The PCI config space register defines in i915_drm.h are
a bit of a mess; Whitespace is all over the place, register
masks and values are defined in inconsistent ways.
Clean it up a bit.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-19-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Use the proper IS0_R name for the VGA input status register 0, instead
of using the VGA_MIS_W alias which is meant for write accesses to the
same address. Yes, VGA registers are weird.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-16-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Add a proper name for the "Input status register 0" IO address.
Currently we have some code that does reads using the aliasing
VGA_MSR_W define, making it unclear what register we're
actually reading.
v2: Remove stray '?'
Cc: Helge Deller <deller@gmx.de>
Cc: linux-fbdev@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251209075549.14051-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Helge Deller <deller@gmx.de>
On pre-g4x VGA registers are accessible via MMIO. Make use of
it so that we can avoid dealing with the VGA arbiter.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-14-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
VGA register are rather special since they either get accessed
via the global IO addresses, or possibly through MMIO on
pre-g4x platforms. Wrap all VGA register accesses in
intel_vga_{read,write}() to make it obvious where they get
accessed.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-13-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
intel_de_read8() is only needed for VGA register MMIO access
by the CRT code on gen2/3. Remove the redundant wakelock stuff,
and add a platform check to make sure this won't get used on
any platform where MMIO VGA register accesses don't work.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-11-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
We want our VGA register accesses to land on the correct GPU.
Check that the VGA routing is appropriately configured.
For the iGPU this just means the IO decode enable on the GPU, but
for dGPUs we also need the entire chain of bridges to forward the
VGA accesses.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-10-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
intel_gmch_vga_set_state() is a complete lie on ILK+ because
the GMCH_CTRL register is locked and can't actually be written.
But we still need to remove the iGPU from the VGA arbitration
on iGPU+dGPU systems, or else Xorg performance will tank due
to the constant VGA arbiter accesses.
For VGA memory decode we can't turn off the PCI_COMMAND
memory deocde as that would disable even normal MMIO.
Instead we can disable just the VGA memory decode via
the VGA MSR register. And we can do that just once
when disabling the VGA plane. That way we don't have
to touch VGA registers anywhere else.
We can also inform the arbiter that we're no longer decoding
VGA memory. This will stop the arbiter from disabling all
memory decode for the iGPU via PCI_COMMAND (and thus breaking
everything) whenever some other GPU wants to own the VGA memory
accesses.
For IO we can disable all IO decode via the PCI_COMMAND
register, except around the few VGA register accesses that
we need to do in intel_vga_disable(). Unfortunately we can't
disable IO decode permanently as it makes some laptops (eg.
Dell Latitude E5400) hang during reboot/shutdown. One option
would be to re-enable IO decode from the poweroff hooks, but
that won't help the sysrq emergency reboot/shutdown since it
won't call said hooks. So let's try to keep IO decode in its
original setting unless we really need to disable it to
exclude the GPU from VGA arbitration.
I suppose we could keep frobbing GMCH_CTRL on pre-ILK, but
it seems better to not do it since it has other side effects
such as changing the class code of the PCI device.
For discrete GPUs we'll rely on the bridge control instead.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-9-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Avoid using the VGA arbiter during intel_vga_get() for iGPUs because
that will clobber the VGA routing for whatever external GPU is the
current VGA device. That will cause all reads from VGA memory to
come back as 0xff/white, and thus we get a white rectangle on screen
when the external GPU switches from vgacon to fbcon.
The iGPU has the highest VGA decode priority so it will steal all
VGA register accesses whenever its IO decoding is enabled. We'll only
keep the IO decode enabled for a short time so hopefully we don't
end up eating too many unrelated VGA register accesses.
For discrete GPUs we need all the bridges to have their VGA forwarding
bits correctly configured so we can't really avoid the VGA arbiter
there. Although we only do this stuff on dGPUs when the VGA plane was
actaully enabled, so the dGPU should be the current VGA device
and thus have VGA routed to it already anyway.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-8-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Turns out at least some systems (eg. HSW Lenovo ThinkCentre E73)
configure the VGA registers even when booting in UEFI mode. So
in order to avoid any issues with the MSR register we should
clean up the VGA registers anyway.
