From 0d1fac6d26aff5df21bb4ec980d9b7a11c410b96 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Wed, 12 Feb 2025 12:15:35 +0100 Subject: net: wwan: mhi_wwan_mbim: Silence sequence number glitch errors When using the Qualcomm X55 modem on the ThinkPad X13s, the kernel log is constantly being filled with errors related to a "sequence number glitch", e.g.: [ 1903.284538] sequence number glitch prev=16 curr=0 [ 1913.812205] sequence number glitch prev=50 curr=0 [ 1923.698219] sequence number glitch prev=142 curr=0 [ 2029.248276] sequence number glitch prev=1555 curr=0 [ 2046.333059] sequence number glitch prev=70 curr=0 [ 2076.520067] sequence number glitch prev=272 curr=0 [ 2158.704202] sequence number glitch prev=2655 curr=0 [ 2218.530776] sequence number glitch prev=2349 curr=0 [ 2225.579092] sequence number glitch prev=6 curr=0 Internet connectivity is working fine, so this error seems harmless. It looks like modem does not preserve the sequence number when entering low power state; the amount of errors depends on how actively the modem is being used. A similar issue has also been seen on USB-based MBIM modems [1]. However, in cdc_ncm.c the "sequence number glitch" message is a debug message instead of an error. Apply the same to the mhi_wwan_mbim.c driver to silence these errors when using the modem. [1]: https://lists.freedesktop.org/archives/libmbim-devel/2016-November/000781.html Signed-off-by: Stephan Gerhold Reviewed-by: Loic Poulain Acked-by: Manivannan Sadhasivam Link: https://patch.msgid.link/20250212-mhi-wwan-mbim-sequence-glitch-v1-1-503735977cbd@linaro.org Signed-off-by: Jakub Kicinski --- drivers/net/wwan/mhi_wwan_mbim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index d5a9360323d2..8755c5e6a65b 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -220,7 +220,7 @@ static int mbim_rx_verify_nth16(struct mhi_mbim_context *mbim, struct sk_buff *s if (mbim->rx_seq + 1 != le16_to_cpu(nth16->wSequence) && (mbim->rx_seq || le16_to_cpu(nth16->wSequence)) && !(mbim->rx_seq == 0xffff && !le16_to_cpu(nth16->wSequence))) { - net_err_ratelimited("sequence number glitch prev=%d curr=%d\n", + net_dbg_ratelimited("sequence number glitch prev=%d curr=%d\n", mbim->rx_seq, le16_to_cpu(nth16->wSequence)); } mbim->rx_seq = le16_to_cpu(nth16->wSequence); -- cgit v1.2.3 From 9593172d93b9f91c362baec4643003dc29802929 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 13 Feb 2025 13:33:54 +0900 Subject: geneve: Fix use-after-free in geneve_find_dev(). syzkaller reported a use-after-free in geneve_find_dev() [0] without repro. geneve_configure() links struct geneve_dev.next to net_generic(net, geneve_net_id)->geneve_list. The net here could differ from dev_net(dev) if IFLA_NET_NS_PID, IFLA_NET_NS_FD, or IFLA_TARGET_NETNSID is set. When dev_net(dev) is dismantled, geneve_exit_batch_rtnl() finally calls unregister_netdevice_queue() for each dev in the netns, and later the dev is freed. However, its geneve_dev.next is still linked to the backend UDP socket netns. Then, use-after-free will occur when another geneve dev is created in the netns. Let's call geneve_dellink() instead in geneve_destroy_tunnels(). [0]: BUG: KASAN: slab-use-after-free in geneve_find_dev drivers/net/geneve.c:1295 [inline] BUG: KASAN: slab-use-after-free in geneve_configure+0x234/0x858 drivers/net/geneve.c:1343 Read of size 2 at addr ffff000054d6ee24 by task syz.1.4029/13441 CPU: 1 UID: 0 PID: 13441 Comm: syz.1.4029 Not tainted 6.13.0-g0ad9617c78ac #24 dc35ca22c79fb82e8e7bc5c9c9adafea898b1e3d Hardware name: linux,dummy-virt (DT) Call trace: show_stack+0x38/0x50 arch/arm64/kernel/stacktrace.c:466 (C) __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xbc/0x108 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0x16c/0x6f0 mm/kasan/report.c:489 kasan_report+0xc0/0x120 mm/kasan/report.c:602 __asan_report_load2_noabort+0x20/0x30 mm/kasan/report_generic.c:379 geneve_find_dev drivers/net/geneve.c:1295 [inline] geneve_configure+0x234/0x858 drivers/net/geneve.c:1343 geneve_newlink+0xb8/0x128 drivers/net/geneve.c:1634 rtnl_newlink_create+0x23c/0x868 net/core/rtnetlink.c:3795 __rtnl_newlink net/core/rtnetlink.c:3906 [inline] rtnl_newlink+0x1054/0x1630 net/core/rtnetlink.c:4021 rtnetlink_rcv_msg+0x61c/0x918 net/core/rtnetlink.c:6911 netlink_rcv_skb+0x1dc/0x398 net/netlink/af_netlink.c:2543 rtnetlink_rcv+0x34/0x50 net/core/rtnetlink.c:6938 netlink_unicast_kernel net/netlink/af_netlink.c:1322 [inline] netlink_unicast+0x618/0x838 net/netlink/af_netlink.c:1348 netlink_sendmsg+0x5fc/0x8b0 net/netlink/af_netlink.c:1892 sock_sendmsg_nosec net/socket.c:713 [inline] __sock_sendmsg net/socket.c:728 [inline] ____sys_sendmsg+0x410/0x6f8 net/socket.c:2568 ___sys_sendmsg+0x178/0x1d8 net/socket.c:2622 __sys_sendmsg net/socket.c:2654 [inline] __do_sys_sendmsg net/socket.c:2659 [inline] __se_sys_sendmsg net/socket.c:2657 [inline] __arm64_sys_sendmsg+0x12c/0x1c8 net/socket.c:2657 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x90/0x278 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x13c/0x250 arch/arm64/kernel/syscall.c:132 do_el0_svc+0x54/0x70 arch/arm64/kernel/syscall.c:151 el0_svc+0x4c/0xa8 arch/arm64/kernel/entry-common.c:744 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:762 el0t_64_sync+0x198/0x1a0 arch/arm64/kernel/entry.S:600 Allocated by task 13247: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x30/0x68 mm/kasan/common.c:68 kasan_save_alloc_info+0x44/0x58 mm/kasan/generic.c:568 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x84/0xa0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __do_kmalloc_node mm/slub.c:4298 [inline] __kmalloc_node_noprof+0x2a0/0x560 mm/slub.c:4304 __kvmalloc_node_noprof+0x9c/0x230 mm/util.c:645 alloc_netdev_mqs+0xb8/0x11a0 net/core/dev.c:11470 rtnl_create_link+0x2b8/0xb50 net/core/rtnetlink.c:3604 rtnl_newlink_create+0x19c/0x868 net/core/rtnetlink.c:3780 __rtnl_newlink net/core/rtnetlink.c:3906 [inline] rtnl_newlink+0x1054/0x1630 net/core/rtnetlink.c:4021 rtnetlink_rcv_msg+0x61c/0x918 net/core/rtnetlink.c:6911 netlink_rcv_skb+0x1dc/0x398 net/netlink/af_netlink.c:2543 rtnetlink_rcv+0x34/0x50 net/core/rtnetlink.c:6938 netlink_unicast_kernel net/netlink/af_netlink.c:1322 [inline] netlink_unicast+0x618/0x838 net/netlink/af_netlink.c:1348 netlink_sendmsg+0x5fc/0x8b0 net/netlink/af_netlink.c:1892 sock_sendmsg_nosec net/socket.c:713 [inline] __sock_sendmsg net/socket.c:728 [inline] ____sys_sendmsg+0x410/0x6f8 net/socket.c:2568 ___sys_sendmsg+0x178/0x1d8 net/socket.c:2622 __sys_sendmsg net/socket.c:2654 [inline] __do_sys_sendmsg net/socket.c:2659 [inline] __se_sys_sendmsg net/socket.c:2657 [inline] __arm64_sys_sendmsg+0x12c/0x1c8 net/socket.c:2657 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x90/0x278 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x13c/0x250 arch/arm64/kernel/syscall.c:132 do_el0_svc+0x54/0x70 arch/arm64/kernel/syscall.c:151 el0_svc+0x4c/0xa8 arch/arm64/kernel/entry-common.c:744 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:762 el0t_64_sync+0x198/0x1a0 arch/arm64/kernel/entry.S:600 Freed by task 45: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x30/0x68 mm/kasan/common.c:68 kasan_save_free_info+0x58/0x70 mm/kasan/generic.c:582 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x48/0x68 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:233 [inline] slab_free_hook mm/slub.c:2353 [inline] slab_free mm/slub.c:4613 [inline] kfree+0x140/0x420 mm/slub.c:4761 kvfree+0x4c/0x68 mm/util.c:688 netdev_release+0x94/0xc8 net/core/net-sysfs.c:2065 device_release+0x98/0x1c0 kobject_cleanup lib/kobject.c:689 [inline] kobject_release lib/kobject.c:720 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x2b0/0x438 lib/kobject.c:737 netdev_run_todo+0xe5c/0xfc8 net/core/dev.c:11185 rtnl_unlock+0x20/0x38 net/core/rtnetlink.c:151 cleanup_net+0x4fc/0x8c0 net/core/net_namespace.c:648 process_one_work+0x700/0x1398 kernel/workqueue.c:3236 process_scheduled_works kernel/workqueue.c:3317 [inline] worker_thread+0x8c4/0xe10 kernel/workqueue.c:3398 kthread+0x4bc/0x608 kernel/kthread.c:464 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:862 The buggy address belongs to the object at ffff000054d6e000 which belongs to the cache kmalloc-cg-4k of size 4096 The buggy address is located 3620 bytes inside of freed 4096-byte region [ffff000054d6e000, ffff000054d6f000) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x94d68 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 memcg:ffff000016276181 flags: 0x3fffe0000000040(head|node=0|zone=0|lastcpupid=0x1ffff) page_type: f5(slab) raw: 03fffe0000000040 ffff0000c000f500 dead000000000122 0000000000000000 raw: 0000000000000000 0000000000040004 00000001f5000000 ffff000016276181 head: 03fffe0000000040 ffff0000c000f500 dead000000000122 0000000000000000 head: 0000000000000000 0000000000040004 00000001f5000000 ffff000016276181 head: 03fffe0000000003 fffffdffc1535a01 ffffffffffffffff 0000000000000000 head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff000054d6ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff000054d6ed80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff000054d6ee00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff000054d6ee80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff000054d6ef00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 2d07dc79fe04 ("geneve: add initial netdev driver for GENEVE tunnels") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250213043354.91368-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- drivers/net/geneve.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 642155cb8315..a1f674539965 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1907,16 +1907,11 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head) /* gather any geneve devices that were moved into this ns */ for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &geneve_link_ops) - unregister_netdevice_queue(dev, head); + geneve_dellink(dev, head); /* now gather any other geneve devices that were created in this ns */ - list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { - /* If geneve->dev is in the same netns, it was already added - * to the list by the previous loop. - */ - if (!net_eq(dev_net(geneve->dev), net)) - unregister_netdevice_queue(geneve->dev, head); - } + list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) + geneve_dellink(geneve->dev, head); } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, -- cgit v1.2.3 From bdf5d13aa05ec314d4385b31ac974d6c7e0997c9 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Fri, 14 Feb 2025 09:52:33 -0600 Subject: ibmvnic: Don't reference skb after sending to VIOS Previously, after successfully flushing the xmit buffer to VIOS, the tx_bytes stat was incremented by the length of the skb. It is invalid to access the skb memory after sending the buffer to the VIOS because, at any point after sending, the VIOS can trigger an interrupt to free this memory. A race between reading skb->len and freeing the skb is possible (especially during LPM) and will result in use-after-free: ================================================================== BUG: KASAN: slab-use-after-free in ibmvnic_xmit+0x75c/0x1808 [ibmvnic] Read of size 4 at addr c00000024eb48a70 by task hxecom/14495 <...> Call Trace: [c000000118f66cf0] [c0000000018cba6c] dump_stack_lvl+0x84/0xe8 (unreliable) [c000000118f66d20] [c0000000006f0080] print_report+0x1a8/0x7f0 [c000000118f66df0] [c0000000006f08f0] kasan_report+0x128/0x1f8 [c000000118f66f00] [c0000000006f2868] __asan_load4+0xac/0xe0 [c000000118f66f20] [c0080000046eac84] ibmvnic_xmit+0x75c/0x1808 [ibmvnic] [c000000118f67340] [c0000000014be168] dev_hard_start_xmit+0x150/0x358 <...> Freed by task 0: kasan_save_stack+0x34/0x68 kasan_save_track+0x2c/0x50 kasan_save_free_info+0x64/0x108 __kasan_mempool_poison_object+0x148/0x2d4 napi_skb_cache_put+0x5c/0x194 net_tx_action+0x154/0x5b8 handle_softirqs+0x20c/0x60c do_softirq_own_stack+0x6c/0x88 <...