if (state->task == current) \ + orc_warn(args); \ +}) extern int __start_orc_unwind_ip[]; extern int __stop_orc_unwind_ip[]; extern struct orc_entry __start_orc_unwind[]; extern struct orc_entry __stop_orc_unwind[]; -static DEFINE_MUTEX(sort_mutex); -int *cur_orc_ip_table = __start_orc_unwind_ip; -struct orc_entry *cur_orc_table = __start_orc_unwind; - -unsigned int lookup_num_blocks; -bool orc_init; +static bool orc_init __ro_after_init; +static unsigned int lookup_num_blocks __ro_after_init; static inline unsigned long orc_ip(const int *ip) { @@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip) #ifdef CONFIG_MODULES +static DEFINE_MUTEX(sort_mutex); +static int *cur_orc_ip_table = __start_orc_unwind_ip; +static struct orc_entry *cur_orc_table = __start_orc_unwind; + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -381,9 +384,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -445,43 +477,39 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { + orc_warn_current("missing R10 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { + orc_warn_current("missing R13 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { + orc_warn_current("missing RDI value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { + orc_warn_current("missing DX value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: - orc_warn("unknown SP base reg %d for ip %pB\n", + orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->ip); goto err; } @@ -504,44 +532,48 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access registers at %pB\n", + (void *)orig_ip); goto err; } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; case ORC_TYPE_REGS_IRET: if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference iret registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access iret registers at %pB\n", + (void *)orig_ip); goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; break; default: - orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -564,8 +596,8 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%pB\n", - (void *)orig_ip); + orc_warn_current("stack going in the wrong direction? at %pB\n", + (void *)orig_ip); goto err; } @@ -585,6 +617,9 @@ EXPORT_SYMBOL_GPL(unwind_next_frame); void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { + if (!orc_init) + goto done; + memset(state, 0, sizeof(*state)); state->task = task; @@ -651,7 +686,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 750ff0b29404..d057376bd3d3 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, } /* - * AMD SVM AVIC accelerate EOI write and do not trap, - * in-kernel IOAPIC will not be able to receive the EOI. - * In this case, we do lazy update of the pending EOI when - * trying to set IOAPIC irq. + * AMD SVM AVIC accelerate EOI write iff the interrupt is edge + * triggered, in which case the in-kernel IOAPIC will not be able + * to receive the EOI. In this case, we do a lazy update of the + * pending EOI when trying to set IOAPIC irq. */ - if (kvm_apicv_activated(ioapic->kvm)) + if (edge && kvm_apicv_activated(ioapic->kvm)) ioapic_lazy_update_eoi(ioapic, irq); /* diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index cf912b4aaba8..89f7f3aebd31 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -345,7 +345,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f379bacbb26..38f6aeefeb55 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1752,6 +1752,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6; + kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = DB_VECTOR; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index fd78ffbde644..e44f33c82332 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) */ break; default: - BUG_ON(1); + BUG(); break; } diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 87f3f24fef37..51d1a82742fd 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c5835f9cb9ad..d786c7d27ce5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -926,19 +926,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); __reserved_bits; \ }) -static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) -{ - u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - - if (kvm_cpu_cap_has(X86_FEATURE_LA57)) - reserved_bits &= ~X86_CR4_LA57; - - if (kvm_cpu_cap_has(X86_FEATURE_UMIP)) - reserved_bits &= ~X86_CR4_UMIP; - - return reserved_bits; -} - static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) @@ -3385,6 +3372,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -9675,7 +9663,9 @@ int kvm_arch_hardware_setup(void *opaque) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; - cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has if (kvm_has_tsc_control) { /* @@ -9707,7 +9697,8 @@ int kvm_arch_check_processor_compat(void *opaque) WARN_ON(!irqs_disabled()); - if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; return ops->check_processor_compatibility(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3b289c2f75cd..8b5f73f5e207 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -54,6 +54,7 @@ #include <asm/init.h> #include <asm/uv/uv.h> #include <asm/setup.h> +#include <asm/ftrace.h> #include "mm_internal.h" @@ -1291,6 +1292,8 @@ void mark_rodata_ro(void) all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); + set_ftrace_ops_ro(); + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end); set_memory_rw(start, (end-start) >> PAGE_SHIFT); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 59eca6a94ce7..b8c55a2e402d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -43,7 +43,8 @@ struct cpa_data { unsigned long pfn; unsigned int flags; unsigned int force_split : 1, - force_static_prot : 1; + force_static_prot : 1, + force_flush_all : 1; struct page **pages; }; @@ -355,10 +356,10 @@ static void cpa_flush(struct cpa_data *data, int cache) return; } - if (cpa->numpages <= tlb_single_page_flush_ceiling) - on_each_cpu(__cpa_flush_tlb, cpa, 1); - else + if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) flush_tlb_all(); + else + on_each_cpu(__cpa_flush_tlb, cpa, 1); if (!cache) return; @@ -1598,6 +1599,8 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; + ret = __change_page_attr_set_clr(&alias_cpa, 0); if (ret) return ret; @@ -1618,6 +1621,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the * return value. diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 78ba57efd16b..3d411716d7ee 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -123,6 +123,7 @@ #include <linux/ioprio.h> #include <linux/sbitmap.h> #include <linux/delay.h> +#include <linux/backing-dev.h> #include "blk.h" #include "blk-mq.h" @@ -4976,8 +4977,9 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); switch (ioprio_class) { default: - dev_err(bfqq->bfqd->queue->backing_dev_info->dev, - "bfq: bad prio class %d\n", ioprio_class); + pr_err("bdi %s: bfq: bad prio class %d\n", + bdi_dev_name(bfqq->bfqd->queue->backing_dev_info), + ioprio_class); /* fall through */ case IOPRIO_CLASS_NONE: /* diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c5dc833212e1..930212c1a512 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -496,7 +496,7 @@ const char *blkg_dev_name(struct blkcg_gq *blkg) { /* some drivers (floppy) instantiate a queue w/o disk registered */ if (blkg->q->backing_dev_info->dev) - return dev_name(blkg->q->backing_dev_info->dev); + return bdi_dev_name(blkg->q->backing_dev_info); return NULL; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 3ab0c1c704b6..7c1fe605d0d6 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -466,7 +466,7 @@ struct ioc_gq { */ atomic64_t vtime; atomic64_t done_vtime; - atomic64_t abs_vdebt; + u64 abs_vdebt; u64 last_vtime; /* @@ -1142,7 +1142,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 margin_ns = (u64)(ioc->period_us * WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC; - u64 abs_vdebt, vdebt, vshortage, expires, oexpires; + u64 vdebt, vshortage, expires, oexpires; s64 vbudget; u32 hw_inuse; @@ -1152,18 +1152,15 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ - abs_vdebt = atomic64_read(&iocg->abs_vdebt); - vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse); + vdebt = abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); if (vdebt && vbudget > 0) { u64 delta = min_t(u64, vbudget, vdebt); u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse), - abs_vdebt); + iocg->abs_vdebt); atomic64_add(delta, &iocg->vtime); atomic64_add(delta, &iocg->done_vtime); - atomic64_sub(abs_delta, &iocg->abs_vdebt); - if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0)) - atomic64_set(&iocg->abs_vdebt, 0); + iocg->abs_vdebt -= abs_delta; } /* @@ -1219,12 +1216,18 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) u64 expires, oexpires; u32 hw_inuse; + lockdep_assert_held(&iocg->waitq.lock); + /* debt-adjust vtime */ current_hweight(iocg, NULL, &hw_inuse); - vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse); + vtime += abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); - /* clear or maintain depending on the overage */ - if (time_before_eq64(vtime, now->vnow)) { + /* + * Clear or maintain depending on the overage. Non-zero vdebt is what + * guarantees that @iocg is online and future iocg_kick_delay() will + * clear use_delay. Don't leave it on when there's no vdebt. + */ + if (!iocg->abs_vdebt || time_before_eq64(vtime, now->vnow)) { blkcg_clear_delay(blkg); return false; } @@ -1258,9 +1261,12 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer); struct ioc_now now; + unsigned long flags; + spin_lock_irqsave(&iocg->waitq.lock, flags); ioc_now(iocg->ioc, &now); iocg_kick_delay(iocg, &now, 0); + spin_unlock_irqrestore(&iocg->waitq.lock, flags); return HRTIMER_NORESTART; } @@ -1368,14 +1374,13 @@ static void ioc_timer_fn(struct timer_list *timer) * should have woken up in the last period and expire idle iocgs. */ list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg)) + if (!waitqueue_active(&iocg->waitq) && iocg->abs_vdebt && + !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); - if (waitqueue_active(&iocg->waitq) || - atomic64_read(&iocg->abs_vdebt)) { + if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, &now); iocg_kick_delay(iocg, &now, 0); @@ -1718,28 +1723,49 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && + if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); return; } /* - * We're over budget. If @bio has to be issued regardless, - * remember the abs_cost instead of advancing vtime. - * iocg_kick_waitq() will pay off the debt before waking more IOs. + * We activated above but w/o any synchronization. Deactivation is + * synchronized with waitq.lock and we won't get deactivated as long + * as we're waiting or has debt, so we're good if we're activated + * here. In the unlikely case that we aren't, just issue the IO. + */ + spin_lock_irq(&iocg->waitq.lock); + + if (unlikely(list_empty(&iocg->active_list))) { + spin_unlock_irq(&iocg->waitq.lock); + iocg_commit_bio(iocg, bio, cost); + return; + } + + /* + * We're over budget. If @bio has to be issued regardless, remember + * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay + * off the debt before waking more IOs. + * * This way, the debt is continuously paid off each period with the - * actual budget available to the cgroup. If we just wound vtime, - * we would incorrectly use the current hw_inuse for the entire - * amount which, for example, can lead to the cgroup staying - * blocked for a long time even with substantially raised hw_inuse. + * actual budget available to the cgroup. If we just wound vtime, we + * would incorrectly use the current hw_inuse for the entire amount + * which, for example, can lead to the cgroup staying blocked for a + * long time even with substantially raised hw_inuse. + * + * An iocg with vdebt should stay online so that the timer can keep + * deducting its vdebt and [de]activate use_delay mechanism + * accordingly. We don't want to race against the timer trying to + * clear them and leave @iocg inactive w/ dangling use_delay heavily + * penalizing the cgroup and its descendants. */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { - atomic64_add(abs_cost, &iocg->abs_vdebt); + iocg->abs_vdebt += abs_cost; if (iocg_kick_delay(iocg, &now, cost)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); + spin_unlock_irq(&iocg->waitq.lock); return; } @@ -1756,20 +1782,6 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ - spin_lock_irq(&iocg->waitq.lock); - - /* - * We activated above but w/o any synchronization. Deactivation is - * synchronized with waitq.lock and we won't get deactivated as - * long as we're waiting, so we're good if we're activated here. - * In the unlikely case that we are deactivated, just issue the IO. - */ - if (unlikely(list_empty(&iocg->active_list))) { - spin_unlock_irq(&iocg->waitq.lock); - iocg_commit_bio(iocg, bio, cost); - return; - } - init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; @@ -1801,6 +1813,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct ioc_now now; u32 hw_inuse; u64 abs_cost, cost; + unsigned long flags; /* bypass if disabled or for root cgroup */ if (!ioc->enabled || !iocg->level) @@ -1820,15 +1833,28 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, iocg->cursor = bio_end; /* - * Charge if there's enough vtime budget and the existing request - * has cost assigned. Otherwise, account it as debt. See debt - * handling in ioc_rqos_throttle() for details. + * Charge if there's enough vtime budget and the existing request has + * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && - time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) + time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); - else - atomic64_add(abs_cost, &iocg->abs_vdebt); + return; + } + + /* + * Otherwise, account it as debt if @iocg is online, which it should + * be for the vast majority of cases. See debt handling in + * ioc_rqos_throttle() for details. + */ + spin_lock_irqsave(&iocg->waitq.lock, flags); + if (likely(!list_empty(&iocg->active_list))) { + iocg->abs_vdebt += abs_cost; + iocg_kick_delay(iocg, &now, cost); + } else { + iocg_commit_bio(iocg, bio, cost); + } + spin_unlock_irqrestore(&iocg->waitq.lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) @@ -1998,7 +2024,6 @@ static void ioc_pd_init(struct blkg_policy_data *pd) iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); - atomic64_set(&iocg->abs_vdebt, 0); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); iocg->hweight_active = HWEIGHT_WHOLE; diff --git a/crypto/lrw.c b/crypto/lrw.c index 376d7ed3f1f8..3c734b81b3a2 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -287,7 +287,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_skcipher(ctx->child); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -400,12 +400,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/crypto/xts.c b/crypto/xts.c index dbdd8af629e6..6d8cea94b3cf 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -322,7 +322,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_cipher(ctx->tweak); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -434,12 +434,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index b4c0152e92aa..145ec0b6f20b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1994,23 +1994,31 @@ void acpi_ec_set_gpe_wake_mask(u8 action) acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); } -bool acpi_ec_other_gpes_active(void) -{ - return acpi_any_gpe_status_set(first_ec ? first_ec->gpe : U32_MAX); -} - bool acpi_ec_dispatch_gpe(void) { u32 ret; if (!first_ec) + return acpi_any_gpe_status_set(U32_MAX); + + /* + * Report wakeup if the status bit is set for any enabled GPE other + * than the EC one. + */ + if (acpi_any_gpe_status_set(first_ec->gpe)) + return true; + + if (ec_no_wakeup) return false; + /* + * Dispatch the EC GPE in-band, but do not report wakeup in any case + * to allow the caller to process events properly after that. + */ ret = acpi_dispatch_gpe(NULL, first_ec->gpe); - if (ret == ACPI_INTERRUPT_HANDLED) { + if (ret == ACPI_INTERRUPT_HANDLED) pm_pr_dbg("EC GPE dispatched\n"); - return true; - } + return false; } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index e387517d3354..43411a7457cd 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -202,7 +202,6 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); #ifdef CONFIG_PM_SLEEP void acpi_ec_flush_work(void); -bool acpi_ec_other_gpes_active(void); bool acpi_ec_dispatch_gpe(void); #endif diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 4edc8a3ce40f..3850704570c0 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -1013,21 +1013,11 @@ static bool acpi_s2idle_wake(void) if (acpi_check_wakeup_handlers()) return true; - /* - * If the status bit is set for any enabled GPE other than the - * EC one, the wakeup is regarded as a genuine one. - */ - if (acpi_ec_other_gpes_active()) + /* Check non-EC GPE wakeups and dispatch the EC GPE. */ + if (acpi_ec_dispatch_gpe()) return true; /* - * If the EC GPE status bit has not been set, the wakeup is - * regarded as a spurious one. - */ - if (!acpi_ec_dispatch_gpe()) - return false; - - /* * Cancel the wakeup and process all pending events in case * there are any wakeup ones in there. * diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index fe1523664816..8558b629880b 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -645,6 +645,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name) dev->dev.release = amba_device_release; dev->dev.bus = &amba_bustype; dev->dev.dma_mask = &dev->dev.coherent_dma_mask; + dev->dev.dma_parms = &dev->dma_parms; dev->res.name = dev_name(&dev->dev); } diff --git a/drivers/base/component.c b/drivers/base/component.c index e97704104784..dcfbe7251dc4 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -256,7 +256,8 @@ static int try_to_bring_up_master(struct master *master, ret = master->ops->bind(master->dev); if (ret < 0) { devres_release_group(master->dev, NULL); - dev_info(master->dev, "master bind failed: %d\n", ret); + if (ret != -EPROBE_DEFER) + dev_info(master->dev, "master bind failed: %d\n", ret); return ret; } @@ -611,8 +612,9 @@ static int component_bind(struct component *component, struct master *master, devres_release_group(component->dev, NULL); devres_release_group(master->dev, NULL); - dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", - dev_name(component->dev), component->ops, ret); + if (ret != -EPROBE_DEFER) + dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", + dev_name(component->dev), component->ops, ret); } return ret; diff --git a/drivers/base/core.c b/drivers/base/core.c index 139cdf7e7327..073045cb214e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2370,6 +2370,11 @@ u32 fw_devlink_get_flags(void) return fw_devlink_flags; } +static bool fw_devlink_is_permissive(void) +{ + return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY; +} + /** * device_add - add device to device hierarchy. * @dev: device. @@ -2524,7 +2529,7 @@ int device_add(struct device *dev) if (fw_devlink_flags && is_fwnode_dev && fwnode_has_op(dev->fwnode, add_links)) { fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev); - if (fw_ret == -ENODEV) + if (fw_ret == -ENODEV && !fw_devlink_is_permissive()) device_link_wait_for_mandatory_supplier(dev); else if (fw_ret) device_link_wait_for_optional_supplier(dev); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 06ec0e851fa1..94037be7f5d7 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -224,17 +224,9 @@ static int deferred_devs_show(struct seq_file *s, void *data) } DEFINE_SHOW_ATTRIBUTE(deferred_devs); -#ifdef CONFIG_MODULES -/* - * In the case of modules, set the default probe timeout to - * 30 seconds to give userland some time to load needed modules - */ -int driver_deferred_probe_timeout = 30; -#else -/* In the case of !modules, no probe timeout needed */ -int driver_deferred_probe_timeout = -1; -#endif +int driver_deferred_probe_timeout; EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); +static DECLARE_WAIT_QUEUE_HEAD(probe_timeout_waitqueue); static int __init deferred_probe_timeout_setup(char *str) { @@ -266,8 +258,8 @@ int driver_deferred_probe_check_state(struct device *dev) return -ENODEV; } - if (!driver_deferred_probe_timeout) { - dev_WARN(dev, "deferred probe timeout, ignoring dependency"); + if (!driver_deferred_probe_timeout && initcalls_done) { + dev_warn(dev, "deferred probe timeout, ignoring dependency"); return -ETIMEDOUT; } @@ -284,6 +276,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work) list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe) dev_info(private->device, "deferred probe pending"); + wake_up(&probe_timeout_waitqueue); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); @@ -658,6 +651,9 @@ int driver_probe_done(void) */ void wait_for_device_probe(void) { + /* wait for probe timeout */ + wait_event(probe_timeout_waitqueue, !driver_deferred_probe_timeout); + /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 5255550b7c34..b27d0f6c18c9 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -380,6 +380,8 @@ struct platform_object { */ static void setup_pdev_dma_masks(struct platform_device *pdev) { + pdev->dev.dma_parms = &pdev->dma_parms; + if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); if (!pdev->dev.dma_mask) { diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c index b38359c480ea..eb2ab058a01d 100644 --- a/drivers/bus/mhi/core/init.c +++ b/drivers/bus/mhi/core/init.c @@ -812,10 +812,9 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl, if (!mhi_cntrl) return -EINVAL; - if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put) - return -EINVAL; - - if (!mhi_cntrl->status_cb || !mhi_cntrl->link_status) + if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put || + !mhi_cntrl->status_cb || !mhi_cntrl->read_reg || + !mhi_cntrl->write_reg) return -EINVAL; ret = parse_config(mhi_cntrl, config); diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 5deadfaa053a..095d95bc0e37 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -11,9 +11,6 @@ extern struct bus_type mhi_bus_type; -/* MHI MMIO register mapping */ -#define PCI_INVALID_READ(val) (val == U32_MAX) - #define MHIREGLEN (0x0) #define MHIREGLEN_MHIREGLEN_MASK (0xFFFFFFFF) #define MHIREGLEN_MHIREGLEN_SHIFT (0) diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index eb4256b81406..97e06cc586e4 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -18,16 +18,7 @@ int __must_check mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 *out) { - u32 tmp = readl(base + offset); - - /* If there is any unexpected value, query the link status */ - if (PCI_INVALID_READ(tmp) && - mhi_cntrl->link_status(mhi_cntrl)) - return -EIO; - - *out = tmp; - - return 0; + return mhi_cntrl->read_reg(mhi_cntrl, base + offset, out); } int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, @@ -49,7 +40,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 val) { - writel(val, base + offset); + mhi_cntrl->write_reg(mhi_cntrl, base + offset, val); } void mhi_write_reg_field(struct mhi_controller *mhi_cntrl, void __iomem *base, @@ -294,7 +285,7 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) !(mhi_chan->ee_mask & BIT(mhi_cntrl->ee))) continue; mhi_dev = mhi_alloc_device(mhi_cntrl); - if (!mhi_dev) + if (IS_ERR(mhi_dev)) return; mhi_dev->dev_type = MHI_DEVICE_XFER; @@ -336,7 +327,8 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) /* Channel name is same for both UL and DL */ mhi_dev->chan_name = mhi_chan->name; - dev_set_name(&mhi_dev->dev, "%04x_%s", mhi_chan->chan, + dev_set_name(&mhi_dev->dev, "%s_%s", + dev_name(mhi_cntrl->cntrl_dev), mhi_dev->chan_name); /* Init wakeup source if available */ diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c index 52690cb5c89c..dc83d65f7784 100644 --- a/drivers/bus/mhi/core/pm.c +++ b/drivers/bus/mhi/core/pm.c @@ -902,7 +902,11 @@ int mhi_sync_power_up(struct mhi_controller *mhi_cntrl) MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state), msecs_to_jiffies(mhi_cntrl->timeout_ms)); - return (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -EIO; + ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT; + if (ret) + mhi_power_down(mhi_cntrl, false); + + return ret; } EXPORT_SYMBOL(mhi_sync_power_up); diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 31f9f0e369b9..55b031d2c989 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -16,7 +16,7 @@ int efi_tpm_final_log_size; EXPORT_SYMBOL(efi_tpm_final_log_size); -static int tpm2_calc_event_log_size(void *data, int count, void *size_info) +static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info) { struct tcg_pcr_event2_head *header; int event_size, size = 0; diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 5638b4e5355f..4269ea9a817e 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -531,7 +531,7 @@ static int pca953x_gpio_set_config(struct gpio_chip *gc, unsigned int offset, { struct pca953x_chip *chip = gpiochip_get_data(gc); - switch (config) { + switch (pinconf_to_config_param(config)) { case PIN_CONFIG_BIAS_PULL_UP: case PIN_CONFIG_BIAS_PULL_DOWN: return pca953x_gpio_set_pull_up_down(chip, offset, config); diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index acb99eff9939..86568154cdb3 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -368,6 +368,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d) struct tegra_gpio_info *tgi = bank->tgi; unsigned int gpio = d->hwirq; + tegra_gpio_irq_mask(d); gpiochip_unlock_as_irq(&tgi->gc, gpio); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 40f2d7f69be2..182136d98b97 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1158,8 +1158,19 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, struct gpioline_info *info) { struct gpio_chip *gc = desc->gdev->chip; + bool ok_for_pinctrl; unsigned long flags; + /* + * This function takes a mutex so we must check this before taking + * the spinlock. + * + * FIXME: find a non-racy way to retrieve this information. Maybe a + * lock common to both frameworks? + */ + ok_for_pinctrl = + pinctrl_gpio_can_use_line(gc->base + info->line_offset); + spin_lock_irqsave(&gpio_lock, flags); if (desc->name) { @@ -1186,7 +1197,7 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, test_bit(FLAG_USED_AS_IRQ, &desc->flags) || test_bit(FLAG_EXPORT, &desc->flags) || test_bit(FLAG_SYSFS, &desc->flags) || - !pinctrl_gpio_can_use_line(gc->base + info->line_offset)) + !ok_for_pinctrl) info->flags |= GPIOLINE_FLAG_KERNEL; if (test_bit(FLAG_IS_OUT, &desc->flags)) info->flags |= GPIOLINE_FLAG_IS_OUT; @@ -1227,6 +1238,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) void __user *ip = (void __user *)arg; struct gpio_desc *desc; __u32 offset; + int hwgpio; /* We fail any subsequent ioctl():s when the chip is gone */ if (!gc) @@ -1259,13 +1271,19 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (IS_ERR(desc)) return PTR_ERR(desc); + hwgpio = gpio_chip_hwgpio(desc); + + if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL && + test_bit(hwgpio, priv->watched_lines)) + return -EBUSY; + gpio_desc_to_lineinfo(desc, &lineinfo); if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) return -EFAULT; if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL) - set_bit(gpio_chip_hwgpio(desc), priv->watched_lines); + set_bit(hwgpio, priv->watched_lines); return 0; } else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) { @@ -1280,7 +1298,12 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (IS_ERR(desc)) return PTR_ERR(desc); - clear_bit(gpio_chip_hwgpio(desc), priv->watched_lines); + hwgpio = gpio_chip_hwgpio(desc); + + if (!test_bit(hwgpio, priv->watched_lines)) + return -EBUSY; + + clear_bit(hwgpio, priv->watched_lines); return 0; } return -EINVAL; @@ -5289,8 +5312,9 @@ static int __init gpiolib_dev_init(void) gpiolib_initialized = true; gpiochip_setup_devs(); - if (IS_ENABLED(CONFIG_OF_DYNAMIC)) - WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier)); +#if IS_ENABLED(CONFIG_OF_DYNAMIC) && IS_ENABLED(CONFIG_OF_GPIO) + WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier)); +#endif /* CONFIG_OF_DYNAMIC && CONFIG_OF_GPIO */ return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 2992a49ad4a5..8ac1581a6b53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -945,6 +945,7 @@ struct amdgpu_device { /* s3/s4 mask */ bool in_suspend; + bool in_hibernate; /* record last mm index being written through WREG32*/ unsigned long last_mm_index; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 9dff792c9290..6a5b91d23fd9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1343,7 +1343,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( } /* Free the BO*/ - amdgpu_bo_unref(&mem->bo); + drm_gem_object_put_unlocked(&mem->bo->tbo.base); mutex_destroy(&mem->lock); kfree(mem); @@ -1688,7 +1688,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd, | KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE | KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE; - (*mem)->bo = amdgpu_bo_ref(bo); + drm_gem_object_get(&bo->tbo.base); + (*mem)->bo = bo; (*mem)->va = va; (*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f84f9e35a73b..affde2de2a0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3372,15 +3372,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) } } - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - - amdgpu_amdkfd_suspend(adev, !fbcon); - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); + amdgpu_amdkfd_suspend(adev, !fbcon); + /* evict vram memory */ amdgpu_bo_evict_vram(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 466bfe541e45..a735d79a717b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1181,7 +1181,9 @@ static int amdgpu_pmops_freeze(struct device *dev) struct amdgpu_device *adev = drm_dev->dev_private; int r; + adev->in_hibernate = true; r = amdgpu_device_suspend(drm_dev, true); + adev->in_hibernate = false; if (r) return r; return amdgpu_asic_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 9ae7b61f696a..25ddb482466a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -133,8 +133,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev, u32 cpp; u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS | - AMDGPU_GEM_CREATE_VRAM_CLEARED | - AMDGPU_GEM_CREATE_CPU_GTT_USWC; + AMDGPU_GEM_CREATE_VRAM_CLEARED; info = drm_get_format_info(adev->ddev, mode_cmd); cpp = info->cpp[0]; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f92c158d89a1..0e0daf0021b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4273,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === CGCG /CGLS for GFX 3D Only === */ gfx_v10_0_update_3d_clock_gating(adev, enable); /* === MGCG + MGLS === */ - /* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */ + gfx_v10_0_update_medium_grain_clock_gating(adev, enable); } if (adev->cg_flags & @@ -4353,11 +4353,7 @@ static int gfx_v10_0_set_powergating_state(void *handle, switch (adev->asic_type) { case CHIP_NAVI10: case CHIP_NAVI14: - if (!enable) { - amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } else - amdgpu_gfx_off_ctrl(adev, true); + amdgpu_gfx_off_ctrl(adev, enable); break; default: break; @@ -4918,6 +4914,19 @@ static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, ref, mask); } +static void gfx_v10_0_ring_soft_recovery(struct amdgpu_ring *ring, + unsigned vmid) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t value = 0; + + value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03); + value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01); + value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1); + value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid); + WREG32_SOC15(GC, 0, mmSQ_CMD, value); +} + static void gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, uint32_t me, uint32_t pipe, @@ -5309,6 +5318,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { .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, + .soft_recovery = gfx_v10_0_ring_soft_recovery, }; static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 0c390485bc10..d2d9dce68c2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1236,6 +1236,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 }, /* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */ { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, + /* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */ + { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, { 0, 0, 0, 0, 0 }, }; @@ -5025,10 +5027,9 @@ static int gfx_v9_0_set_powergating_state(void *handle, switch (adev->asic_type) { case CHIP_RAVEN: case CHIP_RENOIR: - if (!enable) { + if (!enable) amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } + if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) { gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true); gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true); @@ -5052,12 +5053,7 @@ static int gfx_v9_0_set_powergating_state(void *handle, amdgpu_gfx_off_ctrl(adev, true); break; case CHIP_VEGA12: - if (!enable) { - amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } else { - amdgpu_gfx_off_ctrl(adev, true); - } + amdgpu_gfx_off_ctrl(adev, enable); break; default: break; 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 94c29b74c086..28e651b173ab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -441,7 +441,7 @@ static void dm_vupdate_high_irq(void *interrupt_params) /** * dm_crtc_high_irq() - Handles CRTC interrupt - * @interrupt_params: ignored + * @interrupt_params: used for determining the CRTC instance * * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK * event handler. @@ -455,70 +455,6 @@ static void dm_crtc_high_irq(void *interrupt_params) unsigned long flags; acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); - - if (acrtc) { - acrtc_state = to_dm_crtc_state(acrtc->base.state); - - DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n", - acrtc->crtc_id, - amdgpu_dm_vrr_active(acrtc_state)); - - /* Core vblank handling at start of front-porch is only possible - * in non-vrr mode, as only there vblank timestamping will give - * valid results while done in front-porch. Otherwise defer it - * to dm_vupdate_high_irq after end of front-porch. - */ - if (!amdgpu_dm_vrr_active(acrtc_state)) - drm_crtc_handle_vblank(&acrtc->base); - - /* Following stuff must happen at start of vblank, for crc - * computation and below-the-range btr support in vrr mode. - */ - amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); - - if (acrtc_state->stream && adev->family >= AMDGPU_FAMILY_AI && - acrtc_state->vrr_params.supported && - acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { - spin_lock_irqsave(&adev->ddev->event_lock, flags); - mod_freesync_handle_v_update( - adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); - - dc_stream_adjust_vmin_vmax( - adev->dm.dc, - acrtc_state->stream, - &acrtc_state->vrr_params.adjust); - spin_unlock_irqrestore(&adev->ddev->event_lock, flags); - } - } -} - -#if defined(CONFIG_DRM_AMD_DC_DCN) -/** - * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs - * @interrupt params - interrupt parameters - * - * Notify DRM's vblank event handler at VSTARTUP - * - * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which: - * * We are close enough to VUPDATE - the point of no return for hw - * * We are in the fixed portion of variable front porch when vrr is enabled - * * We are before VUPDATE, where double-buffered vrr registers are swapped - * - * It is therefore the correct place to signal vblank, send user flip events, - * and update VRR. - */ -static void dm_dcn_crtc_high_irq(void *interrupt_params) -{ - struct common_irq_params *irq_params = interrupt_params; - struct amdgpu_device *adev = irq_params->adev; - struct amdgpu_crtc *acrtc; - struct dm_crtc_state *acrtc_state; - unsigned long flags; - - acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); - if (!acrtc) return; @@ -528,22 +464,35 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) amdgpu_dm_vrr_active(acrtc_state), acrtc_state->active_planes); + /** + * Core vblank handling at start of front-porch is only possible + * in non-vrr mode, as only there vblank timestamping will give + * valid results while done in front-porch. Otherwise defer it + * to dm_vupdate_high_irq after end of front-porch. + */ + if (!amdgpu_dm_vrr_active(acrtc_state)) + drm_crtc_handle_vblank(&acrtc->base); + + /** + * Following stuff must happen at start of vblank, for crc + * computation and below-the-range btr support in vrr mode. + */ amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); - drm_crtc_handle_vblank(&acrtc->base); + + /* BTR updates need to happen before VUPDATE on Vega and above. */ + if (adev->family < AMDGPU_FAMILY_AI) + return; spin_lock_irqsave(&adev->ddev->event_lock, flags); - if (acrtc_state->vrr_params.supported && + if (acrtc_state->stream && acrtc_state->vrr_params.supported && acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { - mod_freesync_handle_v_update( - adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); + mod_freesync_handle_v_update(adev->dm.freesync_module, + acrtc_state->stream, + &acrtc_state->vrr_params); - dc_stream_adjust_vmin_vmax( - adev->dm.dc, - acrtc_state->stream, - &acrtc_state->vrr_params.adjust); + dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream, + &acrtc_state->vrr_params.adjust); } /* @@ -556,7 +505,8 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) * avoid race conditions between flip programming and completion, * which could cause too early flip completion events. */ - if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + if (adev->family >= AMDGPU_FAMILY_RV && + acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && acrtc_state->active_planes == 0) { if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); @@ -568,7 +518,6 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) spin_unlock_irqrestore(&adev->ddev->event_lock, flags); } -#endif static int dm_set_clockgating_state(void *handle, enum amd_clockgating_state state) @@ -2008,17 +1957,22 @@ void amdgpu_dm_update_connector_after_detect( dc_sink_retain(aconnector->dc_sink); if (sink->dc_edid.length == 0) { aconnector->edid = NULL; - drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux); + if (aconnector->dc_link->aux_mode) { + drm_dp_cec_unset_edid( + &aconnector->dm_dp_aux.aux); + } } else { aconnector->edid = - (struct edid *) sink->dc_edid.raw_edid; - + (struct edid *)sink->dc_edid.raw_edid; drm_connector_update_edid_property(connector, - aconnector->edid); - drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, - aconnector->edid); + aconnector->edid); + + if (aconnector->dc_link->aux_mode) + drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, + aconnector->edid); } + amdgpu_dm_update_freesync_caps(connector, aconnector->edid); update_connector_ext_caps(aconnector); } else { @@ -2440,8 +2394,36 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) c_irq_params->adev = adev; c_irq_params->irq_src = int_params.irq_source; + amdgpu_dm_irq_register_interrupt( + adev, &int_params, dm_crtc_high_irq, c_irq_params); + } + + /* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to + * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx + * to trigger at end of each vblank, regardless of state of the lock, + * matching DCE behaviour. + */ + for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT; + i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1; + i++) { + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq); + + if (r) { + DRM_ERROR("Failed to add vupdate irq id!