When MCONFIG.SKEW=0 and MCONFIG.ODHPP=0, the ENTDAA transaction gets
corrupted and results in a no repeated-start condition at the end of
address assignment.
Workaround: Set MCONFIG.SKEW to 1 before initiating the DAA process.
After the DAA process is completed, return MCONFIG.SKEW to its previous
value.
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Stanley Chu <yschu@nuvoton.com>
Link: https://lore.kernel.org/r/20250306075429.2265183-6-yschu@nuvoton.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
I3C HW may generate an invalid SlvStart event when emitting a STOP.
If it is a true SlvStart, the MSTATUS state is SLVREQ. Check the
MSTATUS state to ignore the false event.
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Stanley Chu <yschu@nuvoton.com>
Link: https://lore.kernel.org/r/20250306075429.2265183-5-yschu@nuvoton.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
I3C HW stalls the write transfer if the transmit FIFO becomes empty,
when new data is written to FIFO, I3C HW resumes the transfer but the
first transmitted data bit may have the wrong value.
Fill the FIFO in advance to prevent FIFO from becoming empty.
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Stanley Chu <yschu@nuvoton.com>
Link: https://lore.kernel.org/r/20250306075429.2265183-4-yschu@nuvoton.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Nuvoton npcm845 SoC uses an older IP version, which has specific
hardware issues that need to be addressed with a different compatible
string.
Add driver data for different compatible strings to define platform
specific quirks.
Add compatible string for npcm845 to define its own driver data.
Signed-off-by: Stanley Chu <yschu@nuvoton.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20250306075429.2265183-3-yschu@nuvoton.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Nuvoton npcm845 SoC uses the same Silvico IP but an older version.
Need to add a new compatible string to distinguish between different
hardware versions.
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Stanley Chu <yschu@nuvoton.com>
Link: https://lore.kernel.org/r/20250306075429.2265183-2-yschu@nuvoton.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Marcus Wichelmann says:
====================
XDP metadata support for tun driver
Hi all,
this v5 of the patch series is very similar to v4, but rebased onto the
bpf-next/net branch instead of bpf-next/master.
Because the commit c047e0e0e4 ("selftests/bpf: Optionally open a
dedicated namespace to run test in it") is not yet included in this branch,
I changed the xdp_context_tuntap test to manually create a namespace to run
the test in.
Not so successful pipeline: https://github.com/kernel-patches/bpf/actions/runs/13682405154
The CI pipeline failed because of veristat changes in seemingly unrelated
eBPF programs. I don't think this has to do with the changes from this
patch series, but if it does, please let me know what I may have to do
different to make the CI pass.
====================
Link: https://patch.msgid.link/20250305213438.3863922-1-marcus.wichelmann@hetzner-cloud.de
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
The open_tuntap helper function uses open() to get a file descriptor for
/dev/net/tun.
The open(2) manpage writes this about its return value:
On success, open(), openat(), and creat() return the new file
descriptor (a nonnegative integer). On error, -1 is returned and
errno is set to indicate the error.
This means that the fd > 0 assertion in the open_tuntap helper is
incorrect and should rather check for fd >= 0.
When running the BPF selftests locally, this incorrect assertion was not
an issue, but the BPF kernel-patches CI failed because of this:
open_tuntap:FAIL:open(/dev/net/tun) unexpected open(/dev/net/tun):
actual 0 <= expected 0
Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250305213438.3863922-7-marcus.wichelmann@hetzner-cloud.de
Add a selftest that creates a tap device, attaches XDP and TC programs,
writes a packet with a test payload into the tap device and checks the
test result. This test ensures that the XDP metadata support in the tun
driver is enabled and that the metadata size is correctly passed to the
skb.
See the previous commit ("selftests/bpf: refactor xdp_context_functional
test and bpf program") for details about the test design.
The test runs in its own network namespace. This provides some extra
safety against conflicting interface names.
Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250305213438.3863922-6-marcus.wichelmann@hetzner-cloud.de
The existing XDP metadata test works by creating a veth pair and
attaching XDP & TC programs that drop the packet when the condition of
the test isn't fulfilled. The test then pings through the veth pair and
succeeds when the ping comes through.
While this test works great for a veth pair, it is hard to replicate for
tap devices to test the XDP metadata support of them. A similar test for
the tun driver would either involve logic to reply to the ping request,
or would have to capture the packet to check if it was dropped or not.
