From f15f29fd4779be8a418b66e9d52979bb6d6c2325 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 7 Sep 2023 08:22:33 +0200 Subject: netfilter: nf_tables: disallow rule removal from chain binding Chain binding only requires the rule addition/insertion command within the same transaction. Removal of rules from chain bindings within the same transaction makes no sense, userspace does not utilize this feature. Replace nft_chain_is_bound() check to nft_chain_binding() in rule deletion commands. Replace command implies a rule deletion, reject this command too. Rule flush command can also safely rely on this nft_chain_binding() check because unbound chains are not allowed since 62e1e94b246e ("netfilter: nf_tables: reject unbound chain set before commit phase"). Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e429ebba74b3..895c6e4fba97 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1432,7 +1432,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1477,7 +1477,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2910,6 +2910,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (nla[NFTA_CHAIN_HOOK]) { @@ -3971,6 +3974,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err_destroy_flow_rule; + } + err = nft_delrule(&ctx, old_rule); if (err < 0) goto err_destroy_flow_rule; @@ -4078,7 +4086,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -4112,7 +4120,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -11054,7 +11062,7 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; -- cgit v1.2.3 From 96b33300fba880ec0eafcf3d82486f3463b4b6da Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 5 Sep 2023 12:52:24 +0200 Subject: netfilter: nft_set_rbtree: use read spinlock to avoid datapath contention rbtree GC does not modify the datastructure, instead it collects expired elements and it enqueues a GC transaction. Use a read spinlock instead to avoid data contention while GC worker is running. Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_rbtree.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index f250b5399344..70491ba98dec 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -622,8 +622,7 @@ static void nft_rbtree_gc(struct work_struct *work) if (!gc) goto done; - write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); + read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { /* Ruleset has been updated, try later. */ @@ -673,8 +672,7 @@ dead_elem: gc = nft_trans_gc_catchall(gc, gc_seq); try_later: - write_seqcount_end(&priv->count); - write_unlock_bh(&priv->lock); + read_unlock_bh(&priv->lock); if (gc) nft_trans_gc_queue_async_done(gc); -- cgit v1.2.3 From 4a9e12ea7e70223555ec010bec9f711089ce96f6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 6 Sep 2023 15:07:53 +0200 Subject: netfilter: nft_set_pipapo: call nft_trans_gc_queue_sync() in catchall GC pipapo needs to enqueue GC transactions for catchall elements through nft_trans_gc_queue_sync(). Add nft_trans_gc_catchall_sync() and nft_trans_gc_catchall_async() to handle GC transaction queueing accordingly. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 5 +++-- net/netfilter/nf_tables_api.c | 22 +++++++++++++++++++--- net/netfilter/nft_set_hash.c | 2 +- net/netfilter/nft_set_pipapo.c | 2 +- net/netfilter/nft_set_rbtree.c | 2 +- 5 files changed, 25 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index dd40c75011d2..a4455f4995ab 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1700,8 +1700,9 @@ 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); -struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq); +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq); +struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc); void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 895c6e4fba97..7b59311931fb 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9613,8 +9613,9 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) call_rcu(&trans->rcu, nft_trans_gc_trans_free); } -struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq) +static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq, + bool sync) { struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; @@ -9630,7 +9631,11 @@ struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, nft_set_elem_dead(ext); dead_elem: - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (sync) + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + else + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) return NULL; @@ -9640,6 +9645,17 @@ dead_elem: return gc; } +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + return nft_trans_gc_catchall(gc, gc_seq, false); +} + +struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) +{ + return nft_trans_gc_catchall(gc, 0, true); +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 524763659f25..eca20dc60138 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -372,7 +372,7 @@ dead_elem: nft_trans_gc_elem_add(gc, he); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: /* catchall list iteration requires rcu read side lock. */ diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 6af9c9ed4b5c..10b89ac74476 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1610,7 +1610,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall(gc, 0); + gc = nft_trans_gc_catchall_sync(gc); if (gc) { nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 70491ba98dec..487572dcd614 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -669,7 +669,7 @@ dead_elem: nft_trans_gc_elem_add(gc, rbe); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: read_unlock_bh(&priv->lock); -- cgit v1.2.3 From 6d365eabce3c018a80f6e0379b17df2abb17405e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 6 Sep 2023 17:22:58 +0200 Subject: netfilter: nft_set_pipapo: stop GC iteration if GC transaction allocation fails nft_trans_gc_queue_sync() enqueues the GC transaction and it allocates a new one. If this allocation fails, then stop this GC sync run and retry later. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_pipapo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 10b89ac74476..c0dcc40de358 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1596,7 +1596,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (!gc) - break; + return; nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); -- cgit v1.2.3 From b079155faae94e9b3ab9337e82100a914ebb4e8d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 8 Sep 2023 01:39:43 +0200 Subject: netfilter: nft_set_hash: try later when GC hits EAGAIN on iteration Skip GC run if iterator rewinds to the beginning with EAGAIN, otherwise GC might collect the same element more than once. Fixes: f6c383b8c31a ("netfilter: nf_tables: adapt set backend to use GC transaction API") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_set_hash.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index eca20dc60138..2013de934cef 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -338,12 +338,9 @@ static void nft_rhash_gc(struct work_struct *work) while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) { - nft_trans_gc_destroy(gc); - gc = NULL; - goto try_later; - } - continue; + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; } /* Ruleset has been updated, try later. */ -- cgit v1.2.3 From 23a3bfd4ba7acd36abf52b78605f61b21bdac216 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 10 Sep 2023 19:04:45 +0200 Subject: netfilter: nf_tables: disallow element removal on anonymous sets Anonymous sets need to be populated once at creation and then they are bound to rule since 938154b93be8 ("netfilter: nf_tables: reject unbound anonymous set before commit phase"), otherwise transaction reports EINVAL. Userspace does not need to delete elements of anonymous sets that are not yet bound, reject this with EOPNOTSUPP. From flush command path, skip anonymous sets, they are expected to be bound already. Otherwise, EINVAL is hit at the end of this transaction for unbound sets. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7b59311931fb..c1e485aee763 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1446,8 +1446,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, set)) continue; - if (nft_set_is_anonymous(set) && - !list_empty(&set->bindings)) + if (nft_set_is_anonymous(set)) continue; err = nft_delset(ctx, set); @@ -7191,8 +7190,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && - (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) + if (nft_set_is_anonymous(set)) + return -EOPNOTSUPP; + + if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); -- cgit v1.2.3 From 4908d5af16676b9d2901830551c2af911e452524 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 12 Sep 2023 10:56:07 +0200 Subject: netfilter: conntrack: fix extension size table The size table is incorrect due to copypaste error, this reserves more size than needed. TSTAMP reserved 32 instead of 16 bytes. TIMEOUT reserved 16 instead of 8 bytes. Fixes: 5f31edc0676b ("netfilter: conntrack: move extension sizes into core") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_extend.