wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

7 files changed, 34 insertions, 5 deletions

diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h
index 3d5ebd24652b..564a8c675d85 100644
--- a/include/asm-generic/bitops/generic-non-atomic.h
+++ b/include/asm-generic/bitops/generic-non-atomic.h
@@ -4,6 +4,7 @@
 #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
 
 #include <linux/bits.h>
+#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
@@ -127,6 +128,18 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * const_*() definitions provide good compile-time optimizations when
  * the passed arguments can be resolved at compile time.
@@ -137,6 +150,7 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
 #define const___test_and_set_bit	generic___test_and_set_bit
 #define const___test_and_clear_bit	generic___test_and_clear_bit
 #define const___test_and_change_bit	generic___test_and_change_bit
+#define const_test_bit_acquire		generic_test_bit_acquire
 
 /**
  * const_test_bit - Determine whether a bit is set
diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
index 988a3bbfba34..2b238b161a62 100644
--- a/include/asm-generic/bitops/instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -142,4 +142,16 @@ _test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 5c37ced343ae..71f8d54a5195 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -13,6 +13,7 @@
 #define arch___test_and_change_bit generic___test_and_change_bit
 
 #define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 #include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h
index bdb9b1ffaee9..0ddc78dfc358 100644
--- a/include/asm-generic/bitops/non-instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h
@@ -12,5 +12,6 @@
 #define ___test_and_change_bit	arch___test_and_change_bit
 
 #define _test_bit		arch_test_bit
+#define _test_bit_acquire	arch_test_bit_acquire
 
 #endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf9bf65039f2..3b89c64bcfd8 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -59,6 +59,7 @@ extern unsigned long __sw_hweight64(__u64 w);
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
+#define test_bit_acquire(nr, addr)	bitop(_test_bit_acquire, nr, addr)
 
 /*
  * Include this here because some architectures need generic_ffs/fls in
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index def8b8d30ccc..089c9ade4325 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -156,7 +156,7 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh)
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 7dec36aecbd9..7725b7579b78 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }