* [RFC PATCH net-next 5/5] selftests: mlxsw: Add a test case for devlink-trap
From: Ido Schimmel @ 2019-07-07 8:03 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707080336.3794-1-idosch@idosch.org>
From: Ido Schimmel <idosch@mellanox.com>
Test generic devlink-trap functionality over mlxsw. These tests are not
specific to a single trap, but do not check the devlink-trap common
infrastructure either.
Currently, the only test case is device deletion (by reloading the
driver) while packets are being trapped.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
---
.../drivers/net/mlxsw/devlink_trap.sh | 130 ++++++++++++++++++
1 file changed, 130 insertions(+)
create mode 100755 tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
new file mode 100755
index 000000000000..8e1d0dc44256
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
@@ -0,0 +1,130 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test generic devlink-trap functionality over mlxsw. These tests are not
+# specific to a single trap, but do not check the devlink-trap common
+# infrastructure either.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ dev_del_test
+"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1
+}
+
+h2_create()
+{
+ simple_if_init $h2
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2
+}
+
+switch_create()
+{
+ ip link add dev br0 type bridge vlan_filtering 1 mcast_snooping 0
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+}
+
+switch_destroy()
+{
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+
+ ip link del dev br0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+dev_del_test()
+{
+ local trap_name="source_mac_is_multicast"
+ local smac=01:02:03:04:05:06
+ local num_iter=5
+ local mz_pid
+ local i
+
+ $MZ $h1 -c 0 -p 100 -a $smac -b bcast -t ip -q &
+ mz_pid=$!
+
+ # The purpose of this test is to make sure we correctly dismantle a
+ # port while packets are trapped from it. This is done by reloading the
+ # the driver while the 'ingress_smac_mc_drop' trap is triggered.
+ RET=0
+
+ for i in $(seq 1 $num_iter); do
+ log_info "Iteration $i / $num_iter"
+
+ devlink_trap_action_set $trap_name "trap"
+ devlink_trap_report_set $trap_name "true"
+ sleep 1
+
+ devlink_reload
+ # Allow netdevices to be re-created following the reload
+ sleep 20
+
+ cleanup
+ setup_prepare
+ setup_wait
+ done
+
+ log_test "Device delete"
+
+ kill $mz_pid && wait $mz_pid &> /dev/null
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
--
2.20.1
^ permalink raw reply related
* pull request: bluetooth-next 2019-07-07
From: Johan Hedberg @ 2019-07-07 8:07 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-bluetooth
[-- Attachment #1: Type: text/plain, Size: 6074 bytes --]
Hi Dave,
Here's the main bluetooth-next pull request for 5.3:
- Added support for new devices from Qualcomm, Realtek and Broadcom and
MediaTek
- Various fixes to 6LoWPAN
- Fix L2CAP PSM namespace separation for LE & BR/EDR
- Fix behavior with Microsoft Surface Precision Mouse
- Added support for LE Ping feature
- Fix L2CAP Disconnect response handling if received in wrong state
Please let me know if there are any issues pulling. Thanks.
Johan
---
The following changes since commit 23f30c41c732fe9800f4a2d545b37c9515d35ad6:
Merge branch 'mlx5-TLS-TX-HW-offload-support' (2019-07-05 16:42:00 -0700)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git for-upstream
for you to fetch changes up to 9ce67c3235be71e8cf922a9b3d0b7359ed3f4ce5:
Bluetooth: btusb: Add protocol support for MediaTek MT7663U USB devices (2019-07-06 21:44:25 +0200)
----------------------------------------------------------------
Balakrishna Godavarthi (1):
Bluetooth: btqca: inject command complete event during fw download
Dan Carpenter (1):
Bluetooth: hidp: NUL terminate a string in the compat ioctl
Fabian Schindlatz (2):
Bluetooth: hci_ll: Refactor download_firmware
Bluetooth: Cleanup formatting and coding style
Greg Kroah-Hartman (1):
6lowpan: no need to check return value of debugfs_create functions
Jian-Hong Pan (1):
Bluetooth: btrtl: HCI reset on close for Realtek BT chip
Josua Mayer (3):
Bluetooth: 6lowpan: search for destination address in all peers
Bluetooth: 6lowpan: check neighbour table for SLAAC
Bluetooth: 6lowpan: always check destination address
João Paulo Rechi Vita (2):
Bluetooth: Add new 13d3:3501 QCA_ROME device
Bluetooth: Add new 13d3:3491 QCA_ROME device
Larry Finger (1):
Bluetooth:: btrtl: Add support for RTL8723DU
Luiz Augusto von Dentz (2):
Bluetooth: Use controller sets when available
Bluetooth: L2CAP: Check bearer type on __l2cap_global_chan_by_addr
Matias Karhumaa (1):
Bluetooth: Check state in l2cap_disconnect_rsp
Matthias Kaehlcke (1):
Bluetooth: hci_qca: wcn3990: Drop baudrate change vendor event
Neil Armstrong (1):
Bluetooth: btbcm: Add entry for BCM4359C0 UART bluetooth
Peter Robinson (1):
Bluetooth: btsdio: Do not bind to non-removable BCM4356
Philipp Puschmann (1):
Bluetooth: hci_ll: set operational frequency earlier
Rocky Liao (2):
Bluetooth: hci_qca: Load customized NVM based on the device property
dt-bindings: net: bluetooth: Add device property firmware-name for QCA6174
Sascha Hauer (3):
Bluetooth: hci_ldisc: Add function to wait for characters to be sent
Bluetooth: hci_mrvl: Wait for final ack before switching baudrate
Bluetooth: hci_mrvl: Add serdev support
Sean Wang (6):
dt-bindings: net: bluetooth: add boot-gpios property to UART-based device
dt-bindings: net: bluetooth: add clock property to UART-based device
Bluetooth: btmtkuart: add an implementation for boot-gpios property
Bluetooth: btmtkuart: add an implementation for clock osc property
Bluetooth: btusb: Add protocol support for MediaTek MT7668U USB devices
Bluetooth: btusb: Add protocol support for MediaTek MT7663U USB devices
Spoorthi Ravishankar Koppad (1):
Bluetooth: Add support for LE ping feature
Szymon Janc (1):
Bluetooth: Add SMP workaround Microsoft Surface Precision Mouse bug
Tomas Bortoli (1):
Bluetooth: hci_bcsp: Fix memory leak in rx_skb
csonsino (1):
Bluetooth: validate BLE connection interval updates
.../devicetree/bindings/net/marvell-bluetooth.txt | 25 +
.../devicetree/bindings/net/mediatek-bluetooth.txt | 17 +
.../devicetree/bindings/net/qualcomm-bluetooth.txt | 4 +
drivers/bluetooth/Kconfig | 12 +
drivers/bluetooth/bpa10x.c | 3 +-
drivers/bluetooth/btbcm.c | 1 +
drivers/bluetooth/btmtkuart.c | 51 +-
drivers/bluetooth/btqca.c | 47 +-
drivers/bluetooth/btqca.h | 10 +-
drivers/bluetooth/btrtl.c | 28 +
drivers/bluetooth/btrtl.h | 6 +
drivers/bluetooth/btsdio.c | 1 +
drivers/bluetooth/btusb.c | 584 +++++++++++++++++++++
drivers/bluetooth/hci_bcsp.c | 5 +
drivers/bluetooth/hci_ldisc.c | 8 +
drivers/bluetooth/hci_ll.c | 109 ++--
drivers/bluetooth/hci_mrvl.c | 72 ++-
drivers/bluetooth/hci_qca.c | 73 ++-
drivers/bluetooth/hci_uart.h | 1 +
include/net/bluetooth/hci.h | 20 +
include/net/bluetooth/hci_core.h | 4 +
net/6lowpan/6lowpan_i.h | 16 +-
net/6lowpan/core.c | 8 +-
net/6lowpan/debugfs.c | 97 +---
net/bluetooth/6lowpan.c | 41 +-
net/bluetooth/hci_conn.c | 5 +-
net/bluetooth/hci_core.c | 4 +-
net/bluetooth/hci_debugfs.c | 31 ++
net/bluetooth/hci_event.c | 77 +++
net/bluetooth/hci_request.c | 40 +-
net/bluetooth/hci_request.h | 2 +-
net/bluetooth/hidp/core.c | 2 +-
net/bluetooth/hidp/sock.c | 1 +
net/bluetooth/l2cap_core.c | 29 +-
net/bluetooth/smp.c | 13 +
35 files changed, 1266 insertions(+), 181 deletions(-)
create mode 100644 Documentation/devicetree/bindings/net/marvell-bluetooth.txt
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Re: [PATCH net-next 00/11] Add drop monitor for offloaded data paths
From: Ido Schimmel @ 2019-07-07 8:15 UTC (permalink / raw)
To: netdev
Cc: davem, jiri, mlxsw, dsahern, roopa, nikolay, andy, pablo,
jakub.kicinski, pieter.jansenvanvuuren, andrew, f.fainelli,
vivien.didelot, Ido Schimmel
In-Reply-To: <20190707075828.3315-1-idosch@idosch.org>
More info that I did not want to put in the cover letter:
Wrote a Wireshark dissector [1] for devlink packets. It dissects various
devlink packets and is especially useful for trap report packets. Both
the metadata about the trapped packet (e.g., trap reason) and also the
trapped Ethernet packet itself are dissected and displayed. Example [6].
Will submit it after the kernel infrastructure is accepted.
Jiri wrote devlink_exporter [2] for Prometheus [3]. This allows one to
export trap statistics as metrics to Prometheus. Eventually, this should
be integrated into node_exporter [4]. We also experimented with
Cloudflare's ebpf_exporter [5], which allows for more fine-grained
statistics (e.g., number of drops per {5-tuple, drop reason}).
I imagine that Wireshark will be mainly used by kernel engineers that
need to pinpoint a specific problem, whereas Prometheus (and similar
time series databases) will be used by network engineers that need to
monitor the network 24x7.
[1] https://github.com/idosch/wireshark/blob/devlink/epan/dissectors/packet-netlink-devlink.c
[2] https://github.com/jpirko/prometheus-devlink-exporter/blob/master/devlink-exporter.py
[3] https://prometheus.io/
[4] https://github.com/prometheus/node_exporter
[5] https://blog.cloudflare.com/introducing-ebpf_exporter/
[6]
Linux netlink (cooked header)
Link-layer address type: Netlink (824)
Family: Generic (0x0010)
Linux Generic Netlink protocol
Netlink message header (type: 0x0013)
Length: 224
Family ID: 0x13 (devlink)
Flags: 0x0000
.... .... .... ...0 = Request: 0
.... .... .... ..0. = Multipart message: 0
.... .... .... .0.. = Ack: 0
.... .... .... 0... = Echo: 0
.... .... ...0 .... = Dump inconsistent: 0
.... .... ..0. .... = Dump filtered: 0
Sequence: 0
Port ID: 0
Command: Trap report (65)
Family Version: 1
Reserved
Linux devlink (device netlink) protocol
Attribute: Bus name: pci
Len: 8
Type: 0x0001, Bus name (1)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Bus name (1)
Bus name: pci
Attribute: Device name: 0000:01:00.0
Len: 17
Type: 0x0002, Device name (2)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Device name (2)
Device name: 0000:01:00.0
Attribute: Trap group name: l2_drops
Len: 13
Type: 0x0089, Trap group name (137)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Trap group name (137)
Trap group name: l2_drops
Attribute: Trap name: source_mac_is_multicast
Len: 28
Type: 0x0080, Trap name (128)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Trap name (128)
Trap name: source_mac_is_multicast
Attribute: Trap type
Len: 5
Type: 0x0083, Trap type (131)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Trap type (131)
Trap type: Drop (0)
Attribute: Trap timestamp
Len: 20
Type: 0x0086, Trap timestamp (134)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Trap timestamp (134)
Trap timestamp: Jul 6, 2019 18:16:11.396492223 IDT
Attribute: Trap input port
Len: 40
Type: 0x8087, Nested, Trap input port (135)
1... .... .... .... = Nested: 1
.0.. .... .... .... = Network byte order: 0
Attribute type: Unknown (32903)
Attribute: Port index: 17
Len: 8
Type: 0x0003, Port index (3)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Port index (3)
Port index: 17
Attribute: Port type
Len: 6
Type: 0x0004, Port type (4)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Port type (4)
Port type: Ethernet (2)
Attribute: Net device index: 133
Len: 8
Type: 0x0006, Net device index (6)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Net device index (6)
Port net device index: 133
Attribute: Net device name: swp3
Len: 9
Type: 0x0007, Net device name (7)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Net device name (7)
Port net device name: swp3
Attribute: Trap payload
Len: 64
Type: 0x0088, Trap payload (136)
0... .... .... .... = Nested: 0
.0.. .... .... .... = Network byte order: 0
Attribute type: Trap payload (136)
Ethernet II, Src: Woonsang_04:05:06 (01:02:03:04:05:06), Dst: Mellanox_ff:27:d1 (7c:fe:90:ff:27:d1)
Destination: Mellanox_ff:27:d1 (7c:fe:90:ff:27:d1)
Address: Mellanox_ff:27:d1 (7c:fe:90:ff:27:d1)
.... ..0. .... .... .... .... = LG bit: Globally unique address (factory default)
.... ...0 .... .... .... .... = IG bit: Individual address (unicast)
Source: Woonsang_04:05:06 (01:02:03:04:05:06)
[Expert Info (Warning/Protocol): Source MAC must not be a group address: IEEE 802.3-2002, Section 3.2.3(b)]
[Source MAC must not be a group address: IEEE 802.3-2002, Section 3.2.3(b)]
[Severity level: Warning]
[Group: Protocol]
Address: Woonsang_04:05:06 (01:02:03:04:05:06)
.... ..0. .... .... .... .... = LG bit: Globally unique address (factory default)
.... ...1 .... .... .... .... = IG bit: Group address (multicast/broadcast)
Type: IPv4 (0x0800)
Trailer: 000000000000000000000000000000000000000000000000…
Internet Protocol Version 4, Src: 192.0.2.1, Dst: 192.0.2.2
0100 .... = Version: 4
.... 0101 = Header Length: 20 bytes (5)
Differentiated Services Field: 0x00 (DSCP: CS0, ECN: Not-ECT)
0000 00.. = Differentiated Services Codepoint: Default (0)
.... ..00 = Explicit Congestion Notification: Not ECN-Capable Transport (0)
Total Length: 20
Identification: 0x0000 (0)
Flags: 0x0000
0... .... .... .... = Reserved bit: Not set
.0.. .... .... .... = Don't fragment: Not set
..0. .... .... .... = More fragments: Not set
...0 0000 0000 0000 = Fragment offset: 0
Time to live: 255
Protocol: IPv6 Hop-by-Hop Option (0)
Header checksum: 0x37e6 [validation disabled]
[Header checksum status: Unverified]
Source: 192.0.2.1
Destination: 192.0.2.2
^ permalink raw reply
* [PATCH net-next iproute2 0/3] net/sched: Introduce tc connection tracking
From: Paul Blakey @ 2019-07-07 8:53 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
Hi,
This patch series add connection tracking capabilities in tc.
It does so via a new tc action, called act_ct, and new tc flower classifier matching.
Act ct and relevant flower matches, are still under review in net-next mailing list.
