linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Byungchul Park <byungchul@sk.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: kernel_team@skhynix.com, akpm@linux-foundation.org,
	ying.huang@intel.com, namit@vmware.com, xhao@linux.alibaba.com,
	mgorman@techsingularity.net, hughd@google.com,
	willy@infradead.org, david@redhat.com, peterz@infradead.org,
	luto@kernel.org, tglx@linutronix.de, mingo@redhat.com,
	bp@alien8.de, dave.hansen@linux.intel.com
Subject: [v4 1/3] mm/rmap: Recognize read-only TLB entries during batched TLB flush
Date: Thu,  9 Nov 2023 13:59:06 +0900	[thread overview]
Message-ID: <20231109045908.54996-2-byungchul@sk.com> (raw)
In-Reply-To: <20231109045908.54996-1-byungchul@sk.com>

Functionally, no change. This is a preparation for migrc mechanism that
requires to recognize read-only TLB entries and makes use of them to
batch more aggressively.

Signed-off-by: Byungchul Park <byungchul@sk.com>
---
 arch/x86/include/asm/tlbflush.h |  3 +++
 arch/x86/mm/tlb.c               | 11 +++++++++++
 include/linux/sched.h           |  1 +
 mm/internal.h                   |  4 ++++
 mm/rmap.c                       | 30 +++++++++++++++++++++++++++++-
 5 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 25726893c6f4..5c618a8821de 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -292,6 +292,9 @@ static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
 }
 
 extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+extern void arch_tlbbatch_clear(struct arch_tlbflush_unmap_batch *batch);
+extern void arch_tlbbatch_fold(struct arch_tlbflush_unmap_batch *bdst,
+			       struct arch_tlbflush_unmap_batch *bsrc);
 
 static inline bool pte_flags_need_flush(unsigned long oldflags,
 					unsigned long newflags,
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 453ea95b667d..d3c89a3d91eb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1274,6 +1274,17 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	put_cpu();
 }
 
+void arch_tlbbatch_clear(struct arch_tlbflush_unmap_batch *batch)
+{
+	cpumask_clear(&batch->cpumask);
+}
+
+void arch_tlbbatch_fold(struct arch_tlbflush_unmap_batch *bdst,
+			struct arch_tlbflush_unmap_batch *bsrc)
+{
+	cpumask_or(&bdst->cpumask, &bdst->cpumask, &bsrc->cpumask);
+}
+
 /*
  * Blindly accessing user memory from NMI context can be dangerous
  * if we're in the middle of switching the current user task or
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 77f01ac385f7..8a31527d9ed8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1324,6 +1324,7 @@ struct task_struct {
 #endif
 
 	struct tlbflush_unmap_batch	tlb_ubc;
+	struct tlbflush_unmap_batch	tlb_ubc_ro;
 
 	/* Cache last used pipe for splice(): */
 	struct pipe_inode_info		*splice_pipe;
diff --git a/mm/internal.h b/mm/internal.h
index 30cf724ddbce..9764b240e259 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -861,6 +861,7 @@ extern struct workqueue_struct *mm_percpu_wq;
 void try_to_unmap_flush(void);
 void try_to_unmap_flush_dirty(void);
 void flush_tlb_batched_pending(struct mm_struct *mm);
+void fold_ubc_ro(void);
 #else
 static inline void try_to_unmap_flush(void)
 {
@@ -871,6 +872,9 @@ static inline void try_to_unmap_flush_dirty(void)
 static inline void flush_tlb_batched_pending(struct mm_struct *mm)
 {
 }
+static inline void fold_ubc_ro(void)
+{
+}
 #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
 
 extern const struct trace_print_flags pageflag_names[];
diff --git a/mm/rmap.c b/mm/rmap.c
index 9f795b93cf40..c787ae94b4c6 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -605,6 +605,28 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
 }
 
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+
+void fold_ubc_ro(void)
+{
+	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+	struct tlbflush_unmap_batch *tlb_ubc_ro = &current->tlb_ubc_ro;
+
+	if (!tlb_ubc_ro->flush_required)
+		return;
+
+	/*
+	 * Fold tlb_ubc_ro's data to tlb_ubc.
+	 */
+	arch_tlbbatch_fold(&tlb_ubc->arch, &tlb_ubc_ro->arch);
+	tlb_ubc->flush_required = true;
+
+	/*
+	 * Reset tlb_ubc_ro's data.
+	 */
+	arch_tlbbatch_clear(&tlb_ubc_ro->arch);
+	tlb_ubc_ro->flush_required = false;
+}
+
 /*
  * Flush TLB entries for recently unmapped pages from remote CPUs. It is
  * important if a PTE was dirty when it was unmapped that it's flushed
@@ -615,6 +637,7 @@ void try_to_unmap_flush(void)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
 
+	fold_ubc_ro();
 	if (!tlb_ubc->flush_required)
 		return;
 
@@ -645,13 +668,18 @@ void try_to_unmap_flush_dirty(void)
 static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval,
 				      unsigned long uaddr)
 {
-	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+	struct tlbflush_unmap_batch *tlb_ubc;
 	int batch;
 	bool writable = pte_dirty(pteval);
 
 	if (!pte_accessible(mm, pteval))
 		return;
 
+	if (pte_write(pteval) || writable)
+		tlb_ubc = &current->tlb_ubc;
+	else
+		tlb_ubc = &current->tlb_ubc_ro;
+
 	arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr);
 	tlb_ubc->flush_required = true;
 
-- 
2.17.1



  reply	other threads:[~2023-11-09  4:59 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-09  4:59 [v4 0/3] Reduce TLB flushes under some specific conditions Byungchul Park
2023-11-09  4:59 ` Byungchul Park [this message]
2023-11-09 20:26   ` [v4 1/3] mm/rmap: Recognize read-only TLB entries during batched TLB flush kernel test robot
2023-11-09  4:59 ` [v4 2/3] mm: Defer TLB flush by keeping both src and dst folios at migration Byungchul Park
2023-11-09 14:36   ` Matthew Wilcox
2023-11-10  1:29     ` Byungchul Park
2024-01-15  7:55     ` Byungchul Park
2023-11-09 17:09   ` kernel test robot
2023-11-09 19:07   ` kernel test robot
2023-11-09  4:59 ` [v4 3/3] mm: Pause migrc mechanism at high memory pressure Byungchul Park
2023-11-09  5:20 ` [v4 0/3] Reduce TLB flushes under some specific conditions Huang, Ying
2023-11-10  1:32   ` Byungchul Park
2023-11-15  2:57   ` Byungchul Park
2023-11-09 14:26 ` Dave Hansen
2023-11-10  1:08   ` Byungchul Park
2023-11-15  6:43   ` Byungchul Park
2024-01-15  7:58   ` Byungchul Park

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=20231109045908.54996-2-byungchul@sk.com \
    --to=byungchul@sk.com \
    --cc=akpm@linux-foundation.org \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@redhat.com \
    --cc=hughd@google.com \
    --cc=kernel_team@skhynix.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mingo@redhat.com \
    --cc=namit@vmware.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=willy@infradead.org \
    --cc=xhao@linux.alibaba.com \
    --cc=ying.huang@intel.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