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>
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>
ice_cfg_txq_interrupt() internally handles XDP Tx ring. Do not use
ice_for_each_tx_ring() in ice_qvec_cfg_msix() as this causing us to
treat XDP ring that belongs to queue vector as Tx ring and therefore
misconfiguring the interrupts.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
xsk_buff_pool pointers that ice ring structs hold are updated via
ndo_bpf that is executed in process context while it can be read by
remote CPU at the same time within NAPI poll. Use synchronize_net()
after pointer update and {READ,WRITE}_ONCE() when working with mentioned
pointer.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
This so we prevent Tx timeout issues. One of conditions checked on
running in the background dev_watchdog() is netif_carrier_ok(), so let
us turn it off when we disable the queues that belong to a q_vector
where XSK pool is being configured. Turn carrier on in ice_qp_ena()
only when ice_get_link_status() tells us that physical link is up.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Don't bail out right when spotting an error within ice_qp_{dis,ena}()
but rather track error and go through whole flow of disabling and
enabling queue pair.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Given that ice_qp_dis() is called under rtnl_lock, synchronize_net() can
be called instead of synchronize_rcu() so that XDP rings can finish its
job in a faster way. Also let us do this as earlier in XSK queue disable
flow.
Additionally, turn off regular Tx queue before disabling irqs and NAPI.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
When ice driver is spammed with multiple xdpsock instances and flow
control is enabled, there are cases when Rx queue gets stuck and unable
to reflect the disable state in QRX_CTRL register. Similar issue has
previously been addressed in commit 13a6233b03 ("ice: Add support to
enable/disable all Rx queues before waiting").
To workaround this, let us simply not wait for a disabled state as later
patch will make sure that regardless of the encountered error in the
process of disabling a queue pair, the Rx queue will be enabled.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Address a scenario in which XSK ZC Tx produces descriptors to XDP Tx
ring when link is either not yet fully initialized or process of
stopping the netdev has already started. To avoid this, add checks
against carrier readiness in ice_xsk_wakeup() and in ice_xmit_zc().
One could argue that bailing out early in ice_xsk_wakeup() would be
sufficient but given the fact that we produce Tx descriptors on behalf
of NAPI that is triggered for Rx traffic, the latter is also needed.
Bringing link up is an asynchronous event executed within
ice_service_task so even though interface has been brought up there is
still a time frame where link is not yet ok.
Without this patch, when AF_XDP ZC Tx is used simultaneously with stack
Tx, Tx timeouts occur after going through link flap (admin brings
interface down then up again). HW seem to be unable to transmit
descriptor to the wire after HW tail register bump which in turn causes
bit __QUEUE_STATE_STACK_XOFF to be set forever as
netdev_tx_completed_queue() sees no cleaned bytes on the input.
Fixes: 126cdfe100 ("ice: xsk: Improve AF_XDP ZC Tx and use batching API")
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Referenced commit has introduced a bitmap to distinguish between ZC and
copy-mode AF_XDP queues, because xsk_get_pool_from_qid() does not do this
for us.
The bitmap would be especially useful when restoring previous state after
rebuild, if only it was not reallocated in the process. This leads to e.g.
xdpsock dying after changing number of queues.
Instead of preserving the bitmap during the rebuild, remove it completely
and distinguish between ZC and copy-mode queues based on the presence of
a device associated with the pool.
Fixes: e102db780e ("ice: track AF_XDP ZC enabled queues in bitmap")
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-3-e3563aa89b0c@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
- optimize DMA sync calls when they are no-ops (Alexander Lobakin)
- fix swiotlb padding for untrusted devices (Michael Kelley)
- add documentation for swiotb (Michael Kelley)
-----BEGIN PGP SIGNATURE-----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=Pa8W
-----END PGP SIGNATURE-----
Merge tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping
Pull dma-mapping updates from Christoph Hellwig:
- optimize DMA sync calls when they are no-ops (Alexander Lobakin)
- fix swiotlb padding for untrusted devices (Michael Kelley)
- add documentation for swiotb (Michael Kelley)
* tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping:
dma: fix DMA sync for drivers not calling dma_set_mask*()
xsk: use generic DMA sync shortcut instead of a custom one
page_pool: check for DMA sync shortcut earlier
page_pool: don't use driver-set flags field directly
page_pool: make sure frag API fields don't span between cachelines
iommu/dma: avoid expensive indirect calls for sync operations
dma: avoid redundant calls for sync operations
dma: compile-out DMA sync op calls when not used
iommu/dma: fix zeroing of bounce buffer padding used by untrusted devices
swiotlb: remove alloc_size argument to swiotlb_tbl_map_single()
Documentation/core-api: add swiotlb documentation
XSk infra's been using its own DMA sync shortcut to try avoiding
redundant function calls. Now that there is a generic one, remove
the custom implementation and rely on the generic helpers.
xsk_buff_dma_sync_for_cpu() doesn't need the second argument anymore,
remove it.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
__napi_alloc_skb() is napi_alloc_skb() with the added flexibility
of choosing gfp_mask. This is a NAPI function, so GFP_ATOMIC is
implied. The only practical choice the caller has is whether to
set __GFP_NOWARN. But that's a false choice, too, allocation failures
in atomic context will happen, and printing warnings in logs,
effectively for a packet drop, is both too much and very likely
non-actionable.
This leads me to a conclusion that most uses of napi_alloc_skb()
are simply misguided, and should use __GFP_NOWARN in the first
place. We also have a "standard" way of reporting allocation
failures via the queue stat API (qstats::rx-alloc-fail).
The direct motivation for this patch is that one of the drivers
used at Meta calls napi_alloc_skb() (so prior to this patch without
__GFP_NOWARN), and the resulting OOM warning is the top networking
warning in our fleet.
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240327040213.3153864-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ice_qp_dis() currently does things in very mixed way. Tx is stopped
before disabling IRQ on related queue vector, then it takes care of
disabling Rx and finally NAPI is disabled.
Let us start with disabling IRQs in the first place followed by turning
off NAPI. Then it is safe to handle queues.
One subtle change on top of that is that even though ice_qp_ena() looks
more sane, clear ICE_CFG_BUSY as the last thing there.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Currently, XSK control path in ice driver calls directly
ice_vsi_cfg_txq() whereas we have ice_vsi_cfg_single_txq() for that
purpose. Use the latter from XSK side and make ice_vsi_cfg_txq() static.
ice_vsi_cfg_txq() resides in ice_base.c and is rather big, so to reduce
the code churn let us move the callers of it from ice_lib.c to
ice_base.c.
This change puts ice_qp_ena() on nice diet due to the checks and
operations that ice_vsi_cfg_single_{r,t}xq() do internally.
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-182 (-182)
Function old new delta
ice_xsk_pool_setup 2165 1983 -182
Total: Before=472597, After=472415, chg -0.04%
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Currently, XSK control path in ice driver calls directly
ice_vsi_cfg_rxq() whereas we have ice_vsi_cfg_single_rxq() for that
purpose. Use the latter from XSK side and make ice_vsi_cfg_rxq() static.
ice_vsi_cfg_rxq() resides in ice_base.c and is rather big, so to reduce
the code churn let us move two callers of it from ice_lib.c to
ice_base.c.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Ice and i40e ZC drivers currently set offset of a frag within
skb_shared_info to 0, which is incorrect. xdp_buffs that come from
xsk_buff_pool always have 256 bytes of a headroom, so they need to be
taken into account to retrieve xdp_buff::data via skb_frag_address().
Otherwise, bpf_xdp_frags_increase_tail() would be starting its job from
xdp_buff::data_hard_start which would result in overwriting existing
payload.
Fixes: 1c9ba9c146 ("i40e: xsk: add RX multi-buffer support")
Fixes: 1bbc04de60 ("ice: xsk: add RX multi-buffer support")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-8-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
XDP multi-buffer support introduced XDP_FLAGS_HAS_FRAGS flag that is
used by drivers to notify data path whether xdp_buff contains fragments
or not. Data path looks up mentioned flag on first buffer that occupies
the linear part of xdp_buff, so drivers only modify it there. This is
sufficient for SKB and XDP_DRV modes as usually xdp_buff is allocated on
stack or it resides within struct representing driver's queue and
fragments are carried via skb_frag_t structs. IOW, we are dealing with
only one xdp_buff.
ZC mode though relies on list of xdp_buff structs that is carried via
xsk_buff_pool::xskb_list, so ZC data path has to make sure that
fragments do *not* have XDP_FLAGS_HAS_FRAGS set. Otherwise,
xsk_buff_free() could misbehave if it would be executed against xdp_buff
that carries a frag with XDP_FLAGS_HAS_FRAGS flag set. Such scenario can
take place when within supplied XDP program bpf_xdp_adjust_tail() is
used with negative offset that would in turn release the tail fragment
from multi-buffer frame.
Calling xsk_buff_free() on tail fragment with XDP_FLAGS_HAS_FRAGS would
result in releasing all the nodes from xskb_list that were produced by
driver before XDP program execution, which is not what is intended -
only tail fragment should be deleted from xskb_list and then it should
be put onto xsk_buff_pool::free_list. Such multi-buffer frame will never
make it up to user space, so from AF_XDP application POV there would be
no traffic running, however due to free_list getting constantly new
nodes, driver will be able to feed HW Rx queue with recycled buffers.
Bottom line is that instead of traffic being redirected to user space,
it would be continuously dropped.
To fix this, let us clear the mentioned flag on xsk_buff_pool side
during xdp_buff initialization, which is what should have been done
right from the start of XSK multi-buffer support.
Fixes: 1bbc04de60 ("ice: xsk: add RX multi-buffer support")
Fixes: 1c9ba9c146 ("i40e: xsk: add RX multi-buffer support")
Fixes: 24ea50127e ("xsk: support mbuf on ZC RX")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-3-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Implement .xmo_rx_vlan_tag callback to allow XDP code to read
packet's VLAN tag.
At the same time, use vlan_tci instead of vlan_tag in touched code,
because VLAN tag often refers to VLAN proto and VLAN TCI combined,
while in the code we clearly store only VLAN TCI.
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-11-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In AF_XDP ZC, xdp_buff is not stored on ring,
instead it is provided by xsk_buff_pool.
Space for metadata sources right after such buffers was already reserved
in commit 94ecc5ca4d ("xsk: Add cb area to struct xdp_buff_xsk").
Some things (such as pointer to packet context) do not change on a
per-packet basis, so they can be set at the same time as RX queue info.
On the other hand, RX descriptor is unique for each packet, but is already
known when setting DMA addresses. This minimizes performance impact of
hints on regular packet processing.
Update AF_XDP ZC packet processing to support XDP hints.
Co-developed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-9-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently, rx_ptype variable is used only as an argument
to ice_process_skb_fields() and is computed
just before the function call.
Therefore, there is no reason to pass this value as an argument.
Instead, remove this argument and compute the value directly inside
ice_process_skb_fields() function.
Also, separate its calculation into a short function, so the code
can later be reused in .xmo_() callbacks.
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-4-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Most of this patch is about actually supporting XDP_TX action. Pure Tx
ZC support is only about looking at XDP_PKT_CONTD presence at options
field and based on that generating EOP bit on Tx HW descriptor. This is
that simple due to the implementation on
xsk_tx_peek_release_desc_batch() where we are making sure that last
produced descriptor is an EOP one.
Overwrite xdp_zc_max_segs with a value that defines max scatter-gatter
count on Tx side that HW can handle.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-16-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This support is strongly inspired by work that introduced multi-buffer
support to regular Rx data path in ice. There are some differences,
though. When adding a frag, besides adding it to skb_shared_info, use
also fresh xsk_buff_add_frag() helper. Reason for doing both things is
that we can not rule out the fact that AF_XDP pipeline could use XDP
program that needs to access frame fragments. Without them being in
skb_shared_info it will not be possible. Another difference is that
XDP_PASS has to allocate a new pages for each frags and copy contents
from memory backed by xsk_buff_pool.
chain_len that is used for programming HW Rx descriptors no longer has
to be limited to 1 when xsk_pool is present - remove this restriction.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-13-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently interrupt allocations, depending on a feature are distributed
in batches. Also, after allocation there is a series of operations that
distributes per irq settings through that batch of interrupts.
Although driver does not yet support dynamic interrupt allocation, keep
allocated interrupts in a pool and add allocation abstraction logic to
make code more flexible. Keep per interrupt information in the
ice_q_vector structure, which yields ice_vsi::base_vector redundant.
Also, as a result there are a few functions that can be removed.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Currently, driver gets interrupt number directly from ice_pf::msix_entries
array. Use helper function dedicated to do just that.
While at it use a variable to store interrupt number in
ice_free_irq_msix_misc instead of calling the helper function twice.
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCY+/uBgAKCRDbK58LschI
g0ngAPwJHd1RicBuy2C4fLv0nGKZtmYZBAnTGlI2RisPxU6BRwEAwUDLHuc5K6nR
j261okOxOy/MRxdN1NhmR6Qe7nMyQAk=
=tYU+
-----END PGP SIGNATURE-----
Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2023-02-17
We've added 64 non-merge commits during the last 7 day(s) which contain
a total of 158 files changed, 4190 insertions(+), 988 deletions(-).
The main changes are:
1) Add a rbtree data structure following the "next-gen data structure"
precedent set by recently-added linked-list, that is, by using
kfunc + kptr instead of adding a new BPF map type, from Dave Marchevsky.
2) Add a new benchmark for hashmap lookups to BPF selftests,
from Anton Protopopov.
3) Fix bpf_fib_lookup to only return valid neighbors and add an option
to skip the neigh table lookup, from Martin KaFai Lau.
4) Add cgroup.memory=nobpf kernel parameter option to disable BPF memory
accouting for container environments, from Yafang Shao.
5) Batch of ice multi-buffer and driver performance fixes,
from Alexander Lobakin.
6) Fix a bug in determining whether global subprog's argument is
PTR_TO_CTX, which is based on type names which breaks kprobe progs,
from Andrii Nakryiko.
7) Prep work for future -mcpu=v4 LLVM option which includes usage of
BPF_ST insn. Thus improve BPF_ST-related value tracking in verifier,
from Eduard Zingerman.
8) More prep work for later building selftests with Memory Sanitizer
in order to detect usages of undefined memory, from Ilya Leoshkevich.
9) Fix xsk sockets to check IFF_UP earlier to avoid a NULL pointer
dereference via sendmsg(), from Maciej Fijalkowski.
10) Implement BPF trampoline for RV64 JIT compiler, from Pu Lehui.
11) Fix BPF memory allocator in combination with BPF hashtab where it could
corrupt special fields e.g. used in bpf_spin_lock, from Hou Tao.
12) Fix LoongArch BPF JIT to always use 4 instructions for function
address so that instruction sequences don't change between passes,
from Hengqi Chen.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (64 commits)
selftests/bpf: Add bpf_fib_lookup test
bpf: Add BPF_FIB_LOOKUP_SKIP_NEIGH for bpf_fib_lookup
riscv, bpf: Add bpf trampoline support for RV64
riscv, bpf: Add bpf_arch_text_poke support for RV64
riscv, bpf: Factor out emit_call for kernel and bpf context
riscv: Extend patch_text for multiple instructions
Revert "bpf, test_run: fix &xdp_frame misplacement for LIVE_FRAMES"
selftests/bpf: Add global subprog context passing tests
selftests/bpf: Convert test_global_funcs test to test_loader framework
bpf: Fix global subprog context argument resolution logic
LoongArch, bpf: Use 4 instructions for function address in JIT
bpf: bpf_fib_lookup should not return neigh in NUD_FAILED state
bpf: Disable bh in bpf_test_run for xdp and tc prog
xsk: check IFF_UP earlier in Tx path
Fix typos in selftest/bpf files
selftests/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
samples/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
bpftool: Use bpf_{btf,link,map,prog}_get_info_by_fd()
libbpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
libbpf: Introduce bpf_{btf,link,map,prog}_get_info_by_fd()
...
====================
Link: https://lore.kernel.org/r/20230217221737.31122-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When queueing frames from a Page Pool for redirecting to a device backed
by the ice driver, `perf top` shows heavy load on page_alloc() and
page_frag_free(), despite that on a properly working system it must be
fully or at least almost zero-alloc. The problem is in fact a bit deeper
and raises from how ice cleans up completed Tx buffers.
