[dpdk-dev] [PATCH] librte_lpm: use field access instead of type conversion.

[Bruce Richardson]

On Wed, Feb 11, 2015 at 02:12:59PM +0800, xuelin.shi at freescale.com wrote:
> From: Xuelin Shi <xuelin.shi at freescale.com>
> 
> struct tbl_entry{
>         uint8_t next_hop;
>         uint8_t valid :1;
>         uint8_t valid_group :1;
>         uint8_t depth :6
> }
> uint16_t tbl = (uint16_t)tbl_entry;
> next_hop = (uint8_t)tbl;
> 
> next_hop cannot get the correct value of the field
> if the cpu arch is BIG_ENDIAN.
> 
> change it to field access.
> 
> Signed-off-by: Xuelin Shi <xuelin.shi at freescale.com>
> ---
>  lib/librte_lpm/rte_lpm.h | 7 +++++--
>  1 file changed, 5 insertions(+), 2 deletions(-)
> 
> diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
> index 586300b..1af150c 100644
> --- a/lib/librte_lpm/rte_lpm.h
> +++ b/lib/librte_lpm/rte_lpm.h
> @@ -273,6 +273,7 @@ rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip, uint8_t 
> *next_hop)
>  {
>       unsigned tbl24_index = (ip >> 8);
>       uint16_t tbl_entry;
> +     struct rte_lpm_tbl8_entry *entry;
>  
>       /* DEBUG: Check user input arguments. */
>       RTE_LPM_RETURN_IF_TRUE(((lpm == NULL) || (next_hop == NULL)), -EINVAL);
> @@ -290,8 +291,10 @@ rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip, uint8_t 
> *next_hop)
>               tbl_entry = *(const uint16_t *)&lpm->tbl8[tbl8_index];
>       }
>  
> -     *next_hop = (uint8_t)tbl_entry;
> -     return (tbl_entry & RTE_LPM_LOOKUP_SUCCESS) ? 0 : -ENOENT;
> +     entry = (struct rte_lpm_tbl8_entry *)&tbl_entry;
> +     *next_hop = entry->next_hop;
> +
> +     return (entry->valid) ? 0 : -ENOENT;
>  }
>  
>  /**
> -- 
> 1.9.1
> 
I've run a quick test using "lpm_autotest" inside the test app, and on my 
(Intel)
platform, this patch has a small (but none-the-less significant) performance
regression. How about the below as an alternative fix?

/Bruce

diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
index 586300b..de6f1cb 100644
--- a/lib/librte_lpm/rte_lpm.h
+++ b/lib/librte_lpm/rte_lpm.h
@@ -44,6 +44,7 @@
 #include <stdint.h>
 #include <stdlib.h>
 #include <rte_branch_prediction.h>
+#include <rte_byteorder.h>
 #include <rte_memory.h>
 #include <rte_common.h>
 #include <rte_common_vect.h>
@@ -287,7 +288,8 @@ rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip, uint8_t 
*next_hop)
                unsigned tbl8_index = (uint8_t)ip +
                                ((uint8_t)tbl_entry * 
RTE_LPM_TBL8_GROUP_NUM_ENTRIES);

-               tbl_entry = *(const uint16_t *)&lpm->tbl8[tbl8_index];
+               tbl_entry = rte_cpu_to_le_16(
+                               *(const uint16_t *)&lpm->tbl8[tbl8_index]);
        }

        *next_hop = (uint8_t)tbl_entry;