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 0b513f7bf9f3..dd62cc12e775 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -40,10 +40,10 @@ static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = { [NF_CT_EXT_ECACHE] = sizeof(struct nf_conntrack_ecache), #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP - [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_acct), + [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_tstamp), #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT - [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_tstamp), + [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_timeout), #endif #ifdef CONFIG_NF_CONNTRACK_LABELS [NF_CT_EXT_LABELS] = sizeof(struct nf_conn_labels), -- cgit v1.2.3 From 7fb818f248cff996180b7cdcdcb86b6b4f6e44e2 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 13 Sep 2023 15:51:36 +0200 Subject: netfilter: nf_tables: Fix entries val in rule reset audit log The value in idx and the number of rules handled in that particular __nf_tables_dump_rules() call is not identical. The former is a cursor to pick up from if multiple netlink messages are needed, so its value is ever increasing. Fixing this is not just a matter of subtracting s_idx from it, though: When resetting rules in multiple chains, __nf_tables_dump_rules() is called for each and cb->args[0] is not adjusted in between. Introduce a dedicated counter to record the number of rules reset in this call in a less confusing way. While being at it, prevent the direct return upon buffer exhaustion: Any rules previously dumped into that skb would evade audit logging otherwise. Fixes: 9b5ba5c9c5109 ("netfilter: nf_tables: Unbreak audit log reset") Signed-off-by: Phil Sutter Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c1e485aee763..d819b4d42962 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3451,6 +3451,8 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int s_idx = cb->args[0]; + unsigned int entries = 0; + int ret = 0; u64 handle; prule = NULL; @@ -3473,9 +3475,11 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, handle, reset) < 0) - return 1; - + table, chain, rule, handle, reset) < 0) { + ret = 1; + break; + } + entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: prule = rule; @@ -3483,10 +3487,10 @@ cont_skip: (*idx)++; } - if (reset && *idx) - audit_log_rule_reset(table, cb->seq, *idx); + if (reset && entries) + audit_log_rule_reset(table, cb->seq, entries); - return 0; + return ret; } static int nf_tables_dump_rules(struct sk_buff *skb, -- cgit v1.2.3 From 75ad80ed88a182ab2ad5513e448cf07b403af5c3 Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Wed, 13 Sep 2023 09:39:05 +0300 Subject: net/core: Fix ETH_P_1588 flow dissector When a PTP ethernet raw frame with a size of more than 256 bytes followed by a 0xff pattern is sent to __skb_flow_dissect, nhoff value calculation is wrong. For example: hdr->message_length takes the wrong value (0xffff) and it does not replicate real header length. In this case, 'nhoff' value was overridden and the PTP header was badly dissected. This leads to a kernel crash. net/core: flow_dissector net/core flow dissector nhoff = 0x0000000e net/core flow dissector hdr->message_length = 0x0000ffff net/core flow dissector nhoff = 0x0001000d (u16 overflow) ... skb linear: 00000000: 00 a0 c9 00 00 00 00 a0 c9 00 00 00 88 skb frag: 00000000: f7 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Using the size of the ptp_header struct will allow the corrected calculation of the nhoff value. net/core flow dissector nhoff = 0x0000000e net/core flow dissector nhoff = 0x00000030 (sizeof ptp_header) ... skb linear: 00000000: 00 a0 c9 00 00 00 00 a0 c9 00 00 00 88 f7 ff ff skb linear: 00000010: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff skb linear: 00000020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff skb frag: 00000000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Kernel trace: [ 74.984279] ------------[ cut here ]------------ [ 74.989471] kernel BUG at include/linux/skbuff.h:2440! [ 74.995237] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [ 75.001098] CPU: 4 PID: 0 Comm: swapper/4 Tainted: G U 5.15.85-intel-ese-standard-lts #1 [ 75.011629] Hardware name: Intel Corporation A-Island (CPU:AlderLake)/A-Island (ID:06), BIOS SB_ADLP.01.01.00.01.03.008.D-6A9D9E73-dirty Mar 30 2023 [ 75.026507] RIP: 0010:eth_type_trans+0xd0/0x130 [ 75.031594] Code: 03 88 47 78 eb c7 8b 47 68 2b 47 6c 48 8b 97 c0 00 00 00 83 f8 01 7e 1b 48 85 d2 74 06 66 83 3a ff 74 09 b8 00 04 00 00 eb ab <0f> 0b b8 00 01 00 00 eb a2 48 85 ff 74 eb 48 8d 54 24 06 31 f6 b9 [ 75.052612] RSP: 0018:ffff9948c0228de0 EFLAGS: 00010297 [ 75.058473] RAX: 00000000000003f2 RBX: ffff8e47047dc300 RCX: 0000000000001003 [ 75.066462] RDX: ffff8e4e8c9ea040 RSI: ffff8e4704e0a000 RDI: ffff8e47047dc300 [ 75.074458] RBP: ffff8e4704e2acc0 R08: 00000000000003f3 R09: 0000000000000800 [ 75.082466] R10: 000000000000000d R11: ffff9948c0228dec R12: ffff8e4715e4e010 [ 75.090461] R13: ffff9948c0545018 R14: 0000000000000001 R15: 0000000000000800 [ 75.098464] FS: 0000000000000000(0000) GS:ffff8e4e8fb00000(0000) knlGS:0000000000000000 [ 75.107530] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 75.113982] CR2: 00007f5eb35934a0 CR3: 0000000150e0a002 CR4: 0000000000770ee0 [ 75.121980] PKRU: 55555554 [ 75.125035] Call Trace: [ 75.127792] [ 75.130063] ? eth_get_headlen+0xa4/0xc0 [ 75.134472] igc_process_skb_fields+0xcd/0x150 [ 75.139461] igc_poll+0xc80/0x17b0 [ 75.143272] __napi_poll+0x27/0x170 [ 75.147192] net_rx_action+0x234/0x280 [ 75.151409] __do_softirq+0xef/0x2f4 [ 75.155424] irq_exit_rcu+0xc7/0x110 [ 75.159432] common_interrupt+0xb8/0xd0 [ 75.163748] [ 75.166112] [ 75.168473] asm_common_interrupt+0x22/0x40 [ 75.173175] RIP: 0010:cpuidle_enter_state+0xe2/0x350 [ 75.178749] Code: 85 c0 0f 8f 04 02 00 00 31 ff e8 39 6c 67 ff 45 84 ff 74 12 9c 58 f6 c4 02 0f 85 50 02 00 00 31 ff e8 52 b0 6d ff fb 45 85 f6 <0f> 88 b1 00 00 00 49 63 ce 4c 2b 2c 24 48 89 c8 48 6b d1 68 48 c1 [ 75.199757] RSP: 0018:ffff9948c013bea8 EFLAGS: 00000202 [ 75.205614] RAX: ffff8e4e8fb00000 RBX: ffffb948bfd23900 RCX: 000000000000001f [ 75.213619] RDX: 0000000000000004 RSI: ffffffff94206161 RDI: ffffffff94212e20 [ 75.221620] RBP: 0000000000000004 R08: 000000117568973a R09: 0000000000000001 [ 75.229622] R10: 000000000000afc8 R11: ffff8e4e8fb29ce4 R12: ffffffff945ae980 [ 75.237628] R13: 000000117568973a R14: 0000000000000004 R15: 0000000000000000 [ 75.245635] ? cpuidle_enter_state+0xc7/0x350 [ 75.250518] cpuidle_enter+0x29/0x40 [ 75.254539] do_idle+0x1d9/0x260 [ 75.258166] cpu_startup_entry+0x19/0x20 [ 75.262582] secondary_startup_64_no_verify+0xc2/0xcb [ 75.268259] [ 75.270721] Modules linked in: 8021q snd_sof_pci_intel_tgl snd_sof_intel_hda_common tpm_crb snd_soc_hdac_hda snd_sof_intel_hda snd_hda_ext_core snd_sof_pci snd_sof snd_sof_xtensa_dsp snd_soc_acpi_intel_match snd_soc_acpi snd_soc_core snd_compress iTCO_wdt ac97_bus intel_pmc_bxt mei_hdcp iTCO_vendor_support snd_hda_codec_hdmi pmt_telemetry intel_pmc_core pmt_class snd_hda_intel x86_pkg_temp_thermal snd_intel_dspcfg snd_hda_codec snd_hda_core kvm_intel snd_pcm snd_timer kvm snd mei_me soundcore tpm_tis irqbypass i2c_i801 mei tpm_tis_core pcspkr intel_rapl_msr tpm i2c_smbus intel_pmt thermal sch_fq_codel uio uhid i915 drm_buddy video drm_display_helper drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm fuse configfs [ 75.342736] ---[ end trace 3785f9f360400e3a ]--- [ 75.347913] RIP: 0010:eth_type_trans+0xd0/0x130 [ 75.352984] Code: 03 88 47 78 eb c7 8b 47 68 2b 47 6c 48 8b 97 c0 00 00 00 83 f8 01 7e 1b 48 85 d2 74 06 66 83 3a ff 74 09 b8 00 04 00 00 eb ab <0f> 0b b8 00 01 00 00 eb a2 48 85 ff 74 eb 48 8d 54 24 06 31 f6 b9 [ 75.373994] RSP: 0018:ffff9948c0228de0 EFLAGS: 00010297 [ 75.379860] RAX: 00000000000003f2 RBX: ffff8e47047dc300 RCX: 0000000000001003 [ 75.387856] RDX: ffff8e4e8c9ea040 RSI: ffff8e4704e0a000 RDI: ffff8e47047dc300 [ 75.395864] RBP: ffff8e4704e2acc0 R08: 00000000000003f3 R09: 0000000000000800 [ 75.403857] R10: 000000000000000d R11: ffff9948c0228dec R12: ffff8e4715e4e010 [ 75.411863] R13: ffff9948c0545018 R14: 0000000000000001 R15: 0000000000000800 [ 75.419875] FS: 0000000000000000(0000) GS:ffff8e4e8fb00000(0000) knlGS:0000000000000000 [ 75.428946] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 75.435403] CR2: 00007f5eb35934a0 CR3: 0000000150e0a002 CR4: 0000000000770ee0 [ 75.443410] PKRU: 55555554 [ 75.446477] Kernel panic - not syncing: Fatal exception in interrupt [ 75.453738] Kernel Offset: 0x11c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 75.465794] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fixes: 4f1cc51f3488 ("net: flow_dissector: Parse PTP L2 packet header") Signed-off-by: Sasha Neftin Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b3b3af0e7844..272f09251343 