linux-kernel - [v4 1/3] mm/rmap: Recognize read-only TLB entries during batched TLB flush

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: <20231109045908.54996-2-byungchul@sk.com>
Date:   Thu,  9 Nov 2023 13:59:06 +0900
From:   Byungchul Park <byungchul@...com>
To:     linux-kernel@...r.kernel.org, linux-mm@...ck.org
Cc:     kernel_team@...ynix.com, akpm@...ux-foundation.org,
        ying.huang@...el.com, namit@...are.com, xhao@...ux.alibaba.com,
        mgorman@...hsingularity.net, hughd@...gle.com, willy@...radead.org,
        david@...hat.com, peterz@...radead.org, luto@...nel.org,
        tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
        dave.hansen@...ux.intel.com
Subject: [v4 1/3] mm/rmap: Recognize read-only TLB entries during batched TLB flush

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@...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