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)