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1446,7 +1446,7 @@ proto_again: break; } - nhoff += ntohs(hdr->message_length); + nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } -- cgit v1.2.3 From 837723b22a63cfbff584655b009b9d488d0e9087 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Wed, 30 Aug 2023 03:07:43 +0200 Subject: netfilter, bpf: Adjust timeouts of non-confirmed CTs in bpf_ct_insert_entry() bpf_nf testcase fails on s390x: bpf_skb_ct_lookup() cannot find the entry that was added by bpf_ct_insert_entry() within the same BPF function. The reason is that this entry is deleted by nf_ct_gc_expired(). The CT timeout starts ticking after the CT confirmation; therefore nf_conn.timeout is initially set to the timeout value, and __nf_conntrack_confirm() sets it to the deadline value. bpf_ct_insert_entry() sets IPS_CONFIRMED_BIT, but does not adjust the timeout, making its value meaningless and causing false positives. Fix the problem by making bpf_ct_insert_entry() adjust the timeout, like __nf_conntrack_confirm(). Fixes: 2cdaa3eefed8 ("netfilter: conntrack: restore IPS_CONFIRMED out of nf_conntrack_hash_check_insert()") Signed-off-by: Ilya Leoshkevich Signed-off-by: Daniel Borkmann Cc: Florian Westphal Link: https://lore.kernel.org/bpf/20230830011128.1415752-3-iii@linux.ibm.com Signed-off-by: Alexei Starovoitov --- net/netfilter/nf_conntrack_bpf.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index c7a6114091ae..b21799d468d2 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -381,6 +381,8 @@ __bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) struct nf_conn *nfct = (struct nf_conn *)nfct_i; int err; + if (!nf_ct_is_confirmed(nfct)) + nfct->timeout += nfct_time_stamp; nfct->status |= IPS_CONFIRMED; err = nf_conntrack_hash_check_insert(nfct); if (err < 0) { -- cgit v1.2.3 From aabb4af9bb29f8532e19c872b48ad1e7fd208617 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 13 Sep 2023 14:09:57 +0300 Subject: net: core: Use the bitmap API to allocate bitmaps Use bitmap_zalloc() and bitmap_free() instead of hand-writing them. It is less verbose and it improves the type checking and semantic. While at it, add missing header inclusion (should be bitops.h, but with the above change it becomes bitmap.h). Suggested-by: Sergey Ryazanov Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230911154534.4174265-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Przemek Kitszel Signed-off-by: David S. Miller --- net/core/dev.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index ccff2b6ef958..85df22f05c38 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -69,7 +69,7 @@ */ #include -#include +#include #include #include #include @@ -1080,7 +1080,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -EINVAL; /* Use one page as a bit array of possible slots */ - inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC); + inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); if (!inuse) return -ENOMEM; @@ -1109,7 +1109,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } i = find_first_zero_bit(inuse, max_netdevices); - free_page((unsigned long) inuse); + bitmap_free(inuse); } snprintf(buf, IFNAMSIZ, name, i); -- cgit v1.2.3 From 0113d9c9d1ccc07f5a3710dac4aa24b6d711278c Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Thu, 14 Sep 2023 22:12:57 -0700 Subject: ipv4: fix null-deref in ipv4_link_failure Currently, we assume the skb is associated with a device before calling __ip_options_compile, which is not always the case if it is re-routed by ipvs. When skb->dev is NULL, dev_net(skb->dev) will become null-dereference. This patch adds a check for the edge case and switch to use the net_device from the rtable when skb->dev is NULL. Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure") Suggested-by: David Ahern Signed-off-by: Kyle Zeng Cc: Stephen Suryaputra Cc: Vadim Fedorenko Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/route.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 66f419e7f9a7..a57062283219 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1213,6 +1213,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1230,7 +1231,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) -- cgit v1.2.3 From 3780bb29311eccb7a1c9641032a112eed237f7e3 Mon Sep 17 00:00:00 2001 From: Johnathan Mantey Date: Fri, 15 Sep 2023 09:12:35 -0700 Subject: ncsi: Propagate carrier gain/loss events to the NCSI controller Report the carrier/no-carrier state for the network interface shared between the BMC and the passthrough channel. Without this functionality the BMC is unable to reconfigure the NIC in the event of a re-cabling to a different subnet. Signed-off-by: Johnathan Mantey Signed-off-by: David S. Miller --- net/ncsi/ncsi-aen.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net') diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 62fb1031763d..f8854bff286c 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -89,6 +89,11 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, if ((had_link == has_link) || chained) return 0; + if (had_link) + netif_carrier_off(ndp->ndev.dev); + else + netif_carrier_on(ndp->ndev.dev); + if (!ndp->multi_package && !nc->package->multi_channel) { if (had_link) { ndp->flags |= NCSI_DEV_RESHUFFLE; -- cgit v1.2.3 From 6af289746a636f71f4c0535a9801774118486c7a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Sep 2023 19:00:35 +0000 Subject: dccp: fix dccp_v4_err()/dccp_v6_err() again dh->dccph_x is the 9th byte (offset 8) in "struct dccp_hdr", not in the "byte 7" as Jann claimed. We need to make sure the ICMP messages are big enough, using more standard ways (no more assumptions). syzbot reported: BUG: KMSAN: uninit-value in pskb_may_pull_reason include/linux/skbuff.h:2667 [inline] BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2681 [inline] BUG: KMSAN: uninit-value in dccp_v6_err+0x426/0x1aa0 net/dccp/ipv6.c:94 pskb_may_pull_reason include/linux/skbuff.h:2667 [inline] pskb_may_pull include/linux/skbuff.h:2681 [inline] dccp_v6_err+0x426/0x1aa0 net/dccp/ipv6.c:94 icmpv6_notify+0x4c7/0x880 net/ipv6/icmp.c:867 icmpv6_rcv+0x19d5/0x30d0 ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438 ip6_input_finish net/ipv6/ip6_input.c:483 [inline] NF_HOOK include/linux/netfilter.h:304 [inline] ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492 ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586 dst_input include/net/dst.h:468 [inline] ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:304 [inline] ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310 __netif_receive_skb_one_core net/core/dev.c:5523 [inline] __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5637 netif_receive_skb_internal net/core/dev.c:5723 [inline] netif_receive_skb+0x58/0x660 net/core/dev.c:5782 tun_rx_batched+0x83b/0x920 tun_get_user+0x564c/0x6940 drivers/net/tun.c:2002 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:1985 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x8ef/0x15c0 fs/read_write.c:584 ksys_write+0x20f/0x4c0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12f/0xb70 mm/slab.h:767 slab_alloc_node mm/slub.c:3478 [inline] kmem_cache_alloc_node+0x577/0xa80 mm/slub.c:3523 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:559 __alloc_skb+0x318/0x740 net/core/skbuff.c:650 alloc_skb include/linux/skbuff.h:1286 [inline] alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6313 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2795 tun_alloc_skb drivers/net/tun.c:1531 [inline] tun_get_user+0x23cf/0x6940 drivers/net/tun.c:1846 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:1985 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x8ef/0x15c0 fs/read_write.c:584 ksys_write+0x20f/0x4c0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd CPU: 0 PID: 4995 Comm: syz-executor153 Not tainted 6.6.0-rc1-syzkaller-00014-ga747acc0b752 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/04/2023 Fixes: 977ad86c2a1b ("dccp: Fix out of bounds access in DCCP error handler") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Jann Horn Reviewed-by: Jann Horn Signed-off-by: David S. Miller --- net/dccp/ipv4.c | 9 ++------- net/dccp/ipv6.c | 9 ++------- 2 files changed, 4 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8f56e8723c73..69453b936bd5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -254,13 +254,8 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 33f6ccf6ba77..c693a570682f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -83,13 +83,8 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmpv6_notify()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; -- cgit v1.2.3 From 295de650d3aaf9e50258465c5f1c84b465d836f6 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Fri, 15 Sep 2023 20:10:02 +0200 Subject: net: hsr: Properly parse HSRv1 supervisor frames. While adding support for parsing the redbox supervision frames, the author added `pull_size' and `total_pull_size' to track the amount of bytes that were pulled from the skb during while parsing the skb so it can be reverted/ pushed back at the end. In the process probably copy&paste error occurred and for the HSRv1 case the ethhdr was used instead of the hsr_tag. Later the hsr_tag was used instead of hsr_sup_tag. The later error didn't matter because both structs have the size so HSRv0 was still working. It broke however HSRv1 parsing because struct ethhdr is larger than struct hsr_tag. Reinstate the old pulling flow and pull first ethhdr, hsr_tag in v1 case followed by hsr_sup_tag. [bigeasy: commit message] Fixes: eafaa88b3eb7 ("net: hsr: Add support for redbox supervision frames")' Suggested-by: Tristram.Ha@microchip.com Signed-off-by: Lukasz Majewski Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- net/hsr/hsr_framereg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index b77f1189d19d..6d14d935ee82 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -288,13 +288,13 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) /* And leave the HSR tag. */ if (ethhdr->h_proto == htons(ETH_P_HSR)) { - pull_size = sizeof(struct ethhdr); + pull_size = sizeof(struct hsr_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; } /* And leave the HSR sup tag. */ - pull_size = sizeof(struct hsr_tag); + pull_size = sizeof(struct hsr_sup_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; -- cgit v1.2.3 From fbd825fcd7dd4c11d4c48c3d0adc248a4a0ce90b Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 15 Sep 2023 20:10:03 +0200 Subject: net: hsr: Add __packed to struct hsr_sup_tlv. Struct hsr_sup_tlv describes HW layout and therefore it needs a __packed attribute to ensure the compiler does not add any padding. Due to the size and __packed attribute of the structs that use hsr_sup_tlv it has no functional impact. Add __packed to struct hsr_sup_tlv. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- net/hsr/hsr_main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 6851e33df7d1..18e01791ad79 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -83,7 +83,7 @@ struct hsr_vlan_ethhdr { struct hsr_sup_tlv { u8 HSR_TLV_type; u8 HSR_TLV_length; -}; +} __packed; /* HSR/PRP Supervision Frame data types. * Field names as defined in the IEC:2010 standard for HSR. -- cgit v1.2.3 From 6bec041147a2a64a490d1f813e8a004443061b38 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:45 +0200 Subject: mptcp: fix bogus receive window shrinkage with multiple subflows In case multiple subflows race to update the mptcp-level receive window, the subflow losing the race should use the window value provided by the "winning" subflow to update it's own tcp-level rcv_wnd. To such goal, the current code bogusly uses the mptcp-level rcv_wnd value as observed before the update attempt. On unlucky circumstances that may lead to TCP-level window shrinkage, and stall the other end. Address the issue feeding to the rcv wnd update the correct value. Fixes: f3589be0c420 ("mptcp: never shrink offered window") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/427 Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/options.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c254accb14de..cd15ec73073e 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1269,12 +1269,13 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) if (rcv_wnd == rcv_wnd_old) break; - if (before64(rcv_wnd_new, rcv_wnd)) { + + rcv_wnd_old = rcv_wnd; + if (before64(rcv_wnd_new, rcv_wnd_old)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE); goto raise_win; } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); - rcv_wnd_old = rcv_wnd; } return; } -- cgit v1.2.3 From d5fbeff1ab812b6c473b6924bee8748469462e2c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:46 +0200 Subject: mptcp: move __mptcp_error_report in protocol.c This will simplify the next patch ("mptcp: process pending subflow error on close"). No functional change intended. Cc: stable@vger.kernel.org # v5.12+ Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 36 ++++++++++++++++++++++++++++++++++++ net/mptcp/subflow.c | 36 ------------------------------------ 2 files changed, 36 insertions(+), 36 deletions(-) (limited to 'net') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a7fc16f5175d..915860027b1a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -770,6 +770,42 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) return moved; } +void __mptcp_error_report(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int err = sock_error(ssk); + int ssk_state; + + if (!err) + continue; + + /* only propagate errors on fallen-back sockets or + * on MPC connect + */ + if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) + continue; + + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); + WRITE_ONCE(sk->sk_err, -err); + + /* This barrier is coupled with smp_rmb() in mptcp_poll() */ + smp_wmb(); + sk_error_report(sk); + break; + } +} + /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9bf3c7bc1762..2f40c23fdb0d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1362,42 +1362,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } -void __mptcp_error_report(struct sock *sk) -{ - struct mptcp_subflow_context *subflow; - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int err = sock_error(ssk); - int ssk_state; - - if (!err) - continue; - - /* only propagate errors on fallen-back sockets or - * on MPC connect - */ - if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) - continue; - - /* We need to propagate only transition to CLOSE state. - * Orphaned socket will see such state change via - * subflow_sched_work_if_closed() and that path will properly - * destroy the msk as needed. - */ - ssk_state = inet_sk_state_load(ssk); - if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); - WRITE_ONCE(sk->sk_err, -err); - - /* This barrier is coupled with smp_rmb() in mptcp_poll() */ - smp_wmb(); - sk_error_report(sk); - break; - } -} - static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; -- cgit v1.2.3 From 9f1a98813b4b686482e5ef3c9d998581cace0ba6 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:47 +0200 Subject: mptcp: process pending subflow error on close On incoming TCP reset, subflow closing could happen before error propagation. That in turn could cause the socket error being ignored, and a missing socket state transition, as reported by Daire-Byrne. Address the issues explicitly checking for subflow socket error at close time. To avoid code duplication, factor-out of __mptcp_error_report() a new helper implementing the relevant bits. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/429 Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 63 ++++++++++++++++++++++++++++------------------------ 1 file changed, 34 insertions(+), 29 deletions(-) (limited to 'net') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 915860027b1a..1c96b8da71df 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -770,40 +770,44 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) return moved; } -void __mptcp_error_report(struct sock *sk) +static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) { - struct mptcp_subflow_context *subflow; - struct mptcp_sock *msk = mptcp_sk(sk); + int err = sock_error(ssk); + int ssk_state; - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int err = sock_error(ssk); - int ssk_state; + if (!err) + return false; - if (!err) - continue; + /* only propagate errors on fallen-back sockets or + * on MPC connect + */ + if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) + return false; - /* only propagate errors on fallen-back sockets or - * on MPC connect - */ - if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) - continue; + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); + WRITE_ONCE(sk->sk_err, -err); - /* We need to propagate only transition to CLOSE state. - * Orphaned socket will see such state change via - * subflow_sched_work_if_closed() and that path will properly - * destroy the msk as needed. - */ - ssk_state = inet_sk_state_load(ssk); - if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); - WRITE_ONCE(sk->sk_err, -err); - - /* This barrier is coupled with smp_rmb() in mptcp_poll() */ - smp_wmb(); - sk_error_report(sk); - break; - } + /* This barrier is coupled with smp_rmb() in mptcp_poll() */ + smp_wmb(); + sk_error_report(sk); + return true; +} + +void __mptcp_error_report(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) + if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow))) + break; } /* In most cases we will be able to lock the mptcp socket. If its already @@ -2428,6 +2432,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } out_release: + __mptcp_subflow_error_report(sk, ssk); release_sock(ssk); sock_put(ssk); -- cgit v1.2.3 From f6909dc1c1f4452879278128012da6c76bc186a5 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:48 +0200 Subject: mptcp: rename timer related helper