diff options
216 files changed, 1165 insertions, 568 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 46b826fcb5ad..7ccd158b3894 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2545,7 +2545,7 @@ mem_encrypt=on: Activate SME mem_encrypt=off: Do not activate SME - Refer to Documentation/virtual/kvm/amd-memory-encryption.rst + Refer to Documentation/virt/kvm/amd-memory-encryption.rst for details on when memory encryption can be activated. mem_sleep_default= [SUSPEND] Default system suspend mode: diff --git a/Documentation/hwmon/k8temp.rst b/Documentation/hwmon/k8temp.rst index 72da12aa17e5..fe9109521056 100644 --- a/Documentation/hwmon/k8temp.rst +++ b/Documentation/hwmon/k8temp.rst @@ -9,7 +9,7 @@ Supported chips: Addresses scanned: PCI space - Datasheet: http://support.amd.com/us/Processor_TechDocs/32559.pdf + Datasheet: http://www.amd.com/system/files/TechDocs/32559.pdf Author: Rudolf Marek diff --git a/Documentation/virtual/index.rst b/Documentation/virt/index.rst index 062ffb527043..062ffb527043 100644 --- a/Documentation/virtual/index.rst +++ b/Documentation/virt/index.rst diff --git a/Documentation/virtual/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst index d18c97b4e140..d18c97b4e140 100644 --- a/Documentation/virtual/kvm/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/amd-memory-encryption.rst diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virt/kvm/api.txt index e54a3f51ddc5..2d067767b617 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -3781,7 +3781,7 @@ encrypted VMs. Currently, this ioctl is used for issuing Secure Encrypted Virtualization (SEV) commands on AMD Processors. The SEV commands are defined in -Documentation/virtual/kvm/amd-memory-encryption.rst. +Documentation/virt/kvm/amd-memory-encryption.rst. 4.111 KVM_MEMORY_ENCRYPT_REG_REGION diff --git a/Documentation/virtual/kvm/arm/hyp-abi.txt b/Documentation/virt/kvm/arm/hyp-abi.txt index a20a0bee268d..a20a0bee268d 100644 --- a/Documentation/virtual/kvm/arm/hyp-abi.txt +++ b/Documentation/virt/kvm/arm/hyp-abi.txt diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virt/kvm/arm/psci.txt index 559586fc9d37..559586fc9d37 100644 --- a/Documentation/virtual/kvm/arm/psci.txt +++ b/Documentation/virt/kvm/arm/psci.txt diff --git a/Documentation/virtual/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst index 01b081f6e7ea..01b081f6e7ea 100644 --- a/Documentation/virtual/kvm/cpuid.rst +++ b/Documentation/virt/kvm/cpuid.rst diff --git a/Documentation/virtual/kvm/devices/README b/Documentation/virt/kvm/devices/README index 34a69834124a..34a69834124a 100644 --- a/Documentation/virtual/kvm/devices/README +++ b/Documentation/virt/kvm/devices/README diff --git a/Documentation/virtual/kvm/devices/arm-vgic-its.txt b/Documentation/virt/kvm/devices/arm-vgic-its.txt index eeaa95b893a8..eeaa95b893a8 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic-its.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-its.txt diff --git a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt b/Documentation/virt/kvm/devices/arm-vgic-v3.txt index ff290b43c8e5..ff290b43c8e5 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-v3.txt diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virt/kvm/devices/arm-vgic.txt index 97b6518148f8..97b6518148f8 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic.txt +++ b/Documentation/virt/kvm/devices/arm-vgic.txt diff --git a/Documentation/virtual/kvm/devices/mpic.txt b/Documentation/virt/kvm/devices/mpic.txt index 8257397adc3c..8257397adc3c 100644 --- a/Documentation/virtual/kvm/devices/mpic.txt +++ b/Documentation/virt/kvm/devices/mpic.txt diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virt/kvm/devices/s390_flic.txt index a4e20a090174..a4e20a090174 100644 --- a/Documentation/virtual/kvm/devices/s390_flic.txt +++ b/Documentation/virt/kvm/devices/s390_flic.txt diff --git a/Documentation/virtual/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt index 2b5dab16c4f2..2b5dab16c4f2 100644 --- a/Documentation/virtual/kvm/devices/vcpu.txt +++ b/Documentation/virt/kvm/devices/vcpu.txt diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virt/kvm/devices/vfio.txt index 528c77c8022c..528c77c8022c 100644 --- a/Documentation/virtual/kvm/devices/vfio.txt +++ b/Documentation/virt/kvm/devices/vfio.txt diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virt/kvm/devices/vm.txt index 4ffb82b02468..4ffb82b02468 100644 --- a/Documentation/virtual/kvm/devices/vm.txt +++ b/Documentation/virt/kvm/devices/vm.txt diff --git a/Documentation/virtual/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.txt index 42864935ac5d..42864935ac5d 100644 --- a/Documentation/virtual/kvm/devices/xics.txt +++ b/Documentation/virt/kvm/devices/xics.txt diff --git a/Documentation/virtual/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.txt index 9a24a4525253..9a24a4525253 100644 --- a/Documentation/virtual/kvm/devices/xive.txt +++ b/Documentation/virt/kvm/devices/xive.txt diff --git a/Documentation/virtual/kvm/halt-polling.txt b/Documentation/virt/kvm/halt-polling.txt index 4f791b128dd2..4f791b128dd2 100644 --- a/Documentation/virtual/kvm/halt-polling.txt +++ b/Documentation/virt/kvm/halt-polling.txt diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virt/kvm/hypercalls.txt index da210651f714..5f6d291bd004 100644 --- a/Documentation/virtual/kvm/hypercalls.txt +++ b/Documentation/virt/kvm/hypercalls.txt @@ -18,7 +18,7 @@ S390: number in R1. For further information on the S390 diagnose call as supported by KVM, - refer to Documentation/virtual/kvm/s390-diag.txt. + refer to Documentation/virt/kvm/s390-diag.txt. PowerPC: It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers. @@ -26,7 +26,7 @@ S390: KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions' property inside the device tree's /hypervisor node. - For more information refer to Documentation/virtual/kvm/ppc-pv.txt + For more information refer to Documentation/virt/kvm/ppc-pv.txt MIPS: KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall diff --git a/Documentation/virtual/kvm/index.rst b/Documentation/virt/kvm/index.rst index 0b206a06f5be..0b206a06f5be 100644 --- a/Documentation/virtual/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virt/kvm/locking.txt index 635cd6eaf714..635cd6eaf714 100644 --- a/Documentation/virtual/kvm/locking.txt +++ b/Documentation/virt/kvm/locking.txt diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virt/kvm/mmu.txt index 2efe0efc516e..1b9880dfba0a 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virt/kvm/mmu.txt @@ -298,7 +298,7 @@ Handling a page fault is performed as follows: vcpu->arch.mmio_gfn, and call the emulator - If both P bit and R/W bit of error code are set, this could possibly be handled as a "fast page fault" (fixed without taking the MMU lock). See - the description in Documentation/virtual/kvm/locking.txt. + the description in Documentation/virt/kvm/locking.txt. - if needed, walk the guest page tables to determine the guest translation (gva->gpa or ngpa->gpa) - if permissions are insufficient, reflect the fault back to the guest diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virt/kvm/msr.txt index df1f4338b3ca..df1f4338b3ca 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virt/kvm/msr.txt diff --git a/Documentation/virtual/kvm/nested-vmx.txt b/Documentation/virt/kvm/nested-vmx.txt index 97eb1353e962..97eb1353e962 100644 --- a/Documentation/virtual/kvm/nested-vmx.txt +++ b/Documentation/virt/kvm/nested-vmx.txt diff --git a/Documentation/virtual/kvm/ppc-pv.txt b/Documentation/virt/kvm/ppc-pv.txt index e26115ce4258..e26115ce4258 100644 --- a/Documentation/virtual/kvm/ppc-pv.txt +++ b/Documentation/virt/kvm/ppc-pv.txt diff --git a/Documentation/virtual/kvm/review-checklist.txt b/Documentation/virt/kvm/review-checklist.txt index a83b27635fdd..499af499e296 100644 --- a/Documentation/virtual/kvm/review-checklist.txt +++ b/Documentation/virt/kvm/review-checklist.txt @@ -7,7 +7,7 @@ Review checklist for kvm patches 2. Patches should be against kvm.git master branch. 3. If the patch introduces or modifies a new userspace API: - - the API must be documented in Documentation/virtual/kvm/api.txt + - the API must be documented in Documentation/virt/kvm/api.txt - the API must be discoverable using KVM_CHECK_EXTENSION 4. New state must include support for save/restore. diff --git a/Documentation/virtual/kvm/s390-diag.txt b/Documentation/virt/kvm/s390-diag.txt index 7c52e5f8b210..7c52e5f8b210 100644 --- a/Documentation/virtual/kvm/s390-diag.txt +++ b/Documentation/virt/kvm/s390-diag.txt diff --git a/Documentation/virtual/kvm/timekeeping.txt b/Documentation/virt/kvm/timekeeping.txt index 76808a17ad84..76808a17ad84 100644 --- a/Documentation/virtual/kvm/timekeeping.txt +++ b/Documentation/virt/kvm/timekeeping.txt diff --git a/Documentation/virtual/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 5feb3706a7ae..5feb3706a7ae 100644 --- a/Documentation/virtual/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst diff --git a/Documentation/virtual/paravirt_ops.rst b/Documentation/virt/paravirt_ops.rst index 6b789d27cead..6b789d27cead 100644 --- a/Documentation/virtual/paravirt_ops.rst +++ b/Documentation/virt/paravirt_ops.rst diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virt/uml/UserModeLinux-HOWTO.txt index 87b80f589e1c..87b80f589e1c 100644 --- a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt +++ b/Documentation/virt/uml/UserModeLinux-HOWTO.txt diff --git a/MAINTAINERS b/MAINTAINERS index 3d5577d5ca3d..ce6546c02dff 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8808,7 +8808,7 @@ L: kvm@vger.kernel.org W: http://www.linux-kvm.org T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git S: Supported -F: Documentation/virtual/kvm/ +F: Documentation/virt/kvm/ F: include/trace/events/kvm.h F: include/uapi/asm-generic/kvm* F: include/uapi/linux/kvm* @@ -12137,7 +12137,7 @@ M: Thomas Hellstrom <thellstrom@vmware.com> M: "VMware, Inc." <pv-drivers@vmware.com> L: virtualization@lists.linux-foundation.org S: Supported -F: Documentation/virtual/paravirt_ops.txt +F: Documentation/virt/paravirt_ops.txt F: arch/*/kernel/paravirt* F: arch/*/include/asm/paravirt*.h F: include/linux/hypervisor.h @@ -13725,6 +13725,7 @@ F: drivers/mtd/nand/raw/r852.c F: drivers/mtd/nand/raw/r852.h RISC-V ARCHITECTURE +M: Paul Walmsley <paul.walmsley@sifive.com> M: Palmer Dabbelt <palmer@sifive.com> M: Albert Ou <aou@eecs.berkeley.edu> L: linux-riscv@lists.infradead.org @@ -16854,7 +16855,7 @@ W: http://user-mode-linux.sourceforge.net Q: https://patchwork.ozlabs.org/project/linux-um/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git S: Maintained -F: Documentation/virtual/uml/ +F: Documentation/virt/uml/ F: arch/um/ F: arch/x86/um/ F: fs/hostfs/ diff --git a/arch/parisc/include/asm/kprobes.h b/arch/parisc/include/asm/kprobes.h index e09cf2deeafe..904034da4974 100644 --- a/arch/parisc/include/asm/kprobes.h +++ b/arch/parisc/include/asm/kprobes.h @@ -50,6 +50,10 @@ struct kprobe_ctlblk { int __kprobes parisc_kprobe_break_handler(struct pt_regs *regs); int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs); +static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + return 0; +} #endif /* CONFIG_KPROBES */ #endif /* _PARISC_KPROBES_H */ diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index ba67893a1d72..df46b0e5a915 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -63,7 +63,7 @@ ENTRY_CFI(flush_tlb_all_local) /* Flush Instruction Tlb */ - LDREG ITLB_SID_BASE(%r1), %r20 +88: LDREG ITLB_SID_BASE(%r1), %r20 LDREG ITLB_SID_STRIDE(%r1), %r21 LDREG ITLB_SID_COUNT(%r1), %r22 LDREG ITLB_OFF_BASE(%r1), %arg0 @@ -103,6 +103,7 @@ fitonemiddle: /* Loop if LOOP = 1 */ add %r21, %r20, %r20 /* increment space */ fitdone: + ALTERNATIVE(88b, fitdone, ALT_COND_NO_SPLIT_TLB, INSN_NOP) /* Flush Data Tlb */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d8dcd8820369..77f6ebf97113 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -121,6 +121,7 @@ config PPC select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED + select ARCH_HAS_DMA_MMAP_PGPROT select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 463c63a9fcf1..11112023e327 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -302,9 +302,14 @@ #define H_SCM_UNBIND_MEM 0x3F0 #define H_SCM_QUERY_BLOCK_MEM_BINDING 0x3F4 #define H_SCM_QUERY_LOGICAL_MEM_BINDING 0x3F8 -#define H_SCM_MEM_QUERY 0x3FC -#define H_SCM_BLOCK_CLEAR 0x400 -#define MAX_HCALL_OPCODE H_SCM_BLOCK_CLEAR +#define H_SCM_UNBIND_ALL 0x3FC +#define H_SCM_HEALTH 0x400 +#define H_SCM_PERFORMANCE_STATS 0x418 +#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS + +/* Scope args for H_SCM_UNBIND_ALL */ +#define H_UNBIND_SCOPE_ALL (0x1) +#define H_UNBIND_SCOPE_DRC (0x2) /* H_VIOCTL functions */ #define H_GET_VIOA_DUMP_SIZE 0x01 diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h index dc9a1ca70edf..c6bbe9778d3c 100644 --- a/arch/powerpc/include/asm/pmc.h +++ b/arch/powerpc/include/asm/pmc.h @@ -27,11 +27,10 @@ static inline void ppc_set_pmu_inuse(int inuse) #ifdef CONFIG_PPC_PSERIES get_lppaca()->pmcregs_in_use = inuse; #endif - } else { + } #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - get_paca()->pmcregs_in_use = inuse; + get_paca()->pmcregs_in_use = inuse; #endif - } #endif } diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index 01555c6ae0f5..be48c2215fa2 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -31,7 +31,7 @@ * Struct fields are always 32 or 64 bit aligned, depending on them being 32 * or 64 bit wide respectively. * - * See Documentation/virtual/kvm/ppc-pv.txt + * See Documentation/virt/kvm/ppc-pv.txt */ struct kvm_vcpu_arch_shared { __u64 scratch1; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 56dfa7a2a6f2..ea0c69236789 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -49,7 +49,8 @@ obj-y := cputable.o ptrace.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o + of_platform.o prom_parse.o \ + dma-common.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o diff --git a/arch/powerpc/kernel/dma-common.c b/arch/powerpc/kernel/dma-common.c new file mode 100644 index 000000000000..dc7ef6b17b69 --- /dev/null +++ b/arch/powerpc/kernel/dma-common.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Contains common dma routines for all powerpc platforms. + * + * Copyright (C) 2019 Shawn Anastasio. + */ + +#include <linux/mm.h> +#include <linux/dma-noncoherent.h> + +pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + return pgprot_noncached(prot); + return prot; +} diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index f50b708d6d77..98600b276f76 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1198,6 +1198,9 @@ SYSCALL_DEFINE0(rt_sigreturn) goto bad; if (MSR_TM_ACTIVE(msr_hi<<32)) { + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto bad; /* We only recheckpoint on return if we're * transaction. */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2f80e270c7b0..117515564ec7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -771,6 +771,11 @@ SYSCALL_DEFINE0(rt_sigreturn) if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; + + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (__get_user(uc_transact, &uc->uc_link)) goto badframe; if (restore_tm_sigcontexts(current, &uc->uc_mcontext, diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ec1804f822af..cde3f5a4b3e4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3569,9 +3569,18 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); if (kvmhv_on_pseries()) { + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_load_hv_regs_and_go() below otherwise. + */ + unsigned long host_psscr; /* call our hypervisor to load up HV regs and go */ struct hv_guest_state hvregs; + host_psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); kvmhv_save_hv_regs(vcpu, &hvregs); hvregs.lpcr = lpcr; vcpu->arch.regs.msr = vcpu->arch.shregs.msr; @@ -3590,6 +3599,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.shregs.msr = vcpu->arch.regs.msr; vcpu->arch.shregs.dar = mfspr(SPRN_DAR); vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, host_psscr); /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && @@ -3654,6 +3665,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.vpa.dirty = 1; save_pmu = lp->pmcregs_in_use; } + /* Must save pmu if this guest is capable of running nested guests */ + save_pmu |= nesting_enabled(vcpu->kvm); kvmhv_save_guest_pmu(vcpu, save_pmu); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 6ca0d7376a9f..e3ba67095895 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1986,10 +1986,8 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->single_escalation = xive_native_has_single_escalation(); - if (ret) { - kfree(xive); + if (ret) return ret; - } return 0; } diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 5596c8ec221a..a998823f68a3 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -1090,9 +1090,9 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) xive->ops = &kvmppc_xive_native_ops; if (ret) - kfree(xive); + return ret; - return ret; + return 0; } /* diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 9a5963e07a82..b8ad14bb1170 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1899,11 +1899,20 @@ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, * * For guests on platforms before POWER9, we clamp the it limit to 1G * to avoid some funky things such as RTAS bugs etc... + * + * On POWER9 we limit to 1TB in case the host erroneously told us that + * the RMA was >1TB. Effective address bits 0:23 are treated as zero + * (meaning the access is aliased to zero i.e. addr = addr % 1TB) + * for virtual real mode addressing and so it doesn't make sense to + * have an area larger than 1TB as it can't be addressed. */ if (!early_cpu_has_feature(CPU_FTR_HVMODE)) { ppc64_rma_size = first_memblock_size; if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000); + else + ppc64_rma_size = min_t(u64, ppc64_rma_size, + 1UL << SID_SHIFT_1T); /* Finally limit subsequent allocations */ memblock_set_current_limit(ppc64_rma_size); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9259337d7374..9191a66b3bc5 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -239,7 +239,7 @@ void __init paging_init(void) #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - ((1UL << ARCH_ZONE_DMA_BITS) - 1) >> PAGE_SHIFT); + 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index c8ec670ee924..2c07908359b2 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -11,6 +11,7 @@ #include <linux/sched.h> #include <linux/libnvdimm.h> #include <linux/platform_device.h> +#include <linux/delay.h> #include <asm/plpar_wrappers.h> @@ -43,8 +44,9 @@ struct papr_scm_priv { static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; uint64_t saved = 0; + uint64_t token; + int64_t rc; /* * When the hypervisor cannot map all the requested memory in a single @@ -64,6 +66,10 @@ static int drc_pmem_bind(struct papr_scm_priv *p) } while (rc == H_BUSY); if (rc) { + /* H_OVERLAP needs a separate error path */ + if (rc == H_OVERLAP) + return -EBUSY; + dev_err(&p->pdev->dev, "bind err: %lld\n", rc); return -ENXIO; } @@ -78,22 +84,36 @@ static int drc_pmem_bind(struct papr_scm_priv *p) static int drc_pmem_unbind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; + uint64_t token = 0; + int64_t rc; - token = 0; + dev_dbg(&p->pdev->dev, "unbind drc %x\n", p->drc_index); - /* NB: unbind has the same retry requirements mentioned above */ + /* NB: unbind has the same retry requirements as drc_pmem_bind() */ do { - rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index, - p->bound_addr, p->blocks, token); + + /* Unbind of all SCM resources associated with drcIndex */ + rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC, + p->drc_index, token); token = ret[0]; - cond_resched(); + + /* Check if we are stalled for some time */ + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } else if (rc == H_BUSY) { + cond_resched(); + } + } while (rc == H_BUSY); if (rc) dev_err(&p->pdev->dev, "unbind error: %lld\n", rc); + else + dev_dbg(&p->pdev->dev, "unbind drc %x complete\n", + p->drc_index); - return !!rc; + return rc == H_SUCCESS ? 0 : -ENXIO; } static int papr_scm_meta_get(struct papr_scm_priv *p, @@ -389,6 +409,14 @@ static int papr_scm_probe(struct platform_device *pdev) /* request the hypervisor to bind this region to somewhere in memory */ rc = drc_pmem_bind(p); + + /* If phyp says drc memory still bound then force unbound and retry */ + if (rc == -EBUSY) { + dev_warn(&pdev->dev, "Retrying bind after unbinding\n"); + drc_pmem_unbind(p); + rc = drc_pmem_bind(p); + } + if (rc) goto err; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 082c7e1c20f0..1cdb39575eae 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -479,7 +479,7 @@ static int xive_find_target_in_mask(const struct cpumask *mask, * Now go through the entire mask until we find a valid * target. */ - for (;;) { + do { /* * We re-check online as the fallback case passes us * an untested affinity mask @@ -487,12 +487,11 @@ static int xive_find_target_in_mask(const struct cpumask *mask, if (cpu_online(cpu) && xive_try_pick_target(cpu)) return cpu; cpu = cpumask_next(cpu, mask); - if (cpu == first) - break; /* Wrap around */ if (cpu >= nr_cpu_ids) cpu = cpumask_first(mask); - } + } while (cpu != first); + return -1; } diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 40983491b95f..9bf63f0ab253 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -217,5 +217,20 @@ #size-cells = <0>; status = "disabled"; }; + eth0: ethernet@10090000 { + compatible = "sifive,fu540-c000-gem"; + interrupt-parent = <&plic0>; + interrupts = <53>; + reg = <0x0 0x10090000 0x0 0x2000 + 0x0 0x100a0000 0x0 0x1000>; + local-mac-address = [00 00 00 00 00 00]; + clock-names = "pclk", "hclk"; + clocks = <&prci PRCI_CLK_GEMGXLPLL>, + <&prci PRCI_CLK_GEMGXLPLL>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + }; }; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 0b55c53c08c7..93d68cbd64fe 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -76,3 +76,12 @@ disable-wp; }; }; + +ð0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 1efaeddf1e4b..16970f246860 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -22,6 +22,7 @@ generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mm-arch-hooks.h +generic-y += msi.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h index 0e2eeeb1fd27..13ce76cc5aff 100644 --- a/arch/riscv/include/uapi/asm/unistd.h +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -18,6 +18,7 @@ #ifdef __LP64__ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT +#define __ARCH_WANT_SYS_CLONE3 #endif /* __LP64__ */ #include <asm-generic/unistd.h> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8282b8d41209..7b0a4ee77313 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -607,15 +607,16 @@ struct kvm_vcpu_arch { /* * QEMU userspace and the guest each have their own FPU state. - * In vcpu_run, we switch between the user, maintained in the - * task_struct struct, and guest FPU contexts. While running a VCPU, - * the VCPU thread will have the guest FPU context. + * In vcpu_run, we switch between the user and guest FPU contexts. + * While running a VCPU, the VCPU thread will have the guest FPU + * context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ + struct fpu *user_fpu; struct fpu *guest_fpu; u64 xcr0; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8f72526e2f68..24843cf49579 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3466,7 +3466,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, /* * Currently, fast page fault only works for direct mapping * since the gfn is not stable for indirect shadow page. See - * Documentation/virtual/kvm/locking.txt to get more detail. + * Documentation/virt/kvm/locking.txt to get more detail. */ fault_handled = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 19f69df96758..7eafc6907861 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2143,12 +2143,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } + svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!svm->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_svm; + } + svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!svm->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_svm; + goto free_user_fpu; } err = kvm_vcpu_init(&svm->vcpu, kvm, id); @@ -2211,6 +2219,8 @@ uninit: kvm_vcpu_uninit(&svm->vcpu); free_svm: kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); free_partial_svm: kmem_cache_free(kvm_vcpu_cache, svm); out: @@ -2241,6 +2251,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, svm); } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0f1378789bd0..ced9fba32598 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -220,6 +220,8 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; + kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu); + vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); @@ -232,7 +234,9 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); + vmx->nested.cached_vmcs12 = NULL; kfree(vmx->nested.cached_shadow_vmcs12); + vmx->nested.cached_shadow_vmcs12 = NULL; /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a279447eb75b..074385c86c09 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6598,6 +6598,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, vmx); } @@ -6613,12 +6614,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); + vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vmx->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_vcpu; + } + vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_vcpu; + goto free_user_fpu; } vmx->vpid = allocate_vpid(); @@ -6721,6 +6730,8 @@ uninit_vcpu: free_vcpu: free_vpid(vmx->vpid); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); free_partial_vcpu: kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 58305cf81182..c6d951cbd76c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3306,6 +3306,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); + /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -7202,7 +7206,7 @@ static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id) rcu_read_unlock(); - if (target) + if (target && READ_ONCE(target->ready)) kvm_vcpu_yield_to(target); } @@ -7242,6 +7246,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) break; case KVM_HC_KICK_CPU: kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + kvm_sched_yield(vcpu->kvm, a1); ret = 0; break; #ifdef CONFIG_X86_64 @@ -7990,9 +7995,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) trace_kvm_entry(vcpu->vcpu_id); guest_enter_irqoff(); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); + /* The preempt notifier should have taken care of the FPU already. */ + WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -8270,7 +8274,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(¤t->thread.fpu); + copy_fpregs_to_fpstate(vcpu->arch.user_fpu); /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8287,7 +8291,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) fpregs_lock(); copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(¤t->thread.fpu.state); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); fpregs_unlock(); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 72860325245a..586fcfe227ea 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -3354,38 +3354,57 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq) * there is no active group, then the primary expectation for * this device is probably a high throughput. * - * We are now left only with explaining the additional - * compound condition that is checked below for deciding - * whether the scenario is asymmetric. To explain this - * compound condition, we need to add that the function + * We are now left only with explaining the two sub-conditions in the + * additional compound condition that is checked below for deciding + * whether the scenario is asymmetric. To explain the first + * sub-condition, we need to add that the function * bfq_asymmetric_scenario checks the weights of only - * non-weight-raised queues, for efficiency reasons (see - * comments on bfq_weights_tree_add()). Then the fact that - * bfqq is weight-raised is checked explicitly here. More - * precisely, the compound condition below takes into account - * also the fact that, even if bfqq is being weight-raised, - * the scenario is still symmetric if all queues with requests - * waiting for completion happen to be - * weight-raised. Actually, we should be even more precise - * here, and differentiate between interactive weight raising - * and soft real-time weight raising. + * non-weight-raised queues, for efficiency reasons (see comments on + * bfq_weights_tree_add()). Then the fact that bfqq is weight-raised + * is checked explicitly here. More precisely, the compound condition + * below takes into account also the fact that, even if bfqq is being + * weight-raised, the scenario is still symmetric if all queues with + * requests waiting for completion happen to be + * weight-raised. Actually, we should be even more precise here, and + * differentiate between interactive weight raising and soft real-time + * weight raising. + * + * The second sub-condition checked in the compound condition is + * whether there is a fair amount of already in-flight I/O not + * belonging to bfqq. If so, I/O dispatching is to be plugged, for the + * following reason. The drive may decide to serve in-flight + * non-bfqq's I/O requests before bfqq's ones, thereby delaying the + * arrival of new I/O requests for bfqq (recall that bfqq is sync). If + * I/O-dispatching is not plugged, then, while bfqq remains empty, a + * basically uncontrolled amount of I/O from other queues may be + * dispatched too, possibly causing the service of bfqq's I/O to be + * delayed even longer in the drive. This problem gets more and more + * serious as the speed and the queue depth of the drive grow, + * because, as these two quantities grow, the probability to find no + * queue busy but many requests in flight grows too. By contrast, + * plugging I/O dispatching minimizes the delay induced by already + * in-flight I/O, and enables bfqq to recover the bandwidth it may + * lose because of this delay. * * As a side note, it is worth considering that the above - * device-idling countermeasures may however fail in the - * following unlucky scenario: if idling is (correctly) - * disabled in a time period during which all symmetry - * sub-conditions hold, and hence the device is allowed to - * enqueue many requests, but at some later point in time some - * sub-condition stops to hold, then it may become impossible - * to let requests be served in the desired order until all - * the requests already queued in the device have been served. + * device-idling countermeasures may however fail in the following + * unlucky scenario: if I/O-dispatch plugging is (correctly) disabled + * in a time period during which all symmetry sub-conditions hold, and + * therefore the device is allowed to enqueue many requests, but at + * some later point in time some sub-condition stops to hold, then it + * may become impossible to make requests be served in the desired + * order until all the requests already queued in the device have been + * served. The last sub-condition commented above somewhat mitigates + * this problem for weight-raised queues. */ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, struct bfq_queue *bfqq) { return (bfqq->wr_coeff > 1 && - bfqd->wr_busy_queues < - bfq_tot_busy_queues(bfqd)) || + (bfqd->wr_busy_queues < + bfq_tot_busy_queues(bfqd) || + bfqd->rq_in_driver >= + bfqq->dispatched + 4)) || bfq_asymmetric_scenario(bfqd, bfqq); } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 24ed26957367..55a7dc227dfb 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -54,7 +54,7 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ -static bool blkcg_debug_stats = false; +bool blkcg_debug_stats = false; static struct workqueue_struct *blkcg_punt_bio_wq; static bool blkcg_policy_enabled(struct request_queue *q, @@ -944,10 +944,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) dbytes, dios); } - if (!blkcg_debug_stats) - goto next; - - if (atomic_read(&blkg->use_delay)) { + if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { has_stats = true; off += scnprintf(buf+off, size-off, " use_delay=%d delay_nsec=%llu", @@ -967,7 +964,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) has_stats = true; off += written; } -next: + if (has_stats) { if (off < size - 1) { off += scnprintf(buf+off, size-off, "\n"); diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index d973c38ee4fd..0fff7b56df0e 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -917,6 +917,9 @@ static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf, unsigned long long avg_lat; unsigned long long cur_win; + if (!blkcg_debug_stats) + return 0; + if (iolat->ssd) return iolatency_ssd_stat(iolat, buf, size); diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index cf22ab00fefb..126021fc3a11 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -61,15 +61,6 @@ static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) e->type->ops.completed_request(rq, now); } -static inline void blk_mq_sched_started_request(struct request *rq) -{ - struct request_queue *q = rq->q; - struct elevator_queue *e = q->elevator; - - if (e && e->type->ops.started_request) - e->type->ops.started_request(rq); -} - static inline void blk_mq_sched_requeue_request(struct request *rq) { struct request_queue *q = rq->q; diff --git a/block/blk-mq.c b/block/blk-mq.c index b038ec680e84..f78d3287dd82 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -669,8 +669,6 @@ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; - blk_mq_sched_started_request(rq); - trace_block_rq_issue(q, rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { @@ -1960,9 +1958,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) rq = blk_mq_get_request(q, bio, &data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); - if (bio->bi_opf & REQ_NOWAIT) + + cookie = BLK_QC_T_NONE; + if (bio->bi_opf & REQ_NOWAIT_INLINE) + cookie = BLK_QC_T_EAGAIN; + else if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); - return BLK_QC_T_NONE; + return cookie; } trace_block_getrq(q, bio, bio->bi_opf); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 659ccb8b693f..3954c0dc1443 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -202,6 +202,7 @@ static int rq_qos_wake_function(struct wait_queue_entry *curr, return -1; data->got_token = true; + smp_wmb(); list_del_init(&curr->entry); wake_up_process(data->task); return 1; @@ -244,7 +245,9 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, return; prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); + has_sleeper = !wq_has_single_sleeper(&rqw->wait); do { + /* The memory barrier in set_task_state saves us here. */ if (data.got_token) break; if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) { @@ -255,12 +258,14 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, * which means we now have two. Put our local token * and wake anyone else potentially waiting for one. */ + smp_rmb(); if (data.got_token) cleanup_cb(rqw, private_data); break; } io_schedule(); - has_sleeper = false; + has_sleeper = true; + set_current_state(TASK_UNINTERRUPTIBLE); } while (1); finish_wait(&rqw->wait, &data.wq); } diff --git a/block/genhd.c b/block/genhd.c index 97887e59f3b2..54f1f0d381f4 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1969,7 +1969,7 @@ static const struct attribute *disk_events_attrs[] = { * The default polling interval can be specified by the kernel * parameter block.events_dfl_poll_msecs which defaults to 0 * (disable). This can also be modified runtime by writing to - * /sys/module/block/events_dfl_poll_msecs. + * /sys/module/block/parameters/events_dfl_poll_msecs. */ static int disk_events_set_dfl_poll_msecs(const char *val, const struct kernel_param *kp) diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 72312ad2e142..3a36e76eca83 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -408,7 +408,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, hpriv->mmio = devm_ioremap_resource(dev, platform_get_resource(pdev, IORESOURCE_MEM, 0)); if (IS_ERR(hpriv->mmio)) { - dev_err(dev, "no mmio space\n"); rc = PTR_ERR(hpriv->mmio); goto err_out; } diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 90ebfcae0ce6..2b3103c30857 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -5417,7 +5417,7 @@ static int drbd_do_auth(struct drbd_connection *connection) unsigned int key_len; char secret[SHARED_SECRET_MAX]; /* 64 byte */ unsigned int resp_size; - SHASH_DESC_ON_STACK(desc, connection->cram_hmac_tfm); + struct shash_desc *desc; struct packet_info pi; struct net_conf *nc; int err, rv; @@ -5430,6 +5430,13 @@ static int drbd_do_auth(struct drbd_connection *connection) memcpy(secret, nc->shared_secret, key_len); rcu_read_unlock(); + desc = kmalloc(sizeof(struct shash_desc) + + crypto_shash_descsize(connection->cram_hmac_tfm), + GFP_KERNEL); + if (!desc) { + rv = -1; + goto fail; + } desc->tfm = connection->cram_hmac_tfm; rv = crypto_shash_setkey(connection->cram_hmac_tfm, (u8 *)secret, key_len); @@ -5571,7 +5578,10 @@ static int drbd_do_auth(struct drbd_connection *connection) kfree(peers_ch); kfree(response); kfree(right_response); - shash_desc_zero(desc); + if (desc) { + shash_desc_zero(desc); + kfree(desc); + } return rv; } diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 23553ed6b548..2d22d6bf52f2 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -248,16 +248,12 @@ static int __maybe_unused cn_proc_show(struct seq_file *m, void *v) return 0; } -static struct cn_dev cdev = { - .input = cn_rx_skb, -}; - static int cn_init(void) { struct cn_dev *dev = &cdev; struct netlink_kernel_cfg cfg = { .groups = CN_NETLINK_USERS + 0xf, - .input = dev->input, + .input = cn_rx_skb, }; dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg); diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index 93f39a1d4c3d..c66f566a854c 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -131,10 +131,18 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) int err = -ENODEV; cpu = of_get_cpu_node(policy->cpu, NULL); + if (!cpu) + goto out; + max_freqp = of_get_property(cpu, "clock-frequency", NULL); of_node_put(cpu); - if (!cpu) + if (!max_freqp) { + err = -EINVAL; goto out; + } + + /* we need the freq in kHz */ + max_freq = *max_freqp / 1000; dn = of_find_compatible_node(NULL, NULL, "1682m-sdc"); if (!dn) @@ -171,16 +179,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) } pr_debug("init cpufreq on CPU %d\n", policy->cpu); - - max_freqp = of_get_property(cpu, "clock-frequency", NULL); - if (!max_freqp) { - err = -EINVAL; - goto out_unmap_sdcpwr; - } - - /* we need the freq in kHz */ - max_freq = *max_freqp / 1000; - pr_debug("max clock-frequency is at %u kHz\n", max_freq); pr_debug("initializing frequency table\n"); @@ -199,9 +197,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) cpufreq_generic_init(policy, pas_freqs, get_gizmo_latency()); return 0; -out_unmap_sdcpwr: - iounmap(sdcpwr_mapbase); - out_unmap_sdcasr: iounmap(sdcasr_mapbase); out: diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 53446e39a32c..ba8d3d0ef32c 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -157,7 +157,7 @@ config DMI_SCAN_MACHINE_NON_EFI_FALLBACK config ISCSI_IBFT_FIND bool "iSCSI Boot Firmware Table Attributes" - depends on X86 && ACPI + depends on X86 && ISCSI_IBFT default n help This option enables the kernel to find the region of memory @@ -168,7 +168,8 @@ config ISCSI_IBFT_FIND config ISCSI_IBFT tristate "iSCSI Boot Firmware Table Attributes module" select ISCSI_BOOT_SYSFS - depends on ISCSI_IBFT_FIND && SCSI && SCSI_LOWLEVEL + select ISCSI_IBFT_FIND if X86 + depends on ACPI && SCSI && SCSI_LOWLEVEL default n help This option enables support for detection and exposing of iSCSI diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index ab3aa3983833..7e12cbdf957c 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -84,6 +84,10 @@ MODULE_DESCRIPTION("sysfs interface to BIOS iBFT information"); MODULE_LICENSE("GPL"); MODULE_VERSION(IBFT_ISCSI_VERSION); +#ifndef CONFIG_ISCSI_IBFT_FIND +struct acpi_table_ibft *ibft_addr; +#endif + struct ibft_hdr { u8 id; u8 version; diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index e7dff5febe16..d42bc0883a32 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -852,7 +852,7 @@ static const u16 NCT6106_REG_TARGET[] = { 0x111, 0x121, 0x131 }; static const u16 NCT6106_REG_WEIGHT_TEMP_SEL[] = { 0x168, 0x178, 0x188 }; static const u16 NCT6106_REG_WEIGHT_TEMP_STEP[] = { 0x169, 0x179, 0x189 }; static const u16 NCT6106_REG_WEIGHT_TEMP_STEP_TOL[] = { 0x16a, 0x17a, 0x18a }; -static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x17c }; +static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x18b }; static const u16 NCT6106_REG_WEIGHT_TEMP_BASE[] = { 0x16c, 0x17c, 0x18c }; static const u16 NCT6106_REG_WEIGHT_DUTY_BASE[] = { 0x16d, 0x17d, 0x18d }; @@ -3764,6 +3764,7 @@ static int nct6775_probe(struct platform_device *pdev) data->REG_FAN_TIME[0] = NCT6106_REG_FAN_STOP_TIME; data->REG_FAN_TIME[1] = NCT6106_REG_FAN_STEP_UP_TIME; data->REG_FAN_TIME[2] = NCT6106_REG_FAN_STEP_DOWN_TIME; + data->REG_TOLERANCE_H = NCT6106_REG_TOLERANCE_H; data->REG_PWM[0] = NCT6106_REG_PWM; data->REG_PWM[1] = NCT6106_REG_FAN_START_OUTPUT; data->REG_PWM[2] = NCT6106_REG_FAN_STOP_OUTPUT; diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index a7d2b16dd702..30e18eb60da7 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -408,8 +408,10 @@ static ssize_t occ_show_power_1(struct device *dev, static u64 occ_get_powr_avg(u64 *accum, u32 *samples) { - return div64_u64(get_unaligned_be64(accum) * 1000000ULL, - get_unaligned_be32(samples)); + u64 divisor = get_unaligned_be32(samples); + + return (divisor == 0) ? 