The story so far: when cleaning/freeing the resources related to
a particular completed Tx frame (skbs, DMA mappings etc.), ice uses some
heuristics only without setting any type explicitly (except for dummy
Flow Director packets, which are marked via ice_tx_buf::tx_flags).
This kinda works, but only up to some point. For example, currently ice
assumes that each frame coming to __ice_xmit_xdp_ring(), is backed by
either plain order-0 page or plain page frag, while it may also be
backed by Page Pool or any other possible memory models introduced in
future. This means any &xdp_frame must be freed properly via
xdp_return_frame() family with no assumptions.
In order to do that, the whole heuristics must be replaced with setting
the Tx buffer/frame type explicitly, just how it's always been done via
an enum. Let us reuse 16 bits from ::tx_flags -- 1 bit-and instr won't
hurt much -- especially given that sometimes there was a check for
%ICE_TX_FLAGS_DUMMY_PKT, which is now turned from a flag to an enum
member. The rest of the changes is straightforward and most of it is
just a conversion to rely now on the type set in &ice_tx_buf rather than
to some secondary properties.
For now, no functional changes intended, the change only prepares the
ground for starting freeing XDP frames properly next step. And it must
be done atomically/synchronously to not break stuff.
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20230210170618.1973430-5-alexandr.lobakin@intel.com
Incrementation of xsk_frames inside the for-loop produces
infinite loop, if we have both normal AF_XDP-TX and XDP_TXed
buffers to complete.
Split xsk_frames into 2 variables (xsk_frames and completed_frames)
to eliminate this bug.
Fixes: 29322791bc ("ice: xsk: change batched Tx descriptor cleaning")
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Acked-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20230209160130.1779890-1-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Let us store pointer to xdp_buff that came from xsk_buff_pool on tx_buf
so that it will be possible to recycle it via xsk_buff_free() on Tx
cleaning side. This way it is not necessary to do expensive copy to
another xdp_buff backed by a newly allocated page.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Link: https://lore.kernel.org/bpf/20230131204506.219292-14-maciej.fijalkowski@intel.com
Similarly as for Rx side in previous patch, logic on XDP Tx in ice
driver needs to be adjusted for multi-buffer support. Specifically, the
way how HW Tx descriptors are produced and cleaned.
Currently, XDP_TX works on strict ring boundaries, meaning it sets RS
bit (on producer side) / looks up DD bit (on consumer/cleaning side)
every quarter of the ring. It means that if for example multi buffer
frame would span across the ring quarter boundary (say that frame
consists of 4 frames and we start from 62 descriptor where ring is sized
to 256 entries), RS bit would be produced in the middle of multi buffer
frame, which would be a broken behavior as it needs to be set on the
last descriptor of the frame.
To make it work, set RS bit at the last descriptor from the batch of
frames that XDP_TX action was used on and make the first entry remember
the index of last descriptor with RS bit set. This way, cleaning side
can take the index of descriptor with RS bit, look up DD bit's presence
and clean from first entry to last.
In order to clean up the code base introduce the common ice_set_rs_bit()
which will return index of descriptor that got RS bit produced on so
that standard driver can store this within proper ice_tx_buf and ZC
driver can simply ignore return value.
Co-developed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Link: https://lore.kernel.org/bpf/20230131204506.219292-12-maciej.fijalkowski@intel.com
Previously ice XDP xmit routine was changed in a way that it avoids
xdp_buff->xdp_frame conversion as it is simply not needed for handling
XDP_TX action and what is more it saves us CPU cycles. This routine is
re-used on ZC driver to handle XDP_TX action.
Although for XDP_TX on Rx ZC xdp_buff that comes from xsk_buff_pool is
converted to xdp_frame, xdp_frame itself is not stored inside
ice_tx_buf, we only store raw data pointer. Casting this pointer to
xdp_frame and calling against it xdp_return_frame in
ice_clean_xdp_tx_buf() results in undefined behavior.
To fix this, simply call page_frag_free() on tx_buf->raw_buf.
