@@ -28,6 +28,7 @@
#define SCSI_TRANSPORT_FC_H
#include <linux/sched.h>
+#include <asm/unaligned.h>
#include <scsi/scsi.h>
#include <scsi/scsi_netlink.h>
@@ -797,22 +798,12 @@ fc_remote_port_chkready(struct fc_rport *rport)
static inline u64 wwn_to_u64(u8 *wwn)
{
- return (u64)wwn[0] << 56 | (u64)wwn[1] << 48 |
- (u64)wwn[2] << 40 | (u64)wwn[3] << 32 |
- (u64)wwn[4] << 24 | (u64)wwn[5] << 16 |
- (u64)wwn[6] << 8 | (u64)wwn[7];
+ return get_unaligned_be64(wwn);
}
static inline void u64_to_wwn(u64 inm, u8 *wwn)
{
- wwn[0] = (inm >> 56) & 0xff;
- wwn[1] = (inm >> 48) & 0xff;
- wwn[2] = (inm >> 40) & 0xff;
- wwn[3] = (inm >> 32) & 0xff;
- wwn[4] = (inm >> 24) & 0xff;
- wwn[5] = (inm >> 16) & 0xff;
- wwn[6] = (inm >> 8) & 0xff;
- wwn[7] = inm & 0xff;
+ put_unaligned_be64(inm, wwn);
}
/**
A bug in the gcc-6.0 prerelease version caused at least one driver (lpfc) to have excessive stack usage when dealing with wwn data, on the ARM architecture. lpfc_scsi.c: In function 'lpfc_find_next_oas_lun': lpfc_scsi.c:117:1: warning: the frame size of 1152 bytes is larger than 1024 bytes [-Wframe-larger-than=] I have reported this as a gcc regression in https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70232 However, using a better implementation of wwn_to_u64() not only helps with the particular gcc problem but also leads to better object code for any version or architecture. The kernel already provides get_unaligned_be64() and put_unaligned_be64() helper functions that provide an optimized implementation with the desired semantics. The lpfc_find_next_oas_lun() function in the example that grew from 1146 bytes to 5144 bytes when moving from gcc-5.3 to gcc-6.0 is now 804 bytes, as the optimized get_unaligned_be64() load can be done in three instructions. The stack usage is now down to 28 bytes from 128 bytes with gcc-5.3 before. Signed-off-by: Arnd Bergmann <arnd@arndb.de> --- include/scsi/scsi_transport_fc.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) -- 2.7.0