From cc4a9cc03faa6d8db1a6954bb536f2c1e63bdff6 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 15 Sep 2021 13:25:31 +0300 Subject: net/mlx5e: kTLS, Fix crash in RX resync flow For the TLS RX resync flow, we maintain a list of TLS contexts that require some attention, to communicate their resync information to the HW. Here we fix list corruptions, by protecting the entries against movements coming from resync_handle_seq_match(), until their resync handling in napi is fully completed. Fixes: e9ce991bce5b ("net/mlx5e: kTLS, Add resiliency to RX resync failures") Signed-off-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c | 23 ++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 62abce008c7b..a2a9f68579dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -55,6 +55,7 @@ struct mlx5e_ktls_offload_context_rx { DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS); /* resync */ + spinlock_t lock; /* protects resync fields */ struct mlx5e_ktls_rx_resync_ctx resync; struct list_head list; }; @@ -386,14 +387,18 @@ static void resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_r struct mlx5e_icosq *sq; bool trigger_poll; - memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq)); - sq = &c->async_icosq; ktls_resync = sq->ktls_resync; + trigger_poll = false; spin_lock_bh(&ktls_resync->lock); - list_add_tail(&priv_rx->list, &ktls_resync->list); - trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state); + spin_lock_bh(&priv_rx->lock); + memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq)); + if (list_empty(&priv_rx->list)) { + list_add_tail(&priv_rx->list, &ktls_resync->list); + trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state); + } + spin_unlock_bh(&priv_rx->lock); spin_unlock_bh(&ktls_resync->lock); if (!trigger_poll) @@ -617,6 +622,8 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, if (err) goto err_create_key; + INIT_LIST_HEAD(&priv_rx->list); + spin_lock_init(&priv_rx->lock); priv_rx->crypto_info = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info; @@ -730,10 +737,14 @@ bool mlx5e_ktls_rx_handle_resync_list(struct mlx5e_channel *c, int budget) priv_rx = list_first_entry(&local_list, struct mlx5e_ktls_offload_context_rx, list); + spin_lock(&priv_rx->lock); cseg = post_static_params(sq, priv_rx); - if (IS_ERR(cseg)) + if (IS_ERR(cseg)) { + spin_unlock(&priv_rx->lock); break; - list_del(&priv_rx->list); + } + list_del_init(&priv_rx->list); + spin_unlock(&priv_rx->lock); db_cseg = cseg; } if (db_cseg) -- cgit v1.2.3-59-g8ed1b From 362980eada85b5ea691e5e0d9257a991aa7ade47 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 21 Oct 2021 18:15:10 +0300 Subject: net/mlx5e: Wait for concurrent flow deletion during neigh/fib events Function mlx5e_take_tmp_flow() skips flows with zero reference count. This can cause syndrome 0x179e84 when the called from neigh or route update code and the skipped flow is not removed from the hardware by the time underlying encap/decap resource is deleted. Add new completion 'del_hw_done' that is completed when flow is unoffloaded. This is safe to do because flow with reference count zero needs to be detached from encap/decap entry before its memory is deallocated, which requires taking the encap_tbl_lock mutex that is held by the event handlers code. Fixes: 8914add2c9e5 ("net/mlx5e: Handle FIB events to update tunnel endpoint device") Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c | 8 +++++++- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 ++ 3 files changed, 10 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 8f64f2c8895a..b689701ac7d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -102,6 +102,7 @@ struct mlx5e_tc_flow { refcount_t refcnt; struct rcu_head rcu_head; struct completion init_done; + struct completion del_hw_done; int tunnel_id; /* the mapped tunnel id of this flow */ struct mlx5_flow_attr *attr; }; 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 660cca73c36c..042b1abe1437 