From 2bf8d2ae3480da06e64dad3b326ebd2e40c0be86 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 4 Jun 2021 18:08:27 +0800 Subject: [PATCH 01/12] net/mlx5e: Fix an error code in mlx5e_arfs_create_tables() When the code execute 'if (!priv->fs.arfs->wq)', the value of err is 0. So, we use -ENOMEM to indicate that the function create_singlethread_workqueue() return NULL. Clean up smatch warning: drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c:373 mlx5e_arfs_create_tables() warn: missing error code 'err'. Reported-by: Abaci Robot Fixes: f6755b80d693 ("net/mlx5e: Dynamic alloc arfs table for netdev when needed") Signed-off-by: Yang Li Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 5cd466ec6492..25403af32859 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -356,7 +356,7 @@ err: int mlx5e_arfs_create_tables(struct mlx5e_priv *priv) { - int err = 0; + int err = -ENOMEM; int i; if (!(priv->netdev->hw_features & NETIF_F_NTUPLE)) From fb1a3132ee1ac968316e45d21a48703a6db0b6c3 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 31 May 2021 16:28:39 +0300 Subject: [PATCH 02/12] net/mlx5e: Fix use-after-free of encap entry in neigh update handler Function mlx5e_rep_neigh_update() wasn't updated to accommodate rtnl lock removal from TC filter update path and properly handle concurrent encap entry insertion/deletion which can lead to following use-after-free: [23827.464923] ================================================================== [23827.469446] BUG: KASAN: use-after-free in mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.470971] Read of size 4 at addr ffff8881d132228c by task kworker/u20:6/21635 [23827.472251] [23827.472615] CPU: 9 PID: 21635 Comm: kworker/u20:6 Not tainted 5.13.0-rc3+ #5 [23827.473788] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [23827.475639] Workqueue: mlx5e mlx5e_rep_neigh_update [mlx5_core] [23827.476731] Call Trace: [23827.477260] dump_stack+0xbb/0x107 [23827.477906] print_address_description.constprop.0+0x18/0x140 [23827.478896] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.479879] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.480905] kasan_report.cold+0x7c/0xd8 [23827.481701] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.482744] kasan_check_range+0x145/0x1a0 [23827.493112] mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.494054] ? mlx5e_tc_tun_encap_info_equal_generic+0x140/0x140 [mlx5_core] [23827.495296] mlx5e_rep_neigh_update+0x41e/0x5e0 [mlx5_core] [23827.496338] ? mlx5e_rep_neigh_entry_release+0xb80/0xb80 [mlx5_core] [23827.497486] ? read_word_at_a_time+0xe/0x20 [23827.498250] ? strscpy+0xa0/0x2a0 [23827.498889] process_one_work+0x8ac/0x14e0 [23827.499638] ? lockdep_hardirqs_on_prepare+0x400/0x400 [23827.500537] ? pwq_dec_nr_in_flight+0x2c0/0x2c0 [23827.501359] ? rwlock_bug.part.0+0x90/0x90 [23827.502116] worker_thread+0x53b/0x1220 [23827.502831] ? process_one_work+0x14e0/0x14e0 [23827.503627] kthread+0x328/0x3f0 [23827.504254] ? _raw_spin_unlock_irq+0x24/0x40 [23827.505065] ? __kthread_bind_mask+0x90/0x90 [23827.505912] ret_from_fork+0x1f/0x30 [23827.506621] [23827.506987] Allocated by task 28248: [23827.507694] kasan_save_stack+0x1b/0x40 [23827.508476] __kasan_kmalloc+0x7c/0x90 [23827.509197] mlx5e_attach_encap+0xde1/0x1d40 [mlx5_core] [23827.510194] mlx5e_tc_add_fdb_flow+0x397/0xc40 [mlx5_core] [23827.511218] __mlx5e_add_fdb_flow+0x519/0xb30 [mlx5_core] [23827.512234] mlx5e_configure_flower+0x191c/0x4870 [mlx5_core] [23827.513298] tc_setup_cb_add+0x1d5/0x420 [23827.514023] fl_hw_replace_filter+0x382/0x6a0 [cls_flower] [23827.514975] fl_change+0x2ceb/0x4a51 [cls_flower] [23827.515821] tc_new_tfilter+0x89a/0x2070 [23827.516548] rtnetlink_rcv_msg+0x644/0x8c0 [23827.517300] netlink_rcv_skb+0x11d/0x340 [23827.518021] netlink_unicast+0x42b/0x700 [23827.518742] netlink_sendmsg+0x743/0xc20 [23827.519467] sock_sendmsg+0xb2/0xe0 [23827.520131] ____sys_sendmsg+0x590/0x770 [23827.520851] ___sys_sendmsg+0xd8/0x160 [23827.521552] __sys_sendmsg+0xb7/0x140 [23827.522238] do_syscall_64+0x3a/0x70 [23827.522907] entry_SYSCALL_64_after_hwframe+0x44/0xae [23827.523797] [23827.524163] Freed by task 25948: [23827.524780] kasan_save_stack+0x1b/0x40 [23827.525488] kasan_set_track+0x1c/0x30 [23827.526187] kasan_set_free_info+0x20/0x30 [23827.526968] __kasan_slab_free+0xed/0x130 [23827.527709] slab_free_freelist_hook+0xcf/0x1d0 [23827.528528] kmem_cache_free_bulk+0x33a/0x6e0 [23827.529317] kfree_rcu_work+0x55f/0xb70 [23827.530024] process_one_work+0x8ac/0x14e0 [23827.530770] worker_thread+0x53b/0x1220 [23827.531480] kthread+0x328/0x3f0 [23827.532114] ret_from_fork+0x1f/0x30 [23827.532785] [23827.533147] Last potentially related work creation: [23827.534007] kasan_save_stack+0x1b/0x40 [23827.534710] kasan_record_aux_stack+0xab/0xc0 [23827.535492] kvfree_call_rcu+0x31/0x7b0 [23827.536206] mlx5e_tc_del_fdb_flow+0x577/0xef0 [mlx5_core] [23827.537305] mlx5e_flow_put+0x49/0x80 [mlx5_core] [23827.538290] mlx5e_delete_flower+0x6d1/0xe60 [mlx5_core] [23827.539300] tc_setup_cb_destroy+0x18e/0x2f0 [23827.540144] fl_hw_destroy_filter+0x1d2/0x310 [cls_flower] [23827.541148] __fl_delete+0x4dc/0x660 [cls_flower] [23827.541985] fl_delete+0x97/0x160 [cls_flower] [23827.542782] tc_del_tfilter+0x7ab/0x13d0 [23827.543503] rtnetlink_rcv_msg+0x644/0x8c0 [23827.544257] netlink_rcv_skb+0x11d/0x340 [23827.544981] netlink_unicast+0x42b/0x700 [23827.545700] netlink_sendmsg+0x743/0xc20 [23827.546424] sock_sendmsg+0xb2/0xe0 [23827.547084] ____sys_sendmsg+0x590/0x770 [23827.547850] ___sys_sendmsg+0xd8/0x160 [23827.548606] __sys_sendmsg+0xb7/0x140 [23827.549303] do_syscall_64+0x3a/0x70 [23827.549969] entry_SYSCALL_64_after_hwframe+0x44/0xae [23827.550853] [23827.551217] The buggy address belongs to the object at ffff8881d1322200 [23827.551217] which belongs to the cache kmalloc-256 of size 256 [23827.553341] The buggy address is located 140 bytes inside of [23827.553341] 256-byte region [ffff8881d1322200, ffff8881d1322300) [23827.555747] The buggy address belongs to the page: [23827.556847] page:00000000898762aa refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1d1320 [23827.558651] head:00000000898762aa order:2 compound_mapcount:0 compound_pincount:0 [23827.559961] flags: 0x2ffff800010200(slab|head|node=0|zone=2|lastcpupid=0x1ffff) [23827.561243] raw: 002ffff800010200 dead000000000100 dead000000000122 ffff888100042b40 [23827.562653] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 [23827.564112] page dumped because: kasan: bad access detected [23827.565439] [23827.565932] Memory state around the buggy address: [23827.566917] ffff8881d1322180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.568485] ffff8881d1322200: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [23827.569818] >ffff8881d1322280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [23827.571143] ^ [23827.571879] ffff8881d1322300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.573283] ffff8881d1322380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.574654] ================================================================== Most of the necessary logic is already correctly implemented by mlx5e_get_next_valid_encap() helper that is used in neigh stats update handler. Make the handler generic by renaming it to mlx5e_get_next_matching_encap() and use callback to test whether flow is matching instead of hardcoded check for 'valid' flag value. Implement mlx5e_get_next_valid_encap() by calling mlx5e_get_next_matching_encap() with callback that tests encap MLX5_ENCAP_ENTRY_VALID flag. Implement new mlx5e_get_next_init_encap() helper by calling mlx5e_get_next_matching_encap() with callback that tests encap completion result to be non-error and use it in mlx5e_rep_neigh_update() to safely iterate over nhe->encap_list. Remove encap completion logic from mlx5e_rep_update_flows() since the encap entries passed to this function are already guaranteed to be properly initialized by similar code in mlx5e_get_next_init_encap(). Fixes: 2a1f1768fa17 ("net/mlx5e: Refactor neigh update for concurrent