linux.git/net/ethtool, branch v6.14-rc2

ethtool: ntuple: fix rss + ring_cookie check

2025-02-04T02:38:58+00:00

The info.flow_type is for RXFH commands, ntuple flow_type is inside
the flow spec. The check currently does nothing, as info.flow_type
is 0 (or even uninitialized by user space) for ETHTOOL_SRXCLSRLINS.

Fixes: 9e43ad7a1ede ("net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in")
Reviewed-by: Gal Pressman 
Reviewed-by: Joe Damato 
Link: https://patch.msgid.link/20250201013040.725123-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski

ethtool: rss: fix hiding unsupported fields in dumps

2025-02-04T02:38:52+00:00

Commit ec6e57beaf8b ("ethtool: rss: don't report key if device
doesn't support it") intended to stop reporting key fields for
additional rss contexts if device has a global hashing key.

Later we added dump support and the filtering wasn't properly
added there. So we end up reporting the key fields in dumps
but not in dos:

  # ./pyynl/cli.py --spec netlink/specs/ethtool.yaml --do rss-get \
		--json '{"header": {"dev-index":2}, "context": 1 }'
  {
     "header": { ... },
     "context": 1,
     "indir": [0, 1, 2, 3, ...]]
  }

  # ./pyynl/cli.py --spec netlink/specs/ethtool.yaml --dump rss-get
  [
     ... snip context 0 ...
     { "header": { ... },
       "context": 1,
       "indir": [0, 1, 2, 3, ...],
 ->    "input_xfrm": 255,
 ->    "hfunc": 1,
 ->    "hkey": "000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000"
     }
  ]

Hide these fields correctly.

The drivers/net/hw/rss_ctx.py selftest catches this when run on
a device with single key, already:

  # Check| At /root/./ksft-net-drv/drivers/net/hw/rss_ctx.py, line 381, in test_rss_context_dump:
  # Check|     ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero")
  # Check failed {0} == {0} key is all zero
  not ok 8 rss_ctx.test_rss_context_dump

Fixes: f6122900f4e2 ("ethtool: rss: support dumping RSS contexts")
Reviewed-by: Gal Pressman 
Reviewed-by: Joe Damato 
Link: https://patch.msgid.link/20250201013040.725123-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski

ethtool: Fix set RXNFC command with symmetric RSS hash

2025-01-28T11:25:42+00:00

The sanity check that both source and destination are set when symmetric
RSS hash is requested is only relevant for ETHTOOL_SRXFH (rx-flow-hash),
it should not be performed on any other commands (e.g.
ETHTOOL_SRXCLSRLINS/ETHTOOL_SRXCLSRLDEL).

This resolves accessing uninitialized 'info.data' field, and fixes false
errors in rule insertion:
  # ethtool --config-ntuple eth2 flow-type ip4 dst-ip 255.255.255.255 action -1 loc 0
  rmgr: Cannot insert RX class rule: Invalid argument
  Cannot insert classification rule

Fixes: 13e59344fb9d ("net: ethtool: add support for symmetric-xor RSS hash")
Cc: Ahmed Zaki 
Reviewed-by: Tariq Toukan 
Signed-off-by: Gal Pressman 
Reviewed-by: Michal Swiatkowski 
Reviewed-by: Edward Cree 
Reviewed-by: Ahmed Zaki 
Link: https://patch.msgid.link/20250126191845.316589-1-gal@nvidia.com
Signed-off-by: Paolo Abeni

Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

2025-01-21T09:24:33+00:00

No conflicts and no adjacent changes.

Signed-off-by: Paolo Abeni

net: ethtool: populate the default HDS params in the core

2025-01-20T19:44:58+00:00

The core has the current HDS config, it can pre-populate the values
for the drivers. While at it, remove the zero-setting in netdevsim.
Zero are the default values since the config is zalloc'ed.

Reviewed-by: Michael Chan 
Link: https://patch.msgid.link/20250119020518.1962249-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski

net: provide pending ring configuration in net_device

2025-01-20T19:44:57+00:00

Record the pending configuration in net_device struct.
ethtool core duplicates the current config and the specific
handlers (for now just ringparam) can modify it.

