scheduler changes for v3.13

index 23f5118..8e9c0b3 100644
@@ -26,6 +26,8 @@
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
 	.nr_balance_failed	= 0,			\
+	.max_newidle_lb_cost	= 0,			\
+	.next_decay_max_lb_cost	= jiffies,		\
 }
 
 #define cpu_to_node(cpu)	((void)(cpu), 0)

index d763f11..2c12ea1 100644
@@ -172,8 +172,9 @@ int rtlx_open(int index, int can_sleep)
 	if (rtlx == NULL) {
 		if( (p = vpe_get_shared(tclimit)) == NULL) {
 		    if (can_sleep) {
-			__wait_event_interruptible(channel_wqs[index].lx_queue,
-				(p = vpe_get_shared(tclimit)), ret);
+			ret = __wait_event_interruptible(
+					channel_wqs[index].lx_queue,
+					(p = vpe_get_shared(tclimit)));
 			if (ret)
 				goto out_fail;
 		    } else {

@@ -263,11 +264,10 @@ unsigned int rtlx_read_poll(int index, int can_sleep)
 	/* data available to read? */
 	if (chan->lx_read == chan->lx_write) {
 		if (can_sleep) {
-			int ret = 0;
-
-			__wait_event_interruptible(channel_wqs[index].lx_queue,
+			int ret = __wait_event_interruptible(
+				channel_wqs[index].lx_queue,
 				(chan->lx_read != chan->lx_write) ||
-				sp_stopping, ret);
+				sp_stopping);
 			if (ret)
 				return ret;
 

@@ -440,14 +440,13 @@ static ssize_t file_write(struct file *file, const char __user * buffer,
 
 	/* any space left... */
 	if (!rtlx_write_poll(minor)) {
-		int ret = 0;
+		int ret;
 
 		if (file->f_flags & O_NONBLOCK)
 			return -EAGAIN;
 
-		__wait_event_interruptible(channel_wqs[minor].rt_queue,
-					   rtlx_write_poll(minor),
-					   ret);
+		ret = __wait_event_interruptible(channel_wqs[minor].rt_queue,
+					   rtlx_write_poll(minor));
 		if (ret)
 			return ret;
 	}

index e205ef5..1215617 100644
@@ -124,7 +124,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
 
 	BUG_ON(Page_dcache_dirty(page));
 
-	inc_preempt_count();
+	pagefault_disable();
 	idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
 #ifdef CONFIG_MIPS_MT_SMTC
 	idx += FIX_N_COLOURS * smp_processor_id() +

@@ -193,8 +193,7 @@ void kunmap_coherent(void)
 	write_c0_entryhi(old_ctx);
 	EXIT_CRITICAL(flags);
 #endif
-	dec_preempt_count();
-	preempt_check_resched();
+	pagefault_enable();
 }
 
 void copy_user_highpage(struct page *to, struct page *from,

index 722aa3b..da31c8b 100644
@@ -6,6 +6,7 @@
 #include <asm/processor.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
+#include <asm/rmwcc.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for

@@ -76,12 +77,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  */
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, i, "%0", "e");
 }
 
 /**

@@ -118,12 +114,7 @@ static inline void atomic_dec(atomic_t *v)
  */
 static inline int atomic_dec_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
 
 /**

@@ -136,12 +127,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
  */
 static inline int atomic_inc_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
 
 /**

@@ -155,12 +141,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  */
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, i, "%0", "s");
 }
 
 /**

index 0e1cbfc..3f065c9 100644
@@ -72,12 +72,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  */
 static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, i, "%0", "e");
 }
 
 /**

@@ -116,12 +111,7 @@ static inline void atomic64_dec(atomic64_t *v)
  */
 static inline int atomic64_dec_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
 }
 
 /**

@@ -134,12 +124,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  */
 static inline int atomic64_inc_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
 }
 
 /**

@@ -153,12 +138,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  */
 static inline int atomic64_add_negative(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, i, "%0", "s");
 }
 
 /**

index 41639ce..6d76d09 100644
@@ -14,6 +14,7 @@
 
 #include <linux/compiler.h>
 #include <asm/alternative.h>
+#include <asm/rmwcc.h>
 
 #if BITS_PER_LONG == 32
 # define _BITOPS_LONG_SHIFT 5

@@ -204,12 +205,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
-		     "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, nr, "%0", "c");
 }
 
