From 4bc12818b363bd30f0f7348dd9ab077290a637ae Mon Sep 17 00:00:00 2001 From: Bui Quang Minh Date: Thu, 17 Apr 2025 14:28:03 +0700 Subject: [PATCH 01/16] virtio-net: disable delayed refill when pausing rx When pausing rx (e.g. set up xdp, xsk pool, rx resize), we call napi_disable() on the receive queue's napi. In delayed refill_work, it also calls napi_disable() on the receive queue's napi. When napi_disable() is called on an already disabled napi, it will sleep in napi_disable_locked while still holding the netdev_lock. As a result, later napi_enable gets stuck too as it cannot acquire the netdev_lock. This leads to refill_work and the pause-then-resume tx are stuck altogether. This scenario can be reproducible by binding a XDP socket to virtio-net interface without setting up the fill ring. As a result, try_fill_recv will fail until the fill ring is set up and refill_work is scheduled. This commit adds virtnet_rx_(pause/resume)_all helpers and fixes up the virtnet_rx_resume to disable future and cancel all inflights delayed refill_work before calling napi_disable() to pause the rx. Fixes: 413f0271f396 ("net: protect NAPI enablement with netdev_lock()") Acked-by: Michael S. Tsirkin Signed-off-by: Bui Quang Minh Acked-by: Jason Wang Link: https://patch.msgid.link/20250417072806.18660-2-minhquangbui99@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 69 +++++++++++++++++++++++++++++++++------- 1 file changed, 57 insertions(+), 12 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 7e4617216a4b..848fab51dfa1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3342,7 +3342,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) +static void __virtnet_rx_pause(struct virtnet_info *vi, + struct receive_queue *rq) { bool running = netif_running(vi->dev); @@ -3352,17 +3353,63 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) } } -static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) +static void virtnet_rx_pause_all(struct virtnet_info *vi) +{ + int i; + + /* + * Make sure refill_work does not run concurrently to + * avoid napi_disable race which leads to deadlock. + */ + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + for (i = 0; i < vi->max_queue_pairs; i++) + __virtnet_rx_pause(vi, &vi->rq[i]); +} + +static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) +{ + /* + * Make sure refill_work does not run concurrently to + * avoid napi_disable race which leads to deadlock. + */ + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + __virtnet_rx_pause(vi, rq); +} + +static void __virtnet_rx_resume(struct virtnet_info *vi, + struct receive_queue *rq, + bool refill) { bool running = netif_running(vi->dev); - if (!try_fill_recv(vi, rq, GFP_KERNEL)) + if (refill && !try_fill_recv(vi, rq, GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); if (running) virtnet_napi_enable(rq); } +static void virtnet_rx_resume_all(struct virtnet_info *vi) +{ + int i; + + enable_delayed_refill(vi); + for (i = 0; i < vi->max_queue_pairs; i++) { + if (i < vi->curr_queue_pairs) + __virtnet_rx_resume(vi, &vi->rq[i], true); + else + __virtnet_rx_resume(vi, &vi->rq[i], false); + } +} + +static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) +{ + enable_delayed_refill(vi); + __virtnet_rx_resume(vi, rq, true); +} + static int virtnet_rx_resize(struct virtnet_info *vi, struct receive_queue *rq, u32 ring_num) { @@ -5959,12 +6006,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (prog) bpf_prog_add(prog, vi->max_queue_pairs - 1); + virtnet_rx_pause_all(vi); + /* Make sure NAPI is not using any XDP TX queues for RX. */ if (netif_running(dev)) { - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_disable(&vi->rq[i]); + for (i = 0; i < vi->max_queue_pairs; i++) virtnet_napi_tx_disable(&vi->sq[i]); - } } if (!prog) { @@ -5996,13 +6043,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, vi->xdp_enabled = false; } + virtnet_rx_resume_all(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev)) { - virtnet_napi_enable(&vi->rq[i]); + if (netif_running(dev)) virtnet_napi_tx_enable(&vi->sq[i]); - } } return 0; @@ -6014,11 +6060,10 @@ err: rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); } + virtnet_rx_resume_all(vi); if (netif_running(dev)) { - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_enable(&vi->rq[i]); + for (i = 0; i < vi->max_queue_pairs; i++) virtnet_napi_tx_enable(&vi->sq[i]); - } } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); -- 2.51.0 From d63527e109e811ef11abb1c2985048fdb528b4cb Mon Sep 17 00:00:00 2001 From: Tung Nguyen Date: Thu, 17 Apr 2025 14:47:15 +0700 Subject: [PATCH 02/16] tipc: fix NULL pointer dereference in tipc_mon_reinit_self() syzbot reported: tipc: Node number set to 1055423674 Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 3 UID: 0 PID: 6017 Comm: kworker/3:5 Not tainted 6.15.0-rc1-syzkaller-00246-g900241a5cc15 #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Workqueue: events tipc_net_finalize_work RIP: 0010:tipc_mon_reinit_self+0x11c/0x210 net/tipc/monitor.c:719 ... RSP: 0018:ffffc9000356fb68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 000000003ee87cba RDX: 0000000000000000 RSI: ffffffff8dbc56a7 RDI: ffff88804c2cc010 RBP: dffffc0000000000 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000007 R13: fffffbfff2111097 R14: ffff88804ead8000 R15: ffff88804ead9010 FS: 0000000000000000(0000) GS:ffff888097ab9000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000f720eb00 CR3: 000000000e182000 CR4: 0000000000352ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tipc_net_finalize+0x10b/0x180 net/tipc/net.c:140 process_one_work+0x9cc/0x1b70 kernel/workqueue.c:3238 process_scheduled_works kernel/workqueue.c:3319 [inline] worker_thread+0x6c8/0xf10 kernel/workqueue.c:3400 kthread+0x3c2/0x780 kernel/kthread.c:464 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:153 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 ... RIP: 0010:tipc_mon_reinit_self+0x11c/0x210 net/tipc/monitor.c:719 ... RSP: 0018:ffffc9000356fb68 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 000000003ee87cba RDX: 0000000000000000 RSI: ffffffff8dbc56a7 RDI: ffff88804c2cc010 RBP: dffffc0000000000 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000007 R13: fffffbfff2111097 R14: ffff88804ead8000 R15: ffff88804ead9010 FS: 0000000000000000(0000) GS:ffff888097ab9000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000f720eb00 CR3: 000000000e182000 CR4: 0000000000352ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 There is a racing condition between workqueue created when enabling bearer and another thread created when disabling bearer right after that as follow: enabling_bearer | disabling_bearer --------------- | ---------------- tipc_disc_timeout() | { | bearer_disable() ... | { schedule_work(&tn->work); | tipc_mon_delete() ... | { } | ... | write_lock_bh(&mon->lock); | mon->self = NULL; | write_unlock_bh(&mon->lock); | ... | } tipc_net_finalize_work() | } { | ... | tipc_net_finalize() | { | ... | tipc_mon_reinit_self() | { | ... | write_lock_bh(&mon->lock); | mon->self->addr = tipc_own_addr(net); | write_unlock_bh(&mon->lock); | ... | } | ... | } | ... | } | 'mon->self' is set to NULL in disabling_bearer thread and dereferenced later in enabling_bearer thread. This commit fixes this issue by validating 'mon->self' before assigning node address to it. Reported-by: syzbot+ed60da8d686dc709164c@syzkaller.appspotmail.com Fixes: 46cb01eeeb86 ("tipc: update mon's self addr when node addr generated") Signed-off-by: Tung Nguyen Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250417074826.578115-1-tung.quang.nguyen@est.tech Signed-off-by: Jakub Kicinski --- net/tipc/monitor.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index e2f19627e43d..b45c5b91bc7a 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -716,7 +716,8 @@ void tipc_mon_reinit_self(struct net *net) if (!mon) continue; write_lock_bh(&mon->lock); - mon->self->addr = tipc_own_addr(net); + if (mon->self) + mon->self->addr = tipc_own_addr(net); write_unlock_bh(&mon->lock); } } -- 2.51.0 From 491ef1117c56476f199b481f8c68820fe4c3a7c2 Mon Sep 17 00:00:00 2001 From: Bo-Cun Chen Date: Thu, 17 Apr 2025 17:41:07 +0100 Subject: [PATCH 03/16] net: ethernet: mtk_eth_soc: net: revise NETSYSv3 hardware configuration Change hardware configuration for the NETSYSv3. - Enable PSE dummy page mechanism for the GDM1/2/3 - Enable PSE drop mechanism when the WDMA Rx ring full - Enable PSE no-drop mechanism for packets from the WDMA Tx - Correct PSE free drop threshold - Correct PSE CDMA high threshold Fixes: 1953f134a1a8b ("net: ethernet: mtk_eth_soc: add NETSYS_V3 version support") Signed-off-by: Bo-Cun Chen Signed-off-by: Daniel Golle Reviewed-by: Simon Horman Link: https://patch.msgid.link/b71f8fd9d4bb69c646c4d558f9331dd965068606.1744907886.git.daniel@makrotopia.