seqlock: Introduce raw_read_seqcount_latch()
Because with latches there is a strict data dependency on the seq load we can avoid the rmb in favour of a read_barrier_depends. Suggested-by:Ingo Molnar <mingo@kernel.org> Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by:
Rusty Russell <rusty@rustcorp.com.au>
parent
0a04b016
Please register or sign in to comment