From 79618e952ef4dfa1a17ee0631d5549603fab58d8 Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Mon, 17 Mar 2025 22:42:02 -0700 Subject: [PATCH 01/29] idpf: fix adapter NULL pointer dereference on reboot [ Upstream commit 4c9106f4906a85f6b13542d862e423bcdc118cc3 ] With SRIOV enabled, idpf ends up calling into idpf_remove() twice. First via idpf_shutdown() and then again when idpf_remove() calls into sriov_disable(), because the VF devices use the idpf driver, hence the same remove routine. When that happens, it is possible for the adapter to be NULL from the first call to idpf_remove(), leading to a NULL pointer dereference. echo 1 > /sys/class/net//device/sriov_numvfs reboot BUG: kernel NULL pointer dereference, address: 0000000000000020 ... RIP: 0010:idpf_remove+0x22/0x1f0 [idpf] ... ? idpf_remove+0x22/0x1f0 [idpf] ? idpf_remove+0x1e4/0x1f0 [idpf] pci_device_remove+0x3f/0xb0 device_release_driver_internal+0x19f/0x200 pci_stop_bus_device+0x6d/0x90 pci_stop_and_remove_bus_device+0x12/0x20 pci_iov_remove_virtfn+0xbe/0x120 sriov_disable+0x34/0xe0 idpf_sriov_configure+0x58/0x140 [idpf] idpf_remove+0x1b9/0x1f0 [idpf] idpf_shutdown+0x12/0x30 [idpf] pci_device_shutdown+0x35/0x60 device_shutdown+0x156/0x200 ... Replace the direct idpf_remove() call in idpf_shutdown() with idpf_vc_core_deinit() and idpf_deinit_dflt_mbx(), which perform the bulk of the cleanup, such as stopping the init task, freeing IRQs, destroying the vports and freeing the mailbox. This avoids the calls to sriov_disable() in addition to a small netdev cleanup, and destroying workqueues, which don't seem to be required on shutdown. Reported-by: Yuying Ma Fixes: e850efed5e15 ("idpf: add module register and probe functionality") Reviewed-by: Madhu Chittim Signed-off-by: Emil Tantilov Reviewed-by: Simon Horman Tested-by: Samuel Salin Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/idpf/idpf_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index dfd56fc5ff65..7557bb6694c0 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -87,7 +87,11 @@ destroy_wqs: */ static void idpf_shutdown(struct pci_dev *pdev) { - idpf_remove(pdev); + struct idpf_adapter *adapter = pci_get_drvdata(pdev); + + cancel_delayed_work_sync(&adapter->vc_event_task); + idpf_vc_core_deinit(adapter); + idpf_deinit_dflt_mbx(adapter); if (system_state == SYSTEM_POWER_OFF) pci_set_power_state(pdev, PCI_D3hot); From 86bd9609fd3ec64e4807117d635e187d523b3438 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 21 Mar 2025 23:24:20 +0100 Subject: [PATCH 02/29] netfilter: nft_set_hash: GC reaps elements with conncount for dynamic sets only [ Upstream commit 9d74da1177c800eb3d51c13f9821b7b0683845a5 ] conncount has its own GC handler which determines when to reap stale elements, this is convenient for dynamic sets. However, this also reaps non-dynamic sets with static configurations coming from control plane. Always run connlimit gc handler but honor feedback to reap element if this set is dynamic. Fixes: 290180e2448c ("netfilter: nf_tables: add connlimit support") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_hash.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index b93f046ac7d1..4b3452dff2ec 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -309,7 +309,8 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, nft_setelem_expr_foreach(expr, elem_expr, size) { if (expr->ops->gc && - expr->ops->gc(read_pnet(&set->net), expr)) + expr->ops->gc(read_pnet(&set->net), expr) && + set->flags & NFT_SET_EVAL) return true; } From feb1fa2a03a27fec7001e93e4223be4120d1784b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 1 Apr 2025 14:36:47 +0200 Subject: [PATCH 03/29] netfilter: nf_tables: don't unregister hook when table is dormant [ Upstream commit 688c15017d5cd5aac882400782e7213d40dc3556 ] When nf_tables_updchain encounters an error, hook registration needs to be rolled back. This should only be done if the hook has been registered, which won't happen when the table is flagged as dormant (inactive). Just move the assignment into the registration block. Reported-by: syzbot+53ed3a6440173ddbf499@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=53ed3a6440173ddbf499 Fixes: b9703ed44ffb ("netfilter: nf_tables: support for adding new devices to an existing netdev chain") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index eb3a6f96b094..bdee187bc5dd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2732,11 +2732,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, err = nft_netdev_register_hooks(ctx->net, &hook.list); if (err < 0) goto err_hooks; + + unregister = true; } } - unregister = true; - if (nla[NFTA_CHAIN_COUNTERS]) { if (!nft_is_base_chain(chain)) { err = -EOPNOTSUPP; From 3ba9cf69de50e8abed32b448616c313baa4c5712 Mon Sep 17 00:00:00 2001 From: Debin Zhu Date: Tue, 1 Apr 2025 20:40:18 +0800 Subject: [PATCH 04/29] netlabel: Fix NULL pointer exception caused by CALIPSO on IPv4 sockets [ Upstream commit 078aabd567de3d63d37d7673f714e309d369e6e2 ] When calling netlbl_conn_setattr(), addr->sa_family is used to determine the function behavior. If sk is an IPv4 socket, but the connect function is called with an IPv6 address, the function calipso_sock_setattr() is triggered. Inside this function, the following code is executed: sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; Since sk is an IPv4 socket, pinet6 is NULL, leading to a null pointer dereference. This patch fixes the issue by checking if inet6_sk(sk) returns a NULL pointer before accessing pinet6. Signed-off-by: Debin Zhu Signed-off-by: Bitao Ouyang <1985755126@qq.com> Acked-by: Paul Moore Fixes: ceba1832b1b2 ("calipso: Set the calipso socket label to match the secattr.") Link: https://patch.msgid.link/20250401124018.4763-1-mowenroot@163.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv6/calipso.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index dbcea9fee626..62618a058b8f 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1072,8 +1072,13 @@ static int calipso_sock_getattr(struct sock *sk, struct ipv6_opt_hdr *hop; int opt_len, len, ret_val = -ENOMSG, offset; unsigned char *opt; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + if (!pinfo) + return -EAFNOSUPPORT; + + txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; @@ -1125,8 +1130,13 @@ static int calipso_sock_setattr(struct sock *sk, { int ret_val; struct ipv6_opt_hdr *old, *new; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + if (!pinfo) + return -EAFNOSUPPORT; + + txopts = txopt_get(pinfo); old = NULL; if (txopts) old = txopts->hopopt; @@ -1153,8 +1163,13 @@ static int calipso_sock_setattr(struct sock *sk, static void calipso_sock_delattr(struct sock *sk) { struct ipv6_opt_hdr *new_hop; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + if (!pinfo) + return; + + txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; From 2f35b7673a3aa3d09b3eb05811669622ebaa98ca Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 29 Mar 2025 15:25:35 -0700 Subject: [PATCH 05/29] net_sched: skbprio: Remove overly strict queue assertions [ Upstream commit ce8fe975fd99b49c29c42e50f2441ba53112b2e8 ] In the current implementation, skbprio enqueue/dequeue contains an assertion that fails under certain conditions when SKBPRIO is used as a child qdisc under TBF with specific parameters. The failure occurs because TBF sometimes peeks at packets in the child qdisc without actually dequeuing them when tokens are unavailable. This peek operation creates a discrepancy between the parent and child qdisc queue length counters. When TBF later receives a high-priority packet, SKBPRIO's queue length may show a different value than what's reflected in its internal priority queue tracking, triggering the assertion. The fix removes this overly strict assertions in SKBPRIO, they are not necessary at all. Reported-by: syzbot+a3422a19b05ea96bee18@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=a3422a19b05ea96bee18 Fixes: aea5f654e6b7 ("net/sched: add skbprio scheduler") Cc: Nishanth Devarajan Signed-off-by: Cong Wang Acked-by: Paolo Abeni Link: https://patch.msgid.link/20250329222536.696204-2-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_skbprio.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 20ff7386b74b..f485f62ab721 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -123,8 +123,6 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Check to update highest and lowest priorities. */ if (skb_queue_empty(lp_qdisc)) { if (q->lowest_prio == q->highest_prio) { - /* The incoming packet is the only packet in queue. */ - BUG_ON(sch->q.qlen != 1); q->lowest_prio = prio; q->highest_prio = prio; } else { @@ -156,7 +154,6 @@ static struct sk_buff *skbprio_dequeue(struct Qdisc *sch) /* Update highest priority field. */ if (skb_queue_empty(hpq)) { if (q->lowest_prio == q->highest_prio) { - BUG_ON(sch->q.qlen); q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; } else { From e5178bfc55b3a78000f0f8298e7ade88783ce581 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 31 Mar 2025 09:15:32 +0000 Subject: [PATCH 06/29] sctp: add mutual exclusion in proc_sctp_do_udp_port() [ Upstream commit 10206302af856791fbcc27a33ed3c3eb09b2793d ] We must serialize calls to sctp_udp_sock_stop() and sctp_udp_sock_start() or risk a crash as syzbot reported: Oops: general protection fault, probably for non-canonical address 0xdffffc000000000d: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000068-0x000000000000006f] CPU: 1 UID: 0 PID: 6551 Comm: syz.1.44 Not tainted 6.14.0-syzkaller-g7f2ff7b62617 #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025 RIP: 0010:kernel_sock_shutdown+0x47/0x70 net/socket.c:3653 Call Trace: udp_tunnel_sock_release+0x68/0x80 net/ipv4/udp_tunnel_core.c:181 sctp_udp_sock_stop+0x71/0x160 net/sctp/protocol.c:930 proc_sctp_do_udp_port+0x264/0x450 net/sctp/sysctl.c:553 proc_sys_call_handler+0x3d0/0x5b0 fs/proc/proc_sysctl.c:601 iter_file_splice_write+0x91c/0x1150 fs/splice.c:738 do_splice_from fs/splice.c:935 [inline] direct_splice_actor+0x18f/0x6c0 fs/splice.c:1158 splice_direct_to_actor+0x342/0xa30 fs/splice.c:1102 do_splice_direct_actor fs/splice.c:1201 [inline] do_splice_direct+0x174/0x240 fs/splice.c:1227 do_sendfile+0xafd/0xe50 fs/read_write.c:1368 __do_sys_sendfile64 fs/read_write.c:1429 [inline] __se_sys_sendfile64 fs/read_write.c:1415 [inline] __x64_sys_sendfile64+0x1d8/0x220 fs/read_write.c:1415 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] Fixes: 046c052b475e ("sctp: enable udp tunneling socks") Reported-by: syzbot+fae49d997eb56fa7c74d@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/67ea5c01.050a0220.1547ec.012b.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Cc: Marcelo Ricardo Leitner Acked-by: Xin Long Link: https://patch.msgid.link/20250331091532.224982-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/sysctl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 8e1e97be4df7..ee3eac338a9d 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -525,6 +525,8 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, return ret; } +static DEFINE_MUTEX(sctp_sysctl_mutex); + static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -549,6 +551,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, if (new_value > max || new_value < min) return -EINVAL; + mutex_lock(&sctp_sysctl_mutex); net->sctp.udp_port = new_value; sctp_udp_sock_stop(net); if (new_value) { @@ -561,6 +564,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, lock_sock(sk); sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); release_sock(sk); + mutex_unlock(&sctp_sysctl_mutex); } return ret; From fcbfb54a0269875cf3cd6a2bff4f85a2e0a0b552 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Tue, 1 Apr 2025 08:58:04 +0200 Subject: [PATCH 07/29] net: mvpp2: Prevent parser TCAM memory corruption [ Upstream commit 96844075226b49af25a69a1d084b648ec2d9b08d ] Protect the parser TCAM/SRAM memory, and the cached (shadow) SRAM information, from concurrent modifications. Both the TCAM and SRAM tables are indirectly accessed by configuring an index register that selects the row to read or write to. This means that operations must be atomic in order to, e.g., avoid spreading writes across multiple rows. Since the shadow SRAM array is used to find free rows in the hardware table, it must also be protected in order to avoid TOCTOU errors where multiple cores allocate the same row. This issue was detected in a situation where `mvpp2_set_rx_mode()` ran concurrently on two CPUs. In this particular case the MVPP2_PE_MAC_UC_PROMISCUOUS entry was corrupted, causing the classifier unit to drop all incoming unicast - indicated by the `rx_classifier_drops` counter. Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Tobias Waldekranz Reviewed-by: Maxime Chevallier Tested-by: Maxime Chevallier Link: https://patch.msgid.link/20250401065855.3113635-1-tobias@waldekranz.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 3 + .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 3 +- .../net/ethernet/marvell/mvpp2/mvpp2_prs.c | 201 ++++++++++++------ 3 files changed, 140 insertions(+), 67 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 9e02e4367bec..9bd3d76b5fe2 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -1108,6 +1108,9 @@ struct mvpp2 { /* Spinlocks for CM3 shared memory configuration */ spinlock_t mss_spinlock; + + /* Spinlock for shared PRS parser memory and shadow table */ + spinlock_t prs_spinlock; }; struct mvpp2_pcpu_stats { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 3880dcc0418b..66b5a80c9c28 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7640,8 +7640,9 @@ static int mvpp2_probe(struct platform_device *pdev) if (mvpp2_read(priv, MVPP2_VER_ID_REG) == MVPP2_VER_PP23) priv->hw_version = MVPP23; - /* Init mss lock */ + /* Init locks for shared packet processor resources */ spin_lock_init(&priv->mss_spinlock); + spin_lock_init(&priv->prs_spinlock); /* Initialize network controller */ err = mvpp2_init(pdev, priv); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c index 9af22f497a40..93e978bdf303 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c @@ -23,6 +23,8 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe) { int i; + lockdep_assert_held(&priv->prs_spinlock); + if (pe->index > MVPP2_PRS_TCAM_SRAM_SIZE - 1) return -EINVAL; @@ -43,11 +45,13 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe) } /* Initialize tcam entry from hw */ -int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe, - int tid) +static int __mvpp2_prs_init_from_hw(struct mvpp2 *priv, + struct mvpp2_prs_entry *pe, int tid) { int i; + lockdep_assert_held(&priv->prs_spinlock); + if (tid > MVPP2_PRS_TCAM_SRAM_SIZE - 1) return -EINVAL; @@ -73,6 +77,18 @@ int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe, return 0; } +int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe, + int tid) +{ + int err; + + spin_lock_bh(&priv->prs_spinlock); + err = __mvpp2_prs_init_from_hw(priv, pe, tid); + spin_unlock_bh(&priv->prs_spinlock); + + return err; +} + /* Invalidate tcam hw entry */ static void mvpp2_prs_hw_inv(struct mvpp2 *priv, int index) { @@ -374,7 +390,7 @@ static int mvpp2_prs_flow_find(struct mvpp2 *priv, int flow) priv->prs_shadow[tid].lu != MVPP2_PRS_LU_FLOWS) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); bits = mvpp2_prs_sram_ai_get(&pe); /* Sram store classification lookup ID in AI bits [5:0] */ @@ -441,7 +457,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add) if (priv->prs_shadow[MVPP2_PE_DROP_ALL].valid) { /* Entry exist - update port only */ - mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL); + __mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL); } else { /* Entry doesn't exist - create new */ memset(&pe, 0, sizeof(pe)); @@ -469,14 +485,17 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add) } /* Set port to unicast or multicast promiscuous mode */ -void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, - enum mvpp2_prs_l2_cast l2_cast, bool add) +static void __mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, + enum mvpp2_prs_l2_cast l2_cast, + bool add) { struct mvpp2_prs_entry pe; unsigned char cast_match; unsigned int ri; int tid; + lockdep_assert_held(&priv->prs_spinlock); + if (l2_cast == MVPP2_PRS_L2_UNI_CAST) { cast_match = MVPP2_PRS_UCAST_VAL; tid = MVPP2_PE_MAC_UC_PROMISCUOUS; @@ -489,7 +508,7 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, /* promiscuous mode - Accept unknown unicast or multicast packets */ if (priv->prs_shadow[tid].valid) { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } else { memset(&pe, 0, sizeof(pe)); mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC); @@ -522,6 +541,14 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, mvpp2_prs_hw_write(priv, &pe); } +void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port, + enum mvpp2_prs_l2_cast l2_cast, bool add) +{ + spin_lock_bh(&priv->prs_spinlock); + __mvpp2_prs_mac_promisc_set(priv, port, l2_cast, add); + spin_unlock_bh(&priv->prs_spinlock); +} + /* Set entry for dsa packets */ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add, bool tagged, bool extend) @@ -539,7 +566,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add, if (priv->prs_shadow[tid].valid) { /* Entry exist - update port only */ - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } else { /* Entry doesn't exist - create new */ memset(&pe, 0, sizeof(pe)); @@ -610,7 +637,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port, if (priv->prs_shadow[tid].valid) { /* Entry exist - update port only */ - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } else { /* Entry doesn't exist - create new */ memset(&pe, 0, sizeof(pe)); @@ -673,7 +700,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai) priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid); if (!match) continue; @@ -726,7 +753,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai, priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid_aux); + __mvpp2_prs_init_from_hw(priv, &pe, tid_aux); ri_bits = mvpp2_prs_sram_ri_get(&pe); if ((ri_bits & MVPP2_PRS_RI_VLAN_MASK) == MVPP2_PRS_RI_VLAN_DOUBLE) @@ -760,7 +787,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai, mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } /* Update ports' mask */ mvpp2_prs_tcam_port_map_set(&pe, port_map); @@ -800,7 +827,7 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1, priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) && mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2); @@ -849,7 +876,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid_aux); + __mvpp2_prs_init_from_hw(priv, &pe, tid_aux); ri_bits = mvpp2_prs_sram_ri_get(&pe); ri_bits &= MVPP2_PRS_RI_VLAN_MASK; if (ri_bits == MVPP2_PRS_RI_VLAN_SINGLE || @@ -880,7 +907,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } /* Update ports' mask */ @@ -1213,8 +1240,8 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv) /* Create dummy entries for drop all and promiscuous modes */ mvpp2_prs_drop_fc(priv); mvpp2_prs_mac_drop_all_set(priv, 0, false); - mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false); - mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false); + __mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false); + __mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false); } /* Set default entries for various types of dsa packets */ @@ -1533,12 +1560,6 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv) struct mvpp2_prs_entry pe; int err; - priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool), - MVPP2_PRS_DBL_VLANS_MAX, - GFP_KERNEL); - if (!priv->prs_double_vlans) - return -ENOMEM; - /* Double VLAN: 0x88A8, 0x8100 */ err = mvpp2_prs_double_vlan_add(priv, ETH_P_8021AD, ETH_P_8021Q, MVPP2_PRS_PORT_MASK); @@ -1941,7 +1962,7 @@ static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask) port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID) continue; - mvpp2_prs_init_from_hw(port->priv, &pe, tid); + __mvpp2_prs_init_from_hw(port->priv, &pe, tid); mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]); mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]); @@ -1970,6 +1991,8 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&priv->prs_spinlock); + /* Scan TCAM and see if entry with this already exist */ tid = mvpp2_prs_vid_range_find(port, vid, mask); @@ -1988,8 +2011,10 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) MVPP2_PRS_VLAN_FILT_MAX_ENTRY); /* There isn't room for a new VID filter */ - if (tid < 0) + if (tid < 0) { + spin_unlock_bh(&priv->prs_spinlock); return tid; + } mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID); pe.index = tid; @@ -1997,7 +2022,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) /* Mask all ports */ mvpp2_prs_tcam_port_map_set(&pe, 0); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } /* Enable the current port */ @@ -2019,6 +2044,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); mvpp2_prs_hw_write(priv, &pe); + spin_unlock_bh(&priv->prs_spinlock); return 0; } @@ -2028,15 +2054,16 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid) struct mvpp2 *priv = port->priv; int tid; - /* Scan TCAM and see if entry with this already exist */ + spin_lock_bh(&priv->prs_spinlock); + + /* Invalidate TCAM entry with this , if it exists */ tid = mvpp2_prs_vid_range_find(port, vid, 0xfff); + if (tid >= 0) { + mvpp2_prs_hw_inv(priv, tid); + priv->prs_shadow[tid].valid = false; + } - /* No such entry */ - if (tid < 0) - return; - - mvpp2_prs_hw_inv(priv, tid); - priv->prs_shadow[tid].valid = false; + spin_unlock_bh(&priv->prs_spinlock); } /* Remove all existing VID filters on this port */ @@ -2045,6 +2072,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port) struct mvpp2 *priv = port->priv; int tid; + spin_lock_bh(&priv->prs_spinlock); + for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id); tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) { if (priv->prs_shadow[tid].valid) { @@ -2052,6 +2081,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port) priv->prs_shadow[tid].valid = false; } } + + spin_unlock_bh(&priv->prs_spinlock); } /* Remove VID filering entry for this port */ @@ -2060,10 +2091,14 @@ void mvpp2_prs_vid_disable_filtering(struct mvpp2_port *port) unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id); struct mvpp2 *priv = port->priv; + spin_lock_bh(&priv->prs_spinlock); + /* Invalidate the guard entry */ mvpp2_prs_hw_inv(priv, tid); priv->prs_shadow[tid].valid = false; + + spin_unlock_bh(&priv->prs_spinlock); } /* Add guard entry that drops packets when no VID is matched on this port */ @@ -2079,6 +2114,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&priv->prs_spinlock); + pe.index = tid; reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id)); @@ -2111,6 +2148,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port) /* Update shadow table */ mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); mvpp2_prs_hw_write(priv, &pe); + + spin_unlock_bh(&priv->prs_spinlock); } /* Parser default initialization */ @@ -2118,6 +2157,20 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv) { int err, index, i; + priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE, + sizeof(*priv->prs_shadow), + GFP_KERNEL); + if (!priv->prs_shadow) + return -ENOMEM; + + priv->prs_double_vlans = devm_kcalloc(&pdev->dev, sizeof(bool), + MVPP2_PRS_DBL_VLANS_MAX, + GFP_KERNEL); + if (!priv->prs_double_vlans) + return -ENOMEM; + + spin_lock_bh(&priv->prs_spinlock); + /* Enable tcam table */ mvpp2_write(priv, MVPP2_PRS_TCAM_CTRL_REG, MVPP2_PRS_TCAM_EN_MASK); @@ -2136,12 +2189,6 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv) for (index = 0; index < MVPP2_PRS_TCAM_SRAM_SIZE; index++) mvpp2_prs_hw_inv(priv, index); - priv->prs_shadow = devm_kcalloc(&pdev->dev, MVPP2_PRS_TCAM_SRAM_SIZE, - sizeof(*priv->prs_shadow), - GFP_KERNEL); - if (!priv->prs_shadow) - return -ENOMEM; - /* Always start from lookup = 0 */ for (index = 0; index < MVPP2_MAX_PORTS; index++) mvpp2_prs_hw_port_init(priv, index, MVPP2_PRS_LU_MH, @@ -2158,26 +2205,13 @@ int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_prs_vid_init(priv); err = mvpp2_prs_etype_init(priv); - if (err) - return err; + err = err ? : mvpp2_prs_vlan_init(pdev, priv); + err = err ? : mvpp2_prs_pppoe_init(priv); + err = err ? : mvpp2_prs_ip6_init(priv); + err = err ? : mvpp2_prs_ip4_init(priv); - err = mvpp2_prs_vlan_init(pdev, priv); - if (err) - return err; - - err = mvpp2_prs_pppoe_init(priv); - if (err) - return err; - - err = mvpp2_prs_ip6_init(priv); - if (err) - return err; - - err = mvpp2_prs_ip4_init(priv); - if (err) - return err; - - return 0; + spin_unlock_bh(&priv->prs_spinlock); + return