* THP doesn't start to split while we are adjusting the
* refcounts.
*
- * We are sure this doesn't happen, because mmu_notifier_retry
+ * We are sure this doesn't happen, because mmu_invalidate_retry
* was successful and we are holding the mmu_lock, so if this
* THP is trying to split, it will be blocked in the mmu
* notifier before touching any of the pages, specifically
return ret;
}
- mmu_seq = vcpu->kvm->mmu_notifier_seq;
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
/*
- * Ensure the read of mmu_notifier_seq happens before we call
+ * Ensure the read of mmu_invalidate_seq happens before we call
* gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
* the page we just got a reference to gets unmapped before we have a
* chance to grab the mmu_lock, which ensure that if the page gets
else
write_lock(&kvm->mmu_lock);
pgt = vcpu->arch.hw_mmu->pgt;
- if (mmu_notifier_retry(kvm, mmu_seq))
+ if (mmu_invalidate_retry(kvm, mmu_seq))
goto out_unlock;
/*
* Used to check for invalidations in progress, of the pfn that is
* returned by pfn_to_pfn_prot below.
*/
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
/*
- * Ensure the read of mmu_notifier_seq isn't reordered with PTE reads in
- * gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
+ * Ensure the read of mmu_invalidate_seq isn't reordered with PTE reads
+ * in gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
* risk the page we get a reference to getting unmapped before we have a
- * chance to grab the mmu_lock without mmu_notifier_retry() noticing.
+ * chance to grab the mmu_lock without mmu_invalidate_retry() noticing.
*
* This smp_rmb() pairs with the effective smp_wmb() of the combination
* of the pte_unmap_unlock() after the PTE is zapped, and the
* spin_lock() in kvm_mmu_notifier_invalidate_<page|range_end>() before
- * mmu_notifier_seq is incremented.
+ * mmu_invalidate_seq is incremented.
*/
smp_rmb();
spin_lock(&kvm->mmu_lock);
/* Check if an invalidation has taken place since we got pfn */
- if (mmu_notifier_retry(kvm, mmu_seq)) {
+ if (mmu_invalidate_retry(kvm, mmu_seq)) {
/*
* This can happen when mappings are changed asynchronously, but
* also synchronously if a COW is triggered by
VM_WARN(!spin_is_locked(&kvm->mmu_lock),
"%s called with kvm mmu_lock not held \n", __func__);
- if (mmu_notifier_retry(kvm, mmu_seq))
+ if (mmu_invalidate_retry(kvm, mmu_seq))
return NULL;
pte = __find_linux_pte(kvm->mm->pgd, ea, NULL, hshift);
unsigned long pfn;
/* used to check for invalidations in progress */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
/* Get host physical address for gpa */
cpte = kvmppc_mmu_hpte_cache_next(vcpu);
spin_lock(&kvm->mmu_lock);
- if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) {
+ if (!cpte || mmu_invalidate_retry(kvm, mmu_seq)) {
r = -EAGAIN;
goto out_unlock;
}
return -EFAULT;
/* used to check for invalidations in progress */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
ret = -EFAULT;
/* Check if we might have been invalidated; let the guest retry if so */
ret = RESUME_GUEST;
- if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
+ if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) {
unlock_rmap(rmap);
goto out_unlock;
}
/* Check if we might have been invalidated; let the guest retry if so */
spin_lock(&kvm->mmu_lock);
ret = -EAGAIN;
- if (mmu_notifier_retry(kvm, mmu_seq))
+ if (mmu_invalidate_retry(kvm, mmu_seq))
goto out_unlock;
/* Now traverse again under the lock and change the tree */
bool large_enable;
/* used to check for invalidations in progress */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
/*
* Increase the mmu notifier sequence number to prevent any page
* fault that read the memslot earlier from writing a PTE.
*/
- kvm->mmu_notifier_seq++;
+ kvm->mmu_invalidate_seq++;
spin_unlock(&kvm->mmu_lock);
}
/* 2. Find the host pte for this L1 guest real address */
/* Used to check for invalidations in progress */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
/* See if can find translation in our partition scoped tables for L1 */
g_ptel = ptel;
/* used later to detect if we might have been invalidated */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
/* Find the memslot (if any) for this address */
rmap = real_vmalloc_addr(rmap);
lock_rmap(rmap);
/* Check for pending invalidations under the rmap chain lock */
- if (mmu_notifier_retry(kvm, mmu_seq)) {
+ if (mmu_invalidate_retry(kvm, mmu_seq)) {
/* inval in progress, write a non-present HPTE */
pteh |= HPTE_V_ABSENT;
pteh &= ~HPTE_V_VALID;
int i;
/* Used later to detect if we might have been invalidated */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
long ret = H_SUCCESS;
/* Used later to detect if we might have been invalidated */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
unsigned long flags;
/* used to check for invalidations in progress */
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
/*
}
spin_lock(&kvm->mmu_lock);
- if (mmu_notifier_retry(kvm, mmu_seq)) {
+ if (mmu_invalidate_retry(kvm, mmu_seq)) {
ret = -EAGAIN;
goto out;
}
return ret;
}
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable);
if (hfn == KVM_PFN_ERR_HWPOISON) {
spin_lock(&kvm->mmu_lock);
- if (mmu_notifier_retry(kvm, mmu_seq))
+ if (mmu_invalidate_retry(kvm, mmu_seq))
goto out_unlock;
if (writable) {
* If addresses are being invalidated, skip prefetching to avoid
* accidentally prefetching those addresses.
*/
- if (unlikely(vcpu->kvm->mmu_notifier_count))
+ if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
return;
__direct_pte_prefetch(vcpu, sp, sptep);
*
* There are several ways to safely use this helper:
*
- * - Check mmu_notifier_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
* consuming it. In this case, mmu_lock doesn't need to be held during the
* lookup, but it does need to be held while checking the MMU notifier.
*
return;
/*
- * mmu_notifier_retry() was successful and mmu_lock is held, so
+ * mmu_invalidate_retry() was successful and mmu_lock is held, so
* the pmd can't be split from under us.
*/
fault->goal_level = fault->req_level;
return true;
return fault->slot &&
- mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+ mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
}
static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
if (r)
return r;
- mmu_seq = vcpu->kvm->mmu_notifier_seq;
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
r = kvm_faultin_pfn(vcpu, fault);
write_lock(&kvm->mmu_lock);
- kvm_inc_notifier_count(kvm, gfn_start, gfn_end);
+ kvm_mmu_invalidate_begin(kvm, gfn_start, gfn_end);
flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
gfn_end - gfn_start);
- kvm_dec_notifier_count(kvm, gfn_start, gfn_end);
+ kvm_mmu_invalidate_end(kvm, gfn_start, gfn_end);
write_unlock(&kvm->mmu_lock);
}
* If addresses are being invalidated, skip prefetching to avoid
* accidentally prefetching those addresses.
*/
- if (unlikely(vcpu->kvm->mmu_notifier_count))
+ if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
return;
if (sp->role.direct)
else
fault->max_level = walker.level;
- mmu_seq = vcpu->kvm->mmu_notifier_seq;
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
r = kvm_faultin_pfn(vcpu, fault);
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
struct mmu_notifier mmu_notifier;
- unsigned long mmu_notifier_seq;
- long mmu_notifier_count;
- unsigned long mmu_notifier_range_start;
- unsigned long mmu_notifier_range_end;
+ unsigned long mmu_invalidate_seq;
+ long mmu_invalidate_in_progress;
+ unsigned long mmu_invalidate_range_start;
+ unsigned long mmu_invalidate_range_end;
#endif
struct list_head devices;
u64 manual_dirty_log_protect;
void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
#endif
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
- unsigned long end);
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
- unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+ unsigned long end);
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+ unsigned long end);
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
+static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
{
- if (unlikely(kvm->mmu_notifier_count))
+ if (unlikely(kvm->mmu_invalidate_in_progress))
return 1;
/*
- * Ensure the read of mmu_notifier_count happens before the read
- * of mmu_notifier_seq. This interacts with the smp_wmb() in
- * mmu_notifier_invalidate_range_end to make sure that the caller
- * either sees the old (non-zero) value of mmu_notifier_count or
- * the new (incremented) value of mmu_notifier_seq.
- * PowerPC Book3s HV KVM calls this under a per-page lock
- * rather than under kvm->mmu_lock, for scalability, so
- * can't rely on kvm->mmu_lock to keep things ordered.
+ * Ensure the read of mmu_invalidate_in_progress happens before
+ * the read of mmu_invalidate_seq. This interacts with the
+ * smp_wmb() in mmu_notifier_invalidate_range_end to make sure
+ * that the caller either sees the old (non-zero) value of
+ * mmu_invalidate_in_progress or the new (incremented) value of
+ * mmu_invalidate_seq.
+ *
+ * PowerPC Book3s HV KVM calls this under a per-page lock rather
+ * than under kvm->mmu_lock, for scalability, so can't rely on
+ * kvm->mmu_lock to keep things ordered.
*/
smp_rmb();
- if (kvm->mmu_notifier_seq != mmu_seq)
+ if (kvm->mmu_invalidate_seq != mmu_seq)
return 1;
return 0;
}
-static inline int mmu_notifier_retry_hva(struct kvm *kvm,
- unsigned long mmu_seq,
- unsigned long hva)
+static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+ unsigned long mmu_seq,
+ unsigned long hva)
{
lockdep_assert_held(&kvm->mmu_lock);
/*
- * If mmu_notifier_count is non-zero, then the range maintained by
- * kvm_mmu_notifier_invalidate_range_start contains all addresses that
- * might be being invalidated. Note that it may include some false
+ * If mmu_invalidate_in_progress is non-zero, then the range maintained
+ * by kvm_mmu_notifier_invalidate_range_start contains all addresses
+ * that might be being invalidated. Note that it may include some false
* positives, due to shortcuts when handing concurrent invalidations.
