Merge remote branch 'tip/perf/core' into oprofile/core

Conflicts:
	arch/arm/oprofile/common.c
	kernel/perf_event.c

5 files changed, 110 insertions, 98 deletions

diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S
index ab1ee0ab082..6d159cee5f2 100644
--- a/arch/alpha/kernel/entry.S
+++ b/arch/alpha/kernel/entry.S
@@ -73,8 +73,6 @@
 	ldq	$20, HAE_REG($19);	\
 	stq	$21, HAE_CACHE($19);	\
 	stq	$21, 0($20);		\
-	ldq	$0, 0($sp);		\
-	ldq	$1, 8($sp);		\
 99:;					\
 	ldq	$19, 72($sp);		\
 	ldq	$20, 80($sp);		\
@@ -316,7 +314,7 @@ ret_from_sys_call:
 	cmovne	$26, 0, $19		/* $19 = 0 => non-restartable */
 	ldq	$0, SP_OFF($sp)
 	and	$0, 8, $0
-	beq	$0, restore_all
+	beq	$0, ret_to_kernel
 ret_to_user:
 	/* Make sure need_resched and sigpending don't change between
 		sampling and the rti.  */
@@ -329,6 +327,11 @@ restore_all:
 	RESTORE_ALL
 	call_pal PAL_rti
 
+ret_to_kernel:
+	lda	$16, 7
+	call_pal PAL_swpipl
+	br restore_all
+
 	.align 3
 $syscall_error:
 	/*
@@ -657,7 +660,7 @@ kernel_thread:
 	/* We don't actually care for a3 success widgetry in the kernel.
 	   Not for positive errno values.  */
 	stq	$0, 0($sp)		/* $0 */
-	br	restore_all
+	br	ret_to_kernel
 .end kernel_thread
 
 /*
@@ -912,15 +915,6 @@ sys_execve:
 .end sys_execve
 
 	.align	4
-	.globl	osf_sigprocmask
-	.ent	osf_sigprocmask
-osf_sigprocmask:
-	.prologue 0
-	mov	$sp, $18
-	jmp	$31, sys_osf_sigprocmask
-.end osf_sigprocmask
-
-	.align	4
 	.globl	alpha_ni_syscall
 	.ent	alpha_ni_syscall
 alpha_ni_syscall:
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 85d8e4f58c8..1cc49683fb6 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -307,7 +307,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count  - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
+	delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
 
 	/* It is possible on very rare occasions that the PMC has overflowed
 	 * but the interrupt is yet to come.  Detect and fix this situation.
@@ -402,14 +402,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
 		struct hw_perf_event *hwc = &pe->hw;
 		int idx = hwc->idx;
 
-		if (cpuc->current_idx[j] != PMC_NO_INDEX) {
-			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
-			continue;
+		if (cpuc->current_idx[j] == PMC_NO_INDEX) {
+			alpha_perf_event_set_period(pe, hwc, idx);
+			cpuc->current_idx[j] = idx;
 		}
 
-		alpha_perf_event_set_period(pe, hwc, idx);
-		cpuc->current_idx[j] = idx;
-		cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
+		if (!(hwc->state & PERF_HES_STOPPED))
+			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
 	}
 	cpuc->config = cpuc->event[0]->hw.config_base;
 }
@@ -420,12 +419,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static int alpha_pmu_enable(struct perf_event *event)
+static int alpha_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	/*
 	 * The Sparc code has the IRQ disable first followed by the perf
@@ -435,8 +435,8 @@ static int alpha_pmu_enable(struct perf_event *event)
 	 * nevertheless we disable the PMCs first to enable a potential
 	 * final PMI to occur before we disable interrupts.
 	 */
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	/* Default to error to be returned */
 	ret = -EAGAIN;
@@ -455,8 +455,12 @@ static int alpha_pmu_enable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	hwc->state = PERF_HES_UPTODATE;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_STOPPED;
+
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 
 	return ret;
 }
@@ -467,15 +471,15 @@ static int alpha_pmu_enable(struct perf_event *event)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static void alpha_pmu_disable(struct perf_event *event)
+static void alpha_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	unsigned long flags;
+	unsigned long irq_flags;
 	int j;
 
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	for (j = 0; j < cpuc->n_events; j++) {
 		if (event == cpuc->event[j]) {
@@ -501,8 +505,8 @@ static void alpha_pmu_disable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 }
 
 
@@ -514,13 +518,44 @@ static void alpha_pmu_read(struct perf_event *event)
 }
 
 
-static void alpha_pmu_unthrottle(struct perf_event *event)
+static void alpha_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		cpuc->idx_mask &= ~(1UL<<hwc->idx);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		alpha_perf_event_update(event, hwc, hwc->idx, 0);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_DISABLE, (1UL<<hwc->idx));
+}
+
+
+static void alpha_pmu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+		alpha_perf_event_set_period(event, hwc, hwc->idx);
+	}
+
+	hwc->state = 0;
+
 	cpuc->idx_mask |= 1UL<<hwc->idx;
-	wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
 }
 
 
@@ -642,39 +677,36 @@ static int __hw_perf_event_init(struct perf_event *event)
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= alpha_pmu_enable,
-	.disable	= alpha_pmu_disable,
-	.read		= alpha_pmu_read,
-	.unthrottle	= alpha_pmu_unthrottle,
-};
-
-
 /*
  * Main entry point to initialise a HW performance event.
  */
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!alpha_pmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	/* Do the real initialisation work. */
 	err = __hw_perf_event_init(event);
 
-	if (err)
-		return ERR_PTR(err);
-
-	return &pmu;
+	return err;
 }
 
-
-
 /*
  * Main entry point - enable HW performance counters.
  */
-void hw_perf_enable(void)
+static void alpha_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -700,7 +732,7 @@ void hw_perf_enable(void)
  * Main entry point - disable HW performance counters.
  */
 
-void hw_perf_disable(void)
+static void alpha_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -713,6 +745,17 @@ void hw_perf_disable(void)
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= alpha_pmu_enable,
+	.pmu_disable	= alpha_pmu_disable,
+	.event_init	= alpha_pmu_event_init,
+	.add		= alpha_pmu_add,
+	.del		= alpha_pmu_del,
+	.start		= alpha_pmu_start,
+	.stop		= alpha_pmu_stop,
+	.read		= alpha_pmu_read,
+};
+
 
 /*
  * Main entry point - don't know when this is called but it
@@ -766,7 +809,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 
 	/* la_ptr is the counter that overflowed. */
-	if (unlikely(la_ptr >= perf_max_events)) {
+	if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) {
 		/* This should never occur! */
 		irq_err_count++;
 		pr_warning("PMI: silly index %ld\n", la_ptr);
@@ -807,7 +850,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 			/* Interrupts coming too quickly; "throttle" the
 			 * counter, i.e., disable it for a little while.
 			 */
-			cpuc->idx_mask &= ~(1UL<<idx);
+			alpha_pmu_stop(event, 0);
 		}
 	}
 	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
@@ -837,6 +880,7 @@ void __init init_hw_perf_events(void)
 
 	/* And set up PMU specification */
 	alpha_pmu = &ev67_pmu;
-	perf_max_events = alpha_pmu->num_pmcs;
+
+	perf_pmu_register(&pmu);
 }
 
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 842dba308ea..3ec35066f1d 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -356,7 +356,7 @@ dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, struct thread_info *ti)
 	dest[27] = pt->r27;
 	dest[28] = pt->r28;
 	dest[29] = pt->gp;
-	dest[30] = rdusp();
+	dest[30] = ti == current_thread_info() ? rdusp() : ti->pcb.usp;
 	dest[31] = pt->pc;
 
 	/* Once upon a time this was the PS value.  Which is stupid
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 0f6b51ae865..6f7feb5db27 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -41,46 +41,20 @@ static void do_signal(struct pt_regs *, struct switch_stack *,
 /*
  * The OSF/1 sigprocmask calling sequence is different from the
  * C sigprocmask() sequence..
- *
- * how:
- * 1 - SIG_BLOCK
- * 2 - SIG_UNBLOCK
- * 3 - SIG_SETMASK
- *
- * We change the range to -1 .. 1 in order to let gcc easily
- * use the conditional move instructions.
- *
- * Note that we don't need to acquire the kernel lock for SMP
- * operation, as all of this is local to this thread.
  */
-SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask,
-		struct pt_regs *, regs)
+SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask)
 {
-	unsigned long oldmask = -EINVAL;
-
-	if ((unsigned long)how-1 <= 2) {
-		long sign = how-2;		/* -1 .. 1 */
-		unsigned long block, unblock;
-
-		newmask &= _BLOCKABLE;
-		spin_lock_irq(&current->sighand->siglock);
-		oldmask = current->blocked.sig[0];
-
-		unblock = oldmask & ~newmask;
-		block = oldmask | newmask;
-		if (!sign)
-			block = unblock;
-		if (sign <= 0)
-			newmask = block;
-		if (_NSIG_WORDS > 1 && sign > 0)
-			sigemptyset(&current->blocked);
-		current->blocked.sig[0] = newmask;
-		recalc_sigpending();
-		spin_unlock_irq(&current->sighand->siglock);
-
-		regs->r0 = 0;		/* special no error return */
+	sigset_t oldmask;
+	sigset_t mask;
+	unsigned long res;
+
+	siginitset(&mask, newmask & _BLOCKABLE);
+	res = sigprocmask(how, &mask, &oldmask);
+	if (!res) {
+		force_successful_syscall_return();
+		res = oldmask.sig[0];
 	}
-	return oldmask;
+	return res;
 }
 
 SYSCALL_DEFINE3(osf_sigaction, int, sig,
@@ -94,9 +68,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
 		old_sigset_t mask;
 		if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
 		    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-		    __get_user(new_ka.sa.sa_flags, &act->sa_flags))
+		    __get_user(new_ka.sa.sa_flags, &act->sa_flags) ||
+		    __get_user(mask, &act->sa_mask))
 			return -EFAULT;
-		__get_user(mask, &act->sa_mask);
 		siginitset(&new_ka.sa.sa_mask, mask);
 		new_ka.ka_restorer = NULL;
 	}
@@ -106,9 +80,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig,
 	if (!ret && oact) {
 		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
 		    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags))
+		    __put_user(old_ka.sa.sa_flags, &oact->sa_flags) ||
+		    __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask))
 			return -EFAULT;
-		__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
 	}
 
 	return ret;
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index ce594ef533c..a6a1de9db16 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -58,7 +58,7 @@ sys_call_table:
 	.quad sys_open				/* 45 */
 	.quad alpha_ni_syscall
 	.quad sys_getxgid
-	.quad osf_sigprocmask
+	.quad sys_osf_sigprocmask
 	.quad alpha_ni_syscall
 	.quad alpha_ni_syscall			/* 50 */
 	.quad sys_acct