From 574c3c55e969096cea770eda3375ff35ccf91702 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Mon, 15 Nov 2021 13:17:04 -0800 Subject: [PATCH 1/6] KVM: x86/mmu: Fix TLB flush range when handling disconnected pt When recursively clearing out disconnected pts, the range based TLB flush in handle_removed_tdp_mmu_page uses the wrong starting GFN, resulting in the flush mostly missing the affected range. Fix this by using base_gfn for the flush. In response to feedback from David Matlack on the RFC version of this patch, also move a few definitions into the for loop in the function to prevent unintended references to them in the future. Fixes: a066e61f13cf ("KVM: x86/mmu: Factor out handling of removed page tables") CC: stable@vger.kernel.org Signed-off-by: Ben Gardon Message-Id: <20211115211704.2621644-1-bgardon@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index a54c3491af42..377a96718a2e 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt)); int level = sp->role.level; gfn_t base_gfn = sp->gfn; - u64 old_child_spte; - u64 *sptep; - gfn_t gfn; int i; trace_kvm_mmu_prepare_zap_page(sp); @@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, tdp_mmu_unlink_page(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - sptep = rcu_dereference(pt) + i; - gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 *sptep = rcu_dereference(pt) + i; + gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); + u64 old_child_spte; if (shared) { /* @@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, shared); } - kvm_flush_remote_tlbs_with_address(kvm, gfn, + kvm_flush_remote_tlbs_with_address(kvm, base_gfn, KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); From bda44d844758c70c8dc1478e6fc9c25efa90c5a7 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 4 Nov 2021 00:25:02 +0000 Subject: [PATCH 2/6] KVM: Ensure local memslot copies operate on up-to-date arch-specific data When modifying memslots, snapshot the "old" memslot and copy it to the "new" memslot's arch data after (re)acquiring slots_arch_lock. x86 can change a memslot's arch data while memslot updates are in-progress so long as it holds slots_arch_lock, thus snapshotting a memslot without holding the lock can result in the consumption of stale data. Fixes: b10a038e84d1 ("KVM: mmu: Add slots_arch_lock for memslot arch fields") Cc: stable@vger.kernel.org Cc: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20211104002531.1176691-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 47 ++++++++++++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 16 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9646bb9112c1..2104fc29cdd2 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1531,11 +1531,10 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, static int kvm_set_memslot(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot *old, struct kvm_memory_slot *new, int as_id, enum kvm_mr_change change) { - struct kvm_memory_slot *slot; + struct kvm_memory_slot *slot, old; struct kvm_memslots *slots; int r; @@ -1566,7 +1565,7 @@ static int kvm_set_memslot(struct kvm *kvm, * Note, the INVALID flag needs to be in the appropriate entry * in the freshly allocated memslots, not in @old or @new. */ - slot = id_to_memslot(slots, old->id); + slot = id_to_memslot(slots, new->id); slot->flags |= KVM_MEMSLOT_INVALID; /* @@ -1597,6 +1596,26 @@ static int kvm_set_memslot(struct kvm *kvm, kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id)); } + /* + * Make a full copy of the old memslot, the pointer will become stale + * when the memslots are re-sorted by update_memslots(), and the old + * memslot needs to be referenced after calling update_memslots(), e.g. + * to free its resources and for arch specific behavior. This needs to + * happen *after* (re)acquiring slots_arch_lock. + */ + slot = id_to_memslot(slots, new->id); + if (slot) { + old = *slot; + } else { + WARN_ON_ONCE(change != KVM_MR_CREATE); + memset(&old, 0, sizeof(old)); + old.id = new->id; + old.as_id = as_id; + } + + /* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */ + memcpy(&new->arch, &old.arch, sizeof(old.arch)); + r = kvm_arch_prepare_memory_region(kvm, new, mem, change); if (r) goto out_slots; @@ -1604,14 +1623,18 @@ static int kvm_set_memslot(struct kvm *kvm, update_memslots(slots, new, change); slots = install_new_memslots(kvm, as_id, slots); - kvm_arch_commit_memory_region(kvm, mem, old, new, change); + kvm_arch_commit_memory_region(kvm, mem, &old, new, change); + + /* Free the old memslot's metadata. Note, this is the full copy!!! */ + if (change == KVM_MR_DELETE) + kvm_free_memslot(kvm, &old); kvfree(slots); return 0; out_slots: if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { - slot = id_to_memslot(slots, old->id); + slot = id_to_memslot(slots, new->id); slot->flags &= ~KVM_MEMSLOT_INVALID; slots = install_new_memslots(kvm, as_id, slots); } else { @@ -1626,7 +1649,6 @@ static int kvm_delete_memslot(struct kvm *kvm, struct kvm_memory_slot *old, int as_id) { struct kvm_memory_slot new; - int r; if (!old->npages) return -EINVAL; @@ -1639,12 +1661,7 @@ static int kvm_delete_memslot(struct kvm *kvm, */ new.as_id = as_id; - r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE); - if (r) - return r; - - kvm_free_memslot(kvm, old); - return 0; + return kvm_set_memslot(kvm, mem, &new, as_id, KVM_MR_DELETE); } /* @@ -1718,7 +1735,6 @@ int __kvm_set_memory_region(struct kvm *kvm, if (!old.npages) { change = KVM_MR_CREATE; new.dirty_bitmap = NULL; - memset(&new.arch, 0, sizeof(new.arch)); } else { /* Modify an existing slot. */ if ((new.userspace_addr != old.userspace_addr) || (new.npages != old.npages) || @@ -1732,9 +1748,8 @@ int __kvm_set_memory_region(struct kvm *kvm, else /* Nothing to change. */ return 0; - /* Copy dirty_bitmap and arch from the current memslot. */ + /* Copy dirty_bitmap from