linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Moshe Shemesh <moshe@mellanox.com>,
	Tariq Toukan <tariqt@mellanox.com>,
	Saeed Mahameed <saeedm@mellanox.com>
Subject: [PATCH 4.19 21/42] net/mlx5e: RX, verify received packet size in Linear Striding RQ
Date: Wed, 21 Nov 2018 20:05:57 +0100	[thread overview]
Message-ID: <20181121183148.934564642@linuxfoundation.org> (raw)
In-Reply-To: <20181121183147.869199006@linuxfoundation.org>

4.19-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Moshe Shemesh <moshe@mellanox.com>

[ Upstream commit 0073c8f72736b423aade8a817587a5f3e4df4ad8 ]

In case of striding RQ, we use  MPWRQ (Multi Packet WQE RQ), which means
that WQE (RX descriptor) can be used for many packets and so the WQE is
much bigger than MTU.  In virtualization setups where the port mtu can
be larger than the vf mtu, if received packet is bigger than MTU, it
won't be dropped by HW on too small receive WQE. If we use linear SKB in
striding RQ, since each stride has room for mtu size payload and skb
info, an oversized packet can lead to crash for crossing allocated page
boundary upon the call to build_skb. So driver needs to check packet
size and drop it.

Introduce new SW rx counter, rx_oversize_pkts_sw_drop, which counts the
number of packets dropped by the driver for being too large.

As a new field is added to the RQ struct, re-open the channels whenever
this field is being used in datapath (i.e., in the case of linear
Striding RQ).

Fixes: 619a8f2a42f1 ("net/mlx5e: Use linear SKB in Striding RQ")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |    1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |    4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |    6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |    3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |    2 ++
 5 files changed, 15 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -566,6 +566,7 @@ struct mlx5e_rq {
 
 	unsigned long          state;
 	int                    ix;
+	unsigned int           hw_mtu;
 
 	struct net_dim         dim; /* Dynamic Interrupt Moderation */
 
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -492,6 +492,7 @@ static int mlx5e_alloc_rq(struct mlx5e_c
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
+	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats   = &c->priv->channel_stats[c->ix].rq;
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
@@ -3758,10 +3759,11 @@ int mlx5e_change_mtu(struct net_device *
 	}
 
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+		bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, &new_channels.params);
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
 
-		reset = reset && (ppw_old != ppw_new);
+		reset = reset && (is_linear || (ppw_old != ppw_new));
 	}
 
 	if (!reset) {
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1064,6 +1064,12 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct m
 	u32 frag_size;
 	bool consumed;
 
+	/* Check packet size. Note LRO doesn't use linear SKB */
+	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
+		rq->stats->oversize_pkts_sw_drop++;
+		return NULL;
+	}
+
 	va             = page_address(di->page) + head_offset;
 	data           = va + rx_headroom;
 	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -82,6 +82,7 @@ static const struct counter_desc sw_stat
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_oversize_pkts_sw_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
@@ -158,6 +159,7 @@ void mlx5e_grp_sw_update_stats(struct ml
 		s->rx_wqe_err   += rq_stats->wqe_err;
 		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
 		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
+		s->rx_oversize_pkts_sw_drop += rq_stats->oversize_pkts_sw_drop;
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
@@ -1148,6 +1150,7 @@ static const struct counter_desc rq_stat
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, oversize_pkts_sw_drop) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -95,6 +95,7 @@ struct mlx5e_sw_stats {
 	u64 rx_wqe_err;
 	u64 rx_mpwqe_filler_cqes;
 	u64 rx_mpwqe_filler_strides;
+	u64 rx_oversize_pkts_sw_drop;
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
@@ -190,6 +191,7 @@ struct mlx5e_rq_stats {
 	u64 wqe_err;
 	u64 mpwqe_filler_cqes;
 	u64 mpwqe_filler_strides;
+	u64 oversize_pkts_sw_drop;
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;



  parent reply	other threads:[~2018-11-21 19:07 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-21 19:05 [PATCH 4.19 00/42] 4.19.4-stable review Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 01/42] flow_dissector: do not dissect l4 ports for fragments Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 02/42] ibmvnic: fix accelerated VLAN handling Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 03/42] ip_tunnel: dont force DF when MTU is locked Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 04/42] ipv6: fix a dst leak when removing its exception Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 05/42] ipv6: Fix PMTU updates for UDP/raw sockets in presence of VRF Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 06/42] net: bcmgenet: protect stop from timeout Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 07/42] net-gro: reset skb->pkt_type in napi_reuse_skb() Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 08/42] sctp: not allow to set asoc prsctp_enable by sockopt Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 09/42] tcp: Fix SOF_TIMESTAMPING_RX_HARDWARE to use the latest timestamp during TCP coalescing Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 10/42] tg3: Add PHY reset for 5717/5719/5720 in change ring and flow control paths Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 11/42] tipc: dont assume linear buffer when reading ancillary data Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 12/42] tipc: fix lockdep warning when reinitilaizing sockets Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 13/42] tuntap: fix multiqueue rx Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 14/42] net: systemport: Protect stop from timeout Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 15/42] net/sched: act_pedit: fix memory leak when IDR allocation fails Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 16/42] net: sched: cls_flower: validate nested enc_opts_policy to avoid warning Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 17/42] tipc: fix link re-establish failure Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 18/42] net/mlx5e: Dont match on vlan non-existence if ethertype is wildcarded Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 19/42] net/mlx5e: Claim TC hw offloads support only under a proper build config Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 20/42] net/mlx5e: Adjust to max number of channles when re-attaching Greg Kroah-Hartman
2018-11-21 19:05 ` Greg Kroah-Hartman [this message]
2018-11-21 19:05 ` [PATCH 4.19 22/42] Revert "sctp: remove sctp_transport_pmtu_check" Greg Kroah-Hartman
2018-11-21 19:05 ` [PATCH 4.19 23/42] net/mlx5e: Always use the match level enum when parsing TC rule match Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 24/42] net/mlx5e: Fix selftest for small MTUs Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 25/42] net/mlx5e: Removed unnecessary warnings in FEC caps query Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 26/42] inet: frags: better deal with smp races Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 27/42] l2tp: fix a sock refcnt leak in l2tp_tunnel_register Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 28/42] net/mlx5: IPSec, Fix the SA context hash key Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 29/42] net/mlx5e: IPoIB, Reset QP after channels are closed Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 30/42] net: dsa: mv88e6xxx: Fix clearing of stats counters Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 31/42] net: phy: realtek: fix RTL8201F sysfs name Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 32/42] sctp: define SCTP_SS_DEFAULT for Stream schedulers Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 33/42] net: qualcomm: rmnet: Fix incorrect assignment of real_dev Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 34/42] net: dsa: microchip: initialize mutex before use Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 35/42] sctp: fix strchange_flags name for Stream Change Event Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 36/42] net: phy: mdio-gpio: Fix working over slow can_sleep GPIOs Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 37/42] sctp: not increase streams incnt before sending addstrm_in request Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 38/42] mlxsw: spectrum: Fix IP2ME CPU policer configuration Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 39/42] net: smsc95xx: Fix MTU range Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 40/42] rxrpc: Fix lockup due to no error backoff after ack transmit error Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 41/42] usbnet: smsc95xx: disable carrier check while suspending Greg Kroah-Hartman
2018-11-21 19:06 ` [PATCH 4.19 42/42] Revert "x86/speculation: Enable cross-hyperthread spectre v2 STIBP mitigation" Greg Kroah-Hartman
2018-11-22  5:26 ` [PATCH 4.19 00/42] 4.19.4-stable review kernelci.org bot
2018-11-22  7:15 ` Harsh Shandilya
2018-11-22  8:24   ` Greg Kroah-Hartman
2018-11-22 16:36 ` Guenter Roeck
2018-11-23  7:16   ` Greg Kroah-Hartman
2018-11-22 20:53 ` Thomas Voegtle
2018-11-22 22:01   ` Thomas Voegtle
2018-11-22 22:30     ` Guenter Roeck
2018-11-23  6:52       ` Greg Kroah-Hartman
2018-11-23  7:45       ` Greg Kroah-Hartman
2018-11-23 12:06         ` Guenter Roeck
2018-11-23  6:51   ` Greg Kroah-Hartman
2018-11-23 15:40     ` Thomas Voegtle
2018-11-23 15:44       ` David Laight
2018-11-23  8:13 ` Naresh Kamboju

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=20181121183148.934564642@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=moshe@mellanox.com \
    --cc=saeedm@mellanox.com \
    --cc=stable@vger.kernel.org \
    --cc=tariqt@mellanox.com \
    /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;
as well as URLs for NNTP newsgroup(s).