| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
RX hash XDP hint requests both hash value and type.
Type is XDP-specific, so we need a separate way to map
these values to the hardware ptypes, so create a lookup table.
Instead of creating a new long list, reuse contents
of ice_decode_rx_desc_ptype[] through preprocessor.
Current hash type enum does not contain ICMP packet type,
but ice devices support it, so also add a new type into core code.
Then use previously refactored code and create a function
that allows XDP code to read RX hash.
Signed-off-by: Larysa Zaremba <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
Use previously refactored code and create a function
that allows XDP code to read HW timestamp.
Also, introduce packet context, where hints-related data will be stored.
ice_xdp_buff contains only a pointer to this structure, to avoid copying it
in ZC mode later in the series.
HW timestamp is the first supported hint in the driver,
so also add xdp_metadata_ops.
Reviewed-by: Maciej Fijalkowski <[email protected]>
Signed-off-by: Larysa Zaremba <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
In order to use XDP hints via kfuncs we need to put
RX descriptor and miscellaneous data next to xdp_buff.
Same as in hints implementations in other drivers, we achieve
this through putting xdp_buff into a child structure.
Currently, xdp_buff is stored in the ring structure,
so replace it with union that includes child structure.
This way enough memory is available while existing XDP code
remains isolated from hints.
Minimum size of the new child structure (ice_xdp_buff) is exactly
64 bytes (single cache line). To place it at the start of a cache line,
move 'next' field from CL1 to CL4, as it isn't used often. This still
leaves 192 bits available in CL3 for packet context extensions.
Signed-off-by: Larysa Zaremba <[email protected]>
Reviewed-by: Maciej Fijalkowski <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
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 <[email protected]>
Signed-off-by: Larysa Zaremba <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
Previously, we only needed RX HW timestamp in skb path,
hence all related code was written with skb in mind.
But with the addition of XDP hints via kfuncs to the ice driver,
the same logic will be needed in .xmo_() callbacks.
Put generic process of reading RX HW timestamp from a descriptor
into a separate function.
Move skb-related code into another source file.
Reviewed-by: Maciej Fijalkowski <[email protected]>
Signed-off-by: Larysa Zaremba <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
Previously, we only needed RX hash in skb path,
hence all related code was written with skb in mind.
But with the addition of XDP hints via kfuncs to the ice driver,
the same logic will be needed in .xmo_() callbacks.
Separate generic process of reading RX hash from a descriptor
into a separate function.
Reviewed-by: Maciej Fijalkowski <[email protected]>
Signed-off-by: Larysa Zaremba <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>
|
|
Set up the pci_error_handlers error_detected and resume to be useful in
handling AER events. If the error detected is pci_channel_io_frozen we
set up to do an FLR at the end of the AER handling - this tends to clear
things up well enough that traffic can continue. Else, let the AER/PCI
machinery do what is needed for the less serious errors seen.
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Remove and restore the lif's debugfs pointers on a reset,
and make sure to check for the dentry before removing it
in case an earlier reset failed to rebuild the lif.
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
When stopping the watchdog timer at remove time we should
be using the new timer_shutdown_sync to assure the timer
doesn't ever get rearmed.
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
If there was a failed attempt to reset the PCI connection,
don't later try to read from PCI as the space is unmapped
and will cause a paging request crash. When clearing the PCI
setup we can clear the dev_info register pointer, and check
it before using it in the fw_running test.
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
If a reset fails, the PCI device is left in a disabled
state, so don't try to disable it again on driver remove.
This prevents a scary looking WARN trace in the kernel log.
ionic 0000:2b:00.0: disabling already-disabled device
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
If the driver or firmware is stuck in reset state, don't bother
trying to use adminq commands. This speeds up shutdown and
prevents unnecessary timeouts and error messages.
This includes a bit of rework on ionic_adminq_post_wait()
and ionic_adminq_post_wait_nomsg() to both use
__ionic_adminq_post_wait() which can do the checks needed in
both cases.
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Make sure we keep and replay the filters and RSS config across
an FLR by using our FW_RESET flag. This gets checked on the
way down and on the way back up to help determine how much LIF
state to keep and restore across a reset action.
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Don't rely on the PCI memory for the devcmd opcode because we
read a 0xff value if the PCI bus is broken, which can cause us
to report a bogus dev_cmd opcode later.