Usage is as follows:
$ tc qdisc add dev ens1f0_0 ingress
$ tc qdisc add dev ens1f0_1 ingress
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 2
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_state +trk+new \
action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_0 ingress \
prio 1 chain 2 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 0 proto ip \
flower ip_proto tcp ct_state -trk \
action ct zone 2 pipe \
action goto chain 1
$ tc filter add dev ens1f0_1 ingress \
prio 1 chain 1 proto ip \
flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \
action ct nat pipe \
action mirred egress redirect dev ens1f0_0
Paul Blakey (3):
tc: add NLA_F_NESTED flag to all actions options nested block
tc: Introduce tc ct action
tc: flower: Add matching on conntrack info
include/uapi/linux/pkt_cls.h | 17 ++
include/uapi/linux/tc_act/tc_ct.h | 41 ++++
man/man8/tc-flower.8 | 35 +++
tc/Makefile | 1 +
tc/f_flower.c | 276 ++++++++++++++++++++-
tc/m_action.c | 3 +-
tc/m_ct.c | 497 ++++++++++++++++++++++++++++++++++++++
tc/tc_util.c | 44 ++++
tc/tc_util.h | 4 +
9 files changed, 916 insertions(+), 2 deletions(-)
create mode 100644 include/uapi/linux/tc_act/tc_ct.h
create mode 100644 tc/m_ct.c
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next iproute2 3/3] tc: flower: Add matching on conntrack info
From: Paul Blakey @ 2019-07-07 8:53 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562489628-5925-1-git-send-email-paulb@mellanox.com>
Matches on conntrack state, zone, mark, and label.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Roi Dayan <roid@mellanox.com>
---
include/uapi/linux/pkt_cls.h | 17 +++
man/man8/tc-flower.8 | 35 ++++++
tc/f_flower.c | 276 ++++++++++++++++++++++++++++++++++++++++++-
3 files changed, 327 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 8cc6b67..6992df1 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -106,6 +106,7 @@ enum tca_id {
TCA_ID_SAMPLE = TCA_ACT_SAMPLE,
/* other actions go here */
TCA_ID_CTINFO,
+ TCA_ID_CT,
__TCA_ID_MAX = 255
};
@@ -535,12 +536,28 @@ enum {
TCA_FLOWER_KEY_PORT_DST_MIN, /* be16 */
TCA_FLOWER_KEY_PORT_DST_MAX, /* be16 */
+ TCA_FLOWER_KEY_CT_STATE, /* u16 */
+ TCA_FLOWER_KEY_CT_STATE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_MARK, /* u32 */
+ TCA_FLOWER_KEY_CT_MARK_MASK, /* u32 */
+ TCA_FLOWER_KEY_CT_LABELS, /* u128 */
+ TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */
+
__TCA_FLOWER_MAX,
};
#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
enum {
+ TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */
+};
+
+enum {
TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
* TCA_FLOWER_KEY_ENC_OPT_GENEVE_
diff --git a/man/man8/tc-flower.8 b/man/man8/tc-flower.8
index adff41e..04ee194 100644
--- a/man/man8/tc-flower.8
+++ b/man/man8/tc-flower.8
@@ -289,6 +289,41 @@ bits is assumed.
.TQ
.BI enc_ttl " NUMBER"
.TQ
+.BR
+.TP
+.BI ct_state " CT_STATE"
+.TQ
+.BI ct_zone " CT_MASKED_ZONE"
+.TQ
+.BI ct_mark " CT_MASKED_MARK"
+.TQ
+.BI ct_label " CT_MASKED_LABEL"
+Matches on connection tracking info
+.RS
+.TP
+.I CT_STATE
+Match the connection state, and can ne combination of [{+|-}flag] flags, where flag can be one of
+.RS
+.TP
+trk - Tracked connection.
+.TP
+new - New connection.
+.TP
+est - Established connection.
+.TP
+Example: +trk+est
+.RE
+.TP
+.I CT_MASKED_ZONE
+Match the connection zone, and can be masked.
+.TP
+.I CT_MASKED_MARK
+32bit match on the connection mark, and can be masked.
+.TP
+.I CT_MASKED_LABEL
+128bit match on the connection label, and can be masked.
+.RE
+.TP
.BI geneve_opts " OPTIONS"
Match on IP tunnel metadata. Key id
.I NUMBER
diff --git a/tc/f_flower.c b/tc/f_flower.c
index 70d40d3..a2a2301 100644
--- a/tc/f_flower.c
+++ b/tc/f_flower.c
@@ -82,9 +82,14 @@ static void explain(void)
" enc_ttl MASKED-IP_TTL |\n"
" geneve_opts MASKED-OPTIONS |\n"
" ip_flags IP-FLAGS | \n"
- " enc_dst_port [ port_number ] }\n"
+ " enc_dst_port [ port_number ] |\n"
+ " ct_state MASKED_CT_STATE |\n"
+ " ct_label MASKED_CT_LABEL |\n"
+ " ct_mark MASKED_CT_MARK |\n"
+ " ct_zone MASKED_CT_ZONE }\n"
" FILTERID := X:Y:Z\n"
" MASKED_LLADDR := { LLADDR | LLADDR/MASK | LLADDR/BITS }\n"
+ " MASKED_CT_STATE := combination of {+|-} and flags trk,est,new\n"
" ACTION-SPEC := ... look at individual actions\n"
"\n"
"NOTE: CLASSID, IP-PROTO are parsed as hexadecimal input.\n"
@@ -214,6 +219,159 @@ static int flower_parse_matching_flags(char *str,
return 0;
}
+static int flower_parse_u16(char *str, int value_type, int mask_type,
+ struct nlmsghdr *n)
+{
+ __u16 value, mask;
+ char *slash;
+
+ slash = strchr(str, '/');
+ if (slash)
+ *slash = '\0';
+
+ if (get_u16(&value, str, 0))
+ return -1;
+
+ if (slash) {
+ if (get_u16(&mask, slash + 1, 0))
+ return -1;
+ } else {
+ mask = UINT16_MAX;
+ }
+
+ addattr16(n, MAX_MSG, value_type, value);
+ addattr16(n, MAX_MSG, mask_type, mask);
+
+ return 0;
+}
+
+static int flower_parse_u32(char *str, int value_type, int mask_type,
+ struct nlmsghdr *n)
+{
+ __u32 value, mask;
+ char *slash;
+
+ slash = strchr(str, '/');
+ if (slash)
+ *slash = '\0';
+
+ if (get_u32(&value, str, 0))
+ return -1;
+
+ if (slash) {
+ if (get_u32(&mask, slash + 1, 0))
+ return -1;
+ } else {
+ mask = UINT32_MAX;
+ }
+
+ addattr32(n, MAX_MSG, value_type, value);
+ addattr32(n, MAX_MSG, mask_type, mask);
+
+ return 0;
+}
+
+static int flower_parse_ct_mark(char *str, struct nlmsghdr *n)
+{
+ return flower_parse_u32(str,
+ TCA_FLOWER_KEY_CT_MARK,
+ TCA_FLOWER_KEY_CT_MARK_MASK,
+ n);
+}
+
+static int flower_parse_ct_zone(char *str, struct nlmsghdr *n)
+{
+ return flower_parse_u16(str,
+ TCA_FLOWER_KEY_CT_ZONE,
+ TCA_FLOWER_KEY_CT_ZONE_MASK,
+ n);
+}
+
+static int flower_parse_ct_labels(char *str, struct nlmsghdr *n)
+{
+#define LABELS_SIZE 16
+ uint8_t labels[LABELS_SIZE], lmask[LABELS_SIZE];
+ char *slash, *mask = NULL;
+ size_t slen, slen_mask = 0;
+
+ slash = index(str, '/');
+ if (slash) {
+ *slash = 0;
+ mask = slash + 1;
+ slen_mask = strlen(mask);
+ }
+
+ slen = strlen(str);
+ if (slen > LABELS_SIZE * 2 || slen_mask > LABELS_SIZE * 2) {
+ char errmsg[128];
+
+ snprintf(errmsg, sizeof(errmsg),
+ "%zd Max allowed size %d",
+ slen, LABELS_SIZE*2);
+ invarg(errmsg, str);
+ }
+
+ if (hex2mem(str, labels, slen / 2) < 0)
+ invarg("labels must be a hex string\n", str);
+ addattr_l(n, MAX_MSG, TCA_FLOWER_KEY_CT_LABELS, labels, slen / 2);
+
+ if (mask) {
+ if (hex2mem(mask, lmask, slen_mask / 2) < 0)
+ invarg("labels mask must be a hex string\n", mask);
+ } else {
+ memset(lmask, 0xff, sizeof(lmask));
+ slen_mask = sizeof(lmask) * 2;
+ }
+ addattr_l(n, MAX_MSG, TCA_FLOWER_KEY_CT_LABELS_MASK, lmask,
+ slen_mask / 2);
+
+ return 0;
+}
+
+static struct flower_ct_states {
+ char *str;
+ int flag;
+} flower_ct_states[] = {
+ { "trk", TCA_FLOWER_KEY_CT_FLAGS_TRACKED },
+ { "new", TCA_FLOWER_KEY_CT_FLAGS_NEW },
+ { "est", TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED },
+};
+
+static int flower_parse_ct_state(char *str, struct nlmsghdr *n)
+{
+ int flags = 0, mask = 0, len, i;
+ bool p;
+
+ while (*str != '\0') {
+ if (*str == '+')
+ p = true;
+ else if (*str == '-')
+ p = false;
+ else
+ return -1;
+
+ for (i = 0; i < ARRAY_SIZE(flower_ct_states); i++) {
+ len = strlen(flower_ct_states[i].str);
+ if (strncmp(str + 1, flower_ct_states[i].str, len))
+ continue;
+
+ if (p)
+ flags |= flower_ct_states[i].flag;
+ mask |= flower_ct_states[i].flag;
+ break;
+ }
+
+ if (i == ARRAY_SIZE(flower_ct_states))
+ return -1;
+
+ str += len + 1;
+ }
+
+ addattr16(n, MAX_MSG, TCA_FLOWER_KEY_CT_STATE, flags);
+ addattr16(n, MAX_MSG, TCA_FLOWER_KEY_CT_STATE_MASK, mask);
+ return 0;
+}
+
static int flower_parse_ip_proto(char *str, __be16 eth_type, int type,
__u8 *p_ip_proto, struct nlmsghdr *n)
{
@@ -898,6 +1056,34 @@ static int flower_parse_opt(struct filter_util *qu, char *handle,
flags |= TCA_CLS_FLAGS_SKIP_HW;
} else if (matches(*argv, "skip_sw") == 0) {
flags |= TCA_CLS_FLAGS_SKIP_SW;
+ } else if (matches(*argv, "ct_state") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_ct_state(*argv, n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"ct_state\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "ct_zone") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_ct_zone(*argv, n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"ct_zone\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "ct_mark") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_ct_mark(*argv, n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"ct_mark\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "ct_label") == 0) {
+ NEXT_ARG();
+ ret = flower_parse_ct_labels(*argv, n);
+ if (ret < 0) {
+ fprintf(stderr, "Illegal \"ct_label\"\n");
+ return -1;
+ }
} else if (matches(*argv, "indev") == 0) {
NEXT_ARG();
if (check_ifname(*argv))
@@ -1590,6 +1776,85 @@ static void flower_print_tcp_flags(const char *name, struct rtattr *flags_attr,
print_string(PRINT_ANY, name, namefrm, out);
}
+static void flower_print_ct_state(struct rtattr *flags_attr,
+ struct rtattr *mask_attr)
+{
+ SPRINT_BUF(out);
+ uint16_t state;
+ uint16_t state_mask;
+ size_t done = 0;
+ int i;
+
+ if (!flags_attr)
+ return;
+
+ state = rta_getattr_u16(flags_attr);
+ if (mask_attr)
+ state_mask = rta_getattr_u16(mask_attr);
+ else
+ state_mask = UINT16_MAX;
+
+ for (i = 0; i < ARRAY_SIZE(flower_ct_states); i++) {
+ if (!(state_mask & flower_ct_states[i].flag))
+ continue;
+
+ if (state & flower_ct_states[i].flag)
+ done += sprintf(out + done, "+%s",
+ flower_ct_states[i].str);
+ else
+ done += sprintf(out + done, "-%s",
+ flower_ct_states[i].str);
+ }
+
+ print_string(PRINT_ANY, "ct_state", "\n ct_state %s", out);
+}
+
+static void flower_print_ct_label(struct rtattr *attr,
+ struct rtattr *mask_attr)
+{
+ const unsigned char *str;
+ bool print_mask = false;
+ int data_len, i;
+ SPRINT_BUF(out);
+ char *p;
+
+ if (!attr)
+ return;
+
+ data_len = RTA_PAYLOAD(attr);
+ hexstring_n2a(RTA_DATA(attr), data_len, out, sizeof(out));
+ p = out + data_len*2;
+
+ data_len = RTA_PAYLOAD(attr);
+ str = RTA_DATA(mask_attr);
+ if (data_len != 16)
+ print_mask = true;
+ for (i = 0; !print_mask && i < data_len; i++) {
+ if (str[i] != 0xff)
+ print_mask = true;
+ }
+ if (print_mask) {
+ *p++ = '/';
+ hexstring_n2a(RTA_DATA(mask_attr), data_len, p,
+ sizeof(out)-(p-out));
+ p += data_len*2;
+ }
+ *p = '\0';
+
+ print_string(PRINT_ANY, "ct_label", "\n ct_label %s", out);
+}
+
+static void flower_print_ct_zone(struct rtattr *attr,
+ struct rtattr *mask_attr)
+{
+ print_masked_u16("ct_zone", attr, mask_attr);
+}
+
+static void flower_print_ct_mark(struct rtattr *attr,
+ struct rtattr *mask_attr)
+{
+ print_masked_u32("ct_mark", attr, mask_attr);
+}
static void flower_print_key_id(const char *name, struct rtattr *attr)
{
@@ -1949,6 +2214,15 @@ static int flower_print_opt(struct filter_util *qu, FILE *f,
tb[TCA_FLOWER_KEY_FLAGS],
tb[TCA_FLOWER_KEY_FLAGS_MASK]);
+ flower_print_ct_state(tb[TCA_FLOWER_KEY_CT_STATE],
+ tb[TCA_FLOWER_KEY_CT_STATE_MASK]);
+ flower_print_ct_zone(tb[TCA_FLOWER_KEY_CT_ZONE],
+ tb[TCA_FLOWER_KEY_CT_ZONE_MASK]);
+ flower_print_ct_mark(tb[TCA_FLOWER_KEY_CT_MARK],
+ tb[TCA_FLOWER_KEY_CT_MARK_MASK]);
+ flower_print_ct_label(tb[TCA_FLOWER_KEY_CT_LABELS],
+ tb[TCA_FLOWER_KEY_CT_LABELS_MASK]);
+
close_json_object();
if (tb[TCA_FLOWER_FLAGS]) {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next iproute2 1/3] tc: add NLA_F_NESTED flag to all actions options nested block
From: Paul Blakey @ 2019-07-07 8:53 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562489628-5925-1-git-send-email-paulb@mellanox.com>
Strict netlink validation now requires this flag on all nested
attributes, add it for action options.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
---
tc/m_action.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tc/m_action.c b/tc/m_action.c
index ab6bc0a..2d36a69 100644
--- a/tc/m_action.c
+++ b/tc/m_action.c
@@ -214,7 +214,8 @@ done0:
tail = addattr_nest(n, MAX_MSG, ++prio);
addattr_l(n, MAX_MSG, TCA_ACT_KIND, k, strlen(k) + 1);
- ret = a->parse_aopt(a, &argc, &argv, TCA_ACT_OPTIONS,
+ ret = a->parse_aopt(a, &argc, &argv,
+ TCA_ACT_OPTIONS | NLA_F_NESTED,
n);
if (ret < 0) {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next iproute2 2/3] tc: Introduce tc ct action
From: Paul Blakey @ 2019-07-07 8:53 UTC (permalink / raw)
To: Jiri Pirko, Paul Blakey, Roi Dayan, Yossi Kuperman, Oz Shlomo,
Marcelo Ricardo Leitner, netdev, David Miller, Aaron Conole,
Zhike Wang
Cc: Rony Efraim, nst-kernel, John Hurley, Simon Horman, Justin Pettit
In-Reply-To: <1562489628-5925-1-git-send-email-paulb@mellanox.com>
New tc action to send packets to conntrack module, commit
them, and set a zone, labels, mark, and nat on the connection.
It can also clear the packet's conntrack state by using clear.
