From bc50682128bde778a1ddc457a02d92a637c20c6f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 22 Feb 2025 12:28:04 -0500 Subject: [PATCH 01/16] MAINTAINERS: socket timestamping: add Jason Xing as reviewer Jason has been helping as reviewer for this area already, and has contributed various features directly, notably BPF timestamping. Also extend coverage to all timestamping tests, including those new with BPF timestamping. Link: https://lore.kernel.org/netdev/20250220072940.99994-1-kerneljasonxing@gmail.com/ Signed-off-by: Willem de Bruijn Reviewed-by: Jason Xing Link: https://patch.msgid.link/20250222172839.642079-1-willemdebruijn.kernel@gmail.com Signed-off-by: Paolo Abeni --- MAINTAINERS | 3 +++ 1 file changed, 3 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index ac15093537c6..c92bcd02049e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21923,10 +21923,13 @@ F: sound/soc/uniphier/ SOCKET TIMESTAMPING M: Willem de Bruijn +R: Jason Xing S: Maintained F: Documentation/networking/timestamping.rst F: include/linux/net_tstamp.h F: include/uapi/linux/net_tstamp.h +F: tools/testing/selftests/bpf/*/net_timestamping* +F: tools/testing/selftests/net/*timestamp* F: tools/testing/selftests/net/so_txtime.c SOEKRIS NET48XX LED SUPPORT -- 2.51.0 From bab3a6e9ffd600f9db0ebaf8f45e1c6111cf314c Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Mon, 24 Feb 2025 06:17:16 +0100 Subject: [PATCH 02/16] 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(+) 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 -- 2.51.0 From 18912c520674ec4d920fe3826e7e4fefeecdf5ae Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 24 Feb 2025 09:44:01 -0800 Subject: [PATCH 03/16] tcp: devmem: don't write truncated dmabuf CMSGs to userspace Currently, we report -ETOOSMALL (err) only on the first iteration (!sent). When we get put_cmsg error after a bunch of successful put_cmsg calls, we don't signal the error at all. This might be confusing on the userspace side which will see truncated CMSGs but no MSG_CTRUNC signal. Consider the following case: - sizeof(struct cmsghdr) = 16 - sizeof(struct dmabuf_cmsg) = 24 - total cmsg size (CMSG_LEN) = 40 (16+24) When calling recvmsg with msg_controllen=60, the userspace will receive two(!) dmabuf_cmsg(s), the first one will be a valid one and the second one will be silently truncated. There is no easy way to discover the truncation besides doing something like "cm->cmsg_len != CMSG_LEN(sizeof(dmabuf_cmsg))". Introduce new put_devmem_cmsg wrapper that reports an error instead of doing the truncation. Mina suggests that it's the intended way this API should work. Note that we might now report MSG_CTRUNC when the users (incorrectly) call us with msg_control == NULL. Fixes: 8f0b3cc9a4c1 ("tcp: RX path for devmem TCP") Reviewed-by: Mina Almasry Signed-off-by: Stanislav Fomichev Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250224174401.3582695-1-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 2 ++ net/core/scm.c | 10 ++++++++++ net/ipv4/tcp.c | 26 ++++++++++---------------- 3 files changed, 22 insertions(+), 16 deletions(-) diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..c3322eb3d686 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -392,6 +392,8 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); +extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data); struct timespec64; struct __kernel_timespec; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..733c0cbd393d 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -282,6 +282,16 @@ efault: } EXPORT_SYMBOL(put_cmsg); +int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data) +{ + /* Don't produce truncated CMSGs */ + if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len)) + return -ETOOSMALL; + + return put_cmsg(msg, level, type, len, data); +} + void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping64 tss; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d704bda6c41..d74281eca14f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2438,14 +2438,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, */ memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); dmabuf_cmsg.frag_size = copy; - err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, - sizeof(dmabuf_cmsg), &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } sent += copy; @@ -2499,16 +2497,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, offset += copy; remaining_len -= copy; - err = put_cmsg(msg, SOL_SOCKET, - SO_DEVMEM_DMABUF, - sizeof(dmabuf_cmsg), - &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } atomic_long_inc(&niov->pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); -- 2.51.0 From f865c24bc55158313d5779fc81116023a6940ca3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 24 Feb 2025 19:11:50 +0100 Subject: [PATCH 04/16] mptcp: always handle address removal under msk socket lock Syzkaller reported a lockdep splat in the PM control path: WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 sock_owned_by_me include/net/sock.h:1711 [inline] WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 msk_owned_by_me net/mptcp/protocol.h:363 [inline] WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788 Modules linked in: CPU: 0 UID: 0 PID: 6693 Comm: syz.0.205 Not tainted 6.14.0-rc2-syzkaller-00303-gad1b832bf1cf #0 Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 12/27/2024 RIP: 0010:sock_owned_by_me include/net/sock.h:1711 [inline] RIP: 0010:msk_owned_by_me net/mptcp/protocol.h:363 [inline] RIP: 0010:mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788 Code: 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc e8 ca 7b d3 f5 eb b9 e8 c3 7b d3 f5 90 0f 0b 90 e9 dd fb ff ff e8 b5 7b d3 f5 90 <0f> 0b 90 e9 3e fb ff ff 44 89 f1 80 e1 07 38 c1 0f 8c eb fb ff ff RSP: 0000:ffffc900034f6f60 EFLAGS: 00010283 RAX: ffffffff8bee3c2b RBX: 0000000000000001 RCX: 0000000000080000 RDX: ffffc90004d42000 RSI: 000000000000a407 RDI: 000000000000a408 RBP: ffffc900034f7030 R08: ffffffff8bee37f6 R09: 0100000000000000 R10: dffffc0000000000 R11: ffffed100bcc62e4 R12: ffff88805e6316e0 R13: ffff88805e630c00 R14: dffffc0000000000 R15: ffff88805e630c00 FS: 00007f7e9a7e96c0(0000) GS:ffff8880b8600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2fd18ff8 CR3: 0000000032c24000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mptcp_pm_remove_addr+0x103/0x1d0 net/mptcp/pm.c:59 mptcp_pm_remove_anno_addr+0x1f4/0x2f0 net/mptcp/pm_netlink.c:1486 mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_netlink.c:1518 [inline] mptcp_pm_nl_del_addr_doit+0x118d/0x1af0 net/mptcp/pm_netlink.c:1629 genl_family_rcv_msg_doit net/netlink/genetlink.c:1115 [inline] genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline] genl_rcv_msg+0xb1f/0xec0 net/netlink/genetlink.c:1210 netlink_rcv_skb+0x206/0x480 net/netlink/af_netlink.c:2543 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219 netlink_unicast_kernel net/netlink/af_netlink.c:1322 [inline] netlink_unicast+0x7f6/0x990 net/netlink/af_netlink.c:1348 netlink_sendmsg+0x8de/0xcb0 net/netlink/af_netlink.c:1892 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0x221/0x270 net/socket.c:733 ____sys_sendmsg+0x53a/0x860 net/socket.c:2573 ___sys_sendmsg net/socket.c:2627 [inline] __sys_sendmsg+0x269/0x350 net/socket.c:2659 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f7e9998cde9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f7e9a7e9038 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f7e99ba5fa0 RCX: 00007f7e9998cde9 RDX: 000000002000c094 RSI: 0000400000000000 RDI: 0000000000000007 RBP: 00007f7e99a0e2a0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f7e99ba5fa0 R15: 00007fff49231088 Indeed the PM can try to send a RM_ADDR over a msk without acquiring first the msk socket lock. The bugged code-path comes from an early optimization: when there are no subflows, the PM should (usually) not send RM_ADDR notifications. The above statement is incorrect, as without locks another process could concurrent create a new subflow and cause the RM_ADDR generation. Additionally the supposed optimization is not very effective even performance-wise, as most mptcp sockets should have at least one subflow: the MPC one. Address the issue removing the buggy code path, the existing "slow-path" will handle correctly even the edge case. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reported-by: syzbot+cd3ce3d03a3393ae9700@syzkaller.appspotmail.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/546 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-1-f550f636b435@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 572d160edca3..c0e47f4f7b1a 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1514,11 +1514,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, if (mptcp_pm_is_userspace(msk)) goto next; - if (list_empty(&msk->conn_list)) { - mptcp_pm_remove_anno_addr(msk, addr, false); - goto next; - } - lock_sock(sk); remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && -- 2.51.0 From 8668860b0ad32a13fcd6c94a0995b7aa7638c9ef Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 24 Feb 2025 19:11:51 +0100 Subject: [PATCH 05/16] mptcp: reset when MPTCP opts are dropped after join Before this patch, if the checksum was not used, the subflow was only reset if map_data_len was != 0. If there were no MPTCP options or an invalid mapping, map_data_len was not set to the data len, and then the subflow was not reset as it should have been, leaving the MPTCP connection in a wrong fallback mode. This map_data_len condition has been introduced to handle the reception of the infinite mapping. Instead, a new dedicated mapping error could have been returned and treated as a special case. However, the commit 31bf11de146c ("mptcp: introduce MAPPING_BAD_CSUM") has been introduced by Paolo Abeni soon after, and backported later on to stable. It better handle the csum case, and it means the exception for valid_csum_seen in subflow_can_fallback(), plus this one for the infinite mapping in subflow_check_data_avail(), are no longer needed. In other words, the code can be simplified there: a fallback should only be done if msk->allow_infinite_fallback is set. This boolean is set to false once MPTCP-specific operations acting on the whole MPTCP connection vs the initial path have been done, e.g. a second path has been created, or an MPTCP re-injection -- yes, possible even with a single subflow. The subflow_can_fallback() helper can then be dropped, and replaced by this single condition. This also makes the code clearer: a fallback should only be done if it is possible to do so. While at it, no need to set map_data_len to 0 in get_mapping_status() for the infinite mapping case: it will be set to skb->len just after, at the end of subflow_check_data_avail(), and not read in between. Fixes: f8d4bcacff3b ("mptcp: infinite mapping receiving") Cc: stable@vger.kernel.org Reported-by: Chester A. Unal Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/544 Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Tested-by: Chester A. Unal Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-2-f550f636b435@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index dfcbef9c4624..9f18217dddc8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1142,7 +1142,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (data_len == 0) { pr_debug("infinite mapping received\n"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); - subflow->map_data_len = 0; return MAPPING_INVALID; } @@ -1286,18 +1285,6 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss mptcp_schedule_work(sk); } -static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) -{ - struct mptcp_sock *msk = mptcp_sk(subflow->conn); - - if (subflow->mp_join) - return false; - else if (READ_ONCE(msk->csum_enabled)) - return !subflow->valid_csum_seen; - else - return READ_ONCE(msk->allow_infinite_fallback); -} - static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1393,7 +1380,7 @@ fallback: return true; } - if (!subflow_can_fallback(subflow) && subflow->map_data_len) { + if (!READ_ONCE(msk->allow_infinite_fallback)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ -- 2.51.0 From db75a16813aabae3b78c06b1b99f5e314c1f55d3 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 24 Feb 2025 19:11:52 +0100 Subject: [PATCH 06/16] mptcp: safety check before fallback Recently, some fallback have been initiated, while the connection was not supposed to fallback. Add a safety check with a warning to detect when an wrong attempt to fallback is being done. This should help detecting any future issues quicker. Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-3-f550f636b435@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index f6a207958459..ad21925af061 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1199,6 +1199,8 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) pr_debug("TCP fallback already done (msk=%p)\n", msk); return; } + if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback))) + return; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } -- 2.51.0 From 79990cf5e7aded76d0c092c9f5ed31eb1c75e02c Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Mon, 24 Feb 2025 11:06:41 -0800 Subject: [PATCH 07/16] 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(-) 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); -- 2.51.0 From 5c07be96d8b3f8447e980f29b967bf2e1d7ac732 Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Mon, 24 Feb 2025 11:06:42 -0800 Subject: [PATCH 08/16] 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(-) 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, -- 2.51.0 From c6124f6fd3ca37d53ec5cbf62f9d9130ef439eca Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 24 Feb 2025 11:06:44 -0800 Subject: [PATCH 09/16] 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(-) 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(); } -- 2.51.0 From b1e44b4aecb551727a368df5b85c535f2ce932ea Mon Sep 17 00:00:00 2001 From: Piotr Kwapulinski Date: Mon, 24 Feb 2025 11:06:45 -0800 Subject: [PATCH 10/16] 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(-) 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); } /** -- 2.51.0 From 39ab773e4c120f7f98d759415ccc2aca706bbc10 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:44 +0800 Subject: [PATCH 11/16] 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(-) 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; } -- 2.51.0 From da291996b16ebd10626d4b20288327b743aff110 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:45 +0800 Subject: [PATCH 12/16] 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(-) 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; -- 2.51.0 From 432a2cb3ee97a7c6ea578888fe81baad035b9307 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:46 +0800 Subject: [PATCH 13/16] 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(-) 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 -- 2.51.0 From a562d0c4a893eae3ea51d512c4d90ab858a6b7ec Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:47 +0800 Subject: [PATCH 14/16] 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(-) 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); -- 2.51.0 From bbcbc906ab7b5834c1219cd17a38d78dba904aa0 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:48 +0800 Subject: [PATCH 15/16] 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(-) 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; -- 2.51.0 From 8e43decdfbb477dd7800e3902d2d2f105d22ef5f Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:49 +0800 Subject: [PATCH 16/16] 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(+) 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); } -- 2.51.0