> The buggy address belongs to the object at c00000024eb48a00 which belongs to the cache skbuff_head_cache of size 224 ================================================================== Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Nick Child Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250214155233.235559-1-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index e95ae0d39948..0676fc547b6f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2408,6 +2408,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) dma_addr_t data_dma_addr; struct netdev_queue *txq; unsigned long lpar_rc; + unsigned int skblen; union sub_crq tx_crq; unsigned int offset; bool use_scrq_send_direct = false; @@ -2522,6 +2523,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->skb = skb; tx_buff->index = bufidx; tx_buff->pool_index = queue_num; + skblen = skb->len; memset(&tx_crq, 0, sizeof(tx_crq)); tx_crq.v1.first = IBMVNIC_CRQ_CMD; @@ -2614,7 +2616,7 @@ early_exit: netif_stop_subqueue(netdev, queue_num); } - tx_bytes += skb->len; + tx_bytes += skblen; txq_trans_cond_update(txq); ret = NETDEV_TX_OK; goto out; -- cgit v1.2.3 From 415cadd505464d9a11ff5e0f6e0329c127849da5 Mon Sep 17 00:00:00 2001 From: Joshua Washington Date: Fri, 14 Feb 2025 14:43:59 -0800 Subject: gve: set xdp redirect target only when it is available Before this patch the NETDEV_XDP_ACT_NDO_XMIT XDP feature flag is set by default as part of driver initialization, and is never cleared. However, this flag differs from others in that it is used as an indicator for whether the driver is ready to perform the ndo_xdp_xmit operation as part of an XDP_REDIRECT. Kernel helpers xdp_features_(set|clear)_redirect_target exist to convey this meaning. This patch ensures that the netdev is only reported as a redirect target when XDP queues exist to forward traffic. Fixes: 39a7f4aa3e4a ("gve: Add XDP REDIRECT support for GQI-QPL format") Cc: stable@vger.kernel.org Reviewed-by: Praveen Kaligineedi Reviewed-by: Jeroen de Borst Signed-off-by: Joshua Washington Link: https://patch.msgid.link/20250214224417.1237818-1-joshwash@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve.h | 10 ++++++++++ drivers/net/ethernet/google/gve/gve_main.c | 6 +++++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 8167cc5fb0df..78d2a19593d1 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1116,6 +1116,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv) return gve_xdp_tx_queue_id(priv, 0); } +static inline bool gve_supports_xdp_xmit(struct gve_priv *priv) +{ + switch (priv->queue_format) { + case GVE_GQI_QPL_FORMAT: + return true; + default: + return false; + } +} + /* gqi napi handler defined in gve_main.c */ int gve_napi_poll(struct napi_struct *napi, int budget); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 533e659b15b3..92237fb0b60c 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1903,6 +1903,8 @@ static void gve_turndown(struct gve_priv *priv) /* Stop tx queues */ netif_tx_disable(priv->dev); + xdp_features_clear_redirect_target(priv->dev); + gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); @@ -1972,6 +1974,9 @@ static void gve_turnup(struct gve_priv *priv) napi_schedule(&block->napi); } + if (priv->num_xdp_queues && gve_supports_xdp_xmit(priv)) + xdp_features_set_redirect_target(priv->dev, false); + gve_set_napi_enabled(priv); } @@ -2246,7 +2251,6 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv) if (priv->queue_format == GVE_GQI_QPL_FORMAT) { xdp_features = NETDEV_XDP_ACT_BASIC; xdp_features |= NETDEV_XDP_ACT_REDIRECT; - xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { xdp_features = 0; -- cgit v1.2.3 From f6093c5ec74d5cc495f89bd359253d9c738d04d9 Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Mon, 17 Feb 2025 14:48:11 +0100 Subject: net: pse-pd: pd692x0: Fix power limit retrieval Fix incorrect data offset read in the pd692x0_pi_get_pw_limit callback. The issue was previously unnoticed as it was only used by the regulator API and not thoroughly tested, since the PSE is mainly controlled via ethtool. The function became actively used by ethtool after commit 3e9dbfec4998 ("net: pse-pd: Split ethtool_get_status into multiple callbacks"), which led to the discovery of this issue. Fix it by using the correct data offset. Fixes: a87e699c9d33 ("net: pse-pd: pd692x0: Enhance with new current limit and voltage read callbacks") Signed-off-by: Kory Maincent Link: https://patch.msgid.link/20250217134812.1925345-1-kory.maincent@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/pse-pd/pd692x0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index fc9e23927b3b..7d60a714ca53 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -1047,7 +1047,7 @@ static int pd692x0_pi_get_pw_limit(struct pse_controller_dev *pcdev, if (ret < 0) return ret; - return pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); + return pd692x0_pi_get_pw_from_table(buf.data[0], buf.data[1]); } static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev, -- cgit v1.2.3 From 4ccacf86491d33d2486b62d4d44864d7101b299d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 17 Feb 2025 12:37:04 -0800 Subject: gtp: Suppress list corruption splat in gtp_net_exit_batch_rtnl(). Brad Spengler reported the list_del() corruption splat in gtp_net_exit_batch_rtnl(). [0] Commit eb28fd76c0a0 ("gtp: Destroy device along with udp socket's netns dismantle.") added the for_each_netdev() loop in gtp_net_exit_batch_rtnl() to destroy devices in each netns as done in geneve and ip tunnels. However, this could trigger ->dellink() twice for the same device during ->exit_batch_rtnl(). Say we have two netns A & B and gtp device B that resides in netns B but whose UDP socket is in netns A. 1. cleanup_net() processes netns A and then B. 2. gtp_net_exit_batch_rtnl() finds the device B while iterating netns A's gn->gtp_dev_list and calls ->dellink(). [ device B is not yet unlinked from netns B as unregister_netdevice_many() has not been called. ] 3. gtp_net_exit_batch_rtnl() finds the device B while iterating netns B's for_each_netdev() and calls ->dellink(). gtp_dellink() cleans up the device's hash table, unlinks the dev from gn->gtp_dev_list, and calls unregister_netdevice_queue(). Basically, calling gtp_dellink() multiple times is fine unless CONFIG_DEBUG_LIST is enabled. Let's remove for_each_netdev() in gtp_net_exit_batch_rtnl() and delegate the destruction to default_device_exit_batch() as done in bareudp. [0]: list_del corruption, ffff8880aaa62c00->next (autoslab_size_M_dev_P_net_core_dev_11127_8_1328_8_S_4096_A_64_n_139+0xc00/0x1000 [slab object]) is LIST_POISON1 (ffffffffffffff02) (prev is 0xffffffffffffff04) kernel BUG at lib/list_debug.c:58! Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 UID: 0 PID: 1804 Comm: kworker/u8:7 Tainted: G T 6.12.13-grsec-full-20250211091339 #1 Tainted: [T]=RANDSTRUCT Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: netns cleanup_net RIP: 0010:[] __list_del_entry_valid_or_report+0x141/0x200 lib/list_debug.c:58 Code: c2 76 91 31 c0 e8 9f b1 f7 fc 0f 0b 4d 89 f0 48 c7 c1 02 ff ff ff 48 89 ea 48 89 ee 48 c7 c7 e0 c2 76 91 31 c0 e8 7f b1 f7 fc <0f> 0b 4d 89 e8 48 c7 c1 04 ff ff ff 48 89 ea 48 89 ee 48 c7 c7 60 RSP: 0018:fffffe8040b4fbd0 EFLAGS: 00010283 RAX: 00000000000000cc RBX: dffffc0000000000 RCX: ffffffff818c4054 RDX: ffffffff84947381 RSI: ffffffff818d1512 RDI: 0000000000000000 RBP: ffff8880aaa62c00 R08: 0000000000000001 R09: fffffbd008169f32 R10: fffffe8040b4f997 R11: 0000000000000001 R12: a1988d84f24943e4 R13: ffffffffffffff02 R14: ffffffffffffff04 R15: ffff8880aaa62c08 RBX: kasan shadow of 0x0 RCX: __wake_up_klogd.part.0+0x74/0xe0 kernel/printk/printk.c:4554 RDX: __list_del_entry_valid_or_report+0x141/0x200 lib/list_debug.c:58 RSI: vprintk+0x72/0x100 kernel/printk/printk_safe.c:71 RBP: autoslab_size_M_dev_P_net_core_dev_11127_8_1328_8_S_4096_A_64_n_139+0xc00/0x1000 [slab object] RSP: process kstack fffffe8040b4fbd0+0x7bd0/0x8000 [kworker/u8:7+netns 1804 ] R09: kasan shadow of process kstack fffffe8040b4f990+0x7990/0x8000 [kworker/u8:7+netns 1804 ] R10: process kstack fffffe8040b4f997+0x7997/0x8000 [kworker/u8:7+netns 1804 ] R15: autoslab_size_M_dev_P_net_core_dev_11127_8_1328_8_S_4096_A_64_n_139+0xc08/0x1000 [slab object] FS: 0000000000000000(0000) GS:ffff888116000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000748f5372c000 CR3: 0000000015408000 CR4: 00000000003406f0 shadow CR4: 00000000003406f0 Stack: 0000000000000000 ffffffff8a0c35e7 ffffffff8a0c3603 ffff8880aaa62c00 ffff8880aaa62c00 0000000000000004 ffff88811145311c 0000000000000005 0000000000000001 ffff8880aaa62000 fffffe8040b4fd40 ffffffff8a0c360d Call Trace: [] __list_del_entry_valid include/linux/list.h:131 [inline] fffffe8040b4fc28 [] __list_del_entry include/linux/list.h:248 [inline] fffffe8040b4fc28 [] list_del include/linux/list.h:262 [inline] fffffe8040b4fc28 [] gtp_dellink+0x16d/0x360 drivers/net/gtp.c:1557 fffffe8040b4fc28 [] gtp_net_exit_batch_rtnl+0x124/0x2c0 drivers/net/gtp.c:2495 fffffe8040b4fc88 [] cleanup_net+0x5a4/0xbe0 net/core/net_namespace.c:635 fffffe8040b4fcd0 [] process_one_work+0xbd7/0x2160 kernel/workqueue.c:3326 fffffe8040b4fd88 [] process_scheduled_works kernel/workqueue.c:3407 [inline] fffffe8040b4fec0 [] worker_thread+0x6b5/0xfa0 kernel/workqueue.c:3488 fffffe8040b4fec0 [] kthread+0x360/0x4c0 kernel/kthread.c:397 fffffe8040b4ff78 [] ret_from_fork+0x74/0xe0 arch/x86/kernel/process.c:172 fffffe8040b4ffb8 [] ret_from_fork_asm+0x29/0xc0 arch/x86/entry/entry_64.S:399 fffffe8040b4ffe8 Modules linked in: Fixes: eb28fd76c0a0 ("gtp: Destroy device along with udp socket's netns dismantle.") Reported-by: Brad Spengler Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250217203705.40342-2-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- drivers/net/gtp.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index d64740bf44ed..b7b46c5e6399 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -2481,11 +2481,6 @@ static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list, list_for_each_entry(net, net_list, exit_list) { struct gtp_net *gn = net_generic(net, gtp_net_id); struct gtp_dev *gtp, *gtp_next; - struct net_device *dev; - - for_each_netdev(net, dev) - if (dev->rtnl_link_ops == >p_link_ops) - gtp_dellink(dev, dev_to_kill); list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list) gtp_dellink(gtp->dev, dev_to_kill); -- cgit v1.2.3 From 62fab6eef61f245dc8797e3a6a5b890ef40e8628 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 17 Feb 2025 12:37:05 -0800 Subject: geneve: Suppress list corruption splat in geneve_destroy_tunnels(). As explained in the previous patch, iterating for_each_netdev() and gn->geneve_list during ->exit_batch_rtnl() could trigger ->dellink() twice for the same device. If CONFIG_DEBUG_LIST is enabled, we will see a list_del() corruption splat in the 2nd call of geneve_dellink(). Let's remove for_each_netdev() in geneve_destroy_tunnels() and delegate that part to default_device_exit_batch(). Fixes: 9593172d93b9 ("geneve: Fix use-after-free in geneve_find_dev().") Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250217203705.40342-3-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- drivers/net/geneve.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index a1f674539965..dbb3960126ee 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1902,14 +1902,7 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; - struct net_device *dev, *aux; - /* gather any geneve devices that were moved into this ns */ - for_each_netdev_safe(net, dev, aux) - if (dev->rtnl_link_ops == &geneve_link_ops) - geneve_dellink(dev, head); - - /* now gather any other geneve devices that were created in this ns */ list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) geneve_dellink(geneve->dev, head); } -- cgit v1.2.3 From a370295367b55662a32a4be92565fe72a5aa79bb Mon Sep 17 00:00:00 2001 From: Nick Hu Date: Mon, 17 Feb 2025 13:58:42 +0800 Subject: net: axienet: Set mac_managed_pm The external PHY will undergo a soft reset twice during the resume process when it wake up from suspend. The first reset occurs when the axienet driver calls phylink_of_phy_connect(), and the second occurs when mdio_bus_phy_resume() invokes phy_init_hw(). The second soft reset of the external PHY does not reinitialize the internal PHY, which causes issues with the internal PHY, resulting in the PHY link being down. To prevent this, setting the mac_managed_pm flag skips the mdio_bus_phy_resume() function. Fixes: a129b41fe0a8 ("Revert "net: phy: dp83867: perform soft reset and retain established link"") Signed-off-by: Nick Hu Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250217055843.19799-1-nick.hu@sifive.