February 2020 - Linux-stable-mirror

FAILED: patch "[PATCH] KVM: x86: Use gpa_t for cr2/gpa to fix TDP support on 32-bit" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 736c291c9f36b07f8889c61764c28edce20e715d Mon Sep 17 00:00:00 2001 From: Sean Christopherson <sean.j.christopherson(a)intel.com> Date: Fri, 6 Dec 2019 15:57:14 -0800 Subject: [PATCH] KVM: x86: Use gpa_t for cr2/gpa to fix TDP support on 32-bit KVM Convert a plethora of parameters and variables in the MMU and page fault flows from type gva_t to gpa_t to properly handle TDP on 32-bit KVM. Thanks to PSE and PAE paging, 32-bit kernels can access 64-bit physical addresses. When TDP is enabled, the fault address is a guest physical address and thus can be a 64-bit value, even when both KVM and its guest are using 32-bit virtual addressing, e.g. VMX's VMCS.GUEST_PHYSICAL is a 64-bit field, not a natural width field. Using a gva_t for the fault address means KVM will incorrectly drop the upper 32-bits of the GPA. Ditto for gva_to_gpa() when it is used to translate L2 GPAs to L1 GPAs. Opportunistically rename variables and parameters to better reflect the dual address modes, e.g. use "cr2_or_gpa" for fault addresses and plain "addr" instead of "vaddr" when the address may be either a GVA or an L2 GPA. Similarly, use "gpa" in the nonpaging_page_fault() flows to avoid a confusing "gpa_t gva" declaration; this also sets the stage for a future patch to combing nonpaging_page_fault() and tdp_page_fault() with minimal churn. Sprinkle in a few comments to document flows where an address is known to be a GVA and thus can be safely truncated to a 32-bit value. Add WARNs in kvm_handle_page_fault() and FNAME(gva_to_gpa_nested)() to help document such cases and detect bugs. Cc: stable(a)vger.kernel.org Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2893eae5df9f..159a28512e4c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -378,12 +378,12 @@ struct kvm_mmu { void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); - int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, + int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, + u32 access, struct x86_exception *exception); gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, @@ -1473,7 +1473,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c19f3ccaace3..2cb199817837 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3532,7 +3532,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte) * - true: let the vcpu to access on the same address again. * - false: let the real page fault path to fix it. */ -static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, +static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level, u32 error_code) { struct kvm_shadow_walk_iterator iterator; @@ -3552,7 +3552,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, do { u64 new_spte; - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte) if (!is_shadow_present_pte(spte) || iterator.level < level) break; @@ -3630,7 +3630,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } while (true); - trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep, spte, fault_handled); walk_shadow_page_lockless_end(vcpu); @@ -3638,10 +3638,11 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable); static int make_mmu_pages_available(struct kvm_vcpu *vcpu); -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, +static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn, bool prefault) { int r; @@ -3667,16 +3668,16 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); } - if (fast_page_fault(vcpu, v, level, error_code)) + if (fast_page_fault(vcpu, gpa, level, error_code)) return RET_PF_RETRY; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) return RET_PF_RETRY; - if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) + if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r)) return r; r = RET_PF_RETRY; @@ -3687,7 +3688,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault, false); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); @@ -3985,7 +3986,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { if (exception) @@ -3993,7 +3994,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, return vaddr; } -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -4153,13 +4154,14 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault) { - gfn_t gfn = gva >> PAGE_SHIFT; + gfn_t gfn = gpa >> PAGE_SHIFT; int r; - pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); + /* Note, paging is disabled, ergo gva == gpa. */ + pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code); if (page_fault_handle_page_track(vcpu, error_code, gfn)) return RET_PF_EMULATE; @@ -4171,11 +4173,12 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); - return nonpaging_map(vcpu, gva & PAGE_MASK, + return nonpaging_map(vcpu, gpa & PAGE_MASK, error_code, gfn, prefault); } -static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + gfn_t gfn) { struct kvm_arch_async_pf arch; @@ -4184,11 +4187,13 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, cr2_or_gpa, + kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -4208,12 +4213,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; /* *pfn has correct page already */ if (!prefault && kvm_can_do_async_pf(vcpu)) { - trace_kvm_try_async_get_page(gva, gfn); + trace_kvm_try_async_get_page(cr2_or_gpa, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { - trace_kvm_async_pf_doublefault(gva, gfn); + trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return true; - } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn)) + } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) return true; } @@ -4226,6 +4231,12 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, { int r = 1; +#ifndef CONFIG_X86_64 + /* A 64-bit CR2 should be impossible on 32-bit KVM. */ + if (WARN_ON_ONCE(fault_address >> 32)) + return -EFAULT; +#endif + vcpu->arch.l1tf_flush_l1d = true; switch (vcpu->arch.apf.host_apf_reason) { default: @@ -4263,7 +4274,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); } -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, +static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault) { kvm_pfn_t pfn; @@ -5520,7 +5531,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) return 0; } -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { int r, emulation_type = 0; @@ -5529,18 +5540,18 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, /* With shadow page tables, fault_address contains a GVA or nGPA. */ if (vcpu->arch.mmu->direct_map) { vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2; + vcpu->arch.gpa_val = cr2_or_gpa; } r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, cr2, direct); + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2, + r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); @@ -5560,7 +5571,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, */ if (vcpu->arch.mmu->direct_map && (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2)); + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); return 1; } @@ -5575,7 +5586,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, * explicitly shadowing L1's page tables, i.e. unprotecting something * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ - if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* @@ -5590,7 +5601,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, return 1; } - return x86_emulate_instruction(vcpu, cr2, emulation_type, insn, + return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 97b21e7fd013..c1d7b866a03f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -291,11 +291,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte) } /* - * Fetch a guest pte for a guest virtual address + * Fetch a guest pte for a guest virtual address, or for an L2's GPA. */ static int