To make the testing of other drivers easier while still maximizing code
reuse, this commit refactors the existing xdp_context_functional test to
use a test_result map. Instead of conditionally passing or dropping the
packet, the TC program is changed to copy the received metadata into the
value of that single-entry array map. Tests can then verify that the map
value matches the expectation.
This testing logic is easy to adapt to other network drivers as the only
remaining requirement is that there is some way to send a custom
Ethernet packet through it that triggers the XDP & TC programs.
The Ethernet header of that custom packet is all-zero, because it is not
required to be valid for the test to work. The zero ethertype also helps
to filter out packets that are not related to the test and would
otherwise interfere with it.
The payload of the Ethernet packet is used as the test data that is
expected to be passed as metadata from the XDP to the TC program and
written to the map. It has a fixed size of 32 bytes which is a
reasonable size that should be supported by both drivers. Additional
packet headers are not necessary for the test and were therefore skipped
to keep the testing code short.
This new testing methodology no longer requires the veth interfaces to
have IP addresses assigned, therefore these were removed.
Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250305213438.3863922-5-marcus.wichelmann@hetzner-cloud.de
To test the XDP metadata functionality of the tun driver, it's necessary
to create a new tap device first. A helper function for this already
exists in lwt_helpers.h. Move it to the common network helpers header,
so it can be reused in other tests.
Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250305213438.3863922-4-marcus.wichelmann@hetzner-cloud.de
When the XDP metadata area was used, it is expected that the same
metadata can also be accessed from TC, as can be read in the description
of the bpf_xdp_adjust_meta helper function. In the tun driver, this was
not yet implemented.
To make this work, the skb that is being built on XDP_PASS should know
of the current size of the metadata area. This is ensured by adding
calls to skb_metadata_set. For the tun_xdp_one code path, an additional
check is necessary to handle the case where the externally initialized
xdp_buff has no metadata support (xdp->data_meta == xdp->data + 1).
More information about this feature can be found in the commit message
of commit de8f3a83b0 ("bpf: add meta pointer for direct access").
Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250305213438.3863922-3-marcus.wichelmann@hetzner-cloud.de
Enable the support for the bpf_xdp_adjust_meta helper function for XDP
buffers initialized by the tun driver. This allows to reserve a metadata
area that is useful to pass any information from one XDP program to
another one, for example when using tail-calls.
Whether this helper function can be used in an XDP program depends on
how the xdp_buff was initialized. Most net drivers initialize the
xdp_buff in a way, that allows bpf_xdp_adjust_meta to be used. In case
of the tun driver, this is currently not the case.
There are two code paths in the tun driver that lead to a
bpf_prog_run_xdp and where metadata support should be enabled:
1. tun_build_skb, which is called by tun_get_user and is used when
writing packets from userspace into the device. In this case, the
xdp_buff created in tun_build_skb has no support for
bpf_xdp_adjust_meta and calls of that helper function result in
ENOTSUPP.
For this code path, it's sufficient to set the meta_valid argument of
the xdp_prepare_buff call. The reserved headroom is large enough
already.
2. tun_xdp_one, which is called by tun_sendmsg which again is called by
other drivers (e.g. vhost_net). When the TUN_MSG_PTR mode is used,
another driver may pass a batch of xdp_buffs to the tun driver. In
this case, that other driver is the one initializing the xdp_buff.
See commit 043d222f93 ("tuntap: accept an array of XDP buffs
through sendmsg()") for details.
For now, the vhost_net driver is the only one using TUN_MSG_PTR and
it already initializes the xdp_buffs with metadata support and
sufficient headroom. But the tun driver disables it again, so the
xdp_set_data_meta_invalid call has to be removed.
Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250305213438.3863922-2-marcus.wichelmann@hetzner-cloud.de
A lot of code optimization to avoid cases where call paths will end up calling
the same writes multiple times and needlessly caching variables. To accomplish
this some of the writes are now made into an atomically written "perf" variable.
Locking has been overhauled to ensure it only applies to the necessary functions.
Tracing has been adjusted to ensure trace events only are used right before
writing out to the hardware.
NOTE: This is a redo of amd-pstate-v6.15-2025-03-03 with a fixed Fixes tag.