Usage:
ct clear
ct commit [force] [zone] [mark] [label] [nat]
ct [nat] [zone]
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Roi Dayan <roid@mellanox.com>
---
include/uapi/linux/tc_act/tc_ct.h | 41 ++++
tc/Makefile | 1 +
tc/m_ct.c | 497 ++++++++++++++++++++++++++++++++++++++
tc/tc_util.c | 44 ++++
tc/tc_util.h | 4 +
5 files changed, 587 insertions(+)
create mode 100644 include/uapi/linux/tc_act/tc_ct.h
create mode 100644 tc/m_ct.c
diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h
new file mode 100644
index 0000000..5fb1d7a
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ct.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_CT_H
+#define __UAPI_TC_CT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_CT_UNSPEC,
+ TCA_CT_PARMS,
+ TCA_CT_TM,
+ TCA_CT_ACTION, /* u16 */
+ TCA_CT_ZONE, /* u16 */
+ TCA_CT_MARK, /* u32 */
+ TCA_CT_MARK_MASK, /* u32 */
+ TCA_CT_LABELS, /* u128 */
+ TCA_CT_LABELS_MASK, /* u128 */
+ TCA_CT_NAT_IPV4_MIN, /* be32 */
+ TCA_CT_NAT_IPV4_MAX, /* be32 */
+ TCA_CT_NAT_IPV6_MIN, /* struct in6_addr */
+ TCA_CT_NAT_IPV6_MAX, /* struct in6_addr */
+ TCA_CT_NAT_PORT_MIN, /* be16 */
+ TCA_CT_NAT_PORT_MAX, /* be16 */
+ TCA_CT_PAD,
+ __TCA_CT_MAX
+};
+
+#define TCA_CT_MAX (__TCA_CT_MAX - 1)
+
+#define TCA_CT_ACT_COMMIT (1 << 0)
+#define TCA_CT_ACT_FORCE (1 << 1)
+#define TCA_CT_ACT_CLEAR (1 << 2)
+#define TCA_CT_ACT_NAT (1 << 3)
+#define TCA_CT_ACT_NAT_SRC (1 << 4)
+#define TCA_CT_ACT_NAT_DST (1 << 5)
+
+struct tc_ct {
+ tc_gen;
+};
+
+#endif /* __UAPI_TC_CT_H */
diff --git a/tc/Makefile b/tc/Makefile
index 60abdde..973692a 100644
--- a/tc/Makefile
+++ b/tc/Makefile
@@ -52,6 +52,7 @@ TCMODULES += m_ctinfo.o
TCMODULES += m_bpf.o
TCMODULES += m_tunnel_key.o
TCMODULES += m_sample.o
+TCMODULES += m_ct.o
TCMODULES += p_ip.o
TCMODULES += p_ip6.o
TCMODULES += p_icmp.o
diff --git a/tc/m_ct.c b/tc/m_ct.c
new file mode 100644
index 0000000..8589cb9
--- /dev/null
+++ b/tc/m_ct.c
@@ -0,0 +1,497 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* -
+ * m_ct.c Connection tracking action
+ *
+ * Authors: Paul Blakey <paulb@mellanox.com>
+ * Yossi Kuperman <yossiku@mellanox.com>
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include "utils.h"
+#include "tc_util.h"
+#include <linux/tc_act/tc_ct.h>
+
+static void
+usage(void)
+{
+ fprintf(stderr,
+ "Usage: ct clear\n"
+ " ct commit [force] [zone ZONE] [mark MASKED_MARK] [label MASKED_LABEL] [nat NAT_SPEC]\n"
+ " ct [nat] [zone ZONE]\n"
+ "Where: ZONE is the conntrack zone table number\n"
+ " NAT_SPEC is {src|dst} addr addr1[-addr2] [port port1[-port2]]\n"
+ "\n");
+ exit(-1);
+}
+
+static int ct_parse_nat_addr_range(const char *str, struct nlmsghdr *n)
+{
+ inet_prefix addr = { .family = AF_UNSPEC, };
+ char *addr1, *addr2 = 0;
+ SPRINT_BUF(buffer);
+ int attr;
+ int ret;
+
+ strncpy(buffer, str, sizeof(buffer) - 1);
+
+ addr1 = buffer;
+ addr2 = strchr(addr1, '-');
+ if (addr2) {
+ *addr2 = '\0';
+ addr2++;
+ }
+
+ ret = get_addr(&addr, addr1, AF_UNSPEC);
+ if (ret)
+ return ret;
+ attr = addr.family == AF_INET ? TCA_CT_NAT_IPV4_MIN :
+ TCA_CT_NAT_IPV6_MIN;
+ addattr_l(n, MAX_MSG, attr, addr.data, addr.bytelen);
+
+ if (addr2) {
+ ret = get_addr(&addr, addr2, addr.family);
+ if (ret)
+ return ret;
+ }
+ attr = addr.family == AF_INET ? TCA_CT_NAT_IPV4_MAX :
+ TCA_CT_NAT_IPV6_MAX;
+ addattr_l(n, MAX_MSG, attr, addr.data, addr.bytelen);
+
+ return 0;
+}
+
+static int ct_parse_nat_port_range(const char *str, struct nlmsghdr *n)
+{
+ char *port1, *port2 = 0;
+ SPRINT_BUF(buffer);
+ __be16 port;
+ int ret;
+
+ strncpy(buffer, str, sizeof(buffer) - 1);
+
+ port1 = buffer;
+ port2 = strchr(port1, '-');
+ if (port2) {
+ *port2 = '\0';
+ port2++;
+ }
+
+ ret = get_be16(&port, port1, 10);
+ if (ret)
+ return -1;
+ addattr16(n, MAX_MSG, TCA_CT_NAT_PORT_MIN, port);
+
+ if (port2) {
+ ret = get_be16(&port, port2, 10);
+ if (ret)
+ return -1;
+ }
+ addattr16(n, MAX_MSG, TCA_CT_NAT_PORT_MAX, port);
+
+ return 0;
+}
+
+
+static int ct_parse_u16(char *str, int value_type, int mask_type,
+ struct nlmsghdr *n)
+{
+ __u16 value, mask;
+ char *slash = 0;
+
+ if (mask_type != TCA_CT_UNSPEC) {
+ slash = strchr(str, '/');
+ if (slash)
+ *slash = '\0';
+ }
+
+ if (get_u16(&value, str, 0))
+ return -1;
+
+ if (slash) {
+ if (get_u16(&mask, slash + 1, 0))
+ return -1;
+ } else {
+ mask = UINT16_MAX;
+ }
+
+ addattr16(n, MAX_MSG, value_type, value);
+ if (mask_type != TCA_CT_UNSPEC)
+ addattr16(n, MAX_MSG, mask_type, mask);
+
+ return 0;
+}
+
+static int ct_parse_u32(char *str, int value_type, int mask_type,
+ struct nlmsghdr *n)
+{
+ __u32 value, mask;
+ char *slash;
+
+ slash = strchr(str, '/');
+ if (slash)
+ *slash = '\0';
+
+ if (get_u32(&value, str, 0))
+ return -1;
+
+ if (slash) {
+ if (get_u32(&mask, slash + 1, 0))
+ return -1;
+ } else {
+ mask = UINT32_MAX;
+ }
+
+ addattr32(n, MAX_MSG, value_type, value);
+ addattr32(n, MAX_MSG, mask_type, mask);
+
+ return 0;
+}
+
+static int ct_parse_mark(char *str, struct nlmsghdr *n)
+{
+ return ct_parse_u32(str, TCA_CT_MARK, TCA_CT_MARK_MASK, n);
+}
+
+static int ct_parse_labels(char *str, struct nlmsghdr *n)
+{
+#define LABELS_SIZE 16
+ uint8_t labels[LABELS_SIZE], lmask[LABELS_SIZE];
+ char *slash, *mask = NULL;
+ size_t slen, slen_mask = 0;
+
+ slash = index(str, '/');
+ if (slash) {
+ *slash = 0;
+ mask = slash+1;
+ slen_mask = strlen(mask);
+ }
+
+ slen = strlen(str);
+ if (slen > LABELS_SIZE*2 || slen_mask > LABELS_SIZE*2) {
+ char errmsg[128];
+
+ snprintf(errmsg, sizeof(errmsg),
+ "%zd Max allowed size %d",
+ slen, LABELS_SIZE*2);
+ invarg(errmsg, str);
+ }
+
+ if (hex2mem(str, labels, slen/2) < 0)
+ invarg("ct: labels must be a hex string\n", str);
+ addattr_l(n, MAX_MSG, TCA_CT_LABELS, labels, slen/2);
+
+ if (mask) {
+ if (hex2mem(mask, lmask, slen_mask/2) < 0)
+ invarg("ct: labels mask must be a hex string\n", mask);
+ } else {
+ memset(lmask, 0xff, sizeof(lmask));
+ slen_mask = sizeof(lmask)*2;
+ }
+ addattr_l(n, MAX_MSG, TCA_CT_LABELS_MASK, lmask, slen_mask/2);
+
+ return 0;
+}
+
+static int
+parse_ct(struct action_util *a, int *argc_p, char ***argv_p, int tca_id,
+ struct nlmsghdr *n)
+{
+ struct tc_ct sel = {};
+ char **argv = *argv_p;
+ struct rtattr *tail;
+ int argc = *argc_p;
+ int ct_action = 0;
+ int ret;
+
+ tail = addattr_nest(n, MAX_MSG, tca_id);
+
+ if (argc && matches(*argv, "ct") == 0)
+ NEXT_ARG_FWD();
+
+ while (argc > 0) {
+ if (matches(*argv, "zone") == 0) {
+ NEXT_ARG();
+
+ if (ct_parse_u16(*argv,
+ TCA_CT_ZONE, TCA_CT_UNSPEC, n)) {
+ fprintf(stderr, "ct: Illegal \"zone\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "nat") == 0) {
+ ct_action |= TCA_CT_ACT_NAT;
+
+ NEXT_ARG();
+ if (matches(*argv, "src") == 0)
+ ct_action |= TCA_CT_ACT_NAT_SRC;
+ else if (matches(*argv, "dst") == 0)
+ ct_action |= TCA_CT_ACT_NAT_DST;
+ else
+ continue;
+
+ NEXT_ARG();
+ if (matches(*argv, "addr") != 0)
+ usage();
+
+ NEXT_ARG();
+ ret = ct_parse_nat_addr_range(*argv, n);
+ if (ret) {
+ fprintf(stderr, "ct: Illegal nat address range\n");
+ return -1;
+ }
+
+ NEXT_ARG_FWD();
+ if (matches(*argv, "port") != 0)
+ continue;
+
+ NEXT_ARG();
+ ret = ct_parse_nat_port_range(*argv, n);
+ if (ret) {
+ fprintf(stderr, "ct: Illegal nat port range\n");
+ return -1;
+ }
+ } else if (matches(*argv, "clear") == 0) {
+ ct_action |= TCA_CT_ACT_CLEAR;
+ } else if (matches(*argv, "commit") == 0) {
+ ct_action |= TCA_CT_ACT_COMMIT;
+ } else if (matches(*argv, "force") == 0) {
+ ct_action |= TCA_CT_ACT_FORCE;
+ } else if (matches(*argv, "index") == 0) {
+ NEXT_ARG();
+ if (get_u32(&sel.index, *argv, 10)) {
+ fprintf(stderr, "ct: Illegal \"index\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "mark") == 0) {
+ NEXT_ARG();
+
+ ret = ct_parse_mark(*argv, n);
+ if (ret) {
+ fprintf(stderr, "ct: Illegal \"mark\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "label") == 0) {
+ NEXT_ARG();
+
+ ret = ct_parse_labels(*argv, n);
+ if (ret) {
+ fprintf(stderr, "ct: Illegal \"label\"\n");
+ return -1;
+ }
+ } else if (matches(*argv, "help") == 0) {
+ usage();
+ } else {
+ break;
+ }
+ NEXT_ARG_FWD();
+ }
+
+ if (ct_action & TCA_CT_ACT_CLEAR &&
+ ct_action & ~TCA_CT_ACT_CLEAR) {
+ fprintf(stderr, "ct: clear can only be used alone\n");
+ return -1;
+ }
+
+ if (ct_action & TCA_CT_ACT_NAT_SRC &&
+ ct_action & TCA_CT_ACT_NAT_DST) {
+ fprintf(stderr, "ct: src and dst nat can't be used together\n");
+ return -1;
+ }
+
+ if ((ct_action & TCA_CT_ACT_COMMIT) &&
+ (ct_action & TCA_CT_ACT_NAT) &&
+ !(ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) {
+ fprintf(stderr, "ct: commit and nat must set src or dst\n");
+ return -1;
+ }
+
+ if (!(ct_action & TCA_CT_ACT_COMMIT) &&
+ (ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) {
+ fprintf(stderr, "ct: src or dst is only valid if commit is set\n");
+ return -1;
+ }
+
+ parse_action_control_dflt(&argc, &argv, &sel.action, false,
+ TC_ACT_PIPE);
+ NEXT_ARG_FWD();
+
+ addattr16(n, MAX_MSG, TCA_CT_ACTION, ct_action);
+ addattr_l(n, MAX_MSG, TCA_CT_PARMS, &sel, sizeof(sel));
+ addattr_nest_end(n, tail);
+
+ *argc_p = argc;
+ *argv_p = argv;
+ return 0;
+}
+
+static int ct_sprint_port(char *buf, const char *prefix, struct rtattr *attr)
+{
+ if (!attr)
+ return 0;
+
+ return sprintf(buf, "%s%d", prefix, rta_getattr_be16(attr));
+}
+
+static int ct_sprint_ip_addr(char *buf, const char *prefix,
+ struct rtattr *attr)
+{
+ int family;
+ size_t len;
+
+ if (!attr)
+ return 0;
+
+ len = RTA_PAYLOAD(attr);
+
+ if (len == 4)
+ family = AF_INET;
+ else if (len == 16)
+ family = AF_INET6;
+ else
+ return 0;
+
+ return sprintf(buf, "%s%s", prefix, rt_addr_n2a_rta(family, attr));
+}
+
+static void ct_print_nat(int ct_action, struct rtattr **tb)
+{
+ size_t done = 0;
+ char out[256] = "";
+ bool nat;
+
+ if (!(ct_action & TCA_CT_ACT_NAT))
+ return;
+
+ if (ct_action & TCA_CT_ACT_NAT_SRC) {
+ nat = true;
+ done += sprintf(out + done, "src");
+ } else if (ct_action & TCA_CT_ACT_NAT_DST) {
+ nat = true;
+ done += sprintf(out + done, "dst");
+ }
+
+ if (nat) {
+ done += ct_sprint_ip_addr(out + done, " addr ",
+ tb[TCA_CT_NAT_IPV4_MIN]);
+ done += ct_sprint_ip_addr(out + done, " addr ",
+ tb[TCA_CT_NAT_IPV6_MIN]);
+ if (tb[TCA_CT_NAT_IPV4_MAX] &&
+ memcmp(RTA_DATA(tb[TCA_CT_NAT_IPV4_MIN]),
+ RTA_DATA(tb[TCA_CT_NAT_IPV4_MAX]), 4))
+ done += ct_sprint_ip_addr(out + done, "-",
+ tb[TCA_CT_NAT_IPV4_MAX]);
+ else if (tb[TCA_CT_NAT_IPV6_MAX] &&
+ memcmp(RTA_DATA(tb[TCA_CT_NAT_IPV6_MIN]),
+ RTA_DATA(tb[TCA_CT_NAT_IPV6_MAX]), 16))
+ done += ct_sprint_ip_addr(out + done, "-",
+ tb[TCA_CT_NAT_IPV6_MAX]);
+ done += ct_sprint_port(out + done, " port ",
+ tb[TCA_CT_NAT_PORT_MIN]);
+ if (tb[TCA_CT_NAT_PORT_MAX] &&
+ memcmp(RTA_DATA(tb[TCA_CT_NAT_PORT_MIN]),
+ RTA_DATA(tb[TCA_CT_NAT_PORT_MAX]), 2))
+ done += ct_sprint_port(out + done, "-",
+ tb[TCA_CT_NAT_PORT_MAX]);
+ }
+
+ if (done)
+ print_string(PRINT_ANY, "nat", " nat %s", out);
+ else
+ print_string(PRINT_ANY, "nat", " nat", "");
+}
+
+static void ct_print_labels(struct rtattr *attr,
+ struct rtattr *mask_attr)
+{
+ const unsigned char *str;
+ bool print_mask = false;
+ char out[256], *p;
+ int data_len, i;
+
+ if (!attr)
+ return;
+
+ data_len = RTA_PAYLOAD(attr);
+ hexstring_n2a(RTA_DATA(attr), data_len, out, sizeof(out));
+ p = out + data_len*2;
+
+ data_len = RTA_PAYLOAD(attr);
+ str = RTA_DATA(mask_attr);
+ if (data_len != 16)
+ print_mask = true;
+ for (i = 0; !print_mask && i < data_len; i++) {
+ if (str[i] != 0xff)
+ print_mask = true;
+ }
+ if (print_mask) {
+ *p++ = '/';
+ hexstring_n2a(RTA_DATA(mask_attr), data_len, p,
+ sizeof(out)-(p-out));
+ p += data_len*2;
+ }
+ *p = '\0';
+
+ print_string(PRINT_ANY, "label", " label %s", out);
+}
+
+static int print_ct(struct action_util *au, FILE *f, struct rtattr *arg)
+{
+ struct rtattr *tb[TCA_CT_MAX + 1];
+ const char *commit;
+ struct tc_ct *p;
+ int ct_action = 0;
+
+ if (arg == NULL)
+ return -1;
+
+ parse_rtattr_nested(tb, TCA_CT_MAX, arg);
+ if (tb[TCA_CT_PARMS] == NULL) {
+ print_string(PRINT_FP, NULL, "%s", "[NULL ct parameters]");
+ return -1;
+ }
+
+ p = RTA_DATA(tb[TCA_CT_PARMS]);
+
+ print_string(PRINT_ANY, "kind", "%s", "ct");
+
+ if (tb[TCA_CT_ACTION])
+ ct_action = rta_getattr_u16(tb[TCA_CT_ACTION]);
+ if (ct_action & TCA_CT_ACT_COMMIT) {
+ commit = ct_action & TCA_CT_ACT_FORCE ?
