Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes are:

   - lockless wakeup support for futexes and IPC message queues
     (Davidlohr Bueso, Peter Zijlstra)

   - Replace spinlocks with atomics in thread_group_cputimer(), to
     improve scalability (Jason Low)

   - NUMA balancing improvements (Rik van Riel)

   - SCHED_DEADLINE improvements (Wanpeng Li)

   - clean up and reorganize preemption helpers (Frederic Weisbecker)

   - decouple page fault disabling machinery from the preemption
     counter, to improve debuggability and robustness (David
     Hildenbrand)

   - SCHED_DEADLINE documentation updates (Luca Abeni)

   - topology CPU masks cleanups (Bartosz Golaszewski)

   - /proc/sched_debug improvements (Srikar Dronamraju)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (79 commits)
  sched/deadline: Remove needless parameter in dl_runtime_exceeded()
  sched: Remove superfluous resetting of the p->dl_throttled flag
  sched/deadline: Drop duplicate init_sched_dl_class() declaration
  sched/deadline: Reduce rq lock contention by eliminating locking of non-feasible target
  sched/deadline: Make init_sched_dl_class() __init
  sched/deadline: Optimize pull_dl_task()
  sched/preempt: Add static_key() to preempt_notifiers
  sched/preempt: Fix preempt notifiers documentation about hlist_del() within unsafe iteration
  sched/stop_machine: Fix deadlock between multiple stop_two_cpus()
  sched/debug: Add sum_sleep_runtime to /proc/<pid>/sched
  sched/debug: Replace vruntime with wait_sum in /proc/sched_debug
  sched/debug: Properly format runnable tasks in /proc/sched_debug
  sched/numa: Only consider less busy nodes as numa balancing destinations
  Revert 095bebf ("sched/numa: Do not move past the balance point if unbalanced")
  sched/fair: Prevent throttling in early pick_next_task_fair()
  preempt: Reorganize the notrace definitions a bit
  preempt: Use preempt_schedule_context() as the official tracing preemption point
  sched: Make preempt_schedule_context() function-tracing safe
  x86: Remove cpu_sibling_mask() and cpu_core_mask()
  x86: Replace cpu_**_mask() with topology_**_cpumask()
  ...

Documentation/cputopology.txt

@@ -1,6 +1,6 @@
 
 Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo.
+to /proc/cpuinfo output of some architectures:
 
 1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
 
@@ -23,41 +23,58 @@ to /proc/cpuinfo.
 4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
-	core as cpuX
+	core as cpuX.
 
-5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	core as cpuX.
+
+6) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+7) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	physical_package_id.
+
+8) /sys/devices/system/cpu/cpuX/topology/book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
+9) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+drivers/base/topology.c, is to export the 6 or 9 attributes. The three book
 related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
 #define topology_book_id(cpu)
-#define topology_thread_cpumask(cpu)
+#define topology_sibling_cpumask(cpu)
 #define topology_core_cpumask(cpu)
 #define topology_book_cpumask(cpu)
 
-The type of **_id is int.
-The type of siblings is (const) struct cpumask *.
+The type of **_id macros is int.
+The type of **_cpumask macros is (const) struct cpumask *. The latter
+correspond with appropriate **_siblings sysfs attributes (except for
+topology_sibling_cpumask() which corresponds with thread_siblings).
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
 not defined by include/asm-XXX/topology.h:
 1) physical_package_id: -1
 2) core_id: 0
-3) thread_siblings: just the given CPU
-4) core_siblings: just the given CPU
+3) sibling_cpumask: just the given CPU
+4) core_cpumask: just the given CPU
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().

arch/alpha/mm/fault.c

@@ -23,8 +23,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
 
@@ -107,7 +106,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 
 	/* If we're in an interrupt context, or have no user context,
 	   we must not take the fault.  */
-	if (!mm || in_atomic())
+	if (!mm || faulthandler_disabled())
 		goto no_context;
 
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC

arch/arc/include/asm/futex.h

@@ -53,7 +53,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -75,7 +75,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	if (!ret) {
 		switch (cmp) {
@@ -104,7 +104,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-/* Compare-xchg with preemption disabled.
+/* Compare-xchg with pagefaults disabled.
  *  Notes:
  *      -Best-Effort: Exchg happens only if compare succeeds.
  *          If compare fails, returns; leaving retry/looping to upper layers
@@ -121,7 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
@@ -142,7 +142,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
 	: "cc", "memory");
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	*uval = val;
 	return val;

arch/arc/mm/fault.c

@@ -86,7 +86,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/arm/include/asm/futex.h

@@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	preempt_disable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "cc", "memory");
 
 	*uval = val;
+	preempt_enable();
+
 	return ret;
 }
 
@@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+#ifndef CONFIG_SMP
+	preempt_disable();
+#endif
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
+#ifndef CONFIG_SMP
+	preempt_enable();
+#endif
 
 	if (!ret) {
 		switch (cmp) {

arch/arm/include/asm/topology.h

@@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);

arch/arm/mm/fault.c

@@ -276,7 +276,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/arm/mm/highmem.c

@@ -59,6 +59,7 @@ void *kmap_atomic(struct page *page)
 	void *kmap;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -121,6 +122,7 @@ void __kunmap_atomic(void *kvaddr)
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
@@ -130,6 +132,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	int idx, type;
 	struct page *page = pfn_to_page(pfn);
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);

arch/arm64/include/asm/futex.h

@@ -58,7 +58,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -85,7 +85,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	if (!ret) {
 		switch (cmp) {

arch/arm64/include/asm/topology.h

@@ -18,7 +18,7 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);

arch/arm64/mm/fault.c

@@ -211,7 +211,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	 * If we're in an interrupt or have no user context, we must not take
 	 * the fault.
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/avr32/include/asm/uaccess.h

@@ -97,7 +97,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -116,7 +117,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -136,7 +138,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -158,7 +161,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger

arch/avr32/mm/fault.c

@@ -14,11 +14,11 @@
 #include <linux/pagemap.h>
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
+#include <linux/uaccess.h>
 
 #include <asm/mmu_context.h>
 #include <asm/sysreg.h>
 #include <asm/tlb.h>
-#include <asm/uaccess.h>
 
 #ifdef CONFIG_KPROBES
 static inline int notify_page_fault(struct pt_regs *regs, int trap)
@@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user context, we must
 	 * not take the fault...
 	 */
-	if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+	if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
 		goto no_context;
 
 	local_irq_enable();

arch/cris/mm/fault.c

@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/system.h>
 
 extern int find_fixup_code(struct pt_regs *);
@@ -109,11 +109,11 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	info.si_code = SEGV_MAPERR;
 
 	/*
-	 * If we're in an interrupt or "atomic" operation or have no
+	 * If we're in an interrupt, have pagefaults disabled or have no
 	 * user context, we must not take the fault.
 	 */
 
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))

arch/frv/mm/fault.c

@@ -19,9 +19,9 @@
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
 #include <asm/gdb-stub.h>
 
 /*****************************************************************************/
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(__frame))

arch/frv/mm/highmem.c

@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long paddr;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 	type = kmap_atomic_idx_push();
 	paddr = page_to_phys(page);
@@ -85,5 +86,6 @@ void __kunmap_atomic(void *kvaddr)
 	}
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);

arch/hexagon/include/asm/uaccess.h

@@ -36,7 +36,8 @@
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *