Pull PCI updates from Bjorn Helgaas:
"Enumeration:
- Enable host bridge emulation for PCI_DOMAINS_GENERIC platforms (Dan
Williams)
- Switch vmd from custom domain number allocator to the common
allocator to prevent a potential race with new non-VMD buses (Dan
Williams)
- Enable Precision Time Measurement (PTM) only if device advertises
support for a relevant role, to prevent invalid PTM Requests that
cause ACS violations that are reported as AER Uncorrectable
Non-Fatal errors (Mika Westerberg)
Resource management:
- Prevent resource tree corruption when BAR resize fails (Ilpo
Järvinen)
- Restore BARs to the original size if a BAR resize fails (Ilpo
Järvinen)
- Remove BAR release from BAR resize attempts by the xe, i915, and
amdgpu drivers so the PCI core can restore BARs if the resize fails
(Ilpo Järvinen)
- Move Resizable BAR code to rebar.c (Ilpo Järvinen)
- Add pci_rebar_size_supported() and use it in i915 and xe (Ilpo
Järvinen)
- Add pci_rebar_get_max_size() and use it in xe and amdgpu (Ilpo
Järvinen)
Power management and error handling:
- For drivers using PCI legacy suspend, save config state at suspend
so that state (not any earlier state from enumeration, probe, or
error recovery) will be restored when resuming (Lukas Wunner)
- For devices with no driver or a driver that lacks power management,
save config state at hibernate so that state (not any earlier state
from enumeration, probe, or error recovery) will be restored when
resuming (Lukas Wunner)
- Save device config space on device addition, before driver binding,
so error recovery works more reliably (Lukas Wunner)
- Drop pci_save_state() from several drivers that no longer need it
since the PCI core always does it and pci_restore_state() no longer
invalidates the saved state (Lukas Wunner)
- Document use of pci_save_state() by drivers to capture the state
they want restored during error recovery (Lukas Wunner)
Power control:
- Add a struct pci_ops.assert_perst() function pointer to
assert/deassert PCIe PERST# and implement it for the qcom driver
(Krishna Chaitanya Chundru)
- Add DT binding and pwrctrl driver for the Toshiba TC9563 PCIe
switch, which must be held in reset after poweron so the pwrctrl
driver can configure the switch via I2C before bringing up the
links (Krishna Chaitanya Chundru)
Endpoint framework:
- Convert the endpoint doorbell test to use a threaded IRQ to fix a
'sleeping while atomic' issue (Bhanu Seshu Kumar Valluri)
- Add endpoint VNTB MSI doorbell support to reduce latency between
host and endpoint (Frank Li)
New native PCIe controller drivers:
- Add CIX Sky1 host controller DT binding and driver (Hans Zhang)
- Add NXP S32G host controller DT binding and driver (Vincent
Guittot)
- Add Renesas RZ/G3S host controller DT binding and driver (Claudiu
Beznea)
- Add SpacemiT K1 host controller DT binding and driver (Alex Elder)
Amlogic Meson PCIe controller driver:
- Update DT binding to name DBI region 'dbi', not 'elbi', and update
driver to support both (Manivannan Sadhasivam)
Apple PCIe controller driver:
- Move struct pci_host_bridge allocation from pci_host_common_init()
to callers, which significantly simplifies pcie-apple (Marc
Zyngier)
Broadcom STB PCIe controller driver:
- Disable advertising ASPM L0s support correctly (Jim Quinlan)
- Add a panic/die handler to print diagnostic info in case PCIe
caused an unrecoverable abort (Jim Quinlan)
Cadence PCIe controller driver:
- Add module support for Cadence platform host and endpoint
controller driver (Manikandan K Pillai)
- Split headers into 'legacy' (LGA) and 'high perf' (HPA) to prepare
for new CIX Sky1 driver (Manikandan K Pillai)
MediaTek PCIe controller driver:
- Convert DT binding to YAML schema (Christian Marangi)
- Add Airoha AN7583 DT compatible and driver support (Christian
Marangi)
Qualcomm PCIe controller driver:
- Add Qualcomm Kaanapali to SM8550 DT binding (Qiang Yu)
- Add required 'power-domains' and 'resets' to qcom sa8775p, sc7280,