the current memslot. */ new.dirty_bitmap = old.dirty_bitmap; - memcpy(&new.arch, &old.arch, sizeof(new.arch)); } if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { @@ -1760,7 +1775,7 @@ int __kvm_set_memory_region(struct kvm *kvm, bitmap_set(new.dirty_bitmap, 0, new.npages); } - r = kvm_set_memslot(kvm, mem, &old, &new, as_id, change); + r = kvm_set_memslot(kvm, mem, &new, as_id, change); if (r) goto out_bitmap; From 6b285a5587506bae084cf9a3ed5aa491d623b91b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 4 Nov 2021 00:25:03 +0000 Subject: [PATCH 3/6] KVM: Disallow user memslot with size that exceeds "unsigned long" Reject userspace memslots whose size exceeds the storage capacity of an "unsigned long". KVM's uAPI takes the size as u64 to support large slots on 64-bit hosts, but does not account for the size being truncated on 32-bit hosts in various flows. The access_ok() check on the userspace virtual address in particular casts the size to "unsigned long" and will check the wrong number of bytes. KVM doesn't actually support slots whose size doesn't fit in an "unsigned long", e.g. KVM's internal kvm_memory_slot.npages is an "unsigned long", not a "u64", and misc arch specific code follows that behavior. Fixes: fa3d315a4ce2 ("KVM: Validate userspace_addr of memslot when registered") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Reviewed-by: Maciej S. Szmigiero Message-Id: <20211104002531.1176691-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2104fc29cdd2..6c5083f2eb50 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1689,7 +1689,8 @@ int __kvm_set_memory_region(struct kvm *kvm, id = (u16)mem->slot; /* General sanity checks */ - if (mem->memory_size & (PAGE_SIZE - 1)) + if ((mem->memory_size & (PAGE_SIZE - 1)) || + (mem->memory_size != (unsigned long)mem->memory_size)) return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) return -EINVAL; From 9dba4d24cbb5524dd39ab1e08886373b17f07ff2 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 17 Nov 2021 08:16:17 +0100 Subject: [PATCH 4/6] x86/kvm: remove unused ack_notifier callbacks Commit f52447261bc8c2 ("KVM: irq ack notification") introduced an ack_notifier() callback in struct kvm_pic and in struct kvm_ioapic without using them anywhere. Remove those callbacks again. Signed-off-by: Juergen Gross Message-Id: <20211117071617.19504-1-jgross@suse.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/ioapic.h | 1 - arch/x86/kvm/irq.h | 1 - 2 files changed, 2 deletions(-) diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index e66e620c3bed..539333ac4b38 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -81,7 +81,6 @@ struct kvm_ioapic { unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; - void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; struct rtc_status rtc_status; struct delayed_work eoi_inject; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 650642b18d15..c2d7cfe82d00 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -56,7 +56,6 @@ struct kvm_pic { struct kvm_io_device dev_master; struct kvm_io_device dev_slave; struct kvm_io_device dev_elcr; - void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[PIC_NUM_PINS]; }; From c7785d85b6c6cc9f3d0f1a8cab128f4062b30abb Mon Sep 17 00:00:00 2001 From: Hou Wenlong Date: Wed, 17 Nov 2021 17:20:39 +0800 Subject: [PATCH 5/6] KVM: x86/mmu: Skip tlb flush if it has been done in zap_gfn_range() If the parameter flush is set, zap_gfn_range() would flush remote tlb when yield, then tlb flush is not needed outside. So use the return value of zap_gfn_range() directly instead of OR on it in kvm_unmap_gfn_range() and kvm_tdp_mmu_unmap_gfn_range(). Fixes: 3039bcc744980 ("KVM: Move x86's MMU notifier memslot walkers to generic code") Signed-off-by: Hou Wenlong Message-Id: <5e16546e228877a4d974f8c0e448a93d52c7a5a9.1637140154.git.houwenlong93@linux.alibaba.com> Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/mmu/tdp_mmu.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 3be9beea838d..0a8436ea0090 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1582,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp); if (is_tdp_mmu_enabled(kvm)) - flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 377a96718a2e..1f8c9f783b78 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1032,8 +1032,8 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, struct kvm_mmu_page *root; for_each_tdp_mmu_root(kvm, root, range->slot->as_id) - flush |= zap_gfn_range(kvm, root, range->start, range->end, - range->may_block, flush, false); + flush = zap_gfn_range(kvm, root, range->start, range->end, + range->may_block, flush, false); return flush; } From 8ed716ca7dc91f058be0ba644a3048667a20db13 Mon Sep 17 00:00:00 2001 From: Hou Wenlong Date: Wed, 17 Nov 2021 17:20:40 +0800 Subject: [PATCH 6/6] KVM: x86/mmu: Pass parameter flush as false in kvm_tdp_mmu_zap_collapsible_sptes() Since tlb flush has been done for legacy MMU before kvm_tdp_mmu_zap_collapsible_sptes(), so the parameter flush should be false for kvm_tdp_mmu_zap_collapsible_sptes(). Fixes: e2209710ccc5d ("KVM: x86/mmu: Skip rmap operations if rmaps not allocated") Signed-off-by: Hou Wenlong Message-Id: <21453a1d2533afb6e59fb6c729af89e771ff2e76.1637140154.git.houwenlong93@linux.alibaba.com> Signed-off-by: Paolo Bonzini --- 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 0a8436ea0090..0c839ee1282c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5854,7 +5854,7 @@ restart: void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) { - bool flush = false; + bool flush; if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); @@ -5871,7 +5871,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush); + flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, false); if (flush) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); read_unlock(&kvm->mmu_lock);