Reviewed-by: Michael Chan 
Link: https://patch.msgid.link/20250119020518.1962249-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski

net: ethtool: store netdev in a temp variable in ethnl_default_set_doit()

2025-01-20T19:44:57+00:00

For ease of review of the next patch store the dev pointer
on the stack, instead of referring to req_info.dev every time.

No functional changes.

Reviewed-by: Michael Chan 
Link: https://patch.msgid.link/20250119020518.1962249-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski

net: move HDS config from ethtool state

2025-01-20T19:44:57+00:00

Separate the HDS config from the ethtool state struct.
The HDS config contains just simple parameters, not state.
Having it as a separate struct will make it easier to clone / copy
and also long term potentially make it per-queue.

Reviewed-by: Michael Chan 
Link: https://patch.msgid.link/20250119020518.1962249-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski

net: avoid race between device unregistration and ethnl ops

2025-01-19T01:37:31+00:00

The following trace can be seen if a device is being unregistered while
its number of channels are being modified.

  DEBUG_LOCKS_WARN_ON(lock->magic != lock)
  WARNING: CPU: 3 PID: 3754 at kernel/locking/mutex.c:564 __mutex_lock+0xc8a/0x1120
  CPU: 3 UID: 0 PID: 3754 Comm: ethtool Not tainted 6.13.0-rc6+ #771
  RIP: 0010:__mutex_lock+0xc8a/0x1120
  Call Trace:
   
   ethtool_check_max_channel+0x1ea/0x880
   ethnl_set_channels+0x3c3/0xb10
   ethnl_default_set_doit+0x306/0x650
   genl_family_rcv_msg_doit+0x1e3/0x2c0
   genl_rcv_msg+0x432/0x6f0
   netlink_rcv_skb+0x13d/0x3b0
   genl_rcv+0x28/0x40
   netlink_unicast+0x42e/0x720
   netlink_sendmsg+0x765/0xc20
   __sys_sendto+0x3ac/0x420
   __x64_sys_sendto+0xe0/0x1c0
   do_syscall_64+0x95/0x180
   entry_SYSCALL_64_after_hwframe+0x76/0x7e

This is because unregister_netdevice_many_notify might run before the
rtnl lock section of ethnl operations, eg. set_channels in the above
example. In this example the rss lock would be destroyed by the device
unregistration path before being used again, but in general running
ethnl operations while dismantle has started is not a good idea.

Fix this by denying any operation on devices being unregistered. A check
was already there in ethnl_ops_begin, but not wide enough.

Note that the same issue cannot be seen on the ioctl version
(__dev_ethtool) because the device reference is retrieved from within
the rtnl lock section there. Once dismantle started, the net device is
unlisted and no reference will be found.

Fixes: dde91ccfa25f ("ethtool: do not perform operations on net devices being unregistered")
Signed-off-by: Antoine Tenart 
Reviewed-by: Przemek Kitszel 
Reviewed-by: Edward Cree 
Link: https://patch.msgid.link/20250116092159.50890-1-atenart@kernel.org
Signed-off-by: Jakub Kicinski

net: ethtool: ts: add separate counter for unconfirmed one-step TX timestamps

2025-01-18T04:01:09+00:00

For packets with two-step timestamp requests, the hardware timestamp
comes back to the driver through a confirmation mechanism of sorts,
which allows the driver to confidently bump the successful "pkts"
counter.

For one-step PTP, the NIC is supposed to autonomously insert its
hardware TX timestamp in the packet headers while simultaneously
transmitting it. There may be a confirmation that this was done
successfully, or there may not.

None of the current drivers which implement ethtool_ops :: get_ts_stats()
also support HWTSTAMP_TX_ONESTEP_SYNC or HWTSTAMP_TX_ONESTEP_SYNC, so it
is a bit unclear which model to follow. But there are NICs, such as DSA,
where there is no transmit confirmation at all. Here, it would be wrong /
misleading to increment the successful "pkts" counter, because one-step
PTP packets can be dropped on TX just like any other packets.

So introduce a special counter which signifies "yes, an attempt was made,
but we don't know whether it also exited the port or not". I expect that
for one-step PTP packets where a confirmation is available, the "pkts"
counter would be bumped.

Signed-off-by: Vladimir Oltean 
Reviewed-by: Jakub Kicinski 
Link: https://patch.msgid.link/20250116104628.123555-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski