All of lore.kernel.org
 help / color / mirror / Atom feed
From: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
To: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
	LKML <linux-kernel@vger.kernel.org>, KVM <kvm@vger.kernel.org>
Subject: [PATCH v2 08/22] KVM: MMU: optimize to handle dirty bit
Date: Wed, 22 Jun 2011 22:31:27 +0800	[thread overview]
Message-ID: <4E01FCBF.1030005@cn.fujitsu.com> (raw)
In-Reply-To: <4E01FBC9.3020009@cn.fujitsu.com>

If dirty bit is not set, we can make the pte access read-only to avoid handing
dirty bit everywhere

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
---
 arch/x86/kvm/mmu.c         |   13 +++++------
 arch/x86/kvm/paging_tmpl.h |   46 ++++++++++++++++++-------------------------
 2 files changed, 25 insertions(+), 34 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7f53210..9e35577 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1923,7 +1923,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int user_fault,
-		    int write_fault, int dirty, int level,
+		    int write_fault, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
@@ -1938,8 +1938,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	spte = PT_PRESENT_MASK;
 	if (!speculative)
 		spte |= shadow_accessed_mask;
-	if (!dirty)
-		pte_access &= ~ACC_WRITE_MASK;
+
 	if (pte_access & ACC_EXEC_MASK)
 		spte |= shadow_x_mask;
 	else
@@ -2023,7 +2022,7 @@ done:
 
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			 unsigned pt_access, unsigned pte_access,
-			 int user_fault, int write_fault, int dirty,
+			 int user_fault, int write_fault,
 			 int *ptwrite, int level, gfn_t gfn,
 			 pfn_t pfn, bool speculative,
 			 bool host_writable)
@@ -2059,7 +2058,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	}
 
 	if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
-		      dirty, level, gfn, pfn, speculative, true,
+		      level, gfn, pfn, speculative, true,
 		      host_writable)) {
 		if (write_fault)
 			*ptwrite = 1;
@@ -2129,7 +2128,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 
 	for (i = 0; i < ret; i++, gfn++, start++)
 		mmu_set_spte(vcpu, start, ACC_ALL,
-			     access, 0, 0, 1, NULL,
+			     access, 0, 0, NULL,
 			     sp->role.level, gfn,
 			     page_to_pfn(pages[i]), true, true);
 
@@ -2193,7 +2192,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			unsigned pte_access = ACC_ALL;
 
 			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
-				     0, write, 1, &pt_write,
+				     0, write, &pt_write,
 				     level, gfn, pfn, prefault, map_writable);
 			direct_pte_prefetch(vcpu, iterator.sptep);
 			++vcpu->stat.pf_fixed;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 13978dc..e06c9e4 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -101,11 +101,15 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	return (ret != orig_pte);
 }
 
-static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte)
+static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte,
+				   bool last)
 {
 	unsigned access;
 
 	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+	if (last && !is_dirty_gpte(gpte))
+		access &= ~ACC_WRITE_MASK;
+
 #if PTTYPE == 64
 	if (vcpu->arch.mmu.nx)
 		access &= ~(gpte >> PT64_NX_SHIFT);
@@ -227,8 +231,6 @@ walk:
 			pte |= PT_ACCESSED_MASK;
 		}
 
-		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
-
 		walker->ptes[walker->level - 1] = pte;
 
 		if ((walker->level == PT_PAGE_TABLE_LEVEL) ||
@@ -269,7 +271,7 @@ walk:
 			break;
 		}
 
-		pt_access = pte_access;
+		pt_access &= FNAME(gpte_access)(vcpu, pte, false);
 		--walker->level;
 	}
 
@@ -293,6 +295,7 @@ walk:
 		walker->ptes[walker->level - 1] = pte;
 	}
 
+	pte_access = pt_access & FNAME(gpte_access)(vcpu, pte, true);
 	walker->pt_access = pt_access;
 	walker->pte_access = pte_access;
 	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
@@ -373,7 +376,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		return;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
-	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte, true);
 	pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte));
 	if (is_error_pfn(pfn)) {
 		kvm_release_pfn_clean(pfn);
@@ -385,7 +388,7 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
 	 */
 	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
-		     is_dirty_gpte(gpte), NULL, PT_PAGE_TABLE_LEVEL,
+		     NULL, PT_PAGE_TABLE_LEVEL,
 		     gpte_to_gfn(gpte), pfn, true, true);
 }
 
