Merge branches 'perf-urgent-for-linus', 'sched-urgent-for-linus',...

Merge branches 'perf-urgent-for-linus', 'sched-urgent-for-linus', 'timers-urgent-for-linus' and 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  tools/perf: Fix static build of perf tool
  tracing: Fix regression in printk_formats file

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  generic-ipi: Fix kexec boot crash by initializing call_single_queue before enabling interrupts

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  clocksource: Make watchdog robust vs. interruption
  timerfd: Fix wakeup of processes when timer is cancelled on clock change

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, MAINTAINERS: Add x86 MCE people
  x86, efi: Do not reserve boot services regions within reserved areas

MAINTAINERS

@@ -7007,6 +7007,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86.
 S:	Maintained
 F:	drivers/platform/x86
 
+X86 MCE INFRASTRUCTURE
+M:	Tony Luck <tony.luck@intel.com>
+M:	Borislav Petkov <bp@amd64.org>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	arch/x86/kernel/cpu/mcheck/*
+
 XEN HYPERVISOR INTERFACE
 M:	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

arch/x86/include/asm/memblock.h

@@ -4,7 +4,6 @@
 #define ARCH_DISCARD_MEMBLOCK
 
 u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
-void memblock_x86_to_bootmem(u64 start, u64 end);
 
 void memblock_x86_reserve_range(u64 start, u64 end, char *name);
 void memblock_x86_free_range(u64 start, u64 end);
@@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end);
 u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
 u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
 u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
 
 #endif

arch/x86/mm/memblock.c

@@ -8,7 +8,7 @@
 #include <linux/range.h>
 
 /* Check for already reserved areas */
-static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align)
+bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align)
 {
 	struct memblock_region *r;
 	u64 addr = *addrp, last;
@@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
 		if (addr >= ei_last)
 			continue;
 		*sizep = ei_last - addr;
-		while (check_with_memblock_reserved_size(&addr, sizep, align))
+		while (memblock_x86_check_reserved_size(&addr, sizep, align))
 			;
 
 		if (*sizep)

arch/x86/platform/efi/efi.c

@@ -310,14 +310,31 @@ void __init efi_reserve_boot_services(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		efi_memory_desc_t *md = p;
-		unsigned long long start = md->phys_addr;
-		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
-
-		memblock_x86_reserve_range(start, start + size, "EFI Boot");
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start+size >= virt_to_phys(_text)
+				&& start <= virt_to_phys(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_x86_check_reserved_size(&start, &size,
+							1<<EFI_PAGE_SHIFT)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg(PFX "Could not reserve boot range "
+					"[0x%010llx-0x%010llx]\n",
+						start, start+size-1);
+		} else
+			memblock_x86_reserve_range(start, start+size,
+							"EFI Boot");
 	}
 }
 
@@ -334,6 +351,10 @@ static void __init efi_free_boot_services(void)
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
 		free_bootmem_late(start, size);
 	}
 }

fs/timerfd.c

@@ -61,7 +61,9 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
 
 /*
  * Called when the clock was set to cancel the timers in the cancel
- * list.
+ * list. This will wake up processes waiting on these timers. The
+ * wake-up requires ctx->ticks to be non zero, therefore we increment
+ * it before calling wake_up_locked().
  */
 void timerfd_clock_was_set(void)
 {
@@ -76,6 +78,7 @@ void timerfd_clock_was_set(void)
 		spin_lock_irqsave(&ctx->wqh.lock, flags);
 		if (ctx->moffs.tv64 != moffs.tv64) {
 			ctx->moffs.tv64 = KTIME_MAX;
+			ctx->ticks++;
 			wake_up_locked(&ctx->wqh);
 		}
 		spin_unlock_irqrestore(&ctx->wqh.lock, flags);

include/linux/clocksource.h

@@ -188,6 +188,7 @@ struct clocksource {
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
 	struct list_head wd_list;
+	cycle_t cs_last;
 	cycle_t wd_last;
 #endif
 } ____cacheline_aligned;

include/linux/smp.h

@@ -85,12 +85,15 @@ int smp_call_function_any(const struct cpumask *mask,
  * Generic and arch helpers
  */
 #ifdef CONFIG_USE_GENERIC_SMP_HELPERS
+void __init call_function_init(void);
 void generic_smp_call_function_single_interrupt(void);
 void generic_smp_call_function_interrupt(void);
 void ipi_call_lock(void);
 void ipi_call_unlock(void);
 void ipi_call_lock_irq(void);
 void ipi_call_unlock_irq(void);
+#else
+static inline void call_function_init(void) { }
 #endif
 