 /**

@@ -255,13 +251,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, nr, "%0", "c");
 }
 
 /**

@@ -314,13 +304,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, nr, "%0", "c");
 }
 
 static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)

59 lines not on this page · raw message

index 2d89e39..5b23e60 100644
@@ -52,12 +52,7 @@ static inline void local_sub(long i, local_t *l)
  */
 static inline int local_sub_and_test(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_SUB "%2,%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e");
 }
 
 /**

@@ -70,12 +65,7 @@ static inline int local_sub_and_test(long i, local_t *l)
  */
 static inline int local_dec_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_DEC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
 }
 
 /**

@@ -88,12 +78,7 @@ static inline int local_dec_and_test(local_t *l)
  */
 static inline int local_inc_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_INC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
 }
 
 /**

@@ -107,12 +92,7 @@ static inline int local_inc_and_test(local_t *l)
  */
 static inline int local_add_negative(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_ADD "%2,%0; sets %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s");
 }
 
 /**

100 lines not on this page · raw message

41 lines not on this page · raw message

index 2781119..c46a46b 100644
@@ -28,8 +28,7 @@ struct thread_info {
 	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable,
-						   <0 => BUG */
+	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
 	struct restart_block    restart_block;
 	void __user		*sysenter_return;

@@ -49,7 +48,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= INIT_PREEMPT_COUNT,	\
+	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\

index 2861082..9f6b934 100644
@@ -32,7 +32,6 @@ void common(void) {
 	OFFSET(TI_flags, thread_info, flags);
 	OFFSET(TI_status, thread_info, status);
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
-	OFFSET(TI_preempt_count, thread_info, preempt_count);
 
 	BLANK();
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);

index 2793d1f..5223fe6 100644
@@ -1095,6 +1095,9 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) =
 
 DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
+
 DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 /*

@@ -1169,6 +1172,8 @@ void debug_stack_reset(void)
 
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
 DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 #ifdef CONFIG_CC_STACKPROTECTOR

index 0fa6912..05fd74f 100644
@@ -37,3 +37,10 @@ EXPORT_SYMBOL(strstr);
 
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(empty_zero_page);
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif

index 4186755..3fe0663 100644
@@ -100,9 +100,6 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 	irqctx->tinfo.task = curctx->tinfo.task;
 	irqctx->tinfo.previous_esp = current_stack_pointer;
 
-	/* Copy the preempt_count so that the [soft]irq checks work. */
-	irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count;
-
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
 

@@ -131,7 +128,6 @@ void irq_ctx_init(int cpu)
 					       THREAD_SIZE_ORDER));
 	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
 	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
 	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
 	per_cpu(hardirq_ctx, cpu) = irqctx;

index c83516b..3fb8d95 100644
@@ -391,9 +391,9 @@ static void amd_e400_idle(void)
 		 * The switch back from broadcast mode needs to be
 		 * called with interrupts disabled.
 		 */
-		 local_irq_disable();
-		 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
-		 local_irq_enable();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
 	} else
 		default_idle();
 }

index 884f98f..c2ec1aa 100644
@@ -292,6 +292,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		set_iopl_mask(next->iopl);
 
 	/*
+	 * If it were not for PREEMPT_ACTIVE we could guarantee that the
+	 * preempt_count of all tasks was equal here and this would not be
+	 * needed.
+	 */
+	task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
+	this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+
+	/*
 	 * Now maybe handle debug registers and/or IO bitmaps
 	 */
 	if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||

index bb1dc51..45ab4d6 100644
@@ -363,6 +363,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(old_rsp, next->usersp);
 	this_cpu_write(current_task, next_p);
 
+	/*
+	 * If it were not for PREEMPT_ACTIVE we could guarantee that the
+	 * preempt_count of all tasks was equal here and this would not be
+	 * needed.
+	 */
+	task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
+	this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+
 	this_cpu_write(kernel_stack,
 		  (unsigned long)task_stack_page(next_p) +
 		  THREAD_SIZE - KERNEL_STACK_OFFSET);

index 8c8093b..729aa77 100644
@@ -88,7 +88,7 @@ static inline void conditional_sti(struct pt_regs *regs)
 
 static inline void preempt_conditional_sti(struct pt_regs *regs)
 {
-	inc_preempt_count();
+	preempt_count_inc();
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }

@@ -103,7 +103,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_disable();
-	dec_preempt_count();
+	preempt_count_dec();
 }
 
 static int __kprobes

index b014d94..0406819 100644
@@ -66,3 +66,10 @@ EXPORT_SYMBOL(empty_zero_page);
 #ifndef CONFIG_PARAVIRT
 EXPORT_SYMBOL(native_load_gs_index);
 #endif
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif

87 lines not on this page · raw message

index fa6964d..f116d66 100644
@@ -359,7 +359,7 @@ static int intel_idle(struct cpuidle_device *dev,
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
-	if (!need_resched()) {
+	if (!current_set_polling_and_test()) {
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();

index 8875dd1..2ea437e 100644
@@ -1547,6 +1547,7 @@ static int do_execve_common(const char *filename,
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
 	acct_update_integrals(current);
+	task_numa_free(current);
 	free_bprm(bprm);
 	if (displaced)
 		put_files_struct(displaced);

index cbd0f1b..1bd2077 100644
@@ -183,6 +183,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	seq_printf(m,
 		"State:\t%s\n"
 		"Tgid:\t%d\n"
+		"Ngid:\t%d\n"
 		"Pid:\t%d\n"
 		"PPid:\t%d\n"
 		"TracerPid:\t%d\n"

@@ -190,6 +191,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		"Gid:\t%d\t%d\t%d\t%d\n",
 		get_task_state(p),
 		task_tgid_nr_ns(p, ns),
+		task_numa_group_id(p),
 		pid_nr_ns(pid, ns),
 		ppid, tpid,
 		from_kuid_munged(user_ns, cred->uid),

105 lines not on this page · raw message

index 3cd574d..22c33e3 100644
@@ -5,7 +5,7 @@
  * (C) Copyright 2001 Linus Torvalds
  *
  * Atomic wait-for-completion handler data structures.
- * See kernel/sched/core.c for details.
+ * See kernel/sched/completion.c for details.
  */
 
 #include <linux/wait.h>

index 1e04106..d9cf963 100644
@@ -33,7 +33,7 @@ extern void rcu_nmi_exit(void);
 #define __irq_enter()					\
 	do {						\
 		account_irq_enter_time(current);	\
-		add_preempt_count(HARDIRQ_OFFSET);	\
+		preempt_count_add(HARDIRQ_OFFSET);	\
 		trace_hardirq_enter();			\
 	} while (0)
 

@@ -49,7 +49,7 @@ extern void irq_enter(void);
 	do {						\
 		trace_hardirq_exit();			\
 		account_irq_exit_time(current);		\
-		sub_preempt_count(HARDIRQ_OFFSET);	\
+		preempt_count_sub(HARDIRQ_OFFSET);	\
 	} while (0)
 
 /*

@@ -62,7 +62,7 @@ extern void irq_exit(void);
 		lockdep_off();					\
 		ftrace_nmi_enter();				\
 		BUG_ON(in_nmi());				\
-		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		rcu_nmi_enter();				\
 		trace_hardirq_enter();				\
 	} while (0)

@@ -72,7 +72,7 @@ extern void irq_exit(void);
 		trace_hardirq_exit();				\
 		rcu_nmi_exit();					\
 		BUG_ON(!in_nmi());				\
-		sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		ftrace_nmi_exit();				\
 		lockdep_on();					\
 	} while (0)

index da6716b..ea4d249 100644
@@ -136,6 +136,7 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 
 struct mempolicy *get_vma_policy(struct task_struct *tsk,
 		struct vm_area_struct *vma, unsigned long addr);
+bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);

index 8d3c57f..f5096b5 100644
@@ -90,11 +90,12 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
-extern int migrate_misplaced_page(struct page *page, int node);
-extern int migrate_misplaced_page(struct page *page, int node);
+extern int migrate_misplaced_page(struct page *page,
+				  struct vm_area_struct *vma, int node);
 extern bool migrate_ratelimited(int node);
 #else
-static inline int migrate_misplaced_page(struct page *page, int node)
+static inline int migrate_misplaced_page(struct page *page,
+					 struct vm_area_struct *vma, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }

168 lines not on this page · raw message

index d9851ee..a3198e5 100644
@@ -174,8 +174,8 @@ struct page {
 	void *shadow;
 #endif
 
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
-	int _last_nid;
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+	int _last_cpupid;
 #endif
 }
 /*

