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: <20241105184333.2305744-5-jthoughton@google.com>
Date: Tue,  5 Nov 2024 18:43:26 +0000
From: James Houghton <jthoughton@...gle.com>
To: Sean Christopherson <seanjc@...gle.com>, Paolo Bonzini <pbonzini@...hat.com>
Cc: David Matlack <dmatlack@...gle.com>, David Rientjes <rientjes@...gle.com>, 
	James Houghton <jthoughton@...gle.com>, Marc Zyngier <maz@...nel.org>, 
	Oliver Upton <oliver.upton@...ux.dev>, Wei Xu <weixugc@...gle.com>, Yu Zhao <yuzhao@...gle.com>, 
	Axel Rasmussen <axelrasmussen@...gle.com>, kvm@...r.kernel.org, 
	linux-kernel@...r.kernel.org
Subject: [PATCH v8 04/11] KVM: x86/mmu: Relax locking for kvm_test_age_gfn and kvm_age_gfn

Walk the TDP MMU in an RCU read-side critical section without holding
mmu_lock when harvesting and potentially updating age information on
sptes. This requires a way to do RCU-safe walking of the tdp_mmu_roots;
do this with a new macro. The PTE modifications are now done atomically,
and kvm_tdp_mmu_spte_need_atomic_write() has been updated to account for
the fact that kvm_age_gfn can now locklessly update the accessed bit and
the W/R/X bits).

If the cmpxchg for marking the spte for access tracking fails, leave it
as is and treat it as if it were young, as if the spte is being actively
modified, it is most likely young.

Harvesting age information from the shadow MMU is still done while
holding the MMU write lock.

Suggested-by: Yu Zhao <yuzhao@...gle.com>
Signed-off-by: James Houghton <jthoughton@...gle.com>
Reviewed-by: David Matlack <dmatlack@...gle.com>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/Kconfig            |  1 +
 arch/x86/kvm/mmu/mmu.c          | 10 ++++++++--
 arch/x86/kvm/mmu/tdp_iter.h     | 12 ++++++------
 arch/x86/kvm/mmu/tdp_mmu.c      | 23 ++++++++++++++++-------
 5 files changed, 32 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 70c7ed0ef184..84ee08078686 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1455,6 +1455,7 @@ struct kvm_arch {
 	 * tdp_mmu_page set.
 	 *
 	 * For reads, this list is protected by:
+	 *	RCU alone or
 	 *	the MMU lock in read mode + RCU or
 	 *	the MMU lock in write mode
 	 *
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 1ed1e4f5d51c..97f747d60fe9 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,6 +23,7 @@ config KVM_X86
 	select KVM_COMMON
 	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_ELIDE_TLB_FLUSH_IF_YOUNG
+	select KVM_MMU_NOTIFIER_YOUNG_LOCKLESS
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
 	select HAVE_KVM_DIRTY_RING_TSO
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 443845bb2e01..26797ccd34d8 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1586,8 +1586,11 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	bool young = false;
 
-	if (kvm_memslots_have_rmaps(kvm))
+	if (kvm_memslots_have_rmaps(kvm)) {
+		write_lock(&kvm->mmu_lock);
 		young = kvm_rmap_age_gfn_range(kvm, range, false);
+		write_unlock(&kvm->mmu_lock);
+	}
 
 	if (tdp_mmu_enabled)
 		young |= kvm_tdp_mmu_age_gfn_range(kvm, range);
@@ -1599,8 +1602,11 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	bool young = false;
 
-	if (kvm_memslots_have_rmaps(kvm))
+	if (kvm_memslots_have_rmaps(kvm)) {
+		write_lock(&kvm->mmu_lock);
 		young = kvm_rmap_age_gfn_range(kvm, range, true);
+		write_unlock(&kvm->mmu_lock);
+	}
 
 	if (tdp_mmu_enabled)
 		young |= kvm_tdp_mmu_test_age_gfn(kvm, range);
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index a24fca3f9e7f..f26d0b60d2dd 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -39,10 +39,11 @@ static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
 }
 
 /*
- * SPTEs must be modified atomically if they are shadow-present, leaf
- * SPTEs, and have volatile bits, i.e. has bits that can be set outside
- * of mmu_lock.  The Writable bit can be set by KVM's fast page fault
- * handler, and Accessed and Dirty bits can be set by the CPU.
+ * SPTEs must be modified atomically if they have bits that can be set outside
+ * of the mmu_lock. This can happen for any shadow-present leaf SPTEs, as the
+ * Writable bit can be set by KVM's fast page fault handler, the Accessed and
+ * Dirty bits can be set by the CPU, and the Accessed and W/R/X bits can be
+ * cleared by age_gfn_range().
  *
  * Note, non-leaf SPTEs do have Accessed bits and those bits are
  * technically volatile, but KVM doesn't consume the Accessed bit of
@@ -53,8 +54,7 @@ static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
 static inline bool kvm_tdp_mmu_spte_need_atomic_write(u64 old_spte, int level)
 {
 	return is_shadow_present_pte(old_spte) &&
-	       is_last_spte(old_spte, level) &&
-	       spte_has_volatile_bits(old_spte);
+	       is_last_spte(old_spte, level);
 }
 
 static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 4508d868f1cd..f5b4f1060fff 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -178,6 +178,15 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 		     ((_only_valid) && (_root)->role.invalid))) {		\
 		} else
 
+/*
+ * Iterate over all TDP MMU roots in an RCU read-side critical section.
+ */
+#define for_each_valid_tdp_mmu_root_rcu(_kvm, _root, _as_id)			\
+	list_for_each_entry_rcu(_root, &_kvm->arch.tdp_mmu_roots, link)		\
+		if ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) ||	\
+		    (_root)->role.invalid) {					\
+		} else
+
 #define for_each_tdp_mmu_root(_kvm, _root, _as_id)			\
 	__for_each_tdp_mmu_root(_kvm, _root, _as_id, false)
 
@@ -1168,16 +1177,16 @@ static void kvm_tdp_mmu_age_spte(struct tdp_iter *iter)
 	u64 new_spte;
 
 	if (spte_ad_enabled(iter->old_spte)) {
-		iter->old_spte = tdp_mmu_clear_spte_bits(iter->sptep,
-							 iter->old_spte,
-							 shadow_accessed_mask,
-							 iter->level);
+		iter->old_spte = tdp_mmu_clear_spte_bits_atomic(iter->sptep,
+						shadow_accessed_mask);
 		new_spte = iter->old_spte & ~shadow_accessed_mask;
 	} else {
 		new_spte = mark_spte_for_access_track(iter->old_spte);
-		iter->old_spte = kvm_tdp_mmu_write_spte(iter->sptep,
-							iter->old_spte, new_spte,
-							iter->level);
+		/*
+		 * It is safe for the following cmpxchg to fail. Leave the
+		 * Accessed bit set, as the spte is most likely young anyway.
+		 */
+		(void)__tdp_mmu_set_spte_atomic(iter, new_spte);
 	}
 
 	trace_kvm_tdp_mmu_spte_changed(iter->as_id, iter->gfn, iter->level,
-- 
2.47.0.199.ga7371fff76-goog


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