linux-kernel - [PATCH 5.10 091/126] KVM: x86/mmu: Ensure TLBs are flushed when yielding during GFN range zap

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]

Date:   Mon,  5 Apr 2021 10:54:13 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Ben Gardon <bgardon@...gle.com>,
        Sean Christopherson <seanjc@...gle.com>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Sasha Levin <sashal@...nel.org>
Subject: [PATCH 5.10 091/126] KVM: x86/mmu: Ensure TLBs are flushed when yielding during GFN range zap

From: Sean Christopherson <seanjc@...gle.com>

[ Upstream commit a835429cda91621fca915d80672a157b47738afb ]

When flushing a range of GFNs across multiple roots, ensure any pending
flush from a previous root is honored before yielding while walking the
tables of the current root.

Note, kvm_tdp_mmu_zap_gfn_range() now intentionally overwrites its local
"flush" with the result to avoid redundant flushes.  zap_gfn_range()
preserves and return the incoming "flush", unless of course the flush was
performed prior to yielding and no new flush was triggered.

Fixes: 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed")
Cc: stable@...r.kernel.org
Reviewed-by: Ben Gardon <bgardon@...gle.com>
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
Message-Id: <20210325200119.1359384-2-seanjc@...gle.com>
Signed-off-by: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index a54a9ed979d1..34ef3e1a0f84 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -111,7 +111,7 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
 }
 
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield);
+			  gfn_t start, gfn_t end, bool can_yield, bool flush);
 
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
@@ -124,7 +124,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 
 	list_del(&root->link);
 
-	zap_gfn_range(kvm, root, 0, max_gfn, false);
+	zap_gfn_range(kvm, root, 0, max_gfn, false, false);
 
 	free_page((unsigned long)root->spt);
 	kmem_cache_free(mmu_page_header_cache, root);
@@ -504,20 +504,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
  * scheduler needs the CPU or there is contention on the MMU lock. If this
  * function cannot yield, it will not release the MMU lock or reschedule and
  * the caller must ensure it does not supply too large a GFN range, or the
- * operation can cause a soft lockup.
+ * operation can cause a soft lockup.  Note, in some use cases a flush may be
+ * required by prior actions.  Ensure the pending flush is performed prior to
+ * yielding.
  */
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield)
+			  gfn_t start, gfn_t end, bool can_yield, bool flush)
 {
 	struct tdp_iter iter;
-	bool flush_needed = false;
 
 	rcu_read_lock();
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 		if (can_yield &&
-		    tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
-			flush_needed = false;
+		    tdp_mmu_iter_cond_resched(kvm, &iter, flush)) {
+			flush = false;
 			continue;
 		}
 
@@ -535,11 +536,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			continue;
 
 		tdp_mmu_set_spte(kvm, &iter, 0);
-		flush_needed = true;
+		flush = true;
 	}
 
 	rcu_read_unlock();
-	return flush_needed;
+	return flush;
 }
 
 /*
@@ -554,7 +555,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
 	bool flush = false;
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root)
-		flush |= zap_gfn_range(kvm, root, start, end, true);
+		flush = zap_gfn_range(kvm, root, start, end, true, flush);
 
 	return flush;
 }
@@ -757,7 +758,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm,
 				     struct kvm_mmu_page *root, gfn_t start,
 				     gfn_t end, unsigned long unused)
 {
-	return zap_gfn_range(kvm, root, start, end, false);
+	return zap_gfn_range(kvm, root, start, end, false, false);
 }
 
 int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,
-- 
2.30.1