@@ -436,7 +439,6 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 		unsigned pte_access;
 		gfn_t gfn;
 		pfn_t pfn;
-		bool dirty;
 
 		if (spte == sptep)
 			continue;
@@ -449,18 +451,18 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 			continue;
 
-		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte,
+								  true);
 		gfn = gpte_to_gfn(gpte);
-		dirty = is_dirty_gpte(gpte);
 		pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
-				      (pte_access & ACC_WRITE_MASK) && dirty);
+				      pte_access & ACC_WRITE_MASK);
 		if (is_error_pfn(pfn)) {
 			kvm_release_pfn_clean(pfn);
 			break;
 		}
 
 		mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
-			     dirty, NULL, PT_PAGE_TABLE_LEVEL, gfn,
+			     NULL, PT_PAGE_TABLE_LEVEL, gfn,
 			     pfn, true, true);
 	}
 }
@@ -476,7 +478,6 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 {
 	unsigned access = gw->pt_access;
 	struct kvm_mmu_page *sp = NULL;
-	bool dirty = is_dirty_gpte(gw->ptes[gw->level - 1]);
 	int top_level;
 	unsigned direct_access;
 	struct kvm_shadow_walk_iterator it;
@@ -485,8 +486,6 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 		return NULL;
 
 	direct_access = gw->pt_access & gw->pte_access;
-	if (!dirty)
-		direct_access &= ~ACC_WRITE_MASK;
 
 	top_level = vcpu->arch.mmu.root_level;
 	if (top_level == PT32E_ROOT_LEVEL)
@@ -545,7 +544,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	}
 
 	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access & access,
-		     user_fault, write_fault, dirty, ptwrite, it.level,
+		     user_fault, write_fault, ptwrite, it.level,
 		     gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
@@ -628,17 +627,9 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return 0;
 
 	/* mmio */
-	if (is_error_pfn(pfn)) {
-		unsigned access = walker.pte_access;
-		bool dirty = is_dirty_gpte(walker.ptes[walker.level - 1]);
-
-		if (dirty)
-			access &= ~ACC_WRITE_MASK;
-
+	if (is_error_pfn(pfn))
 		return kvm_handle_bad_page(vcpu, mmu_is_nested(vcpu) ? 0 :
-					   addr, access, walker.gfn, pfn);
-	}
-
+				      addr, walker.pte_access, walker.gfn, pfn);
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu, mmu_seq))
 		goto out_unlock;
@@ -855,11 +846,12 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		}
 
 		nr_present++;
-		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte,
+								  true);
 		host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE;
 
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
-			 is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn,
+			 PT_PAGE_TABLE_LEVEL, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false,
 			 host_writable);
 	}
-- 
1.7.5.4