+ "commit force" : "commit";
+ print_string(PRINT_ANY, "action", " %s", commit);
+ } else if (ct_action & TCA_CT_ACT_CLEAR) {
+ print_string(PRINT_ANY, "action", " %s", "clear");
+ }
+
+ print_masked_u32("mark", tb[TCA_CT_MARK], tb[TCA_CT_MARK_MASK]);
+ print_masked_u16("zone", tb[TCA_CT_ZONE], NULL);
+ ct_print_labels(tb[TCA_CT_LABELS], tb[TCA_CT_LABELS_MASK]);
+ ct_print_nat(ct_action, tb);
+
+ print_action_control(f, " ", p->action, "");
+
+ print_uint(PRINT_ANY, "index", "\n\t index %u", p->index);
+ print_int(PRINT_ANY, "ref", " ref %d", p->refcnt);
+ print_int(PRINT_ANY, "bind", " bind %d", p->bindcnt);
+
+ if (show_stats) {
+ if (tb[TCA_CT_TM]) {
+ struct tcf_t *tm = RTA_DATA(tb[TCA_CT_TM]);
+
+ print_tm(f, tm);
+ }
+ }
+ print_string(PRINT_FP, NULL, "%s", "\n ");
+
+ return 0;
+}
+
+struct action_util ct_action_util = {
+ .id = "ct",
+ .parse_aopt = parse_ct,
+ .print_aopt = print_ct,
+};
diff --git a/tc/tc_util.c b/tc/tc_util.c
index 53d15e0..8e461ba 100644
--- a/tc/tc_util.c
+++ b/tc/tc_util.c
@@ -913,3 +913,47 @@ compat_xstats:
if (tb[TCA_XSTATS] && xstats)
*xstats = tb[TCA_XSTATS];
}
+
+void print_masked_u32(const char *name, struct rtattr *attr,
+ struct rtattr *mask_attr)
+{
+ __u32 value, mask;
+ SPRINT_BUF(namefrm);
+ SPRINT_BUF(out);
+ size_t done;
+
+ if (!attr)
+ return;
+
+ value = rta_getattr_u32(attr);
+ mask = mask_attr ? rta_getattr_u32(mask_attr) : UINT32_MAX;
+
+ done = sprintf(out, "%u", value);
+ if (mask != UINT32_MAX)
+ sprintf(out + done, "/0x%x", mask);
+
+ sprintf(namefrm, " %s %%s", name);
+ print_string(PRINT_ANY, name, namefrm, out);
+}
+
+void print_masked_u16(const char *name, struct rtattr *attr,
+ struct rtattr *mask_attr)
+{
+ __u16 value, mask;
+ SPRINT_BUF(namefrm);
+ SPRINT_BUF(out);
+ size_t done;
+
+ if (!attr)
+ return;
+
+ value = rta_getattr_u16(attr);
+ mask = mask_attr ? rta_getattr_u16(mask_attr) : UINT16_MAX;
+
+ done = sprintf(out, "%u", value);
+ if (mask != UINT16_MAX)
+ sprintf(out + done, "/0x%x", mask);
+
+ sprintf(namefrm, " %s %%s", name);
+ print_string(PRINT_ANY, name, namefrm, out);
+}
diff --git a/tc/tc_util.h b/tc/tc_util.h
index eb4b60d..0c3425a 100644
--- a/tc/tc_util.h
+++ b/tc/tc_util.h
@@ -127,4 +127,8 @@ int action_a2n(char *arg, int *result, bool allow_num);
bool tc_qdisc_block_exists(__u32 block_index);
+void print_masked_u32(const char *name, struct rtattr *attr,
+ struct rtattr *mask_attr);
+void print_masked_u16(const char *name, struct rtattr *attr,
+ struct rtattr *mask_attr);
#endif
--
1.8.3.1
^ permalink raw reply related
* Re: [RFC net-next] net: dsa: add support for MC_DISABLED attribute
From: Ido Schimmel @ 2019-07-07 9:07 UTC (permalink / raw)
To: Linus Lüssing
Cc: Florian Fainelli, Jiri Pirko, nikolay, netdev@vger.kernel.org,
bridge, Russell King - ARM Linux admin, davem@davemloft.net,
Ido Schimmel, Vivien Didelot, b.a.t.m.a.n
In-Reply-To: <20190702231308.GA2414@otheros>
On Wed, Jul 03, 2019 at 01:13:08AM +0200, Linus Lüssing wrote:
> Hi Ido,
>
> > Do you differentiate between IPv4 and IPv6 in batman-adv?
>
> For most things, yes: The querier state is kept separately for
> IPv4 and IPv6. And we do have something like a "router node"
> flag to signalize that a node needs all multicast traffic, which
> is split into IPv4 and IPv6.
>
> The "MDB" equivalent in batman-adv (multicast entries in our "TT",
> translation table) are on MAC address base right now, not on an IP
> address base yet, so that sounds similar to what you do in mlxsw?
Yes.
> Regarding querier state, we periodically ask the
> bridge via "br_multicast_has_querier_anywhere(dev, ETH_P_IP)"
> and "br_multicast_has_querier_anywhere(dev, ETH_P_IPV6)".
>
> (Something more event based with handler functions would probably
> be nicer, but this was the easier thing to start with.)
Thanks for the reference. Will check the code. I believe that we will
add switchdev notifications for querier state change, so it might be
useful for you as well.
> > 1. All the IPv6 MDB entries need to be removed from the device. At least
> > in mlxsw, we do not have a way to ignore only IPv6 entries. From the
> > device's perspective, an MDB entry is just a multicast DMAC with a
> > bitmap of ports packets should be replicated to.
>
> Ah, I see, yes. We had a similar "issue". Initially we just always
> added any multicast entry into our translation table offered by
> the IP stack or bridge, no matter what a querier state or "router
> node" state said. Which would have led to a node receiving two
> copies of a multicast packet if it were both a querier or router
> and were also having a listener announced via IGMP/MLD.
>
> So there we also just recently changed that, to filter out
> IPv6 multicast TT entries if this node were also announcing itself as
> an MLD querier or IPv6 router. And same, independently for
> IPv4/IGMP.
This is actually not a problem with mlxsw. The ports a packet should be
replicated to are represented using a bitmap. It does not matter if we
set the bit because it has an MDB entry or because it is an mrouter
port. And obviously it does not matter if we set it twice :)
> > 2. We need to split the flood tables used for IPv4 and IPv6 unregistered
> > multicast packets. For IPv4, packets should only be flooded to mrouter
> > ports whereas for IPv6 packets should be flooded to all the member
> > ports.
>
> This one I do not fully understand yet. Why don't you apply the
> "flood to all ports" (in the no IGMP querier present case)
> for IPv4, too?
>
> Sure, for IPv4 nothing "essential" will break, as IPv4 unicast
> does not rely on multicast (contrary to IPv6, due to NDP, as you
> mentioned). But still there would be potential multicast packet loss
> for a 239.x.x.x listener on the local link, for instance, wouldn't
> there?
>
>
> If I'm not mistaken, we do not apply differing behaviour for IPv4
> vs. IPv6 in the bridge either and would flood on all ports for IPv4
> with no querier present, too.
I think I was not clear, so I will explain again. I was referring to a
situation where IPv4 has a querier, but IPv6 does not. In this case, the
bridge will flood IPv4 unregistered multicast packets to mrouter ports
only. On the other hand, IPv6 unregistered multicast packets will be
flooded to all the ports. Based on my reading of the code, this is
controlled by 'mcast_hit' in br_handle_frame_finish().
In mlxsw, each packet type (e.g., unknown unicast, IPvX unregistered
multicast) is associated with a flood table (basically a huge matrix,
where row corresponds to VLAN and column corresponds to a port). If we
are to handle the case where IPv4 unregistered multicast packets need to
be flooded to mrouter ports only, whereas IPv6 unregistered multicast
packets need to be flooded to all the ports, then we need to use a
separate flood table for each.
Alternatively, we can use the same flood table, but flood to all the
ports if IPv4 or IPv6 querier is missing. I do not think anything will
break, it is just very efficient. This seems to be allowed by RFC 4541
(Section 2.1.2):
"If a switch receives an unregistered packet, it must forward that
packet on all ports to which an IGMP router is attached. A switch may
default to forwarding unregistered packets on all ports."
> Regards, Linus
Linus, thanks a lot for the great feedback. I really appreciate it!
^ permalink raw reply
* [PATCH net-next] ipv6: elide flowlabel check if no exclusive leases exist
From: Willem de Bruijn @ 2019-07-07 9:34 UTC (permalink / raw)
To: netdev; +Cc: davem, Willem de Bruijn
From: Willem de Bruijn <willemb@google.com>
Processes can request ipv6 flowlabels with cmsg IPV6_FLOWINFO.
If not set, by default an autogenerated flowlabel is selected.
Explicit flowlabels require a control operation per label plus a
datapath check on every connection (every datagram if unconnected).
This is particularly expensive on unconnected sockets multiplexing
many flows, such as QUIC.
In the common case, where no lease is exclusive, the check can be
safely elided, as both lease request and check trivially succeed.
Indeed, autoflowlabel does the same even with exclusive leases.
Elide the check if no process has requested an exclusive lease.
fl6_sock_lookup previously returns either a reference to a lease or
NULL to denote failure. Modify to return a real error and update
all callers. On return NULL, they can use the label and will elide
the atomic_dec in fl6_sock_release.
This is an optimization. Robust applications still have to revert to
requesting leases if the fast path fails due to an exclusive lease.
Changes RFC->v1:
- use static_key_false_deferred to rate limit jump label operations
- call static_key_deferred_flush to stop timers on exit
- move decrement out of RCU context
- defer optimization also if opt data is associated with a lease
- updated all fp6_sock_lookup callers, not just udp
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
include/net/ipv6.h | 14 +++++++++++++-
net/dccp/ipv6.c | 2 +-
net/ipv6/ip6_flowlabel.c | 27 +++++++++++++++++++++++----
net/ipv6/raw.c | 4 ++--
net/ipv6/tcp_ipv6.c | 2 +-
net/ipv6/udp.c | 4 ++--
net/l2tp/l2tp_ip6.c | 4 ++--
net/sctp/ipv6.c | 2 +-
8 files changed, 45 insertions(+), 14 deletions(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8eca5fb30376f..8dfc65639aa4c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -13,6 +13,7 @@
#include <linux/hardirq.h>
#include <linux/jhash.h>
#include <linux/refcount.h>
+#include <linux/jump_label_ratelimit.h>
#include <net/if_inet6.h>
#include <net/ndisc.h>
#include <net/flow.h>
@@ -389,7 +390,18 @@ static inline void txopt_put(struct ipv6_txoptions *opt)
kfree_rcu(opt, rcu);
}
-struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
+struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label);
+
+extern struct static_key_false_deferred ipv6_flowlabel_exclusive;
+static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk,
+ __be32 label)
+{
+ if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key))
+ return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT);
+
+ return NULL;
+}
+
struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
struct ip6_flowlabel *fl,
struct ipv6_txoptions *fopt);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 85c10c8f50bd1..1b7381ff787b3 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -830,7 +830,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (flowlabel == NULL)
+ if (IS_ERR(flowlabel))
return -EINVAL;
fl6_sock_release(flowlabel);
}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 545e339b8c4fb..ad284b1fd308a 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -17,6 +17,7 @@
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/pid_namespace.h>
+#include <linux/jump_label_ratelimit.h>
#include <net/net_namespace.h>
#include <net/sock.h>
@@ -53,6 +54,9 @@ static DEFINE_SPINLOCK(ip6_fl_lock);
static DEFINE_SPINLOCK(ip6_sk_fl_lock);
+DEFINE_STATIC_KEY_DEFERRED_FALSE(ipv6_flowlabel_exclusive, HZ);
+EXPORT_SYMBOL(ipv6_flowlabel_exclusive);
+
#define for_each_fl_rcu(hash, fl) \
for (fl = rcu_dereference_bh(fl_ht[(hash)]); \
fl != NULL; \
@@ -90,6 +94,13 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
return fl;
}
+static bool fl_shared_exclusive(struct ip6_flowlabel *fl)
+{
+ return fl->share == IPV6_FL_S_EXCL ||
+ fl->share == IPV6_FL_S_PROCESS ||
+ fl->share == IPV6_FL_S_USER;
+}
+
static void fl_free_rcu(struct rcu_head *head)
{
struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
@@ -103,8 +114,13 @@ static void fl_free_rcu(struct rcu_head *head)
static void fl_free(struct ip6_flowlabel *fl)
{
- if (fl)
- call_rcu(&fl->rcu, fl_free_rcu);
+ if (!fl)
+ return;
+
+ if (fl_shared_exclusive(fl) || fl->opt)
+ static_branch_slow_dec_deferred(&ipv6_flowlabel_exclusive);
+
+ call_rcu(&fl->rcu, fl_free_rcu);
}
static void fl_release(struct ip6_flowlabel *fl)
@@ -240,7 +256,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
/* Socket flowlabel lists */
-struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
+struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label)
{
struct ipv6_fl_socklist *sfl;
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -260,7 +276,7 @@ struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
rcu_read_unlock_bh();
return NULL;
}
-EXPORT_SYMBOL_GPL(fl6_sock_lookup);
+EXPORT_SYMBOL_GPL(__fl6_sock_lookup);
void fl6_free_socklist(struct sock *sk)
{
@@ -419,6 +435,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
}
fl->dst = freq->flr_dst;
atomic_set(&fl->users, 1);
+ if (fl_shared_exclusive(fl) || fl->opt)
+ static_branch_deferred_inc(&ipv6_flowlabel_exclusive);
switch (fl->share) {
case IPV6_FL_S_EXCL:
case IPV6_FL_S_ANY:
@@ -854,6 +872,7 @@ int ip6_flowlabel_init(void)
void ip6_flowlabel_cleanup(void)
{
+ static_key_deferred_flush(&ipv6_flowlabel_exclusive);
del_timer(&ip6_fl_gc_timer);
unregister_pernet_subsys(&ip6_flowlabel_net_ops);
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 70693bc7ad9d2..8a6131991e38f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -834,7 +834,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (!flowlabel)
+ if (IS_ERR(flowlabel))
return -EINVAL;
}
}
@@ -876,7 +876,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (!flowlabel)
+ if (IS_ERR(flowlabel))
return -EINVAL;
}
if (!(opt->opt_nflen|opt->opt_flen))
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4f3f99b398209..d56a9019a0feb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -171,7 +171,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (!flowlabel)
+ if (IS_ERR(flowlabel))
return -EINVAL;
fl6_sock_release(flowlabel);
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4406e059da680..827fe73850788 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1319,7 +1319,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (!flowlabel)
+ if (IS_ERR(flowlabel))
return -EINVAL;
}
}
@@ -1371,7 +1371,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (!flowlabel)
+ if (IS_ERR(flowlabel))
return -EINVAL;
}
if (!(opt->opt_nflen|opt->opt_flen))
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 1a76a0a4e3abb..687e23a8b3266 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -536,7 +536,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowlabel = lsa->l2tp_flowinfo & IPV6_FLOWINFO_MASK;
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (flowlabel == NULL)
+ if (IS_ERR(flowlabel))
return -EINVAL;
}
}
@@ -577,7 +577,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if ((fl6.flowlabel & IPV6_FLOWLABEL_MASK) && !flowlabel) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (flowlabel == NULL)
+ if (IS_ERR(flowlabel))
return -EINVAL;
}
if (!(opt->opt_nflen|opt->opt_flen))
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 64e0a594a6516..e5f2fc726a983 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -253,7 +253,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
- if (!flowlabel)
+ if (IS_ERR(flowlabel))
goto out;
fl6_sock_release(flowlabel);
}
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* [PATCH net-next v2] skbuff: increase verbosity when dumping skb data
From: Willem de Bruijn @ 2019-07-07 9:51 UTC (permalink / raw)
To: netdev; +Cc: davem, linyunsheng, Willem de Bruijn
From: Willem de Bruijn <willemb@google.com>
skb_warn_bad_offload and netdev_rx_csum_fault trigger on hard to debug
issues. Dump more state and the header.
