1 files changed, 284 insertions, 157 deletions

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index e3673ff6b7a..248ee7e5beb 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -57,7 +57,6 @@
 #include <linux/of_irq.h>
 
 #include <asm/uaccess.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/irq.h>
@@ -67,6 +66,7 @@
 #include <asm/machdep.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
+#include <asm/debug.h>
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -93,20 +93,16 @@ extern int tau_interrupts(int);
 
 #ifdef CONFIG_PPC64
 
-#ifndef CONFIG_SPARSE_IRQ
-EXPORT_SYMBOL(irq_desc);
-#endif
-
 int distribute_irqs = 1;
 
-static inline notrace unsigned long get_hard_enabled(void)
+static inline notrace unsigned long get_irq_happened(void)
 {
-	unsigned long enabled;
+	unsigned long happened;
 
 	__asm__ __volatile__("lbz %0,%1(13)"
-	: "=r" (enabled) : "i" (offsetof(struct paca_struct, hard_enabled)));
+	: "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened)));
 
-	return enabled;
+	return happened;
 }
 
 static inline notrace void set_soft_enabled(unsigned long enable)
@@ -115,84 +111,232 @@ static inline notrace void set_soft_enabled(unsigned long enable)
 	: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
 }
 
-static inline notrace void decrementer_check_overflow(void)
+static inline notrace int decrementer_check_overflow(void)
 {
-	u64 now = get_tb_or_rtc();
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-
-	if (now >= *next_tb)
-		set_dec(1);
+ 	u64 now = get_tb_or_rtc();
+ 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+ 
+	return now >= *next_tb;
 }
 
-notrace void arch_local_irq_restore(unsigned long en)
+/* This is called whenever we are re-enabling interrupts
+ * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if
+ * there's an EE, DEC or DBELL to generate.
+ *
+ * This is called in two contexts: From arch_local_irq_restore()
+ * before soft-enabling interrupts, and from the exception exit
+ * path when returning from an interrupt from a soft-disabled to
+ * a soft enabled context. In both case we have interrupts hard
+ * disabled.
+ *
+ * We take care of only clearing the bits we handled in the
+ * PACA irq_happened field since we can only re-emit one at a
+ * time and we don't want to "lose" one.
+ */
+notrace unsigned int __check_irq_replay(void)
 {
 	/*
-	 * get_paca()->soft_enabled = en;
-	 * Is it ever valid to use local_irq_restore(0) when soft_enabled is 1?
-	 * That was allowed before, and in such a case we do need to take care
-	 * that gcc will set soft_enabled directly via r13, not choose to use
-	 * an intermediate register, lest we're preempted to a different cpu.
+	 * We use local_paca rather than get_paca() to avoid all
+	 * the debug_smp_processor_id() business in this low level
+	 * function
+	 */
+	unsigned char happened = local_paca->irq_happened;
+
+	/* Clear bit 0 which we wouldn't clear otherwise */
+	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+
+	/*
+	 * Force the delivery of pending soft-disabled interrupts on PS3.
+	 * Any HV call will have this side effect.
+	 */
+	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+		u64 tmp, tmp2;
+		lv1_get_version_info(&tmp, &tmp2);
+	}
+
+	/*
+	 * We may have missed a decrementer interrupt. We check the
+	 * decrementer itself rather than the paca irq_happened field
+	 * in case we also had a rollover while hard disabled
 	 */
+	local_paca->irq_happened &= ~PACA_IRQ_DEC;
+	if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
+		return 0x900;
+
+	/* Finally check if an external interrupt happened */
+	local_paca->irq_happened &= ~PACA_IRQ_EE;
+	if (happened & PACA_IRQ_EE)
+		return 0x500;
+
+#ifdef CONFIG_PPC_BOOK3E
+	/* Finally check if an EPR external interrupt happened
+	 * this bit is typically set if we need to handle another
+	 * "edge" interrupt from within the MPIC "EPR" handler
+	 */
+	local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE;
+	if (happened & PACA_IRQ_EE_EDGE)
+		return 0x500;
+
+	local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+	if (happened & PACA_IRQ_DBELL)
+		return 0x280;
+#else
+	local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+	if (happened & PACA_IRQ_DBELL) {
+		if (cpu_has_feature(CPU_FTR_HVMODE))
+			return 0xe80;
+		return 0xa00;
+	}
+#endif /* CONFIG_PPC_BOOK3E */
+
+	/* There should be nothing left ! */
+	BUG_ON(local_paca->irq_happened != 0);
+
+	return 0;
+}
+
+notrace void arch_local_irq_restore(unsigned long en)
+{
+	unsigned char irq_happened;
+	unsigned int replay;
+
+	/* Write the new soft-enabled value */
 	set_soft_enabled(en);
 	if (!en)
 		return;
+	/*
+	 * From this point onward, we can take interrupts, preempt,
+	 * etc... unless we got hard-disabled. We check if an event
+	 * happened. If none happened, we know we can just return.
+	 *
+	 * We may have preempted before the check below, in which case
+	 * we are checking the "new" CPU instead of the old one. This
+	 * is only a problem if an event happened on the "old" CPU.
+	 *
+	 * External interrupt events will have caused interrupts to
+	 * be hard-disabled, so there is no problem, we
+	 * cannot have preempted.
+	 */
+	irq_happened = get_irq_happened();
+	if (!irq_happened)
+		return;
 