sc8280xp, sm8150, sm8250, sm8350, sm8450, sm8550, x1e80100 DT
schemas (Krzysztof Kozlowski)
- Look up OPP using both frequency and data rate (not just frequency)
so RPMh votes can account for both (Krishna Chaitanya Chundru)
Rockchip DesignWare PCIe controller driver:
- Add Rockchip RK3528 compatible strings in DT binding (Yao Zi)
STMicroelectronics STM32MP25 PCIe controller driver:
- Fix a race between link training and endpoint register
initialization (Christian Bruel)
- Align endpoint allocations to match the ATU requirements (Christian
Bruel)
Synopsys DesignWare PCIe controller driver:
- Clear L1 PM Substate Capability 'Supported' bits unless glue driver
says it's supported, which prevents users from enabling non-working
L1SS. Currently only qcom and tegra194 support L1SS (Bjorn Helgaas)
- Remove now-superfluous L1SS disable code from tegra194 (Bjorn
Helgaas)
- Configure L1SS support in dw-rockchip when DT says
'supports-clkreq' (Shawn Lin)
TI Keystone PCIe controller driver:
- Fail the probe instead of silently succeeding if ks_pcie_of_data
didn't specify Root Complex or Endpoint mode (Siddharth Vadapalli)
- Make keystone buildable as a loadable module, except on ARM32 where
hook_fault_code() is __init (Siddharth Vadapalli)"
* tag 'pci-v6.19-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci: (100 commits)
MAINTAINERS: Add Manivannan Sadhasivam as PCI/pwrctrl maintainer
MAINTAINERS: Add CIX Sky1 PCIe controller driver maintainer
PCI: sky1: Add PCIe host support for CIX Sky1
dt-bindings: PCI: Add CIX Sky1 PCIe Root Complex bindings
PCI: cadence: Add support for High Perf Architecture (HPA) controller
MAINTAINERS: Add NXP S32G PCIe controller driver maintainer
PCI: s32g: Add NXP S32G PCIe controller driver (RC)
PCI: dwc: Add register and bitfield definitions
dt-bindings: PCI: s32g: Add NXP S32G PCIe controller
PCI: Add Renesas RZ/G3S host controller driver
PCI: host-generic: Move bridge allocation outside of pci_host_common_init()
dt-bindings: PCI: Add Renesas RZ/G3S PCIe controller binding
PCI: Validate pci_rebar_size_supported() input
Documentation: PCI: Amend error recovery doc with pci_save_state() rules
treewide: Drop pci_save_state() after pci_restore_state()
PCI/ERR: Ensure error recoverability at all times
PCI/PM: Stop needlessly clearing state_saved on enumeration and thaw
PCI/PM: Reinstate clearing state_saved in legacy and !PM codepaths
PCI: dw-rockchip: Configure L1SS support
PCI: tegra194: Remove unnecessary L1SS disable code
...
As we have exposed the PCS registers via the SWMII we can now start looking
at connecting the XPCS driver to those registers and let it mange the PCS
instead of us doing it directly from the fbnic driver.
For now this just gets us the ability to detect link. The hope is in the
future to add some of the vendor specific registers to begin enabling XPCS
configuration of the interface.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/176374325295.959489.14521115864034905277.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In order for us to support a PCS device we need to add an MDIO bus to allow
the drivers to have access to the registers for the device. This change
adds such an interface.
The interface will consist of 2 PHY addrs, the first one consisting of a
PMD and PCS, and the second just being a PCS. There is a need for 2 PHYs
addrs due to the fact that in order to support the 50GBase-CR2 mode we will
need to access and configure the PCS vendor registers and RSFEC registers
from the second lane identical to the first.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/176374324532.959489.15389723111560978054.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
One complication with the design of our part is that the PMD doesn't
provide a direct signal to the host. Instead we have visibility to signals
that the PCS provides to the MAC that allow us to check the link state
through that.
We will need to account for several things in the PMD and firmware when
managing the link. Specifically when the link first starts to come up the
PMD will cause the link to flap. This is due to the firmware starting a
training cycle when the link is first detected. This will cause link
flapping if we were to immediately report link up when the PCS first
detects it.
To address that we are adding a pmd_state variable that is meant to be a
countdown of sorts indicating the state of the PMD. If the link is down or
has been reconfigured the PMD will start out in the initialize state. By
default the link is assumed to be in the SEND_DATA state if it is available
on initial link inspection. If link is detected while in the initialize
state the PMD state will switch to training, and if after 4 seconds the
link is still stable we will transition to link_ready, and finally the
send_data state. With this we can avoid link flapping when a cable is
first connected to the NIC.
One side effect of this is that we need to pull the link state away from
the PCS. For now we use a union of the PCS link state register value and
the pmd_state. The plan is to add a PMD register to report the pmd_state
to the phylink interface. With that we can then look at switching over to
the use of the XPCS driver for fbnic instead of having an internal one.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/176374323107.959489.14951134213387615059.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Throughout several spots in the code I had called out the IRQ as being
related to the PCS. However the actual IRQ is a part of the MAC and it is
just exposing PCS data. To more accurately reflect the owner of the calls
this change makes it so that we rename the functions and values that are
taking in the interrupt value and processing it to reflect that it is a MAC
call and not a PCS one.
This change is mostly motivated by the fact that we will be moving the
handling of this interrupt from being PCS focused to being more PMA/PMD
focused as this will drive the phydev driver that I am adding instead of
driving the PCS directly.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/176374322373.959489.12018231545479053860.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Fix a potential counter roll-over issue in fbnic_mbx_alloc_rx_msgs()
when calculating descriptor slots. The issue occurs when head - tail
results in a large positive value (unsigned) and the compiler interprets
head - tail - 1 as a signed value.
Since FBNIC_IPC_MBX_DESC_LEN is a power of two, use a masking operation,
which is a common way of avoiding this problem when dealing with these
sort of ring space calculations.
Fixes: da3cde0820 ("eth: fbnic: Add FW communication mechanism")
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20251125211704.3222413-1-mohsin.bashr@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In 2009, commit c82f63e411 ("PCI: check saved state before restore")
changed the behavior of pci_restore_state() such that it became necessary
to call pci_save_state() afterwards, lest recovery from subsequent PCI
errors fails.
The commit has just been reverted and so all the pci_save_state() after
pci_restore_state() calls that have accumulated in the tree are now
superfluous. Drop them.
Two drivers chose a different approach to achieve the same result:
drivers/scsi/ipr.c and drivers/net/ethernet/intel/e1000e/netdev.c set the
pci_dev's "state_saved" flag to true before calling pci_restore_state().
Drop this as well.
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com> # qat
Link: https://patch.msgid.link/c2b28cc4defa1b743cf1dedee23c455be98b397a.1760274044.git.lukas@wunner.de
fbnic supports pause frames. When pause frames are enabled presumably
user expects lossless operation from the NIC. Make sure we configure
RDE (Rx DMA Engine) to DROP_NEVER mode to avoid discards due to delays
in fetching Rx descriptors from the host.
While at it enable DROP_NEVER when NIC only has a single queue
configured. In this case the NIC acts as a FIFO so there's no risk
of head-of-line blocking other queues by making RDE wait. If pause
is disabled this just moves the packet loss from the DMA engine to
the Rx buffer.
Remove redundant call to fbnic_config_drop_mode_rcq(), introduced by
commit 0cb4c0a137 ("eth: fbnic: Implement Rx queue
alloc/start/stop/free"). This call does not add value as
fbnic_enable_rcq(), which is called immediately afterward, already
handles this.
Although we do not support autoneg at this time, preserve tx_pause in
.mac_link_up instead of fbnic_phylink_get_pauseparam()
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20251113232610.1151712-1-mohsin.bashr@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The TLV_MAX_DATA macro calculates (PAGE_SIZE - 512) which can exceed
the maximum value of a 16-bit unsigned integer on architectures with
large page sizes, causing compiler warnings:
drivers/net/ethernet/meta/fbnic/fbnic_tlv.h:83:24: warning: conversion
from 'long unsigned int' to 'short unsigned int' changes value from
'261632' to '65024' [-Woverflow]
Fix this by explicitly masking the result to 16 bits using bitwise AND
with 0xFFFF, ensuring the value fits within the expected data type
while maintaining the intended behavior for normal page sizes.
This preserves the existing functionality while eliminating the
compiler warning and potential undefined behavior from integer
truncation.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202510190832.3SQkTCHe-lkp@intel.com/
Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>
Link: https://patch.msgid.link/182b9d0235d044d69d7a57c1296cc6f46e395beb.1761039651.git.xiaopei01@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The HW always works on a 4K page size. When the OS supports larger
pages, we fragment them across multiple BDQ descriptors.
We were not properly incrementing the descriptor, which resulted in us
specifying the last chunks id/addr and then 15 zero descriptors. This
would cause packet loss and driver crashes. This is not a fix since the
Kconfig prevents use outside of x86.
Signed-off-by: Dimitri Daskalakis <dimitri.daskalakis1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20251013211449.1377054-2-dimitri.daskalakis1@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Fix several minor typos and grammatical errors in comments and log
(in fbnic firmware, PCI, and time modules)
Changes include:
- "cordeump" -> "coredump"
- "of" -> "off" in RPC config comment
- "healty" -> "healthy" in firmware heartbeat comment
- "Firmware crashed detected!" -> "Firmware crash detected!"
- "The could be caused" -> "This could be caused"
- "lockng" -> "locking" in fbnic_time.c
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20251013160507.768820-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Rx processing under normal circumstances has 3 rings - 2 buffer
rings (heads, payloads) and a completion ring. All the rings
have a struct fbnic_ring. Make sure we expose alloc_failed
counter from the buffer rings, previously only the alloc_failed
from the completion ring was reported, even tho all ring types
may increment this counter (buffer rings in __fbnic_fill_bdq()).
This makes the pp_alloc_fail.py test pass, it expects the qstat
to be incrementing as page pool injections happen.
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: 67dc4eb5fc ("eth: fbnic: report software Rx queue stats")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251007232653.2099376-7-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When rings are freed - stats get added to the device level stat
structs. Save the stats from the XDP_TX ring just as Tx stats.
Previously they would be saved to Rx and Tx stats. So we'd not
see XDP_TX packets as Rx during runtime but after an down/up cycle
the packets would appear in stats.
Correct the helper used by ethtool code which does a runtime
config switch.
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: 5213ff0863 ("eth: fbnic: Collect packet statistics for XDP")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251007232653.2099376-4-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Make XDP-handled packets appear in the Rx stats. The driver has been
counting XDP_TX packets on the Tx ring, but there wasn't much accounting
on the Rx side (the Rx bytes appear to be incremented on XDP_TX but
XDP_DROP / XDP_ABORT are only counted as Rx drops).
Counting XDP_TX packets (not just bytes) in Rx stats looks like
a simple bug of omission.
The XDP_DROP handling appears to be intentional. Whether XDP_DROP
packets should be counted in interface-level Rx stats is a bit
unclear historically. When we were defining qstats, however,
we clarified based on operational experience that in this context:
name: rx-packets
doc: |
Number of wire packets successfully received and passed to the stack.
For drivers supporting XDP, XDP is considered the first layer
of the stack, so packets consumed by XDP are still counted here.
fbnic does not obey this requirement. Since XDP support has been added
in current release cycle, instead of splitting interface and qstat
handling - make them both follow the qstat definition.
Another small tweak here is that we count bytes as received on the wire
rather than post-XDP bytes (xdp_get_buff_len() vs skb->len).
