public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: stable@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>,
	"David S . Miller" <davem@davemloft.net>,
	Sasha Levin <sashal@kernel.org>
Subject: [PATCH AUTOSEL 4.14 52/61] nfp: avoid soft lockups under control message storm
Date: Tue, 16 Oct 2018 00:13:54 -0400	[thread overview]
Message-ID: <20181016041403.135678-52-sashal@kernel.org> (raw)
In-Reply-To: <20181016041403.135678-1-sashal@kernel.org>

From: Jakub Kicinski <jakub.kicinski@netronome.com>

[ Upstream commit ff58e2df62ce29d0552278c290ae494b30fe0c6f ]

When FW floods the driver with control messages try to exit the cmsg
processing loop every now and then to avoid soft lockups.  Cmsg
processing is generally very lightweight so 512 seems like a reasonable
budget, which should not be exceeded under normal conditions.

Fixes: 77ece8d5f196 ("nfp: add control vNIC datapath")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Tested-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 56751990bcee..6df2c8b2ce6f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2058,14 +2058,17 @@ nfp_ctrl_rx_one(struct nfp_net *nn, struct nfp_net_dp *dp,
 	return true;
 }
 
-static void nfp_ctrl_rx(struct nfp_net_r_vector *r_vec)
+static bool nfp_ctrl_rx(struct nfp_net_r_vector *r_vec)
 {
 	struct nfp_net_rx_ring *rx_ring = r_vec->rx_ring;
 	struct nfp_net *nn = r_vec->nfp_net;
 	struct nfp_net_dp *dp = &nn->dp;
+	unsigned int budget = 512;
 
-	while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring))
+	while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring) && budget--)
 		continue;
+
+	return budget;
 }
 
 static void nfp_ctrl_poll(unsigned long arg)
@@ -2077,9 +2080,13 @@ static void nfp_ctrl_poll(unsigned long arg)
 	__nfp_ctrl_tx_queued(r_vec);
 	spin_unlock_bh(&r_vec->lock);
 
-	nfp_ctrl_rx(r_vec);
-
-	nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
+	if (nfp_ctrl_rx(r_vec)) {
+		nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
+	} else {
+		tasklet_schedule(&r_vec->tasklet);
+		nn_dp_warn(&r_vec->nfp_net->dp,
+			   "control message budget exceeded!\n");
+	}
 }
 
 /* Setup and Configuration
-- 
2.17.1


  parent reply	other threads:[~2018-10-16  4:14 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-16  4:13 [PATCH AUTOSEL 4.14 01/61] xfrm: Validate address prefix lengths in the xfrm selector Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 02/61] xfrm6: call kfree_skb when skb is toobig Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 03/61] xfrm: reset transport header back to network header after all input transforms ahave been applied Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 04/61] xfrm: reset crypto_done when iterating over multiple input xfrms Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 05/61] mac80211: Always report TX status Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 06/61] cfg80211: reg: Init wiphy_idx in regulatory_hint_core() Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 07/61] mac80211: fix pending queue hang due to TX_DROP Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 08/61] cfg80211: Address some corner cases in scan result channel updating Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 09/61] mac80211: TDLS: fix skb queue/priority assignment Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 10/61] mac80211: fix TX status reporting for ieee80211s Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 11/61] xfrm: Fix NULL pointer dereference when skb_dst_force clears the dst_entry Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 12/61] ARM: 8799/1: mm: fix pci_ioremap_io() offset check Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 13/61] xfrm: validate template mode Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 14/61] netfilter: bridge: Don't sabotage nf_hook calls from an l3mdev Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 15/61] arm64: hugetlb: Fix handling of young ptes Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 16/61] ARM: dts: BCM63xx: Fix incorrect interrupt specifiers Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 17/61] net: macb: Clean 64b dma addresses if they are not detected Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 18/61] net: hns: fix for unmapping problem when SMMU is on Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 19/61] soc: fsl: qbman: qman: avoid allocating from non existing gen_pool Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 20/61] soc: fsl: qe: Fix copy/paste bug in ucc_get_tdm_sync_shift() Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 21/61] nl80211: Fix possible Spectre-v1 for NL80211_TXRATE_HT Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 22/61] mac80211_hwsim: do not omit multicast announce of first added radio Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 23/61] Bluetooth: SMP: fix crash in unpairing Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 24/61] pxa168fb: prepare the clock Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 25/61] qed: Avoid implicit enum conversion in qed_set_tunn_cls_info Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 26/61] qed: Fix mask parameter in qed_vf_prep_tunn_req_tlv Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 27/61] qed: Avoid implicit enum conversion in qed_roce_mode_to_flavor Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 28/61] bonding: pass link-local packets to bonding master also Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 29/61] bonding: avoid possible dead-lock Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 30/61] qed: Avoid constant logical operation warning in qed_vf_pf_acquire Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 31/61] qed: Avoid implicit enum conversion in qed_iwarp_parse_rx_pkt Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 32/61] bnxt_en: Fix TX timeout during netpoll Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 33/61] nl80211: Fix possible Spectre-v1 for CQM RSSI thresholds Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 34/61] asix: Check for supported Wake-on-LAN modes Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 35/61] ax88179_178a: " Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 36/61] lan78xx: " Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 37/61] sr9800: " Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 38/61] r8152: Check for supported Wake-on-LAN Modes Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 39/61] smsc75xx: Check for Wake-on-LAN modes Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 40/61] smsc95xx: " Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 41/61] qlcnic: fix Tx descriptor corruption on 82xx devices Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 42/61] i2c: i2c-scmi: fix for i2c_smbus_write_block_data Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 43/61] cfg80211: fix use-after-free in reg_process_hint() Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 44/61] net/mlx5: E-Switch, Fix out of bound access when setting vport rate Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 45/61] net/mlx5e: Set vlan masks for all offloaded TC rules Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 46/61] perf/core: Fix perf_pmu_unregister() locking Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 47/61] perf/ring_buffer: Prevent concurent ring buffer access Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 48/61] perf/x86/intel/uncore: Fix PCI BDF address of M3UPI on SKX Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 49/61] perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 50/61] net: fec: fix rare tx timeout Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 51/61] declance: Fix continuation with the adapter identification message Sasha Levin
2018-10-16  4:13 ` Sasha Levin [this message]
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 53/61] bonding: fix warning message Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 54/61] net: qualcomm: rmnet: Skip processing loopback packets Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 55/61] locking/ww_mutex: Fix runtime warning in the WW mutex selftest Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 56/61] net/usb: cancel pending work when unbinding smsc75xx Sasha Levin
2018-10-16  4:13 ` [PATCH AUTOSEL 4.14 57/61] be2net: don't flip hw_features when VXLANs are added/deleted Sasha Levin
2018-10-16  4:14 ` [PATCH AUTOSEL 4.14 58/61] net: cxgb3_main: fix a missing-check bug Sasha Levin
2018-10-16  4:14 ` [PATCH AUTOSEL 4.14 59/61] yam: " Sasha Levin
2018-10-16  4:14 ` [PATCH AUTOSEL 4.14 60/61] ocfs2: fix crash in ocfs2_duplicate_clusters_by_page() Sasha Levin
2018-10-16  4:14 ` [PATCH AUTOSEL 4.14 61/61] mm/vmstat.c: fix outdated vmstat_text Sasha Levin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20181016041403.135678-52-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=davem@davemloft.net \
    --cc=jakub.kicinski@netronome.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox