diff options
253 files changed, 3283 insertions, 1945 deletions
diff --git a/.mailmap b/.mailmap index 8284692f96107..625b496bf5f45 100644 --- a/.mailmap +++ b/.mailmap @@ -446,7 +446,8 @@ Mythri P K <mythripk@ti.com> Nadav Amit <nadav.amit@gmail.com> <namit@vmware.com> Nadav Amit <nadav.amit@gmail.com> <namit@cs.technion.ac.il> Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com> -Naoya Horiguchi <naoya.horiguchi@nec.com> <n-horiguchi@ah.jp.nec.com> +Naoya Horiguchi <nao.horiguchi@gmail.com> <n-horiguchi@ah.jp.nec.com> +Naoya Horiguchi <nao.horiguchi@gmail.com> <naoya.horiguchi@nec.com> Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com> Neeraj Upadhyay <quic_neeraju@quicinc.com> <neeraju@codeaurora.org> Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com> diff --git a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml index afcdeed4e88af..bc813fe74faba 100644 --- a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml +++ b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml @@ -52,6 +52,9 @@ properties: - const: main - const: mm + power-domains: + maxItems: 1 + required: - compatible - reg diff --git a/Documentation/mm/page_owner.rst b/Documentation/mm/page_owner.rst index 0d0334cd51798..3a45a20fc05a1 100644 --- a/Documentation/mm/page_owner.rst +++ b/Documentation/mm/page_owner.rst @@ -24,10 +24,10 @@ fragmentation statistics can be obtained through gfp flag information of each page. It is already implemented and activated if page owner is enabled. Other usages are more than welcome. -It can also be used to show all the stacks and their outstanding -allocations, which gives us a quick overview of where the memory is going -without the need to screen through all the pages and match the allocation -and free operation. +It can also be used to show all the stacks and their current number of +allocated base pages, which gives us a quick overview of where the memory +is going without the need to screen through all the pages and match the +allocation and free operation. page owner is disabled by default. So, if you'd like to use it, you need to add "page_owner=on" to your boot cmdline. If the kernel is built @@ -75,42 +75,45 @@ Usage cat /sys/kernel/debug/page_owner_stacks/show_stacks > stacks.txt cat stacks.txt - prep_new_page+0xa9/0x120 - get_page_from_freelist+0x7e6/0x2140 - __alloc_pages+0x18a/0x370 - new_slab+0xc8/0x580 - ___slab_alloc+0x1f2/0xaf0 - __slab_alloc.isra.86+0x22/0x40 - kmem_cache_alloc+0x31b/0x350 - __khugepaged_enter+0x39/0x100 - dup_mmap+0x1c7/0x5ce - copy_process+0x1afe/0x1c90 - kernel_clone+0x9a/0x3c0 - __do_sys_clone+0x66/0x90 - do_syscall_64+0x7f/0x160 - entry_SYSCALL_64_after_hwframe+0x6c/0x74 - stack_count: 234 + post_alloc_hook+0x177/0x1a0 + get_page_from_freelist+0xd01/0xd80 + __alloc_pages+0x39e/0x7e0 + allocate_slab+0xbc/0x3f0 + ___slab_alloc+0x528/0x8a0 + kmem_cache_alloc+0x224/0x3b0 + sk_prot_alloc+0x58/0x1a0 + sk_alloc+0x32/0x4f0 + inet_create+0x427/0xb50 + __sock_create+0x2e4/0x650 + inet_ctl_sock_create+0x30/0x180 + igmp_net_init+0xc1/0x130 + ops_init+0x167/0x410 + setup_net+0x304/0xa60 + copy_net_ns+0x29b/0x4a0 + create_new_namespaces+0x4a1/0x820 + nr_base_pages: 16 ... ... echo 7000 > /sys/kernel/debug/page_owner_stacks/count_threshold cat /sys/kernel/debug/page_owner_stacks/show_stacks> stacks_7000.txt cat stacks_7000.txt - prep_new_page+0xa9/0x120 - get_page_from_freelist+0x7e6/0x2140 - __alloc_pages+0x18a/0x370 - alloc_pages_mpol+0xdf/0x1e0 - folio_alloc+0x14/0x50 - filemap_alloc_folio+0xb0/0x100 - page_cache_ra_unbounded+0x97/0x180 - filemap_fault+0x4b4/0x1200 - __do_fault+0x2d/0x110 - do_pte_missing+0x4b0/0xa30 - __handle_mm_fault+0x7fa/0xb70 - handle_mm_fault+0x125/0x300 - do_user_addr_fault+0x3c9/0x840 - exc_page_fault+0x68/0x150 - asm_exc_page_fault+0x22/0x30 - stack_count: 8248 + post_alloc_hook+0x177/0x1a0 + get_page_from_freelist+0xd01/0xd80 + __alloc_pages+0x39e/0x7e0 + alloc_pages_mpol+0x22e/0x490 + folio_alloc+0xd5/0x110 + filemap_alloc_folio+0x78/0x230 + page_cache_ra_order+0x287/0x6f0 + filemap_get_pages+0x517/0x1160 + filemap_read+0x304/0x9f0 + xfs_file_buffered_read+0xe6/0x1d0 [xfs] + xfs_file_read_iter+0x1f0/0x380 [xfs] + __kernel_read+0x3b9/0x730 + kernel_read_file+0x309/0x4d0 + __do_sys_finit_module+0x381/0x730 + do_syscall_64+0x8d/0x150 + entry_SYSCALL_64_after_hwframe+0x62/0x6a + nr_base_pages: 20824 ... cat /sys/kernel/debug/page_owner > page_owner_full.txt diff --git a/MAINTAINERS b/MAINTAINERS index c23fda1aa1f09..261023998c5b4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10024,7 +10024,7 @@ F: drivers/media/platform/st/sti/hva HWPOISON MEMORY FAILURE HANDLING M: Miaohe Lin <linmiaohe@huawei.com> -R: Naoya Horiguchi <naoya.horiguchi@nec.com> +R: Naoya Horiguchi <nao.horiguchi@gmail.com> L: linux-mm@kvack.org S: Maintained F: mm/hwpoison-inject.c @@ -11995,7 +11995,7 @@ F: include/keys/encrypted-type.h F: security/keys/encrypted-keys/ KEYS-TRUSTED -M: James Bottomley <jejb@linux.ibm.com> +M: James Bottomley <James.Bottomley@HansenPartnership.com> M: Jarkko Sakkinen <jarkko@kernel.org> M: Mimi Zohar <zohar@linux.ibm.com> L: linux-integrity@vger.kernel.org @@ -19669,7 +19669,7 @@ F: drivers/scsi/sg.c F: include/scsi/sg.h SCSI SUBSYSTEM -M: "James E.J. Bottomley" <jejb@linux.ibm.com> +M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> M: "Martin K. Petersen" <martin.petersen@oracle.com> L: linux-scsi@vger.kernel.org S: Maintained diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 06234c3a15f3d..cb68adcabe078 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -289,6 +289,11 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) adr_l x1, __hyp_text_end adr_l x2, dcache_clean_poc blr x2 + + mov_q x0, INIT_SCTLR_EL2_MMU_OFF + pre_disable_mmu_workaround + msr sctlr_el2, x0 + isb 0: mov_q x0, HCR_HOST_NVHE_FLAGS @@ -323,13 +328,11 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) cbz x0, 2f /* Set a sane SCTLR_EL1, the VHE way */ - pre_disable_mmu_workaround msr_s SYS_SCTLR_EL12, x1 mov x2, #BOOT_CPU_FLAG_E2H b 3f 2: - pre_disable_mmu_workaround msr sctlr_el1, x1 mov x2, xzr 3: diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 0f0e10bb0a954..b872b003a55f3 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -276,7 +276,10 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *ptep = NULL; pgdp = pgd_offset(mm, addr); - p4dp = p4d_offset(pgdp, addr); + p4dp = p4d_alloc(mm, pgdp, addr); + if (!p4dp) + return NULL; + pudp = pud_alloc(mm, p4dp, addr); if (!pudp) return NULL; diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 0c4e3ecf989d4..0e270a1c51e64 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -219,9 +219,6 @@ bool kernel_page_present(struct page *page) pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - if (!can_set_direct_map()) - return true; - pgdp = pgd_offset_k(addr); if (pgd_none(READ_ONCE(*pgdp))) return false; diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c index 74fb86b0d2097..7c728755852e1 100644 --- a/arch/powerpc/crypto/chacha-p10-glue.c +++ b/arch/powerpc/crypto/chacha-p10-glue.c @@ -197,6 +197,9 @@ static struct skcipher_alg algs[] = { static int __init chacha_p10_init(void) { + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return 0; + static_branch_enable(&have_p10); return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); @@ -204,10 +207,13 @@ static int __init chacha_p10_init(void) static void __exit chacha_p10_exit(void) { + if (!static_branch_likely(&have_p10)) + return; + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); } -module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init); +module_init(chacha_p10_init); module_exit(chacha_p10_exit); MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)"); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 1185efebf032b..29a8c8e185851 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1285,15 +1285,14 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, struct device *dev) { struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - struct iommu_group *grp = iommu_group_get(dev); struct iommu_table_group *table_group; + struct iommu_group *grp; /* At first attach the ownership is already set */ - if (!domain) { - iommu_group_put(grp); + if (!domain) return 0; - } + grp = iommu_group_get(dev); table_group = iommu_group_get_iommudata(grp); /* * The domain being set to PLATFORM from earlier diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 3dc85638bc63b..6a1e0fbbaa15b 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -340,7 +340,8 @@ SYM_CODE_START(pgm_check_handler) mvc __PT_LAST_BREAK(8,%r11),__LC_PGM_LAST_BREAK stctg %c1,%c1,__PT_CR1(%r11) #if IS_ENABLED(CONFIG_KVM) - lg %r12,__LC_GMAP + ltg %r12,__LC_GMAP + jz 5f clc __GMAP_ASCE(8,%r12), __PT_CR1(%r11) jne 5f BPENTER __SF_SIE_FLAGS(%r10),_TIF_ISOLATE_BP_GUEST diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6de50b80702e6..51cc9c7cb9bdc 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -255,6 +255,71 @@ __visible noinstr void do_int80_emulation(struct pt_regs *regs) instrumentation_end(); syscall_exit_to_user_mode(regs); } + +#ifdef CONFIG_X86_FRED +/* + * A FRED-specific INT80 handler is warranted for the follwing reasons: + * + * 1) As INT instructions and hardware interrupts are separate event + * types, FRED does not preclude the use of vector 0x80 for external + * interrupts. As a result, the FRED setup code does not reserve + * vector 0x80 and calling int80_is_external() is not merely + * suboptimal but actively incorrect: it could cause a system call + * to be incorrectly ignored. + * + * 2) It is called only for handling vector 0x80 of event type + * EVENT_TYPE_SWINT and will never be called to handle any external + * interrupt (event type EVENT_TYPE_EXTINT). + * + * 3) FRED has separate entry flows depending on if the event came from + * user space or kernel space, and because the kernel does not use + * INT insns, the FRED kernel entry handler fred_entry_from_kernel() + * falls through to fred_bad_type() if the event type is + * EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling + * an INT insn, it can only be from a user level. + * + * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will + * likely take a different approach if it is ever needed: it + * probably belongs in either fred_intx()/ fred_other() or + * asm_fred_entrypoint_user(), depending on if this ought to be done + * for all entries from userspace or only system + * calls. + * + * 5) INT $0x80 is the fast path for 32-bit system calls under FRED. + */ +DEFINE_FREDENTRY_RAW(int80_emulation) +{ + int nr; + + enter_from_user_mode(regs); + + instrumentation_begin(); + add_random_kstack_offset(); + + /* + * FRED pushed 0 into regs::orig_ax and regs::ax contains the + * syscall number. + * + * User tracing code (ptrace or signal handlers) might assume + * that the regs::orig_ax contains a 32-bit number on invoking + * a 32-bit syscall. + * + * Establish the syscall convention by saving the 32bit truncated + * syscall number in regs::orig_ax and by invalidating regs::ax. + */ + regs->orig_ax = regs->ax & GENMASK(31, 0); + regs->ax = -ENOSYS; + + nr = syscall_32_enter(regs); + + local_irq_enable(); + nr = syscall_enter_from_user_mode_work(regs, nr); + do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); + syscall_exit_to_user_mode(regs); +} +#endif #else /* CONFIG_IA32_EMULATION */ /* Handles int $0x80 on a 32bit kernel */ diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c index ac120cbdaaf2b..89c1476fcdd9f 100644 --- a/arch/x86/entry/entry_fred.c +++ b/arch/x86/entry/entry_fred.c @@ -28,9 +28,9 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code if (regs->fred_cs.sl > 0) { pr_emerg("PANIC: invalid or fatal FRED event; event type %u " "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", - regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + regs->fred_ss.type, regs->fred_ss.vector, error_code, fred_event_data(regs), regs->cs, regs->ip); - die("invalid or fatal FRED event", regs, regs->orig_ax); + die("invalid or fatal FRED event", regs, error_code); panic("invalid or fatal FRED event"); } else { unsigned long flags = oops_begin(); @@ -38,10 +38,10 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code pr_alert("BUG: invalid or fatal FRED event; event type %u " "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", - regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + regs->fred_ss.type, regs->fred_ss.vector, error_code, fred_event_data(regs), regs->cs, regs->ip); - if (__die("Invalid or fatal FRED event", regs, regs->orig_ax)) + if (__die("Invalid or fatal FRED event", regs, error_code)) sig = 0; oops_end(flags, regs, sig); @@ -66,7 +66,7 @@ static noinstr void fred_intx(struct pt_regs *regs) /* INT80 */ case IA32_SYSCALL_VECTOR: if (ia32_enabled()) - return int80_emulation(regs); + return fred_int80_emulation(regs); fallthrough; #endif diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 78cd5084104e9..4367aa77cb8d9 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1693,6 +1693,7 @@ void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) lbr->from = x86_pmu.lbr_from; lbr->to = x86_pmu.lbr_to; lbr->info = x86_pmu.lbr_info; + lbr->has_callstack = x86_pmu_has_lbr_callstack(); } EXPORT_SYMBOL_GPL(x86_perf_get_lbr); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 16e07a2eee195..6efd1497b0263 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -855,6 +855,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; struct kvm_hypervisor_cpuid kvm_cpuid; + bool is_amd_compatible; /* * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 3736b8a46c04d..7f1e17250546b 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -555,6 +555,7 @@ struct x86_pmu_lbr { unsigned int from; unsigned int to; unsigned int info; + bool has_callstack; }; extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ca295b0c1eeee..ab18185894dfd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1652,7 +1652,8 @@ static void __init bhi_select_mitigation(void) return; /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { spec_ctrl_disable_kernel_rrsba(); if (rrsba_disabled) return; @@ -2804,11 +2805,13 @@ static const char *spectre_bhi_state(void) { if (!boot_cpu_has_bug(X86_BUG_BHI)) return "; BHI: Not affected"; - else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) return "; BHI: BHI_DIS_S"; - else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) return "; BHI: SW loop, KVM: SW loop"; - else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && rrsba_disabled) + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && + rrsba_disabled) return "; BHI: Retpoline"; else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) return "; BHI: Vulnerable, KVM: SW loop"; diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index b7174209d855c..946813d816bfc 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a88bb14266b69..addc44fc7187d 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,11 +3,6 @@ ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror -ifeq ($(CONFIG_FRAME_POINTER),y) -OBJECT_FILES_NON_STANDARD_vmx/vmenter.o := y -OBJECT_FILES_NON_STANDARD_svm/vmenter.o := y -endif - include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index bfc0bfcb2bc60..77352a4abd87f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -376,6 +376,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); + vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 856e3037e74f3..23dbb9eb277c7 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -120,6 +120,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } +static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.is_amd_compatible; +} + +static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu) +{ + return !guest_cpuid_is_amd_compatible(vcpu); +} + static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cf37586f04668..ebf41023be382 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2776,7 +2776,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); - if (r && lvt_type == APIC_LVTPC) + if (r && lvt_type == APIC_LVTPC && + guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 992e651540e85..db007a4dffa2e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4935,7 +4935,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, context->cpu_role.base.level, is_efer_nx(context), guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), - guest_cpuid_is_amd_or_hygon(vcpu)); + guest_cpuid_is_amd_compatible(vcpu)); } static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, @@ -5576,9 +5576,9 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ - vcpu->arch.root_mmu.root_role.word = 0; - vcpu->arch.guest_mmu.root_role.word = 0; - vcpu->arch.nested_mmu.root_role.word = 0; + vcpu->arch.root_mmu.root_role.invalid = 1; + vcpu->arch.guest_mmu.root_role.invalid = 1; + vcpu->arch.nested_mmu.root_role.invalid = 1; vcpu->arch.root_mmu.cpu_role.ext.valid = 0; vcpu->arch.guest_mmu.cpu_role.ext.valid = 0; vcpu->arch.nested_mmu.cpu_role.ext.valid = 0; @@ -7399,7 +7399,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, * by the memslot, KVM can't use a hugepage due to the * misaligned address regardless of memory attributes. */ - if (gfn >= slot->base_gfn) { + if (gfn >= slot->base_gfn && + gfn + nr_pages <= slot->base_gfn + slot->npages) { if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d078157e62aa4..04c1f0957fea8 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1548,17 +1548,21 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, } } -/* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. - */ +static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) +{ + /* + * All TDP MMU shadow pages share the same role as their root, aside + * from level, so it is valid to key off any shadow page to determine if + * write protection is needed for an entire tree. + */ + return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); +} + static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { - u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; + const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; bool spte_set = false; @@ -1573,7 +1577,7 @@ retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) @@ -1590,11 +1594,9 @@ retry: } /* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. + * Clear the dirty status (D-bit or W-bit) of all the SPTEs mapping GFNs in the + * memslot. Returns true if an SPTE has been changed and the TLBs need to be + * flushed. */ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -1610,18 +1612,11 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, return spte_set; } -/* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. - */ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { - u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : - shadow_dirty_mask; + const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; lockdep_assert_held_write(&kvm->mmu_lock); @@ -1633,7 +1628,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || @@ -1659,11 +1654,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. + * Clear the dirty status (D-bit or W-bit) of all the 4k SPTEs mapping GFNs for + * which a bit is set in mask, starting at gfn. The given memslot is expected to + * contain all the GFNs represented by set bits in the mask. */ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index c397b28e3d1b6..a593b03c9aed6 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -775,8 +775,20 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) pmu->pebs_data_cfg_mask = ~0ull; bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); - if (vcpu->kvm->arch.enable_pmu) - static_call(kvm_x86_pmu_refresh)(vcpu); + if (!vcpu->kvm->arch.enable_pmu) + return; + + static_call(kvm_x86_pmu_refresh)(vcpu); + + /* + * At RESET, both Intel and AMD CPUs set all enable bits for general + * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that + * was written for v1 PMUs don't unknowingly leave GP counters disabled + * in the global controls). Emulate that behavior when refreshing the + * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL. + */ + if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters) + pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0); } void kvm_pmu_init(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 61a7531d41b01..759581bb2128d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -434,7 +434,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT); else pages = kmalloc(size, GFP_KERNEL_ACCOUNT); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d1a9f99516358..9aaf83c8d57df 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1503,6 +1503,11 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) +{ + return page_address(sd->save_area) + 0x400; +} + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1519,12 +1524,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * or subsequent vmload of host save area. */ vmsave(sd->save_area_pa); - if (sev_es_guest(vcpu->kvm)) { - struct sev_es_save_area *hostsa; - hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); - - sev_es_prepare_switch_to_guest(hostsa); - } + if (sev_es_guest(vcpu->kvm)) + sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd)); if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); @@ -4101,6 +4102,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) { + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); guest_state_enter_irqoff(); @@ -4108,7 +4110,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in amd_clear_divider(); if (sev_es_guest(vcpu->kvm)) - __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted, + sev_es_host_save_area(sd)); else __svm_vcpu_run(svm, spec_ctrl_intercepted); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 7f1fbd874c458..33878efdebc82 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -698,7 +698,8 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); /* vmenter.S */ -void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted, + struct sev_es_save_area *hostsa); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); #define DEFINE_KVM_GHCB_ACCESSORS(field) \ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 187018c424bfb..a0c8eb37d3e1c 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/bitsperlong.h> +#include <asm/frame.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> #include "kvm-asm-offsets.h" @@ -67,7 +68,7 @@ "", X86_FEATURE_V_SPEC_CTRL 901: .endm -.macro RESTORE_HOST_SPEC_CTRL_BODY +.macro RESTORE_HOST_SPEC_CTRL_BODY spec_ctrl_intercepted:req 900: /* Same for after vmexit. */ mov $MSR_IA32_SPEC_CTRL, %ecx @@ -76,7 +77,7 @@ * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, * if it was not intercepted during guest execution. */ - cmpb $0, (%_ASM_SP) + cmpb $0, \spec_ctrl_intercepted jnz 998f rdmsr movl %eax, SVM_spec_ctrl(%_ASM_DI) @@ -99,6 +100,7 @@ */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP + mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 push %r15 push %r14 @@ -268,7 +270,7 @@ SYM_FUNC_START(__svm_vcpu_run) RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY (%_ASM_SP) 10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b @@ -290,66 +292,68 @@ SYM_FUNC_START(__svm_vcpu_run) SYM_FUNC_END(__svm_vcpu_run) +#ifdef CONFIG_KVM_AMD_SEV + + +#ifdef CONFIG_X86_64 +#define SEV_ES_GPRS_BASE 0x300 +#define SEV_ES_RBX (SEV_ES_GPRS_BASE + __VCPU_REGS_RBX * WORD_SIZE) +#define SEV_ES_RBP (SEV_ES_GPRS_BASE + __VCPU_REGS_RBP * WORD_SIZE) +#define SEV_ES_RSI (SEV_ES_GPRS_BASE + __VCPU_REGS_RSI * WORD_SIZE) +#define SEV_ES_RDI (SEV_ES_GPRS_BASE + __VCPU_REGS_RDI * WORD_SIZE) +#define SEV_ES_R12 (SEV_ES_GPRS_BASE + __VCPU_REGS_R12 * WORD_SIZE) +#define SEV_ES_R13 (SEV_ES_GPRS_BASE + __VCPU_REGS_R13 * WORD_SIZE) +#define SEV_ES_R14 (SEV_ES_GPRS_BASE + __VCPU_REGS_R14 * WORD_SIZE) +#define SEV_ES_R15 (SEV_ES_GPRS_BASE + __VCPU_REGS_R15 * WORD_SIZE) +#endif + /** * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode * @svm: struct vcpu_svm * * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_sev_es_vcpu_run) - push %_ASM_BP -#ifdef CONFIG_X86_64 - push %r15 - push %r14 - push %r13 - push %r12 -#else - push %edi - push %esi -#endif - push %_ASM_BX + FRAME_BEGIN /* - * Save variables needed after vmexit on the stack, in inverse - * order compared to when they are needed. + * Save non-volatile (callee-saved) registers to the host save area. + * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not + * saved on VMRUN. */ + mov %rbp, SEV_ES_RBP (%rdx) + mov %r15, SEV_ES_R15 (%rdx) + mov %r14, SEV_ES_R14 (%rdx) + mov %r13, SEV_ES_R13 (%rdx) + mov %r12, SEV_ES_R12 (%rdx) + mov %rbx, SEV_ES_RBX (%rdx) - /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ - push %_ASM_ARG2 - - /* Save @svm. */ - push %_ASM_ARG1 - -.ifnc _ASM_ARG1, _ASM_DI /* - * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX - * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + * Save volatile registers that hold arguments that are needed after + * #VMEXIT (RDI=@svm and RSI=@spec_ctrl_intercepted). */ - mov %_ASM_ARG1, %_ASM_DI -.endif + mov %rdi, SEV_ES_RDI (%rdx) + mov %rsi, SEV_ES_RSI (%rdx) - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX (@hostsa). */ RESTORE_GUEST_SPEC_CTRL /* Get svm->current_vmcb->pa into RAX. */ - mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX - mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX + mov SVM_current_vmcb(%rdi), %rax + mov KVM_VMCB_pa(%rax), %rax /* Enter guest mode */ sti -1: vmrun %_ASM_AX +1: vmrun %rax 2: cli - /* Pop @svm to RDI, guest registers have been saved already. */ - pop %_ASM_DI - #ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL /* @@ -361,30 +365,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) */ UNTRAIN_RET_VM - /* "Pop" @spec_ctrl_intercepted. */ - pop %_ASM_BX - - pop %_ASM_BX - -#ifdef CONFIG_X86_64 - pop %r12 - pop %r13 - pop %r14 - pop %r15 -#else - pop %esi - pop %edi -#endif - pop %_ASM_BP + FRAME_END RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY %sil -3: cmpb $0, _ASM_RIP(kvm_rebooting) +3: cmpb $0, kvm_rebooting(%rip) jne 2b ud2 _ASM_EXTABLE(1b, 3b) SYM_FUNC_END(__svm_sev_es_vcpu_run) +#endif /* CONFIG_KVM_AMD_SEV */ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 12ade343a17ed..be40474de6e4d 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -535,7 +535,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) perf_capabilities = vcpu_get_perf_capabilities(vcpu); if (cpuid_model_is_consistent(vcpu) && (perf_capabilities & PMU_CAP_LBR_FMT)) - x86_perf_get_lbr(&lbr_desc->records); + memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps)); else lbr_desc->records.nr = 0; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c37a89eda90f8..22411f4aff530 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -218,6 +218,8 @@ module_param(ple_window_max, uint, 0444); int __read_mostly pt_mode = PT_MODE_SYSTEM; module_param(pt_mode, int, S_IRUGO); +struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; + static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); @@ -7862,10 +7864,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } -static u64 vmx_get_perf_capabilities(void) +static __init u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; - struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -7875,15 +7876,43 @@ static u64 vmx_get_perf_capabilities(void) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { - x86_perf_get_lbr(&lbr); - if (lbr.nr) + x86_perf_get_lbr(&vmx_lbr_caps); + + /* + * KVM requires LBR callstack support, as the overhead due to + * context switching LBRs without said support is too high. + * See intel_pmu_create_guest_lbr_event() for more info. + */ + if (!vmx_lbr_caps.has_callstack) + memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); + else if (vmx_lbr_caps.nr) perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; } if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 65786dbe7d60b..90f9e44346464 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -15,6 +15,7 @@ #include "vmx_ops.h" #include "../cpuid.h" #include "run_flags.h" +#include "../mmu.h" #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -109,6 +110,8 @@ struct lbr_desc { bool msr_passthrough; }; +extern struct x86_pmu_lbr vmx_lbr_caps; + /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -719,7 +722,8 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) if (!enable_ept) return true; - return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + return allow_smaller_maxphyaddr && + cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits(); } static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 984ea2089efc3..91478b769af08 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3470,7 +3470,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index e674ccf720b9f..391059b2c6fbc 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -382,8 +382,15 @@ SYM_FUNC_END(call_depth_return_thunk) SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || \ + defined(CONFIG_MITIGATION_SRSO) || \ + defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \ "jmp warn_thunk_thunk", X86_FEATURE_ALWAYS +#else + ANNOTATE_UNRET_SAFE + ret +#endif int3 SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) diff --git a/block/bdev.c b/block/bdev.c index b8e32d933a636..4dc94145eb533 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -645,6 +645,14 @@ static void blkdev_flush_mapping(struct block_device *bdev) bdev_write_inode(bdev); } +static void blkdev_put_whole(struct block_device *bdev) +{ + if (atomic_dec_and_test(&bdev->bd_openers)) + blkdev_flush_mapping(bdev); + if (bdev->bd_disk->fops->release) + bdev->bd_disk->fops->release(bdev->bd_disk); +} + static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) { struct gendisk *disk = bdev->bd_disk; @@ -663,20 +671,21 @@ static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) if (!atomic_read(&bdev->bd_openers)) set_init_blocksize(bdev); - if (test_bit(GD_NEED_PART_SCAN, &disk->state)) - bdev_disk_changed(disk, false); atomic_inc(&bdev->bd_openers); + if (test_bit(GD_NEED_PART_SCAN, &disk->state)) { + /* + * Only return scanning errors if we are called from contexts + * that explicitly want them, e.g. the BLKRRPART ioctl. + */ + ret = bdev_disk_changed(disk, false); + if (ret && (mode & BLK_OPEN_STRICT_SCAN)) { + blkdev_put_whole(bdev); + return ret; + } + } return 0; } -static void blkdev_put_whole(struct block_device *bdev) -{ - if (atomic_dec_and_test(&bdev->bd_openers)) - blkdev_flush_mapping(bdev); - if (bdev->bd_disk->fops->release) - bdev->bd_disk->fops->release(bdev->bd_disk); -} - static int blkdev_get_part(struct block_device *part, blk_mode_t mode) { struct gendisk *disk = part->bd_disk; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index baa20c85799d5..690ca99dfaca6 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1439,8 +1439,11 @@ static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); - /* make sure that nobody messed with @iocg */ - WARN_ON_ONCE(list_empty(&iocg->active_list)); + /* + * make sure that nobody messed with @iocg. Check iocg->pd.online + * to avoid warn when removing blkcg or disk. + */ + WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); diff --git a/block/ioctl.c b/block/ioctl.c index a9028a2c2db57..f505f9c341eb0 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -563,7 +563,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, return -EACCES; if (bdev_is_partition(bdev)) return -EINVAL; - return disk_scan_partitions(bdev->bd_disk, mode); + return disk_scan_partitions(bdev->bd_disk, + mode | BLK_OPEN_STRICT_SCAN); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN: diff --git a/drivers/char/random.c b/drivers/char/random.c index 456be28ba67cb..2597cb43f4387 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -702,7 +702,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -718,8 +718,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -890,8 +890,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 25371c91a58fe..8cca52be993f4 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -37,6 +37,10 @@ static HLIST_HEAD(clk_root_list); static HLIST_HEAD(clk_orphan_list); static LIST_HEAD(clk_notifier_list); +/* List of registered clks that use runtime PM */ +static HLIST_HEAD(clk_rpm_list); +static DEFINE_MUTEX(clk_rpm_list_lock); + static const struct hlist_head *all_lists[] = { &clk_root_list, &clk_orphan_list, @@ -59,6 +63,7 @@ struct clk_core { struct clk_hw *hw; struct module *owner; struct device *dev; + struct hlist_node rpm_node; struct device_node *of_node; struct clk_core *parent; struct clk_parent_map *parents; @@ -122,6 +127,89 @@ static void clk_pm_runtime_put(struct clk_core *core) pm_runtime_put_sync(core->dev); } +/** + * clk_pm_runtime_get_all() - Runtime "get" all clk provider devices + * + * Call clk_pm_runtime_get() on all runtime PM enabled clks in the clk tree so + * that disabling unused clks avoids a deadlock where a device is runtime PM + * resuming/suspending and the runtime PM callback is trying to grab the + * prepare_lock for something like clk_prepare_enable() while + * clk_disable_unused_subtree() holds the prepare_lock and is trying to runtime + * PM resume/suspend the device as well. + * + * Context: Acquires the 'clk_rpm_list_lock' and returns with the lock held on + * success. Otherwise the lock is released on failure. + * + * Return: 0 on success, negative errno otherwise. + */ +static int clk_pm_runtime_get_all(void) +{ + int ret; + struct clk_core *core, *failed; + + /* + * Grab the list lock to prevent any new clks from being registered + * or unregistered until clk_pm_runtime_put_all(). + */ + mutex_lock(&clk_rpm_list_lock); + + /* + * Runtime PM "get" all the devices that are needed for the clks + * currently registered. Do this without holding the prepare_lock, to + * avoid the deadlock. + */ + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + ret = clk_pm_runtime_get(core); + if (ret) { + failed = core; + pr_err("clk: Failed to runtime PM get '%s' for clk '%s'\n", + dev_name(failed->dev), failed->name); + goto err; + } + } + + return 0; + +err: + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + if (core == failed) + break; + + clk_pm_runtime_put(core); + } + mutex_unlock(&clk_rpm_list_lock); + + return ret; +} + +/** + * clk_pm_runtime_put_all() - Runtime "put" all clk provider devices + * + * Put the runtime PM references taken in clk_pm_runtime_get_all() and release + * the 'clk_rpm_list_lock'. + */ +static void clk_pm_runtime_put_all(void) +{ + struct clk_core *core; + + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) + clk_pm_runtime_put(core); + mutex_unlock(&clk_rpm_list_lock); +} + +static void clk_pm_runtime_init(struct clk_core *core) +{ + struct device *dev = core->dev; + + if (dev && pm_runtime_enabled(dev)) { + core->rpm_enabled = true; + + mutex_lock(&clk_rpm_list_lock); + hlist_add_head(&core->rpm_node, &clk_rpm_list); + mutex_unlock(&clk_rpm_list_lock); + } +} + /*** locking ***/ static void clk_prepare_lock(void) { @@ -1381,9 +1469,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) if (core->flags & CLK_IGNORE_UNUSED) return; - if (clk_pm_runtime_get(core)) - return; - if (clk_core_is_prepared(core)) { trace_clk_unprepare(core); if (core->ops->unprepare_unused) @@ -1392,8 +1477,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) core->ops->unprepare(core->hw); trace_clk_unprepare_complete(core); } - - clk_pm_runtime_put(core); } static void __init clk_disable_unused_subtree(struct clk_core *core) @@ -1409,9 +1492,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); - if (clk_pm_runtime_get(core)) - goto unprepare_out; - flags = clk_enable_lock(); if (core->enable_count) @@ -1436,8 +1516,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) unlock_out: clk_enable_unlock(flags); - clk_pm_runtime_put(core); -unprepare_out: if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_disable_unprepare(core->parent); } @@ -1453,6 +1531,7 @@ __setup("clk_ignore_unused", clk_ignore_unused_setup); static int __init clk_disable_unused(void) { struct clk_core *core; + int ret; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); @@ -1461,6 +1540,13 @@ static int __init clk_disable_unused(void) pr_info("clk: Disabling unused clocks\n"); + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; + /* + * Grab the prepare lock to keep the clk topology stable while iterating + * over clks. + */ clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) @@ -1477,6 +1563,8 @@ static int __init clk_disable_unused(void) clk_prepare_unlock(); + clk_pm_runtime_put_all(); + return 0; } late_initcall_sync(clk_disable_unused); @@ -3252,9 +3340,7 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, { struct clk_core *child; - clk_pm_runtime_get(c); clk_summary_show_one(s, c, level); - clk_pm_runtime_put(c); hlist_for_each_entry(child, &c->children, child_node) clk_summary_show_subtree(s, child, level + 1); @@ -3264,11 +3350,15 @@ static int clk_summary_show(struct seq_file *s, void *data) { struct clk_core *c; struct hlist_head **lists = s->private; + int ret; seq_puts(s, " enable prepare protect duty hardware connection\n"); seq_puts(s, " clock count count count rate accuracy phase cycle enable consumer id\n"); seq_puts(s, "---------------------------------------------------------------------------------------------------------------------------------------------\n"); + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; clk_prepare_lock(); @@ -3277,6 +3367,7 @@ static int clk_summary_show(struct seq_file *s, void *data) clk_summary_show_subtree(s, c, 0); clk_prepare_unlock(); + clk_pm_runtime_put_all(); return 0; } @@ -3324,8 +3415,14 @@ static int clk_dump_show(struct seq_file *s, void *data) struct clk_core *c; bool first_node = true; struct hlist_head **lists = s->private; + int ret; + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; seq_putc(s, '{'); + clk_prepare_lock(); for (; *lists; lists++) { @@ -3338,6 +3435,7 @@ static int clk_dump_show(struct seq_file *s, void *data) } clk_prepare_unlock(); + clk_pm_runtime_put_all(); seq_puts(s, "}\n"); return 0; @@ -3981,8 +4079,6 @@ static int __clk_core_init(struct clk_core *core) } clk_core_reparent_orphans_nolock(); - - kref_init(&core->ref); out: clk_pm_runtime_put(core); unlock: @@ -4211,6 +4307,22 @@ static void clk_core_free_parent_map(struct clk_core *core) kfree(core->parents); } +/* Free memory allocated for a struct clk_core */ +static void __clk_release(struct kref *ref) +{ + struct clk_core *core = container_of(ref, struct clk_core, ref); + + if (core->rpm_enabled) { + mutex_lock(&clk_rpm_list_lock); + hlist_del(&core->rpm_node); + mutex_unlock(&clk_rpm_list_lock); + } + + clk_core_free_parent_map(core); + kfree_const(core->name); + kfree(core); +} + static struct clk * __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) { @@ -4231,6 +4343,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_out; } + kref_init(&core->ref); + core->name = kstrdup_const(init->name, GFP_KERNEL); if (!core->name) { ret = -ENOMEM; @@ -4243,9 +4357,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) } core->ops = init->ops; - if (dev && pm_runtime_enabled(dev)) - core->rpm_enabled = true; core->dev = dev; + clk_pm_runtime_init(core); core->of_node = np; if (dev && dev->driver) core->owner = dev->driver->owner; @@ -4285,12 +4398,10 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) hw->clk = NULL; fail_create_clk: - clk_core_free_parent_map(core); fail_parents: fail_ops: - kfree_const(core->name); fail_name: - kfree(core); + kref_put(&core->ref, __clk_release); fail_out: return ERR_PTR(ret); } @@ -4370,18 +4481,6 @@ int of_clk_hw_register(struct device_node *node, struct clk_hw *hw) } EXPORT_SYMBOL_GPL(of_clk_hw_register); -/* Free memory allocated for a clock. */ -static void __clk_release(struct kref *ref) -{ - struct clk_core *core = container_of(ref, struct clk_core, ref); - - lockdep_assert_held(&prepare_lock); - - clk_core_free_parent_map(core); - kfree_const(core->name); - kfree(core); -} - /* * Empty clk_ops for unregistered clocks. These are used temporarily * after clk_unregister() was called on a clock and until last clock @@ -4472,7 +4571,8 @@ void clk_unregister(struct clk *clk) if (ops == &clk_nodrv_ops) { pr_err("%s: unregistered clock: %s\n", __func__, clk->core->name); - goto unlock; + clk_prepare_unlock(); + return; } /* * Assign empty clock ops for consumers that might still hold @@ -4506,11 +4606,10 @@ void clk_unregister(struct clk *clk) if (clk->core->protect_count) pr_warn("%s: unregistering protected clock: %s\n", __func__, clk->core->name); + clk_prepare_unlock(); kref_put(&clk->core->ref, __clk_release); free_clk(clk); -unlock: - clk_prepare_unlock(); } EXPORT_SYMBOL_GPL(clk_unregister); @@ -4669,13 +4768,11 @@ void __clk_put(struct clk *clk) if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX) clk_set_rate_range_nolock(clk, 0, ULONG_MAX); - owner = clk->core->owner; - kref_put(&clk->core->ref, __clk_release); - clk_prepare_unlock(); + owner = clk->core->owner; + kref_put(&clk->core->ref, __clk_release); module_put(owner); - free_clk(clk); } diff --git a/drivers/clk/mediatek/clk-mt7988-infracfg.c b/drivers/clk/mediatek/clk-mt7988-infracfg.c index 449041f8abbc9..c8c023afe3e5a 100644 --- a/drivers/clk/mediatek/clk-mt7988-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7988-infracfg.c @@ -156,7 +156,7 @@ static const struct mtk_gate infra_clks[] = { GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P1, "infra_pcie_peri_ck_26m_ck_p1", "csw_infra_f26m_sel", 8), GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P2, "infra_pcie_peri_ck_26m_ck_p2", - "csw_infra_f26m_sel", 9), + "infra_pcie_peri_ck_26m_ck_p3", 9), GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P3, "infra_pcie_peri_ck_26m_ck_p3", "csw_infra_f26m_sel", 10), /* INFRA1 */ diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 2e55368dc4d82..bd37ab4d1a9bb 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -13,6 +13,7 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/slab.h> #include "clk-mtk.h" @@ -494,6 +495,16 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, return IS_ERR(base) ? PTR_ERR(base) : -ENOMEM; } + + devm_pm_runtime_enable(&pdev->dev); + /* + * Do a pm_runtime_resume_and_get() to workaround a possible + * deadlock between clk_register() and the genpd framework. + */ + r = pm_runtime_resume_and_get(&pdev->dev); + if (r) + return r; + /* Calculate how many clk_hw_onecell_data entries to allocate */ num_clks = mcd->num_clks + mcd->num_composite_clks; num_clks += mcd->num_fixed_clks + mcd->num_factor_clks; @@ -574,6 +585,8 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, goto unregister_clks; } + pm_runtime_put(&pdev->dev); + return r; unregister_clks: @@ -604,6 +617,8 @@ free_data: free_base: if (mcd->shared_io && base) iounmap(base); + + pm_runtime_put(&pdev->dev); return r; } diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 1ee62cd58582b..25db014494a4d 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -92,7 +92,7 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type) case 0x5e: return GPIOPANELCTL; default: - return -EOPNOTSUPP; + return -ENOTSUPP; } } diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c index 5ef8af8249806..c097e310c9e84 100644 --- a/drivers/gpio/gpio-lpc32xx.c +++ b/drivers/gpio/gpio-lpc32xx.c @@ -529,6 +529,7 @@ static const struct of_device_id lpc32xx_gpio_of_match[] = { { .compatible = "nxp,lpc3220-gpio", }, { }, }; +MODULE_DEVICE_TABLE(of, lpc32xx_gpio_of_match); static struct platform_driver lpc32xx_gpio_driver = { .driver = { diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c index c18b6b47384f1..94ca9d03c0949 100644 --- a/drivers/gpio/gpio-wcove.c +++ b/drivers/gpio/gpio-wcove.c @@ -104,7 +104,7 @@ static inline int to_reg(int gpio, enum ctrl_register type) unsigned int reg = type == CTRL_IN ? GPIO_IN_CTRL_BASE : GPIO_OUT_CTRL_BASE; if (gpio >= WCOVE_GPIO_NUM) - return -EOPNOTSUPP; + return -ENOTSUPP; return reg + gpio; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 0a4b09709cfb1..ec888fc6ead8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -819,7 +819,7 @@ retry: p->bytes_moved += ctx.bytes_moved; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) p->bytes_moved_vis += ctx.bytes_moved; if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 010b0cb7693c9..2099159a693fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -617,8 +617,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, return r; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - bo->tbo.resource->mem_type == TTM_PL_VRAM && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, ctx.bytes_moved); else @@ -1272,23 +1271,25 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct ttm_resource *res = bo->tbo.resource; uint64_t size = amdgpu_bo_size(bo); struct drm_gem_object *obj; unsigned int domain; bool shared; /* Abort if the BO doesn't currently have a backing store */ - if (!bo->tbo.resource) + if (!res) return; obj = &bo->tbo.base; shared = drm_gem_object_is_shared_for_memory_stats(obj); - domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); + domain = amdgpu_mem_type_to_domain(res->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: stats->vram += size; - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) stats->visible_vram += size; if (shared) stats->vram_shared += size; @@ -1389,10 +1390,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - if (bo->resource->mem_type != TTM_PL_VRAM) - return 0; - - if (amdgpu_bo_in_cpu_visible_vram(abo)) + if (amdgpu_res_cpu_visible(adev, bo->resource)) return 0; /* Can't move a pinned BO to visible VRAM */ @@ -1415,7 +1413,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* this should never happen */ if (bo->resource->mem_type == TTM_PL_VRAM && - !amdgpu_bo_in_cpu_visible_vram(abo)) + !amdgpu_res_cpu_visible(adev, bo->resource)) return VM_FAULT_SIGBUS; ttm_bo_move_to_lru_tail_unlocked(bo); @@ -1579,6 +1577,7 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, */ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct dma_buf_attachment *attachment; struct dma_buf *dma_buf; const char *placement; @@ -1587,10 +1586,11 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) if (dma_resv_trylock(bo->tbo.base.resv)) { unsigned int domain; + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) placement = "VRAM VISIBLE"; else placement = "VRAM"; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index be679c42b0b8c..fa03d9e4874cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -251,28 +251,6 @@ static inline u64 amdgpu_bo_mmap_offset(struct amdgpu_bo *bo) } /** - * amdgpu_bo_in_cpu_visible_vram - check if BO is (partly) in visible VRAM - */ -static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - struct amdgpu_res_cursor cursor; - - if (!bo->tbo.resource || bo->tbo.resource->mem_type != TTM_PL_VRAM) - return false; - - amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor); - while (cursor.remaining) { - if (cursor.start < adev->gmc.visible_vram_size) - return true; - - amdgpu_res_next(&cursor, cursor.size); - } - - return false; -} - -/** * amdgpu_bo_explicit_sync - return whether the bo is explicitly synced */ static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index fc418e670fdae..1d71729e3f6bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -133,7 +133,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, } else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) && - amdgpu_bo_in_cpu_visible_vram(abo)) { + amdgpu_res_cpu_visible(adev, bo->resource)) { /* Try evicting to the CPU inaccessible part of VRAM * first, but only set GTT as busy placement, so this @@ -403,40 +403,55 @@ error: return r; } -/* - * amdgpu_mem_visible - Check that memory can be accessed by ttm_bo_move_memcpy +/** + * amdgpu_res_cpu_visible - Check that resource can be accessed by CPU + * @adev: amdgpu device + * @res: the resource to check * - * Called by amdgpu_bo_move() + * Returns: true if the full resource is CPU visible, false otherwise. */ -static bool amdgpu_mem_visible(struct amdgpu_device *adev, - struct ttm_resource *mem) +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res) { - u64 mem_size = (u64)mem->size; struct amdgpu_res_cursor cursor; - u64 end; - if (mem->mem_type == TTM_PL_SYSTEM || - mem->mem_type == TTM_PL_TT) + if (!res) + return false; + + if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT || + res->mem_type == AMDGPU_PL_PREEMPT) return true; - if (mem->mem_type != TTM_PL_VRAM) + + if (res->mem_type != TTM_PL_VRAM) return false; - amdgpu_res_first(mem, 0, mem_size, &cursor); - end = cursor.start + cursor.size; + amdgpu_res_first(res, 0, res->size, &cursor); while (cursor.remaining) { + if ((cursor.start + cursor.size) >= adev->gmc.visible_vram_size) + return false; amdgpu_res_next(&cursor, cursor.size); + } - if (!cursor.remaining) - break; + return true; +} - /* ttm_resource_ioremap only supports contiguous memory */ - if (end != cursor.start) - return false; +/* + * amdgpu_res_copyable - Check that memory can be accessed by ttm_bo_move_memcpy + * + * Called by amdgpu_bo_move() + */ +static bool amdgpu_res_copyable(struct amdgpu_device *adev, + struct ttm_resource *mem) +{ + if (!amdgpu_res_cpu_visible(adev, mem)) + return false; - end = cursor.start + cursor.size; - } + /* ttm_resource_ioremap only supports contiguous memory */ + if (mem->mem_type == TTM_PL_VRAM && + !(mem->placement & TTM_PL_FLAG_CONTIGUOUS)) + return false; - return end <= adev->gmc.visible_vram_size; + return true; } /* @@ -529,8 +544,8 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, if (r) { /* Check that all memory is CPU accessible */ - if (!amdgpu_mem_visible(adev, old_mem) || - !amdgpu_mem_visible(adev, new_mem)) { + if (!amdgpu_res_copyable(adev, old_mem) || + !amdgpu_res_copyable(adev, new_mem)) { pr_err("Move buffer fallback to memcpy unavailable\n"); return r; } @@ -557,7 +572,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); - size_t bus_size = (size_t)mem->size; switch (mem->mem_type) { case TTM_PL_SYSTEM: @@ -568,9 +582,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, break; case TTM_PL_VRAM: mem->bus.offset = mem->start << PAGE_SHIFT; - /* check if it's visible */ - if ((mem->bus.offset + bus_size) > adev->gmc.visible_vram_size) - return -EINVAL; if (adev->mman.aper_base_kaddr && mem->placement & TTM_PL_FLAG_CONTIGUOUS) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 65ec82141a8e0..32cf6b6f6efd9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -139,6 +139,9 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res); + int amdgpu_ttm_init(struct amdgpu_device *adev); void amdgpu_ttm_fini(struct amdgpu_device *adev); void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 4299ce386322e..94089069c9ada 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1613,6 +1613,37 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, trace_amdgpu_vm_bo_map(bo_va, mapping); } +/* Validate operation parameters to prevent potential abuse */ +static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev, + struct amdgpu_bo *bo, + uint64_t saddr, + uint64_t offset, + uint64_t size) +{ + uint64_t tmp, lpfn; + + if (saddr & AMDGPU_GPU_PAGE_MASK + || offset & AMDGPU_GPU_PAGE_MASK + || size & AMDGPU_GPU_PAGE_MASK) + return -EINVAL; + + if (check_add_overflow(saddr, size, &tmp) + || check_add_overflow(offset, size, &tmp) + || size == 0 /* which also leads to end < begin */) + return -EINVAL; + + /* make sure object fit at this offset */ + if (bo && offset + size > amdgpu_bo_size(bo)) + return -EINVAL; + + /* Ensure last pfn not exceed max_pfn */ + lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT; + if (lpfn >= adev->vm_manager.max_pfn) + return -EINVAL; + + return 0; +} + /** * amdgpu_vm_bo_map - map bo inside a vm * @@ -1639,21 +1670,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; uint64_t eaddr; + int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr); if (tmp) { @@ -1706,17 +1730,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, uint64_t eaddr; int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; /* Allocate all the needed memory */ mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); @@ -1730,7 +1746,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, } saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; mapping->start = saddr; mapping->last = eaddr; @@ -1817,10 +1833,14 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *before, *after, *tmp, *next; LIST_HEAD(removed); uint64_t eaddr; + int r; + + r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size); + if (r) + return r; - eaddr = saddr + size - 1; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; /* Allocate all the needed memory */ before = kzalloc(sizeof(*before), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 717a60d7a4ea9..b79986412cd83 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -819,9 +819,9 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) mutex_lock(&kfd_processes_mutex); if (kfd_is_locked()) { - mutex_unlock(&kfd_processes_mutex); pr_debug("KFD is locked! Cannot create process"); - return ERR_PTR(-EINVAL); + process = ERR_PTR(-EINVAL); + goto out; } /* A prior open of /dev/kfd could have already created the process. */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c index e224a028d68ac..8a0460e863097 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c @@ -248,14 +248,12 @@ void dcn32_link_encoder_construct( enc10->base.hpd_source = init_data->hpd_source; enc10->base.connector = init_data->connector; - enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; - - enc10->base.features = *enc_features; if (enc10->base.connector.id == CONNECTOR_ID_USBC) enc10->base.features.flags.bits.DP_IS_USB_C = 1; - if (enc10->base.connector.id == CONNECTOR_ID_USBC) - enc10->base.features.flags.bits.DP_IS_USB_C = 1; + enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; + + enc10->base.features = *enc_features; enc10->base.transmitter = init_data->transmitter; diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c index 81e349d5835bb..da94e5309fbaf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c @@ -184,6 +184,8 @@ void dcn35_link_encoder_construct( enc10->base.hpd_source = init_data->hpd_source; enc10->base.connector = init_data->connector; + if (enc10->base.connector.id == CONNECTOR_ID_USBC) + enc10->base.features.flags.bits.DP_IS_USB_C = 1; enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; @@ -238,8 +240,6 @@ void dcn35_link_encoder_construct( } enc10->base.features.flags.bits.HDMI_6GB_EN = 1; - if (enc10->base.connector.id == CONNECTOR_ID_USBC) - enc10->base.features.flags.bits.DP_IS_USB_C = 1; if (bp_funcs->get_connector_speed_cap_info) result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios, diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 479effcf607e2..79cfab53f80e2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -23,6 +23,7 @@ */ #include "nouveau_drv.h" +#include "nouveau_bios.h" #include "nouveau_reg.h" #include "dispnv04/hw.h" #include "nouveau_encoder.h" @@ -1677,7 +1678,7 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) */ if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) { if (*conn == 0xf2005014 && *conf == 0xffffffff) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B); return false; } } @@ -1763,26 +1764,26 @@ fabricate_dcb_encoder_table(struct drm_device *dev, struct nvbios *bios) #ifdef __powerpc__ /* Apple iMac G4 NV17 */ if (of_machine_is_compatible("PowerMac4,5")) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1); - fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B); + fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C); return; } #endif /* Make up some sane defaults */ fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, - bios->legacy.i2c_indices.crt, 1, 1); + bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B); if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0) fabricate_dcb_output(dcb, DCB_OUTPUT_TV, bios->legacy.i2c_indices.tv, - all_heads, 0); + all_heads, DCB_OUTPUT_A); else if (bios->tmds.output0_script_ptr || bios->tmds.output1_script_ptr) fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, bios->legacy.i2c_indices.panel, - all_heads, 1); + all_heads, DCB_OUTPUT_B); } static int diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 7de7707ec6a89..a72c45809484a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -225,12 +225,18 @@ nouveau_dp_detect(struct nouveau_connector *nv_connector, u8 *dpcd = nv_encoder->dp.dpcd; int ret = NOUVEAU_DP_NONE, hpd; - /* If we've already read the DPCD on an eDP device, we don't need to - * reread it as it won't change + /* eDP ports don't support hotplugging - so there's no point in probing eDP ports unless we + * haven't probed them once before. */ - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && - dpcd[DP_DPCD_REV] != 0) - return NOUVEAU_DP_SST; + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + if (connector->status == connector_status_connected) + return NOUVEAU_DP_SST; + else if (connector->status == connector_status_disconnected) + return NOUVEAU_DP_NONE; + } + + // Ensure that the aux bus is enabled for probing + drm_dp_dpcd_set_powered(&nv_connector->aux, true); mutex_lock(&nv_encoder->dp.hpd_irq_lock); if (mstm) { @@ -293,6 +299,13 @@ out: if (mstm && !mstm->suspended && ret != NOUVEAU_DP_MST) nv50_mstm_remove(mstm); + /* GSP doesn't like when we try to do aux transactions on a port it considers disconnected, + * and since we don't really have a usecase for that anyway - just disable the aux bus here + * if we've decided the connector is disconnected + */ + if (ret == NOUVEAU_DP_NONE) + drm_dp_dpcd_set_powered(&nv_connector->aux, false); + mutex_unlock(&nv_encoder->dp.hpd_irq_lock); return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index a7f3fc342d87e..dd5b5a17ece0b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -222,8 +222,11 @@ nv50_instobj_acquire(struct nvkm_memory *memory) void __iomem *map = NULL; /* Already mapped? */ - if (refcount_inc_not_zero(&iobj->maps)) + if (refcount_inc_not_zero(&iobj->maps)) { + /* read barrier match the wmb on refcount set */ + smp_rmb(); return iobj->map; + } /* Take the lock, and re-check that another thread hasn't * already mapped the object in the meantime. @@ -250,6 +253,8 @@ nv50_instobj_acquire(struct nvkm_memory *memory) iobj->base.memory.ptrs = &nv50_instobj_fast; else iobj->base.memory.ptrs = &nv50_instobj_slow; + /* barrier to ensure the ptrs are written before refcount is set */ + smp_wmb(); refcount_set(&iobj->maps, 1); } diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c index cb7406d744669..c39fe0fc5d69c 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c @@ -614,8 +614,6 @@ static void nt36672e_panel_remove(struct mipi_dsi_device *dsi) struct nt36672e_panel *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); } diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index 775144695283f..b15ca56a09a74 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -253,8 +253,6 @@ static void visionox_rm69299_remove(struct mipi_dsi_device *dsi) struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); } diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index 94947229888ba..b7f22597ee95e 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -424,7 +424,7 @@ typedef struct _ATOM_PPLIB_SUMO_CLOCK_INFO{ typedef struct _ATOM_PPLIB_STATE_V2 { //number of valid dpm levels in this state; Driver uses it to calculate the whole - //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR) + //size of the state: struct_size(ATOM_PPLIB_STATE_V2, clockInfoIndex, ucNumDPMLevels) UCHAR ucNumDPMLevels; //a index to the array of nonClockInfos @@ -432,14 +432,14 @@ typedef struct _ATOM_PPLIB_STATE_V2 /** * Driver will read the first ucNumDPMLevels in this array */ - UCHAR clockInfoIndex[1]; + UCHAR clockInfoIndex[] __counted_by(ucNumDPMLevels); } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ //how many states we have UCHAR ucNumEntries; - ATOM_PPLIB_STATE_V2 states[1]; + ATOM_PPLIB_STATE_V2 states[] __counted_by(ucNumEntries); }StateArray; @@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{ //sizeof(ATOM_PPLIB_CLOCK_INFO) UCHAR ucEntrySize; - UCHAR clockInfo[1]; + UCHAR clockInfo[] __counted_by(ucNumEntries); }ClockInfoArray; typedef struct _NonClockInfoArray{ @@ -460,7 +460,7 @@ typedef struct _NonClockInfoArray{ //sizeof(ATOM_PPLIB_NONCLOCK_INFO) UCHAR ucEntrySize; - ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1]; + ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries); }NonClockInfoArray; typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index bb1f0a3371ab5..10793a433bf58 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -923,8 +923,12 @@ bool radeon_get_atom_connector_info_from_supported_devices_table(struct max_device = ATOM_MAX_SUPPORTED_DEVICE_INFO; for (i = 0; i < max_device; i++) { - ATOM_CONNECTOR_INFO_I2C ci = - supported_devices->info.asConnInfo[i]; + ATOM_CONNECTOR_INFO_I2C ci; + + if (frev > 1) + ci = supported_devices->info_2d1.asConnInfo[i]; + else + ci = supported_devices->info.asConnInfo[i]; bios_connectors[i].valid = false; diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 112438d965ffb..6e1fd6985ffcb 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -288,17 +288,23 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool, enum ttm_caching caching, unsigned int order) { - if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) + if (pool->use_dma_alloc) return &pool->caching[caching].orders[order]; #ifdef CONFIG_X86 switch (caching) { case ttm_write_combined: + if (pool->nid != NUMA_NO_NODE) + return &pool->caching[caching].orders[order]; + if (pool->use_dma32) return &global_dma32_write_combined[order]; return &global_write_combined[order]; case ttm_uncached: + if (pool->nid != NUMA_NO_NODE) + return &pool->caching[caching].orders[order]; + if (pool->use_dma32) return &global_dma32_uncached[order]; @@ -566,11 +572,17 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev, pool->use_dma_alloc = use_dma_alloc; pool->use_dma32 = use_dma32; - if (use_dma_alloc || nid != NUMA_NO_NODE) { - for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < NR_PAGE_ORDERS; ++j) - ttm_pool_type_init(&pool->caching[i].orders[j], - pool, i, j); + for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) { + for (j = 0; j < NR_PAGE_ORDERS; ++j) { + struct ttm_pool_type *pt; + + /* Initialize only pool types which are actually used */ + pt = ttm_pool_select_type(pool, i, j); + if (pt != &pool->caching[i].orders[j]) + continue; + + ttm_pool_type_init(pt, pool, i, j); + } } } EXPORT_SYMBOL(ttm_pool_init); @@ -599,10 +611,16 @@ void ttm_pool_fini(struct ttm_pool *pool) { unsigned int i, j; - if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) { - for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < NR_PAGE_ORDERS; ++j) - ttm_pool_type_fini(&pool->caching[i].orders[j]); + for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) { + for (j = 0; j < NR_PAGE_ORDERS; ++j) { + struct ttm_pool_type *pt; + + pt = ttm_pool_select_type(pool, i, j); + if (pt != &pool->caching[i].orders[j]) + continue; + + ttm_pool_type_fini(pt); + } } /* We removed the pool types from the LRU, but we need to also make sure diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index 2e04f6cb661e4..ce6b2fb341d1f 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -105,7 +105,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->bin_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_BIN]; - file->enabled_ns[V3D_BIN] += local_clock() - file->start_ns[V3D_BIN]; file->jobs_sent[V3D_BIN]++; v3d->queue[V3D_BIN].jobs_sent++; @@ -126,7 +125,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->render_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_RENDER]; - file->enabled_ns[V3D_RENDER] += local_clock() - file->start_ns[V3D_RENDER]; file->jobs_sent[V3D_RENDER]++; v3d->queue[V3D_RENDER].jobs_sent++; @@ -147,7 +145,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->csd_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_CSD]; - file->enabled_ns[V3D_CSD] += local_clock() - file->start_ns[V3D_CSD]; file->jobs_sent[V3D_CSD]++; v3d->queue[V3D_CSD].jobs_sent++; @@ -195,7 +192,6 @@ v3d_hub_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->tfu_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_TFU]; - file->enabled_ns[V3D_TFU] += local_clock() - file->start_ns[V3D_TFU]; file->jobs_sent[V3D_TFU]++; v3d->queue[V3D_TFU].jobs_sent++; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index c52c7bf1485b1..717d624e9a052 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -456,8 +456,10 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, .no_wait_gpu = false }; u32 j, initial_line = dst_offset / dst_stride; - struct vmw_bo_blit_line_data d; + struct vmw_bo_blit_line_data d = {0}; int ret = 0; + struct page **dst_pages = NULL; + struct page **src_pages = NULL; /* Buffer objects need to be either pinned or reserved: */ if (!(dst->pin_count)) @@ -477,12 +479,35 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, return ret; } + if (!src->ttm->pages && src->ttm->sg) { + src_pages = kvmalloc_array(src->ttm->num_pages, + sizeof(struct page *), GFP_KERNEL); + if (!src_pages) + return -ENOMEM; + ret = drm_prime_sg_to_page_array(src->ttm->sg, src_pages, + src->ttm->num_pages); + if (ret) + goto out; + } + if (!dst->ttm->pages && dst->ttm->sg) { + dst_pages = kvmalloc_array(dst->ttm->num_pages, + sizeof(struct page *), GFP_KERNEL); + if (!dst_pages) { + ret = -ENOMEM; + goto out; + } + ret = drm_prime_sg_to_page_array(dst->ttm->sg, dst_pages, + dst->ttm->num_pages); + if (ret) + goto out; + } + d.mapped_dst = 0; d.mapped_src = 0; d.dst_addr = NULL; d.src_addr = NULL; - d.dst_pages = dst->ttm->pages; - d.src_pages = src->ttm->pages; + d.dst_pages = dst->ttm->pages ? dst->ttm->pages : dst_pages; + d.src_pages = src->ttm->pages ? src->ttm->pages : src_pages; d.dst_num_pages = PFN_UP(dst->resource->size); d.src_num_pages = PFN_UP(src->resource->size); d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL); @@ -504,6 +529,10 @@ out: kunmap_atomic(d.src_addr); if (d.dst_addr) kunmap_atomic(d.dst_addr); + if (src_pages) + kvfree(src_pages); + if (dst_pages) + kvfree(dst_pages); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index bfd41ce3c8f4f..e5eb21a471a60 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -377,7 +377,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv, { struct ttm_operation_ctx ctx = { .interruptible = params->bo_type != ttm_bo_type_kernel, - .no_wait_gpu = false + .no_wait_gpu = false, + .resv = params->resv, }; struct ttm_device *bdev = &dev_priv->bdev; struct drm_device *vdev = &dev_priv->drm; @@ -394,8 +395,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv, vmw_bo_placement_set(vmw_bo, params->domain, params->busy_domain); ret = ttm_bo_init_reserved(bdev, &vmw_bo->tbo, params->bo_type, - &vmw_bo->placement, 0, &ctx, NULL, - NULL, destroy); + &vmw_bo->placement, 0, &ctx, + params->sg, params->resv, destroy); if (unlikely(ret)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h index 0d496dc9c6af7..f349642e6190d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h @@ -55,6 +55,8 @@ struct vmw_bo_params { enum ttm_bo_type bo_type; size_t size; bool pin; + struct dma_resv *resv; + struct sg_table *sg; }; /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 0a304706e0132..58fb40c93100a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1628,6 +1628,7 @@ static const struct drm_driver driver = { .prime_fd_to_handle = vmw_prime_fd_to_handle, .prime_handle_to_fd = vmw_prime_handle_to_fd, + .gem_prime_import_sg_table = vmw_prime_import_sg_table, .fops = &vmwgfx_driver_fops, .name = VMWGFX_DRIVER_NAME, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 12efecc17df66..b019a1a1787af 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1130,6 +1130,9 @@ extern int vmw_prime_handle_to_fd(struct drm_device *dev, struct drm_file *file_priv, uint32_t handle, uint32_t flags, int *prime_fd); +struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *table); /* * MemoryOBject management - vmwgfx_mob.c diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index 12787bb9c111d..d6bcaf078b1f4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -149,6 +149,38 @@ out_no_bo: return ret; } +struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *table) +{ + int ret; + struct vmw_private *dev_priv = vmw_priv(dev); + struct drm_gem_object *gem = NULL; + struct vmw_bo *vbo; + struct vmw_bo_params params = { + .domain = (dev_priv->has_mob) ? VMW_BO_DOMAIN_SYS : VMW_BO_DOMAIN_VRAM, + .busy_domain = VMW_BO_DOMAIN_SYS, + .bo_type = ttm_bo_type_sg, + .size = attach->dmabuf->size, + .pin = false, + .resv = attach->dmabuf->resv, + .sg = table, + + }; + + dma_resv_lock(params.resv, NULL); + + ret = vmw_bo_create(dev_priv, ¶ms, &vbo); + if (ret != 0) + goto out_no_bo; + + vbo->tbo.base.funcs = &vmw_gem_object_funcs; + + gem = &vbo->tbo.base; +out_no_bo: + dma_resv_unlock(params.resv); + return gem; +} int vmw_gem_object_create_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index cd4925346ed45..84ae4e10a2ebe 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -933,6 +933,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane, int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { + struct vmw_private *vmw = vmw_priv(crtc->dev); struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc); struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc); @@ -940,9 +941,13 @@ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, bool has_primary = new_state->plane_mask & drm_plane_mask(crtc->primary); - /* We always want to have an active plane with an active CRTC */ - if (has_primary != new_state->enable) - return -EINVAL; + /* + * This is fine in general, but broken userspace might expect + * some actual rendering so give a clue as why it's blank. + */ + if (new_state->enable && !has_primary) + drm_dbg_driver(&vmw->drm, + "CRTC without a primary plane will be blank.