linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Yu Zhao <yuzhao@google.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	Paolo Bonzini <pbonzini@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>,
	Anup Patel <anup@brainfault.org>, Ben Gardon <bgardon@google.com>,
	Borislav Petkov <bp@alien8.de>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Chao Peng <chao.p.peng@linux.intel.com>,
	Christophe Leroy <christophe.leroy@csgroup.eu>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Fabiano Rosas <farosas@linux.ibm.com>,
	Gaosheng Cui <cuigaosheng1@huawei.com>,
	Gavin Shan <gshan@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
	Ingo Molnar <mingo@redhat.com>, James Morse <james.morse@arm.com>,
	"Jason A. Donenfeld" <Jason@zx2c4.com>,
	Jason Gunthorpe <jgg@ziepe.ca>, Jonathan Corbet <corbet@lwn.net>,
	Marc Zyngier <maz@kernel.org>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Michael Larabel <michael@michaellarabel.com>,
	Mike Rapoport <rppt@kernel.org>,
	Nicholas Piggin <npiggin@gmail.com>,
	Oliver Upton <oliver.upton@linux.dev>,
	Paul Mackerras <paulus@ozlabs.org>, Peter Xu <peterx@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Thomas Huth <thuth@redhat.com>, Will Deacon <will@kernel.org>,
	Zenghui Yu <yuzenghui@huawei.com>,
	kvmarm@lists.linux.dev, kvm@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	linuxppc-dev@lists.ozlabs.org,
	linux-trace-kernel@vger.kernel.org, x86@kernel.org,
	linux-mm@google.com, Yu Zhao <yuzhao@google.com>
Subject: [PATCH mm-unstable v2 02/10] mm/kvm: use mmu_notifier_ops->test_clear_young()
Date: Fri, 26 May 2023 17:44:27 -0600	[thread overview]
Message-ID: <20230526234435.662652-3-yuzhao@google.com> (raw)
In-Reply-To: <20230526234435.662652-1-yuzhao@google.com>

Replace test_young() and clear_young() with test_clear_young().

Signed-off-by: Yu Zhao <yuzhao@google.com>
---
 include/linux/mmu_notifier.h | 29 ++-----------------
 include/trace/events/kvm.h   | 15 ----------
 mm/mmu_notifier.c            | 42 ----------------------------
 virt/kvm/kvm_main.c          | 54 ------------------------------------
 4 files changed, 2 insertions(+), 138 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index dfdbb370682d..c8f35fc08703 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -104,26 +104,6 @@ struct mmu_notifier_ops {
 				 unsigned long start,
 				 unsigned long end);
 
-	/*
-	 * clear_young is a lightweight version of clear_flush_young. Like the
-	 * latter, it is supposed to test-and-clear the young/accessed bitflag
-	 * in the secondary pte, but it may omit flushing the secondary tlb.
-	 */
-	int (*clear_young)(struct mmu_notifier *subscription,
-			   struct mm_struct *mm,
-			   unsigned long start,
-			   unsigned long end);
-
-	/*
-	 * test_young is called to check the young/accessed bitflag in
-	 * the secondary pte. This is used to know if the page is
-	 * frequently used without actually clearing the flag or tearing
-	 * down the secondary mapping on the page.
-	 */
-	int (*test_young)(struct mmu_notifier *subscription,
-			  struct mm_struct *mm,
-			  unsigned long address);
-
 	int (*test_clear_young)(struct mmu_notifier *mn, struct mm_struct *mm,
 				unsigned long start, unsigned long end,
 				bool clear, unsigned long *bitmap);
@@ -393,11 +373,6 @@ extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					  unsigned long start,
 					  unsigned long end);
-extern int __mmu_notifier_clear_young(struct mm_struct *mm,
-				      unsigned long start,
-				      unsigned long end);
-extern int __mmu_notifier_test_young(struct mm_struct *mm,
-				     unsigned long address);
 extern int __mmu_notifier_test_clear_young(struct mm_struct *mm,
 					   unsigned long start, unsigned long end,
 					   bool clear, unsigned long *bitmap);
@@ -437,7 +412,7 @@ static inline int mmu_notifier_clear_young(struct mm_struct *mm,
 					   unsigned long end)
 {
 	if (mm_has_notifiers(mm))
-		return __mmu_notifier_clear_young(mm, start, end);
+		return __mmu_notifier_test_clear_young(mm, start, end, true, NULL);
 	return 0;
 }
 