 /*
@@ -134,7 +137,7 @@ static inline void smp_send_reschedule(int cpu) { }
 #define smp_prepare_boot_cpu()			do {} while (0)
 #define smp_call_function_many(mask, func, info, wait) \
 			(up_smp_call_function(func, info))
-static inline void init_call_single_data(void) { }
+static inline void call_function_init(void) { }
 
 static inline int
 smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,

init/main.c

@@ -542,6 +542,7 @@ asmlinkage void __init start_kernel(void)
 	timekeeping_init();
 	time_init();
 	profile_init();
+	call_function_init();
 	if (!irqs_disabled())
 		printk(KERN_CRIT "start_kernel(): bug: interrupts were "
 				 "enabled early\n");

kernel/smp.c

@@ -74,7 +74,7 @@ static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
 	.notifier_call		= hotplug_cfd,
 };
 
-static int __cpuinit init_call_single_data(void)
+void __init call_function_init(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
 	int i;
@@ -88,10 +88,7 @@ static int __cpuinit init_call_single_data(void)
 
 	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
 	register_cpu_notifier(&hotplug_cfd_notifier);
-
-	return 0;
 }
-early_initcall(init_call_single_data);
 
 /*
  * csd_lock/csd_unlock used to serialize access to per-cpu csd resources

kernel/time/clocksource.c

@@ -185,7 +185,6 @@ static struct clocksource *watchdog;
 static struct timer_list watchdog_timer;
 static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
-static cycle_t watchdog_last;
 static int watchdog_running;
 
 static int clocksource_watchdog_kthread(void *data);
@@ -254,11 +253,6 @@ static void clocksource_watchdog(unsigned long data)
 	if (!watchdog_running)
 		goto out;
 
-	wdnow = watchdog->read(watchdog);
-	wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask,
-				     watchdog->mult, watchdog->shift);
-	watchdog_last = wdnow;
-
 	list_for_each_entry(cs, &watchdog_list, wd_list) {
 
 		/* Clocksource already marked unstable? */
@@ -268,19 +262,28 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 		}
 
+		local_irq_disable();
 		csnow = cs->read(cs);
+		wdnow = watchdog->read(watchdog);
+		local_irq_enable();
 
 		/* Clocksource initialized ? */
 		if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
 			cs->flags |= CLOCK_SOURCE_WATCHDOG;
-			cs->wd_last = csnow;
+			cs->wd_last = wdnow;
+			cs->cs_last = csnow;
 			continue;
 		}
 
-		/* Check the deviation from the watchdog clocksource. */
-		cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) &
+		wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask,
+					     watchdog->mult, watchdog->shift);
+
+		cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) &
 					     cs->mask, cs->mult, cs->shift);
-		cs->wd_last = csnow;
+		cs->cs_last = csnow;
+		cs->wd_last = wdnow;
+
+		/* Check the deviation from the watchdog clocksource. */
 		if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
 			clocksource_unstable(cs, cs_nsec - wd_nsec);
 			continue;
@@ -318,7 +321,6 @@ static inline void clocksource_start_watchdog(void)
 		return;
 	init_timer(&watchdog_timer);
 	watchdog_timer.function = clocksource_watchdog;
-	watchdog_last = watchdog->read(watchdog);
 	watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
 	add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
 	watchdog_running = 1;

kernel/trace/trace_printk.c

@@ -240,13 +240,10 @@ static const char **find_next(void *v, loff_t *pos)
 	const char **fmt = v;
 	int start_index;
 
-	if (!fmt)
-		fmt = __start___trace_bprintk_fmt + *pos;
-
 	start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt;
 
 	if (*pos < start_index)
-		return fmt;
+		return __start___trace_bprintk_fmt + *pos;
 
 	return find_next_mod_format(start_index, v, fmt, pos);
 }

tools/perf/Makefile

@@ -633,7 +633,7 @@ prefix_SQ = $(subst ','\'',$(prefix))
 
 SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
 
-LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS)
+LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
 ALL_CFLAGS += $(BASIC_CFLAGS)
 ALL_CFLAGS += $(ARCH_CFLAGS)