err; } /* Compare MAC DA with tcam entry data */ @@ -2217,7 +2251,7 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da, (priv->prs_shadow[tid].udf != udf_type)) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); entry_pmap = mvpp2_prs_tcam_port_map_get(&pe); if (mvpp2_prs_mac_range_equals(&pe, da, mask) && @@ -2229,7 +2263,8 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da, } /* Update parser's mac da entry */ -int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) +static int __mvpp2_prs_mac_da_accept(struct mvpp2_port *port, + const u8 *da, bool add) { unsigned char mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; struct mvpp2 *priv = port->priv; @@ -2261,7 +2296,7 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) /* Mask all ports */ mvpp2_prs_tcam_port_map_set(&pe, 0); } else { - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); } mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC); @@ -2317,6 +2352,17 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) return 0; } +int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add) +{ + int err; + + spin_lock_bh(&port->priv->prs_spinlock); + err = __mvpp2_prs_mac_da_accept(port, da, add); + spin_unlock_bh(&port->priv->prs_spinlock); + + return err; +} + int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da) { struct mvpp2_port *port = netdev_priv(dev); @@ -2345,6 +2391,8 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port) unsigned long pmap; int index, tid; + spin_lock_bh(&priv->prs_spinlock); + for (tid = MVPP2_PE_MAC_RANGE_START; tid <= MVPP2_PE_MAC_RANGE_END; tid++) { unsigned char da[ETH_ALEN], da_mask[ETH_ALEN]; @@ -2354,7 +2402,7 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port) (priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF)) continue; - mvpp2_prs_init_from_hw(priv, &pe, tid); + __mvpp2_prs_init_from_hw(priv, &pe, tid); pmap = mvpp2_prs_tcam_port_map_get(&pe); @@ -2375,14 +2423,17 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port) continue; /* Remove entry from TCAM */ - mvpp2_prs_mac_da_accept(port, da, false); + __mvpp2_prs_mac_da_accept(port, da, false); } + + spin_unlock_bh(&priv->prs_spinlock); } int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) { switch (type) { case MVPP2_TAG_TYPE_EDSA: + spin_lock_bh(&priv->prs_spinlock); /* Add port to EDSA entries */ mvpp2_prs_dsa_tag_set(priv, port, true, MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA); @@ -2393,9 +2444,11 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) MVPP2_PRS_TAGGED, MVPP2_PRS_DSA); mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_UNTAGGED, MVPP2_PRS_DSA); + spin_unlock_bh(&priv->prs_spinlock); break; case MVPP2_TAG_TYPE_DSA: + spin_lock_bh(&priv->prs_spinlock); /* Add port to DSA entries */ mvpp2_prs_dsa_tag_set(priv, port, true, MVPP2_PRS_TAGGED, MVPP2_PRS_DSA); @@ -2406,10 +2459,12 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA); mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA); + spin_unlock_bh(&priv->prs_spinlock); break; case MVPP2_TAG_TYPE_MH: case MVPP2_TAG_TYPE_NONE: + spin_lock_bh(&priv->prs_spinlock); /* Remove port form EDSA and DSA entries */ mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_TAGGED, MVPP2_PRS_DSA); @@ -2419,6 +2474,7 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type) MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA); mvpp2_prs_dsa_tag_set(priv, port, false, MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA); + spin_unlock_bh(&priv->prs_spinlock); break; default: @@ -2437,11 +2493,15 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&priv->prs_spinlock); + tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_LAST_FREE_TID, MVPP2_PE_FIRST_FREE_TID); - if (tid < 0) + if (tid < 0) { + spin_unlock_bh(&priv->prs_spinlock); return tid; + } pe.index = tid; @@ -2461,6 +2521,7 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask) mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK); mvpp2_prs_hw_write(priv, &pe); + spin_unlock_bh(&priv->prs_spinlock); return 0; } @@ -2472,6 +2533,8 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port) memset(&pe, 0, sizeof(pe)); + spin_lock_bh(&port->priv->prs_spinlock); + tid = mvpp2_prs_flow_find(port->priv, port->id); /* Such entry not exist */ @@ -2480,8 +2543,10 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port) tid = mvpp2_prs_tcam_first_free(port->priv, MVPP2_PE_LAST_FREE_TID, MVPP2_PE_FIRST_FREE_TID); - if (tid < 0) + if (tid < 0) { + spin_unlock_bh(&port->priv->prs_spinlock); return tid; + } pe.index = tid; @@ -2492,13 +2557,14 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port) /* Update shadow table */ mvpp2_prs_shadow_set(port->priv, pe.index, MVPP2_PRS_LU_FLOWS); } else { - mvpp2_prs_init_from_hw(port->priv, &pe, tid); + __mvpp2_prs_init_from_hw(port->priv, &pe, tid); } mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS); mvpp2_prs_tcam_port_map_set(&pe, (1 << port->id)); mvpp2_prs_hw_write(port->priv, &pe); + spin_unlock_bh(&port->priv->prs_spinlock); return 0; } @@ -2509,11 +2575,14 @@ int mvpp2_prs_hits(struct mvpp2 *priv, int index) if (index > MVPP2_PRS_TCAM_SRAM_SIZE) return -EINVAL; + spin_lock_bh(&priv->prs_spinlock); + mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index); val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG); val &= MVPP2_PRS_TCAM_HIT_CNT_MASK; + spin_unlock_bh(&priv->prs_spinlock); return val; } From 94d5ad7b41122be33ebc2a6830fe710cba1ecd75 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 1 Apr 2025 11:44:42 -0700 Subject: [PATCH 08/29] udp: Fix multiple wraparounds of sk->sk_rmem_alloc. [ Upstream commit 5a465a0da13ee9fbd7d3cd0b2893309b0fe4b7e3 ] __udp_enqueue_schedule_skb() has the following condition: if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) goto drop; sk->sk_rcvbuf is initialised by net.core.rmem_default and later can be configured by SO_RCVBUF, which is limited by net.core.rmem_max, or SO_RCVBUFFORCE. If we set INT_MAX to sk->sk_rcvbuf, the condition is always false as sk->sk_rmem_alloc is also signed int. Then, the size of the incoming skb is added to sk->sk_rmem_alloc unconditionally. This results in integer overflow (possibly multiple times) on sk->sk_rmem_alloc and allows a single socket to have skb up to net.core.udp_mem[1]. For example, if we set a large value to udp_mem[1] and INT_MAX to sk->sk_rcvbuf and flood packets to the socket, we can see multiple overflows: # cat /proc/net/sockstat | grep UDP: UDP: inuse 3 mem 7956736 <-- (7956736 << 12) bytes > INT_MAX * 15 ^- PAGE_SHIFT # ss -uam State Recv-Q ... UNCONN -1757018048 ... <-- flipping the sign repeatedly skmem:(r2537949248,rb2147483646,t0,tb212992,f1984,w0,o0,bl0,d0) Previously, we had a boundary check for INT_MAX, which was removed by commit 6a1f12dd85a8 ("udp: relax atomic operation on sk->sk_rmem_alloc"). A complete fix would be to revert it and cap the right operand by INT_MAX: rmem = atomic_add_return(size, &sk->sk_rmem_alloc); if (rmem > min(size + (unsigned int)sk->sk_rcvbuf, INT_MAX)) goto uncharge_drop; but we do not want to add the expensive atomic_add_return() back just for the corner case. Casting rmem to unsigned int prevents multiple wraparounds, but we still allow a single wraparound. # cat /proc/net/sockstat | grep UDP: UDP: inuse 3 mem 524288 <-- (INT_MAX + 1) >> 12 # ss -uam State Recv-Q ... UNCONN -2147482816 ... <-- INT_MAX + 831 bytes skmem:(r2147484480,rb2147483646,t0,tb212992,f3264,w0,o0,bl0,d14468947) So, let's define rmem and rcvbuf as unsigned int and check skb->truesize only when rcvbuf is large enough to lower the overflow possibility. Note that we still have a small chance to see overflow if multiple skbs to the same socket are processed on different core at the same time and each size does not exceed the limit but the total size does. Note also that we must ignore skb->truesize for a small buffer as explained in commit 363dc73acacb ("udp: be less conservative with sock rmem accounting"). Fixes: 6a1f12dd85a8 ("udp: relax atomic operation on sk->sk_rmem_alloc") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250401184501.67377-2-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/udp.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8da74dc63061..4f52d220f4d0 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1570,17 +1570,25 @@ static int udp_rmem_schedule(struct sock *sk, int size) int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; - int rmem, err = -ENOMEM; + unsigned int rmem, rcvbuf; spinlock_t *busy = NULL; - int size, rcvbuf; + int size, err = -ENOMEM; - /* Immediately drop when the receive queue is full. - * Always allow at least one packet. - */ rmem = atomic_read(&sk->sk_rmem_alloc); rcvbuf = READ_ONCE(sk->sk_rcvbuf); - if (rmem > rcvbuf) - goto drop; + size = skb->truesize; + + /* Immediately drop when the receive queue is full. + * Cast to unsigned int performs the boundary check for INT_MAX. + */ + if (rmem + size > rcvbuf) { + if (rcvbuf > INT_MAX >> 1) + goto drop; + + /* Always allow at least one packet for small buffer. */ + if (rmem > rcvbuf) + goto drop; + } /* Under mem pressure, it might be helpful to help udp_recvmsg() * having linear skbs : @@ -1590,10 +1598,10 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) */ if (rmem > (rcvbuf >> 1)) { skb_condense(skb); - + size = skb->truesize; busy = busylock_acquire(sk); } - size = skb->truesize; + udp_set_dev_scratch(skb); atomic_add(size, &sk->sk_rmem_alloc); From a116b271bf3cb72c8155b6b7f39083c1b80dcd00 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 1 Apr 2025 11:44:43 -0700 Subject: [PATCH 09/29] udp: Fix memory accounting leak. [ Upstream commit df207de9d9e7a4d92f8567e2c539d9c8c12fd99d ] Matt Dowling reported a weird UDP memory usage issue. Under normal operation, the UDP memory usage reported in /proc/net/sockstat remains close to zero. However, it occasionally spiked to 524,288 pages and never dropped. Moreover, the value doubled when the application was terminated. Finally, it caused intermittent packet drops. We can reproduce the issue with the script below [0]: 1. /proc/net/sockstat reports 0 pages # cat /proc/net/sockstat | grep UDP: UDP: inuse 1 mem 0 2. Run the script till the report reaches 524,288 # python3 test.py & sleep 5 # cat /proc/net/sockstat | grep UDP: UDP: inuse 3 mem 524288 <-- (INT_MAX + 1) >> PAGE_SHIFT 3. Kill the socket and confirm the number never drops # pkill python3 && sleep 5 # cat /proc/net/sockstat | grep UDP: UDP: inuse 1 mem 524288 4. (necessary since v6.0) Trigger proto_memory_pcpu_drain() # python3 test.py & sleep 1 && pkill python3 5. The number doubles # cat /proc/net/sockstat | grep UDP: UDP: inuse 1 mem 1048577 The application set INT_MAX to SO_RCVBUF, which triggered an integer overflow in udp_rmem_release(). When a socket is close()d, udp_destruct_common() purges its receive queue and sums up skb->truesize in the queue. This total is calculated and stored in a local unsigned integer variable. The total size is then passed to udp_rmem_release() to adjust memory accounting. However, because the function takes a signed integer argument, the total size can wrap around, causing an overflow. Then, the released amount is calculated as follows: 1) Add size to sk->sk_forward_alloc. 2) Round down sk->sk_forward_alloc to the nearest lower multiple of PAGE_SIZE and assign it to amount. 3) Subtract amount from sk->sk_forward_alloc. 4) Pass amount >> PAGE_SHIFT to __sk_mem_reduce_allocated(). When the issue occurred, the total in udp_destruct_common() was 2147484480 (INT_MAX + 833), which was cast to -2147482816 in udp_rmem_release(). At 1) sk->sk_forward_alloc is changed from 3264 to -2147479552, and 2) sets -2147479552 to amount. 