-----BEGIN PGP SIGNATURE-----
iQJOBAABCgA4FiEECwtuSU6dXvs5GA2aLRkspiR3AnYFAmfJ8w8aHG1hcmlvLmxp
bW9uY2llbGxvQGFtZC5jb20ACgkQLRkspiR3AnaugQ/9GvheK3/lWweGF3f4ixdl
xS0XTj3DYQBxDvP2H35QRBHaUQQADJnJLjpl1HHy0x9Hem6m3oLZH3QpqKDLb1xX
QWzI2JJZ9+KPZRKRwlBnzENcHtBraKX4M/+vvhTo6LSbLfSz47cdZhX6r+9siwPR
ofWfusfBlEVPPLaul2Q+oOaQzvwy9Or2q2y3xICzo+Vo3QilSk3pekN8bd2CVd9y
L1t1sAeN1StiOLBRbdbh8B2oyJfCCmSI85P8+sEKKR58G1q42Dv4NRl7fgzuJAfO
4ATgX0RjNZcI9yLPmLr5PFmHJYvpHr29MAWKAo5a8VwMu1cBTv0FFkEboRvUgiXl
3+hjQJGkyCZJTxIWhnvKl6Ci00N5apmwc1iMeoa1A1xvvTVkXLmn8RrYIJm2xMCH
27SPJAQx+7e2cRcgjb3orz2Ymj+I9WoGy68/wdmnWM+ZxF1QaKguhM0lrIKFbu7K
6CzVnndVgtYt9kFi/SQ4m1e8zr6RnvPWTxqQxTCVQZBNahe3b7DgnrrNrB/NBU86
QotiTBIxQed6oqHAtL2mFRb9SdTGh9PE5xGcR94qlEGqVtu9KZIFqCDG1OgZKkR5
9yLLai7sUGfMCLuEsdM5hXvf4fOHaGSQ0Cxx2qYWC3DDnS651fMNKh/taBo8RmS3
r18loH2dKvBvOi2beCA5sMk=
=VkdW
-----END PGP SIGNATURE-----
Merge tag 'amd-pstate-v6.15-2025-03-06' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/superm1/linux
Merge amd-pstate updates for 6.15 (3/6/25) from Mario Limonciello:
"A lot of code optimization to avoid cases where call paths will end up
calling the same writes multiple times and needlessly caching variables.
To accomplish this some of the writes are now made into an atomically
written "perf" variable. Locking has been overhauled to ensure it only
applies to the necessary functions. Tracing has been adjusted to ensure
trace events only are used right before writing out to the hardware."
NOTE: This is a redo of amd-pstate-v6.15-2025-03-03 with a fixed Fixes tag.
* tag 'amd-pstate-v6.15-2025-03-06' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/superm1/linux: (29 commits)
cpufreq/amd-pstate: Drop actions in amd_pstate_epp_cpu_offline()
cpufreq/amd-pstate: Stop caching EPP
cpufreq/amd-pstate: Rework CPPC enabling
cpufreq/amd-pstate: Drop debug statements for policy setting
cpufreq/amd-pstate: Update cppc_req_cached for shared mem EPP writes
cpufreq/amd-pstate: Move all EPP tracing into *_update_perf and *_set_epp functions
cpufreq/amd-pstate: Cache CPPC request in shared mem case too
cpufreq/amd-pstate: Replace all AMD_CPPC_* macros with masks
cpufreq/amd-pstate-ut: Adjust variable scope
cpufreq/amd-pstate-ut: Run on all of the correct CPUs
cpufreq/amd-pstate-ut: Drop SUCCESS and FAIL enums
cpufreq/amd-pstate-ut: Allow lowest nonlinear and lowest to be the same
cpufreq/amd-pstate-ut: Use _free macro to free put policy
cpufreq/amd-pstate: Drop `cppc_cap1_cached`
cpufreq/amd-pstate: Overhaul locking
cpufreq/amd-pstate: Move perf values into a union
cpufreq/amd-pstate: Drop min and max cached frequencies
cpufreq/amd-pstate: Show a warning when a CPU fails to setup
cpufreq/amd-pstate: Invalidate cppc_req_cached during suspend
cpufreq/amd-pstate: Fix the clamping of perf values
...
