From 90e7cb78b81543998217b0eb446c067ce2191a79 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 5 Jan 2023 19:42:20 +0800 Subject: net/mlx5: fix missing mutex_unlock in mlx5_fw_fatal_reporter_err_work() Add missing mutex_unlock() before returning from mlx5_fw_fatal_reporter_err_work(). Fixes: 9078e843efec ("net/mlx5: Avoid recovery in probe flows") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Yang Yingliang Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 96417c5feed7..879555ba847d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -677,6 +677,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) { mlx5_core_err(dev, "health works are not permitted at this stage\n"); + mutex_unlock(&dev->intf_state_mutex); return; } mutex_unlock(&dev->intf_state_mutex); -- cgit v1.2.3 From 5aa56105930374928d567744595fd7ac525d0688 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 15 Dec 2022 16:44:33 +0100 Subject: net/mlx5e: Avoid false lock dependency warning on tc_ht even more The cited commit changed class of tc_ht internal mutex in order to avoid false lock dependency with fs_core node and flow_table hash table structures. However, hash table implementation internally also includes a workqueue task with its own lockdep map which causes similar bogus lockdep splat[0]. Fix it by also adding dedicated class for hash table workqueue work structure of tc_ht. [0]: [ 1139.672465] ====================================================== [ 1139.673552] WARNING: possible circular locking dependency detected [ 1139.674635] 6.1.0_for_upstream_debug_2022_12_12_17_02 #1 Not tainted [ 1139.675734] ------------------------------------------------------ [ 1139.676801] modprobe/5998 is trying to acquire lock: [ 1139.677726] ffff88811e7b93b8 (&node->lock){++++}-{3:3}, at: down_write_ref_node+0x7c/0xe0 [mlx5_core] [ 1139.679662] but task is already holding lock: [ 1139.680703] ffff88813c1f96a0 (&tc_ht_lock_key){+.+.}-{3:3}, at: rhashtable_free_and_destroy+0x38/0x6f0 [ 1139.682223] which lock already depends on the new lock. [ 1139.683640] the existing dependency chain (in reverse order) is: [ 1139.684887] -> #2 (&tc_ht_lock_key){+.+.}-{3:3}: [ 1139.685975] __mutex_lock+0x12c/0x14b0 [ 1139.686659] rht_deferred_worker+0x35/0x1540 [ 1139.687405] process_one_work+0x7c2/0x1310 [ 1139.688134] worker_thread+0x59d/0xec0 [ 1139.688820] kthread+0x28f/0x330 [ 1139.689444] ret_from_fork+0x1f/0x30 [ 1139.690106] -> #1 ((work_completion)(&ht->run_work)){+.+.}-{0:0}: [ 1139.691250] __flush_work+0xe8/0x900 [ 1139.691915] __cancel_work_timer+0x2ca/0x3f0 [ 1139.692655] rhashtable_free_and_destroy+0x22/0x6f0 [ 1139.693472] del_sw_flow_table+0x22/0xb0 [mlx5_core] [ 1139.694592] tree_put_node+0x24c/0x450 [mlx5_core] [ 1139.695686] tree_remove_node+0x6e/0x100 [mlx5_core] [ 1139.696803] mlx5_destroy_flow_table+0x187/0x690 [mlx5_core] [ 1139.698017] mlx5e_tc_nic_cleanup+0x2f8/0x400 [mlx5_core] [ 1139.699217] mlx5e_cleanup_nic_rx+0x2b/0x210 [mlx5_core] [ 1139.700397] mlx5e_detach_netdev+0x19d/0x2b0 [mlx5_core] [ 1139.701571] mlx5e_suspend+0xdb/0x140 [mlx5_core] [ 1139.702665] mlx5e_remove+0x89/0x190 [mlx5_core] [ 1139.703756] auxiliary_bus_remove+0x52/0x70 [ 1139.704492] device_release_driver_internal+0x3c1/0x600 [ 1139.705360] bus_remove_device+0x2a5/0x560 [ 1139.706080] device_del+0x492/0xb80 [ 1139.706724] mlx5_rescan_drivers_locked+0x194/0x6a0 [mlx5_core] [ 1139.707961] mlx5_unregister_device+0x7a/0xa0 [mlx5_core] [ 