execution") Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/en/rep/neigh.c | 15 ++++----- .../ethernet/mellanox/mlx5/core/en/rep/tc.c | 6 +--- .../mellanox/mlx5/core/en/tc_tun_encap.c | 33 +++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/en_tc.h | 3 ++ 4 files changed, 40 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index be0ee03de721..2e9bee4e5209 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -129,10 +129,9 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) work); struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; struct neighbour *n = update_work->n; + struct mlx5e_encap_entry *e = NULL; bool neigh_connected, same_dev; - struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; - struct mlx5e_priv *priv; u8 nud_state, dead; rtnl_lock(); @@ -156,14 +155,12 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) if (!same_dev) goto out; - list_for_each_entry(e, &nhe->encap_list, encap_list) { - if (!mlx5e_encap_take(e)) - continue; + /* mlx5e_get_next_init_encap() releases previous encap before returning + * the next one. + */ + while ((e = mlx5e_get_next_init_encap(nhe, e)) != NULL) + mlx5e_rep_update_flows(netdev_priv(e->out_dev), e, neigh_connected, ha); - priv = netdev_priv(e->out_dev); - mlx5e_rep_update_flows(priv, e, neigh_connected, ha); - mlx5e_encap_put(priv, e); - } out: rtnl_unlock(); mlx5e_release_neigh_update_work(update_work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 311382261840..85eaadc989df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -94,13 +94,9 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv, ASSERT_RTNL(); - /* wait for encap to be fully initialized */ - wait_for_completion(&e->res_ready); - mutex_lock(&esw->offloads.encap_tbl_lock); encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); - if (e->compl_result < 0 || (encap_connected == neigh_connected && - ether_addr_equal(e->h_dest, ha))) + if (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha)) goto unlock; mlx5e_take_all_encap_flows(e, &flow_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index f1fb11680d20..490131e06efb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -251,9 +251,12 @@ static void mlx5e_take_all_route_decap_flows(struct mlx5e_route_entry *r, mlx5e_take_tmp_flow(flow, flow_list, 0); } +typedef bool (match_cb)(struct mlx5e_encap_entry *); + static struct mlx5e_encap_entry * -mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, - struct mlx5e_encap_entry *e) +mlx5e_get_next_matching_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e, + match_cb match) { struct mlx5e_encap_entry *next = NULL; @@ -288,7 +291,7 @@ retry: /* wait for encap to be fully initialized */ wait_for_completion(&next->res_ready); /* continue searching if encap entry is not in valid state after completion */ - if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) { + if (!match(next)) { e = next; goto retry; } @@ -296,6 +299,30 @@ retry: return next; } +static bool mlx5e_encap_valid(struct mlx5e_encap_entry *e) +{ + return e->flags & MLX5_ENCAP_ENTRY_VALID; +} + +static struct mlx5e_encap_entry * +mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_valid); +} + +static bool mlx5e_encap_initialized(struct mlx5e_encap_entry *e) +{ + return e->compl_result >= 0; +} + +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_initialized); +} + void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 25c091795bcd..17027536efba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -178,6 +178,9 @@ void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *f void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list); struct mlx5e_neigh_hash_entry; +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e); void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); void mlx5e_tc_reoffload_flows_work(struct work_struct *work); From 8ad893e516a77209a1818a2072d2027d87db809f Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 28 May 2021 13:20:32 -0500 Subject: [PATCH 03/12] net/mlx5e: Remove dependency in IPsec initialization