Skip to content

barrier: Add smp_cond_load_*_timeout() #6232

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 8 commits into
base: bpf-next_base
Choose a base branch
from
Open

barrier: Add smp_cond_load_*_timeout() #6232

wants to merge 8 commits into from

Conversation

@kernel-patches-daemon-bpf-rc
Copy link

Pull request for series with
subject: barrier: Add smp_cond_load_*_timeout()
version: 7
url: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554

@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: f9db3a3
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: 8842732
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: 8842732
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: 23f852d
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: 54c134f
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: 9f317bd
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: 54c134f
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@terminus
asm-generic: barrier: Add smp_cond_load_relaxed_timeout()
3e9ac2f 
Add smp_cond_load_relaxed_timeout(), which extends
smp_cond_load_relaxed() to allow waiting for a duration.

The waiting loop uses cpu_poll_relax() to wait on the condition
variable with a periodic evaluation of a time-check.

cpu_poll_relax() unless overridden by the arch code, amounts to
a cpu_relax().

The number of times we spin is defined by SMP_TIMEOUT_POLL_COUNT
(chosen to be 200 by default) which, assuming each cpu_poll_relax()
iteration takes around 20-30 cycles (measured on a variety of x86
platforms), for a total of ~4000-6000 cycles.

Cc: Arnd Bergmann <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Reviewed-by: Catalin Marinas <[email protected]>
Reviewed-by: Haris Okanovic <[email protected]>
Tested-by: Haris Okanovic <[email protected]>
Signed-off-by: Ankur Arora <[email protected]>
Reviewed-by: Christoph Lameter (Ampere) <[email protected]>
@terminus
arm64: barrier: Support smp_cond_load_relaxed_timeout()
1ecba4d 
Support waiting in smp_cond_load_relaxed_timeout() via
__cmpwait_relaxed(). Limit this to when the event-stream is enabled,
to ensure that we wake from WFE periodically and don't block forever
if there are no stores to the cacheline.

In the unlikely event that the event-stream is unavailable, fallback
to spin-waiting.

Also set SMP_TIMEOUT_POLL_COUNT to 1 so we do the time-check for each
iteration in smp_cond_load_relaxed_timeout().

Cc: [email protected]
Cc: Catalin Marinas <[email protected]>
Suggested-by: Will Deacon <[email protected]>
Signed-off-by: Ankur Arora <[email protected]>
@terminus
arm64: rqspinlock: Remove private copy of smp_cond_load_acquire_timew…
14dc7c5 
…ait()

In preparation for defining smp_cond_load_acquire_timeout(), remove
the private copy. Lacking this, the rqspinlock code falls back to using
smp_cond_load_acquire().

Cc: Kumar Kartikeya Dwivedi <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Reviewed-by: Catalin Marinas <[email protected]>
Reviewed-by: Haris Okanovic <[email protected]>
Signed-off-by: Ankur Arora <[email protected]>
@kernel-patches-daemon-bpf-rc
Copy link
Author

Upstream branch: e2e668b
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1016554
version: 7

@terminus
asm-generic: barrier: Add smp_cond_load_acquire_timeout()
e1e70ac 
Add the acquire variant of smp_cond_load_relaxed_timeout(). This
reuses the relaxed variant, with an additional LOAD->LOAD
ordering.

Cc: Arnd Bergmann <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Reviewed-by: Catalin Marinas <[email protected]>
Reviewed-by: Haris Okanovic <[email protected]>
Tested-by: Haris Okanovic <[email protected]>
Signed-off-by: Ankur Arora <[email protected]>
@terminus
atomic: Add atomic_cond_read_*_timeout()
7bf3210 
Add atomic load wrappers, atomic_cond_read_*_timeout() and
atomic64_cond_read_*_timeout() for the cond-load timeout interfaces.

Cc: Will Deacon <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Boqun Feng <[email protected]>
Signed-off-by: Ankur Arora <[email protected]>
@terminus
rqspinlock: Use smp_cond_load_acquire_timeout()
ffa164f 
Switch out the conditional load interfaces used by rqspinlock
to atomic_cond_read_acquire_timeout(), and
smp_cond_read_acquire_timeout().

Both these handle the timeout and amortize as needed, so use
check_timeout() directly.

Also, when using spin-wait implementations, redefine SMP_TIMEOUT_POLL_COUNT
to be 16k to be similar to the spin-count used in RES_CHECK_TIMEOUT().

Cc: Kumar Kartikeya Dwivedi <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Signed-off-by: Ankur Arora <[email protected]>
@terminus
cpuidle/poll_state: Poll via smp_cond_load_relaxed_timeout()
2771a34 
The inner loop in poll_idle() polls over the thread_info flags,
waiting to see if the thread has TIF_NEED_RESCHED set. The loop
exits once the condition is met, or if the poll time limit has
been exceeded.

To minimize the number of instructions executed in each iteration,
the time check is done only intermittently (once every
POLL_IDLE_RELAX_COUNT iterations). In addition, each loop iteration
executes cpu_relax() which on certain platforms provides a hint to
the pipeline that the loop busy-waits, allowing the processor to
reduce power consumption.

This is close to what smp_cond_load_relaxed_timeout() provides. So,
restructure the loop and fold the loop condition and the timeout check
in smp_cond_load_relaxed_timeout().

Cc: "Rafael J. Wysocki" <[email protected]>
Cc: Daniel Lezcano <[email protected]>
Signed-off-by: Ankur Arora <[email protected]>
Reviewed-by: Christoph Lameter (Ampere) <[email protected]>
@kernel-patches-daemon-bpf-rc kernel-patches-daemon-bpf-rc bot force-pushed the bpf-next_base branch 2 times, most recently from 75ba762 to 385f65b Compare October 30, 2025 01:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

bpf-next new V7-ci-fail V7

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@terminus