Cross-merge networking fixes after downstream PR.
No conflicts (sort of) and no adjacent changes.
This merge reverts commit b3c9e65eb2 ("net: hsr: remove seqnr_lock")
from net, as it was superseded by
commit 430d67bdcb ("net: hsr: Use the seqnr lock for frames received via interlink port.")
in net-next.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The description of function ice_find_vsi_list_entry says:
Search VSI list map with VSI count 1
However, since the blamed commit (see Fixes below), the function no
longer checks vsi_count. This causes a problem in ice_add_vlan_internal,
where the decision to share VSI lists between filter rules relies on the
vsi_count of the found existing VSI list being 1.
The reproducing steps:
1. Have a PF and two VFs.
There will be a filter rule for VLAN 0, referring to a VSI list
containing VSIs: 0 (PF), 2 (VF#0), 3 (VF#1).
2. Add VLAN 1234 to VF#0.
ice will make the wrong decision to share the VSI list with the new
rule. The wrong behavior may not be immediately apparent, but it can
be observed with debug prints.
3. Add VLAN 1234 to VF#1.
ice will unshare the VSI list for the VLAN 1234 rule. Due to the
earlier bad decision, the newly created VSI list will contain
VSIs 0 (PF) and 3 (VF#1), instead of expected 2 (VF#0) and 3 (VF#1).
4. Try pinging a network peer over the VLAN interface on VF#0.
This fails.
Reproducer script at:
https://gitlab.com/mschmidt2/repro/-/blob/master/RHEL-46814/test-vlan-vsi-list-confusion.sh
Commented debug trace:
https://gitlab.com/mschmidt2/repro/-/blob/master/RHEL-46814/ice-vlan-vsi-lists-debug.txt
Patch adding the debug prints:
f8a8814623
(Unsafe, by the way. Lacks rule_lock when dumping in ice_remove_vlan.)
Michal Swiatkowski added to the explanation that the bug is caused by
reusing a VSI list created for VLAN 0. All created VFs' VSIs are added
to VLAN 0 filter. When a non-zero VLAN is created on a VF which is already
in VLAN 0 (normal case), the VSI list from VLAN 0 is reused.
It leads to a problem because all VFs (VSIs to be specific) that are
subscribed to VLAN 0 will now receive a new VLAN tag traffic. This is
one bug, another is the bug described above. Removing filters from
one VF will remove VLAN filter from the previous VF. It happens a VF is
reset. Example:
- creation of 3 VFs
- we have VSI list (used for VLAN 0) [0 (pf), 2 (vf1), 3 (vf2), 4 (vf3)]
- we are adding VLAN 100 on VF1, we are reusing the previous list
because 2 is there
- VLAN traffic works fine, but VLAN 100 tagged traffic can be received
on all VSIs from the list (for example broadcast or unicast)
- trust is turning on VF2, VF2 is resetting, all filters from VF2 are
removed; the VLAN 100 filter is also removed because 3 is on the list
- VLAN traffic to VF1 isn't working anymore, there is a need to recreate
VLAN interface to readd VLAN filter
One thing I'm not certain about is the implications for the LAG feature,
which is another caller of ice_find_vsi_list_entry. I don't have a
LAG-capable card at hand to test.
Fixes: 23ccae5ce1 ("ice: changes to the interface with the HW and FW for SRIOV_VF+LAG")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Dave Ertman <David.m.ertman@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Our driver uses devres to manage resources, in particular we call
pcim_enable_device(), what also means we express the intent to get
automatic pci_disable_device() call at driver removal. Manual calls to
pci_disable_device() misuse the API.
Recent commit (see "Fixes" tag) has changed the removal action from
conditional (silent ignore of double call to pci_disable_device()) to
unconditional, but able to catch unwanted redundant calls; see cited
"Fixes" commit for details.
Since that, unloading the driver yields following warn+splat:
[70633.628490] ice 0000:af:00.7: disabling already-disabled device
[70633.628512] WARNING: CPU: 52 PID: 33890 at drivers/pci/pci.c:2250 pci_disable_device+0xf4/0x100
...
