wait_on_bit tests the bit without any memory barriers, consequently the
code that follows wait_on_bit may be moved before testing the bit on
architectures with weak memory ordering. When the code tests for some
event using wait_on_bit and then performs a load operation, the load may
be unexpectedly moved before wait_on_bit and it may return data that
existed before the event occurred.
Such bugs exist in fs/buffer.c:__wait_on_buffer,
drivers/md/dm-bufio.c:new_read,
drivers/media/usb/dvb-usb-v2/dvb_usb_core.c:dvb_usb_start_feed,
drivers/bluetooth/btusb.c:btusb_mtk_hci_wmt_sync
and perhaps in other places.
We fix this class of bugs by adding a new function test_bit_acquire that
reads the bit and provides acquire memory ordering semantics.
Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
---
arch/s390/include/asm/bitops.h | 10 ++++++++++
arch/x86/include/asm/bitops.h | 7 ++++++-
include/asm-generic/bitops/instrumented-non-atomic.h | 11 +++++++++++
include/asm-generic/bitops/non-atomic.h | 13 +++++++++++++
include/linux/wait_bit.h | 8 ++++----
kernel/sched/wait_bit.c | 6 +++---
6 files changed, 47 insertions(+), 8 deletions(-)
Index: linux-2.6/arch/x86/include/asm/bitops.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/bitops.h 2022-08-01 12:27:43.000000000 +0200
+++ linux-2.6/arch/x86/include/asm/bitops.h 2022-08-01 12:27:43.000000000 +0200
@@ -203,8 +203,10 @@ arch_test_and_change_bit(long nr, volati
static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
{
- return ((1UL << (nr & (BITS_PER_LONG-1))) &
+ bool r = ((1UL << (nr & (BITS_PER_LONG-1))) &
(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
+ barrier();
+ return r;
}
static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
@@ -224,6 +226,9 @@ static __always_inline bool variable_tes
? constant_test_bit((nr), (addr)) \
: variable_test_bit((nr), (addr)))
+#define arch_test_bit_acquire(nr, addr) \
+ arch_test_bit(nr, addr)
+
/**
* __ffs - find first set bit in word
* @word: The word to search
Index: linux-2.6/include/asm-generic/bitops/instrumented-non-atomic.h
===================================================================
--- linux-2.6.orig/include/asm-generic/bitops/instrumented-non-atomic.h 2022-08-01 12:27:43.000000000 +0200
+++ linux-2.6/include/asm-generic/bitops/instrumented-non-atomic.h 2022-08-01 12:28:33.000000000 +0200
@@ -135,4 +135,15 @@ static __always_inline bool test_bit(lon
return arch_test_bit(nr, addr);
}
+/**
+ * test_bit_acquire - Determine whether a bit is set with acquire semantics
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool test_bit_acquire(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 */
Index: linux-2.6/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-2.6.orig/include/asm-generic/bitops/non-atomic.h 2022-08-01 12:27:43.000000000 +0200
+++ linux-2.6/include/asm-generic/bitops/non-atomic.h 2022-08-01 12:27:43.000000000 +0200
@@ -119,4 +119,17 @@ arch_test_bit(unsigned int nr, const vol
}
#define test_bit arch_test_bit
+/**
+ * arch_test_bit - Determine whether a bit is set with acquire semantics
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline int
+arch_test_bit_acquire(unsigned int nr, const volatile unsigned long *addr)
+{
+ unsigned val = smp_load_acquire(&addr[BIT_WORD(nr)]);
+ return 1UL & (val >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-2.6/arch/s390/include/asm/bitops.h
===================================================================
--- linux-2.6.orig/arch/s390/include/asm/bitops.h 2022-08-01 12:27:43.000000000 +0200
+++ linux-2.6/arch/s390/include/asm/bitops.h 2022-08-01 12:27:43.000000000 +0200
@@ -184,6 +184,16 @@ static inline bool arch_test_bit(unsigne
return *addr & mask;
}
+static inline bool arch_test_bit_acquire(unsigned long nr,
+ const volatile unsigned long *ptr)
+{
+ const volatile unsigned long *addr = __bitops_word(nr, ptr);
+ unsigned long val = smp_load_acquire(addr);
+ unsigned long mask = __bitops_mask(nr);
+
+ return val & mask;
+}
+
static inline bool arch_test_and_set_bit_lock(unsigned long nr,
volatile unsigned long *ptr)
{
Index: linux-2.6/include/linux/wait_bit.h
===================================================================
--- linux-2.6.orig/include/linux/wait_bit.h 2022-08-01 12:27:43.000000000 +0200
+++ linux-2.6/include/linux/wait_bit.h 2022-08-01 12:27:43.000000000 +0200
@@ -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,
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,
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);
}
Index: linux-2.6/kernel/sched/wait_bit.c
===================================================================
--- linux-2.6.orig/kernel/sched/wait_bit.c 2022-08-01 12:27:43.000000000 +0200
+++ linux-2.6/kernel/sched/wait_bit.c 2022-08-01 12:27:43.000000000 +0200
@@ -25,7 +25,7 @@ int wake_bit_function(struct wait_queue_
if (wait_bit->key.flags != key->flags ||
wait_bit->key.bit_nr != key->bit_nr ||
- test_bit(key->bit_nr, key->flags))
+ test_bit_acquire(key->bit_nr, key->flags))
return 0;
return autoremove_wake_function(wq_entry, mode, sync, key);
@@ -45,9 +45,9 @@ __wait_on_bit(struct wait_queue_head *wq
do {
prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
- if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
+ if (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags))
ret = (*action)(&wbq_entry->key, mode);
- } while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+ } while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
finish_wait(wq_head, &wbq_entry->wq_entry);