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 @@ -245,8 +245,14 @@ static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow, struct list_head *flow_list, int index) { - if (IS_ERR(mlx5e_flow_get(flow))) + if (IS_ERR(mlx5e_flow_get(flow))) { + /* Flow is being deleted concurrently. Wait for it to be + * unoffloaded from hardware, otherwise deleting encap will + * fail. + */ + wait_for_completion(&flow->del_hw_done); return; + } wait_for_completion(&flow->init_done); flow->tmp_entry_index = index; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 835caa1c7b74..cb76c41fe163 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1600,6 +1600,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, else mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); } + complete_all(&flow->del_hw_done); if (mlx5_flow_has_geneve_opt(flow)) mlx5_geneve_tlv_option_del(priv->mdev->geneve); @@ -4465,6 +4466,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, INIT_LIST_HEAD(&flow->l3_to_l2_reformat); refcount_set(&flow->refcnt, 1); init_completion(&flow->init_done); + init_completion(&flow->del_hw_done); *__flow = flow; *__parse_attr = parse_attr; -- cgit v1.2.3-59-g8ed1b From d7751d6476185ff754b9dad2cba0c0a6e43ecadc Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 20 May 2021 17:09:58 +0300 Subject: net/mlx5: E-Switch, Fix resetting of encap mode when entering switchdev E-Switch encap mode is relevant only when in switchdev mode. The RDMA driver can query the encap configuration via mlx5_eswitch_get_encap_mode(). Make sure it returns the currently used mode and not the set one. This reverts the cited commit which reset the encap mode on entering switchdev and fixes the original issue properly. Fixes: 9a64144d683a ("net/mlx5: E-Switch, Fix default encap mode") Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 9 +++++++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 7 ------- include/linux/mlx5/eswitch.h | 4 ++-- 3 files changed, 9 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index ec136b499204..5872cc8bf953 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1572,6 +1572,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->enabled_vports = 0; esw->mode = MLX5_ESWITCH_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) && + MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)) + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; + else + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; dev->priv.eswitch = esw; BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); @@ -1934,7 +1939,7 @@ free_out: return err; } -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1948,7 +1953,7 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) struct mlx5_eswitch *esw; esw = dev->priv.eswitch; - return mlx5_esw_allowed(esw) ? esw->offloads.encap : + return (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS) ? esw->offloads.encap : DEVLINK_ESWITCH_ENCAP_MODE_NONE; } EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f4eaa5893886..80fa76f60e1e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3183,12 +3183,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) u64 mapping_id; int err; - if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) && - MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap)) - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; - else - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; - mutex_init(&esw->offloads.termtbl_mutex); mlx5_rdma_enable_roce(esw->dev); @@ -3286,7 +3280,6 @@ void esw_offloads_disable(struct mlx5_eswitch *esw) esw_offloads_metadata_uninit(esw); mlx5_rdma_disable_roce(esw->dev); mutex_destroy(&esw->offloads.termtbl_mutex); - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 97afcea39a7b..8b18fe9771f9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -145,13 +145,13 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { return MLX5_ESWITCH_NONE; } -- cgit v1.2.3-59-g8ed1b From 76ded29d3fcda4928da8849ffc446ea46871c1c2 