--- /dev/null
+From fb50942b0b7deaf416331b5ca2b5ce1c11a78d45 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sat, 6 Feb 2021 09:53:33 -0500
+Subject: KVM: x86: compile out TDP MMU on 32-bit systems
+
+From: Paolo Bonzini <pbonzini@redhat.com>
+
+[ Upstream commit 897218ff7cf19290ec2d69652ce673d8ed6fedeb ]
+
+The TDP MMU assumes that it can do atomic accesses to 64-bit PTEs.
+Rather than just disabling it, compile it out completely so that it
+is possible to use for example 64-bit xchg.
+
+To limit the number of stubs, wrap all accesses to tdp_mmu_enabled
+or tdp_mmu_page with a function. Calls to all other functions in
+tdp_mmu.c are eliminated and do not even reach the linker.
+
+Reviewed-by: Sean Christopherson <seanjc@google.com>
+Tested-by: Sean Christopherson <seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/include/asm/kvm_host.h | 2 ++
+ arch/x86/kvm/Makefile | 3 ++-
+ arch/x86/kvm/mmu/mmu.c | 36 ++++++++++++++++-----------------
+ arch/x86/kvm/mmu/mmu_internal.h | 2 ++
+ arch/x86/kvm/mmu/tdp_mmu.c | 29 +-------------------------
+ arch/x86/kvm/mmu/tdp_mmu.h | 32 +++++++++++++++++++++++++----
+ 6 files changed, 53 insertions(+), 51 deletions(-)
+
+diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
+index 47cd8f9b3fe7..af858f495e75 100644
+--- a/arch/x86/include/asm/kvm_host.h
++++ b/arch/x86/include/asm/kvm_host.h
+@@ -1001,6 +1001,7 @@ struct kvm_arch {
+ struct kvm_pmu_event_filter *pmu_event_filter;
+ struct task_struct *nx_lpage_recovery_thread;
+
++#ifdef CONFIG_X86_64
+ /*
+ * Whether the TDP MMU is enabled for this VM. This contains a
+ * snapshot of the TDP MMU module parameter from when the VM was
+@@ -1027,6 +1028,7 @@ struct kvm_arch {
+ * the thread holds the MMU lock in write mode.
+ */
+ spinlock_t tdp_mmu_pages_lock;
++#endif /* CONFIG_X86_64 */
+ };
+
+ struct kvm_vm_stat {
+diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
+index b804444e16d4..1d1e31917a88 100644
+--- a/arch/x86/kvm/Makefile
++++ b/arch/x86/kvm/Makefile
+@@ -16,7 +16,8 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
+ kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \
+ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
+ hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \
+- mmu/spte.o mmu/tdp_iter.o mmu/tdp_mmu.o
++ mmu/spte.o
++kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
+
+ kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
+ vmx/evmcs.o vmx/nested.o vmx/posted_intr.o
+diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
+index 0f45ad05f895..94e6bf004576 100644
+--- a/arch/x86/kvm/mmu/mmu.c
++++ b/arch/x86/kvm/mmu/mmu.c
+@@ -1225,7 +1225,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+ {
+ struct kvm_rmap_head *rmap_head;
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+ slot->base_gfn + gfn_offset, mask, true);
+ while (mask) {
+@@ -1254,7 +1254,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+ {
+ struct kvm_rmap_head *rmap_head;
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+ slot->base_gfn + gfn_offset, mask, false);
+ while (mask) {
+@@ -1301,7 +1301,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+ write_protected |= __rmap_write_protect(kvm, rmap_head, true);
+ }
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ write_protected |=
+ kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn);
+
+@@ -1513,7 +1513,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+
+ r = kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ r |= kvm_tdp_mmu_zap_hva_range(kvm, start, end);
+
+ return r;
+@@ -1525,7 +1525,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+
+ r = kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ r |= kvm_tdp_mmu_set_spte_hva(kvm, hva, &pte);
+
+ return r;
+@@ -1580,7 +1580,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
+ int young = false;
+
+ young = kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ young |= kvm_tdp_mmu_age_hva_range(kvm, start, end);
+
+ return young;
+@@ -1591,7 +1591,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+ int young = false;
+
+ young = kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp);
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ young |= kvm_tdp_mmu_test_age_hva(kvm, hva);
+
+ return young;
+@@ -3153,7 +3153,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
+ sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK);
+
+ if (kvm_mmu_put_root(kvm, sp)) {
+- if (sp->tdp_mmu_page)
++ if (is_tdp_mmu_page(sp))
+ kvm_tdp_mmu_free_root(kvm, sp);
+ else if (sp->role.invalid)
+ kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
+@@ -3247,7 +3247,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
+ hpa_t root;
+ unsigned i;
+
+- if (vcpu->kvm->arch.tdp_mmu_enabled) {
++ if (is_tdp_mmu_enabled(vcpu->kvm)) {
+ root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu);
+
+ if (!VALID_PAGE(root))
+@@ -5434,7 +5434,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
+
+ kvm_zap_obsolete_pages(kvm);
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_zap_all(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+@@ -5497,7 +5497,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
+ }
+ }
+
+- if (kvm->arch.tdp_mmu_enabled) {
++ if (is_tdp_mmu_enabled(kvm)) {
+ flush = kvm_tdp_mmu_zap_gfn_range(kvm, gfn_start, gfn_end);
+ if (flush)
+ kvm_flush_remote_tlbs(kvm);
+@@ -5521,7 +5521,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
+ spin_lock(&kvm->mmu_lock);
+ flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect,
+ start_level, KVM_MAX_HUGEPAGE_LEVEL, false);
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_4K);
+ spin_unlock(&kvm->mmu_lock);
+
+@@ -5587,7 +5587,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
+ slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
+ kvm_mmu_zap_collapsible_spte, true);
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_zap_collapsible_sptes(kvm, memslot);
+ spin_unlock(&kvm->mmu_lock);
+ }
+@@ -5614,7 +5614,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
+
+ spin_lock(&kvm->mmu_lock);
+ flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
+ spin_unlock(&kvm->mmu_lock);
+
+@@ -5637,7 +5637,7 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
+ spin_lock(&kvm->mmu_lock);
+ flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
+ false);
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M);
+ spin_unlock(&kvm->mmu_lock);
+
+@@ -5653,7 +5653,7 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm,
+
+ spin_lock(&kvm->mmu_lock);
+ flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot);
+ spin_unlock(&kvm->mmu_lock);
+
+@@ -5681,7 +5681,7 @@ void kvm_mmu_zap_all(struct kvm *kvm)
+
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+
+- if (kvm->arch.tdp_mmu_enabled)
++ if (is_tdp_mmu_enabled(kvm))
+ kvm_tdp_mmu_zap_all(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+@@ -5992,7 +5992,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
+ struct kvm_mmu_page,
+ lpage_disallowed_link);
+ WARN_ON_ONCE(!sp->lpage_disallowed);
+- if (sp->tdp_mmu_page) {
++ if (is_tdp_mmu_page(sp)) {
+ kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
+ sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+ } else {
+diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
+index 7f599cc64178..cf67fa6fb8fe 100644
+--- a/arch/x86/kvm/mmu/mmu_internal.h
++++ b/arch/x86/kvm/mmu/mmu_internal.h
+@@ -56,10 +56,12 @@ struct kvm_mmu_page {
+ /* Number of writes since the last time traversal visited this page. */
+ atomic_t write_flooding_count;
+
++#ifdef CONFIG_X86_64
+ bool tdp_mmu_page;
+
+ /* Used for freeing the page asyncronously if it is a TDP MMU page. */
+ struct rcu_head rcu_head;
++#endif
+ };
+
+ extern struct kmem_cache *mmu_page_header_cache;
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index eb38f74af3f2..075b9d63bd57 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -10,24 +10,13 @@
+ #include <asm/cmpxchg.h>
+ #include <trace/events/kvm.h>
+
+-#ifdef CONFIG_X86_64
+ static bool __read_mostly tdp_mmu_enabled = false;
+ module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
+-#endif
+-
+-static bool is_tdp_mmu_enabled(void)
+-{
+-#ifdef CONFIG_X86_64
+- return tdp_enabled && READ_ONCE(tdp_mmu_enabled);
+-#else
+- return false;
+-#endif /* CONFIG_X86_64 */
+-}
+
+ /* Initializes the TDP MMU for the VM, if enabled. */
+ void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+ {
+- if (!is_tdp_mmu_enabled())
++ if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled))
+ return;
+
+ /* This should not be changed for the lifetime of the VM. */
+@@ -96,22 +85,6 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
+ #define for_each_tdp_mmu_root(_kvm, _root) \
+ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
+
+-bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
+-{
+- struct kvm_mmu_page *sp;
+-
+- if (!kvm->arch.tdp_mmu_enabled)
+- return false;
+- if (WARN_ON(!VALID_PAGE(hpa)))
+- return false;
+-
+- sp = to_shadow_page(hpa);
+- if (WARN_ON(!sp))
+- return false;
+-
+- return sp->tdp_mmu_page && sp->root_count;
+-}
+-
+ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end, bool can_yield, bool flush);
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
+index cbbdbadd1526..b4b65e3699b3 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.h
++++ b/arch/x86/kvm/mmu/tdp_mmu.h
+@@ -5,10 +5,6 @@
+
+ #include <linux/kvm_host.h>
+
+-void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+-void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
+-
+-bool is_tdp_mmu_root(struct kvm *kvm, hpa_t root);
+ 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);
+
+@@ -47,4 +43,32 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
+ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+ int *root_level);
+
++#ifdef CONFIG_X86_64
++void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
++void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
++static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; }
++static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; }
++#else
++static inline void kvm_mmu_init_tdp_mmu(struct kvm *kvm) {}
++static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {}
++static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; }
++static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; }
++#endif
++
++static inline bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
++{
++ struct kvm_mmu_page *sp;
++
++ if (!is_tdp_mmu_enabled(kvm))
++ return false;
++ if (WARN_ON(!VALID_PAGE(hpa)))
++ return false;
++
++ sp = to_shadow_page(hpa);
++ if (WARN_ON(!sp))
++ return false;
++
++ return is_tdp_mmu_page(sp) && sp->root_count;
++}
++
+ #endif /* __KVM_X86_MMU_TDP_MMU_H */
+--
+2.30.1
+
--- /dev/null
+From de4f8e1d8284e0976baa40ef79d6e0f6cbf5c6c6 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:08 -0800
+Subject: KVM: x86/mmu: Add comment on __tdp_mmu_set_spte
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit fe43fa2f407b9d513f7bcf18142e14e1bf1508d6 ]
+
+__tdp_mmu_set_spte is a very important function in the TDP MMU which
+already accepts several arguments and will take more in future commits.