[70633.628744] ? pci_disable_device+0xf4/0x100
[70633.628752] release_nodes+0x4a/0x70
[70633.628759] devres_release_all+0x8b/0xc0
[70633.628768] device_unbind_cleanup+0xe/0x70
[70633.628774] device_release_driver_internal+0x208/0x250
[70633.628781] driver_detach+0x47/0x90
[70633.628786] bus_remove_driver+0x80/0x100
[70633.628791] pci_unregister_driver+0x2a/0xb0
[70633.628799] ice_module_exit+0x11/0x3a [ice]
Note that this is the only Intel ethernet driver that needs such fix.
Fixes: f748a07a0b ("PCI: Remove legacy pcim_release()")
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
When adding a switch filter (such as a MAC or VLAN filter), it is expected
that the driver will detect the case where the filter already exists, and
return -EEXIST. This is used by calling code such as ice_vc_add_mac_addr,
and ice_vsi_add_vlan to avoid incrementing the accounting fields such as
vsi->num_vlan or vf->num_mac.
This logic works correctly for the case where only a single VSI has added a
given switch filter.
When a second VSI adds the same switch filter, the driver converts the
existing filter from an ICE_FWD_TO_VSI filter into an ICE_FWD_TO_VSI_LIST
filter. This saves switch resources, by ensuring that multiple VSIs can
re-use the same filter.
The ice_add_update_vsi_list() function is responsible for doing this
conversion. When first converting a filter from the FWD_TO_VSI into
FWD_TO_VSI_LIST, it checks if the VSI being added is the same as the
existing rule's VSI. In such a case it returns -EEXIST.
However, when the switch rule has already been converted to a
FWD_TO_VSI_LIST, the logic is different. Adding a new VSI in this case just
requires extending the VSI list entry. The logic for checking if the rule
already exists in this case returns 0 instead of -EEXIST.
This breaks the accounting logic mentioned above, so the counters for how
many MAC and VLAN filters exist for a given VF or VSI no longer accurately
reflect the actual count. This breaks other code which relies on these
counts.
In typical usage this primarily affects such filters generally shared by
multiple VSIs such as VLAN 0, or broadcast and multicast MAC addresses.
Fix this by correctly reporting -EEXIST in the case of adding the same VSI
to a switch rule already converted to ICE_FWD_TO_VSI_LIST.
Fixes: 9daf8208dd ("ice: Add support for switch filter programming")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
After vsi setup refactor commit 6624e780a5 ("ice: split ice_vsi_setup
into smaller functions") ice_cfg_sw_lldp function which removes rx rule
directing LLDP packets to vsi is moved from ice_vsi_release to
ice_vsi_decfg function. ice_vsi_decfg is used in more cases than just in
vsi_release resulting in unnecessary removal of rx lldp packets handling
switch rule. This leads to lldp packets being dropped after a change number
of channels via ethtool.
This patch moves ice_cfg_sw_lldp function that removes rx lldp sw rule back
to ice_vsi_release function.
Fixes: 6624e780a5 ("ice: split ice_vsi_setup into smaller functions")
Reported-by: Matěj Grégr <mgregr@netx.as>
Closes: https://lore.kernel.org/intel-wired-lan/1be45a76-90af-4813-824f-8398b69745a9@netx.as/T/#u
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Flow for creating Tx topology is the same as for VF port representors,
but the devlink port is stored in different place (sf->devlink_port).
When creating VF devlink lock isn't taken, when creating subfunction it
is. Setting Tx topology function needs to take this lock, check if it
was taken before to not do it twice.
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Implement attaching and detaching SF port representor. It is done in the
same way as the VF port representor.
SF port representor is always added or removed with devlink
lock taken.
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Keep the same flow of port representor creation, but instead of general
attach function create helpers for specific representor type.
Store function pointer for add and remove representor.
Type of port representor can be also known based on VSI type, but it
is more clean to have it directly saved in port representor structure.
Add devlink lock for whole port representor creation and destruction.
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Implement subfunction driver. It is probe when subfunction port is
activated.
VSI is already created. During the probe VSI is being configured.
MAC unicast and broadcast filter is added to allow traffic to pass.
Store subfunction pointer in VSI struct. The same is done for VF
pointer. Make union of subfunction and VF pointer as only one of them
can be set with one VSI.
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
When subfunction VSI is open the same code as for PF VSI should be
executed. Also when up is complete. Reflect that in code by adding
subfunction VSI to consideration.
In case of stopping, PF doesn't have additional tasks, so the same
is with subfunction VSI.
