From 554fe75c1b3f679b1eebf193a4e56492837d3f5a Mon Sep 17 00:00:00 2001 From: Dmytro Linkin Date: Thu, 31 Oct 2019 18:15:51 +0200 Subject: [PATCH 1/7] net/mlx5e: Avoid duplicating rule destinations Following scenario easily break driver logic and crash the kernel: 1. Add rule with mirred actions to same device. 2. Delete this rule. In described scenario rule is not added to database and on deletion driver access invalid entry. Example: $ tc filter add dev ens1f0_0 ingress protocol ip prio 1 \ flower skip_sw \ action mirred egress mirror dev ens1f0_1 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter del dev ens1f0_0 ingress protocol ip prio 1 Dmesg output: [ 376.634396] mlx5_core 0000:82:00.0: mlx5_cmd_check:756:(pid 3439): DESTROY_FLOW_GROUP(0x934) op_mod(0x0) failed, status bad resource state(0x9), syndrome (0x563e2f) [ 376.654983] mlx5_core 0000:82:00.0: del_hw_flow_group:567:(pid 3439): flow steering can't destroy fg 89 of ft 3145728 [ 376.673433] kasan: CONFIG_KASAN_INLINE enabled [ 376.683769] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 376.695229] general protection fault: 0000 [#1] PREEMPT SMP KASAN PTI [ 376.705069] CPU: 7 PID: 3439 Comm: tc Not tainted 5.4.0-rc5+ #76 [ 376.714959] Hardware name: Supermicro SYS-2028TP-DECTR/X10DRT-PT, BIOS 2.0a 08/12/2016 [ 376.726371] RIP: 0010:mlx5_del_flow_rules+0x105/0x960 [mlx5_core] [ 376.735817] Code: 01 00 00 00 48 83 eb 08 e8 28 d9 ff ff 4c 39 e3 75 d8 4c 8d bd c0 02 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 84 04 00 00 48 8d 7d 28 8b 9 d [ 376.761261] RSP: 0018:ffff888847c56db8 EFLAGS: 00010202 [ 376.770054] RAX: dffffc0000000000 RBX: ffff8888582a6da0 RCX: ffff888847c56d60 [ 376.780743] RDX: 0000000000000058 RSI: 0000000000000008 RDI: 0000000000000282 [ 376.791328] RBP: 0000000000000000 R08: fffffbfff0c60ea6 R09: fffffbfff0c60ea6 [ 376.802050] R10: fffffbfff0c60ea5 R11: ffffffff8630752f R12: ffff8888582a6da0 [ 376.812798] R13: dffffc0000000000 R14: ffff8888582a6da0 R15: 00000000000002c0 [ 376.823445] FS: 00007f675f9a8840(0000) GS:ffff88886d200000(0000) knlGS:0000000000000000 [ 376.834971] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.844179] CR2: 00000000007d9640 CR3: 00000007d3f26003 CR4: 00000000001606e0 [ 376.854843] Call Trace: [ 376.868542] __mlx5_eswitch_del_rule+0x49/0x300 [mlx5_core] [ 376.877735] mlx5e_tc_del_fdb_flow+0x6ec/0x9e0 [mlx5_core] [ 376.921549] mlx5e_flow_put+0x2b/0x50 [mlx5_core] [ 376.929813] mlx5e_delete_flower+0x5b6/0xbd0 [mlx5_core] [ 376.973030] tc_setup_cb_reoffload+0x29/0xc0 [ 376.980619] fl_reoffload+0x50a/0x770 [cls_flower] [ 377.015087] tcf_block_playback_offloads+0xbd/0x250 [ 377.033400] tcf_block_setup+0x1b2/0xc60 [ 377.057247] tcf_block_offload_cmd+0x195/0x240 [ 377.098826] tcf_block_offload_unbind+0xe7/0x180 [ 377.107056] __tcf_block_put+0xe5/0x400 [ 377.114528] ingress_destroy+0x3d/0x60 [sch_ingress] [ 377.122894] qdisc_destroy+0xf1/0x5a0 [ 377.129993] qdisc_graft+0xa3d/0xe50 [ 377.151227] tc_get_qdisc+0x48e/0xa20 [ 377.165167] rtnetlink_rcv_msg+0x35d/0x8d0 [ 377.199528] netlink_rcv_skb+0x11e/0x340 [ 377.219638] netlink_unicast+0x408/0x5b0 [ 377.239913] netlink_sendmsg+0x71b/0xb30 [ 377.267505] sock_sendmsg+0xb1/0xf0 [ 377.273801] ___sys_sendmsg+0x635/0x900 [ 377.312784] __sys_sendmsg+0xd3/0x170 [ 377.338693] do_syscall_64+0x95/0x460 [ 377.344833] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 377.352321] RIP: 0033:0x7f675e58e090 To avoid this, for every mirred action check if output device was already processed. If so - drop rule with EOPNOTSUPP error. Signed-off-by: Dmytro Linkin Reviewed-by: Roi Dayan Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 58 ++++++++++++++++++- 1 file changed, 57 