3) reverts the wraparound, so we don't see a warning in inet_sock_destruct(). However, udp_memory_allocated ends up doubling at 4). Since commit 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated"), memory usage no longer doubles immediately after a socket is close()d because __sk_mem_reduce_allocated() caches the amount in udp_memory_per_cpu_fw_alloc. However, the next time a UDP socket receives a packet, the subtraction takes effect, causing UDP memory usage to double. This issue makes further memory allocation fail once the socket's sk->sk_rmem_alloc exceeds net.ipv4.udp_rmem_min, resulting in packet drops. To prevent this issue, let's use unsigned int for the calculation and call sk_forward_alloc_add() only once for the small delta. Note that first_packet_length() also potentially has the same problem. [0]: from socket import * SO_RCVBUFFORCE = 33 INT_MAX = (2 ** 31) - 1 s = socket(AF_INET, SOCK_DGRAM) s.bind(('', 0)) s.setsockopt(SOL_SOCKET, SO_RCVBUFFORCE, INT_MAX) c = socket(AF_INET, SOCK_DGRAM) c.connect(s.getsockname()) data = b'a' * 100 while True: c.send(data) Fixes: f970bd9e3a06 ("udp: implement memory accounting helpers") Reported-by: Matt Dowling Signed-off-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250401184501.67377-3-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/udp.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4f52d220f4d0..f4e24fc878fa 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1470,12 +1470,12 @@ static bool udp_skb_has_head_state(struct sk_buff *skb) } /* fully reclaim rmem/fwd memory allocated for skb */ -static void udp_rmem_release(struct sock *sk, int size, int partial, - bool rx_queue_lock_held) +static void udp_rmem_release(struct sock *sk, unsigned int size, + int partial, bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); struct sk_buff_head *sk_queue; - int amt; + unsigned int amt; if (likely(partial)) { up->forward_deficit += size; @@ -1495,10 +1495,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (!rx_queue_lock_held) spin_lock(&sk_queue->lock); - - sk_forward_alloc_add(sk, size); - amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); - sk_forward_alloc_add(sk, -amt); + amt = (size + sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); + sk_forward_alloc_add(sk, size - amt); if (amt) __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); @@ -1688,7 +1686,7 @@ EXPORT_SYMBOL_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, - int *total) + unsigned int *total) { struct sk_buff *skb; @@ -1721,8 +1719,8 @@ static int first_packet_length(struct sock *sk) { struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + unsigned int total = 0; struct sk_buff *skb; - int total = 0; int res; spin_lock_bh(&rcvq->lock); From 47744d0d5f3bd413e8153d721c57886a81f84831 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 28 Mar 2025 15:15:28 +0100 Subject: [PATCH 10/29] vsock: avoid timeout during connect() if the socket is closing [ Upstream commit fccd2b711d9628c7ce0111d5e4938652101ee30a ] When a peer attempts to establish a connection, vsock_connect() contains a loop that waits for the state to be TCP_ESTABLISHED. However, the other peer can be fast enough to accept the connection and close it immediately, thus moving the state to TCP_CLOSING. When this happens, the peer in the vsock_connect() is properly woken up, but since the state is not TCP_ESTABLISHED, it goes back to sleep until the timeout expires, returning -ETIMEDOUT. If the socket state is TCP_CLOSING, waiting for the timeout is pointless. vsock_connect() can return immediately without errors or delay since the connection actually happened. The socket will be in a closing state, but this is not an issue, and subsequent calls will fail as expected. We discovered this issue while developing a test that accepts and immediately closes connections to stress the transport switch between two connect() calls, where the first one was interrupted by a signal (see Closes link). Reported-by: Luigi Leonardi Closes: https://lore.kernel.org/virtualization/bq6hxrolno2vmtqwcvb5bljfpb7mvwb3kohrvaed6auz5vxrfv@ijmd2f3grobn/ Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Signed-off-by: Stefano Garzarella Acked-by: Paolo Abeni Tested-by: Luigi Leonardi Reviewed-by: Luigi Leonardi Link: https://patch.msgid.link/20250328141528.420719-1-sgarzare@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/vmw_vsock/af_vsock.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index eb6ea26b390e..d08f205b33dc 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1551,7 +1551,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) { + /* If the socket is already closing or it is in an error state, there + * is no point in waiting. + */ + while (sk->sk_state != TCP_ESTABLISHED && + sk->sk_state != TCP_CLOSING && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection From 9539c1721a36ef6d5b5e342b7b4927d01629cc0a Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Sat, 29 Mar 2025 01:33:44 +0100 Subject: [PATCH 11/29] tunnels: Accept PACKET_HOST in skb_tunnel_check_pmtu(). [ Upstream commit 8930424777e43257f5bf6f0f0f53defd0d30415c ] Because skb_tunnel_check_pmtu() doesn't handle PACKET_HOST packets, commit 30a92c9e3d6b ("openvswitch: Set the skbuff pkt_type for proper pmtud support.") forced skb->pkt_type to PACKET_OUTGOING for openvswitch packets that are sent using the OVS_ACTION_ATTR_OUTPUT action. This allowed such packets to invoke the iptunnel_pmtud_check_icmp() or iptunnel_pmtud_check_icmpv6() helpers and thus trigger PMTU update on the input device. However, this also broke other parts of PMTU discovery. Since these packets don't have the PACKET_HOST type anymore, they won't trigger the sending of ICMP Fragmentation Needed or Packet Too Big messages to remote hosts when oversized (see the skb_in->pkt_type condition in __icmp_send() for example). These two skb->pkt_type checks are therefore incompatible as one requires skb->pkt_type to be PACKET_HOST, while the other requires it to be anything but PACKET_HOST. It makes sense to not trigger ICMP messages for non-PACKET_HOST packets as these messages should be generated only for incoming l2-unicast packets. However there doesn't seem to be any reason for skb_tunnel_check_pmtu() to ignore PACKET_HOST packets. Allow both cases to work by allowing skb_tunnel_check_pmtu() to work on PACKET_HOST packets and not overriding skb->pkt_type in openvswitch anymore. Fixes: 30a92c9e3d6b ("openvswitch: Set the skbuff pkt_type for proper pmtud support.") Fixes: 4cb47a8644cc ("tunnels: PMTU discovery support for directly bridged IP packets") Signed-off-by: Guillaume Nault Reviewed-by: Stefano Brivio Reviewed-by: Aaron Conole Tested-by: Aaron Conole Link: https://patch.msgid.link/eac941652b86fddf8909df9b3bf0d97bc9444793.1743208264.git.gnault@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/ip_tunnel_core.c | 2 +- net/openvswitch/actions.c | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index a3676155be78..364ea798511e 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -416,7 +416,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, skb_dst_update_pmtu_no_confirm(skb, mtu); - if (!reply || skb->pkt_type == PACKET_HOST) + if (!reply) return 0; if (skb->protocol == htons(ETH_P_IP)) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 704c858cf209..61fea7baae5d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -947,12 +947,6 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, pskb_trim(skb, ovs_mac_header_len(key)); } - /* Need to set the pkt_type to involve the routing layer. The - * packet movement through the OVS datapath doesn't generally - * use routing, but this is needed for tunnel cases. - */ - skb->pkt_type = PACKET_OUTGOING; - if (likely(!mru || (skb->len <= mru + vport->dev->hard_header_len))) { ovs_vport_send(vport, skb, ovs_key_mac_proto(key)); From 92a5c18513117be69bc00419dd1724c1940f8fcd Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Wed, 26 Mar 2025 18:36:32 +0100 Subject: [PATCH 12/29] net: decrease cached dst counters in dst_release [ Upstream commit 3a0a3ff6593d670af2451ec363ccb7b18aec0c0a ] Upstream fix ac888d58869b ("net: do not delay dst_entries_add() in dst_release()") moved decrementing the dst count from dst_destroy to dst_release to avoid accessing already freed data in case of netns dismantle. However in case CONFIG_DST_CACHE is enabled and OvS+tunnels are used, this fix is incomplete as the same issue will be seen for cached dsts: Unable to handle kernel paging request at virtual address ffff5aabf6b5c000 Call trace: percpu_counter_add_batch+0x3c/0x160 (P) dst_release+0xec/0x108 dst_cache_destroy+0x68/0xd8 dst_destroy+0x13c/0x168 dst_destroy_rcu+0x1c/0xb0 rcu_do_batch+0x18c/0x7d0 rcu_core+0x174/0x378 rcu_core_si+0x18/0x30 Fix this by invalidating the cache, and thus decrementing cached dst counters, in dst_release too. Fixes: d71785ffc7e7 ("net: add dst_cache to ovs vxlan lwtunnel") Signed-off-by: Antoine Tenart Link: https://patch.msgid.link/20250326173634.31096-1-atenart@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/core/dst.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/core/dst.c b/net/core/dst.c index 9552a90d4772..6d76b799ce64 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -165,6 +165,14 @@ static void dst_count_dec(struct dst_entry *dst) void dst_release(struct dst_entry *dst) { if (dst && rcuref_put(&dst->__rcuref)) { +#ifdef CONFIG_DST_CACHE + if (dst->flags & DST_METADATA) { + struct metadata_dst *md_dst = (struct metadata_dst *)dst; + + if (md_dst->type == METADATA_IP_TUNNEL) + dst_cache_reset_now(&md_dst->u.tun_info.dst_cache); + } +#endif dst_count_dec(dst); call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); } From 0a93a710d6df334b828ea064c6d39fda34f901dc Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Thu, 3 Apr 2025 01:00:26 +0800 Subject: [PATCH 13/29] netfilter: nft_tunnel: fix geneve_opt type confusion addition [ Upstream commit 1b755d8eb1ace3870789d48fbd94f386ad6e30be ] When handling multiple NFTA_TUNNEL_KEY_OPTS_GENEVE attributes, the parsing logic should place every geneve_opt structure one by one compactly. Hence, when deciding the next geneve_opt position, the pointer addition should be in units of char *. However, the current implementation erroneously does type conversion before the addition, which will lead to heap out-of-bounds write. [ 6.989857] ================================================================== [ 6.990293] BUG: KASAN: slab-out-of-bounds in nft_tunnel_obj_init+0x977/0xa70 [ 6.990725] Write of size 124 at addr ffff888005f18974 by task poc/178 [ 6.991162] [ 6.991259] CPU: 0 PID: 178 Comm: poc-oob-write Not tainted 6.1.132 #1 [ 6.991655] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 [ 6.992281] Call Trace: [ 6.992423] [ 6.992586] dump_stack_lvl+0x44/0x5c [ 6.992801] print_report+0x184/0x4be [ 6.993790] kasan_report+0xc5/0x100 [ 6.994252] kasan_check_range+0xf3/0x1a0 [ 6.994486] memcpy+0x38/0x60 [ 6.994692] nft_tunnel_obj_init+0x977/0xa70 [ 6.995677] nft_obj_init+0x10c/0x1b0 [ 6.995891] nf_tables_newobj+0x585/0x950 [ 6.996922] nfnetlink_rcv_batch+0xdf9/0x1020 [ 6.998997] nfnetlink_rcv+0x1df/0x220 [ 6.999537] netlink_unicast+0x395/0x530 [ 7.000771] netlink_sendmsg+0x3d0/0x6d0 [ 7.001462] __sock_sendmsg+0x99/0xa0 [ 7.001707] ____sys_sendmsg+0x409/0x450 [ 7.002391] ___sys_sendmsg+0xfd/0x170 [ 7.003145] __sys_sendmsg+0xea/0x170 [ 7.004359] do_syscall_64+0x5e/0x90 [ 7.005817] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 7.006127] RIP: 0033:0x7ec756d4e407 [ 7.006339] Code: 48 89 fa 4c 89 df e8 38 aa 00 00 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 1a 5b c3 0f 1f 84 00 00 00 00 00 48 8b 44 24 10 0f 05 <5b> c3 0f 1f 80 00 00 00 00 83 e2 39 83 faf [ 7.007364] RSP: 002b:00007ffed5d46760 EFLAGS: 00000202 ORIG_RAX: 000000000000002e [ 7.007827] RAX: ffffffffffffffda RBX: 00007ec756cc4740 RCX: 00007ec756d4e407 [ 7.008223] RDX: 0000000000000000 RSI: 00007ffed5d467f0 RDI: 0000000000000003 [ 7.008620] RBP: 00007ffed5d468a0 R08: 0000000000000000 R09: 0000000000000000 [ 7.009039] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000 [ 7.009429] R13: 00007ffed5d478b0 R14: 00007ec756ee5000 R15: 00005cbd4e655cb8 Fix this bug with correct pointer addition and conversion in parse and dump code. Fixes: 925d844696d9 ("netfilter: nft_tunnel: add support for geneve opts") Signed-off-by: Lin Ma Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_tunnel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 5c6ed68cc6e0..52d76b8d15db 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -341,7 +341,7 @@ static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GEN static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, struct nft_tunnel_opts *opts) { - struct geneve_opt *opt = (struct geneve_opt *)opts->u.data + opts->len; + struct geneve_opt *opt = (struct geneve_opt *)(opts->u.data + opts->len); struct nlattr *tb[NFTA_TUNNEL_KEY_GENEVE_MAX + 1]; int err, data_len; @@ -628,7 +628,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, if (!inner) goto failure; while (opts->len > offset) { - opt = (struct geneve_opt *)opts->u.data + offset; + opt = (struct geneve_opt *)(opts->u.data + offset); if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS, opt->opt_class) || nla_put_u8(skb, NFTA_TUNNEL_KEY_GENEVE_TYPE, From de579015d132e742af32611900b038ffbe5a0850 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 2 Apr 2025 14:17:51 +0200 Subject: [PATCH 14/29] ipv6: fix omitted netlink attributes when using RTEXT_FILTER_SKIP_STATS [ Upstream commit 7ac6ea4a3e0898db76aecccd68fb2c403eb7d24e ] Using RTEXT_FILTER_SKIP_STATS is incorrectly skipping non-stats IPv6 netlink attributes on link dump. This causes issues on userspace tools, e.g iproute2 is not rendering address generation mode as it should due to missing netlink attribute. Move the filling of IFLA_INET6_STATS and IFLA_INET6_ICMP6STATS to a helper function guarded by a flag check to avoid hitting the same situation in the future. Fixes: d5566fd72ec1 ("rtnetlink: RTEXT_FILTER_SKIP_STATS support to avoid dumping inet/inet6 stats") Signed-off-by: Fernando Fernandez Mancera Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250402121751.3108-1-ffmancera@riseup.net Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv6/addrconf.c | 37 +++++++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 12 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f7c17388ff6a..f5d49162f798 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5807,6 +5807,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, } } +static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb, + struct inet6_dev *idev) +{ + struct nlattr *nla; + + nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); + if (!nla) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); + + nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); + if (!nla) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, u32 ext_filter_mask) { @@ -5829,18 +5850,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, /* XXX - MC not implemented */ - if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS) - return 0; - - nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); - if (!nla) - goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); - - nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); - if (!nla) - goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) { + if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0) + goto nla_put_failure; + } nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); if (!nla) From 9dec9dacaeeda0b87c9833fa85d8a015677fa65a Mon Sep 17 00:00:00 2001 From: David Oberhollenzer Date: Tue, 1 Apr 2025 15:56:37 +0200 Subject: [PATCH 15/29] net: dsa: mv88e6xxx: propperly shutdown PPU re-enable timer on destroy [ Upstream commit a58d882841a0750da3c482cd3d82432b1c7edb77 ] The mv88e6xxx has an internal PPU that polls PHY state. If we want to access the internal PHYs, we need to disable the PPU first. Because that is a slow operation, a 10ms timer is used to re-enable it, canceled with every access, so bulk operations effectively only disable it once and re-enable it some 10ms after the last access. If a PHY is accessed and then the mv88e6xxx module is removed before the 10ms are up, the PPU re-enable ends up accessing a dangling pointer. This especially affects probing during bootup. The MDIO bus and PHY registration may succeed, but registration with the DSA framework may fail later on (e.g. because the CPU port depends on another, very slow device that isn't done probing yet, returning -EPROBE_DEFER). In this case, probe() fails, but the MDIO subsystem may already have accessed the MIDO bus or PHYs, arming the timer. This is fixed as follows: - If probe fails after mv88e6xxx_phy_init(), make sure we also call mv88e6xxx_phy_destroy() before returning - In mv88e6xxx_remove(), make sure we do the teardown in the correct order, calling mv88e6xxx_phy_destroy() after unregistering the switch device. - In mv88e6xxx_phy_destroy(), destroy both the timer and the work item that the timer might schedule, synchronously waiting in case one of the callbacks already fired and destroying the timer first, before waiting for the work item. - Access to the PPU is guarded by a mutex, the worker acquires it with a mutex_trylock(), not proceeding with the expensive shutdown if that fails. We grab the mutex in mv88e6xxx_phy_destroy() to make sure the slow PPU shutdown is already done or won't even enter, when we wait for the work item. Fixes: 2e5f032095ff ("dsa: add support for the Marvell 88E6131 switch chip") Signed-off-by: David Oberhollenzer Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20250401135705.92760-1-david.oberhollenzer@sigma-star.at Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 11 +++++++---- drivers/net/dsa/mv88e6xxx/phy.c | 3 +++ 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 5aeecfab9630..5935100e7d65 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -7301,13 +7301,13 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) err = mv88e6xxx_switch_reset(chip); mv88e6xxx_reg_unlock(chip); if (err) - goto out; + goto out_phy; if (np) { chip->irq = of_irq_get(np, 0); if (chip->irq == -EPROBE_DEFER) { err = chip->irq; - goto out; + goto out_phy; } } @@ -7326,7 +7326,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) mv88e6xxx_reg_unlock(chip); if (err) - goto out; + goto out_phy; if (chip->info->g2_irqs > 0) { err = mv88e6xxx_g2_irq_setup(chip); @@ -7360,6 +7360,8 @@ out_g1_irq: mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); +out_phy: + mv88e6xxx_phy_destroy(chip); out: if (pdata) dev_put(pdata->netdev); @@ -7382,7 +7384,6 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) mv88e6xxx_ptp_free(chip); } - mv88e6xxx_phy_destroy(chip); mv88e6xxx_unregister_switch(chip); mv88e6xxx_g1_vtu_prob_irq_free(chip); @@ -7395,6 +7396,8 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); + + mv88e6xxx_phy_destroy(chip); } static void mv88e6xxx_shutdown(struct mdio_device *mdiodev) diff --git a/drivers/net/dsa/mv88e6xxx/phy.c b/drivers/net/dsa/mv88e6xxx/phy.c index 8bb88b3d900d..ee9e5d7e5277 100644 --- a/drivers/net/dsa/mv88e6xxx/phy.c +++ b/drivers/net/dsa/mv88e6xxx/phy.c @@ -229,7 +229,10 @@ static void mv88e6xxx_phy_ppu_state_init(struct mv88e6xxx_chip *chip) static void mv88e6xxx_phy_ppu_state_destroy(struct mv88e6xxx_chip *chip) { + mutex_lock(&chip->ppu_mutex); del_timer_sync(&chip->ppu_timer); + cancel_work_sync(&chip->ppu_work); + mutex_unlock(&chip->ppu_mutex); } int mv88e6185_phy_ppu_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus, From 2952776c69a1a551649ed770bf22e3f691f6ec65 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Thu, 3 Apr 2025 00:56:32 +0800 Subject: [PATCH 16/29] net: fix geneve_opt length integer overflow [ Upstream commit b27055a08ad4b415dcf15b63034f9cb236f7fb40 ] struct geneve_opt uses 5 bit length for each single option, which means every vary size option should be smaller than 128 bytes. However, all current related Netlink policies cannot promise this length condition and the attacker can exploit a exact 128-byte size option to *fake* a zero length option and confuse the parsing logic, further achieve heap out-of-bounds read. One example crash log is like below: [ 3.905425] ================================================================== [ 3.905925] BUG: KASAN: slab-out-of-bounds in nla_put+0xa9/0xe0 [ 3.906255] Read of size 124 at addr ffff888005f291cc by task poc/177 [ 3.906646] [ 3.906775] CPU: 0 PID: 177 Comm: poc-oob-read Not tainted 6.1.132 #1 [ 3.907131] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 [ 3.907784] Call Trace: [ 3.907925] [ 3.908048] dump_stack_lvl+0x44/0x5c [ 3.908258] print_report+0x184/0x4be [ 3.909151] kasan_report+0xc5/0x100 [ 3.909539] kasan_check_range+0xf3/0x1a0 [ 3.909794] memcpy+0x1f/0x60 [ 3.909968] nla_put+0xa9/0xe0 [ 3.910147] tunnel_key_dump+0x945/0xba0 [ 3.911536] tcf_action_dump_1+0x1c1/0x340 [ 3.912436] tcf_action_dump+0x101/0x180 [ 3.912689] tcf_exts_dump+0x164/0x1e0 [ 3.912905] fw_dump+0x18b/0x2d0 [ 3.913483] tcf_fill_node+0x2ee/0x460 [ 3.914778] tfilter_notify+0xf4/0x180 [ 3.915208] tc_new_tfilter+0xd51/0x10d0 [ 3.918615] rtnetlink_rcv_msg+0x4a2/0x560 [ 3.919118] netlink_rcv_skb+0xcd/0x200 [ 3.919787] netlink_unicast+0x395/0x530 [ 3.921032] netlink_sendmsg+0x3d0/0x6d0 [ 3.921987] __sock_sendmsg+0x99/0xa0 [ 3.922220] __sys_sendto+0x1b7/0x240 [ 3.922682] __x64_sys_sendto+0x72/0x90 [ 3.922906] do_syscall_64+0x5e/0x90 [ 3.923814] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 3.924122] RIP: 0033:0x7e83eab84407 [ 3.924331] Code: 48 89 fa 4c 89 df e8 38 aa 00 00 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 1a 5b c3 0f 1f 84 00 00 00 00 00 48 8b 44 24 10 0f 05 <5b> c3 0f 1f 80 00 00 00 00 83 e2 39 83 faf [ 3.925330] RSP: 002b:00007ffff505e370 EFLAGS: 00000202 ORIG_RAX: 000000000000002c [ 3.925752] RAX: ffffffffffffffda RBX: 00007e83eaafa740 RCX: 00007e83eab84407 [ 3.926173] RDX: 00000000000001a8 RSI: 00007ffff505e3c0 RDI: 0000000000000003 [ 3.926587] RBP: 00007ffff505f460 R08: 00007e83eace1000 R09: 000000000000000c [ 3.926977] R10: 0000000000000000 R11: 0000000000000202 R12: 00007ffff505f3c0 [ 3.927367] R13: 00007ffff505f5c8 R14: 00007e83ead1b000 R15: 00005d4fbbe6dcb8 Fix these issues by enforing correct length condition in related policies. Fixes: 925d844696d9 ("netfilter: nft_tunnel: add support for geneve opts") Fixes: 4ece47787077 ("lwtunnel: add options setting and dumping for geneve") Fixes: 0ed5269f9e41 ("net/sched: add tunnel option support to act_tunnel_key") Fixes: 0a6e77784f49 ("net/sched: allow flower to match tunnel options") Signed-off-by: Lin Ma Reviewed-by: Xin Long Acked-by: Cong Wang Link: https://patch.msgid.link/20250402165632.6958-1-linma@zju.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/ip_tunnel_core.c | 2 +- net/netfilter/nft_tunnel.c | 2 +- net/sched/act_tunnel_key.c | 2 +- net/sched/cls_flower.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 364ea798511e..f65d2f727381 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -451,7 +451,7 @@ static const struct nla_policy geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = { [LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, - [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, + [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static const struct nla_policy diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 52d76b8d15db..0d99786c322e 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -335,7 +335,7 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GENEVE_MAX + 1] = { [NFTA_TUNNEL_KEY_GENEVE_CLASS] = { .type = NLA_U16 }, [NFTA_TUNNEL_KEY_GENEVE_TYPE] = { .type = NLA_U8 }, - [NFTA_TUNNEL_KEY_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, + [NFTA_TUNNEL_KEY_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index af7c99845948..e296714803dc 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -68,7 +68,7 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, - .len = 128 }, + .len = 127 }, }; static const struct nla_policy diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 03505673d523..099ff6a3e1f5 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -766,7 +766,7 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, - .len = 128 }, + .len = 127 }, }; static const struct nla_policy From 1eb36a2cdf639483d414d193ad31ff476a8fb2a9 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 2 Apr 2025 14:42:23 +0300 Subject: [PATCH 17/29] ipv6: Start path selection from the first nexthop [ Upstream commit 4d0ab3a6885e3e9040310a8d8f54503366083626 ] Cited commit transitioned IPv6 path selection to use hash-threshold instead of modulo-N. With hash-threshold, each nexthop is assigned a region boundary in the multipath hash function's output space and a nexthop is chosen if the calculated hash is smaller than the nexthop's region boundary. Hash-threshold does not work correctly if path selection does not start with the first nexthop. For example, if fib6_select_path() is always passed the last nexthop in the group, then it will always be chosen because its region boundary covers the entire hash function's output space. Fix this by starting the selection process from the first nexthop and do not