FNAME(walk_addr_generic)(struct guest_walker *walker, struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t addr, u32 access) + gpa_t addr, u32 access) { int ret; pt_element_t pte; @@ -496,7 +496,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, } static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, u32 access) + struct kvm_vcpu *vcpu, gpa_t addr, u32 access) { return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr, access); @@ -611,7 +611,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If the guest tries to write a write-protected page, we need to * emulate this operation, return 1 to indicate this case. */ -static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, +static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, struct guest_walker *gw, int write_fault, int hlevel, kvm_pfn_t pfn, bool map_writable, bool prefault, @@ -765,7 +765,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, * Returns: 1 if we need to emulate the instruction, 0 otherwise, or * a negative value on error. */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, bool prefault) { int write_fault = error_code & PFERR_WRITE_MASK; @@ -945,18 +945,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) spin_unlock(&vcpu->kvm->mmu_lock); } -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, +/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr)(&walker, vcpu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; @@ -964,7 +965,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, } #if PTTYPE != PTTYPE_EPT -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, +/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ +static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -972,6 +974,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, gpa_t gpa = UNMAPPED_GVA; int r; +#ifndef CONFIG_X86_64 + /* A 64-bit GVA should be impossible on 32-bit KVM. */ + WARN_ON_ONCE(vaddr >> 32); +#endif + r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); if (r) { diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 7ca8831c7d1a..3c6522b84ff1 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -249,13 +249,13 @@ TRACE_EVENT( TRACE_EVENT( fast_page_fault, - TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code, u64 *sptep, u64 old_spte, bool retry), - TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry), TP_STRUCT__entry( __field(int, vcpu_id) - __field(gva_t, gva) + __field(gpa_t, cr2_or_gpa) __field(u32, error_code) __field(u64 *, sptep) __field(u64, old_spte) @@ -265,7 +265,7 @@ TRACE_EVENT( TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->gva = gva; + __entry->cr2_or_gpa = cr2_or_gpa; __entry->error_code = error_code; __entry->sptep = sptep; __entry->old_spte = old_spte; @@ -273,9 +273,9 @@ TRACE_EVENT( __entry->retry = retry; ), - TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx" " new %llx spurious %d fixed %d", __entry->vcpu_id, - __entry->gva, __print_flags(__entry->error_code, "|", + __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|", kvm_mmu_trace_pferr_flags), __entry->sptep, __entry->old_spte, __entry->new_spte, __spte_satisfied(old_spte), __spte_satisfied(new_spte) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 25aac4c81b12..93bbbce67a03 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6379,11 +6379,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool write_fault_to_shadow_pgtable, int emulation_type) { - gpa_t gpa = cr2; + gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) @@ -6397,7 +6397,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, * Write permission should be allowed since only * write access need to be emulated. */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); /* * If the mapping is invalid in guest, let cpu retry @@ -6454,10 +6454,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - unsigned long cr2, int emulation_type) + gpa_t cr2_or_gpa, int emulation_type) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; last_retry_eip = vcpu->arch.last_retry_eip; last_retry_addr = vcpu->arch.last_retry_addr; @@ -6486,14 +6486,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, if (x86_page_table_writing_insn(ctxt)) return false; - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) return false; vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2; + vcpu->arch.last_retry_addr = cr2_or_gpa; if (!vcpu->arch.mmu->direct_map) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -6639,11 +6639,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } -int x86_emulate_instruction(struct kvm_vcpu *vcpu, - unsigned long cr2, - int emulation_type, - void *insn, - int insn_len) +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; @@ -6689,8 +6686,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) + if (reexecute_instruction(vcpu, cr2_or_gpa, + write_fault_to_spt, + emulation_type)) return 1; if (ctxt->have_exception) { /* @@ -6724,7 +6722,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return 1; } - if (retry_instruction(ctxt, cr2, emulation_type)) + if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) return 1; /* this is needed for vmware backdoor interface to work since it @@ -6736,7 +6734,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, restart: /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2; + ctxt->exception.address = cr2_or_gpa; r = x86_emulate_insn(ctxt); @@ -6744,7 +6742,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, emulation_type)) return 1; @@ -10025,7 +10023,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true); + vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) @@ -10138,7 +10136,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_not_present(work->arch.token, work->gva); + trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (kvm_can_deliver_async_pf(vcpu) && @@ -10173,7 +10171,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); - trace_kvm_async_pf_ready(work->arch.token, work->gva); + trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && !apf_get_user(vcpu, &val)) { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 29391af8871d..cab5e71f0f0f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -289,7 +289,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0d632a75fce9..528ab7a814ab 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -204,7 +204,7 @@ struct kvm_async_pf { struct list_head queue; struct kvm_vcpu *vcpu; struct mm_struct *mm; - gva_t gva; + gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; @@ -212,8 +212,8 @@ struct kvm_async_pf { void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, - struct kvm_arch_async_pf *arch); +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 35305d6e68cc..d8ef708a2ef6 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -64,7 +64,7 @@ static void async_pf_execute(struct work_struct *work) struct mm_struct *mm = apf->mm; struct kvm_vcpu *vcpu = apf->vcpu; unsigned long addr = apf->addr; - gva_t gva = apf->gva; + gpa_t cr2_or_gpa = apf->cr2_or_gpa; int locked = 1; might_sleep(); @@ -92,7 +92,7 @@ static void async_pf_execute(struct work_struct *work) * this point */ - trace_kvm_async_pf_completed(addr, gva); + trace_kvm_async_pf_completed(addr, cr2_or_gpa); if (swq_has_sleeper(&vcpu->wq)) swake_up_one(&vcpu->wq); @@ -165,8 +165,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) } } -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, - struct kvm_arch_async_pf *arch) +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + unsigned long hva, struct kvm_arch_async_pf *arch) { struct kvm_async_pf *work; @@ -185,7 +185,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, work->wakeup_all = false; work->vcpu = vcpu; - work->gva = gva; + work->cr2_or_gpa = cr2_or_gpa; work->addr = hva; work->arch = *arch; work->mm = current->mm;