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 24 +++++++++++++++++---- drivers/net/ethernet/mediatek/mtk_eth_soc.h | 10 ++++++++- 2 files changed, 29 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index bdb98c9d8b1c..47807b202310 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4043,11 +4043,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP); if (mtk_is_netsys_v3_or_greater(eth)) { - /* PSE should not drop port1, port8 and port9 packets */ - mtk_w32(eth, 0x00000302, PSE_DROP_CFG); + /* PSE dummy page mechanism */ + mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) | + PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ); + + /* PSE free buffer drop threshold */ + mtk_w32(eth, 0x00600009, PSE_IQ_REV(8)); + + /* PSE should not drop port8, port9 and port13 packets from + * WDMA Tx + */ + mtk_w32(eth, 0x00002300, PSE_DROP_CFG); + + /* PSE should drop packets to port8, port9 and port13 on WDMA Rx + * ring full + */ + mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0)); + mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1)); + mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2)); /* GDM and CDM Threshold */ - mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES); + mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES); mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES); /* Disable GDM1 RX CRC stripping */ @@ -4064,7 +4080,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) mtk_w32(eth, 0x00000300, PSE_DROP_CFG); /* PSE should drop packets to port 8/9 on WDMA Rx ring full */ - mtk_w32(eth, 0x00000300, PSE_PPE0_DROP); + mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0)); /* PSE Free Queue Flow Control */ mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 39709649ea8d..88ef2e9c50fc 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -151,7 +151,15 @@ #define PSE_FQFC_CFG1 0x100 #define PSE_FQFC_CFG2 0x104 #define PSE_DROP_CFG 0x108 -#define PSE_PPE0_DROP 0x110 +#define PSE_PPE_DROP(x) (0x110 + ((x) * 0x4)) + +/* PSE Last FreeQ Page Request Control */ +#define PSE_DUMY_REQ 0x10C +/* PSE_DUMY_REQ is not a typo but actually called like that also in + * MediaTek's datasheet + */ +#define PSE_DUMMY_WORK_GDM(x) BIT(16 + (x)) +#define DUMMY_PAGE_THR 0x1 /* PSE Input Queue Reservation Register*/ #define PSE_IQ_REV(x) (0x140 + (((x) - 1) << 2)) -- 2.51.0 From 13b4ece33cf9def67966bb8716783c42cec20617 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Mon, 21 Apr 2025 19:07:13 +0200 Subject: [PATCH 04/16] mptcp: pm: Defer freeing of MPTCP userspace path manager entries When path manager entries are deleted from the local address list, they are first unlinked from the address list using list_del_rcu(). The entries must not be freed until after the RCU grace period, but the existing code immediately frees the entry. Use kfree_rcu_mightsleep() and adjust sk_omem_alloc in open code instead of using the sock_kfree_s() helper. This code path is only called in a netlink handler, so the "might sleep" function is preferable to adding a rarely-used rcu_head member to struct mptcp_pm_addr_entry. Fixes: 88d097316371 ("mptcp: drop free_list for deleting entries") Cc: stable@vger.kernel.org Signed-off-by: Mat Martineau Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250421-net-mptcp-pm-defer-freeing-v1-1-e731dc6e86b9@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 2cb62f026b1f..a715dcbe0146 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -337,7 +337,11 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) release_sock(sk); - sock_kfree_s(sk, match, sizeof(*match)); + kfree_rcu_mightsleep(match); + /* Adjust sk_omem_alloc like sock_kfree_s() does, to match + * with allocation of this memory by sock_kmemdup() + */ + atomic_sub(sizeof(*match), &sk->sk_omem_alloc); err = 0; out: -- 2.51.0 From ce72fea219c13c6485503928181c547d0e26756b Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Mon, 21 Apr 2025 19:07:14 +0200 Subject: [PATCH 05/16] selftests: mptcp: diag: use mptcp_lib_get_info_value When running diag.sh in a loop, chk_dump_one will report the following "grep: write error": 13 ....chk 2 cestab [ OK ] grep: write error 14 ....chk dump_one [ OK ] 15 ....chk 2->0 msk in use after flush [ OK ] 16 ....chk 2->0 cestab after flush [ OK ] This error is caused by a broken pipe. When the output of 'ss' is processed by grep, 'head -n 1' will exit immediately after getting the first line, causing the subsequent pipe to close. At this time, if 'grep' is still trying to write data to the closed pipe, it will trigger a SIGPIPE signal, causing a write error. One solution is not to use this problematic "head -n 1" command, but to use mptcp_lib_get_info_value() helper defined in mptcp_lib.sh to get the value of 'token'. Fixes: ba2400166570 ("selftests: mptcp: add a test for mptcp_diag_dump_one") Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Tested-by: Gang Yan Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250421-net-mptcp-pm-defer-freeing-v1-2-e731dc6e86b9@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/diag.sh | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 4f55477ffe08..e7a75341f0f3 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -206,9 +206,8 @@ chk_dump_one() local token local msg - ss_token="$(ss -inmHMN $ns | grep 'token:' |\ - head -n 1 |\ - sed 's/.*token:\([0-9a-f]*\).