| Age | Commit message (Collapse) | Author |
|---|
|
The error messages in idpf_rx_desc_alloc_all() used the group index i
when reporting memory allocation failures for individual Rx and Rx buffer
queues. This is incorrect.
Update the messages to use the correct queue index j and include the
queue group index i for clearer identification of the affected Rx and Rx
buffer queues.
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20251125223632.1857532-10-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
idpf_compl_queue uses a union for comp, comp_4b, and desc_ring. The
release path should check complq->desc_ring to determine whether the DMA
descriptor ring is allocated. The current check against comp works but is
leftover from a previous commit and is misleading in this context.
Switching the check to desc_ring improves readability and more directly
reflects the intended meaning, since desc_ring is the field representing
the allocated DMA-backed descriptor ring.
No functional change.
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20251125223632.1857532-9-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Convert vport state to a bitmap and remove the DOWN state which is
redundant in the existing logic. There are no functional changes aside
from the use of bitwise operations when setting and checking the states.
Removed the double underscore to be consistent with the naming of other
bitmaps in the header and renamed current_state to vport_is_up to match
the meaning of the new variable.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Chittim Madhu <madhu.chittim@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20251125223632.1857532-6-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Now that AF_XDP functionality is fully implemented, advertise XSk XDP
feature and add .ndo_xsk_wakeup() callback to be able to use it with
this driver.
Co-developed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Implement Rx packet processing specific to AF_XDP ZC using the libeth
XSk infra. Initialize queue registers before allocating buffers to
avoid redundant ifs when updating the queue tail.
Co-developed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Implement the XSk transmit path using the libeth (libeth_xdp)
XSk infra.
When the NAPI poll is called, XSk Tx queues are polled first,
before regular Tx and Rx. They're generally faster to serve
and have higher priority comparing to regular traffic.
Co-developed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add functionality to setup an XSk buffer pool, including ability to
stop, reconfig and start only selected queues, not the whole device.
Pool DMA mapping is managed by libeth_xdp.
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Implement VC functions dedicated to enabling, disabling and configuring
not all but only selected queues.
Also, refactor the existing implementation to make the code more
modular. Introduce new generic functions for sending VC messages
consisting of chunks, in order to isolate the sending algorithm
and its implementation for specific VC messages.
Finally, rewrite the function for mapping queues to q_vectors using the
new modular approach to avoid copying the code that implements the VC
message sending algorithm.
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Co-developed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Use libeth XDP infra to support running XDP program on Rx polling.
This includes all of the possible verdicts/actions.
XDP Tx queues are cleaned only in "lazy" mode when there are less than
1/4 free descriptors left on the ring. libeth helper macros to define
driver-specific XDP functions make sure the compiler could uninline
them when needed.
Use __LIBETH_WORD_ACCESS to parse descriptors more efficiently when
applicable. It really gives some good boosts and code size reduction
on x86_64:
XDP only: add/remove: 0/0 grow/shrink: 3/3 up/down: 5/-59 (-54)
with XSk: add/remove: 0/0 grow/shrink: 5/6 up/down: 23/-124 (-101)
with the most demanding workloads like XSk xmit differing in up to 5-8%.
Co-developed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
In preparation of XDP support, move from having skb as the main frame
container during the Rx polling to &xdp_buff.
This allows to use generic and libeth helpers for building an XDP
buffer and changes the logics: now we try to allocate an skb only
when we processed all the descriptors related to the frame.
Store &libeth_xdp_stash instead of the skb pointer on the Rx queue.
It's only 8 bytes wider, but contains everything we may need.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Implement loading/removing XDP program using .ndo_bpf callback
in the split queue mode. Reconfigure and restart the queues if needed
(!!old_prog != !!new_prog), otherwise, just update the pointers.
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Extend basic structures of the driver (e.g. 'idpf_vport', 'idpf_*_queue',
'idpf_vport_user_config_data') by adding members necessary to support XDP.
Add extra XDP Tx queues needed to support XDP_TX and XDP_REDIRECT actions
without interfering with regular Tx traffic.
Also add functions dedicated to support XDP initialization for Rx and
Tx queues and call those functions from the existing algorithms of
queues configuration.