Later intention is to remove the buff->frame conversion in order to
simplify the codebase and improve XDP_TX performance on ZC.
Fixes: 126cdfe100 ("ice: xsk: Improve AF_XDP ZC Tx and use batching API")
Reported-and-tested-by: Robin Cowley <robin.cowley@thehutgroup.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>
Reviewed-by: Piotr Raczynski <piotr.raczynski@.intel.com>
Link: https://lore.kernel.org/r/20221220175448.693999-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Resets may occur with or without user interaction. For example, a TX hang
or reconfiguration of parameters will result in a reset. During reset, the
VSI is freed, freeing any statistics structures inside as well. This would
create an issue for the user where a reset happens in the background,
statistics set to zero, and the user checks ring statistics expecting them
to be populated.
To ensure this doesn't happen, accumulate ring statistics over reset.
Define a new ring statistics structure, ice_ring_stats. The new structure
lives in the VSI's parent, preserving ring statistics when VSI is freed.
1. Define a new structure vsi_ring_stats in the PF scope
2. Allocate/free stats only during probe, unload, or change in ring size
3. Replace previous ring statistics functionality with new structure
Signed-off-by: Benjamin Mikailenko <benjamin.mikailenko@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
We had multiple customers in the past months that reported commit
296f13ff38 ("ice: xsk: Force rings to be sized to power of 2")
makes them unable to use ring size of 8160 in conjunction with AF_XDP.
Remove this restriction.
Fixes: 296f13ff38 ("ice: xsk: Force rings to be sized to power of 2")
CC: Alasdair McWilliam <alasdair.mcwilliam@outlook.com>
Signed-off-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>
AF_XDP Tx descriptor cleaning in ice driver currently works in a "lazy"
way - descriptors are not cleaned immediately after send. We rather hold
on with cleaning until we see that free space in ring drops below
particular threshold. This was supposed to reduce the amount of
unnecessary work related to cleaning and instead of keeping the ring
empty, ring was rather saturated.
In AF_XDP realm cleaning Tx descriptors implies producing them to CQ.
This is a way of letting know user space that particular descriptor has
been sent, as John points out in [0].
We tried to implement serial descriptor cleaning which would be used in
conjunction with batched cleaning but it made code base more convoluted
and probably harder to maintain in future. Therefore we step away from
batched cleaning in a current form in favor of an approach where we set
RS bit on every last descriptor from a batch and clean always at the
beginning of ice_xmit_zc().
This means that we give up a bit of Tx performance, but this doesn't
hurt l2fwd scenario which is way more meaningful than txonly as this can
be treaten as AF_XDP based packet generator. l2fwd is not hurt due to
the fact that Tx side is much faster than Rx and Rx is the one that has
to catch Tx up.
FWIW Tx descriptors are still produced in a batched way.
[0]: https://lore.kernel.org/bpf/62b0a20232920_3573208ab@john.notmuch/
Fixes: 126cdfe100 ("ice: xsk: Improve AF_XDP ZC Tx and use batching API")
Signed-off-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>
Fix leak, when user changes ring parameters.
During reallocation of RX buffers, new DMA mappings are created for
those buffers. New buffers with different RX ring count should
substitute older ones, but those buffers were freed in ice_vsi_cfg_rxq
and reallocated again with ice_alloc_rx_buf. kfree on rx_buf caused
leak of already mapped DMA.
Reallocate ZC with xdp_buf struct, when BPF program loads. Reallocate
back to rx_buf, when BPF program unloads.
If BPF program is loaded/unloaded and XSK pools are created, reallocate
RX queues accordingly in XDP_SETUP_XSK_POOL handler.
Steps for reproduction:
while :
do
for ((i=0; i<=8160; i=i+32))
do
ethtool -G enp130s0f0 rx $i tx $i
sleep 0.5
ethtool -g enp130s0f0
done
done
Fixes: 617f3e1b58 ("ice: xsk: allocate separate memory for XDP SW ring")
Signed-off-by: Przemyslaw Patynowski <przemyslawx.patynowski@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Chandan <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Ice driver allocates per cpu XDP queues so that redirect path can safely
use smp_processor_id() as an index to the array. At the same time
though, XDP rings are used to pick NAPI context to call napi_schedule()
or set NAPIF_STATE_MISSED. When user reduces queue count, say to 8, and
num_possible_cpus() of underlying platform is 44, then this means queue
vectors with correlated NAPI contexts will carry several XDP queues.
