linux-stable.git/net/ethtool/ioctl.c, branch linux-6.10.y

ethtool: fail closed if we can't get max channel used in indirection tables

2024-09-12T09:13:02+00:00

[ Upstream commit 2899d58462ba868287d6ff3acad3675e7adf934f ]

Commit 0d1b7d6c9274 ("bnxt: fix crashes when reducing ring count with
active RSS contexts") proves that allowing indirection table to contain
channels with out of bounds IDs may lead to crashes. Currently the
max channel check in the core gets skipped if driver can't fetch
the indirection table or when we can't allocate memory.

Both of those conditions should be extremely rare but if they do
happen we should try to be safe and fail the channel change.

Reviewed-by: Jacob Keller 
Link: https://patch.msgid.link/20240710174043.754664-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

ethtool: check device is present when getting link settings

2024-09-04T11:30:09+00:00

[ Upstream commit a699781c79ecf6cfe67fb00a0331b4088c7c8466 ]

A sysfs reader can race with a device reset or removal, attempting to
read device state when the device is not actually present. eg:

     [exception RIP: qed_get_current_link+17]
  #8 [ffffb9e4f2907c48] qede_get_link_ksettings at ffffffffc07a994a [qede]
  #9 [ffffb9e4f2907cd8] __rh_call_get_link_ksettings at ffffffff992b01a3
 #10 [ffffb9e4f2907d38] __ethtool_get_link_ksettings at ffffffff992b04e4
 #11 [ffffb9e4f2907d90] duplex_show at ffffffff99260300
 #12 [ffffb9e4f2907e38] dev_attr_show at ffffffff9905a01c
 #13 [ffffb9e4f2907e50] sysfs_kf_seq_show at ffffffff98e0145b
 #14 [ffffb9e4f2907e68] seq_read at ffffffff98d902e3
 #15 [ffffb9e4f2907ec8] vfs_read at ffffffff98d657d1
 #16 [ffffb9e4f2907f00] ksys_read at ffffffff98d65c3f
 #17 [ffffb9e4f2907f38] do_syscall_64 at ffffffff98a052fb

 crash> struct net_device.state ffff9a9d21336000
    state = 5,

state 5 is __LINK_STATE_START (0b1) and __LINK_STATE_NOCARRIER (0b100).
The device is not present, note lack of __LINK_STATE_PRESENT (0b10).

This is the same sort of panic as observed in commit 4224cfd7fb65
("net-sysfs: add check for netdevice being present to speed_show").

There are many other callers of __ethtool_get_link_ksettings() which
don't have a device presence check.

Move this check into ethtool to protect all callers.

Fixes: d519e17e2d01 ("net: export device speed and duplex via sysfs")
Fixes: 4224cfd7fb65 ("net-sysfs: add check for netdevice being present to speed_show")
Signed-off-by: Jamie Bainbridge 
Link: https://patch.msgid.link/8bae218864beaa44ed01628140475b9bf641c5b0.1724393671.git.jamie.bainbridge@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

ethtool: fix setting key and resetting indir at once

2024-08-11T10:57:51+00:00

[ Upstream commit 7195f0ef7f5b8c678cf28de7c9b619cb908b482c ]

The indirection table and the key follow struct ethtool_rxfh
in user memory.

To reset the indirection table user space calls SET_RXFH with
table of size 0 (OTOH to say "no change" it should use -1 / ~0).
The logic for calculating the offset where they key sits is
incorrect in this case, as kernel would still offset by the full
table length, while for the reset there is no indir table and
key is immediately after the struct.

  $ ethtool -X eth0 default hkey 01:02:03...
  $ ethtool -x eth0
  [...]
  RSS hash key:
00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00
  [...]

Fixes: 3de0b592394d ("ethtool: Support for configurable RSS hash key")
Signed-off-by: Jakub Kicinski 
Signed-off-by: David S. Miller 
Signed-off-by: Sasha Levin

net: ethtool: Fix RSS setting

2024-07-12T00:21:08+00:00

When user submits a rxfh set command without touching XFRM_SYM_XOR,
rxfh.input_xfrm is set to RXH_XFRM_NO_CHANGE, which is equal to 0xff.