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Implement devlink port handlers responsible for ethernet type devlink
subfunctions. Create subfunction devlink port and setup all resources
needed for a subfunction netdev to operate. Configure new VSI for each
new subfunction, initialize and configure interrupts and Tx/Rx resources.
Set correct MAC filters and create new netdev.
For now, subfunction is limited to only one Tx/Rx queue pair.
Only allocate new subfunction VSI with devlink port new command.
Allocate and free subfunction MSIX interrupt vectors using new API
calls with pci_msix_alloc_irq_at and pci_msix_free_irq.
Support both automatic and manual subfunction numbers. If no subfunction
number is provided, use xa_alloc to pick a number automatically. This
will find the first free index and use that as the number. This reduces
burden on users in the simple case where a specific number is not
required. It may also be slightly faster to check that a number exists
since xarray lookup should be faster than a linear scan of the dyn_ports
xarray.
Co-developed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Locking used in ice_qp_ena() and ice_qp_dis() does pretty much nothing,
because ICE_CFG_BUSY is a state flag that is supposed to be set in a PF
state, not VSI one. Therefore it does not protect the queue pair from
e.g. reset.
Remove ICE_CFG_BUSY locking from ice_qp_dis() and ice_qp_ena().
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Consider the following scenario:
.ndo_bpf() | ice_prepare_for_reset() |
________________________|_______________________________________|
rtnl_lock() | |
ice_down() | |
| test_bit(ICE_VSI_DOWN) - true |
| ice_dis_vsi() returns |
ice_up() | |
| proceeds to rebuild a running VSI |
.ndo_bpf() is not the only rtnl-locked callback that toggles the interface
to apply new configuration. Another example is .set_channels().
To avoid the race condition above, act only after reading ICE_VSI_DOWN
under rtnl_lock.
Fixes: 0f9d5027a7 ("ice: Refactor VSI allocation, deletion and rebuild flow")
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
If VSI rebuild is pending, .ndo_bpf() can attach/detach the XDP program on
VSI without applying new ring configuration. When unconfiguring the VSI, we
can encounter the state in which there is an XDP program but no XDP rings
to destroy or there will be XDP rings that need to be destroyed, but no XDP
program to indicate their presence.
When unconfiguring, rely on the presence of XDP rings rather then XDP
program, as they better represent the current state that has to be
destroyed.
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The main threat to data consistency in ice_xdp() is a possible asynchronous
PF reset. It can be triggered by a user or by TX timeout handler.
XDP setup and PF reset code access the same resources in the following
sections:
* ice_vsi_close() in ice_prepare_for_reset() - already rtnl-locked
* ice_vsi_rebuild() for the PF VSI - not protected
* ice_vsi_open() - already rtnl-locked
With an unfortunate timing, such accesses can result in a crash such as the
one below:
[ +1.999878] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 14
[ +2.002992] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 18
[Mar15 18:17] ice 0000:b1:00.0 ens801f0np0: NETDEV WATCHDOG: CPU: 38: transmit queue 14 timed out 80692736 ms
[ +0.000093] ice 0000:b1:00.0 ens801f0np0: tx_timeout: VSI_num: 6, Q 14, NTC: 0x0, HW_HEAD: 0x0, NTU: 0x0, INT: 0x4000001
[ +0.000012] ice 0000:b1:00.0 ens801f0np0: tx_timeout recovery level 1, txqueue 14
[ +0.394718] ice 0000:b1:00.0: PTP reset successful
[ +0.006184] BUG: kernel NULL pointer dereference, address: 0000000000000098
[ +0.000045] #PF: supervisor read access in kernel mode
[ +0.000023] #PF: error_code(0x0000) - not-present page
[ +0.000023] PGD 0 P4D 0
[ +0.000018] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ +0.000023] CPU: 38 PID: 7540 Comm: kworker/38:1 Not tainted 6.8.0-rc7 #1
[ +0.000031] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021
[ +0.000036] Workqueue: ice ice_service_task [ice]
[ +0.000183] RIP: 0010:ice_clean_tx_ring+0xa/0xd0 [ice]
[...]