@@ -420,28 +420,15 @@ struct mm_struct {
 	 */
 	unsigned long numa_next_scan;
 
-	/* numa_next_reset is when the PTE scanner period will be reset */
-	unsigned long numa_next_reset;
-
 	/* Restart point for scanning and setting pte_numa */
 	unsigned long numa_scan_offset;
 
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
-
-	/*
-	 * The first node a task was scheduled on. If a task runs on
-	 * a different node than Make PTE Scan Go Now.
-	 */
-	int first_nid;
 #endif
 	struct uprobes_state uprobes_state;
 };
 
-/* first nid will either be a valid NID or one of these values */
-#define NUMA_PTE_SCAN_INIT	-1
-#define NUMA_PTE_SCAN_ACTIVE	-2
-
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
 #ifdef CONFIG_CPUMASK_OFFSTACK

index 93506a1..da52366 100644
@@ -38,10 +38,10 @@
  * The last is when there is insufficient space in page->flags and a separate
  * lookup is necessary.
  *
- * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE |          ... | FLAGS |
- *         " plus space for last_nid: |       NODE     | ZONE | LAST_NID ... | FLAGS |
- * classic sparse with space for node:| SECTION | NODE | ZONE |          ... | FLAGS |
- *         " plus space for last_nid: | SECTION | NODE | ZONE | LAST_NID ... | FLAGS |
+ * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE |             ... | FLAGS |
+ *      " plus space for last_cpupid: |       NODE     | ZONE | LAST_CPUPID ... | FLAGS |
+ * classic sparse with space for node:| SECTION | NODE | ZONE |             ... | FLAGS |
+ *      " plus space for last_cpupid: | SECTION | NODE | ZONE | LAST_CPUPID ... | FLAGS |
  * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS |
  */
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)

@@ -62,15 +62,21 @@
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
-#define LAST_NID_SHIFT NODES_SHIFT
+#define LAST__PID_SHIFT 8
+#define LAST__PID_MASK  ((1 << LAST__PID_SHIFT)-1)
+
+#define LAST__CPU_SHIFT NR_CPUS_BITS
+#define LAST__CPU_MASK  ((1 << LAST__CPU_SHIFT)-1)
+
+#define LAST_CPUPID_SHIFT (LAST__PID_SHIFT+LAST__CPU_SHIFT)
 #else
-#define LAST_NID_SHIFT 0
+#define LAST_CPUPID_SHIFT 0
 #endif
 
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
-#define LAST_NID_WIDTH LAST_NID_SHIFT
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT
 #else
-#define LAST_NID_WIDTH 0
+#define LAST_CPUPID_WIDTH 0
 #endif
 
 /*

@@ -81,8 +87,8 @@
 #define NODE_NOT_IN_PAGE_FLAGS
 #endif
 
-#if defined(CONFIG_NUMA_BALANCING) && LAST_NID_WIDTH == 0
-#define LAST_NID_NOT_IN_PAGE_FLAGS
+#if defined(CONFIG_NUMA_BALANCING) && LAST_CPUPID_WIDTH == 0
+#define LAST_CPUPID_NOT_IN_PAGE_FLAGS
 #endif
 
 #endif /* _LINUX_PAGE_FLAGS_LAYOUT */

167 lines not on this page · raw message

273 lines not on this page · raw message

index bf8086b..10d16c4f 100644
@@ -47,7 +47,6 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_period_reset;
 extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_numa_balancing_settle_count;
 

index 3b5e910..d2abbdb 100644
@@ -28,6 +28,7 @@ struct cpu_stop_work {
 };
 
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
+int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg);
 void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
 int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);

index e7e0473..fddbe20 100644
@@ -104,8 +104,21 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define test_thread_flag(flag) \
 	test_ti_thread_flag(current_thread_info(), flag)
 
-#define set_need_resched()	set_thread_flag(TIF_NEED_RESCHED)
-#define clear_need_resched()	clear_thread_flag(TIF_NEED_RESCHED)
+static inline __deprecated void set_need_resched(void)
+{
+	/*
+	 * Use of this function in deprecated.
+	 *
+	 * As of this writing there are only a few users in the DRM tree left
+	 * all of which are wrong and can be removed without causing too much
+	 * grief.
+	 *
+	 * The DRM people are aware and are working on removing the last few
+	 * instances.
+	 */
+}
+
+#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
 
 #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
 /*

index d3cf0d6..12ae6ce 100644
@@ -106,6 +106,8 @@ int arch_update_cpu_topology(void);
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
 	.smt_gain		= 1178,	/* 15% */			\
+	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */

@@ -135,6 +137,8 @@ int arch_update_cpu_topology(void);
 				,					\
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
+	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 #endif /* CONFIG_SCHED_MC */

@@ -166,6 +170,8 @@ int arch_update_cpu_topology(void);
 				,					\
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
+	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 

index 64f8646..633cac7 100644
@@ -672,31 +672,17 @@ static inline void tty_wait_until_sent_from_close(struct tty_struct *tty,
 #define wait_event_interruptible_tty(tty, wq, condition)		\
 ({									\
 	int __ret = 0;							\
-	if (!(condition)) {						\
-		__wait_event_interruptible_tty(tty, wq, condition, __ret);	\
-	}								\
+	if (!(condition))						\
+		__ret = __wait_event_interruptible_tty(tty, wq,		\
+						       condition);	\
 	__ret;								\
 })
 
-#define __wait_event_interruptible_tty(tty, wq, condition, ret)		\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (condition)						\
-			break;						\
-		if (!signal_pending(current)) {				\
-			tty_unlock(tty);					\
+#define __wait_event_interruptible_tty(tty, wq, condition)		\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+			tty_unlock(tty);				\
 			schedule();					\
-			tty_lock(tty);					\
-			continue;					\
-		}							\
-		ret = -ERESTARTSYS;					\
-		break;							\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+			tty_lock(tty))
 
 #ifdef CONFIG_PROC_FS
 extern void proc_tty_register_driver(struct tty_driver *);

index 5ca0951..9d8cf05 100644
@@ -15,7 +15,7 @@
  */
 static inline void pagefault_disable(void)
 {
-	inc_preempt_count();
+	preempt_count_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
 	 * can hit.

@@ -30,11 +30,7 @@ static inline void pagefault_enable(void)
 	 * the pagefault handler again.
 	 */
 	barrier();
-	dec_preempt_count();
-	/*
-	 * make sure we do..
-	 */
-	barrier();
+	preempt_count_dec();
 	preempt_check_resched();
 }
 

588 lines not on this page · raw message

index 2e7d994..613381b 100644
@@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	/*
 	 * For all intents and purposes a preempted task is a running task.
 	 */
-	if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)
+	if (task_preempt_count(p) & PREEMPT_ACTIVE)
 		state = TASK_RUNNING | TASK_STATE_MAX;
 #endif
 

index 63d3e8f..379090f 100644
@@ -693,7 +693,7 @@ int __init_or_module do_one_initcall(initcall_t fn)
 
 	if (preempt_count() != count) {
 		sprintf(msgbuf, "preemption imbalance ");
-		preempt_count() = count;
+		preempt_count_set(count);
 	}
 	if (irqs_disabled()) {
 		strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf));

index 0c9b862..e8ca97b 100644
@@ -10,6 +10,7 @@
 #include <linux/mmzone.h>
 #include <linux/kbuild.h>
 #include <linux/page_cgroup.h>
+#include <linux/log2.h>
 
 void foo(void)
 {

@@ -17,5 +18,8 @@ void foo(void)
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
 	DEFINE(NR_PCG_FLAGS, __NR_PCG_FLAGS);
+#ifdef CONFIG_SMP
+	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
+#endif
 	/* End of constants */
 }

index 859c8df..e5f3917 100644
@@ -120,7 +120,7 @@ void context_tracking_user_enter(void)
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-void __sched notrace preempt_schedule_context(void)
+asmlinkage void __sched notrace preempt_schedule_context(void)
 {
 	enum ctx_state prev_ctx;
 

index d7f07a2..63aa50d 100644
@@ -308,6 +308,23 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	}
 	smpboot_park_threads(cpu);
 
+	/*
+	 * By now we've cleared cpu_active_mask, wait for all preempt-disabled
+	 * and RCU users of this state to go away such that all new such users
+	 * will observe it.
+	 *
+	 * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
+	 * not imply sync_sched(), so explicitly call both.
+	 */
+#ifdef CONFIG_PREEMPT
+	synchronize_sched();
+#endif
+	synchronize_rcu();
+
+	/*
+	 * So now all preempt/rcu users must observe !cpu_active().
+	 */
+
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */

index e695c0a..988573a 100644
@@ -44,7 +44,7 @@ static inline int cpu_idle_poll(void)
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	while (!need_resched())
+	while (!tif_need_resched())
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	rcu_idle_exit();