*/\1/')" + ss_token="$(ss -inmHMN $ns | + mptcp_lib_get_info_value "token" "token")" token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\ awk -F':[ \t]+' '/^token/ {print $2}')" -- 2.51.0 From 3df275ef0a6ae181e8428a6589ef5d5231e58b5c Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Apr 2025 11:47:30 -0700 Subject: [PATCH 06/16] net_sched: hfsc: Fix a UAF vulnerability in class handling This patch fixes a Use-After-Free vulnerability in the HFSC qdisc class handling. The issue occurs due to a time-of-check/time-of-use condition in hfsc_change_class() when working with certain child qdiscs like netem or codel. The vulnerability works as follows: 1. hfsc_change_class() checks if a class has packets (q.qlen != 0) 2. It then calls qdisc_peek_len(), which for certain qdiscs (e.g., codel, netem) might drop packets and empty the queue 3. The code continues assuming the queue is still non-empty, adding the class to vttree 4. This breaks HFSC scheduler assumptions that only non-empty classes are in vttree 5. Later, when the class is destroyed, this can lead to a Use-After-Free The fix adds a second queue length check after qdisc_peek_len() to verify the queue wasn't emptied. Fixes: 21f4d5cc25ec ("net_sched/hfsc: fix curve activation in hfsc_change_class()") Reported-by: Gerrard Tai Reviewed-by: Konstantin Khlebnikov Signed-off-by: Cong Wang Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20250417184732.943057-2-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski --- net/sched/sch_hfsc.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index ce5045eea065..b368ac0595d5 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -961,6 +961,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl != NULL) { int old_flags; + int len = 0; if (parentid) { if (cl->cl_parent && @@ -991,9 +992,13 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (usc != NULL) hfsc_change_usc(cl, usc, cur_time); + if (cl->qdisc->q.qlen != 0) + len = qdisc_peek_len(cl->qdisc); + /* Check queue length again since some qdisc implementations + * (e.g., netem/codel) might empty the queue during the peek + * operation. + */ if (cl->qdisc->q.qlen != 0) { - int len = qdisc_peek_len(cl->qdisc); - if (cl->cl_flags & HFSC_RSC) { if (old_flags & HFSC_RSC) update_ed(cl, len); -- 2.51.0 From 6ccbda44e2cc3d26fd22af54c650d6d5d801addf Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Apr 2025 11:47:31 -0700 Subject: [PATCH 07/16] net_sched: hfsc: Fix a potential UAF in hfsc_dequeue() too Similarly to the previous patch, we need to safe guard hfsc_dequeue() too. But for this one, we don't have a reliable reproducer. Fixes: 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 ("Linux-2.6.12-rc2") Reported-by: Gerrard Tai Signed-off-by: Cong Wang Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20250417184732.943057-3-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski --- net/sched/sch_hfsc.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b368ac0595d5..6c8ef826cec0 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1641,10 +1641,16 @@ hfsc_dequeue(struct Qdisc *sch) if (cl->qdisc->q.qlen != 0) { /* update ed */ next_len = qdisc_peek_len(cl->qdisc); - if (realtime) - update_ed(cl, next_len); - else - update_d(cl, next_len); + /* Check queue length again since some qdisc implementations + * (e.g., netem/codel) might empty the queue during the peek + * operation. + */ + if (cl->qdisc->q.qlen != 0) { + if (realtime) + update_ed(cl, next_len); + else + update_d(cl, next_len); + } } else { /* the class becomes passive */ eltree_remove(cl); -- 2.51.0 From 7629d1a04ad2e76709401b655263040486972c2c Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Apr 2025 11:47:32 -0700 Subject: [PATCH 08/16] selftests/tc-testing: Add test for HFSC queue emptying during peek operation Add a selftest to exercise the condition where qdisc implementations like netem or codel might empty the queue during a peek operation. This tests the defensive code path in HFSC that checks the queue length again after peeking to handle this case. Based on the reproducer from Gerrard, improved by Jamal. Reported-by: Gerrard Tai Signed-off-by: Cong Wang Tested-by: Victor Nogueira Reviewed-by: Jamal Hadi Salim Link: https://patch.msgid.link/20250417184732.943057-4-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski --- .../tc-testing/tc-tests/infra/qdiscs.json | 39 +++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index d4ea9cd845a3..e26bbc169783 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -313,5 +313,44 @@ "$TC qdisc del dev $DUMMY handle 1: root", "$IP addr del 10.10.10.10/24 dev $DUMMY || true" ] + }, + { + "id": "a4c3", + "name": "Test HFSC with netem/blackhole - queue emptying during peek operation", + "category": [ + "qdisc", + "hfsc", + "netem", + "blackhole" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY handle 1:0 root drr", + "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr", + "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024", + "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1", + "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit", + "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms", + "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole", + "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true", + "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit", + "$TC class del dev $DUMMY parent 3:0 classid 3:1", + "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit", + "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true" + ], + "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1:0 root", + "$IP addr del 10.10.10.10/24 dev $DUMMY || true" + ] } ] -- 2.51.0 From 497041d763016c2e8314d2f6a329a9b77c3797ca Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Tue, 22 Apr 2025 04:10:20 +0100 Subject: [PATCH 09/16] net: dsa: mt7530: sync driver-specific behavior of MT7531 variants MT7531 standalone and MMIO variants found in MT7988 and EN7581 share most basic properties. Despite that, assisted_learning_on_cpu_port and mtu_enforcement_ingress were only applied for MT7531 but not for MT7988 or EN7581, causing the expected issues on MMIO devices. Apply both settings equally also for MT7988 and EN7581 by moving both assignments form mt7531_setup() to mt7531_setup_common(). This fixes unwanted flooding of packets due to unknown unicast during DA lookup, as well as issues with heterogenous MTU settings. Fixes: 7f54cc9772ce ("net: dsa: mt7530: split-off common parts from mt7531_setup") Signed-off-by: Daniel Golle Reviewed-by: Chester A. Unal Link: https://patch.msgid.link/89ed7ec6d4fa0395ac53ad2809742bb1ce61ed12.1745290867.git.daniel@makrotopia.org Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mt7530.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d70399bce5b9..c5d6628d7980 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2419,6 +2419,9 @@ mt7531_setup_common(struct dsa_switch *ds) struct mt7530_priv *priv = ds->priv; int ret, i; + ds->assisted_learning_on_cpu_port = true; + ds->mtu_enforcement_ingress = true; + mt753x_trap_frames(priv); /* Enable and reset MIB counters */ @@ -2571,9 +2574,6 @@ mt7531_setup(struct dsa_switch *ds) if (ret) return ret; - ds->assisted_learning_on_cpu_port = true; - ds->mtu_enforcement_ingress = true; - return 0; } -- 2.51.0 From d9e2f070d8af60f2c8c02b2ddf0a9e90b4e9220c Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 21 Apr 2025 10:46:03 -0700 Subject: [PATCH 10/16] pds_core: Prevent possible adminq overflow/stuck condition The pds_core's adminq is protected by the adminq_lock, which prevents more than 1 command to be posted onto it at any one time. This makes it so the client drivers cannot simultaneously post adminq commands. However, the completions happen in a different context, which means multiple adminq commands can be posted sequentially and all waiting on completion. On the FW side, the backing adminq request queue is only 16 entries long and the retry mechanism and/or overflow/stuck prevention is lacking. This can cause the adminq to get stuck, so commands are no longer processed and completions are no longer sent by the FW. As an initial fix, prevent more than 16 outstanding adminq commands so there's no way to cause the adminq from getting stuck. This works because the backing adminq request queue will never have more than 16 pending adminq commands, so it will never overflow. This is done by reducing the adminq depth to 16. Fixes: 45d76f492938 ("pds_core: set up device and adminq") Reviewed-by: Michal Swiatkowski Reviewed-by: Simon Horman Signed-off-by: Brett Creeley Signed-off-by: Shannon Nelson Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250421174606.3892-2-shannon.nelson@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/core.c | 5 +---- drivers/net/ethernet/amd/pds_core/core.h | 2 +- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 1eb0d92786f7..55163457f12b 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -325,10 +325,7 @@ static int pdsc_core_init(struct pdsc *pdsc) size_t sz; int err; - /* Scale the descriptor ring length based on number of CPUs and VFs */ - numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus()); - numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev); - numdescs = roundup_pow_of_two(numdescs); + numdescs = PDSC_ADMINQ_MAX_LENGTH; err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq", PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR, numdescs, diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index 0bf320c43083..199473112c29 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -16,7 +16,7 @@ #define PDSC_WATCHDOG_SECS 5 #define PDSC_QUEUE_NAME_MAX_SZ 16 -#define PDSC_ADMINQ_MIN_LENGTH 16 /* must be a power of two */ +#define PDSC_ADMINQ_MAX_LENGTH 16 /* must be a power of two */ #define PDSC_NOTIFYQ_LENGTH 64 /* must be a power of two */ #define PDSC_TEARDOWN_RECOVERY false #define PDSC_TEARDOWN_REMOVING true -- 2.51.0 From 2567daad69cd1107fc0ec29b1615f110d7cf7385 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 21 Apr 2025 10:46:04 -0700 Subject: [PATCH 11/16] pds_core: handle unsupported PDS_CORE_CMD_FW_CONTROL result If the FW doesn't support the PDS_CORE_CMD_FW_CONTROL command the driver might at the least print garbage and at the worst crash when the user runs the "devlink dev info" devlink command. This happens because the stack variable fw_list is not 0 initialized which results in fw_list.num_fw_slots being a garbage value from the stack. Then the driver tries to access fw_list.fw_names[i] with i >= ARRAY_SIZE and runs off the end of the array. Fix this by initializing the fw_list and by not failing completely if the devcmd fails because other useful information is printed via devlink dev info even if the devcmd fails. Fixes: 45d76f492938 ("pds_core: set up device and adminq") Signed-off-by: Brett Creeley Reviewed-by: Simon Horman Signed-off-by: Shannon Nelson Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250421174606.3892-3-shannon.nelson@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/devlink.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index c5c787df61a4..d8dc39da4161 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -105,7 +105,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, .fw_control.opcode = PDS_CORE_CMD_FW_CONTROL, .fw_control.oper = PDS_CORE_FW_GET_LIST, }; - struct pds_core_fw_list_info fw_list; + struct pds_core_fw_list_info fw_list = {}; struct pdsc *pdsc = devlink_priv(dl); union pds_core_dev_comp comp; char buf[32]; @@ -118,8 +118,6 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, if (!err) memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list)); mutex_unlock(&pdsc->devcmd_lock); - if (err && err != -EIO) - return err; listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names)); for (i = 0; i < listlen; i++) { -- 2.51.0 From f9559d818205a4a0b9cd87181ef46e101ea11157 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 21 Apr 2025 10:46:05 -0700 Subject: [PATCH 12/16] pds_core: Remove unnecessary check in pds_client_adminq_cmd() When the pds_core driver was first created there were some race conditions around using the adminq, especially for client drivers. To reduce the possibility of a race condition there's a check against pf->state in pds_client_adminq_cmd(). This is problematic for a couple of reasons: 1. The PDSC_S_INITING_DRIVER bit is set during probe, but not cleared until after everything in probe is complete, which includes creating the auxiliary devices. For pds_fwctl this means it can't make any adminq commands until after pds_core's probe is complete even though the adminq is fully up by the time pds_fwctl's auxiliary device is created. 2. The race conditions around using the adminq have been fixed and this path is already protected against client drivers calling pds_client_adminq_cmd() if the adminq isn't ready, i.e. see pdsc_adminq_post() -> pdsc_adminq_inc_if_up(). Fix this by removing the pf->state check in pds_client_adminq_cmd() because invalid accesses to pds_core's adminq is already handled by pdsc_adminq_post()->pdsc_adminq_inc_if_up(). Fixes: 10659034c622 ("pds_core: add the aux client API") Reviewed-by: Simon Horman Signed-off-by: Brett Creeley Signed-off-by: Shannon Nelson Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250421174606.3892-4-shannon.nelson@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/auxbus.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c index eeb72b1809ea..c9aac27883a3 100644 --- a/drivers/net/ethernet/amd/pds_core/auxbus.c +++ b/drivers/net/ethernet/amd/pds_core/auxbus.c @@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev, dev_dbg(pf->dev, "%s: %s opcode %d\n", __func__, dev_name(&padev->aux_dev.dev), req->opcode); - if (pf->state) - return -ENXIO; - /* Wrap the client's request */ cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD; cmd.client_request.client_id = cpu_to_le16(padev->client_id); -- 2.51.0 From 3f77c3dfffc7063428b100c4945ca2a7a8680380 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Mon, 21 Apr 2025 10:46:06 -0700 Subject: [PATCH 13/16] pds_core: make wait_context part of q_info Make the wait_context a full part of the q_info struct rather than a stack variable that goes away after pdsc_adminq_post() is