Mon Sep 17 00:00:00 2001 From: Valentine Fatiev Date: Tue, 26 Oct 2021 11:42:41 +0300 Subject: net/mlx5e: nullify cq->dbg pointer in mlx5_debug_cq_remove() Prior to this patch in case mlx5_core_destroy_cq() failed it proceeds to rest of destroy operations. mlx5_core_destroy_cq() could be called again by user and cause additional call of mlx5_debug_cq_remove(). cq->dbg was not nullify in previous call and cause the crash. Fix it by nullify cq->dbg pointer after removal. Also proceed to destroy operations only if FW return 0 for MLX5_CMD_OP_DESTROY_CQ command. general protection fault, probably for non-canonical address 0x2000300004058: 0000 [#1] SMP PTI CPU: 5 PID: 1228 Comm: python Not tainted 5.15.0-rc5_for_upstream_min_debug_2021_10_14_11_06 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:lockref_get+0x1/0x60 Code: 5d e9 53 ff ff ff 48 8d 7f 70 e8 0a 2e 48 00 c7 85 d0 00 00 00 02 00 00 00 c6 45 70 00 fb 5d c3 c3 cc cc cc cc cc cc cc cc 53 <48> 8b 17 48 89 fb 85 d2 75 3d 48 89 d0 bf 64 00 00 00 48 89 c1 48 RSP: 0018:ffff888137dd7a38 EFLAGS: 00010206 RAX: 0000000000000000 RBX: ffff888107d5f458 RCX: 00000000fffffffe RDX: 000000000002c2b0 RSI: ffffffff8155e2e0 RDI: 0002000300004058 RBP: ffff888137dd7a88 R08: 0002000300004058 R09: ffff8881144a9f88 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8881141d4000 R13: ffff888137dd7c68 R14: ffff888137dd7d58 R15: ffff888137dd7cc0 FS: 00007f4644f2a4c0(0000) GS:ffff8887a2d40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b4500f4380 CR3: 0000000114f7a003 CR4: 0000000000170ea0 Call Trace: simple_recursive_removal+0x33/0x2e0 ? debugfs_remove+0x60/0x60 debugfs_remove+0x40/0x60 mlx5_debug_cq_remove+0x32/0x70 [mlx5_core] mlx5_core_destroy_cq+0x41/0x1d0 [mlx5_core] devx_obj_cleanup+0x151/0x330 [mlx5_ib] ? __pollwait+0xd0/0xd0 ? xas_load+0x5/0x70 ? xa_load+0x62/0xa0 destroy_hw_idr_uobject+0x20/0x80 [ib_uverbs] uverbs_destroy_uobject+0x3b/0x360 [ib_uverbs] uobj_destroy+0x54/0xa0 [ib_uverbs] ib_uverbs_cmd_verbs+0xaf2/0x1160 [ib_uverbs] ? uverbs_finalize_object+0xd0/0xd0 [ib_uverbs] ib_uverbs_ioctl+0xc4/0x1b0 [ib_uverbs] __x64_sys_ioctl+0x3e4/0x8e0 Fixes: 94b960b9deff ("net/mlx5e: Fix memory leak in mlx5_core_destroy_cq() error path") Signed-off-by: Valentine Fatiev Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 5 +++-- drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 4 +++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 02e77ffe5c3e..5371ad0a12eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -164,13 +164,14 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); MLX5_SET(destroy_cq_in, in, uid, cq->uid); err = mlx5_cmd_exec_in(dev, destroy_cq, in); + if (err) + return err; synchronize_irq(cq->irqn); - mlx5_cq_put(cq); wait_for_completion(&cq->free); - return err; + return 0; } EXPORT_SYMBOL(mlx5_core_destroy_cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 07c8d9811bc8..10d195042ab5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -507,6 +507,8 @@ void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) if (!mlx5_debugfs_root) return; - if (cq->dbg) + if (cq->dbg) { rem_res_tree(cq->dbg); + cq->dbg = NULL; + } } -- cgit v1.2.3-59-g8ed1b From 9091b821aaa4c2d107ca8f97c32baefcb1e7e40d Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Wed, 3 Nov 2021 01:09:04 +0200 Subject: net/mlx5: DR, Handle eswitch manager and uplink vports separately When querying eswitch manager vport capabilities as "other = 1", we encounter a FW compatibility issue with older FW versions. To maintain backward compatibility, eswitch manager vport should be queried as "other = 0" vport both for ECPF and non-ECPF cases. This patch fixes these queries and improves the code readability by handling eswitch manager and uplink vports separately, avoiding the excessive 'if' conditions. Also, uplink caps are stored similar to esw manager and not as part of xarray. Fixes: dd4acb2a0954 ("net/mlx5: DR, Add missing query for vport 0") Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/steering/dr_domain.c | 56 +++++++++------------- .../mellanox/mlx5/core/steering/dr_types.h | 1 + 2 files changed, 24 insertions(+), 33 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 49089cbe897c..8cbd36c82b3b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -135,25 +135,14 @@ static void dr_domain_fill_uplink_caps(struct mlx5dr_domain *dmn, static int dr_domain_query_vport(struct mlx5dr_domain *dmn, u16 vport_number, + bool other_vport, struct mlx5dr_cmd_vport_cap *vport_caps) { - u16 cmd_vport = vport_number; - bool other_vport = true; int ret; - if (vport_number == MLX5_VPORT_UPLINK) { - dr_domain_fill_uplink_caps(dmn, vport_caps); - return 0; - } - - if (dmn->info.caps.is_ecpf && vport_number == MLX5_VPORT_ECPF) { - other_vport = false; - cmd_vport = 0; - } - ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev, other_vport, - cmd_vport, + vport_number, &vport_caps->icm_address_rx, &vport_caps->icm_address_tx); if (ret) @@ -161,7 +150,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn, ret = mlx5dr_cmd_query_gvmi(dmn->mdev, other_vport, - cmd_vport, + vport_number, &vport_caps->vport_gvmi); if (ret) return ret; @@ -176,9 +165,15 @@ static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn) { return dr_domain_query_vport(dmn, dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0, + false, &dmn->info.caps.vports.esw_manager_caps); } +static void dr_domain_query_uplink(struct mlx5dr_domain *dmn) +{ + dr_domain_fill_uplink_caps(dmn, &dmn->info.caps.vports.uplink_caps); +} + static struct mlx5dr_cmd_vport_cap * dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) { @@ -190,7 +185,7 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) if (!vport_caps) return NULL; - ret = dr_domain_query_vport(dmn, vport, vport_caps); + ret = dr_domain_query_vport(dmn, vport, true, vport_caps); if (ret) { kvfree(vport_caps); return NULL; @@ -207,16 +202,26 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) return vport_caps; } +static bool dr_domain_is_esw_mgr_vport(struct mlx5dr_domain *dmn, u16 vport) +{ + struct mlx5dr_cmd_caps *caps = &dmn->info.caps; + + return (caps->is_ecpf && vport == MLX5_VPORT_ECPF) || + (!caps->is_ecpf && vport == 0); +} + struct mlx5dr_cmd_vport_cap * mlx5dr_domain_get_vport_cap(struct mlx5dr_domain *dmn, u16 vport) { struct mlx5dr_cmd_caps *caps = &dmn->info.caps; struct mlx5dr_cmd_vport_cap *vport_caps; - if ((caps->is_ecpf && vport == MLX5_VPORT_ECPF) || - (!caps->is_ecpf && vport == 0)) + if (dr_domain_is_esw_mgr_vport(dmn, vport)) return &caps->vports.esw_manager_caps; + if (vport == MLX5_VPORT_UPLINK) + return &caps->vports.uplink_caps; + vport_load: vport_caps = xa_load(&caps->vports.vports_caps_xa, vport); if (vport_caps) @@ -241,17 +246,6 @@ static void dr_domain_clear_vports(struct mlx5dr_domain *dmn) } } -static int dr_domain_query_uplink(struct mlx5dr_domain *dmn) -{ - struct mlx5dr_cmd_vport_cap *vport_caps; - - vport_caps = mlx5dr_domain_get_vport_cap(dmn, MLX5_VPORT_UPLINK); - if (!vport_caps) - return -EINVAL; - - return 0; -} - static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, struct mlx5dr_domain *dmn) { @@ -281,11 +275,7 @@ static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, goto free_vports_caps_xa; } - ret = dr_domain_query_uplink(dmn); - if (ret) { - mlx5dr_err(dmn, "Failed to query uplink vport caps (err: %d)", ret); - goto free_vports_caps_xa; - } + dr_domain_query_uplink(dmn); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 3028b776da00..2333c2439c28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -764,6 +764,7 @@ struct mlx5dr_roce_cap { struct mlx5dr_vports { struct mlx5dr_cmd_vport_cap esw_manager_caps; + struct mlx5dr_cmd_vport_cap uplink_caps; struct xarray vports_caps_xa; }; -- cgit v1.2.3-59-g8ed1b From 455832d49666e1765acf812be79710b9f84a8cbf Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Wed, 3 Nov 2021 17:51:03 +0200 Subject: net/mlx5: DR, Fix check for