Testing if (rxfh.input_xfrm & RXH_XFRM_SYM_XOR &&
	    !ops->cap_rss_sym_xor_supported)
		return -EOPNOTSUPP;

Will always be true on devices that don't set cap_rss_sym_xor_supported,
since rxfh.input_xfrm & RXH_XFRM_SYM_XOR is always true, if input_xfrm
was not set, i.e RXH_XFRM_NO_CHANGE=0xff, which will result in failure
of any command that doesn't require any change of XFRM, e.g RSS context
or hash function changes.

To avoid this breakage, test if rxfh.input_xfrm != RXH_XFRM_NO_CHANGE
before testing other conditions. Note that the problem will only trigger
with XFRM-aware userspace, old ethtool CLI would continue to work.

Fixes: 0dd415d15505 ("net: ethtool: add a NO_CHANGE uAPI for new RXFH's input_xfrm")
Signed-off-by: Saeed Mahameed 
Reviewed-by: Ahmed Zaki 
Link: https://patch.msgid.link/20240710225538.43368-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski

net: ethtool: fix the error condition in ethtool_get_phy_stats_ethtool()

2024-06-06T11:34:33+00:00

Clang static checker (scan-build) warning:
net/ethtool/ioctl.c:line 2233, column 2
Called function pointer is null (null dereference).

Return '-EOPNOTSUPP' when 'ops->get_ethtool_phy_stats' is NULL to fix
this typo error.

Fixes: 201ed315f967 ("net/ethtool/ioctl: split ethtool_get_phy_stats into multiple helpers")
Signed-off-by: Su Hui 
Reviewed-by: Przemek Kitszel 
Reviewed-by: Hariprasad Kelam 
Link: https://lore.kernel.org/r/20240605034742.921751-1-suhui@nfschina.com
Signed-off-by: Paolo Abeni

ethtool: ignore unused/unreliable fields in set_eee op

2024-03-06T03:07:13+00:00

This function is used with the set_eee() ethtool operation. Certain
fields of struct ethtool_keee() are relevant only for the get_eee()
operation. In addition, in case of the ioctl interface, we have no
guarantee that userspace sends sane values in struct ethtool_eee.
Therefore explicitly ignore all fields not needed for set_eee().
This protects from drivers trying to use unchecked and unreliable
data, relying on specific userspace behavior.

Note: Such unsafe driver behavior has been found and fixed in the
tg3 driver.

Signed-off-by: Heiner Kallweit 
Reviewed-by: Andrew Lunn 
Link: https://lore.kernel.org/r/ad7ee11e-eb7a-4975-9122-547e13a161d8@gmail.com
Signed-off-by: Jakub Kicinski

net: ethtool: eee: Remove legacy _u32 from keee

2024-02-28T12:18:05+00:00

All MAC drivers have been converted to use the link mode members of
keee. So remove the _u32 values, and the code in the ethtool core to
convert the legacy _u32 values to link modes.

Reviewed-by: Simon Horman 
Signed-off-by: Andrew Lunn 
Signed-off-by: David S. Miller

net: ethtool: avoid rebuilds on UTS_RELEASE change

2024-02-24T00:22:25+00:00

Currently, when you switch between branches or something like that and
rebuild, net/ethtool/ioctl.c has to be built again because it depends
on UTS_RELEASE.

By instead referencing a string variable stored in another object file,
this can be avoided.

Signed-off-by: Jann Horn 
Reviewed-by: John Garry 
Link: https://lore.kernel.org/r/20240220194244.2056384-1-jannh@google.com
Signed-off-by: Jakub Kicinski

ethtool: add linkmode bitmap support to struct ethtool_keee

2024-01-31T12:30:47+00:00

Add linkmode bitmap members to struct ethtool_keee, but keep the legacy
u32 bitmaps for compatibility with existing drivers.
Use linkmode "supported" not being empty as indicator that a user wants
to use the linkmode bitmap members instead of the legacy bitmaps.

Signed-off-by: Heiner Kallweit 
Reviewed-by: Andrew Lunn 
Signed-off-by: David S. Miller

ethtool: add suffix _u32 to legacy bitmap members of struct ethtool_keee

2024-01-31T12:30:47+00:00

This is in preparation of using the existing names for linkmode
bitmaps.

Suggested-by: Andrew Lunn 
Signed-off-by: Heiner Kallweit 
Reviewed-by: Andrew Lunn 
Signed-off-by: David S. Miller