Signed-off-by: Shannon Nelson <[email protected]>
Reviewed-by: Brett Creeley <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Device binds to proper PCI ID (LOONGSON, 0x7a03), already listed in DTS,
so checking for some other compatible does not make sense. It cannot be
bound to unsupported platform.
Drop useless, incorrect (space in between) and undocumented compatible.
Signed-off-by: Krzysztof Kozlowski <[email protected]>
Signed-off-by: Yanteng Si <[email protected]>
Reviewed-by: Conor Dooley <[email protected]>
Acked-by: Jiaxun Yang <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Generic code will use mdio. If it is not initialized before use,
the kernel will Oops.
Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson")
Signed-off-by: Yanteng Si <[email protected]>
Signed-off-by: Feiyang Chen <[email protected]>
Reviewed-by: Andrew Lunn <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Complete all counters on XGMAC Core.
These can be useful for debugging.
Signed-off-by: Furong Xu <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Mode supported is currently reported to the user exactly the same, as
the current mode. That's because mode changing is not implemented.
Remove the leftover mode_supported() op and use mode_get() to fill up
the supported mode exposed to user.
One, if even, mode changing is going to be introduced, this could be
very easily taken back. In the meantime, prevent drivers form
implementing this in wrong way (as for example recent netdevsim
implementation attempt intended to do).
Signed-off-by: Jiri Pirko <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
When sending TX packets, the meta descriptor can be all zeroes
as no meta information is required (as in XDP).
This patch removes the validity check, as when
`disable_meta_caching` is enabled, such TX packets will be
dropped otherwise.
Fixes: 0e3a3f6dacf0 ("net: ena: support new LLQ acceleration mode")
Signed-off-by: Shay Agroskin <[email protected]>
Signed-off-by: David Arinzon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
This patch fixes two issues:
Issue 1
-------
Description
```````````
Current code does not call dma_sync_single_for_cpu() to sync data from
the device side memory to the CPU side memory before the XDP code path
uses the CPU side data.
This causes the XDP code path to read the unset garbage data in the CPU
side memory, resulting in incorrect handling of the packet by XDP.
Solution
````````
1. Add a call to dma_sync_single_for_cpu() before the XDP code starts to
use the data in the CPU side memory.
2. The XDP code verdict can be XDP_PASS, in which case there is a
fallback to the non-XDP code, which also calls
dma_sync_single_for_cpu().
To avoid calling dma_sync_single_for_cpu() twice:
2.1. Put the dma_sync_single_for_cpu() in the code in such a place where
it happens before XDP and non-XDP code.
2.2. Remove the calls to dma_sync_single_for_cpu() in the non-XDP code
for the first buffer only (rx_copybreak and non-rx_copybreak
cases), since the new call that was added covers these cases.
The call to dma_sync_single_for_cpu() for the second buffer and on
stays because only the first buffer is handled by the newly added
dma_sync_single_for_cpu(). And there is no need for special
handling of the second buffer and on for the XDP path since
currently the driver supports only single buffer packets.
Issue 2
-------
Description
```````````
In case the XDP code forwarded the packet (ENA_XDP_FORWARDED),
ena_unmap_rx_buff_attrs() is called with attrs set to 0.
This means that before unmapping the buffer, the internal function
dma_unmap_page_attrs() will also call dma_sync_single_for_cpu() on
the whole buffer (not only on the data part of it).
This sync is both wasteful (since a sync was already explicitly
called before) and also causes a bug, which will be explained
using the below diagram.
The following diagram shows the flow of events causing the bug.
The order of events is (1)-(4) as shown in the diagram.
CPU side memory area
(3)convert_to_xdp_frame() initializes the
headroom with xdpf metadata
||
\/
___________________________________
| |
0 | V 4K
---------------------------------------------------------------------
| xdpf->data | other xdpf | < data > | tailroom ||...|
| | fields | | GARBAGE || |
---------------------------------------------------------------------
/\ /\
|| ||
(4)ena_unmap_rx_buff_attrs() calls (2)dma_sync_single_for_cpu()
dma_sync_single_for_cpu() on the copies data from device
whole buffer page, overwriting side to CPU side memory
the xdpf->data with GARBAGE. ||
0 4K
---------------------------------------------------------------------
| headroom | < data > | tailroom ||...|
| GARBAGE | | GARBAGE || |
---------------------------------------------------------------------
Device side memory area /\
||
(1) device writes RX packet data
After the call to ena_unmap_rx_buff_attrs() in (4), the xdpf->data
becomes corrupted, and so when it is later accessed in
ena_clean_xdp_irq()->xdp_return_frame(), it causes a page fault,
crashing the kernel.