For now this mostly avoids the potential for unclaimed register
accesses due to the power well vs. MDA/CGA selection. But this
will become more important soon as we'll start to rely on the
MSR register to control VGA memory decode as well.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-7-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
On some systems the BIOS will disable the VGA decode logic in the
iGPU (via GMCH_CTRL) when an external GPU is used as the primary
VGA device. In that case the iGPU will never claim any VGA register
accesses, and any access we do will in fact end up on the external
GPU. Don't go poking around in the other GPUs' registers.
Note that (at least on the g4x board where I tested this) the BIOS
forgets to set the VGACNTR VGA_DISP_DISABLE bit, and the reset
value for said bit is 0. That apparently prevents the pipes from
running, so we must still remember to set the bit, despite the VGA
plane was never actually enabled. On more modern platforms (hsw+
maybe?) the reset value for VGACNTR was changed to have
VGA_DISP_DISABLE already set.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-6-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Enable flexible thread-to-queue mapping in batch I/O mode to support
arbitrary combinations of threads and queues, improving resource
utilization and scalability.
Key improvements:
- Support N:M thread-to-queue mapping (previously limited to 1:1)
- Dynamic buffer allocation based on actual queue assignment per thread
- Thread-safe queue preparation with spinlock protection
- Intelligent buffer index calculation for multi-queue scenarios
- Enhanced validation for thread/queue combination constraints
Implementation details:
- Add q_thread_map matrix to track queue-to-thread assignments
- Dynamic allocation of commit and fetch buffers per thread
- Round-robin queue assignment algorithm for load balancing
- Per-queue spinlock to prevent race conditions during prep
- Updated buffer index calculation using queue position within thread
This enables efficient configurations like:
- Any other N:M combinations for optimal resource matching
Testing:
- Added test_batch_02.sh: 4 threads vs 1 queue
- Added test_batch_03.sh: 1 thread vs 4 queues
- Validates correctness across different mapping scenarios
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add --batch/-b for enabling F_BATCH_IO.
Add batch_01 for covering its basic function.
Add stress_08 and stress_09 for covering stress test.
Add recovery test for F_BATCH_IO in generic_04 and generic_05.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
More tests need to be covered in existing generic tests, and default
45sec isn't enough, and timeout is often triggered, increase timeout
by adding setting file.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add support for UBLK_U_IO_FETCH_IO_CMDS to enable efficient batch
fetching of I/O commands using multishot io_uring operations.
Key improvements:
- Implement multishot UBLK_U_IO_FETCH_IO_CMDS for continuous command fetching
- Add fetch buffer management with page-aligned, mlocked buffers
- Process fetched I/O command tags from kernel-provided buffers
- Integrate fetch operations with existing batch I/O infrastructure
- Significantly reduce uring_cmd issuing overhead through batching
The implementation uses two fetch buffers per thread with automatic
requeuing to maintain continuous I/O command flow. Each fetch operation
retrieves multiple command tags in a single syscall, dramatically
improving performance compared to individual command fetching.
Technical details:
- Fetch buffers are page-aligned and mlocked for optimal performance
- Uses IORING_URING_CMD_MULTISHOT for continuous operation
- Automatic buffer management and requeuing on completion
- Enhanced CQE handling for fetch command completions
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Implement UBLK_U_IO_COMMIT_IO_CMDS to enable efficient batched
completion of I/O operations in the batch I/O framework.
This completes the batch I/O infrastructure by adding the commit
phase that notifies the kernel about completed I/O operations:
Key features:
- Batch multiple I/O completions into single UBLK_U_IO_COMMIT_IO_CMDS
- Dynamic commit buffer allocation and management per thread
- Automatic commit buffer preparation before processing events
- Commit buffer submission after processing completed I/Os
- Integration with existing completion workflows
Implementation details:
- ublk_batch_prep_commit() allocates and initializes commit buffers
- ublk_batch_complete_io() adds completed I/Os to current batch
- ublk_batch_commit_io_cmds() submits batched completions to kernel
- Modified ublk_process_io() to handle batch commit lifecycle
- Enhanced ublk_complete_io() to route to batch or legacy completion
The commit buffer stores completion information (tag, result, buffer
details) for multiple I/Os, then submits them all at once, significantly
reducing syscall overhead compared to individual I/O completions.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Implement support for UBLK_U_IO_PREP_IO_CMDS in the batch I/O framework:
- Add batch command initialization and setup functions
- Implement prep command queueing with proper buffer management
- Add command completion handling for prep and commit commands
- Integrate batch I/O setup into thread initialization
- Update CQE handling to support batch commands
The implementation uses the previously established buffer management
infrastructure to queue UBLK_U_IO_PREP_IO_CMDS commands. Commands are
prepared in the first thread context and use commit buffers for
efficient command batching.