Optionally dump the entire packet and linear segment. This is required
to debug checksum bugs that may include bytes past skb_tail_pointer().
Both call sites call this function inside a net_ratelimit() block.
Limit full packet log further to a hard limit of can_dump_full (5).
Based on an earlier patch by Cong Wang, see link below.
Changes v1 -> v2
- dump frag_list only on full_pkt
Link: https://patchwork.ozlabs.org/patch/1000841/
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
include/linux/skbuff.h | 1 +
net/core/dev.c | 16 ++-----
net/core/skbuff.c | 99 ++++++++++++++++++++++++++++++++++++++++++
3 files changed, 104 insertions(+), 12 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7ece49d5f8ef7..1fdfdbb34e8e8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1024,6 +1024,7 @@ static inline bool skb_unref(struct sk_buff *skb)
void skb_release_head_state(struct sk_buff *skb);
void kfree_skb(struct sk_buff *skb);
void kfree_skb_list(struct sk_buff *segs);
+void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt);
void skb_tx_error(struct sk_buff *skb);
void consume_skb(struct sk_buff *skb);
void __consume_stateless_skb(struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 58529318b3a94..fc676b2610e3c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2900,12 +2900,10 @@ static void skb_warn_bad_offload(const struct sk_buff *skb)
else
name = netdev_name(dev);
}
- WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d "
- "gso_type=%d ip_summed=%d\n",
+ skb_dump(KERN_WARNING, skb, false);
+ WARN(1, "%s: caps=(%pNF, %pNF)\n",
name, dev ? &dev->features : &null_features,
- skb->sk ? &skb->sk->sk_route_caps : &null_features,
- skb->len, skb->data_len, skb_shinfo(skb)->gso_size,
- skb_shinfo(skb)->gso_type, skb->ip_summed);
+ skb->sk ? &skb->sk->sk_route_caps : &null_features);
}
/*
@@ -3124,13 +3122,7 @@ void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb)
{
if (net_ratelimit()) {
pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
- if (dev)
- pr_err("dev features: %pNF\n", &dev->features);
- pr_err("skb len=%u data_len=%u pkt_type=%u gso_size=%u gso_type=%u nr_frags=%u ip_summed=%u csum=%x csum_complete_sw=%d csum_valid=%d csum_level=%u\n",
- skb->len, skb->data_len, skb->pkt_type,
- skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type,
- skb_shinfo(skb)->nr_frags, skb->ip_summed, skb->csum,
- skb->csum_complete_sw, skb->csum_valid, skb->csum_level);
+ skb_dump(KERN_ERR, skb, true);
dump_stack();
}
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5323441a12ccf..cdb0ccdaac0bf 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -707,6 +707,105 @@ void kfree_skb_list(struct sk_buff *segs)
}
EXPORT_SYMBOL(kfree_skb_list);
+/* Dump skb information and contents.
+ *
+ * Must only be called from net_ratelimit()-ed paths.
+ *
+ * Dumps up to can_dump_full whole packets if full_pkt, headers otherwise.
+ */
+void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
+{
+ static atomic_t can_dump_full = ATOMIC_INIT(5);
+ struct skb_shared_info *sh = skb_shinfo(skb);
+ struct net_device *dev = skb->dev;
+ struct sock *sk = skb->sk;
+ struct sk_buff *list_skb;
+ bool has_mac, has_trans;
+ int headroom, tailroom;
+ int i, len, seg_len;
+
+ if (full_pkt)
+ full_pkt = atomic_dec_if_positive(&can_dump_full) >= 0;
+
+ if (full_pkt)
+ len = skb->len;
+ else
+ len = min_t(int, skb->len, MAX_HEADER + 128);
+
+ headroom = skb_headroom(skb);
+ tailroom = skb_tailroom(skb);
+
+ has_mac = skb_mac_header_was_set(skb);
+ has_trans = skb_transport_header_was_set(skb);
+
+ printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n"
+ "mac=(%d,%d) net=(%d,%d) trans=%d\n"
+ "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n"
+ "csum(0x%x ip_summed=%u complete_sw=%u valid=%u level=%u)\n"
+ "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n",
+ level, skb->len, headroom, skb_headlen(skb), tailroom,
+ has_mac ? skb->mac_header : -1,
+ has_mac ? skb_mac_header_len(skb) : -1,
+ skb->network_header,
+ has_trans ? skb_network_header_len(skb) : -1,
+ has_trans ? skb->transport_header : -1,
+ sh->tx_flags, sh->nr_frags,
+ sh->gso_size, sh->gso_type, sh->gso_segs,
+ skb->csum, skb->ip_summed, skb->csum_complete_sw,
+ skb->csum_valid, skb->csum_level,
+ skb->hash, skb->sw_hash, skb->l4_hash,
+ ntohs(skb->protocol), skb->pkt_type, skb->skb_iif);
+
+ if (dev)
+ printk("%sdev name=%s feat=0x%pNF\n",
+ level, dev->name, &dev->features);
+ if (sk)
+ printk("%ssk family=%hu type=%hu proto=%hu\n",
+ level, sk->sk_family, sk->sk_type, sk->sk_protocol);
+
+ if (full_pkt && headroom)
+ print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET,
+ 16, 1, skb->head, headroom, false);
+
+ seg_len = min_t(int, skb_headlen(skb), len);
+ if (seg_len)
+ print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET,
+ 16, 1, skb->data, seg_len, false);
+ len -= seg_len;
+
+ if (full_pkt && tailroom)
+ print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET,
+ 16, 1, skb_tail_pointer(skb), tailroom, false);
+
+ for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ u32 p_off, p_len, copied;
+ struct page *p;
+ u8 *vaddr;
+
+ skb_frag_foreach_page(frag, frag->page_offset,
+ skb_frag_size(frag), p, p_off, p_len,
+ copied) {
+ seg_len = min_t(int, p_len, len);
+ vaddr = kmap_atomic(p);
+ print_hex_dump(level, "skb frag: ",
+ DUMP_PREFIX_OFFSET,
+ 16, 1, vaddr + p_off, seg_len, false);
+ kunmap_atomic(vaddr);
+ len -= seg_len;
+ if (!len)
+ break;
+ }
+ }
+
+ if (full_pkt && skb_has_frag_list(skb)) {
+ printk("skb fraglist:\n");
+ skb_walk_frags(skb, list_skb)
+ skb_dump(level, list_skb, true);
+ }
+}
+EXPORT_SYMBOL(skb_dump);
+
/**
* skb_tx_error - report an sk_buff xmit error
* @skb: buffer that triggered an error
--
2.22.0.410.gd8fdbe21b5-goog
^ permalink raw reply related
* Re: [RFC net-next] net: dsa: add support for MC_DISABLED attribute
From: Ido Schimmel @ 2019-07-07 10:28 UTC (permalink / raw)
To: Vivien Didelot
Cc: Ido Schimmel, Florian Fainelli, netdev@vger.kernel.org,
Jiri Pirko, linux@armlinux.org.uk, andrew@lunn.ch,
davem@davemloft.net
In-Reply-To: <20190705120149.GB17996@t480s.localdomain>
On Fri, Jul 05, 2019 at 12:01:49PM -0400, Vivien Didelot wrote:
> Hi Ido,
>
> On Sun, 23 Jun 2019 07:09:52 +0000, Ido Schimmel <idosch@mellanox.com> wrote:
> > > Russell, Ido, Florian, so far I understand that a multicast-unaware
> > > bridge must flood unknown traffic everywhere (CPU included);
> > > and a multicast-aware bridge must only flood its ports if their
> > > mcast_flood is on, and known traffic targeting the bridge must be
> > > offloaded accordingly. Do you guys agree with this?
> >
> > When multicast snooping is enabled unregistered multicast traffic should
> > only be flooded to mrouter ports.
>
> I've figured out that this is what I need to prevent the flooding of undesired
> multicast traffic to the CPU port of the switch. The bridge itself has a
> multicast_router attribute which can be disabled, that is when I should drop
> unknown multicast traffic.
>
> However with SWITCHDEV_ATTR_ID_BRIDGE_MROUTER implemented, this
> attribute is always called with .mrouter=0, regardless the value of
> /sys/class/net/br0/bridge/multicast_router. Do I miss something here?
Hi Vivien,
I just checked this and it seems to work as expected:
# echo 2 > /sys/class/net/br0/bridge/multicast_router
We get a notification with mrouter=1 to mlxsw
# echo 0 > /sys/class/net/br0/bridge/multicast_router
We get a notification with mrouter=0 to mlxsw
^ permalink raw reply
* [PATCH net-next 00/16] mlx5e devlink health reporters
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
Hi Dave,
I'm submitting this series myself as Saeed is on vacation.
This series from Aya to the mlx5e driver introduces changes in
devlink health reporters.
Most noticeable is adding a new reporter, RX reporter, which
reports and recovers from timeout and completion errors in the
receive path.
In patches 1-6, we perform TX reporter cleanup. In order to maintain
the code flow as similar as possible between RX and TX reporters.
In patch 7, we prepare for code sharing, generalize and move shared
functionality.
Patches 8-10 refactor and extend TX reporter diagnostics information
to align the TX reporter diagnostics output with the RX reporter's
diagnostics output.
Patch 11 adds RX reporter, initially supports only the diagnostics
call back.
In patch 12 we split ICOSQ open/close functions into two stages, to call
specific parts from the recover flow.
Patches 13-16 introduce recovery flows for: RX timeout on ICOSQ, completion
error on receive path.
Series generated against net-next commit:
23f30c41c732 Merge branch 'mlx5-TLS-TX-HW-offload-support'
Regards,
Tariq
Aya Levin (15):
Revert "net/mlx5e: Fix mlx5e_tx_reporter_create return value"
net/mlx5e: Fix error flow in tx reporter diagnose
net/mlx5e: Set tx reporter only on successful creation
net/mlx5e: TX reporter cleanup
net/mlx5e: Rename reporter header file
net/mlx5e: Change naming convention for reporter's functions
net/mlx5e: Generalize tx reporter's functionality
net/mlx5e: Extend tx diagnose function
net/mlx5e: Extend tx reporter diagnostics output
net/mlx5e: Add cq info to tx reporter diagnose
net/mlx5e: Add support to rx reporter diagnose
net/mlx5e: Split open/close ICOSQ into stages
net/mlx5e: Recover from CQE error on ICOSQ
net/mlx5e: Recover from rx timeout
net/mlx5e: Recover from CQE with error on RQ
Saeed Mahameed (1):
net/mlx5e: RX, Handle CQE with error at the earliest stage
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 5 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 32 ++
.../net/ethernet/mellanox/mlx5/core/en/health.c | 205 +++++++++++
.../net/ethernet/mellanox/mlx5/core/en/health.h | 53 +++
.../net/ethernet/mellanox/mlx5/core/en/reporter.h | 15 -
.../ethernet/mellanox/mlx5/core/en/reporter_rx.c | 390 +++++++++++++++++++++
.../ethernet/mellanox/mlx5/core/en/reporter_tx.c | 226 ++++++------
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 84 +++--
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 62 ++--
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 +
drivers/net/ethernet/mellanox/mlx5/core/wq.c | 5 +
drivers/net/ethernet/mellanox/mlx5/core/wq.h | 1 +
13 files changed, 883 insertions(+), 200 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/health.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/health.h
delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next 06/16] net/mlx5e: Change naming convention for reporter's functions
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Change from mlx5e_tx_reporter_* to mlx5e_reporter_tx_*. In the following
patches in the set rx reporter is added, the new naming convention is
more uniformed.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/health.h | 8 ++++----
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 8 ++++----
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++----
3 files changed, 12 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index e78e92753d73..e3a3bcee89e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -7,9 +7,9 @@
#include <linux/mlx5/driver.h>
#include "en.h"
-int mlx5e_tx_reporter_create(struct mlx5e_priv *priv);
-void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv);
-void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq);
-int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq);
+int mlx5e_reporter_tx_create(struct mlx5e_priv *priv);
+void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv);
+void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
+int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 0035ae9306ec..d5ecfcfe5d52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -124,7 +124,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
return devlink_health_report(tx_reporter, err_str, err_ctx);
}
-void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
+void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq)
{
char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
struct mlx5e_tx_err_ctx err_ctx = {0};
@@ -159,7 +159,7 @@ static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
return ret;
}
-int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
+int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
{
char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
struct mlx5e_tx_err_ctx err_ctx;
@@ -288,7 +288,7 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500
-int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
+int mlx5e_reporter_tx_create(struct mlx5e_priv *priv)
{
struct devlink_health_reporter *reporter;
struct mlx5_core_dev *mdev = priv->mdev;
@@ -307,7 +307,7 @@ int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
return PTR_ERR_OR_ZERO(reporter);
}
-void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
+void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv)
{
if (!priv->tx_reporter)
return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ce4533f8169c..98c925e72706 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1376,7 +1376,7 @@ static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
recover_work);
- mlx5e_tx_reporter_err_cqe(sq);
+ mlx5e_reporter_tx_err_cqe(sq);
}
int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
@@ -3201,7 +3201,7 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
{
int tc;
- mlx5e_tx_reporter_destroy(priv);
+ mlx5e_reporter_tx_destroy(priv);
for (tc = 0; tc < priv->profile->max_tc; tc++)
mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
}
@@ -4286,7 +4286,7 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
if (!netif_xmit_stopped(dev_queue))
continue;
- if (mlx5e_tx_reporter_timeout(sq))
+ if (mlx5e_reporter_tx_timeout(sq))
report_failed = true;
}
@@ -5093,7 +5093,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
#ifdef CONFIG_MLX5_CORE_EN_DCB
mlx5e_dcbnl_initialize(priv);
#endif
- mlx5e_tx_reporter_create(priv);
+ mlx5e_reporter_tx_create(priv);
return 0;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 08/16] net/mlx5e: Extend tx diagnose function
From: Tariq Toukan @ 2019-07-07 11:53 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
The following patches in the set enhance the diagnostics info of tx
reporter. Therefore, it is better to pass a pointer to the SQ for
further data extraction.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 3e03a1ac8e5a..dd6417930461 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -138,15 +138,22 @@ static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
static int
mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg,
- u32 sqn, u8 state, bool stopped)
+ struct mlx5e_txqsq *sq)
{
+ struct mlx5e_priv *priv = sq->channel->priv;
+ bool stopped = netif_xmit_stopped(sq->txq);
+ u8 state;
int err;
+ err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
+ if (err)
+ return err;
+
err = devlink_fmsg_obj_nest_start(fmsg);
if (err)
return err;
- err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn);
+ err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn);
if (err)
return err;
@@ -183,15 +190,8 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
for (i = 0; i < priv->channels.num * priv->channels.params.num_tc;
i++) {
struct mlx5e_txqsq *sq = priv->txq2sq[i];
- u8 state;
-
- err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
- if (err)
- goto unlock;
- err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
- state,
- netif_xmit_stopped(sq->txq));
+ err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq);
if (err)
goto unlock;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 05/16] net/mlx5e: Rename reporter header file
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Rename reporter.h -> health.h so patches in the set can use it for
health related functionality.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/health.h | 15 +++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h | 15 ---------------
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
4 files changed, 17 insertions(+), 17 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/health.h
delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
new file mode 100644
index 000000000000..e78e92753d73
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5E_EN_REPORTER_H
+#define __MLX5E_EN_REPORTER_H
+
+#include <linux/mlx5/driver.h>
+#include "en.h"
+
+int mlx5e_tx_reporter_create(struct mlx5e_priv *priv);
+void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv);
+void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq);
+int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
deleted file mode 100644
index e78e92753d73..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2019 Mellanox Technologies. */
-
-#ifndef __MLX5E_EN_REPORTER_H
-#define __MLX5E_EN_REPORTER_H
-
-#include <linux/mlx5/driver.h>
-#include "en.h"
-
-int mlx5e_tx_reporter_create(struct mlx5e_priv *priv);
-void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv);
-void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq);
-int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq);
-
-#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 83555894bacb..0035ae9306ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2019 Mellanox Technologies. */
-#include "reporter.h"
+#include "health.h"
#include "lib/eq.h"
#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c5f11a05c34b..ce4533f8169c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -56,7 +56,7 @@
#include "en/xdp.h"
#include "lib/eq.h"
#include "en/monitor_stats.h"
-#include "en/reporter.h"
+#include "en/health.h"
#include "en/params.h"
#include "en/xsk/umem.h"
#include "en/xsk/setup.h"
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 01/16] Revert "net/mlx5e: Fix mlx5e_tx_reporter_create return value"
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
This reverts commit 2e5b0534622fa87fd570d54af2d01ce304b88077.