This patch is also an issue report. get_cpu_topology will always save
into cpupower_topology a cores size of 0. The code to handle this looks
like it was commented out, and what is commented out is missing a curly
bracket.
https://elixir.bootlin.com/linux/v6.13.5/source/tools/power/cpupower/lib/cpupower.c#L206-L212
Inspiration was taken from psutil to implement this by querying
core_cpu_list. Instead of using a hashmap, I used a sorted array, and
counted the number of valid unique strings. The counting of this takes
place before the qsort for .pkg as the following code says it is
dependent on the order of that sort.
The previous code claimed Intel CPUs are not numbered correctly. I was
not able to reproduce that issue and removed that comment and the code.
This commit was tested with the libcpupower SWIG Python bindings and
performed correctly on 4 different setups. The most notable is the
Framework Intel laptop; a hybrid system of 4 P cores (8 threads) and 8 E
cores (8 threads).
The 4 setups: A 4 core virt-manager VM running Fedora 41 4c/4t (specs not
listed) was tested as a sanity test for VMs. A Lenovo Ryzen 7 Pro 7840HS
8c/16t. A Supermico Intel(R) Xeon(R) Gold 6330 CPU w/ 56c/112t with 2 CPU
sockets. A Framework 12th Gen Intel(R) Core(TM) i5-1240P with hybrid
cores.
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: AuthenticAMD
Model name: AMD Ryzen 7 PRO 7840HS w/ Radeon 780M Graphics
CPU family: 25
Model: 116
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
Stepping: 1
CPU(s): 112
On-line CPU(s) list: 0-111
Vendor ID: GenuineIntel
BIOS Vendor ID: Intel(R) Corporation
Model name: Intel(R) Xeon(R) Gold 6330 CPU @ 2.00GHz
BIOS Model name: Intel(R) Xeon(R) Gold 6330 CPU @ 2.00GHz CPU @ 2.0GHz
BIOS CPU family: 179
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 28
Socket(s): 2
Stepping: 6
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: GenuineIntel
Model name: 12th Gen Intel(R) Core(TM) i5-1240P
CPU family: 6
Model: 154
Thread(s) per core: 2
Core(s) per socket: 12
Socket(s): 1
Stepping: 3
Link: https://lore.kernel.org/r/20250305210901.24177-1-jwyatt@redhat.com
Signed-off-by: "John B. Wyatt IV" <jwyatt@redhat.com>
Signed-off-by: "John B. Wyatt IV" <sageofredondo@gmail.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
cmd_monitor() calls get_cpu_topology() to allocate memory for
cpu topology and fails to release in error legs.
Fix it to call cpu_topology_release() from error legs.
Link: https://lore.kernel.org/r/20250305225342.19447-2-skhan@linuxfoundation.org
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Notice that em_dev_register_perf_domain() and the functions called by it
do not update objects pointed to by its cb and cpus parameters, so the
const modifier can be added to them.
This allows the return value of cpumask_of() or a pointer to a
struct em_data_callback declared as const to be passed to
em_dev_register_perf_domain() directly without explicit type
casting which is rather handy.
No intentional functional impact.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/4648962.LvFx2qVVIh@rjwysocki.net
The Pid type alias represents the integer type used for pids in the
kernel. It's the Rust equivalent to pid_t, and there are various methods
on Task that use Pid as the return type.
Binder needs to use Pid as the type for function arguments and struct
fields in many places. Thus, make the type public so that Binder can
access it.
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Fiona Behrens <me@kloenk.dev>
Link: https://lore.kernel.org/r/20250130-task-pid-pub-v1-1-508808bcfcdc@google.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Add DWI backlight controller nodes for Apple A10 SoC, and enable it for:
- iPhone 7
- iPhone 7 Plus
- iPod touch 7
- iPad 6
- iPad 7
Signed-off-by: Nick Chan <towinchenmi@gmail.com>
Link: https://lore.kernel.org/r/20250228-dwi-dt-v2-4-69e450bc4bfb@gmail.com
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Add DWI backlight controller nodes for Apple A9 SoC, and enable it for:
- iPhone 6
- iPhone 6s
- iPhone SE
- iPad 5
Signed-off-by: Nick Chan <towinchenmi@gmail.com>
Link: https://lore.kernel.org/r/20250228-dwi-dt-v2-3-69e450bc4bfb@gmail.com
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Add DWI backlight controller nodes for Apple A8 SoC, and enable it for:
- iPhone 6
- iPhone 6 Plus
- iPad mini 4
- iPod touch 6
Signed-off-by: Nick Chan <towinchenmi@gmail.com>
Link: https://lore.kernel.org/r/20250228-dwi-dt-v2-2-69e450bc4bfb@gmail.com
Signed-off-by: Sven Peter <sven@svenpeter.dev>
This function can be called with different function pointers when
different allocator (e.g. Kmalloc, Vmalloc, KVmalloc), however since
this function is not polymorphic, only one instance is generated,
and function pointers are used. Given that this function is called
for any Rust-side allocation/deallocation, performance matters a lot,
so making this function inlineable.