Key changes:
- ublk_batch_queue_prep_io_cmds() prepares I/O command batches
- ublk_batch_compl_cmd() handles batch command completions
- Modified thread setup to use batch operations when enabled
- Enhanced buffer index calculation for batch mode
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add the foundational infrastructure for UBLK_F_BATCH_IO buffer
management including:
- Allocator utility functions for small sized per-thread allocation
- Batch buffer allocation and deallocation functions
- Buffer index management for commit buffers
- Thread state management for batch I/O mode
- Buffer size calculation based on device features
This prepares the groundwork for handling batch I/O commands by
establishing the buffer management layer needed for UBLK_U_IO_PREP_IO_CMDS
and UBLK_U_IO_COMMIT_IO_CMDS operations.
The allocator uses CPU sets for efficient per-thread buffer tracking,
and commit buffers are pre-allocated with 2 buffers per thread to handle
overlapping command operations.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since UBLK_F_PER_IO_DAEMON is added, io buffer index may depend on current
thread because the common way is to use per-pthread io_ring_ctx for issuing
ublk uring_cmd.
Add one helper for returning io buffer index, so we can hide the buffer
index implementation details for target code.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Replace assert() with ublk_assert() since it is often triggered in daemon,
and we may get nothing shown in terminal.
Add ublk_assert(), so we can log something to syslog when assert() is
triggered.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The build_user_data() function packs multiple fields into a __u64
value using bit shifts. Without explicit __u64 casts before shifting,
the shift operations are performed on 32-bit unsigned integers before
being promoted to 64-bit, causing data loss.
Specifically, when tgt_data >= 256, the expression (tgt_data << 24)
shifts on a 32-bit value, truncating the upper 8 bits before promotion
to __u64. Since tgt_data can be up to 16 bits (assertion allows up to
65535), values >= 256 would have their high byte lost.
Add explicit __u64 casts to both op and tgt_data before shifting to
ensure the shift operations happen in 64-bit space, preserving all
bits of the input values.
user_data_to_tgt_data() is only used by stripe.c, in which the max
supported member disks are 4, so won't trigger this issue.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
During recovery with batch I/O, UBLK_U_IO_FETCH_IO_CMDS command fails with
-ENODEV because ublk_batch_attach() rejects them when ubq->canceling is set.
The canceling flag remains set until all queues are ready.
Fix this by tracking per-queue readiness and clearing ubq->canceling as
soon as each individual queue becomes ready, rather than waiting for all
queues. This allows subsequent UBLK_U_IO_FETCH_IO_CMDS commands to succeed
during recovery.
Changes:
- Add ubq->nr_io_ready to track I/Os ready per queue
- Add ub->nr_queue_ready to track number of ready queues
- Add ublk_queue_ready() helper to check queue readiness
- Redefine ublk_dev_ready() based on queue count instead of I/O count
- Clear ubq->canceling immediately when queue becomes ready
- Add ublk_queue_reset_io_flags() to reset per-queue flags
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Reduce overhead when completing multiple requests in batch I/O mode by
accumulating them in an io_comp_batch structure and completing them
together via blk_mq_end_request_batch(). This minimizes per-request
completion overhead and improves performance for high IOPS workloads.
The implementation adds an io_comp_batch pointer to struct ublk_io and
initializes it in __ublk_fetch(). For batch I/O, the pointer is set to
the batch structure in ublk_batch_commit_io(). The __ublk_complete_rq()
function uses io->iob to call blk_mq_add_to_batch() for batch mode.
After processing all batch I/Os, the completion callback is invoked in
ublk_handle_batch_commit_cmd() to complete all accumulated requests
efficiently.