This in turn can result in a broken behavior where NAPI context of
interest will never be scheduled and AF_XDP socket will not process any
traffic.
To fix this, let us change the way how XDP rings are assigned to Rx
rings and use this information later on when setting
ice_tx_ring::xsk_pool pointer. For each Rx ring, grab the associated
queue vector and walk through Tx ring's linked list. Once we stumble
upon XDP ring in it, assign this ring to ice_rx_ring::xdp_ring.
Previous [0] approach of fixing this issue was for txonly scenario
because of the described grouping of XDP rings across queue vectors. So,
relying on Rx ring meant that NAPI context could be scheduled with a
queue vector without XDP ring with associated XSK pool.
[0]: https://lore.kernel.org/netdev/20220707161128.54215-1-maciej.fijalkowski@intel.com/
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Fixes: 22bf877e52 ("ice: introduce XDP_TX fallback path")
Signed-off-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>
Daniel Borkmann says:
====================
pull-request: bpf-next 2022-04-27
We've added 85 non-merge commits during the last 18 day(s) which contain
a total of 163 files changed, 4499 insertions(+), 1521 deletions(-).
The main changes are:
1) Teach libbpf to enhance BPF verifier log with human-readable and relevant
information about failed CO-RE relocations, from Andrii Nakryiko.
2) Add typed pointer support in BPF maps and enable it for unreferenced pointers
(via probe read) and referenced ones that can be passed to in-kernel helpers,
from Kumar Kartikeya Dwivedi.
3) Improve xsk to break NAPI loop when rx queue gets full to allow for forward
progress to consume descriptors, from Maciej Fijalkowski & Björn Töpel.
4) Fix a small RCU read-side race in BPF_PROG_RUN routines which dereferenced
the effective prog array before the rcu_read_lock, from Stanislav Fomichev.
5) Implement BPF atomic operations for RV64 JIT, and add libbpf parsing logic
for USDT arguments under riscv{32,64}, from Pu Lehui.
6) Implement libbpf parsing of USDT arguments under aarch64, from Alan Maguire.
7) Enable bpftool build for musl and remove nftw with FTW_ACTIONRETVAL usage
so it can be shipped under Alpine which is musl-based, from Dominique Martinet.
8) Clean up {sk,task,inode} local storage trace RCU handling as they do not
need to use call_rcu_tasks_trace() barrier, from KP Singh.
9) Improve libbpf API documentation and fix error return handling of various
API functions, from Grant Seltzer.
10) Enlarge offset check for bpf_skb_{load,store}_bytes() helpers given data
length of frags + frag_list may surpass old offset limit, from Liu Jian.
11) Various improvements to prog_tests in area of logging, test execution
and by-name subtest selection, from Mykola Lysenko.
12) Simplify map_btf_id generation for all map types by moving this process
to build time with help of resolve_btfids infra, from Menglong Dong.
13) Fix a libbpf bug in probing when falling back to legacy bpf_probe_read*()
helpers; the probing caused always to use old helpers, from Runqing Yang.
14) Add support for ARCompact and ARCv2 platforms for libbpf's PT_REGS
tracing macros, from Vladimir Isaev.
15) Cleanup BPF selftests to remove old & unneeded rlimit code given kernel
switched to memcg-based memory accouting a while ago, from Yafang Shao.
16) Refactor of BPF sysctl handlers to move them to BPF core, from Yan Zhu.
17) Fix BPF selftests in two occasions to work around regressions caused by latest
LLVM to unblock CI until their fixes are worked out, from Yonghong Song.
