linux-kernel - [PATCH v11 08/12] 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: <20240531092001.30428-9-byungchul@sk.com>
Date: Fri, 31 May 2024 18:19:57 +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,
	vernhao@...cent.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,
	rjgolo@...il.com
Subject: [PATCH v11 08/12] mm/rmap: recognize read-only tlb entries during batched tlb flush

Functionally, no change.  This is a preparation for luf mechanism that
requires to recognize read-only tlb entries and handle them in a
different way.  The newly introduced API in this patch, fold_ubc(), will
be used by luf mechanism.

Signed-off-by: Byungchul Park <byungchul@...com>
---
 include/linux/sched.h |  1 +
 mm/internal.h         |  4 ++++
 mm/rmap.c             | 34 ++++++++++++++++++++++++++++++++--
 3 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ab5a2ed79b88..d9722c014157 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1340,6 +1340,7 @@ struct task_struct {
 #endif
 
 	struct tlbflush_unmap_batch	tlb_ubc;
+	struct tlbflush_unmap_batch	tlb_ubc_ro;
 	unsigned short int		ugen;
 
 	/* Cache last used pipe for splice(): */
diff --git a/mm/internal.h b/mm/internal.h
index dba6d0eb7b6d..ca6fb5b2a640 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1124,6 +1124,7 @@ 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(struct tlbflush_unmap_batch *dst, struct tlbflush_unmap_batch *src);
 #else
 static inline void try_to_unmap_flush(void)
 {
@@ -1134,6 +1135,9 @@ 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(struct tlbflush_unmap_batch *dst, struct tlbflush_unmap_batch *src)
+{
+}
 #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 a65a94aada8d..1a246788e867 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -634,6 +634,28 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
 }
 
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+
+void fold_ubc(struct tlbflush_unmap_batch *dst,
+	      struct tlbflush_unmap_batch *src)
+{
+	if (!src->flush_required)
+		return;
+
+	/*
+	 * Fold src to dst.
+	 */
+	arch_tlbbatch_fold(&dst->arch, &src->arch);
+	dst->writable = dst->writable || src->writable;
+	dst->flush_required = true;
+
+	/*
+	 * Reset src.
+	 */
+	arch_tlbbatch_clear(&src->arch);
+	src->flush_required = false;
+	src->writable = 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
@@ -643,7 +665,9 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
 void try_to_unmap_flush(void)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+	struct tlbflush_unmap_batch *tlb_ubc_ro = &current->tlb_ubc_ro;
 
+	fold_ubc(tlb_ubc, tlb_ubc_ro);
 	if (!tlb_ubc->flush_required)
 		return;
 
@@ -657,8 +681,9 @@ void try_to_unmap_flush(void)
 void try_to_unmap_flush_dirty(void)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
+	struct tlbflush_unmap_batch *tlb_ubc_ro = &current->tlb_ubc_ro;
 
-	if (tlb_ubc->writable)
+	if (tlb_ubc->writable || tlb_ubc_ro->writable)
 		try_to_unmap_flush();
 }
 
@@ -675,13 +700,18 @@ 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))
+		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