1139.709138] mlx5_uninit_one+0x5f/0x160 [mlx5_core] [ 1139.710252] remove_one+0xd1/0x160 [mlx5_core] [ 1139.711297] pci_device_remove+0x96/0x1c0 [ 1139.722721] device_release_driver_internal+0x3c1/0x600 [ 1139.723590] unbind_store+0x1b1/0x200 [ 1139.724259] kernfs_fop_write_iter+0x348/0x520 [ 1139.725019] vfs_write+0x7b2/0xbf0 [ 1139.725658] ksys_write+0xf3/0x1d0 [ 1139.726292] do_syscall_64+0x3d/0x90 [ 1139.726942] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 1139.727769] -> #0 (&node->lock){++++}-{3:3}: [ 1139.728698] __lock_acquire+0x2cf5/0x62f0 [ 1139.729415] lock_acquire+0x1c1/0x540 [ 1139.730076] down_write+0x8e/0x1f0 [ 1139.730709] down_write_ref_node+0x7c/0xe0 [mlx5_core] [ 1139.731841] mlx5_del_flow_rules+0x6f/0x610 [mlx5_core] [ 1139.732982] __mlx5_eswitch_del_rule+0xdd/0x560 [mlx5_core] [ 1139.734207] mlx5_eswitch_del_offloaded_rule+0x14/0x20 [mlx5_core] [ 1139.735491] mlx5e_tc_rule_unoffload+0x104/0x2b0 [mlx5_core] [ 1139.736716] mlx5e_tc_unoffload_fdb_rules+0x10c/0x1f0 [mlx5_core] [ 1139.738007] mlx5e_tc_del_fdb_flow+0xc3c/0xfa0 [mlx5_core] [ 1139.739213] mlx5e_tc_del_flow+0x146/0xa20 [mlx5_core] [ 1139.740377] _mlx5e_tc_del_flow+0x38/0x60 [mlx5_core] [ 1139.741534] rhashtable_free_and_destroy+0x3be/0x6f0 [ 1139.742351] mlx5e_tc_ht_cleanup+0x1b/0x30 [mlx5_core] [ 1139.743512] mlx5e_cleanup_rep_tx+0x4a/0xe0 [mlx5_core] [ 1139.744683] mlx5e_detach_netdev+0x1ca/0x2b0 [mlx5_core] [ 1139.745860] mlx5e_netdev_change_profile+0xd9/0x1c0 [mlx5_core] [ 1139.747098] mlx5e_netdev_attach_nic_profile+0x1b/0x30 [mlx5_core] [ 1139.748372] mlx5e_vport_rep_unload+0x16a/0x1b0 [mlx5_core] [ 1139.749590] __esw_offloads_unload_rep+0xb1/0xd0 [mlx5_core] [ 1139.750813] mlx5_eswitch_unregister_vport_reps+0x409/0x5f0 [mlx5_core] [ 1139.752147] mlx5e_rep_remove+0x62/0x80 [mlx5_core] [ 1139.753293] auxiliary_bus_remove+0x52/0x70 [ 1139.754028] device_release_driver_internal+0x3c1/0x600 [ 1139.754885] driver_detach+0xc1/0x180 [ 1139.755553] bus_remove_driver+0xef/0x2e0 [ 1139.756260] auxiliary_driver_unregister+0x16/0x50 [ 1139.757059] mlx5e_rep_cleanup+0x19/0x30 [mlx5_core] [ 1139.758207] mlx5e_cleanup+0x12/0x30 [mlx5_core] [ 1139.759295] mlx5_cleanup+0xc/0x49 [mlx5_core] [ 1139.760384] __x64_sys_delete_module+0x2b5/0x450 [ 1139.761166] do_syscall_64+0x3d/0x90 [ 1139.761827] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 1139.762663] other info that might help us debug this: [ 1139.763925] Chain exists of: &node->lock --> (work_completion)(&ht->run_work) --> &tc_ht_lock_key [ 1139.765743] Possible unsafe locking scenario: [ 1139.766688] CPU0 CPU1 [ 1139.767399] ---- ---- [ 1139.768111] lock(&tc_ht_lock_key); [ 1139.768704] lock((work_completion)(&ht->run_work)); [ 1139.769869] lock(&tc_ht_lock_key); [ 1139.770770] lock(&node->lock); [ 1139.771326] *** DEADLOCK *** [ 1139.772345] 2 locks held by modprobe/5998: [ 1139.772994] #0: ffff88813c1ff0e8 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x8d/0x600 [ 1139.774399] #1: ffff88813c1f96a0 (&tc_ht_lock_key){+.+.