It has been reported that the tag setting operation on newly-allocated
pages can cause the page flags to be corrupted when performed
concurrently with other flag updates as a result of the use of
non-atomic operations. Fix the problem by using a compare-exchange
loop to update the tag.
Signed-off-by: Peter Collingbourne <pcc(a)google.com>
Link: https://linux-review.googlesource.com/id/I456b24a2b9067d93968d43b4bb3351c0c…
Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc")
Cc: stable(a)vger.kernel.org
---
v3:
- use try_cmpxchg() as suggested by Peter Zijlstra on another
patch
v2:
- use READ_ONCE()
include/linux/mm.h | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c768a7c81b0b..87473fe52c3f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1531,11 +1531,18 @@ static inline u8 page_kasan_tag(const struct page *page)
static inline void page_kasan_tag_set(struct page *page, u8 tag)
{
- if (kasan_enabled()) {
- tag ^= 0xff;
- page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
- page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
- }
+ unsigned long old_flags, flags;
+
+ if (!kasan_enabled())
+ return;
+
+ tag ^= 0xff;
+ old_flags = READ_ONCE(page->flags);
+ do {
+ flags = old_flags;
+ flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
+ flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
+ } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags)));
}
static inline void page_kasan_tag_reset(struct page *page)
--
2.34.1.703.g22d0c6ccf7-goog
The membarrier command MEMBARRIER_CMD_QUERY allows querying the
available membarrier commands. When the membarrier-rseq fence commands
were added, a new MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK was
introduced with the intent to expose them with the MEMBARRIER_CMD_QUERY
command, the but it was never added to MEMBARRIER_CMD_BITMASK.
The membarrier-rseq fence commands are therefore not wired up with the
query command.
Rename MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK to
MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK (the bitmask is not a command
per-se), and change the erroneous
MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK (which does not
actually exist) to MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ.
Wire up MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK in
MEMBARRIER_CMD_BITMASK. Fixing this allows discovering availability of
the membarrier-rseq fence feature.
Fixes: 2a36ab717e8f ("rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com>
Cc: Peter Oskolkov <posk(a)google.com>
Cc: Peter Zijlstra (Intel) <peterz(a)infradead.org>
Cc: <stable(a)vger.kernel.org> # 5.10+
---
kernel/sched/membarrier.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index b5add64d9698..3d2825408e3a 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -147,11 +147,11 @@
#endif
#ifdef CONFIG_RSEQ
-#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK \
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \
(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ \
- | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ)
#else
-#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK 0
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK 0
#endif
#define MEMBARRIER_CMD_BITMASK \
@@ -159,7 +159,8 @@
| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \
| MEMBARRIER_CMD_PRIVATE_EXPEDITED \
| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \
- | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK)
+ | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \
+ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
static void ipi_mb(void *info)
{
--
2.17.1
In Linux 4.14 and 4.19 these architectures still have their own
implementations of get_user_pages_fast(). These also need to force
the write flag on when taking the fast path.
Fixes: 407faed92b4a ("gup: document and work around "COW can break either way" issue")
Fixes: 5e24029791e8 ("gup: document and work around "COW can break either way" issue")
Signed-off-by: Ben Hutchings <ben(a)decadent.org.uk>
---
arch/mips/mm/gup.c | 9 ++++++++-
arch/s390/mm/gup.c | 9 ++++++++-
arch/sh/mm/gup.c | 9 ++++++++-
arch/sparc/mm/gup.c | 9 ++++++++-
4 files changed, 32 insertions(+), 4 deletions(-)
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index 5a4875cac1ec..2e7a0d201c09 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -274,7 +274,14 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
goto slow;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ /*
+ * The FAST_GUP case requires FOLL_WRITE even for pure reads,
+ * because get_user_pages() may need to cause an early COW in
+ * order to avoid confusing the normal COW routines. So only
+ * targets that are already writable are safe to do by just
+ * looking at the page tables.
+ */
+ if (!gup_pud_range(pgd, addr, next, 1, pages, &nr))
goto slow;
} while (pgdp++, addr = next, addr != end);
local_irq_enable();
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 9b5b866d8adf..5389bf5bc828 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -287,7 +287,14 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
might_sleep();
start &= PAGE_MASK;
- nr = __get_user_pages_fast(start, nr_pages, write, pages);
+ /*
+ * The FAST_GUP case requires FOLL_WRITE even for pure reads,
+ * because get_user_pages() may need to cause an early COW in
+ * order to avoid confusing the normal COW routines. So only
+ * targets that are already writable are safe to do by just
+ * looking at the page tables.
+ */
+ nr = __get_user_pages_fast(start, nr_pages, 1, pages);
if (nr == nr_pages)
return nr;
diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c
index 56c86ca98ecf..23fa2fc8aabc 100644
--- a/arch/sh/mm/gup.c
+++ b/arch/sh/mm/gup.c
@@ -242,7 +242,14 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
goto slow;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ /*
+ * The FAST_GUP case requires FOLL_WRITE even for pure reads,
+ * because get_user_pages() may need to cause an early COW in
+ * order to avoid confusing the normal COW routines. So only
+ * targets that are already writable are safe to do by just
+ * looking at the page tables.
+ */
+ if (!gup_pud_range(pgd, addr, next, 1, pages, &nr))
goto slow;
} while (pgdp++, addr = next, addr != end);
local_irq_enable();
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index aee6dba83d0e..f291d34a1cd5 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -303,7 +303,14 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
goto slow;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ /*
+ * The FAST_GUP case requires FOLL_WRITE even for pure reads,
+ * because get_user_pages() may need to cause an early COW in
+ * order to avoid confusing the normal COW routines. So only
+ * targets that are already writable are safe to do by just
+ * looking at the page tables.
+ */
+ if (!gup_pud_range(pgd, addr, next, 1, pages, &nr))
goto slow;
} while (pgdp++, addr = next, addr != end);