\n"); + return r; + } + + int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT; + int_params.irq_source = + dc_interrupt_to_irq_source(dc, i, 0); + + c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1]; + + c_irq_params->adev = adev; + c_irq_params->irq_src = int_params.irq_source; + amdgpu_dm_irq_register_interrupt(adev, &int_params, - dm_dcn_crtc_high_irq, c_irq_params); + dm_vupdate_high_irq, c_irq_params); } /* Use GRPH_PFLIP interrupt */ @@ -4448,10 +4430,6 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable) struct amdgpu_device *adev = crtc->dev->dev_private; int rc; - /* Do not set vupdate for DCN hardware */ - if (adev->family > AMDGPU_FAMILY_AI) - return 0; - irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst; rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; @@ -7877,6 +7855,7 @@ static int dm_update_plane_state(struct dc *dc, struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state; struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state; + struct amdgpu_crtc *new_acrtc; bool needs_reset; int ret = 0; @@ -7886,9 +7865,30 @@ static int dm_update_plane_state(struct dc *dc, dm_new_plane_state = to_dm_plane_state(new_plane_state); dm_old_plane_state = to_dm_plane_state(old_plane_state); - /*TODO Implement atomic check for cursor plane */ - if (plane->type == DRM_PLANE_TYPE_CURSOR) + /*TODO Implement better atomic check for cursor plane */ + if (plane->type == DRM_PLANE_TYPE_CURSOR) { + if (!enable || !new_plane_crtc || + drm_atomic_plane_disabling(plane->state, new_plane_state)) + return 0; + + new_acrtc = to_amdgpu_crtc(new_plane_crtc); + + if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) || + (new_plane_state->crtc_h > new_acrtc->max_cursor_height)) { + DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n", + new_plane_state->crtc_w, new_plane_state->crtc_h); + return -EINVAL; + } + + if (new_plane_state->crtc_x <= -new_acrtc->max_cursor_width || + new_plane_state->crtc_y <= -new_acrtc->max_cursor_height) { + DRM_DEBUG_ATOMIC("Bad cursor position %d, %d\n", + new_plane_state->crtc_x, new_plane_state->crtc_y); + return -EINVAL; + } + return 0; + } needs_reset = should_reset_plane(state, plane, old_plane_state, new_plane_state); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 78e1c11d4ae5..dcf84a61de37 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -398,15 +398,15 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) struct mod_hdcp_display *display = &hdcp_work[link_index].display; struct mod_hdcp_link *link = &hdcp_work[link_index].link; - memset(display, 0, sizeof(*display)); - memset(link, 0, sizeof(*link)); - - display->index = aconnector->base.index; - if (config->dpms_off) { hdcp_remove_display(hdcp_work, link_index, aconnector); return; } + + memset(display, 0, sizeof(*display)); + memset(link, 0, sizeof(*link)); + + display->index = aconnector->base.index; display->state = MOD_HDCP_DISPLAY_ACTIVE; if (aconnector->dc_sink != NULL) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 8489f1e56892..47431ca6986d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -834,11 +834,10 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) { int i; - int count = 0; - struct pipe_ctx *pipe; PERF_TRACE(); for (i = 0; i < MAX_PIPES; i++) { - pipe = &context->res_ctx.pipe_ctx[i]; + int count = 0; + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; if (!pipe->plane_state) continue; 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 c3535bd3965b..e4348e3b6389 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3068,25 +3068,32 @@ validate_out: return out; } - -bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, - bool fast_validate) +/* + * This must be noinline to ensure anything that deals with FP registers + * is contained within this call; previously our compiling with hard-float + * would result in fp instructions being emitted outside of the boundaries + * of the DC_FP_START/END macros, which makes sense as the compiler has no + * idea about what is wrapped and what is not + * + * This is largely just a workaround to avoid breakage introduced with 5.6, + * ideally all fp-using code should be moved into its own file, only that + * should be compiled with hard-float, and all code exported from there + * should be strictly wrapped with DC_FP_START/END + */ +static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, bool fast_validate) { bool voltage_supported = false; bool full_pstate_supported = false; bool dummy_pstate_supported = false; double p_state_latency_us; - DC_FP_START(); p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = dc->debug.disable_dram_clock_change_vactive_support; if (fast_validate) { - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true); - - DC_FP_END(); - return voltage_supported; + return dcn20_validate_bandwidth_internal(dc, context, true); } // Best case, we support full UCLK switch latency @@ -3115,7 +3122,15 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, restore_dml_state: context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; + return voltage_supported; +} +bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, + bool fast_validate) +{ + bool voltage_supported = false; + DC_FP_START(); + voltage_supported = dcn20_validate_bandwidth_fp(dc, context, fast_validate); DC_FP_END(); return voltage_supported; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index a38baa73d484..b8ec08e3b7a3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -1200,7 +1200,7 @@ static void dml_rq_dlg_get_dlg_params( min_hratio_fact_l = 1.0; min_hratio_fact_c = 1.0; - if (htaps_l <= 1) + if (hratio_l <= 1) min_hratio_fact_l = 2.0; else if (htaps_l <= 6) { if ((hratio_l * 2.0) > 4.0) @@ -1216,7 +1216,7 @@ static void dml_rq_dlg_get_dlg_params( hscale_pixel_rate_l = min_hratio_fact_l * dppclk_freq_in_mhz; - if (htaps_c <= 1) + if (hratio_c <= 1) min_hratio_fact_c = 2.0; else if (htaps_c <= 6) { if ((hratio_c * 2.0) > 4.0) @@ -1522,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params( disp_dlg_regs->refcyc_per_vm_group_vblank = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; disp_dlg_regs->refcyc_per_vm_group_flip = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; + disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); + disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); // Clamp to max for now if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23)) diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index c34eba19860a..6d7bca562eec 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -108,7 +108,7 @@ #define ASSERT(expr) ASSERT_CRITICAL(expr) #else -#define ASSERT(expr) WARN_ON(!(expr)) +#define ASSERT(expr) WARN_ON_ONCE(!(expr)) #endif #define BREAK_TO_DEBUGGER() ASSERT(0) diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index e4e5a53b2b4e..8e2acb4df860 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -319,12 +319,12 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr *hwmgr, if (*level & profile_mode_mask) { hwmgr->saved_dpm_level = hwmgr->dpm_level; hwmgr->en_umd_pstate = true; - amdgpu_device_ip_set_clockgating_state(hwmgr->adev, - AMD_IP_BLOCK_TYPE_GFX, - AMD_CG_STATE_UNGATE); amdgpu_device_ip_set_powergating_state(hwmgr->adev, AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_UNGATE); + amdgpu_device_ip_set_clockgating_state(hwmgr->adev, + AMD_IP_BLOCK_TYPE_GFX, + AMD_CG_STATE_UNGATE); } } else { /* exit umd pstate, restore level, enable gfx cg*/ diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index e8b27fab6aa1..e77046931e4c 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -1476,7 +1476,7 @@ static int smu_disable_dpm(struct smu_context *smu) bool use_baco = !smu->is_apu && ((adev->in_gpu_reset && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || - (adev->in_runpm && amdgpu_asic_supports_baco(adev))); + ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev))); ret = smu_get_smc_version(smu, NULL, &smu_version); if (ret) { @@ -1744,12 +1744,12 @@ static int smu_enable_umd_pstate(void *handle, if (*level & profile_mode_mask) { smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level; smu_dpm_ctx->enable_umd_pstate = true; - amdgpu_device_ip_set_clockgating_state(smu->adev, - AMD_IP_BLOCK_TYPE_GFX, - AMD_CG_STATE_UNGATE); amdgpu_device_ip_set_powergating_state(smu->adev, AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_UNGATE); + amdgpu_device_ip_set_clockgating_state(smu->adev, + AMD_IP_BLOCK_TYPE_GFX, + AMD_CG_STATE_UNGATE); } } else { /* exit umd pstate, restore level, enable gfx cg*/ diff --git a/drivers/gpu/drm/drm_hdcp.c b/drivers/gpu/drm/drm_hdcp.c index 7f386adcf872..910108ccaae1 100644 --- a/drivers/gpu/drm/drm_hdcp.c +++ b/drivers/gpu/drm/drm_hdcp.c @@ -241,8 +241,12 @@ static int drm_hdcp_request_srm(struct drm_device *drm_dev, ret = request_firmware_direct(&fw, (const char *)fw_name, drm_dev->dev); - if (ret < 0) + if (ret < 0) { + *revoked_ksv_cnt = 0; + *revoked_ksv_list = NULL; + ret = 0; goto exit; + } if (fw->size && fw->data) ret = drm_hdcp_srm_update(fw->data, fw->size, revoked_ksv_list, @@ -287,6 +291,8 @@ int drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs, ret = drm_hdcp_request_srm(drm_dev, &revoked_ksv_list, &revoked_ksv_cnt); + if (ret) + return ret; /* revoked_ksv_cnt will be zero when above function failed */ for (i = 0; i < revoked_ksv_cnt; i++) diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 2e5d835a9eaa..c125ca9ab9b3 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -485,8 +485,7 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, if (!ret) goto err_llb; else if (ret > 1) { - DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); - + DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); } fbc->threshold = ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 0cc40e77bbd2..4f96c8788a2e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -368,7 +368,6 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_vma *vma; - GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); if (!atomic_read(&obj->bind_count)) return; @@ -400,12 +399,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma) { - struct drm_i915_gem_object *obj = vma->obj; - - assert_object_held(obj); - /* Bump the LRU to try and avoid premature eviction whilst flipping */ - i915_gem_object_bump_inactive_ggtt(obj); + i915_gem_object_bump_inactive_ggtt(vma->obj); i915_vma_unpin(vma); } diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 07cb83a0d017..ca0d4f4f3615 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -69,7 +69,13 @@ struct intel_context { #define CONTEXT_NOPREEMPT 7 u32 *lrc_reg_state; - u64 lrc_desc; + union { + struct { + u32 lrca; + u32 ccid; + }; + u64 desc; + } lrc; u32 tag; /* cookie passed to HW to track this context on submission */ /* Time on GPU as tracked by the hw. */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index b469de0dd9b6..a1aa0d3e8be1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -333,13 +333,4 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) return intel_engine_has_preemption(engine); } -static inline bool -intel_engine_has_timeslices(const struct intel_engine_cs *engine) -{ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) - return false; - - return intel_engine_has_semaphores(engine); -} - #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 3aa8a652c16d..883a9b7fe88d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1295,6 +1295,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7)) drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID)); + if (HAS_EXECLISTS(dev_priv)) { + drm_printf(m, "\tEL_STAT_HI: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_HI)); + drm_printf(m, "\tEL_STAT_LO: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_LO)); + } drm_printf(m, "\tRING_START: 0x%08x\n", ENGINE_READ(engine, RING_START)); drm_printf(m, "\tRING_HEAD: 0x%08x\n", diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 80cdde712842..0be674ae1cf6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -157,6 +157,20 @@ struct intel_engine_execlists { struct i915_priolist default_priolist; /** + * @ccid: identifier for contexts submitted to this engine + */ + u32 ccid; + + /** + * @yield: CCID at the time of the last semaphore-wait interrupt. + * + * Instead of leaving a semaphore busy-spinning on an engine, we would + * like to switch to another ready context, i.e. yielding the semaphore + * timeslice. + */ + u32 yield; + + /** * @error_interrupt: CS Master EIR * * The CS generates an interrupt when it detects an error. We capture @@ -295,8 +309,7 @@ struct intel_engine_cs { u32 context_size; u32 mmio_base; - unsigned int context_tag; -#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS) + unsigned long context_tag; struct rb_node uabi_node; @@ -483,10 +496,11 @@ struct intel_engine_cs { #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_HAS_RELATIVE_MMIO BIT(6) -#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7) +#define I915_ENGINE_HAS_TIMESLICES BIT(4) +#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5) +#define I915_ENGINE_IS_VIRTUAL BIT(6) +#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8) unsigned int flags; /* @@ -585,6 +599,15 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine) } static inline bool +intel_engine_has_timeslices(const struct intel_engine_cs *engine) +{ + if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + return false; + + return engine->flags & I915_ENGINE_HAS_TIMESLICES; +} + +static inline bool intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine) { return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index f0e7fd95165a..0cc7dd54f4f9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir) } } + if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) { + WRITE_ONCE(engine->execlists.yield, + ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI)); + ENGINE_TRACE(engine, "semaphore yield: %08x\n", + engine->execlists.yield); + if (del_timer(&engine->execlists.timer)) + tasklet = true; + } + if (iir & GT_CONTEXT_SWITCH_INTERRUPT) tasklet = true; @@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; struct intel_uncore *uncore = gt->uncore; const u32 dmask = irqs << 16 | irqs; const u32 smask = irqs << 16; @@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; const u32 gt_interrupts[] = { irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT, irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 683014e7bc51..2dfaddb8811e 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -456,10 +456,10 @@ assert_priority_queue(const struct i915_request *prev, * engine info, SW context ID and SW counter need to form a unique number * (Context ID) per lrc. */ -static u64 +static u32 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) { - u64 desc; + u32 desc; desc = INTEL_LEGACY_32B_CONTEXT; if (i915_vm_is_4lvl(ce->vm)) @@ -470,21 +470,7 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) if (IS_GEN(engine->i915, 8)) desc |= GEN8_CTX_L3LLC_COHERENT; - desc |= i915_ggtt_offset(ce->state); /* bits 12-31 */ - /* - * The following 32bits are copied into the OA reports (dword 2). - * Consider updating oa_get_render_ctx_id in i915_perf.c when changing - * anything below. - */ - if (INTEL_GEN(engine->i915) >= 11) { - desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT; - /* bits 48-53 */ - - desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT; - /* bits 61-63 */ - } - - return desc; + return i915_ggtt_offset(ce->state) | desc; } static inline unsigned int dword_in_page(void *addr) @@ -1192,7 +1178,7 @@ static void reset_active(struct i915_request *rq, __execlists_update_reg_state(ce, engine, head); /* We've switched away, so this should be a no-op, but intent matters */ - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static u32 intel_context_get_runtime(const struct intel_context *ce) @@ -1251,18 +1237,23 @@ __execlists_schedule_in(struct i915_request *rq) if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) execlists_check_context(ce, engine); - ce->lrc_desc &= ~GENMASK_ULL(47, 37); if (ce->tag) { /* Use a fixed tag for OA and friends */ - ce->lrc_desc |= (u64)ce->tag << 32; + GEM_BUG_ON(ce->tag <= BITS_PER_LONG); + ce->lrc.ccid = ce->tag; } else { /* We don't need a strict matching tag, just different values */ - ce->lrc_desc |= - (u64)(++engine->context_tag % NUM_CONTEXT_TAG) << - GEN11_SW_CTX_ID_SHIFT; - BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID); + unsigned int tag = ffs(engine->context_tag); + + GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG); + clear_bit(tag - 1, &engine->context_tag); + ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32); + + BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID); } + ce->lrc.ccid |= engine->execlists.ccid; + __intel_gt_pm_get(engine->gt); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN); intel_engine_context_in(engine); @@ -1302,7 +1293,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce) static inline void __execlists_schedule_out(struct i915_request *rq, - struct intel_engine_cs * const engine) + struct intel_engine_cs * const engine, + unsigned int ccid) { struct intel_context * const ce = rq->context; @@ -1320,6 +1312,14 @@ __execlists_schedule_out(struct i915_request *rq, i915_request_completed(rq)) intel_engine_add_retire(engine, ce->timeline); + ccid >>= GEN11_SW_CTX_ID_SHIFT - 32; + ccid &= GEN12_MAX_CONTEXT_HW_ID; + if (ccid < BITS_PER_LONG) { + GEM_BUG_ON(ccid == 0); + GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag)); + set_bit(ccid - 1, &engine->context_tag); + } + intel_context_update_runtime(ce); intel_engine_context_out(engine); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT); @@ -1345,15 +1345,17 @@ execlists_schedule_out(struct i915_request *rq) { struct intel_context * const ce = rq->context; struct intel_engine_cs *cur, *old; + u32 ccid; trace_i915_request_out(rq); + ccid = rq->context->lrc.ccid; old = READ_ONCE(ce->inflight); do cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL; while (!try_cmpxchg(&ce->inflight, &old, cur)); if (!cur) - __execlists_schedule_out(rq, old); + __execlists_schedule_out(rq, old, ccid); i915_request_put(rq); } @@ -1361,7 +1363,7 @@ execlists_schedule_out(struct i915_request *rq) static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; u32 tail, prev; /* @@ -1400,7 +1402,7 @@ static u64 execlists_update_context(struct i915_request *rq) */ wmb(); - ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; + ce->lrc.desc &= ~CTX_DESC_FORCE_RESTORE; return desc; } @@ -1719,6 +1721,9 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Leave semaphores spinning on the other engines */ if (w->engine != rq->engine) continue; @@ -1754,7 +1759,8 @@ static void defer_active(struct intel_engine_cs *engine) } static bool -need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) +need_timeslice(const struct intel_engine_cs *engine, + const struct i915_request *rq) { int hint; @@ -1768,6 +1774,32 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) return hint >= effective_prio(rq); } +static bool +timeslice_yield(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + /* + * Once bitten, forever smitten! + * + * If the active context ever busy-waited on a semaphore, + * it will be treated as a hog until the end of its timeslice (i.e. + * until it is scheduled out and replaced by a new submission, + * possibly even its own lite-restore). The HW only sends an interrupt + * on the first miss, and we do know if that semaphore has been + * signaled, or even if it is now stuck on another semaphore. Play + * safe, yield if it might be stuck -- it will be given a fresh + * timeslice in the near future. + */ + return rq->context->lrc.ccid == READ_ONCE(el->yield); +} + +static bool +timeslice_expired(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + return timer_expired(&el->timer) || timeslice_yield(el, rq); +} + static int switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq) { @@ -1783,8 +1815,7 @@ timeslice(const struct intel_engine_cs *engine) return READ_ONCE(engine->props.timeslice_duration_ms); } -static unsigned long -active_timeslice(const struct intel_engine_cs *engine) +static unsigned long active_timeslice(const struct intel_engine_cs *engine) { const struct intel_engine_execlists *execlists = &engine->execlists; const struct i915_request *rq = *execlists->active; @@ -1946,13 +1977,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine) last = NULL; } else if (need_timeslice(engine, last) && - timer_expired(&engine->execlists.timer)) { + timeslice_expired(execlists, last)) { ENGINE_TRACE(engine, - "expired last=%llx:%lld, prio=%d, hint=%d\n", + "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n", last->fence.context, last->fence.seqno, last->sched.attr.priority, - execlists->queue_priority_hint); + execlists->queue_priority_hint, + yesno(timeslice_yield(execlists, last))); ring_set_paused(engine, 1); defer_active(engine); @@ -2213,6 +2245,7 @@ done: } clear_ports(port + 1, last_port - port); + WRITE_ONCE(execlists->yield, -1); execlists_submit_ports(engine); set_preempt_timeout(engine, *active); } else { @@ -3043,7 +3076,7 @@ __execlists_context_pin(struct intel_context *ce, if (IS_ERR(vaddr)) return PTR_ERR(vaddr); - ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; + ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; __execlists_update_reg_state(ce, engine, ce->ring->tail); @@ -3072,7 +3105,7 @@ static void execlists_context_reset(struct intel_context *ce) ce, ce->engine, ce->ring, true); __execlists_update_reg_state(ce, ce->engine, ce->ring->tail); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static const struct intel_context_ops execlists_context_ops = { @@ -3541,7 +3574,7 @@ static void enable_execlists(struct intel_engine_cs *engine) enable_error_interrupt(engine); - engine->context_tag = 0; + engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0); } static bool unexpected_starting_state(struct intel_engine_cs *engine) @@ -3753,7 +3786,7 @@ out_replay: head, ce->ring->tail); __execlists_reset_reg_state(ce, engine); __execlists_update_reg_state(ce, engine, head); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ unwind: /* Push back any incomplete requests for replay after the reset. */ @@ -4369,8 +4402,11 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine) engine->flags |= I915_ENGINE_SUPPORTS_STATS; if (!intel_vgpu_active(engine->i915)) { engine->flags |= I915_ENGINE_HAS_SEMAPHORES; - if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) + if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) { engine->flags |= I915_ENGINE_HAS_PREEMPTION; + if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + engine->flags |= I915_ENGINE_HAS_TIMESLICES; + } } if (INTEL_GEN(engine->i915) >= 12) @@ -4449,6 +4485,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine) engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift; engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift; engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift; + engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift; } static void rcs_submission_override(struct intel_engine_cs *engine) @@ -4516,6 +4553,11 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) else execlists->csb_size = GEN11_CSB_ENTRIES; + if (INTEL_GEN(engine->i915) >= 11) { + execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32); + execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32); + } + reset_csb_pointers(engine); /* Finally, take ownership and responsibility for cleanup! */ diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 6f06ba750a0a..f95ae15ce865 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -929,7 +929,7 @@ create_rewinder(struct intel_context *ce, goto err; } - cs = intel_ring_begin(rq, 10); + cs = intel_ring_begin(rq, 14); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err; @@ -941,8 +941,8 @@ create_rewinder(struct intel_context *ce, *cs++ = MI_SEMAPHORE_WAIT | MI_SEMAPHORE_GLOBAL_GTT | MI_SEMAPHORE_POLL | - MI_SEMAPHORE_SAD_NEQ_SDD; - *cs++ = 0; + MI_SEMAPHORE_SAD_GTE_SDD; + *cs++ = idx; *cs++ = offset; *cs++ = 0; @@ -951,6 +951,11 @@ create_rewinder(struct intel_context *ce, *cs++ = offset + idx * sizeof(u32); *cs++ = 0; + *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *cs++ = offset; + *cs++ = 0; + *cs++ = idx + 1; + intel_ring_advance(rq, cs); rq->sched.attr.priority = I915_PRIORITY_MASK; @@ -984,7 +989,7 @@ static int live_timeslice_rewind(void *arg) for_each_engine(engine, gt, id) { enum { A1, A2, B1 }; - enum { X = 1, Y, Z }; + enum { X = 1, Z, Y }; struct i915_request *rq[3] = {}; struct intel_context *ce; unsigned long heartbeat; @@ -1017,13 +1022,13 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[0] = create_rewinder(ce, NULL, slot, 1); + rq[0] = create_rewinder(ce, NULL, slot, X); if (IS_ERR(rq[0])) { intel_context_put(ce); goto err; } - rq[1] = create_rewinder(ce, NULL, slot, 2); + rq[1] = create_rewinder(ce, NULL, slot, Y); intel_context_put(ce); if (IS_ERR(rq[1])) goto err; @@ -1041,7 +1046,7 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[2] = create_rewinder(ce, rq[0], slot, 3); + rq[2] = create_rewinder(ce, rq[0], slot, Z); intel_context_put(ce); if (IS_ERR(rq[2])) goto err; @@ -1055,15 +1060,12 @@ static int live_timeslice_rewind(void *arg) GEM_BUG_ON(!timer_pending(&engine->execlists.timer)); /* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */ - GEM_BUG_ON(!i915_request_is_active(rq[A1])); - GEM_BUG_ON(!i915_request_is_active(rq[A2])); - GEM_BUG_ON(!i915_request_is_active(rq[B1])); - - /* Wait for the timeslice to kick in */ - del_timer(&engine->execlists.timer); - tasklet_hi_schedule(&engine->execlists.tasklet); - intel_engine_flush_submission(engine); - + if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */ + /* Wait for the timeslice to kick in */ + del_timer(&engine->execlists.timer); + tasklet_hi_schedule(&engine->execlists.tasklet); + intel_engine_flush_submission(engine); + } /* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */ GEM_BUG_ON(!i915_request_is_active(rq[A1])); GEM_BUG_ON(!i915_request_is_active(rq[B1])); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index fe7778c28d2d..aa6d56e25a10 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -217,7 +217,7 @@ static void guc_wq_item_append(struct intel_guc *guc, static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) { struct intel_engine_cs *engine = rq->engine; - u32 ctx_desc = lower_32_bits(rq->context->lrc_desc); + u32 ctx_desc = rq->context->lrc.ccid; u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64); guc_wq_item_append(guc, engine->guc_id, ctx_desc, diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index a83df2f84eb9..a1696e9ce4b6 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -208,14 +208,41 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) SKL_FUSE_PG_DIST_STATUS(SKL_PG0) | SKL_FUSE_PG_DIST_STATUS(SKL_PG1) | SKL_FUSE_PG_DIST_STATUS(SKL_PG2); - vgpu_vreg_t(vgpu, LCPLL1_CTL) |= - LCPLL_PLL_ENABLE | - LCPLL_PLL_LOCK; - vgpu_vreg_t(vgpu, LCPLL2_CTL) |= LCPLL_PLL_ENABLE; - + /* + * Only 1 PIPE enabled in current vGPU display and PIPE_A is + * tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A, + * TRANSCODER_A can be enabled. PORT_x depends on the input of + * setup_virtual_dp_monitor, we can bind DPLL0 to any PORT_x + * so we fixed to DPLL0 here. + * Setup DPLL0: DP link clk 1620 MHz, non SSC, DP Mode + */ + vgpu_vreg_t(vgpu, DPLL_CTRL1) = + DPLL_CTRL1_OVERRIDE(DPLL_ID_SKL_DPLL0); + vgpu_vreg_t(vgpu, DPLL_CTRL1) |= + DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, DPLL_ID_SKL_DPLL0); + vgpu_vreg_t(vgpu, LCPLL1_CTL) = + LCPLL_PLL_ENABLE | LCPLL_PLL_LOCK; + vgpu_vreg_t(vgpu, DPLL_STATUS) = DPLL_LOCK(DPLL_ID_SKL_DPLL0); + /* + * Golden M/N are calculated based on: + * 24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID), + * DP link clk 1620 MHz and non-constant_n. + * TODO: calculate DP link symbol clk and stream clk m/n. + */ + vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT; + vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e; + vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000; + vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e; + vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000; } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_B); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_B); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_B); vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | @@ -236,6 +263,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_C); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_C); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_C); vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | @@ -256,6 +289,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_D); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_D); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_D); vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index cb11c3184085..e92ed96c9b23 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -290,7 +290,7 @@ static void shadow_context_descriptor_update(struct intel_context *ce, struct intel_vgpu_workload *workload) { - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; /* * Update bits 0-11 of the context descriptor which includes flags @@ -300,7 +300,7 @@ shadow_context_descriptor_update(struct intel_context *ce, desc |= (u64)workload->ctx_desc.addressing_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; - ce->lrc_desc = desc; + ce->lrc.desc = desc; } static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload) @@ -379,7 +379,11 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) { struct i915_page_directory * const pd = i915_pd_entry(ppgtt->pd, i); - + /* skip now as current i915 ppgtt alloc won't allocate + top level pdp for non 4-level table, won't impact + shadow ppgtt. */ + if (!pd) + break; px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i]; } } diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 4518b9b35c3d..02ad1acd117c 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -128,6 +128,13 @@ search_again: active = NULL; INIT_LIST_HEAD(&eviction_list); list_for_each_entry_safe(vma, next, &vm->bound_list, vm_link) { + if (vma == active) { /* now seen this vma twice */ + if (flags & PIN_NONBLOCK) + break; + + active = ERR_PTR(-EAGAIN); + } + /* * We keep this list in a rough least-recently scanned order * of active elements (inactive elements are cheap to reap). @@ -143,21 +150,12 @@ search_again: * To notice when we complete one full cycle, we record the * first active element seen, before moving it to the tail. */ - if (i915_vma_is_active(vma)) { - if (vma == active) { - if (flags & PIN_NONBLOCK) - break; - - active = ERR_PTR(-EAGAIN); - } - - if (active != ERR_PTR(-EAGAIN)) { - if (!active) - active = vma; + if (active != ERR_PTR(-EAGAIN) && i915_vma_is_active(vma)) { + if (!active) + active = vma; - list_move_tail(&vma->vm_link, &vm->bound_list); - continue; - } + list_move_tail(&vma->vm_link, &vm->bound_list); + continue; } if (mark_free(&scan, vma, flags, &eviction_list)) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2a4cd0ba5464..5c8e51d2ba5b 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1207,8 +1207,6 @@ static void engine_record_registers(struct intel_engine_coredump *ee) static void record_request(const struct i915_request *request, struct i915_request_coredump *erq) { - const struct i915_gem_context *ctx; - erq->flags = request->fence.flags; erq->context = request->fence.context; erq->seqno = request->fence.seqno; @@ -1219,9 +1217,13 @@ static void record_request(const struct i915_request *request, erq->pid = 0; rcu_read_lock(); - ctx = rcu_dereference(request->context->gem_context); - if (ctx) - erq->pid = pid_nr(ctx->pid); + if (!intel_context_is_closed(request->context)) { + const struct i915_gem_context *ctx; + + ctx = rcu_dereference(request->context->gem_context); + if (ctx) + erq->pid = pid_nr(ctx->pid); + } rcu_read_unlock(); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index d91557d842dc..8a2b83807ffc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3361,7 +3361,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) u32 de_pipe_masked = gen8_de_pipe_fault_mask(dev_priv) | GEN8_PIPE_CDCLK_CRC_DONE; u32 de_pipe_enables; - u32 de_port_masked = GEN8_AUX_CHANNEL_A; + u32 de_port_masked = gen8_de_port_aux_mask(dev_priv); u32 de_port_enables; u32 de_misc_masked = GEN8_DE_EDP_PSR; enum pipe pipe; @@ -3369,18 +3369,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) <= 10) de_misc_masked |= GEN8_DE_MISC_GSE; - if (INTEL_GEN(dev_priv) >= 9) { - de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | - GEN9_AUX_CHANNEL_D; - if (IS_GEN9_LP(dev_priv)) - de_port_masked |= BXT_DE_PORT_GMBUS; - } - - if (INTEL_GEN(dev_priv) >= 11) - de_port_masked |= ICL_AUX_CHANNEL_E; - - if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11) - de_port_masked |= CNL_AUX_CHANNEL_F; + if (IS_GEN9_LP(dev_priv)) + de_port_masked |= BXT_DE_PORT_GMBUS; de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN; diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 66a46e41d5ef..cf2c01f17da8 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1310,8 +1310,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) * dropped by GuC. They won't be part of the context * ID in the OA reports, so squash those lower bits. */ - stream->specific_ctx_id = - lower_32_bits(ce->lrc_desc) >> 12; + stream->specific_ctx_id = ce->lrc.lrca >> 12; /* * GuC uses the top bit to signal proxy submission, so @@ -1328,11 +1327,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); /* * Pick an unused context id - * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts + * 0 - BITS_PER_LONG are used by other contexts * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context */ stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); - BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG); break; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e0c6021fdaf9..6e12000c4b6b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3094,6 +3094,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GT_BSD_CS_ERROR_INTERRUPT (1 << 15) #define GT_BSD_USER_INTERRUPT (1 << 12) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 (1 << 11) /* hsw+; rsvd on snb, ivb, vlv */ +#define GT_WAIT_SEMAPHORE_INTERRUPT REG_BIT(11) /* bdw+ */ #define GT_CONTEXT_SWITCH_INTERRUPT (1 << 8) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT (1 << 5) /* !snb */ #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT (1 << 4) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index c0df71d7d0ff..e2b78db685ea 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1017,11 +1017,15 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) GEM_BUG_ON(to == from); GEM_BUG_ON(to->timeline == from->timeline); - if (i915_request_completed(from)) + if (i915_request_completed(from)) { + i915_sw_fence_set_error_once(&to->submit, from->fence.error); return 0; + } if (to->engine->schedule) { - ret = i915_sched_node_add_dependency(&to->sched, &from->sched); + ret = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_EXTERNAL); if (ret < 0) return ret; } @@ -1183,7 +1187,9 @@ __i915_request_await_execution(struct i915_request *to, /* Couple the dependency tree for PI on this exposed to->fence */ if (to->engine->schedule) { - err = i915_sched_node_add_dependency(&to->sched, &from->sched); + err = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_WEAK); if (err < 0) return err; } diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 68b06a7ba667..f0a9e8958ca0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -456,7 +456,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, } int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal) + struct i915_sched_node *signal, + unsigned long flags) { struct i915_dependency *dep; @@ -465,8 +466,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node, return -ENOMEM; if (!