This commit was needed prior to commit f6b19b354d50 ("net: devlink:
select NET_DEVLINK from drivers") Then, reporter's pointer could have
been a NULL. But with NET_DEVLINK mandatory to MLX5_CORE in Kconfig,
pointer can only hold an error in bad path.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 476dd97f7f2f..24626bb55598 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -302,7 +302,7 @@ int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
netdev_warn(priv->netdev,
"Failed to create tx reporter, err = %ld\n",
PTR_ERR(priv->tx_reporter));
- return IS_ERR_OR_NULL(priv->tx_reporter);
+ return PTR_ERR_OR_ZERO(priv->tx_reporter);
}
void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 03/16] net/mlx5e: Set tx reporter only on successful creation
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
When failing to create tx reporter, don't set the reporter's pointer.
Creating a reporter is not mandatory for driver load, avoid
garbage/error pointer.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 19 +++++++++++--------
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
2 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index b2bc8d8ca80e..259811811e06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -117,7 +117,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
char *err_str,
struct mlx5e_tx_err_ctx *err_ctx)
{
- if (IS_ERR_OR_NULL(tx_reporter)) {
+ if (!tx_reporter) {
netdev_err(err_ctx->sq->channel->netdev, err_str);
return err_ctx->recover(err_ctx->sq);
}
@@ -291,23 +291,26 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
{
+ struct devlink_health_reporter *reporter;
struct mlx5_core_dev *mdev = priv->mdev;
struct devlink *devlink = priv_to_devlink(mdev);
- priv->tx_reporter =
+ reporter =
devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
MLX5_REPORTER_TX_GRACEFUL_PERIOD,
true, priv);
- if (IS_ERR(priv->tx_reporter))
- netdev_warn(priv->netdev,
- "Failed to create tx reporter, err = %ld\n",
- PTR_ERR(priv->tx_reporter));
- return PTR_ERR_OR_ZERO(priv->tx_reporter);
+ if (IS_ERR(reporter))
+ netdev_warn(priv->netdev, "Failed to create tx reporter, err = %ld\n",
+ PTR_ERR(reporter));
+ else
+ priv->tx_reporter = reporter;
+
+ return PTR_ERR_OR_ZERO(reporter);
}
void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
{
- if (IS_ERR_OR_NULL(priv->tx_reporter))
+ if (!priv->tx_reporter)
return;
devlink_health_reporter_destroy(priv->tx_reporter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 83194d56434d..c5f11a05c34b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2320,7 +2320,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
goto err_close_channels;
}
- if (!IS_ERR_OR_NULL(priv->tx_reporter))
+ if (priv->tx_reporter)
devlink_health_reporter_state_update(priv->tx_reporter,
DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 10/16] net/mlx5e: Add cq info to tx reporter diagnose
From: Tariq Toukan @ 2019-07-07 11:53 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Add cq information to general diagnose output: CQ size and stride size.
Per SQ add information about the related CQ: cqn and CQ's HW status.
$ devlink health diagnose pci/0000:00:0b.0 reporter tx
Common config:
SQ: stride size: 64 size: 1024
CQ: stride size: 64 size: 1024
SQs:
channel ix: 0 sqn: 4283 HW state: 1 stopped: false cc: 0 pc: 0 CQ: cqn: 1030 HW status: 0
channel ix: 1 sqn: 4288 HW state: 1 stopped: false cc: 0 pc: 0 CQ: cqn: 1034 HW status: 0
channel ix: 2 sqn: 4293 HW state: 1 stopped: false cc: 0 pc: 0 CQ: cqn: 1038 HW status: 0
channel ix: 3 sqn: 4298 HW state: 1 stopped: false cc: 0 pc: 0 CQ: cqn: 1042 HW status: 0
$ devlink health diagnose pci/0000:00:0b.0 reporter tx -jp
{
"Common config": [
"SQ": {
"stride size": 64,
"size": 1024
},
"CQ": {
"stride size": 64,
"size": 1024
} ],
"SQs": [ {
"channel ix": 0,
"sqn": 4283,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0,
"CQ": {
"cqn": 1030,
"HW status": 0
}
},{
"channel ix": 1,
"sqn": 4288,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0,
"CQ": {
"cqn": 1034,
"HW status": 0
}
},{
"channel ix": 2,
"sqn": 4293,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0,
"CQ": {
"cqn": 1038,
"HW status": 0
}
},{
"channel ix": 3,
"sqn": 4298,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0,
"CQ": {
"cqn": 1042,
"HW status": 0
}
} ]
}
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en/health.c | 62 ++++++++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/en/health.h | 2 +
.../ethernet/mellanox/mlx5/core/en/reporter_tx.c | 8 +++
drivers/net/ethernet/mellanox/mlx5/core/wq.c | 5 ++
drivers/net/ethernet/mellanox/mlx5/core/wq.h | 1 +
5 files changed, 78 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 0d44b081259f..a266717d41e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -34,6 +34,68 @@ int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg)
return 0;
}
+int mlx5e_reporter_cq_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg)
+{
+ struct mlx5e_priv *priv = cq->channel->priv;
+ u32 out[MLX5_ST_SZ_DW(query_cq_out)] = {};
+ u8 hw_status;
+ void *cqc;
+ int err;
+
+ err = mlx5_core_query_cq(priv->mdev, &cq->mcq, out, sizeof(out));
+ if (err)
+ return err;
+
+ cqc = MLX5_ADDR_OF(query_cq_out, out, cq_context);
+ hw_status = MLX5_GET(cqc, cqc, status);
+
+ err = mlx5e_reporter_named_obj_nest_start(fmsg, "CQ");
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "cqn", cq->mcq.cqn);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u8_pair_put(fmsg, "HW status", hw_status);
+ if (err)
+ return err;
+
+ err = mlx5e_reporter_named_obj_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+int mlx5e_reporter_cq_common_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg)
+{
+ u8 cq_log_stride;
+ u32 cq_sz;
+ int err;
+
+ cq_sz = mlx5_cqwq_get_size(&cq->wq);
+ cq_log_stride = mlx5_cqwq_get_log_stride_size(&cq->wq);
+
+ err = mlx5e_reporter_named_obj_nest_start(fmsg, "CQ");
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u64_pair_put(fmsg, "stride size", BIT(cq_log_stride));
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "size", cq_sz);
+ if (err)
+ return err;
+
+ err = mlx5e_reporter_named_obj_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+
int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn)
{
struct mlx5_core_dev *mdev = channel->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index 0fecad63135c..b0c8bda3d25f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -11,6 +11,8 @@
void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq);
+int mlx5e_reporter_cq_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg);
+int mlx5e_reporter_cq_common_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg);
int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name);
int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index c481f7142a12..47e788cf05bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -177,6 +177,10 @@ static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
if (err)
return err;
+ err = mlx5e_reporter_cq_diagnose(&sq->cq, fmsg);
+ if (err)
+ return err;
+
err = devlink_fmsg_obj_nest_end(fmsg);
if (err)
return err;
@@ -221,6 +225,10 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
if (err)
goto unlock;
+ err = mlx5e_reporter_cq_common_diagnose(&generic_sq->cq, fmsg);
+ if (err)
+ goto unlock;
+
err = mlx5e_reporter_named_obj_nest_end(fmsg);
if (err)
goto unlock;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index 953cc8efba69..dd2315ce4441 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -44,6 +44,11 @@ u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
return wq->fbc.sz_m1 + 1;
}
+u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq)
+{
+ return wq->fbc.log_stride;
+}
+
u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
{
return (u32)wq->fbc.sz_m1 + 1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index f1ec58c9e9e3..55791f71a778 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -89,6 +89,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
void *cqc, struct mlx5_cqwq *wq,
struct mlx5_wq_ctrl *wq_ctrl);
u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq);
+u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq);
int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
void *wqc, struct mlx5_wq_ll *wq,
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 11/16] net/mlx5e: Add support to rx reporter diagnose
From: Tariq Toukan @ 2019-07-07 11:53 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Add rx reporter, which supports diagnose call-back. Diagnostics output
include: information common to all RQs: RQ type, RQ size, RQ stride
size, CQ size and CQ stride size. In addition advertise information per
RQ and its related icosq and attached CQ.
$ devlink health diagnose pci/0000:00:0b.0 reporter rx
Common config:
RQ: type: 2 stride size: 2048 size: 8
CQ: stride size: 64 size: 1024
RQs:
channel ix: 0 rqn: 4284 HW state: 1 SW state: 3 posted WQEs: 7 cc: 7 ICOSQ HW state: 1 CQ: cqn: 1032 HW status: 0
channel ix: 1 rqn: 4289 HW state: 1 SW state: 3 posted WQEs: 7 cc: 7 ICOSQ HW state: 1 CQ: cqn: 1036 HW status: 0
channel ix: 2 rqn: 4294 HW state: 1 SW state: 3 posted WQEs: 7 cc: 7 ICOSQ HW state: 1 CQ: cqn: 1040 HW status: 0
channel ix: 3 rqn: 4299 HW state: 1 SW state: 3 posted WQEs: 7 cc: 7 ICOSQ HW state: 1 CQ: cqn: 1044 HW status: 0
$ devlink health diagnose pci/0000:00:0b.0 reporter rx -jp
{
"Common config": [
"RQ": {
"type": 2,
"stride size": 2048,
"size": 8
},
"CQ": {
"stride size": 64,
"size": 1024
} ],
"RQs": [ {
"channel ix": 0,
"rqn": 4284,
"HW state": 1,
"SW state": 3,
"posted WQEs": 7,
"cc": 7,
"ICOSQ HW state": 1,
"CQ": {
"cqn": 1032,
"HW status": 0
}
},{
"channel ix": 1,
"rqn": 4289,
"HW state": 1,
"SW state": 3,
"posted WQEs": 7,
"cc": 7,
"ICOSQ HW state": 1,
"CQ": {
"cqn": 1036,
"HW status": 0
}
},{
"channel ix": 2,
"rqn": 4294,
"HW state": 1,
"SW state": 3,
"posted WQEs": 7,
"cc": 7,
"ICOSQ HW state": 1,
"CQ": {
"cqn": 1040,
"HW status": 0
}
},{
"channel ix": 3,
"rqn": 4299,
"HW state": 1,
"SW state": 3,
"posted WQEs": 7,
"cc": 7,
"ICOSQ HW state": 1,
"CQ": {
"cqn": 1044,
"HW status": 0
}
} ]
}
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 4 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 21 +++
.../net/ethernet/mellanox/mlx5/core/en/health.c | 31 ++++
.../net/ethernet/mellanox/mlx5/core/en/health.h | 7 +
.../ethernet/mellanox/mlx5/core/en/reporter_rx.c | 194 +++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 29 +--
6 files changed, 258 insertions(+), 28 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 23d566a45a30..a3b9659649a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -24,8 +24,8 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
en_selftest.o en/port.o en/monitor_stats.o en/health.o \
- en/reporter_tx.o en/params.o en/xsk/umem.o en/xsk/setup.o \
- en/xsk/rx.o en/xsk/tx.o
+ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/umem.o \
+ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o
#
# Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 263558875f20..f7c5cf7a7064 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -848,6 +848,7 @@ struct mlx5e_priv {
struct mlx5e_tls *tls;
#endif
struct devlink_health_reporter *tx_reporter;
+ struct devlink_health_reporter *rx_reporter;
struct mlx5e_xsk xsk;
};
@@ -888,6 +889,26 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
+static inline u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq)
+{
+ switch (rq->wq_type) {
+ case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ return mlx5_wq_ll_get_size(&rq->mpwqe.wq);
+ default:
+ return mlx5_wq_cyc_get_size(&rq->wqe.wq);
+ }
+}
+
+static inline u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq)
+{
+ switch (rq->wq_type) {
+ case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ return rq->mpwqe.wq.cur_sz;
+ default:
+ return rq->wqe.wq.cur_sz;
+ }
+}
+
bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev);
bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index a266717d41e5..a0579de8e2e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -96,6 +96,37 @@ int mlx5e_reporter_cq_common_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *
return 0;
}
+int mlx5e_health_create_reporters(struct mlx5e_priv *priv)
+{
+ int err;
+
+ err = mlx5e_reporter_tx_create(priv);
+ if (err)
+ return err;
+
+ err = mlx5e_reporter_rx_create(priv);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv)
+{
+ mlx5e_reporter_rx_destroy(priv);
+ mlx5e_reporter_tx_destroy(priv);
+}
+
+void mlx5e_health_channels_update(struct mlx5e_priv *priv)
+{
+ if (priv->tx_reporter)
+ devlink_health_reporter_state_update(priv->tx_reporter,
+ DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+ if (priv->rx_reporter)
+ devlink_health_reporter_state_update(priv->rx_reporter,
+ DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+}
+
int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn)
{
struct mlx5_core_dev *mdev = channel->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index b0c8bda3d25f..7829ea229914 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -16,6 +16,9 @@
int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name);
int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg);
+int mlx5e_reporter_rx_create(struct mlx5e_priv *priv);
+void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv);
+
#define MLX5E_REPORTER_PER_Q_MAX_LEN 256
struct mlx5e_err_ctx {
@@ -29,5 +32,9 @@ struct mlx5e_err_ctx {
int mlx5e_health_report(struct mlx5e_priv *priv,
struct devlink_health_reporter *reporter, char *err_str,
struct mlx5e_err_ctx *err_ctx);
+int mlx5e_health_create_reporters(struct mlx5e_priv *priv);
+void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv);
+void mlx5e_health_channels_update(struct mlx5e_priv *priv);
+
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
new file mode 100644
index 000000000000..b24bdff473b0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include "health.h"
+#include "params.h"
+
+static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state)
+{
+ int outlen = MLX5_ST_SZ_BYTES(query_rq_out);
+ void *out;
+ void *rqc;
+ int err;
+
+ out = kvzalloc(outlen, GFP_KERNEL);
+ if (!out)
+ return -ENOMEM;
+
+ err = mlx5_core_query_rq(dev, rqn, out);
+ if (err)
+ goto out;
+
+ rqc = MLX5_ADDR_OF(query_rq_out, out, rq_context);
+ *state = MLX5_GET(rqc, rqc, state);
+
+out:
+ kvfree(out);
+ return err;
+}
+
+static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq,
+ struct devlink_fmsg *fmsg)
+{
+ struct mlx5e_priv *priv = rq->channel->priv;
+ struct mlx5e_params *params = &priv->channels.params;
+ struct mlx5e_icosq *icosq = &rq->channel->icosq;
+ u8 icosq_hw_state;
+ int wqes_sz;
+ u8 hw_state;
+ u16 wq_head;
+ int err;
+
+ err = mlx5e_query_rq_state(priv->mdev, rq->rqn, &hw_state);
+ if (err)
+ return err;
+
+ err = mlx5_core_query_sq_state(priv->mdev, icosq->sqn, &icosq_hw_state);
+ if (err)
+ return err;
+
+ wqes_sz = mlx5e_rqwq_get_cur_sz(rq);
+ wq_head = params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
+ rq->mpwqe.wq.head : mlx5_wq_cyc_get_head(&rq->wqe.wq);
+
+ err = devlink_fmsg_obj_nest_start(fmsg);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", rq->channel->ix);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "rqn", rq->rqn);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u8_pair_put(fmsg, "HW state", hw_state);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u8_pair_put(fmsg, "SW state", rq->state);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "posted WQEs", wqes_sz);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "cc", wq_head);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u8_pair_put(fmsg, "ICOSQ HW state", icosq_hw_state);
+ if (err)
+ return err;
+
+ err = mlx5e_reporter_cq_diagnose(&rq->cq, fmsg);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_obj_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
+ struct devlink_fmsg *fmsg)
+{
+ struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+ struct mlx5e_params *params = &priv->channels.params;
+ struct mlx5e_rq *generic_rq;
+ u32 rq_stride, rq_sz;
+ int i, err = 0;
+
+ mutex_lock(&priv->state_lock);
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ goto unlock;
+