18) Misc cleanups all over the place, from various others.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (85 commits)
selftests/bpf: Add libbpf's log fixup logic selftests
libbpf: Fix up verifier log for unguarded failed CO-RE relos
libbpf: Simplify bpf_core_parse_spec() signature
libbpf: Refactor CO-RE relo human description formatting routine
libbpf: Record subprog-resolved CO-RE relocations unconditionally
selftests/bpf: Add CO-RE relos and SEC("?...") to linked_funcs selftests
libbpf: Avoid joining .BTF.ext data with BPF programs by section name
libbpf: Fix logic for finding matching program for CO-RE relocation
libbpf: Drop unhelpful "program too large" guess
libbpf: Fix anonymous type check in CO-RE logic
bpf: Compute map_btf_id during build time
selftests/bpf: Add test for strict BTF type check
selftests/bpf: Add verifier tests for kptr
selftests/bpf: Add C tests for kptr
libbpf: Add kptr type tag macros to bpf_helpers.h
bpf: Make BTF type match stricter for release arguments
bpf: Teach verifier about kptr_get kfunc helpers
bpf: Wire up freeing of referenced kptr
bpf: Populate pairs of btf_id and destructor kfunc in btf
bpf: Adapt copy_map_value for multiple offset case
...
====================
Link: https://lore.kernel.org/r/20220427224758.20976-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, when debugging AF_XDP workloads, one can correlate the -ENXIO
return code as the case that XSK is not in the bound state. Returning
same code from ndo_xsk_wakeup can be misleading and simply makes it
harder to follow what is going on.
Change ENXIOs in ice's ndo_xsk_wakeup() implementation to EINVALs, so
that when probing it is clear that something is wrong on the driver
side, not the xsk_{recv,send}msg.
There is a -ENETDOWN that can happen from both kernel/driver sides
though, but I don't have a correct replacement for this on one of the
sides, so let's keep it that way.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220413153015.453864-9-maciej.fijalkowski@intel.com
When XSK pool uses need_wakeup feature, correlate -ENOBUFS that was
returned from xdp_do_redirect() with a XSK Rx queue being full. In such
case, terminate the Rx processing that is being done on the current HW
Rx ring and let the user space consume descriptors from XSK Rx queue so
that there is room that driver can use later on.
Introduce new internal return code ICE_XDP_EXIT that will indicate case
described above.
Note that it does not affect Tx processing that is bound to the same
NAPI context, nor the other Rx rings.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220413153015.453864-6-maciej.fijalkowski@intel.com
ice_run_xdp_zc() suggests to compiler that XDP_REDIRECT is the most
probable action returned from BPF program that AF_XDP has in its
pipeline. Let's also bring this suggestion up to the callsite of
ice_run_xdp_zc() so that compiler will be able to generate more
optimized code which in turn will make branch predictor happy.
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220413153015.453864-4-maciej.fijalkowski@intel.com
__ice_alloc_rx_bufs_zc() checks if a number of the descriptors to be
allocated would cause the ring wrap. In that case, driver will issue two
calls to xsk_buff_alloc_batch() - one that will fill the ring up to the
end and the second one that will start with filling descriptors from the
beginning of the ring.
ice_fill_rx_descs() is a wrapper for taking care of what
xsk_buff_alloc_batch() gave back to the driver. It works in a best
effort approach, so for example when driver asks for 64 buffers,
ice_fill_rx_descs() could assign only 32. Such case needs to be checked
when ring is being filled up to the end, because in that situation ntu
might not reached the end of the ring.
Fix the ring wrap by checking if nb_buffs_extra has the expected value.
If not, bump ntu and go directly to tail update.
Fixes: 3876ff525d ("ice: xsk: Handle SW XDP ring wrap and bump tail more often")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Shwetha Nagaraju <Shwetha.nagaraju@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
ICE_DOWN is dedicated for pf->state. Check for ICE_VSI_DOWN being set on
vsi->state in ice_xsk_wakeup().
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Shwetha Nagaraju <shwetha.nagaraju@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Unfortunately, the ice driver doesn't respect the RCU critical section that
XSK wakeup is surrounded with. To fix this, add synchronize_rcu() calls to
paths that destroy resources that might be in use.
This was addressed in other AF_XDP ZC enabled drivers, for reference see
for example commit b3873a5be7 ("net/i40e: Fix concurrency issues
between config flow and XSK")
Fixes: efc2214b60 ("ice: Add support for XDP")
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Shwetha Nagaraju <shwetha.nagaraju@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