consider nexthops for which rt6_score_route() provided a negative score. Fixes: 3d709f69a3e7 ("ipv6: Use hash-threshold instead of modulo-N") Reported-by: Stanislav Fomichev Closes: https://lore.kernel.org/netdev/Z9RIyKZDNoka53EO@mini-arch/ Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20250402114224.293392-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv6/route.c | 38 +++++++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b393c37d2424..54ce948835a0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -412,11 +412,35 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } +static struct fib6_info * +rt6_multipath_first_sibling_rcu(const struct fib6_info *rt) +{ + struct fib6_info *iter; + struct fib6_node *fn; + + fn = rcu_dereference(rt->fib6_node); + if (!fn) + goto out; + iter = rcu_dereference(fn->leaf); + if (!iter) + goto out; + + while (iter) { + if (iter->fib6_metric == rt->fib6_metric && + rt6_qualify_for_ecmp(iter)) + return iter; + iter = rcu_dereference(iter->fib6_next); + } + +out: + return NULL; +} + void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { - struct fib6_info *match = res->f6i; + struct fib6_info *first, *match = res->f6i; struct fib6_info *sibling; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) @@ -440,10 +464,18 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, return; } - if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) + first = rt6_multipath_first_sibling_rcu(match); + if (!first) goto out; - list_for_each_entry_rcu(sibling, &match->fib6_siblings, + if (fl6->mp_hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) && + rt6_score_route(first->fib6_nh, first->fib6_flags, oif, + strict) >= 0) { + match = first; + goto out; + } + + list_for_each_entry_rcu(sibling, &first->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; From f4fea25f5c7f2841d356c438aba34e44ad341bde Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 2 Apr 2025 14:42:24 +0300 Subject: [PATCH 18/29] ipv6: Do not consider link down nexthops in path selection [ Upstream commit 8b8e0dd357165e0258d9f9cdab5366720ed2f619 ] Nexthops whose link is down are not supposed to be considered during path selection when the "ignore_routes_with_linkdown" sysctl is set. This is done by assigning them a negative region boundary. However, when comparing the computed hash (unsigned) with the region boundary (signed), the negative region boundary is treated as unsigned, resulting in incorrect nexthop selection. Fix by treating the computed hash as signed. Note that the computed hash is always in range of [0, 2^31 - 1]. Fixes: 3d709f69a3e7 ("ipv6: Use hash-threshold instead of modulo-N") Signed-off-by: Ido Schimmel Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250402114224.293392-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv6/route.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 54ce948835a0..987492dcb07c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -442,6 +442,7 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, { struct fib6_info *first, *match = res->f6i; struct fib6_info *sibling; + int hash; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; @@ -468,7 +469,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, if (!first) goto out; - if (fl6->mp_hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) && + hash = fl6->mp_hash; + if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) && rt6_score_route(first->fib6_nh, first->fib6_flags, oif, strict) >= 0) { match = first; @@ -481,7 +483,7 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); - if (fl6->mp_hash > nh_upper_bound) + if (hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; From ebebeb58d48e25525fa654f2c53a24713fe141c3 Mon Sep 17 00:00:00 2001 From: Henry Martin Date: Wed, 2 Apr 2025 21:50:36 +0800 Subject: [PATCH 19/29] arcnet: Add NULL check in com20020pci_probe() [ Upstream commit fda8c491db2a90ff3e6fbbae58e495b4ddddeca3 ] devm_kasprintf() returns NULL when memory allocation fails. Currently, com20020pci_probe() does not check for this case, which results in a NULL pointer dereference. Add NULL check after devm_kasprintf() to prevent this issue and ensure no resources are left allocated. Fixes: 6b17a597fc2f ("arcnet: restoring support for multiple Sohard Arcnet cards") Signed-off-by: Henry Martin Link: https://patch.msgid.link/20250402135036.44697-1-bsdhenrymartin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/arcnet/com20020-pci.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index c5e571ec94c9..0472bcdff130 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -251,18 +251,33 @@ static int com20020pci_probe(struct pci_dev *pdev, card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, GFP_KERNEL, "arc%d-%d-tx", dev->dev_id, i); + if (!card->tx_led.default_trigger) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "pci:green:tx:%d-%d", dev->dev_id, i); - + if (!card->tx_led.name) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->tx_led.dev = &dev->dev; card->recon_led.brightness_set = led_recon_set; card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, GFP_KERNEL, "arc%d-%d-recon", dev->dev_id, i); + if (!card->recon_led.default_trigger) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "pci:red:recon:%d-%d", dev->dev_id, i); + if (!card->recon_led.name) { + ret = -ENOMEM; + goto err_free_arcdev; + } card->recon_led.dev = &dev->dev; ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); From 8a88bb092f4208355880b9fdcc69d491aa297595 Mon Sep 17 00:00:00 2001 From: Dave Marquardt Date: Wed, 2 Apr 2025 10:44:03 -0500 Subject: [PATCH 20/29] net: ibmveth: make veth_pool_store stop hanging [ Upstream commit 053f3ff67d7feefc75797863f3d84b47ad47086f ] v2: - Created a single error handling unlock and exit in veth_pool_store - Greatly expanded commit message with previous explanatory-only text Summary: Use rtnl_mutex to synchronize veth_pool_store with itself, ibmveth_close and ibmveth_open, preventing multiple calls in a row to napi_disable. Background: Two (or more) threads could call veth_pool_store through writing to /sys/devices/vio/30000002/pool*/*. You can do this easily with a little shell script. This causes a hang. I configured LOCKDEP, compiled ibmveth.c with DEBUG, and built a new kernel. I ran this test again and saw: Setting pool0/active to 0 Setting pool1/active to 1 [ 73.911067][ T4365] ibmveth 30000002 eth0: close starting Setting pool1/active to 1 Setting pool1/active to 0 [ 73.911367][ T4366] ibmveth 30000002 eth0: close starting [ 73.916056][ T4365] ibmveth 30000002 eth0: close complete [ 73.916064][ T4365] ibmveth 30000002 eth0: open starting [ 110.808564][ T712] systemd-journald[712]: Sent WATCHDOG=1 notification. [ 230.808495][ T712] systemd-journald[712]: Sent WATCHDOG=1 notification. [ 243.683786][ T123] INFO: task stress.sh:4365 blocked for more than 122 seconds. [ 243.683827][ T123] Not tainted 6.14.0-01103-g2df0c02dab82-dirty #8 [ 243.683833][ T123] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 243.683838][ T123] task:stress.sh state:D stack:28096 pid:4365 tgid:4365 ppid:4364 task_flags:0x400040 flags:0x00042000 [ 243.683852][ T123] Call Trace: [ 243.683857][ T123] [c00000000c38f690] [0000000000000001] 0x1 (unreliable) [ 243.683868][ T123] [c00000000c38f840] [c00000000001f908] __switch_to+0x318/0x4e0 [ 243.683878][ T123] [c00000000c38f8a0] [c000000001549a70] __schedule+0x500/0x12a0 [ 243.683888][ T123] [c00000000c38f9a0] [c00000000154a878] schedule+0x68/0x210 [ 243.683896][ T123] [c00000000c38f9d0] [c00000000154ac80] schedule_preempt_disabled+0x30/0x50 [ 243.683904][ T123] [c00000000c38fa00] [c00000000154dbb0] __mutex_lock+0x730/0x10f0 [ 243.683913][ T123] [c00000000c38fb10] [c000000001154d40] napi_enable+0x30/0x60 [ 243.683921][ T123] [c00000000c38fb40] [c000000000f4ae94] ibmveth_open+0x68/0x5dc [ 243.683928][ T123] [c00000000c38fbe0] [c000000000f4aa20] veth_pool_store+0x220/0x270 [ 243.683936][ T123] [c00000000c38fc70] [c000000000826278] sysfs_kf_write+0x68/0xb0 [ 243.683944][ T123] [c00000000c38fcb0] [c0000000008240b8] kernfs_fop_write_iter+0x198/0x2d0 [ 243.683951][ T123] [c00000000c38fd00] [c00000000071b9ac] vfs_write+0x34c/0x650 [ 243.683958][ T123] [c00000000c38fdc0] [c00000000071bea8] ksys_write+0x88/0x150 [ 243.683966][ T123] [c00000000c38fe10] [c0000000000317f4] system_call_exception+0x124/0x340 [ 243.683973][ T123] [c00000000c38fe50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec ... [ 243.684087][ T123] Showing all locks held in the system: [ 243.684095][ T123] 1 lock held by khungtaskd/123: [ 243.684099][ T123] #0: c00000000278e370 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x50/0x248 [ 243.684114][ T123] 4 locks held by stress.sh/4365: [ 243.684119][ T123] #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150 [ 243.684132][ T123] #1: c000000041aea888 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x154/0x2d0 [ 243.684143][ T123] #2: c0000000366fb9a8 (kn->active#64){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x160/0x2d0 [ 243.684155][ T123] #3: c000000035ff4cb8 (&dev->lock){+.+.}-{3:3}, at: napi_enable+0x30/0x60 [ 243.684166][ T123] 5 locks held by stress.sh/4366: [ 243.684170][ T123] #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150 [ 243.684183][ T123] #1: c00000000aee2288 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x154/0x2d0 [ 243.684194][ T123] #2: c0000000366f4ba8 (kn->active#64){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x160/0x2d0 [ 243.684205][ T123] #3: c000000035ff4cb8 (&dev->lock){+.+.}-{3:3}, at: napi_disable+0x30/0x60 [ 243.684216][ T123] #4: c0000003ff9bbf18 (&rq->__lock){-.-.}-{2:2}, at: __schedule+0x138/0x12a0 From the ibmveth debug, two threads are calling veth_pool_store, which calls ibmveth_close and ibmveth_open. Here's the sequence: T4365 T4366 ----------------- ----------------- --------- veth_pool_store veth_pool_store ibmveth_close ibmveth_close napi_disable napi_disable ibmveth_open napi_enable <- HANG ibmveth_close calls napi_disable at the top and ibmveth_open calls napi_enable at the top. https://docs.kernel.org/networking/napi.html]] says The control APIs are not idempotent. Control API calls are safe against concurrent use of datapath APIs but an incorrect sequence of control API calls may result in crashes, deadlocks, or race conditions. For example, calling napi_disable() multiple times in a row will deadlock. In the normal open and close paths, rtnl_mutex is acquired to prevent other callers. This is missing from veth_pool_store. Use rtnl_mutex in veth_pool_store fixes these hangs. Signed-off-by: Dave Marquardt Fixes: 860f242eb534 ("[PATCH] ibmveth change buffer pools dynamically") Reviewed-by: Nick Child Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250402154403.386744-1-davemarq@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/ibm/ibmveth.c | 39 +++++++++++++++++++++--------- 1 file changed, 27 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index b619a3ec245b..04192190beba 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1802,18 +1802,22 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, long value = simple_strtol(buf, NULL, 10); long rc; + rtnl_lock(); + if (attr == &veth_active_attr) { if (value && !pool->active) { if (netif_running(netdev)) { if (ibmveth_alloc_buffer_pool(pool)) { netdev_err(netdev, "unable to alloc pool\n"); - return -ENOMEM; + rc = -ENOMEM; + goto unlock_err; } pool->active = 1; ibmveth_close(netdev); - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } else { pool->active = 1; } @@ -1833,48 +1837,59 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, if (i == IBMVETH_NUM_BUFF_POOLS) { netdev_err(netdev, "no active pool >= MTU\n"); - return -EPERM; + rc = -EPERM; + goto unlock_err; } if (netif_running(netdev)) { ibmveth_close(netdev); pool->active = 0; - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } pool->active = 0; } } else if (attr == &veth_num_attr) { if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) { - return -EINVAL; + rc = -EINVAL; + goto unlock_err; } else { if (netif_running(netdev)) { ibmveth_close(netdev); pool->size = value; - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } else { pool->size = value; } } } else if (attr == &veth_size_attr) { if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) { - return -EINVAL; + rc = -EINVAL; + goto