summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband
diff options
context:
space:
mode:
authorSebastian Sanchez <sebastian.sanchez@intel.com>2018-02-01 10:46:23 -0800
committerJason Gunthorpe <jgg@mellanox.com>2018-02-01 15:43:28 -0700
commit6d6b8848c882b22e3170cc9f217101773e8bd8d2 (patch)
tree4e694d7e1ac69e73dcc01d11515189991fce8f76 /drivers/infiniband
parentf150e2736f346a3171f002e660c3dfc653cc11cd (diff)
downloadop-kernel-dev-6d6b8848c882b22e3170cc9f217101773e8bd8d2.zip
op-kernel-dev-6d6b8848c882b22e3170cc9f217101773e8bd8d2.tar.gz
IB/hfi1: Optimize packet type comparison using 9B and bypass code paths
The packet type comparison used to find out if a packet is a bypass packet in the hot path is an expensive operation as seen in a profile. Determine packet's pkey and migration bit through the bypass and 9B code paths instead. Reviewed-by: Don Hiatt <don.hiatt@intel.com> Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/hw/hfi1/driver.c4
-rw-r--r--drivers/infiniband/hw/hfi1/hfi.h2
-rw-r--r--drivers/infiniband/hw/hfi1/ruc.c15
-rw-r--r--drivers/infiniband/hw/hfi1/verbs.h5
4 files changed, 13 insertions, 13 deletions
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 067b29f..bb1a41b 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -1440,6 +1440,8 @@ static int hfi1_setup_9B_packet(struct hfi1_packet *packet)
packet->extra_byte = 0;
packet->fecn = ib_bth_get_fecn(packet->ohdr);
packet->becn = ib_bth_get_becn(packet->ohdr);
+ packet->pkey = ib_bth_get_pkey(packet->ohdr);
+ packet->migrated = ib_bth_is_migration(packet->ohdr);
return 0;
drop:
@@ -1506,6 +1508,8 @@ static int hfi1_setup_bypass_packet(struct hfi1_packet *packet)
packet->extra_byte = SIZE_OF_LT;
packet->fecn = hfi1_16B_get_fecn(packet->hdr);
packet->becn = hfi1_16B_get_becn(packet->hdr);
+ packet->pkey = hfi1_16B_get_pkey(packet->hdr);
+ packet->migrated = opa_bth_is_migration(packet->ohdr);
if (hfi1_bypass_ingress_pkt_check(packet))
goto drop;
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 5757d0e..2c257ac 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -341,6 +341,7 @@ struct hfi1_packet {
u32 slid;
u16 tlen;
s16 etail;
+ u16 pkey;
u8 hlen;
u8 numpkt;
u8 rsize;
@@ -353,6 +354,7 @@ struct hfi1_packet {
u8 opcode;
bool becn;
bool fecn;
+ bool migrated;
};
/* Packet types */
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 0cced9a..6434207 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -225,19 +225,8 @@ int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet)
u32 dlid = packet->dlid;
u32 slid = packet->slid;
u32 sl = packet->sl;
- int migrated;
- u32 bth0, bth1;
- u16 pkey;
-
- bth0 = be32_to_cpu(packet->ohdr->bth[0]);
- bth1 = be32_to_cpu(packet->ohdr->bth[1]);
- if (packet->etype == RHF_RCV_TYPE_BYPASS) {
- pkey = hfi1_16B_get_pkey(packet->hdr);
- migrated = bth1 & OPA_BTH_MIG_REQ;
- } else {
- pkey = ib_bth_get_pkey(packet->ohdr);
- migrated = bth0 & IB_BTH_MIG_REQ;
- }
+ bool migrated = packet->migrated;
+ u16 pkey = packet->pkey;
if (qp->s_mig_state == IB_MIG_ARMED && migrated) {
if (!packet->grh) {
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index c2aeb32..ffc933e 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -405,6 +405,11 @@ static inline void cacheless_memcpy(void *dst, void *src, size_t n)
__copy_user_nocache(dst, (void __user *)src, n, 0);
}
+static inline bool opa_bth_is_migration(struct ib_other_headers *ohdr)
+{
+ return ohdr->bth[1] & cpu_to_be32(OPA_BTH_MIG_REQ);
+}
+
extern const enum ib_wc_opcode ib_hfi1_wc_opcode[];
extern const u8 hdr_len_by_opcode[];
OpenPOWER on IntegriCloud