\n"); if (new_state->connector_mask != connector_mask && diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index a94947b588e85..19a843da87b78 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -243,10 +243,10 @@ struct vmw_framebuffer_bo { static const uint32_t __maybe_unused vmw_primary_plane_formats[] = { - DRM_FORMAT_XRGB1555, - DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGB565, + DRM_FORMAT_XRGB1555, }; static const uint32_t __maybe_unused vmw_cursor_plane_formats[] = { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c index 2d72a5ee7c0c7..c99cad4449915 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c @@ -75,8 +75,12 @@ int vmw_prime_fd_to_handle(struct drm_device *dev, int fd, u32 *handle) { struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; + int ret = ttm_prime_fd_to_handle(tfile, fd, handle); - return ttm_prime_fd_to_handle(tfile, fd, handle); + if (ret) + ret = drm_gem_prime_fd_to_handle(dev, file_priv, fd, handle); + + return ret; } int vmw_prime_handle_to_fd(struct drm_device *dev, @@ -85,5 +89,12 @@ int vmw_prime_handle_to_fd(struct drm_device *dev, int *prime_fd) { struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; - return ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd); + int ret; + + if (handle > VMWGFX_NUM_MOB) + ret = ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd); + else + ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd); + + return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 4d23d0a70bcb7..621d98b376bbb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -188,13 +188,18 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) switch (dev_priv->map_mode) { case vmw_dma_map_bind: case vmw_dma_map_populate: - vsgt->sgt = &vmw_tt->sgt; - ret = sg_alloc_table_from_pages_segment( - &vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, - (unsigned long)vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL); - if (ret) - goto out_sg_alloc_fail; + if (vmw_tt->dma_ttm.page_flags & TTM_TT_FLAG_EXTERNAL) { + vsgt->sgt = vmw_tt->dma_ttm.sg; + } else { + vsgt->sgt = &vmw_tt->sgt; + ret = sg_alloc_table_from_pages_segment(&vmw_tt->sgt, + vsgt->pages, vsgt->num_pages, 0, + (unsigned long)vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->drm.dev), + GFP_KERNEL); + if (ret) + goto out_sg_alloc_fail; + } ret = vmw_ttm_map_for_dma(vmw_tt); if (unlikely(ret != 0)) @@ -209,8 +214,9 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) return 0; out_map_fail: - sg_free_table(vmw_tt->vsgt.sgt); - vmw_tt->vsgt.sgt = NULL; + drm_warn(&dev_priv->drm, "VSG table map failed!"); + sg_free_table(vsgt->sgt); + vsgt->sgt = NULL; out_sg_alloc_fail: return ret; } @@ -356,15 +362,17 @@ static void vmw_ttm_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) static int vmw_ttm_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx) { - int ret; + bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0; - /* TODO: maybe completely drop this ? */ if (ttm_tt_is_populated(ttm)) return 0; - ret = ttm_pool_alloc(&bdev->pool, ttm, ctx); + if (external && ttm->sg) + return drm_prime_sg_to_dma_addr_array(ttm->sg, + ttm->dma_address, + ttm->num_pages); - return ret; + return ttm_pool_alloc(&bdev->pool, ttm, ctx); } static void vmw_ttm_unpopulate(struct ttm_device *bdev, @@ -372,6 +380,10 @@ static void vmw_ttm_unpopulate(struct ttm_device *bdev, { struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt, dma_ttm); + bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0; + + if (external) + return; vmw_ttm_unbind(bdev, ttm); @@ -390,6 +402,7 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, { struct vmw_ttm_tt *vmw_be; int ret; + bool external = bo->type == ttm_bo_type_sg; vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL); if (!vmw_be) @@ -398,7 +411,10 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, vmw_be->dev_priv = vmw_priv_from_ttm(bo->bdev); vmw_be->mob = NULL; - if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent) + if (external) + page_flags |= TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE; + + if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent || external) ret = ttm_sg_tt_init(&vmw_be->dma_ttm, bo, page_flags, ttm_cached); else diff --git a/drivers/gpu/drm/xe/display/intel_fb_bo.c b/drivers/gpu/drm/xe/display/intel_fb_bo.c index b21da7b745a5e..a9c1f9885c6bb 100644 --- a/drivers/gpu/drm/xe/display/intel_fb_bo.c +++ b/drivers/gpu/drm/xe/display/intel_fb_bo.c @@ -31,7 +31,7 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, ret = ttm_bo_reserve(&bo->ttm, true, false, NULL); if (ret) - return ret; + goto err; if (!(bo->flags & XE_BO_SCANOUT_BIT)) { /* @@ -42,12 +42,16 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, */ if (XE_IOCTL_DBG(i915, !list_empty(&bo->ttm.base.gpuva.list))) { ttm_bo_unreserve(&bo->ttm); - return -EINVAL; + ret = -EINVAL; + goto err; } bo->flags |= XE_BO_SCANOUT_BIT; } ttm_bo_unreserve(&bo->ttm); + return 0; +err: + xe_bo_put(bo); return ret; } diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 62d1ef8867a84..3d4c8f342e215 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1577,6 +1577,16 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe->usm.num_vm_in_fault_mode--; else if (!(vm->flags & XE_VM_FLAG_MIGRATION)) xe->usm.num_vm_in_non_fault_mode--; + + if (vm->usm.asid) { + void *lookup; + + xe_assert(xe, xe->info.has_asid); + xe_assert(xe, !(vm->flags & XE_VM_FLAG_MIGRATION)); + + lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid); + xe_assert(xe, lookup == vm); + } mutex_unlock(&xe->usm.lock); for_each_tile(tile, xe, id) @@ -1592,24 +1602,15 @@ static void vm_destroy_work_func(struct work_struct *w) struct xe_device *xe = vm->xe; struct xe_tile *tile; u8 id; - void *lookup; /* xe_vm_close_and_put was not called? */ xe_assert(xe, !vm->size); mutex_destroy(&vm->snap_mutex); - if (!(vm->flags & XE_VM_FLAG_MIGRATION)) { + if (!(vm->flags & XE_VM_FLAG_MIGRATION)) xe_device_mem_access_put(xe); - if (xe->info.has_asid && vm->usm.asid) { - mutex_lock(&xe->usm.lock); - lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid); - xe_assert(xe, lookup == vm); - mutex_unlock(&xe->usm.lock); - } - } - for_each_tile(tile, xe, id) XE_WARN_ON(vm->pt_root[id]); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index bf0df6ee4f785..07fb8d3c037f0 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1026,23 +1026,26 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv) } } -static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id) +static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id, + enum ib_cm_state old_state) { struct cm_id_private *cm_id_priv; cm_id_priv = container_of(cm_id, struct cm_id_private, id); - pr_err("%s: cm_id=%p timed out. state=%d refcnt=%d\n", __func__, - cm_id, cm_id->state, refcount_read(&cm_id_priv->refcount)); + pr_err("%s: cm_id=%p timed out. state %d -> %d, refcnt=%d\n", __func__, + cm_id, old_state, cm_id->state, refcount_read(&cm_id_priv->refcount)); } static void cm_destroy_id(struct ib_cm_id *cm_id, int err) { struct cm_id_private *cm_id_priv; + enum ib_cm_state old_state; struct cm_work *work; int ret; cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irq(&cm_id_priv->lock); + old_state = cm_id->state; retest: switch (cm_id->state) { case IB_CM_LISTEN: @@ -1151,7 +1154,7 @@ retest: msecs_to_jiffies( CM_DESTROY_ID_WAIT_TIMEOUT)); if (!ret) /* timeout happened */ - cm_destroy_id_wait_timeout(cm_id); + cm_destroy_id_wait_timeout(cm_id, old_state); } while (!ret); while ((work = cm_dequeue_work(cm_id_priv)) != NULL) diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 0c3c4e64812c5..3e43687a7f6f7 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -188,7 +188,8 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num, mdev = dev->mdev; mdev_port_num = 1; } - if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) { + if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1 && + !mlx5_core_mp_enabled(mdev)) { /* set local port to one for Function-Per-Port HCA. */ mdev = dev->mdev; mdev_port_num = 1; diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index ae466e72fc43b..255677bc12b2a 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -33,6 +33,8 @@ void rxe_dealloc(struct ib_device *ib_dev) if (rxe->tfm) crypto_free_shash(rxe->tfm); + + mutex_destroy(&rxe->usdev_lock); } /* initialize rxe device parameters */ diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig index 99d4b075df49e..76656fe0470d7 100644 --- a/drivers/iommu/iommufd/Kconfig +++ b/drivers/iommu/iommufd/Kconfig @@ -37,6 +37,7 @@ config IOMMUFD_TEST depends on DEBUG_KERNEL depends on FAULT_INJECTION depends on RUNTIME_TESTING_MENU + select IOMMUFD_DRIVER default n help This is dangerous, do not enable unless running diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index c0d0bce0b5942..8090390edaf9d 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1883,14 +1883,16 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port, static int mt753x_mirror_port_get(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_GET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_GET(val) : + MIRROR_PORT(val); } static int mt753x_mirror_port_set(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_SET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_SET(val) : + MIRROR_PORT(val); } static int mt753x_port_mirror_add(struct dsa_switch *ds, int port, @@ -2480,6 +2482,9 @@ mt7530_setup(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Setup VLAN ID 0 for VLAN-unaware bridges */ ret = mt7530_setup_vlan0(priv); if (ret) @@ -2591,6 +2596,9 @@ mt7531_setup_common(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Flush the FDB table */ ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); if (ret < 0) diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 585db03c05487..a08053390b285 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -32,6 +32,10 @@ enum mt753x_id { #define SYSC_REG_RSTCTRL 0x34 #define RESET_MCM BIT(2) +/* Register for ARL global control */ +#define MT753X_AGC 0xc +#define LOCAL_EN BIT(7) + /* Registers to mac forward control for unknown frames */ #define MT7530_MFC 0x10 #define BC_FFP(x) (((x) & 0xff) << 24) diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index b890410a2bc0b..688ccb0615ab9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -28,6 +28,8 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) * - Tunnel flag (present if tunnel) */ + if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) + lkups_cnt++; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -363,6 +365,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, /* Always add direction metadata */ ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + ice_rule_add_src_vsi_metadata(&list[i]); + i++; + } + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); @@ -772,7 +779,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) int ret; int i; - if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) { + if (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); return -EOPNOTSUPP; } @@ -820,6 +827,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) /* specify the cookie as filter_rule_id */ rule_info.fltr_rule_id = fltr->cookie; + rule_info.src_vsi = vsi->idx; ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); if (ret == -EEXIST) { @@ -1481,7 +1489,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 87bdb93cb066e..f4655a8c0705d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -689,6 +689,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control match; + u32 val; flow_rule_match_control(rule, &match); if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { @@ -697,12 +698,14 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, } if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + val = match.key->flags & FLOW_DIS_IS_FRAGMENT; if (ntohs(flow_spec->etype) == ETH_P_IP) { - flow_spec->ip_flag = IPV4_FLAG_MORE; + flow_spec->ip_flag = val ? IPV4_FLAG_MORE : 0; flow_mask->ip_flag = IPV4_FLAG_MORE; req->features |= BIT_ULL(NPC_IPFRAG_IPV4); } else if (ntohs(flow_spec->etype) == ETH_P_IPV6) { - flow_spec->next_header = IPPROTO_FRAGMENT; + flow_spec->next_header = val ? + IPPROTO_FRAGMENT : 0; flow_mask->next_header = 0xff; req->features |= BIT_ULL(NPC_IPFRAG_IPV6); } else { diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index c895e265ae0eb..61334a71058c7 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1074,13 +1074,13 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) static void mtk_wed_stop(struct mtk_wed_device *dev) { + mtk_wed_dma_disable(dev); mtk_wed_set_ext_int(dev, false); wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0); wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0); wdma_w32(dev, MTK_WDMA_INT_MASK, 0); wdma_w32(dev, MTK_WDMA_INT_GRP2, 0); - wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0); if (!mtk_wed_get_rx_capa(dev)) return; @@ -1093,7 +1093,6 @@ static void mtk_wed_deinit(struct mtk_wed_device *dev) { mtk_wed_stop(dev); - mtk_wed_dma_disable(dev); wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WDMA_INT_AGENT_EN | @@ -2605,9 +2604,6 @@ mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask) static void mtk_wed_irq_set_mask(struct mtk_wed_device *dev, u32 mask) { - if (!dev->running) - return; - mtk_wed_set_ext_int(dev, !!mask); wed_w32(dev, MTK_WED_INT_MASK, mask); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 0ab9db3195302..22918b2ef7f12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -108,7 +108,10 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) mlx5e_reset_txqsq_cc_pc(sq); sq->stats->recover++; clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); + rtnl_lock(); mlx5e_activate_txqsq(sq); + rtnl_unlock(); + if (sq->channel) mlx5e_trigger_napi_icosq(sq->channel); else @@ -179,12 +182,16 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx) carrier_ok = netif_carrier_ok(netdev); netif_carrier_off(netdev); + rtnl_lock(); mlx5e_deactivate_priv_channels(priv); + rtnl_unlock(); mlx5e_ptp_close(chs->ptp); err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp); + rtnl_lock(); mlx5e_activate_priv_channels(priv); + rtnl_unlock(); /* return carrier back if needed */ if (carrier_ok) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index c7f542d0b8f08..93cf23278d93c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -46,6 +46,10 @@ struct arfs_table { struct hlist_head rules_hash[ARFS_HASH_SIZE]; }; +enum { + MLX5E_ARFS_STATE_ENABLED, +}; + enum arfs_type { ARFS_IPV4_TCP, ARFS_IPV6_TCP, @@ -60,6 +64,7 @@ struct mlx5e_arfs_tables { spinlock_t arfs_lock; int last_filter_id; struct workqueue_struct *wq; + unsigned long state; }; struct arfs_tuple { @@ -170,6 +175,8 @@ int mlx5e_arfs_enable(struct mlx5e_flow_steering *fs) return err; } } + set_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + return 0; } @@ -455,6 +462,8 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs) int i; int j; + clear_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + spin_lock_bh(&arfs->arfs_lock); mlx5e_for_each_arfs_rule(rule, htmp, arfs->arfs_tables, i, j) { hlist_del_init(&rule->hlist); @@ -627,17 +636,8 @@ static void arfs_handle_work(struct work_struct *work) struct mlx5_flow_handle *rule; arfs = mlx5e_fs_get_arfs(priv->fs); - mutex_lock(&priv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - spin_lock_bh(&arfs->arfs_lock); - hlist_del(&arfs_rule->hlist); - spin_unlock_bh(&arfs->arfs_lock); - - mutex_unlock(&priv->state_lock); - kfree(arfs_rule); - goto out; - } - mutex_unlock(&priv->state_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) + return; if (!arfs_rule->rule) { rule = arfs_add_rule(priv, arfs_rule); @@ -753,6 +753,11 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, return -EPROTONOSUPPORT; spin_lock_bh(&arfs->arfs_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) { + spin_unlock_bh(&arfs->arfs_lock); + return -EPERM; + } + arfs_rule = arfs_find_rule(arfs_t, &fk); if (arfs_rule) { if (arfs_rule->rxq == rxq_index || work_busy(&arfs_rule->arfs_work)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8f101181648c6..67a29826bb570 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -589,12 +589,12 @@ static int mlx5e_get_coalesce(struct net_device *netdev, static void mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { - struct mlx5_core_dev *mdev = priv->mdev; int tc; int i; for (i = 0; i < priv->channels.num; ++i) { struct mlx5e_channel *c = priv->channels.c[i]; + struct mlx5_core_dev *mdev = c->mdev; for (tc = 0; tc < c->num_tc; tc++) { mlx5_core_modify_cq_moderation(mdev, @@ -608,11 +608,11 @@ mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coal static void mlx5e_set_priv_channels_rx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { - struct mlx5_core_dev *mdev = priv->mdev; int i; for (i = 0; i < priv->channels.num; ++i) { struct mlx5e_channel *c = priv->channels.c[i]; + struct mlx5_core_dev *mdev = c->mdev; mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq, coal->rx_coalesce_usecs, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b375ef268671a..319930c04093b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -209,8 +209,8 @@ static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data) *data, mlx5e_devcom_event_mpv, priv); - if (IS_ERR_OR_NULL(priv->devcom)) - return -EOPNOTSUPP; + if (IS_ERR(priv->devcom)) + return PTR_ERR(priv->devcom); if (mlx5_core_is_mp_master(priv->mdev)) { mlx5_devcom_send_event(priv->devcom, MPV_DEVCOM_MASTER_UP, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1f60954c12f72..844d3e3a65ddf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3060,7 +3060,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key) key, mlx5_esw_offloads_devcom_event, esw); - if (IS_ERR_OR_NULL(esw->devcom)) + if (IS_ERR(esw->devcom)) return; mlx5_devcom_send_event(esw->devcom, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index d14459e5c04fc..69d482f7c5a29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -703,8 +703,10 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev) return err; } - if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) + if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) { mlx5_lag_port_sel_destroy(ldev); + ldev->buckets = 1; + } if (mlx5_lag_has_drop_rule(ldev)) mlx5_lag_drop_rule_cleanup(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index e7d59cfa8708e..7b0766c89f4cf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -220,7 +220,7 @@ mlx5_devcom_register_component(struct mlx5_devcom_dev *devc, struct mlx5_devcom_comp *comp; if (IS_ERR_OR_NULL(devc)) - return NULL; + return ERR_PTR(-EINVAL); mutex_lock(&comp_list_lock); comp = devcom_component_get(devc, id, key, handler); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index 5b28084e8a03c..dd5d186dc6148 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -213,8 +213,8 @@ static int sd_register(struct mlx5_core_dev *dev) sd = mlx5_get_sd(dev); devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, sd->group_id, NULL, dev); - if (!devcom) - return -ENOMEM; + if (IS_ERR(devcom)) + return PTR_ERR(devcom); sd->devcom = devcom; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 59806553889e9..331ce47f51a17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -956,7 +956,7 @@ static void mlx5_register_hca_devcom_comp(struct mlx5_core_dev *dev) mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS, mlx5_query_nic_system_image_guid(dev), NULL, dev); - if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp)) + if (IS_ERR(dev->priv.hca_devcom_comp)) mlx5_core_err(dev, "Failed to register devcom HCA component\n"); } @@ -1699,12 +1699,15 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev) err = mlx5_devlink_params_register(priv_to_devlink(dev)); if (err) { mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err); - goto query_hca_caps_err; + goto params_reg_err; } devl_unlock(devlink); return 0; +params_reg_err: + devl_unregister(devlink); + devl_unlock(devlink); query_hca_caps_err: devl_unregister(devlink); devl_unlock(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index e3bf8c7e4baa6..7ebe712808275 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -75,7 +75,6 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto peer_devlink_set_err; } - devlink_register(devlink); return 0; peer_devlink_set_err: diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 523e0c470894f..55f255a3c9db6 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -36,6 +36,27 @@ struct sparx5_tc_flower_template { u16 l3_proto; /* protocol specified in the template */ }; +/* SparX-5 VCAP fragment types: + * 0 = no fragment, 1 = initial fragment, + * 2 = suspicious fragment, 3 = valid follow-up fragment + */ +enum { /* key / mask */ + FRAG_NOT = 0x03, /* 0 / 3 */ + FRAG_SOME = 0x11, /* 1 / 1 */ + FRAG_FIRST = 0x13, /* 1 / 3 */ + FRAG_LATER = 0x33, /* 3 / 3 */ + FRAG_INVAL = 0xff, /* invalid */ +}; + +/* Flower fragment flag to VCAP fragment type mapping */ +static const u8 sparx5_vcap_frag_map[4][4] = { /* is_frag */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_FIRST }, /* 0/0 */ + { FRAG_NOT, FRAG_NOT, FRAG_INVAL, FRAG_INVAL }, /* 0/1 */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_INVAL }, /* 1/0 */ + { FRAG_SOME, FRAG_LATER, FRAG_INVAL, FRAG_FIRST } /* 1/1 */ + /* 0/0 0/1 1/0 1/1 <-- first_frag */ +}; + static int sparx5_tc_flower_es0_tpid(struct vcap_tc_flower_parse_usage *st) { @@ -145,29 +166,27 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) flow_rule_match_control(st->frule, &mt); if (mt.mask->flags) { - if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { - if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { - value = 1; /* initial fragment */ - mask = 0x3; - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } + u8 is_frag_key = !!(mt.key->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_mask = !!(mt.mask->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_idx = (is_frag_key << 1) | is_frag_mask; + + u8 first_frag_key = !!(mt.key->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_mask = !!(mt.mask->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_idx = (first_frag_key << 1) | first_frag_mask; + + /* Lookup verdict based on the 2 + 2 input bits */ + u8 vdt = sparx5_vcap_frag_map[is_frag_idx][first_frag_idx]; + + if (vdt == FRAG_INVAL) { + NL_SET_ERR_MSG_MOD(st->fco->common.extack, + "Match on invalid fragment flag combination"); + return -EINVAL; } + /* Extract VCAP fragment key and mask from verdict */ + value = (vdt >> 4) & 0x3; + mask = vdt & 0x3; + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_FRAGMENT_TYPE, value, mask); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ba01c8cc3c906..fcb756d77681c 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -769,25 +769,28 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) dma_addr_t dma_addr; int rx_packets = 0; u8 desc_status; - u16 pkt_len; + u16 desc_len; u8 die_dt; int entry; int limit; int i; - entry = priv->cur_rx[q] % priv->num_rx_ring[q]; limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; stats = &priv->stats[q]; - desc = &priv->rx_ring[q].desc[entry]; - for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) { + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; + /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; - pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; + desc_len = le16_to_cpu(desc->ds_cc) & RX_DS; /* We use 0-byte descriptors to mark the DMA mapping errors */ - if (!pkt_len) + if (!desc_len) continue; if (desc_status & MSC_MC) @@ -808,25 +811,25 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) switch (die_dt) { case DT_FSINGLE: skb = ravb_get_skb_gbeth(ndev, entry, desc); - skb_put(skb, pkt_len); + skb_put(skb, desc_len); skb->protocol = eth_type_trans(skb, ndev); if (ndev->features & NETIF_F_RXCSUM) ravb_rx_csum_gbeth(skb); napi_gro_receive(&priv->napi[q], skb); rx_packets++; - stats->rx_bytes += pkt_len; + stats->rx_bytes += desc_len; break; case DT_FSTART: priv->rx_1st_skb = ravb_get_skb_gbeth(ndev, entry, desc); - skb_put(priv->rx_1st_skb, pkt_len); + skb_put(priv->rx_1st_skb, desc_len); break; case DT_FMID: skb = ravb_get_skb_gbeth(ndev, entry, desc); skb_copy_to_linear_data_offset(priv->rx_1st_skb, priv->rx_1st_skb->len, skb->data, - pkt_len); - skb_put(priv->rx_1st_skb, pkt_len); + desc_len); + skb_put(priv->rx_1st_skb, desc_len); dev_kfree_skb(skb); break; case DT_FEND: @@ -834,23 +837,20 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) skb_copy_to_linear_data_offset(priv->rx_1st_skb, priv->rx_1st_skb->len, skb->data, - pkt_len); - skb_put(priv->rx_1st_skb, pkt_len); + desc_len); + skb_put(priv->rx_1st_skb, desc_len); dev_kfree_skb(skb); priv->rx_1st_skb->protocol = eth_type_trans(priv->rx_1st_skb, ndev); if (ndev->features & NETIF_F_RXCSUM) - ravb_rx_csum_gbeth(skb); + ravb_rx_csum_gbeth(priv->rx_1st_skb); + stats->rx_bytes += priv->rx_1st_skb->len; napi_gro_receive(&priv->napi[q], priv->rx_1st_skb); rx_packets++; - stats->rx_bytes += pkt_len; break; } } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q].desc[entry]; } /* Refill the RX ring buffers. */ @@ -891,30 +891,29 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - int entry = priv->cur_rx[q] % priv->num_rx_ring[q]; - int boguscnt = (priv->dirty_rx[q] + priv->num_rx_ring[q]) - - priv->cur_rx[q]; struct net_device_stats *stats = &priv->stats[q]; struct ravb_ex_rx_desc *desc; + unsigned int limit, i; struct sk_buff *skb; dma_addr_t dma_addr; struct timespec64 ts; + int rx_packets = 0; u8 desc_status; u16 pkt_len; - int limit; + int entry; + + limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].ex_desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; - boguscnt = min(boguscnt, *quota); - limit = boguscnt; - desc = &priv->rx_ring[q].ex_desc[entry]; - while (desc->die_dt != DT_FEMPTY) { /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; - if (--boguscnt < 0) - break; - /* We use 0-byte descriptors to mark the DMA mapping errors */ if (!pkt_len) continue; @@ -960,12 +959,9 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) if (ndev->features & NETIF_F_RXCSUM) ravb_rx_csum(skb); napi_gro_receive(&priv->napi[q], skb); - stats->rx_packets++; + rx_packets++; stats->rx_bytes += pkt_len; } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q].ex_desc[entry]; } /* Refill the RX ring buffers. */ @@ -995,9 +991,9 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) desc->die_dt = DT_FEMPTY; } - *quota -= limit - (++boguscnt); - - return boguscnt <= 0; + stats->rx_packets += rx_packets; + *quota -= rx_packets; + return *quota == 0; } /* Packet receive function for Ethernet AVB */ diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index a6fefe675ef15..3b7d4ac1e7be0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -553,6 +553,7 @@ extern const struct stmmac_hwtimestamp stmmac_ptp; extern const struct stmmac_mode_ops dwmac4_ring_mode_ops; struct mac_link { + u32 caps; u32 speed_mask; u32 speed10; u32 speed100; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index b21d99faa2d04..e1b761dcfa1dd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1096,6 +1096,8 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv) priv->dev->priv_flags |= IFF_UNICAST_FLT; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; /* The loopback bit seems to be re-set when link change * Simply mask it each time * Speed 10/100/1000 are set in BIT(2)/BIT(3) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 3927609abc441..8555299443f4e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -539,6 +539,8 @@ int dwmac1000_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; mac->link.duplex = GMAC_CONTROL_DM; mac->link.speed10 = GMAC_CONTROL_PS; mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index a6e8d7bd95886..7667d103cd0eb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -175,6 +175,8 @@ int dwmac100_setup(struct stmmac_priv *priv) dev_info(priv->device, "\tDWMAC100\n"); mac->pcsr = priv->ioaddr; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; mac->link.duplex = MAC_CONTROL_F; mac->link.speed10 = 0; mac->link.speed100 = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index cef25efbdff99..a38226d7cc6a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -70,7 +70,10 @@ static void dwmac4_core_init(struct mac_device_info *hw, static void dwmac4_phylink_get_caps(struct stmmac_priv *priv) { - priv->phylink_config.mac_capabilities |= MAC_2500FD; + if (priv->plat->tx_queues_to_use > 1) + priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD | MAC_1000HD); + else + priv->hw->link.caps |= (MAC_10HD | MAC_100HD | MAC_1000HD); } static void dwmac4_rx_queue_enable(struct mac_device_info *hw, @@ -1378,6 +1381,8 @@ int dwmac4_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; mac->link.duplex = GMAC_CONFIG_DM; mac->link.speed10 = GMAC_CONFIG_PS; mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index e841e312077ef..f8e7775bb6336 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -47,14 +47,6 @@ static void dwxgmac2_core_init(struct mac_device_info *hw, writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN); } -static void xgmac_phylink_get_caps(struct stmmac_priv *priv) -{ - priv->phylink_config.mac_capabilities |= MAC_2500FD | MAC_5000FD | - MAC_10000FD | MAC_25000FD | - MAC_40000FD | MAC_50000FD | - MAC_100000FD; -} - static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable) { u32 tx = readl(ioaddr + XGMAC_TX_CONFIG); @@ -1540,7 +1532,6 @@ static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg * const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxgmac2_rx_queue_enable, @@ -1601,7 +1592,6 @@ static void dwxlgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode, const struct stmmac_ops dwxlgmac2_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxlgmac2_rx_queue_enable, @@ -1661,6 +1651,9 @@ int dwxgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD; mac->link.duplex = 0; mac->link.speed10 = XGMAC_CONFIG_SS_10_MII; mac->link.speed100 = XGMAC_CONFIG_SS_100_MII; @@ -1698,6 +1691,11 @@ int dwxlgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD | MAC_25000FD | + MAC_40000FD | MAC_50000FD | + MAC_100000FD; mac->link.duplex = 0; mac->link.speed1000 = XLGMAC_CONFIG_SS_1000; mac->link.speed2500 = XLGMAC_CONFIG_SS_2500; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 24cd80490d19c..7c6fb14b55550 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1198,17 +1198,6 @@ static int stmmac_init_phy(struct net_device *dev) return ret; } -static void stmmac_set_half_duplex(struct stmmac_priv *priv) -{ - /* Half-Duplex can only work with single tx queue */ - if (priv->plat->tx_queues_to_use > 1) - priv->phylink_config.mac_capabilities &= - ~(MAC_10HD | MAC_100HD | MAC_1000HD); - else - priv->phylink_config.mac_capabilities |= - (MAC_10HD | MAC_100HD | MAC_1000HD); -} - static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data; @@ -1236,15 +1225,11 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) xpcs_get_interfaces(priv->hw->xpcs, priv->phylink_config.supported_interfaces); - priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | - MAC_10FD | MAC_100FD | - MAC_1000FD; - - stmmac_set_half_duplex(priv); - /* Get the MAC specific capabilities */ stmmac_mac_phylink_get_caps(priv); + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + max_speed = priv->plat->max_speed; if (max_speed) phylink_limit_mac_speed(&priv->phylink_config, max_speed); @@ -7342,6 +7327,7 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) { struct stmmac_priv *priv = netdev_priv(dev); int ret = 0, i; + int max_speed; if (netif_running(dev)) stmmac_release(dev); @@ -7355,7 +7341,14 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) priv->rss.table[i] = ethtool_rxfh_indir_default(i, rx_cnt); - stmmac_set_half_duplex(priv); + stmmac_mac_phylink_get_caps(priv); + + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + + max_speed = priv->plat->max_speed; + if (max_speed) + phylink_limit_mac_speed(&priv->phylink_config, max_speed); + stmmac_napi_add(dev); if (netif_running(dev)) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2939a21ca74f3..1d00e21808c1c 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2793,6 +2793,8 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { + struct am65_cpsw_rx_chn *rx_chan = &common->rx_chns; + struct am65_cpsw_tx_chn *tx_chan = common->tx_chns; struct device *dev = common->dev; struct am65_cpsw_port *port; int ret = 0, i; @@ -2805,6 +2807,22 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) if (ret) return ret; + /* The DMA Channels are not guaranteed to be in a clean state. + * Reset and disable them to ensure that they are back to the + * clean state and ready to be used. + */ + for (i = 0; i < common->tx_ch_num; i++) { + k3_udma_glue_reset_tx_chn(tx_chan[i].tx_chn, &tx_chan[i], + am65_cpsw_nuss_tx_cleanup); + k3_udma_glue_disable_tx_chn(tx_chan[i].tx_chn); + } + + for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) + k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, rx_chan, + am65_cpsw_nuss_rx_cleanup, !!i); + + k3_udma_glue_disable_rx_chn(rx_chan->rx_chn); + ret = am65_cpsw_nuss_register_devlink(common); if (ret) return ret; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 0b3f21cba552f..92da8c03d960c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2125,14 +2125,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); - pr_err("unexpected GSO type: " - "0x%x, gso_size %d, hdr_len %d\n", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index a9c418890a1ca..752f821a19901 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1317,6 +1317,8 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) netif_set_tso_max_size(dev->net, 16384); + ax88179_reset(dev); + return 0; } @@ -1695,7 +1697,6 @@ static const struct driver_info ax88179_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1708,7 +1709,6 @@ static const struct driver_info ax88178a_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index e2e181378f412..edc34402e787f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1431,6 +1431,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ {QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ + {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index b456370166b6b..b4f49720c87f6 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -208,6 +208,15 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BIOS_VERSION, "03.03"), } }, + { + .ident = "Framework Laptop 13 (Phoenix)", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Framework"), + DMI_MATCH(DMI_PRODUCT_NAME, "Laptop 13 (AMD Ryzen 7040Series)"), + DMI_MATCH(DMI_BIOS_VERSION, "03.05"), + } + }, {} }; diff --git a/drivers/platform/x86/amd/pmf/Makefile b/drivers/platform/x86/amd/pmf/Makefile index 6b26e48ce8ad2..7d6079b02589c 100644 --- a/drivers/platform/x86/amd/pmf/Makefile +++ b/drivers/platform/x86/amd/pmf/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_AMD_PMF) += amd-pmf.o amd-pmf-objs := core.o acpi.o sps.o \ auto-mode.o cnqf.o \ - tee-if.o spc.o + tee-if.o spc.o pmf-quirks.o diff --git a/drivers/platform/x86/amd/pmf/acpi.c b/drivers/platform/x86/amd/pmf/acpi.c index d0cf46e2fc8e8..1157ec148880b 100644 --- a/drivers/platform/x86/amd/pmf/acpi.c +++ b/drivers/platform/x86/amd/pmf/acpi.c @@ -343,7 +343,10 @@ static int apmf_if_verify_interface(struct amd_pmf_dev *pdev) if (err) return err; - pdev->supported_func = output.supported_functions; + /* only set if not already set by a quirk */ + if (!pdev->supported_func) + pdev->supported_func = output.supported_functions; + dev_dbg(pdev->dev, "supported functions:0x%x notifications:0x%x version:%u\n", output.supported_functions, output.notification_mask, output.version); @@ -437,7 +440,7 @@ int apmf_check_smart_pc(struct amd_pmf_dev *pmf_dev) status = acpi_walk_resources(ahandle, METHOD_NAME__CRS, apmf_walk_resources, pmf_dev); if (ACPI_FAILURE(status)) { - dev_err(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status); + dev_dbg(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status); return -EINVAL; } diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index 5d4f80698a8b8..64e6e34a2a9ac 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -445,6 +445,7 @@ static int amd_pmf_probe(struct platform_device *pdev) mutex_init(&dev->lock); mutex_init(&dev->update_mutex); + amd_pmf_quirks_init(dev); apmf_acpi_init(dev); platform_set_drvdata(pdev, dev); amd_pmf_dbgfs_register(dev); diff --git a/drivers/platform/x86/amd/pmf/pmf-quirks.c b/drivers/platform/x86/amd/pmf/pmf-quirks.c new file mode 100644 index 0000000000000..0b2eb0ae85feb --- /dev/null +++ b/drivers/platform/x86/amd/pmf/pmf-quirks.