From 28ca053314898b19049213c9be57cf7f4480bd04 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Nov 2023 13:13:09 +0100 Subject: [PATCH 01/13] UPSTREAM: netfilter: nftables: rename set element data activation/deactivation functions commit f8bb7889af58d8e74d2d61c76b1418230f1610fa upstream. Rename: - nft_set_elem_activate() to nft_set_elem_data_activate(). - nft_set_elem_deactivate() to nft_set_elem_data_deactivate(). To prepare for updates in the set element infrastructure to add support for the special catch-all element. Bug: 299922216 Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6b880f3b2c043d91e7fcc6e41ef78cb859f084ec) Signed-off-by: Lee Jones Change-Id: I6411a3604194564f35dd7d59b7b6da1e40a9bbe4 --- net/netfilter/nf_tables_api.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 20202a2371c9..049053203ebb 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4606,8 +4606,8 @@ 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_set_elem_deactivate() already deals with - * the refcounting from the preparation phase. +/* Only called from commit path, nft_setelem_data_deactivate() already deals + * with the refcounting from the preparation phase. */ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, void *elem) @@ -4923,9 +4923,9 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) } } -static void nft_set_elem_activate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -4935,9 +4935,9 @@ static void nft_set_elem_activate(const struct net *net, nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } -static void nft_set_elem_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5004,7 +5004,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, kfree(elem.priv); elem.priv = priv; - nft_set_elem_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, &elem); nft_trans_elem(trans) = elem; nft_trans_commit_list_add_tail(ctx->net, trans); @@ -5038,7 +5038,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; - nft_set_elem_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; nft_trans_commit_list_add_tail(ctx->net, trans); @@ -7279,7 +7279,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_set_elem_activate(net, te->set, &te->elem); + nft_setelem_data_activate(net, te->set, &te->elem); te->set->ops->activate(net, te->set, &te->elem); te->set->ndeact--; From 3a298023c912c600eb9df0288c7398cbb55ced83 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Nov 2023 13:13:10 +0100 Subject: [PATCH 02/13] UPSTREAM: netfilter: nf_tables: drop map element references from preparation phase commit 628bd3e49cba1c066228e23d71a852c23e26da73 upstream. 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. Bug: 299922216 Fixes: 591054469b3e ("netfilter: nf_tables: revisit chain/object refcounting from elements") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3c7ec098e3b588434a8b07ea9b5b36f04cef1f50) Signed-off-by: Lee Jones Change-Id: I3fa17ba11bc3dcdb05d4f50eee79357e806581ad --- 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_rbtree.c | 5 +- 5 files changed, 108 insertions(+), 19 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index a2d1ec4aba1a..aa5e76a1446b 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -371,7 +371,8 @@ 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; @@ -665,6 +666,8 @@ 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 049053203ebb..7149b77e8cc9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -403,6 +403,31 @@ 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; @@ -411,6 +436,9 @@ 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); nft_use_dec(&ctx->table->use); @@ -3840,7 +3868,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, return 0; err4: - ops->destroy(set); + ops->destroy(&ctx, set); err3: kfree(set->name); err2: @@ -3857,7 +3885,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) if (WARN_ON(set->use > 0)) return; - set->ops->destroy(set); + set->ops->destroy(ctx, set); module_put(to_set_type(set->ops)->owner); kfree(set->name); kvfree(set); @@ -3981,10 +4009,39 @@ 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); + } nft_use_inc_restore(&set->use); } @@ -4005,13 +4062,20 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_use_dec(&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); + } nft_use_dec(&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); + nft_use_dec(&set->use); /* fall through */ default: @@ -4578,6 +4642,7 @@ void *nft_set_elem_init(const struct nft_set *set, return elem; } +/* 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) { @@ -4606,11 +4671,11 @@ 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); @@ -4618,6 +4683,7 @@ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, nf_tables_expr_destroy(ctx, nft_set_ext_expr(ext)); kfree(elem); } +EXPORT_SYMBOL_GPL(nf_tables_set_elem_destroy); static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) @@ -7265,6 +7331,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSET: nft_use_inc_restore(&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: @@ -7959,6 +8027,9 @@ 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); nft_use_dec(&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 087a056e34d1..b0f6b1490e1a 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 fb68d3783309..34ab10847b93 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -378,19 +378,31 @@ 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 */ @@ -619,7 +631,8 @@ 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; @@ -629,7 +642,7 @@ 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_rbtree.c b/net/netfilter/nft_set_rbtree.c index deda1a064af6..1edcb7504835 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -478,7 +478,8 @@ 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; @@ -489,7 +490,7 @@ 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); } } From f896aebc9163076facc38c8627ff6db9e1931ea9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Nov 2023 13:13:11 +0100 Subject: [PATCH 03/13] UPSTREAM: netfilter: nft_set_rbtree: Switch to node list walk for overlap detection commit c9e6978e2725a7d4b6cd23b2facd3f11422c0643 upstream. ...instead of a tree descent, which became overly complicated in an attempt to cover cases where expired or inactive elements would affect comparisons with the new element being inserted. Further, it turned out that it's probably impossible to cover all those cases, as inactive nodes might entirely hide subtrees consisting of a complete interval plus a node that makes the current insertion not overlap. To speed up the overlap check, descent the tree to find a greater element that is closer to the key value to insert. Then walk down the node list for overlap detection. Starting the overlap check from rb_first() unconditionally is slow, it takes 10 times longer due to the full linear traversal of the list. Moreover, perform garbage collection of expired elements when walking down the node list to avoid bogus overlap reports. For the insertion operation itself, this essentially reverts back to the implementation before commit 7c84d41416d8 ("netfilter: nft_set_rbtree: Detect partial overlaps on insertion"), except that cases of complete overlap are already handled in the overlap detection phase itself, which slightly simplifies the loop to find the insertion point. Based on initial patch from Stefano Brivio, including text from the original patch description too. Bug: 299922216 Fixes: 7c84d41416d8 ("netfilter: nft_set_rbtree: Detect partial overlaps on insertion") Reviewed-by: Stefano Brivio Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 181859bdfb9734aca449512fccaee4cacce64aed) Signed-off-by: Lee Jones Change-Id: Id8979dd639294bfae9a8c8440b4f19a54b33cb0c --- net/netfilter/nft_set_rbtree.c | 227 +++++++++++++++++++++++++++++---- 1 file changed, 200 insertions(+), 27 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 1edcb7504835..ebfb266b8619 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -38,10 +38,12 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) return !nft_rbtree_interval_end(rbe); } -static bool nft_rbtree_equal(const struct nft_set *set, const void *this, - const struct nft_rbtree_elem *interval) +static int nft_rbtree_cmp(const struct nft_set *set, + const struct nft_rbtree_elem *e1, + const struct nft_rbtree_elem *e2) { - return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0; + return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext), + set->klen); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, @@ -52,7 +54,6 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; - const void *this; int d; parent = rcu_dereference_raw(priv->root.rb_node); @@ -62,12 +63,11 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set rbe = rb_entry(parent, struct nft_rbtree_elem, node); - this = nft_set_ext_key(&rbe->ext); - d = memcmp(this, key, set->klen); + d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (interval && - nft_rbtree_equal(set, this, interval) && + !nft_rbtree_cmp(set, rbe, interval) && nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; @@ -214,43 +214,216 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static int nft_rbtree_gc_elem(const struct nft_set *__set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set *set = (struct nft_set *)__set; + struct rb_node *prev = rb_prev(&rbe->node); + struct nft_rbtree_elem *rbe_prev; + struct nft_set_gc_batch *gcb; + + gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); + if (!gcb) + return -ENOMEM; + + /* search for expired end interval coming before this element. */ + do { + rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + if (nft_rbtree_interval_end(rbe_prev)) + break; + + prev = rb_prev(prev); + } while (prev != NULL); + + rb_erase(&rbe_prev->node, &priv->root); + rb_erase(&rbe->node, &priv->root); + atomic_sub(2, &set->nelems); + + nft_set_gc_batch_add(gcb, rbe); + nft_set_gc_batch_complete(gcb); + + return 0; +} + +static bool nft_rbtree_update_first(const struct nft_set *set, + struct nft_rbtree_elem *rbe, + struct rb_node *first) +{ + struct nft_rbtree_elem *first_elem; + + first_elem = rb_entry(first, struct nft_rbtree_elem, node); + /* this element is closest to where the new element is to be inserted: + * update the first element for the node list path. + */ + if (nft_rbtree_cmp(set, rbe, first_elem) < 0) + return true; + + return false; +} + static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) { + struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; + struct rb_node *node, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); - struct nft_rbtree_elem *rbe; - struct rb_node *parent, **p; - int d; + int d, err; + /* Descend the tree to search for an existing element greater than the + * key value to insert that is greater than the new element. This is the + * first element to walk the ordered elements to find possible overlap. + */ parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = memcmp(nft_set_ext_key(&rbe->ext), - nft_set_ext_key(&new->ext), - set->klen); + d = nft_rbtree_cmp(set, rbe, new); + + if (d < 0) { + p = &parent->rb_left; + } else if (d > 0) { + if (!first || + nft_rbtree_update_first(set, rbe, first)) + first = &rbe->node; + + p = &parent->rb_right; + } else { + if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + } + + if (!first) + first = rb_first(&priv->root); + + /* Detect overlap by going through the list of valid tree nodes. + * Values stored in the tree are in reversed order, starting from + * highest to lowest value. + */ + for (node = first; node != NULL; node = rb_next(node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); + + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* perform garbage collection to avoid bogus overlap reports. */ + if (nft_set_elem_expired(&rbe->ext)) { + err = nft_rbtree_gc_elem(set, priv, rbe); + if (err < 0) + return err; + + continue; + } + + d = nft_rbtree_cmp(set, rbe, new); + if (d == 0) { + /* Matching end element: no need to look for an + * overlapping greater or equal element. + */ + if (nft_rbtree_interval_end(rbe)) { + rbe_le = rbe; + break; + } + + /* first element that is greater or equal to key value. */ + if (!rbe_ge) { + rbe_ge = rbe; + continue; + } + + /* this is a closer more or equal element, update it. */ + if (nft_rbtree_cmp(set, rbe_ge, new) != 0) { + rbe_ge = rbe; + continue; + } + + /* element is equal to key value, make sure flags are + * the same, an existing more or equal start element + * must not be replaced by more or equal end element. + */ + if ((nft_rbtree_interval_start(new) && + nft_rbtree_interval_start(rbe_ge)) || + (nft_rbtree_interval_end(new) && + nft_rbtree_interval_end(rbe_ge))) { + rbe_ge = rbe; + continue; + } + } else if (d > 0) { + /* annotate element greater than the new element. */ + rbe_ge = rbe; + continue; + } else if (d < 0) { + /* annotate element less than the new element. */ + rbe_le = rbe; + break; + } + } + + /* - new start element matching existing start element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && + nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { + *ext = &rbe_ge->ext; + return -EEXIST; + } + + /* - new end element matching existing end element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && + nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { + *ext = &rbe_le->ext; + return -EEXIST; + } + + /* - new start element with existing closest, less or equal key value + * being a start element: partial overlap, reported as -ENOTEMPTY. + * Anonymous sets allow for two consecutive start element since they + * are constant, skip them to avoid bogus overlap reports. + */ + if (!nft_set_is_anonymous(set) && rbe_le && + nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) + return -ENOTEMPTY; + + /* - new end element with existing closest, less or equal key value + * being a end element: partial overlap, reported as -ENOTEMPTY. + */ + if (rbe_le && + nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new)) + return -ENOTEMPTY; + + /* - new end element with existing closest, greater or equal key value + * being an end element: partial overlap, reported as -ENOTEMPTY + */ + if (rbe_ge && + nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) + return -ENOTEMPTY; + + /* Accepted element: pick insertion point depending on key value */ + parent = NULL; + p = &priv->root.rb_node; + while (*p != NULL) { + parent = *p; + rbe = rb_entry(parent, struct nft_rbtree_elem, node); + d = nft_rbtree_cmp(set, rbe, new); + if (d < 0) p = &parent->rb_left; else if (d > 0) p = &parent->rb_right; - else { - if (nft_rbtree_interval_end(rbe) && - nft_rbtree_interval_start(new)) { - p = &parent->rb_left; - } else if (nft_rbtree_interval_start(rbe) && - nft_rbtree_interval_end(new)) { - p = &parent->rb_right; - } else if (nft_set_elem_active(&rbe->ext, genmask)) { - *ext = &rbe->ext; - return -EEXIST; - } else { - p = &parent->rb_left; - } - } + else if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; } + rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; From 1b7330db23155c0935c12dfc00c07341a1dd1b8a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 21 Nov 2023 13:13:12 +0100 Subject: [PATCH 04/13] UPSTREAM: netfilter: nft_set_rbtree: fix null deref on element insertion commit 61ae320a29b0540c16931816299eb86bf2b66c08 upstream. There is no guarantee that rb_prev() will not return NULL in nft_rbtree_gc_elem(): general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] nft_add_set_elem+0x14b0/0x2990 nf_tables_newsetelem+0x528/0xb30 Furthermore, there is a possible use-after-free while iterating, 'node' can be free'd so we need to cache the next value to use. Bug: 299922216 Fixes: c9e6978e2725 ("netfilter: nft_set_rbtree: Switch to node list walk for overlap detection") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 899aa5638568abf5d69de7a7bb95e4615157375b) Signed-off-by: Lee Jones Change-Id: Ie5223611ff2b9dd937648e5e0c5f4095a1c4dca7 --- net/netfilter/nft_set_rbtree.