From: Pablo Neira Ayuso pablo@netfilter.org
stable inclusion from stable-v5.10.188 commit a136b7942ad2a50de708f76ea299ccb45ac7a7f9 bugzilla: https://gitee.com/openeuler/kernel/issues/I86JB6
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit 628bd3e49cba1c066228e23d71a852c23e26da73 ]
set .destroy callback releases the references to other objects in maps. This is very late and it results in spurious EBUSY errors. Drop refcount from the preparation phase instead, update set backend not to drop reference counter from set .destroy path.
Exceptions: NFT_TRANS_PREPARE_ERROR does not require to drop the reference counter because the transaction abort path releases the map references for each element since the set is unbound. The abort path also deals with releasing reference counter for new elements added to unbound sets.
Fixes: 591054469b3e ("netfilter: nf_tables: revisit chain/object refcounting from elements") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lu Wei luwei32@huawei.com --- include/net/netfilter/nf_tables.h | 5 +- net/netfilter/nf_tables_api.c | 89 +++++++++++++++++++++++++++---- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 ++++++-- net/netfilter/nft_set_pipapo.c | 14 +++-- net/netfilter/nft_set_rbtree.c | 5 +- 6 files changed, 117 insertions(+), 24 deletions(-)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5513b9d4f39b..ea893a6d9b36 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -383,7 +383,8 @@ struct nft_set_ops { int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); - void (*destroy)(const struct nft_set *set); + void (*destroy)(const struct nft_ctx *ctx, + const struct nft_set *set); void (*gc_init)(const struct nft_set *set);
unsigned int elemsize; @@ -687,6 +688,8 @@ void *nft_set_elem_init(const struct nft_set *set, u64 timeout, u64 expiration, gfp_t gfp); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem);
/** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d614633e7e1e..3a7ebe56cfa0 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -557,6 +557,31 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return 0; }
+static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_deactivate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_deactivate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_deactivate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); +} + static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; @@ -565,6 +590,9 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) if (err < 0) return err;
+ if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + nft_deactivate_next(ctx->net, set); ctx->table->use--;
@@ -4472,7 +4500,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (set->expr) nft_expr_destroy(&ctx, set->expr);
- ops->destroy(set); + ops->destroy(&ctx, set); err_set_init: kfree(set->name); err_set_name: @@ -4488,7 +4516,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) if (set->expr) nft_expr_destroy(ctx, set->expr);
- set->ops->destroy(set); + set->ops->destroy(ctx, set); kfree(set->name); kvfree(set); } @@ -4612,10 +4640,39 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } }
+static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_activate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_activate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_activate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); +} + void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (nft_set_is_anonymous(set)) + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(ctx, set); + nft_clear(ctx->net, set); + }
set->use++; } @@ -4634,13 +4691,20 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->use--; break; case NFT_TRANS_PREPARE: - if (nft_set_is_anonymous(set)) - nft_deactivate_next(ctx->net, set); + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set);
+ nft_deactivate_next(ctx->net, set); + } set->use--; return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: + if (nft_set_is_anonymous(set) && + set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + set->use--; fallthrough; default: @@ -5247,6 +5311,7 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, } }
+/* Drop references and destroy. Called from gc, dynset and abort path. */ void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr) { @@ -5268,11 +5333,11 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
-/* Only called from commit path, nft_setelem_data_deactivate() already deals - * with the refcounting from the preparation phase. +/* Destroy element. References have been already dropped in the preparation + * path via nft_setelem_data_deactivate(). */ -static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem) +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
@@ -8392,6 +8457,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSET: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_set(trans)); + if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(&trans->ctx, nft_trans_set(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: @@ -9134,6 +9202,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); table->use--; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(&ctx, set); + nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 2a81ea421819..3c63f8acebd8 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -270,13 +270,14 @@ static int nft_bitmap_init(const struct nft_set *set, return 0; }
-static void nft_bitmap_destroy(const struct nft_set *set) +static void nft_bitmap_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be, *n;
list_for_each_entry_safe(be, n, &priv->list, head) - nft_set_elem_destroy(set, be, true); + nf_tables_set_elem_destroy(ctx, set, be); }
static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index a5cfb321ae23..51d3e6f0934a 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -380,19 +380,31 @@ static int nft_rhash_init(const struct nft_set *set, return 0; }
+struct nft_rhash_ctx { + const struct nft_ctx ctx; + const struct nft_set *set; +}; + static void nft_rhash_elem_destroy(void *ptr, void *arg) { - nft_set_elem_destroy(arg, ptr, true); + struct nft_rhash_ctx *rhash_ctx = arg; + + nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr); }
-static void nft_rhash_destroy(const struct nft_set *set) +static void nft_rhash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_ctx rhash_ctx = { + .ctx = *ctx, + .set = set, + };
cancel_delayed_work_sync(&priv->gc_work); rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, - (void *)set); + (void *)&rhash_ctx); }
/* Number of buckets is stored in u32, so cap our result to 1U<<31 */ @@ -621,7 +633,8 @@ static int nft_hash_init(const struct nft_set *set, return 0; }
-static void nft_hash_destroy(const struct nft_set *set) +static void nft_hash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; @@ -631,7 +644,7 @@ static void nft_hash_destroy(const struct nft_set *set) for (i = 0; i < priv->buckets; i++) { hlist_for_each_entry_safe(he, next, &priv->table[i], node) { hlist_del_rcu(&he->node); - nft_set_elem_destroy(set, he, true); + nf_tables_set_elem_destroy(ctx, set, he); } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9dbb8677d2a0..cbdf5090ab0f 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2126,10 +2126,12 @@ static int nft_pipapo_init(const struct nft_set *set,
/** * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array + * @ctx: context * @set: nftables API set representation * @m: matching data pointing to key mapping array */ -static void nft_set_pipapo_match_destroy(const struct nft_set *set, +static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo_field *f; @@ -2146,15 +2148,17 @@ static void nft_set_pipapo_match_destroy(const struct nft_set *set,
e = f->mt[r].e;
- nft_set_elem_destroy(set, e, true); + nf_tables_set_elem_destroy(ctx, set, e); } }
/** * nft_pipapo_destroy() - Free private data for set and all committed elements + * @ctx: context * @set: nftables API set representation */ -static void nft_pipapo_destroy(const struct nft_set *set) +static void nft_pipapo_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; @@ -2164,7 +2168,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) if (m) { rcu_barrier();
- nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m);
#ifdef NFT_PIPAPO_ALIGN free_percpu(m->scratch_aligned); @@ -2181,7 +2185,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) m = priv->clone;
if (priv->dirty) - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m);
#ifdef NFT_PIPAPO_ALIGN free_percpu(priv->clone->scratch_aligned); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 94a5446c5eae..08ed2b3e1d82 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -575,7 +575,8 @@ static int nft_rbtree_init(const struct nft_set *set, return 0; }
-static void nft_rbtree_destroy(const struct nft_set *set) +static void nft_rbtree_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; @@ -586,7 +587,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe, true); + nf_tables_set_elem_destroy(ctx, set, rbe); } }