So far just covers direct completion. For deferred completion(zero copy,
auto buffer reg), ublk_io_release() is often delayed in freeing buffer
consumer io_uring request's code path, so this patch often doesn't work,
also it is hard to pass the per-task 'struct io_comp_batch' for deferred
completion.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add new feature UBLK_F_BATCH_IO which replaces the following two
per-io commands:
- UBLK_U_IO_FETCH_REQ
- UBLK_U_IO_COMMIT_AND_FETCH_REQ
with three per-queue batch io uring_cmd:
- UBLK_U_IO_PREP_IO_CMDS
- UBLK_U_IO_COMMIT_IO_CMDS
- UBLK_U_IO_FETCH_IO_CMDS
Then ublk can deliver batch io commands to ublk server in single
multishort uring_cmd, also allows to prepare & commit multiple
commands in batch style via single uring_cmd, communication cost is
reduced a lot.
This feature also doesn't limit task context any more for all supported
commands, so any allowed uring_cmd can be issued in any task context.
ublk server implementation becomes much easier.
Meantime load balance becomes much easier to support with this feature.
The command `UBLK_U_IO_FETCH_IO_CMDS` can be issued from multiple task
contexts, so each task can adjust this command's buffer length or number
of inflight commands for controlling how much load is handled by current
task.
Later, priority parameter will be added to command `UBLK_U_IO_FETCH_IO_CMDS`
for improving load balance support.
UBLK_U_IO_NEED_GET_DATA isn't supported in batch io yet, but it may be
enabled in future via its batch pair.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In case of BATCH_IO, any request filled in event kfifo, they don't get
chance to be dispatched any more when releasing ublk char device, so
we have to abort them too.
Add ublk_abort_batch_queue() for aborting this kind of requests.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Extract common request preparation and cancellation logic into
__ublk_queue_rq_common() helper function. Add dedicated
ublk_batch_queue_rq() for batch mode operations to eliminate runtime check
in ublk_queue_rq().
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add UBLK_U_IO_FETCH_IO_CMDS command to enable efficient batch processing
of I/O requests. This multishot uring_cmd allows the ublk server to fetch
multiple I/O commands in a single operation, significantly reducing
submission overhead compared to individual FETCH_REQ* commands.
Key Design Features:
1. Multishot Operation: One UBLK_U_IO_FETCH_IO_CMDS can fetch many I/O
commands, with the batch size limited by the provided buffer length.
2. Dynamic Load Balancing: Multiple fetch commands can be submitted
simultaneously, but only one is active at any time. This enables
efficient load distribution across multiple server task contexts.
3. Implicit State Management: The implementation uses three key variables
to track state:
- evts_fifo: Queue of request tags awaiting processing
- fcmd_head: List of available fetch commands
- active_fcmd: Currently active fetch command (NULL = none active)
States are derived implicitly:
- IDLE: No fetch commands available
- READY: Fetch commands available, none active
- ACTIVE: One fetch command processing events
4. Lockless Reader Optimization: The active fetch command can read from
evts_fifo without locking (single reader guarantee), while writers
(ublk_queue_rq/ublk_queue_rqs) use evts_lock protection. The memory
barrier pairing plays key role for the single lockless reader
optimization.
Implementation Details:
- ublk_queue_rq() and ublk_queue_rqs() save request tags to evts_fifo
- __ublk_acquire_fcmd() selects an available fetch command when
events arrive and no command is currently active
- ublk_batch_dispatch() moves tags from evts_fifo to the fetch command's
buffer and posts completion via io_uring_mshot_cmd_post_cqe()
- State transitions are coordinated via evts_lock to maintain consistency
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add infrastructure for delivering I/O commands to ublk server in batches,
preparing for the upcoming UBLK_U_IO_FETCH_IO_CMDS feature.
Key components:
- struct ublk_batch_fetch_cmd: Represents a batch fetch uring_cmd that will
receive multiple I/O tags in a single operation, using io_uring's
multishot command for efficient ublk IO delivery.