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Platform Management Framework Driver Quirks + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Mario Limonciello <mario.limonciello@amd.com> + */ + +#include <linux/dmi.h> + +#include "pmf.h" + +struct quirk_entry { + u32 supported_func; +}; + +static struct quirk_entry quirk_no_sps_bug = { + .supported_func = 0x4003, +}; + +static const struct dmi_system_id fwbug_list[] = { + { + .ident = "ROG Zephyrus G14", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA403UV"), + }, + .driver_data = &quirk_no_sps_bug, + }, + {} +}; + +void amd_pmf_quirks_init(struct amd_pmf_dev *dev) +{ + const struct dmi_system_id *dmi_id; + struct quirk_entry *quirks; + + dmi_id = dmi_first_match(fwbug_list); + if (!dmi_id) + return; + + quirks = dmi_id->driver_data; + if (quirks->supported_func) { + dev->supported_func = quirks->supported_func; + pr_info("Using supported funcs quirk to avoid %s platform firmware bug\n", + dmi_id->ident); + } +} + diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index 8c4df5753f40d..eeedd0c0395a8 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -720,4 +720,7 @@ int apmf_check_smart_pc(struct amd_pmf_dev *pmf_dev); void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in); void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in); +/* Quirk infrastructure */ +void amd_pmf_quirks_init(struct amd_pmf_dev *dev); + #endif /* PMF_H */ diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 08df9494603c5..30951f7131cd9 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -719,6 +719,7 @@ static struct miscdevice isst_if_char_driver = { }; static const struct x86_cpu_id hpm_cpu_ids[] = { + X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, NULL), X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, NULL), X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, NULL), {} diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c index bd75d61ff8a66..ef730200a04bd 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c @@ -29,7 +29,7 @@ #include "uncore-frequency-common.h" #define UNCORE_MAJOR_VERSION 0 -#define UNCORE_MINOR_VERSION 1 +#define UNCORE_MINOR_VERSION 2 #define UNCORE_HEADER_INDEX 0 #define UNCORE_FABRIC_CLUSTER_OFFSET 8 @@ -329,7 +329,7 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_ goto remove_clusters; } - if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) != UNCORE_MINOR_VERSION) + if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) > UNCORE_MINOR_VERSION) dev_info(&auxdev->dev, "Uncore: Ignore: Unsupported minor version:%lx\n", TPMI_MINOR_VERSION(pd_info->ufs_header_ver)); diff --git a/drivers/pwm/pwm-dwc-core.c b/drivers/pwm/pwm-dwc-core.c index 043736972cb92..c8425493b95d8 100644 --- a/drivers/pwm/pwm-dwc-core.c +++ b/drivers/pwm/pwm-dwc-core.c @@ -172,7 +172,6 @@ struct pwm_chip *dwc_pwm_alloc(struct device *dev) dwc->clk_ns = 10; chip->ops = &dwc_pwm_ops; - dev_set_drvdata(dev, chip); return chip; } EXPORT_SYMBOL_GPL(dwc_pwm_alloc); diff --git a/drivers/pwm/pwm-dwc.c b/drivers/pwm/pwm-dwc.c index 676eaf8d7a53f..fb3eadf6fbc46 100644 --- a/drivers/pwm/pwm-dwc.c +++ b/drivers/pwm/pwm-dwc.c @@ -31,26 +31,34 @@ static const struct dwc_pwm_info ehl_pwm_info = { .size = 0x1000, }; -static int dwc_pwm_init_one(struct device *dev, void __iomem *base, unsigned int offset) +static int dwc_pwm_init_one(struct device *dev, struct dwc_pwm_drvdata *ddata, unsigned int idx) { struct pwm_chip *chip; struct dwc_pwm *dwc; + int ret; chip = dwc_pwm_alloc(dev); if (IS_ERR(chip)) return PTR_ERR(chip); dwc = to_dwc_pwm(chip); - dwc->base = base + offset; + dwc->base = ddata->io_base + (ddata->info->size * idx); - return devm_pwmchip_add(dev, chip); + ret = devm_pwmchip_add(dev, chip); + if (ret) + return ret; + + ddata->chips[idx] = chip; + return 0; } static int dwc_pwm_probe(struct pci_dev *pci, const struct pci_device_id *id) { const struct dwc_pwm_info *info; struct device *dev = &pci->dev; - int i, ret; + struct dwc_pwm_drvdata *ddata; + unsigned int idx; + int ret; ret = pcim_enable_device(pci); if (ret) @@ -63,17 +71,25 @@ static int dwc_pwm_probe(struct pci_dev *pci, const struct pci_device_id *id) return dev_err_probe(dev, ret, "Failed to iomap PCI BAR\n"); info = (const struct dwc_pwm_info *)id->driver_data; - - for (i = 0; i < info->nr; i++) { - /* - * No need to check for pcim_iomap_table() failure, - * pcim_iomap_regions() already does it for us. - */ - ret = dwc_pwm_init_one(dev, pcim_iomap_table(pci)[0], i * info->size); + ddata = devm_kzalloc(dev, struct_size(ddata, chips, info->nr), GFP_KERNEL); + if (!ddata) + return -ENOMEM; + + /* + * No need to check for pcim_iomap_table() failure, + * pcim_iomap_regions() already does it for us. + */ + ddata->io_base = pcim_iomap_table(pci)[0]; + ddata->info = info; + + for (idx = 0; idx < ddata->info->nr; idx++) { + ret = dwc_pwm_init_one(dev, ddata, idx); if (ret) return ret; } + dev_set_drvdata(dev, ddata); + pm_runtime_put(dev); pm_runtime_allow(dev); @@ -88,19 +104,24 @@ static void dwc_pwm_remove(struct pci_dev *pci) static int dwc_pwm_suspend(struct device *dev) { - struct pwm_chip *chip = dev_get_drvdata(dev); - struct dwc_pwm *dwc = to_dwc_pwm(chip); - int i; - - for (i = 0; i < DWC_TIMERS_TOTAL; i++) { - if (chip->pwms[i].state.enabled) { - dev_err(dev, "PWM %u in use by consumer (%s)\n", - i, chip->pwms[i].label); - return -EBUSY; + struct dwc_pwm_drvdata *ddata = dev_get_drvdata(dev); + unsigned int idx; + + for (idx = 0; idx < ddata->info->nr; idx++) { + struct pwm_chip *chip = ddata->chips[idx]; + struct dwc_pwm *dwc = to_dwc_pwm(chip); + unsigned int i; + + for (i = 0; i < DWC_TIMERS_TOTAL; i++) { + if (chip->pwms[i].state.enabled) { + dev_err(dev, "PWM %u in use by consumer (%s)\n", + i, chip->pwms[i].label); + return -EBUSY; + } + dwc->ctx[i].cnt = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT(i)); + dwc->ctx[i].cnt2 = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT2(i)); + dwc->ctx[i].ctrl = dwc_pwm_readl(dwc, DWC_TIM_CTRL(i)); } - dwc->ctx[i].cnt = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT(i)); - dwc->ctx[i].cnt2 = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT2(i)); - dwc->ctx[i].ctrl = dwc_pwm_readl(dwc, DWC_TIM_CTRL(i)); } return 0; @@ -108,14 +129,19 @@ static int dwc_pwm_suspend(struct device *dev) static int dwc_pwm_resume(struct device *dev) { - struct pwm_chip *chip = dev_get_drvdata(dev); - struct dwc_pwm *dwc = to_dwc_pwm(chip); - int i; - - for (i = 0; i < DWC_TIMERS_TOTAL; i++) { - dwc_pwm_writel(dwc, dwc->ctx[i].cnt, DWC_TIM_LD_CNT(i)); - dwc_pwm_writel(dwc, dwc->ctx[i].cnt2, DWC_TIM_LD_CNT2(i)); - dwc_pwm_writel(dwc, dwc->ctx[i].ctrl, DWC_TIM_CTRL(i)); + struct dwc_pwm_drvdata *ddata = dev_get_drvdata(dev); + unsigned int idx; + + for (idx = 0; idx < ddata->info->nr; idx++) { + struct pwm_chip *chip = ddata->chips[idx]; + struct dwc_pwm *dwc = to_dwc_pwm(chip); + unsigned int i; + + for (i = 0; i < DWC_TIMERS_TOTAL; i++) { + dwc_pwm_writel(dwc, dwc->ctx[i].cnt, DWC_TIM_LD_CNT(i)); + dwc_pwm_writel(dwc, dwc->ctx[i].cnt2, DWC_TIM_LD_CNT2(i)); + dwc_pwm_writel(dwc, dwc->ctx[i].ctrl, DWC_TIM_CTRL(i)); + } } return 0; diff --git a/drivers/pwm/pwm-dwc.h b/drivers/pwm/pwm-dwc.h index a8b074841ae80..c6e2df5a61227 100644 --- a/drivers/pwm/pwm-dwc.h +++ b/drivers/pwm/pwm-dwc.h @@ -38,6 +38,12 @@ struct dwc_pwm_info { unsigned int size; }; +struct dwc_pwm_drvdata { + const struct dwc_pwm_info *info; + void __iomem *io_base; + struct pwm_chip *chips[]; +}; + struct dwc_pwm_ctx { u32 cnt; u32 cnt2; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index f95d12345d98a..920f550bc313b 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -363,10 +363,8 @@ int ccw_device_set_online(struct ccw_device *cdev) spin_lock_irq(cdev->ccwlock); ret = ccw_device_online(cdev); - spin_unlock_irq(cdev->ccwlock); - if (ret == 0) - wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); - else { + if (ret) { + spin_unlock_irq(cdev->ccwlock); CIO_MSG_EVENT(0, "ccw_device_online returned %d, " "device 0.%x.%04x\n", ret, cdev->private->dev_id.ssid, @@ -375,7 +373,12 @@ int ccw_device_set_online(struct ccw_device *cdev) put_device(&cdev->dev); return ret; } - spin_lock_irq(cdev->ccwlock); + /* Wait until a final state is reached */ + while (!dev_fsm_final_state(cdev)) { + spin_unlock_irq(cdev->ccwlock); + wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); + spin_lock_irq(cdev->ccwlock); + } /* Check if online processing was successful */ if ((cdev->private->state != DEV_STATE_ONLINE) && (cdev->private->state != DEV_STATE_W4SENSE)) { diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c index 65d8b2cfd6262..42791fa0b80e2 100644 --- a/drivers/s390/cio/device_fsm.c +++ b/drivers/s390/cio/device_fsm.c @@ -504,6 +504,11 @@ callback: ccw_device_done(cdev, DEV_STATE_ONLINE); /* Deliver fake irb to device driver, if needed. */ if (cdev->private->flags.fake_irb) { + CIO_MSG_EVENT(2, "fakeirb: deliver device 0.%x.%04x intparm %lx type=%d\n", + cdev->private->dev_id.ssid, + cdev->private->dev_id.devno, + cdev->private->intparm, + cdev->private->flags.fake_irb); create_fake_irb(&cdev->private->dma_area->irb, cdev->private->flags.fake_irb); cdev->private->flags.fake_irb = 0; diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index 40c97f8730751..acd6790dba4dd 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -208,6 +208,10 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, if (!cdev->private->flags.fake_irb) { cdev->private->flags.fake_irb = FAKE_CMD_IRB; cdev->private->intparm = intparm; + CIO_MSG_EVENT(2, "fakeirb: queue device 0.%x.%04x intparm %lx type=%d\n", + cdev->private->dev_id.ssid, + cdev->private->dev_id.devno, intparm, + cdev->private->flags.fake_irb); return 0; } else /* There's already a fake I/O around. */ @@ -551,6 +555,10 @@ int ccw_device_tm_start_timeout_key(struct ccw_device *cdev, struct tcw *tcw, if (!cdev->private->flags.fake_irb) { cdev->private->flags.fake_irb = FAKE_TM_IRB; cdev->private->intparm = intparm; + CIO_MSG_EVENT(2, "fakeirb: queue device 0.%x.%04x intparm %lx type=%d\n", + cdev->private->dev_id.ssid, + cdev->private->dev_id.devno, intparm, + cdev->private->flags.fake_irb); return 0; } else /* There's already a fake I/O around. */ diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 3d9f0834c78bf..a1cb39f4b7a27 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -722,8 +722,8 @@ static void qdio_handle_activate_check(struct qdio_irq *irq_ptr, lgr_info_log(); } -static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, - int dstat) +static int qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, + int dstat, int dcc) { DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qest irq"); @@ -731,15 +731,18 @@ static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, goto error; if (dstat & ~(DEV_STAT_DEV_END | DEV_STAT_CHN_END)) goto error; + if (dcc == 1) + return -EAGAIN; if (!(dstat & DEV_STAT_DEV_END)) goto error; qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ESTABLISHED); - return; + return 0; error: DBF_ERROR("%4x EQ:error", irq_ptr->schid.sch_no); DBF_ERROR("ds: %2x cs:%2x", dstat, cstat); qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + return -EIO; } /* qdio interrupt handler */ @@ -748,7 +751,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, { struct qdio_irq *irq_ptr = cdev->private->qdio_data; struct subchannel_id schid; - int cstat, dstat; + int cstat, dstat, rc, dcc; if (!intparm || !irq_ptr) { ccw_device_get_schid(cdev, &schid); @@ -768,10 +771,12 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, qdio_irq_check_sense(irq_ptr, irb); cstat = irb->scsw.cmd.cstat; dstat = irb->scsw.cmd.dstat; + dcc = scsw_cmd_is_valid_cc(&irb->scsw) ? irb->scsw.cmd.cc : 0; + rc = 0; switch (irq_ptr->state) { case QDIO_IRQ_STATE_INACTIVE: - qdio_establish_handle_irq(irq_ptr, cstat, dstat); + rc = qdio_establish_handle_irq(irq_ptr, cstat, dstat, dcc); break; case QDIO_IRQ_STATE_CLEANUP: qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE); @@ -785,12 +790,25 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, if (cstat || dstat) qdio_handle_activate_check(irq_ptr, intparm, cstat, dstat); + else if (dcc == 1) + rc = -EAGAIN; break; case QDIO_IRQ_STATE_STOPPED: break; default: WARN_ON_ONCE(1); } + + if (rc == -EAGAIN) { + DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qint retry"); + rc = ccw_device_start(cdev, irq_ptr->ccw, intparm, 0, 0); + if (!rc) + return; + DBF_ERROR("%4x RETRY ERR", irq_ptr->schid.sch_no); + DBF_ERROR("rc:%4x", rc); + qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + } + wake_up(&cdev->private->wait_q); } diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 2c8e964425dc3..43778b088ffac 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -292,13 +292,16 @@ out: static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { clear_bit(dmb->sba_idx, ism->sba_bitmap); - dma_free_coherent(&ism->pdev->dev, dmb->dmb_len, - dmb->cpu_addr, dmb->dma_addr); + dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len, + DMA_FROM_DEVICE); + folio_put(virt_to_folio(dmb->cpu_addr)); } static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { + struct folio *folio; unsigned long bit; + int rc; if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev)) return -EINVAL; @@ -315,14 +318,30 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) test_and_set_bit(dmb->sba_idx, ism->sba_bitmap)) return -EINVAL; - dmb->cpu_addr = dma_alloc_coherent(&ism->pdev->dev, dmb->dmb_len, - &dmb->dma_addr, - GFP_KERNEL | __GFP_NOWARN | - __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!dmb->cpu_addr) - clear_bit(dmb->sba_idx, ism->sba_bitmap); + folio = folio_alloc(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | + __GFP_NORETRY, get_order(dmb->dmb_len)); - return dmb->cpu_addr ? 0 : -ENOMEM; + if (!folio) { + rc = -ENOMEM; + goto out_bit; + } + + dmb->cpu_addr = folio_address(folio); + dmb->dma_addr = dma_map_page(&ism->pdev->dev, + virt_to_page(dmb->cpu_addr), 0, + dmb->dmb_len, DMA_FROM_DEVICE); + if (dma_mapping_error(&ism->pdev->dev, dmb->dma_addr)) { + rc = -ENOMEM; + goto out_free; + } + + return 0; + +out_free: + kfree(dmb->cpu_addr); +out_bit: + clear_bit(dmb->sba_idx, ism->sba_bitmap); + return rc; } int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb, diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 2e28e2360c857..5b3230ef51fe6 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -635,10 +635,9 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (blk_queue_add_random(q)) add_disk_randomness(req->q->disk); - if (!blk_rq_is_passthrough(req)) { - WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED)); - cmd->flags &= ~SCMD_INITIALIZED; - } + WARN_ON_ONCE(!blk_rq_is_passthrough(req) && + !(cmd->flags & SCMD_INITIALIZED)); + cmd->flags = 0; /* * Calling rcu_barrier() is not necessary here because the diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c index c617e8b9f0ddf..d78d54ae2605e 100644 --- a/drivers/thermal/thermal_debugfs.c +++ b/drivers/thermal/thermal_debugfs.c @@ -616,6 +616,7 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz, tze->trip_stats[trip_id].timestamp = now; tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature); tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature); + tze->trip_stats[trip_id].count++; tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg + (temperature - tze->trip_stats[trip_id].avg) / tze->trip_stats[trip_id].count; diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 06859e17b67b7..7a00004bfd036 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -47,7 +47,7 @@ enum { TSTBUS_MAX, }; -#define QCOM_UFS_MAX_GEAR 4 +#define QCOM_UFS_MAX_GEAR 5 #define QCOM_UFS_MAX_LANE 2 enum { @@ -67,26 +67,32 @@ static const struct __ufs_qcom_bw_table { [MODE_PWM][UFS_PWM_G2][UFS_LANE_1] = { 1844, 1000 }, [MODE_PWM][UFS_PWM_G3][UFS_LANE_1] = { 3688, 1000 }, [MODE_PWM][UFS_PWM_G4][UFS_LANE_1] = { 7376, 1000 }, + [MODE_PWM][UFS_PWM_G5][UFS_LANE_1] = { 14752, 1000 }, [MODE_PWM][UFS_PWM_G1][UFS_LANE_2] = { 1844, 1000 }, [MODE_PWM][UFS_PWM_G2][UFS_LANE_2] = { 3688, 1000 }, [MODE_PWM][UFS_PWM_G3][UFS_LANE_2] = { 7376, 1000 }, [MODE_PWM][UFS_PWM_G4][UFS_LANE_2] = { 14752, 1000 }, + [MODE_PWM][UFS_PWM_G5][UFS_LANE_2] = { 29504, 1000 }, [MODE_HS_RA][UFS_HS_G1][UFS_LANE_1] = { 127796, 1000 }, [MODE_HS_RA][UFS_HS_G2][UFS_LANE_1] = { 255591, 1000 }, [MODE_HS_RA][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 }, [MODE_HS_RA][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 }, + [MODE_HS_RA][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 }, [MODE_HS_RA][UFS_HS_G1][UFS_LANE_2] = { 255591, 1000 }, [MODE_HS_RA][UFS_HS_G2][UFS_LANE_2] = { 511181, 1000 }, [MODE_HS_RA][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RA][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, + [MODE_HS_RA][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, [MODE_HS_RB][UFS_HS_G1][UFS_LANE_1] = { 149422, 1000 }, [MODE_HS_RB][UFS_HS_G2][UFS_LANE_1] = { 298189, 1000 }, [MODE_HS_RB][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 }, + [MODE_HS_RB][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 }, [MODE_HS_RB][UFS_HS_G1][UFS_LANE_2] = { 298189, 1000 }, [MODE_HS_RB][UFS_HS_G2][UFS_LANE_2] = { 596378, 1000 }, [MODE_HS_RB][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, + [MODE_HS_RB][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, [MODE_MAX][0][0] = { 7643136, 307200 }, }; diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c index b67a28da47026..a1c467a0e9f71 100644 --- a/drivers/virt/vmgenid.c +++ b/drivers/virt/vmgenid.c @@ -68,7 +68,6 @@ out: static void vmgenid_notify(struct acpi_device *device, u32 event) { struct vmgenid_state *state = acpi_driver_data(device); - char *envp[] = { "NEW_VMGENID=1", NULL }; u8 old_id[VMGENID_SIZE]; memcpy(old_id, state->this_id, sizeof(old_id)); @@ -76,7 +75,6 @@ static void vmgenid_notify(struct acpi_device *device, u32 event) if (!memcmp(old_id, state->this_id, sizeof(old_id))) return; add_vmfork_randomness(state->this_id, sizeof(state->this_id)); - kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp); } static const struct acpi_device_id vmgenid_ids[] = { diff --git a/fs/9p/fid.h b/fs/9p/fid.h index 29281b7c38870..0d6138bee2a3d 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -49,9 +49,6 @@ static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry) static inline void v9fs_fid_add_modes(struct p9_fid *fid, unsigned int s_flags, unsigned int s_cache, unsigned int f_flags) { - if (fid->qid.type != P9_QTFILE) - return; - if ((!s_cache) || ((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) || (s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) { diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index abdbbaee51846..348cc90bf9c56 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -520,6 +520,7 @@ const struct file_operations v9fs_file_operations = { .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, + .setlease = simple_nosetlease, }; const struct file_operations v9fs_file_operations_dotl = { @@ -534,4 +535,5 @@ const struct file_operations v9fs_file_operations_dotl = { .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, + .setlease = simple_nosetlease, }; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index b01b1bbf24937..47bd77199e20c 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -83,7 +83,7 @@ static int p9mode2perm(struct v9fs_session_info *v9ses, int res; int mode = stat->mode; - res = mode & S_IALLUGO; + res = mode & 0777; /* S_IRWXUGO */ if (v9fs_proto_dotu(v9ses)) { if ((mode & P9_DMSETUID) == P9_DMSETUID) res |= S_ISUID; @@ -178,6 +178,9 @@ int v9fs_uflags2omode(int uflags, int extended) break; } + if (uflags & O_TRUNC) + ret |= P9_OTRUNC; + if (extended) { if (uflags & O_EXCL) ret |= P9_OEXCL; @@ -1061,8 +1064,6 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, struct v9fs_session_info *v9ses = sb->s_fs_info; struct v9fs_inode *v9inode = V9FS_I(inode); - set_nlink(inode, 1); - inode_set_atime(inode, stat->atime, 0); inode_set_mtime(inode, stat->mtime, 0); inode_set_ctime(inode, stat->mtime, 0); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 4236058c7bbd1..55e67e36ae682 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -244,6 +244,21 @@ done: return res; } +static int v9fs_drop_inode(struct inode *inode) +{ + struct v9fs_session_info *v9ses; + + v9ses = v9fs_inode2v9ses(inode); + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) + return generic_drop_inode(inode); + /* + * in case of non cached mode always drop the + * inode because we want the inode attribute + * to always match that on the server. + */ + return 1; +} + static int v9fs_write_inode(struct inode *inode, struct writeback_control *wbc) { @@ -268,6 +283,7 @@ static const struct super_operations v9fs_super_ops = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = simple_statfs, + .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, @@ -278,6 +294,7 @@ static const struct super_operations v9fs_super_ops_dotl = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = v9fs_statfs, + .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 114328acde720..fadb1078903d2 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -49,13 +49,15 @@ int bch2_backpointer_invalid(struct bch_fs *c, struct bkey_s_c k, if (!bch2_dev_exists2(c, bp.k->p.inode)) return 0; + struct bch_dev *ca = bch_dev_bkey_exists(c, bp.k->p.inode); struct bpos bucket = bp_pos_to_bucket(c, bp.k->p); int ret = 0; - bkey_fsck_err_on(!bpos_eq(bp.k->p, bucket_pos_to_bp(c, bucket, bp.v->bucket_offset)), + bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size || + !bpos_eq(bp.k->p, bucket_pos_to_bp(c, bucket, bp.v->bucket_offset)), c, err, - backpointer_pos_wrong, - "backpointer at wrong pos"); + backpointer_bucket_offset_wrong, + "backpointer bucket_offset wrong"); fsck_err: return ret; } diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h index da012ca7daee5..85949b9fd880c 100644 --- a/fs/bcachefs/backpointers.h +++ b/fs/bcachefs/backpointers.h @@ -53,14 +53,11 @@ static inline struct bpos bucket_pos_to_bp(const struct bch_fs *c, u64 bucket_offset) { struct bch_dev *ca = bch_dev_bkey_exists(c, bucket.inode); - struct bpos ret; - - ret = POS(bucket.inode, - (bucket_to_sector(ca, bucket.offset) << - MAX_EXTENT_COMPRESS_RATIO_SHIFT) + bucket_offset); + struct bpos ret = POS(bucket.inode, + (bucket_to_sector(ca, bucket.offset) << + MAX_EXTENT_COMPRESS_RATIO_SHIFT) + bucket_offset); EBUG_ON(!bkey_eq(bucket, bp_pos_to_bucket(c, ret))); - return ret; } diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index a31a5f706929e..91c3c1fef233d 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -709,6 +709,8 @@ struct btree_trans_buf { x(stripe_delete) \ x(reflink) \ x(fallocate) \ + x(fsync) \ + x(dio_write) \ x(discard) \ x(discard_fast) \ x(invalidate) \ diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 364ae42022af1..085987435a5ea 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -578,7 +578,8 @@ struct bch_member { __le64 nbuckets; /* device size */ __le16 first_bucket; /* index of first bucket used */ __le16 bucket_size; /* sectors */ - __le32 pad; + __u8 btree_bitmap_shift; + __u8 pad[3]; __le64 last_mount; /* time_t */ __le64 flags; @@ -587,6 +588,7 @@ struct bch_member { __le64 errors_at_reset[BCH_MEMBER_ERROR_NR]; __le64 errors_reset_time; __le64 seq; + __le64 btree_allocated_bitmap; }; #define BCH_MEMBER_V1_BYTES 56 @@ -876,7 +878,8 @@ struct bch_sb_field_downgrade { x(rebalance_work, BCH_VERSION(1, 3)) \ x(member_seq, BCH_VERSION(1, 4)) \ x(subvolume_fs_parent, BCH_VERSION(1, 5)) \ - x(btree_subvolume_children, BCH_VERSION(1, 6)) + x(btree_subvolume_children, BCH_VERSION(1, 6)) \ + x(mi_btree_bitmap, BCH_VERSION(1, 7)) enum bcachefs_metadata_version { bcachefs_metadata_version_min = 9, @@ -1314,7 +1317,7 @@ static inline __u64 __bset_magic(struct bch_sb *sb) x(write_buffer_keys, 11) \ x(datetime, 12) -enum { +enum bch_jset_entry_type { #define x(f, nr) BCH_JSET_ENTRY_##f = nr, BCH_JSET_ENTRY_TYPES() #undef x @@ -1360,7 +1363,7 @@ struct jset_entry_blacklist_v2 { x(inodes, 1) \ x(key_version, 2) -enum { +enum bch_fs_usage_type { #define x(f, nr) BCH_FS_USAGE_##f = nr, BCH_FS_USAGE_TYPES() #undef x diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h index cf23ff47bed8b..3a45d128f608d 100644 --- a/fs/bcachefs/bkey.h +++ b/fs/bcachefs/bkey.h @@ -314,6 +314,12 @@ static inline unsigned bkeyp_key_u64s(const struct bkey_format *format, return bkey_packed(k) ? format->key_u64s : BKEY_U64s; } +static inline bool bkeyp_u64s_valid(const struct bkey_format *f, + const struct bkey_packed *k) +{ + return ((unsigned) k->u64s - bkeyp_key_u64s(f, k) <= U8_MAX - BKEY_U64s); +} + static inline unsigned bkeyp_key_bytes(const struct bkey_format *format, const struct bkey_packed *k) { diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index 5e52684764eb1..db336a43fc083 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -171,11 +171,15 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, if (type >= BKEY_TYPE_NR) return 0; - bkey_fsck_err_on((flags & BKEY_INVALID_COMMIT) && + bkey_fsck_err_on((type == BKEY_TYPE_btree || + (flags & BKEY_INVALID_COMMIT)) && !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), c, err, bkey_invalid_type_for_btree, "invalid key type for btree %s (%s)", - bch2_btree_node_type_str(type), bch2_bkey_types[k.k->type]); + bch2_btree_node_type_str(type), + k.k->type < KEY_TYPE_MAX + ? bch2_bkey_types[k.k->type] + : "(unknown)"); if (btree_node_type_is_extents(type) && !bkey_whiteout(k.k)) { bkey_fsck_err_on(k.k->size == 0, c, err, diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 84474324dba9b..02c70e813face 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -709,9 +709,31 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans, struct bch_fs *c = trans->c; struct btree_cache *bc = &c->btree_cache; struct btree *b; - u32 seq; - BUG_ON(level + 1 >= BTREE_MAX_DEPTH); + if (unlikely(level >= BTREE_MAX_DEPTH)) { + int ret = bch2_fs_topology_error(c, "attempting to get btree node at level %u, >= max depth %u", + level, BTREE_MAX_DEPTH); + return ERR_PTR(ret); + } + + if (unlikely(!bkey_is_btree_ptr(&k->k))) { + struct printbuf buf = PRINTBUF; + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k)); + + int ret = bch2_fs_topology_error(c, "attempting to get btree node with non-btree key %s", buf.buf); + printbuf_exit(&buf); + return ERR_PTR(ret); + } + + if (unlikely(k->k.u64s > BKEY_BTREE_PTR_U64s_MAX)) { + struct printbuf buf = PRINTBUF; + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k)); + + int ret = bch2_fs_topology_error(c, "attempting to get btree node with too big key %s", buf.buf); + printbuf_exit(&buf); + return ERR_PTR(ret); + } + /* * Parent node must be locked, else we could read in a btree node that's * been freed: @@ -752,34 +774,26 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans, } set_btree_node_read_in_flight(b); - six_unlock_write(&b->c.lock); - seq = six_lock_seq(&b->c.lock); - six_unlock_intent(&b->c.lock); - /* Unlock before doing IO: */ - if (path && sync) - bch2_trans_unlock_noassert(trans); - - bch2_btree_node_read(trans, b, sync); + if (path) { + u32 seq = six_lock_seq(&b->c.lock); - if (!sync) - return NULL; + /* Unlock before doing IO: */ + six_unlock_intent(&b->c.lock); + bch2_trans_unlock_noassert(trans); - if (path) { - int ret = bch2_trans_relock(trans) ?: - bch2_btree_path_relock_intent(trans, path); - if (ret) { - BUG_ON(!trans->restarted); - return ERR_PTR(ret); - } - } + bch2_btree_node_read(trans, b, sync); - if (!six_relock_type(&b->c.lock, lock_type, seq)) { - BUG_ON(!path); + if (!sync) + return NULL; - trace_and_count(c, trans_restart_relock_after_fill, trans, _THIS_IP_, path); - return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_relock_after_fill)); + if (!six_relock_type(&b->c.lock, lock_type, seq)) + b = NULL; + } else { + bch2_btree_node_read(trans, b, sync); + if (lock_type == SIX_LOCK_read) + six_lock_downgrade(&b->c.lock); } return b; @@ -1112,18 +1126,19 @@ int bch2_btree_node_prefetch(struct btree_trans *trans, { struct bch_fs *c = trans->c; struct btree_cache *bc = &c->btree_cache; - struct btree *b; BUG_ON(path && !btree_node_locked(path, level + 1)); BUG_ON(level >= BTREE_MAX_DEPTH); - b = btree_cache_find(bc, k); + struct btree *b = btree_cache_find(bc, k); if (b) return 0; b = bch2_btree_node_fill(trans, path, k, btree_id, level, SIX_LOCK_read, false); - return PTR_ERR_OR_ZERO(b); + if (!IS_ERR_OR_NULL(b)) + six_unlock_read(&b->c.lock); + return bch2_trans_relock(trans) ?: PTR_ERR_OR_ZERO(b); } void bch2_btree_node_evict(struct btree_trans *trans, const struct bkey_i *k) @@ -1148,6 +1163,8 @@ wait_on_io: btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write); + if (unlikely(b->hash_val != btree_ptr_hash_val(k))) + goto out; if (btree_node_dirty(b)) { __bch2_btree_node_write(c, b, BTREE_WRITE_cache_reclaim); @@ -1162,7 +1179,7 @@ wait_on_io: btree_node_data_free(c, b); bch2_btree_node_hash_remove(bc, b); mutex_unlock(&bc->lock); - +out: six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); } diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index d2555da55c6da..ecbd9598f69fd 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -828,6 +828,7 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, struct bch_fs *c = trans->c; struct bkey deleted = KEY(0, 0, 0); struct bkey_s_c old = (struct bkey_s_c) { &deleted, NULL }; + struct printbuf buf = PRINTBUF; int ret = 0; deleted.p = k->k->p; @@ -848,11 +849,23 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, if (ret) goto err; + if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, *k), + c, btree_bitmap_not_marked, + "btree ptr not marked in member info btree allocated bitmap\n %s", + (bch2_bkey_val_to_text(&buf, c, *k), + buf.buf))) { + mutex_lock(&c->sb_lock); + bch2_dev_btree_bitmap_mark(c, *k); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); + } + ret = commit_do(trans, NULL, NULL, 0, bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC)); fsck_err: err: + printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index d7de82ac38935..9678b2375bedd 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -831,7 +831,7 @@ static int bset_key_invalid(struct bch_fs *c, struct btree *b, (rw == WRITE ? bch2_bkey_val_invalid(c, k, READ, err) : 0); } -static bool __bkey_valid(struct bch_fs *c, struct btree *b, +static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, struct bset *i, struct bkey_packed *k) { if (bkey_p_next(k) > vstruct_last(i)) @@ -840,7 +840,7 @@ static bool __bkey_valid(struct bch_fs *c, struct btree *b, if (k->format > KEY_FORMAT_CURRENT) return false; - if (k->u64s < bkeyp_key_u64s(&b->format, k)) + if (!bkeyp_u64s_valid(&b->format, k)) return false; struct printbuf buf = PRINTBUF; @@ -884,11 +884,13 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, "invalid bkey format %u", k->format)) goto drop_this_key; - if (btree_err_on(k->u64s < bkeyp_key_u64s(&b->format, k), + if (btree_err_on(!bkeyp_u64s_valid(&b->format, k), -BCH_ERR_btree_node_read_err_fixable, c, NULL, b, i, btree_node_bkey_bad_u64s, - "k->u64s too small (%u < %u)", k->u64s, bkeyp_key_u64s(&b->format, k))) + "bad k->u64s %u (min %u max %lu)", k->u64s, + bkeyp_key_u64s(&b->format, k), + U8_MAX - BKEY_U64s + bkeyp_key_u64s(&b->format, k))) goto drop_this_key; if (!write) @@ -947,13 +949,12 @@ drop_this_key: * do */ - if (!__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) { + if (!bkey_packed_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) { for (next_good_key = 1; next_good_key < (u64 *) vstruct_last(i) - (u64 *) k; next_good_key++) - if (__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) + if (bkey_packed_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) goto got_good_key; - } /* @@ -1339,7 +1340,9 @@ start: rb->start_time); bio_put(&rb->bio); - if (saw_error && !btree_node_read_error(b)) { + if (saw_error && + !btree_node_read_error(b) && + c->curr_recovery_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->key.k.p); bch_err_ratelimited(c, "%s: rewriting btree node at btree=%s level=%u %s due to error", diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index 1d58d447b386c..1c70836dd7cce 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -498,8 +498,13 @@ static inline void set_btree_iter_dontneed(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; - if (!trans->restarted) - btree_iter_path(trans, iter)->preserve = false; + if (!iter->path || trans->restarted) + return; + + struct btree_path *path = btree_iter_path(trans, iter); + path->preserve = false; + if (path->ref == 1) + path->should_be_locked = false; } void *__bch2_trans_kmalloc(struct btree_trans *, size_t); diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 556f76f5c84e1..866bd278439f8 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -133,9 +133,19 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, if (le64_to_cpu(bn->magic) != bset_magic(c)) return; + if (bch2_csum_type_is_encryption(BSET_CSUM_TYPE(&bn->keys))) { + struct nonce nonce = btree_nonce(&bn->keys, 0); + unsigned bytes = (void *) &bn->keys - (void *) &bn->flags; + + bch2_encrypt(c, BSET_CSUM_TYPE(&bn->keys), nonce, &bn->flags, bytes); + } + if (btree_id_is_alloc(BTREE_NODE_ID(bn))) return; + if (BTREE_NODE_LEVEL(bn) >= BTREE_MAX_DEPTH) + return; + rcu_read_lock(); struct found_btree_node n = { .btree_id = BTREE_NODE_ID(bn), @@ -195,8 +205,13 @@ static int read_btree_nodes_worker(void *p) last_print = jiffies; } - try_read_btree_node(w->f, ca, bio, buf, - bucket * ca->mi.bucket_size + bucket_offset); + u64 sector = bucket * ca->mi.bucket_size + bucket_offset; + + if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_mi_btree_bitmap && + !bch2_dev_btree_bitmap_marked_sectors(ca, sector, btree_sectors(c))) + continue; + + try_read_btree_node(w->f, ca, bio, buf, sector); } err: bio_put(bio); diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index aa9da49707404..bbec91e8e6506 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -397,12 +397,13 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags struct bkey_cached *ck = (void *) path->l[0].b; unsigned new_u64s; struct bkey_i *new_k; + unsigned watermark = flags & BCH_WATERMARK_MASK; EBUG_ON(path->level); - if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) && - bch2_btree_key_cache_must_wait(c) && - !