@@ -445,7 +420,7 @@ static inline int mmu_notifier_test_young(struct mm_struct *mm,
 					  unsigned long address)
 {
 	if (mm_has_notifiers(mm))
-		return __mmu_notifier_test_young(mm, address);
+		return __mmu_notifier_test_clear_young(mm, address, address + 1, false, NULL);
 	return 0;
 }
 
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 3bd31ea23fee..46c347e56e60 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -489,21 +489,6 @@ TRACE_EVENT(kvm_age_hva,
 		  __entry->start, __entry->end)
 );
 
-TRACE_EVENT(kvm_test_age_hva,
-	TP_PROTO(unsigned long hva),
-	TP_ARGS(hva),
-
-	TP_STRUCT__entry(
-		__field(	unsigned long,	hva		)
-	),
-
-	TP_fast_assign(
-		__entry->hva		= hva;
-	),
-
-	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
-);
-
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 7e6aba4bddcb..c7e9747c9920 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -382,48 +382,6 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 	return young;
 }
 
-int __mmu_notifier_clear_young(struct mm_struct *mm,
-			       unsigned long start,
-			       unsigned long end)
-{
-	struct mmu_notifier *subscription;
-	int young = 0, id;
-
-	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist,
-				 srcu_read_lock_held(&srcu)) {
-		if (subscription->ops->clear_young)
-			young |= subscription->ops->clear_young(subscription,
-								mm, start, end);
-	}
-	srcu_read_unlock(&srcu, id);
-
-	return young;
-}
-
-int __mmu_notifier_test_young(struct mm_struct *mm,
-			      unsigned long address)
-{
-	struct mmu_notifier *subscription;
-	int young = 0, id;
-
-	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist,
-				 srcu_read_lock_held(&srcu)) {
-		if (subscription->ops->test_young) {
-			young = subscription->ops->test_young(subscription, mm,
-							      address);
-			if (young)
-				break;
-		}
-	}
-	srcu_read_unlock(&srcu, id);
-
-	return young;
-}
-
 int __mmu_notifier_test_clear_young(struct mm_struct *mm,
 				    unsigned long start, unsigned long end,
 				    bool clear, unsigned long *bitmap)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 31ee58754b19..977baaf1b248 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -674,25 +674,6 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 	return __kvm_handle_hva_range(kvm, &range);
 }
 
-static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
-							 unsigned long start,
-							 unsigned long end,
-							 hva_handler_t handler)
-{
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range range = {
-		.start		= start,
-		.end		= end,
-		.pte		= __pte(0),
-		.handler	= handler,
-		.on_lock	= (void *)kvm_null_fn,
-		.on_unlock	= (void *)kvm_null_fn,
-		.flush_on_ret	= false,
-		.may_block	= false,
-	};
-
-	return __kvm_handle_hva_range(kvm, &range);
-}
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					struct mm_struct *mm,
 					unsigned long address,
@@ -854,39 +835,6 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 	return kvm_handle_hva_range(mn, start, end, __pte(0), kvm_age_gfn);
 }
 
-static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
-					struct mm_struct *mm,
-					unsigned long start,
-					unsigned long end)
-{
-	trace_kvm_age_hva(start, end);
-
-	/*
-	 * Even though we do not flush TLB, this will still adversely
-	 * affect performance on pre-Haswell Intel EPT, where there is
-	 * no EPT Access Bit to clear so that we have to tear down EPT
-	 * tables instead. If we find this unacceptable, we can always
-	 * add a parameter to kvm_age_hva so that it effectively doesn't
-	 * do anything on clear_young.
-	 *
-	 * Also note that currently we never issue secondary TLB flushes
-	 * from clear_young, leaving this job up to the regular system
-	 * cadence. If we find this inaccurate, we might come up with a
-	 * more sophisticated heuristic later.
-	 */
-	return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn);
-}
-
-static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
-				       struct mm_struct *mm,
-				       unsigned long address)
-{
-	trace_kvm_test_age_hva(address);
-
-	return kvm_handle_hva_range_no_flush(mn, address, address + 1,
-					     kvm_test_age_gfn);
-}
-
 struct test_clear_young_args {
 	unsigned long *bitmap;
 	unsigned long end;
@@ -969,8 +917,6 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
-	.clear_young		= kvm_mmu_notifier_clear_young,
-	.test_young		= kvm_mmu_notifier_test_young,
 	.test_clear_young	= kvm_mmu_notifier_test_clear_young,
 	.change_pte		= kvm_mmu_notifier_change_pte,
 	.release		= kvm_mmu_notifier_release,
-- 
2.41.0.rc0.172.g3f132b7071-goog