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9b32a9c0f497..fe83886f5435 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2999,6 +2999,25 @@ static struct ip_tunnel_info *dup_tun_info(const struct ip_tunnel_info *tun_info return kmemdup(tun_info, tun_size, GFP_KERNEL); } +static bool is_duplicated_encap_entry(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + int out_index, + struct mlx5e_encap_entry *e, + struct netlink_ext_ack *extack) +{ + int i; + + for (i = 0; i < out_index; i++) { + if (flow->encaps[i].e != e) + continue; + NL_SET_ERR_MSG_MOD(extack, "can't duplicate encap action"); + netdev_err(priv->netdev, "can't duplicate encap action\n"); + return true; + } + + return false; +} + static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct net_device *mirred_dev, @@ -3034,6 +3053,12 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, /* must verify if encap is valid or not */ if (e) { + /* Check that entry was not already attached to this flow */ + if (is_duplicated_encap_entry(priv, flow, out_index, e, extack)) { + err = -EOPNOTSUPP; + goto out_err; + } + mutex_unlock(&esw->offloads.encap_tbl_lock); wait_for_completion(&e->res_ready); @@ -3220,6 +3245,26 @@ bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv, same_hw_devs(priv, netdev_priv(out_dev)); } +static bool is_duplicated_output_device(struct net_device *dev, + struct net_device *out_dev, + int *ifindexes, int if_count, + struct netlink_ext_ack *extack) +{ + int i; + + for (i = 0; i < if_count; i++) { + if (ifindexes[i] == out_dev->ifindex) { + NL_SET_ERR_MSG_MOD(extack, + "can't duplicate output to same device"); + netdev_err(dev, "can't duplicate output to same device: %s\n", + out_dev->name); + return true; + } + } + + return false; +} + static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct flow_action *flow_action, struct mlx5e_tc_flow *flow, @@ -3231,11 +3276,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; struct mlx5e_rep_priv *rpriv = priv->ppriv; const struct ip_tunnel_info *info = NULL; + int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; bool ft_flow = mlx5e_is_ft_flow(flow); const struct flow_action_entry *act; + int err, i, if_count = 0; bool encap = false; u32 action = 0; - int err, i; if (!flow_action_has_entries(flow_action)) return -EINVAL; @@ -3312,6 +3358,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); struct net_device *uplink_upper; + if (is_duplicated_output_device(priv->netdev, + out_dev, + ifindexes, + if_count, + extack)) + return -EOPNOTSUPP; + + ifindexes[if_count] = out_dev->ifindex; + if_count++; + rcu_read_lock(); uplink_upper = netdev_master_upper_dev_get_rcu(uplink_dev); From 99cda45426c9a2c59bb2f7cb886a405440282455 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 4 Dec 2019 14:34:18 +0200 Subject: [PATCH 2/7] net/mlx5e: Always print health reporter message to dmesg In case a reporter exists, error message is logged only to the devlink tracer. The devlink tracer is a visibility utility only, which user can choose not to monitor. After cited patch, 3rd party monitoring tools that tracks these error message will no longer find them in dmesg, causing a regression. With this patch, error messages are also logged into the dmesg. Fixes: c50de4af1d63 ("net/mlx5e: Generalize tx reporter's functionality") Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/health.