- ublk_batch_dispatch(): Batch version of ublk_dispatch_req() that:
* Pulls multiple request tags from the events FIFO (lock-free reader)
* Prepares each I/O for delivery (including auto buffer registration)
* Delivers tags to userspace via single uring_cmd notification
* Handles partial failures by restoring undelivered tags to FIFO
The batch approach significantly reduces notification overhead by aggregating
multiple I/O completions into single uring_cmd, while maintaining the same
I/O processing semantics as individual operations.
Error handling ensures system consistency: if buffer selection or CQE
posting fails, undelivered tags are restored to the FIFO for retry,
meantime IO state has to be restored.
This runs in task work context, scheduled via io_uring_cmd_complete_in_task()
or called directly from ->uring_cmd(), enabling efficient batch processing
without blocking the I/O submission path.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add ublk io events fifo structure and prepare for supporting command
batch, which will use io_uring multishot uring_cmd for fetching one
batch of io commands each time.
One nice feature of kfifo is to allow multiple producer vs single
consumer. We just need lock the producer side, meantime the single
consumer can be lockless.
The producer is actually from ublk_queue_rq() or ublk_queue_rqs(), so
lock contention can be eased by setting proper blk-mq nr_queues.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Handle UBLK_U_IO_COMMIT_IO_CMDS by walking the uring_cmd fixed buffer:
- read each element into one temp buffer in batch style
- parse and apply each element for committing io result
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit implements the handling of the UBLK_U_IO_PREP_IO_CMDS command,
which allows userspace to prepare a batch of I/O requests.
The core of this change is the `ublk_walk_cmd_buf` function, which iterates
over the elements in the uring_cmd fixed buffer. For each element, it parses
the I/O details, finds the corresponding `ublk_io` structure, and prepares it
for future dispatch.
Add per-io lock for protecting concurrent delivery and committing.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add new command UBLK_U_IO_PREP_IO_CMDS, which is the batch version of
UBLK_IO_FETCH_REQ.
Add new command UBLK_U_IO_COMMIT_IO_CMDS, which is for committing io command
result only, still the batch version.
The new command header type is `struct ublk_batch_io`.
This patch doesn't actually implement these commands yet, just validates the
SQE fields.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
batch io is designed to be independent of task context, and we will not
track task context for batch io feature.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Introduces the basic structure for a batched I/O feature in the ublk driver.
It adds placeholder functions and a new file operations structure,
ublk_ch_batch_io_fops, which will be used for fetching and committing I/O
commands in batches. Currently, the feature is disabled.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Here's a series that lays the groundwork to rid of the deprecated APIs
divider_round_rate(), divider_round_rate_parent(), and
divider_ro_round_rate_parent() since these functions are just wrappers
for the determine_rate variant.
We need to wait for some other changes to land in Linus's tree via the
phy tree before we can actually remove these functions. We should be
able to do that during the next development cycle.
Note that when I converted some of these drivers from round_rate to
determine_rate, this was mistakenly converted to the following in some
cases:
req->rate = divider_round_rate(...)
This is invalid in the case when an error occurs since it can set the
rate to a negative value. So this series fixes those bugs and removes
the deprecated APIs all in one go.
Note that this also contains a clk-specific change to
drivers/rtc/rtc-ac100.c, and that patch carrys an Acked-by from
Alexandre.
-----BEGIN PGP SIGNATURE-----
iIwEABYKADQWIQSkbTJwWGWqPd7cKQS30t0nXX7AhwUCaXJHmxYcbWFzbmV5YkBv
bnN0YXRpb24ub3JnAAoJELfS3SddfsCHHd0A/0NmZNN2x2J8nQ21yLPXRWFP0Wt2
HfAKQ7O1K8PBYC9uAQDpeXy+IAIMES/eUWmV+hM/xSMok4vjaNXG+BDyfoClDg==
=G5GN
-----END PGP SIGNATURE-----
gpgsig -----BEGIN PGP SIGNATURE-----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=jYp6
-----END PGP SIGNATURE-----
Merge tag 'clk-divider-round-rate-v6.20-v2' of https://github.com/masneyb/linux into clk-divider
Pull divider_round_rate() and friends removal series from Brian Masney:
Here's a series that lays the groundwork to rid of the deprecated APIs
divider_round_rate(), divider_round_rate_parent(), and
divider_ro_round_rate_parent() since these functions are just wrappers
for the determine_rate variant.