}-{3:3}, at: rhashtable_free_and_destroy+0x38/0x6f0 [ 1139.775822] stack backtrace: [ 1139.776579] CPU: 3 PID: 5998 Comm: modprobe Not tainted 6.1.0_for_upstream_debug_2022_12_12_17_02 #1 [ 1139.777935] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 1139.779529] Call Trace: [ 1139.779992] [ 1139.780409] dump_stack_lvl+0x57/0x7d [ 1139.781015] check_noncircular+0x278/0x300 [ 1139.781687] ? print_circular_bug+0x460/0x460 [ 1139.782381] ? rcu_read_lock_sched_held+0x3f/0x70 [ 1139.783121] ? lock_release+0x487/0x7c0 [ 1139.783759] ? orc_find.part.0+0x1f1/0x330 [ 1139.784423] ? mark_lock.part.0+0xef/0x2fc0 [ 1139.785091] __lock_acquire+0x2cf5/0x62f0 [ 1139.785754] ? register_lock_class+0x18e0/0x18e0 [ 1139.786483] lock_acquire+0x1c1/0x540 [ 1139.787093] ? down_write_ref_node+0x7c/0xe0 [mlx5_core] [ 1139.788195] ? lockdep_hardirqs_on_prepare+0x3f0/0x3f0 [ 1139.788978] ? register_lock_class+0x18e0/0x18e0 [ 1139.789715] down_write+0x8e/0x1f0 [ 1139.790292] ? down_write_ref_node+0x7c/0xe0 [mlx5_core] [ 1139.791380] ? down_write_killable+0x220/0x220 [ 1139.792080] ? find_held_lock+0x2d/0x110 [ 1139.792713] down_write_ref_node+0x7c/0xe0 [mlx5_core] [ 1139.793795] mlx5_del_flow_rules+0x6f/0x610 [mlx5_core] [ 1139.794879] __mlx5_eswitch_del_rule+0xdd/0x560 [mlx5_core] [ 1139.796032] ? __esw_offloads_unload_rep+0xd0/0xd0 [mlx5_core] [ 1139.797227] ? xa_load+0x11a/0x200 [ 1139.797800] ? __xa_clear_mark+0xf0/0xf0 [ 1139.798438] mlx5_eswitch_del_offloaded_rule+0x14/0x20 [mlx5_core] [ 1139.799660] mlx5e_tc_rule_unoffload+0x104/0x2b0 [mlx5_core] [ 1139.800821] mlx5e_tc_unoffload_fdb_rules+0x10c/0x1f0 [mlx5_core] [ 1139.802049] ? mlx5_eswitch_get_uplink_priv+0x25/0x80 [mlx5_core] [ 1139.803260] mlx5e_tc_del_fdb_flow+0xc3c/0xfa0 [mlx5_core] [ 1139.804398] ? __cancel_work_timer+0x1c2/0x3f0 [ 1139.805099] ? mlx5e_tc_unoffload_from_slow_path+0x460/0x460 [mlx5_core] [ 1139.806387] mlx5e_tc_del_flow+0x146/0xa20 [mlx5_core] [ 1139.807481] _mlx5e_tc_del_flow+0x38/0x60 [mlx5_core] [ 1139.808564] rhashtable_free_and_destroy+0x3be/0x6f0 [ 1139.809336] ? mlx5e_tc_del_flow+0xa20/0xa20 [mlx5_core] [ 1139.809336] ? mlx5e_tc_del_flow+0xa20/0xa20 [mlx5_core] [ 1139.810455] mlx5e_tc_ht_cleanup+0x1b/0x30 [mlx5_core] [ 1139.811552] mlx5e_cleanup_rep_tx+0x4a/0xe0 [mlx5_core] [ 1139.812655] mlx5e_detach_netdev+0x1ca/0x2b0 [mlx5_core] [ 1139.813768] mlx5e_netdev_change_profile+0xd9/0x1c0 [mlx5_core] [ 1139.814952] mlx5e_netdev_attach_nic_profile+0x1b/0x30 [mlx5_core] [ 1139.816166] mlx5e_vport_rep_unload+0x16a/0x1b0 [mlx5_core] [ 1139.817336] __esw_offloads_unload_rep+0xb1/0xd0 [mlx5_core] [ 1139.818507] mlx5_eswitch_unregister_vport_reps+0x409/0x5f0 [mlx5_core] [ 1139.819788] ? mlx5_eswitch_uplink_get_proto_dev+0x30/0x30 [mlx5_core] [ 1139.821051] ? kernfs_find_ns+0x137/0x310 [ 1139.821705] mlx5e_rep_remove+0x62/0x80 [mlx5_core] [ 1139.822778] auxiliary_bus_remove+0x52/0x70 [ 1139.823449] device_release_driver_internal+0x3c1/0x600 [ 1139.824240] driver_detach+0xc1/0x180 [ 1139.824842] bus_remove_driver+0xef/0x2e0 [ 1139.825504] auxiliary_driver_unregister+0x16/0x50 [ 1139.826245] mlx5e_rep_cleanup+0x19/0x30 [mlx5_core] [ 1139.827322] mlx5e_cleanup+0x12/0x30 [mlx5_core] [ 1139.828345] mlx5_cleanup+0xc/0x49 [mlx5_core] [ 1139.829382] __x64_sys_delete_module+0x2b5/0x450 [ 1139.830119] ? module_flags+0x300/0x300 [ 1139.830750] ? task_work_func_match+0x50/0x50 [ 1139.831440] ? task_work_cancel+0x20/0x20 [ 1139.832088] ? lockdep_hardirqs_on_prepare+0x273/0x3f0 [ 1139.832873] ? syscall_enter_from_user_mode+0x1d/0x50 [ 1139.833661] ? trace_hardirqs_on+0x2d/0x100 [ 1139.834328] do_syscall_64+0x3d/0x90 [ 1139.834922] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 1139.835700] RIP: 0033:0x7f153e71288b [ 1139.836302] Code: 73 01 c3 48 8b 0d 9d 75 0e 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 6d 75 0e 00 f7 d8 64 89 01 48 [ 1139.838866] RSP: 002b:00007ffe0a3ed938 