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 1d6b58860da6..3a975641f902 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -197,9 +197,10 @@ int mlx5e_health_report(struct mlx5e_priv *priv, struct devlink_health_reporter *reporter, char *err_str, struct mlx5e_err_ctx *err_ctx) { - if (!reporter) { - netdev_err(priv->netdev, err_str); + netdev_err(priv->netdev, err_str); + + if (!reporter) return err_ctx->recover(&err_ctx->ctx); - } + return devlink_health_report(reporter, err_str, err_ctx); } From a6f3b62386a02c1e94bfa22c543f82d63f5e631b Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Wed, 20 Nov 2019 11:43:49 +0200 Subject: [PATCH 3/7] net/mlx5: Move devlink registration before interfaces load Register devlink before interfaces are added. This will allow interfaces to use devlink while initalizing. For example, call mlx5_is_roce_enabled. Fixes: aba25279c100 ("net/mlx5e: Add TX reporter support") Signed-off-by: Michael Guralnik Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 173e2c12e1c7..cf7b8da0f010 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1193,6 +1193,12 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) if (err) goto err_load; + if (boot) { + err = mlx5_devlink_register(priv_to_devlink(dev), dev->device); + if (err) + goto err_devlink_reg; + } + if (mlx5_device_registered(dev)) { mlx5_attach_device(dev); } else { @@ -1210,6 +1216,9 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) return err; err_reg_dev: + if (boot) + mlx5_devlink_unregister(priv_to_devlink(dev)); +err_devlink_reg: mlx5_unload(dev); err_load: if (boot) @@ -1347,10 +1356,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) request_module_nowait(MLX5_IB_MOD); - err = mlx5_devlink_register(devlink, &pdev->dev); - if (err) - goto clean_load; - err = mlx5_crdump_enable(dev); if (err) dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); @@ -1358,9 +1363,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) pci_save_state(pdev); return 0; -clean_load: - mlx5_unload_one(dev, true); - err_load_one: mlx5_pci_close(dev); pci_init_err: From 1f0593e791ed3fb4074d4470a261cde62d806ed5 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 11 Dec 2019 00:35:18 -0600 Subject: [PATCH 4/7] Revert "net/mlx5: Support lockless FTE read lookups" This reverts commit 7dee607ed0e04500459db53001d8e02f8831f084. During cleanup path, FTE's parent node group is removed which is referenced by the FTE while freeing the FTE. Hence FTE's lockless read lookup optimization done in cited commit is not possible at the moment. Hence, revert the commit. This avoid below KAZAN call trace. [ 110.390896] BUG: KASAN: use-after-free in find_root.isra.14+0x56/0x60 [mlx5_core] [ 110.391048] Read of size 4 at addr ffff888c19e6d220 by task swapper/12/0 [ 110.391219] CPU: 12 PID: 0 Comm: swapper/12 Not tainted 5.5.0-rc1+ [ 110.391222] Hardware name: HP ProLiant DL380p Gen8, BIOS P70 08/02/2014 [ 110.391225] Call Trace: [ 110.391229] [ 110.391246] dump_stack+0x95/0xd5 [ 110.391307] ? find_root.isra.14+0x56/0x60 [mlx5_core] [ 110.391320] print_address_description.constprop.5+0x20/0x320 [ 110.391379] ? find_root.isra.14+0x56/0x60 [mlx5_core] [ 110.391435] ? find_root.isra.14+0x56/0x60 [mlx5_core] [ 110.391441] __kasan_report+0x149/0x18c [ 110.391499] ? find_root.isra.14+0x56/0x60 [mlx5_core] [ 110.391504] kasan_report+0x12/0x20 [ 110.391511] __asan_report_load4_noabort+0x14/0x20 [ 110.391567] find_root.isra.14+0x56/0x60 [mlx5_core] [ 110.391625] del_sw_fte_rcu+0x4a/0x100 [mlx5_core] [ 110.391633] rcu_core+0x404/0x1950 [ 110.391640] ? rcu_accelerate_cbs_unlocked+0x100/0x100 [ 110.391649] ? run_rebalance_domains+0x201/0x280 [ 110.391654] rcu_core_si+0xe/0x10 [ 110.391661] __do_softirq+0x181/0x66c [ 110.391670] irq_exit+0x12c/0x150 [ 110.391675] smp_apic_timer_interrupt+0xf0/0x370 [ 110.391681] apic_timer_interrupt+0xf/0x20 [ 110.391684] [ 110.391695] RIP: 0010:cpuidle_enter_state+0xfa/0xba0 [ 110.391703] Code: 3d c3 9b b5 50 e8 56 75 6e fe 48 89 45 c8 0f 1f 44 00 00 31 ff e8 a6 94 6e fe 45 84 ff 0f 85 f6 02 00 00 fb 66 0f 1f 44 00 00 <45> 85 f6 0f 88 db 06 00 00 4d 