From a835429cda91621fca915d80672a157b47738afb Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 25 Mar 2021 13:01:17 -0700 Subject: [PATCH 1/3] KVM: x86/mmu: Ensure TLBs are flushed when yielding during GFN range zap When flushing a range of GFNs across multiple roots, ensure any pending flush from a previous root is honored before yielding while walking the tables of the current root. Note, kvm_tdp_mmu_zap_gfn_range() now intentionally overwrites its local "flush" with the result to avoid redundant flushes. zap_gfn_range() preserves and return the incoming "flush", unless of course the flush was performed prior to yielding and no new flush was triggered. Fixes: 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed") Cc: stable@vger.kernel.org Reviewed-by: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210325200119.1359384-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d78915019b08..f80648ac1d15 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield); + gfn_t start, gfn_t end, bool can_yield, bool flush); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) { @@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) list_del(&root->link); - zap_gfn_range(kvm, root, 0, max_gfn, false); + zap_gfn_range(kvm, root, 0, max_gfn, false, false); free_page((unsigned long)root->spt); kmem_cache_free(mmu_page_header_cache, root); @@ -678,20 +678,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, * scheduler needs the CPU or there is contention on the MMU lock. If this * function cannot yield, it will not release the MMU lock or reschedule and * the caller must ensure it does not supply too large a GFN range, or the - * operation can cause a soft lockup. + * operation can cause a soft lockup. Note, in some use cases a flush may be + * required by prior actions. Ensure the pending flush is performed prior to + * yielding. */ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield) + gfn_t start, gfn_t end, bool can_yield, bool flush) { struct tdp_iter iter; - bool flush_needed = false; rcu_read_lock(); tdp_root_for_each_pte(iter, root, start, end) { if (can_yield && - tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) { - flush_needed = false; + tdp_mmu_iter_cond_resched(kvm, &iter, flush)) { + flush = false; continue; } @@ -709,11 +710,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, continue; tdp_mmu_set_spte(kvm, &iter, 0); - flush_needed = true; + flush = true; } rcu_read_unlock(); - return flush_needed; + return flush; } /* @@ -728,7 +729,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) bool flush = false; for_each_tdp_mmu_root_yield_safe(kvm, root) - flush |= zap_gfn_range(kvm, root, start, end, true); + flush = zap_gfn_range(kvm, root, start, end, true, flush); return flush; } @@ -940,7 +941,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, unsigned long unused) { - return zap_gfn_range(kvm, root, start, end, false); + return zap_gfn_range(kvm, root, start, end, false, false); } int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start, From 048f49809c526348775425420fb5b8e84fd9a133 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 25 Mar 2021 13:01:18 -0700 Subject: [PATCH 2/3] KVM: x86/mmu: Ensure TLBs are flushed for TDP MMU during NX zapping Honor the "flush needed" return from kvm_tdp_mmu_zap_gfn_range(), which does the flush itself if and only if it yields (which it will never do in this particular scenario), and otherwise expects the caller to do the flush. If pages are zapped from the TDP MMU but not the legacy MMU, then no flush will occur. Fixes: 29cf0f5007a2 ("kvm: x86/mmu: NX largepage recovery for TDP MMU") Cc: stable@vger.kernel.org Cc: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210325200119.1359384-3-seanjc@google.com> Reviewed-by: Ben Gardon Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index d75524bc8423..2705f9fa22b9 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5884,6 +5884,8 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) struct kvm_mmu_page *sp; unsigned int ratio; LIST_HEAD(invalid_list); + bool flush = false; + gfn_t gfn_end; ulong to_zap; rcu_idx = srcu_read_lock(&kvm->srcu); @@ -5905,19 +5907,20 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) lpage_disallowed_link); WARN_ON_ONCE(!sp->lpage_disallowed); if (is_tdp_mmu_page(sp)) { - kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, - sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level)); + gfn_end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); + flush = kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, gfn_end); } else { kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->lpage_disallowed); } if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); cond_resched_rwlock_write(&kvm->mmu_lock); + flush = false; } } - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); From 33a3164161fc86b9cc238f7f2aa2ccb1d5559b1c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 25 Mar 2021 13:01:19 -0700 Subject: [PATCH 3/3] KVM: x86/mmu: Don't allow TDP MMU to yield when recovering NX pages Prevent the TDP MMU from yielding when zapping a gfn range during NX page recovery. If a flush is pending from a previous invocation of the zapping helper, either in the TDP MMU or the legacy MMU, but the TDP MMU has not accumulated a flush for the current invocation, then yielding will release mmu_lock with stale TLB entries. That being said, this isn't technically a bug fix in the current code, as the TDP MMU will never yield in this case. tdp_mmu_iter_cond_resched() will yield if and only if it has made forward progress, as defined by the current gfn vs. the last yielded (or starting) gfn. Because zapping a single shadow page is guaranteed to (a) find that page and (b) step sideways at the level of the shadow page, the TDP iter will break its loop before getting a chance to yield. But that is all very, very subtle, and will break at the slightest sneeze, e.g. zapping while holding mmu_lock for read would break as the TDP MMU wouldn't be guaranteed to see the present shadow page, and thus could step sideways at a lower level. Cc: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210325200119.1359384-4-seanjc@google.com> [Add lockdep assertion. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 4 +--- arch/x86/kvm/mmu/tdp_mmu.c | 5 +++-- arch/x86/kvm/mmu/tdp_mmu.h | 24 +++++++++++++++++++++++- 3 files changed, 27 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2705f9fa22b9..486aa94ecf1d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5885,7 +5885,6 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) unsigned int ratio; LIST_HEAD(invalid_list); bool flush = false; - gfn_t gfn_end; ulong to_zap; rcu_idx = srcu_read_lock(&kvm->srcu); @@ -5907,8 +5906,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) lpage_disallowed_link); WARN_ON_ONCE(!sp->lpage_disallowed); if (is_tdp_mmu_page(sp)) { - gfn_end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); - flush = kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, gfn_end); + flush = kvm_tdp_mmu_zap_sp(kvm, sp); } else { kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->lpage_disallowed); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index f80648ac1d15..81352cd428fa 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -723,13 +723,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, * SPTEs have been cleared and a TLB flush is needed before releasing the * MMU lock. */ -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield) { struct kvm_mmu_page *root; bool flush = false; for_each_tdp_mmu_root_yield_safe(kvm, root) - flush = zap_gfn_range(kvm, root, start, end, true, flush); + flush = zap_gfn_range(kvm, root, start, end, can_yield, flush); return flush; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 3b761c111bff..31096ece9b14 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -8,7 +8,29 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root); -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end); +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield); +static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, + gfn_t end) +{ + return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true); +} +static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); + + /* + * Don't allow yielding, as the caller may have a flush pending. Note, + * if mmu_lock is held for write, zapping will never yield in this case, + * but explicitly disallow it for safety. The TDP MMU does not yield + * until it has made forward progress (steps sideways), and when zapping + * a single shadow page that it's guaranteed to see (thus the mmu_lock + * requirement), its "step sideways" will always step beyond the bounds + * of the shadow page's gfn range and stop iterating before yielding. + */ + lockdep_assert_held_write(&kvm->mmu_lock); + return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false); +} void kvm_tdp_mmu_zap_all(struct kvm *kvm); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,