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Co-developed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Currently, queues are associated 1:1 with interrupt vectors as it's
assumed queues are always interrupt-driven. For XDP, we want to use
Tx queues without interrupts and only do "lazy" cleaning when the number
of free elements is <= threshold (closest pow-2 to 1/4 of the ring).
In order to use a queue without an interrupt, idpf still needs to have
a vector assigned to it to flush descriptors. This vector can be global
and only one for the whole vport to handle all its noirq queues.
Always request one excessive vector and configure it in non-interrupt
mode right away when creating vport, so that it can be used later by
queues when needed (not only XDP ones).
Co-developed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
SW marker descriptors on completion queues are used only when a queue
is about to be destroyed. It's far from hotpath and handling it in the
hotpath NAPI poll makes no sense.
Instead, run a simple poller after a virtchnl message for destroying
the queue is sent and wait for the replies. If replies for all of the
queues are received, this means the synchronization is done correctly
and we can go forth with stopping the link.
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
In the queue-based scheduling mode, Tx completion descriptor is 4 bytes
comparing to 8 bytes in flow-based.
Add definition for it and allocate the corresponding amount of memory
for the descriptors during the completion queue creation.
This does not include handling 4-byte completions during Tx polling, as
for now, the only user of QB will be XDP, which has its own routines.
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add the missing linking of NAPIs to netdev queues when enabling
interrupt vectors in order to support NAPI configuration and
interfaces requiring get_rx_queue()->napi to be set (like XSk
busy polling).
As currently, idpf_vport_{start,stop}() is called from several flows
with inconsistent RTNL locking, we need to synchronize them to avoid
runtime assertions. Notably:
* idpf_{open,stop}() -- regular NDOs, RTNL is always taken;
* idpf_initiate_soft_reset() -- usually called under RTNL;
* idpf_init_task -- called from the init work, needs RTNL;
* idpf_vport_dealloc -- called without RTNL taken, needs it.
Expand common idpf_vport_{start,stop}() to take an additional bool
telling whether we need to manually take the RTNL lock.
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # helper
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Currently, the maximum number of queues available for one vport is 16.
This is hardcoded, but then the function calculating the optimal number
of queues takes min(16, num_online_cpus()).
In order to be able to allocate more queues, which will be then used for
XDP, stop hardcoding 16 and rely on what the device gives us[*]. Instead
of num_online_cpus(), which is considered suboptimal since at least 2013,
use netif_get_num_default_rss_queues() to still have free queues in the
pool.
[*] With the note:
Currently, idpf always allocates `IDPF_MAX_BUFQS_PER_RXQ_GRP` (== 2)
buffer queues for each Rx queue and one completion queue for each Tx for
best performance. But there was no check whether such number is available,
IOW the assumption was not backed by any "harmonizing" / actual checks.
Fix this while at it.
nr_cpu_ids number of Tx queues are needed only for lockless XDP sending,
the regular stack doesn't benefit from that anyhow.
On a 128-thread Xeon, this now gives me 32 regular Tx queues and leaves
224 free for XDP (128 of which will handle XDP_TX, .ndo_xdp_xmit(), and
XSk xmit when enabled).
Note 2:
Unfortunately, some CP/FW versions are not able to
reconfigure/enable/disable large amount of queues within the minimum
timeout (2 seconds). For now, fall back to the default timeout for
every operation until this is resolved.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
No idea what the current barrier position was meant for. At that point,
nothing is read from the descriptor, only the pointer to the actual one
is fetched.
The correct barrier usage here is after the generation check, so that
only the first qword is read if the descriptor is not yet ready and we
need to stop polling. Debatable on coherent DMA as the Rx descriptor
size is <= cacheline size, but anyway, the current barrier position
only makes the codegen worse.
Fixes: 3a8845af66ed ("idpf: add RX splitq napi poll support")
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Ramu R <ramu.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Cross-merge networking fixes after downstream PR (net-6.17-rc4).
No conflicts.
Adjacent changes:
drivers/net/ethernet/intel/idpf/idpf_txrx.c
02614eee26fb ("idpf: do not linearize big TSO packets")
6c4e68480238 ("idpf: remove obsolete stashing code")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
idpf has a limit on number of scatter-gather frags
that can be used per segment.
Currently, idpf_tx_start() checks if the limit is hit
and forces a linearization of the whole packet.