5 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86: use CPUID to locate host page table reserved bits" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 7adacf5eb2d2048045d9fd8fdab861fd9e7e2e96 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini <pbonzini(a)redhat.com> Date: Wed, 4 Dec 2019 15:50:27 +0100 Subject: [PATCH] KVM: x86: use CPUID to locate host page table reserved bits The comment in kvm_get_shadow_phys_bits refers to MKTME, but the same is actually true of SME and SEV. Just use CPUID[0x8000_0008].EAX[7:0] unconditionally if available, it is simplest and works even if memory is not encrypted. Cc: stable(a)vger.kernel.org Reported-by: Tom Lendacky <thomas.lendacky(a)amd.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6f92b40d798c..1e4ee4f8de5f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -538,16 +538,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static u8 kvm_get_shadow_phys_bits(void) { /* - * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected - * in CPU detection code, but MKTME treats those reduced bits as - * 'keyID' thus they are not reserved bits. Therefore for MKTME - * we should still return physical address bits reported by CPUID. + * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected + * in CPU detection code, but the processor treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at + * the physical address bits reported by CPUID. */ - if (!boot_cpu_has(X86_FEATURE_TME) || - WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008)) - return boot_cpu_data.x86_phys_bits; + if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008)) + return cpuid_eax(0x80000008) & 0xff; - return cpuid_eax(0x80000008) & 0xff; + /* + * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with + * custom CPUID. Proceed with whatever the kernel found since these features + * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008). + */ + return boot_cpu_data.x86_phys_bits; } static void kvm_mmu_reset_all_pte_masks(void)