[ +0.000013] Call Trace:
[ +0.000016] <TASK>
[ +0.000014] ? __die+0x1f/0x70
[ +0.000029] ? page_fault_oops+0x171/0x4f0
[ +0.000029] ? schedule+0x3b/0xd0
[ +0.000027] ? exc_page_fault+0x7b/0x180
[ +0.000022] ? asm_exc_page_fault+0x22/0x30
[ +0.000031] ? ice_clean_tx_ring+0xa/0xd0 [ice]
[ +0.000194] ice_free_tx_ring+0xe/0x60 [ice]
[ +0.000186] ice_destroy_xdp_rings+0x157/0x310 [ice]
[ +0.000151] ice_vsi_decfg+0x53/0xe0 [ice]
[ +0.000180] ice_vsi_rebuild+0x239/0x540 [ice]
[ +0.000186] ice_vsi_rebuild_by_type+0x76/0x180 [ice]
[ +0.000145] ice_rebuild+0x18c/0x840 [ice]
[ +0.000145] ? delay_tsc+0x4a/0xc0
[ +0.000022] ? delay_tsc+0x92/0xc0
[ +0.000020] ice_do_reset+0x140/0x180 [ice]
[ +0.000886] ice_service_task+0x404/0x1030 [ice]
[ +0.000824] process_one_work+0x171/0x340
[ +0.000685] worker_thread+0x277/0x3a0
[ +0.000675] ? preempt_count_add+0x6a/0xa0
[ +0.000677] ? _raw_spin_lock_irqsave+0x23/0x50
[ +0.000679] ? __pfx_worker_thread+0x10/0x10
[ +0.000653] kthread+0xf0/0x120
[ +0.000635] ? __pfx_kthread+0x10/0x10
[ +0.000616] ret_from_fork+0x2d/0x50
[ +0.000612] ? __pfx_kthread+0x10/0x10
[ +0.000604] ret_from_fork_asm+0x1b/0x30
[ +0.000604] </TASK>
The previous way of handling this through returning -EBUSY is not viable,
particularly when destroying AF_XDP socket, because the kernel proceeds
with removal anyway.
There is plenty of code between those calls and there is no need to create
a large critical section that covers all of them, same as there is no need
to protect ice_vsi_rebuild() with rtnl_lock().
Add xdp_state_lock mutex to protect ice_vsi_rebuild() and ice_xdp().
Leaving unprotected sections in between would result in two states that
have to be considered:
1. when the VSI is closed, but not yet rebuild
2. when VSI is already rebuild, but not yet open
The latter case is actually already handled through !netif_running() case,
we just need to adjust flag checking a little. The former one is not as
trivial, because between ice_vsi_close() and ice_vsi_rebuild(), a lot of
hardware interaction happens, this can make adding/deleting rings exit
with an error. Luckily, VSI rebuild is pending and can apply new
configuration for us in a managed fashion.
Therefore, add an additional VSI state flag ICE_VSI_REBUILD_PENDING to
indicate that ice_xdp() can just hot-swap the program.
Also, as ice_vsi_rebuild() flow is touched in this patch, make it more
consistent by deconfiguring VSI when coalesce allocation fails.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Fixes: efc2214b60 ("ice: Add support for XDP")
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Currently, netif_queue_set_napi() is called from ice_vsi_rebuild() that is
not rtnl-locked when called from the reset. This creates the need to take
the rtnl_lock just for a single function and complicates the
synchronization with .ndo_bpf. At the same time, there no actual need to
fill napi-to-queue information at this exact point.
Fill napi-to-queue information when opening the VSI and clear it when the
VSI is being closed. Those routines are already rtnl-locked.
Also, rewrite napi-to-queue assignment in a way that prevents inclusion of
XDP queues, as this leads to out-of-bounds writes, such as one below.