unsupported fields in match param The existing loop doesn't cast the buffer while scanning it, which results in out-of-bounds read and failure to create the matcher. Fixes: 941f19798a11 ("net/mlx5: DR, Add check for unsupported fields in match param") Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 75c775bee351..793365242e85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -924,11 +924,12 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, /* Check that all mask data was consumed */ for (i = 0; i < consumed_mask.match_sz; i++) { - if (consumed_mask.match_buf[i]) { - mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n"); - ret = -EOPNOTSUPP; - goto free_consumed_mask; - } + if (!((u8 *)consumed_mask.match_buf)[i]) + continue; + + mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n"); + ret = -EOPNOTSUPP; + goto free_consumed_mask; } ret = 0; -- cgit v1.2.3-59-g8ed1b From ba50cd9451f6c49cf0841c0a4a146ff6a2822699 Mon Sep 17 00:00:00 2001 From: Neta Ostrovsky Date: Wed, 27 Oct 2021 15:16:14 +0300 Subject: net/mlx5: Update error handler for UCTX and UMEM In the fast unload flow, the device state is set to internal error, which indicates that the driver started the destroy process. In this case, when a destroy command is being executed, it should return MLX5_CMD_STAT_OK. Fix MLX5_CMD_OP_DESTROY_UCTX and MLX5_CMD_OP_DESTROY_UMEM to return OK instead of EIO. This fixes a call trace in the umem release process - [ 2633.536695] Call Trace: [ 2633.537518] ib_uverbs_remove_one+0xc3/0x140 [ib_uverbs] [ 2633.538596] remove_client_context+0x8b/0xd0 [ib_core] [ 2633.539641] disable_device+0x8c/0x130 [ib_core] [ 2633.540615] __ib_unregister_device+0x35/0xa0 [ib_core] [ 2633.541640] ib_unregister_device+0x21/0x30 [ib_core] [ 2633.542663] __mlx5_ib_remove+0x38/0x90 [mlx5_ib] [ 2633.543640] auxiliary_bus_remove+0x1e/0x30 [auxiliary] [ 2633.544661] device_release_driver_internal+0x103/0x1f0 [ 2633.545679] bus_remove_device+0xf7/0x170 [ 2633.546640] device_del+0x181/0x410 [ 2633.547606] mlx5_rescan_drivers_locked.part.10+0x63/0x160 [mlx5_core] [ 2633.548777] mlx5_unregister_device+0x27/0x40 [mlx5_core] [ 2633.549841] mlx5_uninit_one+0x21/0xc0 [mlx5_core] [ 2633.550864] remove_one+0x69/0xe0 [mlx5_core] [ 2633.551819] pci_device_remove+0x3b/0xc0 [ 2633.552731] device_release_driver_internal+0x103/0x1f0 [ 2633.553746] unbind_store+0xf6/0x130 [ 2633.554657] kernfs_fop_write+0x116/0x190 [ 2633.555567] vfs_write+0xa5/0x1a0 [ 2633.556407] ksys_write+0x4f/0xb0 [ 2633.557233] do_syscall_64+0x5b/0x1a0 [ 2633.558071] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 2633.559018] RIP: 0033:0x7f9977132648 [ 2633.559821] Code: 89 02 48 c7 c0 ff ff ff ff eb b3 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 55 6f 2d 00 8b 00 85 c0 75 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 41 54 49 89 d4 55 [ 2633.562332] RSP: 002b:00007fffb1a83888 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 2633.563472] RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007f9977132648 [ 2633.564541] RDX: 000000000000000c RSI: 000055b90546e230 RDI: 0000000000000001 [ 2633.565596] RBP: 000055b90546e230 R08: 00007f9977406860 R09: 00007f9977a54740 [ 2633.566653] R10: 0000000000000000 R11: 0000000000000246 R12: 00007f99774056e0 [ 2633.567692] R13: 000000000000000c R14: 00007f9977400880 R15: 000000000000000c [ 2633.568725] ---[ end trace 10b4fe52945e544d ]--- Fixes: 6a6fabbfa3e8 ("net/mlx5: Update pci error handler entries and command translation") Signed-off-by: Neta Ostrovsky Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index f71ec4d9d68e..8eaa24d865c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -339,6 +339,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_PAGE_FAULT_RESUME: case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS: case MLX5_CMD_OP_DEALLOC_SF: + case MLX5_CMD_OP_DESTROY_UCTX: + case MLX5_CMD_OP_DESTROY_UMEM: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -464,9 +466,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT: case MLX5_CMD_OP_QUERY_GENERAL_OBJECT: case MLX5_CMD_OP_CREATE_UCTX: - case MLX5_CMD_OP_DESTROY_UCTX: case MLX5_CMD_OP_CREATE_UMEM: - case MLX5_CMD_OP_DESTROY_UMEM: case MLX5_CMD_OP_ALLOC_MEMIC: case MLX5_CMD_OP_MODIFY_XRQ: case MLX5_CMD_OP_RELEASE_XRQ_ERROR: -- cgit v1.2.3-59-g8ed1b From 2eb0cb31bc4ce2ede5460cf3ef433b40cf5f040d Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Wed, 10 Nov 2021 15:19:12 +0000 Subject: net/mlx5: E-Switch, rebuild lag only when needed A user can enable VFs without changing E-Switch mode, this can happen when a user moves straight to switchdev mode and only once in switchdev VFs are enabled via the sysfs interface. The cited commit assumed this isn't possible and exposed a single API function where the E-switch calls into the lag code, breaks the lag and prevents any other lag operations to take place until the E-switch update has ended. Breaking the hardware lag when it isn't needed can make it such that hardware lag can't be enabled again. In the sysfs call path check if the current E-Switch mode is NONE, in the context of the function it can only mean the E-Switch is moving out of NONE mode and the hardware lag should be disabled and enabled once the mode change has ended. If the mode isn't NONE it means VFs are about to be enabled and such operation doesn't require toggling the hardware lag. Fixes: cac1eb2cf2e3 ("net/mlx5: Lag, properly lock eswitch if needed") Signed-off-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5872cc8bf953..51a8cecc4a7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1305,12 +1305,17 @@ abort: */ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { + bool toggle_lag; int ret; if (!mlx5_esw_allowed(esw)) return 0; - mlx5_lag_disable_change(esw->dev); + toggle_lag = esw->mode == MLX5_ESWITCH_NONE; + + if (toggle_lag) + mlx5_lag_disable_change(esw->dev); + down_write(&esw->mode_lock); if (esw->mode == MLX5_ESWITCH_NONE) { ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs); @@ -1324,7 +1329,10 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) esw->esw_funcs.num_vfs = num_vfs; } up_write(&esw->mode_lock); - mlx5_lag_enable_change(esw->dev); + + if (toggle_lag) + mlx5_lag_enable_change(esw->dev); + return ret; } -- cgit v1.2.3-59-g8ed1b From 38a54cae6f76c3e6a1e6c1e52c2e43a069fa78cb Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Wed, 3 Nov 2021 13:04:23 +0200 Subject: net/mlx5: Fix flow counters SF bulk query len When doing a flow counters bulk query, the number of counters to query must be aligned to 4. Current SF bulk query len is not aligned to 4, which leads to an error when trying to query more than 4 counters. Fix it by aligning SF bulk query len to 4. Fixes: 2fdeb4f4c2ae ("net/mlx5: Reduce flow counters bulk query buffer size for SFs") Signed-off-by: Avihai Horon Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 31c99d53faf7..7e0e04cf26f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,7 +40,7 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) -#define MLX5_SF_NUM_COUNTERS_BULK 6 +#define MLX5_SF_NUM_COUNTERS_BULK 8 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) #define MLX5_FC_POOL_USED_BUFF_RATIO 10 -- cgit v1.2.3-59-g8ed1b From 806401c20a0f9c51b6c8fd7035671e6ca841f6c2 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Mon, 8 Nov 2021 16:41:05 +0200 Subject: net/mlx5e: CT, Fix multiple allocations and memleak of mod acts CT clear action offload adds additional mod hdr actions to the flow's original mod actions in order to clear the registers which hold ct_state. When such flow also includes encap action, a neigh update event can cause the driver to unoffload the flow and then reoffload it. Each time this happens, the ct clear handling adds that same set of mod hdr actions to reset ct_state until the max of mod hdr actions is reached. Also the driver never releases the allocated mod hdr actions and causing a memleak. Fix above two issues by moving