diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-05 12:31:59 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-05 12:31:59 -0700 |
commit | 5518b69b76680a4f2df96b1deca260059db0c2de (patch) | |
tree | f33cd1519c8efb4590500f2f9617400be233238c /drivers/net/ethernet/mellanox/mlx5/core/health.c | |
parent | 8ad06e56dcbc1984ef0ff8f6e3c19982c5809f73 (diff) | |
parent | 0e72582270c07850b92cac351c8b97d4f9c123b9 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Reasonably busy this cycle, but perhaps not as busy as in the 4.12
merge window:
1) Several optimizations for UDP processing under high load from
Paolo Abeni.
2) Support pacing internally in TCP when using the sch_fq packet
scheduler for this is not practical. From Eric Dumazet.
3) Support mutliple filter chains per qdisc, from Jiri Pirko.
4) Move to 1ms TCP timestamp clock, from Eric Dumazet.
5) Add batch dequeueing to vhost_net, from Jason Wang.
6) Flesh out more completely SCTP checksum offload support, from
Davide Caratti.
7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
Neira Ayuso, and Matthias Schiffer.
8) Add devlink support to nfp driver, from Simon Horman.
9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
Prabhu.
10) Add stack depth tracking to BPF verifier and use this information
in the various eBPF JITs. From Alexei Starovoitov.
11) Support XDP on qed device VFs, from Yuval Mintz.
12) Introduce BPF PROG ID for better introspection of installed BPF
programs. From Martin KaFai Lau.
13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.
14) For loads, allow narrower accesses in bpf verifier checking, from
Yonghong Song.
15) Support MIPS in the BPF selftests and samples infrastructure, the
MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
Daney.
16) Support kernel based TLS, from Dave Watson and others.
17) Remove completely DST garbage collection, from Wei Wang.
18) Allow installing TCP MD5 rules using prefixes, from Ivan
Delalande.
19) Add XDP support to Intel i40e driver, from Björn Töpel
20) Add support for TC flower offload in nfp driver, from Simon
Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
Kicinski, and Bert van Leeuwen.
21) IPSEC offloading support in mlx5, from Ilan Tayari.
22) Add HW PTP support to macb driver, from Rafal Ozieblo.
23) Networking refcount_t conversions, From Elena Reshetova.
24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
for tuning the TCP sockopt settings of a group of applications,
currently via CGROUPs"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
cxgb4: Support for get_ts_info ethtool method
cxgb4: Add PTP Hardware Clock (PHC) support
cxgb4: time stamping interface for PTP
nfp: default to chained metadata prepend format
nfp: remove legacy MAC address lookup
nfp: improve order of interfaces in breakout mode
net: macb: remove extraneous return when MACB_EXT_DESC is defined
bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
bpf: fix return in load_bpf_file
mpls: fix rtm policy in mpls_getroute
net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
...
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/health.c')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/health.c | 51 |
1 files changed, 37 insertions, 14 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index f27f84ffbc85..4b6b03d6297f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -67,6 +67,7 @@ enum { enum { MLX5_DROP_NEW_HEALTH_WORK, + MLX5_DROP_NEW_RECOVERY_WORK, }; static u8 get_nic_state(struct mlx5_core_dev *dev) @@ -111,14 +112,14 @@ static int in_fatal(struct mlx5_core_dev *dev) return 0; } -void mlx5_enter_error_state(struct mlx5_core_dev *dev) +void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) { mutex_lock(&dev->intf_state_mutex); if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) goto unlock; mlx5_core_err(dev, "start\n"); - if (pci_channel_offline(dev->pdev) || in_fatal(dev)) { + if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) { dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; trigger_cmd_completions(dev); } @@ -185,6 +186,7 @@ static void health_care(struct work_struct *work) struct mlx5_core_health *health; struct mlx5_core_dev *dev; struct mlx5_priv *priv; + unsigned long flags; health = container_of(work, struct mlx5_core_health, work); priv = container_of(health, struct mlx5_priv, health); @@ -192,13 +194,13 @@ static void health_care(struct work_struct *work) mlx5_core_warn(dev, "handling bad device here\n"); mlx5_handle_bad_state(dev); - spin_lock(&health->wq_lock); - if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) + spin_lock_irqsave(&health->wq_lock, flags); + if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags)) schedule_delayed_work(&health->recover_work, recover_delay); else dev_err(&dev->pdev->dev, "new health works are not permitted at this stage\n"); - spin_unlock(&health->wq_lock); + spin_unlock_irqrestore(&health->wq_lock, flags); } static const char *hsynd_str(u8 synd) @@ -269,6 +271,20 @@ static unsigned long get_next_poll_jiffies(void) return next; } +void mlx5_trigger_health_work(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + unsigned long flags; + + spin_lock_irqsave(&health->wq_lock, flags); + if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) + queue_work(health->wq, &health->work); + else + dev_err(&dev->pdev->dev, + "new health works are not permitted at this stage\n"); + spin_unlock_irqrestore(&health->wq_lock, flags); +} + static void poll_health(unsigned long data) { struct mlx5_core_dev *dev = (struct mlx5_core_dev *)data; @@ -293,13 +309,7 @@ static void poll_health(unsigned long data) if (in_fatal(dev) && !health->sick) { health->sick = true; print_health_info(dev); - spin_lock(&health->wq_lock); - if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) - queue_work(health->wq, &health->work); - else - dev_err(&dev->pdev->dev, - "new health works are not permitted at this stage\n"); - spin_unlock(&health->wq_lock); + mlx5_trigger_health_work(dev); } out: @@ -313,6 +323,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) init_timer(&health->timer); health->sick = 0; clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -332,14 +343,26 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev) void mlx5_drain_health_wq(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; + unsigned long flags; - spin_lock(&health->wq_lock); + spin_lock_irqsave(&health->wq_lock, flags); set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); - spin_unlock(&health->wq_lock); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock_irqrestore(&health->wq_lock, flags); cancel_delayed_work_sync(&health->recover_work); cancel_work_sync(&health->work); } +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + + spin_lock(&health->wq_lock); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock(&health->wq_lock); + cancel_delayed_work_sync(&dev->priv.health.recover_work); +} + void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; |