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 9e7fa012e4fa..f33178f90c42 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2897,6 +2897,7 @@ static int axienet_probe(struct platform_device *pdev) lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; + lp->phylink_config.mac_managed_pm = true; lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD; -- cgit v1.2.3 From 878e7b11736e062514e58f3b445ff343e6705537 Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Tue, 18 Feb 2025 11:04:09 +0800 Subject: nfp: bpf: Add check for nfp_app_ctrl_msg_alloc() Add check for the return value of nfp_app_ctrl_msg_alloc() in nfp_bpf_cmsg_alloc() to prevent null pointer dereference. Fixes: ff3d43f7568c ("nfp: bpf: implement helpers for FW map ops") Cc: stable@vger.kernel.org Signed-off-by: Haoxiang Li Link: https://patch.msgid.link/20250218030409.2425798-1-haoxiang_li2024@163.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/netronome/nfp/bpf/cmsg.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index 2ec62c8d86e1..59486fe2ad18 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -20,6 +20,8 @@ nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size) struct sk_buff *skb; skb = nfp_app_ctrl_msg_alloc(bpf->app, size, GFP_KERNEL); + if (!skb) + return NULL; skb_put(skb, size); return skb; -- cgit v1.2.3 From 992ee3ed6e9fdd0be83a7daa5ff738e3cf86047f Mon Sep 17 00:00:00 2001 From: George Moussalem Date: Wed, 19 Feb 2025 14:09:21 +0100 Subject: net: phy: qcom: qca807x fix condition for DAC_DSP_BIAS_CURRENT While setting the DAC value, the wrong boolean value is evaluated to set the DSP bias current. So let's correct the conditional statement and use the right boolean value read from the DTS set in the priv. Cc: stable@vger.kernel.org Fixes: d1cb613efbd3 ("net: phy: qcom: add support for QCA807x PHY Family") Signed-off-by: George Moussalem Signed-off-by: Christian Marangi Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20250219130923.7216-1-ansuelsmth@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/qcom/qca807x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 3279de857b47..2ad8c2586d64 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -774,7 +774,7 @@ static int qca807x_config_init(struct phy_device *phydev) control_dac &= ~QCA807X_CONTROL_DAC_MASK; if (!priv->dac_full_amplitude) control_dac |= QCA807X_CONTROL_DAC_DSP_AMPLITUDE; - if (!priv->dac_full_amplitude) + if (!priv->dac_full_bias_current) control_dac |= QCA807X_CONTROL_DAC_DSP_BIAS_CURRENT; if (!priv->dac_disable_bias_current_tweak) control_dac |= QCA807X_CONTROL_DAC_BIAS_CURRENT_TWEAK; -- cgit v1.2.3 From f06e4bfd010faefa637689d2df2c727dbf6e1d27 Mon Sep 17 00:00:00 2001 From: Qunqin Zhao Date: Wed, 19 Feb 2025 10:07:01 +0800 Subject: net: stmmac: dwmac-loongson: Add fix_soc_reset() callback Loongson's DWMAC device may take nearly two seconds to complete DMA reset, however, the default waiting time for reset is 200 milliseconds. Therefore, the following error message may appear: [14.427169] dwmac-loongson-pci 0000:00:03.2: Failed to reset the dma Fixes: 803fc61df261 ("net: stmmac: dwmac-loongson: Add Loongson Multi-channels GMAC support") Cc: stable@vger.kernel.org Signed-off-by: Qunqin Zhao Reviewed-by: Huacai Chen Reviewed-by: Jacob Keller Acked-by: Yanteng Si Link: https://patch.msgid.link/20250219020701.15139-1-zhaoqunqin@loongson.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index bfe6e2d631bd..f5acfb7d4ff6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -516,6 +516,19 @@ static int loongson_dwmac_acpi_config(struct pci_dev *pdev, return 0; } +/* Loongson's DWMAC device may take nearly two seconds to complete DMA reset */ +static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr) +{ + u32 value = readl(ioaddr + DMA_BUS_MODE); + + value |= DMA_BUS_MODE_SFT_RESET; + writel(value, ioaddr + DMA_BUS_MODE); + + return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, + !(value & DMA_BUS_MODE_SFT_RESET), + 10000, 2000000); +} + static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct plat_stmmacenet_data *plat; @@ -566,6 +579,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id plat->bsp_priv = ld; plat->setup = loongson_dwmac_setup; + plat->fix_soc_reset = loongson_dwmac_fix_reset; ld->dev = &pdev->dev; ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff; -- cgit v1.2.3 From 0e4427f8f587c4b603475468bb3aee9418574893 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 20 Feb 2025 09:25:59 +0200 Subject: net: loopback: Avoid sending IP packets without an Ethernet header After commit 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev") IPv4 neighbors can be constructed on the blackhole net device, but they are constructed with an output function (neigh_direct_output()) that simply calls dev_queue_xmit(). The latter will transmit packets via 'skb->dev' which might not be the blackhole net device if dst_dev_put() switched 'dst->dev' to the blackhole net device while another CPU was using the dst entry in ip_output(), but after it already initialized 'skb->dev' from 'dst->dev'. Specifically, the following can happen: CPU1 CPU2 udp_sendmsg(sk1) udp_sendmsg(sk2) udp_send_skb() [...] ip_output() skb->dev = skb_dst(skb)->dev dst_dev_put() dst->dev = blackhole_netdev ip_finish_output2() resolves neigh on dst->dev neigh_output() neigh_direct_output() dev_queue_xmit() This will result in IPv4 packets being sent without an Ethernet header via a valid net device: tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on enp9s0, link-type EN10MB (Ethernet), snapshot length 262144 bytes 22:07:02.329668 20:00:40:11:18:fb > 45:00:00:44:f4:94, ethertype Unknown (0x58c6), length 68: 0x0000: 8dda 74ca f1ae ca6c ca6c 0098 969c 0400 ..t....l.l...... 0x0010: 0000 4730 3f18 6800 0000 0000 0000 9971 ..G0?.h........q 0x0020: c4c9 9055 a157 0a70 9ead bf83 38ca ab38 ...U.W.p....8..8 0x0030: 8add ab96 e052 .....R Fix by making sure that neighbors are constructed on top of the blackhole net device with an output function that simply consumes the packets, in a similar fashion to dst_discard_out() and blackhole_netdev_xmit(). Fixes: 8d7017fd621d ("blackhole_netdev: use blackhole_netdev to invalidate dst entries") Fixes: 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev") Reported-by: Florian Meister Closes: https://lore.kernel.org/netdev/20250210084931.23a5c2e4@hermes.local/ Signed-off-by: Ido Schimmel Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250220072559.782296-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/loopback.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index c8840c3b9a1b..f1d68153987e 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -244,8 +244,22 @@ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } +static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb) +{ + kfree_skb(skb); + return 0; +} + +static int blackhole_neigh_construct(struct net_device *dev, + struct neighbour *n) +{ + n->output = blackhole_neigh_output; + return 0; +} + static const struct net_device_ops blackhole_netdev_ops = { .ndo_start_xmit = blackhole_netdev_xmit, + .ndo_neigh_construct = blackhole_neigh_construct, }; /* This is a dst-dummy device used specifically for invalidated -- cgit v1.2.3 From 27843ce6ba3d3122b65066550fe33fb8839f8aef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Feb 2025 15:53:36 +0000 Subject: ipvlan: ensure network headers are in skb linear part syzbot found that ipvlan_process_v6_outbound() was assuming the IPv6 network header isis present in skb->head [1] Add the needed pskb_network_may_pull() calls for both IPv4 and IPv6 handlers. [1] BUG: KMSAN: uninit-value in __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47 __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47 ipv6_addr_type include/net/ipv6.h:555 [inline] ip6_route_output_flags_noref net/ipv6/route.c:2616 [inline] ip6_route_output_flags+0x51/0x720 net/ipv6/route.c:2651 ip6_route_output include/net/ip6_route.h:93 [inline] ipvlan_route_v6_outbound+0x24e/0x520 drivers/net/ipvlan/ipvlan_core.c:476 ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:491 [inline] ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:541 [inline] ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:605 [inline] ipvlan_queue_xmit+0xd72/0x1780 drivers/net/ipvlan/ipvlan_core.c:671 ipvlan_start_xmit+0x5b/0x210 drivers/net/ipvlan/ipvlan_main.c:223 __netdev_start_xmit include/linux/netdevice.h:5150 [inline] netdev_start_xmit include/linux/netdevice.h:5159 [inline] xmit_one net/core/dev.c:3735 [inline] dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3751 sch_direct_xmit+0x399/0xd40 net/sched/sch_generic.c:343 qdisc_restart net/sched/sch_generic.c:408 [inline] __qdisc_run+0x14da/0x35d0 net/sched/sch_generic.c:416 qdisc_run+0x141/0x4d0 include/net/pkt_sched.h:127 net_tx_action+0x78b/0x940 net/core/dev.c:5484 handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:561 __do_softirq+0x14/0x1a kernel/softirq.c:595 do_softirq+0x9a/0x100 kernel/softirq.c:462 __local_bh_enable_ip+0x9f/0xb0 kernel/softirq.c:389 local_bh_enable include/linux/bottom_half.h:33 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline] __dev_queue_xmit+0x2758/0x57d0 net/core/dev.c:4611 dev_queue_xmit include/linux/netdevice.h:3311 [inline] packet_xmit+0x9c/0x6c0 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3132 [inline] packet_sendmsg+0x93e0/0xa7e0 net/packet/af_packet.c:3164 sock_sendmsg_nosec net/socket.c:718 [inline] Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Reported-by: syzbot+93ab4a777bafb9d9f960@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/67b74f01.050a0220.14d86d.02d8.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Cc: Mahesh Bandewar Link: https://patch.msgid.link/20250220155336.61884-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ipvlan/ipvlan_core.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index fd591ddb3884..ca62188a317a 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -416,20 +416,25 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) { - const struct iphdr *ip4h = ip_hdr(skb); struct net_device *dev = skb->dev; struct net *net = dev_net(dev); - struct rtable *rt; int err, ret = NET_XMIT_DROP; + const struct iphdr *ip4h; + struct rtable *rt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, - .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)), .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, - .daddr = ip4h->daddr, - .saddr = ip4h->saddr, }; + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + goto err; + + ip4h = ip_hdr(skb); + fl4.daddr = ip4h->daddr; + fl4.saddr = ip4h->saddr; + fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)); + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; @@ -488,6 +493,12 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) struct net_device *dev = skb->dev; int err, ret = NET_XMIT_DROP; + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) { + DEV_STATS_INC(dev, tx_errors); + kfree_skb(skb); + return ret; + } + err = ipvlan_route_v6_outbound(dev, skb); if (unlikely(err)) { DEV_STATS_INC(dev, tx_errors); -- cgit v1.2.3 From fa52f15c745ce55261b92873676f64f7348cfe82 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 20 Feb 2025 11:29:50 -0500 Subject: net: cadence: macb: Synchronize stats calculations Stats calculations involve a RMW to add the stat update to the existing value. This is currently not protected by any synchronization mechanism, so data races are possible. Add a spinlock to protect the update. The reader side could be protected using u64_stats, but we would still need a spinlock for the update side anyway. And we always do an update immediately before reading the stats anyway. Fixes: 89e5785fc8a6 ("[PATCH] Atmel MACB ethernet driver") Signed-off-by: Sean Anderson Link: https://patch.msgid.link/20250220162950.95941-1-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb.h | 2 ++ drivers/net/ethernet/cadence/macb_main.c | 12 ++++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 5740c98d8c9f..2847278d9cd4 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -1279,6 +1279,8 @@ struct macb { struct clk *rx_clk; struct clk *tsu_clk; struct net_device *dev; + /* Protects hw_stats and ethtool_stats */ + spinlock_t stats_lock; union { struct macb_stats macb; struct gem_stats gem; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 48496209fb16..c1f57d96e63f 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1978,10 +1978,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) if (status & MACB_BIT(ISR_ROVR)) { /* We missed at least one packet */ + spin_lock(&bp->stats_lock); if (macb_is_gem(bp)) bp->hw_stats.gem.rx_overruns++; else bp->hw_stats.macb.rx_overruns++; + spin_unlock(&bp->stats_lock); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(ISR_ROVR)); @@ -3102,6 +3104,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) if (!netif_running(bp->dev)) return nstat; + spin_lock_irq(&bp->stats_lock); gem_update_stats(bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors + @@ -3131,6 +3134,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) nstat->tx_aborted_errors = hwstat->tx_excessive_collisions; nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors; nstat->tx_fifo_errors = hwstat->tx_underrun; + spin_unlock_irq(&bp->stats_lock); return nstat; } @@ -3138,12 +3142,13 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) static void gem_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { - struct macb *bp; + struct macb *bp = netdev_priv(dev); - bp = netdev_priv(dev); + spin_lock_irq(&bp->stats_lock); gem_update_stats(bp); memcpy(data, &bp->ethtool_stats, sizeof(u64) * (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES)); + spin_unlock_irq(&bp->stats_lock); } static int gem_get_sset_count(struct net_device *dev, int sset) @@ -3193,6 +3198,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev) return gem_get_stats(bp); /* read stats from hardware */ + spin_lock_irq(&bp->stats_lock); macb_update_stats(bp); /* Convert HW stats into netdevice stats */ @@ -3226,6 +3232,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev) nstat->tx_carrier_errors = hwstat->tx_carrier_errors; nstat->tx_fifo_errors = hwstat->tx_underruns; /* Don't know about heartbeat or window errors... */ + spin_unlock_irq(&bp->stats_lock); return nstat; } @@ -5097,6 +5104,7 @@ static int macb_probe(struct platform_device *pdev) } } spin_lock_init(&bp->lock); + spin_lock_init(&bp->stats_lock); /* setup capabilities */ macb_configure_caps(bp, macb_config); -- cgit v1.2.3 From f15176b8b6e72ac30e14fd273282d2b72562d26b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 20 Feb 2025 19:48:15 +0100 Subject: net: dsa: rtl8366rb: Fix compilation problem When the kernel is compiled without LED framework support the rtl8366rb fails to build like this: rtl8366rb.o: in function `rtl8366rb_setup_led': rtl8366rb.c:953:(.text.unlikely.rtl8366rb_setup_led+0xe8): undefined reference to `led_init_default_state_get' rtl8366rb.c:980:(.text.unlikely.rtl8366rb_setup_led+0x240): undefined reference to `devm_led_classdev_register_ext' As this is constantly coming up in different randconfig builds, bite the bullet and create a separate file for the offending code, split out a header with all stuff needed both in the core driver and the leds code. Add a new bool Kconfig option for the LED compile target, such that it depends on LEDS_CLASS=y || LEDS_CLASS=RTL8366RB which make LED support always available when LEDS_CLASS is compiled into the kernel and enforce that if the LEDS_CLASS is a module, then the RTL8366RB driver needs to be a module as well so that modprobe can resolve the dependencies. Fixes: 32d617005475 ("net: dsa: realtek: add LED drivers for rtl8366rb") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202502070525.xMUImayb-lkp@intel.com/ Signed-off-by: Linus Walleij Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/realtek/Kconfig | 6 + drivers/net/dsa/realtek/Makefile | 3 + drivers/net/dsa/realtek/rtl8366rb-leds.c | 177 +++++++++++++++++++++ drivers/net/dsa/realtek/rtl8366rb.c | 258 +------------------------------ drivers/net/dsa/realtek/rtl8366rb.h | 107 +++++++++++++ 5 files changed, 299 insertions(+), 252 deletions(-) create mode 100644 drivers/net/dsa/realtek/rtl8366rb-leds.c create mode 100644 drivers/net/dsa/realtek/rtl8366rb.h (limited to 'drivers/net') diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig index 6989972eebc3..10687722d14c 100644 --- a/drivers/net/dsa/realtek/Kconfig +++ b/drivers/net/dsa/realtek/Kconfig @@ -43,4 +43,10 @@ config NET_DSA_REALTEK_RTL8366RB help Select to enable support for Realtek RTL8366RB. +config NET_DSA_REALTEK_RTL8366RB_LEDS + bool "Support RTL8366RB LED control" + depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB) + depends on NET_DSA_REALTEK_RTL8366RB + default NET_DSA_REALTEK_RTL8366RB + endif diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile index 35491dc20d6d..17367bcba496 100644 --- a/drivers/net/dsa/realtek/Makefile +++ b/drivers/net/dsa/realtek/Makefile @@ -12,4 +12,7 @@ endif obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o rtl8366-objs := rtl8366-core.o rtl8366rb.o +ifdef CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS +rtl8366-objs += rtl8366rb-leds.o +endif obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c new file mode 100644 index 000000000000..99c890681ae6 --- /dev/null +++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include "rtl83xx.h" +#include "rtl8366rb.h" + +static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port) +{ + switch (led_group) { + case 0: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + case 1: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + case 2: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + case 3: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + default: + return 0; + } +} + +static int rb8366rb_get_port_led(struct rtl8366rb_led *led) +{ + struct realtek_priv *priv = led->priv; + u8 led_group = led->led_group; + u8 port_num = led->port_num; + int ret; + u32 val; + + ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group), + &val); + if (ret) { + dev_err(priv->dev, "error reading LED on port %d group %d\n", + led_group, port_num); + return ret; + } + + return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num)); +} + +static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable) +{ + struct realtek_priv *priv = led->priv; + u8 led_group = led->led_group; + u8 port_num = led->port_num; + int ret; + + ret = regmap_update_bits(priv->map, + RTL8366RB_LED_X_X_CTRL_REG(led_group), + rtl8366rb_led_group_port_mask(led_group, + port_num), + enable ? 0xffff : 0); + if (ret) { + dev_err(priv->dev, "error updating LED on port %d group %d\n", + led_group, port_num); + return ret; + } + + /* Change the LED group to manual controlled LEDs if required */ + ret = rb8366rb_set_ledgroup_mode(priv, led_group, + RTL8366RB_LEDGROUP_FORCE); + + if (ret) { + dev_err(priv->dev, "error updating LED GROUP group %d\n", + led_group); + return ret; + } + + return 0; +} + +static int +rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev, + enum led_brightness brightness) +{ + struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led, + cdev); + + return rb8366rb_set_port_led(led, brightness == LED_ON); +} + +static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp, + struct fwnode_handle *led_fwnode) +{ + struct rtl8366rb *rb = priv->chip_data; + struct led_init_data init_data = { }; + enum led_default_state state; + struct rtl8366rb_led *led; + u32 led_group; + int ret; + + ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group); + if (ret) + return ret; + + if (led_group >= RTL8366RB_NUM_LEDGROUPS) { + dev_warn(priv->dev, "Invalid LED reg %d defined for port %d", + led_group, dp->index); + return -EINVAL; + } + + led = &rb->leds[dp->index][led_group]; + led->port_num = dp->index; + led->led_group = led_group; + led->priv = priv; + + state = led_init_default_state_get(led_fwnode); + switch (state) { + case LEDS_DEFSTATE_ON: + led->cdev.brightness = 1; + rb8366rb_set_port_led(led, 1); + break; + case LEDS_DEFSTATE_KEEP: + led->cdev.brightness = + rb8366rb_get_port_led(led); + break; + case LEDS_DEFSTATE_OFF: + default: + led->cdev.brightness = 0; + rb8366rb_set_port_led(led, 0); + } + + led->cdev.max_brightness = 1; + led->cdev.brightness_set_blocking = + rtl8366rb_cled_brightness_set_blocking; + init_data.fwnode = led_fwnode; + init_data.devname_mandatory = true; + + init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d", + dp->ds->index, dp->index, led_group); + if (!init_data.devicename) + return -ENOMEM; + + ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data); + if (ret) { + dev_warn(priv->dev, "Failed to init LED %d for port %d", + led_group, dp->index); + return ret; + } + + return 0; +} + +int rtl8366rb_setup_leds(struct realtek_priv *priv) +{ + struct dsa_switch *ds = &priv->ds; + struct device_node *leds_np; + struct dsa_port *dp; + int ret = 0; + + dsa_switch_for_each_port(dp, ds) { + if (!dp->dn) + continue; + + leds_np = of_get_child_by_name(dp->dn, "leds"); + if (!leds_np) { + dev_dbg(priv->dev, "No leds defined for port %d", + dp->index); + continue; + } + + for_each_child_of_node_scoped(leds_np, led_np) { + ret = rtl8366rb_setup_led(priv, dp, + of_fwnode_handle(led_np)); + if (ret) + break; + } + + of_node_put(leds_np); + if (ret) + return ret; + } + return 0; +} diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c index 4c4a95d4380c..f54771cab56d 100644 --- a/drivers/net/dsa/realtek/rtl8366rb.c +++ b/drivers/net/dsa/realtek/rtl8366rb.c @@ -27,11 +27,7 @@ #include "realtek-smi.h" #include "realtek-mdio.h" #include "rtl83xx.h" - -#define RTL8366RB_PORT_NUM_CPU 5 -#define RTL8366RB_NUM_PORTS 6 -#define RTL8366RB_PHY_NO_MAX 4 -#define RTL8366RB_PHY_ADDR_MAX 31 +#include "rtl8366rb.h" /* Switch Global Configuration register */ #define RTL8366RB_SGCR 0x0000 @@ -176,39 +172,6 @@ */ #define RTL8366RB_VLAN_INGRESS_CTRL2_REG 0x037f -/* LED control registers */ -/* The LED blink rate is global; it is used by all triggers in all groups. */ -#define RTL8366RB_LED_BLINKRATE_REG 0x0430 -#define RTL8366RB_LED_BLINKRATE_MASK 0x0007 -#define RTL8366RB_LED_BLINKRATE_28MS 0x0000 -#define RTL8366RB_LED_BLINKRATE_56MS 0x0001 -#define RTL8366RB_LED_BLINKRATE_84MS 0x0002 -#define RTL8366RB_LED_BLINKRATE_111MS 0x0003 -#define RTL8366RB_LED_BLINKRATE_222MS 0x0004 -#define RTL8366RB_LED_BLINKRATE_446MS 0x0005 - -/* LED trigger event for each group */ -#define RTL8366RB_LED_CTRL_REG 0x0431 -#define RTL8366RB_LED_CTRL_OFFSET(led_group) \ - (4 * (led_group)) -#define RTL8366RB_LED_CTRL_MASK(led_group) \ - (0xf << RTL8366RB_LED_CTRL_OFFSET(led_group)) - -/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only - * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is - * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored. - */ -#define RTL8366RB_LED_0_1_CTRL_REG 0x0432 -#define RTL8366RB_LED_2_3_CTRL_REG 0x0433 -#define RTL8366RB_LED_X_X_CTRL_REG(led_group) \ - ((led_group) <= 1 ? \ - RTL8366RB_LED_0_1_CTRL_REG : \ - RTL8366RB_LED_2_3_CTRL_REG) -#define RTL8366RB_LED_0_X_CTRL_MASK GENMASK(5, 0) -#define RTL8366RB_LED_X_1_CTRL_MASK GENMASK(11, 6) -#define RTL8366RB_LED_2_X_CTRL_MASK GENMASK(5, 0) -#define RTL8366RB_LED_X_3_CTRL_MASK GENMASK(11, 6) - #define RTL8366RB_MIB_COUNT 33 #define RTL8366RB_GLOBAL_MIB_COUNT 1 #define RTL8366RB_MIB_COUNTER_PORT_OFFSET 0x0050 @@ -244,7 +207,6 @@ #define RTL8366RB_PORT_STATUS_AN_MASK 0x0080 #define RTL8366RB_NUM_VLANS 16 -#define RTL8366RB_NUM_LEDGROUPS 4 #define RTL8366RB_NUM_VIDS 4096 #define RTL8366RB_PRIORITYMAX 7 #define RTL8366RB_NUM_FIDS 8 @@ -351,46 +313,6 @@ #define RTL8366RB_GREEN_FEATURE_TX BIT(0) #define RTL8366RB_GREEN_FEATURE_RX BIT(2) -enum rtl8366_ledgroup_mode { - RTL8366RB_LEDGROUP_OFF = 0x0, - RTL8366RB_LEDGROUP_DUP_COL = 0x1, - RTL8366RB_LEDGROUP_LINK_ACT = 0x2, - RTL8366RB_LEDGROUP_SPD1000 = 0x3, - RTL8366RB_LEDGROUP_SPD100 = 0x4, - RTL8366RB_LEDGROUP_SPD10 = 0x5, - RTL8366RB_LEDGROUP_SPD1000_ACT = 0x6, - RTL8366RB_LEDGROUP_SPD100_ACT = 0x7, - RTL8366RB_LEDGROUP_SPD10_ACT = 0x8, - RTL8366RB_LEDGROUP_SPD100_10_ACT = 0x9, - RTL8366RB_LEDGROUP_FIBER = 0xa, - RTL8366RB_LEDGROUP_AN_FAULT = 0xb, - RTL8366RB_LEDGROUP_LINK_RX = 0xc, - RTL8366RB_LEDGROUP_LINK_TX = 0xd, - RTL8366RB_LEDGROUP_MASTER = 0xe, - RTL8366RB_LEDGROUP_FORCE = 0xf, - - __RTL8366RB_LEDGROUP_MODE_MAX -}; - -struct rtl8366rb_led { - u8 port_num; - u8 led_group; - struct realtek_priv *priv; - struct led_classdev cdev; -}; - -/** - * struct rtl8366rb - RTL8366RB-specific data - * @max_mtu: per-port max MTU setting - * @pvid_enabled: if PVID is set for respective port - * @leds: per-port and per-ledgroup led info - */ -struct rtl8366rb { - unsigned int max_mtu[RTL8366RB_NUM_PORTS]; - bool pvid_enabled[RTL8366RB_NUM_PORTS]; - struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS]; -}; - static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = { { 0, 0, 4, "IfInOctets" }, { 0, 4, 4, "EtherStatsOctets" }, @@ -831,9 +753,10 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, return 0; } -static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, - u8 led_group, - enum rtl8366_ledgroup_mode mode) +/* This code is used also with LEDs disabled */ +int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, + u8 led_group, + enum rtl8366_ledgroup_mode mode) { int ret; u32 val; @@ -850,144 +773,7 @@ static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, return 0; } -static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port) -{ - switch (led_group) { - case 0: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - case 1: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - case 2: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - case 3: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - default: - return 0; - } -} - -static int rb8366rb_get_port_led(struct rtl8366rb_led *led) -{ - struct realtek_priv *priv = led->priv; - u8 led_group = led->led_group; - u8 port_num = led->port_num; - int ret; - u32 val; - - ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group), - &val); - if (ret) { - dev_err(priv->dev, "error reading LED on port %d group %d\n", - led_group, port_num); - return ret; - } - - return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num)); -} - -static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable) -{ - struct realtek_priv *priv = led->priv; - u8 led_group = led->led_group; - u8 port_num = led->port_num; - int ret; - - ret = regmap_update_bits(priv->map, - RTL8366RB_LED_X_X_CTRL_REG(led_group), - rtl8366rb_led_group_port_mask(led_group, - port_num), - enable ? 