From: Mikulas Patocka mpatocka@redhat.com
mainline inclusion from mainline-v6.0-rc3 commit 8238b4579866b7c1bb99883cfe102a43db5506ff category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IB5UKT
--------------------------------
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
Conflicts: arch/x86/include/asm/bitops.h include/asm-generic/bitops/non-atomic.h include/asm-generic/bitops/instrumented-non-atomic.h include/asm-generic/bitops/non-instrumented-non-atomic.h include/linux/bitops.h include/linux/buffer_head.h include/asm-generic/bitops/generic-non-atomic.h Documentation/atomic_bitops.txt [Due to the large number of patch modifications and conflicts, patch adaptation is performed in the original contexts] Signed-off-by: Zizhi Wo wozizhi@huawei.com Signed-off-by: Baokun Li libaokun1@huawei.com --- Documentation/atomic_bitops.txt | 10 ++++----- arch/x86/include/asm/bitops.h | 21 +++++++++++++++++++ .../bitops/instrumented-non-atomic.h | 12 +++++++++++ include/asm-generic/bitops/non-atomic.h | 14 +++++++++++++ include/linux/wait_bit.h | 8 +++---- kernel/sched/wait_bit.c | 2 +- 6 files changed, 56 insertions(+), 11 deletions(-)
diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt index 093cdaefdb37..edea4656c5c0 100644 --- a/Documentation/atomic_bitops.txt +++ b/Documentation/atomic_bitops.txt @@ -58,13 +58,11 @@ Like with atomic_t, the rule of thumb is:
- RMW operations that have a return value are fully ordered.
- - RMW operations that are conditional are unordered on FAILURE, - otherwise the above rules apply. In the case of test_and_{}_bit() operations, - if the bit in memory is unchanged by the operation then it is deemed to have - failed. + - RMW operations that are conditional are fully ordered.
-Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and -clear_bit_unlock() which has RELEASE semantics. +Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics, +clear_bit_unlock() which has RELEASE semantics and test_bit_acquire which has +ACQUIRE semantics.
Since a platform only has a single means of achieving atomic operations the same barriers as for atomic_t are used, see atomic_t.txt. diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 0367efdc5b7a..c14e861f9956 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; }
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile("testb %2,%1" + CC_SET(nz) + : CC_OUT(nz) (oldbit) + : "m" (((unsigned char *)addr)[nr >> 3]), + "i" (1 << (nr & 7)) + : "memory"); + + return oldbit; +} + static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; @@ -224,6 +238,13 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l ? constant_test_bit((nr), (addr)) \ : variable_test_bit((nr), (addr)))
+static __always_inline bool +arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : + variable_test_bit(nr, addr); +} + /** * __ffs - find first set bit in word * @word: The word to search diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 37363d570b9b..da7f0d0a707c 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -135,4 +135,16 @@ static inline bool test_bit(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 7e10c4b50c5d..46437282d6d0 100644 --- a/include/asm-generic/bitops/non-atomic.h +++ b/include/asm-generic/bitops/non-atomic.h @@ -3,6 +3,7 @@ #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
#include <asm/types.h> +#include <asm/barrier.h>
/** * __set_bit - Set a bit in memory @@ -106,4 +107,17 @@ static inline int test_bit(int nr, const volatile unsigned long *addr) return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); }
+/** + * arch_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 +arch_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))); +} +#define test_bit_acquire arch_test_bit_acquire + #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ 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); } diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c index 02ce292b9bc0..99be72732ee0 100644 --- a/kernel/sched/wait_bit.c +++ b/kernel/sched/wait_bit.c @@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_ prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); if (test_bit(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);