#include "tdp_mmu.h"
#include "spte.h"
+#include <asm/cmpxchg.h>
#include <trace/events/kvm.h>
#ifdef CONFIG_X86_64
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);
}
}
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)
{
*
* @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);
}
/**
*
* @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);
}
/**
*
* @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,
* @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);
*/
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
* @iter: a tdp_iter instance currently on the SPTE that should be set
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);
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
}
/* 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));
*/
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));
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;
}