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index ebfb266b8619..a49cc61ec78a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -220,7 +220,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev; + struct nft_rbtree_elem *rbe_prev = NULL; struct nft_set_gc_batch *gcb; gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); @@ -228,17 +228,21 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, return -ENOMEM; /* search for expired end interval coming before this element. */ - do { + while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev)) break; prev = rb_prev(prev); - } while (prev != NULL); + } + + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + atomic_dec(&set->nelems); + } - rb_erase(&rbe_prev->node, &priv->root); rb_erase(&rbe->node, &priv->root); - atomic_sub(2, &set->nelems); + atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); nft_set_gc_batch_complete(gcb); @@ -267,7 +271,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_set_ext **ext) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; - struct rb_node *node, *parent, **p, *first = NULL; + struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); int d, err; @@ -306,7 +310,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ - for (node = first; node != NULL; node = rb_next(node)) { + for (node = first; node != NULL; node = next) { + next = rb_next(node); + rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) From 4ce6a7332661e6706904a23bdc0c55f69133c485 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 21 Nov 2023 13:13:13 +0100 Subject: [PATCH 05/13] UPSTREAM: netfilter: nft_set_rbtree: fix overlap expiration walk commit f718863aca469a109895cb855e6b81fff4827d71 upstream. The lazy gc on insert that should remove timed-out entries fails to release the other half of the interval, if any. Can be reproduced with tests/shell/testcases/sets/0044interval_overlap_0 in nftables.git and kmemleak enabled kernel. Second bug is the use of rbe_prev vs. prev pointer. If rbe_prev() returns NULL after at least one iteration, rbe_prev points to element that is not an end interval, hence it should not be removed. Lastly, check the genmask of the end interval if this is active in the current generation. Bug: 299922216 Fixes: c9e6978e2725 ("netfilter: nft_set_rbtree: Switch to node list walk for overlap detection") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit acaee227cf79c45a5d2d49c3e9a66333a462802c) Signed-off-by: Lee Jones Change-Id: I0c46b46ba4e0811b37dc4e332e97c157c5d452bb --- net/netfilter/nft_set_rbtree.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index a49cc61ec78a..03264f63064f 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -216,29 +216,37 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, static int nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe) + struct nft_rbtree_elem *rbe, + u8 genmask) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev = NULL; + struct nft_rbtree_elem *rbe_prev; struct nft_set_gc_batch *gcb; gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); if (!gcb) return -ENOMEM; - /* search for expired end interval coming before this element. */ + /* search for end interval coming before this element. + * end intervals don't carry a timeout extension, they + * are coupled with the interval start element. + */ while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); - if (nft_rbtree_interval_end(rbe_prev)) + if (nft_rbtree_interval_end(rbe_prev) && + nft_set_elem_active(&rbe_prev->ext, genmask)) break; prev = rb_prev(prev); } - if (rbe_prev) { + if (prev) { + rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + rb_erase(&rbe_prev->node, &priv->root); atomic_dec(&set->nelems); + nft_set_gc_batch_add(gcb, rbe_prev); } rb_erase(&rbe->node, &priv->root); @@ -320,7 +328,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, /* perform garbage collection to avoid bogus overlap reports. */ if (nft_set_elem_expired(&rbe->ext)) { - err = nft_rbtree_gc_elem(set, priv, rbe); + err = nft_rbtree_gc_elem(set, priv, rbe, genmask); if (err < 0) return err; From adc9cb068362bf80df34570ee38d1ac8903c4540 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Nov 2023 13:13:15 +0100 Subject: [PATCH 06/13] UPSTREAM: netfilter: nf_tables: GC transaction API to avoid race with control plane commit 5f68718b34a531a556f2f50300ead2862278da26 upstream. The set types rhashtable and rbtree use a GC worker to reclaim memory. >From system work queue, in periodic intervals, a scan of the table is done. The major caveat here is that the nft transaction mutex is not held. This causes a race between control plane and GC when they attempt to delete the same element. We cannot grab the netlink mutex from the work queue, because the control plane has to wait for the GC work queue in case the set is to be removed, so we get following deadlock: cpu 1 cpu2 GC work transaction comes in , lock nft mutex `acquire nft mutex // BLOCKS transaction asks to remove the set set destruction calls cancel_work_sync() cancel_work_sync will now block forever, because it is waiting for the mutex the caller already owns. This patch adds a new API that deals with garbage collection in two steps: 1) Lockless GC of expired elements sets on the NFT_SET_ELEM_DEAD_BIT so they are not visible via lookup. Annotate current GC sequence in the GC transaction. Enqueue GC transaction work as soon as it is full. If ruleset is updated, then GC transaction is aborted and retried later. 2) GC work grabs the mutex. If GC sequence has changed then this GC transaction lost race with control plane, abort it as it contains stale references to objects and let GC try again later. If the ruleset is intact, then this GC transaction deactivates and removes the elements and it uses call_rcu() to destroy elements. Note that no elements are removed from GC lockless path, the _DEAD bit is set and pointers are collected. GC catchall does not remove the elements anymore too. There is a new set->dead flag that is set on to abort the GC transaction to deal with set->ops->destroy() path which removes the remaining elements in the set from commit_release, where no mutex is held. To deal with GC when mutex is held, which allows safe deactivate and removal, add sync GC API which releases the set element object via call_rcu(). This is used by rbtree and pipapo backends which also perform garbage collection from control plane path. Since element removal from sets can happen from control plane and element garbage collection/timeout, it is necessary to keep the set structure alive until all elements have been deactivated and destroyed. We cannot do a cancel_work_sync or flush_work in nft_set_destroy because its called with the transaction mutex held, but the aforementioned async work queue might be blocked on the very mutex that nft_set_destroy() callchain is sitting on. This gives us the choice of ABBA deadlock or UaF. To avoid both, add set->refs refcount_t member. The GC API can then increment the set refcount and release it once the elements have been free'd. Set backends are adapted to use the GC transaction API in a follow up patch entitled: ("netfilter: nf_tables: use gc transaction API in set backends") This is joint work with Florian Westphal. Bug: 299922216 Fixes: cfed7e1b1f8e ("netfilter: nf_tables: add set garbage collection helpers") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit bbdb3b65aa91aa0a32b212f27780b28987f2d94f) Signed-off-by: Lee Jones Change-Id: I7a28c04401c8eccdd525ba5dd7ab4f46b96a8822 --- include/net/netfilter/nf_tables.h | 61 +++++++- net/netfilter/nf_tables_api.c | 225 ++++++++++++++++++++++++++++-- 2 files changed, 276 insertions(+), 10 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index aa5e76a1446b..73979ed2f840 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -402,6 +402,7 @@ void nft_unregister_set(struct nft_set_type *type); * * @list: table set list node * @bindings: list of set bindings + * @refs: internal refcounting for async set destruction * @table: table this set belongs to * @net: netnamespace this set belongs to * @name: name of the set @@ -428,6 +429,7 @@ void nft_unregister_set(struct nft_set_type *type); struct nft_set { struct list_head list; struct list_head bindings; + refcount_t refs; struct nft_table *table; possible_net_t net; char *name; @@ -446,7 +448,8 @@ struct nft_set { unsigned char *udata; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; - u16 flags:14, + u16 flags:13, + dead:1, genmask:2; u8 klen; u8 dlen; @@ -1386,6 +1389,32 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) clear_bit(NFT_SET_ELEM_BUSY_BIT, word); } +#define NFT_SET_ELEM_DEAD_MASK (1 << 3) + +#if defined(__LITTLE_ENDIAN_BITFIELD) +#define NFT_SET_ELEM_DEAD_BIT 3 +#elif defined(__BIG_ENDIAN_BITFIELD) +#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 3) +#else +#error +#endif + +static inline void nft_set_elem_dead(struct nft_set_ext *ext) +{ + unsigned long *word = (unsigned long *)ext; + + BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); + set_bit(NFT_SET_ELEM_DEAD_BIT, word); +} + +static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) +{ + unsigned long *word = (unsigned long *)ext; + + BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); + return test_bit(NFT_SET_ELEM_DEAD_BIT, word); +} + /** * struct nft_trans - nf_tables object update in transaction * @@ -1490,6 +1519,35 @@ struct nft_trans_flowtable { #define nft_trans_flowtable(trans) \ (((struct nft_trans_flowtable *)trans->data)->flowtable) +#define NFT_TRANS_GC_BATCHCOUNT 256 + +struct nft_trans_gc { + struct list_head list; + struct net *net; + struct nft_set *set; + u32 seq; + u8 count; + void *priv[NFT_TRANS_GC_BATCHCOUNT]; + struct rcu_head rcu; +}; + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_destroy(struct nft_trans_gc *trans); + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc); + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp); +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); + +void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); + +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); @@ -1510,6 +1568,7 @@ struct nftables_pernet { struct mutex commit_mutex; unsigned int base_seq; u8 validate_state; + unsigned int gc_seq; }; #endif /* _NET_NF_TABLES_H */ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7149b77e8cc9..5b128d6b2dde 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -26,12 +26,15 @@ #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) unsigned int nf_tables_net_id __read_mostly; +EXPORT_SYMBOL_GPL(nf_tables_net_id); static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); +static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); +static DEFINE_SPINLOCK(nf_tables_gc_list_lock); static u64 table_handle; enum { @@ -88,6 +91,9 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); +static void nft_trans_gc_work(struct work_struct *work); +static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); + static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, @@ -403,10 +409,6 @@ 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, @@ -3838,6 +3840,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } INIT_LIST_HEAD(&set->bindings); + refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; @@ -3880,6 +3883,14 @@ err1: return err; } +static void nft_set_put(struct nft_set *set) +{ + if (refcount_dec_and_test(&set->refs)) { + kfree(set->name); + kvfree(set); + } +} + static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { if (WARN_ON(set->use > 0)) @@ -3887,8 +3898,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) set->ops->destroy(ctx, set); module_put(to_set_type(set->ops)->owner); - kfree(set->name); - kvfree(set); + nft_set_put(set); } static int nf_tables_delset(struct net *net, struct sock *nlsk, @@ -5001,9 +5011,9 @@ static void nft_setelem_data_activate(const struct net *net, nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5012,6 +5022,7 @@ static void nft_setelem_data_deactivate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); } +EXPORT_SYMBOL_GPL(nft_setelem_data_deactivate); static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) @@ -6962,6 +6973,186 @@ static void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, + struct nft_trans_gc *trans) +{ + void **priv = trans->priv; + unsigned int i; + + for (i = 0; i < trans->count; i++) { + struct nft_set_elem elem = { + .priv = priv[i], + }; + + nft_setelem_data_deactivate(ctx->net, trans->set, &elem); + trans->set->ops->remove(trans->net, trans->set, &elem); + } +} + +void nft_trans_gc_destroy(struct nft_trans_gc *trans) +{ + nft_set_put(trans->set); + put_net(trans->net); + kfree(trans); +} +EXPORT_SYMBOL_GPL(nft_trans_gc_destroy); + +static void nft_trans_gc_trans_free(struct rcu_head *rcu) +{ + struct nft_set_elem elem = {}; + struct nft_trans_gc *trans; + struct nft_ctx ctx = {}; + unsigned int i; + + trans = container_of(rcu, struct nft_trans_gc, rcu); + ctx.net = read_pnet(&trans->set->net); + + for (i = 0; i < trans->count; i++) { + elem.priv = trans->priv[i]; + atomic_dec(&trans->set->nelems); + + nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + } + + nft_trans_gc_destroy(trans); +} + +static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) +{ + struct nftables_pernet *nft_net; + struct nft_ctx ctx = {}; + + nft_net = net_generic(trans->net, nf_tables_net_id); + + mutex_lock(&nft_net->commit_mutex); + + /* Check for race with transaction, otherwise this batch refers to + * stale objects that might not be there anymore. Skip transaction if + * set has been destroyed from control plane transaction in case gc + * worker loses race. + */ + if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { + mutex_unlock(&nft_net->commit_mutex); + return false; + } + + ctx.net = trans->net; + ctx.table = trans->set->table; + + nft_trans_gc_setelem_remove(&ctx, trans); + mutex_unlock(&nft_net->commit_mutex); + + return true; +} + +static void nft_trans_gc_work(struct work_struct *work) +{ + struct nft_trans_gc *trans, *next; + LIST_HEAD(trans_gc_list); + + spin_lock(&nf_tables_destroy_list_lock); + list_splice_init(&nf_tables_gc_list, &trans_gc_list); + spin_unlock(&nf_tables_destroy_list_lock); + + list_for_each_entry_safe(trans, next, &trans_gc_list, list) { + list_del(&trans->list); + if (!nft_trans_gc_work_done(trans)) { + nft_trans_gc_destroy(trans); + continue; + } + call_rcu(&trans->rcu, nft_trans_gc_trans_free); + } +} + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp) +{ + struct net *net = read_pnet(&set->net); + struct nft_trans_gc *trans; + + trans = kzalloc(sizeof(*trans), gfp); + if (!trans) + return NULL; + + refcount_inc(&set->refs); + trans->set = set; + trans->net = get_net(net); + trans->seq = gc_seq; + + return trans; +} +EXPORT_SYMBOL_GPL(nft_trans_gc_alloc); + +void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) +{ + trans->priv[trans->count++] = priv; +} +EXPORT_SYMBOL_GPL(nft_trans_gc_elem_add); + +static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) +{ + spin_lock(&nf_tables_gc_list_lock); + list_add_tail(&trans->list, &nf_tables_gc_list); + spin_unlock(&nf_tables_gc_list_lock); + + schedule_work(&trans_gc_work); +} + +static int nft_trans_gc_space(struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp) +{ + if (nft_trans_gc_space(gc)) + return gc; + + nft_trans_gc_queue_work(gc); + + return nft_trans_gc_alloc(gc->set, gc_seq, gfp); +} +EXPORT_SYMBOL_GPL(nft_trans_gc_queue_async); + +void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) +{ + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + nft_trans_gc_queue_work(trans); +} +EXPORT_SYMBOL_GPL(nft_trans_gc_queue_async_done); + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) +{ + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) + return NULL; + + if (nft_trans_gc_space(gc)) + return gc; + + call_rcu(&gc->rcu, nft_trans_gc_trans_free); + + return nft_trans_gc_alloc(gc->set, 0, gfp); +} +EXPORT_SYMBOL_GPL(nft_trans_gc_queue_sync); + +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) +{ + WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); + + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + call_rcu(&trans->rcu, nft_trans_gc_trans_free); +} +EXPORT_SYMBOL_GPL(nft_trans_gc_queue_sync_done); + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); @@ -7016,6 +7207,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; + unsigned int gc_seq; int err; if (list_empty(&nft_net->commit_list)) { @@ -7072,6 +7264,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) while (++nft_net->base_seq == 0) ; + /* Bump gc counter, it becomes odd, this is the busy mark. */ + gc_seq = READ_ONCE(nft_net->gc_seq); + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -7149,6 +7345,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELSET: + nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_DELSET, GFP_KERNEL); @@ -7210,6 +7407,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); + + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); nf_tables_commit_release(net); return 0; @@ -8068,6 +8267,7 @@ static int __net_init nf_tables_init_net(struct net *net) mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; nft_net->validate_state = NFT_VALIDATE_SKIP; + nft_net->gc_seq = 0; return 0; } @@ -8094,10 +8294,16 @@ static void __net_exit nf_tables_exit_net(struct net *net) WARN_ON_ONCE(!list_empty(&nft_net->module_list)); } +static void nf_tables_exit_batch(struct list_head *net_exit_list) +{ + flush_work(&trans_gc_work); +} + static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; @@ -8162,6 +8368,7 @@ static void __exit nf_tables_module_exit(void) nft_chain_filter_fini(); nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); + cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); From a65e87c130802a8bb08fe7b18e78d296f372dad8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Nov 2023 13:13:16 +0100 Subject: [PATCH 07/13] UPSTREAM: netfilter: nf_tables: adapt set backend to use GC transaction API commit