diff options
| author | Thomas Gleixner <tglx@kernel.org> | 2026-03-10 21:29:09 +0100 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2026-03-19 16:15:08 +0100 |
| commit | 81f70f0ee9eae29cd06830261a996c39f3bdd818 (patch) | |
| tree | 1f47f14ddb3f060999801d698fdad0bac1f5e8e9 /include/linux | |
| parent | a4787eecf756b3d5e0c8b08e0dfe87471f83fbf8 (diff) | |
sched/mmcid: Avoid full tasklist walks
[ Upstream commit 192d852129b1b7c4f0ddbab95d0de1efd5ee1405 ]
Chasing vfork()'ed tasks on a CID ownership mode switch requires a full
task list walk, which is obviously expensive on large systems.
Avoid that by keeping a list of tasks using a mm MMCID entity in mm::mm_cid
and walk this list instead. This removes the proven to be flaky counting
logic and avoids a full task list walk in the case of vfork()'ed tasks.
Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202526.183824481@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/rseq_types.h | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index ef0811379c54..a612959c5b17 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -103,10 +103,12 @@ struct rseq_data { }; * @active: MM CID is active for the task * @cid: The CID associated to the task either permanently or * borrowed from the CPU + * @node: Queued in the per MM MMCID list */ struct sched_mm_cid { unsigned int active; unsigned int cid; + struct hlist_node node; }; /** @@ -127,6 +129,7 @@ struct mm_cid_pcpu { * @work: Regular work to handle the affinity mode change case * @lock: Spinlock to protect against affinity setting which can't take @mutex * @mutex: Mutex to serialize forks and exits related to this mm + * @user_list: List of the MM CID users of a MM * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map * is growth only. * @users: The number of tasks sharing this MM. Separate from mm::mm_users @@ -147,13 +150,14 @@ struct mm_mm_cid { raw_spinlock_t lock; struct mutex mutex; + struct hlist_head user_list; /* Low frequency modified */ unsigned int nr_cpus_allowed; unsigned int users; unsigned int pcpu_thrs; unsigned int update_deferred; -}____cacheline_aligned_in_smp; +} ____cacheline_aligned; #else /* CONFIG_SCHED_MM_CID */ struct mm_mm_cid { }; struct sched_mm_cid { }; |