__i915_sched_node_add_dependency(node, signal, dep, - I915_DEPENDENCY_EXTERNAL | - I915_DEPENDENCY_ALLOC)) + flags | I915_DEPENDENCY_ALLOC)) i915_dependency_free(dep); return 0; diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h index d1dc4efef77b..6f0bf00fc569 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.h +++ b/drivers/gpu/drm/i915/i915_scheduler.h @@ -34,7 +34,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, unsigned long flags); int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal); + struct i915_sched_node *signal, + unsigned long flags); void i915_sched_node_fini(struct i915_sched_node *node); diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h index d18e70550054..7186875088a0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler_types.h +++ b/drivers/gpu/drm/i915/i915_scheduler_types.h @@ -78,6 +78,7 @@ struct i915_dependency { unsigned long flags; #define I915_DEPENDENCY_ALLOC BIT(0) #define I915_DEPENDENCY_EXTERNAL BIT(1) +#define I915_DEPENDENCY_WEAK BIT(2) }; #endif /* _I915_SCHEDULER_TYPES_H_ */ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 82e3bc280622..2cd7a7e87c0a 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1228,18 +1228,6 @@ int __i915_vma_unbind(struct i915_vma *vma) lockdep_assert_held(&vma->vm->mutex); - /* - * First wait upon any activity as retiring the request may - * have side-effects such as unpinning or even unbinding this vma. - * - * XXX Actually waiting under the vm->mutex is a hinderance and - * should be pipelined wherever possible. In cases where that is - * unavoidable, we should lift the wait to before the mutex. - */ - ret = i915_vma_sync(vma); - if (ret) - return ret; - if (i915_vma_is_pinned(vma)) { vma_print_allocator(vma, "is pinned"); return -EAGAIN; @@ -1313,15 +1301,20 @@ int i915_vma_unbind(struct i915_vma *vma) if (!drm_mm_node_allocated(&vma->node)) return 0; - if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) - /* XXX not always required: nop_clear_range */ - wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); - /* Optimistic wait before taking the mutex */ err = i915_vma_sync(vma); if (err) goto out_rpm; + if (i915_vma_is_pinned(vma)) { + vma_print_allocator(vma, "is pinned"); + return -EAGAIN; + } + + if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) + /* XXX not always required: nop_clear_range */ + wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); + err = mutex_lock_interruptible(&vm->mutex); if (err) goto out_rpm; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8375054ba27d..a52986a9e7a6 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4992,7 +4992,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, * WaIncreaseLatencyIPCEnabled: kbl,cfl * Display WA #1141: kbl,cfl */ - if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) || + if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) && dev_priv->ipc_enabled) latency += 4; diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index 58b5f40a07dd..af89c7fc8f59 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -173,7 +173,7 @@ static int igt_vma_create(void *arg) } nc = 0; - for_each_prime_number(num_ctx, 2 * NUM_CONTEXT_TAG) { + for_each_prime_number(num_ctx, 2 * BITS_PER_LONG) { for (; nc < num_ctx; nc++) { ctx = mock_context(i915, "mock"); if (!ctx) diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c index 9dfe7cb530e1..1754c0547069 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm.c @@ -843,6 +843,7 @@ static const struct of_device_id ingenic_drm_of_match[] = { { .compatible = "ingenic,jz4770-lcd", .data = &jz4770_soc_info }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, ingenic_drm_of_match); static struct platform_driver ingenic_drm_driver = { .driver = { diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index b5f5eb7b4bb9..8c2e1b47e81a 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -412,9 +412,7 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev) if (priv->afbcd.ops) priv->afbcd.ops->init(priv); - drm_mode_config_helper_resume(priv->drm); - - return 0; + return drm_mode_config_helper_resume(priv->drm); } static int compare_of(struct device *dev, void *data) diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 059939789730..3eb89f1eb0e1 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -717,7 +717,7 @@ static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder) struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder); struct mipi_dsi_device *device = dsi->device; - union phy_configure_opts opts = { 0 }; + union phy_configure_opts opts = { }; struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy; u16 delay; int err; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index bd268028fb3d..583cd6e0ae27 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1039,6 +1039,7 @@ void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt, static bool host1x_drm_wants_iommu(struct host1x_device *dev) { + struct host1x *host1x = dev_get_drvdata(dev->dev.parent); struct iommu_domain *domain; /* @@ -1076,7 +1077,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) * sufficient and whether or not the host1x is attached to an IOMMU * doesn't matter. */ - if (!domain && dma_get_mask(dev->dev.parent) <= DMA_BIT_MASK(32)) + if (!domain && host1x_get_dma_mask(host1x) <= DMA_BIT_MASK(32)) return true; return domain != NULL; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index c1824bdf2418..7879ff58236f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -221,6 +221,7 @@ struct virtio_gpu_fpriv { /* virtio_ioctl.c */ #define DRM_VIRTIO_NUM_IOCTLS 10 extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file); /* virtio_kms.c */ int virtio_gpu_init(struct drm_device *dev); diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 0d6152c99a27..f0d5a8974677 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -39,6 +39,9 @@ int virtio_gpu_gem_create(struct drm_file *file, int ret; u32 handle; + if (vgdev->has_virgl_3d) + virtio_gpu_create_context(dev, file); + ret = virtio_gpu_object_create(vgdev, params, &obj, NULL); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 3f60bf2fe05a..512daff92038 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -34,8 +34,7 @@ #include "virtgpu_drv.h" -static void virtio_gpu_create_context(struct drm_device *dev, - struct drm_file *file) +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file) { struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_fpriv *vfpriv = file->driver_priv; diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 388bcc2889aa..d24344e91922 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -192,17 +192,55 @@ static void host1x_setup_sid_table(struct host1x *host) } } +static bool host1x_wants_iommu(struct host1x *host1x) +{ + /* + * If we support addressing a maximum of 32 bits of physical memory + * and if the host1x firewall is enabled, there's no need to enable + * IOMMU support. This can happen for example on Tegra20, Tegra30 + * and Tegra114. + * + * Tegra124 and later can address up to 34 bits of physical memory and + * many platforms come equipped with more than 2 GiB of system memory, + * which requires crossing the 4 GiB boundary. But there's a catch: on + * SoCs before Tegra186 (i.e. Tegra124 and Tegra210), the host1x can + * only address up to 32 bits of memory in GATHER opcodes, which means + * that command buffers need to either be in the first 2 GiB of system + * memory (which could quickly lead to memory exhaustion), or command + * buffers need to be treated differently from other buffers (which is + * not possible with the current ABI). + * + * A third option is to use the IOMMU in these cases to make sure all + * buffers will be mapped into a 32-bit IOVA space that host1x can + * address. This allows all of the system memory to be used and works + * within the limitations of the host1x on these SoCs. + * + * In summary, default to enable IOMMU on Tegra124 and later. For any + * of the earlier SoCs, only use the IOMMU for additional safety when + * the host1x firewall is disabled. + */ + if (host1x->info->dma_mask <= DMA_BIT_MASK(32)) { + if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + return false; + } + + return true; +} + static struct iommu_domain *host1x_iommu_attach(struct host1x *host) { struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev); int err; /* - * If the host1x firewall is enabled, there's no need to enable IOMMU - * support. Similarly, if host1x is already attached to an IOMMU (via - * the DMA API), don't try to attach again. + * We may not always want to enable IOMMU support (for example if the + * host1x firewall is already enabled and we don't support addressing + * more than 32 bits of physical memory), so check for that first. + * + * Similarly, if host1x is already attached to an IOMMU (via the DMA + * API), don't try to attach again. */ - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) || domain) + if (!host1x_wants_iommu(host) || domain) return domain; host->group = iommu_group_get(host->dev); @@ -502,6 +540,19 @@ static void __exit tegra_host1x_exit(void) } module_exit(tegra_host1x_exit); +/** + * host1x_get_dma_mask() - query the supported DMA mask for host1x + * @host1x: host1x instance + * + * Note that this returns the supported DMA mask for host1x, which can be + * different from the applicable DMA mask under certain circumstances. + */ +u64 host1x_get_dma_mask(struct host1x *host1x) +{ + return host1x->info->dma_mask; +} +EXPORT_SYMBOL(host1x_get_dma_mask); + MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>"); MODULE_AUTHOR("Terje Bergstrom <tbergstrom@nvidia.com>"); MODULE_DESCRIPTION("Host1x driver for Tegra products"); diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c index 53b517dbe7e6..4af2fc309c28 100644 --- a/drivers/hwmon/da9052-hwmon.c +++ b/drivers/hwmon/da9052-hwmon.c @@ -244,9 +244,9 @@ static ssize_t da9052_tsi_show(struct device *dev, int channel = to_sensor_dev_attr(devattr)->index; int ret; - mutex_lock(&hwmon->hwmon_lock); + mutex_lock(&hwmon->da9052->auxadc_lock); ret = __da9052_read_tsi(dev, channel); - mutex_unlock(&hwmon->hwmon_lock); + mutex_unlock(&hwmon->da9052->auxadc_lock); if (ret < 0) return ret; diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 9179460c2d9d..0d4f3d97ffc6 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -346,7 +346,7 @@ static int drivetemp_identify_sata(struct drivetemp_data *st) st->have_temp_highest = temp_is_valid(buf[SCT_STATUS_TEMP_HIGHEST]); if (!have_sct_data_table) - goto skip_sct; + goto skip_sct_data; /* Request and read temperature history table */ memset(buf, '\0', sizeof(st->smartdata)); diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index 1f5743d68984..a7eb10d2a053 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -41,6 +41,7 @@ #define FANCTL_MAX 4 /* Counted from 1 */ #define TCPU_MAX 8 /* Counted from 1 */ #define TEMP_MAX 4 /* Counted from 1 */ +#define SMI_STS_MAX 10 /* Counted from 1 */ #define VT_ADC_CTRL0_REG 0x20 /* Bank 0 */ #define VT_ADC_CTRL1_REG 0x21 /* Bank 0 */ @@ -361,6 +362,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel, struct nct7904_data *data = dev_get_drvdata(dev); int ret, temp; unsigned int reg1, reg2, reg3; + s8 temps; switch (attr) { case hwmon_temp_input: @@ -466,7 +468,8 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel, if (ret < 0) return ret; - *val = ret * 1000; + temps = ret; + *val = temps * 1000; return 0; } @@ -1009,6 +1012,13 @@ static int nct7904_probe(struct i2c_client *client, data->fan_mode[i] = ret; } + /* Read all of SMI status register to clear alarms */ + for (i = 0; i < SMI_STS_MAX; i++) { + ret = nct7904_read_reg(data, BANK_0, SMI_STS1_REG + i); + if (ret < 0) + return ret; + } + hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data, &nct7904_chip_info, NULL); diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 717b798cddad..a670209bbce6 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1553,8 +1553,11 @@ int ib_cache_setup_one(struct ib_device *device) if (err) return err; - rdma_for_each_port (device, p) - ib_cache_update(device, p, true); + rdma_for_each_port (device, p) { + err = ib_cache_update(device, p, true); + if (err) + return err; + } return 0; } diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 9eec26d10d7b..e16105be2eb2 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -1292,11 +1292,10 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh, has_cap_net_admin = netlink_capable(skb, CAP_NET_ADMIN); ret = fill_func(msg, has_cap_net_admin, res, port); - - rdma_restrack_put(res); if (ret) goto err_free; + rdma_restrack_put(res); nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 177333d8bcda..bf8e149d3191 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -459,7 +459,8 @@ alloc_begin_fd_uobject(const struct uverbs_api_object *obj, struct ib_uobject *uobj; struct file *filp; - if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release)) + if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release && + fd_type->fops->release != &uverbs_async_event_release)) return ERR_PTR(-EINVAL); new_fd = get_unused_fd_flags(O_CLOEXEC); diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index 7df71983212d..3d189c7ee59e 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -219,6 +219,7 @@ void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue); void ib_uverbs_init_async_event_file(struct ib_uverbs_async_event_file *ev_file); void ib_uverbs_free_event_queue(struct ib_uverbs_event_queue *event_queue); void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res); +int uverbs_async_event_release(struct inode *inode, struct file *filp); int ib_alloc_ucontext(struct uverbs_attr_bundle *attrs); int ib_init_ucontext(struct uverbs_attr_bundle *attrs); @@ -227,6 +228,9 @@ void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file, struct ib_ucq_object *uobj); void ib_uverbs_release_uevent(struct ib_uevent_object *uobj); void ib_uverbs_release_file(struct kref *ref); +void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, + __u64 element, __u64 event, + struct list_head *obj_list, u32 *counter); void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context); void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 17fc25db0311..1bab8de14757 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -346,7 +346,7 @@ const struct file_operations uverbs_async_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_async_event_read, .poll = ib_uverbs_async_event_poll, - .release = uverbs_uobject_fd_release, + .release = uverbs_async_event_release, .fasync = ib_uverbs_async_event_fasync, .llseek = no_llseek, }; @@ -386,10 +386,9 @@ void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN); } -static void -ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, - __u64 element, __u64 event, struct list_head *obj_list, - u32 *counter) +void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, + __u64 element, __u64 event, + struct list_head *obj_list, u32 *counter) { struct ib_uverbs_event *entry; unsigned long flags; @@ -1187,9 +1186,6 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, */ mutex_unlock(&uverbs_dev->lists_mutex); - ib_uverbs_async_handler(READ_ONCE(file->async_file), 0, - IB_EVENT_DEVICE_FATAL, NULL, NULL); - uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE); kref_put(&file->ref, ib_uverbs_release_file); diff --git a/drivers/infiniband/core/uverbs_std_types_async_fd.c b/drivers/infiniband/core/uverbs_std_types_async_fd.c index 82ec0806b34b..61899eaf1f91 100644 --- a/drivers/infiniband/core/uverbs_std_types_async_fd.c +++ b/drivers/infiniband/core/uverbs_std_types_async_fd.c @@ -26,10 +26,38 @@ static int uverbs_async_event_destroy_uobj(struct ib_uobject *uobj, container_of(uobj, struct ib_uverbs_async_event_file, uobj); ib_unregister_event_handler(&event_file->event_handler); - ib_uverbs_free_event_queue(&event_file->ev_queue); + + if (why == RDMA_REMOVE_DRIVER_REMOVE) + ib_uverbs_async_handler(event_file, 0, IB_EVENT_DEVICE_FATAL, + NULL, NULL); return 0; } +int uverbs_async_event_release(struct inode *inode, struct file *filp) +{ + struct ib_uverbs_async_event_file *event_file; + struct ib_uobject *uobj = filp->private_data; + int ret; + + if (!uobj) + return uverbs_uobject_fd_release(inode, filp); + + event_file = + container_of(uobj, struct ib_uverbs_async_event_file, uobj); + + /* + * The async event FD has to deliver IB_EVENT_DEVICE_FATAL even after + * disassociation, so cleaning the event list must only happen after + * release. The user knows it has reached the end of the event stream + * when it sees IB_EVENT_DEVICE_FATAL. + */ + uverbs_uobject_get(uobj); + ret = uverbs_uobject_fd_release(inode, filp); + ib_uverbs_free_event_queue(&event_file->ev_queue); + uverbs_uobject_put(uobj); + return ret; +} + DECLARE_UVERBS_NAMED_METHOD( UVERBS_METHOD_ASYNC_EVENT_ALLOC, UVERBS_ATTR_FD(UVERBS_ATTR_ASYNC_EVENT_ALLOC_FD_HANDLE, diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index d69dece3b1d5..30e08bcc9afb 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -2891,8 +2891,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) srqidx = ABORT_RSS_SRQIDX_G( be32_to_cpu(req->srqidx_status)); if (srqidx) { - complete_cached_srq_buffers(ep, - req->srqidx_status); + complete_cached_srq_buffers(ep, srqidx); } else { /* Hold ep ref until finish_peer_abort() */ c4iw_get_ep(&ep->com); @@ -3878,8 +3877,8 @@ static int read_tcb_rpl(struct c4iw_dev *dev, struct sk_buff *skb) return 0; } - ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_W, - TCB_RQ_START_S); + ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_M, + TCB_RQ_START_S); cleanup: pr_debug("ep %p tid %u %016x\n", ep, ep->hwtid, ep->srqe_idx); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 13e4203497b3..a92346e88628 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -589,10 +589,6 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, set_comp_state(pq, cq, info.comp_idx, QUEUED, 0); pq->state = SDMA_PKT_Q_ACTIVE; - /* Send the first N packets in the request to buy us some time */ - ret = user_sdma_send_pkts(req, pcount); - if (unlikely(ret < 0 && ret != -EBUSY)) - goto free_req; /* * This is a somewhat blocking send implementation. diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index bb78d3280acc..fa7a5ff498c7 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -1987,7 +1987,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev, struct rtable *rt; struct neighbour *neigh; int rc = arpindex; - struct net_device *netdev = iwdev->netdev; __be32 dst_ipaddr = htonl(dst_ip); __be32 src_ipaddr = htonl(src_ip); @@ -1997,9 +1996,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev, return rc; } - if (netif_is_bond_slave(netdev)) - netdev = netdev_master_upper_dev_get(netdev); - neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr); rcu_read_lock(); @@ -2065,7 +2061,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, { struct neighbour *neigh; int rc = arpindex; - struct net_device *netdev = iwdev->netdev; struct dst_entry *dst; struct sockaddr_in6 dst_addr; struct sockaddr_in6 src_addr; @@ -2086,9 +2081,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, return rc; } - if (netif_is_bond_slave(netdev)) - netdev = netdev_master_upper_dev_get(netdev); - neigh = dst_neigh_lookup(dst, dst_addr.sin6_addr.in6_u.u6_addr32); rcu_read_lock(); diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c index 55a1fbf0e670..ae8b97c30665 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_hw.c +++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c @@ -534,7 +534,7 @@ void i40iw_manage_arp_cache(struct i40iw_device *iwdev, int arp_index; arp_index = i40iw_arp_table(iwdev, ip_addr, ipv4, mac_addr, action); - if (arp_index == -1) + if (arp_index < 0) return; cqp_request = i40iw_get_cqp_request(&iwdev->cqp, false); if (!cqp_request) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 2f9f78912267..cf51e3cbd969 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -2891,6 +2891,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, int send_size; int header_size; int spc; + int err; int i; if (wr->wr.opcode != IB_WR_SEND) @@ -2925,7 +2926,9 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, sqp->ud_header.lrh.virtual_lane = 0; sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED); - ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey); + err = ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey); + if (err) + return err; sqp->ud_header.bth.pkey = cpu_to_be16(pkey); if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_TUN_SMI_OWNER) sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn); @@ -3212,9 +3215,14 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr, } sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED); if (!sqp->qp.ibqp.qp_num) - ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, &pkey); + err = ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, + &pkey); else - ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index, &pkey); + err = ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index, + &pkey); + if (err) + return err; + sqp->ud_header.bth.pkey = cpu_to_be16(pkey); sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn); sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1)); diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c index 48f48122ddcb..6a413d73b95d 100644 --- a/drivers/infiniband/sw/rxe/rxe_mmap.c +++ b/drivers/infiniband/sw/rxe/rxe_mmap.c @@ -151,7 +151,7 @@ struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *rxe, u32 size, ip = kmalloc(sizeof(*ip), GFP_KERNEL); if (!ip) - return NULL; + return ERR_PTR(-ENOMEM); size = PAGE_ALIGN(size); diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c index ff92704de32f..245040c3a35d 100644 --- a/drivers/infiniband/sw/rxe/rxe_queue.c +++ b/drivers/infiniband/sw/rxe/rxe_queue.c @@ -45,12 +45,15 @@ int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf, if (outbuf) { ip = rxe_create_mmap_info(rxe, buf_size, udata, buf); - if (!ip) + if (IS_ERR(ip)) { + err = PTR_ERR(ip); goto err1; + } - err = copy_to_user(outbuf, &ip->info, sizeof(ip->info)); - if (err) + if (copy_to_user(outbuf, &ip->info, sizeof(ip->info))) { + err = -EFAULT; goto err2; + } spin_lock_bh(&rxe->pending_lock); list_add(&ip->pending_mmaps, &rxe->pending_mmaps); @@ -64,7 +67,7 @@ int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf, err2: kfree(ip); err1: - return -EINVAL; + return err; } inline void rxe_queue_reset(struct rxe_queue *q) diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index a03c6d6833df..96fb9ff5ff2e 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -78,7 +78,7 @@ static struct qcom_icc_node *sdm845_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sdm845_osm_l3, }; -const static struct qcom_icc_desc sdm845_icc_osm_l3 = { +static const struct qcom_icc_desc sdm845_icc_osm_l3 = { .nodes = sdm845_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sdm845_osm_l3_nodes), }; @@ -91,7 +91,7 @@ static struct qcom_icc_node *sc7180_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sc7180_osm_l3, }; -const static struct qcom_icc_desc sc7180_icc_osm_l3 = { +static const struct qcom_icc_desc sc7180_icc_osm_l3 = { .nodes = sc7180_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sc7180_osm_l3_nodes), }; diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c index b013b80caa45..f6c7b969520d 100644 --- a/drivers/interconnect/qcom/sdm845.c +++ b/drivers/interconnect/qcom/sdm845.c @@ -192,7 +192,7 @@ static struct qcom_icc_node *aggre1_noc_nodes[] = { [SLAVE_ANOC_PCIE_A1NOC_SNOC] = &qns_pcie_a1noc_snoc, }; -const static struct qcom_icc_desc sdm845_aggre1_noc = { +static const struct qcom_icc_desc sdm845_aggre1_noc = { .nodes = aggre1_noc_nodes, .num_nodes = ARRAY_SIZE(aggre1_noc_nodes), .bcms = aggre1_noc_bcms, @@ -220,7 +220,7 @@ static struct qcom_icc_node *aggre2_noc_nodes[] = { [SLAVE_SERVICE_A2NOC] = &srvc_aggre2_noc, }; -const static struct qcom_icc_desc sdm845_aggre2_noc = { +static const struct qcom_icc_desc sdm845_aggre2_noc = { .nodes = aggre2_noc_nodes, .num_nodes = ARRAY_SIZE(aggre2_noc_nodes), .bcms = aggre2_noc_bcms, @@ -281,7 +281,7 @@ static struct qcom_icc_node *config_noc_nodes[] = { [SLAVE_SERVICE_CNOC] = &srvc_cnoc, }; -const static struct qcom_icc_desc sdm845_config_noc = { +static const struct qcom_icc_desc sdm845_config_noc = { .nodes = config_noc_nodes, .num_nodes = ARRAY_SIZE(config_noc_nodes), .bcms = config_noc_bcms, @@ -297,7 +297,7 @@ static struct qcom_icc_node *dc_noc_nodes[] = { [SLAVE_MEM_NOC_CFG] = &qhs_memnoc, }; -const static struct qcom_icc_desc sdm845_dc_noc = { +static const struct qcom_icc_desc sdm845_dc_noc = { .nodes = dc_noc_nodes, .num_nodes = ARRAY_SIZE(dc_noc_nodes), .bcms = dc_noc_bcms, @@ -315,7 +315,7 @@ static struct qcom_icc_node *gladiator_noc_nodes[] = { [SLAVE_SERVICE_GNOC] = &srvc_gnoc, }; -const static struct qcom_icc_desc sdm845_gladiator_noc = { +static const struct qcom_icc_desc sdm845_gladiator_noc = { .nodes = gladiator_noc_nodes, .num_nodes = ARRAY_SIZE(gladiator_noc_nodes), .bcms = gladiator_noc_bcms, @@ -350,7 +350,7 @@ static struct qcom_icc_node *mem_noc_nodes[] = { [SLAVE_EBI1] = &ebi, }; -const static struct qcom_icc_desc sdm845_mem_noc = { +static const struct qcom_icc_desc sdm845_mem_noc = { .nodes = mem_noc_nodes, .num_nodes = ARRAY_SIZE(mem_noc_nodes), .bcms = mem_noc_bcms, @@ -384,7 +384,7 @@ static struct qcom_icc_node *mmss_noc_nodes[] = { [SLAVE_CAMNOC_UNCOMP] = &qns_camnoc_uncomp, }; -const static struct qcom_icc_desc sdm845_mmss_noc = { +static const struct qcom_icc_desc sdm845_mmss_noc = { .nodes = mmss_noc_nodes, .num_nodes = ARRAY_SIZE(mmss_noc_nodes), .bcms = mmss_noc_bcms, @@ -430,7 +430,7 @@ static struct qcom_icc_node *system_noc_nodes[] = { [SLAVE_TCU] = &xs_sys_tcu_cfg, }; -const static struct qcom_icc_desc sdm845_system_noc = { +static const struct qcom_icc_desc sdm845_system_noc = { .nodes = system_noc_nodes, .num_nodes = ARRAY_SIZE(system_noc_nodes), .bcms = system_noc_bcms, diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 20cce366e951..1dc3718560d0 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -101,6 +101,8 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); static void detach_device(struct device *dev); +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable); /**************************************************************************** * @@ -151,6 +153,26 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom) return container_of(dom, struct protection_domain, domain); } +static void amd_iommu_domain_get_pgtable(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + u64 pt_root = atomic64_read(&domain->pt_root); + + pgtable->root = (u64 *)(pt_root & PAGE_MASK); + pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */ +} + +static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode) +{ + u64 pt_root; + + /* lowest 3 bits encode pgtable mode */ + pt_root = mode & 7; + pt_root |= (u64)root; + + return pt_root; +} + static struct iommu_dev_data *alloc_dev_data(u16 devid) { struct iommu_dev_data *dev_data; @@ -1397,13 +1419,18 @@ static struct page *free_sub_pt(unsigned long root, int mode, static void free_pagetable(struct protection_domain *domain) { - unsigned long root = (unsigned long)domain->pt_root; + struct domain_pgtable pgtable; struct page *freelist = NULL; + unsigned long root; - BUG_ON(domain->mode < PAGE_MODE_NONE || - domain->mode > PAGE_MODE_6_LEVEL); + amd_iommu_domain_get_pgtable(domain, &pgtable); + atomic64_set(&domain->pt_root, 0); - freelist = free_sub_pt(root, domain->mode, freelist); + BUG_ON(pgtable.mode < PAGE_MODE_NONE || + pgtable.mode > PAGE_MODE_6_LEVEL); + + root = (unsigned long)pgtable.root; + freelist = free_sub_pt(root, pgtable.mode, freelist); free_page_list(freelist); } @@ -1417,24 +1444,39 @@ static bool increase_address_space(struct protection_domain *domain, unsigned long address, gfp_t gfp) { + struct domain_pgtable pgtable; unsigned long flags; - bool ret = false; - u64 *pte; + bool ret = true; + u64 *pte, root; spin_lock_irqsave(&domain->lock, flags); - if (address <= PM_LEVEL_SIZE(domain->mode) || - WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address <= PM_LEVEL_SIZE(pgtable.mode)) + goto out; + + ret = false; + if (WARN_ON_ONCE(pgtable.mode == PAGE_MODE_6_LEVEL)) goto out; pte = (void *)get_zeroed_page(gfp); if (!pte) goto out; - *pte = PM_LEVEL_PDE(domain->mode, - iommu_virt_to_phys(domain->pt_root)); - domain->pt_root = pte; - domain->mode += 1; + *pte = PM_LEVEL_PDE(pgtable.mode, iommu_virt_to_phys(pgtable.root)); + + pgtable.root = pte; + pgtable.mode += 1; + update_and_flush_device_table(domain, &pgtable); + domain_flush_complete(domain); + + /* + * Device Table needs to be updated and flushed before the new root can + * be published. + */ + root = amd_iommu_domain_encode_pgtable(pte, pgtable.mode); + atomic64_set(&domain->pt_root, root); ret = true; @@ -1451,16 +1493,29 @@ static u64 *alloc_pte(struct protection_domain *domain, gfp_t gfp, bool *updated) { + struct domain_pgtable pgtable; int level, end_lvl; u64 *pte, *page; BUG_ON(!is_power_of_2(page_size)); - while (address > PM_LEVEL_SIZE(domain->mode)) - *updated = increase_address_space(domain, address, gfp) || *updated; + amd_iommu_domain_get_pgtable(domain, &pgtable); + + while (address > PM_LEVEL_SIZE(pgtable.mode)) { + /* + * Return an error if there is no memory to update the + * page-table. + */ + if (!increase_address_space(domain, address, gfp)) + return NULL; + + /* Read new values to check if update was successful */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + } + - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -1536,16 +1591,19 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address, unsigned long *page_size) { + struct domain_pgtable pgtable; int level; u64 *pte; *page_size = 0; - if (address > PM_LEVEL_SIZE(domain->mode)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address > PM_LEVEL_SIZE(pgtable.mode)) return NULL; - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -1660,7 +1718,13 @@ out: unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - update_domain(dom); + /* + * Flush domain TLB(s) and wait for completion. Any Device-Table + * Updates and flushing already happened in + * increase_address_space(). + */ + domain_flush_tlb_pde(dom); + domain_flush_complete(dom); spin_unlock_irqrestore(&dom->lock, flags); } @@ -1806,6 +1870,7 @@ static void dma_ops_domain_free(struct protection_domain *domain) static struct protection_domain *dma_ops_domain_alloc(void) { struct protection_domain *domain; + u64 *pt_root, root; domain = kzalloc(sizeof(struct protection_domain), GFP_KERNEL); if (!domain) @@ -1814,12 +1879,14 @@ static struct protection_domain *dma_ops_domain_alloc(void) if (protection_domain_init(domain)) goto free_domain; - domain->mode = PAGE_MODE_3_LEVEL; - domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - domain->flags = PD_DMA_OPS_MASK; - if (!domain->pt_root) + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) goto free_domain; + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&domain->pt_root, root); + domain->flags = PD_DMA_OPS_MASK; + if (iommu_get_dma_cookie(&domain->domain) == -ENOMEM) goto free_domain; @@ -1841,16 +1908,17 @@ static bool dma_ops_domain(struct protection_domain *domain) } static void set_dte_entry(u16 devid, struct protection_domain *domain, + struct domain_pgtable *pgtable, bool ats, bool ppr) { u64 pte_root = 0; u64 flags = 0; u32 old_domid; - if (domain->mode != PAGE_MODE_NONE) - pte_root = iommu_virt_to_phys(domain->pt_root); + if (pgtable->mode != PAGE_MODE_NONE) + pte_root = iommu_virt_to_phys(pgtable->root); - pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK) + pte_root |= (pgtable->mode & DEV_ENTRY_MODE_MASK) << DEV_ENTRY_MODE_SHIFT; pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V | DTE_FLAG_TV; @@ -1923,6 +1991,7 @@ static void clear_dte_entry(u16 devid) static void do_attach(struct iommu_dev_data *dev_data, struct protection_domain *domain) { + struct domain_pgtable pgtable; struct amd_iommu *iommu; bool ats; @@ -1938,7 +2007,9 @@ static void do_attach(struct iommu_dev_data *dev_data, domain->dev_cnt += 1; /* Update device table */ - set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2); + amd_iommu_domain_get_pgtable(domain, &pgtable); + set_dte_entry(dev_data->devid, domain, &pgtable, + ats, dev_data->iommu_v2); clone_aliases(dev_data->pdev); device_flush_dte(dev_data); @@ -2249,23 +2320,36 @@ static int amd_iommu_domain_get_attr(struct iommu_domain *domain, * *****************************************************************************/ -static void update_device_table(struct protection_domain *domain) +static void update_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) { struct iommu_dev_data *dev_data; list_for_each_entry(dev_data, &domain->dev_list, list) { - set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled, - dev_data->iommu_v2); + set_dte_entry(dev_data->devid, domain, pgtable, + dev_data->ats.enabled, dev_data->iommu_v2); clone_aliases(dev_data->pdev); } } +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + update_device_table(domain, pgtable); + domain_flush_devices(domain); +} + static void update_domain(struct protection_domain *domain) { - update_device_table(domain); + struct domain_pgtable pgtable; - domain_flush_devices(domain); + /* Update device table */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + update_and_flush_device_table(domain, &pgtable); + + /* Flush domain TLB(s) and wait for completion */ domain_flush_tlb_pde(domain); + domain_flush_complete(domain); } int __init amd_iommu_init_api(void) @@ -2375,6 +2459,7 @@ out_err: static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { struct protection_domain *pdomain; + u64 *pt_root, root; switch (type) { case IOMMU_DOMAIN_UNMANAGED: @@ -2382,13 +2467,15 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_3_LEVEL; - pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - if (!pdomain->pt_root) { + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) { protection_domain_free(pdomain); return NULL; } + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&pdomain->pt_root, root); + pdomain->domain.geometry.aperture_start = 0; pdomain->domain.geometry.aperture_end = ~0ULL; pdomain->domain.geometry.force_aperture = true; @@ -2406,7 +2493,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_NONE; + atomic64_set(&pdomain->pt_root, PAGE_MODE_NONE); break; default: return NULL; @@ -2418,6 +2505,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) static void amd_iommu_domain_free(struct iommu_domain *dom) { struct protection_domain *domain; + struct domain_pgtable pgtable; domain = to_pdomain(dom); @@ -2435,7 +2523,9 @@ static void amd_iommu_domain_free(struct iommu_domain *dom) dma_ops_domain_free(domain); break; default: - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (pgtable.mode != PAGE_MODE_NONE) free_pagetable(domain); if (domain->flags & PD_IOMMUV2_MASK) @@ -2518,10 +2608,12 