[ +0.000004] BUG: KASAN: slab-out-of-bounds in netif_queue_set_napi+0x1c2/0x1e0
[ +0.000012] Write of size 8 at addr ffff889881727c80 by task bash/7047
[ +0.000006] CPU: 24 PID: 7047 Comm: bash Not tainted 6.10.0-rc2+ #2
[ +0.000004] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021
[ +0.000003] Call Trace:
[ +0.000003] <TASK>
[ +0.000002] dump_stack_lvl+0x60/0x80
[ +0.000007] print_report+0xce/0x630
[ +0.000007] ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[ +0.000007] ? __virt_addr_valid+0x1c9/0x2c0
[ +0.000005] ? netif_queue_set_napi+0x1c2/0x1e0
[ +0.000003] kasan_report+0xe9/0x120
[ +0.000004] ? netif_queue_set_napi+0x1c2/0x1e0
[ +0.000004] netif_queue_set_napi+0x1c2/0x1e0
[ +0.000005] ice_vsi_close+0x161/0x670 [ice]
[ +0.000114] ice_dis_vsi+0x22f/0x270 [ice]
[ +0.000095] ice_pf_dis_all_vsi.constprop.0+0xae/0x1c0 [ice]
[ +0.000086] ice_prepare_for_reset+0x299/0x750 [ice]
[ +0.000087] pci_dev_save_and_disable+0x82/0xd0
[ +0.000006] pci_reset_function+0x12d/0x230
[ +0.000004] reset_store+0xa0/0x100
[ +0.000006] ? __pfx_reset_store+0x10/0x10
[ +0.000002] ? __pfx_mutex_lock+0x10/0x10
[ +0.000004] ? __check_object_size+0x4c1/0x640
[ +0.000007] kernfs_fop_write_iter+0x30b/0x4a0
[ +0.000006] vfs_write+0x5d6/0xdf0
[ +0.000005] ? fd_install+0x180/0x350
[ +0.000005] ? __pfx_vfs_write+0x10/0xA10
[ +0.000004] ? do_fcntl+0x52c/0xcd0
[ +0.000004] ? kasan_save_track+0x13/0x60
[ +0.000003] ? kasan_save_free_info+0x37/0x60
[ +0.000006] ksys_write+0xfa/0x1d0
[ +0.000003] ? __pfx_ksys_write+0x10/0x10
[ +0.000002] ? __x64_sys_fcntl+0x121/0x180
[ +0.000004] ? _raw_spin_lock+0x87/0xe0
[ +0.000005] do_syscall_64+0x80/0x170
[ +0.000007] ? _raw_spin_lock+0x87/0xe0
[ +0.000004] ? __pfx__raw_spin_lock+0x10/0x10
[ +0.000003] ? file_close_fd_locked+0x167/0x230
[ +0.000005] ? syscall_exit_to_user_mode+0x7d/0x220
[ +0.000005] ? do_syscall_64+0x8c/0x170
[ +0.000004] ? do_syscall_64+0x8c/0x170
[ +0.000003] ? do_syscall_64+0x8c/0x170
[ +0.000003] ? fput+0x1a/0x2c0
[ +0.000004] ? filp_close+0x19/0x30
[ +0.000004] ? do_dup2+0x25a/0x4c0
[ +0.000004] ? __x64_sys_dup2+0x6e/0x2e0
[ +0.000002] ? syscall_exit_to_user_mode+0x7d/0x220
[ +0.000004] ? do_syscall_64+0x8c/0x170
[ +0.000003] ? __count_memcg_events+0x113/0x380
[ +0.000005] ? handle_mm_fault+0x136/0x820
[ +0.000005] ? do_user_addr_fault+0x444/0xa80
[ +0.000004] ? clear_bhb_loop+0x25/0x80
[ +0.000004] ? clear_bhb_loop+0x25/0x80
[ +0.000002] entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ +0.000005] RIP: 0033:0x7f2033593154
Fixes: 080b0c8d6d ("ice: Fix ASSERT_RTNL() warning during certain scenarios")
Fixes: 91fdbce7e8 ("ice: Add support in the driver for associating queue with napi")
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Ethtool callbacks can be executed while reset is in progress and try to
access deleted resources, e.g. getting coalesce settings can result in a
NULL pointer dereference seen below.