-#ifdef CONFIG_PPC_STD_MMU_64
-	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
+	/*
+	 * We need to hard disable to get a trusted value from
+	 * __check_irq_replay(). We also need to soft-disable
+	 * again to avoid warnings in there due to the use of
+	 * per-cpu variables.
+	 *
+	 * We know that if the value in irq_happened is exactly 0x01
+	 * then we are already hard disabled (there are other less
+	 * common cases that we'll ignore for now), so we skip the
+	 * (expensive) mtmsrd.
+	 */
+	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
+		__hard_irq_disable();
+#ifdef CONFIG_TRACE_IRQFLAGS
+	else {
 		/*
-		 * Do we need to disable preemption here?  Not really: in the
-		 * unlikely event that we're preempted to a different cpu in
-		 * between getting r13, loading its lppaca_ptr, and loading
-		 * its any_int, we might call iseries_handle_interrupts without
-		 * an interrupt pending on the new cpu, but that's no disaster,
-		 * is it?  And the business of preempting us off the old cpu
-		 * would itself involve a local_irq_restore which handles the
-		 * interrupt to that cpu.
-		 *
-		 * But use "local_paca->lppaca_ptr" instead of "get_lppaca()"
-		 * to avoid any preemption checking added into get_paca().
+		 * We should already be hard disabled here. We had bugs
+		 * where that wasn't the case so let's dbl check it and
+		 * warn if we are wrong. Only do that when IRQ tracing
+		 * is enabled as mfmsr() can be costly.
 		 */
-		if (local_paca->lppaca_ptr->int_dword.any_int)
-			iseries_handle_interrupts();
+		if (WARN_ON(mfmsr() & MSR_EE))
+			__hard_irq_disable();
 	}
-#endif /* CONFIG_PPC_STD_MMU_64 */
+#endif /* CONFIG_TRACE_IRQFLAG */
+
+	set_soft_enabled(0);
+
+	/*
+	 * Check if anything needs to be re-emitted. We haven't
+	 * soft-enabled yet to avoid warnings in decrementer_check_overflow
+	 * accessing per-cpu variables
+	 */
+	replay = __check_irq_replay();
+
+	/* We can soft-enable now */
+	set_soft_enabled(1);
 
