All of lore.kernel.org
 help / color / mirror / Atom feed
From: guangrong.xiao@gmail.com
To: pbonzini@redhat.com, mtosatti@redhat.com, avi.kivity@gmail.com,
	rkrcmar@redhat.com
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	qemu-devel@nongnu.org, Xiao Guangrong <xiaoguangrong@tencent.com>
Subject: [PATCH 2/7] KVM: MMU: introduce possible_writable_spte_bitmap
Date: Wed,  3 May 2017 18:52:19 +0800	[thread overview]
Message-ID: <20170503105224.19049-3-xiaoguangrong@tencent.com> (raw)
In-Reply-To: <20170503105224.19049-1-xiaoguangrong@tencent.com>

From: Xiao Guangrong <xiaoguangrong@tencent.com>

It is used to track possible writable sptes on the shadow page on
which the bit is set to 1 for the sptes that are already writable
or can be locklessly updated to writable on the fast_page_fault
path, also a counter for the number of possible writable sptes is
introduced to speed up bitmap walking

Later patch will benefit good performance by using this bitmap and
counter to fast figure out writable sptes and write protect them

Signed-off-by: Xiao Guangrong <xiaoguangrong@tencent.com>
---
 arch/x86/include/asm/kvm_host.h |  6 ++++-
 arch/x86/kvm/mmu.c              | 53 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 84c8489..4872ae7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -114,6 +114,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 #define KVM_MIN_ALLOC_MMU_PAGES 64
 #define KVM_MMU_HASH_SHIFT 12
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
+#define KVM_MMU_SP_ENTRY_NR 512
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 80
@@ -287,12 +288,15 @@ struct kvm_mmu_page {
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
+	unsigned int possiable_writable_sptes;
 	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
 
 	/* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen.  */
 	unsigned long mmu_valid_gen;
 
-	DECLARE_BITMAP(unsync_child_bitmap, 512);
+	DECLARE_BITMAP(unsync_child_bitmap, KVM_MMU_SP_ENTRY_NR);
+
+	DECLARE_BITMAP(possible_writable_spte_bitmap, KVM_MMU_SP_ENTRY_NR);
 
 #ifdef CONFIG_X86_32
 	/*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ba8e7af..8a20e4f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -570,6 +570,49 @@ static bool is_dirty_spte(u64 spte)
 				 : spte & PT_WRITABLE_MASK;
 }
 
+static bool is_possible_writable_spte(u64 spte)
+{
+	if (!is_shadow_present_pte(spte))
+		return false;
+
+	if (is_writable_pte(spte))
+		return true;
+
+	if (spte_can_locklessly_be_made_writable(spte))
+		return true;
+
+	/*
+	 * although is_access_track_spte() sptes can be updated out of
+	 * mmu-lock, we need not take them into account as access_track
+	 * drops writable bit for them
+	 */
+	return false;
+}
+
+static void
+mmu_log_possible_writable_spte(u64 *sptep, u64 old_spte, u64 new_spte)
+{
+	struct kvm_mmu_page *sp = page_header(__pa(sptep));
+	bool old_state, new_state;
+
+	old_state = is_possible_writable_spte(old_spte);
+	new_state = is_possible_writable_spte(new_spte);
+
+	if (old_state == new_state)
+		return;
+
+	/* a possible writable spte is dropped */
+	if (old_state) {
+		sp->possiable_writable_sptes--;
+		__clear_bit(sptep - sp->spt, sp->possible_writable_spte_bitmap);
+		return;
+	}
+
+	/* a new possible writable spte is set */
+	sp->possiable_writable_sptes++;
+	__set_bit(sptep - sp->spt, sp->possible_writable_spte_bitmap);
+}
+
 /* Rules for using mmu_spte_set:
  * Set the sptep from nonpresent to present.
  * Note: the sptep being assigned *must* be either not present
@@ -580,6 +623,7 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte)
 {
 	WARN_ON(is_shadow_present_pte(*sptep));
 	__set_spte(sptep, new_spte);
+	mmu_log_possible_writable_spte(sptep, 0ull, new_spte);
 }
 
 /*
@@ -598,6 +642,7 @@ static void mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
 	}
 
 	__update_clear_spte_fast(sptep, new_spte);
+	mmu_log_possible_writable_spte(sptep, old_spte, new_spte);
 }
 
 /*
@@ -623,6 +668,7 @@ static u64 mmu_spte_update_track(u64 *sptep, u64 new_spte)
 
 	WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
 
+	mmu_log_possible_writable_spte(sptep, old_spte, new_spte);
 	return old_spte;
 }
 
@@ -688,6 +734,8 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 	else
 		old_spte = __update_clear_spte_slow(sptep, 0ull);
 
+	mmu_log_possible_writable_spte(sptep, old_spte, 0ull);
+
 	if (!is_shadow_present_pte(old_spte))
 		return 0;
 
