Merge: Sched: Upstream fixes for 10.1

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/507

JIRA: https://issues.redhat.com/browse/RHEL-78822

Omitted-fix: f6147af ("sched/deadline: Ignore special tasks when rebuilding domains")

Omitted-fix: 5620933 ("sched/topology: Wrappers for sched_domains_mutex")

Omitted-fix: 45007c6 ("sched/deadline: Generalize unique visiting of root domains")

Omitted-fix: 2ff899e ("sched/deadline: Rebuild root domain accounting after every update")

The above omitted fixes will be included an a later (as yet
unspecified) rhel 10.1 MR.

Omitted-fix: b9f2b29 ("sched/clock: Don't define sched_clock_irqtime as static key")

This one is here but using the commit hash it got when it moved from
tip to master. The tooling is finding both. But I can only include one.

Preventative maintenance for core scheduler code. This
is a series to pull in fixes and updates through v6.14-rc4.
It includes reverts for a few pieces that came in from
the rt tree before landing upstream, differently. This
will keep the code in line with upstream going forward
which will help us maintaining it.

Signed-off-by: Phil Auld <pauld@redhat.com>

Approved-by: Lenny Szubowicz <lszubowi@redhat.com>
Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: David Arcari <darcari@redhat.com>
Approved-by: Waiman Long <longman@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Julio Faracco <jfaracco@redhat.com>

Author: jcfaracco

Documentation/accounting/delay-accounting.rst

@@ -100,29 +100,29 @@ Get delays, since system boot, for pid 10::
 	# ./getdelays -d -p 10
 	(output similar to next case)
 
-Get sum of delays, since system boot, for all pids with tgid 5::
+Get sum and peak of delays, since system boot, for all pids with tgid 242::
 
-	# ./getdelays -d -t 5
+	bash-4.4# ./getdelays -d -t 242
 	print delayacct stats ON
-	TGID	5
-
-
-	CPU             count     real total  virtual total    delay total  delay average
-	                    8        7000000        6872122        3382277          0.423ms
-	IO              count    delay total  delay average
-                   0              0          0.000ms
-	SWAP            count    delay total  delay average
-                       0              0          0.000ms
-	RECLAIM         count    delay total  delay average
-                   0              0          0.000ms
-	THRASHING       count    delay total  delay average
-                       0              0          0.000ms
-	COMPACT         count    delay total  delay average
-                       0              0          0.000ms
-	WPCOPY          count    delay total  delay average
-                       0              0          0.000ms
-	IRQ             count    delay total  delay average
-                       0              0          0.000ms
+	TGID    242
+
+
+	CPU         count     real total  virtual total    delay total  delay average      delay max      delay min
+	               39      156000000      156576579        2111069          0.054ms     0.212296ms     0.031307ms
+	IO          count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	SWAP        count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	RECLAIM     count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	THRASHING   count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	COMPACT     count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	WPCOPY      count    delay total  delay average      delay max      delay min
+	              156       11215873          0.072ms     0.207403ms     0.033913ms
+	IRQ         count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
 
 Get IO accounting for pid 1, it works only with -p::
 

Documentation/admin-guide/kernel-parameters.txt

@@ -2424,7 +2424,9 @@
 			specified in the flag list (default: domain):
 
 			nohz
-			  Disable the tick when a single task runs.
+			  Disable the tick when a single task runs as well as
+			  disabling other kernel noises like having RCU callbacks
+			  offloaded. This is equivalent to the nohz_full parameter.
 
 			  A residual 1Hz tick is offloaded to workqueues, which you
 			  need to affine to housekeeping through the global
@@ -4810,6 +4812,11 @@
 			       can be preempted anytime.  Tasks will also yield
 			       contended spinlocks (if the critical section isn't
 			       explicitly preempt disabled beyond the lock itself).
+			lazy - Scheduler controlled. Similar to full but instead
+			       of preempting the task immediately, the task gets
+			       one HZ tick time to yield itself before the
+			       preemption will be forced. One preemption is when the
+			       task returns to user space.
 
 	print-fatal-signals=
 			[KNL] debug: print fatal signals

Documentation/trace/ftrace.rst

@@ -1037,8 +1037,8 @@ explains which is which.
 	- 'N' both TIF_NEED_RESCHED and PREEMPT_NEED_RESCHED is set,
 	- 'n' only TIF_NEED_RESCHED is set,
 	- 'p' only PREEMPT_NEED_RESCHED is set,
-	- 'L' borg PREEMPT_NEED_RESCHED and TIF_RESCHED_LAZY is set,
-	- 'b' borg TIF_NEED_RESCHED and TIF_RESCHED_LAZY is set,
+	- 'L' both PREEMPT_NEED_RESCHED and TIF_RESCHED_LAZY is set,
+	- 'b' both TIF_NEED_RESCHED and TIF_RESCHED_LAZY is set,
 	- 'l' only TIF_RESCHED_LAZY is set
 	- '.' otherwise.
 

arch/powerpc/Kconfig

@@ -145,6 +145,7 @@ config PPC
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API
+	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64

arch/powerpc/include/asm/thread_info.h

@@ -103,6 +103,7 @@ void arch_setup_new_exec(void);
 #define TIF_PATCH_PENDING	6	/* pending live patching update */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
+#define TIF_NEED_RESCHED_LAZY	9       /* Scheduler driven lazy preemption */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
 #define TIF_NOERROR		12	/* Force successful syscall return */
@@ -122,6 +123,7 @@ void arch_setup_new_exec(void);
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY	(1<<TIF_NEED_RESCHED_LAZY)
 #define _TIF_NOTIFY_SIGNAL	(1<<TIF_NOTIFY_SIGNAL)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1<<TIF_32BIT)
@@ -142,9 +144,10 @@ void arch_setup_new_exec(void);
 				 _TIF_SYSCALL_EMU)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \
-				 _TIF_NOTIFY_SIGNAL)
+				 _TIF_NEED_RESCHED_LAZY | _TIF_NOTIFY_RESUME | \
+				 _TIF_UPROBE | _TIF_RESTORE_TM | \
+				 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL)
+
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
 
 /* Bits in local_flags */

arch/powerpc/kernel/interrupt.c

@@ -185,7 +185,7 @@ interrupt_exit_user_prepare_main(unsigned long ret, struct pt_regs *regs)
 	ti_flags = read_thread_flags();
 	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
 		local_irq_enable();
-		if (ti_flags & _TIF_NEED_RESCHED) {
+		if (ti_flags & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
 			schedule();
 		} else {
 			/*
@@ -396,7 +396,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 		/* Returning to a kernel context with local irqs enabled. */
 		WARN_ON_ONCE(!(regs->msr & MSR_EE));
 again:
-		if (IS_ENABLED(CONFIG_PREEMPT)) {
+		if (IS_ENABLED(CONFIG_PREEMPTION)) {
 			/* Return to preemptible kernel context */
 			if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
 				if (preempt_count() == 0)

arch/powerpc/lib/vmx-helper.c

@@ -45,7 +45,7 @@ int exit_vmx_usercopy(void)
 	 * set and we are preemptible. The hack here is to schedule a
 	 * decrementer to fire here and reschedule for us if necessary.
 	 */
-	if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+	if (IS_ENABLED(CONFIG_PREEMPTION) && need_resched())
 		set_dec(1);
 	return 0;
 }

arch/s390/Kconfig

@@ -80,6 +80,7 @@ config S390
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
+	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SCALED_CPUTIME
 	select ARCH_HAS_SET_DIRECT_MAP