 	/*
-	 * if (get_paca()->hard_enabled) return;
-	 * But again we need to take care that gcc gets hard_enabled directly
-	 * via r13, not choose to use an intermediate register, lest we're
-	 * preempted to a different cpu in between the two instructions.
+	 * And replay if we have to. This will return with interrupts
+	 * hard-enabled.
 	 */
-	if (get_hard_enabled())
+	if (replay) {
+		__replay_interrupt(replay);
 		return;
+	}
+
+	/* Finally, let's ensure we are hard enabled */
+	__hard_irq_enable();
+}
+EXPORT_SYMBOL(arch_local_irq_restore);
+
+/*
+ * This is specifically called by assembly code to re-enable interrupts
+ * if they are currently disabled. This is typically called before
+ * schedule() or do_signal() when returning to userspace. We do it
+ * in C to avoid the burden of dealing with lockdep etc...
+ *
+ * NOTE: This is called with interrupts hard disabled but not marked
+ * as such in paca->irq_happened, so we need to resync this.
+ */
+void notrace restore_interrupts(void)
+{
+	if (irqs_disabled()) {
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+		local_irq_enable();
+	} else
+		__hard_irq_enable();
+}
 
+/*
+ * This is a helper to use when about to go into idle low-power
+ * when the latter has the side effect of re-enabling interrupts
+ * (such as calling H_CEDE under pHyp).
+ *
+ * You call this function with interrupts soft-disabled (this is
+ * already the case when ppc_md.power_save is called). The function
+ * will return whether to enter power save or just return.
+ *
+ * In the former case, it will have notified lockdep of interrupts
+ * being re-enabled and generally sanitized the lazy irq state,
+ * and in the latter case it will leave with interrupts hard
+ * disabled and marked as such, so the local_irq_enable() call
+ * in arch_cpu_idle() will properly re-enable everything.
+ */
+bool prep_irq_for_idle(void)
+{
 	/*
-	 * Need to hard-enable interrupts here.  Since currently disabled,
-	 * no need to take further asm precautions against preemption; but
-	 * use local_paca instead of get_paca() to avoid preemption checking.
+	 * First we need to hard disable to ensure no interrupt
+	 * occurs before we effectively enter the low power state
 	 */
-	local_paca->hard_enabled = en;
+	hard_irq_disable();
 
 	/*
-	 * Trigger the decrementer if we have a pending event. Some processors
-	 * only trigger on edge transitions of the sign bit. We might also
-	 * have disabled interrupts long enough that the decrementer wrapped
-	 * to positive.
+	 * If anything happened while we were soft-disabled,
+	 * we return now and do not enter the low power state.
 	 */
-	decrementer_check_overflow();
+	if (lazy_irq_pending())
+		return false;
+
+	/* Tell lockdep we are about to re-enable */
+	trace_hardirqs_on();
 
 	/*
-	 * Force the delivery of pending soft-disabled interrupts on PS3.
-	 * Any HV call will have this side effect.
+	 * Mark interrupts as soft-enabled and clear the
+	 * PACA_IRQ_HARD_DIS from the pending mask since we
+	 * are about to hard enable as well as a side effect
+	 * of entering the low power state.
 	 */
-	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
-		u64 tmp, tmp2;
-		lv1_get_version_info(&tmp, &tmp2);
-	}
+	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	local_paca->soft_enabled = 1;
 
-	__hard_irq_enable();
+	/* Tell the caller to enter the low power state */
+	return true;
 }
-EXPORT_SYMBOL(arch_local_irq_restore);
+
 #endif /* CONFIG_PPC64 */
 
 int arch_show_interrupts(struct seq_file *p, int prec)
@@ -210,15 +354,20 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 
 	seq_printf(p, "%*s: ", prec, "LOC");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs);
-        seq_printf(p, "  Local timer interrupts\n");
+		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event);
+        seq_printf(p, "  Local timer interrupts for timer event device\n");
+
+	seq_printf(p, "%*s: ", prec, "LOC");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others);
+        seq_printf(p, "  Local timer interrupts for others\n");
 
 	seq_printf(p, "%*s: ", prec, "SPU");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
 	seq_printf(p, "  Spurious interrupts\n");
 
-	seq_printf(p, "%*s: ", prec, "CNT");
+	seq_printf(p, "%*s: ", prec, "PMI");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
 	seq_printf(p, "  Performance monitoring interrupts\n");
@@ -228,6 +377,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
 	seq_printf(p, "  Machine check exceptions\n");
 
+#ifdef CONFIG_PPC_DOORBELL
+	if (cpu_has_feature(CPU_FTR_DBELL)) {
+		seq_printf(p, "%*s: ", prec, "DBL");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs);
+		seq_printf(p, "  Doorbell interrupts\n");
+	}
+#endif
+
 	return 0;
 }
 
@@ -236,11 +394,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
  */
 u64 arch_irq_stat_cpu(unsigned int cpu)
 {
-	u64 sum = per_cpu(irq_stat, cpu).timer_irqs;
+	u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event;
 
 	sum += per_cpu(irq_stat, cpu).pmu_irqs;
 	sum += per_cpu(irq_stat, cpu).mce_exceptions;
 	sum += per_cpu(irq_stat, cpu).spurious_irqs;
+	sum += per_cpu(irq_stat, cpu).timer_irqs_others;
+#ifdef CONFIG_PPC_DOORBELL
+	sum += per_cpu(irq_stat, cpu).doorbell_irqs;
+#endif
 
 	return sum;
 }
@@ -256,14 +418,10 @@ void migrate_irqs(void)
 
 	alloc_cpumask_var(&mask, GFP_KERNEL);
 
-	for_each_irq(irq) {
+	for_each_irq_desc(irq, desc) {
 		struct irq_data *data;
 		struct irq_chip *chip;
 
-		desc = irq_to_desc(irq);
-		if (!desc)
-			continue;
-
 		data = irq_desc_get_irq_data(desc);
 		if (irqd_is_per_cpu(data))
 			continue;
@@ -289,50 +447,6 @@ void migrate_irqs(void)
 }
 #endif
 
-static inline void handle_one_irq(unsigned int irq)
-{
-	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit;
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	if (!desc)
-		return;
-
-	/* Switch to the irq stack to handle this */
-	curtp = current_thread_info();
-	irqtp = hardirq_ctx[smp_processor_id()];
-
-	if (curtp == irqtp) {
-		/* We're already on the irq stack, just handle it */
-		desc->handle_irq(irq, desc);
-		return;
-	}
-
-	saved_sp_limit = current->thread.ksp_limit;
-
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-
-	/* Copy the softirq bits in preempt_count so that the
-	 * softirq checks work in the hardirq context. */
-	irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
-			       (curtp->preempt_count & SOFTIRQ_MASK);
-
-	current->thread.ksp_limit = (unsigned long)irqtp +
-		_ALIGN_UP(sizeof(struct thread_info), 16);
-
-	call_handle_irq(irq, desc, irqtp, desc->handle_irq);
-	current->thread.ksp_limit = saved_sp_limit;
-	irqtp->task = NULL;
-
-	/* Set any flag that may have been set on the
-	 * alternate stack
-	 */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
-}
-
 static inline void check_stack_overflow(void)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -349,37 +463,72 @@ static inline void check_stack_overflow(void)
 #endif
 }
 
-void do_IRQ(struct pt_regs *regs)
+void __do_irq(struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned int irq;
 
-	trace_irq_entry(regs);
-
 	irq_enter();
 
+	trace_irq_entry(regs);
+
 	check_stack_overflow();
 
+	/*
+	 * Query the platform PIC for the interrupt & ack it.
+	 *
+	 * This will typically lower the interrupt line to the CPU
+	 */
 	irq = ppc_md.get_irq();
 
-	if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
-		handle_one_irq(irq);
-	else if (irq != NO_IRQ_IGNORE)
+	/* We can hard enable interrupts now to allow perf interrupts */
+	may_hard_irq_enable();
+
+	/* And finally process it */
+	if (unlikely(irq == NO_IRQ))
 		__get_cpu_var(irq_stat).spurious_irqs++;
+	else
+		generic_handle_irq(irq);
+
+	trace_irq_exit(regs);
 
 	irq_exit();
-	set_irq_regs(old_regs);
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct thread_info *curtp, *irqtp, *sirqtp;
 
