summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf/prog_tests/autoload.c
diff options
context:
space:
mode:
authorYujun Dong <yujundong@pascal-lab.net>2024-12-30 17:16:24 +0300
committerIngo Molnar <mingo@kernel.org>2025-03-20 12:03:52 +0300
commit3785c7dbae0f733f13f8857beaaada5d7dc63e02 (patch)
tree85b00782c78e666eacf602e51ac3833860a75b14 /tools/testing/selftests/bpf/prog_tests/autoload.c
parentb52173065e0aad82a31863bb5f63ebe46f7eb657 (diff)
downloadlinux-3785c7dbae0f733f13f8857beaaada5d7dc63e02.tar.xz
cpuidle, sched: Use smp_mb__after_atomic() in current_clr_polling()
In architectures that use the polling bit, current_clr_polling() employs smp_mb() to ensure that the clearing of the polling bit is visible to other cores before checking TIF_NEED_RESCHED. However, smp_mb() can be costly. Given that clear_bit() is an atomic operation, replacing smp_mb() with smp_mb__after_atomic() is appropriate. Many architectures implement smp_mb__after_atomic() as a lighter-weight barrier compared to smp_mb(), leading to performance improvements. For instance, on x86, smp_mb__after_atomic() is a no-op. This change eliminates a smp_mb() instruction in the cpuidle wake-up path, saving several CPU cycles and thereby reducing wake-up latency. Architectures that do not use the polling bit will retain the original smp_mb() behavior to ensure that existing dependencies remain unaffected. Signed-off-by: Yujun Dong <yujundong@pascal-lab.net> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20241230141624.155356-1-yujundong@pascal-lab.net
Diffstat (limited to 'tools/testing/selftests/bpf/prog_tests/autoload.c')
0 files changed, 0 insertions, 0 deletions