Reproduction steps:
Once the driver is fully initialized, trigger reset:
# echo 1 > /sys/class/net/<interface>/device/reset
when reset is in progress try to get coalesce settings using ethtool:
# ethtool -c <interface>
BUG: kernel NULL pointer dereference, address: 0000000000000020
PGD 0 P4D 0
Oops: Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 11 PID: 19713 Comm: ethtool Tainted: G S 6.10.0-rc7+ #7
RIP: 0010:ice_get_q_coalesce+0x2e/0xa0 [ice]
RSP: 0018:ffffbab1e9bcf6a8 EFLAGS: 00010206
RAX: 000000000000000c RBX: ffff94512305b028 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff9451c3f2e588 RDI: ffff9451c3f2e588
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: ffff9451c3f2e580 R11: 000000000000001f R12: ffff945121fa9000
R13: ffffbab1e9bcf760 R14: 0000000000000013 R15: ffffffff9e65dd40
FS: 00007faee5fbe740(0000) GS:ffff94546fd80000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000020 CR3: 0000000106c2e005 CR4: 00000000001706f0
Call Trace:
<TASK>
ice_get_coalesce+0x17/0x30 [ice]
coalesce_prepare_data+0x61/0x80
ethnl_default_doit+0xde/0x340
genl_family_rcv_msg_doit+0xf2/0x150
genl_rcv_msg+0x1b3/0x2c0
netlink_rcv_skb+0x5b/0x110
genl_rcv+0x28/0x40
netlink_unicast+0x19c/0x290
netlink_sendmsg+0x222/0x490
__sys_sendto+0x1df/0x1f0
__x64_sys_sendto+0x24/0x30
do_syscall_64+0x82/0x160
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7faee60d8e27
Calling netif_device_detach() before reset makes the net core not call
the driver when ethtool command is issued, the attempt to execute an
ethtool command during reset will result in the following message:
netlink error: No such device
instead of NULL pointer dereference. Once reset is done and
ice_rebuild() is executing, the netif_device_attach() is called to allow
for ethtool operations to occur again in a safe manner.
Fixes: fcea6f3da5 ("ice: Add stats and ethtool support")
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Igor Bagnucki <igor.bagnucki@intel.com>
Signed-off-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Reviewed-by: Michal Schmidt <mschmidt@redhat.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2024-08-26 (ice)
This series contains updates to ice driver only.
Jake implements and uses rd32_poll_timeout to replace a jiffies loop for
calling ice_sq_done. The rd32_poll_timeout() function is designed to allow
simplifying other places in the driver where we need to read a register
until it matches a known value.
Jake, Bruce, and Przemek update ice_debug_cq() to be more robust, and more
useful for tracing control queue messages sent and received by the device
driver.
Jake rewords several commands in the ice_control.c file which previously
referred to the "Admin queue" when they were actually generic functions
usable on any control queue.
Jake removes the unused and unnecessary cmd_buf array allocation for send
queues. This logic originally was going to be useful if we ever implemented
asynchronous completion of transmit messages. This support is unlikely to
materialize, so the overhead of allocating a command buffer is unnecessary.
Sergey improves the log messages when the ice driver reports that the NVM
version on the device is not supported by the driver. Now, these messages
include both the discovered NVM version and the requested/expected NVM
version.
Aleksandr Mishin corrects overallocation of memory related to adding
scheduler nodes.
* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
ice: Adjust over allocation of memory in ice_sched_add_root_node() and ice_sched_add_node()
ice: Report NVM version numbers on mismatch during load
ice: remove unnecessary control queue cmd_buf arrays
ice: reword comments referring to control queues
ice: stop intermixing AQ commands/responses debug dumps
ice: do not clutter debug logs with unused data
ice: improve debug print for control queue messages
ice: implement and use rd32_poll_timeout for ice_sq_done timeout
====================
Link: https://patch.msgid.link/20240826224655.133847-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In ice_sched_add_root_node() and ice_sched_add_node() there are calls to
devm_kcalloc() in order to allocate memory for array of pointers to
'ice_sched_node' structure. But incorrect types are used as sizeof()
arguments in these calls (structures instead of pointers) which leads to
over allocation of memory.
Adjust over allocation of memory by correcting types in devm_kcalloc()
sizeof() arguments.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Aleksandr Mishin <amishin@t-argos.ru>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Report NVM version numbers (both detected and expected) when a mismatch b/w
driver and firmware is detected. This provides more useful information
about which NVM version the driver expects, rather than requiring manual
code inspection.
Signed-off-by: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The driver allocates a cmd_buf array in addition to the desc_buf array.
This array stores an ice_sq_cd command details structure for each entry in
the control queue ring.
The contents of the structure are copied from the value passed in via
ice_sq_send_cmd, and include only a pointer to storage for the write back
descriptor contents.
Originally this array was intended to support asynchronous completion
including features such as a callback function. This support was never
implemented. All that exists today is needless copying and resetting of a
cmd_buf array that is otherwise functionally unused.
Since we do not plan to implement asynchronous completions, drop this
unnecessary memory and logic. This saves memory for each control queue, and
avoids the pointless copying and memset.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Many comments in ice_controlq.c use the term "Admin queue" despite the code
being intended for arbitrary control queues, not just the Admin queue.