-#ifdef CONFIG_PPC_ISERIES
-	if (firmware_has_feature(FW_FEATURE_ISERIES) &&
-			get_lppaca()->int_dword.fields.decr_int) {
-		get_lppaca()->int_dword.fields.decr_int = 0;
-		/* Signal a fake decrementer interrupt */
-		timer_interrupt(regs);
+	/* Switch to the irq stack to handle this */
+	curtp = current_thread_info();
+	irqtp = hardirq_ctx[raw_smp_processor_id()];
+	sirqtp = softirq_ctx[raw_smp_processor_id()];
+
+	/* Already there ? */
+	if (unlikely(curtp == irqtp || curtp == sirqtp)) {
+		__do_irq(regs);
+		set_irq_regs(old_regs);
+		return;
 	}
-#endif
 
-	trace_irq_exit(regs);
+	/* Prepare the thread_info in the irq stack */
+	irqtp->task = curtp->task;
+	irqtp->flags = 0;
+
+	/* Copy the preempt_count so that the [soft]irq checks work. */
+	irqtp->preempt_count = curtp->preempt_count;
+
+	/* Switch stack and call */
+	call_do_irq(regs, irqtp);
+
+	/* Restore stack limit */
+	irqtp->task = NULL;
+
+	/* Copy back updates to the thread_info */
+	if (irqtp->flags)
+		set_bits(irqtp->flags, &curtp->flags);
+
+	set_irq_regs(old_regs);
 }
 
 void __init init_IRQ(void)
@@ -406,8 +555,13 @@ void exc_lvl_ctx_init(void)
 #ifdef CONFIG_PPC64
 		cpu_nr = i;
 #else
+#ifdef CONFIG_SMP
 		cpu_nr = get_hard_smp_processor_id(i);
+#else
+		cpu_nr = 0;
+#endif
 #endif
+
 		memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
 		tp = critirq_ctx[cpu_nr];
 		tp->cpu = cpu_nr;
@@ -440,28 +594,22 @@ void irq_ctx_init(void)
 		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
 		tp = softirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = 0;
 
 		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
 		tp = hardirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = HARDIRQ_OFFSET;
 	}
 }
 
-static inline void do_softirq_onstack(void)
+void do_softirq_own_stack(void)
 {
 	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit = current->thread.ksp_limit;
 
 	curtp = current_thread_info();
 	irqtp = softirq_ctx[smp_processor_id()];
 	irqtp->task = curtp->task;
 	irqtp->flags = 0;
-	current->thread.ksp_limit = (unsigned long)irqtp +
-				    _ALIGN_UP(sizeof(struct thread_info), 16);
 	call_do_softirq(irqtp);
-	current->thread.ksp_limit = saved_sp_limit;
 	irqtp->task = NULL;
 
 	/* Set any flag that may have been set on the
@@ -471,27 +619,6 @@ static inline void do_softirq_onstack(void)
 		set_bits(irqtp->flags, &curtp->flags);
 }
 
-void do_softirq(void)
-{
-	unsigned long flags;
-
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	if (local_softirq_pending())
-		do_softirq_onstack();
-
-	local_irq_restore(flags);
-}
-
-irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
-{
-	return d->hwirq;
-}
-EXPORT_SYMBOL_GPL(irqd_to_hwirq);
-
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
 	struct irq_data *irq_data = irq_get_irq_data(virq);
@@ -504,7 +631,7 @@ int irq_choose_cpu(const struct cpumask *mask)
 {
 	int cpuid;
 
-	if (cpumask_equal(mask, cpu_all_mask)) {
+	if (cpumask_equal(mask, cpu_online_mask)) {
 		static int irq_rover;
 		static DEFINE_RAW_SPINLOCK(irq_rover_lock);
 		unsigned long flags;