Merge tag 'v6.8-rc4' into x86/percpu, to resolve conflicts and refresh the branch

Conflicts:
	arch/x86/include/asm/percpu.h
	arch/x86/include/asm/text-patching.h

Signed-off-by: Ingo Molnar <[email protected]>

14 files changed, 101 insertions, 35 deletions

diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 0ee96ea7a0e9..02f5090ffea2 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
 #define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
+#define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 #define MMF_OOM_REAP_QUEUED	25	/* mm was queued for oom_reaper */
 #define MMF_MULTIPROCESS	26	/* mm is shared between processes */
 /*
@@ -85,10 +86,22 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_HAS_MDWE		28
 #define MMF_HAS_MDWE_MASK	(1 << MMF_HAS_MDWE)
 
-#define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
+
+#define MMF_HAS_MDWE_NO_INHERIT	29
+
+#define MMF_VM_MERGE_ANY	30
+#define MMF_VM_MERGE_ANY_MASK	(1 << MMF_VM_MERGE_ANY)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
-				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK)
+				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\
+				 MMF_VM_MERGE_ANY_MASK)
+
+static inline unsigned long mmf_init_flags(unsigned long flags)
+{
+	if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT))
+		flags &= ~((1UL << MMF_HAS_MDWE) |
+			   (1UL << MMF_HAS_MDWE_NO_INHERIT));
+	return flags & MMF_INIT_MASK;
+}
 
-#define MMF_VM_MERGE_ANY	29
 #endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 7c83d4d5a971..df3aca89d4f5 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -1,4 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_DEADLINE_H
+#define _LINUX_SCHED_DEADLINE_H
 
 /*
  * SCHED_DEADLINE tasks has negative priorities, reflecting
@@ -34,3 +36,5 @@ extern void dl_add_task_root_domain(struct task_struct *p);
 extern void dl_clear_root_domain(struct root_domain *rd);
 
 #endif /* CONFIG_SMP */
+
+#endif /* _LINUX_SCHED_DEADLINE_H */
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index fe1a46f30d24..2b461129d1fa 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -2,6 +2,7 @@
 #define _LINUX_SCHED_ISOLATION_H
 
 #include <linux/cpumask.h>
+#include <linux/cpuset.h>
 #include <linux/init.h>
 #include <linux/tick.h>
 
@@ -67,7 +68,8 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 static inline bool cpu_is_isolated(int cpu)
 {
 	return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) ||
-		 !housekeeping_test_cpu(cpu, HK_TYPE_TICK);
+	       !housekeeping_test_cpu(cpu, HK_TYPE_TICK) ||
+	       cpuset_cpu_is_isolated(cpu);
 }
 
 #endif /* _LINUX_SCHED_ISOLATION_H */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 8d89c8c4fac1..9a19f1b42f64 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -403,6 +403,10 @@ DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
  * __GFP_ACCOUNT allocations till the end of the scope will be charged to the
  * given memcg.
  *
+ * Please, make sure that caller has a reference to the passed memcg structure,
+ * so its lifetime is guaranteed to exceed the scope between two
+ * set_active_memcg() calls.
+ *
  * NOTE: This function can nest. Users must save the return value and
  * reset the previous value after their own charging scope is over.
  */
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index 3988762efe15..52b22c5c396d 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -15,13 +15,23 @@
 #define TNF_FAULT_LOCAL	0x08
 #define TNF_MIGRATE_FAIL 0x10
 
+enum numa_vmaskip_reason {
+	NUMAB_SKIP_UNSUITABLE,
+	NUMAB_SKIP_SHARED_RO,
+	NUMAB_SKIP_INACCESSIBLE,
+	NUMAB_SKIP_SCAN_DELAY,
+	NUMAB_SKIP_PID_INACTIVE,
+	NUMAB_SKIP_IGNORE_PID,
+	NUMAB_SKIP_SEQ_COMPLETED,
+};
+
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 extern void task_numa_free(struct task_struct *p, bool final);
-extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
-					int src_nid, int dst_cpu);
+bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
+				int src_nid, int dst_cpu);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   int flags)
@@ -38,7 +48,7 @@ static inline void task_numa_free(struct task_struct *p, bool final)
 {
 }
 static inline bool should_numa_migrate_memory(struct task_struct *p,
-				struct page *page, int src_nid, int dst_cpu)
+				struct folio *folio, int src_nid, int dst_cpu)
 {
 	return true;
 }
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 994c25640e15..b2b9e6eb9683 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -30,6 +30,10 @@ static inline bool task_is_realtime(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_RT_MUTEXES
+extern void rt_mutex_pre_schedule(void);
+extern void rt_mutex_schedule(void);
+extern void rt_mutex_post_schedule(void);
+
 /*
  * Must hold either p->pi_lock or task_rq(p)->lock.
  */
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index fad77b5172e2..a8b28647aafc 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -110,6 +110,13 @@ SD_FLAG(SD_ASYM_CPUCAPACITY_FULL, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
 SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
+ * Domain members share CPU cluster (LLC tags or L2 cache)
+ *
+ * NEEDS_GROUPS: Clusters are shared between groups.
+ */
+SD_FLAG(SD_CLUSTER, SDF_NEEDS_GROUPS)
+
+/*
  * Domain members share CPU package resources (i.e. caches)
  *
  * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 0014d3adaf84..4b7664c56208 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -9,6 +9,7 @@
 #include <linux/sched/task.h>
 #include <linux/cred.h>
 #include <linux/refcount.h>
+#include <linux/pid.h>
 #include <linux/posix-timers.h>
 #include <linux/mm_types.h>
 #include <asm/ptrace.h>
@@ -303,20 +304,11 @@ static inline void kernel_signal_stop(void)
 
 	schedule();
 }
-#ifdef __ia64__
-# define ___ARCH_SI_IA64(_a1, _a2, _a3) , _a1, _a2, _a3
-#else
-# define ___ARCH_SI_IA64(_a1, _a2, _a3)
-#endif
 
-int force_sig_fault_to_task(int sig, int code, void __user *addr
-	___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
-	, struct task_struct *t);
-int force_sig_fault(int sig, int code, void __user *addr
-	___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr));
-int send_sig_fault(int sig, int code, void __user *addr
-	___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
-	, struct task_struct *t);
+int force_sig_fault_to_task(int sig, int code, void __user *addr,
+			    struct task_struct *t);
+int force_sig_fault(int sig, int code, void __user *addr);
+int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t);
 
 int force_sig_mceerr(int code, void __user *, short);
 int send_sig_mceerr(int code, void __user *, short, struct task_struct *);
@@ -441,7 +433,6 @@ static inline bool fault_signal_pending(vm_fault_t fault_flags,
  * This is required every time the blocked sigset_t changes.
  * callers must hold sighand->siglock.
  */
-extern void recalc_sigpending_and_wake(struct task_struct *t);
 extern void recalc_sigpending(void);
 extern void calculate_sigpending(void);
 
@@ -655,8 +646,12 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define for_other_threads(p, t)	\
+	for (t = p; (t = next_thread(t)) != p; )
+
 #define __for_each_thread(signal, t)	\
-	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \
+		lockdep_is_held(&tasklist_lock))
 
 #define for_each_thread(p, t)		\
 	__for_each_thread((p)->signal, t)
@@ -715,15 +710,26 @@ bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
 	return p1->signal == p2->signal;
 }
 
-static inline struct task_struct *next_thread(const struct task_struct *p)
+/*
+ * returns NULL if p is the last thread in the thread group
+ */
+static inline struct task_struct *__next_thread(struct task_struct *p)
+{
+	return list_next_or_null_rcu(&p->signal->thread_head,
+					&p->thread_node,
+					struct task_struct,
+					thread_node);
+}
+
+static inline struct task_struct *next_thread(struct task_struct *p)
 {
-	return list_entry_rcu(p->thread_group.next,
-			      struct task_struct, thread_group);
+	return __next_thread(p) ?: p->group_leader;
 }
 
 static inline int thread_group_empty(struct task_struct *p)
 {
-	return list_empty(&p->thread_group);
+	return thread_group_leader(p) &&
+	       list_is_last(&p->thread_node, &p->signal->thread_head);
 }
 
 #define delay_group_leader(p) \
diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h
index 59d3736c454c..fb1e295e7e63 100644
--- a/include/linux/sched/smt.h
+++ b/include/linux/sched/smt.h
@@ -17,4 +17,4 @@ static inline bool sched_smt_active(void) { return false; }
 
 void arch_smt_update(void);
 
-#endif
+#endif /* _LINUX_SCHED_SMT_H */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a23af225c898..d362aacf9f89 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -7,6 +7,8 @@
  * functionality:
  */
 
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
@@ -226,4 +228,6 @@ static inline void task_unlock(struct task_struct *p)
 	spin_unlock(&p->alloc_lock);
 }
 
+DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T))
+
 #endif /* _LINUX_SCHED_TASK_H */
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index f158b025c175..ccd72b978e1f 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -8,6 +8,7 @@
 
 #include <linux/sched.h>
 #include <linux/magic.h>
+#include <linux/refcount.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 67b573d5bf28..a6e04b4a21d7 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -45,7 +45,7 @@ static inline int cpu_smt_flags(void)
 #ifdef CONFIG_SCHED_CLUSTER
 static inline int cpu_cluster_flags(void)
 {
-	return SD_SHARE_PKG_RESOURCES;
+	return SD_CLUSTER | SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
@@ -109,8 +109,6 @@ struct sched_domain {
 	u64 max_newidle_lb_cost;
 	unsigned long last_decay_max_lb_cost;
 
-	u64 avg_scan_cost;		/* select_idle_sibling */
-
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
@@ -179,6 +177,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
 bool cpus_share_cache(int this_cpu, int that_cpu);
+bool cpus_share_resources(int this_cpu, int that_cpu);
 
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
@@ -232,6 +231,11 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 	return true;
 }
 
+static inline bool cpus_share_resources(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 #endif	/* !CONFIG_SMP */
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
@@ -275,6 +279,14 @@ void arch_update_thermal_pressure(const struct cpumask *cpus,
 { }
 #endif
 
+#ifndef arch_scale_freq_ref
+static __always_inline
+unsigned int arch_scale_freq_ref(int cpu)
+{
+	return 0;
+}
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
diff --git a/include/linux/sched/types.h b/include/linux/sched/types.h
index 3c3e049224ae..969aaf5ef9d6 100644
--- a/include/linux/sched/types.h
+++ b/include/linux/sched/types.h
@@ -20,4 +20,4 @@ struct task_cputime {
 	unsigned long long		sum_exec_runtime;
 };
 
-#endif
+#endif /* _LINUX_SCHED_TYPES_H */
diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h
index 837a23624a66..bc60243d43b3 100644
--- a/include/linux/sched/vhost_task.h
+++ b/include/linux/sched/vhost_task.h
@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_VHOST_TASK_H
-#define _LINUX_VHOST_TASK_H
-
+#ifndef _LINUX_SCHED_VHOST_TASK_H
+#define _LINUX_SCHED_VHOST_TASK_H
 
 struct vhost_task;
 
@@ -11,4 +10,4 @@ void vhost_task_start(struct vhost_task *vtsk);
 void vhost_task_stop(struct vhost_task *vtsk);
 void vhost_task_wake(struct vhost_task *vtsk);
 
-#endif
+#endif /* _LINUX_SCHED_VHOST_TASK_H */