[PATCH stable-4.19.y backport 1/2] KVM: Pass MMU notifier 'blockable' flag to kvm_unmap_hva_range()
commit fdfe7cbd58806522e799e2a50a15aee7f2cbb7b6 upstream.
The 'blockable' flag passed to the 'invalidate_range_start()' call back of 'struct mmu_notifier' is used to indicate whether the function is permitted to block. In the case of kvm_mmu_notifier_invalidate_range_start(), this field is not forwarded on to the architecture-specific implementation of kvm_unmap_hva_range() and therefore the backend cannot sensibly decide whether or not to block.
Add an extra 'blockable' parameter to kvm_unmap_hva_range() so that architectures are aware as to whether or not they are permitted to block.
Cc: stable@vger.kernel.org # v4.19 only Cc: Marc Zyngier maz@kernel.org Cc: Suzuki K Poulose suzuki.poulose@arm.com Cc: James Morse james.morse@arm.com Signed-off-by: Will Deacon will@kernel.org Message-Id: 20200811102725.7121-2-will@kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com [will: Backport to 4.19; use 'blockable' instead of non-existent range flags] Signed-off-by: Will Deacon will@kernel.org --- arch/arm/include/asm/kvm_host.h | 2 +- arch/arm64/include/asm/kvm_host.h | 2 +- arch/mips/include/asm/kvm_host.h | 2 +- arch/mips/kvm/mmu.c | 3 ++- arch/powerpc/include/asm/kvm_host.h | 3 ++- arch/powerpc/kvm/book3s.c | 3 ++- arch/powerpc/kvm/e500_mmu_host.c | 3 ++- arch/x86/include/asm/kvm_host.h | 3 ++- arch/x86/kvm/mmu.c | 3 ++- virt/kvm/arm/mmu.c | 2 +- virt/kvm/kvm_main.c | 2 +- 11 files changed, 17 insertions(+), 11 deletions(-)
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c9128bb187f9..471859cbfe0b 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -234,7 +234,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
#define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool blockable); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e9afdfcb8403..5e720742d647 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -370,7 +370,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
#define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool blockable); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 2b3fdfc9e0e7..c254761cb8ad 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -936,7 +936,7 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu,
#define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool blockable); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index d8dcdb350405..098a7afd4d38 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -512,7 +512,8 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; }
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 2f95e38f0549..7b54d8412367 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -68,7 +68,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER
extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + bool blockable); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index cc05f346e042..bc9d1321dc73 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -812,7 +812,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new); }
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 8f2985e46f6f..bbb02195dc53 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -737,7 +737,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; }
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ce7b3b22ae86..4876411a072a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1465,7 +1465,8 @@ asmlinkage void __noreturn kvm_spurious_fault(void); ____kvm_handle_fault_on_reboot(insn, "")
#define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 92ff656e1810..a2ff5c214738 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1956,7 +1956,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); }
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + bool blockable) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); } diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index a5bc10d30618..3957ff0ecda5 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1825,7 +1825,7 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *dat }
int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, bool blockable) { if (!kvm->arch.pgd) return 0; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1218ea663c6d..2155b52b17ec 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -410,7 +410,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; - need_tlb_flush = kvm_unmap_hva_range(kvm, start, end); + need_tlb_flush = kvm_unmap_hva_range(kvm, start, end, blockable); need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush)
commit b5331379bc62611d1026173a09c73573384201d9 upstream.
When an MMU notifier call results in unmapping a range that spans multiple PGDs, we end up calling into cond_resched_lock() when crossing a PGD boundary, since this avoids running into RCU stalls during VM teardown. Unfortunately, if the VM is destroyed as a result of OOM, then blocking is not permitted and the call to the scheduler triggers the following BUG():
| BUG: sleeping function called from invalid context at arch/arm64/kvm/mmu.c:394 | in_atomic(): 1, irqs_disabled(): 0, non_block: 1, pid: 36, name: oom_reaper | INFO: lockdep is turned off. | CPU: 3 PID: 36 Comm: oom_reaper Not tainted 5.8.0 #1 | Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015 | Call trace: | dump_backtrace+0x0/0x284 | show_stack+0x1c/0x28 | dump_stack+0xf0/0x1a4 | ___might_sleep+0x2bc/0x2cc | unmap_stage2_range+0x160/0x1ac | kvm_unmap_hva_range+0x1a0/0x1c8 | kvm_mmu_notifier_invalidate_range_start+0x8c/0xf8 | __mmu_notifier_invalidate_range_start+0x218/0x31c | mmu_notifier_invalidate_range_start_nonblock+0x78/0xb0 | __oom_reap_task_mm+0x128/0x268 | oom_reap_task+0xac/0x298 | oom_reaper+0x178/0x17c | kthread+0x1e4/0x1fc | ret_from_fork+0x10/0x30
Use the new 'blockable' argument to kvm_unmap_hva_range() to ensure that we only reschedule if blocking is permitted by the MMU notifier call.
Cc: stable@vger.kernel.org # v4.19 only Fixes: 8b3405e345b5 ("kvm: arm/arm64: Fix locking for kvm_free_stage2_pgd") Cc: Marc Zyngier maz@kernel.org Cc: Suzuki K Poulose suzuki.poulose@arm.com Cc: James Morse james.morse@arm.com Signed-off-by: Will Deacon will@kernel.org Message-Id: 20200811102725.7121-3-will@kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com [will: Backport to 4.19; use 'blockable' instead of non-existent MMU_NOTIFIER_RANGE_BLOCKABLE flag] Signed-off-by: Will Deacon will@kernel.org --- virt/kvm/arm/mmu.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 3957ff0ecda5..41d6285c3da9 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -323,7 +323,8 @@ static void unmap_stage2_puds(struct kvm *kvm, pgd_t *pgd, * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ -static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) +static void __unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size, + bool may_block) { pgd_t *pgd; phys_addr_t addr = start, end = start + size; @@ -348,11 +349,16 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) * If the range is too large, release the kvm->mmu_lock * to prevent starvation and lockup detector warnings. */ - if (next != end) + if (may_block && next != end) cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); }
+static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) +{ + __unmap_stage2_range(kvm, start, size, true); +} + static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -1820,7 +1826,9 @@ static int handle_hva_to_gpa(struct kvm *kvm,
static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) { - unmap_stage2_range(kvm, gpa, size); + bool may_block = *(bool *)data; + + __unmap_stage2_range(kvm, gpa, size, may_block); return 0; }
@@ -1831,7 +1839,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, return 0;
trace_kvm_unmap_hva_range(start, end); - handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &blockable); return 0; }
linux-stable-mirror@lists.linaro.org
-
Will Deacon