All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
To: linux-mm@kvack.org, akpm@linux-foundation.org
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	npiggin@gmail.com, kaleshsingh@google.com,
	joel@joelfernandes.org,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	linuxppc-dev@lists.ozlabs.org
Subject: [RFC PATCH 2/2] mm/mremap: Fix race between MOVE_PUD mremap and pageout
Date: Tue, 25 May 2021 14:03:44 +0530	[thread overview]
Message-ID: <20210525083344.162377-2-aneesh.kumar@linux.ibm.com> (raw)
In-Reply-To: <20210525083344.162377-1-aneesh.kumar@linux.ibm.com>

CPU 1				CPU 2					CPU 3

mremap(old_addr, new_addr)      page_shrinker/try_to_unmap_one

mmap_write_lock_killable()

				addr = old_addr
				lock(pte_ptl)
lock(pud_ptl)
pud = *old_pud
pud_clear(old_pud)
flush_tlb_range(old_addr)

*new_pud = pud
									*new_addr = 10; and fills
									TLB with new addr
									and old pfn

unlock(pud_ptl)
				ptep_clear_flush()
				old pfn is free.
									Stale TLB entry

Fix this race by holding pud lock in pageout.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 include/linux/rmap.h |  4 ++++
 mm/page_vma_mapped.c | 13 ++++++++++---
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 272ab0c2b60b..491c65ce1d46 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -209,6 +209,7 @@ struct page_vma_mapped_walk {
 	pte_t *pte;
 	spinlock_t *pte_ptl;
 	spinlock_t *pmd_ptl;
+	spinlock_t *pud_ptl;
 	unsigned int flags;
 };
 
@@ -221,6 +222,9 @@ static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw)
 		spin_unlock(pvmw->pte_ptl);
 	if (pvmw->pmd_ptl)
 		spin_unlock(pvmw->pmd_ptl);
+	if (pvmw->pud_ptl)
+		spin_unlock(pvmw->pud_ptl);
+
 }
 
 bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw);
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 87a2c94c7e27..c913bc34b1d3 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -180,8 +180,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	pud = pud_offset(p4d, pvmw->address);
 	if (!pud_present(*pud))
 		return false;
+
+	pvmw->pud_ptl = pud_lock(mm, pud);
 	pvmw->pmd = pmd_offset(pud, pvmw->address);
-	pvmw->pmd_ptl = pmd_lock(mm, pvmw->pmd);
+	if (USE_SPLIT_PMD_PTLOCKS)
+		pvmw->pmd_ptl = pmd_lock(mm, pvmw->pmd);
 	/*
 	 * Make sure the pmd value isn't cached in a register by the
 	 * compiler and used as a stale value after we've observed a
@@ -235,8 +238,12 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 					spin_unlock(pvmw->pte_ptl);
 					pvmw->pte_ptl = NULL;
 				}
-				spin_unlock(pvmw->pmd_ptl);
-				pvmw->pmd_ptl = NULL;
+				if (pvmw->pmd_ptl) {
+					spin_unlock(pvmw->pmd_ptl);
+					pvmw->pmd_ptl = NULL;
+				}
+				spin_unlock(pvmw->pud_ptl);
+				pvmw->pud_ptl = NULL;
 				goto restart;
 			} else {
 				pvmw->pte++;
-- 
2.31.1


WARNING: multiple messages have this Message-ID (diff)
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
To: linux-mm@kvack.org, akpm@linux-foundation.org
Cc: mpe@ellerman.id.au, linuxppc-dev@lists.ozlabs.org,
	kaleshsingh@google.com, npiggin@gmail.com,
	joel@joelfernandes.org,
	Christophe Leroy <christophe.leroy@csgroup.eu>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: [RFC PATCH 2/2] mm/mremap: Fix race between MOVE_PUD mremap and pageout
Date: Tue, 25 May 2021 14:03:44 +0530	[thread overview]
Message-ID: <20210525083344.162377-2-aneesh.kumar@linux.ibm.com> (raw)
In-Reply-To: <20210525083344.162377-1-aneesh.kumar@linux.ibm.com>

CPU 1				CPU 2					CPU 3

mremap(old_addr, new_addr)      page_shrinker/try_to_unmap_one

mmap_write_lock_killable()

				addr = old_addr
				lock(pte_ptl)
lock(pud_ptl)
pud = *old_pud
pud_clear(old_pud)
flush_tlb_range(old_addr)

*new_pud = pud
									*new_addr = 10; and fills
									TLB with new addr
									and old pfn

unlock(pud_ptl)
				ptep_clear_flush()
				old pfn is free.
									Stale TLB entry

Fix this race by holding pud lock in pageout.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 include/linux/rmap.h |  4 ++++
 mm/page_vma_mapped.c | 13 ++++++++++---
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 272ab0c2b60b..491c65ce1d46 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -209,6 +209,7 @@ struct page_vma_mapped_walk {
 	pte_t *pte;
 	spinlock_t *pte_ptl;
 	spinlock_t *pmd_ptl;
+	spinlock_t *pud_ptl;
 	unsigned int flags;
 };
 
@@ -221,6 +222,9 @@ static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw)
 		spin_unlock(pvmw->pte_ptl);
 	if (pvmw->pmd_ptl)
 		spin_unlock(pvmw->pmd_ptl);
+	if (pvmw->pud_ptl)
+		spin_unlock(pvmw->pud_ptl);
+
 }
 
 bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw);
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 87a2c94c7e27..c913bc34b1d3 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -180,8 +180,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	pud = pud_offset(p4d, pvmw->address);
 	if (!pud_present(*pud))
 		return false;
+
+	pvmw->pud_ptl = pud_lock(mm, pud);
 	pvmw->pmd = pmd_offset(pud, pvmw->address);
-	pvmw->pmd_ptl = pmd_lock(mm, pvmw->pmd);
+	if (USE_SPLIT_PMD_PTLOCKS)
+		pvmw->pmd_ptl = pmd_lock(mm, pvmw->pmd);
 	/*
 	 * Make sure the pmd value isn't cached in a register by the
 	 * compiler and used as a stale value after we've observed a
@@ -235,8 +238,12 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 					spin_unlock(pvmw->pte_ptl);
 					pvmw->pte_ptl = NULL;
 				}
-				spin_unlock(pvmw->pmd_ptl);
-				pvmw->pmd_ptl = NULL;
+				if (pvmw->pmd_ptl) {
+					spin_unlock(pvmw->pmd_ptl);
+					pvmw->pmd_ptl = NULL;
+				}
+				spin_unlock(pvmw->pud_ptl);
+				pvmw->pud_ptl = NULL;
 				goto restart;
 			} else {
 				pvmw->pte++;
-- 
2.31.1



  reply	other threads:[~2021-05-25  8:34 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-25  8:33 [RFC PATCH 1/2] mm/mremap: Fix race between MOVE_PMD mremap and pageout Aneesh Kumar K.V
2021-05-25  8:33 ` Aneesh Kumar K.V
2021-05-25  8:33 ` Aneesh Kumar K.V [this message]
2021-05-25  8:33   ` [RFC PATCH 2/2] mm/mremap: Fix race between MOVE_PUD " Aneesh Kumar K.V
2021-05-25 17:28   ` Linus Torvalds
2021-05-25 17:28     ` Linus Torvalds

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=20210525083344.162377-2-aneesh.kumar@linux.ibm.com \
    --to=aneesh.kumar@linux.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=joel@joelfernandes.org \
    --cc=kaleshsingh@google.com \
    --cc=kirill@shutemov.name \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=npiggin@gmail.com \
    --cc=torvalds@linux-foundation.org \
    /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.