Solution
````````
Explicitly tell ena_unmap_rx_buff_attrs() not to call
dma_sync_single_for_cpu() by passing it the ENA_DMA_ATTR_SKIP_CPU_SYNC
flag.
Fixes: f7d625adeb7b ("net: ena: Add dynamic recycling mechanism for rx buffers")
Signed-off-by: Arthur Kiyanovski <[email protected]>
Signed-off-by: David Arinzon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Current xdp code drops packets larger than ENA_XDP_MAX_MTU.
This is an incorrect condition since the problem is not the
size of the packet, rather the number of buffers it contains.
This commit:
1. Identifies and drops XDP multi-buffer packets at the
beginning of the function.
2. Increases the xdp drop statistic when this drop occurs.
3. Adds a one-time print that such drops are happening to
give better indication to the user.
Fixes: 838c93dc5449 ("net: ena: implement XDP drop support")
Signed-off-by: Arthur Kiyanovski <[email protected]>
Signed-off-by: David Arinzon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The ena_setup_and_create_all_xdp_queues() function freed all the
resources upon failure, after creating only xdp_num_queues queues,
instead of freeing just the created ones.
In this patch, the only resources that are freed, are the ones
allocated right before the failure occurs.
Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Shahar Itzko <[email protected]>
Signed-off-by: David Arinzon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
In a busy network, especially with flow control enabled, we may
experience timestamp query failures fairly regularly. After a while,
dmesg may be flooded with timestamp query failure error messages.
Silence the error message from the low level hwrm function that
sends the firmware message. Change netdev_err() to netdev_WARN_ONCE()
if this FW call ever fails.
Signed-off-by: Pavan Chebbi <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
We don't have to close and open the nic to make sure we have
valid rx timestamps. Once we have the timestamp filter applied to
the HW and the timestamp_fld_format bit is cleared in the rx
completion and the timestamp is non-zero, we can be sure that rx
timestamp is valid data.
Skip close/open when we set any timestamp filter.
Reviewed-by: Andy Gospodarek <[email protected]>
Signed-off-by: Pavan Chebbi <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The new 5760X chips supports UDP GSO. Tested using udpgso_bench_tx.
Reviewed-by: Andy Gospodarek <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
rx_filter_miss counter is newly added to the rx_port_stats_ext
stats structure for newer chips. Newer firmware will return the
structure size that includes this counter. Add this entry to
the bnxt_port_stats_ext_arr array and the ethtool -S code will
pick up this counter if it is supported.
Signed-off-by: Damodharam Ammepalli <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
On the new P7 chips, TPA for tunnel packets can be independently
enabled for each VNIC. The default TPA configuration should not
include UDP tunnels because the UDP ports for these tunnels are not
known yet. The chip should not aggregate these UDP tunneled packets
using default UDP ports until the ports are known.
Add a new function bnxt_hwrm_vnic_update_tunl_tpa() to enable VXLAN
and Geneve TPA if the corresponding UDP ports are known.
Reviewed-by: Ajit Khaparde <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Add a new bnxt_udp_tunnels_p7 struct to support the new P7 chips that
can parse VXLAN GPE packets. Add VXLAN GPE tunnel type handling to
the .set_port() and .unset_port() functions. .ndo_features_check()
is also enhanced to support VXLAN GPE which may encapsulate inner
IP packets instead of ethernet packets.
Reviewed-by: Damodharam Ammepalli <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
In bnxt_udp_tunnel_set_port(), use the proper ALLOC commands instead
of the FREE commands for correctness. The ALLOC and FREE commands
happen to be identical so this is just a cosmetic fix for correctness.
Reviewed-by: Somnath Kotur <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The Fast QP modify destroy RoCE feature requires additional QP entries
in QP context backing store. FW reports the extra count to be
allocated during backing store query. Use this value and allocate extra
memory. Note that this works for both the V1 and V1 backing store
FW APIs.