0xffff : 0); - if (ret) { - dev_err(priv->dev, "error updating LED on port %d group %d\n", - led_group, port_num); - return ret; - } - - /* Change the LED group to manual controlled LEDs if required */ - ret = rb8366rb_set_ledgroup_mode(priv, led_group, - RTL8366RB_LEDGROUP_FORCE); - - if (ret) { - dev_err(priv->dev, "error updating LED GROUP group %d\n", - led_group); - return ret; - } - - return 0; -} - -static int -rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev, - enum led_brightness brightness) -{ - struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led, - cdev); - - return rb8366rb_set_port_led(led, brightness == LED_ON); -} - -static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp, - struct fwnode_handle *led_fwnode) -{ - struct rtl8366rb *rb = priv->chip_data; - struct led_init_data init_data = { }; - enum led_default_state state; - struct rtl8366rb_led *led; - u32 led_group; - int ret; - - ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group); - if (ret) - return ret; - - if (led_group >= RTL8366RB_NUM_LEDGROUPS) { - dev_warn(priv->dev, "Invalid LED reg %d defined for port %d", - led_group, dp->index); - return -EINVAL; - } - - led = &rb->leds[dp->index][led_group]; - led->port_num = dp->index; - led->led_group = led_group; - led->priv = priv; - - state = led_init_default_state_get(led_fwnode); - switch (state) { - case LEDS_DEFSTATE_ON: - led->cdev.brightness = 1; - rb8366rb_set_port_led(led, 1); - break; - case LEDS_DEFSTATE_KEEP: - led->cdev.brightness = - rb8366rb_get_port_led(led); - break; - case LEDS_DEFSTATE_OFF: - default: - led->cdev.brightness = 0; - rb8366rb_set_port_led(led, 0); - } - - led->cdev.max_brightness = 1; - led->cdev.brightness_set_blocking = - rtl8366rb_cled_brightness_set_blocking; - init_data.fwnode = led_fwnode; - init_data.devname_mandatory = true; - - init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d", - dp->ds->index, dp->index, led_group); - if (!init_data.devicename) - return -ENOMEM; - - ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data); - if (ret) { - dev_warn(priv->dev, "Failed to init LED %d for port %d", - led_group, dp->index); - return ret; - } - - return 0; -} - +/* This code is used also with LEDs disabled */ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv) { int ret = 0; @@ -1008,38 +794,6 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv) return ret; } -static int rtl8366rb_setup_leds(struct realtek_priv *priv) -{ - struct dsa_switch *ds = &priv->ds; - struct device_node *leds_np; - struct dsa_port *dp; - int ret = 0; - - dsa_switch_for_each_port(dp, ds) { - if (!dp->dn) - continue; - - leds_np = of_get_child_by_name(dp->dn, "leds"); - if (!leds_np) { - dev_dbg(priv->dev, "No leds defined for port %d", - dp->index); - continue; - } - - for_each_child_of_node_scoped(leds_np, led_np) { - ret = rtl8366rb_setup_led(priv, dp, - of_fwnode_handle(led_np)); - if (ret) - break; - } - - of_node_put(leds_np); - if (ret) - return ret; - } - return 0; -} - static int rtl8366rb_setup(struct dsa_switch *ds) { struct realtek_priv *priv = ds->priv; diff --git a/drivers/net/dsa/realtek/rtl8366rb.h b/drivers/net/dsa/realtek/rtl8366rb.h new file mode 100644 index 000000000000..685ff3275faa --- /dev/null +++ b/drivers/net/dsa/realtek/rtl8366rb.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RTL8366RB_H +#define _RTL8366RB_H + +#include "realtek.h" + +#define RTL8366RB_PORT_NUM_CPU 5 +#define RTL8366RB_NUM_PORTS 6 +#define RTL8366RB_PHY_NO_MAX 4 +#define RTL8366RB_NUM_LEDGROUPS 4 +#define RTL8366RB_PHY_ADDR_MAX 31 + +/* LED control registers */ +/* The LED blink rate is global; it is used by all triggers in all groups. */ +#define RTL8366RB_LED_BLINKRATE_REG 0x0430 +#define RTL8366RB_LED_BLINKRATE_MASK 0x0007 +#define RTL8366RB_LED_BLINKRATE_28MS 0x0000 +#define RTL8366RB_LED_BLINKRATE_56MS 0x0001 +#define RTL8366RB_LED_BLINKRATE_84MS 0x0002 +#define RTL8366RB_LED_BLINKRATE_111MS 0x0003 +#define RTL8366RB_LED_BLINKRATE_222MS 0x0004 +#define RTL8366RB_LED_BLINKRATE_446MS 0x0005 + +/* LED trigger event for each group */ +#define RTL8366RB_LED_CTRL_REG 0x0431 +#define RTL8366RB_LED_CTRL_OFFSET(led_group) \ + (4 * (led_group)) +#define RTL8366RB_LED_CTRL_MASK(led_group) \ + (0xf << RTL8366RB_LED_CTRL_OFFSET(led_group)) + +/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only + * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is + * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored. + */ +#define RTL8366RB_LED_0_1_CTRL_REG 0x0432 +#define RTL8366RB_LED_2_3_CTRL_REG 0x0433 +#define RTL8366RB_LED_X_X_CTRL_REG(led_group) \ + ((led_group) <= 1 ? \ + RTL8366RB_LED_0_1_CTRL_REG : \ + RTL8366RB_LED_2_3_CTRL_REG) +#define RTL8366RB_LED_0_X_CTRL_MASK GENMASK(5, 0) +#define RTL8366RB_LED_X_1_CTRL_MASK GENMASK(11, 6) +#define RTL8366RB_LED_2_X_CTRL_MASK GENMASK(5, 0) +#define RTL8366RB_LED_X_3_CTRL_MASK GENMASK(11, 6) + +enum rtl8366_ledgroup_mode { + RTL8366RB_LEDGROUP_OFF = 0x0, + RTL8366RB_LEDGROUP_DUP_COL = 0x1, + RTL8366RB_LEDGROUP_LINK_ACT = 0x2, + RTL8366RB_LEDGROUP_SPD1000 = 0x3, + RTL8366RB_LEDGROUP_SPD100 = 0x4, + RTL8366RB_LEDGROUP_SPD10 = 0x5, + RTL8366RB_LEDGROUP_SPD1000_ACT = 0x6, + RTL8366RB_LEDGROUP_SPD100_ACT = 0x7, + RTL8366RB_LEDGROUP_SPD10_ACT = 0x8, + RTL8366RB_LEDGROUP_SPD100_10_ACT = 0x9, + RTL8366RB_LEDGROUP_FIBER = 0xa, + RTL8366RB_LEDGROUP_AN_FAULT = 0xb, + RTL8366RB_LEDGROUP_LINK_RX = 0xc, + RTL8366RB_LEDGROUP_LINK_TX = 0xd, + RTL8366RB_LEDGROUP_MASTER = 0xe, + RTL8366RB_LEDGROUP_FORCE = 0xf, + + __RTL8366RB_LEDGROUP_MODE_MAX +}; + +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS) + +struct rtl8366rb_led { + u8 port_num; + u8 led_group; + struct realtek_priv *priv; + struct led_classdev cdev; +}; + +int rtl8366rb_setup_leds(struct realtek_priv *priv); + +#else + +static inline int rtl8366rb_setup_leds(struct realtek_priv *priv) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS) */ + +/** + * struct rtl8366rb - RTL8366RB-specific data + * @max_mtu: per-port max MTU setting + * @pvid_enabled: if PVID is set for respective port + * @leds: per-port and per-ledgroup led info + */ +struct rtl8366rb { + unsigned int max_mtu[RTL8366RB_NUM_PORTS]; + bool pvid_enabled[RTL8366RB_NUM_PORTS]; +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS) + struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS]; +#endif +}; + +/* This code is used also with LEDs disabled */ +int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, + u8 led_group, + enum rtl8366_ledgroup_mode mode); + +#endif /* _RTL8366RB_H */ -- cgit v1.2.3 From 29b036be1b0bfcfc958380d5931325997fddf08a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 20 Feb 2025 18:51:41 -0800 Subject: selftests: drv-net: test XDP, HDS auto and the ioctl path Test XDP and HDS interaction. While at it add a test for using the IOCTL, as that turned out to be the real culprit. Testing bnxt: # NETIF=eth0 ./ksft-net-drv/drivers/net/hds.py KTAP version 1 1..12 ok 1 hds.get_hds ok 2 hds.get_hds_thresh ok 3 hds.set_hds_disable # SKIP disabling of HDS not supported by the device ok 4 hds.set_hds_enable ok 5 hds.set_hds_thresh_zero ok 6 hds.set_hds_thresh_max ok 7 hds.set_hds_thresh_gt ok 8 hds.set_xdp ok 9 hds.enabled_set_xdp ok 10 hds.ioctl ok 11 hds.ioctl_set_xdp ok 12 hds.ioctl_enabled_set_xdp # Totals: pass:11 fail:0 xfail:0 xpass:0 skip:1 error:0 and netdevsim: # ./ksft-net-drv/drivers/net/hds.py KTAP version 1 1..12 ok 1 hds.get_hds ok 2 hds.get_hds_thresh ok 3 hds.set_hds_disable ok 4 hds.set_hds_enable ok 5 hds.set_hds_thresh_zero ok 6 hds.set_hds_thresh_max ok 7 hds.set_hds_thresh_gt ok 8 hds.set_xdp ok 9 hds.enabled_set_xdp ok 10 hds.ioctl ok 11 hds.ioctl_set_xdp ok 12 hds.ioctl_enabled_set_xdp # Totals: pass:12 fail:0 xfail:0 xpass:0 skip:0 error:0 Netdevsim needs a sane default for tx/rx ring size. ethtool 6.11 is needed for the --disable-netlink option. Acked-by: Stanislav Fomichev Tested-by: Taehee Yoo Link: https://patch.msgid.link/20250221025141.1132944-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/netdevsim/ethtool.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 5c80fbee7913..7ab358616e03 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -184,9 +184,11 @@ static const struct ethtool_ops nsim_ethtool_ops = { static void nsim_ethtool_ring_init(struct netdevsim *ns) { + ns->ethtool.ring.rx_pending = 512; ns->ethtool.ring.rx_max_pending = 4096; ns->ethtool.ring.rx_jumbo_max_pending = 4096; ns->ethtool.ring.rx_mini_max_pending = 4096; + ns->ethtool.ring.tx_pending = 512; ns->ethtool.ring.tx_max_pending = 4096; } -- cgit v1.2.3 From bab3a6e9ffd600f9db0ebaf8f45e1c6111cf314c Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Mon, 24 Feb 2025 06:17:16 +0100 Subject: net: ethernet: ti: am65-cpsw: select PAGE_POOL am65-cpsw uses page_pool_dev_alloc_pages(), thus needs PAGE_POOL selected to avoid linker errors. This is missing since the driver started to use page_pool helpers in 8acacc40f733 ("net: ethernet: ti: am65-cpsw: Add minimal XDP support") Fixes: 8acacc40f733 ("net: ethernet: ti: am65-cpsw: Add minimal XDP support") Signed-off-by: Sascha Hauer Reviewed-by: Michal Swiatkowski Link: https://patch.msgid.link/20250224-net-am654-nuss-kconfig-v2-1-c124f4915c92@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 0d5a862cd78a..3a13d60a947a 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -99,6 +99,7 @@ config TI_K3_AM65_CPSW_NUSS select NET_DEVLINK select TI_DAVINCI_MDIO select PHYLINK + select PAGE_POOL select TI_K3_CPPI_DESC_POOL imply PHY_TI_GMII_SEL depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS -- cgit v1.2.3 From 79990cf5e7aded76d0c092c9f5ed31eb1c75e02c Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Mon, 24 Feb 2025 11:06:41 -0800 Subject: ice: Fix deinitializing VF in error path If ice_ena_vfs() fails after calling ice_create_vf_entries(), it frees all VFs without removing them from snapshot PF-VF mailbox list, leading to list corruption. Reproducer: devlink dev eswitch set $PF1_PCI mode switchdev ip l s $PF1 up ip l s $PF1 promisc on sleep 1 echo 1 > /sys/class/net/$PF1/device/sriov_numvfs sleep 1 echo 1 > /sys/class/net/$PF1/device/sriov_numvfs Trace (minimized): list_add corruption. next->prev should be prev (ffff8882e241c6f0), but was 0000000000000000. (next=ffff888455da1330). kernel BUG at lib/list_debug.c:29! RIP: 0010:__list_add_valid_or_report+0xa6/0x100 ice_mbx_init_vf_info+0xa7/0x180 [ice] ice_initialize_vf_entry+0x1fa/0x250 [ice] ice_sriov_configure+0x8d7/0x1520 [ice] ? __percpu_ref_switch_mode+0x1b1/0x5d0 ? __pfx_ice_sriov_configure+0x10/0x10 [ice] Sometimes a KASAN report can be seen instead with a similar stack trace: BUG: KASAN: use-after-free in __list_add_valid_or_report+0xf1/0x100 VFs are added to this list in ice_mbx_init_vf_info(), but only