This requires high order allocations that can fail
under memory pressure. A full size BIG-TCP packet
would require order-7 alocation on x86_64 :/
We can move the check earlier from idpf_features_check()
for TSO packets, to force GSO in this case, removing the
cost of a big copy.
This means that a linearization will eventually happen
with sizes smaller than one MSS.
__idpf_chk_linearize() is renamed to idpf_chk_tso_segment()
and moved to idpf_lib.c
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Cc: Madhu Chittim <madhu.chittim@intel.com>
Cc: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>
Reviewed-by: Joshua Hay <joshua.a.hay@intel.com>
Tested-by: Brian Vazquez <brianvv@google.com>
Acked-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250818195934.757936-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
With the new Tx buffer management scheme, there is no need for all of
the stashing mechanisms, the hash table, the reserve buffer stack, etc.
Remove all of that.
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
The Tx refillq logic will cause packets to be silently dropped if there
are not enough buffer resources available to send a packet in flow
scheduling mode. Instead, determine how many buffers are needed along
with number of descriptors. Make sure there are enough of both resources
to send the packet, and stop the queue if not.
Fixes: 7292af042bcf ("idpf: fix a race in txq wakeup")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Replace the TxQ buffer ring with one large pool/array of buffers (only
for flow scheduling). This eliminates the tag generation and makes it
impossible for a tag to be associated with more than one packet.
The completion tag passed to HW through the descriptor is the index into
the array. That same completion tag is posted back to the driver in the
completion descriptor, and used to index into the array to quickly
retrieve the buffer during cleaning. In this way, the tags are treated
as a fix sized resource. If all tags are in use, no more packets can be
sent on that particular queue (until some are freed up). The tag pool
size is 64K since the completion tag width is 16 bits.
For each packet, the driver pulls a free tag from the refillq to get the
next free buffer index. When cleaning is complete, the tag is posted
back to the refillq. A multi-frag packet spans multiple buffers in the
driver, therefore it uses multiple buffer indexes/tags from the pool.
Each frag pulls from the refillq to get the next free buffer index.
These are tracked in a next_buf field that replaces the completion tag
field in the buffer struct. This chains the buffers together so that the
packet can be cleaned from the starting completion tag taken from the
completion descriptor, then from the next_buf field for each subsequent
buffer.
In case of a dma_mapping_error occurs or the refillq runs out of free
buf_ids, the packet will execute the rollback error path. This unmaps
any buffers previously mapped for the packet. Since several free
buf_ids could have already been pulled from the refillq, we need to
restore its original state as well. Otherwise, the buf_ids/tags
will be leaked and not used again until the queue is reallocated.
Descriptor completions only advance the descriptor ring index to "clean"
the descriptors. The packet completions only clean the buffers
associated with the given packet completion tag and do not update the
descriptor ring index.
When operating in queue based scheduling mode, the array still acts as a
ring and will only have TxQ descriptor count entries. The tx_bufs are
still associated 1:1 with the descriptor ring entries and we can use the
conventional indexing mechanisms.
Fixes: c2d548cad150 ("idpf: add TX splitq napi poll support")
Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Move (and rename) the existing rollback logic to singleq.c since that
will be the only consumer. Create a simplified splitq specific rollback
function to loop through and unmap tx_bufs based on the completion tag.
This is critical before replacing the Tx buffer ring with the buffer
pool since the previous rollback indexing will not work to unmap the
chained buffers from the pool.
Cache the next_to_use index before any portion of the packet is put on
the descriptor ring. In case of an error, the rollback will bump tail to
the correct next_to_use value. Because the splitq path now supports
different types of context descriptors (and potentially multiple in the
future), this will take care of rolling back any and all context
descriptors encoded on the ring for the erroneous packet. The previous
rollback logic was broken for PTP packets since it would not account for
the PTP context descriptor.
Fixes: 1a49cf814fe1 ("idpf: add Tx timestamp flows")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Track the gap between next_to_use and the last RE index. Set RE again
if the gap is large enough to ensure RE bit is set frequently. This is
critical before removing the stashing mechanisms because the
opportunistic descriptor ring cleaning from the out-of-order completions
will go away. Previously the descriptors would be "cleaned" by both the
descriptor (RE) completion and the out-of-order completions. Without the
latter, we must ensure the RE bit is set more frequently. Otherwise,
it's theoretically possible for the descriptor ring next_to_clean to
never advance. The previous implementation was dependent on the start
of a packet falling on a 64th index in the descriptor ring, which is not
guaranteed with large packets.
Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
In certain production environments, it is possible for completion tags
to collide, meaning N packets with the same completion tag are in flight
at the same time. In this environment, any given Tx queue is effectively
used to send both slower traffic and higher throughput traffic
simultaneously. This is the result of a customer's specific
configuration in the device pipeline, the details of which Intel cannot
provide. This configuration results in a small number of out-of-order
completions, i.e., a small number of packets in flight. The existing
guardrails in the driver only protect against a large number of packets
in flight. The slower flow completions are delayed which causes the
out-of-order completions. The fast flow will continue sending traffic
and generating tags. Because tags are generated on the fly, the fast
flow eventually uses the same tag for a packet that is still in flight
from the slower flow. The driver has no idea which packet it should
clean when it processes the completion with that tag, but it will look
for the packet on the buffer ring before the hash table. If the slower
flow packet completion is processed first, it will end up cleaning the
fast flow packet on the ring prematurely. This leaves the descriptor
ring in a bad state resulting in a crash or Tx timeout.
In summary, generating a tag when a packet is sent can lead to the same
tag being associated with multiple packets. This can lead to resource
leaks, crashes, and/or Tx timeouts.
Before we can replace the tag generation, we need a new mechanism for
the send path to know what tag to use next. The driver will allocate and
initialize a refillq for each TxQ with all of the possible free tag
values. During send, the driver grabs the next free tag from the refillq
from next_to_clean. While cleaning the packet, the clean routine posts
the tag back to the refillq's next_to_use to indicate that it is now
free to use.
This mechanism works exactly the same way as the existing Rx refill
queues, which post the cleaned buffer IDs back to the buffer queue to be
reposted to HW. Since we're using the refillqs for both Rx and Tx now,
genericize some of the existing refillq support.
Note: the refillqs will not be used yet. This is only demonstrating how
they will be used to pass free tags back to the send path.
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
To eliminate the use of struct page in page pool, the page pool users
should use netmem descriptor and APIs instead.
Make idpf access ->pp through netmem_desc instead of page.
Signed-off-by: Byungchul Park <byungchul@sk.com>
Link: https://patch.msgid.link/20250721021835.63939-10-byungchul@sk.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The IRQ coalescing config currently reside only inside struct
idpf_q_vector. However, all idpf_q_vector structs are de-allocated and
re-allocated during resets. This leads to user-set coalesce configuration
to be lost.
Add new fields to struct idpf_vport_user_config_data to save the user
settings and re-apply them after reset.
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Back when the libeth Rx core was initially written, devmem was a draft
and netmem_ref didn't exist in the mainline. Now that it's here, make
libeth MP-agnostic before introducing any new code or any new library
users.
When it's known that the created PP/FQ is for header buffers, use faster
"unsafe" underscored netmem <--> virt accessors as netmem_is_net_iov()
is always false in that case, but consumes some cycles (bit test +
true branch).
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add a helper function to correctly handle the lockless
synchronization when the sender needs to block. The paradigm is
if (no_resources()) {
stop_queue();
barrier();
if (!no_resources())
restart_queue();
}
netif_subqueue_maybe_stop already handles the paradigm correctly, but
the code split the check for resources in three parts, the first one
(descriptors) followed the protocol, but the other two (completions and
tx_buf) were only doing the first part and so race prone.
Luckily netif_subqueue_maybe_stop macro already allows you to use a
function to evaluate the start/stop conditions so the fix only requires
the right helper function to evaluate all the conditions at once.
The patch removes idpf_tx_maybe_stop_common since it's no longer needed
and instead adjusts separately the conditions for singleq and splitq.
Note that idpf_tx_buf_hw_update doesn't need to check for resources
since that will be covered in idpf_tx_splitq_frame.
To reproduce:
Reduce the threshold for pending completions to increase the chances of
hitting this pause by changing your kernel:
drivers/net/ethernet/intel/idpf/idpf_txrx.h
-#define IDPF_TX_COMPLQ_OVERFLOW_THRESH(txcq) ((txcq)->desc_count >> 1)
+#define IDPF_TX_COMPLQ_OVERFLOW_THRESH(txcq) ((txcq)->desc_count >> 4)
Use pktgen to force the host to push small pkts very aggressively:
./pktgen_sample02_multiqueue.sh -i eth1 -s 100 -6 -d $IP -m $MAC \
-p 10000-10000 -t 16 -n 0 -v -x -c 64
Fixes: 6818c4d5b3c2 ("idpf: add splitq start_xmit")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Josh Hay <joshua.a.hay@intel.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Cross-merge networking fixes after downstream PR (net-6.15-rc8).
Conflicts:
80f2ab46c2ee ("irdma: free iwdev->rf after removing MSI-X")
4bcc063939a5 ("ice, irdma: fix an off by one in error handling code")
c24a65b6a27c ("iidc/ice/irdma: Update IDC to support multiple consumers")
https://lore.kernel.org/20250513130630.280ee6c5@canb.auug.org.au
No extra adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
idpf_vport_splitq_napi_poll() can incorrectly return @budget
after napi_complete_done() has been called.
This violates NAPI rules, because after napi_complete_done(),
current thread lost napi ownership.
Move the test against POLL_MODE before the napi_complete_done().
Fixes: c2d548cad150 ("idpf: add TX splitq napi poll support")
Reported-by: Peter Newman <peternewman@google.com>
Closes: https://lore.kernel.org/netdev/20250520121908.1805732-1-edumazet@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Joshua Hay <joshua.a.hay@intel.com>
Cc: Alan Brady <alan.brady@intel.com>
Cc: Madhu Chittim <madhu.chittim@intel.com>
Cc: Phani Burra <phani.r.burra@intel.com>
Cc: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Link: https://patch.msgid.link/20250520124030.1983936-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Add Rx timestamp function when the Rx timestamp value is read directly
from the Rx descriptor. In order to extend the Rx timestamp value to 64
bit in hot path, the PHC time is cached in the receive groups.
Add supported Rx timestamp modes.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: YiFei Zhu <zhuyifei@google.com>
Tested-by: Mina Almasry <almasrymina@google.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add functions to request Tx timestamp for the PTP packets, read the Tx
timestamp when the completion tag for that packet is being received,
extend the Tx timestamp value and set the supported timestamping modes.
Tx timestamp is requested for the PTP packets by setting a TSYN bit and
index value in the Tx context descriptor. The driver assumption is that
the Tx timestamp value is ready to be read when the completion tag is
received. Then the driver schedules delayed work and the Tx timestamp
value read is requested through virtchnl message. At the end, the Tx
timestamp value is extended to 64-bit and provided back to the skb.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Co-developed-by: Josh Hay <joshua.a.hay@intel.com>
Signed-off-by: Josh Hay <joshua.a.hay@intel.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Cross-merge networking fixes after downstream PR (net-6.14-rc5).
Conflicts:
drivers/net/ethernet/cadence/macb_main.c
fa52f15c745c ("net: cadence: macb: Synchronize stats calculations")
75696dd0fd72 ("net: cadence: macb: Convert to get_stats64")
https://lore.kernel.org/20250224125848.68ee63e5@canb.auug.org.au
Adjacent changes:
drivers/net/ethernet/intel/ice/ice_sriov.c
79990cf5e7ad ("ice: Fix deinitializing VF in error path")
a203163274a4 ("ice: simplify VF MSI-X managing")
net/ipv4/tcp.c
18912c520674 ("tcp: devmem: don't write truncated dmabuf CMSGs to userspace")
297d389e9e5b ("net: prefix devmem specific helpers")
net/mptcp/subflow.c
8668860b0ad3 ("mptcp: reset when MPTCP opts are dropped after join")
c3349a22c200 ("mptcp: consolidate subflow cleanup")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
idpf_rx_rsc() uses skb_transport_offset(skb) while the transport header
is not set yet.
This triggers the following warning for CONFIG_DEBUG_NET=y builds.
DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb))
[ 69.261620] WARNING: CPU: 7 PID: 0 at ./include/linux/skbuff.h:3020 idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[ 69.261629] Modules linked in: vfat fat dummy bridge intel_uncore_frequency_tpmi intel_uncore_frequency_common intel_vsec_tpmi idpf intel_vsec cdc_ncm cdc_eem cdc_ether usbnet mii xhci_pci xhci_hcd ehci_pci ehci_hcd libeth
[ 69.261644] CPU: 7 UID: 0 PID: 0 Comm: swapper/7 Tainted: G S W 6.14.0-smp-DEV #1697
[ 69.261648] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN
[ 69.261650] RIP: 0010:idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[ 69.261677] ? __warn (kernel/panic.c:242 kernel/panic.c:748)
[ 69.261682] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[ 69.261687] ? report_bug (lib/bug.c:?)
[ 69.261690] ? handle_bug (arch/x86/kernel/traps.c:285)
[ 69.261694] ? exc_invalid_op (arch/x86/kernel/traps.c:309)
[ 69.261697] ? asm_exc_invalid_op (arch/x86/include/asm/idtentry.h:621)
[ 69.261700] ? __pfx_idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:4011) idpf
[ 69.261704] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[ 69.261708] ? idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:3072) idpf
[ 69.261712] __napi_poll (net/core/dev.c:7194)
[ 69.261716] net_rx_action (net/core/dev.c:7265)
[ 69.261718] ? __qdisc_run (net/sched/sch_generic.c:293)
[ 69.261721] ? sched_clock (arch/x86/include/asm/preempt.h:84 arch/x86/kernel/tsc.c:288)
[ 69.261726] handle_softirqs (kernel/softirq.c:561)
Fixes: 3a8845af66edb ("idpf: add RX splitq napi poll support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alan Brady <alan.brady@intel.com>
Cc: Joshua Hay <joshua.a.hay@intel.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/20250226221253.1927782-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Delete the driver CPU affinity info and use the core's napi config
instead.
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250224232228.990783-6-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Structs idpf_rx_csum_decoded and idpf_rx_extracted are used both in
idpf and iavf Intel drivers. Change the prefix from idpf_* to libeth_*
and move mentioned structs to libeth's rx.h header file.
Adjust usage in idpf driver.
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Move the call to skb_record_rx_queue in idpf_rx_process_skb_fields()
so that RX queue is recorded for RSC packets too.
Fixes: 90912f9f4f2d ("idpf: convert header split mode to libeth + napi_build_skb()")
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Handle rsc packet with a single segment same as a multi
segment rsc packet so that CHECKSUM_PARTIAL is set in the
skb->ip_summed field. The current code is passing CHECKSUM_NONE
resulting in TCP GRO layer doing checksum in SW and hiding the
issue. This will fail when using dmabufs as payload buffers as
skb frag would be unreadable.
Fixes: 3a8845af66ed ("idpf: add RX splitq napi poll support")
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
There is a race condition between exiting wb_on_itr and completion write
backs. For example, we are in wb_on_itr mode and a Tx completion is
generated by HW, ready to be written back, as we are re-enabling
interrupts:
HW SW
| |
| | idpf_tx_splitq_clean_all
| | napi_complete_done
| |
| tx_completion_wb | idpf_vport_intr_update_itr_ena_irq
That tx_completion_wb happens before the vector is fully re-enabled.
Continuing with this example, it is a UDP stream and the
tx_completion_wb is the last one in the flow (there are no rx packets).
Because the HW generated the completion before the interrupt is fully
enabled, the HW will not fire the interrupt once the timer expires and
the write back will not happen. NAPI poll won't be called. We have
indicated we're back in interrupt mode but nothing else will trigger the
interrupt. Therefore, the completion goes unprocessed, triggering a Tx
timeout.
To mitigate this, fire a SW triggered interrupt upon exiting wb_on_itr.
This interrupt will catch the rogue completion and avoid the timeout.
Add logic to set the appropriate bits in the vector's dyn_ctl register.
Fixes: 9c4a27da0ecc ("idpf: enable WB_ON_ITR")
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Commit d9028db618a6 ("idpf: convert to libeth Tx buffer completion")
inadvertently removed code that was necessary for the tx buffer cleaning
routine to iterate over all buffers associated with a packet.