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, gfp_t gfp) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; int prot = 0; int ret; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return -EINVAL; if (iommu_prot & IOMMU_READ) @@ -2541,8 +2633,10 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, struct iommu_iotlb_gather *gather) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return 0; return iommu_unmap_page(domain, iova, page_size); @@ -2553,9 +2647,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, { struct protection_domain *domain = to_pdomain(dom); unsigned long offset_mask, pte_pgsize; + struct domain_pgtable pgtable; u64 *pte, __pte; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return iova; pte = fetch_pte(domain, iova, &pte_pgsize); @@ -2708,16 +2804,26 @@ EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier); void amd_iommu_domain_direct_map(struct iommu_domain *dom) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; unsigned long flags; + u64 pt_root; spin_lock_irqsave(&domain->lock, flags); + /* First save pgtable configuration*/ + amd_iommu_domain_get_pgtable(domain, &pgtable); + /* Update data structure */ - domain->mode = PAGE_MODE_NONE; + pt_root = amd_iommu_domain_encode_pgtable(NULL, PAGE_MODE_NONE); + atomic64_set(&domain->pt_root, pt_root); /* Make changes visible to IOMMUs */ update_domain(domain); + /* Restore old pgtable in domain->ptroot to free page-table */ + pt_root = amd_iommu_domain_encode_pgtable(pgtable.root, pgtable.mode); + atomic64_set(&domain->pt_root, pt_root); + /* Page-table is not visible to IOMMU anymore, so free it */ free_pagetable(domain); @@ -2908,9 +3014,11 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc) static int __set_gcr3(struct protection_domain *domain, int pasid, unsigned long cr3) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, true); @@ -2924,9 +3032,11 @@ static int __set_gcr3(struct protection_domain *domain, int pasid, static int __clear_gcr3(struct protection_domain *domain, int pasid) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, false); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index ca8c4522045b..7a8fdec138bd 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -468,8 +468,7 @@ struct protection_domain { iommu core code */ spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ - int mode; /* paging mode (0-6 levels) */ - u64 *pt_root; /* page table root pointer */ + atomic64_t pt_root; /* pgtable root and pgtable mode */ int glx; /* Number of levels for GCR3 table */ u64 *gcr3_tbl; /* Guest CR3 table */ unsigned long flags; /* flags to find out type of domain */ @@ -477,6 +476,12 @@ struct protection_domain { unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ }; +/* For decocded pt_root */ +struct domain_pgtable { + int mode; + u64 *root; +}; + /* * Structure where we save information about one hardware AMD IOMMU in the * system. diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index d5cac4f46ca5..4e1d11af23c8 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -453,7 +453,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev, if (!region) return -ENOMEM; - list_add(&vdev->resv_regions, ®ion->list); + list_add(®ion->list, &vdev->resv_regions); return 0; } diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 668418d7ea77..f620442addf5 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1465,6 +1465,13 @@ static const struct mei_cfg mei_me_pch12_cfg = { MEI_CFG_DMA_128, }; +/* LBG with quirk for SPS Firmware exclusion */ +static const struct mei_cfg mei_me_pch12_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_FW_SPS, +}; + /* Tiger Lake and newer devices */ static const struct mei_cfg mei_me_pch15_cfg = { MEI_CFG_PCH8_HFS, @@ -1487,6 +1494,7 @@ static const struct mei_cfg *const mei_cfg_list[] = { [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, [MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg, + [MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg, [MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg, }; diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index 4a8d4dcd5a91..b6b94e211464 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -80,6 +80,9 @@ struct mei_me_hw { * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH12_CFG: Platform Controller Hub Gen12 and newer + * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 and newer + * servers platforms with quirk for + * SPS firmware exclusion. * @MEI_ME_PCH15_CFG: Platform Controller Hub Gen15 and newer * @MEI_ME_NUM_CFG: Upper Sentinel. */ @@ -93,6 +96,7 @@ enum mei_cfg_idx { MEI_ME_PCH8_CFG, MEI_ME_PCH8_SPS_CFG, MEI_ME_PCH12_CFG, + MEI_ME_PCH12_SPS_CFG, MEI_ME_PCH15_CFG, MEI_ME_NUM_CFG, }; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 0c390fe421ad..a1ed375fed37 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -70,7 +70,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8499b56a15a8..c5367e2c8487 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1370,6 +1370,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req) struct mmc_request *mrq = &mqrq->brq.mrq; struct request_queue *q = req->q; struct mmc_host *host = mq->card->host; + enum mmc_issue_type issue_type = mmc_issue_type(mq, req); unsigned long flags; bool put_card; int err; @@ -1399,7 +1400,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req) spin_lock_irqsave(&mq->lock, flags); - mq->in_flight[mmc_issue_type(mq, req)] -= 1; + mq->in_flight[issue_type] -= 1; put_card = (mmc_tot_in_flight(mq) == 0); diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 25bee3daf9e2..4b1eb89b401d 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -107,11 +107,10 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req) case MMC_ISSUE_DCMD: if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) { if (recovery_needed) - __mmc_cqe_recovery_notifier(mq); + mmc_cqe_recovery_notifier(mrq); return BLK_EH_RESET_TIMER; } - /* No timeout (XXX: huh? comment doesn't make much sense) */ - blk_mq_complete_request(req); + /* The request has gone already */ return BLK_EH_DONE; default: /* Timeout is handled by mmc core */ @@ -127,18 +126,13 @@ static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req, struct mmc_card *card = mq->card; struct mmc_host *host = card->host; unsigned long flags; - int ret; + bool ignore_tout; spin_lock_irqsave(&mq->lock, flags); - - if (mq->recovery_needed || !mq->use_cqe || host->hsq_enabled) - ret = BLK_EH_RESET_TIMER; - else - ret = mmc_cqe_timed_out(req); - + ignore_tout = mq->recovery_needed || !mq->use_cqe || host->hsq_enabled; spin_unlock_irqrestore(&mq->lock, flags); - return ret; + return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req); } static void mmc_mq_recovery_handler(struct work_struct *work) diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c index 1aee485d56d4..026ca9194ce5 100644 --- a/drivers/mmc/host/alcor.c +++ b/drivers/mmc/host/alcor.c @@ -1104,7 +1104,7 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to get irq for data line\n"); - return ret; + goto free_host; } mutex_init(&host->cmd_mutex); @@ -1116,6 +1116,10 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, host); mmc_add_host(mmc); return 0; + +free_host: + mmc_free_host(mmc); + return ret; } static int alcor_pci_sdmmc_drv_remove(struct platform_device *pdev) diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index faba53cf139b..d8b76cb8698a 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -605,10 +605,12 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev, } static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = { - .chip = &sdhci_acpi_chip_amd, - .caps = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE, - .quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | SDHCI_QUIRK_32BIT_DMA_SIZE | - SDHCI_QUIRK_32BIT_ADMA_SIZE, + .chip = &sdhci_acpi_chip_amd, + .caps = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE, + .quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | + SDHCI_QUIRK_32BIT_DMA_SIZE | + SDHCI_QUIRK_32BIT_ADMA_SIZE, + .quirks2 = SDHCI_QUIRK2_BROKEN_64_BIT_DMA, .probe_slot = sdhci_acpi_emmc_amd_probe_slot, }; diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index ce15a05f23d4..fd76aa672e02 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -26,6 +26,9 @@ #define SDHCI_GLI_9750_DRIVING_2 GENMASK(27, 26) #define GLI_9750_DRIVING_1_VALUE 0xFFF #define GLI_9750_DRIVING_2_VALUE 0x3 +#define SDHCI_GLI_9750_SEL_1 BIT(29) +#define SDHCI_GLI_9750_SEL_2 BIT(31) +#define SDHCI_GLI_9750_ALL_RST (BIT(24)|BIT(25)|BIT(28)|BIT(30)) #define SDHCI_GLI_9750_PLL 0x864 #define SDHCI_GLI_9750_PLL_TX2_INV BIT(23) @@ -122,6 +125,8 @@ static void gli_set_9750(struct sdhci_host *host) GLI_9750_DRIVING_1_VALUE); driving_value |= FIELD_PREP(SDHCI_GLI_9750_DRIVING_2, GLI_9750_DRIVING_2_VALUE); + driving_value &= ~(SDHCI_GLI_9750_SEL_1|SDHCI_GLI_9750_SEL_2|SDHCI_GLI_9750_ALL_RST); + driving_value |= SDHCI_GLI_9750_SEL_2; sdhci_writel(host, driving_value, SDHCI_GLI_9750_DRIVING); sw_ctrl_value &= ~SDHCI_GLI_9750_SW_CTRL_4; @@ -334,6 +339,18 @@ static u32 sdhci_gl9750_readl(struct sdhci_host *host, int reg) return value; } +#ifdef CONFIG_PM_SLEEP +static int sdhci_pci_gli_resume(struct sdhci_pci_chip *chip) +{ + struct sdhci_pci_slot *slot = chip->slots[0]; + + pci_free_irq_vectors(slot->chip->pdev); + gli_pcie_enable_msi(slot); + + return sdhci_pci_resume_host(chip); +} +#endif + static const struct sdhci_ops sdhci_gl9755_ops = { .set_clock = sdhci_set_clock, .enable_dma = sdhci_pci_enable_dma, @@ -348,6 +365,9 @@ const struct sdhci_pci_fixes sdhci_gl9755 = { .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50, .probe_slot = gli_probe_slot_gl9755, .ops = &sdhci_gl9755_ops, +#ifdef CONFIG_PM_SLEEP + .resume = sdhci_pci_gli_resume, +#endif }; static const struct sdhci_ops sdhci_gl9750_ops = { @@ -366,4 +386,7 @@ const struct sdhci_pci_fixes sdhci_gl9750 = { .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50, .probe_slot = gli_probe_slot_gl9750, .ops = &sdhci_gl9750_ops, +#ifdef CONFIG_PM_SLEEP + .resume = sdhci_pci_gli_resume, +#endif }; diff --git a/drivers/most/core.c b/drivers/most/core.c index 06426fc5c990..f781c46cd4af 100644 --- a/drivers/most/core.c +++ b/drivers/most/core.c @@ -1483,7 +1483,7 @@ static void __exit most_exit(void) ida_destroy(&mdev_id); } -module_init(most_init); +subsys_initcall(most_init); module_exit(most_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Christian Gromm <christian.gromm@microchip.com>"); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index cc0703c3d57f..efd1a1d1f35e 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -136,25 +136,21 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) oiph = skb_network_header(skb); skb_reset_network_header(skb); - if (family == AF_INET) + if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET) err = IP_ECN_decapsulate(oiph, skb); -#if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); -#endif if (unlikely(err)) { if (log_ecn_error) { - if (family == AF_INET) + if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); -#if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); -#endif } if (err > 1) { ++bareudp->dev->stats.rx_frame_errors; @@ -350,7 +346,6 @@ free_dst: return err; } -#if IS_ENABLED(CONFIG_IPV6) static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) @@ -411,7 +406,6 @@ free_dst: dst_release(dst); return err; } -#endif static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -435,11 +429,9 @@ static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) } rcu_read_lock(); -#if IS_ENABLED(CONFIG_IPV6) - if (info->mode & IP_TUNNEL_INFO_IPV6) + if (IS_ENABLED(CONFIG_IPV6) && info->mode & IP_TUNNEL_INFO_IPV6) err = bareudp6_xmit_skb(skb, dev, bareudp, info); else -#endif err = bareudp_xmit_skb(skb, dev, bareudp, info); rcu_read_unlock(); @@ -467,7 +459,7 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, use_cache = ip_tunnel_dst_cache_usable(skb, info); - if (ip_tunnel_info_af(info) == AF_INET) { + if (!IS_ENABLED(CONFIG_IPV6) || ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; __be32 saddr; @@ -478,7 +470,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, ip_rt_put(rt); info->key.u.ipv4.src = saddr; -#if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct in6_addr saddr; @@ -492,7 +483,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, dst_release(dst); info->key.u.ipv6.src = saddr; -#endif } else { return -EINVAL; } diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index fdcb70b9f0e4..400207c5c7de 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -360,6 +360,7 @@ static void __exit dsa_loop_exit(void) } module_exit(dsa_loop_exit); +MODULE_SOFTDEP("pre: dsa_loop_bdinfo"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Fainelli"); MODULE_DESCRIPTION("DSA loopback driver"); diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 53055ce5dfd6..2a69c0d06f3c 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -69,6 +69,7 @@ config BCMGENET select BCM7XXX_PHY select MDIO_BCM_UNIMAC select DIMLIB + select BROADCOM_PHY if ARCH_BCM2835 help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 2bd7ace0a953..bfc6bfe94d0a 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -77,6 +77,7 @@ config UCC_GETH depends on QUICC_ENGINE && PPC32 select FSL_PQ_MDIO select PHYLIB + select FIXED_PHY ---help--- This driver supports the Gigabit Ethernet mode of the QUICC Engine, which is available on some Freescale SOCs. @@ -90,6 +91,7 @@ config GIANFAR depends on HAS_DMA select FSL_PQ_MDIO select PHYLIB + select FIXED_PHY select CRC32 ---help--- This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx, diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig index 3b325733a4f8..0a54c7e0e4ae 100644 --- a/drivers/net/ethernet/freescale/dpaa/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa/Kconfig @@ -3,6 +3,7 @@ menuconfig FSL_DPAA_ETH tristate "DPAA Ethernet" depends on FSL_DPAA && FSL_FMAN select PHYLIB + select FIXED_PHY select FSL_FMAN_MAC ---help--- Data Path Acceleration Architecture Ethernet driver, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 8c8d95aa1dfd..5fbaa51b38bc 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -86,7 +86,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv, for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) { addr = dpaa2_sg_get_addr(&sgt[i]); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); free_pages((unsigned long)sg_vaddr, 0); @@ -144,7 +144,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, /* Get the address and length from the S/G entry */ sg_addr = dpaa2_sg_get_addr(sge); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr); - dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, sg_addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); sg_length = dpaa2_sg_get_len(sge); @@ -185,7 +185,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, (page_address(page) - page_address(head_page)); skb_add_rx_frag(skb, i - 1, head_page, page_offset, - sg_length, DPAA2_ETH_RX_BUF_SIZE); + sg_length, priv->rx_buf_size); } if (dpaa2_sg_is_final(sge)) @@ -211,7 +211,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count) for (i = 0; i < count; i++) { vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]); - dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, buf_array[i], priv->rx_buf_size, DMA_BIDIRECTIONAL); free_pages((unsigned long)vaddr, 0); } @@ -367,7 +367,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv, break; case XDP_REDIRECT: dma_unmap_page(priv->net_dev->dev.parent, addr, - DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL); + priv->rx_buf_size, DMA_BIDIRECTIONAL); ch->buf_count--; /* Allow redirect use of full headroom */ @@ -410,7 +410,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, trace_dpaa2_rx_fd(priv->net_dev, fd); vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); - dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); fas = dpaa2_get_fas(vaddr, false); @@ -429,13 +429,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, return; } - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = build_linear_skb(ch, fd, vaddr); } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = build_frag_skb(priv, ch, buf_data); free_pages((unsigned long)vaddr, 0); @@ -1011,7 +1011,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, if (!page) goto err_alloc; - addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE, + addr = dma_map_page(dev, page, 0, priv->rx_buf_size, DMA_BIDIRECTIONAL); if (unlikely(dma_mapping_error(dev, addr))) goto err_map; @@ -1021,7 +1021,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, /* tracing point */ trace_dpaa2_eth_buf_seed(priv->net_dev, page, DPAA2_ETH_RX_BUF_RAW_SIZE, - addr, DPAA2_ETH_RX_BUF_SIZE, + addr, priv->rx_buf_size, bpid); } @@ -1757,7 +1757,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu) int mfl, linear_mfl; mfl = DPAA2_ETH_L2_MAX_FRM(mtu); - linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE - + linear_mfl = priv->rx_buf_size - DPAA2_ETH_RX_HWA_SIZE - dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM; if (mfl > linear_mfl) { @@ -2492,6 +2492,11 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) else rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN; + /* We need to ensure that the buffer size seen by WRIOP is a multiple + * of 64 or 256 bytes depending on the WRIOP version. + */ + priv->rx_buf_size = ALIGN_DOWN(DPAA2_ETH_RX_BUF_SIZE, rx_buf_align); + /* tx buffer */ buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE; buf_layout.pass_timestamp = true; @@ -3177,7 +3182,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv) pools_params.num_dpbp = 1; pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id; pools_params.pools[0].backup_pool = 0; - pools_params.pools[0].buffer_size = DPAA2_ETH_RX_BUF_SIZE; + pools_params.pools[0].buffer_size = priv->rx_buf_size; err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params); if (err) { dev_err(dev, "dpni_set_pools() failed\n"); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index b5f7dbbc2a02..42f0a7a80afa 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -393,6 +393,7 @@ struct dpaa2_eth_priv { u16 tx_data_offset; struct fsl_mc_device *dpbp_dev; + u16 rx_buf_size; u16 bpid; struct iommu_domain *iommu_domain; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index bd13ee48d623..049afd1d6252 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -635,7 +635,7 @@ static int num_rules(struct dpaa2_eth_priv *priv) static int update_cls_rule(struct net_device *net_dev, struct ethtool_rx_flow_spec *new_fs, - int location) + unsigned int location) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpaa2_eth_cls_rule *rule; diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 3892a2062404..2fff43509098 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -64,7 +64,7 @@ config HNS_MDIO the PHY config HNS - tristate "Hisilicon Network Subsystem Support (Framework)" + tristate ---help--- This selects the framework support for Hisilicon Network Subsystem. It is needed by any driver which provides HNS acceleration engine or make diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index eef855f11a01..c33eb1147055 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -45,6 +45,8 @@ #define MGMT_MSG_TIMEOUT 5000 +#define SET_FUNC_PORT_MGMT_TIMEOUT 25000 + #define mgmt_to_pfhwdev(pf_mgmt) \ container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt) @@ -238,12 +240,13 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, u8 *buf_in, u16 in_size, u8 *buf_out, u16 *out_size, enum mgmt_direction_type direction, - u16 resp_msg_id) + u16 resp_msg_id, u32 timeout) { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; struct hinic_recv_msg *recv_msg; struct completion *recv_done; + unsigned long timeo; u16 msg_id; int err; @@ -267,8 +270,9 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, goto unlock_sync_msg; } - if (!wait_for_completion_timeout(recv_done, - msecs_to_jiffies(MGMT_MSG_TIMEOUT))) { + timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT); + + if (!wait_for_completion_timeout(recv_done, timeo)) { dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id); err = -ETIMEDOUT; goto unlock_sync_msg; @@ -342,6 +346,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; + u32 timeout = 0; if (sync != HINIC_MGMT_MSG_SYNC) { dev_err(&pdev->dev, "Invalid MGMT msg type\n"); @@ -353,13 +358,16 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, return -EINVAL; } + if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MGMT_TIMEOUT; + if (HINIC_IS_VF(hwif)) return hinic_mbox_to_pf(pf_to_mgmt->hwdev, mod, cmd, buf_in, in_size, buf_out, out_size, 0); else return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, buf_out, out_size, MGMT_DIRECT_SEND, - MSG_NOT_RESP); + MSG_NOT_RESP, timeout); } /** diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index e3ff119fe341..c8ab129a7ae8 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -488,7 +488,6 @@ int hinic_close(struct net_device *netdev) { struct hinic_dev *nic_dev = netdev_priv(netdev); unsigned int flags; - int err; down(&nic_dev->mgmt_lock); @@ -505,20 +504,9 @@ int hinic_close(struct net_device *netdev) if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) hinic_notify_all_vfs_link_changed(nic_dev->hwdev, 0); - err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, - "Failed to set func port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } + hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); - err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, "Failed to set port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } + hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); if (nic_dev->flags & HINIC_RSS_ENABLE) { hinic_rss_deinit(nic_dev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 187c633a7af5..f4227517dc8e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -497,13 +497,17 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, GFP_KERNEL); - if (!hw->irq_name) + if (!hw->irq_name) { + err = -ENOMEM; goto err_free_netdev; + } hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec, sizeof(cpumask_var_t), GFP_KERNEL); - if (!hw->affinity_mask) + if (!hw->affinity_mask) { + err = -ENOMEM; goto err_free_netdev; + } err = pci_alloc_irq_vectors(hw->pdev, num_vec, num_vec, PCI_IRQ_MSIX); if (err < 0) { diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index fccc4805247f..2c0dcd7acf3f 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1062,7 +1062,7 @@ static int encx24j600_spi_probe(struct spi_device *spi) if (unlikely(ret)) { netif_err(priv, probe, ndev, "Error %d initializing card encx24j600 card\n", ret); - goto out_free; + goto out_stop; } eidled = encx24j600_read_reg(priv, EIDLED); @@ -1080,6 +1080,8 @@ static int encx24j600_spi_probe(struct spi_device *spi) out_unregister: unregister_netdev(priv->ndev); +out_stop: + kthread_stop(priv->kworker_task); out_free: free_netdev(ndev); @@ -1092,6 +1094,7 @@ static int encx24j600_spi_remove(struct spi_device *spi) struct encx24j600_priv *priv = dev_get_drvdata(&spi->dev); unregister_netdev(priv->ndev); + kthread_stop(priv->kworker_task); free_netdev(priv->ndev); diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index 354efffac0f9..bdbf0726145e 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -333,8 +333,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) goto err_free_alink; alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL); - if (!alink->prio_map) + if (!alink->prio_map) { + err = -ENOMEM; goto err_free_alink; + } /* This is a multi-host app, make sure MAC/PHY is up, but don't * make the MAC/PHY state follow the state of any of the ports. diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 80b4d8332109..7321a92f8395 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2175,6 +2175,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) dev_info(ionic->dev, "FW Up: restarting LIFs\n"); ionic_init_devinfo(ionic); + ionic_port_init(ionic); err = ionic_qcqs_alloc(lif); if (err) goto err_out; @@ -2406,7 +2407,17 @@ static int ionic_station_set(struct ionic_lif *lif) if (is_zero_ether_addr(ctx.comp.lif_getattr.mac)) return 0; - if (!ether_addr_equal(ctx.comp.lif_getattr.mac, netdev->dev_addr)) { + if (!is_zero_ether_addr(netdev->dev_addr)) { + /* If the netdev mac is non-zero and doesn't match the default + * device address, it was set by something earlier and we're + * likely here again after a fw-upgrade reset. We need to be + * sure the netdev mac is in our filter list. + */ + if (!ether_addr_equal(ctx.comp.lif_getattr.mac, + netdev->dev_addr)) + ionic_lif_addr(lif, netdev->dev_addr, true); + } else { + /* Update the netdev mac with the device's mac */ memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); addr.sa_family = AF_INET; err = eth_prepare_mac_addr_change(netdev, &addr); @@ -2416,12 +2427,6 @@ static int ionic_station_set(struct ionic_lif *lif) return 0; } - if (!is_zero_ether_addr(netdev->dev_addr)) { - netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n", - netdev->dev_addr); - ionic_lif_addr(lif, netdev->dev_addr, false); - } - eth_commit_mac_addr_change(netdev, &addr); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 92110abcff96..df5b9bcc3aba 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -512,16 +512,16 @@ int ionic_port_init(struct ionic *ionic) size_t sz; int err; - if (idev->port_info) - return 0; - - idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); - idev->port_info = dma_alloc_coherent(ionic->dev, idev->port_info_sz, - &idev->port_info_pa, - GFP_KERNEL); if (!idev->port_info) { - dev_err(ionic->dev, "Failed to allocate port info, aborting\n"); - return -ENOMEM; + idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); + idev->port_info = dma_alloc_coherent(ionic->dev, + idev->port_info_sz, + &idev->port_info_pa, + GFP_KERNEL); + if (!idev->port_info) { + dev_err(ionic->dev, "Failed to allocate port info\n"); + return -ENOMEM; + } } sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data)); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d926583b407f..97a7e27fff16 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2048,6 +2048,8 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) { 0x7cf, 0x348, RTL_GIGA_MAC_VER_07 }, { 0x7cf, 0x248, RTL_GIGA_MAC_VER_07 }, { 0x7cf, 0x340, RTL_GIGA_MAC_VER_13 }, + /* RTL8401, reportedly works if treated as RTL8101e */ + { 0x7cf, 0x240, RTL_GIGA_MAC_VER_13 }, { 0x7cf, 0x343, RTL_GIGA_MAC_VER_10 }, { 0x7cf, 0x342, RTL_GIGA_MAC_VER_16 }, { 0x7c8, 0x348, RTL_GIGA_MAC_VER_09 }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index e0a5fe83d8e0..bfc4a92f1d92 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -75,6 +75,11 @@ struct ethqos_emac_por { unsigned int value; }; +struct ethqos_emac_driver_data { + const struct ethqos_emac_por *por; + unsigned int num_por; +}; + struct qcom_ethqos { struct platform_device *pdev; void __iomem *rgmii_base; @@ -171,6 +176,11 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = { { .offset = RGMII_IO_MACRO_CONFIG2, .value = 0x00002060 }, }; +static const struct ethqos_emac_driver_data emac_v2_3_0_data = { + .por = emac_v2_3_0_por, + .num_por = ARRAY_SIZE(emac_v2_3_0_por), +}; + static int ethqos_dll_configure(struct qcom_ethqos *ethqos) { unsigned int val; @@ -442,6 +452,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; + const struct ethqos_emac_driver_data *data; struct qcom_ethqos *ethqos; struct resource *res; int ret; @@ -471,7 +482,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev) goto err_mem; } - ethqos->por = of_device_get_match_data(&pdev->dev); + data = of_device_get_match_data(&pdev->dev); + ethqos->por = data->por; + ethqos->num_por = data->num_por; ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii"); if (IS_ERR(ethqos->rgmii_clk)) { @@ -526,7 +539,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev) } static const struct of_device_id qcom_ethqos_match[] = { - { .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por}, + { .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data}, { } }; MODULE_DEVICE_TABLE(of, qcom_ethqos_match); diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 4d4852f00ff7..182d10f171f6 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -49,6 +49,7 @@ config TI_CPSW_PHY_SEL config TI_CPSW tristate "TI CPSW Switch Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST + depends on TI_CPTS || !TI_CPTS select TI_DAVINCI_MDIO select MFD_SYSCON select PAGE_POOL @@ -64,6 +65,7 @@ config TI_CPSW_SWITCHDEV tristate "TI CPSW Switch Support with switchdev" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST depends on NET_SWITCHDEV + depends on TI_CPTS || !TI_CPTS select PAGE_POOL select TI_DAVINCI_MDIO select MFD_SYSCON @@ -77,23 +79,16 @@ config TI_CPSW_SWITCHDEV will be called cpsw_new. config TI_CPTS - bool "TI Common Platform Time Sync (CPTS) Support" - depends on TI_CPSW || TI_KEYSTONE_NETCP || TI_CPSW_SWITCHDEV || COMPILE_TEST + tristate "TI Common Platform Time Sync (CPTS) Support" + depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST depends on COMMON_CLK - depends on POSIX_TIMERS + depends on PTP_1588_CLOCK ---help--- This driver supports the Common Platform Time Sync unit of the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem. The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the driver offers a PTP Hardware Clock. -config TI_CPTS_MOD - tristate - depends on TI_CPTS - depends on PTP_1588_CLOCK - default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y || TI_CPSW_SWITCHDEV=y - default m - config TI_K3_AM65_CPSW_NUSS tristate "TI K3 AM654x/J721E CPSW Ethernet driver" depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER @@ -137,6 +132,7 @@ config TI_KEYSTONE_NETCP select TI_DAVINCI_MDIO depends on OF depends on KEYSTONE_NAVIGATOR_DMA && KEYSTONE_NAVIGATOR_QMSS + depends on TI_CPTS || !TI_CPTS ---help--- This driver supports TI's Keystone NETCP Core. diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index be95512d80b5..6e779292545d 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_TI_DAVINCI_EMAC) += ti_davinci_emac.o ti_davinci_emac-y := davinci_emac.o davinci_cpdma.o obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o -obj-$(CONFIG_TI_CPTS_MOD) += cpts.o +obj-$(CONFIG_TI_CPTS) += cpts.o obj-$(CONFIG_TI_CPSW) += ti_cpsw.o ti_cpsw-y := cpsw.o davinci_cpdma.o cpsw_ale.o cpsw_priv.o cpsw_sl.o cpsw_ethtool.o obj-$(CONFIG_TI_CPSW_SWITCHDEV) += ti_cpsw_new.o diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 206688154fdf..60dcaf2a04a9 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -146,7 +146,8 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) { struct bpqdev *bpq; - list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list) { + list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list, + lockdep_rtnl_is_held()) { if (bpq->ethdev == dev) return bpq->axdev; } diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 2fd21d75367d..bdbfeed359db 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -399,13 +399,14 @@ void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size, /* assert(which < trans->tre_count); */ /* Set the page information for the buffer. We also need to fill in - * the DMA address for the buffer (something dma_map_sg() normally - * does). + * the DMA address and length for the buffer (something dma_map_sg() + * normally does). */ sg = &trans->sgl[which]; sg_set_buf(sg, buf, size); sg_dma_address(sg) = addr; + sg_dma_len(sg) = sg->length; info = &trans->info[which]; info->opcode = opcode; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index 394f8a6df086..c9ab865e7290 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -569,23 +569,15 @@ static void ipa_cmd_transfer_add(struct gsi_trans *trans, u16 size) void ipa_cmd_tag_process_add(struct gsi_trans *trans) { - ipa_cmd_register_write_add(trans, 0, 0, 0, true); -#if 1 - /* Reference these functions to avoid a compile error */ - (void)ipa_cmd_ip_packet_init_add; - (void)ipa_cmd_ip_tag_status_add; - (void) ipa_cmd_transfer_add; -#else struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); - struct gsi_endpoint *endpoint; + struct ipa_endpoint *endpoint; endpoint = ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]; - ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id); + ipa_cmd_register_write_add(trans, 0, 0, 0, true); + ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id); ipa_cmd_ip_tag_status_add(trans, 0xcba987654321); - ipa_cmd_transfer_add(trans, 4); -#endif } /* Returns the number of commands required for the tag process */ diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index 4d33aa7ebfbb..a5f7a79a1923 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -53,7 +53,7 @@ * @clock_on: Whether IPA clock is on * @notified: Whether modem has been notified of clock state * @disabled: Whether setup ready interrupt handling is disabled - * @mutex mutex: Motex protecting ready interrupt/shutdown interlock + * @mutex: Mutex protecting ready-interrupt/shutdown interlock * @panic_notifier: Panic notifier structure */ struct ipa_smp2p { diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 9bdc924eea83..d4bbf79dab6c 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1240,9 +1240,11 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data) /* Restart autonegotiation so the new modes get sent to the * link partner. */ - ret = phy_restart_aneg(phydev); - if (ret < 0) - return ret; + if (phydev->autoneg == AUTONEG_ENABLE) { + ret = phy_restart_aneg(phydev); + if (ret < 0) + return ret; + } } return 0; diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index d760a36db28c..beedaad08255 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -490,6 +490,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) goto out; + if (skb->pkt_type != PACKET_HOST) + goto abort; + if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto abort; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 417e42c9fd03..bb8c34d746ab 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2659,7 +2659,7 @@ static struct hso_device *hso_create_bulk_serial_device( if (! (serial->out_endp = hso_get_ep(interface, USB_ENDPOINT_XFER_BULK, USB_DIR_OUT))) { - dev_err(&interface->dev, "Failed to find BULK IN ep\n"); + dev_err(&interface->dev, "Failed to find BULK OUT ep\n"); goto exit2; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 9e1b5d748586..b6951aa76295 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1252,9 +1252,11 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, break; } while (rq->vq->num_free); if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) { - u64_stats_update_begin(&rq->stats.syncp); + unsigned long flags; + + flags = u64_stats_update_begin_irqsave(&rq->stats.syncp); rq->stats.kicks++; - u64_stats_update_end(&rq->stats.syncp); + u64_stats_update_end_irqrestore(&rq->stats.syncp, flags); } return !oom; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f2adea96b04c..f3c037f5a9ba 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1110,7 +1110,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, * Don't treat an error as fatal, as we potentially already * have a NGUID or EUI-64. */ - if (status > 0) + if (status > 0 && !