@@ -92,8 +92,7 @@ static void cpu_idle_loop(void)
 			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
 				cpu_idle_poll();
 			} else {
-				current_clr_polling();
-				if (!need_resched()) {
+				if (!current_clr_polling_and_test()) {
 					stop_critical_timings();
 					rcu_idle_enter();
 					arch_cpu_idle();

@@ -103,9 +102,16 @@ static void cpu_idle_loop(void)
 				} else {
 					local_irq_enable();
 				}
-				current_set_polling();
+				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
+			/*
+			 * We need to test and propagate the TIF_NEED_RESCHED
+			 * bit here because we might not have send the
+			 * reschedule IPI to idle tasks.
+			 */
+			if (tif_need_resched())
+				set_preempt_need_resched();
 		}
 		tick_nohz_idle_exit();
 		schedule_preempt_disabled();

@@ -129,7 +135,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 	 */
 	boot_init_stack_canary();
 #endif
-	current_set_polling();
+	__current_set_polling();
 	arch_cpu_idle_prepare();
 	cpu_idle_loop();
 }

index 086fe73..c93be06 100644
@@ -817,9 +817,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
 #endif
-#ifdef CONFIG_NUMA_BALANCING
-	mm->first_nid = NUMA_PTE_SCAN_INIT;
-#endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 

@@ -1313,7 +1310,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p);
+	sched_fork(clone_flags, p);
 
 	retval = perf_event_init_task(p);
 	if (retval)

index 32618b3..1dc9f36 100644
@@ -898,6 +898,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	force_quiescent_state(rsp);  /* Kick them all. */
 }
 
+/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
 static void print_cpu_stall(struct rcu_state *rsp)
 {
 	int cpu;

@@ -927,7 +933,14 @@ static void print_cpu_stall(struct rcu_state *rsp)
 				     3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
-	set_need_resched();  /* kick ourselves to get things going. */
+	/*
+	 * Attempt to revive the RCU machinery by forcing a context switch.
+	 *
+	 * A context switch would normally allow the RCU state machine to make
+	 * progress and it could be we're stuck in kernel space without context
+	 * switches for an entirely unreasonable amount of time.
+	 */
+	resched_cpu(smp_processor_id());
 }
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)

255 lines not on this page · raw message

683 lines not on this page · raw message

68 lines not on this page · raw message

1,397 lines not on this page · raw message

index 99399f8..5716929 100644

Lines of this file are not shown. View the raw message.

index d8da010..516c3d9 100644

Lines of this file are not shown. View the raw message.

index 01970c8..7d57275 100644

Lines of this file are not shown. View the raw message.

54 lines not on this page · raw message

46 lines not on this page · raw message

index e08fbee..47197de 100644

Lines of this file are not shown. View the raw message.

127 lines not on this page · raw message

index d7d498d..dcab1d3 100644

Lines of this file are not shown. View the raw message.

303 lines not on this page · raw message

index b2f06f3..a159e1f 100644

Lines of this file are not shown. View the raw message.

index 4296d13..6582b82 100644

Lines of this file are not shown. View the raw message.

index 7974ba2..d9fea7d 100644

Lines of this file are not shown. View the raw message.

index 10c86fb..73d08aa 100644

Lines of this file are not shown. View the raw message.

index 34e7cba..ed32284 100644

Lines of this file are not shown. View the raw message.

index 6dc09d8..872a15a 100644

Lines of this file are not shown. View the raw message.

index 4c0d0e5..04abe53 100644

Lines of this file are not shown. View the raw message.

55 lines not on this page · raw message

139 lines not on this page · raw message

82 lines not on this page · raw message

index c046927..dfc8300 100644

Lines of this file are not shown. View the raw message.

index 633c088..68562e9 100644

Lines of this file are not shown. View the raw message.

index 2ac0afb..bf34fb8 100644

Lines of this file are not shown. View the raw message.

65 lines not on this page · raw message

index dd886fa..73d812f 100644

Lines of this file are not shown. View the raw message.

index 0578d4f..0f67690 100644

Lines of this file are not shown. View the raw message.

index f448471..f63c238 100644

Lines of this file are not shown. View the raw message.