From: Mikulas Patocka mpatocka@redhat.com
commit 8238b4579866b7c1bb99883cfe102a43db5506ff upstream.
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 Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/bitops.h | 21 +++++++++++++++++++ include/asm-generic/bitops/instrumented-non-atomic.h | 12 ++++++++++ include/asm-generic/bitops/non-atomic.h | 14 ++++++++++++ include/linux/buffer_head.h | 2 - include/linux/wait_bit.h | 8 +++---- kernel/sched/wait_bit.c | 2 - 6 files changed, 53 insertions(+), 6 deletions(-)
--- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -207,6 +207,20 @@ static __always_inline bool constant_tes (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_tes ? 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 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -135,4 +135,16 @@ static __always_inline bool test_bit(lon 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 */ --- 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>
/** * arch___set_bit - Set a bit in memory @@ -119,4 +120,17 @@ arch_test_bit(unsigned int nr, const vol } #define test_bit arch_test_bit
+/** + * 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_ */ --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda * 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) --- 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, 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); } --- a/kernel/sched/wait_bit.c +++ b/kernel/sched/wait_bit.c @@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq 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);