(status & NVME_SC_DNR)) status = 0; goto free_data; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4e79e412b276..e13c370de830 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -973,9 +973,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) { - if (++nvmeq->cq_head == nvmeq->q_depth) { + u16 tmp = nvmeq->cq_head + 1; + + if (tmp == nvmeq->q_depth) { nvmeq->cq_head = 0; nvmeq->cq_phase ^= 1; + } else { + nvmeq->cq_head = tmp; } } diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index 3708d43b7508..393011a05b48 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -816,6 +816,13 @@ static const struct of_device_id qusb2_phy_of_match_table[] = { .compatible = "qcom,msm8998-qusb2-phy", .data = &msm8998_phy_cfg, }, { + /* + * Deprecated. Only here to support legacy device + * trees that didn't include "qcom,qusb2-v2-phy" + */ + .compatible = "qcom,sdm845-qusb2-phy", + .data = &qusb2_v2_phy_cfg, + }, { .compatible = "qcom,qusb2-v2-phy", .data = &qusb2_v2_phy_cfg, }, diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c index d998e65c89c8..a52a9bf13b75 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c @@ -160,18 +160,11 @@ static int qcom_snps_hsphy_power_on(struct phy *phy) ret = regulator_bulk_enable(VREG_NUM, priv->vregs); if (ret) return ret; - ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); - if (ret) - goto err_disable_regulator; + qcom_snps_hsphy_disable_hv_interrupts(priv); qcom_snps_hsphy_exit_retention(priv); return 0; - -err_disable_regulator: - regulator_bulk_disable(VREG_NUM, priv->vregs); - - return ret; } static int qcom_snps_hsphy_power_off(struct phy *phy) @@ -180,7 +173,6 @@ static int qcom_snps_hsphy_power_off(struct phy *phy) qcom_snps_hsphy_enter_retention(priv); qcom_snps_hsphy_enable_hv_interrupts(priv); - clk_bulk_disable_unprepare(priv->num_clks, priv->clks); regulator_bulk_disable(VREG_NUM, priv->vregs); return 0; @@ -266,21 +258,39 @@ static int qcom_snps_hsphy_init(struct phy *phy) struct hsphy_priv *priv = phy_get_drvdata(phy); int ret; - ret = qcom_snps_hsphy_reset(priv); + ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); if (ret) return ret; + ret = qcom_snps_hsphy_reset(priv); + if (ret) + goto disable_clocks; + qcom_snps_hsphy_init_sequence(priv); ret = qcom_snps_hsphy_por_reset(priv); if (ret) - return ret; + goto disable_clocks; + + return 0; + +disable_clocks: + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); + return ret; +} + +static int qcom_snps_hsphy_exit(struct phy *phy) +{ + struct hsphy_priv *priv = phy_get_drvdata(phy); + + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); return 0; } static const struct phy_ops qcom_snps_hsphy_ops = { .init = qcom_snps_hsphy_init, + .exit = qcom_snps_hsphy_exit, .power_on = qcom_snps_hsphy_power_on, .power_off = qcom_snps_hsphy_power_off, .set_mode = qcom_snps_hsphy_set_mode, diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index c340505150b6..7486f6e4e613 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5754,10 +5754,6 @@ static DECLARE_DELAYED_WORK(regulator_init_complete_work, static int __init regulator_init_complete(void) { - int delay = driver_deferred_probe_timeout; - - if (delay < 0) - delay = 0; /* * Since DT doesn't provide an idiomatic mechanism for * enabling full constraints and since it's much more natural @@ -5768,17 +5764,18 @@ static int __init regulator_init_complete(void) has_full_constraints = true; /* - * If driver_deferred_probe_timeout is set, we punt - * completion for that many seconds since systems like - * distros will load many drivers from userspace so consumers - * might not always be ready yet, this is particularly an - * issue with laptops where this might bounce the display off - * then on. Ideally we'd get a notification from userspace - * when this happens but we don't so just wait a bit and hope - * we waited long enough. It'd be better if we'd only do - * this on systems that need it. + * We punt completion for an arbitrary amount of time since + * systems like distros will load many drivers from userspace + * so consumers might not always be ready yet, this is + * particularly an issue with laptops where this might bounce + * the display off then on. Ideally we'd get a notification + * from userspace when this happens but we don't so just wait + * a bit and hope we waited long enough. It'd be better if + * we'd only do this on systems that need it, and a kernel + * command line option might be useful. */ - schedule_delayed_work(®ulator_init_complete_work, delay * HZ); + schedule_delayed_work(®ulator_init_complete_work, + msecs_to_jiffies(30000)); return 0; } diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index c75112ee7b97..c7fade836d83 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -521,8 +521,10 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops, ISM_NR_DMBS); - if (!ism->smcd) + if (!ism->smcd) { + ret = -ENOMEM; goto err_resource; + } ism->smcd->priv = ism; ret = ism_dev_init(ism); diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 7da9e060b270..635f6f9cffc4 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -3640,6 +3640,11 @@ static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *tgt) struct ibmvfc_host *vhost = tgt->vhost; struct ibmvfc_event *evt; + if (!vhost->logged_in) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT); + return; + } + if (vhost->discovery_threads >= disc_threads) return; diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 7f66a7783209..59f0f1030c54 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -2320,16 +2320,12 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) static int ibmvscsi_remove(struct vio_dev *vdev) { struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev); - unsigned long flags; srp_remove_host(hostdata->host); scsi_remove_host(hostdata->host); purge_requests(hostdata, DID_ERROR); - - spin_lock_irqsave(hostdata->host->host_lock, flags); release_event_pool(&hostdata->pool, hostdata); - spin_unlock_irqrestore(hostdata->host->host_lock, flags); ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, max_events); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 97cabd7e0014..33255968f03a 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -3031,11 +3031,11 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags)) msleep(1000); - qla_nvme_delete(vha); qla24xx_disable_vp(vha); qla2x00_wait_for_sess_deletion(vha); + qla_nvme_delete(vha); vha->flags.delete_progress = 1; qlt_remove_target(ha, vha); diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 4ed90437e8c4..d6c991bd1bde 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3153,7 +3153,7 @@ qla24xx_abort_command(srb_t *sp) ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c, "Entered %s.\n", __func__); - if (vha->flags.qpairs_available && sp->qpair) + if (sp->qpair) req = sp->qpair->req; else return QLA_FUNCTION_FAILED; diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index 8e0575fcb4c8..67325fbaf760 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -925,6 +925,10 @@ do_map_region(const struct gasket_dev *gasket_dev, struct vm_area_struct *vma, gasket_get_bar_index(gasket_dev, (vma->vm_pgoff << PAGE_SHIFT) + driver_desc->legacy_mmap_address_offset); + + if (bar_index < 0) + return DO_MAP_REGION_INVALID; + phys_base = gasket_dev->bar_data[bar_index].phys_base + phys_offset; while (mapped_bytes < map_length) { /* diff --git a/drivers/staging/ks7010/TODO b/drivers/staging/ks7010/TODO index 87a6dac4890d..ab6f39175d99 100644 --- a/drivers/staging/ks7010/TODO +++ b/drivers/staging/ks7010/TODO @@ -30,5 +30,4 @@ Now the TODOs: Please send any patches to: Greg Kroah-Hartman <gregkh@linuxfoundation.org> -Wolfram Sang <wsa@the-dreams.de> Linux Driver Project Developer List <driverdev-devel@linuxdriverproject.org> diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 3d084cec136f..50c7534ba31e 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -182,6 +182,9 @@ static int usb4_switch_op(struct tb_switch *sw, u16 opcode, u8 *status) return ret; ret = tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_26, 1); + if (ret) + return ret; + if (val & ROUTER_CS_26_ONS) return -EOPNOTSUPP; diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index ed0aa5c0d9b7..5674da2b76f0 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -843,10 +843,8 @@ static int bcm_uart_probe(struct platform_device *pdev) if (IS_ERR(clk) && pdev->dev.of_node) clk = of_clk_get(pdev->dev.of_node, 0); - if (IS_ERR(clk)) { - clk_put(clk); + if (IS_ERR(clk)) return -ENODEV; - } port->iotype = UPIO_MEM; port->irq = res_irq->start; diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index ac137b6a1dc1..35e9e8faf8de 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1459,6 +1459,7 @@ static int cdns_uart_probe(struct platform_device *pdev) cdns_uart_uart_driver.nr = CDNS_UART_NR_PORTS; #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE cdns_uart_uart_driver.cons = &cdns_uart_console; + cdns_uart_console.index = id; #endif rc = uart_register_driver(&cdns_uart_uart_driver); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index e5ffed795e4c..48a8199f7845 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -365,9 +365,14 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows) return uniscr; } +static void vc_uniscr_free(struct uni_screen *uniscr) +{ + vfree(uniscr); +} + static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr) { - vfree(vc->vc_uni_screen); + vc_uniscr_free(vc->vc_uni_screen); vc->vc_uni_screen = new_uniscr; } @@ -1230,7 +1235,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, err = resize_screen(vc, new_cols, new_rows, user); if (err) { kfree(newscreen); - kfree(new_uniscr); + vc_uniscr_free(new_uniscr); return err; } diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index af648ba6544d..46105457e1ca 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -114,7 +114,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_ULPI_TX_PKT_EN_CLR_FIX, 0); - if (!IS_ERR(ci->platdata->vbus_extcon.edev)) { + if (!IS_ERR(ci->platdata->vbus_extcon.edev) || ci->role_switch) { hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_SESS_VLD_CTRL_EN, HS_PHY_SESS_VLD_CTRL_EN); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6833c918abce..b9db9812d6c5 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -217,6 +217,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) { struct usb_memory *usbm = NULL; struct usb_dev_state *ps = file->private_data; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); size_t size = vma->vm_end - vma->vm_start; void *mem; unsigned long flags; @@ -250,9 +251,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) usbm->vma_use_count = 1; INIT_LIST_HEAD(&usbm->memlist); - if (remap_pfn_range(vma, vma->vm_start, - virt_to_phys(usbm->mem) >> PAGE_SHIFT, - size, vma->vm_page_prot) < 0) { + if (dma_mmap_coherent(hcd->self.sysdev, vma, mem, dma_handle, size)) { dec_usb_memory_use_count(usbm, &usbm->vma_use_count); return -EAGAIN; } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index a48678a0c83a..6197938dcc2d 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1144,11 +1144,11 @@ void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr, if (usb_endpoint_out(epaddr)) { ep = dev->ep_out[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_out[epnum] = NULL; } else { ep = dev->ep_in[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_in[epnum] = NULL; } if (ep) { diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c index ffd984142171..d63072fee099 100644 --- a/drivers/usb/serial/garmin_gps.c +++ b/drivers/usb/serial/garmin_gps.c @@ -1138,8 +1138,8 @@ static void garmin_read_process(struct garmin_data *garmin_data_p, send it directly to the tty port */ if (garmin_data_p->flags & FLAGS_QUEUING) { pkt_add(garmin_data_p, data, data_length); - } else if (bulk_data || - getLayerId(data) == GARMIN_LAYERID_APPL) { + } else if (bulk_data || (data_length >= sizeof(u32) && + getLayerId(data) == GARMIN_LAYERID_APPL)) { spin_lock_irqsave(&garmin_data_p->lock, flags); garmin_data_p->flags |= APP_RESP_SEEN; diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 613f91add03d..ce0401d3137f 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -173,6 +173,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cc)}, /* Dell Wireless 5816e */ {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 1b23741036ee..37157ed9a881 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -28,6 +28,13 @@ * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org> */ +/* Reported-by: Julian Groß <julian.g@posteo.de> */ +UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, + "LaCie", + "2Big Quadra USB3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others? diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index f5c5e0aef66f..67c5139cfa0d 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -157,6 +157,10 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state) req.mode_data |= (state->mode - TYPEC_STATE_MODAL) << PMC_USB_ALTMODE_DP_MODE_SHIFT; + if (data->status & DP_STATUS_HPD_STATE) + req.mode_data |= PMC_USB_DP_HPD_LVL << + PMC_USB_ALTMODE_DP_MODE_SHIFT; + return pmc_usb_command(port, (void *)&req, sizeof(req)); } @@ -298,11 +302,11 @@ static int pmc_usb_register_port(struct pmc_usb *pmc, int index, struct typec_mux_desc mux_desc = { }; int ret; - ret = fwnode_property_read_u8(fwnode, "usb2-port", &port->usb2_port); + ret = fwnode_property_read_u8(fwnode, "usb2-port-number", &port->usb2_port); if (ret) return ret; - ret = fwnode_property_read_u8(fwnode, "usb3-port", &port->usb3_port); + ret = fwnode_property_read_u8(fwnode, "usb3-port-number", &port->usb3_port); if (ret) return ret; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 185db76300b3..5f3aa4d607de 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2749,7 +2749,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, ret = try_get_cap_refs(inode, need, want, 0, flags, got); /* three special error codes */ - if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN) + if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE) ret = 0; return ret; } @@ -3746,6 +3746,7 @@ retry: WARN_ON(1); tsession = NULL; target = -1; + mutex_lock(&session->s_mutex); } goto retry; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 481ac97b4d25..dcaed75de9e6 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -271,7 +271,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) &congestion_kb_fops); snprintf(name, sizeof(name), "../../bdi/%s", - dev_name(fsc->sb->s_bdi->dev)); + bdi_dev_name(fsc->sb->s_bdi)); fsc->debugfs_bdi = debugfs_create_symlink("bdi", fsc->client->debugfs_dir, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 486f91f9685b..7c63abf5bea9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3251,8 +3251,7 @@ static void handle_session(struct ceph_mds_session *session, void *end = p + msg->front.iov_len; struct ceph_mds_session_head *h; u32 op; - u64 seq; - unsigned long features = 0; + u64 seq, features = 0; int wake = 0; bool blacklisted = false; @@ -3271,9 +3270,8 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_need(&p, end, len, bad); - memcpy(&features, p, min_t(size_t, len, sizeof(features))); - p += len; + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); } mutex_lock(&mdsc->mutex); diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index de56dee60540..19507e2fdb57 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, } if (IS_ERR(in)) { - pr_warn("Can't lookup inode %llx (err: %ld)\n", - realm->ino, PTR_ERR(in)); + dout("Can't lookup inode %llx (err: %ld)\n", + realm->ino, PTR_ERR(in)); qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ } else { qri->timeout = 0; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index cf7b7e1d5bd7..cb733652ecca 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1519,6 +1519,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) spin_lock(&configfs_dirent_lock); configfs_detach_rollback(dentry); spin_unlock(&configfs_dirent_lock); + config_item_put(parent_item); return -EINTR; } frag->frag_dead = true; diff --git a/fs/coredump.c b/fs/coredump.c index 408418e6aa13..478a0d810136 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -788,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (displaced) put_files_struct(displaced); if (!dump_interrupted()) { + /* + * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would + * have this set to NULL. + */ + if (!cprm.file) { + pr_info("Core dump to |%s disabled\n", cn.corename); + goto close_fail; + } file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); file_end_write(cprm.file); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8c596641a72b..12eebcdea9c8 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1171,6 +1171,10 @@ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; + /* Fast preliminary check */ + if (epi->next != EP_UNACTIVE_PTR) + return false; + /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; @@ -1237,16 +1241,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (epi->next == EP_UNACTIVE_PTR && - chain_epi_lockless(epi)) + if (chain_epi_lockless(epi)) + ep_pm_stay_awake_rcu(epi); + } else if (!ep_is_linked(epi)) { + /* In the usual case, add event to ready list. */ + if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); - goto out_unlock; - } - - /* If this file is already in the ready list we exit soon */ - if (!ep_is_linked(epi) && - list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) { - ep_pm_stay_awake_rcu(epi); } /* @@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; u64 slack = 0; - bool waiter = false; wait_queue_entry_t wait; ktime_t expires, *to = NULL; @@ -1867,55 +1866,75 @@ fetch_events: */ ep_reset_busy_poll_napi_id(ep); - /* - * We don't have any available event to return to the caller. We need - * to sleep here, and we will be woken by ep_poll_callback() when events - * become available. - */ - if (!waiter) { - waiter = true; - init_waitqueue_entry(&wait, current); + do { + /* + * Internally init_wait() uses autoremove_wake_function(), + * thus wait entry is removed from the wait queue on each + * wakeup. Why it is important? In case of several waiters + * each new wakeup will hit the next waiter, giving it the + * chance to harvest new event. Otherwise wakeup can be + * lost. This is also good performance-wise, because on + * normal wakeup path no need to call __remove_wait_queue() + * explicitly, thus ep->lock is not taken, which halts the + * event delivery. + */ + init_wait(&wait); write_lock_irq(&ep->lock); - __add_wait_queue_exclusive(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - - for (;;) { /* - * We don't want to sleep if the ep_poll_callback() sends us - * a wakeup in between. That's why we set the task state - * to TASK_INTERRUPTIBLE before doing the checks. + * Barrierless variant, waitqueue_active() is called under + * the same lock on wakeup ep_poll_callback() side, so it + * is safe to avoid an explicit barrier. */ - set_current_state(TASK_INTERRUPTIBLE); + __set_current_state(TASK_INTERRUPTIBLE); + /* - * Always short-circuit for fatal signals to allow - * threads to make a timely exit without the chance of - * finding more events available and fetching - * repeatedly. + * Do the final check under the lock. ep_scan_ready_list() + * plays with two lists (->rdllist and ->ovflist) and there + * is always a race when both lists are empty for short + * period of time although events are pending, so lock is + * important. */ - if (fatal_signal_pending(current)) { - res = -EINTR; - break; + eavail = ep_events_available(ep); + if (!eavail) { + if (signal_pending(current)) + res = -EINTR; + else + __add_wait_queue_exclusive(&ep->wq, &wait); } + write_unlock_irq(&ep->lock); - eavail = ep_events_available(ep); - if (eavail) + if (eavail || res) break; - if (signal_pending(current)) { - res = -EINTR; - break; - } if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) { timed_out = 1; break; } - } + + /* We were woken up, thus go and try to harvest some events */ + eavail = 1; + + } while (0); __set_current_state(TASK_RUNNING); + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + send_events: + if (fatal_signal_pending(current)) { + /* + * Always short-circuit for fatal signals to allow + * threads to make a timely exit without the chance of + * finding more events available and fetching + * repeatedly. + */ + res = -EINTR; + } /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of @@ -1925,12 +1944,6 @@ send_events: !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; - if (waiter) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - return res; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 936a8ec6b48e..6306eaae378b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -528,10 +528,12 @@ lower_metapath: /* Advance in metadata tree. */ (mp->mp_list[hgt])++; - if (mp->mp_list[hgt] >= sdp->sd_inptrs) { - if (!hgt) + if (hgt) { + if (mp->mp_list[hgt] >= sdp->sd_inptrs) + goto lower_metapath; + } else { + if (mp->mp_list[hgt] >= sdp->sd_diptrs) break; - goto lower_metapath; } fill_up_metapath: @@ -876,10 +878,9 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, ret = -ENOENT; goto unlock; } else { - /* report a hole */ iomap->offset = pos; iomap->length = length; - goto do_alloc; + goto hole_found; } } iomap->length = size; @@ -933,8 +934,6 @@ unlock: return ret; do_alloc: - iomap->addr = IOMAP_NULL_ADDR; - iomap->type = IOMAP_HOLE; if (flags & IOMAP_REPORT) { if (pos >= size) ret = -ENOENT; @@ -956,6 +955,9 @@ do_alloc: if (pos < size && height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); } +hole_found: + iomap->addr = IOMAP_NULL_ADDR; + iomap->type = IOMAP_HOLE; goto out; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 29f9b6684b74..bf70e3b14938 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -613,7 +613,7 @@ __acquires(&gl->gl_lockref.lock) fs_err(sdp, "Error %d syncing glock \n", ret); gfs2_dump_glock(NULL, gl, true); } - return; + goto skip_inval; } } if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) { @@ -633,6 +633,7 @@ __acquires(&gl->gl_lockref.lock) clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); } +skip_inval: gfs2_glock_hold(gl); /* * Check for an error encountered since we called go_sync and go_inval. @@ -722,9 +723,6 @@ __acquires(&gl->gl_lockref.lock) goto out_unlock; if (nonblock) goto out_sched; - smp_mb(); - if (atomic_read(&gl->gl_revokes) != 0) - goto out_sched; set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE); gl->gl_target = gl->gl_demote_state; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 70b2d3a1e866..5acd3ce30759 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -622,7 +622,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = finish_no_open(file, NULL); } gfs2_glock_dq_uninit(ghs); - return error; + goto fail; } else if (error != -ENOENT) { goto fail_gunlock; } @@ -764,9 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = finish_open(file, dentry, gfs2_open_common); } gfs2_glock_dq_uninit(ghs); + gfs2_qa_put(ip); gfs2_glock_dq_uninit(ghs + 1); clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); gfs2_glock_put(io_gl); + gfs2_qa_put(dip); return error; fail_gunlock3: @@ -776,7 +778,6 @@ fail_gunlock2: clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); gfs2_glock_put(io_gl); fail_free_inode: - gfs2_qa_put(ip); if (ip->i_gl) { glock_clear_object(ip->i_gl, ip); gfs2_glock_put(ip->i_gl); @@ -1005,7 +1006,7 @@ out_gunlock: out_child: gfs2_glock_dq(ghs); out_parent: - gfs2_qa_put(ip); + gfs2_qa_put(dip); gfs2_holder_uninit(ghs); gfs2_holder_uninit(ghs + 1); return error; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 3a75843ae580..0644e58c6191 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -669,13 +669,13 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct buffer_head *bh = bd->bd_bh; struct gfs2_glock *gl = bd->bd_gl; + sdp->sd_log_num_revoke++; + if (atomic_inc_return(&gl->gl_revokes) == 1) + gfs2_glock_hold(gl); bh->b_private = NULL; bd->bd_blkno = bh->b_blocknr; gfs2_remove_from_ail(bd); /* drops ref on bh */ bd->bd_bh = NULL; - sdp->sd_log_num_revoke++; - if (atomic_inc_return(&gl->gl_revokes) == 1) - gfs2_glock_hold(gl); set_bit(GLF_LFLUSH, &gl->gl_flags); list_add(&bd->bd_list, &sdp->sd_log_revokes); } @@ -1131,6 +1131,10 @@ int gfs2_logd(void *data) while (!kthread_should_stop()) { + if (gfs2_withdrawn(sdp)) { + msleep_interruptible(HZ); + continue; + } /* Check for errors writing to the journal */ if (sdp->sd_log_error) { gfs2_lm(sdp, @@ -1139,6 +1143,7 @@ int gfs2_logd(void *data) "prevent further damage.\n", sdp->sd_fsname, sdp->sd_log_error); gfs2_withdraw(sdp); + continue; } did_flush = false; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 5ea96757afc4..48b54ec1c793 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -263,7 +263,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno, struct super_block *sb = sdp->sd_vfs; struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); - bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9); + bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift; bio_set_dev(bio, sb->s_bdev); bio->bi_end_io = end_io; bio->bi_private = sdp; @@ -509,7 +509,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, unsigned int bsize = sdp->sd_sb.sb_bsize, off; unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; unsigned int shift = PAGE_SHIFT - bsize_shift; - unsigned int readahead_blocks = BIO_MAX_PAGES << shift; + unsigned int max_bio_size = 2 * 1024 * 1024; struct gfs2_journal_extent *je; int sz, ret = 0; struct bio *bio = NULL; @@ -537,12 +537,17 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, off = 0; } - if (!bio || (bio_chained && !off)) { + if (!bio || (bio_chained && !off) || + bio->bi_iter.bi_size >= max_bio_size) { /* start new bio */ } else { - sz = bio_add_page(bio, page, bsize, off); - if (sz == bsize) - goto block_added; + sector_t sector = dblock << sdp->sd_fsb2bb_shift; + + if (bio_end_sector(bio) == sector) { + sz = bio_add_page(bio, page, bsize, off); + if (sz == bsize) + goto block_added; + } if (off) { unsigned int blocks = (PAGE_SIZE - off) >> bsize_shift; @@ -568,7 +573,7 @@ block_added: off += bsize; if (off == PAGE_SIZE) page = NULL; - if (blocks_submitted < blocks_read + readahead_blocks) { + if (blocks_submitted < 2 * max_bio_size >> bsize_shift) { /* Keep at least one bio in flight */ continue; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 4b72abcf83b2..9856cc2e0795 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -252,7 +252,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, int num = 0; if (unlikely(gfs2_withdrawn(sdp)) && - (!sdp->sd_jdesc || (blkno != sdp->sd_jdesc->jd_no_addr))) { + (!sdp->sd_jdesc || gl != sdp->sd_jinode_gl)) { *bhp = NULL; return -EIO; } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index cc0c4b5800be..8259fef3f986 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1051,8 +1051,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) u32 x; int error = 0; - if (capable(CAP_SYS_RESOURCE) || - sdp->sd_args.ar_quota != GFS2_QUOTA_ON) + if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; error = gfs2_quota_hold(ip, uid, gid); @@ -1125,7 +1124,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) int found; if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags)) - goto out; + return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { struct gfs2_quota_data *qd; @@ -1162,7 +1161,6 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) qd_unlock(qda[x]); } -out: gfs2_quota_unhold(ip); } @@ -1210,9 +1208,6 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, if (!test_bit(GIF_QD_LOCKED, &ip->i_flags)) return 0; - if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) - return 0; - for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; @@ -1270,7 +1265,9 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, if (ip->i_diskflags & GFS2_DIF_SYSTEM) return; - BUG_ON(ip->i_qadata->qa_ref <= 0); + if (gfs2_assert_withdraw(sdp, ip->i_qadata && + ip->i_qadata->qa_ref > 0)) + return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 7f9ca8ef40fc..21ada332d555 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -44,7 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, int ret; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ - if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + if (capable(CAP_SYS_RESOURCE) || + sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (ret) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 37fc41632aa2..956fced0a8ec 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1404,7 +1404,6 @@ out: if (ip->i_qadata) gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0); gfs2_rs_delete(ip, NULL); - gfs2_qa_put(ip); gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 9b64d40ab379..aa087a5675af 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -119,6 +119,12 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) if (!sb_rdonly(sdp->sd_vfs)) ret = gfs2_make_fs_ro(sdp); + if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */ + if (!ret) + ret = -EIO; + clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags); + goto skip_recovery; + } /* * Drop the glock for our journal so another node can recover it. */ @@ -159,10 +165,6 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) wait_on_bit(&gl->gl_flags, GLF_FREEING, TASK_UNINTERRUPTIBLE); } - if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */ - clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags); - goto skip_recovery; - } /* * Dequeue the "live" glock, but keep a reference so it's never freed. */ diff --git a/fs/io_uring.c b/fs/io_uring.c index 0b91b0631173..979d9f977409 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -680,8 +680,6 @@ struct io_op_def { unsigned needs_mm : 1; /* needs req->file assigned */ unsigned needs_file : 1; - /* needs req->file assigned IFF fd is >= 0 */ - unsigned fd_non_neg : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -784,8 +782,6 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1, }, [IORING_OP_OPENAT] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -799,8 +795,6 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_STATX] = { .needs_mm = 1, - .needs_file = 1, - .fd_non_neg = 1, .needs_fs = 1, .file_table = 1, }, @@ -837,8 +831,6 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, }, [IORING_OP_OPENAT2] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -5368,15 +5360,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr) io_steal_work(req, workptr); } -static int io_req_needs_file(struct io_kiocb *req, int fd) -{ - if (!io_op_defs[req->opcode].needs_file) - return 0; - if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg) - return 0; - return 1; -} - static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { @@ -5414,14 +5397,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, } static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, - int fd, unsigned int flags) + int fd) { bool fixed; - if (!io_req_needs_file(req, fd)) - return 0; - - fixed = (flags & IOSQE_FIXED_FILE); + fixed = (req->flags & REQ_F_FIXED_FILE) != 0; if (unlikely(!fixed && req->needs_fixed_file)) return -EBADF; @@ -5798,7 +5778,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, struct io_submit_state *state, bool async) { unsigned int sqe_flags; - int id, fd; + int id; /* * All io need record the previous position, if LINK vs DARIN, @@ -5850,8 +5830,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, IOSQE_ASYNC | IOSQE_FIXED_FILE | IOSQE_BUFFER_SELECT | IOSQE_IO_LINK); - fd = READ_ONCE(sqe->fd); - return io_req_set_file(state, req, fd, sqe_flags); + if (!io_op_defs[req->opcode].needs_file) + return 0; + + return io_req_set_file(state, req, READ_ONCE(sqe->fd)); } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, @@ -7360,11 +7342,9 @@ static int io_uring_release(struct inode *inode, struct file *file) 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; + struct io_kiocb *cancel_req = NULL, *req; + DEFINE_WAIT(wait); spin_lock_irq(&ctx->inflight_lock); list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { @@ -7404,6 +7384,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, */ if (refcount_sub_and_test(2, &cancel_req->refs)) { io_put_req(cancel_req); + finish_wait(&ctx->inflight_wait, &wait); continue; } } @@ -7411,8 +7392,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_wq_cancel_work(ctx->io_wq, &cancel_req->work); io_put_req(cancel_req); schedule(); + finish_wait(&ctx->inflight_wait, &wait); } - finish_wait(&ctx->inflight_wait, &wait); } static int io_uring_flush(struct file *file, void *data) @@ -7761,7 +7742,8 @@ err: return ret; } -static int io_uring_create(unsigned entries, struct io_uring_params *p) +static int io_uring_create(unsigned entries, struct io_uring_params *p, + struct io_uring_params __user *params) { struct user_struct *user = NULL; struct io_ring_ctx *ctx; @@ -7853,6 +7835,14 @@ 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 | IORING_FEAT_NODROP | + IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | + IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; + + if (copy_to_user(params, p, sizeof(*p))) { + ret = -EFAULT; + goto err; + } /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup @@ -7861,9 +7851,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret < 0) goto err; - p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | - IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | - IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: @@ -7879,7 +7866,6 @@ err: static long io_uring_setup(u32 entries, struct io_uring_params __user *params) { struct io_uring_params p; - long ret; int i; if (copy_from_user(&p, params, sizeof(p))) @@ -7894,14 +7880,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ)) return -EINVAL; - ret = io_uring_create(entries, &p); - if (ret < 0) - return ret; - - if (copy_to_user(params, &p, sizeof(p))) - return -EFAULT; - - return ret; + return io_uring_create(entries, &p, params); } SYSCALL_DEFINE2(io_uring_setup, u32, entries, diff --git a/fs/splice.c b/fs/splice.c index 4735defc46ee..fd0a1e7e5959 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in, loff_t offset; long ret; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + ipipe = get_pipe_info(in); opipe = get_pipe_info(out); @@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in, if (off_in || off_out) return -ESPIPE; - if (!(in->f_mode & FMODE_READ)) - return -EBADF; - - if (!(out->f_mode & FMODE_WRITE)) - return -EBADF; - /* Splicing to self would be fun, but... */ if (ipipe == opipe) return -EINVAL; @@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in, offset = out->f_pos; } - if (unlikely(!