[dpdk-dev] [PATCH v4 2/3] lib/lpm: memory orderings to avoid race conditions for v20

[Medvedkin, Vladimir]

Hi Wang,

On 03/07/2019 06:44, Ruifeng Wang wrote:
> When a tbl8 group is getting attached to a tbl24 entry, lookup
> might fail even though the entry is configured in the table.
>
> For ex: consider a LPM table configured with 10.10.10.1/24.
> When a new entry 10.10.10.32/28 is being added, a new tbl8
> group is allocated and tbl24 entry is changed to point to
> the tbl8 group. If the tbl24 entry is written without the tbl8
> group entries updated, a lookup on 10.10.10.9 will return
> failure.
>
> Correct memory orderings are required to ensure that the
> store to tbl24 does not happen before the stores to tbl8 group
> entries complete.
>
> Besides, explicit structure alignment is used to address atomic
> operation building issue with older version clang.
>
> Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli at arm.com>
> Signed-off-by: Ruifeng Wang <ruifeng.wang at arm.com>
> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli at arm.com>
> Reviewed-by: Gavin Hu <gavin.hu at arm.com>
> ---
> v4: changed alignment attribute parameter
> v3: no changes
> v2: fixed clang building issue by supplying alignment attribute.
>
>   lib/librte_lpm/rte_lpm.c | 32 +++++++++++++++++++++++++-------
>   lib/librte_lpm/rte_lpm.h |  4 ++--
>   2 files changed, 27 insertions(+), 9 deletions(-)
>
> diff --git a/lib/librte_lpm/rte_lpm.c b/lib/librte_lpm/rte_lpm.c
> index 6ec450a08..baa6e7460 100644
> --- a/lib/librte_lpm/rte_lpm.c
> +++ b/lib/librte_lpm/rte_lpm.c
> @@ -737,7 +737,8 @@ add_depth_small_v20(struct rte_lpm_v20 *lpm, uint32_t ip, uint8_t depth,
>   			/* Setting tbl24 entry in one go to avoid race
>   			 * conditions
>   			 */
> -			lpm->tbl24[i] = new_tbl24_entry;
> +			__atomic_store(&lpm->tbl24[i], &new_tbl24_entry,
> +					__ATOMIC_RELEASE);
>   
>   			continue;
>   		}
> @@ -892,7 +893,8 @@ add_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked, uint8_t depth,
>   			.depth = 0,
>   		};
>   
> -		lpm->tbl24[tbl24_index] = new_tbl24_entry;
> +		__atomic_store(&lpm->tbl24[tbl24_index], &new_tbl24_entry,
> +				__ATOMIC_RELEASE);
>   
>   	} /* If valid entry but not extended calculate the index into Table8. */
>   	else if (lpm->tbl24[tbl24_index].valid_group == 0) {
> @@ -938,7 +940,8 @@ add_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked, uint8_t depth,
>   				.depth = 0,
>   		};
>   
> -		lpm->tbl24[tbl24_index] = new_tbl24_entry;
> +		__atomic_store(&lpm->tbl24[tbl24_index], &new_tbl24_entry,
> +				__ATOMIC_RELEASE);
>   
>   	} else { /*
>   		* If it is valid, extended entry calculate the index into tbl8.
> @@ -1320,7 +1323,15 @@ delete_depth_small_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked,
>   
>   			if (lpm->tbl24[i].valid_group == 0 &&
>   					lpm->tbl24[i].depth <= depth) {
> -				lpm->tbl24[i].valid = INVALID;
> +				struct rte_lpm_tbl_entry_v20
> +					zero_tbl24_entry = {
> +						.valid = INVALID,
> +						.depth = 0,
> +						.valid_group = 0,
> +					};
> +					zero_tbl24_entry.next_hop = 0;
Why don't you use just "struct rte_lpm_tbl_entry_v20 zero_tbl24_entry = 
{0} " like you do for _v1604?
> +				__atomic_store(&lpm->tbl24[i],
> +					&zero_tbl24_entry, __ATOMIC_RELEASE);
>   			} else if (lpm->tbl24[i].valid_group == 1) {
>   				/*
>   				 * If TBL24 entry is extended, then there has
> @@ -1365,7 +1376,8 @@ delete_depth_small_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked,
>   
>   			if (lpm->tbl24[i].valid_group == 0 &&
>   					lpm->tbl24[i].depth <= depth) {
> -				lpm->tbl24[i] = new_tbl24_entry;
> +				__atomic_store(&lpm->tbl24[i], &new_tbl24_entry,
> +						__ATOMIC_RELEASE);
>   			} else  if (lpm->tbl24[i].valid_group == 1) {
>   				/*
>   				 * If TBL24 entry is extended, then there has
> @@ -1647,8 +1659,11 @@ delete_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked,
>   	tbl8_recycle_index = tbl8_recycle_check_v20(lpm->tbl8, tbl8_group_start);
>   
>   	if (tbl8_recycle_index == -EINVAL) {
> -		/* Set tbl24 before freeing tbl8 to avoid race condition. */
> +		/* Set tbl24 before freeing tbl8 to avoid race condition.
> +		 * Prevent the free of the tbl8 group from hoisting.
> +		 */
>   		lpm->tbl24[tbl24_index].valid = 0;
> +		__atomic_thread_fence(__ATOMIC_RELEASE);
>   		tbl8_free_v20(lpm->tbl8, tbl8_group_start);
>   	} else if (tbl8_recycle_index > -1) {
>   		/* Update tbl24 entry. */
> @@ -1659,8 +1674,11 @@ delete_depth_big_v20(struct rte_lpm_v20 *lpm, uint32_t ip_masked,
>   			.depth = lpm->tbl8[tbl8_recycle_index].depth,
>   		};
>   
> -		/* Set tbl24 before freeing tbl8 to avoid race condition. */
> +		/* Set tbl24 before freeing tbl8 to avoid race condition.
> +		 * Prevent the free of the tbl8 group from hoisting.
> +		 */
>   		lpm->tbl24[tbl24_index] = new_tbl24_entry;
> +		__atomic_thread_fence(__ATOMIC_RELEASE);
>   		tbl8_free_v20(lpm->tbl8, tbl8_group_start);
>   	}
>   
> diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
> index 6f5704c5c..906ec4483 100644
> --- a/lib/librte_lpm/rte_lpm.h
> +++ b/lib/librte_lpm/rte_lpm.h
> @@ -88,7 +88,7 @@ struct rte_lpm_tbl_entry_v20 {
>   	 */
>   	uint8_t valid_group :1;
>   	uint8_t depth       :6; /**< Rule depth. */
> -};
> +} __rte_aligned(sizeof(uint16_t));
>   
>   __extension__
>   struct rte_lpm_tbl_entry {
> @@ -121,7 +121,7 @@ struct rte_lpm_tbl_entry_v20 {
>   		uint8_t group_idx;
>   		uint8_t next_hop;
>   	};
> -};
> +} __rte_aligned(sizeof(uint16_t));
>   
>   __extension__
>   struct rte_lpm_tbl_entry {

-- 
Regards,
Vladimir