linux-stable.git/net/ethtool, branch v6.13.2 Linux kernel stable tree ethtool: Fix set RXNFC command with symmetric RSS hash 2025-02-08T09:02:13+00:00 Gal Pressman gal@nvidia.com 2025-01-26T19:18:45+00:00 97f2c87e5141182fa4579a84dc36e11b008e9bbb [ Upstream commit 4f5a52adeb1ad675ca33f1e1eacd9c0bbaf393d4 ] 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 <ahmed.zaki@intel.com> Reviewed-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: Gal Pressman <gal@nvidia.com> Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Reviewed-by: Edward Cree <ecree.xilinx@gmail.com> Reviewed-by: Ahmed Zaki <ahmed.zaki@intel.com> Link: https://patch.msgid.link/20250126191845.316589-1-gal@nvidia.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 4f5a52adeb1ad675ca33f1e1eacd9c0bbaf393d4 ]

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 <ahmed.zaki@intel.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250126191845.316589-1-gal@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
net: avoid race between device unregistration and ethnl ops 2025-02-08T09:01:28+00:00 Antoine Tenart atenart@kernel.org 2025-01-16T09:21:57+00:00 4dc880245f9b529fa8f476b5553c799d2848b47b [ Upstream commit 12e070eb6964b341b41677fd260af5a305316a1f ] 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: <TASK> 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 <atenart@kernel.org> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Reviewed-by: Edward Cree <ecree.xilinx@gmail.com> Link: https://patch.msgid.link/20250116092159.50890-1-atenart@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 12e070eb6964b341b41677fd260af5a305316a1f ]

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:
   <TASK>
   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 <atenart@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20250116092159.50890-1-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
ethtool: Fix wrong mod state in case of verbose and no_mask bitset 2024-12-05T02:54:43+00:00 Kory Maincent kory.maincent@bootlin.com 2024-12-02T15:33:57+00:00 910c4788d6155b2202ec88273376cd7ecdc24f0a A bitset without mask in a _SET request means we want exactly the bits in the bitset to be set. This works correctly for compact format but when verbose format is parsed, ethnl_update_bitset32_verbose() only sets the bits present in the request bitset but does not clear the rest. The commit 6699170376ab ("ethtool: fix application of verbose no_mask bitset") fixes this issue by clearing the whole target bitmap before we start iterating. The solution proposed brought an issue with the behavior of the mod variable. As the bitset is always cleared the old value will always differ to the new value. Fix it by adding a new function to compare bitmaps and a temporary variable which save the state of the old bitmap. Fixes: 6699170376ab ("ethtool: fix application of verbose no_mask bitset") Signed-off-by: Kory Maincent <kory.maincent@bootlin.com> Link: https://patch.msgid.link/20241202153358.1142095-1-kory.maincent@bootlin.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
A bitset without mask in a _SET request means we want exactly the bits in
the bitset to be set. This works correctly for compact format but when
verbose format is parsed, ethnl_update_bitset32_verbose() only sets the
bits present in the request bitset but does not clear the rest. The commit
6699170376ab ("ethtool: fix application of verbose no_mask bitset") fixes
this issue by clearing the whole target bitmap before we start iterating.
The solution proposed brought an issue with the behavior of the mod
variable. As the bitset is always cleared the old value will always
differ to the new value.

Fix it by adding a new function to compare bitmaps and a temporary variable
which save the state of the old bitmap.

Fixes: 6699170376ab ("ethtool: fix application of verbose no_mask bitset")
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20241202153358.1142095-1-kory.maincent@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ethtool: Fix access to uninitialized fields in set RXNFC command 2024-12-04T02:42:28+00:00 Gal Pressman gal@nvidia.com 2024-12-02T16:48:05+00:00 94071909477677fc2a1abf3fb281f203f66cf3ca The check for non-zero ring with RSS is only relevant for ETHTOOL_SRXCLSRLINS command, in other cases the check tries to access memory which was not initialized by the userspace tool. Only perform the check in case of ETHTOOL_SRXCLSRLINS. Without this patch, filter deletion (for example) could statistically result in a false error: # ethtool --config-ntuple eth3 delete 484 rmgr: Cannot delete RX class rule: Invalid argument Cannot delete classification rule Fixes: 9e43ad7a1ede ("net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in") Link: https://lore.kernel.org/netdev/871a9ecf-1e14-40dd-bbd7-e90c92f89d47@nvidia.com/ Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com> Reviewed-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: Gal Pressman <gal@nvidia.com> Reviewed-by: Edward Cree <ecree.xilinx@gmail.com> Link: https://patch.msgid.link/20241202164805.1637093-1-gal@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
The check for non-zero ring with RSS is only relevant for
ETHTOOL_SRXCLSRLINS command, in other cases the check tries to access
memory which was not initialized by the userspace tool. Only perform the
check in case of ETHTOOL_SRXCLSRLINS.

Without this patch, filter deletion (for example) could statistically
result in a false error:
  # ethtool --config-ntuple eth3 delete 484
  rmgr: Cannot delete RX class rule: Invalid argument
  Cannot delete classification rule

Fixes: 9e43ad7a1ede ("net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in")
Link: https://lore.kernel.org/netdev/871a9ecf-1e14-40dd-bbd7-e90c92f89d47@nvidia.com/
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20241202164805.1637093-1-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Revert "net: ethtool: Avoid thousands of -Wflex-array-member-not-at-end warnings" 2024-11-19T02:52:11+00:00 Kees Cook kees@kernel.org 2024-11-15T20:43:03+00:00 1cfb5e57886aa69a992ff0ebd32e4651eb0fc995 This reverts commit 3bd9b9abdf1563a22041b7255baea6d449902f1a. We cannot use the new tagged struct group because it throws C++ errors even under "extern C". Signed-off-by: Kees Cook <kees@kernel.org> Link: https://patch.msgid.link/20241115204308.3821419-1-kees@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
This reverts commit 3bd9b9abdf1563a22041b7255baea6d449902f1a. We cannot
use the new tagged struct group because it throws C++ errors even under
"extern C".

Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20241115204308.3821419-1-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: ethtool: account for RSS+RXNFC add semantics when checking channel count 2024-11-15T03:53:42+00:00 Edward Cree ecree.xilinx@gmail.com 2024-11-13T12:13:10+00:00 a64499f618b2e3ace083727237f8802aabc73008 In ethtool_check_max_channel(), the new RX count must not only cover the max queue indices in RSS indirection tables and RXNFC destinations separately, but must also, for RXNFC rules with FLOW_RSS, cover the sum of the destination queue and the maximum index in the associated RSS context's indirection table, since that is the highest queue that the rule can actually deliver traffic to. It could be argued that the max queue across all custom RSS contexts (ethtool_get_max_rss_ctx_channel()) need no longer be considered, since any context to which packets can actually be delivered will be targeted by some RXNFC rule and its max will thus be allowed for by ethtool_get_max_rxnfc_channel(). For simplicity we keep both checks, so even RSS contexts unused by any RXNFC rule must fit the channel count. Signed-off-by: Edward Cree <ecree.xilinx@gmail.com> Link: https://patch.msgid.link/43257d375434bef388e36181492aa4c458b88336.1731499022.git.ecree.xilinx@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
In ethtool_check_max_channel(), the new RX count must not only cover the
 max queue indices in RSS indirection tables and RXNFC destinations
 separately, but must also, for RXNFC rules with FLOW_RSS, cover the sum
 of the destination queue and the maximum index in the associated RSS
 context's indirection table, since that is the highest queue that the
 rule can actually deliver traffic to.
It could be argued that the max queue across all custom RSS contexts
 (ethtool_get_max_rss_ctx_channel()) need no longer be considered, since
 any context to which packets can actually be delivered will be targeted
 by some RXNFC rule and its max will thus be allowed for by
 ethtool_get_max_rxnfc_channel().  For simplicity we keep both checks, so
 even RSS contexts unused by any RXNFC rule must fit the channel count.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/43257d375434bef388e36181492aa4c458b88336.1731499022.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in 2024-11-15T03:53:41+00:00 Edward Cree ecree.xilinx@gmail.com 2024-11-13T12:13:09+00:00 9e43ad7a1edef268acac603e1975c8f50a20d02f Ethtool ntuple filters with FLOW_RSS were originally defined as adding the base queue ID (ring_cookie) to the value from the indirection table, so that the same table could distribute over more than one set of queues when used by different filters. However, some drivers / hardware ignore the ring_cookie, and simply use the indirection table entries as queue IDs directly. Thus, for drivers which have not opted in by setting ethtool_ops.cap_rss_rxnfc_adds to declare that they support the original (addition) semantics, reject in ethtool_set_rxnfc any filter which combines FLOW_RSS and a nonzero ring. (For a ring_cookie of zero, both behaviours are equivalent.) Set the cap bit in sfc, as it is known to support this feature. Signed-off-by: Edward Cree <ecree.xilinx@gmail.com> Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com> Link: https://patch.msgid.link/cc3da0844083b0e301a33092a6299e4042b65221.1731499022.git.ecree.xilinx@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
Ethtool ntuple filters with FLOW_RSS were originally defined as adding
 the base queue ID (ring_cookie) to the value from the indirection table,
 so that the same table could distribute over more than one set of queues
 when used by different filters.
However, some drivers / hardware ignore the ring_cookie, and simply use
 the indirection table entries as queue IDs directly.  Thus, for drivers
 which have not opted in by setting ethtool_ops.cap_rss_rxnfc_adds to
 declare that they support the original (addition) semantics, reject in
 ethtool_set_rxnfc any filter which combines FLOW_RSS and a nonzero ring.
(For a ring_cookie of zero, both behaviours are equivalent.)
Set the cap bit in sfc, as it is known to support this feature.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://patch.msgid.link/cc3da0844083b0e301a33092a6299e4042b65221.1731499022.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net: ethtool: Avoid thousands of -Wflex-array-member-not-at-end warnings 2024-11-03T19:06:58+00:00 Gustavo A. R. Silva gustavoars@kernel.org 2024-10-29T21:58:47+00:00 3bd9b9abdf1563a22041b7255baea6d449902f1a -Wflex-array-member-not-at-end was introduced in GCC-14, and we are getting ready to enable it, globally. Change the type of the middle struct member currently causing trouble from `struct ethtool_link_settings` to `struct ethtool_link_settings_hdr`. Additionally, update the type of some variables in various functions that don't access the flexible-array member, changing them to the newly created `struct ethtool_link_settings_hdr`. These changes are needed because the type of the conflicting middle members changed. So, those instances that expect the type to be `struct ethtool_link_settings` should be adjusted to the newly created type `struct ethtool_link_settings_hdr`. Also, adjust variable declarations to follow the reverse xmas tree convention. Fix 3338 of the following -Wflex-array-member-not-at-end warnings: include/linux/ethtool.h:214:38: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end] Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org> Link: https://patch.msgid.link/0bc2809fe2a6c11dd4c8a9a10d9bd65cccdb559b.1730238285.git.gustavoars@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org> 
-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Change the type of the middle struct member currently causing trouble from
`struct ethtool_link_settings` to `struct ethtool_link_settings_hdr`.