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: 5213ff0863 ("eth: fbnic: Collect packet statistics for XDP")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251007232653.2099376-3-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
XDP_TX typically uses no offloads. To optimize XDP we added a "default
descriptor" feature to the chip, which allows us to send XDP frames with
just the buffer descriptors (DMA address + length). All the metadata
descriptors are derived from the queue config.
Commit under Fixes missed adding setting the defaults up when transplanting
the code from the prototype driver. Importantly after reset the "request
completion" bit is not set. Packets still get sent but there's no
completion, so ring is not cleaned up. We can send one ring's worth
of packets and then will start dropping all frames that got the XDP_TX
action from the XDP prog.
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: 168deb7b31 ("eth: fbnic: Add support for XDP_TX action")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20251007232653.2099376-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add support to read module EEPROM for fbnic. Towards this, add required
support to issue a new command to the firmware and to receive the response
to the corresponding command.
Create a local copy of the data in the completion struct before writing to
ethtool_module_eeprom to avoid writing to data in case it is freed. Given
that EEPROM pages are small, the overhead of additional copy is
negligible.
Do not block API with explicit checks since API has appropriate checks in
place for length, offset, and page.
Explicitly check bank, page, offset, and length in
fbnic_fw_parse_qsfp_read_resp() to match EEPROM read responses to the
correct request. This is important because if the driver times out waiting
for an EEPROM read response, a subsequent read request with different
values is susceptible to receiving an erroneous response (i.e., the
response to the previous request).
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Link: https://patch.msgid.link/20250922231855.3717483-1-mohsin.bashr@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
FW crashes are detected based on uptime going back, expose the uptime
via devlink health diagnose.
$ devlink -j health diagnose pci/0000:01:00.0 reporter fw
{"last_heartbeat":{"fw_uptime":{"sec":201,"msec":76}}}
$ devlink -j health diagnose pci/0000:01:00.0 reporter fw
last_heartbeat:
fw_uptime:
sec: 201 msec: 76
Reviewed-by: Lee Trager <lee@trager.us>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250916231420.1693955-9-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently we only detect FW crashes when it stops responding
to heartbeat messages. FW has a watchdog which will reset it
in case of crashes. Use FW uptime sent in the ownership and
heartbeat messages to detect that the watchdog has fired
(uptime went down).
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250916231420.1693955-3-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Support devmem Tx. We already use skb_frag_dma_map(), we just need
to make sure we don't try to unmap the frags. Check if frag is
unreadable and mark the ring entry.
# ./tools/testing/selftests/drivers/net/hw/devmem.py
TAP version 13
1..3
ok 1 devmem.check_rx
ok 2 devmem.check_tx
ok 3 devmem.check_tx_chunks
# Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0
Acked-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250916145401.1464550-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Support queue ops. fbnic doesn't shut down the entire device
just to restart a single queue.
./tools/testing/selftests/drivers/net/hw/iou-zcrx.py
TAP version 13
1..3
ok 1 iou-zcrx.test_zcrx
ok 2 iou-zcrx.test_zcrx_oneshot
ok 3 iou-zcrx.test_zcrx_rss
# Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0
Acked-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-15-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Queue API may ask us to allocate page pools when the device
is down, to validate that we ingested a memory provider binding.
Don't require NAPI to be passed to fbnic_alloc_qt_page_pools(),
to make calling fbnic_alloc_qt_page_pools() without NAPI possible.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-14-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
We need to be more careful about when direct page pool recycling
is enabled in preparation for queue ops support. Don't set the
NAPI pointer, call page_pool_enable_direct_recycling() from
the function that activates the queue (once the config can
no longer fail).
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-13-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Allow allocating a page pool with unreadable memory for the payload
ring (sub1). We need to provide the queue ID so that the memory provider
can match the PP. Use the appropriate page pool DMA sync helper.
For unreadable mem the direction has to be FROM_DEVICE. The default
is BIDIR for XDP, but obviously unreadable mem is not compatible
with XDP in the first place, so that's fine. While at it remove
the define for page pool flags.