(out->f_mode & FMODE_WRITE))) - return -EBADF; - if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; @@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, error = -EBADF; in = fdget(fd_in); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - out = fdget(fd_out); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_splice(in.file, off_in, - out.file, off_out, - len, flags); - fdput(out); - } + out = fdget(fd_out); + if (out.file) { + error = do_splice(in.file, off_in, out.file, off_out, + len, flags); + fdput(out); } fdput(in); } @@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len, struct pipe_inode_info *opipe = get_pipe_info(out); int ret = -EINVAL; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + /* * Duplicate the contents of ipipe to opipe without actually * copying the data. @@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len, SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { - struct fd in; + struct fd in, out; int error; if (unlikely(flags & ~SPLICE_F_ALL)) @@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) error = -EBADF; in = fdget(fdin); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - struct fd out = fdget(fdout); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_tee(in.file, out.file, - len, flags); - fdput(out); - } + out = fdget(fdout); + if (out.file) { + error = do_tee(in.file, out.file, len, flags); + fdput(out); } fdput(in); } diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 675e26989376..8fe03b4a0d2b 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -164,7 +164,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) goto fail_free; } - err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id); + err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id); if (err) goto fail_free; diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index 99134d4f35eb..320f8112a0f8 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -48,7 +48,7 @@ struct videomode; * @MODE_HSYNC: hsync out of range * @MODE_VSYNC: vsync out of range * @MODE_H_ILLEGAL: mode has illegal horizontal timings - * @MODE_V_ILLEGAL: mode has illegal horizontal timings + * @MODE_V_ILLEGAL: mode has illegal vertical timings * @MODE_BAD_WIDTH: requires an unsupported linepitch * @MODE_NOMODE: no mode with a matching name * @MODE_NO_INTERLACE: interlaced mode not supported diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 26f0ecf401ea..0bbfd647f5c6 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -65,6 +65,7 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; + struct device_dma_parameters dma_parms; unsigned int periphid; unsigned int cid; struct amba_cs_uci_id uci; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ee577a83cfe6..7367150f962a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -219,6 +219,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f88197c1ffc2..c9ad5c3b7b4b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -505,13 +505,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << WB_async_congested)); } -extern const char *bdi_unknown_name; - -static inline const char *bdi_dev_name(struct backing_dev_info *bdi) -{ - if (!bdi || !bdi->dev) - return bdi_unknown_name; - return dev_name(bdi->dev); -} +const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ddfc377de0d2..dfbbf7a7208b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -210,6 +210,29 @@ struct ftrace_ops { #endif }; +extern struct ftrace_ops __rcu *ftrace_ops_list; +extern struct ftrace_ops ftrace_list_end; + +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw_check() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw_check() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw_check(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + /* * Type of the current tracing. */ diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 62d216ff1097..c230b4e70d75 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -17,9 +17,12 @@ enum host1x_class { HOST1X_CLASS_GR3D = 0x60, }; +struct host1x; struct host1x_client; struct iommu_group; +u64 host1x_get_dma_mask(struct host1x *host1x); + /** * struct host1x_client_ops - host1x client operations * @init: host1x client initialization code diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..5616b2567aa7 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -55,7 +55,7 @@ LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) -LSM_HOOK(int, 0, fs_context_parse_param, struct fs_context *fc, +LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) @@ -243,7 +243,7 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) -LSM_HOOK(int, 0, secid_to_secctx, u32 secid, char **secdata, +LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, u32 *seclen) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d275c72c4f8e..977edd3b7bd8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -783,6 +783,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && diff --git a/include/linux/mhi.h b/include/linux/mhi.h index ad1996001965..3d7c3c26eeb9 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -53,9 +53,9 @@ enum mhi_callback { * @MHI_CHAIN: Linked transfer */ enum mhi_flags { - MHI_EOB, - MHI_EOT, - MHI_CHAIN, + MHI_EOB = BIT(0), + MHI_EOT = BIT(1), + MHI_CHAIN = BIT(2), }; /** @@ -335,14 +335,15 @@ struct mhi_controller_config { * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) - * @link_status: CB function to query link status of the device (required) * @wake_get: CB function to assert device wake (optional) * @wake_put: CB function to de-assert device wake (optional) * @wake_toggle: CB function to assert and de-assert device wake (optional) * @runtime_get: CB function to controller runtime resume (required) - * @runtimet_put: CB function to decrement pm usage (required) + * @runtime_put: CB function to decrement pm usage (required) * @map_single: CB function to create TRE buffer * @unmap_single: CB function to destroy TRE buffer + * @read_reg: Read a MHI register via the physical link (required) + * @write_reg: Write a MHI register via the physical link (required) * @buffer_len: Bounce buffer length * @bounce_buf: Use of bounce buffer * @fbc_download: MHI host needs to do complete image transfer (optional) @@ -417,7 +418,6 @@ struct mhi_controller { void (*status_cb)(struct mhi_controller *mhi_cntrl, enum mhi_callback cb); - int (*link_status)(struct mhi_controller *mhi_cntrl); void (*wake_get)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_put)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_toggle)(struct mhi_controller *mhi_cntrl); @@ -427,6 +427,10 @@ struct mhi_controller { struct mhi_buf_info *buf); void (*unmap_single)(struct mhi_controller *mhi_cntrl, struct mhi_buf_info *buf); + int (*read_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 *out); + void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 val); size_t buffer_len; bool bounce_buf; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index bdc35753ef7c..77a2aada106d 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -25,6 +25,7 @@ struct platform_device { bool id_auto; struct device dev; u64 platform_dma_mask; + struct device_dma_parameters dma_parms; u32 num_resources; struct resource *resource; diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 31144d954d89..d3e8ba5c7125 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -108,10 +108,10 @@ struct ptp_system_timestamp { * parameter func: the desired function to use. * parameter chan: the function channel index to use. * - * @do_work: Request driver to perform auxiliary (periodic) operations - * Driver should return delay of the next auxiliary work scheduling - * time (>=0) or negative value in case further scheduling - * is not required. + * @do_aux_work: Request driver to perform auxiliary (periodic) operations + * Driver should return delay of the next auxiliary work + * scheduling time (>=0) or negative value in case further + * scheduling is not required. * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 8a709f63c5e5..ad31c9fb7158 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -187,6 +187,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; + src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 48c1b1674cbf..bc07e51f20d1 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -21,6 +21,7 @@ struct gss_ctx { struct gss_api_mech *mech_type; void *internal_ctx_id; + unsigned int slack, align; }; #define GSS_C_NO_BUFFER ((struct xdr_netobj) 0) @@ -66,6 +67,7 @@ u32 gss_wrap( u32 gss_unwrap( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *inbuf); u32 gss_delete_sec_context( struct gss_ctx **ctx_id); @@ -126,6 +128,7 @@ struct gss_api_ops { u32 (*gss_unwrap)( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf); void (*gss_delete_sec_context)( void *internal_ctx_id); diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index c1d77dd8ed41..e8f8ffe7448b 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -83,7 +83,7 @@ struct gss_krb5_enctype { u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages); /* v2 encryption function */ - u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, + u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *headskip, u32 *tailskip); /* v2 decryption function */ }; @@ -255,7 +255,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset, struct xdr_buf *outbuf, struct page **pages); u32 -gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, +gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len, struct xdr_buf *buf); @@ -312,7 +312,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct page **pages); u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *plainoffset, u32 *plainlen); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 01bb41908c93..22c207b2425f 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -184,6 +184,7 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); +extern void xdr_buf_trim(struct xdr_buf *, unsigned int); extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 9f551f3b69c6..90690e37a56f 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -87,7 +87,7 @@ struct nf_conn { struct hlist_node nat_bysource; #endif /* all members below initialized via memset */ - u8 __nfct_init_offset[0]; + struct { } __nfct_init_offset; /* If we were expected by an expectation, this will be it */ struct nf_conn *master; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 6bf69652f57d..c54a7f707e50 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -127,6 +127,7 @@ enum nf_flow_flags { NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, NF_FLOW_HW_REFRESH, + NF_FLOW_HW_PENDING, }; enum flow_offload_type { diff --git a/include/net/tcp.h b/include/net/tcp.h index 43b87a8d4790..b681338a8320 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1372,7 +1372,6 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) rx_opt->num_sacks = 0; } -u32 tcp_default_init_rwnd(u32 mss); void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) @@ -1417,6 +1416,19 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +/* We provision sk_rcvbuf around 200% of sk_rcvlowat. + * If 87.5 % (7/8) of the space has been consumed, we want to override + * SO_RCVLOWAT constraint, since we are receiving skbs with too small + * len/truesize ratio. + */ +static inline bool tcp_rmem_pressure(const struct sock *sk) +{ + int rcvbuf = READ_ONCE(sk->sk_rcvbuf); + int threshold = rcvbuf - (rcvbuf >> 3); + + return atomic_read(&sk->sk_rmem_alloc) > threshold; +} + extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 4b1f95e08307..e7312ceb2794 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -143,14 +143,12 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); -#if IS_ENABLED(CONFIG_IPV6) int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); -#endif void udp_tunnel_sock_release(struct socket *sock); diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index a36b7227a15a..334842daa904 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -61,6 +61,7 @@ struct snd_rawmidi_runtime { size_t avail_min; /* min avail for wakeup */ size_t avail; /* max used buffer for wakeup */ size_t xruns; /* over/underruns counter */ + int buffer_ref; /* buffer reference count */ /* misc */ spinlock_t lock; wait_queue_head_t sleep; diff --git a/include/trace/events/gpu_mem.h b/include/trace/events/gpu_mem.h index 1897822a9150..26d871f96e94 100644 --- a/include/trace/events/gpu_mem.h +++ b/include/trace/events/gpu_mem.h @@ -24,7 +24,7 @@ * * @pid: Put 0 for global total, while positive pid for process total. * - * @size: Virtual size of the allocation in bytes. + * @size: Size of the allocation in bytes. * */ TRACE_EVENT(gpu_mem_total, diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index 784814160197..9c66e59d859c 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -33,7 +33,7 @@ TRACE_EVENT(wbt_stat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->rmean = stat[0].mean; __entry->rmin = stat[0].min; @@ -68,7 +68,7 @@ TRACE_EVENT(wbt_lat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->lat = div_u64(lat, 1000); ), @@ -105,7 +105,7 @@ TRACE_EVENT(wbt_step, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->msg = msg; __entry->step = step; @@ -141,7 +141,7 @@ TRACE_EVENT(wbt_timer, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->status = status; __entry->step = step; diff --git a/init/Kconfig b/init/Kconfig index 9e22ee8fbd75..74a5ac65644f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -39,22 +39,6 @@ config TOOLS_SUPPORT_RELR config CC_HAS_ASM_INLINE def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null) -config CC_HAS_WARN_MAYBE_UNINITIALIZED - def_bool $(cc-option,-Wmaybe-uninitialized) - help - GCC >= 4.7 supports this option. - -config CC_DISABLE_WARN_MAYBE_UNINITIALIZED - bool - depends on CC_HAS_WARN_MAYBE_UNINITIALIZED - default CC_IS_GCC && GCC_VERSION < 40900 # unreliable for GCC < 4.9 - help - GCC's -Wmaybe-uninitialized is not reliable by definition. - Lots of false positive warnings are produced in some cases. - - If this option is enabled, -Wno-maybe-uninitialzed is passed - to the compiler to suppress maybe-uninitialized warnings. - config CONSTRUCTORS bool depends on !UML @@ -1257,14 +1241,12 @@ config CC_OPTIMIZE_FOR_PERFORMANCE config CC_OPTIMIZE_FOR_PERFORMANCE_O3 bool "Optimize more for performance (-O3)" depends on ARC - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-O3" to your compiler to optimize the kernel yet more for performance. config CC_OPTIMIZE_FOR_SIZE bool "Optimize for size (-Os)" - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-Os" to your compiler resulting in a smaller kernel. @@ -2279,6 +2261,9 @@ config ASN1 source "kernel/Kconfig.locks" +config ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + bool + config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE bool diff --git a/init/initramfs.c b/init/initramfs.c index 8ec1be4d7d51..7a38012e1af7 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -542,7 +542,7 @@ void __weak free_initrd_mem(unsigned long start, unsigned long end) } #ifdef CONFIG_KEXEC_CORE -static bool kexec_free_initrd(void) +static bool __init kexec_free_initrd(void) { unsigned long crashk_start = (unsigned long)__va(crashk_res.start); unsigned long crashk_end = (unsigned long)__va(crashk_res.end); diff --git a/init/main.c b/init/main.c index a48617f2e5e5..5803ecb411ab 100644 --- a/init/main.c +++ b/init/main.c @@ -257,6 +257,47 @@ static int __init loglevel(char *str) early_param("loglevel", loglevel); +#ifdef CONFIG_BLK_DEV_INITRD +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + u32 size, csum; + char *data; + u32 *hdr; + + if (!initrd_end) + return NULL; + + data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; + if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + return NULL; + + hdr = (u32 *)(data - 8); + size = hdr[0]; + csum = hdr[1]; + + data = ((void *)hdr) - size; + if ((unsigned long)data < initrd_start) { + pr_err("bootconfig size %d is greater than initrd size %ld\n", + size, initrd_end - initrd_start); + return NULL; + } + + /* Remove bootconfig from initramfs/initrd */ + initrd_end = (unsigned long)data; + if (_size) + *_size = size; + if (_csum) + *_csum = csum; + + return data; +} +#else +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + return NULL; +} +#endif + #ifdef CONFIG_BOOT_CONFIG char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; @@ -357,9 +398,11 @@ static void __init setup_boot_config(const char *cmdline) int pos; u32 size, csum; char *data, *copy; - u32 *hdr; int ret; + /* Cut out the bootconfig data even if we have no bootconfig option */ + data = get_boot_config_from_initrd(&size, &csum); + strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL, bootconfig_params); @@ -367,16 +410,10 @@ static void __init setup_boot_config(const char *cmdline) if (!bootconfig_found) return; - if (!initrd_end) - goto not_found; - - data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; - if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) - goto not_found; - - hdr = (u32 *)(data - 8); - size = hdr[0]; - csum = hdr[1]; + if (!data) { + pr_err("'bootconfig' found on command line, but no bootconfig found\n"); + return; + } if (size >= XBC_DATA_MAX) { pr_err("bootconfig size %d greater than max size %d\n", @@ -384,10 +421,6 @@ static void __init setup_boot_config(const char *cmdline) return; } - data = ((void *)hdr) - size; - if ((unsigned long)data < initrd_start) - goto not_found; - if (boot_config_checksum((unsigned char *)data, size) != csum) { pr_err("bootconfig checksum failed\n"); return; @@ -417,11 +450,15 @@ static void __init setup_boot_config(const char *cmdline) extra_init_args = xbc_make_cmdline("init"); } return; -not_found: - pr_err("'bootconfig' found on command line, but no bootconfig found\n"); } + #else -#define setup_boot_config(cmdline) do { } while (0) + +static void __init setup_boot_config(const char *cmdline) +{ + /* Remove bootconfig data from initrd */ + get_boot_config_from_initrd(NULL, NULL); +} static int __init warn_bootconfig(char *str) { diff --git a/ipc/mqueue.c b/ipc/mqueue.c index dc8307bf2d74..beff0cfcd1e8 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -142,6 +142,7 @@ struct mqueue_inode_info { struct sigevent notify; struct pid *notify_owner; + u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct user_struct *user; /* user who created, for accounting */ struct sock *notify_sock; @@ -773,28 +774,44 @@ static void __do_notify(struct mqueue_inode_info *info) * synchronously. */ if (info->notify_owner && info->attr.mq_curmsgs == 1) { - struct kernel_siginfo sig_i; switch (info->notify.sigev_notify) { case SIGEV_NONE: break; - case SIGEV_SIGNAL: - /* sends signal */ + case SIGEV_SIGNAL: { + struct kernel_siginfo sig_i; + struct task_struct *task; + + /* do_mq_notify() accepts sigev_signo == 0, why?? */ + if (!info->notify.sigev_signo) + break; clear_siginfo(&sig_i); sig_i.si_signo = info->notify.sigev_signo; sig_i.si_errno = 0; sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; - /* map current pid/uid into info->owner's namespaces */ rcu_read_lock(); + /* map current pid/uid into info->owner's namespaces */ sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); - sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid()); + sig_i.si_uid = from_kuid_munged(info->notify_user_ns, + current_uid()); + /* + * We can't use kill_pid_info(), this signal should + * bypass check_kill_permission(). It is from kernel + * but si_fromuser() can't know this. + * We do check the self_exec_id, to avoid sending + * signals to programs that don't expect them. + */ + task = pid_task(info->notify_owner, PIDTYPE_TGID); + if (task && task->self_exec_id == + info->notify_self_exec_id) { + do_send_sig_info(info->notify.sigev_signo, + &sig_i, task, PIDTYPE_TGID); + } rcu_read_unlock(); - - kill_pid_info(info->notify.sigev_signo, - &sig_i, info->notify_owner); break; + } case SIGEV_THREAD: set_cookie(info->notify_cookie, NOTIFY_WOKENUP); netlink_sendskb(info->notify_sock, info->notify_cookie); @@ -1383,6 +1400,7 @@ retry: info->notify.sigev_signo = notification->sigev_signo; info->notify.sigev_value = notification->sigev_value; info->notify.sigev_notify = SIGEV_SIGNAL; + info->notify_self_exec_id = current->self_exec_id; break; } diff --git a/ipc/util.c b/ipc/util.c index 7acccfded7cb..cfa0045e748d 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -764,21 +764,21 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, total++; } - *new_pos = pos + 1; + ipc = NULL; if (total >= ids->in_use) - return NULL; + goto out; for (; pos < ipc_mni; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { rcu_read_lock(); ipc_lock_object(ipc); - return ipc; + break; } } - - /* Out of range - return NULL to terminate iteration */ - return NULL; +out: + *new_pos = pos + 1; + return ipc; } static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 1d5bb0d983b2..11584618e861 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -486,7 +486,12 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) if (!(map->map_flags & BPF_F_MMAPABLE)) return -EINVAL; - return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff); + if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > + PAGE_ALIGN((u64)array->map.max_entries * array->elem_size)) + return -EINVAL; + + return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), + vma->vm_pgoff + pgoff); } const struct bpf_map_ops array_map_ops = { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 79bcd8d056d2..57dfc98289d5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1489,8 +1489,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (err) goto free_value; - if (copy_to_user(uvalue, value, value_size) != 0) + if (copy_to_user(uvalue, value, value_size) != 0) { + err = -EFAULT; goto free_value; + } err = 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 180933f6fba9..25b14ee0e26d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4389,7 +4389,9 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, if (ret_type != RET_INTEGER || (func_id != BPF_FUNC_get_stack && - func_id != BPF_FUNC_probe_read_str)) + func_id != BPF_FUNC_probe_read_str && + func_id != BPF_FUNC_probe_read_kernel_str && + func_id != BPF_FUNC_probe_read_user_str)) return; ret_reg->smax_value = meta->msize_max_value; @@ -7113,9 +7115,23 @@ static int check_return_code(struct bpf_verifier_env *env) range = tnum_const(0); break; case BPF_PROG_TYPE_TRACING: - if (env->prog->expected_attach_type != BPF_TRACE_ITER) + switch (env->prog->expected_attach_type) { + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + range = tnum_const(0); + break; + case BPF_TRACE_ITER: + case BPF_TRACE_RAW_TP: + case BPF_MODIFY_RETURN: return 0; + default: + return -ENOTSUPP; + } break; + case BPF_PROG_TYPE_EXT: + /* freplace program can return anything as its return value + * depends on the to-be-replaced kernel func or bpf program. + */ default: return 0; } diff --git a/kernel/fork.c b/kernel/fork.c index 8c700f881d92..48ed22774efa 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2486,11 +2486,11 @@ long do_fork(unsigned long clone_flags, int __user *child_tidptr) { struct kernel_clone_args args = { - .flags = (clone_flags & ~CSIGNAL), + .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, - .exit_signal = (clone_flags & CSIGNAL), + .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = stack_start, .stack_size = stack_size, }; @@ -2508,8 +2508,9 @@ long do_fork(unsigned long clone_flags, pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { - .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), - .exit_signal = (flags & CSIGNAL), + .flags = ((lower_32_bits(flags) | CLONE_VM | + CLONE_UNTRACED) & ~CSIGNAL), + .exit_signal = (lower_32_bits(flags) & CSIGNAL), .stack = (unsigned long)fn, .stack_size = (unsigned long)arg, }; @@ -2570,11 +2571,11 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #endif { struct kernel_clone_args args = { - .flags = (clone_flags & ~CSIGNAL), + .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, - .exit_signal = (clone_flags & CSIGNAL), + .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; diff --git a/kernel/kcov.c b/kernel/kcov.c index f50354202dbe..8accc9722a81 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -740,8 +740,8 @@ static const struct file_operations kcov_fops = { * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an * arbitrary 4-byte non-zero number as the instance id). This common handle * then gets saved into the task_struct of the process that issued the - * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn - * kernel threads, the common handle must be retrived via kcov_common_handle() + * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn + * kernel threads, the common handle must be retrieved via kcov_common_handle() * and passed to the spawned threads via custom annotations. Those kernel * threads must in turn be annotated with kcov_remote_start(common_handle) and * kcov_remote_stop(). All of the threads that are spawned by the same process diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 402eef84c859..743647005f64 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -466,7 +466,6 @@ config PROFILE_ANNOTATED_BRANCHES config PROFILE_ALL_BRANCHES bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help This tracer profiles all branch conditions. Every if () taken in the kernel is recorded whether it hit or miss. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9a84d7fb4869..9531f54d0a3a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -326,17 +326,15 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) /* * Only limited trace_printk() conversion specifiers allowed: - * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s + * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s */ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { + int i, mod[3] = {}, fmt_cnt = 0; + char buf[64], fmt_ptype; + void *unsafe_ptr = NULL; bool str_seen = false; - int mod[3] = {}; - int fmt_cnt = 0; - u64 unsafe_addr; - char buf[64]; - int i; /* * bpf_check()->check_func_arg()->check_stack_boundary() @@ -362,40 +360,71 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; - } else if (fmt[i] == 'p' || fmt[i] == 's') { + } else if (fmt[i] == 'p') { mod[fmt_cnt]++; + if ((fmt[i + 1] == 'k' || + fmt[i + 1] == 'u') && + fmt[i + 2] == 's') { + fmt_ptype = fmt[i + 1]; + i += 2; + goto fmt_str; + } + /* disallow any further format extensions */ if (fmt[i + 1] != 0 && !isspace(fmt[i + 1]) && !ispunct(fmt[i + 1])) return -EINVAL; - fmt_cnt++; - if (fmt[i] == 's') { - if (str_seen) - /* allow only one '%s' per fmt string */ - return -EINVAL; - str_seen = true; - - switch (fmt_cnt) { - case 1: - unsafe_addr = arg1; - arg1 = (long) buf; - break; - case 2: - unsafe_addr = arg2; - arg2 = (long) buf; - break; - case 3: - unsafe_addr = arg3; - arg3 = (long) buf; - break; - } - buf[0] = 0; - strncpy_from_unsafe(buf, - (void *) (long) unsafe_addr, + + goto fmt_next; + } else if (fmt[i] == 's') { + mod[fmt_cnt]++; + fmt_ptype = fmt[i]; +fmt_str: + if (str_seen) + /* allow only one '%s' per fmt string */ + return -EINVAL; + str_seen = true; + + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) + return -EINVAL; + + switch (fmt_cnt) { + case 0: + unsafe_ptr = (void *)(long)arg1; + arg1 = (long)buf; + break; + case 1: + unsafe_ptr = (void *)(long)arg2; + arg2 = (long)buf; + break; + case 2: + unsafe_ptr = (void *)(long)arg3; + arg3 = (long)buf; + break; + } + + buf[0] = 0; + switch (fmt_ptype) { + case 's': +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + strncpy_from_unsafe(buf, unsafe_ptr, sizeof(buf)); + break; +#endif + case 'k': + strncpy_from_unsafe_strict(buf, unsafe_ptr, + sizeof(buf)); + break; + case 'u': + strncpy_from_unsafe_user(buf, + (__force void __user *)unsafe_ptr, + sizeof(buf)); + break; } - continue; + goto fmt_next; } if (fmt[i] == 'l') { @@ -406,6 +435,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') return -EINVAL; +fmt_next: fmt_cnt++; } @@ -1036,14 +1066,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: return &bpf_probe_read_kernel_proto; - case BPF_FUNC_probe_read: - return &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: return &bpf_probe_read_kernel_str_proto; +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + case BPF_FUNC_probe_read: + return &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_compat_str_proto; +#endif #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h index 0456e0a3dab1..382775edf690 100644 --- a/kernel/trace/ftrace_internal.h +++ b/kernel/trace/ftrace_internal.h @@ -4,28 +4,6 @@ #ifdef CONFIG_FUNCTION_TRACER -/* - * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw_check() is that elements removed from this list - * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw_check() calls are needed to handle - * concurrent insertions into the ftrace_global_list. - * - * Silly Alpha and silly pointer-speculation compiler optimizations! - */ -#define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw_check(list); \ - do - -/* - * Optimized for just a single item in the list (as that is the normal case). - */ -#define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw_check((op)->next)) && \ - unlikely((op) != &ftrace_list_end)) - -extern struct ftrace_ops __rcu *ftrace_ops_list; -extern struct ftrace_ops ftrace_list_end; extern struct mutex ftrace_lock; extern struct ftrace_ops global_ops; diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index 31c0fad4cb9e..312d1a0ca3b6 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -16,6 +16,7 @@ #include <linux/printk.h> #include <linux/string.h> #include <linux/sysfs.h> +#include <linux/completion.h> static ulong delay = 100; static char test_mode[12] = "irq"; @@ -28,6 +29,8 @@ MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)"); MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)"); MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)"); +static struct completion done; + #define MIN(x, y) ((x) < (y) ? (x) : (y)) static void busy_wait(ulong time) @@ -113,22 +116,47 @@ static int preemptirq_delay_run(void *data) for (i = 0; i < s; i++) (testfuncs[i])(i); + + complete(&done); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + + __set_current_state(TASK_RUNNING); + return 0; } -static struct task_struct *preemptirq_start_test(void) +static int preemptirq_run_test(void) { + struct task_struct *task; char task_name[50]; + init_completion(&done); + snprintf(task_name, sizeof(task_name), "%s_test", test_mode); - return kthread_run(preemptirq_delay_run, NULL, task_name); + task = kthread_run(preemptirq_delay_run, NULL, task_name); + if (IS_ERR(task)) + return PTR_ERR(task); + if (task) { + wait_for_completion(&done); + kthread_stop(task); + } + return 0; } static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - preemptirq_start_test(); + ssize_t ret; + + ret = preemptirq_run_test(); + if (ret) + return ret; return count; } @@ -148,11 +176,9 @@ static struct kobject *preemptirq_delay_kobj; static int __init preemptirq_delay_init(void) { - struct task_struct *test_task; int retval; - test_task = preemptirq_start_test(); - retval = PTR_ERR_OR_ZERO(test_task); + retval = preemptirq_run_test(); if (retval != 0) return retval; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6f0b42ceeb00..b8e1ca48be50 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -193,7 +193,7 @@ rb_event_length(struct ring_buffer_event *event) case RINGBUF_TYPE_DATA: return rb_event_data_length(event); default: - BUG(); + WARN_ON_ONCE(1); } /* not hit */ return 0; @@ -249,7 +249,7 @@ rb_event_data(struct ring_buffer_event *event) { if (extended_time(event)) event = skip_time_extend(event); - BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); + WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); /* If length is in len field, then array[0] has the data */ if (event->type_len) return (void *)&event->array[0]; @@ -3727,7 +3727,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, return; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return; } @@ -3757,7 +3757,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter, return; default: - BUG(); + RB_WARN_ON(iter->cpu_buffer, 1); } return; } @@ -4020,7 +4020,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, return event; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return NULL; @@ -4034,7 +4034,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int nr_loops = 0; - bool failed = false; if (ts) *ts = 0; @@ -4056,19 +4055,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return NULL; /* - * We repeat when a time extend is encountered or we hit - * the end of the page. Since the time extend is always attached - * to a data event, we should never loop more than three times. - * Once for going to next page, once on time extend, and - * finally once to get the event. - * We should never hit the following condition more than thrice, - * unless the buffer is very small, and there's a writer - * that is causing the reader to fail getting an event. + * As the writer can mess with what the iterator is trying + * to read, just give up if we fail to get an event after + * three tries. The iterator is not as reliable when reading + * the ring buffer with an active write as the consumer is. + * Do not warn if the three failures is reached. */ - if (++nr_loops > 3) { - RB_WARN_ON(cpu_buffer, !failed); + if (++nr_loops > 3) return NULL; - } if (rb_per_cpu_empty(cpu_buffer)) return NULL; @@ -4079,10 +4073,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } event = rb_iter_head_event(iter); - if (!event) { - failed = true; + if (!event) goto again; - } switch (event->type_len) { case RINGBUF_TYPE_PADDING: @@ -4117,7 +4109,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return event; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return NULL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 167a74a15b1a..db0ad96dfd50 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) +static void tracing_snapshot_instance_cond(struct trace_array *tr, + void *cond_data) { struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -8525,6 +8526,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) */ allocate_snapshot = false; #endif + + /* + * Because of some magic with the way alloc_percpu() works on + * x86_64, we need to synchronize the pgd of all the tables, + * otherwise the trace events that happen in x86_64 page fault + * handlers can't cope with accessing the chance that a + * alloc_percpu()'d memory might be touched in the page fault trace + * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() + * calls in tracing, because something might get triggered within a + * page fault trace event! + */ + vmalloc_sync_mappings(); + return 0; } diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 06d7feb5255f..9de29bb45a27 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -95,24 +95,20 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) struct xbc_node *anode; char buf[MAX_BUF_LEN]; const char *val; - int ret; + int ret = 0; - kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); + xbc_node_for_each_array_value(node, "probes", anode, val) { + kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); - ret = kprobe_event_gen_cmd_start(&cmd, event, NULL); - if (ret) - return ret; + ret = kprobe_event_gen_cmd_start(&cmd, event, val); + if (ret) + break; - xbc_node_for_each_array_value(node, "probes", anode, val) { - ret = kprobe_event_add_field(&cmd, val); + ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - return ret; + pr_err("Failed to add probe: %s\n", buf); } - ret = kprobe_event_gen_cmd_end(&cmd); - if (ret) - pr_err("Failed to add probe: %s\n", buf); - return ret; } #else diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d0568af4a0ef..35989383ae11 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr) static bool within_notrace_func(struct trace_kprobe *tk) { - unsigned long addr = addr = trace_kprobe_address(tk); + unsigned long addr = trace_kprobe_address(tk); char symname[KSYM_NAME_LEN], *p; if (!__within_notrace_func(addr)) @@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init); * complete command or only the first part of it; in the latter case, * kprobe_event_add_fields() can be used to add more fields following this. * + * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This + * returns -EINVAL if @loc == NULL. + * * Return: 0 if successful, error otherwise. */ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, @@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, if (cmd->type != DYNEVENT_TYPE_KPROBE) return -EINVAL; + if (!loc) + return -EINVAL; + if (kretprobe) snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name); else diff --git a/kernel/umh.c b/kernel/umh.c index 9788ed481a6a..79f139a7ca03 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info) { struct umh_info *umh_info = info->data; + /* cleanup if umh_pipe_setup() was successful but exec failed */ + if (info->pid && info->retval) { + fput(umh_info->pipe_to_umh); + fput(umh_info->pipe_from_umh); + } + argv_free(info->argv); umh_info->pid = info->pid; } @@ -544,6 +550,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob); * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). + * + * Note: successful return value does not guarantee the helper was called at + * all. You can't rely on sub_info->{init,cleanup} being called even for + * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers + * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 48469c95d78e..929211039bac 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -60,18 +60,15 @@ config UBSAN_SANITIZE_ALL Enabling this option will get kernel image size increased significantly. -config UBSAN_NO_ALIGNMENT - bool "Disable checking of pointers alignment" - default y if HAVE_EFFICIENT_UNALIGNED_ACCESS +config UBSAN_ALIGNMENT + bool "Enable checks for pointers alignment" + default !HAVE_EFFICIENT_UNALIGNED_ACCESS + depends on !X86 || !COMPILE_TEST help - This option disables the check of unaligned memory accesses. - This option should be used when building allmodconfig. - Disabling this option on architectures that support unaligned + This option enables the check of unaligned memory accesses. + Enabling this option on architectures that support unaligned accesses may produce a lot of false positives. -config UBSAN_ALIGNMENT - def_bool !UBSAN_NO_ALIGNMENT - config TEST_UBSAN tristate "Module for testing for undefined behavior detection" depends on m diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 7c488a1ce318..532b6606a18a 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2168,6 +2168,10 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, * f full name * P node name, including a possible unit address * - 'x' For printing the address. Equivalent to "%lx". + * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of + * bpf_trace_printk() where [ku] prefix specifies either kernel (k) + * or user (u) memory to probe, and: + * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst @@ -2251,6 +2255,14 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, if (!IS_ERR(ptr)) break; return err_ptr(buf, end, ptr, spec); + case 'u': + case 'k': + switch (fmt[1]) { + case 's': + return string(buf, end, ptr, spec); + default: + return error_string(buf, end, "(einval)", spec); + } } /* default is to _not_ leak addresses, hash before printing */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c81b4f3a7268..efc5b83acd2d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -21,7 +21,7 @@ struct backing_dev_info noop_backing_dev_info = { EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; -const char *bdi_unknown_name = "(unknown)"; +static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU @@ -938,7 +938,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); + vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); + dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); @@ -1043,6 +1044,14 @@ void bdi_put(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_put); +const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return bdi->dev_name; +} +EXPORT_SYMBOL_GPL(bdi_dev_name); + static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) @@ -1218,6 +1218,10 @@ retry: if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; + if ((fault_flags & FAULT_FLAG_KILLABLE) && + fatal_signal_pending(current)) + return -EINTR; + ret = handle_mm_fault(vma, address, fault_flags); major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { @@ -1230,11 +1234,9 @@ retry: if (ret & VM_FAULT_RETRY) { down_read(&mm->mmap_sem); - if (!