(flags & BCH_TRANS_COMMIT_journal_reclaim)) + if (watermark < BCH_WATERMARK_reclaim && + !test_bit(BKEY_CACHED_DIRTY, &ck->flags) && + bch2_btree_key_cache_must_wait(c)) return -BCH_ERR_btree_insert_need_journal_reclaim; /* @@ -499,9 +500,8 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_ } static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, - struct btree_insert_entry *btree_id_start) + unsigned btree_id_start) { - struct btree_insert_entry *i; bool trans_trigger_run; int ret, overwrite; @@ -514,13 +514,13 @@ static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, do { trans_trigger_run = false; - for (i = btree_id_start; - i < trans->updates + trans->nr_updates && i->btree_id <= btree_id; + for (unsigned i = btree_id_start; + i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; i++) { - if (i->btree_id != btree_id) + if (trans->updates[i].btree_id != btree_id) continue; - ret = run_one_trans_trigger(trans, i, overwrite); + ret = run_one_trans_trigger(trans, trans->updates + i, overwrite); if (ret < 0) return ret; if (ret) @@ -534,8 +534,7 @@ static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, static int bch2_trans_commit_run_triggers(struct btree_trans *trans) { - struct btree_insert_entry *btree_id_start = trans->updates; - unsigned btree_id = 0; + unsigned btree_id = 0, btree_id_start = 0; int ret = 0; /* @@ -549,8 +548,8 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans) if (btree_id == BTREE_ID_alloc) continue; - while (btree_id_start < trans->updates + trans->nr_updates && - btree_id_start->btree_id < btree_id) + while (btree_id_start < trans->nr_updates && + trans->updates[btree_id_start].btree_id < btree_id) btree_id_start++; ret = run_btree_triggers(trans, btree_id, btree_id_start); @@ -558,11 +557,13 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans) return ret; } - trans_for_each_update(trans, i) { + for (unsigned idx = 0; idx < trans->nr_updates; idx++) { + struct btree_insert_entry *i = trans->updates + idx; + if (i->btree_id > BTREE_ID_alloc) break; if (i->btree_id == BTREE_ID_alloc) { - ret = run_btree_triggers(trans, BTREE_ID_alloc, i); + ret = run_btree_triggers(trans, BTREE_ID_alloc, idx); if (ret) return ret; break; @@ -826,7 +827,8 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags struct bch_fs *c = trans->c; int ret = 0, u64s_delta = 0; - trans_for_each_update(trans, i) { + for (unsigned idx = 0; idx < trans->nr_updates; idx++) { + struct btree_insert_entry *i = trans->updates + idx; if (i->cached) continue; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index c4a5e83a56a43..6030c396754f6 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -21,6 +21,7 @@ #include "keylist.h" #include "recovery_passes.h" #include "replicas.h" +#include "sb-members.h" #include "super-io.h" #include "trace.h" @@ -605,6 +606,26 @@ static void btree_update_add_key(struct btree_update *as, bch2_keylist_push(keys); } +static bool btree_update_new_nodes_marked_sb(struct btree_update *as) +{ + for_each_keylist_key(&as->new_keys, k) + if (!bch2_dev_btree_bitmap_marked(as->c, bkey_i_to_s_c(k))) + return false; + return true; +} + +static void btree_update_new_nodes_mark_sb(struct btree_update *as) +{ + struct bch_fs *c = as->c; + + mutex_lock(&c->sb_lock); + for_each_keylist_key(&as->new_keys, k) + bch2_dev_btree_bitmap_mark(c, bkey_i_to_s_c(k)); + + bch2_write_super(c); + mutex_unlock(&c->sb_lock); +} + /* * The transactional part of an interior btree node update, where we journal the * update we did to the interior node and update alloc info: @@ -662,6 +683,9 @@ static void btree_update_nodes_written(struct btree_update *as) if (ret) goto err; + if (!btree_update_new_nodes_marked_sb(as)) + btree_update_new_nodes_mark_sb(as); + /* * Wait for any in flight writes to finish before we free the old nodes * on disk: @@ -1280,23 +1304,29 @@ static void bch2_btree_set_root_inmem(struct bch_fs *c, struct btree *b) bch2_recalc_btree_reserve(c); } -static void bch2_btree_set_root(struct btree_update *as, - struct btree_trans *trans, - struct btree_path *path, - struct btree *b) +static int bch2_btree_set_root(struct btree_update *as, + struct btree_trans *trans, + struct btree_path *path, + struct btree *b, + bool nofail) { struct bch_fs *c = as->c; - struct btree *old; trace_and_count(c, btree_node_set_root, trans, b); - old = btree_node_root(c, b); + struct btree *old = btree_node_root(c, b); /* * Ensure no one is using the old root while we switch to the * new root: */ - bch2_btree_node_lock_write_nofail(trans, path, &old->c); + if (nofail) { + bch2_btree_node_lock_write_nofail(trans, path, &old->c); + } else { + int ret = bch2_btree_node_lock_write(trans, path, &old->c); + if (ret) + return ret; + } bch2_btree_set_root_inmem(c, b); @@ -1310,6 +1340,7 @@ static void bch2_btree_set_root(struct btree_update *as, * depend on the new root would have to update the new root. */ bch2_btree_node_unlock_write(trans, path, old); + return 0; } /* Interior node updates: */ @@ -1652,15 +1683,16 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans, if (parent) { /* Split a non root node */ ret = bch2_btree_insert_node(as, trans, path, parent, &as->parent_keys); - if (ret) - goto err; } else if (n3) { - bch2_btree_set_root(as, trans, trans->paths + path, n3); + ret = bch2_btree_set_root(as, trans, trans->paths + path, n3, false); } else { /* Root filled up but didn't need to be split */ - bch2_btree_set_root(as, trans, trans->paths + path, n1); + ret = bch2_btree_set_root(as, trans, trans->paths + path, n1, false); } + if (ret) + goto err; + if (n3) { bch2_btree_update_get_open_buckets(as, n3); bch2_btree_node_write(c, n3, SIX_LOCK_intent, 0); @@ -1863,7 +1895,9 @@ static void __btree_increase_depth(struct btree_update *as, struct btree_trans * bch2_keylist_add(&as->parent_keys, &b->key); btree_split_insert_keys(as, trans, path_idx, n, &as->parent_keys); - bch2_btree_set_root(as, trans, path, n); + int ret = bch2_btree_set_root(as, trans, path, n, true); + BUG_ON(ret); + bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); bch2_trans_node_add(trans, path, n); @@ -1916,6 +1950,18 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, BUG_ON(!trans->paths[path].should_be_locked); BUG_ON(!btree_node_locked(&trans->paths[path], level)); + /* + * Work around a deadlock caused by the btree write buffer not doing + * merges and leaving tons of merges for us to do - we really don't need + * to be doing merges at all from the interior update path, and if the + * interior update path is generating too many new interior updates we + * deadlock: + */ + if ((flags & BCH_WATERMARK_MASK) == BCH_WATERMARK_interior_updates) + return 0; + + flags &= ~BCH_WATERMARK_MASK; + b = trans->paths[path].l[level].b; if ((sib == btree_prev_sib && bpos_eq(b->data->min_key, POS_MIN)) || @@ -2061,6 +2107,10 @@ err: bch2_path_put(trans, new_path, true); bch2_path_put(trans, sib_path, true); bch2_trans_verify_locks(trans); + if (ret == -BCH_ERR_journal_reclaim_would_deadlock) + ret = 0; + if (!ret) + ret = bch2_trans_relock(trans); return ret; err_free_update: bch2_btree_node_free_never_used(as, trans, n); @@ -2106,12 +2156,13 @@ int bch2_btree_node_rewrite(struct btree_trans *trans, if (parent) { bch2_keylist_add(&as->parent_keys, &n->key); ret = bch2_btree_insert_node(as, trans, iter->path, parent, &as->parent_keys); - if (ret) - goto err; } else { - bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n); + ret = bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n, false); } + if (ret) + goto err; + bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index baf63e2fddb64..36a6f42aba5e6 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -316,6 +316,16 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) bpos_gt(k->k.k.p, path->l[0].b->key.k.p)) { bch2_btree_node_unlock_write(trans, path, path->l[0].b); write_locked = false; + + ret = lockrestart_do(trans, + bch2_btree_iter_traverse(&iter) ?: + bch2_foreground_maybe_merge(trans, iter.path, 0, + BCH_WATERMARK_reclaim| + BCH_TRANS_COMMIT_journal_reclaim| + BCH_TRANS_COMMIT_no_check_rw| + BCH_TRANS_COMMIT_no_enospc)); + if (ret) + goto err; } } @@ -382,10 +392,10 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) ret = commit_do(trans, NULL, NULL, BCH_WATERMARK_reclaim| + BCH_TRANS_COMMIT_journal_reclaim| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_enospc| - BCH_TRANS_COMMIT_no_journal_res| - BCH_TRANS_COMMIT_journal_reclaim, + BCH_TRANS_COMMIT_no_journal_res , btree_write_buffered_insert(trans, i)); if (ret) goto err; diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index 00aaf4bb51397..f9af5adabe836 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -395,14 +395,6 @@ static inline const char *bch2_data_type_str(enum bch_data_type type) : "(invalid data type)"; } -static inline void bch2_prt_data_type(struct printbuf *out, enum bch_data_type type) -{ - if (type < BCH_DATA_NR) - prt_str(out, __bch2_data_types[type]); - else - prt_printf(out, "(invalid data type %u)", type); -} - /* disk reservations: */ static inline void bch2_disk_reservation_put(struct bch_fs *c, diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c index 4701457f6381c..7ed779b411f61 100644 --- a/fs/bcachefs/checksum.c +++ b/fs/bcachefs/checksum.c @@ -429,15 +429,20 @@ int bch2_rechecksum_bio(struct bch_fs *c, struct bio *bio, extent_nonce(version, crc_old), bio); if (bch2_crc_cmp(merged, crc_old.csum) && !c->opts.no_data_io) { - bch_err(c, "checksum error in %s() (memory corruption or bug?)\n" - "expected %0llx:%0llx got %0llx:%0llx (old type %s new type %s)", - __func__, - crc_old.csum.hi, - crc_old.csum.lo, - merged.hi, - merged.lo, - bch2_csum_types[crc_old.csum_type], - bch2_csum_types[new_csum_type]); + struct printbuf buf = PRINTBUF; + prt_printf(&buf, "checksum error in %s() (memory corruption or bug?)\n" + "expected %0llx:%0llx got %0llx:%0llx (old type ", + __func__, + crc_old.csum.hi, + crc_old.csum.lo, + merged.hi, + merged.lo); + bch2_prt_csum_type(&buf, crc_old.csum_type); + prt_str(&buf, " new type "); + bch2_prt_csum_type(&buf, new_csum_type); + prt_str(&buf, ")"); + bch_err(c, "%s", buf.buf); + printbuf_exit(&buf); return -EIO; } diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h index 1b8c2c1016dc6..e40499fde9a40 100644 --- a/fs/bcachefs/checksum.h +++ b/fs/bcachefs/checksum.h @@ -61,11 +61,12 @@ static inline void bch2_csum_err_msg(struct printbuf *out, struct bch_csum expected, struct bch_csum got) { - prt_printf(out, "checksum error: got "); + prt_str(out, "checksum error, type "); + bch2_prt_csum_type(out, type); + prt_str(out, ": got "); bch2_csum_to_text(out, type, got); prt_str(out, " should be "); bch2_csum_to_text(out, type, expected); - prt_printf(out, " type %s", bch2_csum_types[type]); } int bch2_chacha_encrypt_key(struct bch_key *, struct nonce, void *, size_t); diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h index 58c2eb45570ff..607fd5e232c90 100644 --- a/fs/bcachefs/compress.h +++ b/fs/bcachefs/compress.h @@ -47,14 +47,6 @@ static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v) return __bch2_compression_opt_to_type[bch2_compression_decode(v).type]; } -static inline void bch2_prt_compression_type(struct printbuf *out, enum bch_compression_type type) -{ - if (type < BCH_COMPRESSION_TYPE_NR) - prt_str(out, __bch2_compression_types[type]); - else - prt_printf(out, "(invalid compression type %u)", type); -} - int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *, struct bch_extent_crc_unpacked *); int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *, diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index 082075244e16a..556a217108d32 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -131,29 +131,33 @@ fsck_err: void bch2_stripe_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { - const struct bch_stripe *s = bkey_s_c_to_stripe(k).v; - unsigned i, nr_data = s->nr_blocks - s->nr_redundant; + const struct bch_stripe *sp = bkey_s_c_to_stripe(k).v; + struct bch_stripe s = {}; + + memcpy(&s, sp, min(sizeof(s), bkey_val_bytes(k.k))); + + unsigned nr_data = s.nr_blocks - s.nr_redundant; + + prt_printf(out, "algo %u sectors %u blocks %u:%u csum ", + s.algorithm, + le16_to_cpu(s.sectors), + nr_data, + s.nr_redundant); + bch2_prt_csum_type(out, s.csum_type); + prt_printf(out, " gran %u", 1U << s.csum_granularity_bits); + + for (unsigned i = 0; i < s.nr_blocks; i++) { + const struct bch_extent_ptr *ptr = sp->ptrs + i; + + if ((void *) ptr >= bkey_val_end(k)) + break; + + bch2_extent_ptr_to_text(out, c, ptr); - prt_printf(out, "algo %u sectors %u blocks %u:%u csum %u gran %u", - s->algorithm, - le16_to_cpu(s->sectors), - nr_data, - s->nr_redundant, - s->csum_type, - 1U << s->csum_granularity_bits); - - for (i = 0; i < s->nr_blocks; i++) { - const struct bch_extent_ptr *ptr = s->ptrs + i; - struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev); - u32 offset; - u64 b = sector_to_bucket_and_offset(ca, ptr->offset, &offset); - - prt_printf(out, " %u:%llu:%u", ptr->dev, b, offset); - if (i < nr_data) - prt_printf(out, "#%u", stripe_blockcount_get(s, i)); - prt_printf(out, " gen %u", ptr->gen); - if (ptr_stale(ca, ptr)) - prt_printf(out, " stale"); + if (s.csum_type < BCH_CSUM_NR && + i < nr_data && + stripe_blockcount_offset(&s, i) < bkey_val_bytes(k.k)) + prt_printf(out, "#%u", stripe_blockcount_get(sp, i)); } } @@ -607,10 +611,8 @@ static void ec_validate_checksums(struct bch_fs *c, struct ec_stripe_buf *buf) struct printbuf err = PRINTBUF; struct bch_dev *ca = bch_dev_bkey_exists(c, v->ptrs[i].dev); - prt_printf(&err, "stripe checksum error: expected %0llx:%0llx got %0llx:%0llx (type %s)\n", - want.hi, want.lo, - got.hi, got.lo, - bch2_csum_types[v->csum_type]); + prt_str(&err, "stripe "); + bch2_csum_err_msg(&err, v->csum_type, want, got); prt_printf(&err, " for %ps at %u of\n ", (void *) _RET_IP_, i); bch2_bkey_val_to_text(&err, c, bkey_i_to_s_c(&buf->key)); bch_err_ratelimited(ca, "%s", err.buf); diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h index f4369b02e805f..f042616888b0a 100644 --- a/fs/bcachefs/ec.h +++ b/fs/bcachefs/ec.h @@ -32,6 +32,8 @@ static inline unsigned stripe_csums_per_device(const struct bch_stripe *s) static inline unsigned stripe_csum_offset(const struct bch_stripe *s, unsigned dev, unsigned csum_idx) { + EBUG_ON(s->csum_type >= BCH_CSUM_NR); + unsigned csum_bytes = bch_crc_bytes[s->csum_type]; return sizeof(struct bch_stripe) + diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 0e3ca99fbd2de..1a331e5392048 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -998,7 +998,9 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struc prt_str(out, " cached"); if (ptr->unwritten) prt_str(out, " unwritten"); - if (ca && ptr_stale(ca, ptr)) + if (b >= ca->mi.first_bucket && + b < ca->mi.nbuckets && + ptr_stale(ca, ptr)) prt_printf(out, " stale"); } } @@ -1028,11 +1030,12 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct bch_extent_crc_unpacked crc = bch2_extent_crc_unpack(k.k, entry_to_crc(entry)); - prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum %s compress ", + prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum ", crc.compressed_size, crc.uncompressed_size, - crc.offset, crc.nonce, - bch2_csum_types[crc.csum_type]); + crc.offset, crc.nonce); + bch2_prt_csum_type(out, crc.csum_type); + prt_str(out, " compress "); bch2_prt_compression_type(out, crc.compression_type); break; } diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index f49e6c0f0f683..b889370a50881 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -387,6 +387,8 @@ static __always_inline long bch2_dio_write_done(struct dio_write *dio) ret = dio->op.error ?: ((long) dio->written << 9); bio_put(&dio->op.wbio.bio); + bch2_write_ref_put(dio->op.c, BCH_WRITE_REF_dio_write); + /* inode->i_dio_count is our ref on inode and thus bch_fs */ inode_dio_end(&inode->v); @@ -590,22 +592,25 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) prefetch(&inode->ei_inode); prefetch((void *) &inode->ei_inode + 64); + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_dio_write)) + return -EROFS; + inode_lock(&inode->v); ret = generic_write_checks(req, iter); if (unlikely(ret <= 0)) - goto err; + goto err_put_write_ref; ret = file_remove_privs(file); if (unlikely(ret)) - goto err; + goto err_put_write_ref; ret = file_update_time(file); if (unlikely(ret)) - goto err; + goto err_put_write_ref; if (unlikely((req->ki_pos|iter->count) & (block_bytes(c) - 1))) - goto err; + goto err_put_write_ref; inode_dio_begin(&inode->v); bch2_pagecache_block_get(inode); @@ -645,7 +650,7 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) } ret = bch2_dio_write_loop(dio); -err: +out: if (locked) inode_unlock(&inode->v); return ret; @@ -653,7 +658,9 @@ err_put_bio: bch2_pagecache_block_put(inode); bio_put(bio); inode_dio_end(&inode->v); - goto err; +err_put_write_ref: + bch2_write_ref_put(c, BCH_WRITE_REF_dio_write); + goto out; } void bch2_fs_fs_io_direct_exit(struct bch_fs *c) diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c index 8c70123b6a0c8..20b40477425f4 100644 --- a/fs/bcachefs/fs-io.c +++ b/fs/bcachefs/fs-io.c @@ -174,18 +174,18 @@ void __bch2_i_sectors_acct(struct bch_fs *c, struct bch_inode_info *inode, static int bch2_flush_inode(struct bch_fs *c, struct bch_inode_info *inode) { - struct bch_inode_unpacked u; - int ret; - if (c->opts.journal_flush_disabled) return 0; - ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u); - if (ret) - return ret; + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) + return -EROFS; - return bch2_journal_flush_seq(&c->journal, u.bi_journal_seq) ?: - bch2_inode_flush_nocow_writes(c, inode); + struct bch_inode_unpacked u; + int ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u) ?: + bch2_journal_flush_seq(&c->journal, u.bi_journal_seq) ?: + bch2_inode_flush_nocow_writes(c, inode); + bch2_write_ref_put(c, BCH_WRITE_REF_fsync); + return ret; } int bch2_fsync(struct file *file, loff_t start, loff_t end, int datasync) diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 725fcf46f6312..9aa28b52ab926 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -247,7 +247,7 @@ static void journal_entry_err_msg(struct printbuf *out, if (entry) { prt_str(out, " type="); - prt_str(out, bch2_jset_entry_types[entry->type]); + bch2_prt_jset_entry_type(out, entry->type); } if (!jset) { @@ -403,7 +403,8 @@ static void journal_entry_btree_keys_to_text(struct printbuf *out, struct bch_fs jset_entry_for_each_key(entry, k) { if (!first) { prt_newline(out); - prt_printf(out, "%s: ", bch2_jset_entry_types[entry->type]); + bch2_prt_jset_entry_type(out, entry->type); + prt_str(out, ": "); } prt_printf(out, "btree=%s l=%u ", bch2_btree_id_str(entry->btree_id), entry->level); bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(k)); @@ -563,9 +564,9 @@ static void journal_entry_usage_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry_usage *u = container_of(entry, struct jset_entry_usage, entry); - prt_printf(out, "type=%s v=%llu", - bch2_fs_usage_types[u->entry.btree_id], - le64_to_cpu(u->v)); + prt_str(out, "type="); + bch2_prt_fs_usage_type(out, u->entry.btree_id); + prt_printf(out, " v=%llu", le64_to_cpu(u->v)); } static int journal_entry_data_usage_validate(struct bch_fs *c, @@ -827,11 +828,11 @@ int bch2_journal_entry_validate(struct bch_fs *c, void bch2_journal_entry_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { + bch2_prt_jset_entry_type(out, entry->type); + if (entry->type < BCH_JSET_ENTRY_NR) { - prt_printf(out, "%s: ", bch2_jset_entry_types[entry->type]); + prt_str(out, ": "); bch2_jset_entry_ops[entry->type].to_text(out, c, entry); - } else { - prt_printf(out, "(unknown type %u)", entry->type); } } diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c index e1800c4119b5f..bb068fd724656 100644 --- a/fs/bcachefs/opts.c +++ b/fs/bcachefs/opts.c @@ -43,7 +43,7 @@ const char * const __bch2_btree_ids[] = { NULL }; -const char * const bch2_csum_types[] = { +static const char * const __bch2_csum_types[] = { BCH_CSUM_TYPES() NULL }; @@ -53,7 +53,7 @@ const char * const bch2_csum_opts[] = { NULL }; -const char * const __bch2_compression_types[] = { +static const char * const __bch2_compression_types[] = { BCH_COMPRESSION_TYPES() NULL }; @@ -83,18 +83,39 @@ const char * const bch2_member_states[] = { NULL }; -const char * const bch2_jset_entry_types[] = { +static const char * const __bch2_jset_entry_types[] = { BCH_JSET_ENTRY_TYPES() NULL }; -const char * const bch2_fs_usage_types[] = { +static const char * const __bch2_fs_usage_types[] = { BCH_FS_USAGE_TYPES() NULL }; #undef x +static void prt_str_opt_boundscheck(struct printbuf *out, const char * const opts[], + unsigned nr, const char *type, unsigned idx) +{ + if (idx < nr) + prt_str(out, opts[idx]); + else + prt_printf(out, "(unknown %s %u)", type, idx); +} + +#define PRT_STR_OPT_BOUNDSCHECKED(name, type) \ +void bch2_prt_##name(struct printbuf *out, type t) \ +{ \ + prt_str_opt_boundscheck(out, __bch2_##name##s, ARRAY_SIZE(__bch2_##name##s) - 1, #name, t);\ +} + +PRT_STR_OPT_BOUNDSCHECKED(jset_entry_type, enum bch_jset_entry_type); +PRT_STR_OPT_BOUNDSCHECKED(fs_usage_type, enum bch_fs_usage_type); +PRT_STR_OPT_BOUNDSCHECKED(data_type, enum bch_data_type); +PRT_STR_OPT_BOUNDSCHECKED(csum_type, enum bch_csum_type); +PRT_STR_OPT_BOUNDSCHECKED(compression_type, enum bch_compression_type); + static int bch2_opt_fix_errors_parse(struct bch_fs *c, const char *val, u64 *res, struct printbuf *err) { diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 1ac4135cca1c3..84e452835a17d 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -16,18 +16,20 @@ extern const char * const bch2_version_upgrade_opts[]; extern const char * const bch2_sb_features[]; extern const char * const bch2_sb_compat[]; extern const char * const __bch2_btree_ids[]; -extern const char * const bch2_csum_types[]; extern const char * const bch2_csum_opts[]; -extern const char * const __bch2_compression_types[]; extern const char * const bch2_compression_opts[]; extern const char * const bch2_str_hash_types[]; extern const char * const bch2_str_hash_opts[]; extern const char * const __bch2_data_types[]; extern const char * const bch2_member_states[]; -extern const char * const bch2_jset_entry_types[]; -extern const char * const bch2_fs_usage_types[]; extern const char * const bch2_d_types[]; +void bch2_prt_jset_entry_type(struct printbuf *, enum bch_jset_entry_type); +void bch2_prt_fs_usage_type(struct printbuf *, enum bch_fs_usage_type); +void bch2_prt_data_type(struct printbuf *, enum bch_data_type); +void bch2_prt_csum_type(struct printbuf *, enum bch_csum_type); +void bch2_prt_compression_type(struct printbuf *, enum bch_compression_type); + static inline const char *bch2_d_type_str(unsigned d_type) { return (d_type < BCH_DT_MAX ? bch2_d_types[d_type] : NULL) ?: "(bad d_type)"; diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c index cb501460d6152..0cec0f7d97035 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -44,7 +44,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c) set_bit(BCH_FS_may_go_rw, &c->flags); - if (keys->nr || c->opts.fsck || !c->sb.clean) + if (keys->nr || c->opts.fsck || !c->sb.clean || c->recovery_passes_explicit) return bch2_fs_read_write_early(c); return 0; } diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index d6f81179c3a29..a98ef940b7a32 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -51,7 +51,10 @@ BCH_FSCK_ERR_subvol_fs_path_parent_wrong) \ x(btree_subvolume_children, \ BIT_ULL(BCH_RECOVERY_PASS_check_subvols), \ - BCH_FSCK_ERR_subvol_children_not_set) + BCH_FSCK_ERR_subvol_children_not_set) \ + x(mi_btree_bitmap, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_btree_bitmap_not_marked) #define DOWNGRADE_TABLE() diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index d7d609131030a..4ca6e7b0d8aae 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -130,7 +130,7 @@ x(bucket_gens_nonzero_for_invalid_buckets, 122) \ x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ x(need_discard_freespace_key_bad, 124) \ - x(backpointer_pos_wrong, 125) \ + x(backpointer_bucket_offset_wrong, 125) \ x(backpointer_to_missing_device, 126) \ x(backpointer_to_missing_alloc, 127) \ x(backpointer_to_missing_ptr, 128) \ @@ -270,7 +270,8 @@ x(btree_ptr_v2_min_key_bad, 262) \ x(btree_root_unreadable_and_scan_found_nothing, 263) \ x(snapshot_node_missing, 264) \ - x(dup_backpointer_to_bad_csum_extent, 265) + x(dup_backpointer_to_bad_csum_extent, 265) \ + x(btree_bitmap_not_marked, 266) enum bch_sb_error_id { #define x(t, n) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c index eff5ce18c69c0..522a969345e52 100644 --- a/fs/bcachefs/sb-members.c +++ b/fs/bcachefs/sb-members.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" +#include "btree_cache.h" #include "disk_groups.h" #include "opts.h" #include "replicas.h" @@ -426,3 +427,55 @@ void bch2_dev_errors_reset(struct bch_dev *ca) bch2_write_super(c); mutex_unlock(&c->sb_lock); } + +/* + * Per member "range has btree nodes" bitmap: + * + * This is so that if we ever have to run the btree node scan to repair we don't + * have to scan full devices: + */ + +bool bch2_dev_btree_bitmap_marked(struct bch_fs *c, struct bkey_s_c k) +{ + bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) + if (!bch2_dev_btree_bitmap_marked_sectors(bch_dev_bkey_exists(c, ptr->dev), + ptr->offset, btree_sectors(c))) + return false; + return true; +} + +static void __bch2_dev_btree_bitmap_mark(struct bch_sb_field_members_v2 *mi, unsigned dev, + u64 start, unsigned sectors) +{ + struct bch_member *m = __bch2_members_v2_get_mut(mi, dev); + u64 bitmap = le64_to_cpu(m->btree_allocated_bitmap); + + u64 end = start + sectors; + + int resize = ilog2(roundup_pow_of_two(end)) - (m->btree_bitmap_shift + 6); + if (resize > 0) { + u64 new_bitmap = 0; + + for (unsigned i = 0; i < 64; i++) + if (bitmap & BIT_ULL(i)) + new_bitmap |= BIT_ULL(i >> resize); + bitmap = new_bitmap; + m->btree_bitmap_shift += resize; + } + + for (unsigned bit = sectors >> m->btree_bitmap_shift; + bit << m->btree_bitmap_shift < end; + bit++) + bitmap |= BIT_ULL(bit); + + m->btree_allocated_bitmap = cpu_to_le64(bitmap); +} + +void bch2_dev_btree_bitmap_mark(struct bch_fs *c, struct bkey_s_c k) +{ + lockdep_assert_held(&c->sb_lock); + + struct bch_sb_field_members_v2 *mi = bch2_sb_field_get(c->disk_sb.sb, members_v2); + bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) + __bch2_dev_btree_bitmap_mark(mi, ptr->dev, ptr->offset, btree_sectors(c)); +} diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h index be0a941832715..b27c3e4467cf2 100644 --- a/fs/bcachefs/sb-members.h +++ b/fs/bcachefs/sb-members.h @@ -3,6 +3,7 @@ #define _BCACHEFS_SB_MEMBERS_H #include "darray.h" +#include "bkey_types.h" extern char * const bch2_member_error_strs[]; @@ -220,6 +221,8 @@ static inline struct bch_member_cpu bch2_mi_to_cpu(struct bch_member *mi) : 1, .freespace_initialized = BCH_MEMBER_FREESPACE_INITIALIZED(mi), .valid = bch2_member_exists(mi), + .btree_bitmap_shift = mi->btree_bitmap_shift, + .btree_allocated_bitmap = le64_to_cpu(mi->btree_allocated_bitmap), }; } @@ -228,4 +231,22 @@ void bch2_sb_members_from_cpu(struct bch_fs *); void bch2_dev_io_errors_to_text(struct printbuf *, struct bch_dev *); void bch2_dev_errors_reset(struct bch_dev *); +static inline bool bch2_dev_btree_bitmap_marked_sectors(struct bch_dev *ca, u64 start, unsigned sectors) +{ + u64 end = start + sectors; + + if (end > 64 << ca->mi.btree_bitmap_shift) + return false; + + for (unsigned bit = sectors >> ca->mi.btree_bitmap_shift; + bit << ca->mi.btree_bitmap_shift < end; + bit++) + if (!(ca->mi.btree_allocated_bitmap & BIT_ULL(bit))) + return false; + return true; +} + +bool bch2_dev_btree_bitmap_marked(struct bch_fs *, struct bkey_s_c); +void bch2_dev_btree_bitmap_mark(struct bch_fs *, struct bkey_s_c); + #endif /* _BCACHEFS_SB_MEMBERS_H */ diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index 5eee055ee2721..08ea3dbbbe97c 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -700,8 +700,11 @@ retry: return -ENOMEM; sb->sb_name = kstrdup(path, GFP_KERNEL); - if (!sb->sb_name) - return -ENOMEM; + if (!sb->sb_name) { + ret = -ENOMEM; + prt_printf(&err, "error allocating memory for sb_name"); + goto err; + } #ifndef __KERNEL__ if (opt_get(*opts, direct_io) == false) diff --git a/fs/bcachefs/super_types.h b/fs/bcachefs/super_types.h index ec784d975f665..11bcef170c2c2 100644 --- a/fs/bcachefs/super_types.h +++ b/fs/bcachefs/super_types.h @@ -37,6 +37,8 @@ struct bch_member_cpu { u8 durability; u8 freespace_initialized; u8 valid; + u8 btree_bitmap_shift; + u64 btree_allocated_bitmap; }; #endif /* _BCACHEFS_SUPER_TYPES_H */ diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index b18b0cc81b594..5be92fe3f4ea4 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -25,6 +25,7 @@ #include "ec.h" #include "inode.h" #include "journal.h" +#include "journal_reclaim.h" #include "keylist.h" #include "move.h" #include "movinggc.h" @@ -138,6 +139,7 @@ do { \ write_attribute(trigger_gc); write_attribute(trigger_discards); write_attribute(trigger_invalidates); +write_attribute(trigger_journal_flush); write_attribute(prune_cache); write_attribute(btree_wakeup); rw_attribute(btree_gc_periodic); @@ -500,7 +502,7 @@ STORE(bch2_fs) /* Debugging: */ - if (!test_bit(BCH_FS_rw, &c->flags)) + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_sysfs)) return -EROFS; if (attr == &sysfs_prune_cache) { @@ -533,6 +535,11 @@ STORE(bch2_fs) if (attr == &sysfs_trigger_invalidates) bch2_do_invalidates(c); + if (attr == &sysfs_trigger_journal_flush) { + bch2_journal_flush_all_pins(&c->journal); + bch2_journal_meta(&c->journal); + } + #ifdef CONFIG_BCACHEFS_TESTS if (attr == &sysfs_perf_test) { char *tmp = kstrdup(buf, GFP_KERNEL), *p = tmp; @@ -553,6 +560,7 @@ STORE(bch2_fs) size = ret; } #endif + bch2_write_ref_put(c, BCH_WRITE_REF_sysfs); return size; } SYSFS_OPS(bch2_fs); @@ -651,6 +659,7 @@ struct attribute *bch2_fs_internal_files[] = { &sysfs_trigger_gc, &sysfs_trigger_discards, &sysfs_trigger_invalidates, + &sysfs_trigger_journal_flush, &sysfs_prune_cache, &sysfs_btree_wakeup, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index beedd6ed64d39..257d044bca915 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3464,6 +3464,14 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (root_id != BTRFS_TREE_LOG_OBJECTID) { struct btrfs_ref generic_ref = { 0 }; + /* + * Assert that the extent buffer is not cleared due to + * EXTENT_BUFFER_ZONED_ZEROOUT. Please refer + * btrfs_clear_buffer_dirty() and btree_csum_one_bio() for + * detail. + */ + ASSERT(btrfs_header_bytenr(buf) != 0); + btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, buf->start, buf->len, parent, btrfs_header_owner(buf)); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 61594eaf1f896..2776112dbdf8d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -681,31 +681,21 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, gfp_t extra_gfp) { + const gfp_t gfp = GFP_NOFS | extra_gfp; unsigned int allocated; for (allocated = 0; allocated < nr_pages;) { unsigned int last = allocated; - allocated = alloc_pages_bulk_array(GFP_NOFS | extra_gfp, - nr_pages, page_array); - - if (allocated == nr_pages) - return 0; - - /* - * During this iteration, no page could be allocated, even - * though alloc_pages_bulk_array() falls back to alloc_page() - * if it could not bulk-allocate. So we must be out of memory. - */ - if (allocated == last) { + allocated = alloc_pages_bulk_array(gfp, nr_pages, page_array); + if (unlikely(allocated == last)) { + /* No progress, fail and do cleanup. */ for (int i = 0; i < allocated; i++) { __free_page(page_array[i]); page_array[i] = NULL; } return -ENOMEM; } - - memalloc_retry_wait(GFP_NOFS); } return 0; } @@ -4154,7 +4144,7 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans, * The actual zeroout of the buffer will happen later in * btree_csum_one_bio. */ - if (btrfs_is_zoned(fs_info)) { + if (btrfs_is_zoned(fs_info) && test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { set_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags); return; } @@ -4193,6 +4183,7 @@ void set_extent_buffer_dirty(struct extent_buffer *eb) num_folios = num_extent_folios(eb); WARN_ON(atomic_read(&eb->refs) == 0); WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)); + WARN_ON(test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags)); if (!was_dirty) { bool subpage = eb->fs_info->nodesize < PAGE_SIZE; diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index b6cad106c37e4..0b2da7b7e2ad0 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -310,6 +310,10 @@ struct cuse_init_args { /** * cuse_process_init_reply - finish initializing CUSE channel * + * @fm: The fuse mount information containing the CUSE connection. + * @args: The arguments passed to the init reply. + * @error: The error code signifying if any error occurred during the process. + * * This function creates the character device and sets up all the * required data structures for it. Please read the comment at the * top of this file for high level overview. diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4a6df591add61..2b0d4781f3948 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1321,6 +1321,7 @@ retry: err = fuse_do_statx(inode, file, stat); if (err == -ENOSYS) { fc->no_statx = 1; + err = 0; goto retry; } } else { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a56e7bffd0004..b57ce41576407 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1362,7 +1362,7 @@ static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, bool *exclusive) { struct inode *inode = file_inode(iocb->ki_filp); - struct fuse_file *ff = iocb->ki_filp->private_data; + struct fuse_inode *fi = get_fuse_inode(inode); *exclusive = fuse_dio_wr_exclusive_lock(iocb, from); if (*exclusive) { @@ -1377,7 +1377,7 @@ static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, * have raced, so check it again. */ if (fuse_io_past_eof(iocb, from) || - fuse_file_uncached_io_start(inode, ff, NULL) != 0) { + fuse_inode_uncached_io_start(fi, NULL) != 0) { inode_unlock_shared(inode); inode_lock(inode); *exclusive = true; @@ -1388,13 +1388,13 @@ static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive) { struct inode *inode = file_inode(iocb->ki_filp); - struct fuse_file *ff = iocb->ki_filp->private_data; + struct fuse_inode *fi = get_fuse_inode(inode); if (exclusive) { inode_unlock(inode); } else { /* Allow opens in caching mode after last parallel dio end */ - fuse_file_uncached_io_end(inode, ff); + fuse_inode_uncached_io_end(fi); inode_unlock_shared(inode); } } @@ -2574,8 +2574,10 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) * First mmap of direct_io file enters caching inode io mode. * Also waits for parallel dio writers to go into serial mode * (exclusive instead of shared lock). + * After first mmap, the inode stays in caching io mode until + * the direct_io file release. */ - rc = fuse_file_cached_io_start(inode, ff); + rc = fuse_file_cached_io_open(inode, ff); if (rc) return rc; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index b24084b60864e..f239196103137 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1394,9 +1394,10 @@ int fuse_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); /* iomode.c */ -int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff); -int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb); -void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff); +int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff); +int fuse_inode_uncached_io_start(struct fuse_inode *fi, + struct fuse_backing *fb); +void fuse_inode_uncached_io_end(struct fuse_inode *fi); int fuse_file_io_open(struct file *file, struct inode *inode); void fuse_file_io_release(struct fuse_file *ff, struct inode *inode); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 3a5d888783353..99e44ea7d8756 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -175,6 +175,7 @@ static void fuse_evict_inode(struct inode *inode) } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { + WARN_ON(fi->iocachectr != 0); WARN_ON(!list_empty(&fi->write_files)); WARN_ON(!list_empty(&fi->queued_writes)); } diff --git a/fs/fuse/iomode.c b/fs/fuse/iomode.c index c653ddcf05787..c99e285f3183e 100644 --- a/fs/fuse/iomode.c +++ b/fs/fuse/iomode.c @@ -21,12 +21,13 @@ static inline bool fuse_is_io_cache_wait(struct fuse_inode *fi) } /* - * Start cached io mode. + * Called on cached file open() and on first mmap() of direct_io file. + * Takes cached_io inode mode reference to be dropped on file release. * * Blocks new parallel dio writes and waits for the in-progress parallel dio * writes to complete. */ -int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff) +int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -67,10 +68,9 @@ int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff) return 0; } -static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff) +static void fuse_file_cached_io_release(struct fuse_file *ff, + struct fuse_inode *fi) { - struct fuse_inode *fi = get_fuse_inode(inode); - spin_lock(&fi->lock); WARN_ON(fi->iocachectr <= 0); WARN_ON(ff->iomode != IOM_CACHED); @@ -82,16 +82,15 @@ static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff) } /* Start strictly uncached io mode where cache access is not allowed */ -int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb) +int fuse_inode_uncached_io_start(struct fuse_inode *fi, struct fuse_backing *fb) { - struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_backing *oldfb; int err = 0; spin_lock(&fi->lock); /* deny conflicting backing files on same fuse inode */ oldfb = fuse_inode_backing(fi); - if (oldfb && oldfb != fb) { + if (fb && oldfb && oldfb != fb) { err = -EBUSY; goto unlock; } @@ -99,12 +98,10 @@ int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struc err = -ETXTBSY; goto unlock; } - WARN_ON(ff->iomode != IOM_NONE); fi->iocachectr--; - ff->iomode = IOM_UNCACHED; /* fuse inode holds a single refcount of backing file */ - if (!oldfb) { + if (fb && !oldfb) { oldfb = fuse_inode_backing_set(fi, fb); WARN_ON_ONCE(oldfb != NULL); } else { @@ -115,15 +112,29 @@ unlock: return err; } -void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff) +/* Takes uncached_io inode mode reference to be dropped on file release */ +static int fuse_file_uncached_io_open(struct inode *inode, + struct fuse_file *ff, + struct fuse_backing *fb) { struct fuse_inode *fi = get_fuse_inode(inode); + int err; + + err = fuse_inode_uncached_io_start(fi, fb); + if (err) + return err; + + WARN_ON(ff->iomode != IOM_NONE); + ff->iomode = IOM_UNCACHED; + return 0; +} + +void fuse_inode_uncached_io_end(struct fuse_inode *fi) +{ struct fuse_backing *oldfb = NULL; spin_lock(&fi->lock); WARN_ON(fi->iocachectr >= 0); - WARN_ON(ff->iomode != IOM_UNCACHED); - ff->iomode = IOM_NONE; fi->iocachectr++; if (!fi->iocachectr) { wake_up(&fi->direct_io_waitq); @@ -134,6 +145,15 @@ void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff) fuse_backing_put(oldfb); } +/* Drop uncached_io reference from passthrough open */ +static void fuse_file_uncached_io_release(struct fuse_file *ff, + struct fuse_inode *fi) +{ + WARN_ON(ff->iomode != IOM_UNCACHED); + ff->iomode = IOM_NONE; + fuse_inode_uncached_io_end(fi); +} + /* * Open flags that are allowed in combination with FOPEN_PASSTHROUGH. * A combination of FOPEN_PASSTHROUGH and FOPEN_DIRECT_IO means that read/write @@ -163,7 +183,7 @@ static int fuse_file_passthrough_open(struct inode *inode, struct file *file) return PTR_ERR(fb); /* First passthrough file open denies caching inode io mode */ - err = fuse_file_uncached_io_start(inode, ff, fb); + err = fuse_file_uncached_io_open(inode, ff, fb); if (!err) return 0; @@ -216,7 +236,7 @@ int fuse_file_io_open(struct file *file, struct inode *inode) if (ff->open_flags & FOPEN_PASSTHROUGH) err = fuse_file_passthrough_open(inode, file); else - err = fuse_file_cached_io_start(inode, ff); + err = fuse_file_cached_io_open(inode, ff); if (err) goto fail; @@ -236,8 +256,10 @@ fail: /* No more pending io and no new io possible to inode via open/mmapped file */ void fuse_file_io_release(struct fuse_file *ff, struct inode *inode) { + struct fuse_inode *fi = get_fuse_inode(inode); + /* - * Last parallel dio close allows caching inode io mode. + * Last passthrough file close allows caching inode io mode. * Last caching file close exits caching inode io mode. */ switch (ff->iomode) { @@ -245,10 +267,10 @@ void fuse_file_io_release(struct fuse_file *ff, struct inode *inode) /* Nothing to do */ break; case IOM_UNCACHED: - fuse_file_uncached_io_end(inode, ff); + fuse_file_uncached_io_release(ff, fi); break; case IOM_CACHED: - fuse_file_cached_io_end(inode, ff); + fuse_file_cached_io_release(ff, fi); break; } } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index fac938f563ad0..1955481832e03 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3490,11 +3490,13 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct dentry *dentry, const u32 *bmval, int ignore_crossmnt) { + DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); struct nfsd4_fattr_args args; struct svc_fh *tempfh = NULL; int starting_len = xdr->buf->len; __be32 *attrlen_p, status; int attrlen_offset; + u32 attrmask[3]; int err; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; @@ -3502,10 +3504,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, .mnt = exp->ex_path.mnt, .dentry = dentry, }; - union { - u32 attrmask[3]; - unsigned long mask[2]; - } u; unsigned long bit; bool file_modified = false; u64 size = 0; @@ -3521,20 +3519,19 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, /* * Make a local copy of the attribute bitmap that can be modified. */ - memset(&u, 0, sizeof(u)); - u.attrmask[0] = bmval[0]; - u.attrmask[1] = bmval[1]; - u.attrmask[2] = bmval[2]; + attrmask[0] = bmval[0]; + attrmask[1] = bmval[1]; + attrmask[2] = bmval[2]; args.rdattr_err = 0; if (exp->ex_fslocs.migrated) { - status = fattr_handle_absent_fs(&u.attrmask[0], &u.attrmask[1], - &u.attrmask[2], &args.rdattr_err); + status = fattr_handle_absent_fs(&attrmask[0], &attrmask[1], + &attrmask[2], &args.rdattr_err); if (status) goto out; } args.size = 0; - if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { + if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry), &file_modified, &size); if (status) @@ -3553,16 +3550,16 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (!(args.stat.result_mask & STATX_BTIME)) /* underlying FS does not offer btime so we can't share it */ - u.attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; - if ((u.attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; + if ((attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || - (u.attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | + (attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { err = vfs_statfs(&path, &args.statfs); if (err) goto out_nfserr; } - if ((u.attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && + if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) { tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); status = nfserr_jukebox; @@ -3577,10 +3574,10 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.fhp = fhp; args.acl = NULL; - if (u.attrmask[0] & FATTR4_WORD0_ACL) { + if (attrmask[0] & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) - u.attrmask[0] &= ~FATTR4_WORD0_ACL; + attrmask[0] &= ~FATTR4_WORD0_ACL; else if (err == -EINVAL) { status = nfserr_attrnotsupp; goto out; @@ -3592,17 +3589,17 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, #ifdef CONFIG_NFSD_V4_SECURITY_LABEL args.context = NULL; - if ((u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || - u.attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || + attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), &args.context, &args.contextlen); else err = -EOPNOTSUPP; args.contextsupport = (err == 0); - if (u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { if (err == -EOPNOTSUPP) - u.attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; else if (err) goto out_nfserr; } @@ -3610,8 +3607,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ /* attrmask */ - status = nfsd4_encode_bitmap4(xdr, u.attrmask[0], - u.attrmask[1], u.attrmask[2]); + status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1], + attrmask[2]); if (status) goto out; @@ -3620,7 +3617,9 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); if (!attrlen_p) goto out_resource; - for_each_set_bit(bit, (const unsigned long *)&u.mask, + bitmap_from_arr32(attr_bitmap, attrmask, + ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); + for_each_set_bit(bit, attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) { status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args); if (status != nfs_ok) diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index bc846b904b68d..aee40db7a036f 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -240,7 +240,7 @@ nilfs_filetype_table[NILFS_FT_MAX] = { #define S_SHIFT 12 static unsigned char -nilfs_type_by_mode[S_IFMT >> S_SHIFT] = { +nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = NILFS_FT_DIR, [S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV, diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index aa3411354e66d..16bd693d0b3aa 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -48,6 +48,10 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, gid_t i_gid; int err; + inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); + if (inode->i_ino == 0) + return -EINVAL; + err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid); if (err) return err; @@ -58,7 +62,6 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); - inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0); inode_set_atime(inode, inode_get_mtime_sec(inode), 0); inode_set_ctime(inode, inode_get_mtime_sec(inode), 0); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 172c918799995..69e7da33ca49a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -128,6 +128,8 @@ typedef unsigned int __bitwise blk_mode_t; #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) /* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ #define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) +/* return partition scanning errors */ +#define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index e5ee2c694401e..3f4b4ac527ca2 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -288,7 +288,12 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ -void __init xbc_exit(void); +void __init _xbc_exit(bool early); + +static inline void xbc_exit(void) +{ + _xbc_exit(false); +} /* XBC embedded bootconfig data in kernel */ #ifdef CONFIG_BOOT_CONFIG_EMBED diff --git a/include/linux/clk.h b/include/linux/clk.h index 00623f4de5e19..0fa56d6725321 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -286,6 +286,11 @@ static inline int clk_rate_exclusive_get(struct clk *clk) return 0; } +static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk) +{ + return 0; +} + static inline void clk_rate_exclusive_put(struct clk *clk) {} #endif diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h index 6c75c8bd44a0b..1a14e239221f7 100644 --- a/include/linux/gpio/property.h +++ b/include/linux/gpio/property.h @@ -2,7 +2,6 @@ #ifndef __LINUX_GPIO_PROPERTY_H #define __LINUX_GPIO_PROPERTY_H -#include <dt-bindings/gpio/gpio.h> /* for GPIO_* flags */ #include <linux/property.h> #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a4c15db2f5e54..3fb18f7eb73ea 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -110,8 +110,17 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#else +static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags) +{ + return false; +} +#endif + #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); #else diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 48b700ba1d188..a5c560a2f8c25 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -390,6 +390,35 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) } #endif /* CONFIG_MIGRATION */ +#ifdef CONFIG_MEMORY_FAILURE + +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} + +#else + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} +#endif + typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) @@ -483,8 +512,9 @@ static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) /* * A pfn swap entry is a special type of swap entry that always has a pfn stored - * in the swap offset. They are used to represent unaddressable device memory - * and to restrict access to a page undergoing migration. + * in the swap offset. They can either be used to represent unaddressable device + * memory, to restrict access to a page undergoing migration or to represent a + * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { @@ -492,7 +522,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || - is_device_exclusive_entry(entry); + is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; @@ -561,35 +591,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd) } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ -#ifdef CONFIG_MEMORY_FAILURE - -/* - * Support for hardware poisoned pages - */ -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - BUG_ON(!PageLocked(page)); - return swp_entry(SWP_HWPOISON, page_to_pfn(page)); -} - -static inline int is_hwpoison_entry(swp_entry_t entry) -{ - return swp_type(entry) == SWP_HWPOISON; -} - -#else - -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - return swp_entry(0, 0); -} - -static inline int is_hwpoison_entry(swp_entry_t swp) -{ - return 0; -} -#endif - static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; diff --git a/include/linux/udp.h b/include/linux/udp.h index 17539d0896661..e398e1dbd2d36 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -108,7 +108,7 @@ struct udp_sock { #define udp_assign_bit(nr, sk, val) \ assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index a763dd327c6ea..9abb7ee40d72f 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -336,7 +336,7 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); -static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) { __be16 proto; @@ -352,6 +352,16 @@ static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) return 0; } +static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) +{ + if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + return false; + + *inner_proto = __nf_flow_pppoe_proto(skb); + + return true; +} + #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e27c28b612e46..3f1ed467f951f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -307,9 +307,23 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) return (void *)priv; } + +/** + * enum nft_iter_type - nftables set iterator type + * + * @NFT_ITER_READ: read-only iteration over set elements + * @NFT_ITER_UPDATE: iteration under mutex to update set element state + */ +enum nft_iter_type { + NFT_ITER_UNSPEC, + NFT_ITER_READ, + NFT_ITER_UPDATE, +}; + struct nft_set; struct nft_set_iter { u8 genmask; + enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index cefe0c4bdae34..41ca14e81d55f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -117,6 +117,7 @@ struct Qdisc { struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; + int owner; unsigned long state; unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index ba2d96a1bc2f9..f50fcafc69de2 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -609,7 +609,7 @@ TRACE_EVENT(rpcgss_context, __field(unsigned int, timeout) __field(u32, window_size) __field(int, len) - __string(acceptor, data) + __string_len(acceptor, data, len) ), TP_fast_assign( @@ -618,7 +618,7 @@ TRACE_EVENT(rpcgss_context, __entry->timeout = timeout; __entry->window_size = window_size; __entry->len = len; - strncpy(__get_str(acceptor), data, len); + __assign_str(acceptor, data); ), TP_printk("win_size=%u expiry=%lu now=%lu timeout=%u acceptor=%.*s", diff --git a/init/main.c b/init/main.c index 881f6230ee59e..5dcf5274c09c7 100644 --- a/init/main.c +++ b/init/main.c @@ -636,6 +636,8 @@ static void __init setup_command_line(char *command_line) if (!saved_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen); + len = xlen + strlen(command_line) + 1; + static_command_line = memblock_alloc(len, SMP_CACHE_BYTES); if (!static_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len); diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config index 7a5bbfc024b7d..4b4cfcba31901 100644 --- a/kernel/configs/hardening.config +++ b/kernel/configs/hardening.config @@ -39,11 +39,12 @@ CONFIG_UBSAN=y CONFIG_UBSAN_TRAP=y CONFIG_UBSAN_BOUNDS=y # CONFIG_UBSAN_SHIFT is not set -# CONFIG_UBSAN_DIV_ZERO -# CONFIG_UBSAN_UNREACHABLE -# CONFIG_UBSAN_BOOL -# CONFIG_UBSAN_ENUM -# CONFIG_UBSAN_ALIGNMENT +# CONFIG_UBSAN_DIV_ZERO is not set +# CONFIG_UBSAN_UNREACHABLE is not set +# CONFIG_UBSAN_SIGNED_WRAP is not set +# CONFIG_UBSAN_BOOL is not set +# CONFIG_UBSAN_ENUM is not set +# CONFIG_UBSAN_ALIGNMENT is not set # Sampling-based heap out-of-bounds and use-after-free detection. CONFIG_KFENCE=y diff --git a/kernel/fork.c b/kernel/fork.c index 39a5046c2f0bf..aebb3e6c96dc6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -714,6 +714,23 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); + /* + * Copy/update hugetlb private vma information. + */ + if (is_vm_hugetlb_page(tmp)) + hugetlb_dup_vma_private(tmp); + + /* + * Link the vma into the MT. After using __mt_dup(), memory + * allocation is not necessary here, so it cannot fail. + */ + vma_iter_bulk_store(&vmi, tmp); + + mm->map_count++; + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; @@ -730,25 +747,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, i_mmap_unlock_write(mapping); } - /* - * Copy/update hugetlb private vma information. - */ - if (is_vm_hugetlb_page(tmp)) - hugetlb_dup_vma_private(tmp); - - /* - * Link the vma into the MT. After using __mt_dup(), memory - * allocation is not necessary here, so it cannot fail. - */ - vma_iter_bulk_store(&vmi, tmp); - - mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); - if (tmp->vm_ops && tmp->vm_ops->open) - tmp->vm_ops->open(tmp); - if (retval) { mpnt = vma_next(&vmi); goto loop_out; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index c59d26068a640..97f8911ea339e 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -61,9 +61,12 @@ static inline void * __init xbc_alloc_mem(size_t size) return memblock_alloc(size, SMP_CACHE_BYTES); } -static inline void __init xbc_free_mem(void *addr, size_t size) +static inline void __init xbc_free_mem(void *addr, size_t size, bool early) { - memblock_free(addr, size); + if (early) + memblock_free(addr, size); + else if (addr) + memblock_free_late(__pa(addr), size); } #else /* !__KERNEL__ */ @@ -73,7 +76,7 @@ static inline void *xbc_alloc_mem(size_t size) return malloc(size); } -static inline void xbc_free_mem(void *addr, size_t size) +static inline void xbc_free_mem(void *addr, size_t size, bool early) { free(addr); } @@ -898,19 +901,20 @@ static int __init xbc_parse_tree(void) } /** - * xbc_exit() - Clean up all parsed bootconfig + * _xbc_exit() - Clean up all parsed bootconfig + * @early: Set true if this is called before budy system is initialized. * * This clears all data structures of parsed bootconfig on memory. * If you need to reuse xbc_init() with new boot config, you can * use this. */ -void __init xbc_exit(void) +void __init _xbc_exit(bool early) { - xbc_free_mem(xbc_data, xbc_data_size); + xbc_free_mem(xbc_data, xbc_data_size, early); xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); + xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX, early); xbc_nodes = NULL; brace_index = 0; } @@ -963,7 +967,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) if (!xbc_nodes) { if (emsg) *emsg = "Failed to allocate bootconfig nodes"; - xbc_exit(); + _xbc_exit(true); return -ENOMEM; } memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX); @@ -977,7 +981,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) *epos = xbc_err_pos; if (emsg) *emsg = xbc_err_msg; - xbc_exit(); + _xbc_exit(true); } else ret = xbc_node_num; diff --git a/lib/ubsan.c b/lib/ubsan.c index 5fc107f61934c..a1c983d148f16 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -44,9 +44,10 @@ const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type) case ubsan_shift_out_of_bounds: return "UBSAN: shift out of bounds"; #endif -#ifdef CONFIG_UBSAN_DIV_ZERO +#if defined(CONFIG_UBSAN_DIV_ZERO) || defined(CONFIG_UBSAN_SIGNED_WRAP) /* - * SanitizerKind::IntegerDivideByZero emits + * SanitizerKind::IntegerDivideByZero and + * SanitizerKind::SignedIntegerOverflow emit * SanitizerHandler::DivremOverflow. */ case ubsan_divrem_overflow: @@ -78,6 +79,19 @@ const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type) case ubsan_type_mismatch: return "UBSAN: type mismatch"; #endif +#ifdef CONFIG_UBSAN_SIGNED_WRAP + /* + * SanitizerKind::SignedIntegerOverflow emits + * SanitizerHandler::AddOverflow, SanitizerHandler::SubOverflow, + * or SanitizerHandler::MulOverflow. + */ + case ubsan_add_overflow: + return "UBSAN: integer addition overflow"; + case ubsan_sub_overflow: + return "UBSAN: integer subtraction overflow"; + case ubsan_mul_overflow: + return "UBSAN: integer multiplication overflow"; +#endif default: return "UBSAN: unrecognized failure code"; } diff --git a/mm/gup.c b/mm/gup.c index af8edadc05d1b..1611e73b1121b 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1206,6 +1206,22 @@ static long __get_user_pages(struct mm_struct *mm, /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { + /* + * MADV_POPULATE_(READ|WRITE) wants to handle VMA + * lookups+error reporting differently. + */ + if (gup_flags & FOLL_MADV_POPULATE) { + vma = vma_lookup(mm, start); + if (!vma) { + ret = -ENOMEM; + goto out; + } + if (check_vma_flags(vma, gup_flags)) { + ret = -EINVAL; + goto out; + } + goto retry; + } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, @@ -1685,35 +1701,35 @@ long populate_vma_page_range(struct vm_area_struct *vma, } /* - * faultin_vma_page_range() - populate (prefault) page tables inside the - * given VMA range readable/writable + * faultin_page_range() - populate (prefault) page tables inside the + * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * - * @vma: target vma + * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * - * Returns either number of processed pages in the vma, or a negative error - * code on error (see __get_user_pages()). + * Returns either number of processed pages in the MM, or a negative error + * code on error (see __get_user_pages()). Note that this function reports + * errors related to VMAs, such as incompatible mappings, as expected by + * MADV_POPULATE_(READ|WRITE). * - * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and - * covered by the VMA. If it's released, *@locked will be set to 0. + * The range must be page-aligned. + * + * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ -long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, bool write, int *locked) +long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked) { - struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); - VM_BUG_ON_VMA(start < vma->vm_start, vma); - VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* @@ -1725,19 +1741,13 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ - gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE; + gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | + FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; - /* - * We want to report -EINVAL instead of -EFAULT for any permission - * problems or incompatible mappings. - */ - if (check_vma_flags(vma, gup_flags)) - return -EINVAL; - - ret = __get_user_pages(mm, start, nr_pages, gup_flags, - NULL, locked); + ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, + gup_flags); lru_add_drain(); return ret; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9859aa4f75538..89f58c7603b25 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2259,9 +2259,6 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } - folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); - src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { @@ -2270,6 +2267,9 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } + folio_move_anon_rmap(src_folio, dst_vma); + WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 23ef240ba48a6..31d00eee028f1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7044,9 +7044,13 @@ long hugetlb_change_protection(struct vm_area_struct *vma, if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { - /* No other markers apply for now. */ - WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); - if (uffd_wp_resolve) + /* + * Do nothing on a poison marker; page is + * corrupted, permissons do not apply. Here + * pte_marker_uffd_wp()==true implies !poison + * because they're mutual exclusive. + */ + if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { diff --git a/mm/internal.h b/mm/internal.h index 7e486f2c502ce..07ad2675a88b4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -686,9 +686,8 @@ struct anon_vma *folio_anon_vma(struct folio *folio); void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); -extern long faultin_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - bool write, int *locked); +extern long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); @@ -1127,10 +1126,13 @@ enum { FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, + /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ + FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ - FOLL_FAST_ONLY | FOLL_UNLOCKABLE) + FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ + FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, diff --git a/mm/madvise.c b/mm/madvise.c index 44a498c94158c..1a073fcc4c0c0 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -908,27 +908,14 @@ static long madvise_populate(struct vm_area_struct *vma, { const bool write = behavior == MADV_POPULATE_WRITE; struct mm_struct *mm = vma->vm_mm; - unsigned long tmp_end; int locked = 1; long pages; *prev = vma; while (start < end) { - /* - * We might have temporarily dropped the lock. For example, - * our VMA might have been split. - */ - if (!vma || start >= vma->vm_end) { - vma = vma_lookup(mm, start); - if (!vma) - return -ENOMEM; - } - - tmp_end = min_t(unsigned long, end, vma->vm_end); /* Populate (prefault) page tables readable/writable. */ - pages = faultin_vma_page_range(vma, start, tmp_end, write, - &locked); + pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; @@ -949,7 +936,7 @@ static long madvise_populate(struct vm_area_struct *vma, pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; - case -ENOMEM: + case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9349948f1abfd..9e62a00b46dde 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -154,11 +154,23 @@ static int __page_handle_poison(struct page *page) { int ret; - zone_pcp_disable(page_zone(page)); + /* + * zone_pcp_disable() can't be used here. It will + * hold pcp_batch_high_lock and dissolve_free_huge_page() might hold + * cpu_hotplug_lock via static_key_slow_dec() when hugetlb vmemmap + * optimization is enabled. This will break current lock dependency + * chain and leads to deadlock. + * Disabling pcp before dissolving the page was a deterministic + * approach because we made sure that those pages cannot end up in any + * PCP list. Draining PCP lists expels those pages to the buddy system, + * but nothing guarantees that those pages do not get back to a PCP + * queue if we need to refill those. + */ ret = dissolve_free_huge_page(page); - if (!ret) + if (!ret) { + drain_all_pages(page_zone(page)); ret = take_page_off_buddy(page); - zone_pcp_enable(page_zone(page)); + } return ret; } diff --git a/mm/page_owner.c b/mm/page_owner.c index d17d1351ec84a..742f432e5bf06 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -118,7 +118,6 @@ static __init void init_page_owner(void) register_dummy_stack(); register_failure_stack(); register_early_stack(); - static_branch_enable(&page_owner_inited); init_early_allocated_pages(); /* Initialize dummy and failure stacks and link them to stack_list */ dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle); @@ -129,6 +128,7 @@ static __init void init_page_owner(void) refcount_set(&failure_stack.stack_record->count, 1); dummy_stack.next = &failure_stack; stack_list = &dummy_stack; + static_branch_enable(&page_owner_inited); } struct page_ext_operations page_owner_ops = { @@ -196,7 +196,8 @@ static void add_stack_record_to_list(struct stack_record *stack_record, spin_unlock_irqrestore(&stack_list_lock, flags); } -static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask) +static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask, + int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); @@ -217,20 +218,74 @@ static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask) /* Add the new stack_record to our list */ add_stack_record_to_list(stack_record, gfp_mask); } - refcount_inc(&stack_record->count); + refcount_add(nr_base_pages, &stack_record->count); } -static void dec_stack_record_count(depot_stack_handle_t handle) +static void dec_stack_record_count(depot_stack_handle_t handle, + int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); - if (stack_record) - refcount_dec(&stack_record->count); + if (!stack_record) + return; + + if (refcount_sub_and_test(nr_base_pages, &stack_record->count)) + pr_warn("%s: refcount went to 0 for %u handle\n", __func__, + handle); } -void __reset_page_owner(struct page *page, unsigned short order) +static inline void __update_page_owner_handle(struct page_ext *page_ext, + depot_stack_handle_t handle, + unsigned short order, + gfp_t gfp_mask, + short last_migrate_reason, u64 ts_nsec, + pid_t pid, pid_t tgid, char *comm) { int i; + struct page_owner *page_owner; + + for (i = 0; i < (1 << order); i++) { + page_owner = get_page_owner(page_ext); + page_owner->handle = handle; + page_owner->order = order; + page_owner->gfp_mask = gfp_mask; + page_owner->last_migrate_reason = last_migrate_reason; + page_owner->pid = pid; + page_owner->tgid = tgid; + page_owner->ts_nsec = ts_nsec; + strscpy(page_owner->comm, comm, + sizeof(page_owner->comm)); + __set_bit(PAGE_EXT_OWNER, &page_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_ext = page_ext_next(page_ext); + } +} + +static inline void __update_page_owner_free_handle(struct page_ext *page_ext, + depot_stack_handle_t handle, + unsigned short order, + pid_t pid, pid_t tgid, + u64 free_ts_nsec) +{ + int i; + struct page_owner *page_owner; + + for (i = 0; i < (1 << order); i++) { + page_owner = get_page_owner(page_ext); + /* Only __reset_page_owner() wants to clear the bit */ + if (handle) { + __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_owner->free_handle = handle; + } + page_owner->free_ts_nsec = free_ts_nsec; + page_owner->free_pid = current->pid; + page_owner->free_tgid = current->tgid; + page_ext = page_ext_next(page_ext); + } +} + +void __reset_page_owner(struct page *page, unsigned short order) +{ struct page_ext *page_ext; depot_stack_handle_t handle; depot_stack_handle_t alloc_handle; @@ -245,16 +300,10 @@ void __reset_page_owner(struct page *page, unsigned short order) alloc_handle = page_owner->handle; handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); - for (i = 0; i < (1 << order); i++) { - __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - page_owner->free_handle = handle; - page_owner->free_ts_nsec = free_ts_nsec; - page_owner->free_pid = current->pid; - page_owner->free_tgid = current->tgid; - page_ext = page_ext_next(page_ext); - page_owner = get_page_owner(page_ext); - } + __update_page_owner_free_handle(page_ext, handle, order, current->pid, + current->tgid, free_ts_nsec); page_ext_put(page_ext); + if (alloc_handle != early_handle) /* * early_handle is being set as a handle for all those @@ -263,39 +312,14 @@ void __reset_page_owner(struct page *page, unsigned short order) * the machinery is not ready yet, we cannot decrement * their refcount either. */ - dec_stack_record_count(alloc_handle); -} - -static inline void __set_page_owner_handle(struct page_ext *page_ext, - depot_stack_handle_t handle, - unsigned short order, gfp_t gfp_mask) -{ - struct page_owner *page_owner; - int i; - u64 ts_nsec = local_clock(); - - for (i = 0; i < (1 << order); i++) { - page_owner = get_page_owner(page_ext); - page_owner->handle = handle; - page_owner->order = order; - page_owner->gfp_mask = gfp_mask; - page_owner->last_migrate_reason = -1; - page_owner->pid = current->pid; - page_owner->tgid = current->tgid; - page_owner->ts_nsec = ts_nsec; - strscpy(page_owner->comm, current->comm, - sizeof(page_owner->comm)); - __set_bit(PAGE_EXT_OWNER, &page_ext->flags); - __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - - page_ext = page_ext_next(page_ext); - } + dec_stack_record_count(alloc_handle, 1 << order); } noinline void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask) { struct page_ext *page_ext; + u64 ts_nsec = local_clock(); depot_stack_handle_t handle; handle = save_stack(gfp_mask); @@ -303,9 +327,11 @@ noinline void __set_page_owner(struct page *page, unsigned short order, page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; - __set_page_owner_handle(page_ext, handle, order, gfp_mask); + __update_page_owner_handle(page_ext, handle, order, gfp_mask, -1, + current->pid, current->tgid, ts_nsec, + current->comm); page_ext_put(page_ext); - inc_stack_record_count(handle, gfp_mask); + inc_stack_record_count(handle, gfp_mask, 1 << order); } void __set_page_owner_migrate_reason(struct page *page, int reason) @@ -340,9 +366,12 @@ void __split_page_owner(struct page *page, int old_order, int new_order) void __folio_copy_owner(struct folio *newfolio, struct folio *old) { + int i; struct page_ext *old_ext; struct page_ext *new_ext; - struct page_owner *old_page_owner, *new_page_owner; + struct page_owner *old_page_owner; + struct page_owner *new_page_owner; + depot_stack_handle_t migrate_handle; old_ext = page_ext_get(&old->page); if (unlikely(!old_ext)) @@ -356,30 +385,32 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old) old_page_owner = get_page_owner(old_ext); new_page_owner = get_page_owner(new_ext); - new_page_owner->order = old_page_owner->order; - new_page_owner->gfp_mask = old_page_owner->gfp_mask; - new_page_owner->last_migrate_reason = - old_page_owner->last_migrate_reason; - new_page_owner->handle = old_page_owner->handle; - new_page_owner->pid = old_page_owner->pid; - new_page_owner->tgid = old_page_owner->tgid; - new_page_owner->free_pid = old_page_owner->free_pid; - new_page_owner->free_tgid = old_page_owner->free_tgid; - new_page_owner->ts_nsec = old_page_owner->ts_nsec; - new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; - strcpy(new_page_owner->comm, old_page_owner->comm); - + migrate_handle = new_page_owner->handle; + __update_page_owner_handle(new_ext, old_page_owner->handle, + old_page_owner->order, old_page_owner->gfp_mask, + old_page_owner->last_migrate_reason, + old_page_owner->ts_nsec, old_page_owner->pid, + old_page_owner->tgid, old_page_owner->comm); + /* + * Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio + * will be freed after migration. Keep them until then as they may be + * useful. + */ + __update_page_owner_free_handle(new_ext, 0, old_page_owner->order, + old_page_owner->free_pid, + old_page_owner->free_tgid, + old_page_owner->free_ts_nsec); /* - * We don't clear the bit on the old folio as it's going to be freed - * after migration. Until then, the info can be useful in case of - * a bug, and the overall stats will be off a bit only temporarily. - * Also, migrate_misplaced_transhuge_page() can still fail the - * migration and then we want the old folio to retain the info. But - * in that case we also don't need to explicitly clear the info from - * the new page, which will be freed. + * We linked the original stack to the new folio, we need to do the same + * for the new one and the old folio otherwise there will be an imbalance + * when subtracting those pages from the stack. */ - __set_bit(PAGE_EXT_OWNER, &new_ext->flags); - __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); + for (i = 0; i < (1 << new_page_owner->order); i++) { + old_page_owner->handle = migrate_handle; + old_ext = page_ext_next(old_ext); + old_page_owner = get_page_owner(old_ext); + } + page_ext_put(new_ext); page_ext_put(old_ext); } @@ -787,8 +818,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) goto ext_put_continue; /* Found early allocated page */ - __set_page_owner_handle(page_ext, early_handle, - 0, 0); + __update_page_owner_handle(page_ext, early_handle, 0, 0, + -1, local_clock(), current->pid, + current->tgid, current->comm); count++; ext_put_continue: page_ext_put(page_ext); @@ -840,13 +872,11 @@ static void *stack_start(struct seq_file *m, loff_t *ppos) * value of stack_list. */ stack = smp_load_acquire(&stack_list); + m->private = stack; } else { stack = m->private; - stack = stack->next; } - m->private = stack; - return stack; } @@ -861,11 +891,11 @@ static void *stack_next(struct seq_file *m, void *v, loff_t *ppos) return stack; } -static unsigned long page_owner_stack_threshold; +static unsigned long page_owner_pages_threshold; static int stack_print(struct seq_file *m, void *v) { - int i, stack_count; + int i, nr_base_pages; struct stack *stack = v; unsigned long *entries; unsigned long nr_entries; @@ -876,14 +906,14 @@ static int stack_print(struct seq_file *m, void *v) nr_entries = stack_record->size; entries = stack_record->entries; - stack_count = refcount_read(&stack_record->count) - 1; + nr_base_pages = refcount_read(&stack_record->count) - 1; - if (stack_count < 1 || stack_count < page_owner_stack_threshold) + if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold) return 0; for (i = 0; i < nr_entries; i++) seq_printf(m, " %pS\n", (void *)entries[i]); - seq_printf(m, "stack_count: %d\n\n", stack_count); + seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages); return 0; } @@ -913,13 +943,13 @@ static const struct file_operations page_owner_stack_operations = { static int page_owner_threshold_get(void *data, u64 *val) { - *val = READ_ONCE(page_owner_stack_threshold); + *val = READ_ONCE(page_owner_pages_threshold); return 0; } static int page_owner_threshold_set(void *data, u64 val) { - WRITE_ONCE(page_owner_stack_threshold, val); + WRITE_ONCE(page_owner_pages_threshold, val); return 0; } diff --git a/mm/shmem.c b/mm/shmem.c index 0aad0d9a621b8..94ab99b6b574a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -748,12 +748,6 @@ static long shmem_unused_huge_count(struct super_block *sb, #define shmem_huge SHMEM_HUGE_DENY -bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags) -{ - return false; -} - static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f21097e734827..ceaa5a89b947f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -30,7 +30,7 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) return netif_receive_skb(skb); } -static int br_pass_frame_up(struct sk_buff *skb) +static int br_pass_frame_up(struct sk_buff *skb, bool promisc) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); @@ -65,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb) br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb), BR_MCAST_DIR_TX); + BR_INPUT_SKB_CB(skb)->promisc = promisc; + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(indev), NULL, skb, indev, NULL, br_netif_receive_skb); @@ -82,6 +84,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_mcast *brmctx; struct net_bridge_vlan *vlan; struct net_bridge *br; + bool promisc; u16 vid = 0; u8 state; @@ -137,7 +140,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0); - local_rcv = !!