63 fe 4b 8d 04 7f 49 8d 04 87 49 8d [ 110.391706] RSP: 0018:ffff888c23a6fce8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 110.391712] RAX: dffffc0000000000 RBX: ffffe8ffff7002f8 RCX: 000000000000001f [ 110.391715] RDX: 1ffff11184ee6cb5 RSI: 0000000040277d83 RDI: ffff888c277365a8 [ 110.391718] RBP: ffff888c23a6fd40 R08: 0000000000000002 R09: 0000000000035280 [ 110.391721] R10: ffff888c23a6fc80 R11: ffffed11847485d0 R12: ffffffffb1017740 [ 110.391723] R13: 0000000000000003 R14: 0000000000000003 R15: 0000000000000000 [ 110.391732] ? cpuidle_enter_state+0xea/0xba0 [ 110.391738] cpuidle_enter+0x4f/0xa0 [ 110.391747] call_cpuidle+0x6d/0xc0 [ 110.391752] do_idle+0x360/0x430 [ 110.391758] ? arch_cpu_idle_exit+0x40/0x40 [ 110.391765] ? complete+0x67/0x80 [ 110.391771] cpu_startup_entry+0x1d/0x20 [ 110.391779] start_secondary+0x2f3/0x3c0 [ 110.391784] ? set_cpu_sibling_map+0x2500/0x2500 [ 110.391795] secondary_startup_64+0xa4/0xb0 [ 110.391841] Allocated by task 290: [ 110.391917] save_stack+0x21/0x90 [ 110.391921] __kasan_kmalloc.constprop.8+0xa7/0xd0 [ 110.391925] kasan_kmalloc+0x9/0x10 [ 110.391929] kmem_cache_alloc_trace+0xf6/0x270 [ 110.391987] create_root_ns.isra.36+0x58/0x260 [mlx5_core] [ 110.392044] mlx5_init_fs+0x5fd/0x1ee0 [mlx5_core] [ 110.392092] mlx5_load_one+0xc7a/0x3860 [mlx5_core] [ 110.392139] init_one+0x6ff/0xf90 [mlx5_core] [ 110.392145] local_pci_probe+0xde/0x190 [ 110.392150] work_for_cpu_fn+0x56/0xa0 [ 110.392153] process_one_work+0x678/0x1140 [ 110.392157] worker_thread+0x573/0xba0 [ 110.392162] kthread+0x341/0x400 [ 110.392166] ret_from_fork+0x1f/0x40 [ 110.392218] Freed by task 2742: [ 110.392288] save_stack+0x21/0x90 [ 110.392292] __kasan_slab_free+0x137/0x190 [ 110.392296] kasan_slab_free+0xe/0x10 [ 110.392299] kfree+0x94/0x250 [ 110.392357] tree_put_node+0x257/0x360 [mlx5_core] [ 110.392413] tree_remove_node+0x63/0xb0 [mlx5_core] [ 110.392469] clean_tree+0x199/0x240 [mlx5_core] [ 110.392525] mlx5_cleanup_fs+0x76/0x580 [mlx5_core] [ 110.392572] mlx5_unload+0x22/0xc0 [mlx5_core] [ 110.392619] mlx5_unload_one+0x99/0x260 [mlx5_core] [ 110.392666] remove_one+0x61/0x160 [mlx5_core] [ 110.392671] pci_device_remove+0x10b/0x2c0 [ 110.392677] device_release_driver_internal+0x1e4/0x490 [ 110.392681] device_driver_detach+0x36/0x40 [ 110.392685] unbind_store+0x147/0x200 [ 110.392688] drv_attr_store+0x6f/0xb0 [ 110.392693] sysfs_kf_write+0x127/0x1d0 [ 110.392697] kernfs_fop_write+0x296/0x420 [ 110.392702] __vfs_write+0x66/0x110 [ 110.392707] vfs_write+0x1a0/0x500 [ 110.392711] ksys_write+0x164/0x250 [ 110.392715] __x64_sys_write+0x73/0xb0 [ 110.392720] do_syscall_64+0x9f/0x3a0 [ 110.392725] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 7dee607ed0e0 ("net/mlx5: Support lockless FTE read lookups") Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 94 ++++++------------- .../net/ethernet/mellanox/mlx5/core/fs_core.h | 1 - 2 files changed, 27 insertions(+), 68 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9a48c4310887..8c5df6c7d7b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -531,16 +531,9 @@ static void del_hw_fte(struct fs_node *node) } } -static void del_sw_fte_rcu(struct rcu_head *head) -{ - struct fs_fte *fte = container_of(head, struct fs_fte, rcu); - struct mlx5_flow_steering *steering = get_steering(&fte->node); - - kmem_cache_free(steering->ftes_cache, fte); -} - static void del_sw_fte(struct fs_node *node) { + struct mlx5_flow_steering *steering = get_steering(node); struct mlx5_flow_group *fg; struct fs_fte *fte; int err; @@ -553,8 +546,7 @@ static void del_sw_fte(struct fs_node *node) rhash_fte); WARN_ON(err); ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); - - call_rcu(&fte->rcu, del_sw_fte_rcu); + kmem_cache_free(steering->ftes_cache, fte); } static