When a frag is too large for a single data descriptor, it will be split
across multiple data descriptors. This means the frag will span multiple
buffers in the buffer ring in order to keep the descriptor and buffer
ring indexes aligned. The buffer entries in the ring are technically
empty and no cleaning actions need to be performed. These empty buffers
can precede other frags associated with the same packet. I.e. a single
packet on the buffer ring can look like:
buf[0]=skb0.frag0
buf[1]=skb0.frag1
buf[2]=empty
buf[3]=skb0.frag2
The cleaning routine iterates through these buffers based on a matching
completion tag. If the completion tag is not set for buf2, the loop will
end prematurely. Frag2 will be left uncleaned and next_to_clean will be
left pointing to the end of packet, which will break the cleaning logic
for subsequent cleans. This consequently leads to tx timeouts.
Assign the empty bufs the same completion tag for the packet to ensure
the cleaning routine iterates over all of the buffers associated with
the packet.
Fixes: d9028db618a6 ("idpf: convert to libeth Tx buffer completion")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Acked-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Madhu chittim <madhu.chittim@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
net_dim() is currently passed a struct dim_sample argument by value.
struct dim_sample is 24 bytes. Since this is greater 16 bytes, x86-64
passes it on the stack. All callers have already initialized dim_sample
on the stack, so passing it by value requires pushing a duplicated copy
to the stack. Either witing to the stack and immediately reading it, or
perhaps dereferencing addresses relative to the stack pointer in a chain
of push instructions, seems to perform quite poorly.
In a heavy TCP workload, mlx5e_handle_rx_dim() consumes 3% of CPU time,
94% of which is attributed to the first push instruction to copy
dim_sample on the stack for the call to net_dim():
// Call ktime_get()
0.26 |4ead2: call 4ead7 <mlx5e_handle_rx_dim+0x47>
// Pass the address of struct dim in %rdi
|4ead7: lea 0x3d0(%rbx),%rdi
// Set dim_sample.pkt_ctr
|4eade: mov %r13d,0x8(%rsp)
// Set dim_sample.byte_ctr
|4eae3: mov %r12d,0xc(%rsp)
// Set dim_sample.event_ctr
0.15 |4eae8: mov %bp,0x10(%rsp)
// Duplicate dim_sample on the stack
94.16 |4eaed: push 0x10(%rsp)
2.79 |4eaf1: push 0x10(%rsp)
0.07 |4eaf5: push %rax
// Call net_dim()
0.21 |4eaf6: call 4eafb <mlx5e_handle_rx_dim+0x6b>
To allow the caller to reuse the struct dim_sample already on the stack,
pass the struct dim_sample by reference to net_dim().
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Arthur Kiyanovski <akiyano@amazon.com>
Reviewed-by: Louis Peens <louis.peens@corigine.com>
Link: https://patch.msgid.link/20241031002326.3426181-2-csander@purestorage.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Tell hardware to write back completed descriptors even when interrupts
are disabled. Otherwise, descriptors might not be written back until
the hardware can flush a full cacheline of descriptors. This can cause
unnecessary delays when traffic is light (or even trigger Tx queue
timeout).
The example scenario to reproduce the Tx timeout if the fix is not
applied:
- configure at least 2 Tx queues to be assigned to the same q_vector,
- generate a huge Tx traffic on the first Tx queue
- try to send a few packets using the second Tx queue.
In such a case Tx timeout will appear on the second Tx queue because no
completion descriptors are written back for that queue while interrupts
are disabled due to NAPI polling.
Fixes: c2d548cad150 ("idpf: add TX splitq napi poll support")
Fixes: a5ab9ee0df0b ("idpf: add singleq start_xmit and napi poll")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Co-developed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
netif_txq_maybe_stop() returns -1, 0, or 1, while
idpf_tx_maybe_stop_common() says it returns 0 or -EBUSY. As a result,
there sometimes are Tx queue timeout warnings despite that the queue
is empty or there is at least enough space to restart it.
Make idpf_tx_maybe_stop_common() inline and returning true or false,
handling the return of netif_txq_maybe_stop() properly. Use a correct
goto in idpf_tx_maybe_stop_splitq() to avoid stopping the queue or
incrementing the stops counter twice.
Fixes: 6818c4d5b3c2 ("idpf: add splitq start_xmit")
Fixes: a5ab9ee0df0b ("idpf: add singleq start_xmit and napi poll")
Cc: stable@vger.kernel.org # 6.7+
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add a mechanism to guard against stashing partial packets into the hash
table to make the driver more robust, with more efficient decision
making when cleaning.
Don't stash partial packets. This can happen when an RE (Report Event)
completion is received in flow scheduling mode, or when an out of order
RS (Report Status) completion is received. The first buffer with the skb
is stashed, but some or all of its frags are not because the stack is
out of reserve buffers. This leaves the ring in a weird state since
the frags are still on the ring.
Use the field libeth_sqe::nr_frags to track the number of
fragments/tx_bufs representing the packet. The clean routines check to
make sure there are enough reserve buffers on the stack before stashing
any part of the packet. If there are not, next_to_clean is left pointing
to the first buffer of the packet that failed to be stashed. This leaves
the whole packet on the ring, and the next time around, cleaning will
start from this packet.
An RS completion is still expected for this packet in either case. So
instead of being cleaned from the hash table, it will be cleaned from
the ring directly. This should all still be fine since the DESC_UNUSED
and BUFS_UNUSED will reflect the state of the ring. If we ever fall
below the thresholds, the TxQ will still be stopped, giving the
completion queue time to catch up. This may lead to stopping the queue
more frequently, but it guarantees the Tx ring will always be in a good
state.
Also, always use the idpf_tx_splitq_clean function to clean descriptors,
i.e. use it from clean_buf_ring as well. This way we avoid duplicating
the logic and make sure we're using the same reserve buffers guard rail.
This does require a switch from the s16 next_to_clean overflow
descriptor ring wrap calculation to u16 and the normal ring size check.
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
&idpf_tx_buffer is almost identical to the previous generations, as well
as the way it's handled. Moreover, relying on dma_unmap_addr() and
!!buf->skb instead of explicit defining of buffer's type was never good.
Use the newly added libeth helpers to do it properly and reduce the
copy-paste around the Tx code.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
The second tagged commit started sometimes (very rarely, but possible)
throwing WARNs from
net/core/page_pool.c:page_pool_disable_direct_recycling().
Turned out idpf frees interrupt vectors with embedded NAPIs *before*
freeing the queues making page_pools' NAPI pointers lead to freed
memory before these pools are destroyed by libeth.
It's not clear whether there are other accesses to the freed vectors
when destroying the queues, but anyway, we usually free queue/interrupt
vectors only when the queues are destroyed and the NAPIs are guaranteed
to not be referenced anywhere.
Invert the allocation and freeing logic making queue/interrupt vectors
be allocated first and freed last. Vectors don't require queues to be
present, so this is safe. Additionally, this change allows to remove
that useless queue->q_vector pointer cleanup, as vectors are still
valid when freeing the queues (+ both are freed within one function,
so it's not clear why nullify the pointers at all).
Fixes: 1c325aac10a8 ("idpf: configure resources for TX queues")
Fixes: 90912f9f4f2d ("idpf: convert header split mode to libeth + napi_build_skb()")
Reported-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20240806220923.3359860-4-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The initialization of vport interrupt consists of two functions:
1) idpf_vport_intr_init() where a generic configuration is done
2) idpf_vport_intr_req_irq() where the irq for each q_vector is
requested.
The first function used to create a base name for each interrupt using
"kasprintf()" call. Unfortunately, although that call allocated memory
for a text buffer, that memory was never released.
Fix this by removing creating the interrupt base name in 1).
Instead, always create a full interrupt name in the function 2), because
there is no need to create a base name separately, considering that the
function 2) is never called out of idpf_vport_intr_init() context.
Fixes: d4d558718266 ("idpf: initialize interrupts and enable vport")
Cc: stable@vger.kernel.org # 6.7
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20240806220923.3359860-3-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
idpf uses Page Pool for data buffers with hardcoded buffer lengths of
4k for "classic" buffers and 2k for "short" ones. This is not flexible
and does not ensure optimal memory usage. Why would you need 4k buffers
when the MTU is 1500?
Use libeth for the data buffers and don't hardcode any buffer sizes. Let
them be calculated from the MTU for "classics" and then divide the
truesize by 2 for "short" ones. The memory usage is now greatly reduced
and 2 buffer queues starts make sense: on frames <= 1024, you'll recycle
(and resync) a page only after 4 HW writes rather than two.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