f6c383b8c31a93752a52697f8430a71dcbc46adf upstream. Use the GC transaction API to replace the old and buggy gc API and the busy mark approach. No set elements are removed from async garbage collection anymore, instead the _DEAD bit is set on so the set element is not visible from lookup path anymore. Async GC enqueues transaction work that might be aborted and retried later. rbtree and pipapo set backends does not set on the _DEAD bit from the sync GC path since this runs in control plane path where mutex is held. In this case, set elements are deactivated, removed and then released via RCU callback, sync GC never fails. Bug: 299922216 Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Fixes: 8d8540c4f5e0 ("netfilter: nft_set_rbtree: add timeout support") Fixes: 9d0982927e79 ("netfilter: nft_hash: add support for timeouts") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit c357648929c8dff891502349769aafb8f0452bc2) Signed-off-by: Lee Jones Change-Id: If26ac816e495ffe97a14b2be8459b6b0a9fad0d0 --- net/netfilter/nft_set_hash.c | 77 ++++++++++++------ net/netfilter/nft_set_rbtree.c | 140 +++++++++++++++++++++------------ 2 files changed, 141 insertions(+), 76 deletions(-) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 34ab10847b93..766a2a35d08d 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -17,6 +17,9 @@ #include #include #include +#include + +extern unsigned int nf_tables_net_id; /* We target a hash table size of 4, element hint is 75% of final size */ #define NFT_RHASH_ELEMENT_HINT 3 @@ -59,6 +62,8 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; + if (nft_set_elem_is_dead(&he->ext)) + return 1; if (nft_set_elem_expired(&he->ext)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) @@ -187,7 +192,6 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); - nft_set_elem_clear_busy(&he->ext); } static bool nft_rhash_flush(const struct net *net, @@ -195,12 +199,9 @@ static bool nft_rhash_flush(const struct net *net, { struct nft_rhash_elem *he = priv; - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) { - nft_set_elem_change_active(net, set, &he->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &he->ext); + + return true; } static void *nft_rhash_deactivate(const struct net *net, @@ -217,9 +218,8 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_lock(); he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); - if (he != NULL && - !nft_rhash_flush(net, set, he)) - he = NULL; + if (he) + nft_set_elem_change_active(net, set, &he->ext); rcu_read_unlock(); @@ -295,49 +295,77 @@ cont: static void nft_rhash_gc(struct work_struct *work) { + struct nftables_pernet *nft_net; struct nft_set *set; struct nft_rhash_elem *he; struct nft_rhash *priv; - struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; + struct nft_trans_gc *gc; + struct net *net; + u32 gc_seq; priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + nft_net = net_generic(net, nf_tables_net_id); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - break; + if (PTR_ERR(he) != -EAGAIN) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } continue; } + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + + if (nft_set_elem_is_dead(&he->ext)) + goto dead_elem; + if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPR)) { struct nft_expr *expr = nft_set_ext_expr(&he->ext); if (expr->ops->gc && expr->ops->gc(read_pnet(&set->net), expr)) - goto gc; + goto needs_gc_run; } if (!nft_set_elem_expired(&he->ext)) continue; -gc: - if (nft_set_elem_mark_busy(&he->ext)) - continue; - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb == NULL) - break; - rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, he); +needs_gc_run: + nft_set_elem_dead(&he->ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; + + nft_trans_gc_elem_add(gc, he); } + +try_later: + /* catchall list iteration requires rcu read side lock. */ rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); - nft_set_gc_batch_complete(gcb); + if (gc) + nft_trans_gc_queue_async_done(gc); + +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } @@ -400,7 +428,6 @@ static void nft_rhash_destroy(const struct nft_ctx *ctx, }; cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)&rhash_ctx); } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 03264f63064f..6c6975d954d0 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -14,6 +14,9 @@ #include #include #include +#include + +extern unsigned int nf_tables_net_id; struct nft_rbtree { struct rb_root root; @@ -46,6 +49,12 @@ static int nft_rbtree_cmp(const struct nft_set *set, set->klen); } +static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) +{ + return nft_set_elem_expired(&rbe->ext) || + nft_set_elem_is_dead(&rbe->ext); +} + static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) @@ -80,7 +89,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set continue; } - if (nft_set_elem_expired(&rbe->ext)) + if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { @@ -98,7 +107,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_set_elem_expired(&interval->ext) && + !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -214,6 +223,18 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set_elem elem = { + .priv = rbe, + }; + + nft_setelem_data_deactivate(net, set, &elem); + rb_erase(&rbe->node, &priv->root); +} + static int nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe, @@ -221,11 +242,12 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); + struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; - struct nft_set_gc_batch *gcb; + struct nft_trans_gc *gc; - gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); - if (!gcb) + gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); + if (!gc) return -ENOMEM; /* search for end interval coming before this element. @@ -243,17 +265,28 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + nft_rbtree_gc_remove(net, set, priv, rbe_prev); - rb_erase(&rbe_prev->node, &priv->root); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_prev); + /* There is always room in this trans gc for this element, + * memory allocation never actually happens, hence, the warning + * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, + * this is synchronous gc which never fails. + */ + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe_prev); } - rb_erase(&rbe->node, &priv->root); - atomic_dec(&set->nelems); + nft_rbtree_gc_remove(net, set, priv, rbe); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; - nft_set_gc_batch_add(gcb, rbe); - nft_set_gc_batch_complete(gcb); + nft_trans_gc_elem_add(gc, rbe); + + nft_trans_gc_queue_sync_done(gc); return 0; } @@ -481,7 +514,6 @@ static void nft_rbtree_activate(const struct net *net, struct nft_rbtree_elem *rbe = elem->priv; nft_set_elem_change_active(net, set, &rbe->ext); - nft_set_elem_clear_busy(&rbe->ext); } static bool nft_rbtree_flush(const struct net *net, @@ -489,12 +521,9 @@ static bool nft_rbtree_flush(const struct net *net, { struct nft_rbtree_elem *rbe = priv; - if (!nft_set_elem_mark_busy(&rbe->ext) || - !nft_is_active(net, &rbe->ext)) { - nft_set_elem_change_active(net, set, &rbe->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &rbe->ext); + + return true; } static void *nft_rbtree_deactivate(const struct net *net, @@ -571,26 +600,40 @@ cont: static void nft_rbtree_gc(struct work_struct *work) { - struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; - struct nft_set_gc_batch *gcb = NULL; + struct nft_rbtree_elem *rbe, *rbe_end = NULL; + struct nftables_pernet *nft_net; struct nft_rbtree *priv; + struct nft_trans_gc *gc; struct rb_node *node; struct nft_set *set; + unsigned int gc_seq; struct net *net; - u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); - genmask = nft_genmask_cur(net); + nft_net = net_generic(net, nf_tables_net_id); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (!nft_set_elem_active(&rbe->ext, genmask)) - continue; + if (nft_set_elem_is_dead(&rbe->ext)) + goto dead_elem; /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is @@ -600,43 +643,38 @@ static void nft_rbtree_gc(struct work_struct *work) rbe_end = rbe; continue; } + if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) { - rbe_end = NULL; + nft_set_elem_dead(&rbe->ext); + + if (!rbe_end) continue; - } - if (rbe_prev) { - rb_erase(&rbe_prev->node, &priv->root); - rbe_prev = NULL; - } - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (!gcb) - break; + nft_set_elem_dead(&rbe_end->ext); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - rbe_prev = rbe; + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - if (rbe_end) { - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_end); - rb_erase(&rbe_end->node, &priv->root); - rbe_end = NULL; - } - node = rb_next(node); - if (!node) - break; + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; + + nft_trans_gc_elem_add(gc, rbe); } - if (rbe_prev) - rb_erase(&rbe_prev->node, &priv->root); + +try_later: write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); - nft_set_gc_batch_complete(gcb); - + if (gc) + nft_trans_gc_queue_async_done(gc); +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } From bdb31e6ebba9d0d956b81290b621c47e8baeede2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Nov 2023 13:13:17 +0100 Subject: [PATCH 08/13] UPSTREAM: netfilter: nft_set_hash: mark set element as dead when deleting from packet path commit c92db3030492b8ad1d0faace7a93bbcf53850d0c upstream. Set on the NFT_SET_ELEM_DEAD_BIT flag on this element, instead of performing element removal which might race with an ongoing transaction. Enable gc when dynamic flag is set on since dynset deletion requires garbage collection after this patch. Bug: 299922216 Fixes: d0a8d877da97 ("netfilter: nft_dynset: support for element deletion") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 85520a1f1d879455a8b6c950e7a92d3e8fa667b6) Signed-off-by: Lee Jones Change-Id: I21bc35c21e35a44753b18f31169c588f8ac70eba --- net/netfilter/nft_set_hash.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 766a2a35d08d..e0c0f7719e04 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -251,7 +251,9 @@ static bool nft_rhash_delete(const struct nft_set *set, if (he == NULL) return false; - return rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params) == 0; + nft_set_elem_dead(&he->ext); + + return true; } static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, @@ -400,7 +402,7 @@ static int nft_rhash_init(const struct nft_set *set, return err; INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); - if (set->flags & NFT_SET_TIMEOUT) + if (set->flags & (NFT_SET_TIMEOUT | NFT_SET_EVAL)) nft_rhash_gc_init(set); return 0; From 81334f26ac709edb3d8fcf42285d9cd3654caa76 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 21 Nov 2023 13:13:18 +0100 Subject: [PATCH 09/13] UPSTREAM: netfilter: nf_tables: remove busy mark and gc batch API commit a2dd0233cbc4d8a0abb5f64487487ffc9265beb5 upstream. Ditch it, it has been replace it by the GC transaction API and it has no clients anymore. Bug: 299922216 Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 1398a0eee290e3ddf1d5ce2539e47dd41830a0d5) Signed-off-by: Lee Jones Change-Id: Id504dda700e2c2b1c4d27e07eeb0c79ba54ab88f --- include/net/netfilter/nf_tables.h | 97 +------------------------------ net/netfilter/nf_tables_api.c | 28 +-------- 2 files changed, 5 insertions(+), 120 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 73979ed2f840..9fb656dbb73e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -672,62 +672,6 @@ void nft_set_elem_destroy(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_gc_batch_head - nf_tables set garbage collection batch - * - * @rcu: rcu head - * @set: set the elements belong to - * @cnt: count of elements - */ -struct nft_set_gc_batch_head { - struct rcu_head rcu; - const struct nft_set *set; - unsigned int cnt; -}; - -#define NFT_SET_GC_BATCH_SIZE ((PAGE_SIZE - \ - sizeof(struct nft_set_gc_batch_head)) / \ - sizeof(void *)) - -/** - * struct nft_set_gc_batch - nf_tables set garbage collection batch - * - * @head: GC batch head - * @elems: garbage collection elements - */ -struct nft_set_gc_batch { - struct nft_set_gc_batch_head head; - void *elems[NFT_SET_GC_BATCH_SIZE]; -}; - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp); -void nft_set_gc_batch_release(struct rcu_head *rcu); - -static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb) -{ - if (gcb != NULL) - call_rcu(&gcb->head.rcu, nft_set_gc_batch_release); -} - -static inline struct nft_set_gc_batch * -nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb, - gfp_t gfp) -{ - if (gcb != NULL) { - if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems)) - return gcb; - nft_set_gc_batch_complete(gcb); - } - return nft_set_gc_batch_alloc(set, gfp); -} - -static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb, - void *elem) -{ - gcb->elems[gcb->head.cnt++] = elem; -} - struct nft_expr_ops; /** * struct nft_expr_type - nf_tables expression type @@ -1354,47 +1298,12 @@ static inline void nft_set_elem_change_active(const struct net *net, #endif /* IS_ENABLED(CONFIG_NF_TABLES) */ -/* - * We use a free bit in the genmask field to indicate the element - * is busy, meaning it is currently being processed either by - * the netlink API or GC. - * - * Even though the genmask is only a single byte wide, this works - * because the extension structure if fully constant once initialized, - * so there are no non-atomic write accesses unless it is already - * marked busy. - */ -#define NFT_SET_ELEM_BUSY_MASK (1 << 2) +#define NFT_SET_ELEM_DEAD_MASK (1 << 2) #if defined(__LITTLE_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT 2 +#define NFT_SET_ELEM_DEAD_BIT 2 #elif defined(__BIG_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) -#else -#error -#endif - -static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext) -{ - unsigned long *word = (unsigned long *)ext; - - BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); - return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word); -} - -static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) -{ - unsigned long *word = (unsigned long *)ext; - - clear_bit(NFT_SET_ELEM_BUSY_BIT, word); -} - -#define NFT_SET_ELEM_DEAD_MASK (1 << 3) - -#if defined(__LITTLE_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_DEAD_BIT 3 -#elif defined(__BIG_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 3) +#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) #else #error #endif diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5b128d6b2dde..9da46bf1e0cd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4879,7 +4879,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (trans == NULL) goto err4; - ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; + ext->genmask = nft_genmask_cur(ctx->net); + err = set->ops->insert(ctx->net, set, &elem, &ext2); if (err) { if (err == -EEXIST) { @@ -5172,31 +5173,6 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, return err; } -void nft_set_gc_batch_release(struct rcu_head *rcu) -{ - struct nft_set_gc_batch *gcb; - unsigned int i; - - gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); - for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); - kfree(gcb); -} -EXPORT_SYMBOL_GPL(nft_set_gc_batch_release); - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp) -{ - struct nft_set_gc_batch *gcb; - - gcb = kzalloc(sizeof(*gcb), gfp); - if (gcb == NULL) - return gcb; - gcb->head.set = set; - return gcb; -} -EXPORT_SYMBOL_GPL(nft_set_gc_batch_alloc); - /* * Stateful objects */ From 0581932d872f14a36bb8ef7375ca920ed63fe083 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 18 May 2020 10:47:48 -0700 Subject: [PATCH 10/13] UPSTREAM: nvmet-tcp: move send/recv error handling in the send/recv methods instead of call-sites commit 0236d3437909ff888e5c79228e2d5a851651c4c6 upstream. Have routines handle errors and just bail out of the poll loop. This simplifies the code and will help as we may enhance the poll loop logic and these are somewhat in the way. Bug: 310114968 Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Dragos-Marian Panait Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2c9415ec8ea93870b979eb03f5848c4ad5303818) Signed-off-by: Lee Jones Change-Id: I96f2eabd90a4690aa8b388c4d9b0060d06c60d9b --- drivers/nvme/target/tcp.c | 43 ++++++++++++++++++++++----------------- 1 file changed, 24 insertions(+), 19 deletions(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index df7a911d303f..e63a50e22e5a 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -321,6 +321,14 @@ static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) kernel_sock_shutdown(queue->sock, SHUT_RDWR); } +static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) +{ + if (status == -EPIPE || status == -ECONNRESET) + kernel_sock_shutdown(queue->sock, SHUT_RDWR); + else + nvmet_tcp_fatal_error(queue); +} + static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) { struct nvme_sgl_desc *sgl = &cmd->req.cmd->common.dptr.sgl; @@ -714,11 +722,15 @@ static int nvmet_tcp_try_send(struct nvmet_tcp_queue *queue, for (i = 0; i < budget; i++) { ret = nvmet_tcp_try_send_one(queue, i == budget - 1); - if (ret <= 0) + if (unlikely(ret < 0)) { + nvmet_tcp_socket_error(queue, ret); + goto done; + } else if (ret == 0) { break; + } (*sends)++; } - +done: return ret; } @@ -1167,11 +1179,15 @@ static int nvmet_tcp_try_recv(struct nvmet_tcp_queue *queue, for (i = 0; i < budget; i++) { ret = nvmet_tcp_try_recv_one(queue); - if (ret <= 0) + if (unlikely(ret < 0)) { + nvmet_tcp_socket_error(queue, ret); + goto done; + } else if (ret == 0) { break; + } (*recvs)++; } - +done: return ret; } @@ -1196,27 +1212,16 @@ static void nvmet_tcp_io_work(struct work_struct *w) pending = false; ret = nvmet_tcp_try_recv(queue, NVMET_TCP_RECV_BUDGET, &ops); - if (ret > 0) { + if (ret > 0) pending = true; - } else if (ret < 0) { - if (ret == -EPIPE || ret == -ECONNRESET) - kernel_sock_shutdown(queue->sock, SHUT_RDWR); - else - nvmet_tcp_fatal_error(queue); + else if (ret < 0) return; - } ret = nvmet_tcp_try_send(queue, NVMET_TCP_SEND_BUDGET, &ops); - if (ret > 0) { - /* transmitted message/data */ + if (ret > 0) pending = true; - } else if (ret < 0) { - if (ret == -EPIPE || ret == -ECONNRESET) - kernel_sock_shutdown(queue->sock, SHUT_RDWR); - else - nvmet_tcp_fatal_error(queue); + else if (ret < 0) return; - } } while (pending && ops < NVMET_TCP_IO_WORK_BUDGET); From f51804072bcc58759ff6228a3d73edadfb5cf787 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 2 Oct 2023 13:54:28 +0300 Subject: [PATCH 11/13] UPSTREAM: nvmet-tcp: Fix a possible UAF in queue intialization setup commit d920abd1e7c4884f9ecd0749d1921b7ab19ddfbd upstream. From Alon: "Due to a logical bug in the NVMe-oF/TCP subsystem in the Linux kernel, a malicious user can cause a UAF and a double free, which may lead to RCE (may also lead to an LPE in case the attacker already has local privileges)." Hence, when a queue initialization fails after the ahash requests are allocated, it is guaranteed that the queue removal async work will be called, hence leave the deallocation to the queue removal. Also, be extra careful not to continue processing the socket, so set queue rcv_state to NVMET_TCP_RECV_ERR upon a socket error. Bug: 310114968 Cc: stable@vger.kernel.org Reported-by: Alon Zahavi Tested-by: Alon Zahavi Signed-off-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Signed-off-by: Keith Busch Signed-off-by: Dragos-Marian Panait Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 4e53bab11f01a401a5acd3bc94335b27ec79106b) Signed-off-by: Lee Jones Change-Id: Ifd7ec8294182a6bf6d8c261aeda5d989e909f7ff --- drivers/nvme/target/tcp.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index e63a50e22e5a..e8c7135c4c11 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -323,6 +323,7 @@ static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) { + queue->rcv_state = NVMET_TCP_RECV_ERR; if (status == -EPIPE || status == -ECONNRESET) kernel_sock_shutdown(queue->sock, SHUT_RDWR); else @@ -828,15 +829,11 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) iov.iov_len = sizeof(*icresp); ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); if (ret < 0) - goto free_crypto; + return ret; /* queue removal will cleanup */ queue->state = NVMET_TCP_Q_LIVE; nvmet_prepare_receive_pdu(queue); return 0; -free_crypto: - if (queue->hdr_digest || queue->data_digest) - nvmet_tcp_free_crypto(queue); - return ret; } static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, From 5ae6be03f52d1e9ea2b821fd5805681b062ea8ca Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Fri, 15 Dec 2023 09:34:07 +0000 Subject: [PATCH 12/13] ANDROID: Snapshot Mainline's version of checkpatch.pl Nothing fancy here. Keeping full history is not required. `git checkout mainline/master -- scripts/checkpatch.pl` This may need to be done periodically. Bug: 316492624 Signed-off-by: Lee Jones Change-Id: I4c90b50197ca7277c59e96bf332ecf795c4f3d12 --- scripts/checkpatch.pl | 1425 ++++++++++++++++++++++++++++++++--------- 1 file changed, 1117 insertions(+), 308 deletions(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 978cfc9401a3..25fdb7fda112 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -23,6 +23,9 @@ my $V = '0.32'; use Getopt::Long qw(:config no_auto_abbrev); my $quiet = 0; +my $verbose = 0; +my %verbose_messages = (); +my %verbose_emitted = (); my $tree = 1; my $chk_signoff = 1; my $chk_patch = 1; @@ -43,6 +46,8 @@ my $list_types = 0; my $fix = 0; my $fix_inplace = 0; my $root; +my $gitroot = $ENV{'GIT_DIR'}; +$gitroot = ".git" if !defined($gitroot); my %debug; my %camelcase = (); my %use_type = (); @@ -58,13 +63,18 @@ my $min_conf_desc_length = 4; my $spelling_file = "$D/spelling.txt"; my $codespell = 0; my $codespellfile = "/usr/share/codespell/dictionary.txt"; +my $user_codespellfile = ""; my $conststructsfile = "$D/const_structs.checkpatch"; +my $docsfile = "$D/../Documentation/dev-tools/checkpatch.rst"; my $typedefsfile; my $color = "auto"; my $allow_c99_comments = 1; # Can be overridden by --ignore C99_COMMENT_TOLERANCE # git output parsing needs US English output, so first set backtick child process LANGUAGE my $git_command ='export LANGUAGE=en_US.UTF-8; git'; my $tabsize = 8; +my ${CONFIG_} = "CONFIG_"; + +my %maybe_linker_symbol; # for externs in c exceptions, when seen in *vmlinux.lds.h sub help { my ($exitcode) = @_; @@ -75,6 +85,7 @@ Version: $V Options: -q, --quiet quiet + -v, --verbose verbose mode --no-tree run without a kernel tree --no-signoff do not check for 'Signed-off-by' line --patch treat FILE as patchfile (default) @@ -122,11 +133,13 @@ Options: --ignore-perl-version override checking of perl version. expect runtime errors. --codespell Use the codespell dictionary for spelling/typos - (default:/usr/share/codespell/dictionary.txt) + (default:$codespellfile) --codespellfile Use this codespell dictionary --typedefsfile Read additional types from this file --color[=WHEN] Use colors 'always', 'never', or only when output is a terminal ('auto'). Default is 'auto'. + --kconfig-prefix=WORD use WORD as a prefix for Kconfig symbols (default + ${CONFIG_}) -h, --help, --version display this help and exit When FILE is - read standard input. @@ -153,15 +166,51 @@ sub list_types { my $text = <$script>; close($script); - my @types = (); + my %types = (); # Also catch when type or level is passed through a variable - for ($text =~ /(?:(?:\bCHK|\bWARN|\bERROR|&\{\$msg_level})\s*\(|\$msg_type\s*=)\s*"([^"]+)"/g) { - push (@types, $_); + while ($text =~ /(?:(\bCHK|\bWARN|\bERROR|&\{\$msg_level})\s*\(|\$msg_type\s*=)\s*"([^"]+)"/g) { + if (defined($1)) { + if (exists($types{$2})) { + $types{$2} .= ",$1" if ($types{$2} ne $1); + } else { + $types{$2} = $1; + } + } else { + $types{$2} = "UNDETERMINED"; + } } - @types = sort(uniq(@types)); + print("#\tMessage type\n\n"); - foreach my $type (@types) { + if ($color) { + print(" ( Color coding: "); + print(RED . "ERROR" . RESET); + print(" | "); + print(YELLOW . "WARNING" . RESET); + print(" | "); + print(GREEN . "CHECK" . RESET); + print(" | "); + print("Multiple levels / Undetermined"); + print(" )\n\n"); + } + + foreach my $type (sort keys %types) { + my $orig_type = $type; + if ($color) { + my $level = $types{$type}; + if ($level eq "ERROR") { + $type = RED . $type . RESET; + } elsif ($level eq "WARN") { + $type = YELLOW . $type . RESET; + } elsif ($level eq "CHK") { + $type = GREEN . $type . RESET; + } + } print(++$count . "\t" . $type . "\n"); + if ($verbose && exists($verbose_messages{$orig_type})) { + my $message = $verbose_messages{$orig_type}; + $message =~ s/\n/\n\t/g; + print("\t" . $message . "\n\n"); + } } exit($exitcode); @@ -193,6 +242,46 @@ if (-f $conf) { unshift(@ARGV, @conf_args) if @conf_args; } +sub load_docs { + open(my $docs, '<', "$docsfile") + or warn "$P: Can't read the documentation file $docsfile $!\n"; + + my $type = ''; + my $desc = ''; + my $in_desc = 0; + + while (<$docs>) { + chomp; + my $line = $_; + $line =~ s/\s+$//; + + if ($line =~ /^\s*\*\*(.+)\*\*$/) { + if ($desc ne '') { + $verbose_messages{$type} = trim($desc); + } + $type = $1; + $desc = ''; + $in_desc = 1; + } elsif ($in_desc) { + if ($line =~ /^(?:\s{4,}|$)/) { + $line =~ s/^\s{4}//; + $desc .= $line; + $desc .= "\n"; + } else { + $verbose_messages{$type} = trim($desc); + $type = ''; + $desc = ''; + $in_desc = 0; + } + } + } + + if ($desc ne '') { + $verbose_messages{$type} = trim($desc); + } + close($docs); +} + # Perl's Getopt::Long allows options to take optional arguments after a space. # Prevent --color by itself from consuming other arguments foreach (@ARGV) { @@ -203,6 +292,7 @@ foreach (@ARGV) { GetOptions( 'q|quiet+' => \$quiet, + 'v|verbose!' => \$verbose, 'tree!' => \$tree, 'signoff!' => \$chk_signoff, 'patch!' => \$chk_patch, @@ -230,24 +320,62 @@ GetOptions( 'debug=s' => \%debug, 'test-only=s' => \$tst_only, 'codespell!' => \$codespell, - 'codespellfile=s' => \$codespellfile, + 'codespellfile=s' => \$user_codespellfile, 'typedefsfile=s' => \$typedefsfile, 'color=s' => \$color, 'no-color' => \$color, #keep old behaviors of -nocolor 'nocolor' => \$color, #keep old behaviors of -nocolor + 'kconfig-prefix=s' => \${CONFIG_}, 'h|help' => \$help, 'version' => \$help -) or help(1); +) or $help = 2; -help(0) if ($help); +if ($user_codespellfile) { + # Use the user provided codespell file unconditionally + $codespellfile = $user_codespellfile; +} elsif (!(-f $codespellfile)) { + # If /usr/share/codespell/dictionary.txt is not present, try to find it + # under codespell's install directory: /data/dictionary.txt + if (($codespell || $help) && which("python3") ne "") { + my $python_codespell_dict = << "EOF"; +import os.path as op +import codespell_lib +codespell_dir = op.dirname(codespell_lib.__file__) +codespell_file = op.join(codespell_dir, 'data', 'dictionary.txt') +print(codespell_file, end='') +EOF + + my $codespell_dict = `python3 -c "$python_codespell_dict" 2> /dev/null`; + $codespellfile = $codespell_dict if (-f $codespell_dict); + } +} + +# $help is 1 if either -h, --help or --version is passed as option - exitcode: 0 +# $help is 2 if invalid option is passed - exitcode: 1 +help($help - 1) if ($help); + +die "$P: --git cannot be used with --file or --fix\n" if ($git && ($file || $fix)); +die "$P: --verbose cannot be used with --terse\n" if ($verbose && $terse); + +if ($color =~ /^[01]$/) { + $color = !$color; +} elsif ($color =~ /^always$/i) { + $color = 1; +} elsif ($color =~ /^never$/i) { + $color = 0; +} elsif ($color =~ /^auto$/i) { + $color = (-t STDOUT); +} else { + die "$P: Invalid color mode: $color\n"; +} + +load_docs() if ($verbose); list_types(0) if ($list_types); $fix = 1 if ($fix_inplace); $check_orig = $check; -die "$P: --git cannot be used with --file or --fix\n" if ($git && ($file || $fix)); - my $exit = 0; my $perl_version_ok = 1; @@ -262,18 +390,6 @@ if ($#ARGV < 0) { push(@ARGV, '-'); } -if ($color =~ /^[01]$/) { - $color = !$color; -} elsif ($color =~ /^always$/i) { - $color = 1; -} elsif ($color =~ /^never$/i) { - $color = 0; -} elsif ($color =~ /^auto$/i) { - $color = (-t STDOUT); -} else { - die "$P: Invalid color mode: $color\n"; -} - # skip TAB size 1 to avoid additional checks on $tabsize - 1 die "$P: Invalid TAB size: $tabsize\n" if ($tabsize < 2); @@ -376,6 +492,7 @@ our $InitAttribute = qr{$InitAttributeData|$InitAttributeConst|$InitAttributeIni # We need \b after 'init' otherwise 'initconst' will cause a false positive in a check our $Attribute = qr{ const| + volatile| __percpu| __nocast| __safe| @@ -398,7 +515,8 @@ our $Attribute = qr{ ____cacheline_aligned| ____cacheline_aligned_in_smp| ____cacheline_internodealigned_in_smp| - __weak + __weak| + __alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\) }x; our $Modifier; our $Inline = qr{inline|__always_inline|noinline|__inline|__inline__}; @@ -410,7 +528,7 @@ our $Binary = qr{(?i)0b[01]+$Int_type?}; our $Hex = qr{(?i)0x[0-9a-f]+$Int_type?}; our $Int = qr{[0-9]+$Int_type?}; our $Octal = qr{0[0-7]+$Int_type?}; -our $String = qr{"[X\t]*"}; +our $String = qr{(?:\b[Lu])?"[X\t]*"}; our $Float_hex = qr{(?i)0x[0-9a-f]+p-?[0-9]+[fl]?}; our $Float_dec = qr{(?i)(?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?}; our $Float_int = qr{(?i)[0-9]+e-?[0-9]+[fl]?}; @@ -460,10 +578,14 @@ our $typeKernelTypedefs = qr{(?x: (?:__)?(?:u|s|be|le)(?:8|16|32|64)| atomic_t )}; +our $typeStdioTypedefs = qr{(?x: + FILE +)}; our $typeTypedefs = qr{(?x: $typeC99Typedefs\b| $typeOtherOSTypedefs\b| - $typeKernelTypedefs\b + $typeKernelTypedefs\b| + $typeStdioTypedefs\b )}; our $zero_initializer = qr{(?:(?:0[xX])?0+$Int_type?|NULL|false)\b}; @@ -480,7 +602,7 @@ our $logFunctions = qr{(?x: our $allocFunctions = qr{(?x: (?:(?:devm_)? - (?:kv|k|v)[czm]alloc(?:_node|_array)? | + (?:kv|k|v)[czm]alloc(?:_array)?(?:_node)? | kstrdup(?:_const)? | kmemdup(?:_nul)?) | (?:\w+)?alloc_skb(?:_ip_align)? | @@ -500,6 +622,115 @@ our $signature_tags = qr{(?xi: Cc: )}; +our @link_tags = qw(Link Closes); + +#Create a search and print patterns for all these strings to be used directly below +our $link_tags_search = ""; +our $link_tags_print = ""; +foreach my $entry (@link_tags) { + if ($link_tags_search ne "") { + $link_tags_search .= '|'; + $link_tags_print .= ' or '; + } + $entry .= ':'; + $link_tags_search .= $entry; + $link_tags_print .= "'$entry'"; +} +$link_tags_search = "(?:${link_tags_search})"; + +our $tracing_logging_tags = qr{(?xi: + [=-]*> | + <[=-]* | + \[ | + \] | + start | + called | + entered | + entry | + enter | + in | + inside | + here | + begin | + exit | + end | + done | + leave | + completed | + out | + return | + [\.\!:\s]* +)}; + +sub edit_distance_min { + my (@arr) = @_; + my $len = scalar @arr; + if ((scalar @arr) < 1) { + # if underflow, return + return; + } + my $min = $arr[0]; + for my $i (0 .. ($len-1)) { + if ($arr[$i] < $min) { + $min = $arr[$i]; + } + } + return $min; +} + +sub get_edit_distance { + my ($str1, $str2) = @_; + $str1 = lc($str1); + $str2 = lc($str2); + $str1 =~ s/-//g; + $str2 =~ s/-//g; + my $len1 = length($str1); + my $len2 = length($str2); + # two dimensional array storing minimum edit distance + my @distance; + for my $i (0 .. $len1) { + for my $j (0 .. $len2) { + if ($i == 0) { + $distance[$i][$j] = $j; + } elsif ($j == 0) { + $distance[$i][$j] = $i; + } elsif (substr($str1, $i-1, 1) eq substr($str2, $j-1, 1)) { + $distance[$i][$j] = $distance[$i - 1][$j - 1]; + } else { + my $dist1 = $distance[$i][$j - 1]; #insert distance + my $dist2 = $distance[$i - 1][$j]; # remove + my $dist3 = $distance[$i - 1][$j - 1]; #replace + $distance[$i][$j] = 1 + edit_distance_min($dist1, $dist2, $dist3); + } + } + } + return $distance[$len1][$len2]; +} + +sub find_standard_signature { + my ($sign_off) = @_; + my @standard_signature_tags = ( + 'Signed-off-by:', 'Co-developed-by:', 'Acked-by:', 'Tested-by:', + 'Reviewed-by:', 'Reported-by:', 'Suggested-by:' + ); + foreach my $signature (@standard_signature_tags) { + return $signature if (get_edit_distance($sign_off, $signature) <= 2); + } + + return ""; +} + +our $obsolete_archives = qr{(?xi: + \Qfreedesktop.org/archives/dri-devel\E | + \Qlists.infradead.org\E | + \Qlkml.org\E | + \Qmail-archive.com\E | + \Qmailman.alsa-project.org/pipermail\E | + \Qmarc.info\E | + \Qozlabs.org/pipermail\E | + \Qspinics.net\E +)}; + our @typeListMisordered = ( qr{char\s+(?:un)?signed}, qr{int\s+(?:(?:un)?signed\s+)?short\s}, @@ -609,6 +840,10 @@ our %deprecated_apis = ( "rcu_barrier_sched" => "rcu_barrier", "get_state_synchronize_sched" => "get_state_synchronize_rcu", "cond_synchronize_sched" => "cond_synchronize_rcu", + "kmap" => "kmap_local_page", + "kunmap" => "kunmap_local", + "kmap_atomic" => "kmap_local_page", + "kunmap_atomic" => "kunmap_local", ); #Create a search pattern for all these strings to speed up a loop below @@ -844,9 +1079,17 @@ our $FuncArg = qr{$Typecast{0,1}($LvalOrFunc|$Constant|$String)}; our $declaration_macros = qr{(?x: (?:$Storage\s+)?(?:[A-Z_][A-Z0-9]*_){0,2}(?:DEFINE|DECLARE)(?:_[A-Z0-9]+){1,6}\s*\(| (?:$Storage\s+)?[HLP]?LIST_HEAD\s*\(| - (?:SKCIPHER_REQUEST|SHASH_DESC|AHASH_REQUEST)_ON_STACK\s*\( + (?:SKCIPHER_REQUEST|SHASH_DESC|AHASH_REQUEST)_ON_STACK\s*\(| + (?:$Storage\s+)?(?:XA_STATE|XA_STATE_ORDER)\s*\( )}; +our %allow_repeated_words = ( + add => '', + added => '', + bad => '', + be => '', +); + sub deparenthesize { my ($string) = @_; return "" if (!defined($string)); @@ -904,10 +1147,10 @@ sub is_maintained_obsolete { sub is_SPDX_License_valid { my ($license) = @_; - return 1 if (!$tree || which("python") eq "" || !(-e "$root/scripts/spdxcheck.py") || !(-e "$root/.git")); + return 1 if (!$tree || which("python3") eq "" || !(-x "$root/scripts/spdxcheck.py") || !(-e "$gitroot")); my $root_path = abs_path($root); - my $status = `cd "$root_path"; echo "$license" | python scripts/spdxcheck.py -`; + my $status = `cd "$root_path"; echo "$license" | scripts/spdxcheck.py -`; return 0 if ($status ne ""); return 1; } @@ -922,7 +1165,7 @@ sub seed_camelcase_includes { $camelcase_seeded = 1; - if (-e ".git") { + if (-e "$gitroot") { my $git_last_include_commit = `${git_command} log --no-merges --pretty=format:"%h%n" -1 -- include`; chomp $git_last_include_commit; $camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit"; @@ -950,7 +1193,7 @@ sub seed_camelcase_includes { return; } - if (-e ".git") { + if (-e "$gitroot") { $files = `${git_command} ls-files "include/*.h"`; @include_files = split('\n', $files); } @@ -970,10 +1213,20 @@ sub seed_camelcase_includes { } } +sub git_is_single_file { + my ($filename) = @_; + + return 0 if ((which("git") eq "") || !(-e "$gitroot")); + + my $output = `${git_command} ls-files -- $filename 2>/dev/null`; + my $count = $output =~ tr/\n//; + return $count eq 1 && $output =~ m{^${filename}$}; +} + sub git_commit_info { my ($commit, $id, $desc) = @_; - return ($id, $desc) if ((which("git") eq "") || !(-e ".git")); + return ($id, $desc) if ((which("git") eq "") || !(-e "$gitroot")); my $output = `${git_command} log --no-color --format='%H %s' -1 $commit 2>&1`; $output =~ s/^\s*//gm; @@ -991,7 +1244,8 @@ sub git_commit_info { # git log --format='%H %s' -1 $line | # echo "commit $(cut -c 1-12,41-)" # done - } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./) { + } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./ || + $lines[0] =~ /^fatal: bad object $commit/) { $id = undef; } else { $id = substr($lines[0], 0, 12); @@ -1012,7 +1266,7 @@ my $fixlinenr = -1; # If input is git commits, extract all commits from the commit expressions. # For example, HEAD-3 means we need check 'HEAD, HEAD~1, HEAD~2'. -die "$P: No git repository found\n" if ($git && !-e ".git"); +die "$P: No git repository found\n" if ($git && !-e "$gitroot"); if ($git) { my @commits = (); @@ -1043,6 +1297,9 @@ my $vname; $allow_c99_comments = !defined $ignore_type{"C99_COMMENT_TOLERANCE"}; for my $filename (@ARGV) { my $FILE; + my $is_git_file = git_is_single_file($filename); + my $oldfile = $file; + $file = 1 if ($is_git_file); if ($git) { open($FILE, '-|', "git format-patch -M --stdout -1 $filename") || die "$P: $filename: git format-patch failed - $!\n"; @@ -1087,6 +1344,7 @@ for my $filename (@ARGV) { @modifierListFile = (); @typeListFile = (); build_types(); + $file = $oldfile if ($is_git_file); } if (!$quiet) { @@ -1132,6 +1390,7 @@ sub parse_email { my ($formatted_email) = @_; my $name = ""; + my $quoted = ""; my $name_comment = ""; my $address = ""; my $comment = ""; @@ -1163,14 +1422,20 @@ sub parse_email { } } - $name = trim($name); - $name =~ s/^\"|\"$//g; - $name =~ s/(\s*\([^\)]+\))\s*//; - if (defined($1)) { - $name_comment = trim($1); + # Extract comments from names excluding quoted parts + # "John D. (Doe)" - Do not extract + if ($name =~ s/\"(.+)\"//) { + $quoted = $1; } + while ($name =~ s/\s*($balanced_parens)\s*/ /) { + $name_comment .= trim($1); + } + $name =~ s/^[ \"]+|[ \"]+$//g; + $name = trim("$quoted $name"); + $address = trim($address); $address =~ s/^\<|\>$//g; + $comment = trim($comment); if ($name =~ /[^\w \-]/i) { ##has "must quote" chars $name =~ s/(?"; + $formatted_email = "$name$name_comment <$address>"; } - + $formatted_email .= "$comment"; return $formatted_email; } @@ -1207,7 +1477,7 @@ sub reformat_email { my ($email) = @_; my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); - return format_email($email_name, $email_address); + return format_email($email_name, $name_comment, $email_address, $comment); } sub same_email_addresses { @@ -1217,7 +1487,9 @@ sub same_email_addresses { my ($email2_name, $name2_comment, $email2_address, $comment2) = parse_email($email2); return $email1_name eq $email2_name && - $email1_address eq $email2_address; + $email1_address eq $email2_address && + $name1_comment eq $name2_comment && + $comment1 eq $comment2; } sub which { @@ -2085,7 +2357,16 @@ sub report { splice(@lines, 1, 1); $output = join("\n", @lines); } - $output = (split('\n', $output))[0] . "\n" if ($terse); + + if ($terse) { + $output = (split('\n', $output))[0] . "\n"; + } + + if ($verbose && exists($verbose_messages{$type}) && + !exists($verbose_emitted{$type})) { + $output .= $verbose_messages{$type} . "\n\n"; + $verbose_emitted{$type} = 1; + } push(our @report, $output); @@ -2329,6 +2610,15 @@ sub get_raw_comment { return $comment; } +sub exclude_global_initialisers { + my ($realfile) = @_; + + # Do not check for BPF programs (tools/testing/selftests/bpf/progs/*.c, samples/bpf/*_kern.c, *.bpf.c). + return $realfile =~ m@^tools/testing/selftests/bpf/progs/.*\.c$@ || + $realfile =~ m@^samples/bpf/.*_kern\.c$@ || + $realfile =~ m@/bpf/.*\.bpf\.c$@; +} + sub process { my $filename = shift; @@ -2347,6 +2637,7 @@ sub process { my $signoff = 0; my $author = ''; my $authorsignoff = 0; + my $author_sob = ''; my $is_patch = 0; my $is_binding_patch = -1; my $in_header_lines = $file ? 0 : 1; @@ -2360,6 +2651,8 @@ sub process { my $reported_maintainer_file = 0; my $non_utf8_charset = 0; + my $last_git_commit_id_linenr = -1; + my $last_blank_line = 0; my $last_coalesced_string_linenr = -1; @@ -2661,6 +2954,10 @@ sub process { # Check the patch for a From: if (decode("MIME-Header", $line) =~ /^From:\s*(.*)/) { $author = $1; + my $curline = $linenr; + while(defined($rawlines[$curline]) && ($rawlines[$curline++] =~ /^[ \t]\s*(.*)/)) { + $author .= $1; + } $author = encode("utf8", $author) if ($line =~ /=\?utf-8\?/i); $author =~ s/"//g; $author = reformat_email($author); @@ -2670,9 +2967,37 @@ sub process { if ($line =~ /^\s*signed-off-by:\s*(.*)/i) { $signoff++; $in_commit_log = 0; - if ($author ne '') { + if ($author ne '' && $authorsignoff != 1) { if (same_email_addresses($1, $author)) { $authorsignoff = 1; + } else { + my $ctx = $1; + my ($email_name, $email_comment, $email_address, $comment1) = parse_email($ctx); + my ($author_name, $author_comment, $author_address, $comment2) = parse_email($author); + + if (lc $email_address eq lc $author_address && $email_name eq $author_name) { + $author_sob = $ctx; + $authorsignoff = 2; + } elsif (lc $email_address eq lc $author_address) { + $author_sob = $ctx; + $authorsignoff = 3; + } elsif ($email_name eq $author_name) { + $author_sob = $ctx; + $authorsignoff = 4; + + my $address1 = $email_address; + my $address2 = $author_address; + + if ($address1 =~ /(\S+)\+\S+(\@.*)/) { + $address1 = "$1$2"; + } + if ($address2 =~ /(\S+)\+\S+(\@.*)/) { + $address2 = "$1$2"; + } + if ($address1 eq $address2) { + $authorsignoff = 5; + } + } } } } @@ -2699,8 +3024,17 @@ sub process { my $ucfirst_sign_off = ucfirst(lc($sign_off)); if ($sign_off !~ /$signature_tags/) { - WARN("BAD_SIGN_OFF", - "Non-standard signature: $sign_off\n" . $herecurr); + my $suggested_signature = find_standard_signature($sign_off); + if ($suggested_signature eq "") { + WARN("BAD_SIGN_OFF", + "Non-standard signature: $sign_off\n" . $herecurr); + } else { + if (WARN("BAD_SIGN_OFF", + "Non-standard signature: '$sign_off' - perhaps '$suggested_signature'?\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/$sign_off/$suggested_signature/; + } + } } if (defined $space_before && $space_before ne "") { if (WARN("BAD_SIGN_OFF", @@ -2729,7 +3063,7 @@ sub process { } my ($email_name, $name_comment, $email_address, $comment) = parse_email($email); - my $suggested_email = format_email(($email_name, $email_address)); + my $suggested_email = format_email(($email_name, $name_comment, $email_address, $comment)); if ($suggested_email eq "") { ERROR("BAD_SIGN_OFF", "Unrecognized email address: '$email'\n" . $herecurr); @@ -2740,8 +3074,76 @@ sub process { # Don't force email to have quotes # Allow just an angle bracketed address if (!same_email_addresses($email, $suggested_email)) { + if (WARN("BAD_SIGN_OFF", + "email address '$email' might be better as '$suggested_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$suggested_email/; + } + } + + # Address part shouldn't have comments + my $stripped_address = $email_address; + $stripped_address =~ s/\([^\(\)]*\)//g; + if ($email_address ne $stripped_address) { + if (WARN("BAD_SIGN_OFF", + "address part of email should not have comments: '$email_address'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email_address\E/$stripped_address/; + } + } + + # Only one name comment should be allowed + my $comment_count = () = $name_comment =~ /\([^\)]+\)/g; + if ($comment_count > 1) { WARN("BAD_SIGN_OFF", - "email address '$email' might be better as '$suggested_email$comment'\n" . $herecurr); + "Use a single name comment in email: '$email'\n" . $herecurr); + } + + + # stable@vger.kernel.org or stable@kernel.org shouldn't + # have an email name. In addition comments should strictly + # begin with a # + if ($email =~ /^.*stable\@(?:vger\.)?kernel\.org/i) { + if (($comment ne "" && $comment !~ /^#.+/) || + ($email_name ne "")) { + my $cur_name = $email_name; + my $new_comment = $comment; + $cur_name =~ s/[a-zA-Z\s\-\"]+//g; + + # Remove brackets enclosing comment text + # and # from start of comments to get comment text + $new_comment =~ s/^\((.*)\)$/$1/; + $new_comment =~ s/^\[(.*)\]$/$1/; + $new_comment =~ s/^[\s\#]+|\s+$//g; + + $new_comment = trim("$new_comment $cur_name") if ($cur_name ne $new_comment); + $new_comment = " # $new_comment" if ($new_comment ne ""); + my $new_email = "$email_address$new_comment"; + + if (WARN("BAD_STABLE_ADDRESS_STYLE", + "Invalid email format for stable: '$email', prefer '$new_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$new_email/; + } + } + } elsif ($comment ne "" && $comment !~ /^(?:#.+|\(.+\))$/) { + my $new_comment = $comment; + + # Extract comment text from within brackets or + # c89 style /*...*/ comments + $new_comment =~ s/^\[(.*)\]$/$1/; + $new_comment =~ s/^\/\*(.*)\*\/$/$1/; + + $new_comment = trim($new_comment); + $new_comment =~ s/^[^\w]$//; # Single lettered comment with non word character is usually a typo + $new_comment = "($new_comment)" if ($new_comment ne ""); + my $new_email = format_email($email_name, $name_comment, $email_address, $new_comment); + + if (WARN("BAD_SIGN_OFF", + "Unexpected content after email: '$email', should be: '$new_email'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\Q$email\E/$new_email/; + } } } @@ -2760,17 +3162,73 @@ sub process { if ($sign_off =~ /^co-developed-by:$/i) { if ($email eq $author) { WARN("BAD_SIGN_OFF", - "Co-developed-by: should not be used to attribute nominal patch author '$author'\n" . "$here\n" . $rawline); + "Co-developed-by: should not be used to attribute nominal patch author '$author'\n" . $herecurr); } if (!defined $lines[$linenr]) { WARN("BAD_SIGN_OFF", - "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline); - } elsif ($rawlines[$linenr] !~ /^\s*signed-off-by:\s*(.*)/i) { + "Co-developed-by: must be immediately followed by Signed-off-by:\n" . $herecurr); + } elsif ($rawlines[$linenr] !~ /^signed-off-by:\s*(.*)/i) { WARN("BAD_SIGN_OFF", - "Co-developed-by: must be immediately followed by Signed-off-by:\n" . "$here\n" . $rawline . "\n" .$rawlines[$linenr]); + "Co-developed-by: must be immediately followed by Signed-off-by:\n" . $herecurr . $rawlines[$linenr] . "\n"); } elsif ($1 ne $email) { WARN("BAD_SIGN_OFF", - "Co-developed-by and Signed-off-by: name/email do not match \n" . "$here\n" . $rawline . "\n" .$rawlines[$linenr]); + "Co-developed-by and Signed-off-by: name/email do not match\n" . $herecurr . $rawlines[$linenr] . "\n"); + } + } + +# check if Reported-by: is followed by a Closes: tag + if ($sign_off =~ /^reported(?:|-and-tested)-by:$/i) { + if (!defined $lines[$linenr]) { + WARN("BAD_REPORTED_BY_LINK", + "Reported-by: should be immediately followed by Closes: with a URL to the report\n" . $herecurr . "\n"); + } elsif ($rawlines[$linenr] !~ /^closes:\s*/i) { + WARN("BAD_REPORTED_BY_LINK", + "Reported-by: should be immediately followed by Closes: with a URL to the report\n" . $herecurr . $rawlines[$linenr] . "\n"); + } + } + } + + +# Check Fixes: styles is correct + if (!$in_header_lines && + $line =~ /^\s*fixes:?\s*(?:commit\s*)?[0-9a-f]{5,}\b/i) { + my $orig_commit = ""; + my $id = "0123456789ab"; + my $title = "commit title"; + my $tag_case = 1; + my $tag_space = 1; + my $id_length = 1; + my $id_case = 1; + my $title_has_quotes = 0; + + if ($line =~ /(\s*fixes:?)\s+([0-9a-f]{5,})\s+($balanced_parens)/i) { + my $tag = $1; + $orig_commit = $2; + $title = $3; + + $tag_case = 0 if $tag eq "Fixes:"; + $tag_space = 0 if ($line =~ /^fixes:? [0-9a-f]{5,} ($balanced_parens)/i); + + $id_length = 0 if ($orig_commit =~ /^[0-9a-f]{12}$/i); + $id_case = 0 if ($orig_commit !~ /[A-F]/); + + # Always strip leading/trailing parens then double quotes if existing + $title = substr($title, 1, -1); + if ($title =~ /^".*"$/) { + $title = substr($title, 1, -1); + $title_has_quotes = 1; + } + } + + my ($cid, $ctitle) = git_commit_info($orig_commit, $id, + $title); + + if ($ctitle ne $title || $tag_case || $tag_space || + $id_length || $id_case || !$title_has_quotes) { + if (WARN("BAD_FIXES_TAG", + "Please use correct Fixes: style 'Fixes: <12 chars of sha1> (\"\")' - ie: 'Fixes: $cid (\"$ctitle\")'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] = "Fixes: $cid (\"$ctitle\")"; } } } @@ -2784,8 +3242,11 @@ sub process { # Check for Gerrit Change-Ids not in any patch context if ($realfile eq '' && !$has_patch_separator && $line =~ /^\s*change-id:/i) { - ERROR("GERRIT_CHANGE_ID", - "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr); + if (ERROR("GERRIT_CHANGE_ID", + "Remove Gerrit Change-Id's before submitting upstream\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } } # Check if the commit log is in a possible stack dump @@ -2805,13 +3266,13 @@ sub process { length($line) > 75 && !($line =~ /^\s*[a-zA-Z0-9_\/\.]+\s+\|\s+\d+/ || # file delta changes - $line =~ /^\s*(?:[\w\.\-]+\/)++[\w\.\-]+:/ || + $line =~ /^\s*(?:[\w\.\-\+]*\/)++[\w\.\-\+]+:/ || # filename then : - $line =~ /^\s*(?:Fixes:|Link:)/i || - # A Fixes: or Link: line + $line =~ /^\s*(?:Fixes:|$link_tags_search|$signature_tags)/i || + # A Fixes:, link or signature tag line $commit_log_possible_stack_dump)) { WARN("COMMIT_LOG_LONG_LINE", - "Possible unwrapped commit description (prefer a maximum 75 chars per line)\n" . $herecurr); + "Prefer a maximum 75 chars per line (possible unwrapped commit description?)\n" . $herecurr); $commit_log_long_line = 1; } @@ -2821,11 +3282,53 @@ sub process { $commit_log_possible_stack_dump = 0; } +# Check for odd tags before a URI/URL + if ($in_commit_log && + $line =~ /^\s*(\w+:)\s*http/ && $1 !~ /^$link_tags_search$/) { + if ($1 =~ /^v(?:ersion)?\d+/i) { + WARN("COMMIT_LOG_VERSIONING", + "Patch version information should be after the --- line\n" . $herecurr); + } else { + WARN("COMMIT_LOG_USE_LINK", + "Unknown link reference '$1', use $link_tags_print instead\n" . $herecurr); + } + } + +# Check for misuse of the link tags + if ($in_commit_log && + $line =~ /^\s*(\w+:)\s*(\S+)/) { + my $tag = $1; + my $value = $2; + if ($tag =~ /^$link_tags_search$/ && $value !~ m{^https?://}) { + WARN("COMMIT_LOG_WRONG_LINK", + "'$tag' should be followed by a public http(s) link\n" . $herecurr); + } + } + +# Check for lines starting with a # + if ($in_commit_log && $line =~ /^#/) { + if (WARN("COMMIT_COMMENT_SYMBOL", + "Commit log lines starting with '#' are dropped by git as comments\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/^/ /; + } + } + # Check for git id commit length and improperly formed commit descriptions - if ($in_commit_log && !$commit_log_possible_stack_dump && +# A correctly formed commit description is: +# commit <SHA-1 hash length 12+ chars> ("Complete commit subject") +# with the commit subject '("' prefix and '")' suffix +# This is a fairly compilicated block as it tests for what appears to be +# bare SHA-1 hash with minimum length of 5. It also avoids several types of +# possible SHA-1 matches. +# A commit match can span multiple lines so this block attempts to find a +# complete typical commit on a maximum of 3 lines + if ($perl_version_ok && + $in_commit_log && !$commit_log_possible_stack_dump && $line !~ /^\s*(?:Link|Patchwork|http|https|BugLink|base-commit):/i && $line !~ /^This reverts commit [0-9a-f]{7,40}/ && - ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i || + (($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i || + ($line =~ /\bcommit\s*$/i && defined($rawlines[$linenr]) && $rawlines[$linenr] =~ /^\s*[0-9a-f]{5,}\b/i)) || ($line =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i && $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i && $line !~ /\bfixes:\s*[0-9a-f]{12,40}/i))) { @@ -2835,49 +3338,62 @@ sub process { my $long = 0; my $case = 1; my $space = 1; - my $hasdesc = 0; - my $hasparens = 0; my $id = '0123456789ab'; my $orig_desc = "commit description"; my $description = ""; + my $herectx = $herecurr; + my $has_parens = 0; + my $has_quotes = 0; - if ($line =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) { - $init_char = $1; - $orig_commit = lc($2); - } elsif ($line =~ /\b([0-9a-f]{12,40})\b/i) { - $orig_commit = lc($1); + my $input = $line; + if ($line =~ /(?:\bcommit\s+[0-9a-f]{5,}|\bcommit\s*$)/i) { + for (my $n = 0; $n < 2; $n++) { + if ($input =~ /\bcommit\s+[0-9a-f]{5,}\s*($balanced_parens)/i) { + $orig_desc = $1; + $has_parens = 1; + # Always strip leading/trailing parens then double quotes if existing + $orig_desc = substr($orig_desc, 1, -1); + if ($orig_desc =~ /^".*"$/) { + $orig_desc = substr($orig_desc, 1, -1); + $has_quotes = 1; + } + last; + } + last if ($#lines < $linenr + $n); + $input .= " " . trim($rawlines[$linenr + $n]); + $herectx .= "$rawlines[$linenr + $n]\n"; + } + $herectx = $herecurr if (!$has_parens); } - $short = 0 if ($line =~ /\bcommit\s+[0-9a-f]{12,40}/i); - $long = 1 if ($line =~ /\bcommit\s+[0-9a-f]{41,}/i); - $space = 0 if ($line =~ /\bcommit [0-9a-f]/i); - $case = 0 if ($line =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/); - if ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)"\)/i) { - $orig_desc = $1; - $hasparens = 1; - } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s*$/i && - defined $rawlines[$linenr] && - $rawlines[$linenr] =~ /^\s*\("([^"]+)"\)/) { - $orig_desc = $1; - $hasparens = 1; - } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("[^"]+$/i && - defined $rawlines[$linenr] && - $rawlines[$linenr] =~ /^\s*[^"]+"\)/) { - $line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)$/i; - $orig_desc = $1; - $rawlines[$linenr] =~ /^\s*([^"]+)"\)/; - $orig_desc .= " " . $1; - $hasparens = 1; + if ($input =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) { + $init_char = $1; + $orig_commit = lc($2); + $short = 0 if ($input =~ /\bcommit\s+[0-9a-f]{12,40}/i); + $long = 1 if ($input =~ /\bcommit\s+[0-9a-f]{41,}/i); + $space = 0 if ($input =~ /\bcommit [0-9a-f]/i); + $case = 0 if ($input =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/); + } elsif ($input =~ /\b([0-9a-f]{12,40})\b/i) { + $orig_commit = lc($1); } ($id, $description) = git_commit_info($orig_commit, $id, $orig_desc); if (defined($id) && - ($short || $long || $space || $case || ($orig_desc ne $description) || !$hasparens)) { + ($short || $long || $space || $case || ($orig_desc ne $description) || !$has_quotes) && + $last_git_commit_id_linenr != $linenr - 1) { ERROR("GIT_COMMIT_ID", - "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herecurr); + "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herectx); } + #don't report the next line if this line ends in commit and the sha1 hash is the next line + $last_git_commit_id_linenr = $linenr if ($line =~ /\bcommit\s*$/i); + } + +# Check for mailing list archives other than lore.kernel.org + if ($rawline =~ m{http.*\b$obsolete_archives}) { + WARN("PREFER_LORE_ARCHIVE", + "Use lore.kernel.org archive links when possible - see https://lore.kernel.org/lists.html\n" . $herecurr); } # Check for added, moved or deleted files @@ -2897,7 +3413,7 @@ sub process { ($line =~ /^new file mode\s*\d+\s*$/) && ($realfile =~ m@^Documentation/devicetree/bindings/.*\.txt$@)) { WARN("DT_SCHEMA_BINDING_PATCH", - "DT bindings should be in DT schema format. See: Documentation/devicetree/writing-schema.rst\n"); + "DT bindings should be in DT schema format. See: Documentation/devicetree/bindings/writing-schema.rst\n"); } # Check for wrappage within a valid hunk of the file @@ -2961,15 +3477,18 @@ sub process { # Check for various typo / spelling mistakes if (defined($misspellings) && ($in_commit_log || $line =~ /^(?:\+|Subject:)/i)) { - while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:\b|$|[^a-z@])/gi) { + while ($rawline =~ /(?:^|[^\w\-'`])($misspellings)(?:[^\w\-'`]|$)/gi) { my $typo = $1; + my $blank = copy_spacing($rawline); + my $ptr = substr($blank, 0, $-[1]) . "^" x length($typo); + my $hereptr = "$hereline$ptr\n"; my $typo_fix = $spelling_fix{lc($typo)}; $typo_fix = ucfirst($typo_fix) if ($typo =~ /^[A-Z]/); $typo_fix = uc($typo_fix) if ($typo =~ /^[A-Z]+$/); my $msg_level = \&WARN; $msg_level = \&CHK if ($file); if (&{$msg_level}("TYPO_SPELLING", - "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $herecurr) && + "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $hereptr) && $fix) { $fixed[$fixlinenr] =~ s/(^|[^A-Za-z@])($typo)($|[^A-Za-z@])/$1$typo_fix$3/; } @@ -2987,6 +3506,60 @@ sub process { } } +# check for repeated words separated by a single space +# avoid false positive from list command eg, '-rw-r--r-- 1 root root' + if (($rawline =~ /^\+/ || $in_commit_log) && + $rawline !~ /[bcCdDlMnpPs\?-][rwxsStT-]{9}/) { + pos($rawline) = 1 if (!$in_commit_log); + while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) { + + my $first = $1; + my $second = $2; + my $start_pos = $-[1]; + my $end_pos = $+[2]; + if ($first =~ /(?:struct|union|enum)/) { + pos($rawline) += length($first) + length($second) + 1; + next; + } + + next if (lc($first) ne lc($second)); + next if ($first eq 'long'); + + # check for character before and after the word matches + my $start_char = ''; + my $end_char = ''; + $start_char = substr($rawline, $start_pos - 1, 1) if ($start_pos > ($in_commit_log ? 0 : 1)); + $end_char = substr($rawline, $end_pos, 1) if ($end_pos < length($rawline)); + + next if ($start_char =~ /^\S$/); + next if (index(" \t.,;?!", $end_char) == -1); + + # avoid repeating hex occurrences like 'ff ff fe 09 ...' + if ($first =~ /\b[0-9a-f]{2,}\b/i) { + next if (!exists($allow_repeated_words{lc($first)})); + } + + if (WARN("REPEATED_WORD", + "Possible repeated word: '$first'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b$first $second\b/$first/; + } + } + + # if it's a repeated word on consecutive lines in a comment block + if ($prevline =~ /$;+\s*$/ && + $prevrawline =~ /($word_pattern)\s*$/) { + my $last_word = $1; + if ($rawline =~ /^\+\s*\*\s*$last_word /) { + if (WARN("REPEATED_WORD", + "Possible repeated word: '$last_word'\n" . $hereprev) && + $fix) { + $fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/; + } + } + } + } + # ignore non-hunk lines and lines being removed next if (!$hunk_line || $line =~ /^-/); @@ -3029,51 +3602,47 @@ sub process { # Kconfig supports named choices), so use a word boundary # (\b) rather than a whitespace character (\s) $line =~ /^\+\s*(?:config|menuconfig|choice)\b/) { - my $length = 0; - my $cnt = $realcnt; - my $ln = $linenr + 1; - my $f; - my $is_start = 0; - my $is_end = 0; - for (; $cnt > 0 && defined $lines[$ln - 1]; $ln++) { - $f = $lines[$ln - 1]; - $cnt-- if ($lines[$ln - 1] !~ /^-/); - $is_end = $lines[$ln - 1] =~ /^\+/; + my $ln = $linenr; + my $needs_help = 0; + my $has_help = 0; + my $help_length = 0; + while (defined $lines[$ln]) { + my $f = $lines[$ln++]; next if ($f =~ /^-/); - last if (!$file && $f =~ /^\@\@/); + last if ($f !~ /^[\+ ]/); # !patch context - if ($lines[$ln - 1] =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) { - $is_start = 1; - } elsif ($lines[$ln - 1] =~ /^\+\s*(?:help|---help---)\s*$/) { - if ($lines[$ln - 1] =~ "---help---") { - WARN("CONFIG_DESCRIPTION", - "prefer 'help' over '---help---' for new help texts\n" . $herecurr); - } - $length = -1; + if ($f =~ /^\+\s*(?:bool|tristate|prompt)\s*["']/) { + $needs_help = 1; + next; + } + if ($f =~ /^\+\s*help\s*$/) { + $has_help = 1; + next; } - $f =~ s/^.//; - $f =~ s/#.*//; - $f =~ s/^\s+//; - next if ($f =~ /^$/); + $f =~ s/^.//; # strip patch context [+ ] + $f =~ s/#.*//; # strip # directives + $f =~ s/^\s+//; # strip leading blanks + next if ($f =~ /^$/); # skip blank lines + # At the end of this Kconfig block: # This only checks context lines in the patch # and so hopefully shouldn't trigger false # positives, even though some of these are # common words in help texts - if ($f =~ /^\s*(?:config|menuconfig|choice|endchoice| - if|endif|menu|endmenu|source)\b/x) { - $is_end = 1; + if ($f =~ /^(?:config|menuconfig|choice|endchoice| + if|endif|menu|endmenu|source)\b/x) { last; } - $length++; + $help_length++ if ($has_help); } - if ($is_start && $is_end && $length < $min_conf_desc_length) { + if ($needs_help && + $help_length < $min_conf_desc_length) { + my $stat_real = get_stat_real($linenr, $ln - 1); WARN("CONFIG_DESCRIPTION", - "please write a paragraph that describes the config symbol fully\n" . $herecurr); + "please write a help paragraph that fully describes the config symbol\n" . "$here\n$stat_real\n"); } - #print "is_start<$is_start> is_end<$is_end> length<$length>\n"; } # check MAINTAINERS entries @@ -3116,13 +3685,6 @@ sub process { } } -# discourage the use of boolean for type definition attributes of Kconfig options - if ($realfile =~ /Kconfig/ && - $line =~ /^\+\s*\bboolean\b/) { - WARN("CONFIG_TYPE_BOOLEAN", - "Use of boolean is deprecated, please use bool instead.\n" . $herecurr); - } - if (($realfile =~ /Makefile.*/ || $realfile =~ /Kbuild.*/) && ($line =~ /\+(EXTRA_[A-Z]+FLAGS).*/)) { my $flag = $1; @@ -3176,7 +3738,7 @@ sub process { my $comment = ""; if ($realfile =~ /\.(h|s|S)$/) { $comment = '/*'; - } elsif ($realfile =~ /\.(c|dts|dtsi)$/) { + } elsif ($realfile =~ /\.(c|rs|dts|dtsi)$/) { $comment = '//'; } elsif (($checklicenseline == 2) || $realfile =~ /\.(sh|pl|py|awk|tc|yaml)$/) { $comment = '#'; @@ -3203,7 +3765,7 @@ sub process { "'$spdx_license' is not supported in LICENSES/...\n" . $herecurr); } if ($realfile =~ m@^Documentation/devicetree/bindings/@ && - not $spdx_license =~ /GPL-2\.0.*BSD-2-Clause/) { + $spdx_license !~ /GPL-2\.0(?:-only)? OR BSD-2-Clause/) { my $msg_level = \&WARN; $msg_level = \&CHK if ($file); if (&{$msg_level}("SPDX_LICENSE_TAG", @@ -3213,12 +3775,23 @@ sub process { $fixed[$fixlinenr] =~ s/SPDX-License-Identifier: .*/SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)/; } } + if ($realfile =~ m@^include/dt-bindings/@ && + $spdx_license !~ /GPL-2\.0(?:-only)? OR \S+/) { + WARN("SPDX_LICENSE_TAG", + "DT binding headers should be licensed (GPL-2.0-only OR .*)\n" . $herecurr); + } } } } +# check for embedded filenames + if ($rawline =~ /^\+.*\b\Q$realfile\E\b/) { + WARN("EMBEDDED_FILENAME", + "It's generally not useful to have the filename in the file\n" . $herecurr); + } + # check we are in a valid source file if not then ignore this hunk - next if ($realfile !~ /\.(h|c|s|S|sh|dtsi|dts)$/); + next if ($realfile !~ /\.(h|c|rs|s|S|sh|dtsi|dts)$/); # check for using SPDX-License-Identifier on the wrong line number if ($realline != $checklicenseline && @@ -3294,8 +3867,18 @@ sub process { # check for adding lines without a newline. if ($line =~ /^\+/ && defined $lines[$linenr] && $lines[$linenr] =~ /^\\ No newline at end of file/) { - WARN("MISSING_EOF_NEWLINE", - "adding a line without newline at end of file\n" . $herecurr); + if (WARN("MISSING_EOF_NEWLINE", + "adding a line without newline at end of file\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr+1, "No newline at end of file"); + } + } + +# check for .L prefix local symbols in .S files + if ($realfile =~ /\.S$/ && + $line =~ /^\+\s*(?:[A-Z]+_)?SYM_[A-Z]+_(?:START|END)(?:_[A-Z_]+)?\s*\(\s*\.L/) { + WARN("AVOID_L_PREFIX", + "Avoid using '.L' prefixed local symbol names for denoting a range of code via 'SYM_*_START/END' annotations; see Documentation/core-api/asm-annotations.rst\n" . $herecurr); } # check we are in a valid source file C or perl if not then ignore this hunk @@ -3314,42 +3897,6 @@ sub process { } } -# check for repeated words separated by a single space - if ($rawline =~ /^\+/) { - while ($rawline =~ /\b($word_pattern) (?=($word_pattern))/g) { - - my $first = $1; - my $second = $2; - - if ($first =~ /(?:struct|union|enum)/) { - pos($rawline) += length($first) + length($second) + 1; - next; - } - - next if ($first ne $second); - next if ($first eq 'long'); - - if (WARN("REPEATED_WORD", - "Possible repeated word: '$first'\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b$first $second\b/$first/; - } - } - - # if it's a repeated word on consecutive lines in a comment block - if ($prevline =~ /$;+\s*$/ && - $prevrawline =~ /($word_pattern)\s*$/) { - my $last_word = $1; - if ($rawline =~ /^\+\s*\*\s*$last_word /) { - if (WARN("REPEATED_WORD", - "Possible repeated word: '$last_word'\n" . $hereprev) && - $fix) { - $fixed[$fixlinenr] =~ s/(\+\s*\*\s*)$last_word /$1/; - } - } - } - } - # check for space before tabs. if ($rawline =~ /^\+/ && $rawline =~ / \t/) { my $herevet = "$here\n" . cat_vet($rawline) . "\n"; @@ -3365,14 +3912,28 @@ sub process { # check for assignments on the start of a line if ($sline =~ /^\+\s+($Assignment)[^=]/) { - CHK("ASSIGNMENT_CONTINUATIONS", - "Assignment operator '$1' should be on the previous line\n" . $hereprev); + my $operator = $1; + if (CHK("ASSIGNMENT_CONTINUATIONS", + "Assignment operator '$1' should be on the previous line\n" . $hereprev) && + $fix && $prevrawline =~ /^\+/) { + # add assignment operator to the previous line, remove from current line + $fixed[$fixlinenr - 1] .= " $operator"; + $fixed[$fixlinenr] =~ s/\Q$operator\E\s*//; + } } # check for && or || at the start of a line if ($rawline =~ /^\+\s*(&&|\|\|)/) { - CHK("LOGICAL_CONTINUATIONS", - "Logical continuations should be on the previous line\n" . $hereprev); + my $operator = $1; + if (CHK("LOGICAL_CONTINUATIONS", + "Logical continuations should be on the previous line\n" . $hereprev) && + $fix && $prevrawline =~ /^\+/) { + # insert logical operator at last non-comment, non-whitepsace char on previous line + $prevline =~ /[\s$;]*$/; + my $line_end = substr($prevrawline, $-[0]); + $fixed[$fixlinenr - 1] =~ s/\Q$line_end\E$/ $operator$line_end/; + $fixed[$fixlinenr] =~ s/\Q$operator\E\s*//; + } } # check indentation starts on a tab stop @@ -3440,7 +4001,7 @@ sub process { if ($realfile =~ m@^(drivers/net/|net/)@ && $prevrawline =~ /^\+[ \t]*\/\*[ \t]*$/ && $rawline =~ /^\+[ \t]*\*/ && - $realline > 2) { + $realline > 3) { # Do not warn about the initial copyright comment block after SPDX-License-Identifier WARN("NETWORKING_BLOCK_COMMENT_STYLE", "networking block comments don't use an empty /* line, use /* Comment...\n" . $hereprev); } @@ -3493,7 +4054,7 @@ sub process { if ($prevline =~ /^[\+ ]};?\s*$/ && $line =~ /^\+/ && !($line =~ /^\+\s*$/ || - $line =~ /^\+\s*EXPORT_SYMBOL/ || + $line =~ /^\+\s*(?:EXPORT_SYMBOL|early_param)/ || $line =~ /^\+\s*MODULE_/i || $line =~ /^\+\s*\#\s*(?:end|elif|else)/ || $line =~ /^\+[a-z_]*init/ || @@ -3522,43 +4083,48 @@ sub process { } # check for missing blank lines after declarations - if ($sline =~ /^\+\s+\S/ && #Not at char 1 - # actual declarations - ($prevline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || +# (declarations must have the same indentation and not be at the start of line) + if (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/) { + # use temporaries + my $sl = $sline; + my $pl = $prevline; + # remove $Attribute/$Sparse uses to simplify comparisons + $sl =~ s/\b(?:$Attribute|$Sparse)\b//g; + $pl =~ s/\b(?:$Attribute|$Sparse)\b//g; + if (($pl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $prevline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $pl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $prevline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $pl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $prevline =~ /^\+\s+$declaration_macros/) && + $pl =~ /^\+\s+$declaration_macros/) && # for "else if" which can look like "$Ident $Ident" - !($prevline =~ /^\+\s+$c90_Keywords\b/ || + !($pl =~ /^\+\s+$c90_Keywords\b/ || # other possible extensions of declaration lines - $prevline =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || + $pl =~ /(?:$Compare|$Assignment|$Operators)\s*$/ || # not starting a section or a macro "\" extended line - $prevline =~ /(?:\{\s*|\\)$/) && + $pl =~ /(?:\{\s*|\\)$/) && # looks like a declaration - !($sline =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || + !($sl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ || # function pointer declarations - $sline =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || + $sl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ || # foo bar; where foo is some local typedef or #define - $sline =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || + $sl =~ /^\+\s+$Ident(?:\s+|\s*\*\s*)$Ident\s*[=,;\[]/ || # known declaration macros - $sline =~ /^\+\s+$declaration_macros/ || + $sl =~ /^\+\s+$declaration_macros/ || # start of struct or union or enum - $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || + $sl =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || # start or end of block or continuation of declaration - $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || + $sl =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || # bitfield continuation - $sline =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || + $sl =~ /^\+\s+$Ident\s*:\s*\d+\s*[,;]/ || # other possible extensions of declaration lines - $sline =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/) && - # indentation of previous and current line are the same - (($prevline =~ /\+(\s+)\S/) && $sline =~ /^\+$1\S/)) { - if (WARN("LINE_SPACING", - "Missing a blank line after declarations\n" . $hereprev) && - $fix) { - fix_insert_line($fixlinenr, "\+"); + $sl =~ /^\+\s+\(?\s*(?:$Compare|$Assignment|$Operators)/)) { + if (WARN("LINE_SPACING", + "Missing a blank line after declarations\n" . $hereprev) && + $fix) { + fix_insert_line($fixlinenr, "\+"); + } } } @@ -3611,12 +4177,16 @@ sub process { } # check indentation of a line with a break; -# if the previous line is a goto or return and is indented the same # of tabs +# if the previous line is a goto, return or break +# and is indented the same # of tabs if ($sline =~ /^\+([\t]+)break\s*;\s*$/) { my $tabs = $1; - if ($prevline =~ /^\+$tabs(?:goto|return)\b/) { - WARN("UNNECESSARY_BREAK", - "break is not useful after a goto or return\n" . $hereprev); + if ($prevline =~ /^\+$tabs(goto|return|break)\b/) { + if (WARN("UNNECESSARY_BREAK", + "break is not useful after a $1\n" . $hereprev) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } } } @@ -3899,6 +4469,17 @@ sub process { #ignore lines not being added next if ($line =~ /^[^\+]/); +# check for self assignments used to avoid compiler warnings +# e.g.: int foo = foo, *bar = NULL; +# struct foo bar = *(&(bar)); + if ($line =~ /^\+\s*(?:$Declare)?([A-Za-z_][A-Za-z\d_]*)\s*=/) { + my $var = $1; + if ($line =~ /^\+\s*(?:$Declare)?$var\s*=\s*(?:$var|\*\s*\(?\s*&\s*\(?\s*$var\s*\)?\s*\)?)\s*[;,]/) { + WARN("SELF_ASSIGNMENT", + "Do not use self-assignments to avoid compiler warnings\n" . $herecurr); + } + } + # check for dereferences that span multiple lines if ($prevline =~ /^\+.*$Lval\s*(?:\.|->)\s*$/ && $line =~ /^\+\s*(?!\#\s*(?!define\s+|if))\s*$Lval/) { @@ -4014,13 +4595,13 @@ sub process { if (defined $realline_next && exists $lines[$realline_next - 1] && !defined $suppress_export{$realline_next} && - ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $lines[$realline_next - 1] =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($lines[$realline_next - 1] =~ /EXPORT_SYMBOL.*\((.*)\)/)) { # Handle definitions which produce identifiers with # a prefix: # XXX(foo); # EXPORT_SYMBOL(something_foo); my $name = $1; + $name =~ s/^\s*($Ident).*/$1/; if ($stat =~ /^(?:.\s*}\s*\n)?.([A-Z_]+)\s*\(\s*($Ident)/ && $name =~ /^${Ident}_$2/) { #print "FOO C name<$name>\n"; @@ -4042,8 +4623,7 @@ sub process { } if (!defined $suppress_export{$linenr} && $prevline =~ /^.\s*$/ && - ($line =~ /EXPORT_SYMBOL.*\((.*)\)/ || - $line =~ /EXPORT_UNUSED_SYMBOL.*\((.*)\)/)) { + ($line =~ /EXPORT_SYMBOL.*\((.*)\)/)) { #print "FOO B <$lines[$linenr - 1]>\n"; $suppress_export{$linenr} = 2; } @@ -4054,7 +4634,8 @@ sub process { } # check for global initialisers. - if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/) { + if ($line =~ /^\+$Type\s*$Ident(?:\s+$Modifier)*\s*=\s*($zero_initializer)\s*;/ && + !exclude_global_initialisers($realfile)) { if (ERROR("GLOBAL_INITIALISERS", "do not initialise globals to $1\n" . $herecurr) && $fix) { @@ -4133,12 +4714,24 @@ sub process { } } +# check for const static or static <non ptr type> const declarations +# prefer 'static const <foo>' over 'const static <foo>' and 'static <foo> const' + if ($sline =~ /^\+\s*const\s+static\s+($Type)\b/ || + $sline =~ /^\+\s*static\s+($BasicType)\s+const\b/) { + if (WARN("STATIC_CONST", + "Move const after static - use 'static const $1'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bconst\s+static\b/static const/; + $fixed[$fixlinenr] =~ s/\bstatic\s+($BasicType)\s+const\b/static const $1/; + } + } + # check for non-global char *foo[] = {"bar", ...} declarations. if ($line =~ /^.\s+(?:static\s+|const\s+)?char\s+\*\s*\w+\s*\[\s*\]\s*=\s*\{/) { WARN("STATIC_CONST_CHAR_ARRAY", "char * array declaration might be better as static const\n" . $herecurr); - } + } # check for sizeof(foo)/sizeof(foo[0]) that could be ARRAY_SIZE(foo) if ($line =~ m@\bsizeof\s*\(\s*($Lval)\s*\)@) { @@ -4229,12 +4822,12 @@ sub process { } } -# avoid BUG() or BUG_ON() - if ($line =~ /\b(?:BUG|BUG_ON)\b/) { +# do not use BUG() or variants + if ($line =~ /\b(?!AA_|BUILD_|DCCP_|IDA_|KVM_|RWLOCK_|snd_|SPIN_)(?:[a-zA-Z_]*_)?BUG(?:_ON)?(?:_[A-Z_]+)?\s*\(/) { my $msg_level = \&WARN; $msg_level = \&CHK if ($file); &{$msg_level}("AVOID_BUG", - "Avoid crashing the kernel - try using WARN_ON & recovery code rather than BUG() or BUG_ON()\n" . $herecurr); + "Do not crash the kernel unless it is absolutely unavoidable--use WARN_ON_ONCE() plus recovery code (if feasible) instead of BUG() or variants\n" . $herecurr); } # avoid LINUX_VERSION_CODE @@ -4255,16 +4848,23 @@ sub process { "printk() should include KERN_<LEVEL> facility level\n" . $herecurr); } - if ($line =~ /\bprintk\s*\(\s*KERN_([A-Z]+)/) { - my $orig = $1; +# prefer variants of (subsystem|netdev|dev|pr)_<level> to printk(KERN_<LEVEL> + if ($line =~ /\b(printk(_once|_ratelimited)?)\s*\(\s*KERN_([A-Z]+)/) { + my $printk = $1; + my $modifier = $2; + my $orig = $3; + $modifier = "" if (!defined($modifier)); my $level = lc($orig); $level = "warn" if ($level eq "warning"); my $level2 = $level; $level2 = "dbg" if ($level eq "debug"); + $level .= $modifier; + $level2 .= $modifier; WARN("PREFER_PR_LEVEL", - "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(... to printk(KERN_$orig ...\n" . $herecurr); + "Prefer [subsystem eg: netdev]_$level2([subsystem]dev, ... then dev_$level2(dev, ... then pr_$level(... to $printk(KERN_$orig ...\n" . $herecurr); } +# prefer dev_<level> to dev_printk(KERN_<LEVEL> if ($line =~ /\bdev_printk\s*\(\s*KERN_([A-Z]+)/) { my $orig = $1; my $level = lc($orig); @@ -4274,6 +4874,12 @@ sub process { "Prefer dev_$level(... to dev_printk(KERN_$orig, ...\n" . $herecurr); } +# trace_printk should not be used in production code. + if ($line =~ /\b(trace_printk|trace_puts|ftrace_vprintk)\s*\(/) { + WARN("TRACE_PRINTK", + "Do not use $1() in production code (this can be ignored if built only with a debug config option)\n" . $herecurr); + } + # ENOSYS means "bad syscall nr" and nothing else. This will have a small # number of false positives, but assembly files are not checked, so at # least the arch entry code will not trigger this warning. @@ -4442,7 +5048,7 @@ sub process { if|for|while|switch|return|case| volatile|__volatile__| __attribute__|format|__extension__| - asm|__asm__)$/x) + asm|__asm__|scoped_guard)$/x) { # cpp #define statements have non-optional spaces, ie # if there is a space between the name and the open @@ -4715,7 +5321,7 @@ sub process { # A colon needs no spaces before when it is # terminating a case value or a label. } elsif ($opv eq ':C' || $opv eq ':L') { - if ($ctx =~ /Wx./) { + if ($ctx =~ /Wx./ and $realfile !~ m@.*\.lds\.h$@) { if (ERROR("SPACING", "space prohibited before that '$op' $at\n" . $hereptr)) { $good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]); @@ -4799,7 +5405,7 @@ sub process { ## $line !~ /^.\s*$Type\s+$Ident(?:\s*=[^,{]*)?\s*,\s*$Type\s*$Ident.*/) { ## ## # Remove any bracketed sections to ensure we do not -## # falsly report the parameters of functions. +## # falsely report the parameters of functions. ## my $ln = $line; ## while ($ln =~ s/\([^\(\)]*\)//g) { ## } @@ -4929,9 +5535,13 @@ sub process { } } -#goto labels aren't indented, allow a single space however - if ($line=~/^.\s+[A-Za-z\d_]+:(?![0-9]+)/ and - !($line=~/^. [A-Za-z\d_]+:/) and !($line=~/^.\s+default:/)) { +# check that goto labels aren't indented (allow a single space indentation) +# and ignore bitfield definitions like foo:1 +# Strictly, labels can have whitespace after the identifier and before the : +# but this is not allowed here as many ?: uses would appear to be labels + if ($sline =~ /^.\s+[A-Za-z_][A-Za-z\d_]*:(?!\s*\d+)/ && + $sline !~ /^. [A-Za-z\d_][A-Za-z\d_]*:/ && + $sline !~ /^.\s+default:/) { if (WARN("INDENTED_LABEL", "labels should not be indented\n" . $herecurr) && $fix) { @@ -4940,6 +5550,17 @@ sub process { } } +# check if a statement with a comma should be two statements like: +# foo = bar(), /* comma should be semicolon */ +# bar = baz(); + if (defined($stat) && + $stat =~ /^\+\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*,\s*(?:$Lval\s*$Assignment\s*)?$FuncArg\s*;\s*$/) { + my $cnt = statement_rawlines($stat); + my $herectx = get_stat_here($linenr, $cnt, $here); + WARN("SUSPECT_COMMA_SEMICOLON", + "Possible comma where semicolon could be used\n" . $herectx); + } + # return is not a function if (defined($stat) && $stat =~ /^.\s*return(\s*)\(/s) { my $spacing = $1; @@ -4967,7 +5588,7 @@ sub process { $lines[$linenr - 3] !~ /^[ +]\s*$Ident\s*:/) { WARN("RETURN_VOID", "void function return statements are not generally useful\n" . $hereprev); - } + } # if statements using unnecessary parentheses - ie: if ((foo == bar)) if ($perl_version_ok && @@ -5015,7 +5636,7 @@ sub process { # Return of what appears to be an errno should normally be negative if ($sline =~ /\breturn(?:\s*\(+\s*|\s+)(E[A-Z]+)(?:\s*\)+\s*|\s*)[;:,]/) { my $name = $1; - if ($name ne 'EOF' && $name ne 'ERROR') { + if ($name ne 'EOF' && $name ne 'ERROR' && $name !~ /^EPOLL/) { WARN("USE_NEGATIVE_ERRNO", "return of an errno should typically be negative (ie: return -$1)\n" . $herecurr); } @@ -5058,6 +5679,7 @@ sub process { defined($stat) && defined($cond) && $line =~ /\b(?:if|while|for)\s*\(/ && $line !~ /^.\s*#/) { my ($s, $c) = ($stat, $cond); + my $fixed_assign_in_if = 0; if ($c =~ /\bif\s*\(.*[^<>!=]=[^=].*/s) { if (ERROR("ASSIGN_IN_IF", @@ -5082,6 +5704,7 @@ sub process { $newline .= ')'; $newline .= " {" if (defined($brace)); fix_insert_line($fixlinenr + 1, $newline); + $fixed_assign_in_if = 1; } } } @@ -5105,8 +5728,20 @@ sub process { $stat_real = "[...]\n$stat_real"; } - ERROR("TRAILING_STATEMENTS", - "trailing statements should be on next line\n" . $herecurr . $stat_real); + if (ERROR("TRAILING_STATEMENTS", + "trailing statements should be on next line\n" . $herecurr . $stat_real) && + !$fixed_assign_in_if && + $cond_lines == 0 && + $fix && $perl_version_ok && + $fixed[$fixlinenr] =~ /^\+(\s*)((?:if|while|for)\s*$balanced_parens)\s*(.*)$/) { + my $indent = $1; + my $test = $2; + my $rest = rtrim($4); + if ($rest =~ /;$/) { + $fixed[$fixlinenr] = "\+$indent$test"; + fix_insert_line($fixlinenr + 1, "$indent\t$rest"); + } + } } } @@ -5204,14 +5839,18 @@ sub process { #CamelCase if ($var !~ /^$Constant$/ && $var =~ /[A-Z][a-z]|[a-z][A-Z]/ && +#Ignore some autogenerated defines and enum values + $var !~ /^(?:[A-Z]+_){1,5}[A-Z]{1,3}[a-z]/ && #Ignore Page<foo> variants $var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ && +#Ignore ETHTOOL_LINK_MODE_<foo> variants + $var !~ /^ETHTOOL_LINK_MODE_/ && #Ignore SI style variants like nS, mV and dB #(ie: max_uV, regulator_min_uA_show, RANGE_mA_VALUE) $var !~ /^(?:[a-z0-9_]*|[A-Z0-9_]*)?_?[a-z][A-Z](?:_[a-z0-9_]+|_[A-Z0-9_]+)?$/ && #Ignore some three character SI units explicitly, like MiB and KHz $var !~ /^(?:[a-z_]*?)_?(?:[KMGT]iB|[KMGT]?Hz)(?:_[a-z_]+)?$/) { - while ($var =~ m{($Ident)}g) { + while ($var =~ m{\b($Ident)}g) { my $word = $1; next if ($word !~ /[A-Z][a-z]|[a-z][A-Z]/); if ($check) { @@ -5299,9 +5938,9 @@ sub process { $dstat =~ s/\s*$//s; # Flatten any parentheses and braces - while ($dstat =~ s/\([^\(\)]*\)/1/ || - $dstat =~ s/\{[^\{\}]*\}/1/ || - $dstat =~ s/.\[[^\[\]]*\]/1/) + while ($dstat =~ s/\([^\(\)]*\)/1u/ || + $dstat =~ s/\{[^\{\}]*\}/1u/ || + $dstat =~ s/.\[[^\[\]]*\]/1u/) { } @@ -5341,7 +5980,9 @@ sub process { $dstat !~ /$exceptions/ && $dstat !~ /^\.$Ident\s*=/ && # .foo = $dstat !~ /^(?:\#\s*$Ident|\#\s*$Constant)\s*$/ && # stringification #foo + $dstat !~ /^case\b/ && # case ... $dstat !~ /^do\s*$Constant\s*while\s*$Constant;?$/ && # do {...} while (...); // do {...} while (...) + $dstat !~ /^while\s*$Constant\s*$Constant\s*$/ && # while (...) {...} $dstat !~ /^for\s*$Constant$/ && # for (...) $dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar() $dstat !~ /^do\s*{/ && # do {... @@ -5383,7 +6024,7 @@ sub process { next if ($arg =~ /\.\.\./); next if ($arg =~ /^type$/i); my $tmp_stmt = $define_stmt; - $tmp_stmt =~ s/\b(sizeof|typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; + $tmp_stmt =~ s/\b(__must_be_array|offsetof|sizeof|sizeof_field|__stringify|typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; $tmp_stmt =~ s/\#+\s*$arg\b//g; $tmp_stmt =~ s/\b$arg\s*\#\#//g; my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g; @@ -5412,6 +6053,9 @@ sub process { # check for line continuations outside of #defines, preprocessor #, and asm + } elsif ($realfile =~ m@/vmlinux.lds.h$@) { + $line =~ s/(\w+)/$maybe_linker_symbol{$1}++/ge; + #print "REAL: $realfile\nln: $line\nkeys:", sort keys %maybe_linker_symbol; } else { if ($prevline !~ /^..*\\$/ && $line !~ /^\+\s*\#.*\\$/ && # preprocessor @@ -5660,6 +6304,17 @@ sub process { "Prefer using '\"%s...\", __func__' to using '$context_function', this function's name, in a string\n" . $herecurr); } +# check for unnecessary function tracing like uses +# This does not use $logFunctions because there are many instances like +# 'dprintk(FOO, "%s()\n", __func__);' which do not match $logFunctions + if ($rawline =~ /^\+.*\([^"]*"$tracing_logging_tags{0,3}%s(?:\s*\(\s*\)\s*)?$tracing_logging_tags{0,3}(?:\\n)?"\s*,\s*__func__\s*\)\s*;/) { + if (WARN("TRACING_LOGGING", + "Unnecessary ftrace-like logging - prefer using ftrace\n" . $herecurr) && + $fix) { + fix_delete_line($fixlinenr, $rawline); + } + } + # check for spaces before a quoted newline if ($rawline =~ /^.*\".*\s\\n/) { if (WARN("QUOTED_WHITESPACE_BEFORE_NEWLINE", @@ -5671,7 +6326,8 @@ sub process { } # concatenated string without spaces between elements - if ($line =~ /$String[A-Za-z0-9_]/ || $line =~ /[A-Za-z0-9_]$String/) { + if ($line =~ /$String[A-Z_]/ || + ($line =~ /([A-Za-z0-9_]+)$String/ && $1 !~ /^[Lu]$/)) { if (CHK("CONCATENATED_STRING", "Concatenated strings should use spaces between elements\n" . $herecurr) && $fix) { @@ -5684,7 +6340,7 @@ sub process { } # uncoalesced string fragments - if ($line =~ /$String\s*"/) { + if ($line =~ /$String\s*[Lu]?"/) { if (WARN("STRING_FRAGMENTS", "Consecutive strings are generally better as a single string\n" . $herecurr) && $fix) { @@ -5806,6 +6462,28 @@ sub process { "Avoid logging continuation uses where feasible\n" . $herecurr); } +# check for unnecessary use of %h[xudi] and %hh[xudi] in logging functions + if (defined $stat && + $line =~ /\b$logFunctions\s*\(/ && + index($stat, '"') >= 0) { + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + my $stat_real = get_stat_real($linenr, $lc); + pos($stat_real) = index($stat_real, '"'); + while ($stat_real =~ /[^\"%]*(%[\#\d\.\*\-]*(h+)[idux])/g) { + my $pspec = $1; + my $h = $2; + my $lineoff = substr($stat_real, 0, $-[1]) =~ tr@\n@@; + if (WARN("UNNECESSARY_MODIFIER", + "Integer promotion: Using '$h' in '$pspec' is unnecessary\n" . "$here\n$stat_real\n") && + $fix && $fixed[$fixlinenr + $lineoff] =~ /^\+/) { + my $nspec = $pspec; + $nspec =~ s/h//g; + $fixed[$fixlinenr + $lineoff] =~ s/\Q$pspec\E/$nspec/; + } + } + } + # check for mask then right shift without a parentheses if ($perl_version_ok && $line =~ /$LvalOrFunc\s*\&\s*($LvalOrFunc)\s*>>/ && @@ -6052,50 +6730,68 @@ sub process { } } -# Check for __attribute__ packed, prefer __packed +# Check for compiler attributes if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*\bpacked\b/) { - WARN("PREFER_PACKED", - "__packed is preferred over __attribute__((packed))\n" . $herecurr); - } + $rawline =~ /\b__attribute__\s*\(\s*($balanced_parens)\s*\)/) { + my $attr = $1; + $attr =~ s/\s*\(\s*(.*)\)\s*/$1/; -# Check for __attribute__ aligned, prefer __aligned - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*aligned/) { - WARN("PREFER_ALIGNED", - "__aligned(size) is preferred over __attribute__((aligned(size)))\n" . $herecurr); - } + my %attr_list = ( + "alias" => "__alias", + "aligned" => "__aligned", + "always_inline" => "__always_inline", + "assume_aligned" => "__assume_aligned", + "cold" => "__cold", + "const" => "__attribute_const__", + "copy" => "__copy", + "designated_init" => "__designated_init", + "externally_visible" => "__visible", + "format" => "printf|scanf", + "gnu_inline" => "__gnu_inline", + "malloc" => "__malloc", + "mode" => "__mode", + "no_caller_saved_registers" => "__no_caller_saved_registers", + "noclone" => "__noclone", + "noinline" => "noinline", + "nonstring" => "__nonstring", + "noreturn" => "__noreturn", + "packed" => "__packed", + "pure" => "__pure", + "section" => "__section", + "used" => "__used", + "weak" => "__weak" + ); -# Check for __attribute__ section, prefer __section - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(.*_*section_*\s*\(\s*("[^"]*")/) { - my $old = substr($rawline, $-[1], $+[1] - $-[1]); - my $new = substr($old, 1, -1); - if (WARN("PREFER_SECTION", - "__section($new) is preferred over __attribute__((section($old)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*_*section_*\s*\(\s*\Q$old\E\s*\)\s*\)\s*\)/__section($new)/; + while ($attr =~ /\s*(\w+)\s*(${balanced_parens})?