Tests showed that the function inlining caused performance drop
on some x86 platforms with the memory ordering patches applied.
By force no-inline functions, the performance was better than
before on x86 and no impact to arm64 platforms.
Suggested-by: Medvedkin Vladimir <vladimir.medved...@intel.com>
Signed-off-by: Ruifeng Wang <ruifeng.w...@arm.com>
Reviewed-by: Gavin Hu <gavin...@arm.com>
---
v3: use __rte_noinline to force no inline
v2: initail version to remove 'inline' keyword
lib/librte_lpm/rte_lpm.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/lib/librte_lpm/rte_lpm.c b/lib/librte_lpm/rte_lpm.c
index 6b7b28a2e..eb835f052 100644
--- a/lib/librte_lpm/rte_lpm.c
+++ b/lib/librte_lpm/rte_lpm.c
@@ -709,7 +709,7 @@ tbl8_free_v1604(struct rte_lpm_tbl_entry *tbl8, uint32_t
tbl8_group_start)
tbl8[tbl8_group_start].valid_group = INVALID;
}
-static inline int32_t
+static __rte_noinline int32_t
add_depth_small_v20(struct rte_lpm_v20 *lpm, uint32_t ip, uint8_t depth,
uint8_t next_hop)
{
@@ -777,7 +777,7 @@ add_depth_small_v20(struct rte_lpm_v20 *lpm, uint32_t ip,
uint8_t depth,
return 0;
}
-static inline int32_t
+static __rte_noinline int32_t
add_depth_small_v1604(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
uint32_t next_hop)
{
@@ -846,7 +846,7 @@ add_depth_small_v1604(struct rte_lpm *lpm, uint32_t ip,
uint8_t depth,
return 0;
}
-static inline int32_t
+static __rte_noinline int32_t
add_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked, uint8_t depth,
uint8_t next_hop)
{
@@ -971,7 +971,7 @@ add_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t
ip_masked, uint8_t depth,
return 0;
}
-static inline int32_t
+static __rte_noinline int32_t
add_depth_big_v1604(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth,
uint32_t next_hop)
{
--
2.17.1