0 : + div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor); } static ssize_t occ_show_power_2(struct device *dev, diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index eb104c719629..4413aa67000e 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -23,6 +23,8 @@ #include <linux/mem_encrypt.h> #include <asm/pci-direct.h> #include <asm/iommu.h> +#include <asm/apic.h> +#include <asm/msidef.h> #include <asm/gart.h> #include <asm/x86_init.h> #include <asm/iommu_table.h> @@ -1920,6 +1922,90 @@ static int iommu_setup_msi(struct amd_iommu *iommu) return 0; } +#define XT_INT_DEST_MODE(x) (((x) & 0x1ULL) << 2) +#define XT_INT_DEST_LO(x) (((x) & 0xFFFFFFULL) << 8) +#define XT_INT_VEC(x) (((x) & 0xFFULL) << 32) +#define XT_INT_DEST_HI(x) ((((x) >> 24) & 0xFFULL) << 56) + +/** + * Setup the IntCapXT registers with interrupt routing information + * based on the PCI MSI capability block registers, accessed via + * MMIO MSI address low/hi and MSI data registers. + */ +static void iommu_update_intcapxt(struct amd_iommu *iommu) +{ + u64 val; + u32 addr_lo = readl(iommu->mmio_base + MMIO_MSI_ADDR_LO_OFFSET); + u32 addr_hi = readl(iommu->mmio_base + MMIO_MSI_ADDR_HI_OFFSET); + u32 data = readl(iommu->mmio_base + MMIO_MSI_DATA_OFFSET); + bool dm = (addr_lo >> MSI_ADDR_DEST_MODE_SHIFT) & 0x1; + u32 dest = ((addr_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xFF); + + if (x2apic_enabled()) + dest |= MSI_ADDR_EXT_DEST_ID(addr_hi); + + val = XT_INT_VEC(data & 0xFF) | + XT_INT_DEST_MODE(dm) | + XT_INT_DEST_LO(dest) | + XT_INT_DEST_HI(dest); + + /** + * Current IOMMU implemtation uses the same IRQ for all + * 3 IOMMU interrupts. + */ + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET); + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET); + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET); +} + +static void _irq_notifier_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + if (iommu->dev->irq == notify->irq) { + iommu_update_intcapxt(iommu); + break; + } + } +} + +static void _irq_notifier_release(struct kref *ref) +{ +} + +static int iommu_init_intcapxt(struct amd_iommu *iommu) +{ + int ret; + struct irq_affinity_notify *notify = &iommu->intcapxt_notify; + + /** + * IntCapXT requires XTSup=1, which can be inferred + * amd_iommu_xt_mode. + */ + if (amd_iommu_xt_mode != IRQ_REMAP_X2APIC_MODE) + return 0; + + /** + * Also, we need to setup notifier to update the IntCapXT registers + * whenever the irq affinity is changed from user-space. + */ + notify->irq = iommu->dev->irq; + notify->notify = _irq_notifier_notify, + notify->release = _irq_notifier_release, + ret = irq_set_affinity_notifier(iommu->dev->irq, notify); + if (ret) { + pr_err("Failed to register irq affinity notifier (devid=%#x, irq %d)\n", + iommu->devid, iommu->dev->irq); + return ret; + } + + iommu_update_intcapxt(iommu); + iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN); + return ret; +} + static int iommu_init_msi(struct amd_iommu *iommu) { int ret; @@ -1936,6 +2022,10 @@ static int iommu_init_msi(struct amd_iommu *iommu) return ret; enable_faults: + ret = iommu_init_intcapxt(iommu); + if (ret) + return ret; + iommu_feature_enable(iommu, CONTROL_EVT_INT_EN); if (iommu->ppr_log != NULL) diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 52c35d557fad..64edd5a9694c 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -60,6 +60,12 @@ #define MMIO_PPR_LOG_OFFSET 0x0038 #define MMIO_GA_LOG_BASE_OFFSET 0x00e0 #define MMIO_GA_LOG_TAIL_OFFSET 0x00e8 +#define MMIO_MSI_ADDR_LO_OFFSET 0x015C +#define MMIO_MSI_ADDR_HI_OFFSET 0x0160 +#define MMIO_MSI_DATA_OFFSET 0x0164 +#define MMIO_INTCAPXT_EVT_OFFSET 0x0170 +#define MMIO_INTCAPXT_PPR_OFFSET 0x0178 +#define MMIO_INTCAPXT_GALOG_OFFSET 0x0180 #define MMIO_CMD_HEAD_OFFSET 0x2000 #define MMIO_CMD_TAIL_OFFSET 0x2008 #define MMIO_EVT_HEAD_OFFSET 0x2010 @@ -150,6 +156,7 @@ #define CONTROL_GALOG_EN 0x1CULL #define CONTROL_GAINT_EN 0x1DULL #define CONTROL_XT_EN 0x32ULL +#define CONTROL_INTCAPXT_EN 0x33ULL #define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT) #define CTRL_INV_TO_NONE 0 @@ -592,6 +599,8 @@ struct amd_iommu { /* DebugFS Info */ struct dentry *debugfs; #endif + /* IRQ notifier for IntCapXT interrupt */ + struct irq_affinity_notify intcapxt_notify; }; static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev) diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index 73a552914455..2b25d9c59336 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -162,9 +162,9 @@ static inline void print_tbl_walk(struct seq_file *m) (u64)0, (u64)0, (u64)0); else seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n", - tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[0], + tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[2], tbl_wlk->pasid_tbl_entry->val[1], - tbl_wlk->pasid_tbl_entry->val[2]); + tbl_wlk->pasid_tbl_entry->val[0]); } static void pasid_tbl_walk(struct seq_file *m, struct pasid_entry *tbl_entry, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac4172c02244..bdaed2da8a55 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -339,8 +339,6 @@ static void domain_exit(struct dmar_domain *domain); static void domain_remove_dev_info(struct dmar_domain *domain); static void dmar_remove_one_dev_info(struct device *dev); static void __dmar_remove_one_dev_info(struct device_domain_info *info); -static void domain_context_clear(struct intel_iommu *iommu, - struct device *dev); static int domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu); static bool device_is_rmrr_locked(struct device *dev); @@ -1833,9 +1831,65 @@ static inline int guestwidth_to_adjustwidth(int gaw) return agaw; } +static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, + int guest_width) +{ + int adjust_width, agaw; + unsigned long sagaw; + int err; + + init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); + + err = init_iova_flush_queue(&domain->iovad, + iommu_flush_iova, iova_entry_free); + if (err) + return err; + + domain_reserve_special_ranges(domain); + + /* calculate AGAW */ + if (guest_width > cap_mgaw(iommu->cap)) + guest_width = cap_mgaw(iommu->cap); + domain->gaw = guest_width; + adjust_width = guestwidth_to_adjustwidth(guest_width); + agaw = width_to_agaw(adjust_width); + sagaw = cap_sagaw(iommu->cap); + if (!test_bit(agaw, &sagaw)) { + /* hardware doesn't support it, choose a bigger one */ + pr_debug("Hardware doesn't support agaw %d\n", agaw); + agaw = find_next_bit(&sagaw, 5, agaw); + if (agaw >= 5) + return -ENODEV; + } + domain->agaw = agaw; + + if (ecap_coherent(iommu->ecap)) + domain->iommu_coherency = 1; + else + domain->iommu_coherency = 0; + + if (ecap_sc_support(iommu->ecap)) + domain->iommu_snooping = 1; + else + domain->iommu_snooping = 0; + + if (intel_iommu_superpage) + domain->iommu_superpage = fls(cap_super_page_val(iommu->cap)); + else + domain->iommu_superpage = 0; + + domain->nid = iommu->node; + + /* always allocate the top pgd */ + domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); + if (!domain->pgd) + return -ENOMEM; + __iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE); + return 0; +} + static void domain_exit(struct dmar_domain *domain) { - struct page *freelist; /* Remove associated devices and clear attached or cached domains */ domain_remove_dev_info(domain); @@ -1843,9 +1897,12 @@ static void domain_exit(struct dmar_domain *domain) /* destroy iovas */ put_iova_domain(&domain->iovad); - freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); + if (domain->pgd) { + struct page *freelist; - dma_free_pagelist(freelist); + freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); + dma_free_pagelist(freelist); + } free_domain_mem(domain); } @@ -2048,26 +2105,9 @@ out_unlock: return ret; } -struct domain_context_mapping_data { - struct dmar_domain *domain; - struct intel_iommu *iommu; - struct pasid_table *table; -}; - -static int domain_context_mapping_cb(struct pci_dev *pdev, - u16 alias, void *opaque) -{ - struct domain_context_mapping_data *data = opaque; - - return domain_context_mapping_one(data->domain, data->iommu, - data->table, PCI_BUS_NUM(alias), - alias & 0xff); -} - static int domain_context_mapping(struct dmar_domain *domain, struct device *dev) { - struct domain_context_mapping_data data; struct pasid_table *table; struct intel_iommu *iommu; u8 bus, devfn; @@ -2077,17 +2117,7 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev) return -ENODEV; table = intel_pasid_get_table(dev); - - if (!dev_is_pci(dev)) - return domain_context_mapping_one(domain, iommu, table, - bus, devfn); - - data.domain = domain; - data.iommu = iommu; - data.table = table; - - return pci_for_each_dma_alias(to_pci_dev(dev), - &domain_context_mapping_cb, &data); + return domain_context_mapping_one(domain, iommu, table, bus, devfn); } static int domain_context_mapped_cb(struct pci_dev *pdev, @@ -2513,31 +2543,6 @@ static int get_last_alias(struct pci_dev *pdev, u16 alias, void *opaque) return 0; } -static int domain_init(struct dmar_domain *domain, int guest_width) -{ - int adjust_width; - - init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); - domain_reserve_special_ranges(domain); - - /* calculate AGAW */ - domain->gaw = guest_width; - adjust_width = guestwidth_to_adjustwidth(guest_width); - domain->agaw = width_to_agaw(adjust_width); - - domain->iommu_coherency = 0; - domain->iommu_snooping = 0; - domain->iommu_superpage = 0; - domain->max_addr = 0; - - /* always allocate the top pgd */ - domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); - if (!domain->pgd) - return -ENOMEM; - domain_flush_cache(domain, domain->pgd, PAGE_SIZE); - return 0; -} - static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw) { struct device_domain_info *info; @@ -2575,19 +2580,11 @@ static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw) domain = alloc_domain(0); if (!domain) return NULL; - - if (domain_init(domain, gaw)) { + if (domain_init(domain, iommu, gaw)) { domain_exit(domain); return NULL; } - if (init_iova_flush_queue(&domain->iovad, - iommu_flush_iova, - iova_entry_free)) { - pr_warn("iova flush queue initialization failed\n"); - intel_iommu_strict = 1; - } - out: return domain; } @@ -2692,6 +2689,8 @@ static int domain_prepare_identity_map(struct device *dev, return iommu_domain_identity_map(domain, start, end); } +static int md_domain_init(struct dmar_domain *domain, int guest_width); + static int __init si_domain_init(int hw) { struct dmar_rmrr_unit *rmrr; @@ -2702,7 +2701,7 @@ static int __init si_domain_init(int hw) if (!si_domain) return -EFAULT; - if (domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { domain_exit(si_domain); return -EFAULT; } @@ -3564,7 +3563,8 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) freelist = domain_unmap(domain, start_pfn, last_pfn); - if (intel_iommu_strict || (pdev && pdev->untrusted)) { + if (intel_iommu_strict || (pdev && pdev->untrusted) || + !has_iova_flush_queue(&domain->iovad)) { iommu_flush_iotlb_psi(iommu, domain, start_pfn, nrpages, !freelist, 0); /* free iova */ @@ -4758,28 +4758,6 @@ out_free_dmar: return ret; } -static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque) -{ - struct intel_iommu *iommu = opaque; - - domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff); - return 0; -} - -/* - * NB - intel-iommu lacks any sort of reference counting for the users of - * dependent devices. If multiple endpoints have intersecting dependent - * devices, unbinding the driver from any one of them will possibly leave - * the others unable to operate. - */ -static void domain_context_clear(struct intel_iommu *iommu, struct device *dev) -{ - if (!iommu || !dev || !dev_is_pci(dev)) - return; - - pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu); -} - static void __dmar_remove_one_dev_info(struct device_domain_info *info) { struct dmar_domain *domain; @@ -4800,7 +4778,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) PASID_RID2PASID); iommu_disable_dev_iotlb(info); - domain_context_clear(iommu, info->dev); + domain_context_clear_one(iommu, info->bus, info->devfn); intel_pasid_free_table(info->dev); } @@ -4829,6 +4807,31 @@ static void dmar_remove_one_dev_info(struct device *dev) spin_unlock_irqrestore(&device_domain_lock, flags); } +static int md_domain_init(struct dmar_domain *domain, int guest_width) +{ + int adjust_width; + + init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); + domain_reserve_special_ranges(domain); + + /* calculate AGAW */ + domain->gaw = guest_width; + adjust_width = guestwidth_to_adjustwidth(guest_width); + domain->agaw = width_to_agaw(adjust_width); + + domain->iommu_coherency = 0; + domain->iommu_snooping = 0; + domain->iommu_superpage = 0; + domain->max_addr = 0; + + /* always allocate the top pgd */ + domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); + if (!domain->pgd) + return -ENOMEM; + domain_flush_cache(domain, domain->pgd, PAGE_SIZE); + return 0; +} + static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) { struct dmar_domain *dmar_domain; @@ -4843,7 +4846,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) pr_err("Can't allocate dmar_domain\n"); return NULL; } - if (domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { pr_err("Domain initialization failed\n"); domain_exit(dmar_domain); return NULL; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index d499b2621239..3e1a8a675572 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -54,9 +54,14 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, } EXPORT_SYMBOL_GPL(init_iova_domain); +bool has_iova_flush_queue(struct iova_domain *iovad) +{ + return !!iovad->fq; +} + static void free_iova_flush_queue(struct iova_domain *iovad) { - if (!iovad->fq) + if (!has_iova_flush_queue(iovad)) return; if (timer_pending(&iovad->fq_timer)) @@ -74,13 +79,14 @@ static void free_iova_flush_queue(struct iova_domain *iovad) int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) { + struct iova_fq __percpu *queue; int cpu; atomic64_set(&iovad->fq_flush_start_cnt, 0); atomic64_set(&iovad->fq_flush_finish_cnt, 0); - iovad->fq = alloc_percpu(struct iova_fq); - if (!iovad->fq) + queue = alloc_percpu(struct iova_fq); + if (!queue) return -ENOMEM; iovad->flush_cb = flush_cb; @@ -89,13 +95,17 @@ int init_iova_flush_queue(struct iova_domain *iovad, for_each_possible_cpu(cpu) { struct iova_fq *fq; - fq = per_cpu_ptr(iovad->fq, cpu); + fq = per_cpu_ptr(queue, cpu); fq->head = 0; fq->tail = 0; spin_lock_init(&fq->lock); } + smp_wmb(); + + iovad->fq = queue; + timer_setup(&iovad->fq_timer, fq_flush_timeout, 0); atomic_set(&iovad->fq_timer_on, 0); @@ -127,8 +137,9 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) struct iova *cached_iova; cached_iova = rb_entry(iovad->cached32_node, struct iova, node); - if (free->pfn_hi < iovad->dma_32bit_pfn && - free->pfn_lo >= cached_iova->pfn_lo) { + if (free == cached_iova || + (free->pfn_hi < iovad->dma_32bit_pfn && + free->pfn_lo >= cached_iova->pfn_lo)) { iovad->cached32_node = rb_next(&free->node); iovad->max32_alloc_size = iovad->dma_32bit_pfn; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 26e374fbf57c..20ed838e9413 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -931,6 +931,9 @@ int bch_cached_dev_run(struct cached_dev *dc) if (dc->io_disable) { pr_err("I/O disabled on cached dev %s", dc->backing_dev_name); + kfree(env[1]); + kfree(env[2]); + kfree(buf); return -EIO; } diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 21fb90d66bfc..25c73c13cc7e 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -124,7 +124,7 @@ static inline int check_which(__u32 which) static inline int check_pad(struct v4l2_subdev *sd, __u32 pad) { #if defined(CONFIG_MEDIA_CONTROLLER) - if (sd->entity.graph_obj.mdev) { + if (sd->entity.num_pads) { if (pad >= sd->entity.num_pads) return -EINVAL; return 0; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 656ed80647f0..e2be5a685130 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -285,6 +285,9 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata) hw_cons = le16_to_cpu(*txdata->tx_cons_sb); sw_cons = txdata->tx_pkt_cons; + /* Ensure subsequent loads occur after hw_cons */ + smp_rmb(); + while (sw_cons != hw_cons) { u16 pkt_cons; diff --git a/drivers/net/ethernet/chelsio/cxgb/my3126.c b/drivers/net/ethernet/chelsio/cxgb/my3126.c index 20c09cc4b323..60aa45b375b6 100644 --- a/drivers/net/ethernet/chelsio/cxgb/my3126.c +++ b/drivers/net/ethernet/chelsio/cxgb/my3126.c @@ -94,7 +94,7 @@ static int my3126_interrupt_handler(struct cphy *cphy) return cphy_cause_link_change; } -static void my3216_poll(struct work_struct *work) +static void my3126_poll(struct work_struct *work) { struct cphy *cphy = container_of(work, struct cphy, phy_update.work); @@ -177,7 +177,7 @@ static struct cphy *my3126_phy_create(struct net_device *dev, return NULL; cphy_init(cphy, dev, phy_addr, &my3126_ops, mdio_ops); - INIT_DELAYED_WORK(&cphy->phy_update, my3216_poll); + INIT_DELAYED_WORK(&cphy->phy_update, my3126_poll); cphy->bmsr = 0; return cphy; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 67202b6f352e..4311ad9c84b2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5561,7 +5561,6 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) char name[IFNAMSIZ]; u32 devcap2; u16 flags; - int pos; /* If we want to instantiate Virtual Functions, then our * parent bridge's PCI-E needs to support Alternative Routing @@ -5569,9 +5568,8 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) * and above. */ pbridge = pdev->bus->self; - pos = pci_find_capability(pbridge, PCI_CAP_ID_EXP); - pci_read_config_word(pbridge, pos + PCI_EXP_FLAGS, &flags); - pci_read_config_dword(pbridge, pos + PCI_EXP_DEVCAP2, &devcap2); + pcie_capability_read_word(pbridge, PCI_EXP_FLAGS, &flags); + pcie_capability_read_dword(pbridge, PCI_EXP_DEVCAP2, &devcap2); if ((flags & PCI_EXP_FLAGS_VERS) < 2 || !