flows Currently, IPsec feature is disabled because mlx5e_build_nic_netdev is required to be called after mlx5e_ipsec_init. This requirement is invalid as mlx5e_build_nic_netdev and mlx5e_ipsec_init initialize independent resources. Remove ipsec pointer check in mlx5e_build_nic_netdev so that the two functions can be called at any order. Fixes: 547eede070eb ("net/mlx5e: IPSec, Innova IPSec offload infrastructure") Signed-off-by: Huy Nguyen Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 3d45341e2216..26f7fab109d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -532,9 +532,6 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; struct net_device *netdev = priv->netdev; - if (!priv->ipsec) - return; - if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) || !MLX5_CAP_ETH(mdev, swp)) { mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n"); From a3e5fd9314dfc4314a9567cde96e1aef83a7458a Mon Sep 17 00:00:00 2001 From: Dima Chumak Date: Wed, 26 May 2021 13:45:10 +0300 Subject: [PATCH 04/12] net/mlx5e: Fix page reclaim for dead peer hairpin When adding a hairpin flow, a firmware-side send queue is created for the peer net device, which claims some host memory pages for its internal ring buffer. If the peer net device is removed/unbound before the hairpin flow is deleted, then the send queue is not destroyed which leads to a stack trace on pci device remove: [ 748.005230] mlx5_core 0000:08:00.2: wait_func:1094:(pid 12985): MANAGE_PAGES(0x108) timeout. Will cause a leak of a command resource [ 748.005231] mlx5_core 0000:08:00.2: reclaim_pages:514:(pid 12985): failed reclaiming pages: err -110 [ 748.001835] mlx5_core 0000:08:00.2: mlx5_reclaim_root_pages:653:(pid 12985): failed reclaiming pages (-110) for func id 0x0 [ 748.002171] ------------[ cut here ]------------ [ 748.001177] FW pages counter is 4 after reclaiming all pages [ 748.001186] WARNING: CPU: 1 PID: 12985 at drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:685 mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ +0.002771] Modules linked in: cls_flower mlx5_ib mlx5_core ptp pps_core act_mirred sch_ingress openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_umad ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay fuse [last unloaded: pps_core] [ 748.007225] CPU: 1 PID: 12985 Comm: tee Not tainted 5.12.0+ #1 [ 748.001376] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 748.002315] RIP: 0010:mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ 748.001679] Code: 28 00 00 00 0f 85 22 01 00 00 48 81 c4 b0 00 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 c7 c7 40 cc 19 a1 e8 9f 71 0e e2 <0f> 0b e9 30 ff ff ff 48 c7 c7 a0 cc 19 a1 e8 8c 71 0e e2 0f 0b e9 [ 748.003781] RSP: 0018:ffff88815220faf8 EFLAGS: 00010286 [ 748.001149] RAX: 0000000000000000 RBX: ffff8881b4900280 RCX: 0000000000000000 [ 748.001445] RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffffed102a441f51 [ 748.001614] RBP: 00000000000032b9 R08: 0000000000000001 R09: ffffed1054a15ee8 [ 748.001446] R10: ffff8882a50af73b R11: ffffed1054a15ee7 R12: fffffbfff07c1e30 [ 748.001447] R13: dffffc0000000000 R14: ffff8881b492cba8 R15: 0000000000000000 [ 748.001429] FS: 00007f58bd08b580(0000) GS:ffff8882a5080000(0000) knlGS:0000000000000000 [ 748.001695] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 748.001309] CR2: 000055a026351740 CR3: 00000001d3b48006 CR4: 0000000000370ea0 [ 748.001506] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 748.001483] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 748.001654] Call Trace: [ 748.000576] ? mlx5_satisfy_startup_pages+0x290/0x290 [mlx5_core] [ 748.001416] ? mlx5_cmd_teardown_hca+0xa2/0xd0 [mlx5_core] [ 748.001354] ? mlx5_cmd_init_hca+0x280/0x280 [mlx5_core] [ 748.001203] mlx5_function_teardown+0x30/0x60 [mlx5_core] [ 748.001275] mlx5_uninit_one+0xa7/0xc0 [mlx5_core] [ 748.001200] remove_one+0x5f/0xc0 [mlx5_core] [ 748.001075] pci_device_remove+0x9f/0x1d0 [ 748.000833] device_release_driver_internal+0x1e0/0x490 [ 748.001207] unbind_store+0x19f/0x200 [ 748.000942] ? sysfs_file_ops+0x170/0x170 [ 748.001000] kernfs_fop_write_iter+0x2bc/0x450 [ 748.000970] new_sync_write+0x373/0x610 [ 748.001124] ? new_sync_read+0x600/0x600 [ 748.001057] ? lock_acquire+0x4d6/0x700 [ 748.000908] ? lockdep_hardirqs_on_prepare+0x400/0x400 [ 748.001126] ? fd_install+0x1c9/0x4d0 [ 748.000951] vfs_write+0x4d0/0x800 [ 748.000804] ksys_write+0xf9/0x1d0 [ 748.000868] ? __x64_sys_read+0xb0/0xb0 [ 748.000811] ? filp_open+0x50/0x50 [ 748.000919] ? syscall_enter_from_user_mode+0x1d/0x50 [ 748.001223] do_syscall_64+0x3f/0x80 [ 748.000892] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 748.001026] RIP: 0033:0x7f58bcfb22f7 [ 748.000944] Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 [ 748.003925] RSP: 002b:00007fffd7f2aaa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 748.001732] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f58bcfb22f7 [ 748.001426] RDX: 000000000000000d RSI: 00007fffd7f2abc0 RDI: 0000000000000003 [ 748.001746] RBP: 00007fffd7f2abc0 R08: 0000000000000000 R09: 0000000000000001 [ 748.001631] R10: 00000000000001b6 R11: 0000000000000246 R12: 000000000000000d [ 748.001537] R13: 00005597ac2c24a0 R14: 000000000000000d R15: 00007f58bd084700 [ 748.001564] irq event stamp: 0 [ 748.000787] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [ 748.001399] hardirqs last disabled at (0): [] copy_process+0x146f/0x5eb0 [ 748.001854] softirqs last enabled at (0): [] copy_process+0x14ae/0x5eb0 [ 748.013431] softirqs last disabled at (0): [<0000000000000000>] 0x0 [ 748.001492] ---[ end trace a6fabd773d1c51ae ]--- Fix by destroying the send queue of a hairpin peer net device that is being removed/unbound, which returns the allocated ring buffer pages to the host. Fixes: 4d8fcf216c90 ("net/mlx5e: Avoid unbounded peer devices when unpairing TC hairpin rules") Signed-off-by: Dima Chumak Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- .../ethernet/mellanox/mlx5/core/transobj.c | 30 +++++++++++++++---- include/linux/mlx5/transobj.h | 1 + 3 files changed, 26 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dd64878e5b38..d4b0f270b6bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4765,7 +4765,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { wait_for_completion(&hpe->res_ready); if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) - hpe->hp->pair->peer_gone = true; + mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair); mlx5e_hairpin_put(priv, hpe); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index 01cc00ad8acf..b6931bbe52d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -424,6 +424,15 @@ err_modify_sq: return err; } +static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp) +{ + int i; + + for (i = 0; i < hp->num_channels; i++) + mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, + MLX5_SQC_STATE_RST, 0, 0); +} + static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) { int i; @@ -432,13 +441,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_RST, 0, 0); - /* unset peer SQs */ - if (hp->peer_gone) - return; - for (i = 0; i < hp->num_channels; i++) - mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_RST, 0, 0); + if (!hp->peer_gone) + mlx5_hairpin_unpair_peer_sq(hp); } struct mlx5_hairpin * @@ -485,3 +490,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp) mlx5_hairpin_destroy_queues(hp); kfree(hp); } + +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp) +{ + int i; + + mlx5_hairpin_unpair_peer_sq(hp); + + /* destroy peer SQ */ + for (i = 0; i < hp->num_channels; i++) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + + hp->peer_gone = true; +} diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 028f442530cf..60ffeb6b67ae 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -85,4 +85,5 @@ mlx5_core_hairpin_create(struct mlx5_core_dev *func_mdev, struct mlx5_hairpin_params *params); void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair); +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp); #endif /* __TRANSOBJ_H__ */ From c189716b2a7c1d2d8658e269735273caa1c38b54 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 6 Jun 2021 11:20:46 +0300 Subject: [PATCH 05/12] net/mlx5: Consider RoCE cap before init RDMA resources Check if RoCE is supported by the device before enable it in the vport context and create all the RDMA steering objects. Fixes: 80f09dfc237f ("net/mlx5: Eswitch, enable RoCE loopback traffic") Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/rdma.