  parent reply	other threads:[~2023-05-26 23:45 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-26 23:44 [PATCH mm-unstable v2 00/10] mm/kvm: locklessly clear the accessed bit Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 01/10] mm/kvm: add mmu_notifier_ops->test_clear_young() Yu Zhao
2023-06-06  8:34   ` Tzung-Bi Shih
2023-06-09  1:00     ` Yu Zhao
     [not found]   ` <ZHedMX470b7EMwbe@ziepe.ca>
2023-06-09  9:04     ` Paolo Bonzini
2023-06-15 17:42   ` Sean Christopherson
2023-06-20  7:30   ` Nicholas Piggin
2023-05-26 23:44 ` Yu Zhao [this message]
2023-05-26 23:44 ` [PATCH mm-unstable v2 03/10] kvm/arm64: export stage2_try_set_pte() and macros Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 04/10] kvm/arm64: make stage2 page tables RCU safe Yu Zhao
2023-05-27 18:08   ` Oliver Upton
2023-05-27 20:13     ` Yu Zhao
2023-05-30 19:37       ` Oliver Upton
2023-05-30 20:06         ` Yu Zhao
     [not found]           ` <ZHef0VsZvZ1Vnz0u@linux.dev>
2023-05-31 23:10             ` Yu Zhao
2023-05-31 23:22               ` Oliver Upton
2023-05-31 23:41                 ` Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 05/10] kvm/arm64: add kvm_arch_test_clear_young() Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 06/10] kvm/powerpc: make radix page tables RCU safe Yu Zhao
2023-06-20  6:32   ` Nicholas Piggin
2023-06-20  8:00     ` Yu Zhao
2023-06-20 10:49       ` Nicholas Piggin
2023-05-26 23:44 ` [PATCH mm-unstable v2 07/10] kvm/powerpc: add kvm_arch_test_clear_young() Yu Zhao
2023-06-20  7:47   ` Nicholas Piggin
2023-06-21  0:38     ` Yu Zhao
2023-06-21  2:51       ` Nicholas Piggin
2023-05-26 23:44 ` [PATCH mm-unstable v2 08/10] kvm/x86: move tdp_mmu_enabled and shadow_accessed_mask Yu Zhao
2023-06-15 16:59   ` Sean Christopherson
2023-05-26 23:44 ` [PATCH mm-unstable v2 09/10] kvm/x86: add kvm_arch_test_clear_young() Yu Zhao
2023-06-09  9:06   ` Paolo Bonzini
2023-06-15 18:26   ` Sean Christopherson
2023-05-26 23:44 ` [PATCH mm-unstable v2 10/10] mm: multi-gen LRU: use mmu_notifier_test_clear_young() Yu Zhao
2023-06-09  0:59 ` kvm/arm64: Spark benchmark Yu Zhao
2023-06-09 13:04   ` Marc Zyngier
2023-06-18 20:11     ` Yu Zhao
2023-06-09  0:59 ` kvm/powerpc: memcached benchmark Yu Zhao
2023-06-09  0:59 ` kvm/x86: multichase benchmark Yu Zhao
2023-06-18 19:19   ` Yu Zhao
2023-06-09  9:07 ` [PATCH mm-unstable v2 00/10] mm/kvm: locklessly clear the accessed bit Paolo Bonzini
2023-06-20  2:19   ` Yu Zhao

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=20230526234435.662652-3-yuzhao@google.com \
    --to=yuzhao@google.com \
    --cc=Jason@zx2c4.com \
    --cc=akpm@linux-foundation.org \
    --cc=anup@brainfault.org \
    --cc=apopple@nvidia.com \
    --cc=bgardon@google.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=chao.p.peng@linux.intel.com \
    --cc=christophe.leroy@csgroup.eu \
    --cc=corbet@lwn.net \
    --cc=cuigaosheng1@huawei.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=farosas@linux.ibm.com \
    --cc=gshan@redhat.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jgg@ziepe.ca \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@google.com \
    --cc=linux-mm@kvack.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=maz@kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=michael@michaellarabel.com \
    --cc=mingo@redhat.com \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.com \
    --cc=oliver.upton@linux.dev \
    --cc=paulus@ozlabs.org \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=seanjc@google.com \
    --cc=suzuki.poulose@arm.com \
    --cc=tglx@linutronix.de \
    --cc=thuth@redhat.com \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=yuzenghui@huawei.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).