removed in ice_free_vfs(). Move the removing to ice_free_vf_entries(), which is also being called in other places where VFs are being removed (including ice_free_vfs() itself). Fixes: 8cd8a6b17d27 ("ice: move VF overflow message count into struct ice_mbx_vf_info") Reported-by: Sujai Buvaneswaran Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com Reviewed-by: Martyna Szapar-Mudlaw Signed-off-by: Marcin Szycik Reviewed-by: Simon Horman Tested-by: Sujai Buvaneswaran Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-2-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_sriov.c | 5 +---- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 8 ++++++++ drivers/net/ethernet/intel/ice/ice_vf_lib_private.h | 1 + 3 files changed, 10 insertions(+), 4 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index b83f99c01d91..8aabf7749aa5 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf) hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) { hash_del_rcu(&vf->entry); + ice_deinitialize_vf_entry(vf); ice_put_vf(vf); } } @@ -193,10 +194,6 @@ void ice_free_vfs(struct ice_pf *pf) wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); } - /* clear malicious info since the VF is getting released */ - if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) - list_del(&vf->mbx_info.list_entry); - mutex_unlock(&vf->cfg_lock); } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index c7c0c2f50c26..815ad0bfe832 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -1036,6 +1036,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf) mutex_init(&vf->cfg_lock); } +void ice_deinitialize_vf_entry(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + list_del(&vf->mbx_info.list_entry); +} + /** * ice_dis_vf_qs - Disable the VF queues * @vf: pointer to the VF structure diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 0c7e77c0a09f..5392b0404986 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -24,6 +24,7 @@ #endif void ice_initialize_vf_entry(struct ice_vf *vf); +void ice_deinitialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); enum virtchnl_status_code ice_err_to_virt_err(int err); -- cgit v1.2.3 From 5c07be96d8b3f8447e980f29b967bf2e1d7ac732 Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Mon, 24 Feb 2025 11:06:42 -0800 Subject: ice: Avoid setting default Rx VSI twice in switchdev setup As part of switchdev environment setup, uplink VSI is configured as default for both Tx and Rx. Default Rx VSI is also used by promiscuous mode. If promisc mode is enabled and an attempt to enter switchdev mode is made, the setup will fail because Rx VSI is already configured as default (rule exists). Reproducer: devlink dev eswitch set $PF1_PCI mode switchdev ip l s $PF1 up ip l s $PF1 promisc on echo 1 > /sys/class/net/$PF1/device/sriov_numvfs In switchdev setup, use ice_set_dflt_vsi() instead of plain ice_cfg_dflt_vsi(), which avoids repeating setting default VSI for Rx if it's already configured. Fixes: 50d62022f455 ("ice: default Tx rule instead of to queue") Reported-by: Sujai Buvaneswaran Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com Reviewed-by: Martyna Szapar-Mudlaw Signed-off-by: Marcin Szycik Reviewed-by: Simon Horman Tested-by: Sujai Buvaneswaran Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-3-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_eswitch.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index fb527434b58b..d649c197cf67 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -38,8 +38,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) if (ice_vsi_add_vlan_zero(uplink_vsi)) goto err_vlan_zero; - if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, - ICE_FLTR_RX)) + if (ice_set_dflt_vsi(uplink_vsi)) goto err_def_rx; if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, -- cgit v1.2.3 From c6124f6fd3ca37d53ec5cbf62f9d9130ef439eca Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 24 Feb 2025 11:06:44 -0800 Subject: iavf: fix circular lock dependency with netdev_lock We have recently seen reports of lockdep circular lock dependency warnings when loading the iAVF driver: [ 1504.790308] ====================================================== [ 1504.790309] WARNING: possible circular locking dependency detected [ 1504.790310] 6.13.0 #net_next_rt.c2933b2befe2.el9 Not tainted [ 1504.790311] ------------------------------------------------------ [ 1504.790312] kworker/u128:0/13566 is trying to acquire lock: [ 1504.790313] ffff97d0e4738f18 (&dev->lock){+.+.}-{4:4}, at: register_netdevice+0x52c/0x710 [ 1504.790320] [ 1504.790320] but task is already holding lock: [ 1504.790321] ffff97d0e47392e8 (&adapter->crit_lock){+.+.}-{4:4}, at: iavf_finish_config+0x37/0x240 [iavf] [ 1504.790330] [ 1504.790330] which lock already depends on the new lock. [ 1504.790330] [ 1504.790330] [ 1504.790330] the existing dependency chain (in reverse order) is: [ 1504.790331] [ 1504.790331] -> #1 (&adapter->crit_lock){+.+.}-{4:4}: [ 1504.790333] __lock_acquire+0x52d/0xbb0 [ 1504.790337] lock_acquire+0xd9/0x330 [ 1504.790338] mutex_lock_nested+0x4b/0xb0 [ 1504.790341] iavf_finish_config+0x37/0x240 [iavf] [ 1504.790347] process_one_work+0x248/0x6d0 [ 1504.790350] worker_thread+0x18d/0x330 [ 1504.790352] kthread+0x10e/0x250 [ 1504.790354] ret_from_fork+0x30/0x50 [ 1504.790357] ret_from_fork_asm+0x1a/0x30 [ 1504.790361] [ 1504.790361] -> #0 (&dev->lock){+.+.}-{4:4}: [ 1504.790364] check_prev_add+0xf1/0xce0 [ 1504.790366] validate_chain+0x46a/0x570 [ 1504.790368] __lock_acquire+0x52d/0xbb0 [ 1504.790370] lock_acquire+0xd9/0x330 [ 1504.790371] mutex_lock_nested+0x4b/0xb0 [ 1504.790372] register_netdevice+0x52c/0x710 [ 1504.790374] iavf_finish_config+0xfa/0x240 [iavf] [ 1504.790379] process_one_work+0x248/0x6d0 [ 1504.790381] worker_thread+0x18d/0x330 [ 1504.790383] kthread+0x10e/0x250 [ 1504.790385] ret_from_fork+0x30/0x50 [ 1504.790387] ret_from_fork_asm+0x1a/0x30 [ 1504.790389] [ 1504.790389] other info that might help us debug this: [ 1504.790389] [ 1504.790389] Possible unsafe locking scenario: [ 1504.790389] [ 1504.790390] CPU0 CPU1 [ 1504.790391] ---- ---- [ 1504.790391] lock(&adapter->crit_lock); [ 1504.790393] lock(&dev->lock); [ 1504.790394] lock(&adapter->crit_lock); [ 1504.790395] lock(&dev->lock); [ 1504.790397] [ 1504.790397] *** DEADLOCK *** This appears to be caused by the change in commit 5fda3f35349b ("net: make netdev_lock() protect netdev->reg_state"), which added a netdev_lock() in register_netdevice. The iAVF driver calls register_netdevice() from iavf_finish_config(), as a final stage of its state machine post-probe. It currently takes the RTNL lock, then the netdev lock, and then the device critical lock. This pattern is used throughout the driver. Thus there is a strong dependency that the crit_lock should not be acquired before the net device lock. The change to register_netdevice creates an ABBA lock order violation because the iAVF driver is holding the crit_lock while calling register_netdevice, which then takes the netdev_lock. It seems likely that future refactors could result in netdev APIs which hold the netdev_lock while calling into the driver. This means that we should not re-order the locks so that netdev_lock is acquired after the device private crit_lock. Instead, notice that we already release the netdev_lock prior to calling the register_netdevice. This flow only happens during the early driver initialization as we transition through the __IAVF_STARTUP, __IAVF_INIT_VERSION_CHECK, __IAVF_INIT_GET_RESOURCES, etc. Analyzing the places where we take crit_lock in the driver there are two sources: a) several of the work queue tasks including adminq_task, watchdog_task, reset_task, and the finish_config task. b) various callbacks which ultimately stem back to .ndo operations or ethtool operations. The latter cannot be triggered until after the netdevice registration is completed successfully. The iAVF driver uses alloc_ordered_workqueue, which is an unbound workqueue that has a max limit of 1, and thus guarantees that only a single work item on the queue is executing at any given time, so none of the other work threads could be executing due to the ordered workqueue guarantees. The iavf_finish_config() function also does not do anything else after register_netdevice, unless it fails. It seems unlikely that the driver private crit_lock is protecting anything that register_netdevice() itself touches. Thus, to fix this ABBA lock violation, lets simply release the adapter->crit_lock as well as netdev_lock prior to calling register_netdevice(). We do still keep holding the RTNL lock as required by the function. If we do fail to register the netdevice, then we re-acquire the adapter critical lock to finish the transition back to __IAVF_INIT_CONFIG_ADAPTER. This ensures every call where both netdev_lock and the adapter->crit_lock are acquired under the same ordering. Fixes: afc664987ab3 ("eth: iavf: extend the netdev_lock usage") Signed-off-by: Jacob Keller Tested-by: Przemek Kitszel Reviewed-by: Przemek Kitszel Reviewed-by: Jakub Kicinski Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-5-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/iavf/iavf_main.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 852e5b62f0a5..6faa62bced3a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1983,7 +1983,7 @@ err: static void iavf_finish_config(struct work_struct *work) { struct iavf_adapter *adapter; - bool netdev_released = false; + bool locks_released = false; int pairs, err; adapter = container_of(work, struct iavf_adapter, finish_config); @@ -2012,19 +2012,22 @@ static void iavf_finish_config(struct work_struct *work) netif_set_real_num_tx_queues(adapter->netdev, pairs); if (adapter->netdev->reg_state != NETREG_REGISTERED) { + mutex_unlock(&adapter->crit_lock); netdev_unlock(adapter->netdev); - netdev_released = true; + locks_released = true; err = register_netdevice(adapter->netdev); if (err) { dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", err); /* go back and try again.*/ + mutex_lock(&adapter->crit_lock); iavf_free_rss(adapter); iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); + mutex_unlock(&adapter->crit_lock); goto out; } } @@ -2040,9 +2043,10 @@ static void iavf_finish_config(struct work_struct *work) } out: - mutex_unlock(&adapter->crit_lock); - if (!netdev_released) + if (!locks_released) { + mutex_unlock(&adapter->crit_lock); netdev_unlock(adapter->netdev); + } rtnl_unlock(); } -- cgit v1.2.3 From b1e44b4aecb551727a368df5b85c535f2ce932ea Mon Sep 17 00:00:00 2001 From: Piotr Kwapulinski Date: Mon, 24 Feb 2025 11:06:45 -0800 Subject: ixgbe: fix media cage present detection for E610 device The commit 23c0e5a16bcc ("ixgbe: Add link management support for E610 device") introduced incorrect checking of media cage presence for E610 device. Fix it. Fixes: 23c0e5a16bcc ("ixgbe: Add link management support for E610 device") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/e7d73b32-f12a-49d1-8b60-1ef83359ec13@stanley.mountain/ Reviewed-by: Michal Swiatkowski Reviewed-by: Przemek Kitszel Signed-off-by: Piotr Kwapulinski Reviewed-by: Simon Horman Tested-by: Bharath R Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-6-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c index 683c668672d6..cb07ecd8937d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c @@ -1122,7 +1122,7 @@ static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw) * returns error (ENOENT), then no cage present. If no cage present then * connection type is backplane or BASE-T. */ - return ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL); + return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL); } /** -- cgit v1.2.3 From 39ab773e4c120f7f98d759415ccc2aca706bbc10 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:44 +0800 Subject: net: enetc: fix the off-by-one issue in enetc_map_tx_buffs() When a DMA mapping error occurs while processing skb frags, it will free one more tx_swbd than expected, so fix this off-by-one issue. Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers") Cc: stable@vger.kernel.org Suggested-by: Vladimir Oltean Suggested-by: Michal Swiatkowski Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Claudiu Manoil Link: https://patch.msgid.link/20250224111251.1061098-2-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 6a6fc819dfde..55ad31a5073e 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -167,6 +167,24 @@ static bool enetc_skb_is_tcp(struct sk_buff *skb) return skb->csum_offset == offsetof(struct tcphdr, check); } +/** + * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame + * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located + * @count: Number of Tx buffer descriptors which need to be unmapped + * @i: Index of the last successfully mapped Tx buffer descriptor + */ +static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i) +{ + while (count--) { + struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i]; + + enetc_free_tx_frame(tx_ring, tx_swbd); + if (i == 0) + i = tx_ring->bd_count; + i--; + } +} + static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) { bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false; @@ -372,13 +390,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) dma_err: dev_err(tx_ring->dev, "DMA map error"); - do { - tx_swbd = &tx_ring->tx_swbd[i]; - enetc_free_tx_frame(tx_ring, tx_swbd); - if (i == 0) - i = tx_ring->bd_count; - i--; - } while (count--); + enetc_unwind_tx_frame(tx_ring, count, i); return 0; } -- cgit v1.2.3 From da291996b16ebd10626d4b20288327b743aff110 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:45 +0800 Subject: net: enetc: keep track of correct Tx BD count in enetc_map_tx_tso_buffs() When creating a TSO header, if the skb is VLAN tagged, the extended BD will be used and the 'count' should be increased by 2 instead of 1. Otherwise, when an error occurs, less tx_swbd will be freed than the actual number. Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO") Cc: stable@vger.kernel.org Suggested-by: Vladimir Oltean Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Claudiu Manoil Link: https://patch.msgid.link/20250224111251.1061098-3-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 55ad31a5073e..174db9e2ce81 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -395,14 +395,15 @@ dma_err: return 0; } -static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, - struct enetc_tx_swbd *tx_swbd, - union enetc_tx_bd *txbd, int *i, int hdr_len, - int data_len) +static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, int *i, int hdr_len, + int data_len) { union enetc_tx_bd txbd_tmp; u8 flags = 0, e_flags = 0; dma_addr_t addr; + int count = 1; enetc_clear_tx_bd(&txbd_tmp); addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE; @@ -445,7 +446,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, /* Write the BD */ txbd_tmp.ext.e_flags = e_flags; *txbd = txbd_tmp; + count++; } + + return count; } static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb, @@ -802,9 +806,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb /* compute the csum over the L4 header */ csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos); - enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len); + count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, + &i, hdr_len, data_len); bd_data_num = 0; - count++; while (data_len > 0) { int size; -- cgit v1.2.3 From 432a2cb3ee97a7c6ea578888fe81baad035b9307 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:46 +0800 Subject: net: enetc: correct the xdp_tx statistics The 'xdp_tx' is used to count the number of XDP_TX frames sent, not the number of Tx BDs. Fixes: 7ed2bc80074e ("net: enetc: add support for XDP_TX") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Ioana Ciornei Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-4-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 174db9e2ce81..3cb9ebb13b19 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1917,7 +1917,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, enetc_xdp_drop(rx_ring, orig_i, i); tx_ring->stats.xdp_tx_drops++; } else { - tx_ring->stats.xdp_tx += xdp_tx_bd_cnt; + tx_ring->stats.xdp_tx++; rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt; xdp_tx_frm_cnt++; /* The XDP_TX enqueue was successful, so we -- cgit v1.2.3 From a562d0c4a893eae3ea51d512c4d90ab858a6b7ec Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:47 +0800 Subject: net: enetc: VFs do not support HWTSTAMP_TX_ONESTEP_SYNC Actually ENETC VFs do not support HWTSTAMP_TX_ONESTEP_SYNC because only ENETC PF can access PMa_SINGLE_STEP registers. And there will be a crash if VFs are used to test one-step timestamp, the crash log as follows. [ 129.110909] Unable to handle kernel paging request at virtual address 00000000000080c0 [ 129.287769] Call trace: [ 129.290219] enetc_port_mac_wr+0x30/0xec (P) [ 129.294504] enetc_start_xmit+0xda4/0xe74 [ 129.298525] enetc_xmit+0x70/0xec [ 129.301848] dev_hard_start_xmit+0x98/0x118 Fixes: 41514737ecaa ("enetc: add get_ts_info interface for ethtool") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-5-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 3 +++ drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 7 +++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3cb9ebb13b19..e946d8652790 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3244,6 +3244,9 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr) new_offloads |= ENETC_F_TX_TSTAMP; break; case HWTSTAMP_TX_ONESTEP_SYNC: + if (!enetc_si_is_pf(priv->si)) + return -EOPNOTSUPP; + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP; break; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index bf34b5bb1e35..ece3ae28ba82 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -832,6 +832,7 @@ static int enetc_set_coalesce(struct net_device *ndev, static int enetc_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *info) { + struct enetc_ndev_priv *priv = netdev_priv(ndev); int *phc_idx; phc_idx = symbol_get(enetc_phc_index); @@ -852,8 +853,10 @@ static int enetc_get_ts_info(struct net_device *ndev, SOF_TIMESTAMPING_TX_SOFTWARE; info->tx_types = (1 << HWTSTAMP_TX_OFF) | - (1 << HWTSTAMP_TX_ON) | - (1 << HWTSTAMP_TX_ONESTEP_SYNC); + (1 << HWTSTAMP_TX_ON); + + if (enetc_si_is_pf(priv->si)) + info->tx_types |= (1 << HWTSTAMP_TX_ONESTEP_SYNC); info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | (1 << HWTSTAMP_FILTER_ALL); -- cgit v1.2.3 From bbcbc906ab7b5834c1219cd17a38d78dba904aa0 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:48 +0800 Subject: net: enetc: update UDP checksum when updating originTimestamp field There is an issue with one-step timestamp based on UDP/IP. The peer will discard the sync packet because of the wrong UDP checksum. For ENETC v1, the software needs to update the UDP checksum when updating the originTimestamp field, so that the hardware can correctly update the UDP checksum when updating the correction field. Otherwise, the UDP checksum in the sync packet will be wrong. Fixes: 7294380c5211 ("enetc: support PTP Sync packet one-step timestamping") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-6-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 41 +++++++++++++++++++++++----- 1 file changed, 34 insertions(+), 7 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index e946d8652790..9801c51b6a59 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -297,9 +297,11 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) } if (do_onestep_tstamp) { - u32 lo, hi, val; - u64 sec, nsec; + __be32 new_sec_l, new_nsec; + u32 lo, hi, nsec, val; + __be16 new_sec_h; u8 *data; + u64 sec; lo = enetc_rd_hot(hw, ENETC_SICTR0); hi = enetc_rd_hot(hw, ENETC_SICTR1); @@ -313,13 +315,38 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) /* Update originTimestamp field of Sync packet * - 48 bits seconds field * - 32 bits nanseconds field + * + * In addition, the UDP checksum needs to be updated + * by software after updating originTimestamp field, + * otherwise the hardware will calculate the wrong + * checksum when updating the correction field and + * update it to the packet. */ data = skb_mac_header(skb); - *(__be16 *)(data + offset2) = - htons((sec >> 32) & 0xffff); - *(__be32 *)(data + offset2 + 2) = - htonl(sec & 0xffffffff); - *(__be32 *)(data + offset2 + 6) = htonl(nsec); + new_sec_h = htons((sec >> 32) & 0xffff); + new_sec_l = htonl(sec & 0xffffffff); + new_nsec = htonl(nsec); + if (udp) { + struct udphdr *uh = udp_hdr(skb); + __be32 old_sec_l, old_nsec; + __be16 old_sec_h; + + old_sec_h = *(__be16 *)(data + offset2); + inet_proto_csum_replace2(&uh->check, skb, old_sec_h, + new_sec_h, false); + + old_sec_l = *(__be32 *)(data + offset2 + 2); + inet_proto_csum_replace4(&uh->check, skb, old_sec_l, + new_sec_l, false); + + old_nsec = *(__be32 *)(data + offset2 + 6); + inet_proto_csum_replace4(&uh->check, skb, old_nsec, + new_nsec, false); + } + + *(__be16 *)(data + offset2) = new_sec_h; + *(__be32 *)(data + offset2 + 2) = new_sec_l; + *(__be32 *)(data + offset2 + 6) = new_nsec; /* Configure single-step register */ val = ENETC_PM0_SINGLE_STEP_EN; -- cgit v1.2.3 From 8e43decdfbb477dd7800e3902d2d2f105d22ef5f Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:49 +0800 Subject: net: enetc: add missing enetc4_link_deinit() The enetc4_link_init() is called when the PF driver probes to create phylink and MDIO bus, but we forgot to call enetc4_link_deinit() to free the phylink and MDIO bus when the driver was unbound. so add missing enetc4_link_deinit() to enetc4_pf_netdev_destroy(). Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-7-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index fc41078c4f5d..48861c8b499a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -684,6 +684,7 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si) struct net_device *ndev = si->ndev; unregister_netdev(ndev); + enetc4_link_deinit(priv); enetc_free_msix(priv); free_netdev(ndev); } -- cgit v1.2.3 From 119049b66b883c7e7e575a0b69dc6e3d211662cc Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:50 +0800 Subject: net: enetc: remove the mm_lock from the ENETC v4 driver Currently, the ENETC v4 driver has not added the MAC merge layer support in the upstream, so the mm_lock is not initialized and used, so remove the mm_lock from the driver. Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-8-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index 48861c8b499a..73ac8c6afb3a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -672,7 +672,6 @@ err_link_init: err_alloc_msix: err_config_si: err_clk_get: - mutex_destroy(&priv->mm_lock); free_netdev(ndev); return err; -- cgit v1.2.3 From 249df695c3ffe8c8d36d46c2580ce72410976f96 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:51 +0800 Subject: net: enetc: fix the off-by-one issue in enetc_map_tx_tso_buffs() There is an off-by-one issue for the err_chained_bd path, it will free one more tx_swbd than expected. But there is no such issue for the err_map_data path. To fix this off-by-one issue and make the two error handling consistent, the increment of 'i' and 'count' remain in sync and enetc_unwind_tx_frame() is called for error handling. Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO") Cc: stable@vger.kernel.org Suggested-by: Vladimir Oltean Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Claudiu Manoil Link: https://patch.msgid.link/20250224111251.1061098-9-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 9801c51b6a59..2106861463e4 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -859,8 +859,13 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd, tso.data, size, size == data_len); - if (err) + if (err) { + if (i == 0) + i = tx_ring->bd_count; + i--; + goto err_map_data; + } data_len -= size; count++; @@ -889,13 +894,7 @@ err_map_data: dev_err(tx_ring->dev, "DMA map error"); err_chained_bd: - do { - tx_swbd = &tx_ring->tx_swbd[i]; - enetc_free_tx_frame(tx_ring, tx_swbd); - if (i == 0) - i = tx_ring->bd_count; - i--; - } while (count--); + enetc_unwind_tx_frame(tx_ring, count, i); return 0; } -- cgit v1.2.3 From de70981f295e7eab86325db3bf349fa676f16c42 Mon Sep 17 00:00:00 2001 From: Harshitha Ramamurthy Date: Wed, 26 Feb 2025 00:35:26 +0000 Subject: gve: unlink old napi when stopping a queue using queue API When a queue is stopped using the ndo queue API, before destroying its page pool, the associated NAPI instance needs to be unlinked to avoid warnings. Handle this by calling page_pool_disable_direct_recycling() when stopping a queue. Cc: stable@vger.kernel.org Fixes: ebdfae0d377b ("gve: adopt page pool for DQ RDA mode") Reviewed-by: Praveen Kaligineedi Signed-off-by: Harshitha Ramamurthy Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250226003526.1546854-1-hramamurthy@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 8ac0047f1ada..f0674a443567 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -109,10 +109,12 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx) void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); + struct gve_rx_ring *rx = &priv->rx[idx]; if (!gve_rx_was_added_to_block(priv, idx)) return; + page_pool_disable_direct_recycling(rx->dqo.page_pool); gve_remove_napi(priv, ntfy_idx); gve_rx_remove_from_block(priv, idx); gve_rx_reset_ring_dqo(priv, idx); -- cgit v1.2.3 From 2d253726ff7106b39a44483b6864398bba8a2f74 Mon Sep 17 00:00:00 2001 From: Harshal Chaudhari Date: Mon, 24 Feb 2025 20:20:58 -0800 Subject: net: mvpp2: cls: Fixed Non IP flow, with vlan tag flow defination. Non IP flow, with vlan tag not working as expected while running below command for vlan-priority. fixed that. ethtool -N eth1 flow-type ether vlan 0x8000 vlan-mask 0x1fff action 0 loc 0 Fixes: 1274daede3ef ("net: mvpp2: cls: Add steering based on vlan Id and priority.") Signed-off-by: Harshal Chaudhari Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20250225042058.2643838-1-hchaudhari@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 1641791a2d5b..8ed83fb98862 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = { MVPP2_PRS_RI_VLAN_MASK), /* Non IP flow, with vlan tag */ MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG, - MVPP22_CLS_HEK_OPT_VLAN, + MVPP22_CLS_HEK_TAGGED, 0, 0), }; -- cgit v1.2.3 From 7f3528f7d2f98b70e19a6bb7b130fc82c079ac54 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Tue, 25 Feb 2025 09:26:06 +0200 Subject: net/mlx5: Fix vport QoS cleanup on error When enabling vport QoS fails, the scheduling node was never freed, causing a leak. Add the missing free and reset the vport scheduling node pointer to NULL. Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions") Signed-off-by: Carolina Jubran Reviewed-by: Cosmin Ratiu Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20250225072608.526866-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 8b7c843446e1..07a28073a49e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -591,8 +591,11 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t sched_node->vport = vport; vport->qos.sched_node = sched_node; err = esw_qos_vport_enable(vport, parent, extack); - if (err) + if (err) { + __esw_qos_free_node(sched_node); esw_qos_put(esw); + vport->qos.sched_node = NULL; + } return err; } -- cgit v1.2.3 From 47bcd9bf3d231bfd4698d7d3013597490fd5e2d6 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Tue, 25 Feb 2025 09:26:07 +0200 Subject: net/mlx5: Restore missing trace event when enabling vport QoS Restore the `trace_mlx5_esw_vport_qos_create` event when creating the vport scheduling element. This trace event was lost during refactoring. Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions") Signed-off-by: Carolina Jubran Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20250225072608.526866-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 07a28073a49e..823c1ba456cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -564,6 +564,9 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_ return err; esw_qos_normalize_min_rate(parent->esw, parent, extack); + trace_mlx5_esw_vport_qos_create(vport->dev, vport, + vport->qos.sched_node->max_rate, + vport->qos.sched_node->bw_share); return 0; } -- cgit v1.2.3 From 2f5a6014eb168a97b24153adccfa663d3b282767 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 25 Feb 2025 09:26:08 +0200 Subject: net/mlx5: IRQ, Fix null string in debug print irq_pool_alloc() debug print can print a null string. Fix it by providing a default string to print. Fixes: 71e084e26414 ("net/mlx5: Allocating a pool of MSI-X vectors for SFs") Signed-off-by: Shay Drory Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202501141055.SwfIphN0-lkp@intel.com/ Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Reviewed-by: Kalesh AP Link: https://patch.msgid.link/20250225072608.526866-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 7db9cab9bedf..d9362eabc6a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -572,7 +572,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ; pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ; mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d", - name, size, start); + name ? name : "mlx5_pcif_pool", size, start); return pool; } -- cgit v1.2.3 From 1cf9631d836b289bd5490776551961c883ae8a4f Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Mon, 24 Feb 2025 20:29:17 +0300 Subject: usbnet: gl620a: fix endpoint checking in genelink_bind() Syzbot reports [1] a warning in usb_submit_urb() triggered by inconsistencies between expected and actually present endpoints in gl620a driver. Since genelink_bind() does not properly verify whether specified eps are in fact provided by the device, in this case, an artificially manufactured one, one may get a mismatch. Fix the issue by resorting to a usbnet utility function usbnet_get_endpoints(), usually reserved for this very problem. Check for endpoints and return early before proceeding further if any are missing. [1] Syzbot report: usb 5-1: Manufacturer: syz usb 5-1: SerialNumber: syz usb 5-1: config 0 descriptor?? gl620a 5-1:0.23 usb0: register 'gl620a' at usb-dummy_hcd.0-1, ... ------------[ cut here ]------------ usb 5-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 2 PID: 1841 at drivers/usb/core/urb.c:503 usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503 Modules linked in: CPU: 2 UID: 0 PID: 1841 Comm: kworker/2:2 Not tainted 6.12.0-syzkaller-07834-g06afb0f36106 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Workqueue: mld mld_ifc_work RIP: 0010:usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503 ... Call Trace: usbnet_start_xmit+0x6be/0x2780 drivers/net/usb/usbnet.c:1467 __netdev_start_xmit include/linux/netdevice.h:5002 [inline] netdev_start_xmit include/linux/netdevice.h:5011 [inline] xmit_one net/core/dev.c:3590 [inline] dev_hard_start_xmit+0x9a/0x7b0 net/core/dev.c:3606 sch_direct_xmit+0x1ae/0xc30 net/sched/sch_generic.c:343 __dev_xmit_skb net/core/dev.c:3827 [inline] __dev_queue_xmit+0x13d4/0x43e0 net/core/dev.c:4400 dev_queue_xmit include/linux/netdevice.h:3168 [inline] neigh_resolve_output net/core/neighbour.c:1514 [inline] neigh_resolve_output+0x5bc/0x950 net/core/neighbour.c:1494 neigh_output include/net/neighbour.h:539 [inline] ip6_finish_output2+0xb1b/0x2070 net/ipv6/ip6_output.c:141 __ip6_finish_output net/ipv6/ip6_output.c:215 [inline] ip6_finish_output+0x3f9/0x1360 net/ipv6/ip6_output.c:226 NF_HOOK_COND include/linux/netfilter.h:303 [inline] ip6_output+0x1f8/0x540 net/ipv6/ip6_output.c:247 dst_output include/net/dst.h:450 [inline] NF_HOOK include/linux/netfilter.h:314 [inline] NF_HOOK include/linux/netfilter.h:308 [inline] mld_sendpack+0x9f0/0x11d0 net/ipv6/mcast.c:1819 mld_send_cr net/ipv6/mcast.c:2120 [inline] mld_ifc_work+0x740/0xca0 net/ipv6/mcast.c:2651 process_one_work+0x9c5/0x1ba0 kernel/workqueue.c:3229 process_scheduled_works kernel/workqueue.c:3310 [inline] worker_thread+0x6c8/0xf00 kernel/workqueue.c:3391 kthread+0x2c1/0x3a0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Reported-by: syzbot+d693c07c6f647e0388d3@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d693c07c6f647e0388d3 Fixes: 47ee3051c856 ("[PATCH] USB: usbnet (5/9) module for genesys gl620a cables") Cc: stable@vger.kernel.org Signed-off-by: Nikita Zhandarovich Link: https://patch.msgid.link/20250224172919.1220522-1-n.zhandarovich@fintech.ru Signed-off-by: Paolo Abeni --- drivers/net/usb/gl620a.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c index 46af78caf457..0bfa37c14059 100644 --- a/drivers/net/usb/gl620a.c +++ b/drivers/net/usb/gl620a.c @@ -179,9 +179,7 @@ static int genelink_bind(struct usbnet *dev, struct usb_interface *intf) { dev->hard_mtu = GL_RCV_BUF_SIZE; dev->net->hard_header_len += 4; - dev->in = usb_rcvbulkpipe(dev->udev, dev->driver_info->in); - dev->out = usb_sndbulkpipe(dev->udev, dev->driver_info->out); - return 0; + return usbnet_get_endpoints(dev, intf); } static const struct driver_info genelink_info = { -- cgit v1.2.3 From 674fcb4f4a7e3e277417a01788cc6daae47c3804 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Feb 2025 22:12:52 +0000 Subject: idpf: fix checksums set in idpf_rx_rsc() idpf_rx_rsc() uses skb_transport_offset(skb) while the transport header is not set yet. This triggers the following warning for CONFIG_DEBUG_NET=y builds. DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)) [ 69.261620] WARNING: CPU: 7 PID: 0 at ./include/linux/skbuff.h:3020 idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261629] Modules linked in: vfat fat dummy bridge intel_uncore_frequency_tpmi intel_uncore_frequency_common intel_vsec_tpmi idpf intel_vsec cdc_ncm cdc_eem cdc_ether usbnet mii xhci_pci xhci_hcd ehci_pci ehci_hcd libeth [ 69.261644] CPU: 7 UID: 0 PID: 0 Comm: swapper/7 Tainted: G S W 6.14.0-smp-DEV #1697 [ 69.261648] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN [ 69.261650] RIP: 0010:idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261677] ? __warn (kernel/panic.c:242 kernel/panic.c:748) [ 69.261682] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261687] ? report_bug (lib/bug.c:?) [ 69.261690] ? handle_bug (arch/x86/kernel/traps.c:285) [ 69.261694] ? exc_invalid_op (arch/x86/kernel/traps.c:309) [ 69.261697] ? asm_exc_invalid_op (arch/x86/include/asm/idtentry.h:621) [ 69.261700] ? __pfx_idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:4011) idpf [ 69.261704] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261708] ? idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:3072) idpf [ 69.261712] __napi_poll (net/core/dev.c:7194) [ 69.261716] net_rx_action (net/core/dev.c:7265) [ 69.261718] ? __qdisc_run (net/sched/sch_generic.c:293) [ 69.261721] ? sched_clock (arch/x86/include/asm/preempt.h:84 arch/x86/kernel/tsc.c:288) [ 69.261726] handle_softirqs (kernel/softirq.c:561) Fixes: 3a8845af66edb ("idpf: add RX splitq napi poll support") Signed-off-by: Eric Dumazet Cc: Alan Brady Cc: Joshua Hay Cc: Willem de Bruijn Acked-by: Przemek Kitszel Link: https://patch.msgid.link/20250226221253.1927782-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 9be6a6b59c4e..977741c41498 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3013,7 +3013,6 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, skb_shinfo(skb)->gso_size = rsc_seg_len; skb_reset_network_header(skb); - len = skb->len - skb_transport_offset(skb); if (ipv4) { struct iphdr *ipv4h = ip_hdr(skb); @@ -3022,6 +3021,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, /* Reset and set transport header offset in skb */ skb_set_transport_header(skb, sizeof(struct iphdr)); + len = skb->len - skb_transport_offset(skb); /* Compute the TCP pseudo header checksum*/ tcp_hdr(skb)->check = @@ -3031,6 +3031,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + len = skb->len - skb_transport_offset(skb); tcp_hdr(skb)->check = ~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0); } -- cgit v1.2.3 From 54e1b4becf5e220be03db4e1be773c1310e8cbbd Mon Sep 17 00:00:00 2001 From: Meghana Malladi Date: Thu, 27 Feb 2025 14:54:41 +0530 Subject: net: ti: icss-iep: Reject perout generation request IEP driver supports both perout and pps signal generation but perout feature is faulty with half-cooked support due to some missing configuration. Remove perout support from the driver and reject perout requests with "not supported" error code. Fixes: c1e0230eeaab2 ("net: ti: icss-iep: Add IEP driver") Signed-off-by: Meghana Malladi Reviewed-by: Vadim Fedorenko Link: https://patch.msgid.link/20250227092441.1848419-1-m-malladi@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/icssg/icss_iep.c | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 768578c0d958..d59c1744840a 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -474,26 +474,7 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep, static int icss_iep_perout_enable(struct icss_iep *iep, struct ptp_perout_request *req, int on) { - int ret = 0; - - mutex_lock(&iep->ptp_clk_mutex); - - if (iep->pps_enabled) { - ret = -EBUSY; - goto exit; - } - - if (iep->perout_enabled == !!on) - goto exit; - - ret = icss_iep_perout_enable_hw(iep, req, on); - if (!ret) - iep->perout_enabled = !!on; - -exit: - mutex_unlock(&iep->ptp_clk_mutex); - - return ret; + return -EOPNOTSUPP; } static void icss_iep_cap_cmp_work(struct work_struct *work) -- cgit v1.2.3