When adding a hairpin flow, a firmware-side send queue is created for
the peer net device, which claims some host memory pages for its
internal ring buffer. If the peer net device is removed/unbound before
the hairpin flow is deleted, then the send queue is not destroyed which
leads to a stack trace on pci device remove:
[ 748.005230] mlx5_core 0000:08:00.2: wait_func:1094:(pid 12985): MANAGE_PAGES(0x108) timeout. Will cause a leak of a command resource
[ 748.005231] mlx5_core 0000:08:00.2: reclaim_pages:514:(pid 12985): failed reclaiming pages: err -110
[ 748.001835] mlx5_core 0000:08:00.2: mlx5_reclaim_root_pages:653:(pid 12985): failed reclaiming pages (-110) for func id 0x0
[ 748.002171] ------------[ cut here ]------------
[ 748.001177] FW pages counter is 4 after reclaiming all pages
[ 748.001186] WARNING: CPU: 1 PID: 12985 at drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:685 mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ +0.002771] Modules linked in: cls_flower mlx5_ib mlx5_core ptp pps_core act_mirred sch_ingress openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_umad ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay fuse [last unloaded: pps_core]
[ 748.007225] CPU: 1 PID: 12985 Comm: tee Not tainted 5.12.0+ #1
[ 748.001376] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 748.002315] RIP: 0010:mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core]
[ 748.001679] Code: 28 00 00 00 0f 85 22 01 00 00 48 81 c4 b0 00 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 c7 c7 40 cc 19 a1 e8 9f 71 0e e2 <0f> 0b e9 30 ff ff ff 48 c7 c7 a0 cc 19 a1 e8 8c 71 0e e2 0f 0b e9
[ 748.003781] RSP: 0018:
ffff88815220faf8 EFLAGS:
00010286
[ 748.001149] RAX:
0000000000000000 RBX:
ffff8881b4900280 RCX:
0000000000000000
[ 748.001445] RDX:
0000000000000027 RSI:
0000000000000004 RDI:
ffffed102a441f51
[ 748.001614] RBP:
00000000000032b9 R08:
0000000000000001 R09:
ffffed1054a15ee8
[ 748.001446] R10:
ffff8882a50af73b R11:
ffffed1054a15ee7 R12:
fffffbfff07c1e30
[ 748.001447] R13:
dffffc0000000000 R14:
ffff8881b492cba8 R15:
0000000000000000
[ 748.001429] FS:
00007f58bd08b580(0000) GS:
ffff8882a5080000(0000) knlGS:
0000000000000000
[ 748.001695] CS: 0010 DS: 0000 ES: 0000 CR0:
0000000080050033
[ 748.001309] CR2:
000055a026351740 CR3:
00000001d3b48006 CR4:
0000000000370ea0
[ 748.001506] DR0:
0000000000000000 DR1:
0000000000000000 DR2:
0000000000000000
[ 748.001483] DR3:
0000000000000000 DR6:
00000000fffe0ff0 DR7:
0000000000000400
[ 748.001654] Call Trace:
[ 748.000576] ? mlx5_satisfy_startup_pages+0x290/0x290 [mlx5_core]
[ 748.001416] ? mlx5_cmd_teardown_hca+0xa2/0xd0 [mlx5_core]
[ 748.001354] ? mlx5_cmd_init_hca+0x280/0x280 [mlx5_core]
[ 748.001203] mlx5_function_teardown+0x30/0x60 [mlx5_core]
[ 748.001275] mlx5_uninit_one+0xa7/0xc0 [mlx5_core]
[ 748.001200] remove_one+0x5f/0xc0 [mlx5_core]
[ 748.001075] pci_device_remove+0x9f/0x1d0
[ 748.000833] device_release_driver_internal+0x1e0/0x490
[ 748.001207] unbind_store+0x19f/0x200
[ 748.000942] ? sysfs_file_ops+0x170/0x170
[ 748.001000] kernfs_fop_write_iter+0x2bc/0x450
[ 748.000970] new_sync_write+0x373/0x610
[ 748.001124] ? new_sync_read+0x600/0x600
[ 748.001057] ? lock_acquire+0x4d6/0x700