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 441b5453acae..540cf05f6373 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -156,6 +156,9 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { int err; + if (!MLX5_CAP_GEN(dev, roce)) + return; + err = mlx5_nic_vport_enable_roce(dev); if (err) { mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err); From 4aaf96ac8b45d8e2e019b6b53cce65a73c4ace2c Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 6 Jun 2021 11:23:41 +0300 Subject: [PATCH 06/12] net/mlx5: DR, Don't use SW steering when RoCE is not supported SW steering uses RC QP to write/read to/from ICM, hence it's not supported when RoCE is not supported as well. Fixes: 70605ea545e8 ("net/mlx5: DR, Expose APIs for direct rule managing") Signed-off-by: Maor Gottlieb Reviewed-by: Alex Vesker Reviewed-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 612b0ac31db2..9737565cd8d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -124,10 +124,11 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action); static inline bool mlx5dr_is_supported(struct mlx5_core_dev *dev) { - return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || - (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && - (MLX5_CAP_GEN(dev, steering_format_version) <= - MLX5_STEERING_FORMAT_CONNECTX_6DX)); + return MLX5_CAP_GEN(dev, roce) && + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && + (MLX5_CAP_GEN(dev, steering_format_version) <= + MLX5_STEERING_FORMAT_CONNECTX_6DX))); } /* buddy functions & structure */ From 11f5ac3e05c134d333afe6f84ab10e22bc0a5d5a Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Wed, 28 Apr 2021 19:39:26 +0800 Subject: [PATCH 07/12] net/mlx5e: Verify dev is present in get devlink port ndo When changing eswitch mode, the netdev is detached from the hardware resources. So verify dev is present in get devlink port ndo. Otherwise, we will hit the following panic: [241535.973539] RIP: 0010:__devlink_port_phys_port_name_get+0x13/0x1b0 [241535.976471] RSP: 0018:ffff9eaf0ae1b7c8 EFLAGS: 00010292 [241535.977471] RAX: 000000000002d370 RBX: 000000000002d370 RCX: 0000000000000000 [241535.978479] RDX: 0000000000000010 RSI: ffff9eaf0ae1b858 RDI: 000000000002d370 [241535.979482] RBP: ffff9eaf0ae1b7e0 R08: 000000000000002a R09: ffff8888d54d13da [241535.980486] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8888e6700000 [241535.981491] R13: ffff9eaf0ae1b858 R14: 0000000000000010 R15: 0000000000000000 [241535.982489] FS: 00007fd374ef3740(0000) GS:ffff88909ea00000(0000) knlGS:0000000000000000 [241535.983494] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [241535.984487] CR2: 000000000002d444 CR3: 000000089fd26006 CR4: 00000000003706e0 [241535.985502] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [241535.986499] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [241535.987477] Call Trace: [241535.988426] ? nla_put_64bit+0x71/0xa0 [241535.989368] devlink_compat_phys_port_name_get+0x50/0xa0 [241535.990312] dev_get_phys_port_name+0x4b/0x60 [241535.991252] rtnl_fill_ifinfo+0x57b/0xcb0 [241535.992192] rtnl_dump_ifinfo+0x58f/0x6d0 [241535.993123] ? ksize+0x14/0x20 [241535.994033] ? __alloc_skb+0xe8/0x250 [241535.994935] netlink_dump+0x17c/0x300 [241535.995821] netlink_recvmsg+0x1de/0x2c0 [241535.996677] sock_recvmsg+0x70/0x80 [241535.997518] ____sys_recvmsg+0x9b/0x1b0 [241535.998360] ? iovec_from_user+0x82/0x120 [241535.999202] ? __import_iovec+0x2c/0x130 [241536.000031] ___sys_recvmsg+0x94/0x130 [241536.000850] ? __handle_mm_fault+0x56d/0x6e0 [241536.001668] __sys_recvmsg+0x5f/0xb0 [241536.002464] ? syscall_enter_from_user_mode+0x2b/0x80 [241536.003242] __x64_sys_recvmsg+0x1f/0x30 [241536.004008] do_syscall_64+0x38/0x50 [241536.004767] entry_SYSCALL_64_after_hwframe+0x44/0xae [241536.005532] RIP: 0033:0x7fd375014f47 Fixes: 2ff349c5edfe ("net/mlx5e: Verify dev is present in some ndos") Signed-off-by: Roi Dayan Signed-off-by: Chris Mi Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 0dd7615e5931..bc33eaada3b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -64,6 +64,8 @@ struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) struct mlx5e_priv *priv = netdev_priv(dev); struct devlink_port *port; + if (!netif_device_present(dev)) + return NULL; port = mlx5e_devlink_get_dl_port(priv); if (port->registered) return port; From 9ae8c18c5e4d8814d3b405a07712fa5464070e3e Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 29 Apr 2021 10:03:20 +0300 Subject: [PATCH 08/12] net/mlx5e: Don't update netdev RQs with PTP-RQ Since the driver opens the PTP-RQ under channel 0, it appears to the stack as if the SKB was received on rxq0. So from thew stack POV there are still the same number of RX queues. Fixes: 960fbfe222a4 ("net/mlx5e: Allow coexistence of CQE compression and HW TS PTP") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ec6bafe7a2e5..263adc82b4e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2705,8 +2705,6 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) nch = priv->channels.params.num_channels; ntc = priv->channels.params.num_tc; num_rxqs = nch * priv->profile->rq_groups; - if (priv->channels.params.ptp_rx) - num_rxqs++; mlx5e_netdev_set_tcs(netdev, nch, ntc); From a6ee6f5f1082c416f9bfffbae1a87feff8a6ab3d Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 19 Apr 2021 11:58:31 +0300 Subject: [PATCH 09/12] net/mlx5e: Fix select queue to consider SKBTX_HW_TSTAMP Steering packets to PTP-SQ should be done only if the SKB has SKBTX_HW_TSTAMP set in the tx_flags. While here, take the function into a header and inline it. Set the whole condition to select the PTP-SQ to unlikely. Fixes: 24c22dd0918b ("net/mlx5e: Add states to PTP channel") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/ptp.c | 1 - .../net/ethernet/mellanox/mlx5/core/en/ptp.h | 22 ++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/en_tx.c | 25 +++---------------- 3 files changed, 25 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index d907c1acd4d5..778e229310a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2020 Mellanox Technologies -#include #include "en/ptp.h" #include "en/txrx.h" #include "en/params.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index ab935cce952b..c96668bd701c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -6,6 +6,7 @@ #include "en.h" #include "en_stats.h" +#include struct mlx5e_ptpsq { struct mlx5e_txqsq txqsq; @@ -43,6 +44,27 @@ struct mlx5e_ptp { DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES); }; +static inline bool mlx5e_use_ptpsq(struct sk_buff *skb) +{ + struct flow_keys fk; + + if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) + return false; + + if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) + return false; + + if (fk.basic.n_proto == htons(ETH_P_1588)) + return true; + + if (fk.basic.n_proto != htons(ETH_P_IP) && + fk.basic.n_proto != htons(ETH_P_IPV6)) + return false; + + return (fk.basic.ip_proto == IPPROTO_UDP && + fk.ports.dst == htons(PTP_EV_PORT)); +} + int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, u8 lag_port, struct mlx5e_ptp **cp); void mlx5e_ptp_close(struct mlx5e_ptp *c); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 8ba62671f5f1..320fe0cda917 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -32,7 +32,6 @@ #include #include -#include #include #include #include "en.h" @@ -67,24 +66,6 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb } #endif -static bool mlx5e_use_ptpsq(struct sk_buff *skb) -{ - struct flow_keys fk; - - if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) - return false; - - if (fk.basic.n_proto == htons(ETH_P_1588)) - return