This is discovered when doing helper inlining work, since it's discovered
that even with helpers inlined, rust_helper_ symbols are still present
in final vmlinux binary, and it turns out this function is inhibiting
the inlining, and introducing indirect function calls.
Signed-off-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250105194054.545201-4-gary@garyguo.net
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Danilo has been involved with the Rust for Linux project for a year now.
He is primarily working on the Nova GPU driver [1][2].
In addition, he has been active in the mailing list and most recently
submitted the Device / Driver PCI / Platform series.
He is also already a maintainer of `RUST [ALLOC]` as well as several
other DRM-related entries.
His expertise developing Rust abstractions and APIs for one of the major
users of Rust in the kernel will be very useful to have around in the
future. Thus add him to the `RUST` entry as reviewer.
Link: https://rust-for-linux.com/nova-gpu-driver [1]
Link: https://lore.kernel.org/dri-devel/Zfsj0_tb-0-tNrJy@cassiopeiae/ [2]
Acked-by: Boqun Feng <boqun.feng@gmail.com>
Acked-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250129215948.135486-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
The documentation examples in rust/kernel/workqueue.rs use pr_info!
calls that lack a trailing newline. To maintain consistency with
kernel logging practices, this patch adds the newline to all
affected examples.
Fixes: 15b286d1fd ("rust: workqueue: add examples")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-5-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
The pr_info! example in rust/kernel/sync/locked_by.rs was missing
a newline. This patch appends the missing newline to ensure
that log messages for locked resources display correctly.
Fixes: 7b1f55e3a9 ("rust: sync: introduce `LockedBy`")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-4-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Several pr_info! calls in rust/kernel/init.rs (both in code examples
and macro documentation) were missing a newline, causing logs to
run together. This commit updates these calls to include a trailing
newline, improving readability and consistency with the C side.
Fixes: 6841d45a30 ("rust: init: add `stack_pin_init!` macro")
Fixes: 7f8977a7fe ("rust: init: add `{pin_}chain` functions to `{Pin}Init<T, E>`")
Fixes: d0fdc39612 ("rust: init: add `PinnedDrop` trait and macros")
Fixes: 4af84c6a85 ("rust: init: update expanded macro explanation")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-3-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. Added
one more Fixes tag (still same set of stable kernels). - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Add documentation for agree upon GPU SVM design principles, current
status, and future plans.
v4:
- Address Thomas's feedback
v5:
- s/Current/Basline (Thomas)
v7:
- Add license (CI)
- Add examples for design guideline reasoning (Alistair)
- Add snippet about possible livelock with concurrent GPU and and CPU
access (Alistair)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Alistair Popple <apopple@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-33-matthew.brost@intel.com
Used to show we can bounce memory multiple times which will happen once
a real migration policy is implemented. Can be removed once migration
policy is implemented.
v3:
- Pull some changes into the previous patch (Thomas)
- Better commit message (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-32-matthew.brost@intel.com
Useful to experiment with notifier size and how it affects performance.
v3:
- Pull missing changes including in following patch (Thomas)
v5:
- Spell out power of 2 (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-31-matthew.brost@intel.com
Add some useful SVM debug logging fro SVM range which prints the range's
state.
v2:
- Update logging with latest structure layout
v3:
- Better commit message (Thomas)
- New range structure (Thomas)
- s/COLLECTOT/s/COLLECTOR (Thomas)
v4:
- Drop partial evict message (Thomas)
- Use %p for pointers print (Thomas)
v6:
- Cast dma_addr to u64 (CI)
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-30-matthew.brost@intel.com
Wire xe_bo_move to GPU SVM migration via new helper xe_svm_bo_evict.