5 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From e30a7d623dccdb3f880fbcad980b0cb589a1da45 Mon Sep 17 00:00:00 2001 From: Sean Christopherson <sean.j.christopherson(a)intel.com> Date: Tue, 7 Jan 2020 16:12:10 -0800 Subject: [PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM Remove the bogus 64-bit only condition from the check that disables MMIO spte optimization when the system supports the max PA, i.e. doesn't have any reserved PA bits. 32-bit KVM always uses PAE paging for the shadow MMU, and per Intel's SDM: PAE paging translates 32-bit linear addresses to 52-bit physical addresses. The kernel's restrictions on max physical addresses are limits on how much memory the kernel can reasonably use, not what physical addresses are supported by hardware. Fixes: ce88decffd17 ("KVM: MMU: mmio page fault support") Cc: stable(a)vger.kernel.org Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2992ff7b42a7..57e4dbddba72 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6193,7 +6193,7 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);

5 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From e30a7d623dccdb3f880fbcad980b0cb589a1da45 Mon Sep 17 00:00:00 2001 From: Sean Christopherson <sean.j.christopherson(a)intel.com> Date: Tue, 7 Jan 2020 16:12:10 -0800 Subject: [PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM Remove the bogus 64-bit only condition from the check that disables MMIO spte optimization when the system supports the max PA, i.e. doesn't have any reserved PA bits. 32-bit KVM always uses PAE paging for the shadow MMU, and per Intel's SDM: PAE paging translates 32-bit linear addresses to 52-bit physical addresses. The kernel's restrictions on max physical addresses are limits on how much memory the kernel can reasonably use, not what physical addresses are supported by hardware. Fixes: ce88decffd17 ("KVM: MMU: mmio page fault support") Cc: stable(a)vger.kernel.org Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2992ff7b42a7..57e4dbddba72 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6193,7 +6193,7 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);

5 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From e30a7d623dccdb3f880fbcad980b0cb589a1da45 Mon Sep 17 00:00:00 2001 From: Sean Christopherson <sean.j.christopherson(a)intel.com> Date: Tue, 7 Jan 2020 16:12:10 -0800 Subject: [PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM Remove the bogus 64-bit only condition from the check that disables MMIO spte optimization when the system supports the max PA, i.e. doesn't have any reserved PA bits. 32-bit KVM always uses PAE paging for the shadow MMU, and per Intel's SDM: PAE paging translates 32-bit linear addresses to 52-bit physical addresses. The kernel's restrictions on max physical addresses are limits on how much memory the kernel can reasonably use, not what physical addresses are supported by hardware. Fixes: ce88decffd17 ("KVM: MMU: mmio page fault support") Cc: stable(a)vger.kernel.org Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2992ff7b42a7..57e4dbddba72 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6193,7 +6193,7 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);

5 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From e30a7d623dccdb3f880fbcad980b0cb589a1da45 Mon Sep 17 00:00:00 2001 From: Sean Christopherson <sean.j.christopherson(a)intel.com> Date: Tue, 7 Jan 2020 16:12:10 -0800 Subject: [PATCH] KVM: x86/mmu: Apply max PA check for MMIO sptes to 32-bit KVM Remove the bogus 64-bit only condition from the check that disables MMIO spte optimization when the system supports the max PA, i.e. doesn't have any reserved PA bits. 32-bit KVM always uses PAE paging for the shadow MMU, and per Intel's SDM: PAE paging translates 32-bit linear addresses to 52-bit physical addresses. The kernel's restrictions on max physical addresses are limits on how much memory the kernel can reasonably use, not what physical addresses are supported by hardware. Fixes: ce88decffd17 ("KVM: MMU: mmio page fault support") Cc: stable(a)vger.kernel.org Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2992ff7b42a7..57e4dbddba72 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6193,7 +6193,7 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);

5 years, 2 months

1
0
0 0

✅ PASS: Test report for kernel 5.4.19-rc1-e3082a4.cki (stable)

by CKI Project

Hello, We ran automated tests on a recent commit from this kernel tree: Kernel repo: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git Commit: e3082a4e02b8 - Linux 5.4.19-rc1 The results of these automated tests are provided below. Overall result: PASSED Merge: OK Compile: OK Tests: OK All kernel binaries, config files, and logs are available for download here: https://artifacts.cki-project.org/pipelines/427936 Please reply to this email if you have any questions about the tests that we ran or if you have any suggestions on how to make future tests more effective. ,-. ,-. ( C ) ( K ) Continuous `-',-.`-' Kernel ( I ) Integration `-' ______________________________________________________________________________ Compile testing --------------- We compiled the kernel for 3 architectures: aarch64: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg ppc64le: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg x86_64: make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg Hardware testing ---------------- We booted each kernel and ran the following tests: aarch64: Host 1: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking: igmp conformance test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ audit: audit testsuite test ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ storage: SCSI VPD ✅ trace: ftrace/tracer 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm test suite 🚧 ✅ Memory function: kaslr 🚧 ✅ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ✅ iotop: sanity 🚧 ✅ Usex - version 1.9-29 🚧 ✅ storage: dm/common Host 2: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing 🚧 ✅ Storage blktests ppc64le: Host 1: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ✅ Storage blktests Host 2: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - tunnel ✅ audit: audit testsuite test ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ trace: ftrace/tracer 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm test suite 🚧 ✅ Memory function: kaslr 🚧 ✅ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ✅ iotop: sanity 🚧 ✅ Usex - version 1.9-29 🚧 ✅ storage: dm/common x86_64: Host 1: ✅ Boot test ✅ Storage SAN device stress - mpt3sas driver Host 2: ✅ Boot test ✅ Storage SAN device stress - megaraid_sas Host 3: ✅ Boot test ✅ Podman system integration test - as root ✅ Podman system integration test - as user ✅ LTP ✅ Loopdev Sanity ✅ Memory function: memfd_create ✅ AMTU (Abstract Machine Test Utility) ✅ Networking bridge: sanity ✅ Ethernet drivers sanity ✅ Networking MACsec: sanity ✅ Networking socket: fuzz ✅ Networking sctp-auth: sockopts test ✅ Networking: igmp conformance test ✅ Networking route: pmtu ✅ Networking route_func - local ✅ Networking route_func - forward ✅ Networking TCP: keepalive test ✅ Networking UDP: socket ✅ Networking tunnel: geneve basic test ✅ Networking tunnel: gre basic ✅ L2TP basic test ✅ Networking tunnel: vxlan basic ✅ Networking ipsec: basic netns - transport ✅ Networking ipsec: basic netns - tunnel ✅ audit: audit testsuite test ✅ httpd: mod_ssl smoke sanity ✅ tuned: tune-processes-through-perf ✅ pciutils: sanity smoke test ✅ ALSA PCM loopback test ✅ ALSA Control (mixer) Userspace Element test ✅ storage: SCSI VPD ✅ trace: ftrace/tracer 🚧 ✅ CIFS Connectathon 🚧 ✅ POSIX pjd-fstest suites 🚧 ✅ jvm test suite 🚧 ✅ Memory function: kaslr 🚧 ✅ LTP: openposix test suite 🚧 ✅ Networking vnic: ipvlan/basic 🚧 ✅ iotop: sanity 🚧 ✅ Usex - version 1.9-29 🚧 ✅ storage: dm/common Host 4: ✅ Boot test ✅ xfstests - ext4 ✅ xfstests - xfs ✅ selinux-policy: serge-testsuite ✅ lvm thinp sanity ✅ storage: software RAID testing ✅ stress: stress-ng 🚧 ✅ IOMMU boot test 🚧 ✅ IPMI driver test 🚧 ✅ IPMItool loop stress test 🚧 ✅ Storage blktests Test sources: https://github.com/CKI-project/tests-beaker 💚 Pull requests are welcome for new tests or improvements to existing tests! Waived tests ------------ If the test run included waived tests, they are marked with 🚧. Such tests are executed but their results are not taken into account. Tests are waived when their results are not reliable enough, e.g. when they're just introduced or are being fixed. Testing timeout --------------- We aim to provide a report within reasonable timeframe. Tests that haven't finished running are marked with ⏱. Reports for non-upstream kernels have a Beaker recipe linked to next to each host.

5 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: flush write bio if we loop in extent_write_cache_pages" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 42ffb0bf584ae5b6b38f72259af1e0ee417ac77f Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Thu, 23 Jan 2020 15:33:02 -0500 Subject: [PATCH] btrfs: flush write bio if we loop in extent_write_cache_pages There exists a deadlock with range_cyclic that has existed forever. If we loop around with a bio already built we could deadlock with a writer who has the page locked that we're attempting to write but is waiting on a page in our bio to be written out. The task traces are as follows PID: 1329874 TASK: ffff889ebcdf3800 CPU: 33 COMMAND: "kworker/u113:5" #0 [ffffc900297bb658] __schedule at ffffffff81a4c33f #1 [ffffc900297bb6e0] schedule at ffffffff81a4c6e3 #2 [ffffc900297bb6f8] io_schedule at ffffffff81a4ca42 #3 [ffffc900297bb708] __lock_page at ffffffff811f145b #4 [ffffc900297bb798] __process_pages_contig at ffffffff814bc502 #5 [ffffc900297bb8c8] lock_delalloc_pages at ffffffff814bc684 #6 [ffffc900297bb900] find_lock_delalloc_range at ffffffff814be9ff #7 [ffffc900297bb9a0] writepage_delalloc at ffffffff814bebd0 #8 [ffffc900297bba18] __extent_writepage at ffffffff814bfbf2 #9 [ffffc900297bba98] extent_write_cache_pages at ffffffff814bffbd PID: 2167901 TASK: ffff889dc6a59c00 CPU: 14 COMMAND: "aio-dio-invalid" #0 [ffffc9003b50bb18] __schedule at ffffffff81a4c33f #1 [ffffc9003b50bba0] schedule at ffffffff81a4c6e3 #2 [ffffc9003b50bbb8] io_schedule at ffffffff81a4ca42 #3 [ffffc9003b50bbc8] wait_on_page_bit at ffffffff811f24d6 #4 [ffffc9003b50bc60] prepare_pages at ffffffff814b05a7 #5 [ffffc9003b50bcd8] btrfs_buffered_write at ffffffff814b1359 #6 [ffffc9003b50bdb0] btrfs_file_write_iter at ffffffff814b5933 #7 [ffffc9003b50be38] new_sync_write at ffffffff8128f6a8 #8 [ffffc9003b50bec8] vfs_write at ffffffff81292b9d #9 [ffffc9003b50bf00] ksys_pwrite64 at ffffffff81293032 I used drgn to find the respective pages we were stuck on page_entry.page 0xffffea00fbfc7500 index 8148 bit 15 pid 2167901 page_entry.page 0xffffea00f9bb7400 index 7680 bit 0 pid 1329874 As you can see the kworker is waiting for bit 0 (PG_locked) on index 7680, and aio-dio-invalid is waiting for bit 15 (PG_writeback) on index 8148. aio-dio-invalid has 7680, and the kworker epd looks like the following crash> struct extent_page_data ffffc900297bbbb0 struct extent_page_data { bio = 0xffff889f747ed830, tree = 0xffff889eed6ba448, extent_locked = 0, sync_io = 0 } Probably worth mentioning as well that it waits for writeback of the page to complete while holding a lock on it (at prepare_pages()). Using drgn I walked the bio pages looking for page 0xffffea00fbfc7500 which is the one we're waiting for writeback on bio = Object(prog, 'struct bio', address=0xffff889f747ed830) for i in range(0, bio.bi_vcnt.value_()): bv = bio.bi_io_vec[i] if bv.bv_page.value_() == 0xffffea00fbfc7500: print("FOUND IT") which validated what I suspected. The fix for this is simple, flush the epd before we loop back around to the beginning of the file during writeout. Fixes: b293f02e1423 ("Btrfs: Add writepages support") CC: stable(a)vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e2d30287e2d5..8ff17bc30d5a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4166,7 +4166,16 @@ static int extent_write_cache_pages(struct address_space *mapping, */ scanned = 1; index = 0; - goto retry; + + /* + * If we're looping we could run into a page that is locked by a + * writer and that writer could be waiting on writeback for a + * page in our current bio, and thus deadlock, so flush the + * write bio here. + */ + ret = flush_write_bio(epd); + if (!ret) + goto retry; } if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))