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [ 1139.840020] RAX: ffffffffffffffda RBX: 0000564c2cbf8220 RCX: 00007f153e71288b [ 1139.841043] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 0000564c2cbf8288 [ 1139.842072] RBP: 0000564c2cbf8220 R08: 0000000000000000 R09: 0000000000000000 [ 1139.843094] R10: 00007f153e7a3ac0 R11: 0000000000000206 R12: 0000564c2cbf8288 [ 1139.844118] R13: 0000000000000000 R14: 0000564c2cbf7ae8 R15: 00007ffe0a3efcb8 Fixes: 9ba33339c043 ("net/mlx5e: Avoid false lock depenency warning on tc_ht") Signed-off-by: Vlad Buslov Reviewed-by: Eli Cohen Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dbadaf166487..243d5d7750be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -166,6 +166,7 @@ struct mlx5_fs_chains *mlx5e_nic_chains(struct mlx5e_tc_table *tc) * it's different than the ht->mutex here. */ static struct lock_class_key tc_ht_lock_key; +static struct lock_class_key tc_ht_wq_key; static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); static void free_flow_post_acts(struct mlx5e_tc_flow *flow); @@ -5182,6 +5183,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) return err; lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key); + lockdep_init_map(&tc->ht.run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0); mapping_id = mlx5_query_nic_system_image_guid(dev); @@ -5288,6 +5290,7 @@ int mlx5e_tc_ht_init(struct rhashtable *tc_ht) return err; lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key); + lockdep_init_map(&tc_ht->run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0); return 0; } -- cgit v1.2.3 From 6624bfeecf019de114f8100f1468d025d13b77a1 Mon Sep 17 00:00:00 2001 From: Adham Faris Date: Thu, 12 Jan 2023 11:15:00 +0200 Subject: net/mlx5e: Remove redundant xsk pointer check in mlx5e_mpwrq_validate_xsk This validation function is relevant only for XSK cases, hence it assumes to be called only with xsk != NULL. Thus checking for invalid xsk pointer is redundant and misleads static code analyzers. This commit removes redundant xsk pointer check. This solves the following smatch warning: drivers/net/ethernet/mellanox/mlx5/core/en/params.c:481 mlx5e_mpwrq_validate_xsk() error: we previously assumed 'xsk' could be null (see line 478) Fixes: 6470d2e7e8ed ("net/mlx5e: xsk: Use KSM for unaligned XSK") Signed-off-by: Adham Faris Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 585bdc8383ee..4ad19c981294 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -578,7 +578,6 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa { enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk); u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk); - bool unaligned = xsk ? xsk->unaligned : false; u16 max_mtu_pkts; if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode)) @@ -591,7 +590,7 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa * needed number of WQEs exceeds the maximum. */ max_mtu_pkts = min_t(u8, MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE, - mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, unaligned)); + mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, xsk->unaligned)); if (params->log_rq_mtu_frames > max_mtu_pkts) { mlx5_core_err(mdev, "Current RQ length %d is too big for XSK with given frame size %u\n", 1 << params->log_rq_mtu_frames, xsk->chunk_size); -- cgit v1.2.3 From f51471d1935ce1f504fce6c115ce3bfbc32032b0 Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Tue, 27 Dec 2022 10:22:41 +0200 