to less confusing names The msk socket uses to different timeout to track close related events and retransmissions. The existing helpers do not indicate clearly which timer they actually touch, making the related code quite confusing. Change the existing helpers name to avoid such confusion. No functional change intended. This patch is linked to the next one ("mptcp: fix dangling connection hang-up"). The two patches are supposed to be backported together. Cc: stable@vger.kernel.org # v5.11+ Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 42 +++++++++++++++++++++--------------------- net/mptcp/protocol.h | 2 +- net/mptcp/subflow.c | 2 +- 3 files changed, 23 insertions(+), 23 deletions(-) (limited to 'net') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1c96b8da71df..c8f38f303a90 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -405,7 +405,7 @@ drop: return false; } -static void mptcp_stop_timer(struct sock *sk) +static void mptcp_stop_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -911,12 +911,12 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list } } -static bool mptcp_timer_pending(struct sock *sk) +static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); } -static void mptcp_reset_timer(struct sock *sk) +static void mptcp_reset_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; @@ -1050,10 +1050,10 @@ static void __mptcp_clean_una(struct sock *sk) out: if (snd_una == READ_ONCE(msk->snd_nxt) && snd_una == READ_ONCE(msk->write_seq)) { - if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) - mptcp_stop_timer(sk); + if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) + mptcp_stop_rtx_timer(sk); } else { - mptcp_reset_timer(sk); + mptcp_reset_rtx_timer(sk); } } @@ -1626,8 +1626,8 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) mptcp_push_release(ssk, &info); /* ensure the rtx timer is running */ - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (do_check_data_fin) mptcp_check_send_data_fin(sk); } @@ -1690,8 +1690,8 @@ out: if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) @@ -2260,7 +2260,7 @@ static void mptcp_retransmit_timer(struct timer_list *t) sock_put(sk); } -static void mptcp_timeout_timer(struct timer_list *t) +static void mptcp_tout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); @@ -2629,14 +2629,14 @@ static void __mptcp_retrans(struct sock *sk) reset_timer: mptcp_check_and_set_pending(sk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout) +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; @@ -2669,7 +2669,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); - mptcp_reset_timeout(msk, 0); + mptcp_reset_tout_timer(msk, 0); } static void mptcp_do_fastclose(struct sock *sk) @@ -2758,7 +2758,7 @@ static void __mptcp_init_sock(struct sock *sk) /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); - timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); + timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) @@ -2849,8 +2849,8 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } break; } @@ -2933,7 +2933,7 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); msk->pm.status = 0; mptcp_release_sched(msk); @@ -3053,7 +3053,7 @@ cleanup: __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - mptcp_reset_timeout(msk, 0); + mptcp_reset_tout_timer(msk, 0); } return do_cancel_work; @@ -3116,7 +3116,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); if (msk->token) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7254b3562575..5e2026815c8e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -718,7 +718,7 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout); +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 2f40c23fdb0d..433f290984c8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1226,7 +1226,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) WRITE_ONCE(subflow->fail_tout, fail_tout); tcp_send_ack(ssk); - mptcp_reset_timeout(msk, subflow->fail_tout); + mptcp_reset_tout_timer(msk, subflow->fail_tout); } static bool subflow_check_data_avail(struct sock *ssk) -- cgit v1.2.3 From 27e5ccc2d5a50ed61bb73153edb1066104b108b3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 16 Sep 2023 12:52:49 +0200 Subject: mptcp: fix dangling connection hang-up According to RFC 8684 section 3.3: A connection is not closed unless [...] or an implementation-specific connection-level send timeout. Currently the MPTCP protocol does not implement such timeout, and connection timing-out at the TCP-level never move to close state. Introduces a catch-up condition at subflow close time to move the MPTCP socket to close, too. That additionally allows removing similar existing inside the worker. Finally, allow some additional timeout for plain ESTABLISHED mptcp sockets, as the protocol allows creating new subflows even at that point and making the connection functional again. This issue is actually present since the beginning, but it is basically impossible to solve without a long chain of functional pre-requisites topped by commit bbd49d114d57 ("mptcp: consolidate transition to TCP_CLOSE in mptcp_do_fastclose()"). When backporting this current patch, please also backport this other commit as well. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/430 Fixes: e16163b6e2b7 ("mptcp: refactor shutdown and close") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 86 +++++++++++++++++++++++++--------------------------- net/mptcp/protocol.h | 22 ++++++++++++++ net/mptcp/subflow.c | 1 + 3 files changed, 65 insertions(+), 44 deletions(-) (limited to 'net') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c8f38f303a90..e252539b1e19 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -892,6 +892,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); + mptcp_stop_tout_timer(sk); return true; } @@ -2369,18 +2370,14 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, bool dispose_it, need_push = false; /* If the first subflow moved to a close state before accept, e.g. due - * to an incoming reset, mptcp either: - * - if either the subflow or the msk are dead, destroy the context - * (the subflow socket is deleted by inet_child_forget) and the msk - * - otherwise do nothing at the moment and take action at accept and/or - * listener shutdown - user-space must be able to accept() the closed - * socket. + * to an incoming reset or listener shutdown, the subflow socket is + * already deleted by inet_child_forget() and the mptcp socket can't + * survive too. */ - if (msk->in_accept_queue && msk->first == ssk) { - if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) - return; - + if (msk->in_accept_queue && msk->first == ssk && + (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ + mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1)); sock_set_flag(sk, SOCK_DEAD); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); @@ -2443,6 +2440,22 @@ out_release: out: if (need_push) __mptcp_push_pending(sk, 0); + + /* Catch every 'all subflows closed' scenario, including peers silently + * closing them, e.g. due to timeout. + * For established sockets, allow an additional timeout before closing, + * as the protocol can still create more subflows. + */ + if (list_is_singular(&msk->conn_list) && msk->first && + inet_sk_state_load(msk->first) == TCP_CLOSE) { + if (sk->sk_state != TCP_ESTABLISHED || + msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_close_wake_up(sk); + } else { + mptcp_start_tout_timer(sk); + } + } } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, @@ -2486,23 +2499,14 @@ static void __mptcp_close_subflow(struct sock *sk) } -static bool mptcp_should_close(const struct sock *sk) +static bool mptcp_close_tout_expired(const struct sock *sk) { - s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp; - struct mptcp_subflow_context *subflow; - - if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue) - return true; + if (!inet_csk(sk)->icsk_mtup.probe_timestamp || + sk->sk_state == TCP_CLOSE) + return false; - /* if all subflows are in closed status don't bother with additional - * timeout - */ - mptcp_for_each_subflow(mptcp_sk(sk), subflow) { - if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) != - TCP_CLOSE) - return false; - } - return true; + return time_after32(tcp_jiffies32, + inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN); } static void mptcp_check_fastclose(struct mptcp_sock *msk) @@ -2641,15 +2645,16 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; - if (!fail_tout && !sock_flag(sk, SOCK_DEAD)) + if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; - close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN; + close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + + TCP_TIMEWAIT_LEN; /* the close timeout takes precedence on the fail one, and here at least one of * them is active */ - timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout; + timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; sk_reset_timer(sk, &sk->sk_timer, timeout); } @@ -2668,8 +2673,6 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) mptcp_subflow_reset(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); - - mptcp_reset_tout_timer(msk, 0); } static void mptcp_do_fastclose(struct sock *sk) @@ -2706,18 +2709,14 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(sk); - /* There is no point in keeping around an orphaned sk timedout or - * closed, but we need the msk around to reply to incoming DATA_FIN, - * even if it is orphaned and in FIN_WAIT2 state - */ - if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_should_close(sk)) - mptcp_do_fastclose(sk); + if (mptcp_close_tout_expired(sk)) { + mptcp_do_fastclose(sk); + mptcp_close_wake_up(sk); + } - if (sk->sk_state == TCP_CLOSE) { - __mptcp_destroy_sock(sk); - goto unlock; - } + if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) { + __mptcp_destroy_sock(sk); + goto unlock; } if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) @@ -3016,7 +3015,6 @@ bool __mptcp_close(struct sock *sk, long timeout) cleanup: /* orphan all the subflows */ - inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); @@ -3053,7 +3051,7 @@ cleanup: __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - mptcp_reset_tout_timer(msk, 0); + mptcp_start_tout_timer(sk); } return do_cancel_work; @@ -3117,7 +3115,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) inet_sk_state_store(sk, TCP_CLOSE); mptcp_stop_rtx_timer(sk); - sk_stop_timer(sk, &sk->sk_timer); + mptcp_stop_tout_timer(sk); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 5e2026815c8e..ed61d6850cce 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -719,6 +719,28 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); + +static inline void mptcp_stop_tout_timer(struct sock *sk) +{ + if (!inet_csk(sk)->icsk_mtup.probe_timestamp) + return; + + sk_stop_timer(sk, &sk->sk_timer); + inet_csk(sk)->icsk_mtup.probe_timestamp = 0; +} + +static inline void mptcp_set_close_tout(struct sock *sk, unsigned long tout) +{ + /* avoid 0 timestamp, as that means no close timeout */ + inet_csk(sk)->icsk_mtup.probe_timestamp = tout ? : 1; +} + +static inline void mptcp_start_tout_timer(struct sock *sk) +{ + mptcp_set_close_tout(sk, tcp_jiffies32); + mptcp_reset_tout_timer(mptcp_sk(sk), 0); +} + static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 433f290984c8..918c1a235790 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1552,6 +1552,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, mptcp_sock_graft(ssk, sk->sk_socket); iput(SOCK_INODE(sf)); WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_stop_tout_timer(sk); return 0; failed_unlink: -- cgit v1.2.3 From 71273c46a34823e54af7828df67e5983ba85d6c2 Mon Sep 17 00:00:00 2001 From: Peter Lafreniere Date: Sun, 17 Sep 2023 15:30:21 +0000 Subject: ax25: Kconfig: Update link for linux-ax25.org http://linux-ax25.org has been down for nearly a year. Its official replacement is https://linux-ax25.in-berlin.de. Change all references to the old site in the ax25 Kconfig to its replacement. Link: https://marc.info/?m=166792551600315 Signed-off-by: Peter Lafreniere Signed-off-by: David S. Miller --- net/ax25/Kconfig | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/ax25/Kconfig b/net/ax25/Kconfig index d3a9843a043d..fdb666607f10 100644 --- a/net/ax25/Kconfig +++ b/net/ax25/Kconfig @@ -10,7 +10,7 @@ menuconfig HAMRADIO If you want to connect your Linux box to an amateur radio, answer Y here. You want to read and more specifically about AX.25 on Linux - . + . Note that the answer to this question won't directly affect the kernel: saying N will just cause the configurator to skip all @@ -61,7 +61,7 @@ config AX25_DAMA_SLAVE configuration. Linux cannot yet act as a DAMA server. This option only compiles DAMA slave support into the kernel. It still needs to be enabled at runtime. For more about DAMA see - . If unsure, say Y. + . If unsure, say Y. # placeholder until implemented config AX25_DAMA_MASTER @@ -87,9 +87,9 @@ config NETROM A comprehensive listing of all the software for Linux amateur radio users as well as information about how to configure an AX.25 port is contained in the Linux Ham Wiki, available from - . You also might want to check out the - file . More information about - digital amateur radio in general is on the WWW at + . You also might want to check out + the file . More information + about digital amateur radio in general is on the WWW at . To compile this driver as a module, choose M here: the @@ -106,9 +106,9 @@ config ROSE A comprehensive listing of all the software for Linux amateur radio users as well as information about how to configure an AX.25 port is contained in the Linux Ham Wiki, available from - . You also might want to check out the - file . More information about - digital amateur radio in general is on the WWW at + . You also might want to check out + the file . More information + about digital amateur radio in general is on the WWW at . To compile this driver as a module, choose M here: the -- cgit v1.2.3 From 44bdb313da57322c9b3c108eb66981c6ec6509f4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 18 Sep 2023 09:13:51 +0000 Subject: net: bridge: use DEV_STATS_INC() syzbot/KCSAN reported data-races in br_handle_frame_finish() [1] This function can run from multiple cpus without mutual exclusion. Adopt SMP safe DEV_STATS_INC() to update dev->stats fields. Handles updates to dev->stats.tx_dropped while we are at it. [1] BUG: KCSAN: data-race in br_handle_frame_finish / br_handle_frame_finish read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 1: br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189 br_nf_hook_thresh+0x1ed/0x220 br_nf_pre_routing_finish_ipv6+0x50f/0x540 NF_HOOK include/linux/netfilter.h:304 [inline] br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178 br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508 nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline] nf_hook_bridge_pre net/bridge/br_input.c:272 [inline] br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417 __netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417 __netif_receive_skb_one_core net/core/dev.c:5521 [inline] __netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637 process_backlog+0x21f/0x380 net/core/dev.c:5965 __napi_poll+0x60/0x3b0 net/core/dev.c:6527 napi_poll net/core/dev.c:6594 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6727 __do_softirq+0xc1/0x265 kernel/softirq.c:553 run_ksoftirqd+0x17/0x20 kernel/softirq.c:921 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:388 ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 0: br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189 br_nf_hook_thresh+0x1ed/0x220 br_nf_pre_routing_finish_ipv6+0x50f/0x540 NF_HOOK include/linux/netfilter.h:304 [inline] br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178 br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508 nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline] nf_hook_bridge_pre net/bridge/br_input.c:272 [inline] br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417 __netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417 __netif_receive_skb_one_core net/core/dev.c:5521 [inline] __netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637 process_backlog+0x21f/0x380 net/core/dev.c:5965 __napi_poll+0x60/0x3b0 net/core/dev.c:6527 napi_poll net/core/dev.c:6594 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6727 __do_softirq+0xc1/0x265 kernel/softirq.c:553 do_softirq+0x5e/0x90 kernel/softirq.c:454 __local_bh_enable_ip+0x64/0x70 kernel/softirq.c:381 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:167 [inline] _raw_spin_unlock_bh+0x36/0x40 kernel/locking/spinlock.c:210 spin_unlock_bh include/linux/spinlock.h:396 [inline] batadv_tt_local_purge+0x1a8/0x1f0 net/batman-adv/translation-table.c:1356 batadv_tt_purge+0x2b/0x630 net/batman-adv/translation-table.c:3560 process_one_work kernel/workqueue.c:2630 [inline] process_scheduled_works+0x5b8/0xa30 kernel/workqueue.c:2703 worker_thread+0x525/0x730 kernel/workqueue.c:2784 kthread+0x1d7/0x210 kernel/kthread.c:388 ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 value changed: 0x00000000000d7190 -> 0x00000000000d7191 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 14848 Comm: kworker/u4:11 Not tainted 6.6.0-rc1-syzkaller-00236-gad8a69f361b9 #0 Fixes: 1c29fc4989bc ("[BRIDGE]: keep track of received multicast packets") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Roopa Prabhu Cc: Nikolay Aleksandrov Cc: bridge@lists.linux-foundation.org Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230918091351.1356153-1-edumazet@google.com Signed-off-by: Paolo Abeni --- net/bridge/br_forward.c | 4 ++-- net/bridge/br_input.