Sandro/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-09-18 23:09:29 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

sched_ext: scx_qmap: Do not add IMMED to rescue inserts

Browse Source 
qmap's stranded fallback forces a task that can run on none of its self cids
onto its first allowed cid with SCX_ENQ_RESCUE, and adds SCX_ENQ_IMMED when
that cid is a time-share it holds. On such a cid the insert stops being a
rescue request:

1. A task is enqueued while none of its allowed cids is in self_cids. At
   attach self_cids is still empty.
2. qmap inserts it into cid 0's local DSQ with SCX_ENQ_RESCUE |
   SCX_ENQ_IMMED.
3. The kernel finds ENQ_IMMED held on cid 0, admits the insert and skips the
   rescue diversion.
4. cid 0's cpu is busy, so the IMMED task is bounced back to qmap with
   SCX_ENQ_REENQ.
5. qmap's enqueue sees the same inputs and repeats step 2. Nothing runs in
   between.
6. The reenqueue limit ejects qmap with SCX_EXIT_ERROR_REENQ.

The caps granted during the parent's ops.sub_attach() are delivered after
the sub already holds its tasks, while the per-cid effective caps that mark
the time-shares are delivered from the first dispatch after bypass lifts, so
every attach that receives a time-share on a task's first allowed cid starts
the loop. Drop IMMED from the rescue inserts so that step 3 diverts to the
rescue path.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
This commit is contained in:
Tejun Heo
2026-09-05 12:12:20 -10:00
parent 90f19b2816
commit a0d356696f
1 changed files with 10 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/sched_ext/scx_qmap.bpf.c
+10 -8
View File
@@ -358,8 +358,8 @@ s32 BPF_STRUCT_OPS(qmap_select_cid, struct task_struct *p,
}
/*
* A received time-shared cid is held ENQ_IMMED-only, so inserts must set
* SCX_ENQ_IMMED.
* A received time-shared cid is held ENQ_IMMED-only, so inserts meant to run
* there must set SCX_ENQ_IMMED.
*/
static u64 needs_immed(s32 cid)
{
@@ -444,9 +444,11 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
* didn't grant them or we delegated them to children - would starve in
* SHARED/FIFO since we only pull from those on self cids.
*
* Force it onto its first allowed cid's local DSQ. If we hold that cid
* it runs. Otherwise the insert carries SCX_ENQ_RESCUE and the kernel
* diverts the task to its rescue path.
* Force it onto its first allowed cid's local DSQ with SCX_ENQ_RESCUE.
* If we hold ENQ on that cid it runs. Otherwise the kernel diverts the
* task to its rescue path. IMMED would turn the insert into a legal
* placement on a time-shared cid and the kernel would bounce it back
* here instead of rescuing it.
*/
if (!cmask_intersects(&taskc->cpus_allowed, &qa.self_cids.mask)) {
s32 c = cmask_next_set_wrap(&taskc->cpus_allowed, 0);
@@ -455,7 +457,7 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
taskc->force_local = false;
__sync_fetch_and_add(&qa.nr_rescue_dsp, 1);
scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | c, slice_ns,
enq_flags | needs_immed(c) | SCX_ENQ_RESCUE);
enq_flags | SCX_ENQ_RESCUE);
return;
}
}
@@ -618,7 +620,7 @@ static bool scan_shared_dsq(bool from_timer)
if (c >= 0 && c < scx_bpf_nr_cids()) {
__sync_fetch_and_add(&qa.nr_rescue_dsp, 1);
scx_bpf_dsq_move(BPF_FOR_EACH_ITER, p, SCX_DSQ_LOCAL_ON | c,
needs_immed(c) | SCX_ENQ_RESCUE);
SCX_ENQ_RESCUE);
}
continue;
}
@@ -659,7 +661,7 @@ static bool scan_shared_dsq(bool from_timer)
if (c >= 0 && c < nr_cids) {
__sync_fetch_and_add(&qa.nr_rescue_dsp, 1);
scx_bpf_dsq_move(BPF_FOR_EACH_ITER, p, SCX_DSQ_LOCAL_ON | c,
needs_immed(c) | SCX_ENQ_RESCUE);
SCX_ENQ_RESCUE);
}
continue;
}