  parent reply	other threads:[~2011-06-22 14:29 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-22 14:27 [PATCH v2 0/22] KVM: optimize for MMIO handled Xiao Guangrong
2011-06-22 14:28 ` [PATCH v2 01/22] KVM: MMU: fix walking shadow page table Xiao Guangrong
2011-06-22 17:13   ` Marcelo Tosatti
2011-06-23  2:05     ` Xiao Guangrong
2011-06-27  6:35     ` Xiao Guangrong
2011-06-22 14:28 ` [PATCH v2 02/22] KVM: MMU: do not update slot bitmap if spte is nonpresent Xiao Guangrong
2011-06-22 14:29 ` [PATCH v2 03/22] KVM: x86: fix broken read emulation spans a page boundary Xiao Guangrong
2011-06-29  8:21   ` Avi Kivity
2011-06-29 10:53     ` Xiao Guangrong
2011-06-29 11:19       ` Avi Kivity
2011-06-22 14:29 ` [PATCH v2 04/22] KVM: x86: introduce vcpu_gva_to_gpa to cleanup the code Xiao Guangrong
2011-06-29  8:24   ` Avi Kivity
2011-06-29 10:56     ` Xiao Guangrong
2011-06-29 11:09       ` Avi Kivity
2011-06-29 11:26         ` Xiao Guangrong
2011-06-29 11:26           ` Avi Kivity
2011-06-29 11:48             ` Gleb Natapov
2011-06-22 14:30 ` [PATCH v2 05/22] KVM: x86: abstract the operation for read/write emulation Xiao Guangrong
2011-06-29  8:37   ` Avi Kivity
2011-06-29 10:59     ` Xiao Guangrong
2011-06-22 14:30 ` [PATCH v2 06/22] KVM: x86: cleanup the code of " Xiao Guangrong
2011-06-22 14:31 ` [PATCH v2 07/22] KVM: MMU: cache mmio info on page fault path Xiao Guangrong
2011-06-29  8:48   ` Avi Kivity
2011-06-29 11:09     ` Xiao Guangrong
2011-06-29 11:10       ` Avi Kivity
2011-06-22 14:31 ` Xiao Guangrong [this message]
2011-06-22 14:31 ` [PATCH v2 09/22] KVM: MMU: cleanup for FNAME(fetch) Xiao Guangrong
2011-06-22 14:32 ` [PATCH v2 10/22] KVM: MMU: rename 'pt_write' to 'emulate' Xiao Guangrong
2011-06-22 14:32 ` [PATCH v2 11/22] KVM: MMU: count used shadow pages on prepareing path Xiao Guangrong
2011-06-22 14:32 ` [PATCH v2 12/22] KVM: MMU: split kvm_mmu_free_page Xiao Guangrong
2011-06-22 14:33 ` [PATCH v2 13/22] KVM: MMU: remove bypass_guest_pf Xiao Guangrong
2011-06-22 14:33 ` [PATCH v2 14/22] KVM: MMU: filter out the mmio pfn from the fault pfn Xiao Guangrong
2011-06-22 14:34 ` [PATCH v2 15/22] KVM: MMU: abstract some functions to handle " Xiao Guangrong
2011-06-22 14:34 ` [PATCH v2 16/22] KVM: MMU: introduce the rules to modify shadow page table Xiao Guangrong
2011-06-22 14:34 ` [PATCH v2 17/22] KVM: MMU: clean up spte updating and clearing Xiao Guangrong
2011-06-22 14:35 ` [PATCH 18/22] KVM: MMU: do not need atomicly to set/clear spte Xiao Guangrong
2011-06-22 14:35 ` [PATCH v2 19/22] KVM: MMU: lockless walking shadow page table Xiao Guangrong
2011-06-29  9:16   ` Avi Kivity
2011-06-29 11:16     ` Xiao Guangrong
2011-06-29 11:18       ` Avi Kivity
2011-06-29 11:50         ` Xiao Guangrong
2011-06-29 12:18           ` Avi Kivity
2011-06-29 12:28             ` Xiao Guangrong
2011-06-29 12:27               ` Avi Kivity
2011-06-29 12:39                 ` Xiao Guangrong
2011-06-29 13:01                   ` Avi Kivity
2011-06-29 13:05                     ` Xiao Guangrong
2011-06-22 14:35 ` [PATCH v2 20/22] KVM: MMU: reorganize struct kvm_shadow_walk_iterator Xiao Guangrong
2011-06-22 14:36 ` [PATCH v2 21/22] KVM: MMU: mmio page fault support Xiao Guangrong
2011-06-22 21:59   ` Marcelo Tosatti
2011-06-23  3:19     ` Xiao Guangrong
2011-06-23  6:40       ` Xiao Guangrong
2011-06-23 14:21       ` Marcelo Tosatti
2011-06-23 17:55         ` Xiao Guangrong
2011-06-23 20:13           ` Marcelo Tosatti
2011-06-24  2:04             ` Xiao Guangrong
2011-06-26  8:42           ` Avi Kivity
2011-06-27 11:00   ` [PATCH v3 " Xiao Guangrong
2011-06-29  9:22   ` [PATCH v2 " Avi Kivity
2011-06-29 12:28     ` Xiao Guangrong
2011-06-22 14:36 ` [PATCH v2 22/22] KVM: MMU: trace mmio page fault Xiao Guangrong
2011-06-29  9:23 ` [PATCH v2 0/22] KVM: optimize for MMIO handled Avi Kivity

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=4E01FCBF.1030005@cn.fujitsu.com \
    --to=xiaoguangrong@cn.fujitsu.com \
    --cc=avi@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
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.