The rxq_idx is passed to fbnic_alloc_rx_qt_resources() explicitly
to make it easy to allocate page pools without NAPI (see the patch
after the next).
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-12-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Factor out handling a single nv from fbnic_enable() to make
it reusable for queue ops. Use a __ prefix for the factored
out code. The real fbnic_nv_enable() which will include
fbnic_wrfl() will be added with the qops, to avoid unused
function warnings.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-9-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Factor out handling a single nv from fbnic_disable() to make
it reusable for queue ops. Use a __ prefix for the factored
out code. The real fbnic_nv_disable() which will include
fbnic_wrfl() will be added with the qops, to avoid unused
function warnings.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-7-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Use netmem_ref instead of struct page pointer in prep for
unreadable memory. fbnic has separate free buffer submission
queues for headers and for data. Refactor the helper which
returns page pointer for a submission buffer to take the
high level queue container, create a separate handler
for header and payload rings. This ties the "upcast" from
netmem to system page to use of sub0 which we know has
system pages.
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-5-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
page pools are now at the ring level, move page pool alloc
to fbnic_alloc_rx_qt_resources(), and freeing to
fbnic_free_qt_resources().
This significantly simplifies fbnic_alloc_napi_vector() error
handling, by removing a late failure point.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-4-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Move rxq_info and mem model registration from fbnic_alloc_napi_vector()
and fbnic_alloc_nv_resources() to fbnic_alloc_rx_qt_resources().
The rxq_info is now registered later in the process, but that
should not cause any issues.
rxq_info lives in the fbnic_q_triad (qt) struct so qt init is a more
natural place. Encapsulating the logic in the qt functions will also
allow simplifying the cleanup in the NAPI related alloc functions
in the next commit.
Rx does not have a dedicated fbnic_free_rx_qt_resources(),
but we can use xdp_rxq_info_is_reg() to tell whether given
rxq_info was in use (effectively - if it's a qt for an Rx queue).
Having to pass nv into fbnic_alloc_rx_qt_resources() is not
great in terms of layering, but that's temporary, pp will
move soon..
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-3-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In preparation for memory providers we need a closer association
between queues and page pools. We used to have a page pool at the
NAPI level to serve all associated queues but with MP the queues
under a NAPI may no longer be created equal.
The "ring" structure in fbnic is a descriptor ring. We have separate
"rings" for payload and header pages ("to device"), as well as a ring
for completions ("from device"). Technically we only need the page
pool pointers in the "to device" rings, so adding the pointer to
the ring struct is a bit wasteful. But it makes passing the structures
around much easier.
For now both "to device" rings store a pointer to the same
page pool. Using more than one queue per NAPI is extremely rare
so don't bother trying to share a single page pool between queues.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250901211214.1027927-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Cross-merge networking fixes after downstream PR (net-6.17-rc4).
No conflicts.
Adjacent changes:
drivers/net/ethernet/intel/idpf/idpf_txrx.c
02614eee26 ("idpf: do not linearize big TSO packets")
6c4e684802 ("idpf: remove obsolete stashing code")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The MACDA TCAM can only be accessed by one entity at a time and as such we
cannot have simultaneous reads from the firmware to probe for changes from
the host. As such we have to send a message indicating what the state of
the MACDA is to the firmware when we updated it so that the firmware can
sync up the TCAMs it owns to route BMC packets to the host.
To support that we are adding a new message that is invoked when we write
the MACDA that will notify the firmware of updates from the host and allow
it to sync up the TCAM configuration to match the one on the host side.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/175623750782.2246365.9178255870985916357.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The BMC itself can decide to abandon a link and move onto another link in
the event of things such as a link flap. As a result the driver may load
with the BMC not present, and then needs to update things to support the
BMC being present while the link is up and the NIC is passing traffic.
To support this we add support to the watchdog to reinitialize the RPC to
support adding the BMC unicast, multicast, and multicast promiscuous
filters while the link is up and the NIC owns the link.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/175623750101.2246365.8518307324797058580.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