Signed-off-by: Selvin Xavier <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
TX coalesced completions are supported on newer chips to provide
one TX completion record for multiple TX packets up to the
sq_cons_idx in the completion record. This method saves PCIe
bandwidth by reducing the number of TX completions.
Only very minor changes are now required to support this mode
with the new framework that handles TX completions based on
the consumer indices.
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
If xmit_more condition is true, the driver may set the
TX_BD_FLAGS_NO_CMPL flag. If after this packet, the TX ring can no
longer hold a packet with maximum fragments, we will stop the TX
queue. When this happens, we must clear the TX_BD_FLAGS_NO_CMPL flag
on the last packet or there will be no completion and cause TX
timeout.
Fixes: c1056a59aee1 ("bnxt_en: Optimize xmit_more TX path")
Reviewed-by: Somnath Kotur <[email protected]>
Reviewed-by: Andy Gospodarek <[email protected]>
Reviewed-by: Hongguang Gao <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Two spots were missed when modifying the TX ring indexing logic.
The use of unmasked TX index in bnxt_tx_int() will cause unnecessary
__bnxt_tx_int() calls. The same issue in bnxt_tx_int_xdp() can
result in illegal array index.
Fixes: 6d1add95536b ("bnxt_en: Modify TX ring indexing logic.")
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
_bnxt_get_max_rings() that is invoked in bnxt_check_rings() already
accounts for the AGG ring(s) and gives a max value based on that.
Increasing for AGG rings before calling _bnxt_get_max_rings() will
result in checking for twice the number of rings than required and
it can fail. Fix it by adjusting for AGG rings after calling
_bnxt_get_max_rings().
Fixes: f5b29c6afe36 ("bnxt_en: Add helper to get the number of CP rings required for TX rings")
Signed-off-by: Somnath Kotur <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
The recent commit to trim the RX and TX rings on P5 chips by assigning
each with max CP rings divided by 2 is not correct. Max CP rings
divided by 2 may be bigger than the original RX or TX and would
lead to failure. In other words, we may be checking for increased
RX/TX rings than required and it may fail.
Fix it by calling __bnxt_trim_rings() instead that would properly
trim RX and TX without the possibility of increasing their values.
Fixes: f5b29c6afe36 ("bnxt_en: Add helper to get the number of CP rings required for TX rings")
Reviewed-by: Pavan Chebbi <[email protected]>
Signed-off-by: Michael Chan <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
qed_ilt_shadow_alloc() will call qed_ilt_shadow_free() to
free p_hwfn->p_cxt_mngr->ilt_shadow on error. However,
qed_cxt_tables_alloc() accesses the freed pointer on failure
of qed_ilt_shadow_alloc() through calling qed_cxt_mngr_free(),
which may lead to use-after-free. Fix this issue by setting
p_mngr->ilt_shadow to NULL in qed_ilt_shadow_free().
Fixes: fe56b9e6a8d9 ("qed: Add module with basic common support")
Reviewed-by: Przemek Kitszel <[email protected]>
Signed-off-by: Dinghao Liu <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
When compiling with gcc version 14.0.0 20231129 (experimental) and
CONFIG_FORTIFY_SOURCE=y, I've noticed the following warning:
...
In function 'fortify_memcpy_chk',
inlined from 'ax88796c_tx_fixup' at drivers/net/ethernet/asix/ax88796c_main.c:287:2:
./include/linux/fortify-string.h:588:25: warning: call to '__read_overflow2_field'
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
588 | __read_overflow2_field(q_size_field, size);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
...
This call to 'memcpy()' is interpreted as an attempt to copy TX_OVERHEAD
(which is 8) bytes from 4-byte 'sop' field of 'struct tx_pkt_info' and
thus overread warning is issued. Since we actually want to copy both
'sop' and 'seg' fields at once, use the convenient 'struct_group()' here.
Signed-off-by: Dmitry Antipov <[email protected]>
Acked-by: Łukasz Stelmach <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>
|
|
Use pcie_capability_read_word() for reading LNKSTA and remove the
custom define that matches to PCI_EXP_LNKSTA.
As only single user for cap_offset remains, replace it with a call to
pci_pcie_cap(). Instead of e1000_adapter, make local variable out of
pci_dev because both users are interested in it.