CT clear mod acts allocation into the parsing actions phase and only use it when offloading the rule. The release of mod acts will be done in the normal flow_put(). backtrace: [<000000007316e2f3>] krealloc+0x83/0xd0 [<00000000ef157de1>] mlx5e_mod_hdr_alloc+0x147/0x300 [mlx5_core] [<00000000970ce4ae>] mlx5e_tc_match_to_reg_set_and_get_id+0xd7/0x240 [mlx5_core] [<0000000067c5fa17>] mlx5e_tc_match_to_reg_set+0xa/0x20 [mlx5_core] [<00000000d032eb98>] mlx5_tc_ct_entry_set_registers.isra.0+0x36/0xc0 [mlx5_core] [<00000000fd23b869>] mlx5_tc_ct_flow_offload+0x272/0x1f10 [mlx5_core] [<000000004fc24acc>] mlx5e_tc_offload_fdb_rules.part.0+0x150/0x620 [mlx5_core] [<00000000dc741c17>] mlx5e_tc_encap_flows_add+0x489/0x690 [mlx5_core] [<00000000e92e49d7>] mlx5e_rep_update_flows+0x6e4/0x9b0 [mlx5_core] [<00000000f60f5602>] mlx5e_rep_neigh_update+0x39a/0x5d0 [mlx5_core] Fixes: 1ef3018f5af3 ("net/mlx5e: CT: Support clear action") Signed-off-by: Roi Dayan Reviewed-by: Paul Blakey Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 26 ++++++++++++++-------- drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 8 +++++-- 3 files changed, 25 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index c1c6e74c79c4..2445e2ae3324 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1356,9 +1356,13 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; + int err; + if (!priv) { NL_SET_ERR_MSG_MOD(extack, "offload of ct action isn't available"); @@ -1369,6 +1373,17 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.ct_action = act->ct.action; attr->ct_attr.nf_ft = act->ct.flow_table; + if (!clear_action) + goto out; + + err = mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to set registers for ct clear"); + return err; + } + attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + +out: return 0; } @@ -1898,23 +1913,16 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, memcpy(pre_ct_attr, attr, attr_sz); - err = mlx5_tc_ct_entry_set_registers(ct_priv, mod_acts, 0, 0, 0, 0); - if (err) { - ct_dbg("Failed to set register for ct clear"); - goto err_set_registers; - } - mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type, mod_acts->num_actions, mod_acts->actions); if (IS_ERR(mod_hdr)) { err = PTR_ERR(mod_hdr); ct_dbg("Failed to add create ct clear mod hdr"); - goto err_set_registers; + goto err_mod_hdr; } pre_ct_attr->modify_hdr = mod_hdr; - pre_ct_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr); if (IS_ERR(rule)) { @@ -1930,7 +1938,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, err_insert: mlx5_modify_header_dealloc(priv->mdev, mod_hdr); -err_set_registers: +err_mod_hdr: netdev_warn(priv->netdev, "Failed to offload ct clear flow, err %d\n", err); kfree(pre_ct_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 363329f4aac6..99662af1e41a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -110,6 +110,7 @@ int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec); int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack); @@ -172,6 +173,7 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec) static inline int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index cb76c41fe163..3d45f4ae80c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3608,7 +3608,9 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, attr->dest_chain = act->chain_index; break; case FLOW_ACTION_CT: - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack); + err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, + &parse_attr->mod_hdr_acts, + act, extack); if (err) return err; @@ -4277,7 +4279,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported"); return -EOPNOTSUPP; } - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack); + err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, + &parse_attr->mod_hdr_acts, + act, extack); if (err) return err; -- cgit v1.2.3-59-g8ed1b From ae396d85c01c7bdc9eeceecde1f493d03f793465 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Fri, 5 Nov 2021 