5 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: flush write bio if we loop in extent_write_cache_pages" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 42ffb0bf584ae5b6b38f72259af1e0ee417ac77f Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Thu, 23 Jan 2020 15:33:02 -0500 Subject: [PATCH] btrfs: flush write bio if we loop in extent_write_cache_pages There exists a deadlock with range_cyclic that has existed forever. If we loop around with a bio already built we could deadlock with a writer who has the page locked that we're attempting to write but is waiting on a page in our bio to be written out. The task traces are as follows PID: 1329874 TASK: ffff889ebcdf3800 CPU: 33 COMMAND: "kworker/u113:5" #0 [ffffc900297bb658] __schedule at ffffffff81a4c33f #1 [ffffc900297bb6e0] schedule at ffffffff81a4c6e3 #2 [ffffc900297bb6f8] io_schedule at ffffffff81a4ca42 #3 [ffffc900297bb708] __lock_page at ffffffff811f145b #4 [ffffc900297bb798] __process_pages_contig at ffffffff814bc502 #5 [ffffc900297bb8c8] lock_delalloc_pages at ffffffff814bc684 #6 [ffffc900297bb900] find_lock_delalloc_range at ffffffff814be9ff #7 [ffffc900297bb9a0] writepage_delalloc at ffffffff814bebd0 #8 [ffffc900297bba18] __extent_writepage at ffffffff814bfbf2 #9 [ffffc900297bba98] extent_write_cache_pages at ffffffff814bffbd PID: 2167901 TASK: ffff889dc6a59c00 CPU: 14 COMMAND: "aio-dio-invalid" #0 [ffffc9003b50bb18] __schedule at ffffffff81a4c33f #1 [ffffc9003b50bba0] schedule at ffffffff81a4c6e3 #2 [ffffc9003b50bbb8] io_schedule at ffffffff81a4ca42 #3 [ffffc9003b50bbc8] wait_on_page_bit at ffffffff811f24d6 #4 [ffffc9003b50bc60] prepare_pages at ffffffff814b05a7 #5 [ffffc9003b50bcd8] btrfs_buffered_write at ffffffff814b1359 #6 [ffffc9003b50bdb0] btrfs_file_write_iter at ffffffff814b5933 #7 [ffffc9003b50be38] new_sync_write at ffffffff8128f6a8 #8 [ffffc9003b50bec8] vfs_write at ffffffff81292b9d #9 [ffffc9003b50bf00] ksys_pwrite64 at ffffffff81293032 I used drgn to find the respective pages we were stuck on page_entry.page 0xffffea00fbfc7500 index 8148 bit 15 pid 2167901 page_entry.page 0xffffea00f9bb7400 index 7680 bit 0 pid 1329874 As you can see the kworker is waiting for bit 0 (PG_locked) on index 7680, and aio-dio-invalid is waiting for bit 15 (PG_writeback) on index 8148. aio-dio-invalid has 7680, and the kworker epd looks like the following crash> struct extent_page_data ffffc900297bbbb0 struct extent_page_data { bio = 0xffff889f747ed830, tree = 0xffff889eed6ba448, extent_locked = 0, sync_io = 0 } Probably worth mentioning as well that it waits for writeback of the page to complete while holding a lock on it (at prepare_pages()). Using drgn I walked the bio pages looking for page 0xffffea00fbfc7500 which is the one we're waiting for writeback on bio = Object(prog, 'struct bio', address=0xffff889f747ed830) for i in range(0, bio.bi_vcnt.value_()): bv = bio.bi_io_vec[i] if bv.bv_page.value_() == 0xffffea00fbfc7500: print("FOUND IT") which validated what I suspected. The fix for this is simple, flush the epd before we loop back around to the beginning of the file during writeout. Fixes: b293f02e1423 ("Btrfs: Add writepages support") CC: stable(a)vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e2d30287e2d5..8ff17bc30d5a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4166,7 +4166,16 @@ static int extent_write_cache_pages(struct address_space *mapping, */ scanned = 1; index = 0; - goto retry; + + /* + * If we're looping we could run into a page that is locked by a + * writer and that writer could be waiting on writeback for a + * page in our current bio, and thus deadlock, so flush the + * write bio here. + */ + ret = flush_write_bio(epd); + if (!ret) + goto retry; } if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))