+To offset this complexity, add a comment to the function describing each
+of the arguemnts.
+
+No functional change intended.
+
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-3-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 16 ++++++++++++++++
+ 1 file changed, 16 insertions(+)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index 34ef3e1a0f84..f88404033e0c 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -395,6 +395,22 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ new_spte, level);
+ }
+
++/*
++ * __tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping
++ * @kvm: kvm instance
++ * @iter: a tdp_iter instance currently on the SPTE that should be set
++ * @new_spte: The value the SPTE should be set to
++ * @record_acc_track: Notify the MM subsystem of changes to the accessed state
++ * of the page. Should be set unless handling an MMU
++ * notifier for access tracking. Leaving record_acc_track
++ * unset in that case prevents page accesses from being
++ * double counted.
++ * @record_dirty_log: Record the page as dirty in the dirty bitmap if
++ * appropriate for the change being made. Should be set
++ * unless performing certain dirty logging operations.
++ * Leaving record_dirty_log unset in that case prevents page
++ * writes from being double counted.
++ */
+ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
+ u64 new_spte, bool record_acc_track,
+ bool record_dirty_log)
+--
+2.30.1
+
--- /dev/null
+From 9feb78a3670411d4bb2ac2800296123d02824f80 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 27 Oct 2020 10:59:43 -0700
+Subject: kvm: x86/mmu: Add existing trace points to TDP MMU
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 33dd3574f5fef57c2c6caccf98925d63aa2a8d09 ]
+
+The TDP MMU was initially implemented without some of the usual
+tracepoints found in mmu.c. Correct this discrepancy by adding the
+missing trace points to the TDP MMU.
+
+Tested: ran the demand paging selftest on an Intel Skylake machine with
+ all the trace points used by the TDP MMU enabled and observed
+ them firing with expected values.
+
+This patch can be viewed in Gerrit at:
+https://linux-review.googlesource.com/c/virt/kvm/kvm/+/3812
+
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20201027175944.1183301-1-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 12 +++++++++++-
+ 1 file changed, 11 insertions(+), 1 deletion(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index 0d17457f1c84..61be95c6db20 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -7,6 +7,8 @@
+ #include "tdp_mmu.h"
+ #include "spte.h"
+
++#include <trace/events/kvm.h>
++
+ #ifdef CONFIG_X86_64
+ static bool __read_mostly tdp_mmu_enabled = false;
+ module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
+@@ -149,6 +151,8 @@ static struct kvm_mmu_page *alloc_tdp_mmu_page(struct kvm_vcpu *vcpu, gfn_t gfn,
+ sp->gfn = gfn;
+ sp->tdp_mmu_page = true;
+
++ trace_kvm_mmu_get_page(sp, true);
++
+ return sp;
+ }
+
+@@ -319,6 +323,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ pt = spte_to_child_pt(old_spte, level);
+ sp = sptep_to_sp(pt);
+
++ trace_kvm_mmu_prepare_zap_page(sp);
++
+ list_del(&sp->link);
+
+ if (sp->lpage_disallowed)
+@@ -530,11 +536,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
+ if (unlikely(is_noslot_pfn(pfn))) {
+ new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
+ trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte);
+- } else
++ } else {
+ make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn,
+ pfn, iter->old_spte, prefault, true,
+ map_writable, !shadow_accessed_mask,
+ &new_spte);
++ trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
++ }
+
+ if (new_spte == iter->old_spte)
+ ret = RET_PF_SPURIOUS;
+@@ -740,6 +748,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
+
+ tdp_mmu_set_spte_no_acc_track(kvm, &iter, new_spte);
+ young = 1;
++
++ trace_kvm_age_page(iter.gfn, iter.level, slot, young);
+ }
+
+ return young;
+--
+2.30.1
+
--- /dev/null
+From a57a6d516fabcd0ae433d70baa868ba5615722bb Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:09 -0800
+Subject: KVM: x86/mmu: Add lockdep when setting a TDP MMU SPTE
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 3a9a4aa5657471a02ffb7f9b7f3b7a468b3f257b ]
+
+Add lockdep to __tdp_mmu_set_spte to ensure that SPTEs are only modified
+under the MMU lock.
+
+No functional change intended.
+
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Reviewed-by: Sean Christopherson <seanjc@google.com>
+Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-4-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index 61be95c6db20..ad9f8f187045 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -363,6 +363,8 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_mmu_page *root = sptep_to_sp(root_pt);
+ int as_id = kvm_mmu_page_as_id(root);
+
++ lockdep_assert_held(&kvm->mmu_lock);
++
+ WRITE_ONCE(*iter->sptep, new_spte);
+
+ __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
+--
+2.30.1
+
--- /dev/null
+From 39ee9ada40ec00e88a1e2d200d5a27f5cc8ebe73 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:07 -0800
+Subject: KVM: x86/mmu: change TDP MMU yield function returns to match
+ cond_resched
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit e28a436ca4f65384cceaf3f4da0e00aa74244e6a ]
+
+Currently the TDP MMU yield / cond_resched functions either return
+nothing or return true if the TLBs were not flushed. These are confusing
+semantics, especially when making control flow decisions in calling
+functions.
+
+To clean things up, change both functions to have the same
+return value semantics as cond_resched: true if the thread yielded,
+false if it did not. If the function yielded in the _flush_ version,
+then the TLBs will have been flushed.
+
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-2-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 39 ++++++++++++++++++++++++++++----------
+ 1 file changed, 29 insertions(+), 10 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index ffa0bd0e033f..22efd016f05e 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -405,8 +405,15 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
+ _mmu->shadow_root_level, _start, _end)
+
+ /*
+- * Flush the TLB if the process should drop kvm->mmu_lock.
+- * Return whether the caller still needs to flush the tlb.
++ * Flush the TLB and yield if the MMU lock is contended or this thread needs to
++ * return control to the scheduler.
++ *
++ * If this function yields, it will also reset the tdp_iter's walk over the
++ * paging structure and the calling function should allow the iterator to
++ * continue its traversal from the paging structure root.
++ *
++ * Return true if this function yielded, the TLBs were flushed, and the
++ * iterator's traversal was reset. Return false if a yield was not needed.
+ */
+ static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
+ {
+@@ -414,18 +421,32 @@ static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *it
+ kvm_flush_remote_tlbs(kvm);
+ cond_resched_lock(&kvm->mmu_lock);
+ tdp_iter_refresh_walk(iter);
+- return false;
+- } else {
+ return true;
+ }
++
++ return false;
+ }
+
+-static void tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
++/*
++ * Yield if the MMU lock is contended or this thread needs to return control
++ * to the scheduler.
++ *
++ * If this function yields, it will also reset the tdp_iter's walk over the
++ * paging structure and the calling function should allow the iterator to
++ * continue its traversal from the paging structure root.
++ *
++ * Return true if this function yielded and the iterator's traversal was reset.
++ * Return false if a yield was not needed.
++ */
++static bool tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
+ {
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ cond_resched_lock(&kvm->mmu_lock);
+ tdp_iter_refresh_walk(iter);
++ return true;
+ }
++
++ return false;
+ }
+
+ /*
+@@ -461,10 +482,8 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+
+- if (can_yield)
+- flush_needed = tdp_mmu_iter_flush_cond_resched(kvm, &iter);
+- else
+- flush_needed = true;
++ flush_needed = !can_yield ||
++ !tdp_mmu_iter_flush_cond_resched(kvm, &iter);
+ }
+ return flush_needed;
+ }
+@@ -1061,7 +1080,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+
+- spte_set = tdp_mmu_iter_flush_cond_resched(kvm, &iter);
++ spte_set = !tdp_mmu_iter_flush_cond_resched(kvm, &iter);
+ }
+
+ if (spte_set)
+--
+2.30.1
+
--- /dev/null
+From 7ad0aa324fd19e916eae8be382c98efee1b759c6 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:10 -0800
+Subject: KVM: x86/mmu: Don't redundantly clear TDP MMU pt memory
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 734e45b329d626d2c14e2bcf8be3d069a33c3316 ]
+
+The KVM MMU caches already guarantee that shadow page table memory will
+be zeroed, so there is no reason to re-zero the page in the TDP MMU page
+fault handler.
+
+No functional change intended.
+
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Reviewed-by: Sean Christopherson <seanjc@google.com>
+Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-5-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 1 -
+ 1 file changed, 1 deletion(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index f88404033e0c..136311be5890 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -706,7 +706,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+ sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level);
+ list_add(&sp->link, &vcpu->kvm->arch.tdp_mmu_pages);
+ child_pt = sp->spt;
+- clear_page(child_pt);
+ new_spte = make_nonleaf_spte(child_pt,
+ !shadow_accessed_mask);
+
+--
+2.30.1
+
--- /dev/null
+From 102585bd2c96f22c43456229271e8b34177a09db Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:19 -0800
+Subject: KVM: x86/mmu: Ensure forward progress when yielding in TDP MMU iter
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit ed5e484b79e8a9b8be714bd85b6fc70bd6dc99a7 ]
+
+In some functions the TDP iter risks not making forward progress if two
+threads livelock yielding to one another. This is possible if two threads
+are trying to execute wrprot_gfn_range. Each could write protect an entry
+and then yield. This would reset the tdp_iter's walk over the paging
+structure and the loop would end up repeating the same entry over and
+over, preventing either thread from making forward progress.
+
+Fix this issue by only yielding if the loop has made forward progress
+since the last yield.
+
+Fixes: a6a0b05da9f3 ("kvm: x86/mmu: Support dirty logging for the TDP MMU")
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+
+Message-Id: <20210202185734.1680553-14-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_iter.c | 18 +-----------------
+ arch/x86/kvm/mmu/tdp_iter.h | 7 ++++++-
+ arch/x86/kvm/mmu/tdp_mmu.c | 21 ++++++++++++++++-----
+ 3 files changed, 23 insertions(+), 23 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
+index 9917c55b7d24..1a09d212186b 100644
+--- a/arch/x86/kvm/mmu/tdp_iter.c
++++ b/arch/x86/kvm/mmu/tdp_iter.c
+@@ -31,6 +31,7 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
+ WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
+
+ iter->next_last_level_gfn = next_last_level_gfn;
++ iter->yielded_gfn = iter->next_last_level_gfn;
+ iter->root_level = root_level;
+ iter->min_level = min_level;
+ iter->level = root_level;
+@@ -158,23 +159,6 @@ void tdp_iter_next(struct tdp_iter *iter)
+ iter->valid = false;
+ }
+
+-/*
+- * Restart the walk over the paging structure from the root, starting from the
+- * highest gfn the iterator had previously reached. Assumes that the entire
+- * paging structure, except the root page, may have been completely torn down
+- * and rebuilt.
+- */
+-void tdp_iter_refresh_walk(struct tdp_iter *iter)
+-{
+- gfn_t next_last_level_gfn = iter->next_last_level_gfn;
+-
+- if (iter->gfn > next_last_level_gfn)
+- next_last_level_gfn = iter->gfn;
+-
+- tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
+- iter->root_level, iter->min_level, next_last_level_gfn);
+-}
+-
+ u64 *tdp_iter_root_pt(struct tdp_iter *iter)
+ {
+ return iter->pt_path[iter->root_level - 1];
+diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
+index b2dd269c631f..d480c540ee27 100644
+--- a/arch/x86/kvm/mmu/tdp_iter.h
++++ b/arch/x86/kvm/mmu/tdp_iter.h
+@@ -16,6 +16,12 @@ struct tdp_iter {
+ * for this GFN.
+ */
+ gfn_t next_last_level_gfn;
++ /*
++ * The next_last_level_gfn at the time when the thread last
++ * yielded. Only yielding when the next_last_level_gfn !=
++ * yielded_gfn helps ensure forward progress.
++ */
++ gfn_t yielded_gfn;
+ /* Pointers to the page tables traversed to reach the current SPTE */
+ u64 *pt_path[PT64_ROOT_MAX_LEVEL];
+ /* A pointer to the current SPTE */
+@@ -54,7 +60,6 @@ u64 *spte_to_child_pt(u64 pte, int level);
+ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
+ int min_level, gfn_t next_last_level_gfn);
+ void tdp_iter_next(struct tdp_iter *iter);
+-void tdp_iter_refresh_walk(struct tdp_iter *iter);
+ u64 *tdp_iter_root_pt(struct tdp_iter *iter);
+
+ #endif /* __KVM_X86_MMU_TDP_ITER_H */
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index 3b14d0008f92..f0bc5d3ce3d4 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -412,8 +412,9 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
+ * TLB flush before yielding.
+ *
+ * If this function yields, it will also reset the tdp_iter's walk over the
+- * paging structure and the calling function should allow the iterator to
+- * continue its traversal from the paging structure root.
++ * paging structure and the calling function should skip to the next
++ * iteration to allow the iterator to continue its traversal from the
++ * paging structure root.
+ *
+ * Return true if this function yielded and the iterator's traversal was reset.
+ * Return false if a yield was not needed.
+@@ -421,12 +422,22 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
+ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
+ struct tdp_iter *iter, bool flush)
+ {
++ /* Ensure forward progress has been made before yielding. */
++ if (iter->next_last_level_gfn == iter->yielded_gfn)
++ return false;
++
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ if (flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ cond_resched_lock(&kvm->mmu_lock);
+- tdp_iter_refresh_walk(iter);
++
++ WARN_ON(iter->gfn > iter->next_last_level_gfn);
++
++ tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
++ iter->root_level, iter->min_level,
++ iter->next_last_level_gfn);
++
+ return true;
+ }
+
+@@ -466,8 +477,8 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+
+- flush_needed = !can_yield ||
+- !tdp_mmu_iter_cond_resched(kvm, &iter, true);
++ flush_needed = !(can_yield &&
++ tdp_mmu_iter_cond_resched(kvm, &iter, true));
+ }
+ return flush_needed;
+ }
+--
+2.30.1
+
--- /dev/null
+From 9122666303232b5864b8e7926426658024fc61a0 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 25 Mar 2021 13:01:18 -0700
+Subject: KVM: x86/mmu: Ensure TLBs are flushed for TDP MMU during NX zapping
+
+From: Sean Christopherson <seanjc@google.com>
+
+[ Upstream commit 048f49809c526348775425420fb5b8e84fd9a133 ]
+
+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 <bgardon@google.com>
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20210325200119.1359384-3-seanjc@google.com>
+Reviewed-by: Ben Gardon <bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 94e6bf004576..e69248820d01 100644
+--- a/arch/x86/kvm/mmu/mmu.c
++++ b/arch/x86/kvm/mmu/mmu.c
+@@ -5972,6 +5972,8 @@ 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);
+@@ -5993,19 +5995,20 @@ 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() || spin_needbreak(&kvm->mmu_lock)) {
+- kvm_mmu_commit_zap_page(kvm, &invalid_list);
++ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
+ cond_resched_lock(&kvm->mmu_lock);
++ flush = false;
+ }
+ }
+- kvm_mmu_commit_zap_page(kvm, &invalid_list);
++ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, rcu_idx);
+--
+2.30.1
+
--- /dev/null
+From e3018f2b4b268fb9b87ae49094c79601ad19c556 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 25 Mar 2021 13:01:17 -0700
+Subject: KVM: x86/mmu: Ensure TLBs are flushed when yielding during GFN range
+ zap
+
+From: Sean Christopherson <seanjc@google.com>
+
+[ Upstream commit a835429cda91621fca915d80672a157b47738afb ]
+
+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 <bgardon@google.com>
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20210325200119.1359384-2-seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 a54a9ed979d1..34ef3e1a0f84 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -111,7 +111,7 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
+ }
+
+ 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)
+ {
+@@ -124,7 +124,7 @@ 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);
+@@ -504,20 +504,21 @@ 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;
+ }
+
+@@ -535,11 +536,11 @@ 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;
+ }
+
+ /*
+@@ -554,7 +555,7 @@ 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;
+ }
+@@ -757,7 +758,7 @@ 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,
+--
+2.30.1
+
--- /dev/null
+From 2504553be669a5b2f12575b0d7420c35196cf0eb Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:25 -0800
+Subject: KVM: x86/mmu: Factor out functions to add/remove TDP MMU pages
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit a9442f594147f95307f691cfba0c31e25dc79b9d ]
+
+Move the work of adding and removing TDP MMU pages to/from "secondary"
+data structures to helper functions. These functions will be built on in
+future commits to enable MMU operations to proceed (mostly) in parallel.
+
+No functional change expected.
+
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-20-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 47 +++++++++++++++++++++++++++++++-------
+ 1 file changed, 39 insertions(+), 8 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index 136311be5890..14d69c01c710 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -262,6 +262,39 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
+ }
+ }
+
++/**
++ * tdp_mmu_link_page - Add a new page to the list of pages used by the TDP MMU
++ *
++ * @kvm: kvm instance
++ * @sp: the new page
++ * @account_nx: This page replaces a NX large page and should be marked for
++ * eventual reclaim.