Signed-off-by: Ilpo Järvinen <[email protected]>
Reviewed-by: Jonathan Cameron <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Tested-by: Naama Meir <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
Make the flow for pci shutdown be the same to the pci remove.
iavf_shutdown was implementing an incomplete version
of iavf_remove. It misses several calls to the kernel like
iavf_free_misc_irq, iavf_reset_interrupt_capability, iounmap
that might break the system on reboot or hibernation.
Implement the call of iavf_remove directly in iavf_shutdown to
close this gap.
Fixes below error messages (dmesg) during shutdown stress tests -
[685814.900917] ice 0000:88:00.0: MAC 02:d0:5f:82:43:5d does not exist for
VF 0
[685814.900928] ice 0000:88:00.0: MAC 33:33:00:00:00:01 does not exist for
VF 0
Reproduction:
1. Create one VF interface:
echo 1 > /sys/class/net/<interface_name>/device/sriov_numvfs
2. Run live dmesg on the host:
dmesg -wH
3. On SUT, script below steps into vf_namespace_assignment.sh
<#!/bin/sh> // Remove <>. Git removes # line
if=<VF name> (edit this per VF name)
loop=0
while true; do
echo test round $loop
let loop++
ip netns add ns$loop
ip link set dev $if up
ip link set dev $if netns ns$loop
ip netns exec ns$loop ip link set dev $if up
ip netns exec ns$loop ip link set dev $if netns 1
ip netns delete ns$loop
done
4. Run the script for at least 1000 iterations on SUT:
./vf_namespace_assignment.sh
Expected result:
No errors in dmesg.
Fixes: 129cf89e5856 ("iavf: rename functions and structs to new name")
Signed-off-by: Slawomir Laba <[email protected]>
Reviewed-by: Michal Swiatkowski <[email protected]>
Reviewed-by: Ahmed Zaki <[email protected]>
Reviewed-by: Jesse Brandeburg <[email protected]>
Co-developed-by: Ranganatha Rao <[email protected]>
Signed-off-by: Ranganatha Rao <[email protected]>
Tested-by: Rafal Romanowski <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
ntuple-filter feature on/off:
Default is on. If turned off, the filters will be removed from both
PF and iavf list. The removal is irrespective of current filter state.
Steps to reproduce:
-------------------
1. Ensure ntuple is on.
ethtool -K enp8s0 ntuple-filters on
2. Create a filter to receive the traffic into non-default rx-queue like 15
and ensure traffic is flowing into queue into 15.
Now, turn off ntuple. Traffic should not flow to configured queue 15.
It should flow to default RX queue.
Fixes: 0dbfbabb840d ("iavf: Add framework to enable ethtool ntuple filters")
Signed-off-by: Piotr Gardocki <[email protected]>
Reviewed-by: Larysa Zaremba <[email protected]>
Signed-off-by: Ranganatha Rao <[email protected]>
Tested-by: Rafal Romanowski <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
New states introduced:
IAVF_FDIR_FLTR_DIS_REQUEST
IAVF_FDIR_FLTR_DIS_PENDING
IAVF_FDIR_FLTR_INACTIVE
Current FDIR state machines (SM) are not adequate to handle a few
scenarios in the link DOWN/UP event, reset event and ntuple-feature.
For example, when VF link goes DOWN and comes back UP administratively,
the expectation is that previously installed filters should also be
restored. But with current SM, filters are not restored.
So with new SM, during link DOWN filters are marked as INACTIVE in
the iavf list but removed from PF. After link UP, SM will transition
from INACTIVE to ADD_REQUEST to restore the filter.
Similarly, with VF reset, filters will be removed from the PF, but
marked as INACTIVE in the iavf list. Filters will be restored after
reset completion.
Steps to reproduce:
-------------------
1. Create a VF. Here VF is enp8s0.
2. Assign IP addresses to VF and link partner and ping continuously
from remote. Here remote IP is 1.1.1.1.
3. Check default RX Queue of traffic.
ethtool -S enp8s0 | grep -E "rx-[[:digit:]]+\.packets"
4. Add filter - change default RX Queue (to 15 here)
ethtool -U ens8s0 flow-type ip4 src-ip 1.1.1.1 action 15 loc 5
5. Ensure filter gets added and traffic is received on RX queue 15 now.
Link event testing:
-------------------
6. Bring VF link down and up. If traffic flows to configured queue 15,
test is success, otherwise it is a failure.