5 years, 2 months

1
0
0 0

stable-rc/linux-5.4.y boot: 58 boots: 0 failed, 55 passed with 3 offline (v5.4.17-260-ge3082a4e02b8)

by kernelci.org bot

stable-rc/linux-5.4.y boot: 58 boots: 0 failed, 55 passed with 3 offline (v5.4.17-260-ge3082a4e02b8) Full Boot Summary: https://kernelci.org/boot/all/job/stable-rc/branch/linux-5.4.y/kernel/v5.4.… Full Build Summary: https://kernelci.org/build/stable-rc/branch/linux-5.4.y/kernel/v5.4.17-260-… Tree: stable-rc Branch: linux-5.4.y Git Describe: v5.4.17-260-ge3082a4e02b8 Git Commit: e3082a4e02b8a208957ee183e72866caee83f2ff Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git Tested: 56 unique boards, 19 SoC families, 14 builds out of 157 Boot Regressions Detected: arm: qcom_defconfig: gcc-8: qcom-apq8064-cm-qs600: lab-baylibre-seattle: failing since 1 day (last pass: v5.4.17-99-gbd0c6624a110 - first fail: v5.4.17-238-gbffcaa93483d) arm64: defconfig: gcc-8: meson-axg-s400: lab-baylibre-seattle: new failure (last pass: v5.4.17-238-gbffcaa93483d) Offline Platforms: arm: qcom_defconfig: gcc-8 qcom-apq8064-cm-qs600: 1 offline lab imx_v6_v7_defconfig: gcc-8 imx6dl-wandboard_dual: 1 offline lab arm64: defconfig: gcc-8 meson-axg-s400: 1 offline lab --- For more info write to <info(a)kernelci.org>

5 years, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2020