/g) { + my $orig_attr = $1; + my $params = ''; + $params = $2 if defined($2); + my $curr_attr = $orig_attr; + $curr_attr =~ s/^[\s_]+|[\s_]+$//g; + if (exists($attr_list{$curr_attr})) { + my $new = $attr_list{$curr_attr}; + if ($curr_attr eq "format" && $params) { + $params =~ /^\s*\(\s*(\w+)\s*,\s*(.*)/; + $new = "__$1\($2"; + } else { + $new = "$new$params"; + } + if (WARN("PREFER_DEFINED_ATTRIBUTE_MACRO", + "Prefer $new over __attribute__(($orig_attr$params))\n" . $herecurr) && + $fix) { + my $remove = "\Q$orig_attr\E" . '\s*' . "\Q$params\E" . '(?:\s*,\s*)?'; + $fixed[$fixlinenr] =~ s/$remove//; + $fixed[$fixlinenr] =~ s/\b__attribute__/$new __attribute__/; + $fixed[$fixlinenr] =~ s/\}\Q$new\E/} $new/; + $fixed[$fixlinenr] =~ s/ __attribute__\s*\(\s*\(\s*\)\s*\)//; + } + } } - } -# Check for __attribute__ format(printf, prefer __printf - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf/) { - if (WARN("PREFER_PRINTF", - "__printf(string-index, first-to-check) is preferred over __attribute__((format(printf, string-index, first-to-check)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*printf\s*,\s*(.*)\)\s*\)\s*\)/"__printf(" . trim($1) . ")"/ex; - - } - } - -# Check for __attribute__ format(scanf, prefer __scanf - if ($realfile !~ m@\binclude/uapi/@ && - $line =~ /\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\b/) { - if (WARN("PREFER_SCANF", - "__scanf(string-index, first-to-check) is preferred over __attribute__((format(scanf, string-index, first-to-check)))\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b__attribute__\s*\(\s*\(\s*format\s*\(\s*scanf\s*,\s*(.*)\)\s*\)\s*\)/"__scanf(" . trim($1) . ")"/ex; + # Check for __attribute__ unused, prefer __always_unused or __maybe_unused + if ($attr =~ /^_*unused/) { + WARN("PREFER_DEFINED_ATTRIBUTE_MACRO", + "__always_unused or __maybe_unused is preferred over __attribute__((__unused__))\n" . $herecurr); } } @@ -6131,18 +6827,18 @@ sub process { if ($line =~ /(\(\s*$C90_int_types\s*\)\s*)($Constant)\b/) { my $cast = $1; my $const = $2; + my $suffix = ""; + my $newconst = $const; + $newconst =~ s/${Int_type}$//; + $suffix .= 'U' if ($cast =~ /\bunsigned\b/); + if ($cast =~ /\blong\s+long\b/) { + $suffix .= 'LL'; + } elsif ($cast =~ /\blong\b/) { + $suffix .= 'L'; + } if (WARN("TYPECAST_INT_CONSTANT", - "Unnecessary typecast of c90 int constant\n" . $herecurr) && + "Unnecessary typecast of c90 int constant - '$cast$const' could be '$const$suffix'\n" . $herecurr) && $fix) { - my $suffix = ""; - my $newconst = $const; - $newconst =~ s/${Int_type}$//; - $suffix .= 'U' if ($cast =~ /\bunsigned\b/); - if ($cast =~ /\blong\s+long\b/) { - $suffix .= 'LL'; - } elsif ($cast =~ /\blong\b/) { - $suffix .= 'L'; - } $fixed[$fixlinenr] =~ s/\Q$cast\E$const\b/$newconst$suffix/; } } @@ -6202,9 +6898,11 @@ sub process { $specifier = $1; $extension = $2; $qualifier = $3; - if ($extension !~ /[SsBKRraEehMmIiUDdgVCbGNOxtf]/ || + if ($extension !~ /[4SsBKRraEehMmIiUDdgVCbGNOxtf]/ || ($extension eq "f" && - defined $qualifier && $qualifier !~ /^w/)) { + defined $qualifier && $qualifier !~ /^w/) || + ($extension eq "4" && + defined $qualifier && $qualifier !~ /^cc/)) { $bad_specifier = $specifier; last; } @@ -6218,15 +6916,19 @@ sub process { } if ($bad_specifier ne "") { my $stat_real = get_stat_real($linenr, $lc); + my $msg_level = \&WARN; my $ext_type = "Invalid"; my $use = ""; if ($bad_specifier =~ /p[Ff]/) { $use = " - use %pS instead"; $use =~ s/pS/ps/ if ($bad_specifier =~ /pf/); + } elsif ($bad_specifier =~ /pA/) { + $use = " - '%pA' is only intended to be used from Rust code"; + $msg_level = \&ERROR; } - WARN("VSPRINTF_POINTER_EXTENSION", - "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n"); + &{$msg_level}("VSPRINTF_POINTER_EXTENSION", + "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n"); } } } @@ -6291,6 +6993,24 @@ sub process { # } # } +# strcpy uses that should likely be strscpy + if ($line =~ /\bstrcpy\s*\(/) { + WARN("STRCPY", + "Prefer strscpy over strcpy - see: https://github.com/KSPP/linux/issues/88\n" . $herecurr); + } + +# strlcpy uses that should likely be strscpy + if ($line =~ /\bstrlcpy\s*\(/) { + WARN("STRLCPY", + "Prefer strscpy over strlcpy - see: https://github.com/KSPP/linux/issues/89\n" . $herecurr); + } + +# strncpy uses that should likely be strscpy or strscpy_pad + if ($line =~ /\bstrncpy\s*\(/) { + WARN("STRNCPY", + "Prefer strscpy, strscpy_pad, or __nonstring over strncpy - see: https://github.com/KSPP/linux/issues/90\n" . $herecurr); + } + # typecasts on min/max could be min_t/max_t if ($perl_version_ok && defined $stat && @@ -6395,6 +7115,21 @@ sub process { "arguments for function declarations should follow identifier\n" . $herecurr); } + } elsif ($realfile =~ /\.c$/ && defined $stat && + $stat =~ /^\+extern struct\s+(\w+)\s+(\w+)\[\];/) + { + my ($st_type, $st_name) = ($1, $2); + + for my $s (keys %maybe_linker_symbol) { + #print "Linker symbol? $st_name : $s\n"; + goto LIKELY_LINKER_SYMBOL + if $st_name =~ /$s/; + } + WARN("AVOID_EXTERNS", + "found a file-scoped extern type:$st_type name:$st_name in .c file\n" + . "is this a linker symbol ?\n" . $herecurr); + LIKELY_LINKER_SYMBOL: + } elsif ($realfile =~ /\.c$/ && defined $stat && $stat =~ /^.\s*extern\s+/) { @@ -6463,14 +7198,16 @@ sub process { "Prefer $3(sizeof(*$1)...) over $3($4...)\n" . $herecurr); } -# check for k[mz]alloc with multiplies that could be kmalloc_array/kcalloc +# check for (kv|k)[mz]alloc with multiplies that could be kmalloc_array/kvmalloc_array/kvcalloc/kcalloc if ($perl_version_ok && defined $stat && - $stat =~ /^\+\s*($Lval)\s*\=\s*(?:$balanced_parens)?\s*(k[mz]alloc)\s*\(\s*($FuncArg)\s*\*\s*($FuncArg)\s*,/) { + $stat =~ /^\+\s*($Lval)\s*\=\s*(?:$balanced_parens)?\s*((?:kv|k)[mz]alloc)\s*\(\s*($FuncArg)\s*\*\s*($FuncArg)\s*,/) { my $oldfunc = $3; my $a1 = $4; my $a2 = $10; my $newfunc = "kmalloc_array"; + $newfunc = "kvmalloc_array" if ($oldfunc eq "kvmalloc"); + $newfunc = "kvcalloc" if ($oldfunc eq "kvzalloc"); $newfunc = "kcalloc" if ($oldfunc eq "kzalloc"); my $r1 = $a1; my $r2 = $a2; @@ -6487,7 +7224,7 @@ sub process { "Prefer $newfunc over $oldfunc with multiply\n" . $herectx) && $cnt == 1 && $fix) { - $fixed[$fixlinenr] =~ s/\b($Lval)\s*\=\s*(?:$balanced_parens)?\s*(k[mz]alloc)\s*\(\s*($FuncArg)\s*\*\s*($FuncArg)/$1 . ' = ' . "$newfunc(" . trim($r1) . ', ' . trim($r2)/e; + $fixed[$fixlinenr] =~ s/\b($Lval)\s*\=\s*(?:$balanced_parens)?\s*((?:kv|k)[mz]alloc)\s*\(\s*($FuncArg)\s*\*\s*($FuncArg)/$1 . ' = ' . "$newfunc(" . trim($r1) . ', ' . trim($r2)/e; } } } @@ -6501,7 +7238,7 @@ sub process { } # check for alloc argument mismatch - if ($line =~ /\b(kcalloc|kmalloc_array)\s*\(\s*sizeof\b/) { + if ($line =~ /\b((?:devm_)?((?:k|kv)?(calloc|malloc_array)(?:_node)?))\s*\(\s*sizeof\b/) { WARN("ALLOC_ARRAY_ARGS", "$1 uses number as first arg, sizeof is generally wrong\n" . $herecurr); } @@ -6528,16 +7265,16 @@ sub process { } # check for IS_ENABLED() without CONFIG_<FOO> ($rawline for comments too) - if ($rawline =~ /\bIS_ENABLED\s*\(\s*(\w+)\s*\)/ && $1 !~ /^CONFIG_/) { + if ($rawline =~ /\bIS_ENABLED\s*\(\s*(\w+)\s*\)/ && $1 !~ /^${CONFIG_}/) { WARN("IS_ENABLED_CONFIG", - "IS_ENABLED($1) is normally used as IS_ENABLED(CONFIG_$1)\n" . $herecurr); + "IS_ENABLED($1) is normally used as IS_ENABLED(${CONFIG_}$1)\n" . $herecurr); } # check for #if defined CONFIG_<FOO> || defined CONFIG_<FOO>_MODULE - if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(CONFIG_[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) { + if ($line =~ /^\+\s*#\s*if\s+defined(?:\s*\(?\s*|\s+)(${CONFIG_}[A-Z_]+)\s*\)?\s*\|\|\s*defined(?:\s*\(?\s*|\s+)\1_MODULE\s*\)?\s*$/) { my $config = $1; if (WARN("PREFER_IS_ENABLED", - "Prefer IS_ENABLED(<FOO>) to CONFIG_<FOO> || CONFIG_<FOO>_MODULE\n" . $herecurr) && + "Prefer IS_ENABLED(<FOO>) to ${CONFIG_}<FOO> || ${CONFIG_}<FOO>_MODULE\n" . $herecurr) && $fix) { $fixed[$fixlinenr] = "\+#if IS_ENABLED($config)"; } @@ -6667,12 +7404,14 @@ sub process { # use of NR_CPUS is usually wrong # ignore definitions of NR_CPUS and usage to define arrays as likely right +# ignore designated initializers using NR_CPUS if ($line =~ /\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*if\b.*\bNR_CPUS\b/ && $line !~ /^.\s*\s*#\s*define\b.*\bNR_CPUS\b/ && $line !~ /^.\s*$Declare\s.*\[[^\]]*NR_CPUS[^\]]*\]/ && $line !~ /\[[^\]]*\.\.\.[^\]]*NR_CPUS[^\]]*\]/ && - $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/) + $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/ && + $line !~ /^.\s*\.\w+\s*=\s*.*\bNR_CPUS\b/) { WARN("NR_CPUS", "usage of NR_CPUS is often wrong - consider using cpu_possible(), num_possible_cpus(), for_each_possible_cpu(), etc\n" . $herecurr); @@ -6691,6 +7430,27 @@ sub process { "Using $1 should generally have parentheses around the comparison\n" . $herecurr); } +# return sysfs_emit(foo, fmt, ...) fmt without newline + if ($line =~ /\breturn\s+sysfs_emit\s*\(\s*$FuncArg\s*,\s*($String)/ && + substr($rawline, $-[6], $+[6] - $-[6]) !~ /\\n"$/) { + my $offset = $+[6] - 1; + if (WARN("SYSFS_EMIT", + "return sysfs_emit(...) formats should include a terminating newline\n" . $herecurr) && + $fix) { + substr($fixed[$fixlinenr], $offset, 0) = '\\n'; + } + } + +# check for array definition/declarations that should use flexible arrays instead + if ($sline =~ /^[\+ ]\s*\}(?:\s*__packed)?\s*;\s*$/ && + $prevline =~ /^\+\s*(?:\}(?:\s*__packed\s*)?|$Type)\s*$Ident\s*\[\s*(0|1)\s*\]\s*;\s*$/) { + if (ERROR("FLEXIBLE_ARRAY", + "Use C99 flexible arrays - see https://docs.kernel.org/process/deprecated.html#zero-length-and-one-element-arrays\n" . $hereprev) && + $1 == '0' && $fix) { + $fixed[$fixlinenr - 1] =~ s/\[\s*0\s*\]/[]/; + } + } + # nested likely/unlikely calls if ($line =~ /\b(?:(?:un)?likely)\s*\(\s*!?\s*(IS_ERR(?:_OR_NULL|_VALUE)?|WARN)/) { WARN("LIKELY_MISUSE", @@ -6708,10 +7468,28 @@ sub process { } } -# check for mutex_trylock_recursive usage - if ($line =~ /mutex_trylock_recursive/) { - ERROR("LOCKING", - "recursive locking is bad, do not use this ever.\n" . $herecurr); +# Complain about RCU Tasks Trace used outside of BPF (and of course, RCU). + our $rcu_trace_funcs = qr{(?x: + rcu_read_lock_trace | + rcu_read_lock_trace_held | + rcu_read_unlock_trace | + call_rcu_tasks_trace | + synchronize_rcu_tasks_trace | + rcu_barrier_tasks_trace | + rcu_request_urgent_qs_task + )}; + our $rcu_trace_paths = qr{(?x: + kernel/bpf/ | + include/linux/bpf | + net/bpf/ | + kernel/rcu/ | + include/linux/rcu + )}; + if ($line =~ /\b($rcu_trace_funcs)\s*\(/) { + if ($realfile !~ m{^$rcu_trace_paths}) { + WARN("RCU_TASKS_TRACE", + "use of RCU tasks trace is incorrect outside BPF or core RCU code\n" . $herecurr); + } } # check for lockdep_set_novalidate_class @@ -6855,6 +7633,13 @@ sub process { WARN("MODULE_LICENSE", "unknown module license " . $extracted_string . "\n" . $herecurr); } + if (!$file && $extracted_string eq '"GPL v2"') { + if (WARN("MODULE_LICENSE", + "Prefer \"GPL\" over \"GPL v2\" - see commit bf7fbeeae6db (\"module: Cure the MODULE_LICENSE \"GPL\" vs. \"GPL v2\" bogosity\")\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bMODULE_LICENSE\s*\(\s*"GPL v2"\s*\)/MODULE_LICENSE("GPL")/; + } + } } # check for sysctl duplicate constants @@ -6876,7 +7661,7 @@ sub process { exit(0); } - # This is not a patch, and we are are in 'no-patch' mode so + # This is not a patch, and we are in 'no-patch' mode so # just keep quiet. if (!$chk_patch && !$is_patch) { exit(0); @@ -6890,9 +7675,33 @@ sub process { if ($signoff == 0) { ERROR("MISSING_SIGN_OFF", "Missing Signed-off-by: line(s)\n"); - } elsif (!$authorsignoff) { - WARN("NO_AUTHOR_SIGN_OFF", - "Missing Signed-off-by: line by nominal patch author '$author'\n"); + } elsif ($authorsignoff != 1) { + # authorsignoff values: + # 0 -> missing sign off + # 1 -> sign off identical + # 2 -> names and addresses match, comments mismatch + # 3 -> addresses match, names different + # 4 -> names match, addresses different + # 5 -> names match, addresses excluding subaddress details (refer RFC 5233) match + + my $sob_msg = "'From: $author' != 'Signed-off-by: $author_sob'"; + + if ($authorsignoff == 0) { + ERROR("NO_AUTHOR_SIGN_OFF", + "Missing Signed-off-by: line by nominal patch author '$author'\n"); + } elsif ($authorsignoff == 2) { + CHK("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email comments mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 3) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email name mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 4) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email address mismatch: $sob_msg\n"); + } elsif ($authorsignoff == 5) { + WARN("FROM_SIGN_OFF_MISMATCH", + "From:/Signed-off-by: email subaddress mismatch: $sob_msg\n"); + } } } From 70db018a109f8ff0106a193be649d741389d1f69 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao <shaozhengchao@huawei.com> Date: Thu, 23 Nov 2023 15:13:14 +0800 Subject: [PATCH 13/13] UPSTREAM: ipv4: igmp: fix refcnt uaf issue when receiving igmp query packet [ Upstream commit e2b706c691905fe78468c361aaabc719d0a496f1 ] When I perform the following test operations: 1.ip link add br0 type bridge 2.brctl addif br0 eth0 3.ip addr add 239.0.0.1/32 dev eth0 4.ip addr add 239.0.0.1/32 dev br0 5.ip addr add 224.0.0.1/32 dev br0 6.while ((1)) do ifconfig br0 up ifconfig br0 down done 7.send IGMPv2 query packets to port eth0 continuously. For example, ./mausezahn ethX -c 0 "01 00 5e 00 00 01 00 72 19 88 aa 02 08 00 45 00 00 1c 00 01 00 00 01 02 0e 7f c0 a8 0a b7 e0 00 00 01 11 64 ee 9b 00 00 00 00" The preceding tests may trigger the refcnt uaf issue of the mc list. The stack is as follows: refcount_t: addition on 0; use-after-free. WARNING: CPU: 21 PID: 144 at lib/refcount.c:25 refcount_warn_saturate (lib/refcount.c:25) CPU: 21 PID: 144 Comm: ksoftirqd/21 Kdump: loaded Not tainted 6.7.0-rc1-next-20231117-dirty #80 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:refcount_warn_saturate (lib/refcount.c:25) RSP: 0018:ffffb68f00657910 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8a00c3bf96c0 RCX: ffff8a07b6160908 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff8a07b6160900 RBP: ffff8a00cba36862 R08: 0000000000000000 R09: 00000000ffff7fff R10: ffffb68f006577c0 R11: ffffffffb0fdcdc8 R12: ffff8a00c3bf9680 R13: ffff8a00c3bf96f0 R14: 0000000000000000 R15: ffff8a00d8766e00 FS: 0000000000000000(0000) GS:ffff8a07b6140000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f10b520b28 CR3: 000000039741a000 CR4: 00000000000006f0 Call Trace: <TASK> igmp_heard_query (net/ipv4/igmp.c:1068) igmp_rcv (net/ipv4/igmp.c:1132) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205) ip_local_deliver_finish (net/ipv4/ip_input.c:234) __netif_receive_skb_one_core (net/core/dev.c:5529) netif_receive_skb_internal (net/core/dev.c:5729) netif_receive_skb (net/core/dev.c:5788) br_handle_frame_finish (net/bridge/br_input.c:216) nf_hook_bridge_pre (net/bridge/br_input.c:294) __netif_receive_skb_core (net/core/dev.c:5423) __netif_receive_skb_list_core (net/core/dev.c:5606) __netif_receive_skb_list (net/core/dev.c:5674) netif_receive_skb_list_internal (net/core/dev.c:5764) napi_gro_receive (net/core/gro.c:609) e1000_clean_rx_irq (drivers/net/ethernet/intel/e1000/e1000_main.c:4467) e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3805) __napi_poll (net/core/dev.c:6533) net_rx_action (net/core/dev.c:6735) __do_softirq (kernel/softirq.c:554) run_ksoftirqd (kernel/softirq.c:913) smpboot_thread_fn (kernel/smpboot.c:164) kthread (kernel/kthread.c:388) ret_from_fork (arch/x86/kernel/process.c:153) ret_from_fork_asm (arch/x86/entry/entry_64.S:250) </TASK> The root causes are as follows: Thread A Thread B ... netif_receive_skb br_dev_stop ... br_multicast_leave_snoopers ... __ip_mc_dec_group ... __igmp_group_dropped igmp_rcv igmp_stop_timer igmp_heard_query //ref = 1 ip_ma_put igmp_mod_timer refcount_dec_and_test igmp_start_timer //ref = 0 ... refcount_inc //ref increases from 0 When the device receives an IGMPv2 Query message, it starts the timer immediately, regardless of whether the device is running. If the device is down and has left the multicast group, it will cause the mc list refcount uaf issue. Bug: 316932391 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org> (cherry picked from commit 94445d9583079e0ccc5dde1370076ff24800d86e) Signed-off-by: Lee Jones <joneslee@google.com> Change-Id: I277be2304e564994e05b981ccd6cd8cbb9dc85be --- net/ipv4/igmp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 88211a4b3855..c0f922c32a53 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -218,8 +218,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) int tv = prandom_u32() % max_delay; im->tm_running = 1; - if (!mod_timer(&im->timer, jiffies+tv+2)) - refcount_inc(&im->refcnt); + if (refcount_inc_not_zero(&im->refcnt)) { + if (mod_timer(&im->timer, jiffies + tv + 2)) + ip_ma_put(im); + } } static void igmp_gq_start_timer(struct in_device *in_dev)