(devcap2 & PCI_EXP_DEVCAP2_ARI)) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 312599c6b35a..e447976bdd3e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -67,7 +67,8 @@ static struct ch_tc_pedit_fields pedits[] = { static struct ch_tc_flower_entry *allocate_flower_entry(void) { struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL); - spin_lock_init(&new->lock); + if (new) + spin_lock_init(&new->lock); return new; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 9dd5ed9a2965..f7fc553356f2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -7309,7 +7309,6 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, } else { unsigned int pack_align; unsigned int ingpad, ingpack; - unsigned int pcie_cap; /* T5 introduced the separation of the Free List Padding and * Packing Boundaries. Thus, we can select a smaller Padding @@ -7334,8 +7333,7 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, * multiple of the Maximum Payload Size. */ pack_align = fl_align; - pcie_cap = pci_find_capability(adap->pdev, PCI_CAP_ID_EXP); - if (pcie_cap) { + if (pci_is_pcie(adap->pdev)) { unsigned int mps, mps_log; u16 devctl; @@ -7343,9 +7341,8 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, * [bits 7:5] encodes sizes as powers of 2 starting at * 128 bytes. */ - pci_read_config_word(adap->pdev, - pcie_cap + PCI_EXP_DEVCTL, - &devctl); + pcie_capability_read_word(adap->pdev, PCI_EXP_DEVCTL, + &devctl); mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7; mps = 1 << mps_log; if (mps > pack_align) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b7a246b33599..2edb86ec9fe9 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4698,8 +4698,13 @@ int be_update_queues(struct be_adapter *adapter) int status; if (netif_running(netdev)) { + /* be_tx_timeout() must not run concurrently with this + * function, synchronize with an already-running dev_watchdog + */ + netif_tx_lock_bh(netdev); /* device cannot transmit now, avoid dev_watchdog timeouts */ netif_carrier_off(netdev); + netif_tx_unlock_bh(netdev); be_close(netdev); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 8ad5292eebbe..75329ab775a6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -43,7 +43,7 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_GET_QID_IN_PF, /* (VF -> PF) get queue id in pf */ HCLGE_MBX_LINK_STAT_MODE, /* (PF -> VF) link mode has changed */ HCLGE_MBX_GET_LINK_MODE, /* (VF -> PF) get the link mode of pf */ - HLCGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */ + HCLGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */ HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */ HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index a38ac7cfe16b..690b9990215c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -304,7 +304,7 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, memcpy(&msg_data[6], &vlan_tag, sizeof(u16)); return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), - HLCGE_MBX_PUSH_VLAN_INFO, vfid); + HCLGE_MBX_PUSH_VLAN_INFO, vfid); } static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index f60b80bd605e..6a96987bd8f0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -204,7 +204,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) case HCLGE_MBX_LINK_STAT_CHANGE: case HCLGE_MBX_ASSERTING_RESET: case HCLGE_MBX_LINK_STAT_MODE: - case HLCGE_MBX_PUSH_VLAN_INFO: + case HCLGE_MBX_PUSH_VLAN_INFO: /* set this mbx event as pending. This is required as we * might loose interrupt event when mbx task is busy * handling. This shall be cleared when mbx task just @@ -307,7 +307,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) hclgevf_reset_task_schedule(hdev); break; - case HLCGE_MBX_PUSH_VLAN_INFO: + case HCLGE_MBX_PUSH_VLAN_INFO: state = le16_to_cpu(msg_q[1]); vlan_info = &msg_q[1]; hclgevf_update_port_base_vlan_info(hdev, state, diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 93f3b4e6185b..aa9323e55406 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3912,13 +3912,11 @@ void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) { struct igc_adapter *adapter = hw->back; - u16 cap_offset; - cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP); - if (!cap_offset) + if (!pci_is_pcie(adapter->pdev)) return -IGC_ERR_CONFIG; - pci_read_config_word(adapter->pdev, cap_offset + reg, value); + pcie_capability_read_word(adapter->pdev, reg, value); return IGC_SUCCESS; } @@ -3926,13 +3924,11 @@ s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) { struct igc_adapter *adapter = hw->back; - u16 cap_offset; - cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP); - if (!cap_offset) + if (!pci_is_pcie(adapter->pdev)) return -IGC_ERR_CONFIG; - pci_write_config_word(adapter->pdev, cap_offset + reg, *value); + pcie_capability_write_word(adapter->pdev, reg, *value); return IGC_SUCCESS; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7245d287633d..7f747cb1a4f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -735,8 +735,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, list_add(&indr_priv->list, &rpriv->uplink_priv.tc_indr_block_priv_list); - block_cb = flow_block_cb_alloc(f->net, - mlx5e_rep_indr_setup_block_cb, + block_cb = flow_block_cb_alloc(mlx5e_rep_indr_setup_block_cb, indr_priv, indr_priv, mlx5e_rep_indr_tc_block_unbind); if (IS_ERR(block_cb)) { @@ -753,7 +752,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, if (!indr_priv) return -ENOENT; - block_cb = flow_block_cb_lookup(f, + block_cb = flow_block_cb_lookup(f->block, mlx5e_rep_indr_setup_block_cb, indr_priv); if (!block_cb) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 4d34d42b3b0e..650638152bbc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1604,14 +1604,14 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, bool register_block = false; int err; - block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower, + block_cb = flow_block_cb_lookup(f->block, + mlxsw_sp_setup_tc_block_cb_flower, mlxsw_sp); if (!block_cb) { acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, f->net); if (!acl_block) return -ENOMEM; - block_cb = flow_block_cb_alloc(f->net, - mlxsw_sp_setup_tc_block_cb_flower, + block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb_flower, mlxsw_sp, acl_block, mlxsw_sp_tc_block_flower_release); if (IS_ERR(block_cb)) { @@ -1657,7 +1657,8 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_cb *block_cb; int err; - block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower, + block_cb = flow_block_cb_lookup(f->block, + mlxsw_sp_setup_tc_block_cb_flower, mlxsw_sp); if (!block_cb) return; @@ -1680,7 +1681,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f) { struct flow_block_cb *block_cb; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; bool ingress; int err; @@ -1702,7 +1703,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, &mlxsw_sp_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, mlxsw_sp_port, + block_cb = flow_block_cb_alloc(cb, mlxsw_sp_port, mlxsw_sp_port, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -1718,7 +1719,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, case FLOW_BLOCK_UNBIND: mlxsw_sp_setup_tc_block_flower_unbind(mlxsw_sp_port, f, ingress); - block_cb = flow_block_cb_lookup(f, cb, mlxsw_sp_port); + block_cb = flow_block_cb_lookup(f->block, cb, mlxsw_sp_port); if (!block_cb) return -ENOENT; diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 7aaddc09c185..59487d446a09 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -316,15 +316,14 @@ int ocelot_setup_tc_block_flower_bind(struct ocelot_port *port, if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) return -EOPNOTSUPP; - block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower, - port); + block_cb = flow_block_cb_lookup(f->block, + ocelot_setup_tc_block_cb_flower, port); if (!block_cb) { port_block = ocelot_port_block_create(port); if (!port_block) return -ENOMEM; - block_cb = flow_block_cb_alloc(f->net, - ocelot_setup_tc_block_cb_flower, + block_cb = flow_block_cb_alloc(ocelot_setup_tc_block_cb_flower, port, port_block, ocelot_tc_block_unbind); if (IS_ERR(block_cb)) { @@ -351,8 +350,8 @@ void ocelot_setup_tc_block_flower_unbind(struct ocelot_port *port, { struct flow_block_cb *block_cb; - block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower, - port); + block_cb = flow_block_cb_lookup(f->block, + ocelot_setup_tc_block_cb_flower, port); if (!block_cb) return; diff --git a/drivers/net/ethernet/mscc/ocelot_tc.c b/drivers/net/ethernet/mscc/ocelot_tc.c index 9e6464ffae5d..16a6db71ca5e 100644 --- a/drivers/net/ethernet/mscc/ocelot_tc.c +++ b/drivers/net/ethernet/mscc/ocelot_tc.c @@ -134,7 +134,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port, struct flow_block_offload *f) { struct flow_block_cb *block_cb; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; int err; netdev_dbg(port->dev, "tc_block command %d, binder_type %d\n", @@ -156,7 +156,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port, if (flow_block_cb_is_busy(cb, port, &ocelot_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, port, port, NULL); + block_cb = flow_block_cb_alloc(cb, port, port, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -169,7 +169,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port, list_add_tail(&block_cb->driver_list, f->driver_block_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, port); + block_cb = flow_block_cb_lookup(f->block, cb, port); if (!block_cb) return -ENOENT; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index faa8ba012a37..e209f150c5f2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1318,8 +1318,7 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, &nfp_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, - nfp_flower_setup_tc_block_cb, + block_cb = flow_block_cb_alloc(nfp_flower_setup_tc_block_cb, repr, repr, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -1328,7 +1327,8 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, list_add_tail(&block_cb->driver_list, &nfp_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, nfp_flower_setup_tc_block_cb, + block_cb = flow_block_cb_lookup(f->block, + nfp_flower_setup_tc_block_cb, repr); if (!block_cb) return -ENOENT; @@ -1424,8 +1424,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, cb_priv->app = app; list_add(&cb_priv->list, &priv->indr_block_cb_priv); - block_cb = flow_block_cb_alloc(f->net, - nfp_flower_setup_indr_block_cb, + block_cb = flow_block_cb_alloc(nfp_flower_setup_indr_block_cb, cb_priv, cb_priv, nfp_flower_setup_indr_tc_release); if (IS_ERR(block_cb)) { @@ -1442,7 +1441,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, if (!cb_priv) return -ENOENT; - block_cb = flow_block_cb_lookup(f, + block_cb = flow_block_cb_lookup(f->block, nfp_flower_setup_indr_block_cb, cb_priv); if (!block_cb) diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index f900fde448db..17c64e43d6c3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -530,9 +530,8 @@ static void qed_rdma_init_devinfo(struct qed_hwfn *p_hwfn, SET_FIELD(dev->dev_caps, QED_RDMA_DEV_CAP_LOCAL_INV_FENCE, 1); /* Check atomic operations support in PCI configuration space. */ - pci_read_config_dword(cdev->pdev, - cdev->pdev->pcie_cap + PCI_EXP_DEVCTL2, - &pci_status_control); + pcie_capability_read_dword(cdev->pdev, PCI_EXP_DEVCTL2, + &pci_status_control); if (pci_status_control & PCI_EXP_DEVCTL2_LTR_EN) SET_FIELD(dev->dev_caps, QED_RDMA_DEV_CAP_ATOMIC_OP, 1); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 0637c6752a78..6272115b2848 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -3251,9 +3251,9 @@ static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp) ret = phy_read_paged(tp->phydev, 0x0a46, 0x13); if (ret & BIT(8)) - phy_modify_paged(tp->phydev, 0x0c41, 0x12, 0, BIT(1)); + phy_modify_paged(tp->phydev, 0x0c41, 0x15, 0, BIT(1)); else - phy_modify_paged(tp->phydev, 0x0c41, 0x12, BIT(1), 0); + phy_modify_paged(tp->phydev, 0x0c41, 0x15, BIT(1), 0); /* Enable PHY auto speed down */ phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2)); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index afdcc5664ea6..3544e1991579 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -836,7 +836,6 @@ int netvsc_recv_callback(struct net_device *net, if (unlikely(!skb)) { ++net_device_ctx->eth_stats.rx_no_memory; - rcu_read_unlock(); return NVSP_STAT_FAIL; } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 2d816aadea79..e36c04c26866 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -517,7 +517,7 @@ static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value) static void sfp_hwmon_to_rx_power(long *value) { - *value = DIV_ROUND_CLOSEST(*value, 100); + *value = DIV_ROUND_CLOSEST(*value, 10); } static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset, diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 54edf8956a25..6e84328bdd40 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -165,23 +165,29 @@ static int vrf_ip6_local_out(struct net *net, struct sock *sk, static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { - const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph; struct net *net = dev_net(skb->dev); - struct flowi6 fl6 = { - /* needed to match OIF rule */ - .flowi6_oif = dev->ifindex, - .flowi6_iif = LOOPBACK_IFINDEX, - .daddr = iph->daddr, - .saddr = iph->saddr, - .flowlabel = ip6_flowinfo(iph), - .flowi6_mark = skb->mark, - .flowi6_proto = iph->nexthdr, - .flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF, - }; + struct flowi6 fl6; int ret = NET_XMIT_DROP; struct dst_entry *dst; struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; + if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) + goto err; + + iph = ipv6_hdr(skb); + + memset(&fl6, 0, sizeof(fl6)); + /* needed to match OIF rule */ + fl6.flowi6_oif = dev->ifindex; + fl6.flowi6_iif = LOOPBACK_IFINDEX; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = ip6_flowinfo(iph); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = iph->nexthdr; + fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; + dst = ip6_route_output(net, NULL, &fl6); if (dst == dst_null) goto err; @@ -237,21 +243,27 @@ static int vrf_ip_local_out(struct net *net, struct sock *sk, static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, struct net_device *vrf_dev) { - struct iphdr *ip4h = ip_hdr(skb); + struct iphdr *ip4h; int ret = NET_XMIT_DROP; - struct flowi4 fl4 = { - /* needed to match OIF rule */ - .flowi4_oif = vrf_dev->ifindex, - .flowi4_iif = LOOPBACK_IFINDEX, - .flowi4_tos = RT_TOS(ip4h->tos), - .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF, - .flowi4_proto = ip4h->protocol, - .daddr = ip4h->daddr, - .saddr = ip4h->saddr, - }; + struct flowi4 fl4; struct net *net = dev_net(vrf_dev); struct rtable *rt; + if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) + goto err; + + ip4h = ip_hdr(skb); + + memset(&fl4, 0, sizeof(fl4)); + /* needed to match OIF rule */ + fl4.flowi4_oif = vrf_dev->ifindex; + fl4.flowi4_iif = LOOPBACK_IFINDEX; + fl4.flowi4_tos = RT_TOS(ip4h->tos); + fl4.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF; + fl4.flowi4_proto = ip4h->protocol; + fl4.daddr = ip4h->daddr; + fl4.saddr = ip4h->saddr; + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index d436cc51dfd1..2fb4258941a5 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -177,6 +177,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { .info.subcmd = QCA_NL80211_VENDOR_SUBCMD_DMG_RF_GET_SECTOR_CFG, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_get_cfg }, { @@ -184,6 +185,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { .info.subcmd = QCA_NL80211_VENDOR_SUBCMD_DMG_RF_SET_SECTOR_CFG, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_set_cfg }, { @@ -192,6 +194,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { QCA_NL80211_VENDOR_SUBCMD_DMG_RF_GET_SELECTED_SECTOR, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_get_selected }, { @@ -200,6 +203,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { QCA_NL80211_VENDOR_SUBCMD_DMG_RF_SET_SELECTED_SECTOR, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_set_selected }, }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c index f6500899fc14..d07e7c7355d9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c @@ -112,6 +112,7 @@ const struct wiphy_vendor_command brcmf_vendor_cmds[] = { }, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_NETDEV, + .policy = VENDOR_CMD_RAW_DATA, .doit = brcmf_cfg80211_vndr_cmds_dcmd_handler }, }; diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c index 5cf0b32c413b..e1bd344c4ebc 100644 --- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c +++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c @@ -163,6 +163,7 @@ static const struct wiphy_vendor_command wlcore_vendor_commands[] = { .flags = WIPHY_VENDOR_CMD_NEED_NETDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, .doit = wlcore_vendor_cmd_smart_config_start, + .policy = wlcore_vendor_attr_policy, }, { .info = { @@ -172,6 +173,7 @@ static const struct wiphy_vendor_command wlcore_vendor_commands[] = { .flags = WIPHY_VENDOR_CMD_NEED_NETDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, .doit = wlcore_vendor_cmd_smart_config_stop, + .policy = wlcore_vendor_attr_policy, }, { .info = { @@ -181,6 +183,7 @@ static const struct wiphy_vendor_command wlcore_vendor_commands[] = { .flags = WIPHY_VENDOR_CMD_NEED_NETDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, .doit = wlcore_vendor_cmd_smart_config_set_group_key, + .policy = wlcore_vendor_attr_policy, }, }; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index cc09b81fc7f4..8f3fbe5ca937 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2311,17 +2311,15 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off); } -static void __nvme_release_subsystem(struct nvme_subsystem *subsys) +static void nvme_release_subsystem(struct device *dev) { + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + ida_simple_remove(&nvme_subsystems_ida, subsys->instance); kfree(subsys); } -static void nvme_release_subsystem(struct device *dev) -{ - __nvme_release_subsystem(container_of(dev, struct nvme_subsystem, dev)); -} - static void nvme_destroy_subsystem(struct kref *ref) { struct nvme_subsystem *subsys = @@ -2477,7 +2475,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) mutex_lock(&nvme_subsystems_lock); found = __nvme_find_get_subsystem(subsys->subnqn); if (found) { - __nvme_release_subsystem(subsys); + put_device(&subsys->dev); subsys = found; if (!nvme_validate_cntlid(subsys, ctrl, id)) { diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index a9a927677970..4f0d0d12744e 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -12,11 +12,6 @@ module_param(multipath, bool, 0444); MODULE_PARM_DESC(multipath, "turn on native support for multiple controllers per subsystem"); -inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) -{ - return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3)); -} - /* * If multipathing is enabled we need to always use the subsystem instance * number for numbering our devices to avoid conflicts between subsystems that @@ -622,7 +617,8 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { int error; - if (!nvme_ctrl_use_ana(ctrl)) + /* check if multipath is enabled and we have the capability */ + if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3))) return 0; ctrl->anacap = id->anacap; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 716a876119c8..26b563f9985b 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -485,7 +485,11 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct block_device_operations nvme_ns_head_ops; #ifdef CONFIG_NVME_MULTIPATH -bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl); +static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) +{ + return ctrl->ana_log_buf != NULL; +} + void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, struct nvme_ctrl *ctrl, int *flags); void nvme_failover_req(struct request *req); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index bb970ca82517..db160cee42ad 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2254,9 +2254,7 @@ static int nvme_dev_add(struct nvme_dev *dev) if (!dev->ctrl.tagset) { dev->tagset.ops = &nvme_mq_ops; dev->tagset.nr_hw_queues = dev->online_queues - 1; - dev->tagset.nr_maps = 1; /* default */ - if (dev->io_queues[HCTX_TYPE_READ]) - dev->tagset.nr_maps++; + dev->tagset.nr_maps = 2; /* default + read */ if (dev->io_queues[HCTX_TYPE_POLL]) dev->tagset.nr_maps++; dev->tagset.timeout = NVME_IO_TIMEOUT; @@ -3029,6 +3027,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_LIGHTNVM, }, { PCI_DEVICE(0x1d1d, 0x2601), /* CNEX Granby */ .driver_data = NVME_QUIRK_LIGHTNVM, }, + { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */ + .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 9fd6dd342169..6df481896b5f 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1454,7 +1454,7 @@ static void __exit rapl_exit(void) unregister_pm_notifier(&rapl_pm_notifier); } -module_init(rapl_init); +fs_initcall(rapl_init); module_exit(rapl_exit); MODULE_DESCRIPTION("Intel Runtime Average Power Limit (RAPL) common code"); diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index 540e8aafc990..f808c5fa9838 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -671,7 +671,7 @@ static int __init powercap_init(void) return class_register(&powercap_class); } -device_initcall(powercap_init); +fs_initcall(powercap_init); MODULE_DESCRIPTION("PowerCap sysfs Driver"); MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>"); diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c index 213ab3cc6b80..d3446acf9bbd 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c @@ -487,6 +487,7 @@ static int proc_thermal_rapl_add(struct pci_dev *pdev, rapl_mmio_cpu_online, rapl_mmio_cpu_down_prep); if (ret < 0) { powercap_unregister_control_type(rapl_mmio_priv.control_type); + rapl_mmio_priv.control_type = NULL; return ret; } rapl_mmio_priv.pcap_rapl_online = ret; @@ -496,6 +497,9 @@ static int proc_thermal_rapl_add(struct pci_dev *pdev, static void proc_thermal_rapl_remove(void) { + if (IS_ERR_OR_NULL(rapl_mmio_priv.control_type)) + return; + cpuhp_remove_state(rapl_mmio_priv.pcap_rapl_online); powercap_unregister_control_type(rapl_mmio_priv.control_type); } diff --git a/fs/block_dev.c b/fs/block_dev.c index 4707dfff991b..c2a85b587922 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -345,15 +345,24 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) struct bio *bio; bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; bool is_read = (iov_iter_rw(iter) == READ), is_sync; + bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; - int ret = 0; + gfp_t gfp; + ssize_t ret; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool); + if (nowait) + gfp = GFP_NOWAIT; + else + gfp = GFP_KERNEL; + + bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool); + if (!bio) + return -EAGAIN; dio = container_of(bio, struct blkdev_dio, bio); dio->is_sync = is_sync = is_sync_kiocb(iocb); @@ -375,7 +384,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) if (!is_poll) blk_start_plug(&plug); + ret = 0; for (;;) { + int err; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = pos >> 9; bio->bi_write_hint = iocb->ki_hint; @@ -383,8 +395,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; - ret = bio_iov_iter_get_pages(bio, iter); - if (unlikely(ret)) { + err = bio_iov_iter_get_pages(bio, iter); + if (unlikely(err)) { + if (!ret) + ret = err; bio->bi_status = BLK_STS_IOERR; bio_endio(bio); break; @@ -399,6 +413,14 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) task_io_account_write(bio->bi_iter.bi_size); } + /* + * Tell underlying layer to not block for resource shortage. + * And if we would have blocked, return error inline instead + * of through the bio->bi_end_io() callback. + */ + if (nowait) + bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE); + dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; @@ -412,6 +434,11 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } if (polled) WRITE_ONCE(iocb->ki_cookie, qc); @@ -432,8 +459,20 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) atomic_inc(&dio->ref); } - submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, nr_pages); + qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } + ret += bio->bi_iter.bi_size; + + bio = bio_alloc(gfp, nr_pages); + if (!bio) { + if (!ret) + ret = -EAGAIN; + goto error; + } } if (!is_poll) @@ -453,13 +492,16 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } __set_current_state(TASK_RUNNING); +out: if (!ret) ret = blk_status_to_errno(dio->bio.bi_status); - if (likely(!ret)) - ret = dio->size; bio_put(&dio->bio); return ret; +error: + if (!is_poll) + blk_finish_plug(&plug); + goto out; } static ssize_t diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 212b4a854f2c..38651fae7f21 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -4,6 +4,7 @@ config BTRFS_FS tristate "Btrfs filesystem support" select CRYPTO select CRYPTO_CRC32C + select LIBCRC32C select ZLIB_INFLATE select ZLIB_DEFLATE select LZO_COMPRESS diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 41a2bd2e0c56..5f7ee70b3d1a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4106,6 +4106,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); + btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1af069a9a0c7..ee582a36653d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -395,10 +395,31 @@ static noinline int add_async_extent(struct async_chunk *cow, return 0; } +/* + * Check if the inode has flags compatible with compression + */ +static inline bool inode_can_compress(struct inode *inode) +{ + if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW || + BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) + return false; + return true; +} + +/* + * Check if the inode needs to be submitted to compression, based on mount + * options, defragmentation, properties or heuristics. + */ static inline int inode_need_compress(struct inode *inode, u64 start, u64 end) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + if (!inode_can_compress(inode)) { + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: unexpected compression for ino %llu\n", + btrfs_ino(BTRFS_I(inode))); + return 0; + } /* force compress */ if (btrfs_test_opt(fs_info, FORCE_COMPRESS)) return 1; @@ -1631,7 +1652,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - } else if (!inode_need_compress(inode, start, end)) { + } else if (!inode_can_compress(inode) || + !inode_need_compress(inode, start, end)) { ret = cow_file_range(inode, locked_page, start, end, end, page_started, nr_written, 1, NULL); } else { diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 98fccce4208c..393eceda57c8 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -346,9 +346,12 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { btrfs_assert_no_spinning_writers(eb); eb->blocking_writers--; - /* Use the lighter barrier after atomic */ - smp_mb__after_atomic(); - cond_wake_up_nomb(&eb->write_lock_wq); + /* + * We need to order modifying blocking_writers above with + * actually waking up the sleepers to ensure they see the + * updated value of blocking_writers + */ + cond_wake_up(&eb->write_lock_wq); } else { btrfs_assert_spinning_writers_put(eb); write_unlock(&eb->lock); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 1744ba8b2754..ae7f64a8facb 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -985,13 +985,14 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, struct extent_state **cached_state) { struct btrfs_ordered_extent *ordered; - struct extent_state *cachedp = NULL; + struct extent_state *cache = NULL; + struct extent_state **cachedp = &cache; if (cached_state) - cachedp = *cached_state; + cachedp = cached_state; while (1) { - lock_extent_bits(tree, start, end, &cachedp); + lock_extent_bits(tree, start, end, cachedp); ordered = btrfs_lookup_ordered_range(inode, start, end - start + 1); if (!ordered) { @@ -1001,10 +1002,10 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, * aren't exposing it outside of this function */ if (!cached_state) - refcount_dec(&cachedp->refs); + refcount_dec(&cache->refs); break; } - unlock_extent_cached(tree, start, end, &cachedp); + unlock_extent_cached(tree, start, end, cachedp); btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a13ddba1ebc3..d74b74ca07af 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5941,6 +5941,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; + int ret = 0; ASSERT(op != BTRFS_MAP_DISCARD); @@ -5961,8 +5962,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, btrfs_crit(fs_info, "stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", stripe_offset, offset, em->start, logical, stripe_len); - free_extent_map(em); - return -EINVAL; + ret = -EINVAL; + goto out; } /* stripe_offset is the offset of this block in its stripe */ @@ -6009,7 +6010,10 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom->stripe_offset = stripe_offset; io_geom->raid56_stripe_offset = raid56_full_stripe_start; - return 0; +out: + /* once for us */ + free_extent_map(em); + return ret; } static int __btrfs_map_block(struct btrfs_fs_info *fs_info, diff --git a/fs/io_uring.c b/fs/io_uring.c index e2a66e12fbc6..012bc0efb9d3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -202,7 +202,7 @@ struct async_list { struct file *file; off_t io_end; - size_t io_pages; + size_t io_len; }; struct io_ring_ctx { @@ -333,7 +333,8 @@ struct io_kiocb { #define REQ_F_IO_DRAIN 16 /* drain existing IO first */ #define REQ_F_IO_DRAINED 32 /* drain done */ #define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_FAIL_LINK 128 /* fail rest of links */ +#define REQ_F_LINK_DONE 128 /* linked sqes done */ +#define REQ_F_FAIL_LINK 256 /* fail rest of links */ u64 user_data; u32 result; u32 sequence; @@ -429,7 +430,7 @@ static inline bool io_sequence_defer(struct io_ring_ctx *ctx, if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) return false; - return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped; + return req->sequence != ctx->cached_cq_tail + ctx->sq_ring->dropped; } static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) @@ -632,6 +633,7 @@ static void io_req_link_next(struct io_kiocb *req) nxt->flags |= REQ_F_LINK; } + nxt->flags |= REQ_F_LINK_DONE; INIT_WORK(&nxt->work, io_sq_wq_submit_work); queue_work(req->ctx->sqo_wq, &nxt->work); } @@ -1064,8 +1066,44 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, */ offset = buf_addr - imu->ubuf; iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); - if (offset) - iov_iter_advance(iter, offset); + + if (offset) { + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here, because + * we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are PAGE_SIZE in size, except potentially the + * first and last bvec + * + * So just find our index, and adjust the iterator afterwards. + * If the offset is within the first bvec (or the whole first + * bvec, just use iov_iter_advance(). This makes it easier + * since we can just skip the first segment, which may not + * be PAGE_SIZE aligned. + */ + const struct bio_vec *bvec = imu->bvec; + + if (offset <= bvec->bv_len) { + iov_iter_advance(iter, offset); + } else { + unsigned long seg_skip; + + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> PAGE_SHIFT); + + iter->bvec = bvec + seg_skip; + iter->nr_segs -= seg_skip; + iter->count -= (seg_skip << PAGE_SHIFT); + iter->iov_offset = offset & ~PAGE_MASK; + if (iter->iov_offset) + iter->count -= iter->iov_offset; + } + } + return 0; } @@ -1120,28 +1158,26 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) off_t io_end = kiocb->ki_pos + len; if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) { - unsigned long max_pages; + unsigned long max_bytes; /* Use 8x RA size as a decent limiter for both reads/writes */ - max_pages = filp->f_ra.ra_pages; - if (!max_pages) - max_pages = VM_READAHEAD_PAGES; - max_pages *= 8; - - /* If max pages are exceeded, reset the state */ - len >>= PAGE_SHIFT; - if (async_list->io_pages + len <= max_pages) { + max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3); + if (!max_bytes) + max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3); + + /* If max len are exceeded, reset the state */ + if (async_list->io_len + len <= max_bytes) { req->flags |= REQ_F_SEQ_PREV; - async_list->io_pages += len; + async_list->io_len += len; } else { io_end = 0; - async_list->io_pages = 0; + async_list->io_len = 0; } } /* New file? Reset state. */ if (async_list->file != filp) { - async_list->io_pages = 0; + async_list->io_len = 0; async_list->file = filp; } async_list->io_end = io_end; @@ -1630,6 +1666,8 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, io_poll_wake); + INIT_LIST_HEAD(&req->list); + mask = vfs_poll(poll->file, &ipt.pt) & poll->events; spin_lock_irq(&ctx->completion_lock); @@ -1844,6 +1882,10 @@ restart: /* async context always use a copy of the sqe */ kfree(sqe); + /* req from defer and link list needn't decrease async cnt */ + if (req->flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) + goto out; + if (!async_list) break; if (!list_empty(&req_list)) { @@ -1891,6 +1933,7 @@ restart: } } +out: if (cur_mm) { set_fs(old_fs); unuse_mm(cur_mm); @@ -1917,6 +1960,10 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) ret = true; spin_lock(&list->lock); list_add_tail(&req->list, &list->list); + /* + * Ensure we see a simultaneous modification from io_sq_wq_submit_work() + */ + smp_mb(); if (!atomic_read(&list->cnt)) { list_del_init(&req->list); ret = false; diff --git a/fs/namespace.c b/fs/namespace.c index 6464ea4acba9..d28d30b13043 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1463,7 +1463,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); - if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { @@ -1471,10 +1470,11 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); - hlist_add_head(&p->mnt_umount, &unmounted); } } change_mnt_propagation(p, MS_PRIVATE); + if (disconnect) + hlist_add_head(&p->mnt_umount, &unmounted); } } diff --git a/fs/open.c b/fs/open.c index b5b80469b93d..a59abe3c669a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -374,6 +374,25 @@ long do_faccessat(int dfd, const char __user *filename, int mode) override_cred->cap_permitted; } + /* + * The new set of credentials can *only* be used in + * task-synchronous circumstances, and does not need + * RCU freeing, unless somebody then takes a separate + * reference to it. + * + * NOTE! This is _only_ true because this credential + * is used purely for override_creds() that installs + * it as the subjective cred. Other threads will be + * accessing ->real_cred, not the subjective cred. + * + * If somebody _does_ make a copy of this (using the + * 'get_current_cred()' function), that will clear the + * non_rcu field, because now that other user may be + * expecting RCU freeing. But normal thread-synchronous + * cred accesses will keep things non-RCY. + */ + override_cred->non_rcu = 1; + old_cred = override_creds(override_cred); retry: res = user_path_at(dfd, filename, lookup_flags, &path); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 689a58231288..12811091fd50 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -181,6 +181,7 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; +extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index feff3fe4467e..1b1fa1557e68 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -311,6 +311,7 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ + __REQ_NOWAIT_INLINE, /* Return would-block error inline */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread @@ -345,6 +346,7 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) +#define REQ_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) @@ -418,12 +420,13 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U +#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE; + return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) diff --git a/include/linux/connector.h b/include/linux/connector.h index 6b6c7396a584..cb732643471b 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -50,7 +50,6 @@ struct cn_dev { u32 seq, groups; struct sock *nls; - void (*input) (struct sk_buff *skb); struct cn_queue_dev *cbdev; }; diff --git a/include/linux/cred.h b/include/linux/cred.h index 7eb43a038330..f7a30e0099be 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -145,7 +145,11 @@ struct cred { struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ - struct rcu_head rcu; /* RCU deletion hook */ + /* RCU deletion */ + union { + int non_rcu; /* Can we skip RCU deletion? */ + struct rcu_head rcu; /* RCU deletion hook */ + }; } __randomize_layout; extern void __put_cred(struct cred *); @@ -246,6 +250,7 @@ static inline const struct cred *get_cred(const struct cred *cred) if (!cred) return cred; validate_creds(cred); + nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } @@ -257,6 +262,7 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) if (!atomic_inc_not_zero(&nonconst_cred->usage)) return NULL; validate_creds(cred); + nonconst_cred->non_rcu = 0; return cred; } diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index e11b115dd0e4..f7d1eea32c78 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -689,8 +689,8 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) */ static inline bool dma_addressing_limited(struct device *dev) { - return min_not_zero(*dev->dma_mask, dev->bus_dma_mask) < - dma_get_required_mask(dev); + return min_not_zero(dma_get_mask(dev), dev->bus_dma_mask) < + dma_get_required_mask(dev); } #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 17cd0078377c..1dd014c9c87b 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -45,7 +45,6 @@ struct elevator_mq_ops { struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); bool (*has_work)(struct blk_mq_hw_ctx *); void (*completed_request)(struct request *, u64); - void (*started_request)(struct request *); void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); struct request *(*next_request)(struct request_queue *, struct request *); diff --git a/include/linux/iova.h b/include/linux/iova.h index 781b96ac706f..a0637abffee8 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -155,6 +155,7 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); +bool has_iova_flush_queue(struct iova_domain *iovad); int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); @@ -235,6 +236,11 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } +static inline bool has_iova_flush_queue(struct iova_domain *iovad) +{ + return false; +} + static inline int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) diff --git a/include/linux/netfilter/nf_conntrack_h323_asn1.h b/include/linux/netfilter/nf_conntrack_h323_asn1.h index 91d6275292a5..19df78341fb3 100644 --- a/include/linux/netfilter/nf_conntrack_h323_asn1.h +++ b/include/linux/netfilter/nf_conntrack_h323_asn1.