summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPaolo Bonzini <pbonzini@redhat.com>2022-06-07 19:06:39 +0300
committerPaolo Bonzini <pbonzini@redhat.com>2022-06-07 19:06:39 +0300
commitb31455e96f0005bd247d70b59428a90413de0c31 (patch)
tree5a32195b0f4e9a010b54efc1777ef41dacedd55e
parenta280e358465b4ac8982dc1eb2deebcb020443b7f (diff)
parent85165781c5d900d97052be1d2723f6929d56768d (diff)
downloadlinux-b31455e96f0005bd247d70b59428a90413de0c31.tar.xz
Merge branch 'kvm-5.20-early-patches' into HEAD
-rw-r--r--arch/x86/kvm/vmx/vmx.c8
-rw-r--r--arch/x86/kvm/x86.c7
-rw-r--r--include/linux/kvm_types.h2
-rw-r--r--virt/kvm/kvm_main.c9
-rw-r--r--virt/kvm/pfncache.c231
5 files changed, 171 insertions, 86 deletions
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a07e8cd753ec..e1aa14743cdb 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -386,18 +386,20 @@ asmlinkage void vmread_error(unsigned long field, bool fault)
noinline void vmwrite_error(unsigned long field, unsigned long value)
{
- vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n",
+ vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%u\n",
field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
}
noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr)
{
- vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr);
+ vmx_insn_failed("kvm: vmclear failed: %p/%llx err=%u\n",
+ vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR));
}
noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr)
{
- vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr);
+ vmx_insn_failed("kvm: vmptrld failed: %p/%llx err=%u\n",
+ vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR));
}
noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e9473c7c7390..921b1139c303 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3234,10 +3234,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* only 0 or all 1s can be written to IA32_MCi_CTL
* some Linux kernels though clear bit 10 in bank 4 to
* workaround a BIOS/GART TBL issue on AMD K8s, ignore
- * this to avoid an uncatched #GP in the guest
+ * this to avoid an uncatched #GP in the guest.
+ *
+ * UNIXWARE clears bit 0 of MC1_CTL to ignore
+ * correctable, single-bit ECC data errors.
*/
if ((offset & 0x3) == 0 &&
- data != 0 && (data | (1 << 10)) != ~(u64)0)
+ data != 0 && (data | (1 << 10) | 1) != ~(u64)0)
return -1;
/* MCi_STATUS */
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index ac1ebb37a0ff..f328a01db4fe 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -19,6 +19,7 @@ struct kvm_memslots;
enum kvm_mr_change;
#include <linux/bits.h>
+#include <linux/mutex.h>
#include <linux/types.h>
#include <linux/spinlock_types.h>
@@ -69,6 +70,7 @@ struct gfn_to_pfn_cache {
struct kvm_vcpu *vcpu;
struct list_head list;
rwlock_t lock;
+ struct mutex refresh_lock;
void *khva;
kvm_pfn_t pfn;
enum pfn_cache_usage usage;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 44c47670447a..7f79abdbd68d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -724,6 +724,15 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
kvm->mn_active_invalidate_count++;
spin_unlock(&kvm->mn_invalidate_lock);
+ /*
+ * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e.
+ * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring
+ * each cache's lock. There are relatively few caches in existence at
+ * any given time, and the caches themselves can check for hva overlap,
+ * i.e. don't need to rely on memslot overlap checks for performance.
+ * Because this runs without holding mmu_lock, the pfn caches must use
+ * mn_active_invalidate_count (see above) instead of mmu_notifier_count.
+ */
gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
hva_range.may_block);
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index dd84676615f1..ab519f72f2cd 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -95,48 +95,143 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
}
EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_check);
-static void __release_gpc(struct kvm *kvm, kvm_pfn_t pfn, void *khva, gpa_t gpa)
+static void gpc_unmap_khva(struct kvm *kvm, kvm_pfn_t pfn, void *khva)
{
- /* Unmap the old page if it was mapped before, and release it */
- if (!is_error_noslot_pfn(pfn)) {
- if (khva) {
- if (pfn_valid(pfn))
- kunmap(pfn_to_page(pfn));
+ /* Unmap the old pfn/page if it was mapped before. */
+ if (!is_error_noslot_pfn(pfn) && khva) {
+ if (pfn_valid(pfn))
+ kunmap(pfn_to_page(pfn));
#ifdef CONFIG_HAS_IOMEM
- else
- memunmap(khva);
+ else
+ memunmap(khva);
#endif
- }
-
- kvm_release_pfn(pfn, false);
}
}
-static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, unsigned long uhva)
+static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_seq)
{
+ /*
+ * mn_active_invalidate_count acts for all intents and purposes
+ * like mmu_notifier_count here; but the latter cannot be used
+ * here because the invalidation of caches in the mmu_notifier
+ * event occurs _before_ mmu_notifier_count is elevated.
+ *
+ * Note, it does not matter that mn_active_invalidate_count
+ * is not protected by gpc->lock. It is guaranteed to
+ * be elevated before the mmu_notifier acquires gpc->lock, and
+ * isn't dropped until after mmu_notifier_seq is updated.
+ */
+ if (kvm->mn_active_invalidate_count)
+ return true;
+
+ /*
+ * Ensure mn_active_invalidate_count is read before
+ * mmu_notifier_seq. This pairs with the smp_wmb() in
+ * mmu_notifier_invalidate_range_end() to guarantee either the
+ * old (non-zero) value of mn_active_invalidate_count or the
+ * new (incremented) value of mmu_notifier_seq is observed.
+ */
+ smp_rmb();
+ return kvm->mmu_notifier_seq != mmu_seq;
+}
+
+static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+{
+ /* Note, the new page offset may be different than the old! */
+ void *old_khva = gpc->khva - offset_in_page(gpc->khva);
+ kvm_pfn_t new_pfn = KVM_PFN_ERR_FAULT;
+ void *new_khva = NULL;
unsigned long mmu_seq;
- kvm_pfn_t new_pfn;
- int retry;
+
+ lockdep_assert_held(&gpc->refresh_lock);
+
+ lockdep_assert_held_write(&gpc->lock);
+
+ /*
+ * Invalidate the cache prior to dropping gpc->lock, the gpa=>uhva
+ * assets have already been updated and so a concurrent check() from a
+ * different task may not fail the gpa/uhva/generation checks.
+ */
+ gpc->valid = false;
do {
mmu_seq = kvm->mmu_notifier_seq;
smp_rmb();
+ write_unlock_irq(&gpc->lock);
+
+ /*
+ * If the previous iteration "failed" due to an mmu_notifier
+ * event, release the pfn and unmap the kernel virtual address
+ * from the previous attempt. Unmapping might sleep, so this
+ * needs to be done after dropping the lock. Opportunistically
+ * check for resched while the lock isn't held.
+ */
+ if (new_pfn != KVM_PFN_ERR_FAULT) {
+ /*
+ * Keep the mapping if the previous iteration reused
+ * the existing mapping and didn't create a new one.
+ */
+ if (new_khva != old_khva)
+ gpc_unmap_khva(kvm, new_pfn, new_khva);
+
+ kvm_release_pfn_clean(new_pfn);
+
+ cond_resched();
+ }
+
/* We always request a writeable mapping */
- new_pfn = hva_to_pfn(uhva, false, NULL, true, NULL);
+ new_pfn = hva_to_pfn(gpc->uhva, false, NULL, true, NULL);
if (is_error_noslot_pfn(new_pfn))
- break;
+ goto out_error;
+
+ /*
+ * Obtain a new kernel mapping if KVM itself will access the
+ * pfn. Note, kmap() and memremap() can both sleep, so this
+ * too must be done outside of gpc->lock!
+ */
+ if (gpc->usage & KVM_HOST_USES_PFN) {
+ if (new_pfn == gpc->pfn) {
+ new_khva = old_khva;
+ } else if (pfn_valid(new_pfn)) {
+ new_khva = kmap(pfn_to_page(new_pfn));
+#ifdef CONFIG_HAS_IOMEM
+ } else {
+ new_khva = memremap(pfn_to_hpa(new_pfn), PAGE_SIZE, MEMREMAP_WB);
+#endif
+ }
+ if (!new_khva) {
+ kvm_release_pfn_clean(new_pfn);
+ goto out_error;
+ }
+ }
+
+ write_lock_irq(&gpc->lock);
+
+ /*
+ * Other tasks must wait for _this_ refresh to complete before
+ * attempting to refresh.
+ */
+ WARN_ON_ONCE(gpc->valid);
+ } while (mmu_notifier_retry_cache(kvm, mmu_seq));
+
+ gpc->valid = true;
+ gpc->pfn = new_pfn;
+ gpc->khva = new_khva + (gpc->gpa & ~PAGE_MASK);
- KVM_MMU_READ_LOCK(kvm);
- retry = mmu_notifier_retry_hva(kvm, mmu_seq, uhva);
- KVM_MMU_READ_UNLOCK(kvm);
- if (!retry)
- break;
+ /*
+ * Put the reference to the _new_ pfn. The pfn is now tracked by the
+ * cache and can be safely migrated, swapped, etc... as the cache will
+ * invalidate any mappings in response to relevant mmu_notifier events.
+ */
+ kvm_release_pfn_clean(new_pfn);
- cond_resched();
- } while (1);
+ return 0;
- return new_pfn;
+out_error:
+ write_lock_irq(&gpc->lock);
+
+ return -EFAULT;
}
int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
@@ -146,9 +241,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
unsigned long page_offset = gpa & ~PAGE_MASK;
kvm_pfn_t old_pfn, new_pfn;
unsigned long old_uhva;
- gpa_t old_gpa;
void *old_khva;
- bool old_valid;
int ret = 0;
/*
@@ -158,13 +251,18 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
if (page_offset + len > PAGE_SIZE)
return -EINVAL;
+ /*
+ * If another task is refreshing the cache, wait for it to complete.