Subject: net/mlx5: E-switch, Fix setting of reserved fields on MODIFY_SCHEDULING_ELEMENT According to HW spec element_type, element_attributes and parent_element_id fields should be reserved (0x0) when calling MODIFY_SCHEDULING_ELEMENT command. This patch remove initialization of these fields when calling the command. Fixes: bd77bf1cb595 ("net/mlx5: Add SRIOV VF max rate configuration support") Signed-off-by: Maor Dickman Reviewed-by: Eli Cohen Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 4f8a24d84a86..75015d370922 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -22,15 +22,13 @@ struct mlx5_esw_rate_group { }; static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx, - u32 parent_ix, u32 tsar_ix, - u32 max_rate, u32 bw_share) + u32 tsar_ix, u32 max_rate, u32 bw_share) { u32 bitmask = 0; if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) return -EOPNOTSUPP; - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix); MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; @@ -51,7 +49,7 @@ static int esw_qos_group_config(struct mlx5_eswitch *esw, struct mlx5_esw_rate_g int err; err = esw_qos_tsar_config(dev, sched_ctx, - esw->qos.root_tsar_ix, group->tsar_ix, + group->tsar_ix, max_rate, bw_share); if (err) NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed"); @@ -67,23 +65,13 @@ static int esw_qos_vport_config(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; - struct mlx5_esw_rate_group *group = vport->qos.group; struct mlx5_core_dev *dev = esw->dev; - u32 parent_tsar_ix; - void *vport_elem; int err; if (!vport->qos.enabled) return -EIO; - parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix; - MLX5_SET(scheduling_context, sched_ctx, element_type, - SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); - vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, - element_attributes); - MLX5_SET(vport_element, vport_elem, vport_number, vport->vport); - - err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix, + err = esw_qos_tsar_config(dev, sched_ctx, vport->qos.esw_tsar_ix, max_rate, bw_share); if (err) { esw_warn(esw->dev, -- cgit v1.2.3 From 4ddf77f9bc76092d268bd3af447d60d9cc62b652 Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Tue, 27 Dec 2022 10:51:38 +0200 Subject: net/mlx5e: QoS, Fix wrongfully setting parent_element_id on MODIFY_SCHEDULING_ELEMENT According to HW spec parent_element_id field should be reserved (0x0) when calling MODIFY_SCHEDULING_ELEMENT command. This patch remove the wrong initialization of reserved field, parent_element_id, on mlx5_qos_update_node. Fixes: 214baf22870c ("net/mlx5e: Support HTB offload") Signed-off-by: Maor Dickman Reviewed-by: Eli Cohen Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/htb.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/qos.c | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/qos.h | 2 +- 3 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c b/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c index 6dac76fa58a3..09d441ecb9f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c @@ -637,7 +637,7 @@ mlx5e_htb_update_children(struct mlx5e_htb *htb, struct mlx5e_qos_node *node, if (child->bw_share == old_bw_share) continue; - err_one = mlx5_qos_update_node(htb->mdev, child->hw_id, child->bw_share, + err_one = mlx5_qos_update_node(htb->mdev, child->bw_share, child->max_average_bw, child->hw_id); if (!err && err_one) { err = err_one; @@ -671,7 +671,7 @@ mlx5e_htb_node_modify(struct