unlock_err; } else { if (netif_running(netdev)) { ibmveth_close(netdev); pool->buff_size = value; - if ((rc = ibmveth_open(netdev))) - return rc; + rc = ibmveth_open(netdev); + if (rc) + goto unlock_err; } else { pool->buff_size = value; } } } + rtnl_unlock(); /* kick the interrupt handler to allocate/deallocate pools */ ibmveth_interrupt(netdev->irq, netdev); return count; + +unlock_err: + rtnl_unlock(); + return rc; } From 528287815ee52a2f5ea68df83e712513a19f9c8a Mon Sep 17 00:00:00 2001 From: Alexandru Gagniuc Date: Fri, 14 Mar 2025 13:10:53 +0000 Subject: [PATCH 21/29] kbuild: deb-pkg: don't set KBUILD_BUILD_VERSION unconditionally [ Upstream commit 62604063621fb075c7966286bdddcb057d883fa8 ] In ThinPro, we use the convention +hp for the kernel package. This does not have a dash in the name or version. This is built by editing ".version" before a build, and setting EXTRAVERSION="+hp" and KDEB_PKGVERSION make variables: echo 68 > .version make -j EXTRAVERSION="+hp" bindeb-pkg KDEB_PKGVERSION=6.12.2+hp69 .deb name: linux-image-6.12.2+hp_6.12.2+hp69_amd64.deb Since commit 7d4f07d5cb71 ("kbuild: deb-pkg: squash scripts/package/deb-build-option to debian/rules"), this no longer works. The deb build logic changed, even though, the commit message implies that the logic should be unmodified. Before, KBUILD_BUILD_VERSION was not set if the KDEB_PKGVERSION did not contain a dash. After the change KBUILD_BUILD_VERSION is always set to KDEB_PKGVERSION. Since this determines UTS_VERSION, the uname output to look off: (now) uname -a: version 6.12.2+hp ... #6.12.2+hp69 (expected) uname -a: version 6.12.2+hp ... #69 Update the debian/rules logic to restore the original behavior. Fixes: 7d4f07d5cb71 ("kbuild: deb-pkg: squash scripts/package/deb-build-option to debian/rules") Signed-off-by: Alexandru Gagniuc Reviewed-by: Nicolas Schier Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/package/debian/rules | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules index ca07243bd5cd..2b3f9a0bd6c4 100755 --- a/scripts/package/debian/rules +++ b/scripts/package/debian/rules @@ -21,9 +21,11 @@ ifeq ($(origin KBUILD_VERBOSE),undefined) endif endif -revision = $(lastword $(subst -, ,$(shell dpkg-parsechangelog -S Version))) +revision = $(shell dpkg-parsechangelog -S Version | sed -n 's/.*-//p') CROSS_COMPILE ?= $(filter-out $(DEB_BUILD_GNU_TYPE)-, $(DEB_HOST_GNU_TYPE)-) -make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) KBUILD_BUILD_VERSION=$(revision) $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE)) +make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) \ + $(addprefix KBUILD_BUILD_VERSION=,$(revision)) \ + $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE)) binary-targets := $(addprefix binary-, image image-dbg headers libc-dev) From 2ac69453e9e5c24ebb55abe15e075d59b6ca01da Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 26 Mar 2025 09:35:02 -0400 Subject: [PATCH 22/29] drm/amdgpu/gfx11: fix num_mec [ Upstream commit 4161050d47e1b083a7e1b0b875c9907e1a6f1f1f ] GC11 only has 1 mec. Fixes: 3d879e81f0f9 ("drm/amdgpu: add init support for GFX11 (v2)") Reviewed-by: Sunil Khatri Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index d3e8be82a172..84cf5fd297b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1549,7 +1549,7 @@ static int gfx_v11_0_sw_init(void *handle) adev->gfx.me.num_me = 1; adev->gfx.me.num_pipe_per_me = 1; adev->gfx.me.num_queue_per_pipe = 1; - adev->gfx.mec.num_mec = 2; + adev->gfx.mec.num_mec = 1; adev->gfx.mec.num_pipe_per_mec = 4; adev->gfx.mec.num_queue_per_pipe = 4; break; From d3f0a68b2914061e20b004b488034010d83d0be1 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 20 Mar 2025 12:09:11 -0400 Subject: [PATCH 23/29] drm/amdgpu/gfx12: fix num_mec [ Upstream commit dce8bd9137b88735dd0efc4e2693213d98c15913 ] GC12 only has 1 mec. Fixes: 52cb80c12e8a ("drm/amdgpu: Add gfx v12_0 ip block support (v6)") Reviewed-by: Sunil Khatri Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index d3798a333d1f..b259e217930c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -1332,7 +1332,7 @@ static int gfx_v12_0_sw_init(void *handle) adev->gfx.me.num_me = 1; adev->gfx.me.num_pipe_per_me = 1; adev->gfx.me.num_queue_per_pipe = 1; - adev->gfx.mec.num_mec = 2; + adev->gfx.mec.num_mec = 1; adev->gfx.mec.num_pipe_per_mec = 2; adev->gfx.mec.num_queue_per_pipe = 4; break; From e9c92880723979c0ba59dba58161da3a4a00884e Mon Sep 17 00:00:00 2001 From: Yeoreum Yun Date: Wed, 26 Mar 2025 08:20:03 +0000 Subject: [PATCH 24/29] perf/core: Fix child_total_time_enabled accounting bug at task exit [ Upstream commit a3c3c66670cee11eb13aa43905904bf29cb92d32 ] The perf events code fails to account for total_time_enabled of inactive events. Here is a failure case for accounting total_time_enabled for CPU PMU events: sudo ./perf stat -vvv -e armv8_pmuv3_0/event=0x08/ -e armv8_pmuv3_1/event=0x08/ -- stress-ng --pthread=2 -t 2s ... armv8_pmuv3_0/event=0x08/: 1138698008 2289429840 2174835740 armv8_pmuv3_1/event=0x08/: 1826791390 1950025700 847648440 ` ` ` ` ` > total_time_running with child ` > total_time_enabled with child > count with child Performance counter stats for 'stress-ng --pthread=2 -t 2s': 1,138,698,008 armv8_pmuv3_0/event=0x08/ (94.99%) 1,826,791,390 armv8_pmuv3_1/event=0x08/ (43.47%) The two events above are opened on two different CPU PMUs, for example, each event is opened for a cluster in an Arm big.LITTLE system, they will never run on the same CPU. In theory, the total enabled time should be same for both events, as two events are opened and closed together. As the result show, the two events' total enabled time including child event is different (2289429840 vs 1950025700). This is because child events are not accounted properly if a event is INACTIVE state when the task exits: perf_event_exit_event() `> perf_remove_from_context() `> __perf_remove_from_context() `> perf_child_detach() -> Accumulate child_total_time_enabled `> list_del_event() -> Update child event's time The problem is the time accumulation happens prior to child event's time updating. Thus, it misses to account the last period's time when the event exits. The perf core layer follows the rule that timekeeping is tied to state change. To address the issue, make __perf_remove_from_context() handle the task exit case by passing 'DETACH_EXIT' to it and invoke perf_event_state() for state alongside with accounting the time. Then, perf_child_detach() populates the time into the parent's time metrics. After this patch, the bug is fixed: sudo ./perf stat -vvv -e armv8_pmuv3_0/event=0x08/ -e armv8_pmuv3_1/event=0x08/ -- stress-ng --pthread=2 -t 10s ... armv8_pmuv3_0/event=0x08/: 15396770398 32157963940 21898169000 armv8_pmuv3_1/event=0x08/: 22428964974 32157963940 10259794940 Performance counter stats for 'stress-ng --pthread=2 -t 10s': 15,396,770,398 armv8_pmuv3_0/event=0x08/ (68.10%) 22,428,964,974 armv8_pmuv3_1/event=0x08/ (31.90%) [ mingo: Clarified the changelog. ] Fixes: ef54c1a476aef ("perf: Rework perf_event_exit_event()") Suggested-by: Peter Zijlstra Signed-off-by: Yeoreum Yun Signed-off-by: Ingo Molnar Tested-by: Leo Yan Link: https://lore.kernel.org/r/20250326082003.1630986-1-yeoreum.yun@arm.com Signed-off-by: Sasha Levin --- kernel/events/core.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index cf2ec0a1582f..b5ccf52bb71b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2407,6 +2407,7 @@ ctx_time_update_event(struct perf_event_context *ctx, struct perf_event *event) #define DETACH_GROUP 0x01UL #define DETACH_CHILD 0x02UL #define DETACH_DEAD 0x04UL +#define DETACH_EXIT 0x08UL /* * Cross CPU call to remove a performance event @@ -2421,6 +2422,7 @@ __perf_remove_from_context(struct perf_event *event, void *info) { struct perf_event_pmu_context *pmu_ctx = event->pmu_ctx; + enum perf_event_state state = PERF_EVENT_STATE_OFF; unsigned long flags = (unsigned long)info; ctx_time_update(cpuctx, ctx); @@ -2429,16 +2431,19 @@ __perf_remove_from_context(struct perf_event *event, * Ensure event_sched_out() switches to OFF, at the very least * this avoids raising perf_pending_task() at this time. */ - if (flags & DETACH_DEAD) + if (flags & DETACH_EXIT) + state = PERF_EVENT_STATE_EXIT; + if (flags & DETACH_DEAD) { event->pending_disable = 1; + state = PERF_EVENT_STATE_DEAD; + } event_sched_out(event, ctx); + perf_event_set_state(event, min(event->state, state)); if (flags & DETACH_GROUP) perf_group_detach(event); if (flags & DETACH_CHILD) perf_child_detach(event); list_del_event(event, ctx); - if (flags & DETACH_DEAD) - event->state = PERF_EVENT_STATE_DEAD; if (!pmu_ctx->nr_events) { pmu_ctx->rotate_necessary = 0; @@ -13343,12 +13348,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx) mutex_lock(&parent_event->child_mutex); } - perf_remove_from_context(event, detach_flags); - - raw_spin_lock_irq(&ctx->lock); - if (event->state > PERF_EVENT_STATE_EXIT) - perf_event_set_state(event, PERF_EVENT_STATE_EXIT); - raw_spin_unlock_irq(&ctx->lock); + perf_remove_from_context(event, detach_flags | DETACH_EXIT); /* * Child events can be freed. From 7de8290a66df7229eb78b0ae5249f4bcef0a253f Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sun, 6 Apr 2025 11:18:39 -0400 Subject: [PATCH 25/29] tools/power turbostat: report CoreThr per measurement interval [ Upstream commit f729775f79a9c942c6c82ed6b44bd030afe10423 ] The CoreThr column displays total thermal throttling events since boot time. Change it to report events during the measurement interval. This is more useful for showing a user the current conditions. Total events since boot time are still available to the user via /sys/devices/system/cpu/cpu*/thermal_throttle/* Document CoreThr on turbostat.8 Fixes: eae97e053fe30 ("turbostat: Support thermal throttle count print") Reported-by: Arjan van de Ven Signed-off-by: Len Brown Cc: Chen Yu Signed-off-by: Sasha Levin --- tools/power/x86/turbostat/turbostat.8 | 2 ++ tools/power/x86/turbostat/turbostat.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 56c7ff6efcda..a3cf1d17163a 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -168,6 +168,8 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. .PP +\fBCoreThr\fP Core Thermal Throttling events during the measurement interval. Note that events since boot can be find in /sys/devices/system/cpu/cpu*/thermal_throttle/* +.PP \fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms or /sys/class/drm/card0/gt/gt0/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used. .PP \fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 235e82fe7d0a..77ef60980ee5 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3242,7 +3242,7 @@ void delta_core(struct core_data *new, struct core_data *old) old->c6 = new->c6 - old->c6; old->c7 = new->c7 - old->c7; old->core_temp_c = new->core_temp_c; - old->core_throt_cnt = new->core_throt_cnt; + old->core_throt_cnt = new->core_throt_cnt - old->core_throt_cnt; old->mc6_us = new->mc6_us - old->mc6_us; DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value); From 387dc88c2c27c33f6c0422fb79c6470b06b3c046 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:05 -0500 Subject: [PATCH 26/29] tracing: Switch trace_events_hist.c code over to use guard() [ Upstream commit 2b36a97aeeb71b1e4a48bfedc7f21f44aeb1e6fb ] There are a couple functions in trace_events_hist.