(fault_flags & FAULT_FLAG_TRIED)) { - *unlocked = true; - fault_flags |= FAULT_FLAG_TRIED; - goto retry; - } + *unlocked = true; + fault_flags |= FAULT_FLAG_TRIED; + goto retry; } if (tsk) { diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 08b43de2383b..434d503a6525 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -1,23 +1,28 @@ # SPDX-License-Identifier: GPL-2.0 KASAN_SANITIZE := n -UBSAN_SANITIZE_common.o := n -UBSAN_SANITIZE_generic.o := n -UBSAN_SANITIZE_generic_report.o := n -UBSAN_SANITIZE_tags.o := n +UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Disable ftrace to avoid recursion. CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_quarantine.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_tags_report.o = $(CC_FLAGS_FTRACE) # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 - CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_init.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_quarantine.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_tags_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) obj-$(CONFIG_KASAN) := common.o init.o report.o obj-$(CONFIG_KASAN_GENERIC) += generic.o generic_report.o quarantine.o diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index e8f37199d885..cfade6413528 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -212,8 +212,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); void __asan_register_globals(struct kasan_global *globals, size_t size); void __asan_unregister_globals(struct kasan_global *globals, size_t size); -void __asan_loadN(unsigned long addr, size_t size); -void __asan_storeN(unsigned long addr, size_t size); void __asan_handle_no_return(void); void __asan_alloca_poison(unsigned long addr, size_t size); void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom); @@ -228,6 +226,8 @@ void __asan_load8(unsigned long addr); void __asan_store8(unsigned long addr); void __asan_load16(unsigned long addr); void __asan_store16(unsigned long addr); +void __asan_loadN(unsigned long addr, size_t size); +void __asan_storeN(unsigned long addr, size_t size); void __asan_load1_noabort(unsigned long addr); void __asan_store1_noabort(unsigned long addr); @@ -239,6 +239,21 @@ void __asan_load8_noabort(unsigned long addr); void __asan_store8_noabort(unsigned long addr); void __asan_load16_noabort(unsigned long addr); void __asan_store16_noabort(unsigned long addr); +void __asan_loadN_noabort(unsigned long addr, size_t size); +void __asan_storeN_noabort(unsigned long addr, size_t size); + +void __asan_report_load1_noabort(unsigned long addr); +void __asan_report_store1_noabort(unsigned long addr); +void __asan_report_load2_noabort(unsigned long addr); +void __asan_report_store2_noabort(unsigned long addr); +void __asan_report_load4_noabort(unsigned long addr); +void __asan_report_store4_noabort(unsigned long addr); +void __asan_report_load8_noabort(unsigned long addr); +void __asan_report_store8_noabort(unsigned long addr); +void __asan_report_load16_noabort(unsigned long addr); +void __asan_report_store16_noabort(unsigned long addr); +void __asan_report_load_n_noabort(unsigned long addr, size_t size); +void __asan_report_store_n_noabort(unsigned long addr, size_t size); void __asan_set_shadow_00(const void *addr, size_t size); void __asan_set_shadow_f1(const void *addr, size_t size); @@ -247,4 +262,19 @@ void __asan_set_shadow_f3(const void *addr, size_t size); void __asan_set_shadow_f5(const void *addr, size_t size); void __asan_set_shadow_f8(const void *addr, size_t size); +void __hwasan_load1_noabort(unsigned long addr); +void __hwasan_store1_noabort(unsigned long addr); +void __hwasan_load2_noabort(unsigned long addr); +void __hwasan_store2_noabort(unsigned long addr); +void __hwasan_load4_noabort(unsigned long addr); +void __hwasan_store4_noabort(unsigned long addr); +void __hwasan_load8_noabort(unsigned long addr); +void __hwasan_store8_noabort(unsigned long addr); +void __hwasan_load16_noabort(unsigned long addr); +void __hwasan_store16_noabort(unsigned long addr); +void __hwasan_loadN_noabort(unsigned long addr, size_t size); +void __hwasan_storeN_noabort(unsigned long addr, size_t size); + +void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size); + #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5beea03dd58a..a3b97f103966 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4990,19 +4990,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void) unsigned int size; int node; int __maybe_unused i; + long error = -ENOMEM; size = sizeof(struct mem_cgroup); size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); memcg = kzalloc(size, GFP_KERNEL); if (!memcg) - return NULL; + return ERR_PTR(error); memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, GFP_KERNEL); - if (memcg->id.id < 0) + if (memcg->id.id < 0) { + error = memcg->id.id; goto fail; + } memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu); if (!memcg->vmstats_local) @@ -5046,7 +5049,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(error); } static struct cgroup_subsys_state * __ref @@ -5057,8 +5060,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) long error = -ENOMEM; memcg = mem_cgroup_alloc(); - if (!memcg) - return ERR_PTR(error); + if (IS_ERR(memcg)) + return ERR_CAST(memcg); WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; @@ -5108,7 +5111,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) fail: mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); } static int mem_cgroup_css_online(struct cgroup_subsys_state *css) diff --git a/mm/mremap.c b/mm/mremap.c index c881abeba0bf..6aa6ea605068 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -794,7 +794,7 @@ out: if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); userfaultfd_unmap_complete(mm, &uf_unmap_early); - mremap_userfaultfd_complete(&uf, addr, new_addr, old_len); + mremap_userfaultfd_complete(&uf, addr, ret, old_len); userfaultfd_unmap_complete(mm, &uf_unmap); return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0c43e9ae5004..b7e1b76284f9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1607,6 +1607,7 @@ void set_zone_contiguous(struct zone *zone) if (!__pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone)) return; + cond_resched(); } /* We confirm that there is no hole */ @@ -2400,6 +2401,14 @@ static inline void boost_watermark(struct zone *zone) if (!watermark_boost_factor) return; + /* + * Don't bother in zones that are unlikely to produce results. + * On small machines, including kdump capture kernels running + * in a small area, boosting the watermark can cause an out of + * memory situation immediately. + */ + if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) + return; max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); diff --git a/mm/percpu.c b/mm/percpu.c index d7e3bc649f4e..7da7d7737dab 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -80,6 +80,7 @@ #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <asm/cacheflush.h> #include <asm/sections.h> @@ -1557,10 +1558,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { - /* whitelisted flags that can be passed to the backing allocators */ - gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; - bool do_warn = !(gfp & __GFP_NOWARN); + gfp_t pcpu_gfp; + bool is_atomic; + bool do_warn; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; @@ -1569,6 +1569,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, void __percpu *ptr; size_t bits, bit_align; + gfp = current_gfp_context(gfp); + /* whitelisted flags that can be passed to the backing allocators */ + pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; + do_warn = !(gfp & __GFP_NOWARN); + /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. diff --git a/mm/slub.c b/mm/slub.c index 9bf44955c4f1..b762450fc9f0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -551,15 +551,32 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { struct track *p; - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; + p = object + get_info_end(s); return p + alloc; } @@ -686,10 +703,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); - if (s->offset) - off = s->offset + sizeof(void *); - else - off = s->inuse; + off = get_info_end(s); if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); @@ -782,7 +796,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object address * Bytes of the object to be managed. * If the freepointer may overlay the object then the free - * pointer is the first word of the object. + * pointer is at the middle of the object. * * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) @@ -816,11 +830,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) { - unsigned long off = s->inuse; /* The end of info */ - - if (s->offset) - /* Freepointer is placed after the object. */ - off += sizeof(void *); + unsigned long off = get_info_end(s); /* The end of info */ if (s->flags & SLAB_STORE_USER) /* We also have user information there */ @@ -907,7 +917,7 @@ static int check_object(struct kmem_cache *s, struct page *page, check_pad_bytes(s, page, p); } - if (!s->offset && val == SLUB_RED_ACTIVE) + if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) /* * Object and freepointer overlap. Cannot check * freepointer while object is allocated. @@ -3587,6 +3597,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * * This is the case if we do RCU, have a constructor or * destructor or are poisoning the objects. + * + * The assumption that s->offset >= s->inuse means free + * pointer is outside of the object is used in the + * freeptr_outside_object() function. If that is no + * longer true, the function needs to be modified. */ s->offset = size; size += sizeof(void *); diff --git a/mm/vmscan.c b/mm/vmscan.c index b06868fc4926..a37c87b5aee2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1625,7 +1625,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session - * @mode: One of the LRU isolation modes * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. diff --git a/net/core/dev.c b/net/core/dev.c index f937a3ff668d..f36bd3b21997 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9006,11 +9006,13 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; - netdev_update_features(lower); + __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); + else + netdev_features_change(lower); } } } diff --git a/net/core/filter.c b/net/core/filter.c index f8a3c7e9d027..822d662f97ef 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2579,8 +2579,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, } pop = 0; } else if (pop >= sge->length - a) { - sge->length = a; pop -= (sge->length - a); + sge->length = a; } } diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 8881dd943dd0..9bd4cab7d510 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; + cgroup_sk_alloc_disable(); + cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 0bd10a1f477f..a23094b050f8 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; @@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9cf83cc85e4a..5c218db2dede 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -109,8 +109,10 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES -#define ipmr_for_each_table(mrt, net) \ - list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) +#define ipmr_for_each_table(mrt, net) \ + list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list, \ + lockdep_rtnl_is_held() || \ + list_empty(&net->ipv4.mr_tables)) static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 041f4dcac440..2058b94bfa00 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -915,7 +915,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (peer->rate_tokens == 0 || + if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8c1250103959..970064996377 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || - (sk->sk_prot->stream_memory_read ? - sk->sk_prot->stream_memory_read(sk) : false); + int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); + + if (avail > 0) { + if (avail >= target) + return true; + if (tcp_rmem_pressure(sk)) + return true; + } + if (sk->sk_prot->stream_memory_read) + return sk->sk_prot->stream_memory_read(sk); + return false; } /* @@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk, down_read(¤t->mm->mmap_sem); - ret = -EINVAL; vma = find_vma(current->mm, address); - if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) - goto out; + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) { + up_read(¤t->mm->mmap_sem); + return -EINVAL; + } zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); tp = tcp_sk(sk); @@ -2154,13 +2163,15 @@ skip_copy: tp->urg_data = 0; tcp_fast_path_check(sk); } - if (used + offset < skb->len) - continue; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); cmsg_flags |= 2; } + + if (used + offset < skb->len) + continue; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 5a05327f97c1..629aaa9a1eb9 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -125,7 +125,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - msg->sg.size -= apply_bytes; sk_psock_queue_msg(psock, tmp); sk_psock_data_ready(sk, psock); } else { @@ -262,14 +261,17 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct sk_psock *psock; int copied, ret; + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); if (!skb_queue_empty(&sk->sk_receive_queue) && - sk_psock_queue_empty(psock)) + sk_psock_queue_empty(psock)) { + sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } lock_sock(sk); msg_bytes_ready: copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7529c2816f2f..ad90102f5dfb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4769,7 +4769,8 @@ void tcp_data_ready(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); int avail = tp->rcv_nxt - tp->copied_seq; - if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE)) + if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && + !sock_flag(sk, SOCK_DONE)) return; sk->sk_data_ready(sk); diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 221c81f85cbf..8d3f66c310db 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso, goto getattr_return; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } secattr->type = NETLBL_NLTYPE_CALIPSO; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fcf0d5c87d09..a8b4add0b545 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2722,8 +2722,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; - if (dst_metric_locked(dst, RTAX_MTU)) - return; + /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) + * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. + * [see also comment in rt6_mtu_change_route()] + */ if (iph) { daddr = &iph->daddr; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a61e60e94137..1f52a0fa31ed 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1629,6 +1629,8 @@ bool mptcp_finish_join(struct sock *sk) ret = mptcp_pm_allow_new_subflow(msk); if (ret) { + subflow->map_seq = msk->ack_seq; + /* active connections are already on conn_list */ spin_lock_bh(&msk->join_list_lock); if (!WARN_ON_ONCE(!list_empty(&subflow->node))) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3cf2eeea9d80..53c75b0e5dce 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1036,6 +1036,16 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) if (err) return err; + /* the newly created socket really belongs to the owning MPTCP master + * socket, even if for additional subflows the allocation is performed + * by a kernel workqueue. Adjust inode references, so that the + * procfs/diag interaces really show this one belonging to the correct + * user. + */ + SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino; + SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid; + SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid; + subflow = mptcp_subflow_ctx(sf->sk); pr_debug("subflow=%p", subflow); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c4582eb71766..1d57b95d3481 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1519,9 +1519,9 @@ __nf_conntrack_alloc(struct net *net, ct->status = 0; ct->timeout = 0; write_pnet(&ct->ct_net, net); - memset(&ct->__nfct_init_offset[0], 0, + memset(&ct->__nfct_init_offset, 0, offsetof(struct nf_conn, proto) - - offsetof(struct nf_conn, __nfct_init_offset[0])); + offsetof(struct nf_conn, __nfct_init_offset)); nf_ct_zone_add(ct, zone); @@ -2139,8 +2139,19 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), nf_conntrack_lock(lockp); if (*bucket < nf_conntrack_htable_size) { hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) + if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) continue; + /* All nf_conn objects are added to hash table twice, one + * for original direction tuple, once for the reply tuple. + * + * Exception: In the IPS_NAT_CLASH case, only the reply + * tuple is added (the original tuple already existed for + * a different object). + * + * We only need to call the iterator once for each + * conntrack, so we just use the 'reply' direction + * tuple while iterating. + */ ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) goto found; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 4344e572b7f9..42da6e337276 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -284,7 +284,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table, if (nf_flow_has_expired(flow)) flow_offload_fixup_ct(flow->ct); - else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) + else flow_offload_fixup_ct_timeout(flow->ct); flow_offload_free(flow); @@ -361,8 +361,10 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; - if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { + if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct)) + set_bit(NF_FLOW_TEARDOWN, &flow->flags); + + if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { if (!test_bit(NF_FLOW_HW_DYING, &flow->flags)) nf_flow_offload_del(flow_table, flow); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index a2abb0feab7f..2ff4087007a6 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -820,6 +820,7 @@ static void flow_offload_work_handler(struct work_struct *work) WARN_ON_ONCE(1); } + clear_bit(NF_FLOW_HW_PENDING, &offload->flow->flags); kfree(offload); } @@ -834,9 +835,14 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable, { struct flow_offload_work *offload; + if (test_and_set_bit(NF_FLOW_HW_PENDING, &flow->flags)) + return NULL; + offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); - if (!offload) + if (!offload) { + clear_bit(NF_FLOW_HW_PENDING, &flow->flags); return NULL; + } offload->cmd = cmd; offload->flow = flow; @@ -1059,7 +1065,7 @@ static struct flow_indr_block_entry block_ing_entry = { int nf_flow_table_offload_init(void) { nf_flow_offload_wq = alloc_workqueue("nf_flow_table_offload", - WQ_UNBOUND | WQ_MEM_RECLAIM, 0); + WQ_UNBOUND, 0); if (!nf_flow_offload_wq) return -ENOMEM; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3ffef454d469..62f416bc0579 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -79,6 +79,10 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } + + if (nft_set_elem_expired(&rbe->ext)) + return false; + if (nft_rbtree_interval_end(rbe)) { if (nft_set_is_anonymous(set)) return false; @@ -94,6 +98,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && + !nft_set_elem_expired(&interval->ext) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -154,6 +159,9 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, continue; } + if (nft_set_elem_expired(&rbe->ext)) + return false; + if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == (flags & NFT_SET_ELEM_INTERVAL_END)) { @@ -170,6 +178,7 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && + !nft_set_elem_expired(&interval->ext) && ((!nft_rbtree_interval_end(interval) && !(flags & NFT_SET_ELEM_INTERVAL_END)) || (nft_rbtree_interval_end(interval) && @@ -418,6 +427,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; + if (nft_set_elem_expired(&rbe->ext)) + goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 409a3ae47ce2..5e1239cef000 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, if ((off & (BITS_PER_LONG - 1)) != 0) return -EINVAL; + /* a null catmap is equivalent to an empty one */ + if (!catmap) { + *offset = (u32)-1; + return 0; + } + if (off < catmap->startbit) { off = catmap->startbit; *offset = off; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 25fbd8d9de74..ac5cac0dd24b 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -2032,7 +2032,6 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf; struct kvec *head = rqstp->rq_rcv_buf.head; struct rpc_auth *auth = cred->cr_auth; - unsigned int savedlen = rcv_buf->len; u32 offset, opaque_len, maj_stat; __be32 *p; @@ -2043,9 +2042,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, offset = (u8 *)(p) - (u8 *)head->iov_base; if (offset + opaque_len > rcv_buf->len) goto unwrap_failed; - rcv_buf->len = offset + opaque_len; - maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, rcv_buf); + maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, + offset + opaque_len, rcv_buf); if (maj_stat == GSS_S_CONTEXT_EXPIRED) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); if (maj_stat != GSS_S_COMPLETE) @@ -2059,10 +2058,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, */ xdr_init_decode(xdr, rcv_buf, p, rqstp); - auth->au_rslack = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); - auth->au_ralign = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); + auth->au_rslack = auth->au_verfsize + 2 + ctx->gc_gss_ctx->slack; + auth->au_ralign = auth->au_verfsize + 2 + ctx->gc_gss_ctx->align; + return 0; unwrap_failed: trace_rpcgss_unwrap_failed(task); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 6f2d30d7b766..e7180da1fc6a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -851,8 +851,8 @@ out_err: } u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, - u32 *headskip, u32 *tailskip) +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, + struct xdr_buf *buf, u32 *headskip, u32 *tailskip) { struct xdr_buf subbuf; u32 ret = 0; @@ -881,7 +881,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, /* create a segment skipping the header and leaving out the checksum */ xdr_buf_subsegment(buf, &subbuf, offset + GSS_KRB5_TOK_HDR_LEN, - (buf->len - offset - GSS_KRB5_TOK_HDR_LEN - + (len - offset - GSS_KRB5_TOK_HDR_LEN - kctx->gk5e->cksumlength)); nblocks = (subbuf.len + blocksize - 1) / blocksize; @@ -926,7 +926,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, goto out_err; /* Get the packet's hmac value */ - ret = read_bytes_from_xdr_buf(buf, buf->len - kctx->gk5e->cksumlength, + ret = read_bytes_from_xdr_buf(buf, len - kctx->gk5e->cksumlength, pkt_hmac, kctx->gk5e->cksumlength); if (ret) goto out_err; diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 6c1920eed771..cf0fd170ac18 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -261,7 +261,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, } static u32 -gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { int signalg; int sealalg; @@ -279,12 +281,13 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) u32 conflen = kctx->gk5e->conflen; int crypt_offset; u8 *cksumkey; + unsigned int saved_len = buf->len; dprintk("RPC: gss_unwrap_kerberos\n"); ptr = (u8 *)buf->head[0].iov_base + offset; if (g_verify_token_header(&kctx->mech_used, &bodysize, &ptr, - buf->len - offset)) + len - offset)) return GSS_S_DEFECTIVE_TOKEN; if ((ptr[0] != ((KG_TOK_WRAP_MSG >> 8) & 0xff)) || @@ -324,6 +327,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) (!kctx->initiate && direction != 0)) return GSS_S_BAD_SIG; + buf->len = len; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { struct crypto_sync_skcipher *cipher; int err; @@ -376,11 +380,15 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start; memmove(orig_start, data_start, data_len); buf->head[0].iov_len -= (data_start - orig_start); - buf->len -= (data_start - orig_start); + buf->len = len - (data_start - orig_start); if (gss_krb5_remove_padding(buf, blocksize)) return GSS_S_DEFECTIVE_TOKEN; + /* slack must include room for krb5 padding */ + *slack = XDR_QUADLEN(saved_len - buf->len); + /* The GSS blob always precedes the RPC message payload */ + *align = *slack; return GSS_S_COMPLETE; } @@ -486,7 +494,9 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, } static u32 -gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { time64_t now; u8 *ptr; @@ -532,7 +542,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) if (rrc != 0) rotate_left(offset + 16, buf, rrc); - err = (*kctx->gk5e->decrypt_v2)(kctx, offset, buf, + err = (*kctx->gk5e->decrypt_v2)(kctx, offset, len, buf, &headskip, &tailskip); if (err) return GSS_S_FAILURE; @@ -542,7 +552,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * it against the original */ err = read_bytes_from_xdr_buf(buf, - buf->len - GSS_KRB5_TOK_HDR_LEN - tailskip, + len - GSS_KRB5_TOK_HDR_LEN - tailskip, decrypted_hdr, GSS_KRB5_TOK_HDR_LEN); if (err) { dprintk("%s: error %u getting decrypted_hdr\n", __func__, err); @@ -568,18 +578,19 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * Note that buf->head[0].iov_len may indicate the available * head buffer space rather than that actually occupied. */ - movelen = min_t(unsigned int, buf->head[0].iov_len, buf->len); + movelen = min_t(unsigned int, buf->head[0].iov_len, len); movelen -= offset + GSS_KRB5_TOK_HDR_LEN + headskip; - if (offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > - buf->head[0].iov_len) - return GSS_S_FAILURE; + BUG_ON(offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > + buf->head[0].iov_len); memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen); buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; - buf->len -= GSS_KRB5_TOK_HDR_LEN + headskip; + buf->len = len - GSS_KRB5_TOK_HDR_LEN + headskip; /* Trim off the trailing "extra count" and checksum blob */ - buf->len -= ec + GSS_KRB5_TOK_HDR_LEN + tailskip; + xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip); + *align = XDR_QUADLEN(GSS_KRB5_TOK_HDR_LEN + headskip); + *slack = *align + XDR_QUADLEN(ec + GSS_KRB5_TOK_HDR_LEN + tailskip); return GSS_S_COMPLETE; } @@ -603,7 +614,8 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset, } u32 -gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, + int len, struct xdr_buf *buf) { struct krb5_ctx *kctx = gctx->internal_ctx_id; @@ -613,9 +625,11 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: case ENCTYPE_ARCFOUR_HMAC: - return gss_unwrap_kerberos_v1(kctx, offset, buf); + return gss_unwrap_kerberos_v1(kctx, offset, len, buf, + &gctx->slack, &gctx->align); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_unwrap_kerberos_v2(kctx, offset, buf); + return gss_unwrap_kerberos_v2(kctx, offset, len, buf, + &gctx->slack, &gctx->align); } } diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index db550bfc2642..69316ab1b9fa 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -411,10 +411,11 @@ gss_wrap(struct gss_ctx *ctx_id, u32 gss_unwrap(struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf) { return ctx_id->mech_type->gm_ops - ->gss_unwrap(ctx_id, offset, buf); + ->gss_unwrap(ctx_id, offset, len, buf); } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 54ae5be62f6a..50d93c49ef1a 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -906,7 +906,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g if (svc_getnl(&buf->head[0]) != seq) goto out; /* trim off the mic and padding at the end before returning */ - buf->len -= 4 + round_up_to_quad(mic.len); + xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4); stat = 0; out: kfree(mic.data); @@ -934,7 +934,7 @@ static int unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) { u32 priv_len, maj_stat; - int pad, saved_len, remaining_len, offset; + int pad, remaining_len, offset; clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); @@ -954,12 +954,8 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs buf->len -= pad; fix_priv_head(buf, pad); - /* Maybe it would be better to give gss_unwrap a length parameter: */ - saved_len = buf->len; - buf->len = priv_len; - maj_stat = gss_unwrap(ctx, 0, buf); + maj_stat = gss_unwrap(ctx, 0, priv_len, buf); pad = priv_len - buf->len; - buf->len = saved_len; buf->len -= pad; /* The upper layers assume the buffer is aligned on 4-byte boundaries. * In the krb5p case, at least, the data ends up offset, so we need to diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 15b58c5144f9..6f7d82fb1eb0 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1150,6 +1150,47 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, } EXPORT_SYMBOL_GPL(xdr_buf_subsegment); +/** + * xdr_buf_trim - lop at most "len" bytes off the end of "buf" + * @buf: buf to be trimmed + * @len: number of bytes to reduce "buf" by + * + * Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note + * that it's possible that we'll trim less than that amount if the xdr_buf is + * too small, or if (for instance) it's all in the head and the parser has + * already read too far into it. + */ +void xdr_buf_trim(struct xdr_buf *buf, unsigned int len) +{ + size_t cur; + unsigned int trim = len; + + if (buf->tail[0].iov_len) { + cur = min_t(size_t, buf->tail[0].iov_len, trim); + buf->tail[0].iov_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->page_len) { + cur = min_t(unsigned int, buf->page_len, trim); + buf->page_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->head[0].iov_len) { + cur = min_t(size_t, buf->head[0].iov_len, trim); + buf->head[0].iov_len -= cur; + trim -= cur; + } +fix_len: + buf->len -= (len - trim); +} +EXPORT_SYMBOL_GPL(xdr_buf_trim); + static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len) { unsigned int this_len; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 87466607097f..e370ad0edd76 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1739,22 +1739,21 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb, return 0; } -static void tipc_sk_send_ack(struct tipc_sock *tsk) +static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk) { struct sock *sk = &tsk->sk; - struct net *net = sock_net(sk); struct sk_buff *skb = NULL; struct tipc_msg *msg; u32 peer_port = tsk_peer_port(tsk); u32 dnode = tsk_peer_node(tsk); if (!tipc_sk_connected(sk)) - return; + return NULL; skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, dnode, tsk_own_node(tsk), peer_port, tsk->portid, TIPC_OK); if (!skb) - return; + return NULL; msg = buf_msg(skb); msg_set_conn_ack(msg, tsk->rcv_unacked); tsk->rcv_unacked = 0; @@ -1764,7 +1763,19 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk) tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf); msg_set_adv_win(msg, tsk->rcv_win); } - tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg)); + return skb; +} + +static void tipc_sk_send_ack(struct tipc_sock *tsk) +{ + struct sk_buff *skb; + + skb = tipc_sk_build_ack(tsk); + if (!skb) + return; + + tipc_node_xmit_skb(sock_net(&tsk->sk), skb, tsk_peer_node(tsk), + msg_link_selector(buf_msg(skb))); } static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) @@ -1938,7 +1949,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, bool peek = flags & MSG_PEEK; int offset, required, copy, copied = 0; int hlen, dlen, err, rc; - bool ack = false; long timeout; /* Catch invalid receive attempts */ @@ -1983,7 +1993,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Copy data if msg ok, otherwise return error/partial data */ if (likely(!err)) { - ack = msg_ack_required(hdr); offset = skb_cb->bytes_read; copy = min_t(int, dlen - offset, buflen - copied); rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); @@ -2011,7 +2020,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Send connection flow control advertisement when applicable */ tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen); - if (ack || tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) + if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) tipc_sk_send_ack(tsk); /* Exit if all requested data or FIN/error received */ @@ -2105,9 +2114,11 @@ static void tipc_sk_proto_rcv(struct sock *sk, * tipc_sk_filter_connect - check incoming message for a connection-based socket * @tsk: TIPC socket * @skb: pointer to message buffer. + * @xmitq: for Nagle ACK if any * Returns true if message should be added to receive queue, false otherwise */ -static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) +static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); @@ -2171,8 +2182,17 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) if (!skb_queue_empty(&sk->sk_write_queue)) tipc_sk_push_backlog(tsk); /* Accept only connection-based messages sent by peer */ - if (likely(con_msg && !err && pport == oport && pnode == onode)) + if (likely(con_msg && !err && pport == oport && + pnode == onode)) { + if (msg_ack_required(hdr)) { + struct sk_buff *skb; + + skb = tipc_sk_build_ack(tsk); + if (skb) + __skb_queue_tail(xmitq, skb); + } return true; + } if (!tsk_peer_msg(tsk, hdr)) return false; if (!err) @@ -2267,7 +2287,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, while ((skb = __skb_dequeue(&inputq))) { hdr = buf_msg(skb); limit = rcvbuf_limit(sk, skb); - if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || + if ((sk_conn && !tipc_sk_filter_connect(tsk, skb, xmitq)) || (!sk_conn && msg_connected(hdr)) || (!grp && msg_in_group(hdr))) err = TIPC_ERR_NO_PORT; diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index aa015c233898..6ebbec1bedd1 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -96,6 +96,16 @@ void tipc_sub_get(struct tipc_subscription *subscription); (swap_ ? swab32(val__) : val__); \ }) +/* tipc_sub_write - write val_ to field_ of struct sub_ in user endian format + */ +#define tipc_sub_write(sub_, field_, val_) \ + ({ \ + struct tipc_subscr *sub__ = sub_; \ + u32 val__ = val_; \ + int swap_ = !((sub__)->filter & TIPC_FILTER_MASK); \ + (sub__)->field_ = swap_ ? swab32(val__) : val__; \ + }) + /* tipc_evt_write - write val_ to field_ of struct evt_ in user endian format */ #define tipc_evt_write(evt_, field_, val_) \ diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 73dbed0c4b6b..446af7bbd13e 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -237,8 +237,8 @@ static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s) if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) { tipc_sub_unsubscribe(sub); atomic_dec(&tn->subscription_count); - } else if (s) { - break; + if (s) + break; } } spin_unlock_bh(&con->sub_lock); @@ -362,9 +362,10 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, { struct tipc_net *tn = tipc_net(srv->net); struct tipc_subscription *sub; + u32 s_filter = tipc_sub_read(s, filter); - if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) { - s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL); + if (s_filter & TIPC_SUB_CANCEL) { + tipc_sub_write(s, filter, s_filter & ~TIPC_SUB_CANCEL); tipc_conn_delete_sub(con, s); return 0; } @@ -400,7 +401,9 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) return -EWOULDBLOCK; if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); - ret = tipc_conn_rcv_sub(srv, con, &s); + /* RACE: the connection can be closed in the meantime */ + if (likely(connected(con))) + ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); if (!ret) return 0; diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c index 587b68b1f8dd..430a4b7e353e 100644 --- a/samples/bpf/lwt_len_hist_user.c +++ b/samples/bpf/lwt_len_hist_user.c @@ -15,8 +15,6 @@ #define MAX_INDEX 64 #define MAX_STARS 38 -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - static void stars(char *str, long val, long max, int width) { int i; diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h index 80b4a70315b6..13a35f7cbe66 100644 --- a/samples/trace_events/trace-events-sample.h +++ b/samples/trace_events/trace-events-sample.h @@ -416,7 +416,7 @@ TRACE_EVENT_FN(foo_bar_with_fn, * Note, TRACE_EVENT() itself is simply defined as: * * #define TRACE_EVENT(name, proto, args, tstruct, assign, printk) \ - * DEFINE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ + * DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ * DEFINE_EVENT(name, name, proto, args) * * The DEFINE_EVENT() also can be declared with conditions and reg functions: diff --git a/scripts/decodecode b/scripts/decodecode index ba8b8d5834e6..fbdb325cdf4f 100755 --- a/scripts/decodecode +++ b/scripts/decodecode @@ -126,7 +126,7 @@ faultlinenum=$(( $(wc -l $T.oo | cut -d" " -f1) - \ faultline=`cat $T.dis | head -1 | cut -d":" -f2-` faultline=`echo "$faultline" | sed -e 's/\[/\\\[/g; s/\]/\\\]/g'` -cat $T.oo | sed -e "${faultlinenum}s/^\(.