mlx5e_htb *htb, u16 classid, u64 rate, u64 ceil, mlx5e_htb_convert_rate(htb, rate, node->parent, &bw_share); mlx5e_htb_convert_ceil(htb, ceil, &max_average_bw); - err = mlx5_qos_update_node(htb->mdev, node->parent->hw_id, bw_share, + err = mlx5_qos_update_node(htb->mdev, bw_share, max_average_bw, node->hw_id); if (err) { NL_SET_ERR_MSG_MOD(extack, "Firmware error when modifying a node."); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/qos.c index 0777be24a307..8bce730b5c5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.c @@ -62,13 +62,12 @@ int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id) return mlx5_qos_create_inner_node(mdev, MLX5_QOS_DEFAULT_DWRR_UID, 0, 0, id); } -int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id, +int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 bw_share, u32 max_avg_bw, u32 id) { u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; u32 bitmask = 0; - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id); MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_avg_bw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/qos.h index 125e4e47e6f7..624ce822b7f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.h @@ -23,7 +23,7 @@ int mlx5_qos_create_leaf_node(struct mlx5_core_dev *mdev, u32 parent_id, int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 bw_share, u32 max_avg_bw, u32 *id); int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id); -int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 bw_share, +int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 bw_share, u32 max_avg_bw, u32 id); int mlx5_qos_destroy_node(struct mlx5_core_dev *mdev, u32 id); -- cgit v1.2.3 From ffa99b534732f90077f346c62094cab3d1ccddce Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Thu, 12 Jan 2023 04:30:27 +0200 Subject: net/mlx5e: Set decap action based on attr for sample Currently decap action is set based on tunnel_id. That means it is set unconditionally. But for decap, ct and sample actions, decap is done before ct. No need to decap again in sample. And the actions are set correctly when parsing. So set decap action based on attr instead of tunnel_id. Fixes: 2741f2230905 ("net/mlx5e: TC, Support sample offload action for tunneled traffic") Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index 1cbd2eb9d04f..f2c2c752bd1c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -477,7 +477,6 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sample_flow *sample_flow; struct mlx5e_sample_attr *sample_attr; struct mlx5_flow_attr *pre_attr; - u32 tunnel_id = attr->tunnel_id; struct mlx5_eswitch *esw; u32 default_tbl_id; u32 obj_id; @@ -522,7 +521,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, restore_obj.sample.group_id = sample_attr->group_num; restore_obj.sample.rate = sample_attr->rate; restore_obj.sample.trunc_size = sample_attr->trunc_size; - restore_obj.sample.tunnel_id = tunnel_id; + restore_obj.sample.tunnel_id = attr->tunnel_id; err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id); if (err) goto err_obj_id; @@ -548,7 +547,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, /* For decap action, do decap in the original flow table instead of the * default flow table. */ - if (tunnel_id) + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; pre_attr->modify_hdr = sample_flow->restore->modify_hdr; pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE; -- cgit v1.2.3 From 16bccbaa00b6127ed0ebfd77bd1f10341df8d498 