Additionally, update the type of some variables in various functions that
don't access the flexible-array member, changing them to the newly created
`struct ethtool_link_settings_hdr`. These changes are needed because the
type of the conflicting middle members changed. So, those instances that
expect the type to be `struct ethtool_link_settings` should be adjusted to
the newly created type `struct ethtool_link_settings_hdr`.

Also, adjust variable declarations to follow the reverse xmas tree
convention.

Fix 3338 of the following -Wflex-array-member-not-at-end warnings:

include/linux/ethtool.h:214:38: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/0bc2809fe2a6c11dd4c8a9a10d9bd65cccdb559b.1730238285.git.gustavoars@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ethtool: rss: prevent rss ctx deletion when in use 2024-10-17T08:22:01+00:00 Daniel Zahka daniel.zahka@gmail.com 2024-10-11T18:35:47+00:00 42dc431f5d0ea9e9c9caf74dcb5b290ce4dd80b4 ntuple filters can specify an rss context to use for packet hashing and queue selection. When a filter is referencing an rss context, it should be invalid for that context to be deleted. A list of active ntuple filters and their associated rss contexts can be compiled by querying a device's ethtool_ops.get_rxnfc. This patch checks to see if any ntuple filters are referencing an rss context during context deletion, and prevents the deletion if the requested context is still in use. Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> 
ntuple filters can specify an rss context to use for packet hashing
and queue selection. When a filter is referencing an rss context, it
should be invalid for that context to be deleted. A list of active
ntuple filters and their associated rss contexts can be compiled by
querying a device's ethtool_ops.get_rxnfc. This patch checks to see if
any ntuple filters are referencing an rss context during context
deletion, and prevents the deletion if the requested context is still
in use.

Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
net: ethtool: Add support for writing firmware blocks using EPL payload 2024-10-13T17:02:50+00:00 Danielle Ratson danieller@nvidia.com 2024-10-09T10:53:47+00:00 9a3b0d078bd825613c0821bf7bf5a2e1d8d60057 In the CMIS specification for pluggable modules, LPL (Local Payload) and EPL (Extended Payload) are two types of data payloads used for managing various functions and features of the module. EPL payloads are used for more complex and extensive management functions that require a larger amount of data, so writing firmware blocks using EPL is much more efficient. Currently, only LPL payload is supported for writing firmware blocks to the module. Add support for writing firmware block using EPL payload, both to support modules that supports only EPL write mechanism, and to optimize the flashing process of modules that support LPL and EPL. Signed-off-by: Danielle Ratson <danieller@nvidia.com> Reviewed-by: Petr Machata <petrm@nvidia.com> Reviewed-by: Simon Horman <horms@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
In the CMIS specification for pluggable modules, LPL (Local Payload) and
EPL (Extended Payload) are two types of data payloads used for managing
various functions and features of the module.

EPL payloads are used for more complex and extensive management
functions that require a larger amount of data, so writing firmware
blocks using EPL is much more efficient.

Currently, only LPL payload is supported for writing firmware blocks to
the module.

Add support for writing firmware block using EPL payload, both to
support modules that supports only EPL write mechanism, and to optimize
the flashing process of modules that support LPL and EPL.

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>