true; - - if (fk.basic.n_proto != htons(ETH_P_IP) && - fk.basic.n_proto != htons(ETH_P_IPV6)) - return false; - - return (fk.basic.ip_proto == IPPROTO_UDP && - fk.ports.dst == htons(PTP_EV_PORT)); -} - static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -145,9 +126,9 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, } ptp_channel = READ_ONCE(priv->channels.ptp); - if (unlikely(ptp_channel) && - test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) && - mlx5e_use_ptpsq(skb)) + if (unlikely(ptp_channel && + test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) && + mlx5e_use_ptpsq(skb))) return mlx5e_select_ptpsq(dev, skb); txq_ix = netdev_pick_tx(dev, skb, NULL); From 7a545077cb6701957e84c7f158630bb5c984e648 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 25 Feb 2021 12:27:53 +0200 Subject: [PATCH 10/12] Revert "net/mlx5: Arm only EQs with EQEs" In the scenario described below, an EQ can remain in FIRED state which can result in missing an interrupt generation. The scenario: device mlx5_core driver ------ ---------------- EQ1.eqe generated EQ1.MSI-X sent EQ1.state = FIRED EQ2.eqe generated mlx5_irq() polls - eq1_eqes() arm eq1 polls - eq2_eqes() arm eq2 EQ2.MSI-X sent EQ2.state = FIRED mlx5_irq() polls - eq2_eqes() -- no eqes found driver skips EQ arming; ->EQ2 remains fired, misses generating interrupt. Hence, always arm the EQ by reverting the cited commit in fixes tag. Fixes: d894892dda25 ("net/mlx5: Arm only EQs with EQEs") Signed-off-by: Shay Drory Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 77c0ca655975..940333410267 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -136,7 +136,7 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, eqe = next_eqe_sw(eq); if (!eqe) - return 0; + goto out; do { struct mlx5_core_cq *cq; @@ -161,6 +161,8 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); + +out: eq_update_ci(eq, 1); if (cqn != -1) @@ -248,9 +250,9 @@ static int mlx5_eq_async_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); - eq_update_ci(eq, 1); out: + eq_update_ci(eq, 1); mlx5_eq_async_int_unlock(eq_async, recovery, &flags); return unlikely(recovery) ? num_eqes : 0; From 6d6727dddc7f93fcc155cb8d0c49c29ae0e71122 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 10 May 2021 14:34:58 +0300 Subject: [PATCH 11/12] net/mlx5e: Block offload of outer header csum for UDP tunnels The device is able to offload either the outer header csum or inner header csum. The driver utilizes the inner csum offload. Hence, block setting of tx-udp_tnl-csum-segmentation and set it to off[fixed]. Fixes: b49663c8fb49 ("net/mlx5e: Add support for UDP tunnel segmentation with outer checksum offload") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 263adc82b4e1..d4167f7be99c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4822,13 +4822,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) } if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) { - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) { From 54e1217b90486c94b26f24dcee1ee5ef5372f832 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 26 May 2021 10:40:36 +0300 Subject: [PATCH 12/12] net/mlx5e: Block offload of outer header csum for GRE tunnel The device is able to offload either the outer header csum or inner header csum. The driver utilizes the inner csum offload. So, prohibit setting of tx-gre-csum-segmentation and let it be: off[fixed]. Fixes: 2729984149e6 ("net/mlx5e: Support TSO and TX checksum offloads for GRE tunnels") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d4167f7be99c..d26b8ed51195 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4828,12 +4828,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) { - netdev->hw_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->gso_partial_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; + netdev->hw_features |= NETIF_F_GSO_GRE; + netdev->hw_enc_features |= NETIF_F_GSO_GRE; + netdev->gso_partial_features |= NETIF_F_GSO_GRE; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_IPIP)) {