v2:
- Use xe_svm_bo_evict
- Drop bo->range
v3:
- Kernel doc (Thomas)
v4:
- Add missing xe_bo.c code
v5:
- Add XE_BO_FLAG_CPU_ADDR_MIRROR flag in this patch (Thomas)
- Add message on eviction failure
v6:
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-29-matthew.brost@intel.com
Migration is implemented with range granularity, with VRAM backing being
a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime of the
TTM BO is limited to when the SVM range is in VRAM (i.e., when a VRAM
SVM range is migrated to SRAM, the TTM BO is destroyed).
The design choice for using TTM BO for VRAM backing store, as opposed to
direct buddy allocation, is as follows:
- DRM buddy allocations are not at page granularity, offering no
advantage over a BO.
- Unified eviction is required (SVM VRAM and TTM BOs need to be able to
evict each other).
- For exhaustive eviction [1], SVM VRAM allocations will almost certainly
require a dma-resv.
- Likely allocation size is 2M which makes of size of BO (872)
acceptable per allocation (872 / 2M == .0004158).
With this, using TTM BO for VRAM backing store seems to be an obvious
choice as it allows leveraging of the TTM eviction code.
Current migration policy is migrate any SVM range greater than or equal
to 64k once.
[1] https://patchwork.freedesktop.org/series/133643/
v2:
- Rebase on latest GPU SVM
- Retry page fault on get pages returning mixed allocation
- Use drm_gpusvm_devmem
v3:
- Use new BO flags
- New range structure (Thomas)
- Hide migration behind Kconfig
- Kernel doc (Thomas)
- Use check_pages_threshold
v4:
- Don't evict partial unmaps in garbage collector (Thomas)
- Use %pe to print errors (Thomas)
- Use %p to print pointers (Thomas)
v5:
- Use range size helper (Thomas)
- Make BO external (Thomas)
- Set tile to NULL for BO creation (Thomas)
- Drop BO mirror flag (Thomas)
- Hold BO dma-resv lock across migration (Auld, Thomas)
v6:
- s/drm_info/drm_dbg (Thomas)
- s/migrated/skip_migrate (Himal)
- Better debug message on VRAM migration failure (Himal)
- Drop return BO from VRAM allocation function (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-28-matthew.brost@intel.com
Implement with a simple BO put which releases the device memory.
v2:
- Use new drm_gpusvm_devmem_ops
v3:
- Better commit message (Thomas)
v4:
- Use xe_bo_put_async (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-27-matthew.brost@intel.com
Get device pfns from BO's buddy blocks. Used in migrate_* core MM
functions called in GPU SVM to migrate between device and system memory.
v2:
- Use new drm_gpusvm_devmem_ops
v3:
- Better commit message (Thomas)
v5:
- s/xe_mem_region/xe_vram_region (Rebase)
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: Oak Zeng <oak.zeng@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-26-matthew.brost@intel.com
Add GPUSVM device memory copy vfunc functions and connect to migration
layer. Used for device memory migration.
v2:
- Allow NULL device pages in xe_svm_copy
- Use new drm_gpusvm_devmem_ops
v3:
- Prefix defines with XE_ (Thomas)
- Change copy chunk size to 8M
- Add a bunch of comments to xe_svm_copy to clarify behavior (Thomas)
- Better commit message (Thomas)
v5:
- s/xe_mem_region/xe_vram_region (Rebase)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-25-matthew.brost@intel.com
Add support for mapping device pages to Xe SVM by attaching drm_pagemap
to a memory region, which is then linked to a GPU SVM devmem allocation.
