From 96439889b40b83b487fa08637dcc74b1243362af Mon Sep 17 00:00:00 2001 From: Fred Lotter Date: Tue, 15 Jan 2019 19:06:51 -0800 Subject: [PATCH] nfp: flower: increase cmesg reply timeout QA tests report occasional timeouts on REIFY message replies. Profiling of the two cmesg reply types under burst conditions, with a 12-core host under heavy cpu and io load (stress --cpu 12 --io 12), show both PHY MTU change and REIFY replies can exceed the 10ms timeout. The maximum MTU reply wait under burst is 16ms, while the maximum REIFY wait under 40 VF burst is 12ms. Using a 4 VF REIFY burst results in an 8ms maximum wait. A larger VF burst does increase the delay, but not in a linear enough way to justify a scaled REIFY delay. The worse case values between MTU and REIFY appears close enough to justify a common timeout. Pick a conservative 40ms to make a safer future proof common reply timeout. The delay only effects the failure case. Change the REIFY timeout mechanism to use wait_event_timeout() instead of wait_event_interruptible_timeout(), to match the MTU code. In the current implementation, theoretically, a signal could interrupt the REIFY waiting period, with a return code of ERESTARTSYS. However, this is caught under the general timeout error code EIO. I cannot see the benefit of exposing the REIFY waiting period to signals with such a short delay (40ms), while the MTU mechnism does not use the same logic. In the absence of any reply (wakeup() call), both reply types will wake up the task after the timeout period. The REIFY timeout applies to the entire representor group being instantiated (e.g. VFs), while the MTU timeout apples to a single PHY MTU change. Signed-off-by: Fred Lotter Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/cmsg.c | 2 +- .../net/ethernet/netronome/nfp/flower/cmsg.h | 3 +++ .../net/ethernet/netronome/nfp/flower/main.c | 18 +++++++----------- 3 files changed, 11 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index 4c5eaf36d5bb..56b22ea32474 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -203,7 +203,7 @@ nfp_flower_cmsg_portreify_rx(struct nfp_app *app, struct sk_buff *skb) } atomic_inc(&priv->reify_replies); - wake_up_interruptible(&priv->reify_wait_queue); + wake_up(&priv->reify_wait_queue); } static void diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 15f41cfef9f1..4fcaf11ed56e 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -97,6 +97,9 @@ #define NFP_FLOWER_WORKQ_MAX_SKBS 30000 +/* Cmesg reply (empirical) timeout*/ +#define NFP_FL_REPLY_TIMEOUT msecs_to_jiffies(40) + #define nfp_flower_cmsg_warn(app, fmt, args...) \ do { \ if (net_ratelimit()) \ diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 5059110a1768..8ce20bd38965 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -107,16 +107,14 @@ static int nfp_flower_wait_repr_reify(struct nfp_app *app, atomic_t *replies, int tot_repl) { struct nfp_flower_priv *priv = app->priv; - int err; if (!tot_repl) return 0; lockdep_assert_held(&app->pf->lock); - err = wait_event_interruptible_timeout(priv->reify_wait_queue, - atomic_read(replies) >= tot_repl, - msecs_to_jiffies(10)); - if (err <= 0) { + if (!wait_event_timeout(priv->reify_wait_queue, + atomic_read(replies) >= tot_repl, + NFP_FL_REPLY_TIMEOUT)) { nfp_warn(app->cpp, "Not all reprs responded to reify\n"); return -EIO; } @@ -601,7 +599,7 @@ nfp_flower_repr_change_mtu(struct nfp_app *app, struct net_device *netdev, { struct nfp_flower_priv *app_priv = app->priv; struct nfp_repr *repr = netdev_priv(netdev); - int err, ack; + int err; /* Only need to config FW for physical port MTU change. */ if (repr->port->type != NFP_PORT_PHYS_PORT) @@ -628,11 +626,9 @@ nfp_flower_repr_change_mtu(struct nfp_app *app, struct net_device *netdev, } /* Wait for fw to ack the change. */ - ack = wait_event_timeout(app_priv->mtu_conf.wait_q, - nfp_flower_check_ack(app_priv), - msecs_to_jiffies(10)); - - if (!ack) { + if (!wait_event_timeout(app_priv->mtu_conf.wait_q, + nfp_flower_check_ack(app_priv), + NFP_FL_REPLY_TIMEOUT)) { spin_lock_bh(&app_priv->mtu_conf.lock); app_priv->mtu_conf.requested_val = 0; spin_unlock_bh(&app_priv->mtu_conf.lock);