+ generic_rq = &priv->channels.c[0]->rq;
+ rq_sz = mlx5e_rqwq_get_size(generic_rq);
+ rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL));
+
+ err = devlink_fmsg_arr_pair_nest_start(fmsg, "Common config");
+ if (err)
+ goto unlock;
+
+ err = mlx5e_reporter_named_obj_nest_start(fmsg, "RQ");
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type);
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_u64_pair_put(fmsg, "stride size", rq_stride);
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "size", rq_sz);
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_arr_pair_nest_end(fmsg);
+ if (err)
+ goto unlock;
+
+ err = mlx5e_reporter_cq_common_diagnose(&generic_rq->cq, fmsg);
+ if (err)
+ goto unlock;
+
+ err = mlx5e_reporter_named_obj_nest_end(fmsg);
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_arr_pair_nest_start(fmsg, "RQs");
+ if (err)
+ goto unlock;
+
+ for (i = 0; i < priv->channels.num; i++) {
+ struct mlx5e_rq *rq = &priv->channels.c[i]->rq;
+
+ err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg);
+ if (err)
+ goto unlock;
+ }
+ err = devlink_fmsg_arr_pair_nest_end(fmsg);
+ if (err)
+ goto unlock;
+unlock:
+ mutex_unlock(&priv->state_lock);
+ return err;
+}
+
+static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = {
+ .name = "rx",
+ .diagnose = mlx5e_rx_reporter_diagnose,
+};
+
+int mlx5e_reporter_rx_create(struct mlx5e_priv *priv)
+{
+ struct devlink_health_reporter *reporter;
+ struct mlx5_core_dev *mdev = priv->mdev;
+ struct devlink *devlink = priv_to_devlink(mdev);
+
+ reporter =
+ devlink_health_reporter_create(devlink, &mlx5_rx_reporter_ops,
+ 0, false, priv);
+ if (IS_ERR(reporter))
+ netdev_warn(priv->netdev, "Failed to create rx reporter, err = %ld\n",
+ PTR_ERR(reporter));
+ else
+ priv->tx_reporter = reporter;
+ return PTR_ERR_OR_ZERO(reporter);
+}
+
+void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv)
+{
+ if (!priv->rx_reporter)
+ return;
+
+ devlink_health_reporter_destroy(priv->rx_reporter);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 98c925e72706..3922905e909f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -247,26 +247,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
}
-static u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq)
-{
- switch (rq->wq_type) {
- case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- return mlx5_wq_ll_get_size(&rq->mpwqe.wq);
- default:
- return mlx5_wq_cyc_get_size(&rq->wqe.wq);
- }
-}
-
-static u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq)
-{
- switch (rq->wq_type) {
- case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- return rq->mpwqe.wq.cur_sz;
- default:
- return rq->wqe.wq.cur_sz;
- }
-}
-
static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
struct mlx5e_channel *c)
{
@@ -2320,10 +2300,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
goto err_close_channels;
}
- if (priv->tx_reporter)
- devlink_health_reporter_state_update(priv->tx_reporter,
- DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
-
+ mlx5e_health_channels_update(priv);
kvfree(cparam);
return 0;
@@ -3201,7 +3178,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
{
int tc;
- mlx5e_reporter_tx_destroy(priv);
for (tc = 0; tc < priv->profile->max_tc; tc++)
mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
}
@@ -4985,12 +4961,14 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
mlx5e_build_nic_netdev(netdev);
mlx5e_build_tc2txq_maps(priv);
+ mlx5e_health_create_reporters(priv);
return 0;
}
static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
{
+ mlx5e_health_destroy_reporters(priv);
mlx5e_tls_cleanup(priv);
mlx5e_ipsec_cleanup(priv);
mlx5e_netdev_cleanup(priv->netdev, priv);
@@ -5093,7 +5071,6 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
#ifdef CONFIG_MLX5_CORE_EN_DCB
mlx5e_dcbnl_initialize(priv);
#endif
- mlx5e_reporter_tx_create(priv);
return 0;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 09/16] net/mlx5e: Extend tx reporter diagnostics output
From: Tariq Toukan @ 2019-07-07 11:53 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Enhance tx reporter's diagnostics output to include: information common
to all SQs: SQ size, SQ stride size.
In addition add channel ix, cc and pc.
$ devlink health diagnose pci/0000:00:0b.0 reporter tx
Common config:
SQ: stride size: 64 size: 1024
SQs:
channel ix: 0 sqn: 4283 HW state: 1 stopped: false cc: 0 pc: 0
channel ix: 1 sqn: 4288 HW state: 1 stopped: false cc: 0 pc: 0
channel ix: 2 sqn: 4293 HW state: 1 stopped: false cc: 0 pc: 0
channel ix: 3 sqn: 4298 HW state: 1 stopped: false cc: 0 pc: 0
$ devlink health diagnose pci/0000:00:0b.0 reporter tx -jp
{
"Common config": [
"SQ": {
"stride size": 64,
"size": 1024
} ],
"SQs": [ {
"channel ix": 0,
"sqn": 4283,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0
},{
"channel ix": 1,
"sqn": 4288,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0
},{
"channel ix": 2,
"sqn": 4293,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0
},{
"channel ix": 3,
"sqn": 4298,
"HW state": 1,
"stopped": false,
"cc": 0,
"pc": 0
} ]
}
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en/health.c | 30 ++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/en/health.h | 3 ++
.../ethernet/mellanox/mlx5/core/en/reporter_tx.c | 42 ++++++++++++++++++++++
3 files changed, 75 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 60166e5432ae..0d44b081259f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -4,6 +4,36 @@
#include "health.h"
#include "lib/eq.h"
+int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_start(fmsg, name);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_obj_nest_start(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg)
+{
+ int err;
+
+ err = devlink_fmsg_pair_nest_end(fmsg);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_obj_nest_end(fmsg);
+ if (err)
+ return err;
+
+ return 0;
+}
+
int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn)
{
struct mlx5_core_dev *mdev = channel->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index 960aa18c425d..0fecad63135c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -11,6 +11,9 @@
void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq);
+int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name);
+int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg);
+
#define MLX5E_REPORTER_PER_Q_MAX_LEN 256
struct mlx5e_err_ctx {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index dd6417930461..c481f7142a12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -153,6 +153,10 @@ static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
if (err)
return err;
+ err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", sq->channel->ix);
+ if (err)
+ return err;
+
err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn);
if (err)
return err;
@@ -165,6 +169,14 @@ static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
if (err)
return err;
+ err = devlink_fmsg_u32_pair_put(fmsg, "cc", sq->cc);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "pc", sq->pc);
+ if (err)
+ return err;
+
err = devlink_fmsg_obj_nest_end(fmsg);
if (err)
return err;
@@ -176,6 +188,9 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
struct devlink_fmsg *fmsg)
{
struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+ struct mlx5e_txqsq *generic_sq = priv->txq2sq[0];
+ u32 sq_stride, sq_sz;
+
int i, err = 0;
mutex_lock(&priv->state_lock);
@@ -183,6 +198,33 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
goto unlock;
+ sq_sz = mlx5_wq_cyc_get_size(&generic_sq->wq);
+ sq_stride = MLX5_SEND_WQE_BB;
+
+ err = devlink_fmsg_arr_pair_nest_start(fmsg, "Common config");
+ if (err)
+ goto unlock;
+
+ err = mlx5e_reporter_named_obj_nest_start(fmsg, "SQ");
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_u64_pair_put(fmsg, "stride size", sq_stride);
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "size", sq_sz);
+ if (err)
+ goto unlock;
+
+ err = devlink_fmsg_arr_pair_nest_end(fmsg);
+ if (err)
+ goto unlock;
+
+ err = mlx5e_reporter_named_obj_nest_end(fmsg);
+ if (err)
+ goto unlock;
+
err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs");
if (err)
goto unlock;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 13/16] net/mlx5e: Recover from CQE error on ICOSQ
From: Tariq Toukan @ 2019-07-07 11:53 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Add support for recovery from error on completion on ICOSQ. Deactivate
RQ and flush, then deactivate ICOSQ. Set the queue back to ready state
(firmware) and reset the ICOSQ and the RQ (software resources). Finally,
activate the ICOSQ and the RQ.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 8 ++
.../net/ethernet/mellanox/mlx5/core/en/health.h | 1 +
.../ethernet/mellanox/mlx5/core/en/reporter_rx.c | 103 ++++++++++++++++++++-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 23 +++--
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 +
7 files changed, 135 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f7c5cf7a7064..648641e68de2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -554,6 +554,8 @@ struct mlx5e_icosq {
/* control path */
struct mlx5_wq_ctrl wq_ctrl;
struct mlx5e_channel *channel;
+
+ struct work_struct recover_work;
} ____cacheline_aligned_in_smp;
struct mlx5e_wqe_frag_info {
@@ -1027,6 +1029,12 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
+int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
+void mlx5e_activate_rq(struct mlx5e_rq *rq);
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
+void mlx5e_activate_icosq(struct mlx5e_icosq *icosq);
+void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq);
int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
struct mlx5e_modify_sq_param *p);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index 7829ea229914..e8c5d3bd86f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -18,6 +18,7 @@
int mlx5e_reporter_rx_create(struct mlx5e_priv *priv);
void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv);
+void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq);
#define MLX5E_REPORTER_PER_Q_MAX_LEN 256
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index b24bdff473b0..c47e9a53bd53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -27,6 +27,103 @@ static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state)
return err;
}
+static int mlx5e_wait_for_icosq_flush(struct mlx5e_icosq *icosq)
+{
+ unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+
+ while (time_before(jiffies, exp_time)) {
+ if (icosq->cc == icosq->pc)
+ return 0;
+
+ msleep(20);
+ }
+
+ netdev_err(icosq->channel->netdev,
+ "Wait for ICOSQ 0x%x flush timeout (cc = 0x%x, pc = 0x%x)\n",
+ icosq->sqn, icosq->cc, icosq->pc);
+
+ return -ETIMEDOUT;
+}
+
+static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq)
+{
+ WARN_ONCE(icosq->cc != icosq->pc, "ICOSQ 0x%x: cc (0x%x) != pc (0x%x)\n",
+ icosq->sqn, icosq->cc, icosq->pc);
+ icosq->cc = 0;
+ icosq->pc = 0;
+}
+
+static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
+{
+ struct mlx5e_icosq *icosq = (struct mlx5e_icosq *)ctx;
+ struct mlx5_core_dev *mdev = icosq->channel->mdev;
+ struct net_device *dev = icosq->channel->netdev;
+ struct mlx5e_rq *rq = &icosq->channel->rq;
+ u8 state;
+ int err;
+
+ err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state);
+ if (err) {
+ netdev_err(dev, "Failed to query ICOSQ 0x%x state. err = %d\n",
+ icosq->sqn, err);
+ return err;
+ }
+
+ if (state != MLX5_SQC_STATE_ERR)
+ return 0;
+
+ mlx5e_deactivate_rq(rq);
+ err = mlx5e_wait_for_icosq_flush(icosq);
+ if (err)
+ goto out;
+
+ mlx5e_deactivate_icosq(icosq);
+
+ /* At this point, both the rq and the icosq are disabled */
+
+ err = mlx5e_health_sq_to_ready(icosq->channel, icosq->sqn);
+ if (err)
+ goto out;
+
+ mlx5e_reset_icosq_cc_pc(icosq);
+ mlx5e_free_rx_descs(rq);
+ mlx5e_activate_icosq(icosq);
+ mlx5e_activate_rq(rq);
+
+ rq->stats->recover++;
+out:
+ clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+ return err;
+}
+
+void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq)
+{
+ struct mlx5e_priv *priv = icosq->channel->priv;
+ char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+ struct mlx5e_err_ctx err_ctx = {};
+
+ err_ctx.ctx = icosq;
+ err_ctx.recover = mlx5e_rx_reporter_err_icosq_cqe_recover;
+ sprintf(err_str, "ERR CQE on ICOSQ: 0x%x", icosq->sqn);
+
+ mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
+}
+
+static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
+{
+ return err_ctx->recover(err_ctx->ctx);
+}
+
+static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter,
+ void *context)
+{
+ struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+ struct mlx5e_err_ctx *err_ctx = context;
+
+ return err_ctx ? mlx5e_rx_reporter_recover_from_ctx(err_ctx) :
+ mlx5e_health_recover_channels(priv);
+}
+
static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq,
struct devlink_fmsg *fmsg)
{
@@ -165,9 +262,12 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = {
.name = "rx",
+ .recover = mlx5e_rx_reporter_recover,
.diagnose = mlx5e_rx_reporter_diagnose,
};
+#define MLX5E_REPORTER_RX_GRACEFUL_PERIOD 500
+
int mlx5e_reporter_rx_create(struct mlx5e_priv *priv)
{
struct devlink_health_reporter *reporter;
@@ -176,7 +276,8 @@ int mlx5e_reporter_rx_create(struct mlx5e_priv *priv)
reporter =
devlink_health_reporter_create(devlink, &mlx5_rx_reporter_ops,
- 0, false, priv);
+ MLX5E_REPORTER_RX_GRACEFUL_PERIOD,
+ true, priv);
if (IS_ERR(reporter))
netdev_warn(priv->netdev, "Failed to create rx reporter, err = %ld\n",
PTR_ERR(reporter));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7e6ac1e7bdd1..2d57611ac579 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -701,8 +701,7 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq,
return err;
}
-static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state,
- int next_state)
+int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state)
{
struct mlx5_core_dev *mdev = rq->mdev;
@@ -813,7 +812,7 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
return -ETIMEDOUT;
}
-static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
{
__be16 wqe_ix_be;
u16 wqe_ix;
@@ -889,7 +888,7 @@ int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
return err;
}
-static void mlx5e_activate_rq(struct mlx5e_rq *rq)
+void mlx5e_activate_rq(struct mlx5e_rq *rq)
{
set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
mlx5e_trigger_irq(&rq->channel->icosq);
@@ -904,6 +903,7 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
void mlx5e_close_rq(struct mlx5e_rq *rq)
{
cancel_work_sync(&rq->dim.work);
+ cancel_work_sync(&rq->channel->icosq.recover_work);
mlx5e_destroy_rq(rq);
mlx5e_free_rx_descs(rq);
mlx5e_free_rq(rq);
@@ -1020,6 +1020,14 @@ static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
return 0;
}
+static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+ struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+ recover_work);
+
+ mlx5e_reporter_icosq_cqe_err(sq);
+}
+
static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
struct mlx5e_sq_param *param,
struct mlx5e_icosq *sq)
@@ -1042,6 +1050,8 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
if (err)
goto err_sq_wq_destroy;
+ INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work);
+
return 0;
err_sq_wq_destroy:
@@ -1385,12 +1395,13 @@ int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
return err;
}
-static void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
+void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
{
+ clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
set_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
}
-static void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
+void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
{
struct mlx5e_channel *c = icosq->channel;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 56a2f4666c47..4173679254bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -615,6 +615,8 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
netdev_WARN_ONCE(cq->channel->netdev,
"Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
+ if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+ queue_work(cq->channel->priv->wq, &sq->recover_work);
break;
}