@@ -716,7 +764,10 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
  */
 static void mmu_spte_clear_no_track(u64 *sptep)
 {
+	u64 old_spte = *sptep;
+
 	__update_clear_spte_fast(sptep, 0ull);
+	mmu_log_possible_writable_spte(sptep, old_spte, 0ull);
 }
 
 static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -1988,7 +2039,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
 {
 	int i, ret, nr_unsync_leaf = 0;
 
-	for_each_set_bit(i, sp->unsync_child_bitmap, 512) {
+	for_each_set_bit(i, sp->unsync_child_bitmap, KVM_MMU_SP_ENTRY_NR) {
 		struct kvm_mmu_page *child;
 		u64 ent = sp->spt[i];
 
-- 
2.9.3

WARNING: multiple messages have this Message-ID
From: guangrong.xiao@gmail.com
To: pbonzini@redhat.com, mtosatti@redhat.com, avi.kivity@gmail.com,
	rkrcmar@redhat.com
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	qemu-devel@nongnu.org, Xiao Guangrong <xiaoguangrong@tencent.com>
Subject: [Qemu-devel] [PATCH 2/7] KVM: MMU: introduce possible_writable_spte_bitmap
Date: Wed,  3 May 2017 18:52:19 +0800	[thread overview]
Message-ID: <20170503105224.19049-3-xiaoguangrong@tencent.com> (raw)
In-Reply-To: <20170503105224.19049-1-xiaoguangrong@tencent.com>

From: Xiao Guangrong <xiaoguangrong@tencent.com>

It is used to track possible writable sptes on the shadow page on
which the bit is set to 1 for the sptes that are already writable
or can be locklessly updated to writable on the fast_page_fault
path, also a counter for the number of possible writable sptes is
introduced to speed up bitmap walking

Later patch will benefit good performance by using this bitmap and
counter to fast figure out writable sptes and write protect them

Signed-off-by: Xiao Guangrong <xiaoguangrong@tencent.com>
---
 arch/x86/include/asm/kvm_host.h |  6 ++++-
 arch/x86/kvm/mmu.c              | 53 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 84c8489..4872ae7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -114,6 +114,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 #define KVM_MIN_ALLOC_MMU_PAGES 64
 #define KVM_MMU_HASH_SHIFT 12
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
+#define KVM_MMU_SP_ENTRY_NR 512
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 80
@@ -287,12 +288,15 @@ struct kvm_mmu_page {
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
+	unsigned int possiable_writable_sptes;
 	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
 
 	/* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen.  */
 	unsigned long mmu_valid_gen;
 
-	DECLARE_BITMAP(unsync_child_bitmap, 512);
+	DECLARE_BITMAP(unsync_child_bitmap, KVM_MMU_SP_ENTRY_NR);
+
+	DECLARE_BITMAP(possible_writable_spte_bitmap, KVM_MMU_SP_ENTRY_NR);
 
 #ifdef CONFIG_X86_32
 	/*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ba8e7af..8a20e4f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -570,6 +570,49 @@ static bool is_dirty_spte(u64 spte)
 				 : spte & PT_WRITABLE_MASK;
 }
 
+static bool is_possible_writable_spte(u64 spte)
+{
+	if (!is_shadow_present_pte(spte))
+		return false;
+
+	if (is_writable_pte(spte))
+		return true;
+
+	if (spte_can_locklessly_be_made_writable(spte))
+		return true;
+
+	/*
+	 * although is_access_track_spte() sptes can be updated out of
+	 * mmu-lock, we need not take them into account as access_track
+	 * drops writable bit for them
+	 */
+	return false;
+}
+
+static void
+mmu_log_possible_writable_spte(u64 *sptep, u64 old_spte, u64 new_spte)
+{
+	struct kvm_mmu_page *sp = page_header(__pa(sptep));
+	bool old_state, new_state;
+
+	old_state = is_possible_writable_spte(old_spte);
+	new_state = is_possible_writable_spte(new_spte);
+
+	if (old_state == new_state)
+		return;
+
+	/* a possible writable spte is dropped */
+	if (old_state) {
+		sp->possiable_writable_sptes--;
+		__clear_bit(sptep - sp->spt, sp->possible_writable_spte_bitmap);
+		return;
+	}
+
+	/* a new possible writable spte is set */
+	sp->possiable_writable_sptes++;
+	__set_bit(sptep - sp->spt, sp->possible_writable_spte_bitmap);
+}
+
 /* Rules for using mmu_spte_set:
  * Set the sptep from nonpresent to present.
  * Note: the sptep being assigned *must* be either not present
@@ -580,6 +623,7 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte)
 {
 	WARN_ON(is_shadow_present_pte(*sptep));
 	__set_spte(sptep, new_spte);
+	mmu_log_possible_writable_spte(sptep, 0ull, new_spte);
 }
 
 /*
@@ -598,6 +642,7 @@ static void mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
 	}
 
 	__update_clear_spte_fast(sptep, new_spte);
+	mmu_log_possible_writable_spte(sptep, old_spte, new_spte);
 }
 
 /*
@@ -623,6 +668,7 @@ static u64 mmu_spte_update_track(u64 *sptep, u64 new_spte)
 
 	WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
 
+	mmu_log_possible_writable_spte(sptep, old_spte, new_spte);
 	return old_spte;
 }
 
@@ -688,6 +734,8 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 	else
 		old_spte = __update_clear_spte_slow(sptep, 0ull);
 
+	mmu_log_possible_writable_spte(sptep, old_spte, 0ull);
+
 	if (!is_shadow_present_pte(old_spte))
 		return 0;
 
@@ -716,7 +764,10 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
  */
 static void mmu_spte_clear_no_track(u64 *sptep)
 {
+	u64 old_spte = *sptep;
+
 	__update_clear_spte_fast(sptep, 0ull);
+	mmu_log_possible_writable_spte(sptep, old_spte, 0ull);
 }
 
 static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -1988,7 +2039,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
 {
 	int i, ret, nr_unsync_leaf = 0;
 
-	for_each_set_bit(i, sp->unsync_child_bitmap, 512) {
+	for_each_set_bit(i, sp->unsync_child_bitmap, KVM_MMU_SP_ENTRY_NR) {
 		struct kvm_mmu_page *child;
 		u64 ent = sp->spt[i];
 
-- 
2.9.3

  parent reply	other threads:[~2017-05-03 10:53 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-03 10:52 [PATCH 0/7] KVM: MMU: fast write protect guangrong.xiao
2017-05-03 10:52 ` [Qemu-devel] " guangrong.xiao
2017-05-03 10:52 ` [PATCH 1/7] KVM: MMU: correct the behavior of mmu_spte_update_no_track guangrong.xiao
2017-05-03 10:52   ` [Qemu-devel] " guangrong.xiao
2017-05-03 10:52 ` guangrong.xiao [this message]
2017-05-03 10:52   ` [Qemu-devel] [PATCH 2/7] KVM: MMU: introduce possible_writable_spte_bitmap guangrong.xiao
2017-05-03 10:52 ` [PATCH 3/7] KVM: MMU: introduce kvm_mmu_write_protect_all_pages guangrong.xiao
2017-05-03 10:52   ` [Qemu-devel] " guangrong.xiao
2017-05-03 10:52 ` [PATCH 4/7] KVM: MMU: enable KVM_WRITE_PROTECT_ALL_MEM guangrong.xiao
2017-05-03 10:52   ` [Qemu-devel] " guangrong.xiao
2017-05-03 10:52 ` [PATCH 5/7] KVM: MMU: allow dirty log without write protect guangrong.xiao
2017-05-03 10:52   ` [Qemu-devel] " guangrong.xiao
2017-05-03 10:52 ` [PATCH 6/7] KVM: MMU: clarify fast_pf_fix_direct_spte guangrong.xiao
2017-05-03 10:52   ` [Qemu-devel] " guangrong.xiao
2017-05-03 10:52 ` [PATCH 7/7] KVM: MMU: stop using mmu_spte_get_lockless under mmu-lock guangrong.xiao
2017-05-03 10:52   ` [Qemu-devel] " guangrong.xiao
2017-05-03 12:28 ` [PATCH 0/7] KVM: MMU: fast write protect Paolo Bonzini
2017-05-03 12:28   ` [Qemu-devel] " Paolo Bonzini
2017-05-03 14:50   ` Xiao Guangrong
2017-05-03 14:50     ` [Qemu-devel] " Xiao Guangrong
2017-05-03 14:57     ` Paolo Bonzini
2017-05-03 14:57       ` [Qemu-devel] " Paolo Bonzini
2017-05-04  3:36       ` Xiao Guangrong
2017-05-04  3:36         ` [Qemu-devel] " Xiao Guangrong
2017-05-04  7:06         ` Paolo Bonzini
2017-05-04  7:06           ` [Qemu-devel] " Paolo Bonzini
2017-05-23  2:23           ` Xiao Guangrong
2017-05-23  2:23             ` [Qemu-devel] " Xiao Guangrong
2017-05-29 16:48             ` Paolo Bonzini
2017-05-29 16:48               ` [Qemu-devel] " Paolo Bonzini
2017-06-09  3:19               ` Xiao Guangrong
2017-06-09  3:19                 ` [Qemu-devel] " Xiao Guangrong
2017-06-05  7:36 ` Jay Zhou
2017-06-05  7:36   ` Jay Zhou
2017-06-06  2:56   ` Xiao Guangrong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170503105224.19049-3-xiaoguangrong@tencent.com \
    --to=guangrong.xiao@gmail.com \
    --cc=avi.kivity@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=rkrcmar@redhat.com \
    --cc=xiaoguangrong@tencent.com \
    --subject='Re: [PATCH 2/7] KVM: MMU: introduce possible_writable_spte_bitmap' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.