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201345.694601480@goodmis.org Signed-off-by: Steven Rostedt (Google) Stable-dep-of: 0b4ffbe4888a ("tracing: Correct the refcount if the hist/hist_debug file fails to open") Signed-off-by: Sasha Levin --- kernel/trace/trace_events_hist.c | 32 ++++++++++---------------------- 1 file changed, 10 insertions(+), 22 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 31f5ad322fab..5d344bc690d9 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5597,25 +5597,19 @@ static int hist_show(struct seq_file *m, void *v) { struct event_trigger_data *data; struct trace_event_file *event_file; - int n = 0, ret = 0; + int n = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); event_file = event_file_file(m->private); - if (unlikely(!event_file)) { - ret = -ENODEV; - goto out_unlock; - } + if (unlikely(!event_file)) + return -ENODEV; list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } - - out_unlock: - mutex_unlock(&event_mutex); - - return ret; + return 0; } static int event_hist_open(struct inode *inode, struct file *file) @@ -5876,25 +5870,19 @@ static int hist_debug_show(struct seq_file *m, void *v) { struct event_trigger_data *data; struct trace_event_file *event_file; - int n = 0, ret = 0; + int n = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); event_file = event_file_file(m->private); - if (unlikely(!event_file)) { - ret = -ENODEV; - goto out_unlock; - } + if (unlikely(!event_file)) + return -ENODEV; list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_debug_show(m, data, n++); } - - out_unlock: - mutex_unlock(&event_mutex); - - return ret; + return 0; } static int event_hist_debug_open(struct inode *inode, struct file *file) From fe87f8d3a5b485eb8fc605d37437c8a70bf89731 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 27 Dec 2024 13:07:57 +0900 Subject: [PATCH 27/29] tracing/hist: Add poll(POLLIN) support on hist file [ Upstream commit 1bd13edbbed6e7e396f1aab92b224a4775218e68 ] Add poll syscall support on the `hist` file. The Waiter will be waken up when the histogram is updated with POLLIN. Currently, there is no way to wait for a specific event in userspace. So user needs to peek the `trace` periodicaly, or wait on `trace_pipe`. But it is not a good idea to peek at the `trace` for an event that randomly happens. And `trace_pipe` is not coming back until a page is filled with events. This allows a user to wait for a specific event on the `hist` file. User can set a histogram trigger on the event which they want to monitor and poll() on its `hist` file. Since this poll() returns POLLIN, the next poll() will return soon unless a read() happens on that hist file. NOTE: To read the hist file again, you must set the file offset to 0, but just for monitoring the event, you may not need to read the histogram. Cc: Shuah Khan Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173527247756.464571.14236296701625509931.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) Stable-dep-of: 0b4ffbe4888a ("tracing: Correct the refcount if the hist/hist_debug file fails to open") Signed-off-by: Sasha Levin --- include/linux/trace_events.h | 14 +++++++ kernel/trace/trace_events.c | 14 +++++++ kernel/trace/trace_events_hist.c | 70 ++++++++++++++++++++++++++++++-- 3 files changed, 95 insertions(+), 3 deletions(-) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 77769ff50544..fcf5a64d5cfe 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -689,6 +689,20 @@ struct trace_event_file { atomic_t tm_ref; /* trigger-mode reference counter */ }; +#ifdef CONFIG_HIST_TRIGGERS +extern struct irq_work hist_poll_work; +extern wait_queue_head_t hist_poll_wq; + +static inline void hist_poll_wakeup(void) +{ + if (wq_has_sleeper(&hist_poll_wq)) + irq_work_queue(&hist_poll_work); +} + +#define hist_poll_wait(file, wait) \ + poll_wait(file, &hist_poll_wq, wait) +#endif + #define __TRACE_EVENT_FLAGS(name, value) \ static int __init trace_init_flags_##name(void) \ { \ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ea9b44847ce6..29eba68e0785 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3111,6 +3111,20 @@ static bool event_in_systems(struct trace_event_call *call, return !*p || isspace(*p) || *p == ','; } +#ifdef CONFIG_HIST_TRIGGERS +/* + * Wake up waiter on the hist_poll_wq from irq_work because the hist trigger + * may happen in any context. + */ +static void hist_poll_event_irq_work(struct irq_work *work) +{ + wake_up_all(&hist_poll_wq); +} + +DEFINE_IRQ_WORK(hist_poll_work, hist_poll_event_irq_work); +DECLARE_WAIT_QUEUE_HEAD(hist_poll_wq); +#endif + static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5d344bc690d9..9e33cd2a73b5 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5314,6 +5314,8 @@ static void event_hist_trigger(struct event_trigger_data *data, if (resolve_var_refs(hist_data, key, var_ref_vals, true)) hist_trigger_actions(hist_data, elt, buffer, rec, rbe, key, var_ref_vals); + + hist_poll_wakeup(); } static void hist_trigger_stacktrace_print(struct seq_file *m, @@ -5593,15 +5595,36 @@ static void hist_trigger_show(struct seq_file *m, n_entries, (u64)atomic64_read(&hist_data->map->drops)); } +struct hist_file_data { + struct file *file; + u64 last_read; +}; + +static u64 get_hist_hit_count(struct trace_event_file *event_file) +{ + struct hist_trigger_data *hist_data; + struct event_trigger_data *data; + u64 ret = 0; + + list_for_each_entry(data, &event_file->triggers, list) { + if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) { + hist_data = data->private_data; + ret += atomic64_read(&hist_data->map->hits); + } + } + return ret; +} + static int hist_show(struct seq_file *m, void *v) { + struct hist_file_data *hist_file = m->private; struct event_trigger_data *data; struct trace_event_file *event_file; int n = 0; guard(mutex)(&event_mutex); - event_file = event_file_file(m->private); + event_file = event_file_file(hist_file->file); if (unlikely(!event_file)) return -ENODEV; @@ -5609,27 +5632,68 @@ static int hist_show(struct seq_file *m, void *v) if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } + hist_file->last_read = get_hist_hit_count(event_file); + return 0; } +static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wait) +{ + struct trace_event_file *event_file; + struct seq_file *m = file->private_data; + struct hist_file_data *hist_file = m->private; + + guard(mutex)(&event_mutex); + + event_file = event_file_data(file); + if (!event_file) + return EPOLLERR; + + hist_poll_wait(file, wait); + + if (hist_file->last_read != get_hist_hit_count(event_file)) + return EPOLLIN | EPOLLRDNORM; + + return 0; +} + +static int event_hist_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct hist_file_data *hist_file = m->private; + + kfree(hist_file); + return tracing_single_release_file_tr(inode, file); +} + static int event_hist_open(struct inode *inode, struct file *file) { + struct hist_file_data *hist_file; int ret; ret = tracing_open_file_tr(inode, file); if (ret) return ret; + hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL); + if (!hist_file) + return -ENOMEM; + hist_file->file = file; + /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; - return single_open(file, hist_show, file); + ret = single_open(file, hist_show, hist_file); + if (ret) + kfree(hist_file); + return ret; } const struct file_operations event_hist_fops = { .open = event_hist_open, .read = seq_read, .llseek = seq_lseek, - .release = tracing_single_release_file_tr, + .release = event_hist_release, + .poll = event_hist_poll, }; #ifdef CONFIG_HIST_TRIGGERS_DEBUG From eecb62a24b23b89169a6b25a00b47626b322abb8 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 27 Dec 2024 13:08:07 +0900 Subject: [PATCH 28/29] tracing/hist: Support POLLPRI event for poll on histogram [ Upstream commit 66fc6f521a0b91051ce6968a216a30bc52267bf8 ] Since POLLIN will not be flushed until the hist file is read, the user needs to repeatedly read() and poll() on the hist file for monitoring the event continuously. But the read() is somewhat redundant when the user is only monitoring for event updates. Add POLLPRI poll event on the hist file so the event returns when a histogram is updated after open(), poll() or read(). Thus it is possible to wait for the next event without having to issue a read(). Cc: Shuah Khan Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173527248770.464571.2536902137325258133.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) Stable-dep-of: 0b4ffbe4888a ("tracing: Correct the refcount if the hist/hist_debug file fails to open") Signed-off-by: Sasha Levin --- kernel/trace/trace_events_hist.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9e33cd2a73b5..e07d75adab8e 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5598,6 +5598,7 @@ static void hist_trigger_show(struct seq_file *m, struct hist_file_data { struct file *file; u64 last_read; + u64 last_act; }; static u64 get_hist_hit_count(struct trace_event_file *event_file) @@ -5633,6 +5634,11 @@ static int hist_show(struct seq_file *m, void *v) hist_trigger_show(m, data, n++); } hist_file->last_read = get_hist_hit_count(event_file); + /* + * Update last_act too so that poll()/POLLPRI can wait for the next + * event after any syscall on hist file. + */ + hist_file->last_act = hist_file->last_read; return 0; } @@ -5642,6 +5648,8 @@ static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wai struct trace_event_file *event_file; struct seq_file *m = file->private_data; struct hist_file_data *hist_file = m->private; + __poll_t ret = 0; + u64 cnt; guard(mutex)(&event_mutex); @@ -5651,10 +5659,15 @@ static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wai hist_poll_wait(file, wait); - if (hist_file->last_read != get_hist_hit_count(event_file)) - return EPOLLIN | EPOLLRDNORM; + cnt = get_hist_hit_count(event_file); + if (hist_file->last_read != cnt) + ret |= EPOLLIN | EPOLLRDNORM; + if (hist_file->last_act != cnt) { + hist_file->last_act = cnt; + ret |= EPOLLPRI; + } - return 0; + return ret; } static int event_hist_release(struct inode *inode, struct file *file) @@ -5668,6 +5681,7 @@ static int event_hist_release(struct inode *inode, struct file *file) static int event_hist_open(struct inode *inode, struct file *file) { + struct trace_event_file *event_file; struct hist_file_data *hist_file; int ret; @@ -5675,16 +5689,25 @@ static int event_hist_open(struct inode *inode, struct file *file) if (ret) return ret; + guard(mutex)(&event_mutex); + + event_file = event_file_data(file); + if (!event_file) + return -ENODEV; + hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL); if (!hist_file) return -ENOMEM; + hist_file->file = file; + hist_file->last_act = get_hist_hit_count(event_file); /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; ret = single_open(file, hist_show, hist_file); if (ret) kfree(hist_file); + return ret; } From ef79f2dec7a9df7f935530410727bb6b0ec82496 Mon Sep 17 00:00:00 2001 From: Tengda Wu Date: Fri, 14 Mar 2025 06:53:35 +0000 Subject: [PATCH 29/29] tracing: Correct the refcount if the hist/hist_debug file fails to open [ Upstream commit 0b4ffbe4888a2c71185eaf5c1a02dd3586a9bc04 ] The function event_{hist,hist_debug}_open() maintains the refcount of 'file->tr' and 'file' through tracing_open_file_tr(). However, it does not roll back these counts on subsequent failure paths, resulting in a refcount leak. A very obvious case is that if the hist/hist_debug file belongs to a specific instance, the refcount leak will prevent the deletion of that instance, as it relies on the condition 'tr->ref == 1' within __remove_instance(). Fix this by calling tracing_release_file_tr() on all failure paths in event_{hist,hist_debug}_open() to correct the refcount. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Zheng Yejian Link: https://lore.kernel.org/20250314065335.1202817-1-wutengda@huaweicloud.com Fixes: 1cc111b9cddc ("tracing: Fix uaf issue when open the hist or hist_debug file") Signed-off-by: Tengda Wu Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace_events_hist.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index e07d75adab8e..4ebafc655223 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5692,12 +5692,16 @@ static int event_hist_open(struct inode *inode, struct file *file) guard(mutex)(&event_mutex); event_file = event_file_data(file); - if (!event_file) - return -ENODEV; + if (!event_file) { + ret = -ENODEV; + goto err; + } hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL); - if (!hist_file) - return -ENOMEM; + if (!hist_file) { + ret = -ENOMEM; + goto err; + } hist_file->file = file; hist_file->last_act = get_hist_hit_count(event_file); @@ -5705,9 +5709,14 @@ static int event_hist_open(struct inode *inode, struct file *file) /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; ret = single_open(file, hist_show, hist_file); - if (ret) + if (ret) { kfree(hist_file); + goto err; + } + return 0; +err: + tracing_release_file_tr(inode, file); return ret; } @@ -5982,7 +5991,10 @@ static int event_hist_debug_open(struct inode *inode, struct file *file) /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; - return single_open(file, hist_debug_show, file); + ret = single_open(file, hist_debug_show, file); + if (ret) + tracing_release_file_tr(inode, file); + return ret; } const struct file_operations event_hist_debug_fops = {