mirror of
https://github.com/torvalds/linux
synced 2024-10-01 00:39:03 +00:00
b9420e1c87
Even if memset() is inlined (as on x86) using it to zero the union generates a memory word write of zero, followed by a write of the smaller field, and then a read of the word. As well as being a lot of instructions the sequence is unlikely to be optimised by the store-load forward hardware so will be slow. Instead allocate a field of the union that is the same size as the entire union and write a zero value to it. The compiler will then generate the required value in a register. Zeroing the union shouldn't be necessary, but this patch series isn't intended to have a behavioural change. Signed-off-by: David Laight <david.laight@aculab.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
||
|---|---|---|
| .. | ||
| auth.h | ||
| checksum.h | ||
| command.h | ||
| constants.h | ||
| sctp.h | ||
| sm.h | ||
| structs.h | ||
| tsnmap.h | ||
| ulpevent.h | ||
| ulpqueue.h | ||