arch/s390/include/asm/thread_info.h

@@ -61,44 +61,45 @@ void arch_setup_new_exec(void);
 /*
  * thread information flags bit numbers
  */
-/* _TIF_WORK bits */
 #define TIF_NOTIFY_RESUME	0	/* callback before returning to user */
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_UPROBE		3	/* breakpointed or single-stepping */
-#define TIF_GUARDED_STORAGE	4	/* load guarded storage control block */
+#define TIF_NEED_RESCHED_LAZY	3	/* lazy rescheduling needed */
+#define TIF_UPROBE		4	/* breakpointed or single-stepping */
 #define TIF_PATCH_PENDING	5	/* pending live patching update */
 #define TIF_PGSTE		6	/* New mm's will use 4K page tables */
 #define TIF_NOTIFY_SIGNAL	7	/* signal notifications exist */
+#define TIF_GUARDED_STORAGE	8	/* load guarded storage control block */
 #define TIF_ISOLATE_BP_GUEST	9	/* Run KVM guests with isolated BP */
 #define TIF_PER_TRAP		10	/* Need to handle PER trap on exit to usermode */
-
 #define TIF_31BIT		16	/* 32bit process */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal() */
 #define TIF_SINGLE_STEP		19	/* This task is single stepped */
 #define TIF_BLOCK_STEP		20	/* This task is block stepped */
 #define TIF_UPROBE_SINGLESTEP	21	/* This task is uprobe single stepped */
-
-/* _TIF_TRACE bits */
 #define TIF_SYSCALL_TRACE	24	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	25	/* syscall auditing active */
 #define TIF_SECCOMP		26	/* secure computing */
 #define TIF_SYSCALL_TRACEPOINT	27	/* syscall tracepoint instrumentation */
 
 #define _TIF_NOTIFY_RESUME	BIT(TIF_NOTIFY_RESUME)
-#define _TIF_NOTIFY_SIGNAL	BIT(TIF_NOTIFY_SIGNAL)
 #define _TIF_SIGPENDING		BIT(TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	BIT(TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY	BIT(TIF_NEED_RESCHED_LAZY)
 #define _TIF_UPROBE		BIT(TIF_UPROBE)
-#define _TIF_GUARDED_STORAGE	BIT(TIF_GUARDED_STORAGE)
 #define _TIF_PATCH_PENDING	BIT(TIF_PATCH_PENDING)
+#define _TIF_PGSTE		BIT(TIF_PGSTE)
+#define _TIF_NOTIFY_SIGNAL	BIT(TIF_NOTIFY_SIGNAL)
+#define _TIF_GUARDED_STORAGE	BIT(TIF_GUARDED_STORAGE)
 #define _TIF_ISOLATE_BP_GUEST	BIT(TIF_ISOLATE_BP_GUEST)
 #define _TIF_PER_TRAP		BIT(TIF_PER_TRAP)
-
 #define _TIF_31BIT		BIT(TIF_31BIT)
+#define _TIF_MEMDIE		BIT(TIF_MEMDIE)
+#define _TIF_RESTORE_SIGMASK	BIT(TIF_RESTORE_SIGMASK)
 #define _TIF_SINGLE_STEP	BIT(TIF_SINGLE_STEP)
-
+#define _TIF_BLOCK_STEP		BIT(TIF_BLOCK_STEP)
+#define _TIF_UPROBE_SINGLESTEP	BIT(TIF_UPROBE_SINGLESTEP)
 #define _TIF_SYSCALL_TRACE	BIT(TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	BIT(TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		BIT(TIF_SECCOMP)

arch/x86/include/asm/thread_info.h

@@ -87,7 +87,7 @@ struct thread_info {
 #define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
-#define TIF_NEED_RESCHED_LAZY	4	/* rescheduling necessary */
+#define TIF_NEED_RESCHED_LAZY	4	/* Lazy rescheduling needed */
 #define TIF_SINGLESTEP		5	/* reenable singlestep on user return*/
 #define TIF_SSBD		6	/* Speculative store bypass disable */
 #define TIF_SPEC_IB		9	/* Indirect branch speculation mitigation */