++ */
++static void tdp_mmu_link_page(struct kvm *kvm, struct kvm_mmu_page *sp,
++ bool account_nx)
++{
++ lockdep_assert_held_write(&kvm->mmu_lock);
++
++ list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
++ if (account_nx)
++ account_huge_nx_page(kvm, sp);
++}
++
++/**
++ * tdp_mmu_unlink_page - Remove page from the list of pages used by the TDP MMU
++ *
++ * @kvm: kvm instance
++ * @sp: the page to be removed
++ */
++static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp)
++{
++ lockdep_assert_held_write(&kvm->mmu_lock);
++
++ list_del(&sp->link);
++ if (sp->lpage_disallowed)
++ unaccount_huge_nx_page(kvm, sp);
++}
++
+ /**
+ * handle_removed_tdp_mmu_page - handle a pt removed from the TDP structure
+ *
+@@ -281,10 +314,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt)
+
+ trace_kvm_mmu_prepare_zap_page(sp);
+
+- list_del(&sp->link);
+-
+- if (sp->lpage_disallowed)
+- unaccount_huge_nx_page(kvm, sp);
++ tdp_mmu_unlink_page(kvm, sp);
+
+ for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
+ old_child_spte = READ_ONCE(*(pt + i));
+@@ -704,15 +734,16 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+
+ if (!is_shadow_present_pte(iter.old_spte)) {
+ sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level);
+- list_add(&sp->link, &vcpu->kvm->arch.tdp_mmu_pages);
+ child_pt = sp->spt;
++
++ tdp_mmu_link_page(vcpu->kvm, sp,
++ huge_page_disallowed &&
++ req_level >= iter.level);
++
+ new_spte = make_nonleaf_spte(child_pt,
+ !shadow_accessed_mask);
+
+ trace_kvm_mmu_get_page(sp, true);
+- if (huge_page_disallowed && req_level >= iter.level)
+- account_huge_nx_page(vcpu->kvm, sp);
+-
+ tdp_mmu_set_spte(vcpu->kvm, &iter, new_spte);
+ }
+ }
+--
+2.30.1
+
--- /dev/null
+From 342da545328248ab8ea49095d4e9009f77505587 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:11 -0800
+Subject: KVM: x86/mmu: Factor out handling of removed page tables
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit a066e61f13cf4b17d043ad8bea0cdde2b1e5ee49 ]
+
+Factor out the code to handle a disconnected subtree of the TDP paging
+structure from the code to handle the change to an individual SPTE.
+Future commits will build on this to allow asynchronous page freeing.
+
+No functional change intended.
+
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Acked-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+
+Message-Id: <20210202185734.1680553-6-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 71 ++++++++++++++++++++++----------------
+ 1 file changed, 42 insertions(+), 29 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index ad9f8f187045..f52a22bc0fe8 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -234,6 +234,45 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
+ }
+ }
+
++/**
++ * handle_removed_tdp_mmu_page - handle a pt removed from the TDP structure
++ *
++ * @kvm: kvm instance
++ * @pt: the page removed from the paging structure
++ *
++ * Given a page table that has been removed from the TDP paging structure,
++ * iterates through the page table to clear SPTEs and free child page tables.
++ */
++static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt)
++{
++ struct kvm_mmu_page *sp = sptep_to_sp(pt);
++ int level = sp->role.level;
++ gfn_t gfn = sp->gfn;
++ u64 old_child_spte;
++ int i;
++
++ trace_kvm_mmu_prepare_zap_page(sp);
++
++ list_del(&sp->link);
++
++ if (sp->lpage_disallowed)
++ unaccount_huge_nx_page(kvm, sp);
++
++ for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
++ old_child_spte = READ_ONCE(*(pt + i));
++ WRITE_ONCE(*(pt + i), 0);
++ handle_changed_spte(kvm, kvm_mmu_page_as_id(sp),
++ gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)),
++ old_child_spte, 0, level - 1);
++ }
++
++ kvm_flush_remote_tlbs_with_address(kvm, gfn,
++ KVM_PAGES_PER_HPAGE(level));
++
++ free_page((unsigned long)pt);
++ kmem_cache_free(mmu_page_header_cache, sp);
++}
++
+ /**
+ * handle_changed_spte - handle bookkeeping associated with an SPTE change
+ * @kvm: kvm instance
+@@ -254,10 +293,6 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ bool was_leaf = was_present && is_last_spte(old_spte, level);
+ bool is_leaf = is_present && is_last_spte(new_spte, level);
+ bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
+- u64 *pt;
+- struct kvm_mmu_page *sp;
+- u64 old_child_spte;
+- int i;
+
+ WARN_ON(level > PT64_ROOT_MAX_LEVEL);
+ WARN_ON(level < PG_LEVEL_4K);
+@@ -319,31 +354,9 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ * Recursively handle child PTs if the change removed a subtree from
+ * the paging structure.
+ */
+- if (was_present && !was_leaf && (pfn_changed || !is_present)) {
+- pt = spte_to_child_pt(old_spte, level);
+- sp = sptep_to_sp(pt);
+-
+- trace_kvm_mmu_prepare_zap_page(sp);
+-
+- list_del(&sp->link);
+-
+- if (sp->lpage_disallowed)
+- unaccount_huge_nx_page(kvm, sp);
+-
+- for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
+- old_child_spte = READ_ONCE(*(pt + i));
+- WRITE_ONCE(*(pt + i), 0);
+- handle_changed_spte(kvm, as_id,
+- gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)),
+- old_child_spte, 0, level - 1);
+- }
+-
+- kvm_flush_remote_tlbs_with_address(kvm, gfn,
+- KVM_PAGES_PER_HPAGE(level));
+-
+- free_page((unsigned long)pt);
+- kmem_cache_free(mmu_page_header_cache, sp);
+- }
++ if (was_present && !was_leaf && (pfn_changed || !is_present))
++ handle_removed_tdp_mmu_page(kvm,
++ spte_to_child_pt(old_spte, level));
+ }
+
+ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+--
+2.30.1
+
--- /dev/null
+From 6687b6cd3c04a062f341c8c823051a2679167fa9 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:15 -0800
+Subject: KVM: x86/mmu: Fix braces in kvm_recover_nx_lpages
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 8d1a182ea791f0111b0258c8f3eb8d77af0a8386 ]
+
+No functional change intended.
+
+Fixes: 29cf0f5007a2 ("kvm: x86/mmu: NX largepage recovery for TDP MMU")
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-10-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/mmu.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
+index dacbd13d32c6..0f45ad05f895 100644
+--- a/arch/x86/kvm/mmu/mmu.c
++++ b/arch/x86/kvm/mmu/mmu.c
+@@ -5992,10 +5992,10 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
+ struct kvm_mmu_page,
+ lpage_disallowed_link);
+ WARN_ON_ONCE(!sp->lpage_disallowed);
+- if (sp->tdp_mmu_page)
++ if (sp->tdp_mmu_page) {
+ kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
+ sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+- else {
++ } else {
+ kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+ WARN_ON_ONCE(sp->lpage_disallowed);
+ }
+--
+2.30.1
+
--- /dev/null
+From 2e2b695fb5d990619460c0f8515c25fadd44634e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:17 -0800
+Subject: KVM: x86/mmu: Merge flush and non-flush tdp_mmu_iter_cond_resched
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit e139a34ef9d5627a41e1c02210229082140d1f92 ]
+
+The flushing and non-flushing variants of tdp_mmu_iter_cond_resched have
+almost identical implementations. Merge the two functions and add a
+flush parameter.
+
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-12-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 42 ++++++++++++--------------------------
+ 1 file changed, 13 insertions(+), 29 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index 22efd016f05e..3b14d0008f92 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -404,33 +404,13 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
+ for_each_tdp_pte(_iter, __va(_mmu->root_hpa), \
+ _mmu->shadow_root_level, _start, _end)
+
+-/*
+- * Flush the TLB and yield if the MMU lock is contended or this thread needs to
+- * return control to the scheduler.
+- *
+- * If this function yields, it will also reset the tdp_iter's walk over the
+- * paging structure and the calling function should allow the iterator to
+- * continue its traversal from the paging structure root.
+- *
+- * Return true if this function yielded, the TLBs were flushed, and the
+- * iterator's traversal was reset. Return false if a yield was not needed.
+- */
+-static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
+-{
+- if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+- kvm_flush_remote_tlbs(kvm);
+- cond_resched_lock(&kvm->mmu_lock);
+- tdp_iter_refresh_walk(iter);
+- return true;
+- }
+-
+- return false;
+-}
+-
+ /*
+ * Yield if the MMU lock is contended or this thread needs to return control
+ * to the scheduler.
+ *
++ * If this function should yield and flush is set, it will perform a remote
++ * TLB flush before yielding.
++ *
+ * If this function yields, it will also reset the tdp_iter's walk over the
+ * paging structure and the calling function should allow the iterator to
+ * continue its traversal from the paging structure root.
+@@ -438,9 +418,13 @@ static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *it
+ * Return true if this function yielded and the iterator's traversal was reset.
+ * Return false if a yield was not needed.
+ */
+-static bool tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
++static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
++ struct tdp_iter *iter, bool flush)
+ {
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
++ if (flush)
++ kvm_flush_remote_tlbs(kvm);
++
+ cond_resched_lock(&kvm->mmu_lock);
+ tdp_iter_refresh_walk(iter);
+ return true;
+@@ -483,7 +467,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ tdp_mmu_set_spte(kvm, &iter, 0);
+
+ flush_needed = !can_yield ||
+- !tdp_mmu_iter_flush_cond_resched(kvm, &iter);
++ !tdp_mmu_iter_cond_resched(kvm, &iter, true);
+ }
+ return flush_needed;
+ }
+@@ -852,7 +836,7 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ spte_set = true;
+
+- tdp_mmu_iter_cond_resched(kvm, &iter);
++ tdp_mmu_iter_cond_resched(kvm, &iter, false);
+ }
+ return spte_set;
+ }
+@@ -911,7 +895,7 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ spte_set = true;
+
+- tdp_mmu_iter_cond_resched(kvm, &iter);
++ tdp_mmu_iter_cond_resched(kvm, &iter, false);
+ }
+ return spte_set;
+ }
+@@ -1027,7 +1011,7 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ tdp_mmu_set_spte(kvm, &iter, new_spte);
+ spte_set = true;
+
+- tdp_mmu_iter_cond_resched(kvm, &iter);
++ tdp_mmu_iter_cond_resched(kvm, &iter, false);
+ }
+
+ return spte_set;
+@@ -1080,7 +1064,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+
+- spte_set = !tdp_mmu_iter_flush_cond_resched(kvm, &iter);
++ spte_set = !tdp_mmu_iter_cond_resched(kvm, &iter, true);
+ }
+
+ if (spte_set)
+--
+2.30.1
+
--- /dev/null
+From f6946783dd38dbc2bd758be27a17a0d47a563f25 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:23 -0800
+Subject: KVM: x86/mmu: Protect TDP MMU page table memory with RCU
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 7cca2d0b7e7d9f3cd740d41afdc00051c9b508a0 ]
+
+In order to enable concurrent modifications to the paging structures in
+the TDP MMU, threads must be able to safely remove pages of page table
+memory while other threads are traversing the same memory. To ensure
+threads do not access PT memory after it is freed, protect PT memory
+with RCU.