[ 748.000908] ? lockdep_hardirqs_on_prepare+0x400/0x400
[ 748.001126] ? fd_install+0x1c9/0x4d0
[ 748.000951] vfs_write+0x4d0/0x800
[ 748.000804] ksys_write+0xf9/0x1d0
[ 748.000868] ? __x64_sys_read+0xb0/0xb0
[ 748.000811] ? filp_open+0x50/0x50
[ 748.000919] ? syscall_enter_from_user_mode+0x1d/0x50
[ 748.001223] do_syscall_64+0x3f/0x80
[ 748.000892] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 748.001026] RIP: 0033:0x7f58bcfb22f7
[ 748.000944] Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
[ 748.003925] RSP: 002b:
00007fffd7f2aaa8 EFLAGS:
00000246 ORIG_RAX:
0000000000000001
[ 748.001732] RAX:
ffffffffffffffda RBX:
000000000000000d RCX:
00007f58bcfb22f7
[ 748.001426] RDX:
000000000000000d RSI:
00007fffd7f2abc0 RDI:
0000000000000003
[ 748.001746] RBP:
00007fffd7f2abc0 R08:
0000000000000000 R09:
0000000000000001
[ 748.001631] R10:
00000000000001b6 R11:
0000000000000246 R12:
000000000000000d
[ 748.001537] R13:
00005597ac2c24a0 R14:
000000000000000d R15:
00007f58bd084700
[ 748.001564] irq event stamp: 0
[ 748.000787] hardirqs last enabled at (0): [<
0000000000000000>] 0x0
[ 748.001399] hardirqs last disabled at (0): [<
ffffffff813132cf>] copy_process+0x146f/0x5eb0
[ 748.001854] softirqs last enabled at (0): [<
ffffffff8131330e>] copy_process+0x14ae/0x5eb0
[ 748.013431] softirqs last disabled at (0): [<
0000000000000000>] 0x0
[ 748.001492] ---[ end trace
a6fabd773d1c51ae ]---
Fix by destroying the send queue of a hairpin peer net device that is
being removed/unbound, which returns the allocated ring buffer pages to
the host.
Fixes: 4d8fcf216c90 ("net/mlx5e: Avoid unbounded peer devices when unpairing TC hairpin rules")
Signed-off-by: Dima Chumak <dchumak@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) {
wait_for_completion(&hpe->res_ready);
if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id)
- hpe->hp->pair->peer_gone = true;
+ mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair);
mlx5e_hairpin_put(priv, hpe);
}
return err;
}
+static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp)
+{
+ int i;
+
+ for (i = 0; i < hp->num_channels; i++)
+ mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
+ MLX5_SQC_STATE_RST, 0, 0);
+}
+
static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp)
{
int i;
for (i = 0; i < hp->num_channels; i++)
mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY,
MLX5_RQC_STATE_RST, 0, 0);
-
/* unset peer SQs */
- if (hp->peer_gone)
- return;
- for (i = 0; i < hp->num_channels; i++)
- mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
- MLX5_SQC_STATE_RST, 0, 0);
+ if (!hp->peer_gone)
+ mlx5_hairpin_unpair_peer_sq(hp);
}
struct mlx5_hairpin *
mlx5_hairpin_destroy_queues(hp);
kfree(hp);
}
+
+void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp)
+{
+ int i;
+
+ mlx5_hairpin_unpair_peer_sq(hp);
+
+ /* destroy peer SQ */
+ for (i = 0; i < hp->num_channels; i++)
+ mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]);
+
+ hp->peer_gone = true;
+}
struct mlx5_hairpin_params *params);
void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair);
+void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp);
#endif /* __TRANSOBJ_H__ */
projects / kernel.git / commitdiff