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 9 Jan 2023 10:43:13 +0200 Subject: net/mlx5e: Remove optimization which prevented update of ESN state aso->use_cache variable introduced in commit 8c582ddfbb47 ("net/mlx5e: Handle hardware IPsec limits events") was an optimization to skip recurrent calls to mlx5e_ipsec_aso_query(). Such calls are possible when lifetime event is generated: -> mlx5e_ipsec_handle_event() -> mlx5e_ipsec_aso_query() - first call -> xfrm_state_check_expire() -> mlx5e_xfrm_update_curlft() -> mlx5e_ipsec_aso_query() - second call However, such optimization not really effective as mlx5e_ipsec_aso_query() is needed to be called for update ESN anyway, which was missed due to misplaced use_cache assignment. Fixes: cee137a63431 ("net/mlx5e: Handle ESN update events") Reviewed-by: Jianbo Liu Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h | 5 ----- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c | 5 ----- 2 files changed, 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index a92e19c4c499..160f8883b93e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -122,11 +122,6 @@ struct mlx5e_ipsec_aso { u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)]; dma_addr_t dma_addr; struct mlx5_aso *aso; - /* IPsec ASO caches data on every query call, - * so in nested calls, we can use this boolean to save - * recursive calls to mlx5e_ipsec_aso_query() - */ - u8 use_cache : 1; }; struct mlx5e_ipsec { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 8e3614218fc4..aafbd7b244ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -320,7 +320,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) if (ret) goto unlock; - aso->use_cache = true; if (attrs->esn_trigger && !MLX5_GET(ipsec_aso, aso->ctx, esn_event_arm)) { u32 mode_param = MLX5_GET(ipsec_aso, aso->ctx, mode_parameter); @@ -333,7 +332,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) || !MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable)) xfrm_state_check_expire(sa_entry->x); - aso->use_cache = false; unlock: spin_unlock(&sa_entry->x->lock); @@ -458,9 +456,6 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, u8 ds_cnt; lockdep_assert_held(&sa_entry->x->lock); - if (aso->use_cache) - return 0; - res = &mdev->mlx5e_res.hw_objs; memset(aso->ctx, 0, sizeof(aso->ctx)); -- cgit v1.2.3 From e4d38c454ae57e649f09a354d5a9dae063a26ee3 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 9 Jan 2023 10:34:25 +0200 Subject: net/mlx5e: Protect global IPsec ASO ASO operations are global to whole IPsec as they share one DMA address for all operations. As such all WQE operations need to be protected with lock. In this case, it must be spinlock to allow mlx5e_ipsec_aso_query() operate in atomic context. Fixes: 1ed78fc03307 ("net/mlx5e: Update IPsec soft and hard limits") Reviewed-by: Jianbo Liu Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 160f8883b93e..8bed9c361075 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -122,6 +122,8 @@ struct mlx5e_ipsec_aso { u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)]; dma_addr_t dma_addr; struct mlx5_aso *aso; + /* Protect ASO WQ access, as it is global to whole IPsec */ + spinlock_t lock; }; struct mlx5e_ipsec { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index aafbd7b244ee..2461462b7b99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -396,6 +396,7 @@ int mlx5e_ipsec_aso_init(struct mlx5e_ipsec *ipsec) goto