+
+Protecting concurrent accesses to page table memory from use-after-free
+bugs could also have been acomplished using
+walk_shadow_page_lockless_begin/end() and READING_SHADOW_PAGE_TABLES,
+coupling with the barriers in a TLB flush. The use of RCU for this case
+has several distinct advantages over that approach.
+1. Disabling interrupts for long running operations is not desirable.
+ Future commits will allow operations besides page faults to operate
+ without the exclusive protection of the MMU lock and those operations
+ are too long to disable iterrupts for their duration.
+2. The use of RCU here avoids long blocking / spinning operations in
+ perfromance critical paths. By freeing memory with an asynchronous
+ RCU API we avoid the longer wait times TLB flushes experience when
+ overlapping with a thread in walk_shadow_page_lockless_begin/end().
+3. RCU provides a separation of concerns when removing memory from the
+ paging structure. Because the RCU callback to free memory can be
+ scheduled immediately after a TLB flush, there's no need for the
+ thread to manually free a queue of pages later, as commit_zap_pages
+ does.
+
+Fixes: 95fb5b0258b7 ("kvm: x86/mmu: Support MMIO in the TDP MMU")
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Suggested-by: Sean Christopherson <seanjc@google.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+
+Message-Id: <20210202185734.1680553-18-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/mmu_internal.h | 3 ++
+ arch/x86/kvm/mmu/tdp_iter.c | 16 +++---
+ arch/x86/kvm/mmu/tdp_iter.h | 10 ++--
+ arch/x86/kvm/mmu/tdp_mmu.c | 95 +++++++++++++++++++++++++++++----
+ 4 files changed, 103 insertions(+), 21 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
+index bfc6389edc28..7f599cc64178 100644
+--- a/arch/x86/kvm/mmu/mmu_internal.h
++++ b/arch/x86/kvm/mmu/mmu_internal.h
+@@ -57,6 +57,9 @@ struct kvm_mmu_page {
+ atomic_t write_flooding_count;
+
+ bool tdp_mmu_page;
++
++ /* Used for freeing the page asyncronously if it is a TDP MMU page. */
++ struct rcu_head rcu_head;
+ };
+
+ extern struct kmem_cache *mmu_page_header_cache;
+diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
+index 1a09d212186b..e5f148106e20 100644
+--- a/arch/x86/kvm/mmu/tdp_iter.c
++++ b/arch/x86/kvm/mmu/tdp_iter.c
+@@ -12,7 +12,7 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter)
+ {
+ iter->sptep = iter->pt_path[iter->level - 1] +
+ SHADOW_PT_INDEX(iter->gfn << PAGE_SHIFT, iter->level);
+- iter->old_spte = READ_ONCE(*iter->sptep);
++ iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
+ }
+
+ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
+@@ -35,7 +35,7 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
+ iter->root_level = root_level;
+ iter->min_level = min_level;
+ iter->level = root_level;
+- iter->pt_path[iter->level - 1] = root_pt;
++ iter->pt_path[iter->level - 1] = (tdp_ptep_t)root_pt;
+
+ iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+ tdp_iter_refresh_sptep(iter);
+@@ -48,7 +48,7 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
+ * address of the child page table referenced by the SPTE. Returns null if
+ * there is no such entry.
+ */
+-u64 *spte_to_child_pt(u64 spte, int level)
++tdp_ptep_t spte_to_child_pt(u64 spte, int level)
+ {
+ /*
+ * There's no child entry if this entry isn't present or is a
+@@ -57,7 +57,7 @@ u64 *spte_to_child_pt(u64 spte, int level)
+ if (!is_shadow_present_pte(spte) || is_last_spte(spte, level))
+ return NULL;
+
+- return __va(spte_to_pfn(spte) << PAGE_SHIFT);
++ return (tdp_ptep_t)__va(spte_to_pfn(spte) << PAGE_SHIFT);
+ }
+
+ /*
+@@ -66,7 +66,7 @@ u64 *spte_to_child_pt(u64 spte, int level)
+ */
+ static bool try_step_down(struct tdp_iter *iter)
+ {
+- u64 *child_pt;
++ tdp_ptep_t child_pt;
+
+ if (iter->level == iter->min_level)
+ return false;
+@@ -75,7 +75,7 @@ static bool try_step_down(struct tdp_iter *iter)
+ * Reread the SPTE before stepping down to avoid traversing into page
+ * tables that are no longer linked from this entry.
+ */
+- iter->old_spte = READ_ONCE(*iter->sptep);
++ iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
+
+ child_pt = spte_to_child_pt(iter->old_spte, iter->level);
+ if (!child_pt)
+@@ -109,7 +109,7 @@ static bool try_step_side(struct tdp_iter *iter)
+ iter->gfn += KVM_PAGES_PER_HPAGE(iter->level);
+ iter->next_last_level_gfn = iter->gfn;
+ iter->sptep++;
+- iter->old_spte = READ_ONCE(*iter->sptep);
++ iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
+
+ return true;
+ }
+@@ -159,7 +159,7 @@ void tdp_iter_next(struct tdp_iter *iter)
+ iter->valid = false;
+ }
+
+-u64 *tdp_iter_root_pt(struct tdp_iter *iter)
++tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter)
+ {
+ return iter->pt_path[iter->root_level - 1];
+ }
+diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
+index d480c540ee27..4cc177d75c4a 100644
+--- a/arch/x86/kvm/mmu/tdp_iter.h
++++ b/arch/x86/kvm/mmu/tdp_iter.h
+@@ -7,6 +7,8 @@
+
+ #include "mmu.h"
+
++typedef u64 __rcu *tdp_ptep_t;
++
+ /*
+ * A TDP iterator performs a pre-order walk over a TDP paging structure.
+ */
+@@ -23,9 +25,9 @@ struct tdp_iter {
+ */
+ gfn_t yielded_gfn;
+ /* Pointers to the page tables traversed to reach the current SPTE */
+- u64 *pt_path[PT64_ROOT_MAX_LEVEL];
++ tdp_ptep_t pt_path[PT64_ROOT_MAX_LEVEL];
+ /* A pointer to the current SPTE */
+- u64 *sptep;
++ tdp_ptep_t sptep;
+ /* The lowest GFN mapped by the current SPTE */
+ gfn_t gfn;
+ /* The level of the root page given to the iterator */
+@@ -55,11 +57,11 @@ struct tdp_iter {
+ #define for_each_tdp_pte(iter, root, root_level, start, end) \
+ for_each_tdp_pte_min_level(iter, root, root_level, PG_LEVEL_4K, start, end)
+
+-u64 *spte_to_child_pt(u64 pte, int level);
++tdp_ptep_t spte_to_child_pt(u64 pte, int level);
+
+ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
+ int min_level, gfn_t next_last_level_gfn);
+ void tdp_iter_next(struct tdp_iter *iter);
+-u64 *tdp_iter_root_pt(struct tdp_iter *iter);
++tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter);
+
+ #endif /* __KVM_X86_MMU_TDP_ITER_H */
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index f52a22bc0fe8..a54a9ed979d1 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -42,6 +42,12 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
+ return;
+
+ WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
++
++ /*
++ * Ensure that all the outstanding RCU callbacks to free shadow pages
++ * can run before the VM is torn down.
++ */
++ rcu_barrier();
+ }
+
+ static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
+@@ -196,6 +202,28 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
+ return __pa(root->spt);
+ }
+
++static void tdp_mmu_free_sp(struct kvm_mmu_page *sp)
++{
++ free_page((unsigned long)sp->spt);
++ kmem_cache_free(mmu_page_header_cache, sp);
++}
++
++/*
++ * This is called through call_rcu in order to free TDP page table memory
++ * safely with respect to other kernel threads that may be operating on
++ * the memory.
++ * By only accessing TDP MMU page table memory in an RCU read critical
++ * section, and freeing it after a grace period, lockless access to that
++ * memory won't use it after it is freed.
