linux-kernel - [PATCH 21/22] KVM: x86/mmu: Support rmap walks without holding mmu

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240809194335.1726916-22-seanjc@google.com>
Date: Fri,  9 Aug 2024 12:43:33 -0700
From: Sean Christopherson <seanjc@...gle.com>
To: Sean Christopherson <seanjc@...gle.com>, Paolo Bonzini <pbonzini@...hat.com>
Cc: kvm@...r.kernel.org, linux-kernel@...r.kernel.org, 
	Oliver Upton <oliver.upton@...ux.dev>, Marc Zyngier <maz@...nel.org>, Peter Xu <peterx@...hat.com>, 
	James Houghton <jthoughton@...gle.com>
Subject: [PATCH 21/22] KVM: x86/mmu: Support rmap walks without holding
 mmu_lock when aging gfns

DO NOT MERGE, yet...

Cc: James Houghton <jthoughton@...gle.com>
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/mmu/mmu.c | 63 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 59 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 48e8608c2738..9df6b465de06 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -995,13 +995,11 @@ static void kvm_rmap_unlock(struct kvm_rmap_head *rmap_head,
  * locking is the same, but the caller is disallowed from modifying the rmap,
  * and so the unlock flow is a nop if the rmap is/was empty.
  */
-__maybe_unused
 static unsigned long kvm_rmap_lock_readonly(struct kvm_rmap_head *rmap_head)
 {
 	return __kvm_rmap_lock(rmap_head);
 }
 
-__maybe_unused
 static void kvm_rmap_unlock_readonly(struct kvm_rmap_head *rmap_head,
 				     unsigned long old_val)
 {
@@ -1743,8 +1741,53 @@ static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot,
 	__rmap_add(vcpu->kvm, cache, slot, spte, gfn, access);
 }
 
-static bool kvm_rmap_age_gfn_range(struct kvm *kvm,
-				   struct kvm_gfn_range *range, bool test_only)
+static bool kvm_rmap_age_gfn_range_lockless(struct kvm *kvm,
+					    struct kvm_gfn_range *range,
+					    bool test_only)
+{
+	struct kvm_rmap_head *rmap_head;
+	struct rmap_iterator iter;
+	unsigned long rmap_val;
+	bool young = false;
+	u64 *sptep;
+	gfn_t gfn;
+	int level;
+	u64 spte;
+
+	for (level = PG_LEVEL_4K; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		for (gfn = range->start; gfn < range->end;
+		     gfn += KVM_PAGES_PER_HPAGE(level)) {
+			rmap_head = gfn_to_rmap(gfn, level, range->slot);
+			rmap_val = kvm_rmap_lock_readonly(rmap_head);
+
+			for_each_rmap_spte_lockless(rmap_head, &iter, sptep, spte) {
+				if (!is_accessed_spte(spte))
+					continue;
+
+				if (test_only) {
+					kvm_rmap_unlock_readonly(rmap_head, rmap_val);
+					return true;
+				}
+
+				/*
+				 * Marking SPTEs for access tracking outside of
+				 * mmu_lock is unsupported.  Report the page as
+				 * young, but otherwise leave it as-is.
+				 */
+				if (spte_ad_enabled(spte))
+					clear_bit((ffs(shadow_accessed_mask) - 1),
+						  (unsigned long *)sptep);
+				young = true;
+			}
+
+			kvm_rmap_unlock_readonly(rmap_head, rmap_val);
+		}
+	}
+	return young;
+}
+
+static bool __kvm_rmap_age_gfn_range(struct kvm *kvm,
+				     struct kvm_gfn_range *range, bool test_only)
 {
 	struct slot_rmap_walk_iterator iterator;
 	struct rmap_iterator iter;
@@ -1783,6 +1826,18 @@ static bool kvm_rmap_age_gfn_range(struct kvm *kvm,
 	return young;
 }
 
+
+static bool kvm_rmap_age_gfn_range(struct kvm *kvm,
+				   struct kvm_gfn_range *range, bool test_only)
+{
+	/* FIXME: This also needs to be guarded with something like range->fast_only. */
+	if (kvm_ad_enabled())
+		return kvm_rmap_age_gfn_range_lockless(kvm, range, test_only);
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	return __kvm_rmap_age_gfn_range(kvm, range, test_only);
+}
+
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	bool young = false;
-- 
2.46.0.76.ge559c4bf1a-goog