linux-kernel - [PATCH v4 14/18] KVM: MMU: do not need atomicly to set/clear spte

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: <4E1B4F90.90101@cn.fujitsu.com>
Date:	Tue, 12 Jul 2011 03:31:28 +0800
From:	Xiao Guangrong <xiaoguangrong@...fujitsu.com>
To:	Avi Kivity <avi@...hat.com>
CC:	Marcelo Tosatti <mtosatti@...hat.com>,
	LKML <linux-kernel@...r.kernel.org>, KVM <kvm@...r.kernel.org>
Subject: [PATCH v4 14/18] KVM: MMU: do not need atomicly to set/clear spte

Now, the spte is just from nonprsent to present or present to nonprsent, so
we can use some trick to set/clear spte non-atomicly as linux kernel does

Signed-off-by: Xiao Guangrong <xiaoguangrong@...fujitsu.com>
---
 arch/x86/kvm/mmu.c |   86 +++++++++++++++++++++++++++++++++++++++++++---------
 1 files changed, 71 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 982718f..a22b5fe 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -259,26 +259,82 @@ static gfn_t pse36_gfn_delta(u32 gpte)
 	return (gpte & PT32_DIR_PSE36_MASK) << shift;
 }
 
+#ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
-	set_64bit(sptep, spte);
+	*sptep = spte;
 }
 
-static u64 __xchg_spte(u64 *sptep, u64 new_spte)
+static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
-#ifdef CONFIG_X86_64
-	return xchg(sptep, new_spte);
+	*sptep = spte;
+}
+
+static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
+{
+	return xchg(sptep, spte);
+}
 #else
-	u64 old_spte;
+union split_spte {
+	struct {
+		u32 spte_low;
+		u32 spte_high;
+	};
+	u64 spte;
+};
 
-	do {
-		old_spte = *sptep;
-	} while (cmpxchg64(sptep, old_spte, new_spte) != old_spte);
+static void __set_spte(u64 *sptep, u64 spte)
+{
+	union split_spte *ssptep, sspte;
 
-	return old_spte;
-#endif
+	ssptep = (union split_spte *)sptep;
+	sspte = (union split_spte)spte;
+
+	ssptep->spte_high = sspte.spte_high;
+
+	/*
+	 * If we map the spte from nonpresent to present, We should store
+	 * the high bits firstly, then set present bit, so cpu can not
+	 * fetch this spte while we are setting the spte.
+	 */
+	smp_wmb();
+
+	ssptep->spte_low = sspte.spte_low;
 }
 
+static void __update_clear_spte_fast(u64 *sptep, u64 spte)
+{
+	union split_spte *ssptep, sspte;
+
+	ssptep = (union split_spte *)sptep;
+	sspte = (union split_spte)spte;
+
+	ssptep->spte_low = sspte.spte_low;
+
+	/*
+	 * If we map the spte from present to nonpresent, we should clear
+	 * present bit firstly to avoid vcpu fetch the old high bits.
+	 */
+	smp_wmb();
+
+	ssptep->spte_high = sspte.spte_high;
+}
+
+static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
+{
+	union split_spte *ssptep, sspte, orig;
+
+	ssptep = (union split_spte *)sptep;
+	sspte = (union split_spte)spte;
+
+	/* xchg acts as a barrier before the setting of the high bits */
+	orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
+	orig.spte_high = ssptep->spte_high = sspte.spte_high;
+
+	return orig.spte;
+}
+#endif
+
 static bool spte_has_volatile_bits(u64 spte)
 {
 	if (!shadow_accessed_mask)
@@ -330,9 +386,9 @@ static void mmu_spte_update(u64 *sptep, u64 new_spte)
 		mask |= shadow_dirty_mask;
 
 	if (!spte_has_volatile_bits(old_spte) || (new_spte & mask) == mask)
-		__set_spte(sptep, new_spte);
+		__update_clear_spte_fast(sptep, new_spte);
 	else
-		old_spte = __xchg_spte(sptep, new_spte);
+		old_spte = __update_clear_spte_slow(sptep, new_spte);
 
 	if (!shadow_accessed_mask)
 		return;
@@ -354,9 +410,9 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 	u64 old_spte = *sptep;
 
 	if (!spte_has_volatile_bits(old_spte))
-		__set_spte(sptep, 0ull);
+		__update_clear_spte_fast(sptep, 0ull);
 	else
-		old_spte = __xchg_spte(sptep, 0ull);
+		old_spte = __update_clear_spte_slow(sptep, 0ull);
 
 	if (!is_rmap_spte(old_spte))
 		return 0;
@@ -376,7 +432,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
  */
 static void mmu_spte_clear_no_track(u64 *sptep)
 {
-	__set_spte(sptep, 0ull);
+	__update_clear_spte_fast(sptep, 0ull);
 }
 
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
-- 
1.7.5.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/