We need to wait for some other changes to land in Linus's tree via the
phy tree before we can actually remove these functions. We should be
able to do that during the next development cycle.
Note that when I converted some of these drivers from round_rate to
determine_rate, this was mistakenly converted to the following in some
cases:
req->rate = divider_round_rate(...)
This is invalid in the case when an error occurs since it can set the
rate to a negative value. So this series fixes those bugs and removes
the deprecated APIs all in one go.
Note that this also contains a clk-specific change to
drivers/rtc/rtc-ac100.c, and that patch carrys an Acked-by from
Alexandre.
* tag 'clk-divider-round-rate-v6.20-v2' of https://github.com/masneyb/linux:
rtc: ac100: convert from divider_round_rate() to divider_determine_rate()
clk: zynqmp: divider: convert from divider_round_rate() to divider_determine_rate()
clk: x86: cgu: convert from divider_round_rate() to divider_determine_rate()
clk: versaclock3: convert from divider_round_rate() to divider_determine_rate()
clk: stm32: stm32-core: convert from divider_round_rate_parent() to divider_determine_rate()
clk: stm32: stm32-core: convert from divider_ro_round_rate() to divider_ro_determine_rate()
clk: sprd: div: convert from divider_round_rate() to divider_determine_rate()
clk: sophgo: sg2042-clkgen: convert from divider_round_rate() to divider_determine_rate()
clk: nxp: lpc32xx: convert from divider_round_rate() to divider_determine_rate()
clk: nuvoton: ma35d1-divider: convert from divider_round_rate() to divider_determine_rate()
clk: milbeaut: convert from divider_round_rate() to divider_determine_rate()
clk: milbeaut: convert from divider_ro_round_rate() to divider_ro_determine_rate()
clk: loongson1: convert from divider_round_rate() to divider_determine_rate()
clk: hisilicon: clkdivider-hi6220: convert from divider_round_rate() to divider_determine_rate()
clk: bm1880: convert from divider_round_rate() to divider_determine_rate()
clk: bm1880: convert from divider_ro_round_rate() to divider_ro_determine_rate()
clk: actions: owl-divider: convert from divider_round_rate() to divider_determine_rate()
clk: actions: owl-composite: convert from owl_divider_helper_round_rate() to divider_determine_rate()
clk: sunxi-ng: convert from divider_round_rate_parent() to divider_determine_rate()
clk: sophgo: cv18xx-ip: convert from divider_round_rate() to divider_determine_rate()
Extract the GMCH_CTLR register offset determination into a helper
rather than using a local varaible. I'll be needing this in another
function soon.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-5-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Remove the MSR VGA register access from the power well hook, and
just do it once in intel_vga_disable().
Turns out that the hardware has two levels of MDA vs. CGA decode
logic: GPU level and display engine level. When we write the MSR
register MDA/CGA mode selection bit both decode logics are updated
accordingly, so that whichever register accessed the GPU claims
will also be claimed by the display engine on the RMbus. If the
two get out of sync the GPU will claim the register accesses but
the display engine will not, leading to RMbus NoClaim errors.
The way to get the two decode logics out of sync is by resetting
the power well housing the VGA stuff, while we are in CGA mode.
At that point only the display engine level decode logic will be
updated with the new MSR register reset value (which selects MDA
mode), and the GPU level decode logic will retain its previous
state (GGA mode). To avoid the mismatch we just have to switch
to MDA mode with an explicit MSR register write.
Currently this is being done in a somewhat dodgy manner whenever
the power well gets enabled. But doing if from the power well
hook is not actually necessary since the GPU level decode logic
will retain its state even when the power well is disabled. Ie.
doing it just the one time is sufficient, and that can be done
when we're anyway writing other VGA registers while disabling
the VGA plane.
See commit f9dcb0dfee ("drm/i915: touch VGA MSR after we
enable the power well") for the original details.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-3-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
Currently we register to vgaarb way too early. Thus it is
possible that the entire VGA decode logic gets nuked via
GMCH_CTRL before intel_vga_disable() has even disabled the
VGA plane. This could even cause a system hang because
we'll be unable to turn off the VGA plane gracefully.