(br->dev->flags & IFF_PROMISC); + promisc = !!(br->dev->flags & IFF_PROMISC); + local_rcv = promisc; + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) { @@ -200,7 +205,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb unsigned long now = jiffies; if (test_bit(BR_FDB_LOCAL, &dst->flags)) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, false); if (now != dst->used) dst->used = now; @@ -213,7 +218,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } if (local_rcv) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, promisc); out: return 0; @@ -386,6 +391,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; } + BR_INPUT_SKB_CB(skb)->promisc = false; + /* The else clause should be hit when nf_hook(): * - returns < 0 (drop/error) * - returns = 0 (stolen/nf_queue) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 35e10c5a766d5..22e35623c148a 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -600,11 +600,17 @@ static unsigned int br_nf_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; struct nf_conntrack *nfct = skb_nfct(skb); const struct nf_ct_hook *ct_hook; struct nf_conn *ct; int ret; + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 86ea5e6689b5c..d4bedc87b1d8f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -589,6 +589,7 @@ struct br_input_skb_cb { #endif u8 proxyarp_replied:1; u8 src_port_isolated:1; + u8 promisc:1; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_filtered:1; #endif diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 6f877e31709ba..c3c51b9a68265 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -294,18 +294,24 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - enum ip_conntrack_info ctinfo; + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; + struct nf_conntrack *nfct = skb_nfct(skb); struct nf_conn *ct; - if (skb->pkt_type == PACKET_HOST) + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; /* nf_conntrack_confirm() cannot handle concurrent clones, * this happens for broad/multicast frames with e.g. macvlan on top * of the bridge device. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) + ct = container_of(nfct, struct nf_conn, ct_general); + if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) return NF_ACCEPT; /* let inet prerouting call conntrack again */ diff --git a/net/core/dev.c b/net/core/dev.c index 984ff8b9d0e1a..331848eca7d31 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3775,6 +3775,10 @@ no_lock_out: return rc; } + if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { + kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); + return NET_XMIT_DROP; + } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. @@ -3814,7 +3818,9 @@ no_lock_out: qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { + WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); + WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 48741352a88a7..c484b1c0fc00a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1050,6 +1050,11 @@ next: e++; } } + + /* Don't let NLM_DONE coalesce into a message, even if it could. + * Some user space expects NLM_DONE in a separate recv(). + */ + err = skb->len; out: cb->args[1] = e; diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 9505f9d188ff2..6eef15648b7b0 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -21,7 +21,8 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, proto = veth->h_vlan_encapsulated_proto; break; case htons(ETH_P_PPP_SES): - proto = nf_flow_pppoe_proto(skb); + if (!nf_flow_pppoe_proto(skb, &proto)) + return NF_ACCEPT; break; default: proto = skb->protocol; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index e45fade764096..5383bed3d3e00 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -157,7 +157,7 @@ static void nf_flow_tuple_encap(struct sk_buff *skb, tuple->encap[i].proto = skb->protocol; break; case htons(ETH_P_PPP_SES): - phdr = (struct pppoe_hdr *)skb_mac_header(skb); + phdr = (struct pppoe_hdr *)skb_network_header(skb); tuple->encap[i].id = ntohs(phdr->sid); tuple->encap[i].proto = skb->protocol; break; @@ -273,10 +273,11 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } -static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, +static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, u32 *offset) { struct vlan_ethhdr *veth; + __be16 inner_proto; switch (skb->protocol) { case htons(ETH_P_8021Q): @@ -287,7 +288,8 @@ static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, } break; case htons(ETH_P_PPP_SES): - if (nf_flow_pppoe_proto(skb) == proto) { + if (nf_flow_pppoe_proto(skb, &inner_proto) && + inner_proto == proto) { *offset += PPPOE_SES_HLEN; return true; } @@ -316,7 +318,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb, skb_reset_network_header(skb); break; case htons(ETH_P_PPP_SES): - skb->protocol = nf_flow_pppoe_proto(skb); + skb->protocol = __nf_flow_pppoe_proto(skb); skb_pull(skb, PPPOE_SES_HLEN); skb_reset_network_header(skb); break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d89d779467197..167074283ea91 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -594,6 +594,12 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; @@ -617,6 +623,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } @@ -626,6 +633,7 @@ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_deactivate, }; @@ -3060,7 +3068,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, { const struct nft_expr_type *type, *candidate = NULL; - list_for_each_entry(type, &nf_tables_expressions, list) { + list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; @@ -3092,9 +3100,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); + rcu_read_lock(); type = __nft_expr_type_get(family, nla); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -3875,6 +3887,9 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_data *data; int err; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -3898,17 +3913,20 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { - u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_iter dummy_iter = { + .genmask = nft_genmask_next(ctx->net), + }; struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) + if (!nft_set_elem_active(ext, dummy_iter.genmask)) continue; - ret = nft_setelem_validate(ctx, set, NULL, catchall->elem); + ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem); if (ret < 0) return ret; } @@ -5397,6 +5415,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + return nft_setelem_data_validate(ctx, set, elem_priv); } @@ -5441,6 +5464,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, } iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; @@ -5488,6 +5512,13 @@ static int nft_mapelem_activate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + /* called from abort path, reverse check to undo changes. */ + if (nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; @@ -5505,6 +5536,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } @@ -5514,6 +5546,7 @@ static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_activate, }; @@ -5778,6 +5811,9 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; @@ -5888,6 +5924,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.skb = skb; args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); + args.iter.type = NFT_ITER_READ; args.iter.skip = cb->args[0]; args.iter.count = 0; args.iter.err = 0; @@ -6627,7 +6664,7 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_setelem_is_catchall(set, elem_priv)) { - nft_set_elem_change_active(net, set, ext); + nft_clear(net, ext); } else { set->ops->activate(net, set, elem_priv); } @@ -7186,6 +7223,16 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) } } +static int nft_setelem_active_next(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + u8 genmask = nft_genmask_next(net); + + return nft_set_elem_active(ext, genmask); +} + static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) @@ -7309,8 +7356,12 @@ static int nft_setelem_flush(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_trans *trans; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_ATOMIC); if (!trans) @@ -7372,6 +7423,7 @@ static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { struct nft_set_iter iter = { .genmask = genmask, + .type = NFT_ITER_UPDATE, .fn = nft_setelem_flush, }; @@ -7607,7 +7659,7 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; - list_for_each_entry(type, &nf_tables_objects, list) { + list_for_each_entry_rcu(type, &nf_tables_objects, list) { if (type->family != NFPROTO_UNSPEC && type->family != family) continue; @@ -7623,9 +7675,13 @@ nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; + rcu_read_lock(); type = __nft_obj_type_get(objtype, family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -10598,8 +10654,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_data_activate(net, te->set, te->elem_priv); - nft_setelem_activate(net, te->set, te->elem_priv); + if (!nft_setelem_active_next(net, te->set, te->elem_priv)) { + nft_setelem_data_activate(net, te->set, te->elem_priv); + nft_setelem_activate(net, te->set, te->elem_priv); + } if (!nft_setelem_is_catchall(te->set, te->elem_priv)) te->set->ndeact--; @@ -10787,6 +10845,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -10871,6 +10932,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, continue; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index a0055f510e31e..b314ca728a291 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -216,6 +216,7 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, return 0; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 32df7a16835da..1caa04619dc6d 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -172,7 +172,7 @@ static void nft_bitmap_activate(const struct net *net, nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 11 state. */ priv->bitmap[idx] |= (genmask << off); - nft_set_elem_change_active(net, set, &be->ext); + nft_clear(net, &be->ext); } static void nft_bitmap_flush(const struct net *net, @@ -222,8 +222,6 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, list_for_each_entry_rcu(be, &priv->list, head) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&be->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &be->priv); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6968a3b342367..daa56dda737ae 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -199,7 +199,7 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, { struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_rhash_flush(const struct net *net, @@ -286,8 +286,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) @@ -599,7 +597,7 @@ static void nft_hash_activate(const struct net *net, const struct nft_set *set, { struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_hash_flush(const struct net *net, @@ -652,8 +650,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, hlist_for_each_entry_rcu(he, &priv->table[i], node) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index df8de50902463..187138afac45d 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1847,7 +1847,7 @@ static void nft_pipapo_activate(const struct net *net, { struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &e->ext); + nft_clear(net, &e->ext); } /** @@ -2077,6 +2077,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -2089,16 +2091,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** @@ -2115,13 +2119,15 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_pipapo *priv = nft_set_priv(set); - struct net *net = read_pnet(&set->net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; unsigned int i, r; + WARN_ON_ONCE(iter->type != NFT_ITER_READ && + iter->type != NFT_ITER_UPDATE); + rcu_read_lock(); - if (iter->genmask == nft_genmask_cur(net)) + if (iter->type == NFT_ITER_READ) m = rcu_dereference(priv->match); else m = priv->clone; @@ -2143,9 +2149,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; - if (!nft_set_elem_active(&e->ext, iter->genmask)) - goto cont; - iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 9944fe479e536..b7ea21327549b 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -532,7 +532,7 @@ static void nft_rbtree_activate(const struct net *net, { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &rbe->ext); + nft_clear(net, &rbe->ext); } static void nft_rbtree_flush(const struct net *net, @@ -600,8 +600,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&rbe->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index ff53364937775..4a2c763e2d116 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -974,6 +974,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; + sch->owner = -1; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d032eb5fa6df1..9a6ad5974dff5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2663,7 +2663,9 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, WRITE_ONCE(u->oob_skb, NULL); consume_skb(skb); } - } else if (!(flags & MSG_PEEK)) { + } else if (flags & MSG_PEEK) { + skb = NULL; + } else { skb_unlink(skb, &sk->sk_receive_queue); WRITE_ONCE(u->oob_skb, NULL); if (!WARN_ON_ONCE(skb_unref(skb))) @@ -2741,18 +2743,16 @@ redo: last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; +again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { skb = manage_oob(skb, sk, flags, copied); - if (!skb) { + if (!skb && copied) { unix_state_unlock(sk); - if (copied) - break; - goto redo; + break; } } #endif -again: if (skb == NULL) { if (copied >= target) goto unlock; diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index b141024830ecc..ee6ac649df836 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -428,7 +428,7 @@ static int cvt_ump_midi2_to_midi1(struct snd_seq_client *dest, midi1->note.group = midi2->note.group; midi1->note.status = midi2->note.status; midi1->note.channel = midi2->note.channel; - switch (midi2->note.status << 4) { + switch (midi2->note.status) { case UMP_MSG_STATUS_NOTE_ON: case UMP_MSG_STATUS_NOTE_OFF: midi1->note.note = midi2->note.note; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cdcb28aa9d7bf..70d80b6af3fe3 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7467,6 +7467,10 @@ enum { ALC285_FIXUP_CS35L56_I2C_2, ALC285_FIXUP_CS35L56_I2C_4, ALC285_FIXUP_ASUS_GA403U, + ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC, + ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC, + ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1 }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9690,6 +9694,38 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_asus_ga403u, }, + [ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1 + }, + [ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC, + }, + [ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_CS35L56_SPI_2 + }, + [ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_GA403U, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -10084,6 +10120,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), @@ -10143,7 +10181,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), - SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U), + SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2), @@ -10151,7 +10189,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), - SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_CS35L56_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), @@ -10228,6 +10266,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x152d, 0x1082, "Quanta NL3", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x152d, 0x1262, "Huawei NBLB-WAX9N", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1558, 0x0353, "Clevo V35[05]SN[CDE]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1325, "Clevo N15[01][CW]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -10333,6 +10372,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x222e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), + SND_PCI_QUIRK(0x17aa, 0x2234, "Thinkpad ICE-1", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), @@ -10394,8 +10434,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2), @@ -10457,6 +10497,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 48dae33393050..75f7674c66ee7 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -514,10 +514,10 @@ static int tas2563_save_calibration(struct tasdevice_priv *tas_priv) static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) { static const unsigned char page_array[CALIB_MAX] = { - 0x17, 0x18, 0x18, 0x0d, 0x18 + 0x17, 0x18, 0x18, 0x13, 0x18, }; static const unsigned char rgno_array[CALIB_MAX] = { - 0x74, 0x0c, 0x14, 0x3c, 0x7c + 0x74, 0x0c, 0x14, 0x70, 0x7c, }; unsigned char *data; int i, j, rc; diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 7c7493cb571f9..52f076afeb960 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -135,6 +136,8 @@ #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -193,6 +196,7 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 89d2fc872d9f5..964df31da9751 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -37,9 +37,7 @@ #include <asm/ptrace.h> #include <asm/sve_context.h> -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM #define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -76,11 +74,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ - KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK __GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ - KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK __GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 @@ -162,6 +160,11 @@ struct kvm_sync_regs { __u64 device_irq_level; }; +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + /* * PMU filter structure. Describe a range of events with a particular * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 9f18fa090f1f1..1691297a766a9 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -28,7 +28,6 @@ #define __KVM_HAVE_PPC_SMT #define __KVM_HAVE_IRQCHIP #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_GUEST_DEBUG /* Not always available, but if it is, this is the correct offset. */ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -733,4 +732,48 @@ struct kvm_ppc_xive_eq { #define KVM_XIVE_TIMA_PAGE_OFFSET 0 #define KVM_XIVE_ESB_PAGE_OFFSET 4 +/* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + +struct kvm_ppc_pvinfo { + /* out */ + __u32 flags; + __u32 hcall[4]; + __u8 pad[108]; +}; + +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 +#define KVM_PPC_NO_HASH 0x00000004 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index abe926d43cbe0..05eaf6db3ad4c 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -12,7 +12,320 @@ #include <linux/types.h> #define __KVM_S390 -#define __KVM_HAVE_GUEST_DEBUG + +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + union { + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ + }; + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* ignored */ + }; +}; +/* types for kvm_s390_mem_op->op */ +#define KVM_S390_MEMOP_LOGICAL_READ 0 +#define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + +/* flags for kvm_s390_mem_op->flags */ +#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) +#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) + +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u +#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u +#define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u +#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu +#define KVM_S390_INT_IO_AI_MASK 0x04000000u + + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +struct kvm_s390_io_info { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; +}; + +struct kvm_s390_ext_info { + __u32 ext_params; + __u32 pad; + __u64 ext_params2; +}; + +struct kvm_s390_pgm_info { + __u64 trans_exc_code; + __u64 mon_code; + __u64 per_address; + __u32 data_exc_code; + __u16 code; + __u16 mon_class_nr; + __u8 per_code; + __u8 per_atmid; + __u8 exc_access_id; + __u8 per_access_id; + __u8 op_access_id; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; +}; + +struct kvm_s390_prefix_info { + __u32 address; +}; + +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 pad; + __u8 fixed_logout[16]; +}; + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; /* will stay unused for compatibility reasons */ + __u32 len; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ +}; + +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; + +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_dmp_id { + KVM_PV_DUMP_INIT, + KVM_PV_DUMP_CONFIG_STOR_STATE, + KVM_PV_DUMP_COMPLETE, + KVM_PV_DUMP_CPU, +}; + +struct kvm_s390_pv_dmp { + __u64 subcmd; + __u64 buff_addr; + __u64 buff_len; + __u64 gaddr; /* For dump storage state */ + __u64 reserved[4]; +}; + +enum pv_cmd_info_id { + KVM_PV_INFO_VM, + KVM_PV_INFO_DUMP, +}; + +struct kvm_s390_pv_info_dump { + __u64 dump_cpu_buffer_len; + __u64 dump_config_mem_buffer_per_1m; + __u64 dump_config_finalize_len; +}; + +struct kvm_s390_pv_info_vm { + __u64 inst_calls_list[4]; + __u64 max_cpus; + __u64 max_guests; + __u64 max_guest_addr; + __u64 feature_indication; +}; + +struct kvm_s390_pv_info_header { + __u32 id; + __u32 len_max; + __u32 len_written; + __u32 reserved; +}; + +struct kvm_s390_pv_info { + struct kvm_s390_pv_info_header header; + union { + struct kvm_s390_pv_info_dump dump; + struct kvm_s390_pv_info_vm vm; + }; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, + KVM_PV_DUMP, + KVM_PV_ASYNC_CLEANUP_PREPARE, + KVM_PV_ASYNC_CLEANUP_PERFORM, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) /* Device control API: s390-specific devices */ #define KVM_DEV_FLIC_GET_ALL_IRQS 1 diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 25160d26764b5..a38f8f9ba6572 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -81,10 +81,8 @@ #define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ #define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ - -/* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ #define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ #define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ @@ -97,7 +95,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -462,6 +460,14 @@ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ + +/* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) @@ -508,4 +514,5 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 1f23960d2b06e..c492bdc97b059 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -123,6 +123,12 @@ # define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) #endif +#ifdef CONFIG_KVM_AMD_SEV +#define DISABLE_SEV_SNP 0 +#else +#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -147,8 +153,9 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 (DISABLE_IBT) -#define DISABLED_MASK19 0 +#define DISABLED_MASK19 (DISABLE_SEV_SNP) #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h index 3f73ac3ed3a07..d18bfb238f660 100644 --- a/tools/arch/x86/include/asm/irq_vectors.h +++ b/tools/arch/x86/include/asm/irq_vectors.h @@ -84,11 +84,9 @@ #define HYPERVISOR_CALLBACK_VECTOR 0xf3 /* Vector for KVM to deliver posted interrupt IPI */ -#if IS_ENABLED(CONFIG_KVM) #define POSTED_INTR_VECTOR 0xf2 #define POSTED_INTR_WAKEUP_VECTOR 0xf1 #define POSTED_INTR_NESTED_VECTOR 0xf0 -#endif #define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 1f9dc9bd13eb7..05956bd8bacf5 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -176,6 +176,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -605,34 +613,47 @@ #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 -#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) - -/* SNP feature bits enabled by the hypervisor */ -#define MSR_AMD64_SNP_VTOM BIT_ULL(3) -#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) -#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) -#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) -#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) -#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) -#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) -#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) -#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) -#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) -#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) -#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) -#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) - -/* SNP feature bits reserved for future use. */ -#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) -#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) -#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) +#define MSR_AMD64_SNP_VTOM_BIT 3 +#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT) +#define MSR_AMD64_SNP_REFLECT_VC_BIT 4 +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT) +#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5 +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT) +#define MSR_AMD64_SNP_ALT_INJ_BIT 6 +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT) +#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7 +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8 +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT) +#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9 +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT) +#define MSR_AMD64_SNP_VMPL_SSS_BIT 10 +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT) +#define MSR_AMD64_SNP_SECURE_TSC_BIT 11 +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT) +#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12 +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_IBS_VIRT_BIT 14 +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16 +#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) +#define MSR_AMD64_SNP_SMT_PROT_BIT 17 +#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) +#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +#define MSR_AMD64_RMP_BASE 0xc0010132 +#define MSR_AMD64_RMP_END 0xc0010133 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -719,8 +740,15 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_AMD64_SYSCFG 0xc0010010 -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 7ba1726b71c7b..e9187ddd3d1fd 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index a448d0964fc06..ef11aa4cab425 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -7,6 +7,8 @@ * */ +#include <linux/const.h> +#include <linux/bits.h> #include <linux/types.h> #include <linux/ioctl.h> #include <linux/stddef.h> @@ -40,7 +42,6 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 @@ -49,7 +50,6 @@ #define __KVM_HAVE_DEBUGREGS #define __KVM_HAVE_XSAVE #define __KVM_HAVE_XCRS -#define __KVM_HAVE_READONLY_MEM /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -526,9 +526,301 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 -#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for KVM_CAP_XEN_HVM */ +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8) + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + union { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + __u64 hva; + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } u; +}; + + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 hva; + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u32 pad0; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u32 pad0; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u32 pad1; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u32 pad2; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u32 pad3; + __u64 session_uaddr; + __u32 session_len; + __u32 pad4; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description @@ -549,10 +841,10 @@ struct kvm_pmu_event_filter { ((__u64)(!!(exclude)) << 55)) #define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ - (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) -#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) + (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55)) #define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ @@ -560,7 +852,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ /* x86-specific KVM_EXIT_HYPERCALL flags. */ -#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0) #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h index 03f721a8a2b19..54ccccf96e21e 100644 --- a/tools/include/asm-generic/bitops/__fls.h +++ b/tools/include/asm-generic/bitops/__fls.h @@ -5,12 +5,12 @@ #include <asm/types.h> /** - * __fls - find last (most-significant) set bit in a long word + * generic___fls - find last (most-significant) set bit in a long word * @word: the word to search * * Undefined if no set bit exists, so code should check against 0 first. */ -static __always_inline unsigned long __fls(unsigned long word) +static __always_inline unsigned long generic___fls(unsigned long word) { int num = BITS_PER_LONG - 1; @@ -41,4 +41,8 @@ static __always_inline unsigned long __fls(unsigned long word) return num; } +#ifndef __HAVE_ARCH___FLS +#define __fls(word) generic___fls(word) +#endif + #endif /* _ASM_GENERIC_BITOPS___FLS_H_ */ diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h index b168bb10e1be1..26f3ce1dd6e44 100644 --- a/tools/include/asm-generic/bitops/fls.h +++ b/tools/include/asm-generic/bitops/fls.h @@ -3,14 +3,14 @@ #define _ASM_GENERIC_BITOPS_FLS_H_ /** - * fls - find last (most-significant) bit set + * generic_fls - find last (most-significant) bit set * @x: the word to search * * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __always_inline int fls(unsigned int x) +static __always_inline int generic_fls(unsigned int x) { int r = 32; @@ -39,4 +39,8 @@ static __always_inline int fls(unsigned int x) return r; } +#ifndef __HAVE_ARCH_FLS +#define fls(x) generic_fls(x) +#endif + #endif /* _ASM_GENERIC_BITOPS_FLS_H_ */ diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index fd4f9574d177a..2ee338860b7e0 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -3013,6 +3013,7 @@ struct drm_i915_query_item { * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_GUC_SUBMISSION_VERSION (see struct drm_i915_query_guc_submission_version) */ __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 @@ -3021,6 +3022,7 @@ struct drm_i915_query_item { #define DRM_I915_QUERY_MEMORY_REGIONS 4 #define DRM_I915_QUERY_HWCONFIG_BLOB 5 #define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6 +#define DRM_I915_QUERY_GUC_SUBMISSION_VERSION 7 /* Must be kept compact -- no holes and well documented */ /** @@ -3567,6 +3569,20 @@ struct drm_i915_query_memory_regions { }; /** + * struct drm_i915_query_guc_submission_version - query GuC submission interface version + */ +struct drm_i915_query_guc_submission_version { + /** @branch: Firmware branch version. */ + __u32 branch; + /** @major: Firmware major version. */ + __u32 major; + /** @minor: Firmware minor version. */ + __u32 minor; + /** @patch: Firmware patch version. */ + __u32 patch; +}; + +/** * DOC: GuC HWCONFIG blob uAPI * * The GuC produces a blob with information about the current device. diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index 48ad69f7722e1..45e4e64fd6643 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -64,6 +64,24 @@ struct fstrim_range { __u64 minlen; }; +/* + * We include a length field because some filesystems (vfat) have an identifier + * that we do want to expose as a UUID, but doesn't have the standard length. + * + * We use a fixed size buffer beacuse this interface will, by fiat, never + * support "UUIDs" longer than 16 bytes; we don't want to force all downstream + * users to have to deal with that. + */ +struct fsuuid2 { + __u8 len; + __u8 uuid[16]; +}; + +struct fs_sysfs_path { + __u8 len; + __u8 name[128]; +}; + /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ #define FILE_DEDUPE_RANGE_SAME 0 #define FILE_DEDUPE_RANGE_DIFFERS 1 @@ -215,6 +233,13 @@ struct fsxattr { #define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) #define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX]) #define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) +/* Returns the external filesystem UUID, the same one blkid returns */ +#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2) +/* + * Returns the path component under /sys/fs/ that refers to this filesystem; + * also /sys/kernel/debug/ for filesystems with debugfs exports + */ +#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) @@ -301,9 +326,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO O_APPEND */ #define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) +/* per-IO negation of O_APPEND */ +#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND) + RWF_APPEND | RWF_NOAPPEND) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c3308536482bd..2190adbe30027 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -16,6 +16,11 @@ #define KVM_API_VERSION 12 +/* + * Backwards-compatible definitions. + */ +#define __KVM_HAVE_GUEST_DEBUG + /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -85,43 +90,6 @@ struct kvm_pit_config { #define KVM_PIT_SPEAKER_DUMMY 1 -struct kvm_s390_skeys { - __u64 start_gfn; - __u64 count; - __u64 skeydata_addr; - __u32 flags; - __u32 reserved[9]; -}; - -#define KVM_S390_CMMA_PEEK (1 << 0) - -/** - * kvm_s390_cmma_log - Used for CMMA migration. - * - * Used both for input and output. - * - * @start_gfn: Guest page number to start from. - * @count: Size of the result buffer. - * @flags: Control operation mode via KVM_S390_CMMA_* flags - * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty - * pages are still remaining. - * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set - * in the PGSTE. - * @values: Pointer to the values buffer. - * - * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. - */ -struct kvm_s390_cmma_log { - __u64 start_gfn; - __u32 count; - __u32 flags; - union { - __u64 remaining; - __u64 mask; - }; - __u64 values; -}; - struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 @@ -315,11 +283,6 @@ struct kvm_run { __u32 ipb; } s390_sieic; /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; /* KVM_EXIT_S390_UCONTROL */ struct { @@ -536,43 +499,6 @@ struct kvm_translation { __u8 pad[5]; }; -/* for KVM_S390_MEM_OP */ -struct kvm_s390_mem_op { - /* in */ - __u64 gaddr; /* the guest address */ - __u64 flags; /* flags */ - __u32 size; /* amount of bytes */ - __u32 op; /* type of operation */ - __u64 buf; /* buffer in userspace */ - union { - struct { - __u8 ar; /* the access register number */ - __u8 key; /* access key, ignored if flag unset */ - __u8 pad1[6]; /* ignored */ - __u64 old_addr; /* ignored if cmpxchg flag unset */ - }; - __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* ignored */ - }; -}; -/* types for kvm_s390_mem_op->op */ -#define KVM_S390_MEMOP_LOGICAL_READ 0 -#define KVM_S390_MEMOP_LOGICAL_WRITE 1 -#define KVM_S390_MEMOP_SIDA_READ 2 -#define KVM_S390_MEMOP_SIDA_WRITE 3 -#define KVM_S390_MEMOP_ABSOLUTE_READ 4 -#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 -#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 - -/* flags for kvm_s390_mem_op->flags */ -#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) -#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) -#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) - -/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ -#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) -#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) - /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -637,124 +563,6 @@ struct kvm_mp_state { __u32 mp_state; }; -struct kvm_s390_psw { - __u64 mask; - __u64 addr; -}; - -/* valid values for type in kvm_s390_interrupt */ -#define KVM_S390_SIGP_STOP 0xfffe0000u -#define KVM_S390_PROGRAM_INT 0xfffe0001u -#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u -#define KVM_S390_RESTART 0xfffe0003u -#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u -#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u -#define KVM_S390_MCHK 0xfffe1000u -#define KVM_S390_INT_CLOCK_COMP 0xffff1004u -#define KVM_S390_INT_CPU_TIMER 0xffff1005u -#define KVM_S390_INT_VIRTIO 0xffff2603u -#define KVM_S390_INT_SERVICE 0xffff2401u -#define KVM_S390_INT_EMERGENCY 0xffff1201u -#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u -/* Anything below 0xfffe0000u is taken by INT_IO */ -#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ - (((schid)) | \ - ((ssid) << 16) | \ - ((cssid) << 18) | \ - ((ai) << 26)) -#define KVM_S390_INT_IO_MIN 0x00000000u -#define KVM_S390_INT_IO_MAX 0xfffdffffu -#define KVM_S390_INT_IO_AI_MASK 0x04000000u - - -struct kvm_s390_interrupt { - __u32 type; - __u32 parm; - __u64 parm64; -}; - -struct kvm_s390_io_info { - __u16 subchannel_id; - __u16 subchannel_nr; - __u32 io_int_parm; - __u32 io_int_word; -}; - -struct kvm_s390_ext_info { - __u32 ext_params; - __u32 pad; - __u64 ext_params2; -}; - -struct kvm_s390_pgm_info { - __u64 trans_exc_code; - __u64 mon_code; - __u64 per_address; - __u32 data_exc_code; - __u16 code; - __u16 mon_class_nr; - __u8 per_code; - __u8 per_atmid; - __u8 exc_access_id; - __u8 per_access_id; - __u8 op_access_id; -#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 -#define KVM_S390_PGM_FLAGS_ILC_0 0x02 -#define KVM_S390_PGM_FLAGS_ILC_1 0x04 -#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 -#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 - __u8 flags; - __u8 pad[2]; -}; - -struct kvm_s390_prefix_info { - __u32 address; -}; - -struct kvm_s390_extcall_info { - __u16 code; -}; - -struct kvm_s390_emerg_info { - __u16 code; -}; - -#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 -struct kvm_s390_stop_info { - __u32 flags; -}; - -struct kvm_s390_mchk_info { - __u64 cr14; - __u64 mcic; - __u64 failing_storage_address; - __u32 ext_damage_code; - __u32 pad; - __u8 fixed_logout[16]; -}; - -struct kvm_s390_irq { - __u64 type; - union { - struct kvm_s390_io_info io; - struct kvm_s390_ext_info ext; - struct kvm_s390_pgm_info pgm; - struct kvm_s390_emerg_info emerg; - struct kvm_s390_extcall_info extcall; - struct kvm_s390_prefix_info prefix; - struct kvm_s390_stop_info stop; - struct kvm_s390_mchk_info mchk; - char reserved[64]; - } u; -}; - -struct kvm_s390_irq_state { - __u64 buf; - __u32 flags; /* will stay unused for compatibility reasons */ - __u32 len; - __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; - /* for KVM_SET_GUEST_DEBUG */ #define KVM_GUESTDBG_ENABLE 0x00000001 @@ -810,50 +618,6 @@ struct kvm_enable_cap { __u8 pad[64]; }; -/* for KVM_PPC_GET_PVINFO */ - -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) - -struct kvm_ppc_pvinfo { - /* out */ - __u32 flags; - __u32 hcall[4]; - __u8 pad[108]; -}; - -/* for KVM_PPC_GET_SMMU_INFO */ -#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 - -struct kvm_ppc_one_page_size { - __u32 page_shift; /* Page shift (or 0) */ - __u32 pte_enc; /* Encoding in the HPTE (>>12) */ -}; - -struct kvm_ppc_one_seg_page_size { - __u32 page_shift; /* Base page shift of segment (or 0) */ - __u32 slb_enc; /* SLB encoding for BookS */ - struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 -#define KVM_PPC_1T_SEGMENTS 0x00000002 -#define KVM_PPC_NO_HASH 0x00000004 - -struct kvm_ppc_smmu_info { - __u64 flags; - __u32 slb_size; - __u16 data_keys; /* # storage keys supported for data */ - __u16 instr_keys; /* # storage keys supported for instructions */ - struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ -struct kvm_ppc_resize_hpt { - __u64 flags; - __u32 shift; - __u32 pad; -}; - #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ @@ -923,9 +687,7 @@ struct kvm_ppc_resize_hpt { /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 #define KVM_CAP_USER_NMI 22 -#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 -#endif #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif @@ -1156,8 +918,6 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 -#ifdef KVM_CAP_IRQ_ROUTING - struct kvm_irq_routing_irqchip { __u32 irqchip; __u32 pin; @@ -1222,42 +982,6 @@ struct kvm_irq_routing { struct kvm_irq_routing_entry entries[]; }; -#endif - -#ifdef KVM_CAP_MCE -/* x86 MCE */ -struct kvm_x86_mce { - __u64 status; - __u64 addr; - __u64 misc; - __u64 mcg_status; - __u8 bank; - __u8 pad1[7]; - __u64 pad2[3]; -}; -#endif - -#ifdef KVM_CAP_XEN_HVM -#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) -#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) -#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) -#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) -#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) -#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) -#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) -#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) - -struct kvm_xen_hvm_config { - __u32 flags; - __u32 msr; - __u64 blob_addr_32; - __u64 blob_addr_64; - __u8 blob_size_32; - __u8 blob_size_64; - __u8 pad2[30]; -}; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE @@ -1442,11 +1166,6 @@ struct kvm_vfio_spapr_tce { struct kvm_userspace_memory_region2) /* enable ucontrol for s390 */ -struct kvm_s390_ucas_mapping { - __u64 user_addr; - __u64 vcpu_addr; - __u64 length; -}; #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) @@ -1641,89 +1360,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -struct kvm_s390_pv_sec_parm { - __u64 origin; - __u64 length; -}; - -struct kvm_s390_pv_unp { - __u64 addr; - __u64 size; - __u64 tweak; -}; - -enum pv_cmd_dmp_id { - KVM_PV_DUMP_INIT, - KVM_PV_DUMP_CONFIG_STOR_STATE, - KVM_PV_DUMP_COMPLETE, - KVM_PV_DUMP_CPU, -}; - -struct kvm_s390_pv_dmp { - __u64 subcmd; - __u64 buff_addr; - __u64 buff_len; - __u64 gaddr; /* For dump storage state */ - __u64 reserved[4]; -}; - -enum pv_cmd_info_id { - KVM_PV_INFO_VM, - KVM_PV_INFO_DUMP, -}; - -struct kvm_s390_pv_info_dump { - __u64 dump_cpu_buffer_len; - __u64 dump_config_mem_buffer_per_1m; - __u64 dump_config_finalize_len; -}; - -struct kvm_s390_pv_info_vm { - __u64 inst_calls_list[4]; - __u64 max_cpus; - __u64 max_guests; - __u64 max_guest_addr; - __u64 feature_indication; -}; - -struct kvm_s390_pv_info_header { - __u32 id; - __u32 len_max; - __u32 len_written; - __u32 reserved; -}; - -struct kvm_s390_pv_info { - struct kvm_s390_pv_info_header header; - union { - struct kvm_s390_pv_info_dump dump; - struct kvm_s390_pv_info_vm vm; - }; -}; - -enum pv_cmd_id { - KVM_PV_ENABLE, - KVM_PV_DISABLE, - KVM_PV_SET_SEC_PARMS, - KVM_PV_UNPACK, - KVM_PV_VERIFY, - KVM_PV_PREP_RESET, - KVM_PV_UNSHARE_ALL, - KVM_PV_INFO, - KVM_PV_DUMP, - KVM_PV_ASYNC_CLEANUP_PREPARE, - KVM_PV_ASYNC_CLEANUP_PERFORM, -}; - -struct kvm_pv_cmd { - __u32 cmd; /* Command to be executed */ - __u16 rc; /* Ultravisor return code */ - __u16 rrc; /* Ultravisor return reason code */ - __u64 data; /* Data or address */ - __u32 flags; /* flags for future extensions. Must be 0 for now */ - __u32 reserved[3]; -}; - /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) @@ -1737,58 +1373,6 @@ struct kvm_pv_cmd { #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) -struct kvm_xen_hvm_attr { - __u16 type; - __u16 pad[3]; - union { - __u8 long_mode; - __u8 vector; - __u8 runstate_update_flag; - struct { - __u64 gfn; -#define KVM_XEN_INVALID_GFN ((__u64)-1) - } shared_info; - struct { - __u32 send_port; - __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ - __u32 flags; -#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) -#define KVM_XEN_EVTCHN_UPDATE (1 << 1) -#define KVM_XEN_EVTCHN_RESET (1 << 2) - /* - * Events sent by the guest are either looped back to - * the guest itself (potentially on a different port#) - * or signalled via an eventfd. - */ - union { - struct { - __u32 port; - __u32 vcpu; - __u32 priority; - } port; - struct { - __u32 port; /* Zero for eventfd */ - __s32 fd; - } eventfd; - __u32 padding[4]; - } deliver; - } evtchn; - __u32 xen_version; - __u64 pad[8]; - } u; -}; - - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 -#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 -#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 -#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ -#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 - /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) @@ -1799,242 +1383,6 @@ struct kvm_xen_hvm_attr { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -struct kvm_xen_vcpu_attr { - __u16 type; - __u16 pad[3]; - union { - __u64 gpa; -#define KVM_XEN_INVALID_GPA ((__u64)-1) - __u64 pad[8]; - struct { - __u64 state; - __u64 state_entry_time; - __u64 time_running; - __u64 time_runnable; - __u64 time_blocked; - __u64 time_offline; - } runstate; - __u32 vcpu_id; - struct { - __u32 port; - __u32 priority; - __u64 expires_ns; - } timer; - __u8 vector; - } u; -}; - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 -#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 -#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 - -/* Secure Encrypted Virtualization command */ -enum sev_cmd_id { - /* Guest initialization commands */ - KVM_SEV_INIT = 0, - KVM_SEV_ES_INIT, - /* Guest launch commands */ - KVM_SEV_LAUNCH_START, - KVM_SEV_LAUNCH_UPDATE_DATA, - KVM_SEV_LAUNCH_UPDATE_VMSA, - KVM_SEV_LAUNCH_SECRET, - KVM_SEV_LAUNCH_MEASURE, - KVM_SEV_LAUNCH_FINISH, - /* Guest migration commands (outgoing) */ - KVM_SEV_SEND_START, - KVM_SEV_SEND_UPDATE_DATA, - KVM_SEV_SEND_UPDATE_VMSA, - KVM_SEV_SEND_FINISH, - /* Guest migration commands (incoming) */ - KVM_SEV_RECEIVE_START, - KVM_SEV_RECEIVE_UPDATE_DATA, - KVM_SEV_RECEIVE_UPDATE_VMSA, - KVM_SEV_RECEIVE_FINISH, - /* Guest status and debug commands */ - KVM_SEV_GUEST_STATUS, - KVM_SEV_DBG_DECRYPT, - KVM_SEV_DBG_ENCRYPT, - /* Guest certificates commands */ - KVM_SEV_CERT_EXPORT, - /* Attestation report */ - KVM_SEV_GET_ATTESTATION_REPORT, - /* Guest Migration Extension */ - KVM_SEV_SEND_CANCEL, - - KVM_SEV_NR_MAX, -}; - -struct kvm_sev_cmd { - __u32 id; - __u64 data; - __u32 error; - __u32 sev_fd; -}; - -struct kvm_sev_launch_start { - __u32 handle; - __u32 policy; - __u64 dh_uaddr; - __u32 dh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_launch_update_data { - __u64 uaddr; - __u32 len; -}; - - -struct kvm_sev_launch_secret { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_launch_measure { - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_guest_status { - __u32 handle; - __u32 policy; - __u32 state; -}; - -struct kvm_sev_dbg { - __u64 src_uaddr; - __u64 dst_uaddr; - __u32 len; -}; - -struct kvm_sev_attestation_report { - __u8 mnonce[16]; - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_send_start { - __u32 policy; - __u64 pdh_cert_uaddr; - __u32 pdh_cert_len; - __u64 plat_certs_uaddr; - __u32 plat_certs_len; - __u64 amd_certs_uaddr; - __u32 amd_certs_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_send_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_receive_start { - __u32 handle; - __u32 policy; - __u64 pdh_uaddr; - __u32 pdh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_receive_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) - -struct kvm_assigned_pci_dev { - __u32 assigned_dev_id; - __u32 busnr; - __u32 devfn; - __u32 flags; - __u32 segnr; - union { - __u32 reserved[11]; - }; -}; - -#define KVM_DEV_IRQ_HOST_INTX (1 << 0) -#define KVM_DEV_IRQ_HOST_MSI (1 << 1) -#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) - -#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) -#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) -#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) - -#define KVM_DEV_IRQ_HOST_MASK 0x00ff -#define KVM_DEV_IRQ_GUEST_MASK 0xff00 - -struct kvm_assigned_irq { - __u32 assigned_dev_id; - __u32 host_irq; /* ignored (legacy field) */ - __u32 guest_irq; - __u32 flags; - union { - __u32 reserved[12]; - }; -}; - -struct kvm_assigned_msix_nr { - __u32 assigned_dev_id; - __u16 entry_nr; - __u16 padding; -}; - -#define KVM_MAX_MSIX_PER_DEV 256 -struct kvm_assigned_msix_entry { - __u32 assigned_dev_id; - __u32 gsi; - __u16 entry; /* The index of entry in the MSI-X table */ - __u16 padding[3]; -}; - -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) - -/* Available with KVM_CAP_ARM_USER_IRQ */ - -/* Bits for run->s.regs.device_irq_level */ -#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) -#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) -#define KVM_ARM_DEV_PMU (1 << 2) - -struct kvm_hyperv_eventfd { - __u32 conn_id; - __s32 fd; - __u32 flags; - __u32 padding[3]; -}; - -#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff -#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) - #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) @@ -2180,33 +1528,6 @@ struct kvm_stats_desc { /* Available with KVM_CAP_S390_ZPCI_OP */ #define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) -struct kvm_s390_zpci_op { - /* in */ - __u32 fh; /* target device */ - __u8 op; /* operation to perform */ - __u8 pad[3]; - union { - /* for KVM_S390_ZPCIOP_REG_AEN */ - struct { - __u64 ibv; /* Guest addr of interrupt bit vector */ - __u64 sb; /* Guest addr of summary bit */ - __u32 flags; - __u32 noi; /* Number of interrupts */ - __u8 isc; /* Guest interrupt subclass */ - __u8 sbo; /* Offset of guest summary bit vector */ - __u16 pad; - } reg_aen; - __u64 reserved[8]; - } u; -}; - -/* types for kvm_s390_zpci_op->op */ -#define KVM_S390_ZPCIOP_REG_AEN 0 -#define KVM_S390_ZPCIOP_DEREG_AEN 1 - -/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ -#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) - /* Available with KVM_CAP_MEMORY_ATTRIBUTES */ #define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index d5b9cfbd9ceac..628d46a0da92e 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -416,7 +416,7 @@ struct snd_pcm_hw_params { unsigned int rmask; /* W: requested masks */ unsigned int cmask; /* R: changed masks */ unsigned int info; /* R: Info flags for returned setup */ - unsigned int msbits; /* R: used most significant bits */ + unsigned int msbits; /* R: used most significant bits (in sample bit-width) */ unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ec5e219328760..4790c735599bd 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -970,7 +970,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, if (dso->annotate_warned) return -1; - if (not_annotated) { + if (not_annotated || !sym->annotate2) { err = symbol__annotate2(ms, evsel, &browser.arch); if (err) { char msg[BUFSIZ]; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ac002d907d818..50ca92255ff62 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2461,6 +2461,9 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, if (parch) *parch = arch; + if (!list_empty(¬es->src->source)) + return 0; + args.arch = arch; args.ms = *ms; if (annotate_opts.full_addr) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index fb54bd38e7d09..d931a898c434b 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -284,6 +284,7 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) struct task_struct *curr; struct mm_struct___old *mm_old; struct mm_struct___new *mm_new; + struct sighand_struct *sighand; switch (flags) { case LCB_F_READ: /* rwsem */ @@ -305,7 +306,9 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) break; case LCB_F_SPIN: /* spinlock */ curr = bpf_get_current_task_btf(); - if (&curr->sighand->siglock == (void *)lock) + sighand = curr->sighand; + + if (sighand && &sighand->siglock == (void *)lock) return LCD_F_SIGHAND_LOCK; break; default: diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index b1ede62498667..b7c8f29c09a97 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -18,7 +18,7 @@ echo 'sched:*' > set_event yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -29,7 +29,7 @@ echo 1 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -40,7 +40,7 @@ echo 0 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -ne 0 ]; then fail "any of scheduler events should not be recorded" fi diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config index 110d73917615d..02a2a1b267c1e 100644 --- a/tools/testing/selftests/iommu/config +++ b/tools/testing/selftests/iommu/config @@ -1,3 +1,5 @@ CONFIG_IOMMUFD=y +CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION=y CONFIG_IOMMUFD_TEST=y +CONFIG_FAILSLAB=y diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 7b89362da4bfd..14bbab0cce135 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -292,15 +292,17 @@ void ksft_test_result_code(int exit_code, const char *test_name, } /* Docs seem to call for double space if directive is absent */ - if (!directive[0] && msg[0]) + if (!directive[0] && msg) directive = " # "; - va_start(args, msg); printf("%s %u %s%s", tap_code, ksft_test_num(), test_name, directive); errno = saved_errno; - vprintf(msg, args); + if (msg) { + va_start(args, msg); + vprintf(msg, args); + va_end(args); + } printf("\n"); - va_end(args); } static inline __noreturn int ksft_exit_pass(void) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 4fd735e48ee7e..ba3ddeda24bf5 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -383,6 +383,7 @@ FIXTURE_DATA(fixture_name) self; \ pid_t child = 1; \ int status = 0; \ + bool jmp = false; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ if (setjmp(_metadata->env) == 0) { \ /* Use the same _metadata. */ \ @@ -399,8 +400,10 @@ _metadata->exit_code = KSFT_FAIL; \ } \ } \ + else \ + jmp = true; \ if (child == 0) { \ - if (_metadata->setup_completed && !_metadata->teardown_parent) \ + if (_metadata->setup_completed && !_metadata->teardown_parent && !jmp) \ fixture_name##_teardown(_metadata, &self, variant->data); \ _exit(0); \ } \ @@ -1202,7 +1205,7 @@ void __run_test(struct __fixture_metadata *f, diagnostic = "unknown"; ksft_test_result_code(t->exit_code, test_name, - diagnostic ? "%s" : "", diagnostic); + diagnostic ? "%s" : NULL, diagnostic); } static int test_harness_run(int argc, char **argv) diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c index 6628dc4dda89f..1a6da7389bf1f 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -22,10 +22,11 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) { uint64_t gpa; - for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - *((volatile uint64_t *)gpa) = gpa; - - GUEST_DONE(); + for (;;) { + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + *((volatile uint64_t *)gpa) = gpa; + GUEST_SYNC(0); + } } struct vcpu_info { @@ -55,7 +56,7 @@ static void rendezvous_with_boss(void) static void run_vcpu(struct kvm_vcpu *vcpu) { vcpu_run(vcpu); - TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); } static void *vcpu_worker(void *data) @@ -64,17 +65,13 @@ static void *vcpu_worker(void *data) struct kvm_vcpu *vcpu = info->vcpu; struct kvm_vm *vm = vcpu->vm; struct kvm_sregs sregs; - struct kvm_regs regs; vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size); - /* Snapshot regs before the first run. */ - vcpu_regs_get(vcpu, ®s); rendezvous_with_boss(); run_vcpu(vcpu); rendezvous_with_boss(); - vcpu_regs_set(vcpu, ®s); vcpu_sregs_get(vcpu, &sregs); #ifdef __x86_64__ /* Toggle CR0.WP to trigger a MMU context reset. */ diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 06b43ed23580b..bd57d991e27d8 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -333,7 +333,7 @@ static void test_invalid_memory_region_flags(void) struct kvm_vm *vm; int r, i; -#if defined __aarch64__ || defined __x86_64__ +#if defined __aarch64__ || defined __riscv || defined __x86_64__ supported_flags |= KVM_MEM_READONLY; #endif diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c index 29609b52f8fa0..26c85815f7e98 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c @@ -416,12 +416,30 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters static void guest_test_gp_counters(void) { + uint8_t pmu_version = guest_get_pmu_version(); uint8_t nr_gp_counters = 0; uint32_t base_msr; - if (guest_get_pmu_version()) + if (pmu_version) nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + /* + * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is + * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number + * of GP counters. If there are no GP counters, require KVM to leave + * PERF_GLOBAL_CTRL '0'. This edge case isn't covered by the SDM, but + * follow the spirit of the architecture and only globally enable GP + * counters, of which there are none. + */ + if (pmu_version > 1) { + uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL); + + if (nr_gp_counters) + GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0)); + else + GUEST_ASSERT_EQ(global_ctrl, 0); + } + if (this_cpu_has(X86_FEATURE_PDCM) && rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES) base_msr = MSR_IA32_PMC0; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 7f6f5f23fb9b6..977948fd52e6b 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -28,16 +28,16 @@ #define NESTED_TEST_MEM1 0xc0001000 #define NESTED_TEST_MEM2 0xc0002000 -static void l2_guest_code(void) +static void l2_guest_code(u64 *a, u64 *b) { - *(volatile uint64_t *)NESTED_TEST_MEM1; - *(volatile uint64_t *)NESTED_TEST_MEM1 = 1; + READ_ONCE(*a); + WRITE_ONCE(*a, 1); GUEST_SYNC(true); GUEST_SYNC(false); - *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + WRITE_ONCE(*b, 1); GUEST_SYNC(true); - *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + WRITE_ONCE(*b, 1); GUEST_SYNC(true); GUEST_SYNC(false); @@ -45,17 +45,33 @@ static void l2_guest_code(void) vmcall(); } +static void l2_guest_code_ept_enabled(void) +{ + l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2); +} + +static void l2_guest_code_ept_disabled(void) +{ + /* Access the same L1 GPAs as l2_guest_code_ept_enabled() */ + l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM); +} + void l1_guest_code(struct vmx_pages *vmx) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + void *l2_rip; GUEST_ASSERT(vmx->vmcs_gpa); GUEST_ASSERT(prepare_for_vmx_operation(vmx)); GUEST_ASSERT(load_vmcs(vmx)); - prepare_vmcs(vmx, l2_guest_code, - &l2_guest_stack[L2_GUEST_STACK_SIZE]); + if (vmx->eptp_gpa) + l2_rip = l2_guest_code_ept_enabled; + else + l2_rip = l2_guest_code_ept_disabled; + + prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]); GUEST_SYNC(false); GUEST_ASSERT(!vmlaunch()); @@ -64,7 +80,7 @@ void l1_guest_code(struct vmx_pages *vmx) GUEST_DONE(); } -int main(int argc, char *argv[]) +static void test_vmx_dirty_log(bool enable_ept) { vm_vaddr_t vmx_pages_gva = 0; struct vmx_pages *vmx; @@ -76,8 +92,7 @@ int main(int argc, char *argv[]) struct ucall uc; bool done = false; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - TEST_REQUIRE(kvm_cpu_has_ept()); + pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled"); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); @@ -103,11 +118,16 @@ int main(int argc, char *argv[]) * * Note that prepare_eptp should be called only L1's GPA map is done, * meaning after the last call to virt_map. + * + * When EPT is disabled, the L2 guest code will still access the same L1 + * GPAs as the EPT enabled case. */ - prepare_eptp(vmx, vm, 0); - nested_map_memslot(vmx, vm, 0); - nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); - nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); + if (enable_ept) { + prepare_eptp(vmx, vm, 0); + nested_map_memslot(vmx, vm, 0); + nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); + nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); + } bmap = bitmap_zalloc(TEST_MEM_PAGES); host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); @@ -148,3 +168,15 @@ int main(int argc, char *argv[]) } } } + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + test_vmx_dirty_log(/*enable_ept=*/false); + + if (kvm_cpu_has_ept()) + test_vmx_dirty_log(/*enable_ept=*/true); + + return 0; +} diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c index 2fb6dd8adba69..8b984fa042869 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/proc.c +++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c @@ -86,7 +86,7 @@ static void netstat_read_type(FILE *fnetstat, struct netstat **dest, char *line) pos = strchr(line, ' ') + 1; - if (fscanf(fnetstat, type->header_name) == EOF) + if (fscanf(fnetstat, "%[^ :]", type->header_name) == EOF) test_error("fscanf(%s)", type->header_name); if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':') test_error("Unexpected netstat format (%c)", tmp); diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c index 92276f916f2f3..e408b9243b2c5 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/setup.c +++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c @@ -17,37 +17,37 @@ static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER; void __test_msg(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_print_msg(buf); + ksft_print_msg("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_ok(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_pass(buf); + ksft_test_result_pass("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_fail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_fail(buf); + ksft_test_result_fail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_xfail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_xfail(buf); + ksft_test_result_xfail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_error(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_error(buf); + ksft_test_result_error("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_skip(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_skip(buf); + ksft_test_result_skip("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index 7df8b8700e39e..a2fe88d35ac06 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -256,8 +256,6 @@ static int test_wait_fds(int sk[], size_t nr, bool is_writable[], static void test_client_active_rst(unsigned int port) { - /* one in queue, another accept()ed */ - unsigned int wait_for = backlog + 2; int i, sk[3], err; bool is_writable[ARRAY_SIZE(sk)] = {false}; unsigned int last = ARRAY_SIZE(sk) - 1; @@ -275,16 +273,20 @@ static void test_client_active_rst(unsigned int port) for (i = 0; i < last; i++) { err = _test_connect_socket(sk[i], this_ip_dest, port, (i == 0) ? TEST_TIMEOUT_SEC : -1); - if (err < 0) test_error("failed to connect()"); } - synchronize_threads(); /* 2: connection accept()ed, another queued */ - err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC); + synchronize_threads(); /* 2: two connections: one accept()ed, another queued */ + err = test_wait_fds(sk, last, is_writable, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("test_wait_fds(): %d", err); + /* async connect() with third sk to get into request_sock_queue */ + err = _test_connect_socket(sk[last], this_ip_dest, port, -1); + if (err < 0) + test_error("failed to connect()"); + synchronize_threads(); /* 3: close listen socket */ if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); @@ -292,13 +294,14 @@ static void test_client_active_rst(unsigned int port) test_ok("Verified established tcp connection"); synchronize_threads(); /* 4: finishing up */ - err = _test_connect_socket(sk[last], this_ip_dest, port, -1); - if (err < 0) - test_error("failed to connect()"); synchronize_threads(); /* 5: closed active sk */ - err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL, - wait_for, TEST_TIMEOUT_SEC); + /* + * Wait for 2 connections: one accepted, another in the accept queue, + * the one in request_sock_queue won't get fully established, so + * doesn't receive an active RST, see inet_csk_listen_stop(). + */ + err = test_wait_fds(sk, last, NULL, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("select(): %d", err); diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 452de131fa3a9..517930f9721bd 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -21,7 +21,7 @@ static void make_listen(int sk) static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info, const char *tst) { - struct tcp_ao_info_opt tmp; + struct tcp_ao_info_opt tmp = {}; socklen_t len = sizeof(tmp); if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len)) diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 1d975bf52af33..85b3baa3f7f34 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -34,7 +34,7 @@ #endif #ifndef UDP_MAX_SEGMENTS -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #endif #define CONST_MTU_TEST 1500 diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c index 505294da1b9fb..d6f99eb9be659 100644 --- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c +++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c @@ -154,7 +154,7 @@ static int dev_papr_vpd_null_handle(void) static int papr_vpd_close_handle_without_reading(void) { const int devfd = open(DEVPATH, O_RDONLY); - struct papr_location_code lc; + struct papr_location_code lc = { .str = "", }; int fd; SKIP_IF_MSG(devfd < 0 && errno == ENOENT, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fb49c2a602002..ff0a20565f908 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -832,8 +832,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * mn_active_invalidate_count (see above) instead of * mmu_invalidate_in_progress. */ - gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end, - hva_range.may_block); + gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end); /* * If one or more memslots were found and thus zapped, notify arch code diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index ecefc7ec51af8..715f19669d01f 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -26,13 +26,11 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible, #ifdef CONFIG_HAVE_KVM_PFNCACHE void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, - unsigned long end, - bool may_block); + unsigned long end); #else static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, - unsigned long end, - bool may_block) + unsigned long end) { } #endif /* HAVE_KVM_PFNCACHE */ diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index 4e07112a24c2f..e3453e869e92c 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -23,7 +23,7 @@ * MMU notifier 'invalidate_range_start' hook. */ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, - unsigned long end, bool may_block) + unsigned long end) { struct gfn_to_pfn_cache *gpc; @@ -57,6 +57,19 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, spin_unlock(&kvm->gpc_lock); } +static bool kvm_gpc_is_valid_len(gpa_t gpa, unsigned long uhva, + unsigned long len) +{ + unsigned long offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) : + offset_in_page(gpa); + + /* + * The cached access must fit within a single page. The 'len' argument + * to activate() and refresh() exists only to enforce that. + */ + return offset + len <= PAGE_SIZE; +} + bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(gpc->kvm); @@ -74,7 +87,7 @@ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) if (kvm_is_error_hva(gpc->uhva)) return false; - if (offset_in_page(gpc->uhva) + len > PAGE_SIZE) + if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) return false; if (!gpc->valid) @@ -232,8 +245,7 @@ out_error: return -EFAULT; } -static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva, - unsigned long len) +static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva) { unsigned long page_offset; bool unmap_old = false; @@ -247,15 +259,6 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva))) return -EINVAL; - /* - * The cached acces must fit within a single page. The 'len' argument - * exists only to enforce that. - */ - page_offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) : - offset_in_page(gpa); - if (page_offset + len > PAGE_SIZE) - return -EINVAL; - lockdep_assert_held(&gpc->refresh_lock); write_lock_irq(&gpc->lock); @@ -270,6 +273,8 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l old_uhva = PAGE_ALIGN_DOWN(gpc->uhva); if (kvm_is_error_gpa(gpa)) { + page_offset = offset_in_page(uhva); + gpc->gpa = INVALID_GPA; gpc->memslot = NULL; gpc->uhva = PAGE_ALIGN_DOWN(uhva); @@ -279,6 +284,8 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l } else { struct kvm_memslots *slots = kvm_memslots(gpc->kvm); + page_offset = offset_in_page(gpa); + if (gpc->gpa != gpa || gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva)) { gfn_t gfn = gpa_to_gfn(gpa); @@ -354,6 +361,9 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) guard(mutex)(&gpc->refresh_lock); + if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) + return -EINVAL; + /* * If the GPA is valid then ignore the HVA, as a cache can be GPA-based * or HVA-based, not both. For GPA-based caches, the HVA will be @@ -361,7 +371,7 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) */ uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : KVM_HVA_ERR_BAD; - return __kvm_gpc_refresh(gpc, gpc->gpa, uhva, len); + return __kvm_gpc_refresh(gpc, gpc->gpa, uhva); } void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm) @@ -381,6 +391,9 @@ static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned { struct kvm *kvm = gpc->kvm; + if (!kvm_gpc_is_valid_len(gpa, uhva, len)) + return -EINVAL; + guard(mutex)(&gpc->refresh_lock); if (!gpc->active) { @@ -400,11 +413,18 @@ static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned gpc->active = true; write_unlock_irq(&gpc->lock); } - return __kvm_gpc_refresh(gpc, gpa, uhva, len); + return __kvm_gpc_refresh(gpc, gpa, uhva); } int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len) { + /* + * Explicitly disallow INVALID_GPA so that the magic value can be used + * by KVM to differentiate between GPA-based and HVA-based caches. + */ + if (WARN_ON_ONCE(kvm_is_error_gpa(gpa))) + return -EINVAL; + return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len); } |