This enables GPU SVM to derive the device page address.
v3:
- Better commit message (Thomas)
- New drm_pagemap.h location
v5:
- s/xe_mem_region/xe_vram_region (Rebase)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-24-matthew.brost@intel.com
Add SVM device memory mirroring which enables device pages for
migration. Enabled via CONFIG_XE_DEVMEM_MIRROR Kconfig. Kconfig option
defaults to enabled. If not enabled, SVM will work sans migration and
KMD memory footprint will be less.
v3:
- Add CONFIG_XE_DEVMEM_MIRROR
v4:
- Fix Kconfig (Himal)
- Use %pe to print errors (Thomas)
- Fix alignment issue (Checkpatch)
v5:
- s/xe_mem_region/xe_vram_region (Rebase)
v6:
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
- s/drm_info/drm_dbg/
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: Oak Zeng <oak.zeng@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-22-matthew.brost@intel.com
Add functions which migrate to / from VRAM accepting a single DPA
argument (VRAM) and array of dma addresses (SRAM). Used for SVM
migrations.
v2:
- Don't unlock job_mutex in error path of xe_migrate_vram
v3:
- Kernel doc (Thomas)
- Better commit message (Thomas)
- s/dword/num_dword (Thomas)
- Return error on to large of migration (Thomas)
Signed-off-by: Oak Zeng <oak.zeng@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-21-matthew.brost@intel.com
Add the DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR device query flag,
which indicates whether the device supports CPU address mirroring. The
intent is for UMDs to use this query to determine if a VM can be set up
with CPU address mirroring. This flag is implemented by checking if the
device supports GPU faults.
v7:
- Only report enabled if CONFIG_DRM_GPUSVM is selected (CI)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-20-matthew.brost@intel.com
Support for CPU address mirror bindings in SRAM fully in place, enable the
implementation.
v3:
- s/system allocator/CPU address mirror (Thomas)
v7:
- Only enable uAPI if selected by GPU SVM (CI)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-19-matthew.brost@intel.com
uAPI is designed with the use case that only mapping a BO to a malloc'd
address will unbind a CPU-address mirror VMA. Therefore, allowing a
CPU-address mirror VMA to unbind when the GPU has bindings in the range
being unbound does not make much sense. This behavior is not supported,
as it simplifies the code. This decision can always be revisited if a
use case arises.
v3:
- s/arrises/arises (Thomas)
- s/system allocator/GPU address mirror (Thomas)
- Kernel doc (Thomas)
- Newline between function defs (Thomas)
v5:
- Kernel doc (Thomas)
v6:
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-18-matthew.brost@intel.com
Add unbind to SVM garbage collector. To facilitate add unbind support
function to VM layer which unbinds a SVM range. Also teach PT layer to
understand unbinds of SVM ranges.
v3:
- s/INVALID_VMA/XE_INVALID_VMA (Thomas)
- Kernel doc (Thomas)
- New GPU SVM range structure (Thomas)
- s/DRM_GPUVA_OP_USER/DRM_GPUVA_OP_DRIVER (Thomas)
v4:
- Use xe_vma_op_unmap_range (Himal)
v5:
- s/PY/PT (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-17-matthew.brost@intel.com
Add basic SVM garbage collector which destroy a SVM range upon a MMU
UNMAP event. The garbage collector runs on worker or in GPU fault
handler and is required as locks in the path of reclaim are required and
cannot be taken the notifier.
v2:
- Flush garbage collector in xe_svm_close
v3:
- Better commit message (Thomas)
- Kernel doc (Thomas)
- Use list_first_entry_or_null for garbage collector loop (Thomas)
- Don't add to garbage collector if VM is closed (Thomas)
v4:
- Use %pe to print error (Thomas)
v5:
- s/visable/visible (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-16-matthew.brost@intel.com
Add (re)bind to SVM page fault handler. To facilitate add support
function to VM layer which (re)binds a SVM range. Also teach PT layer to
understand (re)binds of SVM ranges.
v2:
- Don't assert BO lock held for range binds
- Use xe_svm_notifier_lock/unlock helper in xe_svm_close
- Use drm_pagemap dma cursor
- Take notifier lock in bind code to check range state
v3:
- Use new GPU SVM range structure (Thomas)
- Kernel doc (Thomas)
- s/DRM_GPUVA_OP_USER/DRM_GPUVA_OP_DRIVER (Thomas)
v5:
- Kernel doc (Thomas)
v6:
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Tested-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-15-matthew.brost@intel.com
Add DRM_GPUVA_OP_DRIVER which allows driver to define their own gpuvm
ops. Useful for driver created ops which can be passed into the bind
software pipeline.
v3:
- s/DRM_GPUVA_OP_USER/DRM_GPUVA_OP_DRIVER (Thomas)
- Better commit message (Thomas)
Cc: Danilo Krummrich <dakr@redhat.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-14-matthew.brost@intel.com