Move the vgaarb registration into intel_display_driver_register().
I suppose we could do it a bit earlier (after intel_vga_disable()),
but not convinced there's any point.
Also the error handling here is pointless since the
registration can't fail (unless the device isn't a VGA class
in which case all VGA decode logic should aleady be disabled
by the BIOS via GMCH_CTRL). But let's toss in a WARN to catch
any future breakage of vga_client_register().
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20251208182637.334-2-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Enhance the grammar of the comment in genphy_update_link()
describing momentary link drop handling.
Found by inspection.
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260121-phy-gra-v1-1-8b4d178939de@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
RFC 4884 extended certain ICMP messages with a length attribute that
encodes the length of the "original datagram" field. This is needed so
that new information could be appended to these messages without
applications thinking that it is part of the "original datagram" field.
In version 5.9, the kernel was extended with two new socket options
(SOL_IP/IP_RECVERR_4884 and SOL_IPV6/IPV6_RECVERR_RFC4884) that allow
user space to retrieve this length which is basically the offset to the
ICMP Extension Structure at the end of the ICMP message. This is
required by user space applications that need to parse the information
contained in the ICMP Extension Structure. For example, the RFC 5837
extension for tracepath.
Add a selftest that verifies correct handling of the RFC 4884 length
field for both IPv4 and IPv6, with and without extension structures,
and validates that malformed extensions are correctly reported as invalid.
For each address family, the test creates:
- a raw socket used to send locally crafted ICMP error packets to the
loopback address, and
- a datagram socket used to receive the encapsulated original datagram
and associated error metadata from the kernel error queue.
ICMP packets are constructed entirely in user space rather than relying
on kernel-generated errors. This allows the test to exercise invalid
scenarios (such as corrupted checksums and incorrect length fields) and
verify that the SO_EE_RFC4884_FLAG_INVALID flag is set as expected.
Output Example:
$ ./icmp_rfc4884
Starting 18 tests from 18 test cases.
RUN rfc4884.ipv4_ext_small_payload.rfc4884 ...
OK rfc4884.ipv4_ext_small_payload.rfc4884
ok 1 rfc4884.ipv4_ext_small_payload.rfc4884
RUN rfc4884.ipv4_ext.rfc4884 ...
OK rfc4884.ipv4_ext.rfc4884
ok 2 rfc4884.ipv4_ext.rfc4884
RUN rfc4884.ipv4_ext_large_payload.rfc4884 ...
OK rfc4884.ipv4_ext_large_payload.rfc4884
ok 3 rfc4884.ipv4_ext_large_payload.rfc4884
RUN rfc4884.ipv4_no_ext_small_payload.rfc4884 ...
OK rfc4884.ipv4_no_ext_small_payload.rfc4884
ok 4 rfc4884.ipv4_no_ext_small_payload.rfc4884
RUN rfc4884.ipv4_no_ext_min_payload.rfc4884 ...
OK rfc4884.ipv4_no_ext_min_payload.rfc4884
ok 5 rfc4884.ipv4_no_ext_min_payload.rfc4884
RUN rfc4884.ipv4_no_ext_large_payload.rfc4884 ...
OK rfc4884.ipv4_no_ext_large_payload.rfc4884
ok 6 rfc4884.ipv4_no_ext_large_payload.rfc4884
RUN rfc4884.ipv4_invalid_ext_checksum.rfc4884 ...
OK rfc4884.ipv4_invalid_ext_checksum.rfc4884
ok 7 rfc4884.ipv4_invalid_ext_checksum.rfc4884
RUN rfc4884.ipv4_invalid_ext_length_small.rfc4884 ...
OK rfc4884.ipv4_invalid_ext_length_small.rfc4884
ok 8 rfc4884.ipv4_invalid_ext_length_small.rfc4884
RUN rfc4884.ipv4_invalid_ext_length_large.rfc4884 ...
OK rfc4884.ipv4_invalid_ext_length_large.rfc4884
ok 9 rfc4884.ipv4_invalid_ext_length_large.rfc4884
RUN rfc4884.ipv6_ext_small_payload.rfc4884 ...
OK rfc4884.ipv6_ext_small_payload.rfc4884
ok 10 rfc4884.ipv6_ext_small_payload.rfc4884
RUN rfc4884.ipv6_ext.rfc4884 ...
OK rfc4884.ipv6_ext.rfc4884
ok 11 rfc4884.ipv6_ext.rfc4884
RUN rfc4884.ipv6_ext_large_payload.rfc4884 ...
OK rfc4884.ipv6_ext_large_payload.rfc4884
ok 12 rfc4884.ipv6_ext_large_payload.rfc4884
RUN rfc4884.ipv6_no_ext_small_payload.rfc4884 ...
OK rfc4884.ipv6_no_ext_small_payload.rfc4884
ok 13 rfc4884.ipv6_no_ext_small_payload.rfc4884
RUN rfc4884.ipv6_no_ext_min_payload.rfc4884 ...
OK rfc4884.ipv6_no_ext_min_payload.rfc4884
ok 14 rfc4884.ipv6_no_ext_min_payload.rfc4884
RUN rfc4884.ipv6_no_ext_large_payload.rfc4884 ...
OK rfc4884.ipv6_no_ext_large_payload.rfc4884
ok 15 rfc4884.ipv6_no_ext_large_payload.rfc4884
RUN rfc4884.ipv6_invalid_ext_checksum.rfc4884 ...
OK rfc4884.ipv6_invalid_ext_checksum.rfc4884
ok 16 rfc4884.ipv6_invalid_ext_checksum.rfc4884
RUN rfc4884.ipv6_invalid_ext_length_small.rfc4884 ...
OK rfc4884.ipv6_invalid_ext_length_small.rfc4884
ok 17 rfc4884.ipv6_invalid_ext_length_small.rfc4884
RUN rfc4884.ipv6_invalid_ext_length_large.rfc4884 ...
OK rfc4884.ipv6_invalid_ext_length_large.rfc4884
ok 18 rfc4884.ipv6_invalid_ext_length_large.rfc4884
PASSED: 18 / 18 tests passed.
Totals: pass:18 fail:0 xfail:0 xpass:0 skip:0 error:0
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260121114644.2863640-1-danieller@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Eric Dumazet says:
====================
tcp: remove tcp_rate.c
Move tcp_rate_gen() to tcp_input.c and tcp_rate_check_app_limited()
to tcp.c for better code generation.
tcp_rate.c was interesting from code maintenance perspective
but was adding cpu costs.
====================
Link: https://patch.msgid.link/20260121095923.3134639-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tcp_rate_check_app_limited() is used from tcp_sendmsg_locked()
fast path and from other callers.
Move it to tcp.c so that it can be inlined in tcp_sendmsg_locked().
Small increase of code, for better TCP performance.
$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/0 grow/shrink: 1/0 up/down: 87/0 (87)
Function old new delta
tcp_sendmsg_locked 4217 4304 +87
Total: Before=22566462, After=22566549, chg +0.00%
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20260121095923.3134639-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This function is called from one caller only, in TCP fast path.
Move it to tcp_input.c so that compiler can inline it.
$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/2 grow/shrink: 1/0 up/down: 226/-300 (-74)
Function old new delta
tcp_ack 5405 5631 +226
__pfx_tcp_rate_gen 16 - -16
tcp_rate_gen 284 - -284
Total: Before=22566536, After=22566462, chg -0.00%
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20260121095923.3134639-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stefan Eichenberger says:
====================
net: stmmac: dwmac: enforce preamble before SFD for i.MX8MP
This series adds a new phy_device flag PHY_F_KEEP_PREAMBLE_BEFORE_SFD
that allows a MAC driver to request to keep the preamble bytes before
the start frame delimiter (SFD) when receiving frames from the PHY.
This flag is set in the stmmac driver for the i.MX8MP SoC due to errata
(ERR050694), which causes it to drop frames without a preamble.
The Micrel KSZ9131 PHY supports keeping the preamble before SFD by
setting an undocumented flag, that was confirmed by NXP and Micrel. This
new feature has been added to the Micrel PHY driver for the KSZ9131 PHY.
====================
Link: https://patch.msgid.link/20260120203905.23805-1-eichest@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
