From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug 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 Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- Documentation/admin-guide/lcd-panel-cgram.rst | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 Documentation/admin-guide/lcd-panel-cgram.rst (limited to 'Documentation/admin-guide/lcd-panel-cgram.rst') diff --git a/Documentation/admin-guide/lcd-panel-cgram.rst b/Documentation/admin-guide/lcd-panel-cgram.rst new file mode 100644 index 000000000..a3eb00c62 --- /dev/null +++ b/Documentation/admin-guide/lcd-panel-cgram.rst @@ -0,0 +1,27 @@ +====================================== +Parallel port LCD/Keypad Panel support +====================================== + +Some LCDs allow you to define up to 8 characters, mapped to ASCII +characters 0 to 7. The escape code to define a new character is +'\e[LG' followed by one digit from 0 to 7, representing the character +number, and up to 8 couples of hex digits terminated by a semi-colon +(';'). Each couple of digits represents a line, with 1-bits for each +illuminated pixel with LSB on the right. Lines are numbered from the +top of the character to the bottom. On a 5x7 matrix, only the 5 lower +bits of the 7 first bytes are used for each character. If the string +is incomplete, only complete lines will be redefined. Here are some +examples:: + + printf "\e[LG0010101050D1F0C04;" => 0 = [enter] + printf "\e[LG1040E1F0000000000;" => 1 = [up] + printf "\e[LG2000000001F0E0400;" => 2 = [down] + printf "\e[LG3040E1F001F0E0400;" => 3 = [up-down] + printf "\e[LG40002060E1E0E0602;" => 4 = [left] + printf "\e[LG500080C0E0F0E0C08;" => 5 = [right] + printf "\e[LG60016051516141400;" => 6 = "IP" + + printf "\e[LG00103071F1F070301;" => big speaker + printf "\e[LG00002061E1E060200;" => small speaker + +Willy -- cgit v1.3.1