[PATCHSET v2 sched_ext/for-6.12] sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()

[Tejun Heo]

Hello,

This is v2. Changes from v1
(http://lkml.kernel.org/r/20240830110415.116090-1-tj@xxxxxxxxxx) are:

- @slice and @vtime dropped from scx_bpf_dispatch[_vtime]_from_dsq() as
  scx_bpf_dispatch_vtime_from_dsq() was pushing past kfunc parameter count
  limit and often weren't needed anyway. Instead
  scx_bpf_dispatch_from_slice_set_{slice|vtime}() are added so that the
  parameters can be overridden when necessary.

- 0010-sched_ext-Compact-struct-bpf_iter_scx_dsq_kern.patch was added to
  enable the above.

- @task_rq renamed to @src_rq for consistency.

Once a task is put into a DSQ, the allowed operations are fairly limited.
Tasks in the built-in local and global DSQs are executed automatically and,
ignoring dequeue, there is only one way a task in a user DSQ can be
manipulated - scx_bpf_consume() moves the first task to the dispatching
local DSQ. This inflexibility sometimes gets in the way and is an area where
multiple feature requests have been made.

Implement scx_bpf_dispatch[_vtime]_from_dsq(), which can be called during
DSQ iteration and can move the task to any DSQ - local DSQs, global DSQ and
user DSQs. The kfuncs can be called from ops.dispatch() and any BPF context
which dosen't hold a rq lock including BPF timers and SYSCALL programs.

This patchset is on top of:

   sched_ext/for-6.12 62607d033bb8 ("sched_ext: Use sched_clock_cpu() instead of rq_clock_task() in touch_core_sched()")
 + bpf/master 2ad6d23f465a ("selftests/bpf: Do not update vmlinux.h unnecessarily")

and is also available at:

 git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-dispatch_from_dsq-v2

This patchset contains the following patches:

 0001-sched_ext-Rename-scx_kfunc_set_sleepable-to-unlocked.patch
 0002-sched_ext-Refactor-consume_remote_task.patch
 0003-sched_ext-Make-find_dsq_for_dispatch-handle-SCX_DSQ_.patch
 0004-sched_ext-Fix-processs_ddsp_deferred_locals-by-unify.patch
 0005-sched_ext-Restructure-dispatch_to_local_dsq.patch
 0006-sched_ext-Reorder-args-for-consume_local-remote_task.patch
 0007-sched_ext-Move-sanity-check-and-dsq_mod_nr-into-task.patch
 0008-sched_ext-Move-consume_local_task-upward.patch
 0009-sched_ext-Replace-consume_local_task-with-move_local.patch
 0010-sched_ext-Compact-struct-bpf_iter_scx_dsq_kern.patch
 0011-sched_ext-Implement-scx_bpf_dispatch-_vtime-_from_ds.patch
 0012-scx_qmap-Implement-highpri-boosting.patch

 0001-0010 are prep patches. The logic to bounce tasks across DSQs and CPUs
 is rather complicated due to synchronization. The prep patches do quite a
 bit of refactoring so that the helpers are more composable and can be used
 for the new kfuncs.

 0011 implements scx_bpf_dispatch[_vtime]_from_dsq().

 0012 adds demo usages to scx_qmap.

diffstat follows. Thanks.

 include/linux/sched/ext.h                |   10
 kernel/sched/ext.c                       |  667 ++++++++++++++++++++++++++++++++++-------------------
 tools/sched_ext/include/scx/common.bpf.h |   10
 tools/sched_ext/scx_qmap.bpf.c           |  133 +++++++++-
 tools/sched_ext/scx_qmap.c               |   11
 5 files changed, 585 insertions(+), 246 deletions(-)

--
tejun