diff options
| author | Tim Chen <tim.c.chen@linux.intel.com> | 2026-09-21 17:37:22 -0700 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2026-09-22 10:49:53 +0200 |
| commit | 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 (patch) | |
| tree | 176dc2d685debcfb082c151ee94f2425ac96b364 /Documentation/driver-api/xilinx | |
| download | linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.tar.gz linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.zip | |
sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted
alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:
env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable
But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.
So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.
Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.
nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.
Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com
Diffstat (limited to 'Documentation/driver-api/xilinx')
| -rw-r--r-- | Documentation/driver-api/xilinx/eemi.rst | 40 | ||||
| -rw-r--r-- | Documentation/driver-api/xilinx/index.rst | 9 |
2 files changed, 49 insertions, 0 deletions
diff --git a/Documentation/driver-api/xilinx/eemi.rst b/Documentation/driver-api/xilinx/eemi.rst new file mode 100644 index 000000000..c1bc47b90 --- /dev/null +++ b/Documentation/driver-api/xilinx/eemi.rst @@ -0,0 +1,40 @@ +==================================== +Xilinx Zynq MPSoC EEMI Documentation +==================================== + +Xilinx Zynq MPSoC Firmware Interface +------------------------------------- +The zynqmp-firmware node describes the interface to platform firmware. +ZynqMP has an interface to communicate with secure firmware. Firmware +driver provides an interface to firmware APIs. Interface APIs can be +used by any driver to communicate with PMC(Platform Management Controller). + +Embedded Energy Management Interface (EEMI) +---------------------------------------------- +The embedded energy management interface is used to allow software +components running across different processing clusters on a chip or +device to communicate with a power management controller (PMC) on a +device to issue or respond to power management requests. + +Any driver who wants to communicate with PMC using EEMI APIs use the +functions provided for each function. + +IOCTL +------ +IOCTL API is for device control and configuration. It is not a system +IOCTL but it is an EEMI API. This API can be used by master to control +any device specific configuration. IOCTL definitions can be platform +specific. This API also manage shared device configuration. + +The following IOCTL IDs are valid for device control: +- IOCTL_SET_PLL_FRAC_MODE 8 +- IOCTL_GET_PLL_FRAC_MODE 9 +- IOCTL_SET_PLL_FRAC_DATA 10 +- IOCTL_GET_PLL_FRAC_DATA 11 + +Refer EEMI API guide [0] for IOCTL specific parameters and other EEMI APIs. + +References +---------- +[0] Embedded Energy Management Interface (EEMI) API guide: + https://www.xilinx.com/support/documentation/user_guides/ug1200-eemi-api.pdf diff --git a/Documentation/driver-api/xilinx/index.rst b/Documentation/driver-api/xilinx/index.rst new file mode 100644 index 000000000..c95bda55d --- /dev/null +++ b/Documentation/driver-api/xilinx/index.rst @@ -0,0 +1,9 @@ + +=========== +Xilinx FPGA +=========== + +.. toctree:: + :maxdepth: 1 + + eemi |