Reword the comments to make it clear that this code is the generic control
queue logic that is shared by all of the control queues, and is not
specific to the Admin queue.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The ice_debug_cq() function is called to generate a debug log of control
queue messages both sent and received. It currently does this over a
potential total of 6 different printk invocations.
The main logic prints over 4 calls to ice_debug():
1. The metadata including opcode, flags, datalength and return value.
2. The cookie in the descriptor.
3. The parameter values.
4. The address for the databuffer.
In addition, if the descriptor has a data buffer, it can be logged with two
additional prints:
5. A message indicating the start of the data buffer.
6. The actual data buffer, printed using print_hex_dump_debug.
This can lead to trouble in the event that two different PFs are logging
messages. The messages become intermixed and it may not be possible to
determine which part of the output belongs to which control queue message.
To fix this, it needs to be possible to unambiguously determine which
messages belong together. This is trivial for the messages that comprise
the main printing. Combine them together into a single invocation of
ice_debug().
The message containing a hex-dump of the data buffer is a bit more
complicated. This is printed separately as part of print_hex_dump_debug.
This function takes a prefix, which is currently always set to
KBUILD_MODNAME. Extend this prefix to include the buffer address for the
databuffer, which is printed as part of the main print, and which is
guaranteed to be unique for each buffer.
Refactor the ice_debug_array(), introducing an ice_debug_array_w_prefix().
Build the prefix by combining KBUILD_MODNAME with the databuffer address
using snprintf().
These changes make it possible to unambiguously determine what data belongs
to what control queue message.
Reported-by: Jacek Wierzbicki <jacek.wierzbicki@intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Currently, debug logs are unnecessarily cluttered with the contents of
command data buffers even if the receiver of that command (i.e. FW or MBX)
are not told to read the buffer. Change to only log command data buffers
when the RD flag (indicates receiver needs to read the buffer) is set.
Continue to log response data buffer when the returned datalen is non-zero.
Also, rename a local variable to reflect what is in the hardware
specification and how it is used elsewhere in the code, use local variables
instead of duplicating endian conversions unnecessarily and remove an
unnecessary assignment.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The ice_debug_cq function is called to print debug data for a control queue
descriptor in multiple places. This includes both before we send a message
on a transmit queue, after the writeback completion of a message on the
transmit queue, and when we receive a message on a receive queue.
This function does not include data about *which* control queue the message
is on, nor whether it was what we sent to the queue or what we received
from the queue.
Modify ice_debug_cq to take two extra parameters, a pointer to the control
queue and a boolean indicating if this was a response or a command. Improve
the debug messages by replacing "CQ CMD" with a string indicating which
specific control queue (based on cq->qtype) and whether this was a command
sent by the PF or a response from the queue.
This helps make the log output easier to understand and consume when
debugging.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The ice_sq_done function is used to check the control queue head register
and determine whether or not the control queue processing is done. This
function is called in a loop checking against jiffies for a specified
timeout.
The pattern of reading a register in a loop until a condition is true or a
timeout is reached is a relatively common pattern. In fact, the kernel
provides a read_poll_timeout function implementing this behavior in
<linux/iopoll.h>
Use of read_poll_timeout is preferred over directly coding these loops.
However, using it in the ice driver is a bit more difficult because of the
rd32 wrapper. Implement a rd32_poll_timeout wrapper based on
read_poll_timeout.
Refactor ice_sq_done to use rd32_poll_timeout, replacing the loop calling
ice_sq_done in ice_sq_send_cmd. This simplifies the logic down to a single
ice_sq_done() call.
The implementation of rd32_poll_timeout uses microseconds for its timeout
value, so update the CQ timeout macros used to be specified in microseconds
units as well instead of using HZ for jiffies.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
When working on multi-buffer packet on arch that has PAGE_SIZE >= 8192,
truesize is calculated and stored in xdp_buff::frame_sz per each
processed Rx buffer. This means that frame_sz will contain the truesize
based on last received buffer, but commit 1dc1a7e7f4 ("ice:
Centrallize Rx buffer recycling") assumed this value will be constant
for each buffer, which breaks the page recycling scheme and mess up the
way we update the page::page_offset.
To fix this, let us work on constant truesize when PAGE_SIZE >= 8192
instead of basing this on size of a packet read from Rx descriptor. This
way we can simplify the code and avoid calculating truesize per each
received frame and on top of that when using
xdp_update_skb_shared_info(), current formula for truesize update will
be valid.