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 9d7bc8b96b53..7431f89e897b 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -124,7 +124,7 @@ static int deliver_clone(const struct net_bridge_port *prev, skb = skb_clone(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return -ENOMEM; } @@ -268,7 +268,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, skb = skb_copy(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index c34a0b0901b0..c729528b5e85 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -181,12 +181,12 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if ((mdst && mdst->host_joined) || br_multicast_is_router(brmctx, skb)) { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } mcast_hit = true; } else { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } break; case BR_PKT_UNICAST: -- cgit v1.2.3 From f1d95df0f31048f1c59092648997686e3f7d9478 Mon Sep 17 00:00:00 2001 From: Artem Chernyshev Date: Mon, 18 Sep 2023 16:56:23 +0300 Subject: net: rds: Fix possible NULL-pointer dereference In rds_rdma_cm_event_handler_cmn() check, if conn pointer exists before dereferencing it as rdma_set_service_type() argument Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: fd261ce6a30e ("rds: rdma: update rdma transport for tos") Signed-off-by: Artem Chernyshev Signed-off-by: David S. Miller --- net/rds/rdma_transport.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index d36f3f6b4351..b15cf316b23a 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -86,11 +86,13 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_RESOLVED: - rdma_set_service_type(cm_id, conn->c_tos); - rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); - /* XXX do we need to clean up if this fails? */ - ret = rdma_resolve_route(cm_id, - RDS_RDMA_RESOLVE_TIMEOUT_MS); + if (conn) { + rdma_set_service_type(cm_id, conn->c_tos); + rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); + /* XXX do we need to clean up if this fails? */ + ret = rdma_resolve_route(cm_id, + RDS_RDMA_RESOLVE_TIMEOUT_MS); + } break; case RDMA_CM_EVENT_ROUTE_RESOLVED: -- cgit v1.2.3 From c9bd26513b3a11b3adb3c2ed8a31a01a87173ff1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 15 Sep 2023 15:18:11 +0200 Subject: netfilter: nf_tables: disable toggling dormant table state more than once nft -f -< Cc: Bing-Jhong Billy Jheng Cc: info@starlabs.sg Signed-off-by: Florian Westphal --- net/netfilter/nf_tables_api.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d819b4d42962..a3680638ec60 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1219,6 +1219,10 @@ static int nf_tables_updtable(struct nft_ctx *ctx) flags & NFT_TABLE_F_OWNER)) return -EOPNOTSUPP; + /* No dormant off/on/off/on games in single transaction */ + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) -- cgit v1.2.3 From cf5000a7787cbc10341091d37245a42c119d26c5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 19 Sep 2023 15:36:13 +0200 Subject: netfilter: nf_tables: fix memleak when more than 255 elements expired When more than 255 elements expired we're supposed to switch to a new gc container structure. This never happens: u8 type will wrap before reaching the boundary and nft_trans_gc_space() always returns true. This means we recycle the initial gc container structure and lose track of the elements that came before. While at it, don't deref 'gc' after we've passed it to call_rcu. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Reported-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal --- include/net/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 10 ++++++++-- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index a4455f4995ab..7c816359d5a9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1682,7 +1682,7 @@ struct nft_trans_gc { struct net *net; struct nft_set *set; u32 seq; - u8 count; + u16 count; void *priv[NFT_TRANS_GC_BATCHCOUNT]; struct rcu_head rcu; }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a3680638ec60..4356189360fb 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9579,12 +9579,15 @@ static int nft_trans_gc_space(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) { + struct nft_set *set; + if (nft_trans_gc_space(gc)) return gc; + set = gc->set; nft_trans_gc_queue_work(gc); - return nft_trans_gc_alloc(gc->set, gc_seq, gfp); + return nft_trans_gc_alloc(set, gc_seq, gfp); } void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) @@ -9599,15 +9602,18 @@ void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) { + struct nft_set *set; + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) return NULL; if (nft_trans_gc_space(gc)) return gc; + set = gc->set; call_rcu(&gc->rcu, nft_trans_gc_trans_free); - return nft_trans_gc_alloc(gc->set, 0, gfp); + return nft_trans_gc_alloc(set, 0, gfp); } void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) -- cgit v1.2.3 From 7433b6d2afd512d04398c73aa984d1e285be125b Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 19 Sep 2023 20:04:45 +0200 Subject: netfilter: ipset: Fix race between IPSET_CMD_CREATE and IPSET_CMD_SWAP Kyle Zeng reported that there is a race between IPSET_CMD_ADD and IPSET_CMD_SWAP in netfilter/ip_set, which can lead to the invocation of `__ip_set_put` on a wrong `set`, triggering the `BUG_ON(set->ref == 0);` check in it. The race is caused by using the wrong reference counter, i.e. the ref counter instead of ref_netlink. Fixes: 24e227896bbf ("netfilter: ipset: Add schedule point in call_ad().") Reported-by: Kyle Zeng Closes: https://lore.kernel.org/netfilter-devel/ZPZqetxOmH+w%2Fmyc@westworld/#r Tested-by: Kyle Zeng Signed-off-by: Jozsef Kadlecsik Signed-off-by: Florian Westphal --- net/netfilter/ipset/ip_set_core.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e564b5174261..35d2f9c9ada0 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -682,6 +682,14 @@ __ip_set_put(struct ip_set *set) /* set->ref can be swapped out by ip_set_swap, netlink events (like dump) need * a separate reference counter */ +static void +__ip_set_get_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + set->ref_netlink++; + write_unlock_bh(&ip_set_ref_lock); +} + static void __ip_set_put_netlink(struct ip_set *set) { @@ -1693,11 +1701,11 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, do { if (retried) { - __ip_set_get(set); + __ip_set_get_netlink(set); nfnl_unlock(NFNL_SUBSYS_IPSET); cond_resched(); nfnl_lock(NFNL_SUBSYS_IPSET); - __ip_set_put(set); + __ip_set_put_netlink(set); } ip_set_lock(set); -- cgit v1.2.3 From 4a0f07d71b0483cc08c03cefa7c85749e187c214 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Tue, 19 Sep 2023 18:44:06 +0800 Subject: net/handshake: Fix memory leak in __sock_create() and sock_alloc_file() When making CONFIG_DEBUG_KMEMLEAK=y and CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y, modprobe handshake-test and then rmmmod handshake-test, the below memory leak is detected. The struct socket_alloc which is allocated by alloc_inode_sb() in __sock_create() is not freed. And the struct dentry which is allocated by __d_alloc() in sock_alloc_file() is not freed. Since fput() will call file->f_op->release() which is sock_close() here and it will call __sock_release(). and fput() will call dput(dentry) to free the struct dentry. So replace sock_release() with fput() to fix the below memory leak. After applying this patch, the following memory leak is never detected. unreferenced object 0xffff888109165840 (size 768): comm "kunit_try_catch", pid 1852, jiffies 4294685807 (age 976.262s) hex dump (first 32 bytes): 01 00 00 00 01 00 5a 5a 20 00 00 00 00 00 00 00 ......ZZ ....... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] sock_alloc_inode+0x1f/0x1b0 [] alloc_inode+0x5b/0x1a0 [] new_inode_pseudo+0xd/0x70 [] sock_alloc+0x3c/0x260 [] __sock_create+0x66/0x3d0 [] 0xffffffffa0209ba2 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810f472008 (size 192): comm "kunit_try_catch", pid 1852, jiffies 4294685808 (age 976.261s) hex dump (first 32 bytes): 00 00 50 40 02 00 00 00 00 00 00 00 00 00 00 00 ..P@............ 00 00 00 00 00 00 00 00 08 20 47 0f 81 88 ff ff ......... G..... backtrace: [] __d_alloc+0x31/0x8a0 [] d_alloc_pseudo+0xe/0x50 [] alloc_file_pseudo+0xce/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0209bbb [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810958e580 (size 224): comm "kunit_try_catch", pid 1852, jiffies 4294685808 (age 976.261s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 03 00 2e 08 01 00 00 00 00 00 00 00 ................ backtrace: [] alloc_empty_file+0x50/0x160 [] alloc_file+0x59/0x730 [] alloc_file_pseudo+0x154/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0209bbb [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810926dc88 (size 192): comm "kunit_try_catch", pid 1854, jiffies 4294685809 (age 976.271s) hex dump (first 32 bytes): 00 00 50 40 02 00 00 00 00 00 00 00 00 00 00 00 ..P@............ 00 00 00 00 00 00 00 00 88 dc 26 09 81 88 ff ff ..........