++ */
++static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
++{
++ struct kvm_mmu_page *sp = container_of(head, struct kvm_mmu_page,
++ rcu_head);
++
++ tdp_mmu_free_sp(sp);
++}
++
+ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ u64 old_spte, u64 new_spte, int level);
+
+@@ -269,8 +297,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt)
+ kvm_flush_remote_tlbs_with_address(kvm, gfn,
+ KVM_PAGES_PER_HPAGE(level));
+
+- free_page((unsigned long)pt);
+- kmem_cache_free(mmu_page_header_cache, sp);
++ call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
+ }
+
+ /**
+@@ -372,13 +399,13 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
+ u64 new_spte, bool record_acc_track,
+ bool record_dirty_log)
+ {
+- u64 *root_pt = tdp_iter_root_pt(iter);
++ tdp_ptep_t root_pt = tdp_iter_root_pt(iter);
+ struct kvm_mmu_page *root = sptep_to_sp(root_pt);
+ int as_id = kvm_mmu_page_as_id(root);
+
+ lockdep_assert_held(&kvm->mmu_lock);
+
+- WRITE_ONCE(*iter->sptep, new_spte);
++ WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
+
+ __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
+ iter->level);
+@@ -448,10 +475,13 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
+ return false;
+
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
++ rcu_read_unlock();
++
+ if (flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ cond_resched_lock(&kvm->mmu_lock);
++ rcu_read_lock();
+
+ WARN_ON(iter->gfn > iter->next_last_level_gfn);
+
+@@ -482,6 +512,8 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ 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)) {
+@@ -505,6 +537,8 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ tdp_mmu_set_spte(kvm, &iter, 0);
+ flush_needed = true;
+ }
++
++ rcu_read_unlock();
+ return flush_needed;
+ }
+
+@@ -550,13 +584,15 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
+
+ if (unlikely(is_noslot_pfn(pfn))) {
+ new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
+- trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte);
++ trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
++ new_spte);
+ } else {
+ make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn,
+ pfn, iter->old_spte, prefault, true,
+ map_writable, !shadow_accessed_mask,
+ &new_spte);
+- trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
++ trace_kvm_mmu_set_spte(iter->level, iter->gfn,
++ rcu_dereference(iter->sptep));
+ }
+
+ if (new_spte == iter->old_spte)
+@@ -579,7 +615,8 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
+ if (unlikely(is_mmio_spte(new_spte)))
+ ret = RET_PF_EMULATE;
+
+- trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
++ trace_kvm_mmu_set_spte(iter->level, iter->gfn,
++ rcu_dereference(iter->sptep));
+ if (!prefault)
+ vcpu->stat.pf_fixed++;
+
+@@ -617,6 +654,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+ huge_page_disallowed, &req_level);
+
+ trace_kvm_mmu_spte_requested(gpa, level, pfn);
++
++ rcu_read_lock();
++
+ tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
+ if (nx_huge_page_workaround_enabled)
+ disallowed_hugepage_adjust(iter.old_spte, gfn,
+@@ -642,7 +682,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+ * because the new value informs the !present
+ * path below.
+ */
+- iter.old_spte = READ_ONCE(*iter.sptep);
++ iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ }
+
+ if (!is_shadow_present_pte(iter.old_spte)) {
+@@ -661,11 +701,14 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+ }
+ }
+
+- if (WARN_ON(iter.level != level))
++ if (WARN_ON(iter.level != level)) {
++ rcu_read_unlock();
+ return RET_PF_RETRY;
++ }
+
+ ret = tdp_mmu_map_handle_target_level(vcpu, write, map_writable, &iter,
+ pfn, prefault);
++ rcu_read_unlock();
+
+ return ret;
+ }
+@@ -736,6 +779,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
+ int young = 0;
+ u64 new_spte = 0;
+
++ rcu_read_lock();
++
+ tdp_root_for_each_leaf_pte(iter, root, start, end) {
+ /*
+ * If we have a non-accessed entry we don't need to change the
+@@ -767,6 +812,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
+ trace_kvm_age_page(iter.gfn, iter.level, slot, young);
+ }
+
++ rcu_read_unlock();
++
+ return young;
+ }
+
+@@ -812,6 +859,8 @@ static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot,
+ u64 new_spte;
+ int need_flush = 0;
+
++ rcu_read_lock();
++
+ WARN_ON(pte_huge(*ptep));
+
+ new_pfn = pte_pfn(*ptep);
+@@ -840,6 +889,8 @@ static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot,
+ if (need_flush)
+ kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+
++ rcu_read_unlock();
++
+ return 0;
+ }
+
+@@ -863,6 +914,8 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ u64 new_spte;
+ bool spte_set = false;
+
++ rcu_read_lock();
++
+ BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL);
+
+ for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
+@@ -879,6 +932,8 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ spte_set = true;
+ }
++
++ rcu_read_unlock();
+ return spte_set;
+ }
+
+@@ -920,6 +975,8 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ u64 new_spte;
+ bool spte_set = false;
+
++ rcu_read_lock();
++
+ tdp_root_for_each_leaf_pte(iter, root, start, end) {
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
+ continue;
+@@ -939,6 +996,8 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ spte_set = true;
+ }
++
++ rcu_read_unlock();
+ return spte_set;
+ }
+
+@@ -980,6 +1039,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
+ struct tdp_iter iter;
+ u64 new_spte;
+
++ rcu_read_lock();
++
+ tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask),
+ gfn + BITS_PER_LONG) {
+ if (!mask)
+@@ -1005,6 +1066,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
+
+ mask &= ~(1UL << (iter.gfn - gfn));
+ }
++
++ rcu_read_unlock();
+ }
+
+ /*
+@@ -1044,6 +1107,8 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ u64 new_spte;
+ bool spte_set = false;
+
++ rcu_read_lock();
++
+ tdp_root_for_each_pte(iter, root, start, end) {
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
+ continue;
+@@ -1057,6 +1122,7 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ spte_set = true;
+ }
+
++ rcu_read_unlock();
+ return spte_set;
+ }
+
+@@ -1094,6 +1160,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
+ kvm_pfn_t pfn;
+ bool spte_set = false;
+
++ rcu_read_lock();
++
+ tdp_root_for_each_pte(iter, root, start, end) {
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, spte_set)) {
+ spte_set = false;
+@@ -1115,6 +1183,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
+ spte_set = true;
+ }
+
++ rcu_read_unlock();
+ if (spte_set)
+ kvm_flush_remote_tlbs(kvm);
+ }
+@@ -1151,6 +1220,8 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
+ u64 new_spte;
+ bool spte_set = false;
+
++ rcu_read_lock();
++
+ tdp_root_for_each_leaf_pte(iter, root, gfn, gfn + 1) {
+ if (!is_writable_pte(iter.old_spte))
+ break;
+@@ -1162,6 +1233,8 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
+ spte_set = true;
+ }
+
++ rcu_read_unlock();
++
+ return spte_set;
+ }
+
+@@ -1202,10 +1275,14 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+
+ *root_level = vcpu->arch.mmu->shadow_root_level;
+
++ rcu_read_lock();
++
+ tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
+ leaf = iter.level;
+ sptes[leaf - 1] = iter.old_spte;
+ }
+
++ rcu_read_unlock();
++
+ return leaf;
+ }
+--
+2.30.1
+
--- /dev/null
+From 53efb1b0b0e39141e285a49dc9eefacc08893d8c Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:18 -0800
+Subject: KVM: x86/mmu: Rename goal_gfn to next_last_level_gfn
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 74953d3530280dc53256054e1906f58d07bfba44 ]
+
+The goal_gfn field in tdp_iter can be misleading as it implies that it
+is the iterator's final goal. It is really a target for the lowest gfn
+mapped by the leaf level SPTE the iterator will traverse towards. Change
+the field's name to be more precise.
+
+Signed-off-by: Ben Gardon <bgardon@google.com>
+Message-Id: <20210202185734.1680553-13-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_iter.c | 20 ++++++++++----------
+ arch/x86/kvm/mmu/tdp_iter.h | 4 ++--
+ 2 files changed, 12 insertions(+), 12 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
+index 87b7e16911db..9917c55b7d24 100644
+--- a/arch/x86/kvm/mmu/tdp_iter.c
++++ b/arch/x86/kvm/mmu/tdp_iter.c
+@@ -22,21 +22,21 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
+
+ /*
+ * Sets a TDP iterator to walk a pre-order traversal of the paging structure
+- * rooted at root_pt, starting with the walk to translate goal_gfn.
++ * rooted at root_pt, starting with the walk to translate next_last_level_gfn.
+ */
+ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
+- int min_level, gfn_t goal_gfn)
++ int min_level, gfn_t next_last_level_gfn)
+ {
+ WARN_ON(root_level < 1);
+ WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
+
+- iter->goal_gfn = goal_gfn;
++ iter->next_last_level_gfn = next_last_level_gfn;
+ iter->root_level = root_level;
+ iter->min_level = min_level;
+ iter->level = root_level;
+ iter->pt_path[iter->level - 1] = root_pt;
+
+- iter->gfn = round_gfn_for_level(iter->goal_gfn, iter->level);
++ iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+ tdp_iter_refresh_sptep(iter);
+
+ iter->valid = true;
+@@ -82,7 +82,7 @@ static bool try_step_down(struct tdp_iter *iter)
+
+ iter->level--;
+ iter->pt_path[iter->level - 1] = child_pt;
+- iter->gfn = round_gfn_for_level(iter->goal_gfn, iter->level);
++ iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+ tdp_iter_refresh_sptep(iter);
+
+ return true;
+@@ -106,7 +106,7 @@ static bool try_step_side(struct tdp_iter *iter)
+ return false;
+
+ iter->gfn += KVM_PAGES_PER_HPAGE(iter->level);
+- iter->goal_gfn = iter->gfn;
++ iter->next_last_level_gfn = iter->gfn;
+ iter->sptep++;
+ iter->old_spte = READ_ONCE(*iter->sptep);
+
+@@ -166,13 +166,13 @@ void tdp_iter_next(struct tdp_iter *iter)
+ */
+ void tdp_iter_refresh_walk(struct tdp_iter *iter)
+ {
+- gfn_t goal_gfn = iter->goal_gfn;
++ gfn_t next_last_level_gfn = iter->next_last_level_gfn;
+
+- if (iter->gfn > goal_gfn)
+- goal_gfn = iter->gfn;
++ if (iter->gfn > next_last_level_gfn)
++ next_last_level_gfn = iter->gfn;
+
+ tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
+- iter->root_level, iter->min_level, goal_gfn);
++ iter->root_level, iter->min_level, next_last_level_gfn);
+ }
+
+ u64 *tdp_iter_root_pt(struct tdp_iter *iter)
+diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
+index 47170d0dc98e..b2dd269c631f 100644
+--- a/arch/x86/kvm/mmu/tdp_iter.h
++++ b/arch/x86/kvm/mmu/tdp_iter.h
+@@ -15,7 +15,7 @@ struct tdp_iter {
+ * The iterator will traverse the paging structure towards the mapping
+ * for this GFN.