11:19:48 +0200 Subject: net/mlx5: Lag, update tracker when state change event received Currently, In NETDEV_CHANGELOWERSTATE/NETDEV_CHANGEUPPERSTATE events handling, tracking is not fully completed if the LAG device is not ready at the time the events occur. But, we must keep track of the upper and lower states after receiving the events because RoCE needs this info in mlx5_lag_get_roce_netdev() - in order to return the corresponding port that its running on. Returning the wrong (not most recent) port will lead to gids table being incorrect. For example: If during the attachment of a slave to the bond, the other non-attached port performs pci_reload, then the LAG device is not ready, but that should not result in dismissing attached slave tracker update automatically (which is performed in mlx5_handle_changelowerstate()), Since these events might not come later, which can lead to both bond ports having tx_enabled=0 - which is not a valid state of LAG bond. Fixes: 9b412cc35f00 ("net/mlx5e: Add LAG warning if bond slave is not lag master") Signed-off-by: Maher Sanalla Reviewed-by: Mark Bloch Reviewed-by: Jianbo Liu Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 28 +++++++++++------------ 1 file changed, 13 insertions(+), 15 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 48d2ea690d7a..4ddf6b330a44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -615,6 +615,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, bool is_bonded, is_in_lag, mode_supported; int bond_status = 0; int num_slaves = 0; + int changed = 0; int idx; if (!netif_is_lag_master(upper)) @@ -653,27 +654,27 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, */ is_in_lag = num_slaves == MLX5_MAX_PORTS && bond_status == 0x3; - if (!mlx5_lag_is_ready(ldev) && is_in_lag) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Can't activate LAG offload, PF is configured with more than 64 VFs"); - return 0; - } - /* Lag mode must be activebackup or hash. */ mode_supported = tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP || tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH; - if (is_in_lag && !mode_supported) - NL_SET_ERR_MSG_MOD(info->info.extack, - "Can't activate LAG offload, TX type isn't supported"); - is_bonded = is_in_lag && mode_supported; if (tracker->is_bonded != is_bonded) { tracker->is_bonded = is_bonded; - return 1; + changed = 1; } - return 0; + if (!is_in_lag) + return changed; + + if (!mlx5_lag_is_ready(ldev)) + NL_SET_ERR_MSG_MOD(info->info.extack, + "Can't activate LAG offload, PF is configured with more than 64 VFs"); + else if (!mode_supported) + NL_SET_ERR_MSG_MOD(info->info.extack, + "Can't activate LAG offload, TX type isn't supported"); + + return changed; } static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev, @@ -716,9 +717,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, ldev = container_of(this, struct mlx5_lag, nb); - if (!mlx5_lag_is_ready(ldev) && event == NETDEV_CHANGELOWERSTATE) - return NOTIFY_DONE; - tracker = ldev->tracker; switch (event) { -- cgit v1.2.3-59-g8ed1b From c4c3176739dfa6efcc5b1d1de4b3fd2b51b048c7 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Mon, 1 Nov 2021 16:18:53 +0200 Subject: net/mlx5: E-Switch, return error if encap isn't supported On regular ConnectX HCAs getting encap mode isn't supported when the E-Switch is in NONE mode. Current code would return no error code when trying to get encap mode in such case which is wrong. Fix by returning error value to indicate failure to caller in such case. Fixes: 8e0aa4bc959c ("net/mlx5: E-switch, Protect eswitch mode changes") Signed-off-by: Raed Salem Reviewed-by: Mark Bloch Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 80fa76f60e1e..a46455694f7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3623,7 +3623,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, *encap = esw->offloads.encap; unlock: up_write(&esw->mode_lock); - return 0; + return err; } static bool -- cgit v1.2.3-59-g8ed1b