*/
- if (unlikely(kvm->mmu_notifier_count) &&
- hva >= kvm->mmu_notifier_range_start &&
- hva < kvm->mmu_notifier_range_end)
+ if (unlikely(kvm->mmu_invalidate_in_progress) &&
+ hva >= kvm->mmu_invalidate_range_start &&
+ hva < kvm->mmu_invalidate_range_end)
return 1;
- if (kvm->mmu_notifier_seq != mmu_seq)
+ if (kvm->mmu_invalidate_seq != mmu_seq)
return 1;
return 0;
}
/*
* .change_pte() must be surrounded by .invalidate_range_{start,end}().
- * If mmu_notifier_count is zero, then no in-progress invalidations,
- * including this one, found a relevant memslot at start(); rechecking
- * memslots here is unnecessary. Note, a false positive (count elevated
- * by a different invalidation) is sub-optimal but functionally ok.
+ * If mmu_invalidate_in_progress is zero, then no in-progress
+ * invalidations, including this one, found a relevant memslot at
+ * start(); rechecking memslots here is unnecessary. Note, a false
+ * positive (count elevated by a different invalidation) is sub-optimal
+ * but functionally ok.
*/
WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
- if (!READ_ONCE(kvm->mmu_notifier_count))
+ if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
return;
kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
}
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
- unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+ unsigned long end)
{
/*
* The count increase must become visible at unlock time as no
* spte can be established without taking the mmu_lock and
* count is also read inside the mmu_lock critical section.
*/
- kvm->mmu_notifier_count++;
- if (likely(kvm->mmu_notifier_count == 1)) {
- kvm->mmu_notifier_range_start = start;
- kvm->mmu_notifier_range_end = end;
+ kvm->mmu_invalidate_in_progress++;
+ if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+ kvm->mmu_invalidate_range_start = start;
+ kvm->mmu_invalidate_range_end = end;
} else {
/*
* Fully tracking multiple concurrent ranges has diminishing
* accumulate and persist until all outstanding invalidates
* complete.
*/
- kvm->mmu_notifier_range_start =
- min(kvm->mmu_notifier_range_start, start);
- kvm->mmu_notifier_range_end =
- max(kvm->mmu_notifier_range_end, end);
+ kvm->mmu_invalidate_range_start =
+ min(kvm->mmu_invalidate_range_start, start);
+ kvm->mmu_invalidate_range_end =
+ max(kvm->mmu_invalidate_range_end, end);
}
}
.end = range->end,
.pte = __pte(0),
.handler = kvm_unmap_gfn_range,
- .on_lock = kvm_inc_notifier_count,
+ .on_lock = kvm_mmu_invalidate_begin,
.on_unlock = kvm_arch_guest_memory_reclaimed,
.flush_on_ret = true,
.may_block = mmu_notifier_range_blockable(range),
/*
* Prevent memslot modification between range_start() and range_end()
* so that conditionally locking provides the same result in both
- * functions. Without that guarantee, the mmu_notifier_count
+ * functions. Without that guarantee, the mmu_invalidate_in_progress
* adjustments will be imbalanced.
*
* Pairs with the decrement in range_end().
* 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.
+ * mn_active_invalidate_count (see above) instead of
+ * mmu_invalidate_in_progress.
*/
gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
hva_range.may_block);
return 0;
}
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
- unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+ unsigned long end)
{
/*
* This sequence increase will notify the kvm page fault that
* the page that is going to be mapped in the spte could have
* been freed.
*/
- kvm->mmu_notifier_seq++;
+ kvm->mmu_invalidate_seq++;
smp_wmb();
/*
* The above sequence increase must be visible before the
* below count decrease, which is ensured by the smp_wmb above
- * in conjunction with the smp_rmb in mmu_notifier_retry().
+ * in conjunction with the smp_rmb in mmu_invalidate_retry().
*/
- kvm->mmu_notifier_count--;
+ kvm->mmu_invalidate_in_progress--;
}
static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
.end = range->end,
.pte = __pte(0),
.handler = (void *)kvm_null_fn,
- .on_lock = kvm_dec_notifier_count,
+ .on_lock = kvm_mmu_invalidate_end,
.on_unlock = (void *)kvm_null_fn,
.flush_on_ret = false,
.may_block = mmu_notifier_range_blockable(range),
if (wake)
rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
- BUG_ON(kvm->mmu_notifier_count < 0);
+ BUG_ON(kvm->mmu_invalidate_in_progress < 0);
}
static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
{
/*
* 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.
+ * like mmu_invalidate_in_progress here; but the latter cannot
+ * be used here because the invalidation of caches in the
+ * mmu_notifier event occurs _before_ mmu_invalidate_in_progress
+ * 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.
+ * isn't dropped until after mmu_invalidate_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_invalidate_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.
+ * new (incremented) value of mmu_invalidate_seq is observed.
*/
smp_rmb();
- return kvm->mmu_notifier_seq != mmu_seq;
+ return kvm->mmu_invalidate_seq != mmu_seq;
}
static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
gpc->valid = false;
do {
- mmu_seq = kvm->mmu_notifier_seq;
+ mmu_seq = kvm->mmu_invalidate_seq;
smp_rmb();
write_unlock_irq(&gpc->lock);