This means ice_rx_frame_truesize() can be removed altogether.
Furthermore, first call to it within ice_clean_rx_irq() for 4k PAGE_SIZE
was redundant as xdp_buff::frame_sz is initialized via xdp_init_buff()
in ice_vsi_cfg_rxq(). This should have been removed at the point where
xdp_buff struct started to be a member of ice_rx_ring and it was no
longer a stack based variable.
There are two fixes tags as my understanding is that the first one
exposed us to broken truesize and page_offset handling and then second
introduced broken skb_shared_info update in ice_{construct,build}_skb().
Reported-and-tested-by: Luiz Capitulino <luizcap@redhat.com>
Closes: https://lore.kernel.org/netdev/8f9e2a5c-fd30-4206-9311-946a06d031bb@redhat.com/
Fixes: 1dc1a7e7f4 ("ice: Centrallize Rx buffer recycling")
Fixes: 2fba7dc515 ("ice: Add support for XDP multi-buffer on Rx side")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
For bigger PAGE_SIZE archs, ice driver works on 3k Rx buffers.
Therefore, ICE_LAST_OFFSET should take into account ICE_RXBUF_3072, not
ICE_RXBUF_2048.
Fixes: 7237f5b0db ("ice: introduce legacy Rx flag")
Suggested-by: Luiz Capitulino <luizcap@redhat.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Architectures that have PAGE_SIZE >= 8192 such as arm64 should act the
same as x86 currently, meaning reuse of a page should only take place
when no one else is busy with it.
Do two things independently of underlying PAGE_SIZE:
- store the page count under ice_rx_buf::pgcnt
- then act upon its value vs ice_rx_buf::pagecnt_bias when making the
decision regarding page reuse
Fixes: 2b245cb294 ("ice: Implement transmit and NAPI support")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Add support for offloading cls U32 filters. Only "skbedit queue_mapping"
and "drop" actions are supported. Also, only "ip" and "802_3" tc
protocols are allowed. The PF must advertise the VIRTCHNL_VF_OFFLOAD_TC_U32
capability flag.
Since the filters will be enabled via the FD stage at the PF, a new type
of FDIR filters is added and the existing list and state machine are used.
The new filters can be used to configure flow directors based on raw
(binary) pattern in the rx packet.
Examples:
0. # tc qdisc add dev enp175s0v0 ingress
1. Redirect UDP from src IP 192.168.2.1 to queue 12:
# tc filter add dev <dev> protocol ip ingress u32 \
match u32 0x45000000 0xff000000 at 0 \
match u32 0x00110000 0x00ff0000 at 8 \
match u32 0xC0A80201 0xffffffff at 12 \
match u32 0x00000000 0x00000000 at 24 \
action skbedit queue_mapping 12 skip_sw
2. Drop all ICMP:
# tc filter add dev <dev> protocol ip ingress u32 \
match u32 0x45000000 0xff000000 at 0 \
match u32 0x00010000 0x00ff0000 at 8 \
match u32 0x00000000 0x00000000 at 24 \
action drop skip_sw
3. Redirect ICMP traffic from MAC 3c:fd:fe:a5:47:e0 to queue 7
(note proto: 802_3):
# tc filter add dev <dev> protocol 802_3 ingress u32 \
match u32 0x00003CFD 0x0000ffff at 4 \
match u32 0xFEA547E0 0xffffffff at 8 \
match u32 0x08004500 0xffffff00 at 12 \
match u32 0x00000001 0x000000ff at 20 \
match u32 0x0000 0x0000 at 40 \
action skbedit queue_mapping 7 skip_sw
Notes on matches:
1 - All intermediate fields that are needed to parse the correct PTYPE
must be provided (in e.g. 3: Ethernet Type 0x0800 in MAC, IP version
and IP length: 0x45 and protocol: 0x01 (ICMP)).
2 - The last match must provide an offset that guarantees all required
headers are accounted for, even if the last header is not matched.
For example, in #2, the last match is 4 bytes at offset 24 starting
from IP header, so the total is 14 (MAC) + 24 + 4 = 42, which is the
sum of MAC+IP+ICMP headers.
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
The SWAP Flag in the FDIR Programming Descriptor doesn't work properly,
it is always set and cannot be unset (hardware bug). Thus, add a method
to effectively disable the FDIR SWAP option by setting the FDSWAP instead
of FDINSET registers.
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
