Merge: sched: Late fixes for 10.1

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1024

JIRA: https://issues.redhat.com/browse/RHEL-92921

Several fixes from upstream need to be included in
10.1 to prevent hitting issues in the field.

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

Approved-by: David Arcari <darcari@redhat.com>
Approved-by: Herton R. Krzesinski <herton@redhat.com>
Approved-by: Juri Lelli <juri.lelli@redhat.com>
Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

arch/arm64/kernel/traps.c

@@ -172,22 +172,14 @@ static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
 	printk("%sCode: %s\n", lvl, str);
 }
 
-#ifdef CONFIG_PREEMPT
-#define S_PREEMPT " PREEMPT"
-#elif defined(CONFIG_PREEMPT_RT)
-#define S_PREEMPT " PREEMPT_RT"
-#else
-#define S_PREEMPT ""
-#endif
-
 #define S_SMP " SMP"
 
 static int __die(const char *str, long err, struct pt_regs *regs)
 {
 	static int die_counter;
 	int ret;
 
-	pr_emerg("Internal error: %s: %016lx [#%d]" S_PREEMPT S_SMP "\n",
+	pr_emerg("Internal error: %s: %016lx [#%d] " S_SMP "\n",
 		 str, err, ++die_counter);
 
 	/* trap and error numbers are mostly meaningless on ARM */

arch/powerpc/kernel/traps.c

@@ -261,17 +261,11 @@ static char *get_mmu_str(void)
 
 static int __die(const char *str, struct pt_regs *regs, long err)
 {
-	const char *pr = "";
-
 	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
 
-	if (IS_ENABLED(CONFIG_PREEMPTION))
-		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
-
-	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
+	printk("%s PAGE_SIZE=%luK%s %s%s%s%s %s\n",
 	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
 	       PAGE_SIZE / 1024, get_mmu_str(),
-	       pr,
 	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
 	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
 	       debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",

arch/s390/kernel/dumpstack.c

@@ -198,13 +198,8 @@ void __noreturn die(struct pt_regs *regs, const char *str)
 	console_verbose();
 	spin_lock_irq(&die_lock);
 	bust_spinlocks(1);
-	printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff,
+	printk("%s: %04x ilc:%d [#%d]", str, regs->int_code & 0xffff,
 	       regs->int_code >> 17, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	pr_cont("PREEMPT ");
-#elif defined(CONFIG_PREEMPT_RT)
-	pr_cont("PREEMPT_RT ");
-#endif
 	pr_cont("SMP ");
 	if (debug_pagealloc_enabled())
 		pr_cont("DEBUG_PAGEALLOC");

arch/x86/kernel/dumpstack.c

@@ -395,18 +395,13 @@ NOKPROBE_SYMBOL(oops_end);
 
 static void __die_header(const char *str, struct pt_regs *regs, long err)
 {
-	const char *pr = "";
-
 	/* Save the regs of the first oops for the executive summary later. */
 	if (!die_counter)
 		exec_summary_regs = *regs;
 
-	if (IS_ENABLED(CONFIG_PREEMPTION))
-		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
-
 	printk(KERN_DEFAULT
-	       "Oops: %s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff,
-	       ++die_counter, pr,
+	       "Oops: %s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff,
+	       ++die_counter,
 	       IS_ENABLED(CONFIG_SMP)     ? " SMP"             : "",
 	       debug_pagealloc_enabled()  ? " DEBUG_PAGEALLOC" : "",
 	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "",

include/linux/cpuset.h

@@ -125,9 +125,11 @@ static inline int cpuset_do_page_mem_spread(void)
 
 extern bool current_cpuset_is_being_rebound(void);
 
+extern void dl_rebuild_rd_accounting(void);
 extern void rebuild_sched_domains(void);
 
 extern void cpuset_print_current_mems_allowed(void);
+extern void cpuset_reset_sched_domains(void);
 
 /*
  * read_mems_allowed_begin is required when making decisions involving
@@ -259,11 +261,20 @@ static inline bool current_cpuset_is_being_rebound(void)
 	return false;
 }
 
+static inline void dl_rebuild_rd_accounting(void)
+{
+}
+
 static inline void rebuild_sched_domains(void)
 {
 	partition_sched_domains(1, NULL, NULL);
 }
 
+static inline void cpuset_reset_sched_domains(void)
+{
+	partition_sched_domains(1, NULL, NULL);
+}
+
 static inline void cpuset_print_current_mems_allowed(void)
 {
 }

include/linux/preempt.h

@@ -515,6 +515,8 @@ static inline bool preempt_model_rt(void)
 	return IS_ENABLED(CONFIG_PREEMPT_RT);
 }
 
+extern const char *preempt_model_str(void);
+
 /*
  * Does the preemption model allow non-cooperative preemption?
  *

include/linux/sched.h

@@ -399,6 +399,11 @@ enum uclamp_id {
 #ifdef CONFIG_SMP
 extern struct root_domain def_root_domain;
 extern struct mutex sched_domains_mutex;
+extern void sched_domains_mutex_lock(void);
+extern void sched_domains_mutex_unlock(void);
+#else
+static inline void sched_domains_mutex_lock(void) { }
+static inline void sched_domains_mutex_unlock(void) { }
 #endif
 
 struct sched_param {
@@ -1398,6 +1403,15 @@ struct task_struct {
 	 * with respect to preemption.
 	 */
 	unsigned long rseq_event_mask;
+# ifdef CONFIG_DEBUG_RSEQ
+	/*
+	 * This is a place holder to save a copy of the rseq fields for
+	 * validation of read-only fields. The struct rseq has a
+	 * variable-length array at the end, so it cannot be used
+	 * directly. Reserve a size large enough for the known fields.
+	 */
+	char				rseq_fields[sizeof(struct rseq)];
+# endif
 #endif
 
 #ifdef CONFIG_SCHED_MM_CID
@@ -1660,8 +1674,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state,
 	 * We're lying here, but rather than expose a completely new task state
 	 * to userspace, we can make this appear as if the task has gone through
 	 * a regular rt_mutex_lock() call.
+	 * Report frozen tasks as uninterruptible.
 	 */
-	if (tsk_state & TASK_RTLOCK_WAIT)
+	if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN))
 		state = TASK_UNINTERRUPTIBLE;
 
 	return fls(state);

include/linux/sched/deadline.h

@@ -34,7 +34,11 @@ static inline bool dl_time_before(u64 a, u64 b)
 struct root_domain;
 extern void dl_add_task_root_domain(struct task_struct *p);
 extern void dl_clear_root_domain(struct root_domain *rd);
+extern void dl_clear_root_domain_cpu(int cpu);
 
 #endif /* CONFIG_SMP */
 
+extern u64 dl_cookie;
+extern bool dl_bw_visited(int cpu, u64 cookie);
+
 #endif /* _LINUX_SCHED_DEADLINE_H */

include/linux/sched/mm.h

@@ -531,6 +531,13 @@ enum {
 
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
+	/*
+	 * The atomic_read() below prevents CSE. The following should
+	 * help the compiler generate more efficient code on architectures
+	 * where sync_core_before_usermode() is a no-op.
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE))
+		return;
 	if (current->mm != mm)
 		return;
 	if (likely(!(atomic_read(&mm->membarrier_state) &

include/linux/sched/topology.h

@@ -166,10 +166,6 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 	return to_cpumask(sd->span);
 }
 
-extern void partition_sched_domains_locked(int ndoms_new,
-					   cpumask_var_t doms_new[],
-					   struct sched_domain_attr *dattr_new);
-
 extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new);
 
@@ -210,12 +206,6 @@ extern void __init set_sched_topology(struct sched_domain_topology_level *tl);
 
 struct sched_domain_attr;
 
-static inline void
-partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
-			       struct sched_domain_attr *dattr_new)
-{
-}
-
 static inline void
 partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			struct sched_domain_attr *dattr_new)