void del_hw_flow_group(struct fs_node *node) @@ -1633,67 +1625,35 @@ static u64 matched_fgs_get_version(struct list_head *match_head) } static struct fs_fte * -lookup_fte_for_write_locked(struct mlx5_flow_group *g, const u32 *match_value) +lookup_fte_locked(struct mlx5_flow_group *g, + const u32 *match_value, + bool take_write) { struct fs_fte *fte_tmp; - nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); - - fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, rhash_fte); - if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { - fte_tmp = NULL; - goto out; - } - - if (!fte_tmp->node.active) { - tree_put_node(&fte_tmp->node, false); - fte_tmp = NULL; - goto out; - } - nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); - -out: - up_write_ref_node(&g->node, false); - return fte_tmp; -} - -static struct fs_fte * -lookup_fte_for_read_locked(struct mlx5_flow_group *g, const u32 *match_value) -{ - struct fs_fte *fte_tmp; - - if (!tree_get_node(&g->node)) - return NULL; - - rcu_read_lock(); - fte_tmp = rhashtable_lookup(&g->ftes_hash, match_value, rhash_fte); - if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { - rcu_read_unlock(); - fte_tmp = NULL; - goto out; - } - rcu_read_unlock(); - - if (!fte_tmp->node.active) { - tree_put_node(&fte_tmp->node, false); - fte_tmp = NULL; - goto out; - } - - nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); - -out: - tree_put_node(&g->node, false); - return fte_tmp; -} - -static struct fs_fte * -lookup_fte_locked(struct mlx5_flow_group *g, const u32 *match_value, bool write) -{ - if (write) - return lookup_fte_for_write_locked(g, match_value); + if (take_write) + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); else - return lookup_fte_for_read_locked(g, match_value); + nested_down_read_ref_node(&g->node, FS_LOCK_PARENT); + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, + rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { + fte_tmp = NULL; + goto out; + } + if (!fte_tmp->node.active) { + tree_put_node(&fte_tmp->node, false); + fte_tmp = NULL; + goto out; + } + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); +out: + if (take_write) + up_write_ref_node(&g->node, false); + else + up_read_ref_node(&g->node); + return fte_tmp; } static struct mlx5_flow_handle * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index e8cd997f413e..c2621b911563 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -203,7 +203,6 @@ struct fs_fte { enum fs_fte_status status; struct mlx5_fc *counter; struct rhash_head hash; - struct rcu_head rcu; int modify_mask; }; From 4ce380ca477507e2f413584cdd99e1698d6682d6 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 23 Dec 2019 16:16:31 +0200 Subject: [PATCH 5/7] net/mlx5: DR, No need for atomic refcount for internal SW steering resources No need for an atomic refcounter for the STE and hashtables. These are internal SW steering resources and they are always under domain mutex. This also fixes the following refcount error: refcount_t: addition on 0; use-after-free. WARNING: CPU: 9 PID: 3527 at lib/refcount.c:25 refcount_warn_saturate+0x81/0xe0 Call Trace: dr_table_init_nic+0x10d/0x110 [mlx5_core] mlx5dr_table_create+0xb4/0x230 [mlx5_core] mlx5_cmd_dr_create_flow_table+0x39/0x120 [mlx5_core] __mlx5_create_flow_table+0x221/0x5f0 [mlx5_core] esw_create_offloads_fdb_tables+0x180/0x5a0 [mlx5_core] ... Fixes: 26d688e33f88 ("net/mlx5: DR, Add Steering entry (STE) utilities") Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/steering/dr_rule.c | 2 +- .../ethernet/mellanox/mlx5/core/steering/dr_ste.c | 10 +++++----- .../mellanox/mlx5/core/steering/dr_types.h | 14 ++++++++------ 3 files changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 32e94d2ee5e4..f21bc1bc77d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -209,7 +209,7 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher, /* We need to copy the refcount since this ste * may have been traversed several times */ - refcount_set(&new_ste->refcount, refcount_read(&cur_ste->refcount)); + new_ste->refcount = cur_ste->refcount; /* Link old STEs rule_mem list to the new ste */ mlx5dr_rule_update_rule_member(cur_ste, new_ste); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index a5a266983dd3..c6c7d1defbd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -348,7 +348,7 @@ static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src) if (dst->next_htbl) dst->next_htbl->pointing_ste = dst; - refcount_set(&dst->refcount, refcount_read(&src->refcount)); + dst->refcount = src->refcount; INIT_LIST_HEAD(&dst->rule_list); list_splice_tail_init(&src->rule_list, &dst->rule_list); @@ -565,7 +565,7 @@ bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste) bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste) { - return !refcount_read(&ste->refcount); + return !ste->refcount; } /* Init one ste as a pattern for ste data array */ @@ -689,14 +689,14 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, htbl->ste_arr = chunk->ste_arr; htbl->hw_ste_arr = chunk->hw_ste_arr; htbl->miss_list = chunk->miss_list; - refcount_set(&htbl->refcount, 0); + htbl->refcount = 0; for (i = 0; i < chunk->num_of_entries; i++) { struct mlx5dr_ste *ste = &htbl->ste_arr[i]; ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED; ste->htbl = htbl; - refcount_set(&ste->refcount, 0); + ste->refcount = 0; INIT_LIST_HEAD(&ste->miss_list_node); INIT_LIST_HEAD(&htbl->miss_list[i]); INIT_LIST_HEAD(&ste->rule_list); @@ -713,7 +713,7 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl) { - if (refcount_read(&htbl->refcount)) + if (htbl->refcount) return -EBUSY; mlx5dr_icm_free_chunk(htbl->chunk); 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 290fe61c33d0..3fdf4a5eb031 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -123,7 +123,7 @@ struct mlx5dr_matcher_rx_tx; struct mlx5dr_ste { u8 *hw_ste; /* refcount: indicates the num of rules that using this ste */ - refcount_t refcount; + u32 refcount; /* attached to the miss_list head at each htbl entry */ struct list_head miss_list_node; @@ -155,7 +155,7 @@ struct mlx5dr_ste_htbl_ctrl { struct mlx5dr_ste_htbl { u8 lu_type; u16 byte_mask; - refcount_t refcount; + u32 refcount; struct mlx5dr_icm_chunk *chunk; struct mlx5dr_ste *ste_arr; u8 *hw_ste_arr; @@ -206,13 +206,14 @@ int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl); static inline void mlx5dr_htbl_put(struct mlx5dr_ste_htbl *htbl) { - if (refcount_dec_and_test(&htbl->refcount)) + htbl->refcount--; + if (!htbl->refcount) mlx5dr_ste_htbl_free(htbl); } static inline void mlx5dr_htbl_get(struct mlx5dr_ste_htbl *htbl) { - refcount_inc(&htbl->refcount); + htbl->refcount++; } /* STE utils */ @@ -254,14 +255,15 @@ static inline void mlx5dr_ste_put(struct mlx5dr_ste *ste, struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher) { - if (refcount_dec_and_test(&ste->refcount)) + ste->refcount--; + if (!ste->refcount) mlx5dr_ste_free(ste, matcher, nic_matcher); } /* initial as 0, increased only when ste appears in a new rule */ static inline void mlx5dr_ste_get(struct mlx5dr_ste *ste) { - refcount_inc(&ste->refcount); + ste->refcount++; } void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste, From 6412bb396a63f28de994b1480edf8e4caf4aa494 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 11 Dec 2019 09:17:40 +0200 Subject: [PATCH 6/7] net/mlx5e: Fix hairpin RSS table size Set hairpin table size to the