Reset event testing:
--------------------
7. Reset the VF. If traffic flows to configured queue 15, test is success,
otherwise it is a failure.
Fixes: 0dbfbabb840d ("iavf: Add framework to enable ethtool ntuple filters")
Signed-off-by: Piotr Gardocki <[email protected]>
Reviewed-by: Larysa Zaremba <[email protected]>
Signed-off-by: Ranganatha Rao <[email protected]>
Tested-by: Rafal Romanowski <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
e1000e has own copy of PCI Negotiated Link Width field defines. Use the
ones from include/uapi/linux/pci_regs.h instead of the custom ones and
remove the custom ones and convert to FIELD_GET().
Suggested-by: Jonathan Cameron <[email protected]>
Signed-off-by: Ilpo Järvinen <[email protected]>
Reviewed-by: Jonathan Cameron <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Tested-by: Naama Meir <[email protected]>
Signed-off-by: Tony Nguyen <[email protected]>
|
|
Use FIELD_GET() to extract PCIe Negotiated Link Width field instead of
custom masking and shifting.
Signed-off-by: Ilpo Järvinen <[email protected]>
Reviewed-by: Jonathan Cameron <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Tested-by: Pucha Himasekhar Reddy <[email protected]> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <[email protected]>
|
|
The driver is using iowriteXX()/ioreadXX() APIs which are LE IO
accessors simplified as
1. Convert given value _from_ CPU _to_ LE
2. Write it to the device as is
The dev_addr is a byte stream, but because the driver uses 16-bit
IO accessors, it wants to perform double conversion on BE CPUs,
but it took it wrong, as it effectivelly does two times _from_ CPU
_to_ LE. What it has to do is to consider dev_addr as an array of
LE16 and hence do _from_ LE _to_ CPU conversion, followed by implied
_from_ CPU _to_ LE in the iowrite16().
To achieve that, use get_unaligned_le16(). This will make it correct
and allows to avoid sparse warning as reported by LKP.
Reported-by: kernel test robot <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
Signed-off-by: Andy Shevchenko <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>
|
|
The current implementation's default Pause Forward setting is causing
unnecessary network traffic. This patch disables Pause Forward to
address this issue.
Fixes: 1121f6b02e7a ("octeontx2-af: Priority flow control configuration support")
Signed-off-by: Hariprasad Kelam <[email protected]>
Signed-off-by: Sunil Kovvuri Goutham <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
The RSS flow algorithm is not set up correctly for promiscuous or all
multi MCAM entries. This has an impact on flow distribution.
This patch fixes the issue by updating flow algorithm index in above
mentioned MCAM entries.
Fixes: 967db3529eca ("octeontx2-af: add support for multicast/promisc packet replication feature")
Signed-off-by: Hariprasad Kelam <[email protected]>
Signed-off-by: Sunil Kovvuri Goutham <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Current implementation is such that, promisc mcam entry action
is set as multicast even when there are no trusted VFs. multicast
action causes the hardware to copy packet data, which reduces
the performance.
This patch fixes this issue by setting the promisc mcam entry action to
unicast instead of multicast when there are no trusted VFs. The same
change is made for the 'allmulti' mcam entry action.
Fixes: ffd2f89ad05c ("octeontx2-pf: Enable promisc/allmulti match MCAM entries.")
Signed-off-by: Hariprasad Kelam <[email protected]>
Signed-off-by: Sunil Kovvuri Goutham <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
The device supports UDP hardware segmentation offload, which helps
improving the performance. Thus, this patch adds support for UDP
segmentation offload from the driver side.
Signed-off-by: Fei Qin <[email protected]>
Signed-off-by: Louis Peens <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
The firmware ready value is 1, and get firmware ready status
function should explicitly test for that value. The firmware
ready value read will be 2 after driver load, and on unbind
till firmware rewrites the firmware ready back to 0, the value
seen by driver will be 2, which should be regarded as not ready.
Fixes: 10c073e40469 ("octeon_ep: defer probe if firmware not ready")
Signed-off-by: Shinas Rasheed <[email protected]>
Reviewed-by: Simon Horman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Allow jumbo frames by changing maximum MTU size and number of RX queues.
Signed-off-by: Yoshihiro Shimoda <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|