Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit d0c4307a authored by Hector Martin's avatar Hector Martin Committed by Greg Kroah-Hartman
Browse files

locking/atomic: Make test_and_*_bit() ordered on failure 



commit 415d832497098030241605c52ea83d4e2cfa7879 upstream.

These operations are documented as always ordered in
include/asm-generic/bitops/instrumented-atomic.h, and producer-consumer
type use cases where one side needs to ensure a flag is left pending
after some shared data was updated rely on this ordering, even in the
failure case.

This is the case with the workqueue code, which currently suffers from a
reproducible ordering violation on Apple M1 platforms (which are
notoriously out-of-order) that ends up causing the TTY layer to fail to
deliver data to userspace properly under the right conditions.  This
change fixes that bug.

Change the documentation to restrict the "no order on failure" story to
the _lock() variant (for which it makes sense), and remove the
early-exit from the generic implementation, which is what causes the
missing barrier semantics in that case.  Without this, the remaining
atomic op is fully ordered (including on ARM64 LSE, as of recent
versions of the architecture spec).

Suggested-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
Cc: stable@vger.kernel.org
Fixes: e986a0d6 ("locking/atomics, asm-generic/bitops/atomic.h: Rewrite using atomic_*() APIs")
Fixes: 61e02392 ("locking/atomic/bitops: Document and clarify ordering semantics for failed test_and_{}_bit()")
Signed-off-by: default avatarHector Martin <marcan@marcan.st>
Acked-by: default avatarWill Deacon <will@kernel.org>
Reviewed-by: default avatarArnd Bergmann <arnd@arndb.de>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent 90fb514a

Documentation/atomic_bitops.txt

+1 −1
Original line number Diff line number Diff line
@@ -59,7 +59,7 @@ 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,

   otherwise the above rules apply. In the case of test_and_set_bit_lock(),

   if the bit in memory is unchanged by the operation then it is deemed to have

   failed.

include/asm-generic/bitops/atomic.h

+0 −6
Original line number Diff line number Diff line
@@ -35,9 +35,6 @@ static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p) 
	unsigned long mask = BIT_MASK(nr);



	p += BIT_WORD(nr);

	if (READ_ONCE(*p) & mask)

		return 1;



	old = atomic_long_fetch_or(mask, (atomic_long_t *)p);

	return !!(old & mask);

}
@@ -48,9 +45,6 @@ static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p) 
	unsigned long mask = BIT_MASK(nr);



	p += BIT_WORD(nr);

	if (!(READ_ONCE(*p) & mask))

		return 0;



	old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);

	return !!(old & mask);

}