[dpdk-dev] [PATCH v5 2/6] lib/lpm: memory orderings to avoid race conditions for v1604

[Ruifeng Wang <ruifeng.wang@arm.com>]

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.

Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
---
 lib/librte_lpm/rte_lpm.c | 32 +++++++++++++++++++++++++-------
 lib/librte_lpm/rte_lpm.h |  4 ++++
 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/lib/librte_lpm/rte_lpm.c b/lib/librte_lpm/rte_lpm.c
index 18efa496c..396ad94e2 100644
--- a/lib/librte_lpm/rte_lpm.c
+++ b/lib/librte_lpm/rte_lpm.c
@@ -806,7 +806,8 @@ add_depth_small_v1604(struct rte_lpm *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;
 		}
@@ -1017,7 +1018,11 @@ add_depth_big_v1604(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth,
 			.depth = 0,
 		};
 
-		lpm->tbl24[tbl24_index] = new_tbl24_entry;
+		/* The tbl24 entry must be written only after the
+		 * tbl8 entries are written.
+		 */
+		__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) {
@@ -1063,7 +1068,11 @@ add_depth_big_v1604(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth,
 				.depth = 0,
 		};
 
-		lpm->tbl24[tbl24_index] = new_tbl24_entry;
+		/* The tbl24 entry must be written only after the
+		 * tbl8 entries are written.
+		 */
+		__atomic_store(&lpm->tbl24[tbl24_index], &new_tbl24_entry,
+				__ATOMIC_RELEASE);
 
 	} else { /*
 		* If it is valid, extended entry calculate the index into tbl8.
@@ -1391,6 +1400,7 @@ delete_depth_small_v1604(struct rte_lpm *lpm, uint32_t ip_masked,
 	/* Calculate the range and index into Table24. */
 	tbl24_range = depth_to_range(depth);
 	tbl24_index = (ip_masked >> 8);
+	struct rte_lpm_tbl_entry zero_tbl24_entry = {0};
 
 	/*
 	 * Firstly check the sub_rule_index. A -1 indicates no replacement rule
@@ -1405,7 +1415,8 @@ delete_depth_small_v1604(struct rte_lpm *lpm, uint32_t ip_masked,
 
 			if (lpm->tbl24[i].valid_group == 0 &&
 					lpm->tbl24[i].depth <= depth) {
-				lpm->tbl24[i].valid = INVALID;
+				__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
@@ -1450,7 +1461,8 @@ delete_depth_small_v1604(struct rte_lpm *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
@@ -1713,8 +1725,11 @@ delete_depth_big_v1604(struct rte_lpm *lpm, uint32_t ip_masked,
 	tbl8_recycle_index = tbl8_recycle_check_v1604(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_v1604(lpm->tbl8, tbl8_group_start);
 	} else if (tbl8_recycle_index > -1) {
 		/* Update tbl24 entry. */
@@ -1725,8 +1740,11 @@ delete_depth_big_v1604(struct rte_lpm *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_v1604(lpm->tbl8, tbl8_group_start);
 	}
 #undef group_idx
diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
index b886f54b4..6f5704c5c 100644
--- a/lib/librte_lpm/rte_lpm.h
+++ b/lib/librte_lpm/rte_lpm.h
@@ -354,6 +354,10 @@ rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip, uint32_t *next_hop)
 	ptbl = (const uint32_t *)(&lpm->tbl24[tbl24_index]);
 	tbl_entry = *ptbl;
 
+	/* Memory ordering is not required in lookup. Because dataflow
+	 * dependency exists, compiler or HW won't be able to re-order
+	 * the operations.
+	 */
 	/* Copy tbl8 entry (only if needed) */
 	if (unlikely((tbl_entry & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
 			RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
-- 
2.17.1