[PATCH v2 14/28] KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed

From: Ben Gardon <bgardon@google.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Peter Shier <pshier@google.com>,
	Peter Feiner <pfeiner@google.com>,
	Junaid Shahid <junaids@google.com>,
	Jim Mattson <jmattson@google.com>,
	Yulei Zhang <yulei.kernel@gmail.com>,
	Wanpeng Li <kernellwp@gmail.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Xiao Guangrong <xiaoguangrong.eric@gmail.com>,
	Ben Gardon <bgardon@google.com>
Subject: [PATCH v2 14/28] KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed
Date: Tue,  2 Feb 2021 10:57:20 -0800	[thread overview]
Message-ID: <20210202185734.1680553-15-bgardon@google.com> (raw)
In-Reply-To: <20210202185734.1680553-1-bgardon@google.com>

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>

---

v1 -> v2
- Split patch into three

 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 7cfc0639b1ef..c8a1149cb229 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -501,6 +501,12 @@ 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;
 
@@ -515,9 +521,7 @@ 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;
 }
@@ -880,6 +884,9 @@ 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;
@@ -888,8 +895,6 @@ 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;
 }
@@ -933,6 +938,9 @@ 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;
@@ -947,8 +955,6 @@ 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;
 }
@@ -1056,6 +1062,9 @@ 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;
 
@@ -1063,8 +1072,6 @@ 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;
@@ -1105,6 +1112,11 @@ 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;
@@ -1116,7 +1128,7 @@ 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)
-- 
2.30.0.365.g02bc693789-goog