err_aso_create; } + spin_lock_init(&aso->lock); ipsec->nb.notifier_call = mlx5e_ipsec_event; mlx5_notifier_register(mdev, &ipsec->nb); @@ -454,10 +455,12 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_hw_objs *res; struct mlx5_aso_wqe *wqe; u8 ds_cnt; + int ret; lockdep_assert_held(&sa_entry->x->lock); res = &mdev->mlx5e_res.hw_objs; + spin_lock_bh(&aso->lock); memset(aso->ctx, 0, sizeof(aso->ctx)); wqe = mlx5_aso_get_wqe(aso->aso); ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS); @@ -472,7 +475,9 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, mlx5e_ipsec_aso_copy(ctrl, data); mlx5_aso_post_wqe(aso->aso, false, &wqe->ctrl); - return mlx5_aso_poll_cq(aso->aso, false); + ret = mlx5_aso_poll_cq(aso->aso, false); + spin_unlock_bh(&aso->lock); + return ret; } void mlx5e_ipsec_aso_update_curlft(struct mlx5e_ipsec_sa_entry *sa_entry, -- cgit v1.2.3 From 7c83d1f4c5adae9583e7fca1e3e830d6b061522d Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Wed, 21 Dec 2022 11:14:37 +0200 Subject: net/mlx5: E-switch, Fix switchdev mode after devlink reload The cited commit removes eswitch mode none. So after devlink reload in switchdev mode, eswitch mode is not changed. But actually eswitch is disabled during devlink reload. Fix it by setting eswitch mode to legacy when disabling eswitch which is called by reload_down. Fixes: f019679ea5f2 ("net/mlx5: E-switch, Remove dependency between sriov and eswitch mode") Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 0dfd5742c6fe..9daf55e90367 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1464,6 +1464,7 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) mlx5_lag_disable_change(esw->dev); down_write(&esw->mode_lock); mlx5_eswitch_disable_locked(esw); + esw->mode = MLX5_ESWITCH_LEGACY; up_write(&esw->mode_lock); mlx5_lag_enable_change(esw->dev); } -- cgit v1.2.3 From 2c1e1b949024989e20907b84e11a731a50778416 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 30 Aug 2022 20:12:29 -0700 Subject: net: mlx5: eliminate anonymous module_init & module_exit Eliminate anonymous module_init() and module_exit(), which can lead to confusion or ambiguity when reading System.map, crashes/oops/bugs, or an initcall_debug log. Give each of these init and exit functions unique driver-specific names to eliminate the anonymous names. Example 1: (System.map) ffffffff832fc78c t init ffffffff832fc79e t init ffffffff832fc8f8 t init Example 2: (initcall_debug log) calling init+0x0/0x12 @ 1 initcall init+0x0/0x12 returned 0 after 15 usecs calling init+0x0/0x60 @ 1 initcall init+0x0/0x60 returned 0 after 2 usecs calling init+0x0/0x9a @ 1 initcall init+0x0/0x9a returned 0 after 74 usecs Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Randy Dunlap Cc: Eli Cohen Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: linux-rdma@vger.kernel.org Reviewed-by: Ira Weiny Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index df134f6d32dc..3d5f2a4b1fed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2098,7 +2098,7 @@ static void mlx5_core_verify_params(void) } } -static int __init init(void) +static int __init mlx5_init(void) { int err; @@ -2133,7 +2133,7 @@ err_debug: return err; } -static void __exit cleanup(void) +static void __exit mlx5_cleanup(void) { mlx5e_cleanup(); mlx5_sf_driver_unregister(); @@ -2141,5 +2141,5 @@ static void __exit cleanup(void) mlx5_unregister_debugfs(); } -module_init(init); -module_exit(cleanup); +module_init(mlx5_init); +module_exit(mlx5_cleanup); -- cgit v1.2.3