corret size, based on the groups that would be created in it. Groups are laid out on the table such that a group occupies a range of entries in the table. This implies that the group ranges should have correspondence to the table they are laid upon. The patch cited below made group 1's size to grow hence causing overflow of group range laid on the table. Fixes: a795d8db2a6d ("net/mlx5e: Support RSS for IP-in-IP and IPv6 tunneled packets") Signed-off-by: Eli Cohen Signed-off-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 16 ++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 16 ---------------- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- 3 files changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 68d593074f6c..d48292ccda29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -122,6 +122,22 @@ enum { #endif }; +#define MLX5E_TTC_NUM_GROUPS 3 +#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT) +#define MLX5E_TTC_GROUP2_SIZE BIT(1) +#define MLX5E_TTC_GROUP3_SIZE BIT(0) +#define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\ + MLX5E_TTC_GROUP2_SIZE +\ + MLX5E_TTC_GROUP3_SIZE) + +#define MLX5E_INNER_TTC_NUM_GROUPS 3 +#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3) +#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1) +#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0) +#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\ + MLX5E_INNER_TTC_GROUP2_SIZE +\ + MLX5E_INNER_TTC_GROUP3_SIZE) + #ifdef CONFIG_MLX5_EN_RXNFC struct mlx5e_ethtool_table { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 15b7f0f1427c..73d3dc07331f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -904,22 +904,6 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv, return err; } -#define MLX5E_TTC_NUM_GROUPS 3 -#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT) -#define MLX5E_TTC_GROUP2_SIZE BIT(1) -#define MLX5E_TTC_GROUP3_SIZE BIT(0) -#define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\ - MLX5E_TTC_GROUP2_SIZE +\ - MLX5E_TTC_GROUP3_SIZE) - -#define MLX5E_INNER_TTC_NUM_GROUPS 3 -#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3) -#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1) -#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0) -#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\ - MLX5E_INNER_TTC_GROUP2_SIZE +\ - MLX5E_INNER_TTC_GROUP3_SIZE) - static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc, bool use_ipv) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fe83886f5435..024e1cddfd0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -592,7 +592,7 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp, for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) ttc_params->indir_tirn[tt] = hp->indir_tirn[tt]; - ft_attr->max_fte = MLX5E_NUM_TT; + ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE; ft_attr->level = MLX5E_TC_TTC_FT_LEVEL; ft_attr->prio = MLX5E_TC_PRIO; } From df55c5586e5185f890192a6802dc5b46fddd3606 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Mon, 25 Nov 2019 10:26:24 +0200 Subject: [PATCH 7/7] net/mlx5: DR, Init lists that are used in rule's member Whenever adding new member of rule object we attach it to 2 lists, These 2 lists should be initialized first. Fixes: 41d07074154c ("net/mlx5: DR, Expose steering rule functionality") Signed-off-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index f21bc1bc77d7..e4cff7abb348 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -638,6 +638,9 @@ static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule, if (!rule_mem) return -ENOMEM; + INIT_LIST_HEAD(&rule_mem->list); + INIT_LIST_HEAD(&rule_mem->use_ste_list); + rule_mem->ste = ste; list_add_tail(&rule_mem->list, &nic_rule->rule_members_list);