+ * There is no guarantee that concurrent refreshes will see the same
+ * gpa, memslots generation, etc..., so they must be fully serialized.
+ */
+ mutex_lock(&gpc->refresh_lock);
+
write_lock_irq(&gpc->lock);
- old_gpa = gpc->gpa;
old_pfn = gpc->pfn;
old_khva = gpc->khva - offset_in_page(gpc->khva);
old_uhva = gpc->uhva;
- old_valid = gpc->valid;
/* If the userspace HVA is invalid, refresh that first */
if (gpc->gpa != gpa || gpc->generation != slots->generation ||
@@ -177,64 +275,17 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn);
if (kvm_is_error_hva(gpc->uhva)) {
- gpc->pfn = KVM_PFN_ERR_FAULT;
ret = -EFAULT;
goto out;
}
-
- gpc->uhva += page_offset;
}
/*
* If the userspace HVA changed or the PFN was already invalid,
* drop the lock and do the HVA to PFN lookup again.
*/
- if (!old_valid || old_uhva != gpc->uhva) {
- unsigned long uhva = gpc->uhva;
- void *new_khva = NULL;
-
- /* Placeholders for "hva is valid but not yet mapped" */
- gpc->pfn = KVM_PFN_ERR_FAULT;
- gpc->khva = NULL;
- gpc->valid = true;
-
- write_unlock_irq(&gpc->lock);
-
- new_pfn = hva_to_pfn_retry(kvm, uhva);
- if (is_error_noslot_pfn(new_pfn)) {
- ret = -EFAULT;
- goto map_done;
- }
-
- if (gpc->usage & KVM_HOST_USES_PFN) {
- if (new_pfn == old_pfn) {
- new_khva = old_khva;
- old_pfn = KVM_PFN_ERR_FAULT;
- old_khva = NULL;
- } else if (pfn_valid(new_pfn)) {
- new_khva = kmap(pfn_to_page(new_pfn));
-#ifdef CONFIG_HAS_IOMEM
- } else {
- new_khva = memremap(pfn_to_hpa(new_pfn), PAGE_SIZE, MEMREMAP_WB);
-#endif
- }
- if (new_khva)
- new_khva += page_offset;
- else
- ret = -EFAULT;
- }
-
- map_done:
- write_lock_irq(&gpc->lock);
- if (ret) {
- gpc->valid = false;
- gpc->pfn = KVM_PFN_ERR_FAULT;
- gpc->khva = NULL;
- } else {
- /* At this point, gpc->valid may already have been cleared */
- gpc->pfn = new_pfn;
- gpc->khva = new_khva;
- }
+ if (!gpc->valid || old_uhva != gpc->uhva) {
+ ret = hva_to_pfn_retry(kvm, gpc);
} else {
/* If the HVA→PFN mapping was already valid, don't unmap it. */
old_pfn = KVM_PFN_ERR_FAULT;
@@ -242,9 +293,26 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
}
out:
+ /*
+ * Invalidate the cache and purge the pfn/khva if the refresh failed.
+ * Some/all of the uhva, gpa, and memslot generation info may still be
+ * valid, leave it as is.
+ */
+ if (ret) {
+ gpc->valid = false;
+ gpc->pfn = KVM_PFN_ERR_FAULT;
+ gpc->khva = NULL;
+ }
+
+ /* Snapshot the new pfn before dropping the lock! */
+ new_pfn = gpc->pfn;
+
write_unlock_irq(&gpc->lock);
- __release_gpc(kvm, old_pfn, old_khva, old_gpa);
+ mutex_unlock(&gpc->refresh_lock);
+
+ if (old_pfn != new_pfn)
+ gpc_unmap_khva(kvm, old_pfn, old_khva);
return ret;
}
@@ -254,14 +322,13 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
{
void *old_khva;
kvm_pfn_t old_pfn;
- gpa_t old_gpa;
+ mutex_lock(&gpc->refresh_lock);
write_lock_irq(&gpc->lock);
gpc->valid = false;
old_khva = gpc->khva - offset_in_page(gpc->khva);
- old_gpa = gpc->gpa;
old_pfn = gpc->pfn;
/*
@@ -272,8 +339,9 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
gpc->pfn = KVM_PFN_ERR_FAULT;
write_unlock_irq(&gpc->lock);
+ mutex_unlock(&gpc->refresh_lock);
- __release_gpc(kvm, old_pfn, old_khva, old_gpa);
+ gpc_unmap_khva(kvm, old_pfn, old_khva);
}
EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap);
@@ -286,6 +354,7 @@ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
if (!gpc->active) {
rwlock_init(&gpc->lock);
+ mutex_init(&gpc->refresh_lock);
gpc->khva = NULL;
gpc->pfn = KVM_PFN_ERR_FAULT;