*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" +cat $T.oo | sed -e "${faultlinenum}s/^\([^:]*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" echo cat $T.aa cleanup diff --git a/scripts/gdb/linux/rbtree.py b/scripts/gdb/linux/rbtree.py index 39db889b874c..c4b991607917 100644 --- a/scripts/gdb/linux/rbtree.py +++ b/scripts/gdb/linux/rbtree.py @@ -12,7 +12,7 @@ rb_node_type = utils.CachedType("struct rb_node") def rb_first(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) @@ -28,7 +28,7 @@ def rb_first(root): def rb_last(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 20dd08e1f675..2a688b711a9a 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -120,6 +120,17 @@ static void snd_rawmidi_input_event_work(struct work_struct *work) runtime->event(runtime->substream); } +/* buffer refcount management: call with runtime->lock held */ +static inline void snd_rawmidi_buffer_ref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref++; +} + +static inline void snd_rawmidi_buffer_unref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref--; +} + static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) { struct snd_rawmidi_runtime *runtime; @@ -669,6 +680,11 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime, if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock); + if (runtime->buffer_ref) { + spin_unlock_irq(&runtime->lock); + kvfree(newbuf); + return -EBUSY; + } oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; @@ -1019,8 +1035,10 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, long result = 0, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; unsigned long appl_ptr; + int err = 0; spin_lock_irqsave(&runtime->lock, flags); + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -1039,16 +1057,19 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); if (copy_to_user(userbuf + result, - runtime->buffer + appl_ptr, count1)) { - return result > 0 ? result : -EFAULT; - } + runtime->buffer + appl_ptr, count1)) + err = -EFAULT; spin_lock_irqsave(&runtime->lock, flags); + if (err) + goto out; } result += count1; count -= count1; } + out: + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); - return result; + return result > 0 ? result : err; } long snd_rawmidi_kernel_read(struct snd_rawmidi_substream *substream, @@ -1342,6 +1363,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, return -EAGAIN; } } + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail > 0) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -1373,6 +1395,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, } __end: count1 = runtime->avail < runtime->buffer_size; + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); if (count1) snd_rawmidi_output_trigger(substream, 1); diff --git a/sound/firewire/amdtp-stream-trace.h b/sound/firewire/amdtp-stream-trace.h index 16c7f6605511..26e7cb555d3c 100644 --- a/sound/firewire/amdtp-stream-trace.h +++ b/sound/firewire/amdtp-stream-trace.h @@ -66,8 +66,7 @@ TRACE_EVENT(amdtp_packet, __entry->irq, __entry->index, __print_array(__get_dynamic_array(cip_header), - __get_dynamic_array_len(cip_header), - sizeof(u8))) + __get_dynamic_array_len(cip_header), 1)) ); #endif diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c16f63957c5a..dc2302171a71 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5856,6 +5856,15 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, } } +static void alc225_fixup_s3_pop_noise(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + codec->power_save_node = 1; +} + /* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */ static void alc274_fixup_bind_dacs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -5960,6 +5969,7 @@ enum { ALC269_FIXUP_HP_LINE1_MIC1_LED, ALC269_FIXUP_INV_DMIC, ALC269_FIXUP_LENOVO_DOCK, + ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, ALC269_FIXUP_NO_SHUTUP, ALC286_FIXUP_SONY_MIC_NO_PRESENCE, ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT, @@ -6045,6 +6055,7 @@ enum { ALC233_FIXUP_ACER_HEADSET_MIC, ALC294_FIXUP_LENOVO_MIC_LOCATION, ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, + ALC225_FIXUP_S3_POP_NOISE, ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, @@ -6080,9 +6091,12 @@ enum { ALC294_FIXUP_ASUS_DUAL_SPK, ALC285_FIXUP_THINKPAD_HEADSET_JACK, ALC294_FIXUP_ASUS_HPE, + ALC294_FIXUP_ASUS_COEF_1B, ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED, + ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, + ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6280,6 +6294,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT }, + [ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_limit_int_mic_boost, + .chained = true, + .chain_id = ALC269_FIXUP_LENOVO_DOCK, + }, [ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_pincfg_no_hp_to_lineout, @@ -6932,6 +6952,12 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, + .chain_id = ALC225_FIXUP_S3_POP_NOISE + }, + [ALC225_FIXUP_S3_POP_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc225_fixup_s3_pop_noise, + .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, [ALC700_FIXUP_INTEL_REFERENCE] = { @@ -7204,6 +7230,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC }, + [ALC294_FIXUP_ASUS_COEF_1B] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Set bit 10 to correct noisy output after reboot from + * Windows 10 (due to pop noise reduction?) + */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x1b }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x4e4b }, + { } + }, + }, [ALC285_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_gpio_led, @@ -7216,6 +7253,22 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_mute_led, }, + [ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x1a, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc5 }, + { } + }, + }, + [ALC295_FIXUP_ASUS_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7383,8 +7436,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), + SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -7410,6 +7465,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), + SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), @@ -7426,7 +7483,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21ca, "Thinkpad L412", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21e9, "Thinkpad Edge 15", ALC269_FIXUP_SKU_IGNORE), - SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK), + SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST), SND_PCI_QUIRK(0x17aa, 0x21fa, "Thinkpad X230", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x21f3, "Thinkpad T430", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x21fb, "Thinkpad T430s", ALC269_FIXUP_LENOVO_DOCK), @@ -7565,6 +7622,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC269_FIXUP_HEADSET_MODE, .name = "headset-mode"}, {.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"}, {.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"}, + {.id = ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, .name = "lenovo-dock-limit-boost"}, {.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"}, {.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"}, {.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"}, @@ -7993,6 +8051,18 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x17, 0x90170110}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60120}, + {0x17, 0x90170110}, + {0x21, 0x04211030}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x03211020}), SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x04211020}), @@ -8209,8 +8279,6 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; break; case 0x10ec0225: - codec->power_save_node = 1; - /* fall through */ case 0x10ec0295: case 0x10ec0299: spec->codec_variant = ALC269_TYPE_ALC225; diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 0260c750e156..bfdc6ad52785 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -549,6 +549,11 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = trx40_mobo_map, .connector_map = trx40_mobo_connector_map, }, + { /* Asrock TRX40 Creator */ + .id = USB_ID(0x26ce, 0x0a01), + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, + }, { 0 } /* terminator */ }; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index a1df4c5b4f8c..6313c30f5c85 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3563,6 +3563,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), ALC1220_VB_DESKTOP(0x0414, 0xa002), /* Gigabyte TRX40 Aorus Pro WiFi */ ALC1220_VB_DESKTOP(0x0db0, 0x0d64), /* MSI TRX40 Creator */ ALC1220_VB_DESKTOP(0x0db0, 0x543d), /* MSI TRX40 */ +ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ #undef ALC1220_VB_DESKTOP #undef USB_DEVICE_VENDOR_SPEC diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 848a4cc25bed..d8a765be5dfe 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1636,13 +1636,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here, - * otherwise requests like get/set frequency return as failed despite - * actually succeeding. + /* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny + * delay here, otherwise requests like get/set frequency return as + * failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || chip->usb_id == USB_ID(0x046d, 0x0a46) || - chip->usb_id == USB_ID(0x0b0e, 0x0349)) && + chip->usb_id == USB_ID(0x0b0e, 0x0349) || + chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) usleep_range(1000, 2000); } diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 16b9a420e6fd..0efaf45f7367 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -314,6 +314,7 @@ int apply_xbc(const char *path, const char *xbc_path) ret = delete_xbc(path); if (ret < 0) { pr_err("Failed to delete previous boot config: %d\n", ret); + free(data); return ret; } @@ -321,24 +322,27 @@ int apply_xbc(const char *path, const char *xbc_path) fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { pr_err("Failed to open %s: %d\n", path, fd); + free(data); return fd; } /* TODO: Ensure the @path is initramfs/initrd image */ ret = write(fd, data, size + 8); if (ret < 0) { pr_err("Failed to apply a boot config: %d\n", ret); - return ret; + goto out; } /* Write a magic word of the bootconfig */ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); if (ret < 0) { pr_err("Failed to apply a boot config magic: %d\n", ret); - return ret; + goto out; } + ret = 0; +out: close(fd); free(data); - return 0; + return ret; } int usage(void) diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 7427a5ee761b..9d8e9613008a 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -159,7 +159,12 @@ class IocgStat: else: self.inflight_pct = 0 - self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + # vdebt used to be an atomic64_t and is now u64, support both + try: + self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + except: + self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 + self.use_delay = blkg.use_delay.counter.value_() self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index cf97d07692b4..58eceb884df3 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -148,11 +148,11 @@ struct pt_regs; #define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4]) #define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5]) #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14]) #define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11]) #define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) #define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr) #elif defined(bpf_target_arm) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4b170fd08a28..3c6da70e6084 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -72,6 +72,17 @@ static struct instruction *next_insn_same_func(struct objtool_file *file, return find_insn(file, func->cfunc->sec, func->cfunc->offset); } +static struct instruction *prev_insn_same_sym(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *prev = list_prev_entry(insn, list); + + if (&prev->list != &file->insn_list && prev->func == insn->func) + return prev; + + return NULL; +} + #define func_for_each_insn(file, func, insn) \ for (insn = find_insn(file, func->sec, func->offset); \ insn; \ @@ -1050,8 +1061,8 @@ static struct rela *find_jump_table(struct objtool_file *file, * it. */ for (; - &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func; - insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { + insn && insn->func && insn->func->pfunc == func; + insn = insn->first_jump_src ?: prev_insn_same_sym(file, insn)) { if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC) break; @@ -1449,7 +1460,7 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s struct cfi_reg *cfa = &state->cfa; struct stack_op *op = &insn->stack_op; - if (cfa->base != CFI_SP) + if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT) return 0; /* push */ diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 0b79c2353a21..12e01ac190ec 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -87,9 +87,10 @@ struct elf { #define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) #define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) -#define for_offset_range(_offset, _start, _end) \ - for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ - _offset <= ((_end) & OFFSET_STRIDE_MASK); \ +#define for_offset_range(_offset, _start, _end) \ + for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ + _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ + _offset <= ((_end) & OFFSET_STRIDE_MASK); \ _offset += OFFSET_STRIDE) static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 56d80adcf4bd..6b9dce431d41 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -217,6 +217,14 @@ void test_mmap(void) munmap(tmp2, 4 * page_size); + /* map all 4 pages, but with pg_off=1 page, should fail */ + tmp1 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, + data_map_fd, page_size /* initial page shift */); + if (CHECK(tmp1 != MAP_FAILED, "adv_mmap7", "unexpected success")) { + munmap(tmp1, 4 * page_size); + goto cleanup; + } + tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0); if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno)) goto cleanup; diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index 450bf819beac..42403d088abc 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -30,13 +30,13 @@ int prog3(struct bpf_raw_tracepoint_args *ctx) SEC("fentry/__set_task_comm") int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec) { - return !tsk; + return 0; } SEC("fexit/__set_task_comm") int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) { - return !tsk; + return 0; } SEC("fmod_ret/__set_task_comm") diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index cd5e1f602ac9..909da9cdda97 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -351,6 +351,7 @@ static int test_alloc_errors(char *heap_name) } printf("Expected error checking passed\n"); + ret = 0; out: if (dmabuf_fd >= 0) close(dmabuf_fd); diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 11eee0b60040..d979ff14775a 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include <poll.h> #include <unistd.h> +#include <assert.h> #include <signal.h> #include <pthread.h> #include <sys/epoll.h> @@ -3136,4 +3137,149 @@ TEST(epoll59) close(ctx.sfd[0]); } +enum { + EPOLL60_EVENTS_NR = 10, +}; + +struct epoll60_ctx { + volatile int stopped; + int ready; + int waiters; + int epfd; + int evfd[EPOLL60_EVENTS_NR]; +}; + +static void *epoll60_wait_thread(void *ctx_) +{ + struct epoll60_ctx *ctx = ctx_; + struct epoll_event e; + sigset_t sigmask; + uint64_t v; + int ret; + + /* Block SIGUSR1 */ + sigemptyset(&sigmask); + sigaddset(&sigmask, SIGUSR1); + sigprocmask(SIG_SETMASK, &sigmask, NULL); + + /* Prepare empty mask for epoll_pwait() */ + sigemptyset(&sigmask); + + while (!ctx->stopped) { + /* Mark we are ready */ + __atomic_fetch_add(&ctx->ready, 1, __ATOMIC_ACQUIRE); + + /* Start when all are ready */ + while (__atomic_load_n(&ctx->ready, __ATOMIC_ACQUIRE) && + !ctx->stopped); + + /* Account this waiter */ + __atomic_fetch_add(&ctx->waiters, 1, __ATOMIC_ACQUIRE); + + ret = epoll_pwait(ctx->epfd, &e, 1, 2000, &sigmask); + if (ret != 1) { + /* We expect only signal delivery on stop */ + assert(ret < 0 && errno == EINTR && "Lost wakeup!\n"); + assert(ctx->stopped); + break; + } + + ret = read(e.data.fd, &v, sizeof(v)); + /* Since we are on ET mode, thus each thread gets its own fd. */ + assert(ret == sizeof(v)); + + __atomic_fetch_sub(&ctx->waiters, 1, __ATOMIC_RELEASE); + } + + return NULL; +} + +static inline unsigned long long msecs(void) +{ + struct timespec ts; + unsigned long long msecs; + + clock_gettime(CLOCK_REALTIME, &ts); + msecs = ts.tv_sec * 1000ull; + msecs += ts.tv_nsec / 1000000ull; + + return msecs; +} + +static inline int count_waiters(struct epoll60_ctx *ctx) +{ + return __atomic_load_n(&ctx->waiters, __ATOMIC_ACQUIRE); +} + +TEST(epoll60) +{ + struct epoll60_ctx ctx = { 0 }; + pthread_t waiters[ARRAY_SIZE(ctx.evfd)]; + struct epoll_event e; + int i, n, ret; + + signal(SIGUSR1, signal_handler); + + ctx.epfd = epoll_create1(0); + ASSERT_GE(ctx.epfd, 0); + + /* Create event fds */ + for (i = 0; i < ARRAY_SIZE(ctx.evfd); i++) { + ctx.evfd[i] = eventfd(0, EFD_NONBLOCK); + ASSERT_GE(ctx.evfd[i], 0); + + e.events = EPOLLIN | EPOLLET; + e.data.fd = ctx.evfd[i]; + ASSERT_EQ(epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd[i], &e), 0); + } + + /* Create waiter threads */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ASSERT_EQ(pthread_create(&waiters[i], NULL, + epoll60_wait_thread, &ctx), 0); + + for (i = 0; i < 300; i++) { + uint64_t v = 1, ms; + + /* Wait for all to be ready */ + while (__atomic_load_n(&ctx.ready, __ATOMIC_ACQUIRE) != + ARRAY_SIZE(ctx.evfd)) + ; + + /* Steady, go */ + __atomic_fetch_sub(&ctx.ready, ARRAY_SIZE(ctx.evfd), + __ATOMIC_ACQUIRE); + + /* Wait all have gone to kernel */ + while (count_waiters(&ctx) != ARRAY_SIZE(ctx.evfd)) + ; + + /* 1ms should be enough to schedule away */ + usleep(1000); + + /* Quickly signal all handles at once */ + for (n = 0; n < ARRAY_SIZE(ctx.evfd); n++) { + ret = write(ctx.evfd[n], &v, sizeof(v)); + ASSERT_EQ(ret, sizeof(v)); + } + + /* Busy loop for 1s and wait for all waiters to wake up */ + ms = msecs(); + while (count_waiters(&ctx) && msecs() < ms + 1000) + ; + + ASSERT_EQ(count_waiters(&ctx), 0); + } + ctx.stopped = 1; + /* Stop waiters */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ret = pthread_kill(waiters[i], SIGUSR1); + for (i = 0; i < ARRAY_SIZE(waiters); i++) + pthread_join(waiters[i], NULL); + + for (i = 0; i < ARRAY_SIZE(waiters); i++) + close(ctx.evfd[i]); + close(ctx.epfd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 063ecb290a5a..a4605b5ee66d 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -17,6 +17,7 @@ echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" echo " --fail-unsupported Treat UNSUPPORTED as a failure" +echo " --fail-unresolved Treat UNRESOLVED as a failure" echo " -d|--debug Debug mode (trace all shell commands)" echo " -l|--logdir <dir> Save logs on the <dir>" echo " If <dir> is -, all logs output in console only" @@ -29,8 +30,25 @@ err_ret=1 # kselftest skip code is 4 err_skip=4 +# cgroup RT scheduling prevents chrt commands from succeeding, which +# induces failures in test wakeup tests. Disable for the duration of +# the tests. + +readonly sched_rt_runtime=/proc/sys/kernel/sched_rt_runtime_us + +sched_rt_runtime_orig=$(cat $sched_rt_runtime) + +setup() { + echo -1 > $sched_rt_runtime +} + +cleanup() { + echo $sched_rt_runtime_orig > $sched_rt_runtime +} + errexit() { # message echo "Error: $1" 1>&2 + cleanup exit $err_ret } @@ -39,6 +57,8 @@ if [ `id -u` -ne 0 ]; then errexit "this must be run by root user" fi +setup + # Utilities absdir() { # file_path (cd `dirname $1`; pwd) @@ -93,6 +113,10 @@ parse_opts() { # opts UNSUPPORTED_RESULT=1 shift 1 ;; + --fail-unresolved) + UNRESOLVED_RESULT=1 + shift 1 + ;; --logdir|-l) LOG_DIR=$2 shift 2 @@ -157,6 +181,7 @@ KEEP_LOG=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 +UNRESOLVED_RESULT=0 STOP_FAILURE=0 # Parse command-line options parse_opts $* @@ -235,6 +260,7 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 + testcase() { # testfile CASENO=$((CASENO+1)) desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:` @@ -260,7 +286,7 @@ eval_result() { # sigval $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" - return 1 # this is a kind of bug.. something happened. + return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" @@ -273,7 +299,7 @@ eval_result() { # sigval return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) - prlog " [${color_red}XFAIL${color_reset}]" + prlog " [${color_green}XFAIL${color_reset}]" XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; @@ -406,5 +432,7 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +cleanup + # if no error, return 0 exit $TOTAL_RESULT diff --git a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc index cbd174334a48..2b82c80edf69 100644 --- a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc +++ b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc @@ -17,7 +17,14 @@ unsup() { #msg exit_unsupported } -modprobe $MOD || unsup "$MOD module not available" +unres() { #msg + reset_tracer + rmmod $MOD || true + echo $1 + exit_unresolved +} + +modprobe $MOD || unres "$MOD module not available" rmmod $MOD grep -q "preemptoff" available_tracers || unsup "preemptoff tracer not enabled" diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 712a2ddd2a27..b728c0a0f9b2 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -5,8 +5,34 @@ all: top_srcdir = ../../../.. KSFT_KHDR_INSTALL := 1 + +# For cross-builds to work, UNAME_M has to map to ARCH and arch specific +# directories and targets in this Makefile. "uname -m" doesn't map to +# arch specific sub-directory names. +# +# UNAME_M variable to used to run the compiles pointing to the right arch +# directories and build the right targets for these supported architectures. +# +# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable. +# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable. +# +# x86_64 targets are named to include x86_64 as a suffix and directories +# for includes are in x86_64 sub-directory. s390x and aarch64 follow the +# same convention. "uname -m" doesn't result in the correct mapping for +# s390x and aarch64. +# +# No change necessary for x86_64 UNAME_M := $(shell uname -m) +# Set UNAME_M for arm64 compile/install to work +ifeq ($(ARCH),arm64) + UNAME_M := aarch64 +endif +# Set UNAME_M s390x compile/install to work +ifeq ($(ARCH),s390) + UNAME_M := s390x +endif + LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c @@ -53,7 +79,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ @@ -84,6 +110,7 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ +x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h index d8f4d6bfe05d..a034438b6266 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -219,8 +219,8 @@ struct hv_enlightened_vmcs { #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) -struct hv_enlightened_vmcs *current_evmcs; -struct hv_vp_assist_page *current_vp_assist; +extern struct hv_enlightened_vmcs *current_evmcs; +extern struct hv_vp_assist_page *current_vp_assist; int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id); diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 6f17f69394be..4ae104f6ce69 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -17,6 +17,9 @@ bool enable_evmcs; +struct hv_enlightened_vmcs *current_evmcs; +struct hv_vp_assist_page *current_vp_assist; + struct eptPageTableEntry { uint64_t readable:1; uint64_t writable:1; diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index dadf819148a4..ee64ff8df8f4 100755 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -25,13 +25,13 @@ fi # Figure out which test to run from our script name. test=$(basename $0 .sh) # Look up details about the test from master list of LKDTM tests. -line=$(egrep '^#?'"$test"'\b' tests.txt) +line=$(grep -E '^#?'"$test"'\b' tests.txt) if [ -z "$line" ]; then echo "Skipped: missing test '$test' in tests.txt" exit $KSELFTEST_SKIP_TEST fi # Check that the test is known to LKDTM. -if ! egrep -q '^'"$test"'$' "$TRIGGER" ; then +if ! grep -E -q '^'"$test"'$' "$TRIGGER" ; then echo "Skipped: test '$test' missing in $TRIGGER!" exit $KSELFTEST_SKIP_TEST fi @@ -59,30 +59,32 @@ if [ -z "$expect" ]; then expect="call trace:" fi -# Clear out dmesg for output reporting -dmesg -c >/dev/null - # Prepare log for report checking -LOG=$(mktemp --tmpdir -t lkdtm-XXXXXX) +LOG=$(mktemp --tmpdir -t lkdtm-log-XXXXXX) +DMESG=$(mktemp --tmpdir -t lkdtm-dmesg-XXXXXX) cleanup() { - rm -f "$LOG" + rm -f "$LOG" "$DMESG" } trap cleanup EXIT +# Save existing dmesg so we can detect new content below +dmesg > "$DMESG" + # Most shells yell about signals and we're expecting the "cat" process # to usually be killed by the kernel. So we have to run it in a sub-shell # and silence errors. ($SHELL -c 'cat <(echo '"$test"') >'"$TRIGGER" 2>/dev/null) || true # Record and dump the results -dmesg -c >"$LOG" +dmesg | diff --changed-group-format='%>' --unchanged-group-format='' "$DMESG" - > "$LOG" || true + cat "$LOG" # Check for expected output -if egrep -qi "$expect" "$LOG" ; then +if grep -E -qi "$expect" "$LOG" ; then echo "$test: saw '$expect': ok" exit 0 else - if egrep -qi XFAIL: "$LOG" ; then + if grep -E -qi XFAIL: "$LOG" ; then echo "$test: saw 'XFAIL': [SKIP]" exit $KSELFTEST_SKIP_TEST else diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 9172746b6cf0..15f4f46ca3a9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -30,7 +30,7 @@ ret=0 cleanup() { - rm -f $out + rm -f $err ip netns del $ns1 } diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/nsfs/pidns.c index e0d86e1668c0..e3c772c6a7c7 100644 --- a/tools/testing/selftests/nsfs/pidns.c +++ b/tools/testing/selftests/nsfs/pidns.c @@ -27,7 +27,7 @@ #define __stack_aligned__ __attribute__((aligned(16))) struct cr_clone_arg { char stack[128] __stack_aligned__; - char stack_ptr[0]; + char stack_ptr[]; }; static int child(void *args) diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index 5909e7ef2a5c..9803dbb54181 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -25,7 +25,6 @@ CONFIG_KASAN=y CONFIG_KASAN_INLINE=y CONFIG_UBSAN=y CONFIG_UBSAN_SANITIZE_ALL=y -CONFIG_UBSAN_NO_ALIGNMENT=y CONFIG_UBSAN_NULL=y CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c index d31f267961e7..25c0e47d57cb 100644 --- a/virt/kvm/arm/hyp/aarch32.c +++ b/virt/kvm/arm/hyp/aarch32.c @@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) */ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { + u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; + pc += 2; else - *vcpu_pc(vcpu) += 4; + pc += 4; + + *vcpu_pc(vcpu) = pc; + kvm_adjust_itstate(vcpu); } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 14a162e295a9..ae364716ee40 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -186,6 +186,33 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET); } +static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) +{ + int i; + + /* + * Zero the input registers' upper 32 bits. They will be fully + * zeroed on exit, so we're fine changing them in place. + */ + for (i = 1; i < 4; i++) + vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i))); +} + +static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) +{ + switch(fn) { + case PSCI_0_2_FN64_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_ON: + case PSCI_0_2_FN64_AFFINITY_INFO: + /* Disallow these functions for 32bit guests */ + if (vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; + break; + } + + return 0; +} + static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; @@ -193,6 +220,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) unsigned long val; int ret = 1; + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) + goto out; + switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* @@ -210,12 +241,16 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) val = PSCI_RET_SUCCESS; break; case PSCI_0_2_FN_CPU_ON: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_CPU_ON: mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); mutex_unlock(&kvm->lock); break; case PSCI_0_2_FN_AFFINITY_INFO: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; @@ -256,6 +291,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } +out: smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } @@ -273,6 +309,10 @@ static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu) break; case PSCI_1_0_FN_PSCI_FEATURES: feature = smccc_get_arg1(vcpu); + val = kvm_psci_check_allowed_function(vcpu, feature); + if (val) + break; + switch(feature) { case PSCI_0_2_FN_PSCI_VERSION: case PSCI_0_2_FN_CPU_SUSPEND: diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index a963b9d766b7..32e32d67a127 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -294,8 +294,15 @@ int vgic_init(struct kvm *kvm) } } - if (vgic_has_its(kvm)) { + if (vgic_has_its(kvm)) vgic_lpi_translation_cache_init(kvm); + + /* + * If we have GICv4.1 enabled, unconditionnaly request enable the + * v4 support so that we get HW-accelerated vSGIs. Otherwise, only + * enable it if we present a virtual ITS to the guest. + */ + if (vgic_supports_direct_msis(kvm)) { ret = vgic_v4_init(kvm); if (ret) goto out; @@ -348,6 +355,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + /* + * Retire all pending LPIs on this vcpu anyway as we're + * going to destroy it. + */ + vgic_flush_pending_lpis(vcpu); + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); } @@ -359,10 +372,10 @@ static void __kvm_vgic_destroy(struct kvm *kvm) vgic_debug_destroy(kvm); - kvm_vgic_dist_destroy(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) kvm_vgic_vcpu_destroy(vcpu); + + kvm_vgic_dist_destroy(kvm); } void kvm_vgic_destroy(struct kvm *kvm) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index d53d34a33e35..c012a52b19f5 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -96,14 +96,21 @@ out_unlock: * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. + * + * Should any of these fail, behave as if we couldn't create the LPI + * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } return irq; } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index 5945f062d749..a016f07adc28 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -409,24 +409,28 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = { NULL, vgic_mmio_uaccess_write_v2_group, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, - vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_spending, + NULL, vgic_uaccess_write_spending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, - vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + NULL, vgic_uaccess_write_cpending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index e72dcc454247..89a14ec8b33b 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -50,7 +50,8 @@ bool vgic_has_its(struct kvm *kvm) bool vgic_supports_direct_msis(struct kvm *kvm) { - return kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm); + return (kvm_vgic_global_state.has_gicv4_1 || + (kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm))); } /* @@ -538,10 +539,12 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -553,11 +556,11 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, @@ -609,11 +612,13 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, vgic_mmio_read_group, vgic_mmio_write_group, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ISENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_senable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_cenable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -625,12 +630,12 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, vgic_mmio_read_priority, vgic_mmio_write_priority, 32, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 2199302597fa..b2d73fc0d1ef 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -184,6 +184,48 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, } } +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = false; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -219,17 +261,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) -{ - if (is_uaccess) - return; - - irq->pending_latch = true; - vgic_irq_set_phys_active(irq, true); -} - static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && @@ -240,7 +271,6 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -270,22 +300,48 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, continue; } + irq->pending_latch = true; if (irq->hw) - vgic_hw_irq_spending(vcpu, irq, is_uaccess); - else - irq->pending_latch = true; + vgic_irq_set_phys_active(irq, true); + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) { - if (is_uaccess) - return; + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + /* + * GICv2 SGIs are terribly broken. We can't restore + * the source of the interrupt, so just pick the vcpu + * itself as the source... + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source |= BIT(vcpu->vcpu_id); + + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) +{ irq->pending_latch = false; /* @@ -308,7 +364,6 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -339,7 +394,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } if (irq->hw) - vgic_hw_irq_cpending(vcpu, irq, is_uaccess); + vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; @@ -348,8 +403,68 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } } -unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + /* + * More fun with GICv2 SGIs! If we're clearing one of them + * from userspace, which source vcpu to clear? Let's not + * even think of it, and blow the whole set. + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source = 0; + + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* + * If we are fiddling with an IRQ's active state, we have to make sure the IRQ + * is not queued on some running VCPU's LRs, because then the change to the + * active state can be overwritten when the VCPU's state is synced coming back + * from the guest. + * + * For shared interrupts as well as GICv3 private interrupts, we have to + * stop all the VCPUs because interrupts can be migrated while we don't hold + * the IRQ locks and we don't want to be chasing moving targets. + * + * For GICv2 private interrupts we don't have to do anything because + * userspace accesses to the VGIC state already require all VCPUs to be + * stopped, and only the VCPU itself can modify its private interrupts + * active state, which guarantees that the VCPU is not running. + */ +static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_halt_guest(vcpu->kvm); +} + +/* See vgic_access_active_prepare */ +static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_resume_guest(vcpu->kvm); +} + +static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; @@ -359,6 +474,10 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + /* + * Even for HW interrupts, don't evaluate the HW state as + * all the guest is interested in is the virtual state. + */ if (irq->active) value |= (1U << i); @@ -368,6 +487,29 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, return value; } +unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 val; + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + val = __vgic_mmio_read_active(vcpu, addr, len); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); + + return val; +} + +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __vgic_mmio_read_active(vcpu, addr, len); +} + /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) @@ -426,36 +568,6 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } -/* - * If we are fiddling with an IRQ's active state, we have to make sure the IRQ - * is not queued on some running VCPU's LRs, because then the change to the - * active state can be overwritten when the VCPU's state is synced coming back - * from the guest. - * - * For shared interrupts, we have to stop all the VCPUs because interrupts can - * be migrated while we don't hold the IRQ locks and we don't want to be - * chasing moving targets. - * - * For private interrupts we don't have to do anything because userspace - * accesses to the VGIC state already require all VCPUs to be stopped, and - * only the VCPU itself can modify its private interrupts active state, which - * guarantees that the VCPU is not running. - */ -static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_halt_guest(vcpu->kvm); -} - -/* See vgic_change_active_prepare */ -static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_resume_guest(vcpu->kvm); -} - static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) @@ -477,11 +589,11 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } @@ -514,11 +626,11 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h index 5af2aefad435..fefcca2b14dc 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.h +++ b/virt/kvm/arm/vgic/vgic-mmio.h @@ -138,6 +138,14 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); @@ -149,9 +157,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); |