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /**************************************************************************** - * ip_conntrack_h323_asn1.h - BER and PER decoding library for H.323 - * conntrack/NAT module. + * BER and PER decoding library for H.323 conntrack/NAT module. * * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net> * diff --git a/include/linux/wait.h b/include/linux/wait.h index b6f77cf60dd7..30c515520fb2 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -127,6 +127,19 @@ static inline int waitqueue_active(struct wait_queue_head *wq_head) } /** + * wq_has_single_sleeper - check if there is only one sleeper + * @wq_head: wait queue head + * + * Returns true of wq_head has only one sleeper on the list. + * + * Please refer to the comment for waitqueue_active. + */ +static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) +{ + return list_is_singular(&wq_head->head); +} + +/** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head * diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 88c27153a4bc..45850a8391d9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4170,7 +4170,7 @@ struct sta_opmode_info { u8 rx_nss; }; -#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)ERR_PTR(-ENODATA)) +#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)(long)(-ENODATA)) /** * struct wiphy_vendor_command - vendor command definition diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index db337299e81e..b16d21636d69 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -2,8 +2,8 @@ #define _NET_FLOW_OFFLOAD_H #include <linux/kernel.h> +#include <linux/list.h> #include <net/flow_dissector.h> -#include <net/sch_generic.h> struct flow_match { struct flow_dissector *dissector; @@ -249,6 +249,10 @@ enum flow_block_binder_type { FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, }; +struct flow_block { + struct list_head cb_list; +}; + struct netlink_ext_ack; struct flow_block_offload { @@ -256,29 +260,33 @@ struct flow_block_offload { enum flow_block_binder_type binder_type; bool block_shared; struct net *net; + struct flow_block *block; struct list_head cb_list; struct list_head *driver_block_list; struct netlink_ext_ack *extack; }; +enum tc_setup_type; +typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data, + void *cb_priv); + struct flow_block_cb { struct list_head driver_list; struct list_head list; - struct net *net; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; void *cb_ident; void *cb_priv; void (*release)(void *cb_priv); unsigned int refcnt; }; -struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, +struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)); void flow_block_cb_free(struct flow_block_cb *block_cb); -struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *offload, - tc_setup_cb_t *cb, void *cb_ident); +struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, + flow_setup_cb_t *cb, void *cb_ident); void *flow_block_cb_priv(struct flow_block_cb *block_cb); void flow_block_cb_incref(struct flow_block_cb *block_cb); @@ -296,11 +304,12 @@ static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, list_move(&block_cb->list, &offload->cb_list); } -bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident, +bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list); int flow_block_cb_setup_simple(struct flow_block_offload *f, - struct list_head *driver_list, tc_setup_cb_t *cb, + struct list_head *driver_list, + flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); enum flow_cls_command { @@ -333,4 +342,9 @@ flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) return flow_cmd->rule; } +static inline void flow_block_init(struct flow_block *flow_block) +{ + INIT_LIST_HEAD(&flow_block->cb_list); +} + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 93ce6b0daaba..573429be4d59 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -76,6 +76,11 @@ struct nf_conntrack_expect_policy { #define NF_CT_EXPECT_CLASS_DEFAULT 0 #define NF_CT_EXPECT_MAX_CNT 255 +/* Allow to reuse expectations with the same tuples from different master + * conntracks. + */ +#define NF_CT_EXP_F_SKIP_MASTER 0x1 + int nf_conntrack_expect_pernet_init(struct net *net); void nf_conntrack_expect_pernet_fini(struct net *net); @@ -122,10 +127,11 @@ void nf_ct_expect_init(struct nf_conntrack_expect *, unsigned int, u_int8_t, u_int8_t, const __be16 *, const __be16 *); void nf_ct_expect_put(struct nf_conntrack_expect *exp); int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, - u32 portid, int report); -static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect) + u32 portid, int report, unsigned int flags); +static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect, + unsigned int flags) { - return nf_ct_expect_related_report(expect, 0, 0); + return nf_ct_expect_related_report(expect, 0, 0, flags); } #endif /*_NF_CONNTRACK_EXPECT_H*/ diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index 8f00125b06f4..44513b93bd55 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -68,6 +68,7 @@ struct synproxy_options { u8 options; u8 wscale; u16 mss; + u16 mss_encode; u32 tsval; u32 tsecr; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 35dfdd9f69b3..9b624566b82d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -11,6 +11,7 @@ #include <linux/rhashtable.h> #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> +#include <net/flow_offload.h> struct module; @@ -951,7 +952,7 @@ struct nft_stats { * @stats: per-cpu chain stats * @chain: the chain * @dev_name: device name that this base chain is attached to (if any) - * @cb_list: list of flow block callbacks (for hardware offload) + * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; @@ -961,7 +962,7 @@ struct nft_base_chain { struct nft_stats __percpu *stats; struct nft_chain chain; char dev_name[IFNAMSIZ]; - struct list_head cb_list; + struct flow_block flow_block; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 841faadceb6e..e429809ca90d 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -6,7 +6,6 @@ #include <linux/workqueue.h> #include <net/sch_generic.h> #include <net/act_api.h> -#include <net/flow_offload.h> #include <net/net_namespace.h> /* TC action not accessible from user space */ @@ -126,14 +125,14 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) } static inline -int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb, +int tc_setup_cb_block_register(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv) { return 0; } static inline -void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb, +void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv) { } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 855167bbc372..6b6b01234dd9 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -15,6 +15,7 @@ #include <linux/mutex.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> +#include <net/flow_offload.h> struct Qdisc_ops; struct qdisc_walker; @@ -22,9 +23,6 @@ struct tcf_walker; struct module; struct bpf_flow_keys; -typedef int tc_setup_cb_t(enum tc_setup_type type, - void *type_data, void *cb_priv); - typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, enum tc_setup_type type, void *type_data); @@ -313,7 +311,7 @@ struct tcf_proto_ops { void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, - tc_setup_cb_t *cb, void *cb_priv, + flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack); void (*bind_class)(void *, u32, unsigned long); void * (*tmplt_create)(struct net *net, @@ -401,7 +399,7 @@ struct tcf_block { refcount_t refcnt; struct net *net; struct Qdisc *q; - struct list_head cb_list; + struct flow_block flow_block; struct list_head owner_list; bool keep_dst; unsigned int offloadcnt; /* Number of oddloaded filters */ diff --git a/include/net/tcp.h b/include/net/tcp.h index f42d300f0cfa..e5cf514ba118 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1709,6 +1709,11 @@ static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) return skb_rb_first(&sk->tcp_rtx_queue); } +static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) +{ + return skb_rb_last(&sk->tcp_rtx_queue); +} + static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index c5188ff724d1..bc88d6f964da 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -173,10 +173,7 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) if (snd_BUG_ON(!stream)) return; - if (stream->direction == SND_COMPRESS_PLAYBACK) - stream->runtime->state = SNDRV_PCM_STATE_SETUP; - else - stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + stream->runtime->state = SNDRV_PCM_STATE_SETUP; wake_up(&stream->runtime->sleep); } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a7c19540ce21..5e3f12d5359e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virtual/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.txt */ union { __u32 irq; @@ -1086,7 +1086,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 75758ec26c8b..beb9a9d0c00a 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2863,7 +2863,7 @@ enum nl80211_attrs { #define NL80211_HT_CAPABILITY_LEN 26 #define NL80211_VHT_CAPABILITY_LEN 12 #define NL80211_HE_MIN_CAPABILITY_LEN 16 -#define NL80211_HE_MAX_CAPABILITY_LEN 51 +#define NL80211_HE_MAX_CAPABILITY_LEN 54 #define NL80211_MAX_NR_CIPHER_SUITES 5 #define NL80211_MAX_NR_AKM_SUITES 2 diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9d9705ceda76..2427bc4d8eba 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -518,7 +518,13 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_RGBX444 v4l2_fourcc('R', 'X', '1', '2') /* 16 rrrrgggg bbbbxxxx */ #define V4L2_PIX_FMT_ABGR444 v4l2_fourcc('A', 'B', '1', '2') /* 16 aaaabbbb ggggrrrr */ #define V4L2_PIX_FMT_XBGR444 v4l2_fourcc('X', 'B', '1', '2') /* 16 xxxxbbbb ggggrrrr */ -#define V4L2_PIX_FMT_BGRA444 v4l2_fourcc('B', 'A', '1', '2') /* 16 bbbbgggg rrrraaaa */ + +/* + * Originally this had 'BA12' as fourcc, but this clashed with the older + * V4L2_PIX_FMT_SGRBG12 which inexplicably used that same fourcc. + * So use 'GA12' instead for V4L2_PIX_FMT_BGRA444. + */ +#define V4L2_PIX_FMT_BGRA444 v4l2_fourcc('G', 'A', '1', '2') /* 16 bbbbgggg rrrraaaa */ #define V4L2_PIX_FMT_BGRX444 v4l2_fourcc('B', 'X', '1', '2') /* 16 bbbbgggg rrrrxxxx */ #define V4L2_PIX_FMT_RGB555 v4l2_fourcc('R', 'G', 'B', 'O') /* 16 RGB-5-5-5 */ #define V4L2_PIX_FMT_ARGB555 v4l2_fourcc('A', 'R', '1', '5') /* 16 ARGB-1-5-5-5 */ diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index fc020c09b7e8..deff97217496 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -35,10 +35,10 @@ config PREEMPT_VOLUNTARY Select this if you are building a kernel for a desktop system. -config PREEMPT_LL +config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT + select PREEMPTION select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK help This option reduces the latency of the kernel by making @@ -58,7 +58,7 @@ config PREEMPT_LL config PREEMPT_RT bool "Fully Preemptible Kernel (Real-Time)" depends on EXPERT && ARCH_SUPPORTS_RT - select PREEMPT + select PREEMPTION help This option turns the kernel into a real-time kernel by replacing various locking primitives (spinlocks, rwlocks, etc.) with @@ -77,6 +77,6 @@ endchoice config PREEMPT_COUNT bool -config PREEMPT +config PREEMPTION bool select PREEMPT_COUNT diff --git a/kernel/cred.c b/kernel/cred.c index f9a0ce66c9c3..c0a4c12d38b2 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -144,7 +144,10 @@ void __put_cred(struct cred *cred) BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); - call_rcu(&cred->rcu, put_cred_rcu); + if (cred->non_rcu) + put_cred_rcu(&cred->rcu); + else + call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); @@ -261,6 +264,7 @@ struct cred *prepare_creds(void) old = task->cred; memcpy(new, old, sizeof(struct cred)); + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_group_info(new->group_info); @@ -544,7 +548,19 @@ const struct cred *override_creds(const struct cred *new) validate_creds(old); validate_creds(new); - get_cred(new); + + /* + * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. + * + * That means that we do not clear the 'non_rcu' flag, since + * we are only installing the cred into the thread-synchronous + * '->cred' pointer, not the '->real_cred' pointer that is + * visible to other threads under RCU. + * + * Also note that we did validate_creds() manually, not depending + * on the validation in 'get_cred()'. + */ + get_new_cred((struct cred *)new); alter_cred_subscribers(new, 1); rcu_assign_pointer(current->cred, new); alter_cred_subscribers(old, -1); @@ -681,6 +697,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) validate_creds(old); *new = *old; + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_uid(new->user); diff --git a/kernel/exit.c b/kernel/exit.c index a75b6a7f458a..4436158a6d30 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -720,6 +720,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead) if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); + tsk->exit_state = EXIT_ZOMBIE; if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 154fa558bb90..5040fe43f4b4 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -6,7 +6,7 @@ menuconfig NF_TABLES_BRIDGE depends on BRIDGE && NETFILTER && NF_TABLES select NETFILTER_FAMILY_BRIDGE - bool "Ethernet Bridge nf_tables support" + tristate "Ethernet Bridge nf_tables support" if NF_TABLES_BRIDGE @@ -25,6 +25,8 @@ config NF_LOG_BRIDGE tristate "Bridge packet logging" select NF_LOG_COMMON +endif # NF_TABLES_BRIDGE + config NF_CONNTRACK_BRIDGE tristate "IPv4/IPV6 bridge connection tracking support" depends on NF_CONNTRACK @@ -39,8 +41,6 @@ config NF_CONNTRACK_BRIDGE To compile it as a module, choose M here. If unsure, say N. -endif # NF_TABLES_BRIDGE - menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" depends on BRIDGE && NETFILTER && NETFILTER_XTABLES diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 76f8db3841d7..d63b970784dc 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -165,7 +165,7 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_enc_opts); -struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, +struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)) { @@ -175,7 +175,6 @@ struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, if (!block_cb) return ERR_PTR(-ENOMEM); - block_cb->net = net; block_cb->cb = cb; block_cb->cb_ident = cb_ident; block_cb->cb_priv = cb_priv; @@ -194,14 +193,13 @@ void flow_block_cb_free(struct flow_block_cb *block_cb) } EXPORT_SYMBOL(flow_block_cb_free); -struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *f, - tc_setup_cb_t *cb, void *cb_ident) +struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, + flow_setup_cb_t *cb, void *cb_ident) { struct flow_block_cb *block_cb; - list_for_each_entry(block_cb, f->driver_block_list, driver_list) { - if (block_cb->net == f->net && - block_cb->cb == cb && + list_for_each_entry(block_cb, &block->cb_list, list) { + if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) return block_cb; } @@ -228,7 +226,7 @@ unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb) } EXPORT_SYMBOL(flow_block_cb_decref); -bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident, +bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list) { struct flow_block_cb *block_cb; @@ -245,7 +243,8 @@ EXPORT_SYMBOL(flow_block_cb_is_busy); int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_block_list, - tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, + flow_setup_cb_t *cb, + void *cb_ident, void *cb_priv, bool ingress_only) { struct flow_block_cb *block_cb; @@ -261,8 +260,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, cb_ident, - cb_priv, NULL); + block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -270,7 +268,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, list_add_tail(&block_cb->driver_list, driver_block_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, cb_ident); + block_cb = flow_block_cb_lookup(f->block, cb, cb_ident); if (!block_cb) return -ENOENT; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 614c38ece104..33f41178afcc 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -951,7 +951,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_slave_setup_tc_block_cb_ig; @@ -967,7 +967,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, dev, dev, NULL); + block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -975,7 +975,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, dev); + block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4d6bf7ac0792..6bdb1ab8af61 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -416,8 +416,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) ctinfo == IP_CT_RELATED_REPLY)) return XT_CONTINUE; - /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, - * TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here + /* nf_conntrack_proto_icmp guarantees us that we only have ICMP_ECHO, + * TIMESTAMP, INFO_REQUEST or ICMP_ADDRESS type icmp packets from here * on, which all have an ID field [relevant for hashing]. */ hash = clusterip_hashfn(skb, cipinfo->config); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 8e7f84ec783d..0e70f3f65f6f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -36,6 +36,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; + opts.mss_encode = opts.mss; + opts.mss = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 59031670b16a..cc23f1ce239c 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; flow.flowi4_tos = RT_TOS(iph->tos); flow.flowi4_scope = RT_SCOPE_UNIVERSE; + flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par)); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 87b711fd5a44..3e2685c120c7 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -221,11 +221,11 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, int ret; rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - ret = nf_ct_expect_related(rtp_exp); + ret = nf_ct_expect_related(rtp_exp, 0); if (ret == 0) { rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); - ret = nf_ct_expect_related(rtcp_exp); + ret = nf_ct_expect_related(rtcp_exp, 0); if (ret == 0) break; else if (ret == -EBUSY) { @@ -296,7 +296,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -352,7 +352,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -444,7 +444,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -537,7 +537,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4af1f5dae9d3..6e4afc48d7bb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1288,6 +1288,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; + long limit; int nlen; u8 flags; @@ -1298,8 +1299,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, if (nsize < 0) nsize = 0; - if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf && - tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) { + /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. + * We need some allowance to not penalize applications setting small + * SO_SNDBUF values. + * Also allow first and last skb in retransmit queue to be split. + */ + limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE); + if (unlikely((sk->sk_wmem_queued >> 1) > limit && + tcp_queue != TCP_FRAG_IN_WRITE_QUEUE && + skb != tcp_rtx_queue_head(sk) && + skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index e77ea1ed5edd..5cdb4a69d277 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -36,6 +36,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; + opts.mss_encode = opts.mss; + opts.mss = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 6bcaf7357183..d800801a5dd2 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -55,7 +55,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, if (rpfilter_addr_linklocal(&iph->saddr)) { lookup_flags |= RT6_LOOKUP_F_IFACE; fl6.flowi6_oif = dev->ifindex; - } else if ((flags & XT_RPFILTER_LOOSE) == 0) + /* Set flowi6_oif for vrf devices to lookup route in l3mdev domain. */ + } else if (netif_is_l3_master(dev) || netif_is_l3_slave(dev) || + (flags & XT_RPFILTER_LOOSE) == 0) fl6.flowi6_oif = dev->ifindex; rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); @@ -70,7 +72,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, goto out; } - if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE)) + if (rt->rt6i_idev->dev == dev || + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex || + (flags & XT_RPFILTER_LOOSE)) ret = true; out: ip6_rt_put(rt); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 76cc9e967fa6..4d458067d80d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -936,8 +936,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, err = ieee80211_set_probe_resp(sdata, params->probe_resp, params->probe_resp_len, csa); - if (err < 0) + if (err < 0) { + kfree(new); return err; + } if (err == 0) changed |= BSS_CHANGED_AP_PROBE_RESP; @@ -949,8 +951,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, params->civicloc, params->civicloc_len); - if (err < 0) + if (err < 0) { + kfree(new); return err; + } changed |= BSS_CHANGED_FTM_RESPONDER; } diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index acd4afb4944b..c9a8a2433e8a 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -187,11 +187,16 @@ int drv_conf_tx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - if (WARN_ONCE(params->cw_min == 0 || - params->cw_min > params->cw_max, - "%s: invalid CW_min/CW_max: %d/%d\n", - sdata->name, params->cw_min, params->cw_max)) + if (params->cw_min == 0 || params->cw_min > params->cw_max) { + /* + * If we can't configure hardware anyway, don't warn. We may + * never have initialized the CW parameters. + */ + WARN_ONCE(local->ops->conf_tx, + "%s: invalid CW_min/CW_max: %d/%d\n", + sdata->name, params->cw_min, params->cw_max); return -EINVAL; + } trace_drv_conf_tx(local, sdata, ac, params); if (local->ops->conf_tx) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 32a45c03786e..0d65f4d39494 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -223,8 +223,6 @@ config NF_CONNTRACK_FTP of Network Address Translation on them. This is FTP support on Layer 3 independent connection tracking. - Layer 3 independent connection tracking is experimental scheme - which generalize ip_conntrack to support other layer 3 protocols. To compile it as a module, choose M here. If unsure, say N. @@ -338,7 +336,7 @@ config NF_CONNTRACK_SIP help SIP is an application-layer control protocol that can establish, modify, and terminate multimedia sessions (conferences) such as - Internet telephony calls. With the ip_conntrack_sip and + Internet telephony calls. With the nf_conntrack_sip and the nf_nat_sip modules you can support the protocol on a connection tracking/NATing firewall. @@ -1313,7 +1311,7 @@ config NETFILTER_XT_MATCH_HELPER depends on NETFILTER_ADVANCED help Helper matching allows you to match packets in dynamic connections - tracked by a conntrack-helper, ie. ip_conntrack_ftp + tracked by a conntrack-helper, ie. nf_conntrack_ftp To compile it as a module, choose M here. If unsure, say Y. diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 403541996952..08adcb222986 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -231,7 +231,7 @@ void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct, IP_VS_DBG_BUF(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n", __func__, ct, ARG_TUPLE(&exp->tuple)); - nf_ct_expect_related(exp); + nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); } EXPORT_SYMBOL(ip_vs_nfct_expect_related); diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 42ee659d0d1e..d011d2eb0848 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -159,7 +159,7 @@ static int amanda_help(struct sk_buff *skb, if (nf_nat_amanda && ct->status & IPS_NAT_MASK) ret = nf_nat_amanda(skb, ctinfo, protoff, off - dataoff, len, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index 921a7b95be68..1ba6becc3079 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -68,7 +68,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->class = NF_CT_EXPECT_CLASS_DEFAULT; exp->helper = NULL; - nf_ct_expect_related(exp); + nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); nf_ct_refresh(ct, skb, timeout * HZ); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index bdfeacee0817..a542761e90d1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1817,9 +1817,7 @@ EXPORT_SYMBOL_GPL(nf_ct_kill_acct); #include <linux/netfilter/nfnetlink_conntrack.h> #include <linux/mutex.h> -/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be - * in ip_conntrack_core, since we don't want the protocols to autoload - * or depend on ctnetlink */ +/* Generic function for tcp/udp/sctp/dccp and alike. */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index ffd1f4906c4f..65364de915d1 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -249,13 +249,22 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { - return a->master == b->master && - nf_ct_tuple_equal(&a->tuple, &b->tuple) && + return nf_ct_tuple_equal(&a->tuple, &b->tuple) && nf_ct_tuple_mask_equal(&a->mask, &b->mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master)); } +static bool master_matches(const struct nf_conntrack_expect *a, + const struct nf_conntrack_expect *b, + unsigned int flags) +{ + if (flags & NF_CT_EXP_F_SKIP_MASTER) + return true; + + return a->master == b->master; +} + /* Generally a bad idea to call this: could have matched already. */ void nf_ct_unexpect_related(struct nf_conntrack_expect *exp) { @@ -399,7 +408,8 @@ static void evict_oldest_expect(struct nf_conn *master, nf_ct_remove_expect(last); } -static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) +static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, + unsigned int flags) { const struct nf_conntrack_expect_policy *p; struct nf_conntrack_expect *i; @@ -417,8 +427,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { - if (expect_matches(i, expect)) { - if (i->class != expect->class) + if (master_matches(i, expect, flags) && + expect_matches(i, expect)) { + if (i->class != expect->class || + i->master != expect->master) return -EALREADY; if (nf_ct_remove_expect(i)) @@ -453,12 +465,12 @@ out: } int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, - u32 portid, int report) + u32 portid, int report, unsigned int flags) { int ret; spin_lock_bh(&nf_conntrack_expect_lock); - ret = __nf_ct_expect_check(expect); + ret = __nf_ct_expect_check(expect, flags); if (ret < 0) goto out; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 8c6c11bab5b6..0ecb3e289ef2 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -525,7 +525,7 @@ skip_nl_seq: protoff, matchoff, matchlen, exp); else { /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } else diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 8f6ba8162f0b..573cb4481481 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -1,11 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323 - * conntrack/NAT module. + * BER and PER decoding library for H.323 conntrack/NAT module. * * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net> * - * See ip_conntrack_helper_h323_asn1.h for details. + * See nf_conntrack_helper_h323_asn1.h for details. */ #ifdef __KERNEL__ diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 6497e5fc0871..8ba037b76ad3 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -305,8 +305,8 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, ret = nat_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, rtp_port, rtp_exp, rtcp_exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(rtp_exp) == 0) { - if (nf_ct_expect_related(rtcp_exp) == 0) { + if (nf_ct_expect_related(rtp_exp, 0) == 0) { + if (nf_ct_expect_related(rtcp_exp, 0) == 0) { pr_debug("nf_ct_h323: expect RTP "); nf_ct_dump_tuple(&rtp_exp->tuple); pr_debug("nf_ct_h323: expect RTCP "); @@ -364,7 +364,7 @@ static int expect_t120(struct sk_buff *skb, ret = nat_t120(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_h323: expect T.120 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -701,7 +701,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, ret = nat_h245(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_q931: expect H.245 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -825,7 +825,7 @@ static int expect_callforwarding(struct sk_buff *skb, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_q931: expect Call Forwarding "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1284,7 +1284,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, ret = nat_q931(skb, ct, ctinfo, protoff, data, taddr, i, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); @@ -1349,7 +1349,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, IPPROTO_UDP, NULL, &port); exp->helper = nf_conntrack_helper_ras; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1561,7 +1561,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, exp->flags = NF_CT_EXPECT_PERMANENT; exp->helper = nf_conntrack_helper_q931; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1615,7 +1615,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, exp->flags = NF_CT_EXPECT_PERMANENT; exp->helper = nf_conntrack_helper_q931; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); } else diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 7ac156f1f3bc..e40988a2f22f 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -213,7 +213,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, addr_beg_p - ib_ptr, addr_end_p - addr_beg_p, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1b77444d5b52..6aa01eb6fe99 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2616,7 +2616,7 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (IS_ERR(exp)) return PTR_ERR(exp); - err = nf_ct_expect_related_report(exp, portid, report); + err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); return err; } @@ -3367,7 +3367,7 @@ ctnetlink_create_expect(struct net *net, goto err_rcu; } - err = nf_ct_expect_related_report(exp, portid, report); + err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index b22042ad0fca..a971183f11af 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -234,9 +234,9 @@ static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid) nf_nat_pptp_exp_gre = rcu_dereference(nf_nat_pptp_hook_exp_gre); if (nf_nat_pptp_exp_gre && ct->status & IPS_NAT_MASK) nf_nat_pptp_exp_gre(exp_orig, exp_reply); - if (nf_ct_expect_related(exp_orig) != 0) + if (nf_ct_expect_related(exp_orig, 0) != 0) goto out_put_both; - if (nf_ct_expect_related(exp_reply) != 0) + if (nf_ct_expect_related(exp_reply, 0) != 0) goto out_unexpect_orig; /* Add GRE keymap entries */ diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index c2eb365f1723..5b05487a60d2 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ip_conntrack_proto_gre.c - Version 3.0 - * * Connection tracking protocol helper module for GRE. * * GRE is a generic encapsulation protocol, which is generally not very diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index dd53e2b20f6b..097deba7441a 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -215,7 +215,7 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, return -NF_ACCEPT; } - /* See ip_conntrack_proto_tcp.c */ + /* See nf_conntrack_proto_tcp.c */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d5fdfa00d683..85c1f8c213b0 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -472,6 +472,7 @@ static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; + u16 win_raw; s32 receiver_offset; bool res, in_recv_win; @@ -480,7 +481,8 @@ static bool tcp_in_window(const struct nf_conn *ct, */ seq = ntohl(tcph->seq); ack = sack = ntohl(tcph->ack_seq); - win = ntohs(tcph->window); + win_raw = ntohs(tcph->window); + win = win_raw; end = segment_seq_plus_len(seq, skb->len, dataoff, tcph); if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM) @@ -655,14 +657,14 @@ static bool tcp_in_window(const struct nf_conn *ct, && state->last_seq == seq && state->last_ack == ack && state->last_end == end - && state->last_win == win) + && state->last_win == win_raw) state->retrans++; else { state->last_dir = dir; state->last_seq = seq; state->last_ack = ack; state->last_end = end; - state->last_win = win; + state->last_win = win_raw; state->retrans = 0; } } diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index 81448c3db661..1aebd6569d4e 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -153,7 +153,7 @@ static int help(struct sk_buff *skb, nf_ct_dump_tuple(&exp->tuple); /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 107251731809..b83dc9bf0a5d 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -977,11 +977,15 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, /* -EALREADY handling works around end-points that send * SDP messages with identical port but different media type, * we pretend expectation was set up. + * It also works in the case that SDP messages are sent with + * identical expect tuples but for different master conntracks. */ - int errp = nf_ct_expect_related(rtp_exp); + int errp = nf_ct_expect_related(rtp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (errp == 0 || errp == -EALREADY) { - int errcp = nf_ct_expect_related(rtcp_exp); + int errcp = nf_ct_expect_related(rtcp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (errcp == 0 || errcp == -EALREADY) ret = NF_ACCEPT; @@ -1296,7 +1300,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, ret = hooks->expect(skb, protoff, dataoff, dptr, datalen, exp, matchoff, matchlen); else { - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } else diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index df6d6d61bd58..80ee53f29f68 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -78,7 +78,7 @@ static int tftp_help(struct sk_buff *skb, nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook); if (nf_nat_tftp && ct->status & IPS_NAT_MASK) ret = nf_nat_tftp(skb, ctinfo, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c index a352604d6186..3bc7e0854efe 100644 --- a/net/netfilter/nf_nat_amanda.c +++ b/net/netfilter/nf_nat_amanda.c @@ -48,7 +48,7 @@ static unsigned int help(struct sk_buff *skb, int res; exp->tuple.dst.u.tcp.port = htons(port); - res = nf_ct_expect_related(exp); + res = nf_ct_expect_related(exp, 0); if (res == 0) break; else if (res != -EBUSY) { diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 9ab410455992..3f6023ed4966 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -519,7 +519,7 @@ another_round: * and NF_INET_LOCAL_OUT, we change the destination to map into the * range. It might not be possible to get a unique tuple, but we try. * At worst (or if we race), we will end up with a final duplicate in - * __ip_conntrack_confirm and drop the packet. */ + * __nf_conntrack_confirm and drop the packet. */ static void get_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig_tuple, diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c index d48484a9d52d..aace6768a64e 100644 --- a/net/netfilter/nf_nat_ftp.c +++ b/net/netfilter/nf_nat_ftp.c @@ -91,7 +91,7 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, int ret; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index dfb7ef8845bd..c691ab8d234c 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -53,7 +53,7 @@ static unsigned int help(struct sk_buff *skb, int ret; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index e338d91980d8..f0a735e86851 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -414,7 +414,7 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, int ret; exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, NF_CT_EXP_F_SKIP_MASTER); if (ret == 0) break; else if (ret != -EBUSY) { @@ -607,7 +607,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, int ret; rtp_exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(rtp_exp); + ret = nf_ct_expect_related(rtp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (ret == -EBUSY) continue; else if (ret < 0) { @@ -615,7 +616,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, break; } rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); - ret = nf_ct_expect_related(rtcp_exp); + ret = nf_ct_expect_related(rtcp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (ret == 0) break; else if (ret == -EBUSY) { diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c index 833a11f68031..1a591132d6eb 100644 --- a/net/netfilter/nf_nat_tftp.c +++ b/net/netfilter/nf_nat_tftp.c @@ -30,7 +30,7 @@ static unsigned int help(struct sk_buff *skb, = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; exp->dir = IP_CT_DIR_REPLY; exp->expectfn = nf_nat_follow_master; - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, exp->master, "cannot add expectation"); return NF_DROP; } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b101f187eda8..c769462a839e 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -470,7 +470,7 @@ synproxy_send_client_synack(struct net *net, struct iphdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; - u16 mss = opts->mss; + u16 mss = opts->mss_encode; iph = ip_hdr(skb); @@ -687,7 +687,7 @@ ipv4_synproxy_hook(void *priv, struct sk_buff *skb, state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: - if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; @@ -884,7 +884,7 @@ synproxy_send_client_synack_ipv6(struct net *net, struct ipv6hdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; - u16 mss = opts->mss; + u16 mss = opts->mss_encode; iph = ipv6_hdr(skb); @@ -1111,7 +1111,7 @@ ipv6_synproxy_hook(void *priv, struct sk_buff *skb, state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: - if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ed17a7c29b86..605a7cfe7ca7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1662,7 +1662,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, chain->flags |= NFT_BASE_CHAIN | flags; basechain->policy = NF_ACCEPT; - INIT_LIST_HEAD(&basechain->cb_list); + flow_block_init(&basechain->flow_block); } else { chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (chain == NULL) @@ -1900,6 +1900,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nla[NFTA_CHAIN_FLAGS]) flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS])); + else if (chain) + flags = chain->flags; nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 2c3302845f67..64f5fd5f240e 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -116,7 +116,7 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain, struct flow_block_cb *block_cb; int err; - list_for_each_entry(block_cb, &basechain->cb_list, list) { + list_for_each_entry(block_cb, &basechain->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; @@ -154,7 +154,7 @@ static int nft_flow_offload_rule(struct nft_trans *trans, static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { - list_splice(&bo->cb_list, &basechain->cb_list); + list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } @@ -198,6 +198,7 @@ static int nft_flow_offload_chain(struct nft_trans *trans, return -EOPNOTSUPP; bo.command = cmd; + bo.block = &basechain->flow_block; bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo.extack = &extack; INIT_LIST_HEAD(&bo.cb_list); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 92077d459109..4abbb452cf6c 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -578,7 +578,7 @@ static int nfnetlink_bind(struct net *net, int group) ss = nfnetlink_get_subsys(type << 8); rcu_read_unlock(); if (!ss) - request_module("nfnetlink-subsys-%d", type); + request_module_nowait("nfnetlink-subsys-%d", type); return 0; } #endif diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 3fd540b2c6ba..b5d5d071d765 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -193,7 +193,7 @@ static inline void nft_chain_filter_inet_init(void) {} static inline void nft_chain_filter_inet_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV6 */ -#ifdef CONFIG_NF_TABLES_BRIDGE +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) static unsigned int nft_do_chain_bridge(void *priv, struct sk_buff *skb, diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index 2f89bde3c61c..ff9ac8ae0031 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -142,3 +142,6 @@ MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat"); #ifdef CONFIG_NF_TABLES_IPV6 MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); #endif +#ifdef CONFIG_NF_TABLES_INET +MODULE_ALIAS_NFT_CHAIN(1, "nat"); /* NFPROTO_INET */ +#endif diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 827ab6196df9..46ca8bcca1bd 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1252,7 +1252,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, priv->l4proto, NULL, &priv->dport); exp->timeout.expires = jiffies + priv->timeout * HZ; - if (nf_ct_expect_related(exp) != 0) + if (nf_ct_expect_related(exp, 0) != 0) regs->verdict.code = NF_DROP; } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index fe93e731dc7f..b836d550b919 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -129,7 +129,7 @@ static int nft_symhash_init(const struct nft_ctx *ctx, priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); - if (priv->modulus <= 1) + if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 76866f77e343..f1b1d948c07b 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -546,7 +546,7 @@ nft_meta_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) return ERR_PTR(-EINVAL); -#ifdef CONFIG_NF_TABLES_BRIDGE +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META) if (ctx->family == NFPROTO_BRIDGE) return ERR_PTR(-EAGAIN); #endif diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 8487eeff5c0e..43eeb1f609f1 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -291,4 +291,4 @@ module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); -MODULE_ALIAS_NFT_EXPR("nat"); +MODULE_ALIAS_NFT_EXPR("redir"); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 80060ade8a5b..928e661d1517 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -31,6 +31,8 @@ static void nft_synproxy_tcp_options(struct synproxy_options *opts, opts->options |= NF_SYNPROXY_OPT_ECN; opts->options &= priv->info.options; + opts->mss_encode = opts->mss; + opts->mss = info->mss; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, opts); else diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index dca3b1e2acf0..bc89e16e0505 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -59,7 +59,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies) void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, const struct sk_buff *skb) { - struct flow_stats *stats; + struct sw_flow_stats *stats; unsigned int cpu = smp_processor_id(); int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); @@ -87,7 +87,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, if (likely(flow->stats_last_writer != -1) && likely(!rcu_access_pointer(flow->stats[cpu]))) { /* Try to allocate CPU-specific stats. */ - struct flow_stats *new_stats; + struct sw_flow_stats *new_stats; new_stats = kmem_cache_alloc_node(flow_stats_cache, @@ -134,7 +134,7 @@ void ovs_flow_stats_get(const struct sw_flow *flow, /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { - struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); + struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); if (stats) { /* Local CPU may write on non-local stats, so we must @@ -158,7 +158,7 @@ void ovs_flow_stats_clear(struct sw_flow *flow) /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { - struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]); + struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]); if (stats) { spin_lock_bh(&stats->lock); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 3e2cc2202d66..a5506e2d4b7a 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -194,7 +194,7 @@ struct sw_flow_actions { struct nlattr actions[]; }; -struct flow_stats { +struct sw_flow_stats { u64 packet_count; /* Number of packets matched. */ u64 byte_count; /* Number of bytes matched. */ unsigned long used; /* Last used time (in jiffies). */ @@ -216,7 +216,7 @@ struct sw_flow { struct cpumask cpu_used_mask; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; - struct flow_stats __rcu *stats[]; /* One for each CPU. First one + struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one * is allocated at flow creation time, * the rest are allocated on demand * while holding the 'stats[0].lock'. diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 988fd8a94e43..cf3582c5ed70 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -66,7 +66,7 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, struct sw_flow *ovs_flow_alloc(void) { struct sw_flow *flow; - struct flow_stats *stats; + struct sw_flow_stats *stats; flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL); if (!flow) @@ -110,7 +110,7 @@ static void flow_free(struct sw_flow *flow) for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, - (struct flow_stats __force *)flow->stats[cpu]); + (struct sw_flow_stats __force *)flow->stats[cpu]); kmem_cache_free(flow_cache, flow); } @@ -712,13 +712,13 @@ int ovs_flow_init(void) flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + (nr_cpu_ids - * sizeof(struct flow_stats *)), + * sizeof(struct sw_flow_stats *)), 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; flow_stats_cache - = kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats), + = kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats), 0, SLAB_HWCACHE_ALIGN, NULL); if (flow_stats_cache == NULL) { kmem_cache_destroy(flow_cache); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d144233423c5..efd3cfb80a2a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -691,6 +691,8 @@ static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, if (!indr_dev->block) return; + bo.block = &indr_dev->block->flow_block; + indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, &bo); tcf_block_setup(indr_dev->block, &bo); @@ -775,6 +777,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, .command = command, .binder_type = ei->binder_type, .net = dev_net(dev), + .block = &block->flow_block, .block_shared = tcf_block_shared(block), .extack = extack, }; @@ -810,6 +813,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block, bo.net = dev_net(dev); bo.command = command; bo.binder_type = ei->binder_type; + bo.block = &block->flow_block; bo.block_shared = tcf_block_shared(block); bo.extack = extack; INIT_LIST_HEAD(&bo.cb_list); @@ -987,8 +991,8 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); - INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); INIT_LIST_HEAD(&block->chain0.filter_chain_list); @@ -1514,7 +1518,7 @@ void tcf_block_put(struct tcf_block *block) EXPORT_SYMBOL(tcf_block_put); static int -tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, +tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv, bool add, bool offload_in_use, struct netlink_ext_ack *extack) { @@ -1570,7 +1574,7 @@ static int tcf_block_bind(struct tcf_block *block, i++; } - list_splice(&bo->cb_list, &block->cb_list); + list_splice(&bo->cb_list, &block->flow_block.cb_list); return 0; @@ -2152,7 +2156,9 @@ replay: tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false, rtnl_held); tfilter_put(tp, fh); - q->flags &= ~TCQ_F_CAN_BYPASS; + /* q pointer is NULL for shared blocks */ + if (q) + q->flags &= ~TCQ_F_CAN_BYPASS; } errout: @@ -3156,7 +3162,7 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, if (block->nooffloaddevcnt && err_stop) return -EOPNOTSUPP; - list_for_each_entry(block_cb, &block->cb_list, list) { + list_for_each_entry(block_cb, &block->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err) { if (err_stop) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 691f71830134..3f7a9c02b70c 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -651,7 +651,7 @@ skip: } } -static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 38d6e85693fc..054123742e32 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1800,7 +1800,7 @@ fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add) return NULL; } -static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index a30d2f8feb32..455ea2793f9b 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -282,7 +282,7 @@ skip: arg->count++; } -static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index be9e46c77e8b..8614088edd1b 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1152,7 +1152,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, } static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, - bool add, tc_setup_cb_t *cb, void *cb_priv, + bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_cls_u32_offload cls_u32 = {}; @@ -1172,7 +1172,7 @@ static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, } static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, - bool add, tc_setup_cb_t *cb, void *cb_priv, + bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); @@ -1213,7 +1213,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, return 0; } -static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index f345662890a6..ca8ac96d22a9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -476,7 +476,7 @@ static void tipc_topsrv_accept(struct work_struct *work) } } -/* tipc_toprsv_listener_data_ready - interrupt callback with connection request +/* tipc_topsrv_listener_data_ready - interrupt callback with connection request * The queued job is launched into tipc_topsrv_accept() */ static void tipc_topsrv_listener_data_ready(struct sock *sk) diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c index 7b977b753a03..7985dd8198b6 100644 --- a/sound/ac97/bus.c +++ b/sound/ac97/bus.c @@ -122,17 +122,12 @@ static int ac97_codec_add(struct ac97_controller *ac97_ctrl, int idx, vendor_id); ret = device_add(&codec->dev); - if (ret) - goto err_free_codec; + if (ret) { + put_device(&codec->dev); + return ret; + } return 0; -err_free_codec: - of_node_put(codec->dev.of_node); - put_device(&codec->dev); - kfree(codec); - ac97_ctrl->codecs[idx] = NULL; - - return ret; } unsigned int snd_ac97_bus_scan_one(struct ac97_controller *adrv, diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 99b882158705..41905afada63 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -574,10 +574,7 @@ snd_compr_set_params(struct snd_compr_stream *stream, unsigned long arg) stream->metadata_set = false; stream->next_track = false; - if (stream->direction == SND_COMPRESS_PLAYBACK) - stream->runtime->state = SNDRV_PCM_STATE_SETUP; - else - stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + stream->runtime->state = SNDRV_PCM_STATE_SETUP; } else { return -EPERM; } @@ -693,8 +690,17 @@ static int snd_compr_start(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state != SNDRV_PCM_STATE_PREPARED) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_SETUP: + if (stream->direction != SND_COMPRESS_CAPTURE) + return -EPERM; + break; + case SNDRV_PCM_STATE_PREPARED: + break; + default: return -EPERM; + } + retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_START); if (!retval) stream->runtime->state = SNDRV_PCM_STATE_RUNNING; @@ -705,9 +711,15 @@ static int snd_compr_stop(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: return -EPERM; + default: + break; + } + retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP); if (!retval) { snd_compr_drain_notify(stream); @@ -795,9 +807,17 @@ static int snd_compr_drain(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: + case SNDRV_PCM_STATE_PAUSED: return -EPERM; + case SNDRV_PCM_STATE_XRUN: + return -EPIPE; + default: + break; + } retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN); if (retval) { @@ -817,6 +837,10 @@ static int snd_compr_next_track(struct snd_compr_stream *stream) if (stream->runtime->state != SNDRV_PCM_STATE_RUNNING) return -EPERM; + /* next track doesn't have any meaning for capture streams */ + if (stream->direction == SND_COMPRESS_CAPTURE) + return -EPERM; + /* you can signal next track if this is intended to be a gapless stream * and current track metadata is set */ @@ -834,9 +858,23 @@ static int snd_compr_next_track(struct snd_compr_stream *stream) static int snd_compr_partial_drain(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: + case SNDRV_PCM_STATE_PAUSED: + return -EPERM; + case SNDRV_PCM_STATE_XRUN: + return -EPIPE; + default: + break; + } + + /* partial drain doesn't have any meaning for capture streams */ + if (stream->direction == SND_COMPRESS_CAPTURE) return -EPERM; + /* stream can be drained only when next track has been signalled */ if (stream->next_track == false) return -EPERM; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 860543a4c840..12dd9b318db1 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -77,7 +77,7 @@ void snd_pcm_group_init(struct snd_pcm_group *group) spin_lock_init(&group->lock); mutex_init(&group->mutex); INIT_LIST_HEAD(&group->substreams); - refcount_set(&group->refs, 0); + refcount_set(&group->refs, 1); } /* define group lock helpers */ @@ -1096,8 +1096,7 @@ static void snd_pcm_group_unref(struct snd_pcm_group *group, if (!group) return; - do_free = refcount_dec_and_test(&group->refs) && - list_empty(&group->substreams); + do_free = refcount_dec_and_test(&group->refs); snd_pcm_group_unlock(group, substream->pcm->nonatomic); if (do_free) kfree(group); @@ -2020,6 +2019,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) snd_pcm_group_lock_irq(target_group, nonatomic); snd_pcm_stream_lock(substream1); snd_pcm_group_assign(substream1, target_group); + refcount_inc(&target_group->refs); snd_pcm_stream_unlock(substream1); snd_pcm_group_unlock_irq(target_group, nonatomic); _end: @@ -2056,13 +2056,14 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) snd_pcm_group_lock_irq(group, nonatomic); relink_to_local(substream); + refcount_dec(&group->refs); /* detach the last stream, too */ if (list_is_singular(&group->substreams)) { relink_to_local(list_first_entry(&group->substreams, struct snd_pcm_substream, link_list)); - do_free = !refcount_read(&group->refs); + do_free = refcount_dec_and_test(&group->refs); } snd_pcm_group_unlock_irq(group, nonatomic); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index e30e86ca6b72..51f10ed9bc43 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2942,7 +2942,7 @@ static int hda_codec_runtime_resume(struct device *dev) static int hda_codec_force_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); - bool forced_resume = !codec->relaxed_resume; + bool forced_resume = !codec->relaxed_resume && codec->jacktbl.used; int ret; /* The get/put pair below enforces the runtime resume even if the diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index cb8b0945547c..1e14d7270adf 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -313,11 +313,10 @@ enum { #define AZX_DCAPS_INTEL_SKYLAKE \ (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ + AZX_DCAPS_SYNC_WRITE |\ AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT) -#define AZX_DCAPS_INTEL_BROXTON \ - (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ - AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT) +#define AZX_DCAPS_INTEL_BROXTON AZX_DCAPS_INTEL_SKYLAKE /* quirks for ATI SB / AMD Hudson */ #define AZX_DCAPS_PRESET_ATI_SB \ diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 4f8d0845ee1e..f299f137eaea 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1083,6 +1083,7 @@ static int patch_conexant_auto(struct hda_codec *codec) */ static const struct hda_device_id snd_hda_id_conexant[] = { + HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index f0662bd4e50f..27bf61c177c0 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -368,7 +368,7 @@ static const struct line6_properties podhd_properties_table[] = { .name = "POD HD500", .capabilities = LINE6_CAP_PCM | LINE6_CAP_HWMON, - .altsetting = 1, + .altsetting = 0, .ep_ctrl_r = 0x81, .ep_ctrl_w = 0x01, .ep_audio_r = 0x86, diff --git a/sound/usb/line6/variax.c b/sound/usb/line6/variax.c index 0d24c72c155f..ed158f04de80 100644 --- a/sound/usb/line6/variax.c +++ b/sound/usb/line6/variax.c @@ -244,5 +244,5 @@ static struct usb_driver variax_driver = { module_usb_driver(variax_driver); -MODULE_DESCRIPTION("Vairax Workbench USB driver"); +MODULE_DESCRIPTION("Variax Workbench USB driver"); MODULE_LICENSE("GPL"); diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c2152f3dd02d..e7c67be7c15f 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virtual/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.txt */ union { __u32 irq; @@ -1085,7 +1085,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/tools/testing/ktest/config-bisect.pl b/tools/testing/ktest/config-bisect.pl index 72525426654b..6fd864935319 100755 --- a/tools/testing/ktest/config-bisect.pl +++ b/tools/testing/ktest/config-bisect.pl @@ -663,7 +663,7 @@ while ($#ARGV >= 0) { } else { - die "Unknow option $opt\n"; + die "Unknown option $opt\n"; } } @@ -732,7 +732,7 @@ if ($start) { } } run_command "cp $good_start $good" or die "failed to copy to $good\n"; - run_command "cp $bad_start $bad" or die "faield to copy to $bad\n"; + run_command "cp $bad_start $bad" or die "failed to copy to $bad\n"; } else { if ( ! -f $good ) { die "Can not find file $good\n"; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index f645c0fbf7ec..acc43242a310 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -727,7 +727,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and - * Documentation/virtual/kvm/vcpu-requests.rst + * Documentation/virt/kvm/vcpu-requests.rst */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 936962abc38d..c45e2d7e942f 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -250,7 +250,7 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, * pending state of interrupt is latched in pending_latch variable. * Userspace will save and restore pending state and line_level * separately. - * Refer to Documentation/virtual/kvm/devices/arm-vgic-v3.txt + * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.txt * for handling of ISPENDR and ICPENDR. */ for (i = 0; i < len * 8; i++) { diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 57205beaa981..3b7525deec80 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -42,7 +42,7 @@ VGIC_AFFINITY_LEVEL(val, 3)) /* - * As per Documentation/virtual/kvm/devices/arm-vgic-v3.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-v3.txt, * below macros are defined for CPUREG encoding. */ #define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000 @@ -63,7 +63,7 @@ KVM_REG_ARM_VGIC_SYSREG_OP2_MASK) /* - * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-its.txt, * below macros are defined for ITS table entry encoding. */ #define KVM_ITS_CTE_VALID_SHIFT 63 |