done so that the context is still available after the wait loop has given up. There was a case where a slow development firmware caused the adminq request to time out, but then later the FW finally finished the request and sent the interrupt. The handler tried to complete_all() the completion context that had been created on the stack in pdsc_adminq_post() but no longer existed. This caused bad pointer usage, kernel crashes, and much wailing and gnashing of teeth. Fixes: 01ba61b55b20 ("pds_core: Add adminq processing and commands") Reviewed-by: Simon Horman Signed-off-by: Shannon Nelson Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250421174606.3892-5-shannon.nelson@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/adminq.c | 36 +++++++++------------- drivers/net/ethernet/amd/pds_core/core.c | 4 ++- drivers/net/ethernet/amd/pds_core/core.h | 2 +- 3 files changed, 18 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c index c83a0a80d533..506f682d15c1 100644 --- a/drivers/net/ethernet/amd/pds_core/adminq.c +++ b/drivers/net/ethernet/amd/pds_core/adminq.c @@ -5,11 +5,6 @@ #include "core.h" -struct pdsc_wait_context { - struct pdsc_qcq *qcq; - struct completion wait_completion; -}; - static int pdsc_process_notifyq(struct pdsc_qcq *qcq) { union pds_core_notifyq_comp *comp; @@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq) q_info = &q->info[q->tail_idx]; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); - /* Copy out the completion data */ - memcpy(q_info->dest, comp, sizeof(*comp)); - - complete_all(&q_info->wc->wait_completion); + if (!completion_done(&q_info->completion)) { + memcpy(q_info->dest, comp, sizeof(*comp)); + complete(&q_info->completion); + } if (cq->tail_idx == cq->num_descs - 1) cq->done_color = !cq->done_color; @@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data) static int __pdsc_adminq_post(struct pdsc *pdsc, struct pdsc_qcq *qcq, union pds_core_adminq_cmd *cmd, - union pds_core_adminq_comp *comp, - struct pdsc_wait_context *wc) + union pds_core_adminq_comp *comp) { struct pdsc_queue *q = &qcq->q; struct pdsc_q_info *q_info; @@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc, /* Post the request */ index = q->head_idx; q_info = &q->info[index]; - q_info->wc = wc; q_info->dest = comp; memcpy(q_info->desc, cmd, sizeof(*cmd)); + reinit_completion(&q_info->completion); dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n", q->head_idx, q->tail_idx); @@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc, union pds_core_adminq_comp *comp, bool fast_poll) { - struct pdsc_wait_context wc = { - .wait_completion = - COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion), - }; unsigned long poll_interval = 1; unsigned long poll_jiffies; unsigned long time_limit; unsigned long time_start; unsigned long time_done; unsigned long remaining; + struct completion *wc; int err = 0; int index; @@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc, return -ENXIO; } - wc.qcq = &pdsc->adminqcq; - index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc); + index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp); if (index < 0) { err = index; goto err_out; } + wc = &pdsc->adminqcq.q.info[index].completion; time_start = jiffies; time_limit = time_start + HZ * pdsc->devcmd_timeout; do { /* Timeslice the actual wait to catch IO errors etc early */ poll_jiffies = msecs_to_jiffies(poll_interval); - remaining = wait_for_completion_timeout(&wc.wait_completion, - poll_jiffies); + remaining = wait_for_completion_timeout(wc, poll_jiffies); if (remaining) break; @@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc, dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n", __func__, jiffies_to_msecs(time_done - time_start)); - /* Check the results */ - if (time_after_eq(time_done, time_limit)) + /* Check the results and clear an un-completed timeout */ + if (time_after_eq(time_done, time_limit) && !completion_done(wc)) { err = -ETIMEDOUT; + complete(wc); + } dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index); dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1, diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 55163457f12b..9512aa4083f0 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa) q->base = base; q->base_pa = base_pa; - for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) + for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) { cur->desc = base + (i * q->desc_size); + init_completion(&cur->completion); + } } static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa) diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index 199473112c29..0b53a1fab46d 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -96,7 +96,7 @@ struct pdsc_q_info { unsigned int bytes; unsigned int nbufs; struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS]; - struct pdsc_wait_context *wc; + struct completion completion; void *dest; }; -- 2.51.0 From 607b310ada5ef4c738f9dffc758a62a9d309b084 Mon Sep 17 00:00:00 2001 From: Johannes Schneider Date: Wed, 23 Apr 2025 06:47:24 +0200 Subject: [PATCH 14/16] net: dp83822: Fix OF_MDIO config check When CONFIG_OF_MDIO is set to be a module the code block is not compiled. Use the IS_ENABLED macro that checks for both built in as well as module. Fixes: 5dc39fd5ef35 ("net: phy: DP83822: Add ability to advertise Fiber connection") Signed-off-by: Johannes Schneider Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20250423044724.1284492-1-johannes.schneider@leica-geosystems.com Signed-off-by: Paolo Abeni --- drivers/net/phy/dp83822.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 14f361549638..e32013eb0186 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -730,7 +730,7 @@ static int dp83822_phy_reset(struct phy_device *phydev) return phydev->drv->config_init(phydev); } -#ifdef CONFIG_OF_MDIO +#if IS_ENABLED(CONFIG_OF_MDIO) static const u32 tx_amplitude_100base_tx_gain[] = { 80, 82, 83, 85, 87, 88, 90, 92, 93, 95, 97, 98, 100, 102, 103, 105, -- 2.51.0 From 73fa4597bdc035437fbcd84d6be32bd39f1f2149 Mon Sep 17 00:00:00 2001 From: Alexis Lothore Date: Wed, 23 Apr 2025 09:12:09 +0200 Subject: [PATCH 15/16] net: stmmac: fix dwmac1000 ptp timestamp status offset MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit When a PTP interrupt occurs, the driver accesses the wrong offset to learn about the number of available snapshots in the FIFO for dwmac1000: it should be accessing bits 29..25, while it is currently reading bits 19..16 (those are bits about the auxiliary triggers which have generated the timestamps). As a consequence, it does not compute correctly the number of available snapshots, and so possibly do not generate the corresponding clock events if the bogus value ends up being 0. Fix clock events generation by reading the correct bits in the timestamp register for dwmac1000. Fixes: 477c3e1f6363 ("net: stmmac: Introduce dwmac1000 timestamping operations") Signed-off-by: Alexis Lothoré Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20250423-stmmac_ts-v2-1-e2cf2bbd61b1@bootlin.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index 967a16212faf..0c011a47d5a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -320,8 +320,8 @@ enum rtc_control { /* PTP and timestamping registers */ -#define GMAC3_X_ATSNS GENMASK(19, 16) -#define GMAC3_X_ATSNS_SHIFT 16 +#define GMAC3_X_ATSNS GENMASK(29, 25) +#define GMAC3_X_ATSNS_SHIFT 25 #define GMAC_PTP_TCR_ATSFC BIT(24) #define GMAC_PTP_TCR_ATSEN0 BIT(25) -- 2.51.0 From 7b7491372f8ec2d8c08da18e5d629e55f41dda89 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Alexis=20Lothor=C3=A9?= Date: Wed, 23 Apr 2025 09:12:10 +0200 Subject: [PATCH 16/16] net: stmmac: fix multiplication overflow when reading timestamp MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit The current way of reading a timestamp snapshot in stmmac can lead to integer overflow, as the computation is done on 32 bits. The issue has been observed on a dwmac-socfpga platform returning chaotic timestamp values due to this overflow. The corresponding multiplication is done with a MUL instruction, which returns 32 bit values. Explicitly casting the value to 64 bits replaced the MUL with a UMLAL, which computes and returns the result on 64 bits, and so returns correctly the timestamps. Prevent this overflow by explicitly casting the intermediate value to u64 to make sure that the whole computation is made on u64. While at it, apply the same cast on the other dwmac variant (GMAC4) method for snapshot retrieval. Fixes: 477c3e1f6363 ("net: stmmac: Introduce dwmac1000 timestamping operations") Signed-off-by: Alexis Lothoré Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20250423-stmmac_ts-v2-2-e2cf2bbd61b1@bootlin.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index a8b901cdf5cb..56b76aaa58f0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -553,7 +553,7 @@ void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time) u64 ns; ns = readl(ptpaddr + GMAC_PTP_ATNR); - ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC; + ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC; *ptp_time = ns; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 0f59aa982604..e2840fa241f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -222,7 +222,7 @@ static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time) u64 ns; ns = readl(ptpaddr + PTP_ATNR); - ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC; + ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC; *ptp_time = ns; } -- 2.51.0