+ */
+- gfn_t goal_gfn;
++ gfn_t next_last_level_gfn;
+ /* Pointers to the page tables traversed to reach the current SPTE */
+ u64 *pt_path[PT64_ROOT_MAX_LEVEL];
+ /* A pointer to the current SPTE */
+@@ -52,7 +52,7 @@ struct tdp_iter {
+ u64 *spte_to_child_pt(u64 pte, int level);
+
+ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
+- int min_level, gfn_t goal_gfn);
++ int min_level, gfn_t next_last_level_gfn);
+ void tdp_iter_next(struct tdp_iter *iter);
+ void tdp_iter_refresh_walk(struct tdp_iter *iter);
+ u64 *tdp_iter_root_pt(struct tdp_iter *iter);
+--
+2.30.1
+
--- /dev/null
+From c5835f6eef689c5931e6365feb547afc21bcab04 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:26 -0800
+Subject: KVM: x86/mmu: Use atomic ops to set SPTEs in TDP MMU map
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 9a77daacc87dee9fd63e31243f21894132ed8407 ]
+
+To prepare for handling page faults in parallel, change the TDP MMU
+page fault handler to use atomic operations to set SPTEs so that changes
+are not lost if multiple threads attempt to modify the same SPTE.
+
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+
+Message-Id: <20210202185734.1680553-21-bgardon@google.com>
+[Document new locking rules. - Paolo]
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ Documentation/virt/kvm/locking.rst | 9 +-
+ arch/x86/include/asm/kvm_host.h | 13 +++
+ arch/x86/kvm/mmu/tdp_mmu.c | 142 ++++++++++++++++++++++-------
+ 3 files changed, 130 insertions(+), 34 deletions(-)
+
+diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
+index b21a34c34a21..0aa4817b466d 100644
+--- a/Documentation/virt/kvm/locking.rst
++++ b/Documentation/virt/kvm/locking.rst
+@@ -16,7 +16,14 @@ The acquisition orders for mutexes are as follows:
+ - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
+ them together is quite rare.
+
+-On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock.
++On x86:
++
++- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock
++
++- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock is
++ taken inside kvm->arch.mmu_lock, and cannot be taken without already
++ holding kvm->arch.mmu_lock (typically with ``read_lock``, otherwise
++ there's no need to take kvm->arch.tdp_mmu_pages_lock at all).
+
+ Everything else is a leaf: no other lock is taken inside the critical
+ sections.
+diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
+index 02d4c74d30e2..47cd8f9b3fe7 100644
+--- a/arch/x86/include/asm/kvm_host.h
++++ b/arch/x86/include/asm/kvm_host.h
+@@ -1014,6 +1014,19 @@ struct kvm_arch {
+ struct list_head tdp_mmu_roots;
+ /* List of struct tdp_mmu_pages not being used as roots */
+ struct list_head tdp_mmu_pages;
++
++ /*
++ * Protects accesses to the following fields when the MMU lock
++ * is held in read mode:
++ * - tdp_mmu_pages (above)
++ * - the link field of struct kvm_mmu_pages used by the TDP MMU
++ * - lpage_disallowed_mmu_pages
++ * - the lpage_disallowed_link field of struct kvm_mmu_pages used
++ * by the TDP MMU
++ * It is acceptable, but not necessary, to acquire this lock when
++ * the thread holds the MMU lock in write mode.
++ */
++ spinlock_t tdp_mmu_pages_lock;
+ };
+
+ struct kvm_vm_stat {
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index 14d69c01c710..eb38f74af3f2 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -7,6 +7,7 @@
+ #include "tdp_mmu.h"
+ #include "spte.h"
+
++#include <asm/cmpxchg.h>
+ #include <trace/events/kvm.h>
+
+ #ifdef CONFIG_X86_64
+@@ -33,6 +34,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+ kvm->arch.tdp_mmu_enabled = true;
+
+ INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
++ spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
+ INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
+ }
+
+@@ -225,7 +227,8 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
+ }
+
+ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+- u64 old_spte, u64 new_spte, int level);
++ u64 old_spte, u64 new_spte, int level,
++ bool shared);
+
+ static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
+ {
+@@ -267,17 +270,26 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
+ *
+ * @kvm: kvm instance
+ * @sp: the new page
++ * @shared: This operation may not be running under the exclusive use of
++ * the MMU lock and the operation must synchronize with other
++ * threads that might be adding or removing pages.
+ * @account_nx: This page replaces a NX large page and should be marked for
+ * eventual reclaim.
+ */
+ static void tdp_mmu_link_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+- bool account_nx)
++ bool shared, bool account_nx)
+ {
+- lockdep_assert_held_write(&kvm->mmu_lock);
++ if (shared)
++ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
++ else
++ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
+ if (account_nx)
+ account_huge_nx_page(kvm, sp);
++
++ if (shared)
++ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ }
+
+ /**
+@@ -285,14 +297,24 @@ static void tdp_mmu_link_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+ *
+ * @kvm: kvm instance
+ * @sp: the page to be removed
++ * @shared: This operation may not be running under the exclusive use of
++ * the MMU lock and the operation must synchronize with other
++ * threads that might be adding or removing pages.
+ */
+-static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp)
++static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp,
++ bool shared)
+ {
+- lockdep_assert_held_write(&kvm->mmu_lock);
++ if (shared)
++ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
++ else
++ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ list_del(&sp->link);
+ if (sp->lpage_disallowed)
+ unaccount_huge_nx_page(kvm, sp);
++
++ if (shared)
++ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ }
+
+ /**
+@@ -300,28 +322,39 @@ static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+ *
+ * @kvm: kvm instance
+ * @pt: the page removed from the paging structure
++ * @shared: This operation may not be running under the exclusive use
++ * of the MMU lock and the operation must synchronize with other
++ * threads that might be modifying SPTEs.
+ *
+ * Given a page table that has been removed from the TDP paging structure,
+ * iterates through the page table to clear SPTEs and free child page tables.
+ */
+-static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt)
++static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
++ bool shared)
+ {
+ struct kvm_mmu_page *sp = sptep_to_sp(pt);
+ int level = sp->role.level;
+ gfn_t gfn = sp->gfn;
+ u64 old_child_spte;
++ u64 *sptep;
+ int i;
+
+ trace_kvm_mmu_prepare_zap_page(sp);
+
+- tdp_mmu_unlink_page(kvm, sp);
++ tdp_mmu_unlink_page(kvm, sp, shared);
+
+ for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
+- old_child_spte = READ_ONCE(*(pt + i));
+- WRITE_ONCE(*(pt + i), 0);
++ sptep = pt + i;
++
++ if (shared) {
++ old_child_spte = xchg(sptep, 0);
++ } else {
++ old_child_spte = READ_ONCE(*sptep);
++ WRITE_ONCE(*sptep, 0);
++ }
+ handle_changed_spte(kvm, kvm_mmu_page_as_id(sp),
+ gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)),
+- old_child_spte, 0, level - 1);
++ old_child_spte, 0, level - 1, shared);
+ }
+
+ kvm_flush_remote_tlbs_with_address(kvm, gfn,
+@@ -338,12 +371,16 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt)
+ * @old_spte: The value of the SPTE before the change
+ * @new_spte: The value of the SPTE after the change
+ * @level: the level of the PT the SPTE is part of in the paging structure
++ * @shared: This operation may not be running under the exclusive use of
++ * the MMU lock and the operation must synchronize with other
++ * threads that might be modifying SPTEs.
+ *
+ * Handle bookkeeping that might result from the modification of a SPTE.
+ * This function must be called for all TDP SPTE modifications.
+ */
+ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+- u64 old_spte, u64 new_spte, int level)
++ u64 old_spte, u64 new_spte, int level,
++ bool shared)
+ {
+ bool was_present = is_shadow_present_pte(old_spte);
+ bool is_present = is_shadow_present_pte(new_spte);
+@@ -413,18 +450,51 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+ */
+ if (was_present && !was_leaf && (pfn_changed || !is_present))
+ handle_removed_tdp_mmu_page(kvm,
+- spte_to_child_pt(old_spte, level));
++ spte_to_child_pt(old_spte, level), shared);
+ }
+
+ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+- u64 old_spte, u64 new_spte, int level)
++ u64 old_spte, u64 new_spte, int level,
++ bool shared)
+ {
+- __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level);
++ __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level,
++ shared);
+ handle_changed_spte_acc_track(old_spte, new_spte, level);
+ handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte,
+ new_spte, level);
+ }
+
++/*
++ * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically and handle the
++ * associated bookkeeping
++ *
++ * @kvm: kvm instance
++ * @iter: a tdp_iter instance currently on the SPTE that should be set
++ * @new_spte: The value the SPTE should be set to
++ * Returns: true if the SPTE was set, false if it was not. If false is returned,
++ * this function will have no side-effects.
