trie_modify() updates rsvd_tbl8s by depth_diff computed from the
current RIB state. The RIB is not invariant between the ADD of a
prefix and its later DEL (a covering parent may be added or removed
in between), so depth_diff at DEL time may not match depth_diff at
ADD time. Repeated over asymmetric pairs, rsvd_tbl8s drifts and
eventually wraps to UINT32_MAX, after which the pre-check rejects
all long-prefix ADDs with -ENOSPC even when the pool is empty.
Replace rsvd_tbl8s with tbl8_pool_pos, which tbl8_get()/tbl8_put()
maintain exactly. To preserve the QSBR_MODE_DQ safety net previously
provided by the retry-with-reclaim inside tbl8_alloc(), the pre-check
now calls rte_rcu_qsbr_dq_reclaim(depth_diff) before returning
-ENOSPC.
The single-tbl8 retry inside tbl8_alloc() is removed: depth_diff is
the algorithmic upper bound for new tbl8 allocations, and the
pre-check now performs the DQ reclaim before allocation, so the
retry inside the allocator is no longer needed.
Fixes: c3e12e0f0354 ("fib: add dataplane algorithm for IPv6")
Cc: [email protected]
Signed-off-by: Maxime Leroy <[email protected]>
---
lib/fib/trie.c | 23 ++++++++++-------------
lib/fib/trie.h | 3 +--
2 files changed, 11 insertions(+), 15 deletions(-)
diff --git a/lib/fib/trie.c b/lib/fib/trie.c
index fa5d9ec6b0..52f25d499c 100644
--- a/lib/fib/trie.c
+++ b/lib/fib/trie.c
@@ -161,12 +161,6 @@ tbl8_alloc(struct rte_trie_tbl *dp, uint64_t nh)
uint8_t *tbl8_ptr;
tbl8_idx = tbl8_get(dp);
-
- /* If there are no tbl8 groups try to reclaim one. */
- if (unlikely(tbl8_idx == -ENOSPC && dp->dq &&
- !rte_rcu_qsbr_dq_reclaim(dp->dq, 1, NULL, NULL, NULL)))
- tbl8_idx = tbl8_get(dp);
-
if (tbl8_idx < 0)
return tbl8_idx;
tbl8_ptr = get_tbl_p_by_idx(dp->tbl8,
@@ -603,8 +597,15 @@ trie_modify(struct rte_fib6 *fib, const struct
rte_ipv6_addr *ip,
return 0;
}
- if ((depth > 24) && (dp->rsvd_tbl8s + depth_diff >
dp->number_tbl8s))
- return -ENOSPC;
+ if ((depth > 24) &&
+ (dp->tbl8_pool_pos + depth_diff > dp->number_tbl8s)) {
+ /* Reclaim deferred tbl8s before failing. */
+ if (dp->dq != NULL)
+ rte_rcu_qsbr_dq_reclaim(dp->dq, depth_diff,
+ NULL, NULL, NULL);
+ if (dp->tbl8_pool_pos + depth_diff > dp->number_tbl8s)
+ return -ENOSPC;
+ }
node = rte_rib6_insert(rib, &ip_masked, depth);
if (node == NULL)
@@ -614,15 +615,13 @@ trie_modify(struct rte_fib6 *fib, const struct
rte_ipv6_addr *ip,
if (parent != NULL) {
rte_rib6_get_nh(parent, &par_nh);
if (par_nh == next_hop)
- goto successfully_added;
+ return 0;
}
ret = modify_dp(dp, rib, &ip_masked, depth, next_hop);
if (ret != 0) {
rte_rib6_remove(rib, &ip_masked, depth);
return ret;
}
-successfully_added:
- dp->rsvd_tbl8s += depth_diff;
return 0;
case RTE_FIB6_DEL:
if (node == NULL)
@@ -641,8 +640,6 @@ trie_modify(struct rte_fib6 *fib, const struct
rte_ipv6_addr *ip,
if (ret != 0)
return ret;
rte_rib6_remove(rib, ip, depth);
-
- dp->rsvd_tbl8s -= depth_diff;
return 0;
default:
break;
diff --git a/lib/fib/trie.h b/lib/fib/trie.h
index c34cc2c057..b42a28f84e 100644
--- a/lib/fib/trie.h
+++ b/lib/fib/trie.h
@@ -31,8 +31,7 @@
struct rte_trie_tbl {
uint32_t number_tbl8s; /**< Total number of tbl8s */
- uint32_t rsvd_tbl8s; /**< Number of reserved tbl8s */
- uint32_t cur_tbl8s; /**< Current cumber of tbl8s */
+ uint32_t cur_tbl8s; /**< Current number of tbl8s */
uint64_t def_nh; /**< Default next hop */
enum rte_fib_trie_nh_sz nh_sz; /**< Size of nexthop entry */
uint64_t *tbl8; /**< tbl8 table. */
--
2.43.0