&..... backtrace: [] __d_alloc+0x31/0x8a0 [] d_alloc_pseudo+0xe/0x50 [] alloc_file_pseudo+0xce/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0208fdc [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810a241380 (size 224): comm "kunit_try_catch", pid 1854, jiffies 4294685809 (age 976.271s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 03 00 2e 08 01 00 00 00 00 00 00 00 ................ backtrace: [] alloc_empty_file+0x50/0x160 [] alloc_file+0x59/0x730 [] alloc_file_pseudo+0x154/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0208fdc [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888109165040 (size 768): comm "kunit_try_catch", pid 1856, jiffies 4294685811 (age 976.269s) hex dump (first 32 bytes): 01 00 00 00 01 00 5a 5a 20 00 00 00 00 00 00 00 ......ZZ ....... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] sock_alloc_inode+0x1f/0x1b0 [] alloc_inode+0x5b/0x1a0 [] new_inode_pseudo+0xd/0x70 [] sock_alloc+0x3c/0x260 [] __sock_create+0x66/0x3d0 [] 0xffffffffa0208860 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810926d568 (size 192): comm "kunit_try_catch", pid 1856, jiffies 4294685811 (age 976.269s) hex dump (first 32 bytes): 00 00 50 40 02 00 00 00 00 00 00 00 00 00 00 00 ..P@............ 00 00 00 00 00 00 00 00 68 d5 26 09 81 88 ff ff ........h.&..... backtrace: [] __d_alloc+0x31/0x8a0 [] d_alloc_pseudo+0xe/0x50 [] alloc_file_pseudo+0xce/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0208879 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810a240580 (size 224): comm "kunit_try_catch", pid 1856, jiffies 4294685811 (age 976.347s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 03 00 2e 08 01 00 00 00 00 00 00 00 ................ backtrace: [] alloc_empty_file+0x50/0x160 [] alloc_file+0x59/0x730 [] alloc_file_pseudo+0x154/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0208879 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888109164c40 (size 768): comm "kunit_try_catch", pid 1858, jiffies 4294685816 (age 976.342s) hex dump (first 32 bytes): 01 00 00 00 01 00 5a 5a 20 00 00 00 00 00 00 00 ......ZZ ....... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] sock_alloc_inode+0x1f/0x1b0 [] alloc_inode+0x5b/0x1a0 [] new_inode_pseudo+0xd/0x70 [] sock_alloc+0x3c/0x260 [] __sock_create+0x66/0x3d0 [] 0xffffffffa0208541 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810926cd18 (size 192): comm "kunit_try_catch", pid 1858, jiffies 4294685816 (age 976.342s) hex dump (first 32 bytes): 00 00 50 40 02 00 00 00 00 00 00 00 00 00 00 00 ..P@............ 00 00 00 00 00 00 00 00 18 cd 26 09 81 88 ff ff ..........&..... backtrace: [] __d_alloc+0x31/0x8a0 [] d_alloc_pseudo+0xe/0x50 [] alloc_file_pseudo+0xce/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa020855a [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810a240200 (size 224): comm "kunit_try_catch", pid 1858, jiffies 4294685816 (age 976.342s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 03 00 2e 08 01 00 00 00 00 00 00 00 ................ backtrace: [] alloc_empty_file+0x50/0x160 [] alloc_file+0x59/0x730 [] alloc_file_pseudo+0x154/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa020855a [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888109164840 (size 768): comm "kunit_try_catch", pid 1860, jiffies 4294685817 (age 976.416s) hex dump (first 32 bytes): 01 00 00 00 01 00 5a 5a 20 00 00 00 00 00 00 00 ......ZZ ....... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] sock_alloc_inode+0x1f/0x1b0 [] alloc_inode+0x5b/0x1a0 [] new_inode_pseudo+0xd/0x70 [] sock_alloc+0x3c/0x260 [] __sock_create+0x66/0x3d0 [] 0xffffffffa02093e2 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810926cab8 (size 192): comm "kunit_try_catch", pid 1860, jiffies 4294685817 (age 976.416s) hex dump (first 32 bytes): 00 00 50 40 02 00 00 00 00 00 00 00 00 00 00 00 ..P@............ 00 00 00 00 00 00 00 00 b8 ca 26 09 81 88 ff ff ..........&..... backtrace: [] __d_alloc+0x31/0x8a0 [] d_alloc_pseudo+0xe/0x50 [] alloc_file_pseudo+0xce/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa02093fb [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810a240040 (size 224): comm "kunit_try_catch", pid 1860, jiffies 4294685817 (age 976.416s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 03 00 2e 08 01 00 00 00 00 00 00 00 ................ backtrace: [] alloc_empty_file+0x50/0x160 [] alloc_file+0x59/0x730 [] alloc_file_pseudo+0x154/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa02093fb [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888109166440 (size 768): comm "kunit_try_catch", pid 1862, jiffies 4294685819 (age 976.489s) hex dump (first 32 bytes): 01 00 00 00 01 00 5a 5a 20 00 00 00 00 00 00 00 ......ZZ ....... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] sock_alloc_inode+0x1f/0x1b0 [] alloc_inode+0x5b/0x1a0 [] new_inode_pseudo+0xd/0x70 [] sock_alloc+0x3c/0x260 [] __sock_create+0x66/0x3d0 [] 0xffffffffa02097c1 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810926c398 (size 192): comm "kunit_try_catch", pid 1862, jiffies 4294685819 (age 976.489s) hex dump (first 32 bytes): 00 00 50 40 02 00 00 00 00 00 00 00 00 00 00 00 ..P@............ 00 00 00 00 00 00 00 00 98 c3 26 09 81 88 ff ff ..........&..... backtrace: [] __d_alloc+0x31/0x8a0 [] d_alloc_pseudo+0xe/0x50 [] alloc_file_pseudo+0xce/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa02097da [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888107e0b8c0 (size 224): comm "kunit_try_catch", pid 1862, jiffies 4294685819 (age 976.489s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 03 00 2e 08 01 00 00 00 00 00 00 00 ................ backtrace: [] alloc_empty_file+0x50/0x160 [] alloc_file+0x59/0x730 [] alloc_file_pseudo+0x154/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa02097da [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888109164440 (size 768): comm "kunit_try_catch", pid 1864, jiffies 4294685821 (age 976.487s) hex dump (first 32 bytes): 01 00 00 00 01 00 5a 5a 20 00 00 00 00 00 00 00 ......ZZ ....... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] sock_alloc_inode+0x1f/0x1b0 [] alloc_inode+0x5b/0x1a0 [] new_inode_pseudo+0xd/0x70 [] sock_alloc+0x3c/0x260 [] __sock_create+0x66/0x3d0 [] 0xffffffffa020824e [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff88810f4cf698 (size 192): comm "kunit_try_catch", pid 1864, jiffies 4294685821 (age 976.501s) hex dump (first 32 bytes): 00 00 50 40 02 00 00 00 00 00 00 00 00 00 00 00 ..P@............ 00 00 00 00 00 00 00 00 98 f6 4c 0f 81 88 ff ff ..........L..... backtrace: [] __d_alloc+0x31/0x8a0 [] d_alloc_pseudo+0xe/0x50 [] alloc_file_pseudo+0xce/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0208267 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 unreferenced object 0xffff888107e0b000 (size 224): comm "kunit_try_catch", pid 1864, jiffies 4294685821 (age 976.501s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 03 00 2e 08 01 00 00 00 00 00 00 00 ................ backtrace: [] alloc_empty_file+0x50/0x160 [] alloc_file+0x59/0x730 [] alloc_file_pseudo+0x154/0x210 [] sock_alloc_file+0x42/0x1b0 [] 0xffffffffa0208267 [] kunit_generic_run_threadfn_adapter+0x4a/0x90 [] kthread+0x2b6/0x380 [] ret_from_fork+0x2d/0x70 [] ret_from_fork_asm+0x11/0x20 Fixes: 88232ec1ec5e ("net/handshake: Add Kunit tests for the handshake consumer API") Signed-off-by: Jinjie Ruan Signed-off-by: David S. Miller --- net/handshake/handshake-test.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index 6d37bab35c8f..16ed7bfd29e4 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -235,7 +235,7 @@ static void handshake_req_submit_test4(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, req, result); handshake_req_cancel(sock->sk); - sock_release(sock); + fput(filp); } static void handshake_req_submit_test5(struct kunit *test) @@ -272,7 +272,7 @@ static void handshake_req_submit_test5(struct kunit *test) /* Assert */ KUNIT_EXPECT_EQ(test, err, -EAGAIN); - sock_release(sock); + fput(filp); hn->hn_pending = saved; } @@ -306,7 +306,7 @@ static void handshake_req_submit_test6(struct kunit *test) KUNIT_EXPECT_EQ(test, err, -EBUSY); handshake_req_cancel(sock->sk); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test1(struct kunit *test) @@ -340,7 +340,7 @@ static void handshake_req_cancel_test1(struct kunit *test) /* Assert */ KUNIT_EXPECT_TRUE(test, result); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test2(struct kunit *test) @@ -382,7 +382,7 @@ static void handshake_req_cancel_test2(struct kunit *test) /* Assert */ KUNIT_EXPECT_TRUE(test, result); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test3(struct kunit *test) @@ -427,7 +427,7 @@ static void handshake_req_cancel_test3(struct kunit *test) /* Assert */ KUNIT_EXPECT_FALSE(test, result); - sock_release(sock); + fput(filp); } static struct handshake_req *handshake_req_destroy_test; @@ -471,7 +471,7 @@ static void handshake_req_destroy_test1(struct kunit *test) handshake_req_cancel(sock->sk); /* Act */ - sock_release(sock); + fput(filp); /* Assert */ KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req); -- cgit v1.2.3