++ */
++static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
++ struct tdp_iter *iter,
++ u64 new_spte)
++{
++ u64 *root_pt = tdp_iter_root_pt(iter);
++ struct kvm_mmu_page *root = sptep_to_sp(root_pt);
++ int as_id = kvm_mmu_page_as_id(root);
++
++ lockdep_assert_held_read(&kvm->mmu_lock);
++
++ if (cmpxchg64(rcu_dereference(iter->sptep), iter->old_spte,
++ new_spte) != iter->old_spte)
++ return false;
++
++ handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
++ iter->level, true);
++
++ return true;
++}
++
++
+ /*
+ * __tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping
+ * @kvm: kvm instance
+@@ -454,7 +524,7 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
+ WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
+
+ __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
+- iter->level);
++ iter->level, false);
+ if (record_acc_track)
+ handle_changed_spte_acc_track(iter->old_spte, new_spte,
+ iter->level);
+@@ -629,23 +699,18 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
+ int ret = 0;
+ int make_spte_ret = 0;
+
+- if (unlikely(is_noslot_pfn(pfn))) {
++ if (unlikely(is_noslot_pfn(pfn)))
+ new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
+- trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
+- new_spte);
+- } else {
++ else
+ make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn,
+ pfn, iter->old_spte, prefault, true,
+ map_writable, !shadow_accessed_mask,
+ &new_spte);
+- trace_kvm_mmu_set_spte(iter->level, iter->gfn,
+- rcu_dereference(iter->sptep));
+- }
+
+ if (new_spte == iter->old_spte)
+ ret = RET_PF_SPURIOUS;
+- else
+- tdp_mmu_set_spte(vcpu->kvm, iter, new_spte);
++ else if (!tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte))
++ return RET_PF_RETRY;
+
+ /*
+ * If the page fault was caused by a write but the page is write
+@@ -659,8 +724,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
+ }
+
+ /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
+- if (unlikely(is_mmio_spte(new_spte)))
++ if (unlikely(is_mmio_spte(new_spte))) {
++ trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
++ new_spte);
+ ret = RET_PF_EMULATE;
++ } else
++ trace_kvm_mmu_set_spte(iter->level, iter->gfn,
++ rcu_dereference(iter->sptep));
+
+ trace_kvm_mmu_set_spte(iter->level, iter->gfn,
+ rcu_dereference(iter->sptep));
+@@ -719,7 +789,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+ */
+ if (is_shadow_present_pte(iter.old_spte) &&
+ is_large_pte(iter.old_spte)) {
+- tdp_mmu_set_spte(vcpu->kvm, &iter, 0);
++ if (!tdp_mmu_set_spte_atomic(vcpu->kvm, &iter, 0))
++ break;
+
+ kvm_flush_remote_tlbs_with_address(vcpu->kvm, iter.gfn,
+ KVM_PAGES_PER_HPAGE(iter.level));
+@@ -736,19 +807,24 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+ sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level);
+ child_pt = sp->spt;
+
+- tdp_mmu_link_page(vcpu->kvm, sp,
+- huge_page_disallowed &&
+- req_level >= iter.level);
+-
+ new_spte = make_nonleaf_spte(child_pt,
+ !shadow_accessed_mask);
+
+- trace_kvm_mmu_get_page(sp, true);
+- tdp_mmu_set_spte(vcpu->kvm, &iter, new_spte);
++ if (tdp_mmu_set_spte_atomic(vcpu->kvm, &iter,
++ new_spte)) {
++ tdp_mmu_link_page(vcpu->kvm, sp, true,
++ huge_page_disallowed &&
++ req_level >= iter.level);
++
++ trace_kvm_mmu_get_page(sp, true);
++ } else {
++ tdp_mmu_free_sp(sp);
++ break;
++ }
+ }
+ }
+
+- if (WARN_ON(iter.level != level)) {
++ if (iter.level != level) {
+ rcu_read_unlock();
+ return RET_PF_RETRY;
+ }
+--
+2.30.1
+
--- /dev/null
+From 9216beb7a73a9159aca1662dcab60e3ba45b428e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Feb 2021 10:57:20 -0800
+Subject: KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed
+
+From: Ben Gardon <bgardon@google.com>
+
+[ Upstream commit 1af4a96025b33587ca953c7ef12a1b20c6e70412 ]
+
+Given certain conditions, some TDP MMU functions may not yield
+reliably / frequently enough. For example, if a paging structure was
+very large but had few, if any writable entries, wrprot_gfn_range
+could traverse many entries before finding a writable entry and yielding
+because the check for yielding only happens after an SPTE is modified.
+
+Fix this issue by moving the yield to the beginning of the loop.
+
+Fixes: a6a0b05da9f3 ("kvm: x86/mmu: Support dirty logging for the TDP MMU")
+Reviewed-by: Peter Feiner <pfeiner@google.com>
+Signed-off-by: Ben Gardon <bgardon@google.com>
+
+Message-Id: <20210202185734.1680553-15-bgardon@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/kvm/mmu/tdp_mmu.c | 32 ++++++++++++++++++++++----------
+ 1 file changed, 22 insertions(+), 10 deletions(-)
+
+diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
+index f0bc5d3ce3d4..0d17457f1c84 100644
+--- a/arch/x86/kvm/mmu/tdp_mmu.c
++++ b/arch/x86/kvm/mmu/tdp_mmu.c
+@@ -462,6 +462,12 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ bool flush_needed = false;
+
+ tdp_root_for_each_pte(iter, root, start, end) {
++ if (can_yield &&
++ tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
++ flush_needed = false;
++ continue;
++ }
++
+ if (!is_shadow_present_pte(iter.old_spte))
+ continue;
+
+@@ -476,9 +482,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ continue;
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+-
+- flush_needed = !(can_yield &&
+- tdp_mmu_iter_cond_resched(kvm, &iter, true));
++ flush_needed = true;
+ }
+ return flush_needed;
+ }
+@@ -838,6 +842,9 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+
+ for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
+ min_level, start, end) {
++ if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
++ continue;
++
+ if (!is_shadow_present_pte(iter.old_spte) ||
+ !is_last_spte(iter.old_spte, iter.level))
+ continue;
+@@ -846,8 +853,6 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+
+ tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ spte_set = true;
+-
+- tdp_mmu_iter_cond_resched(kvm, &iter, false);
+ }
+ return spte_set;
+ }
+@@ -891,6 +896,9 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ bool spte_set = false;
+
+ tdp_root_for_each_leaf_pte(iter, root, start, end) {
++ if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
++ continue;
++
+ if (spte_ad_need_write_protect(iter.old_spte)) {
+ if (is_writable_pte(iter.old_spte))
+ new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+@@ -905,8 +913,6 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+
+ tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ spte_set = true;
+-
+- tdp_mmu_iter_cond_resched(kvm, &iter, false);
+ }
+ return spte_set;
+ }
+@@ -1014,6 +1020,9 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+ bool spte_set = false;
+
+ tdp_root_for_each_pte(iter, root, start, end) {
++ if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
++ continue;
++
+ if (!is_shadow_present_pte(iter.old_spte))
+ continue;
+
+@@ -1021,8 +1030,6 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+
+ tdp_mmu_set_spte(kvm, &iter, new_spte);
+ spte_set = true;
+-
+- tdp_mmu_iter_cond_resched(kvm, &iter, false);
+ }
+
+ return spte_set;
+@@ -1063,6 +1070,11 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
+ bool spte_set = false;
+
+ tdp_root_for_each_pte(iter, root, start, end) {
++ if (tdp_mmu_iter_cond_resched(kvm, &iter, spte_set)) {
++ spte_set = false;
++ continue;
++ }
++
+ if (!is_shadow_present_pte(iter.old_spte) ||
+ !is_last_spte(iter.old_spte, iter.level))
+ continue;
+@@ -1075,7 +1087,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
+
+ tdp_mmu_set_spte(kvm, &iter, 0);
+
+- spte_set = !tdp_mmu_iter_cond_resched(kvm, &iter, true);
++ spte_set = true;
+ }
+
+ if (spte_set)
+--
+2.30.1
+
drm-tegra-sor-grab-runtime-pm-reference-across-reset.patch
vfio-nvlink-add-missing-spapr_tce_iommu-depends.patch
pinctrl-rockchip-fix-restore-error-in-resume.patch
+kvm-x86-mmu-change-tdp-mmu-yield-function-returns-to.patch
+kvm-x86-mmu-merge-flush-and-non-flush-tdp_mmu_iter_c.patch
+kvm-x86-mmu-rename-goal_gfn-to-next_last_level_gfn.patch
+kvm-x86-mmu-ensure-forward-progress-when-yielding-in.patch
+kvm-x86-mmu-yield-in-tdu-mmu-iter-even-if-no-sptes-c.patch
+kvm-x86-mmu-add-existing-trace-points-to-tdp-mmu.patch
+kvm-x86-mmu-add-lockdep-when-setting-a-tdp-mmu-spte.patch
+kvm-x86-mmu-factor-out-handling-of-removed-page-tabl.patch
+kvm-x86-mmu-protect-tdp-mmu-page-table-memory-with-r.patch
+kvm-x86-mmu-ensure-tlbs-are-flushed-when-yielding-du.patch
+kvm-x86-mmu-add-comment-on-__tdp_mmu_set_spte.patch
+kvm-x86-mmu-don-t-redundantly-clear-tdp-mmu-pt-memor.patch
+kvm-x86-mmu-fix-braces-in-kvm_recover_nx_lpages.patch
+kvm-x86-mmu-factor-out-functions-to-add-remove-tdp-m.patch
+kvm-x86-mmu-use-atomic-ops-to-set-sptes-in-tdp-mmu-m.patch
+kvm-x86-compile-out-tdp-mmu-on-32-bit-systems.patch
+kvm-x86-mmu-ensure-tlbs-are-flushed-for-tdp-mmu-duri.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