do {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 539b4d3656da..7de3d87dc434 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -107,6 +107,7 @@
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
@@ -217,6 +218,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
s->rx_cache_waive += rq_stats->cache_waive;
s->rx_congst_umr += rq_stats->congst_umr;
s->rx_arfs_err += rq_stats->arfs_err;
+ s->rx_recover += rq_stats->recover;
s->ch_events += ch_stats->events;
s->ch_poll += ch_stats->poll;
s->ch_arm += ch_stats->arm;
@@ -1294,6 +1296,7 @@ static int mlx5e_grp_tls_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
};
static const struct counter_desc sq_stats_desc[] = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 76ac111e14d0..a50caa70453c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -114,6 +114,7 @@ struct mlx5e_sw_stats {
u64 rx_cache_waive;
u64 rx_congst_umr;
u64 rx_arfs_err;
+ u64 rx_recover;
u64 ch_events;
u64 ch_poll;
u64 ch_arm;
@@ -247,6 +248,7 @@ struct mlx5e_rq_stats {
u64 cache_waive;
u64 congst_umr;
u64 arfs_err;
+ u64 recover;
};
struct mlx5e_sq_stats {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 07/16] net/mlx5e: Generalize tx reporter's functionality
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Prepare for code sharing with rx reporter, which is added in the
following patches in the set. Introduce a generic error_ctx for
agnostic recovery despatch.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 5 +-
.../net/ethernet/mellanox/mlx5/core/en/health.c | 82 ++++++++++++++
.../net/ethernet/mellanox/mlx5/core/en/health.h | 15 ++-
.../ethernet/mellanox/mlx5/core/en/reporter_tx.c | 126 ++++-----------------
4 files changed, 124 insertions(+), 104 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/health.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 57d2cc666fe3..23d566a45a30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -23,8 +23,9 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
#
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
- en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \
- en/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o
+ en_selftest.o en/port.o en/monitor_stats.o en/health.o \
+ en/reporter_tx.o en/params.o en/xsk/umem.o en/xsk/setup.o \
+ en/xsk/rx.o en/xsk/tx.o
#
# Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
new file mode 100644
index 000000000000..60166e5432ae
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include "health.h"
+#include "lib/eq.h"
+
+int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn)
+{
+ struct mlx5_core_dev *mdev = channel->mdev;
+ struct net_device *dev = channel->netdev;
+ struct mlx5e_modify_sq_param msp = {0};
+ int err;
+
+ msp.curr_state = MLX5_SQC_STATE_ERR;
+ msp.next_state = MLX5_SQC_STATE_RST;
+
+ err = mlx5e_modify_sq(mdev, sqn, &msp);
+ if (err) {
+ netdev_err(dev, "Failed to move sq 0x%x to reset\n", sqn);
+ return err;
+ }
+
+ memset(&msp, 0, sizeof(msp));
+ msp.curr_state = MLX5_SQC_STATE_RST;
+ msp.next_state = MLX5_SQC_STATE_RDY;
+
+ err = mlx5e_modify_sq(mdev, sqn, &msp);
+ if (err) {
+ netdev_err(dev, "Failed to move sq 0x%x to ready\n", sqn);
+ return err;
+ }
+
+ return 0;
+}
+
+int mlx5e_health_recover_channels(struct mlx5e_priv *priv)
+{
+ int err = 0;
+
+ rtnl_lock();
+ mutex_lock(&priv->state_lock);
+
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+ goto out;
+
+ err = mlx5e_safe_reopen_channels(priv);
+
+out:
+ mutex_unlock(&priv->state_lock);
+ rtnl_unlock();
+
+ return err;
+}
+
+int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel)
+{
+ u32 eqe_count;
+
+ netdev_err(channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
+ eq->core.eqn, eq->core.cons_index, eq->core.irqn);
+
+ eqe_count = mlx5_eq_poll_irq_disabled(eq);
+ if (!eqe_count)
+ return -EIO;
+
+ netdev_err(channel->netdev, "Recovered %d eqes on EQ 0x%x\n",
+ eqe_count, eq->core.eqn);
+
+ channel->stats->eq_rearm++;
+ return 0;
+}
+
+int mlx5e_health_report(struct mlx5e_priv *priv,
+ struct devlink_health_reporter *reporter, char *err_str,
+ struct mlx5e_err_ctx *err_ctx)
+{
+ if (!reporter) {
+ netdev_err(priv->netdev, err_str);
+ return err_ctx->recover(&err_ctx->ctx);
+ }
+ return devlink_health_report(reporter, err_str, err_ctx);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index e3a3bcee89e7..960aa18c425d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -4,7 +4,6 @@
#ifndef __MLX5E_EN_REPORTER_H
#define __MLX5E_EN_REPORTER_H
-#include <linux/mlx5/driver.h>
#include "en.h"
int mlx5e_reporter_tx_create(struct mlx5e_priv *priv);
@@ -12,4 +11,18 @@
void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq);
+#define MLX5E_REPORTER_PER_Q_MAX_LEN 256
+
+struct mlx5e_err_ctx {
+ int (*recover)(void *ctx);
+ void *ctx;
+};
+
+int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn);
+int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel);
+int mlx5e_health_recover_channels(struct mlx5e_priv *priv);
+int mlx5e_health_report(struct mlx5e_priv *priv,
+ struct devlink_health_reporter *reporter, char *err_str,
+ struct mlx5e_err_ctx *err_ctx);
+
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index d5ecfcfe5d52..3e03a1ac8e5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -2,14 +2,6 @@
/* Copyright (c) 2019 Mellanox Technologies. */
#include "health.h"
-#include "lib/eq.h"
-
-#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256
-
-struct mlx5e_tx_err_ctx {
- int (*recover)(struct mlx5e_txqsq *sq);
- struct mlx5e_txqsq *sq;
-};
static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
{
@@ -39,37 +31,9 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
sq->pc = 0;
}
-static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
-{
- struct mlx5_core_dev *mdev = sq->channel->mdev;
- struct net_device *dev = sq->channel->netdev;
- struct mlx5e_modify_sq_param msp = {0};
- int err;
-
- msp.curr_state = curr_state;
- msp.next_state = MLX5_SQC_STATE_RST;
-
- err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
- if (err) {
- netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
- return err;
- }
-
- memset(&msp, 0, sizeof(msp));
- msp.curr_state = MLX5_SQC_STATE_RST;
- msp.next_state = MLX5_SQC_STATE_RDY;
-
- err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
- if (err) {
- netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
- return err;
- }
-
- return 0;
-}
-
-static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
+static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
{
+ struct mlx5e_txqsq *sq = (struct mlx5e_txqsq *)ctx;
struct mlx5_core_dev *mdev = sq->channel->mdev;
struct net_device *dev = sq->channel->netdev;
u8 state;
@@ -101,7 +65,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
* pending WQEs. SQ can safely reset the SQ.
*/
- err = mlx5e_sq_to_ready(sq, state);
+ err = mlx5e_health_sq_to_ready(sq->channel, sq->sqn);
if (err)
return err;
@@ -112,104 +76,64 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
return 0;
}
-static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
- char *err_str,
- struct mlx5e_tx_err_ctx *err_ctx)
-{
- if (!tx_reporter) {
- netdev_err(err_ctx->sq->channel->netdev, err_str);
- return err_ctx->recover(err_ctx->sq);
- }
-
- return devlink_health_report(tx_reporter, err_str, err_ctx);
-}
-
void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq)
{
- char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
- struct mlx5e_tx_err_ctx err_ctx = {0};
+ struct mlx5e_priv *priv = sq->channel->priv;
+ char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+ struct mlx5e_err_ctx err_ctx = {0};
- err_ctx.sq = sq;
- err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover;
+ err_ctx.ctx = sq;
+ err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover;
sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn);
- mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
- &err_ctx);
+ mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx);
}
-static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
+static int mlx5e_tx_reporter_timeout_recover(void *ctx)
{
+ struct mlx5e_txqsq *sq = (struct mlx5e_txqsq *)ctx;
struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
- u32 eqe_count;
- int ret;
-
- netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
- eq->core.eqn, eq->core.cons_index, eq->core.irqn);
+ int err;
- eqe_count = mlx5_eq_poll_irq_disabled(eq);
- ret = eqe_count ? false : true;
- if (!eqe_count) {
+ err = mlx5e_health_channel_eq_recover(eq, sq->channel);
+ if (err)
clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
- return ret;
- }
- netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n",
- eqe_count, eq->core.eqn);
- sq->channel->stats->eq_rearm++;
- return ret;
+ return err;
}
int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
{
- char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
- struct mlx5e_tx_err_ctx err_ctx;
+ struct mlx5e_priv *priv = sq->channel->priv;
+ char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
+ struct mlx5e_err_ctx err_ctx;
- err_ctx.sq = sq;
- err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
+ err_ctx.ctx = sq;
+ err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
sprintf(err_str,
"TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
jiffies_to_usecs(jiffies - sq->txq->trans_start));
- return mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
- &err_ctx);
+ return mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx);
}
/* state lock cannot be grabbed within this function.
* It can cause a dead lock or a read-after-free.
*/
-static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
+static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
{
- return err_ctx->recover(err_ctx->sq);
-}
-
-static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
-{
- int err = 0;
-
- rtnl_lock();
- mutex_lock(&priv->state_lock);
-
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
- goto out;
-
- err = mlx5e_safe_reopen_channels(priv);
-
-out:
- mutex_unlock(&priv->state_lock);
- rtnl_unlock();
-
- return err;
+ return err_ctx->recover(err_ctx->ctx);
}
static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
void *context)
{
struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
- struct mlx5e_tx_err_ctx *err_ctx = context;
+ struct mlx5e_err_ctx *err_ctx = context;
return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) :
- mlx5e_tx_reporter_recover_all(priv);
+ mlx5e_health_recover_channels(priv);
}
static int
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 04/16] net/mlx5e: TX reporter cleanup
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Remove redundant include file.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 259811811e06..83555894bacb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -1,7 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2019 Mellanox Technologies. */
-#include <net/devlink.h>
#include "reporter.h"
#include "lib/eq.h"
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 02/16] net/mlx5e: Fix error flow in tx reporter diagnose
From: Tariq Toukan @ 2019-07-07 11:52 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Fix tx reporter's diagnose call back. Propagate error when failing to
gather diagnostics information or failing to print diagnostic data per
queue.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 24626bb55598..b2bc8d8ca80e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -264,13 +264,13 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
if (err)
- break;
+ goto unlock;
err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
state,
netif_xmit_stopped(sq->txq));
if (err)
- break;
+ goto unlock;
}
err = devlink_fmsg_arr_pair_nest_end(fmsg);
if (err)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 15/16] net/mlx5e: RX, Handle CQE with error at the earliest stage
From: Tariq Toukan @ 2019-07-07 11:53 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, ayal, jiri, Saeed Mahameed, moshe,
Tariq Toukan
In-Reply-To: <1562500388-16847-1-git-send-email-tariqt@mellanox.com>
From: Saeed Mahameed <saeedm@mellanox.com>
Just to be aligned with the MPWQE handlers, handle RX WQE with error
for legacy RQs in the top RX handlers, just before calling skb_from_cqe().
CQE error handling will now be called at the same stage regardless of
the RQ type or netdev mode NIC, Representor, IPoIB, etc ..
This will be useful for down stream patches to improve error CQE
handling.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en/health.h | 2 +
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 49 ++++++++++++----------
2 files changed, 30 insertions(+), 21 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index aa46f7ecae53..435e31ad1cfb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -6,6 +6,8 @@
#include "en.h"
+#define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)
+
int mlx5e_reporter_tx_create(struct mlx5e_priv *priv);
void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv);
void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 4173679254bf..3b730d3436e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -48,6 +48,7 @@
#include "lib/clock.h"
#include "en/xdp.h"
#include "en/xsk/rx.h"
+#include "en/health.h"
static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
{
@@ -1062,11 +1063,6 @@ struct sk_buff *
prefetchw(va); /* xdp_frame data area */
prefetch(data);
- if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
- rq->stats->wqe_err++;
- return NULL;
- }
-
rcu_read_lock();
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false);
rcu_read_unlock();
@@ -1094,11 +1090,6 @@ struct sk_buff *
u16 byte_cnt = cqe_bcnt - headlen;
struct sk_buff *skb;
- if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
- rq->stats->wqe_err++;
- return NULL;
- }
-
/* XDP is not supported in this configuration, as incoming packets
* might spread among multiple pages.
*/
@@ -1144,6 +1135,11 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
wi = get_frag(rq, ci);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
+ if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+ rq->stats->wqe_err++;
+ goto free_wqe;
+ }
+
skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
mlx5e_skb_from_cqe_linear,
mlx5e_skb_from_cqe_nonlinear,
@@ -1185,6 +1181,11 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
wi = get_frag(rq, ci);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
+ if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+ rq->stats->wqe_err++;
+ goto free_wqe;
+ }
+
skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
if (!skb) {
/* probably for XDP */
@@ -1319,7 +1320,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
wi->consumed_strides += cstrides;
- if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
+ if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
rq->stats->wqe_err++;
goto mpwrq_cqe_out;
}
@@ -1495,6 +1496,11 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
wi = get_frag(rq, ci);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
+ if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+ rq->stats->wqe_err++;
+ goto wq_free_wqe;
+ }
+
skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
mlx5e_skb_from_cqe_linear,
mlx5e_skb_from_cqe_nonlinear,
@@ -1530,26 +1536,27 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
wi = get_frag(rq, ci);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
+ if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+ rq->stats->wqe_err++;
+ goto wq_free_wqe;
+ }
+
skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
mlx5e_skb_from_cqe_linear,
mlx5e_skb_from_cqe_nonlinear,
rq, cqe, wi, cqe_bcnt);
- if (unlikely(!skb)) {
- /* a DROP, save the page-reuse checks */
- mlx5e_free_rx_wqe(rq, wi, true);
- goto wq_cyc_pop;
- }
+ if (unlikely(!skb)) /* a DROP, save the page-reuse checks */
+ goto wq_free_wqe;
+
skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
- if (unlikely(!skb)) {
- mlx5e_free_rx_wqe(rq, wi, true);
- goto wq_cyc_pop;
- }
+ if (unlikely(!skb))
+ goto wq_free_wqe;
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
napi_gro_receive(rq->cq.napi, skb);
+wq_free_wqe:
mlx5e_free_rx_wqe(rq, wi, true);
-wq_cyc_pop:
mlx5_wq_cyc_pop(wq);
}
--
1.8.3.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox