AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

IB/mlx4: Micro-optimize mlx4_ib_poll_one()

Browse Source 
Rather than byte-swapping cqe->g_mlpath_rqpn each time we extract a
field from it, byte-swap it once into a temporary variable.  This 
results in smaller, better code -- eg, on 32-bit x86:

add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-5 (-5)
function                                     old     new   delta
mlx4_ib_poll_cq                             1188    1183      -5

Signed-off-by: Roland Dreier <rolandd@cisco.com>
This commit is contained in:
Roland Dreier 2008-01-25 14:15:34 -08:00
parent e57895d389
commit b3226184af
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
drivers/infiniband/hw/mlx4/cq.c
View File

@ -313,6 +313,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
struct mlx4_ib_srq *srq;
int is_send;
int is_error;
u32 g_mlpath_rqpn;
u16 wqe_ctr;
cqe = next_cqe_sw(cq);
@ -426,10 +427,10 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
wc->slid = be16_to_cpu(cqe->rlid);
wc->sl = cqe->sl >> 4;
wc->src_qp = be32_to_cpu(cqe->g_mlpath_rqpn) & 0xffffff;
wc->dlid_path_bits = (be32_to_cpu(cqe->g_mlpath_rqpn) >> 24) & 0x7f;
wc->wc_flags |= be32_to_cpu(cqe->g_mlpath_rqpn) & 0x80000000 ?
IB_WC_GRH : 0;
g_mlpath_rqpn = be32_to_cpu(cqe->g_mlpath_rqpn);
wc->src_qp = g_mlpath_rqpn & 0xffffff;
wc->dlid_path_bits = (g_mlpath_rqpn >> 24) & 0x7f;
wc->wc_flags |= g_mlpath_rqpn & 0x80000000 ? IB_WC_GRH : 0;
wc->pkey_index = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f;
}