Merge branch 'for-jens' of git://git.drbd.org/linux-drbd into for-3.6/drivers

5 files changed, 106 insertions, 70 deletions

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index ed1718feb9d9..5971c85df136 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -558,27 +558,54 @@ _GLOBAL(ret_from_except_lite)
 	mtmsrd	r10,1		  /* Update machine state */
 #endif /* CONFIG_PPC_BOOK3E */
 
-#ifdef CONFIG_PREEMPT
 	clrrdi	r9,r1,THREAD_SHIFT	/* current_thread_info() */
-	li	r0,_TIF_NEED_RESCHED	/* bits to check */
 	ld	r3,_MSR(r1)
 	ld	r4,TI_FLAGS(r9)
-	/* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */
-	rlwimi	r0,r3,32+TIF_SIGPENDING-MSR_PR_LG,_TIF_SIGPENDING
-	and.	r0,r4,r0	/* check NEED_RESCHED and maybe SIGPENDING */
-	bne	do_work
-
-#else /* !CONFIG_PREEMPT */
-	ld	r3,_MSR(r1)	/* Returning to user mode? */
 	andi.	r3,r3,MSR_PR
-	beq	restore		/* if not, just restore regs and return */
+	beq	resume_kernel
 
 	/* Check current_thread_info()->flags */
+	andi.	r0,r4,_TIF_USER_WORK_MASK
+	beq	restore
+
+	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq	1f
+	bl	.restore_interrupts
+	bl	.schedule
+	b	.ret_from_except_lite
+
+1:	bl	.save_nvgprs
+	bl	.restore_interrupts
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.do_notify_resume
+	b	.ret_from_except
+
+resume_kernel:
+#ifdef CONFIG_PREEMPT
+	/* Check if we need to preempt */
+	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq+	restore
+	/* Check that preempt_count() == 0 and interrupts are enabled */
+	lwz	r8,TI_PREEMPT(r9)
+	cmpwi	cr1,r8,0
+	ld	r0,SOFTE(r1)
+	cmpdi	r0,0
+	crandc	eq,cr1*4+eq,eq
+	bne	restore
+
+	/*
+	 * Here we are preempting the current task. We want to make
+	 * sure we are soft-disabled first
+	 */
+	SOFT_DISABLE_INTS(r3,r4)
+1:	bl	.preempt_schedule_irq
+
+	/* Re-test flags and eventually loop */
 	clrrdi	r9,r1,THREAD_SHIFT
 	ld	r4,TI_FLAGS(r9)
-	andi.	r0,r4,_TIF_USER_WORK_MASK
-	bne	do_work
-#endif /* !CONFIG_PREEMPT */
+	andi.	r0,r4,_TIF_NEED_RESCHED
+	bne	1b
+#endif /* CONFIG_PREEMPT */
 
 	.globl	fast_exc_return_irq
 fast_exc_return_irq:
@@ -759,50 +786,6 @@ restore_check_irq_replay:
 #endif /* CONFIG_PPC_BOOK3E */
 1:	b	.ret_from_except /* What else to do here ? */
  
-
-
-3:
-do_work:
-#ifdef CONFIG_PREEMPT
-	andi.	r0,r3,MSR_PR	/* Returning to user mode? */
-	bne	user_work
-	/* Check that preempt_count() == 0 and interrupts are enabled */
-	lwz	r8,TI_PREEMPT(r9)
-	cmpwi	cr1,r8,0
-	ld	r0,SOFTE(r1)
-	cmpdi	r0,0
-	crandc	eq,cr1*4+eq,eq
-	bne	restore
-
-	/*
-	 * Here we are preempting the current task. We want to make
-	 * sure we are soft-disabled first
-	 */
-	SOFT_DISABLE_INTS(r3,r4)
-1:	bl	.preempt_schedule_irq
-
-	/* Re-test flags and eventually loop */
-	clrrdi	r9,r1,THREAD_SHIFT
-	ld	r4,TI_FLAGS(r9)
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	bne	1b
-	b	restore
-
-user_work:
-#endif /* CONFIG_PREEMPT */
-
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq	1f
-	bl	.restore_interrupts
-	bl	.schedule
-	b	.ret_from_except_lite
-
-1:	bl	.save_nvgprs
-	bl	.restore_interrupts
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_notify_resume
-	b	.ret_from_except
-
 unrecov_restore:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.unrecoverable_exception
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 7835a5e1ea5f..1f017bb7a7ce 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -229,7 +229,7 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
 		__hard_irq_disable();
-#ifdef CONFIG_TRACE_IRQFLAG
+#ifdef CONFIG_TRACE_IRQFLAGS
 	else {
 		/*
 		 * We should already be hard disabled here. We had bugs
@@ -277,7 +277,7 @@ EXPORT_SYMBOL(arch_local_irq_restore);
  * NOTE: This is called with interrupts hard disabled but not marked
  * as such in paca->irq_happened, so we need to resync this.
  */
-void restore_interrupts(void)
+void notrace restore_interrupts(void)
 {
 	if (irqs_disabled()) {
 		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
@@ -286,6 +286,52 @@ void restore_interrupts(void)
 		__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 cpu_idle() will properly re-enable everything.
+ */
+bool prep_irq_for_idle(void)
+{
+	/*
+	 * First we need to hard disable to ensure no interrupt
+	 * occurs before we effectively enter the low power state
+	 */
+	hard_irq_disable();
+
+	/*
+	 * If anything happened while we were soft-disabled,
+	 * we return now and do not enter the low power state.
+	 */
+	if (lazy_irq_pending())
+		return false;
+
+	/* Tell lockdep we are about to re-enable */
+	trace_hardirqs_on();
+
+	/*
+	 * 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.
+	 */
+	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	local_paca->soft_enabled = 1;
+
+	/* Tell the caller to enter the low power state */
+	return true;
+}
+
 #endif /* CONFIG_PPC64 */
 
 int arch_show_interrupts(struct seq_file *p, int prec)
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 0b6d79617d7b..2e3200ca485f 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -176,8 +176,8 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr,
 
 static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
 {
-	if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16)
-	    && entry->jump[1] == 0x396b0000 + (val & 0xffff))
+	if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16)
+	    && entry->jump[1] == 0x398c0000 + (val & 0xffff))
 		return 1;
 	return 0;
 }
@@ -204,10 +204,9 @@ static uint32_t do_plt_call(void *location,
 		entry++;
 	}
 
-	/* Stolen from Paul Mackerras as well... */
-	entry->jump[0] = 0x3d600000+((val+0x8000)>>16);	/* lis r11,sym@ha */
-	entry->jump[1] = 0x396b0000 + (val&0xffff);	/* addi r11,r11,sym@l*/
-	entry->jump[2] = 0x7d6903a6;			/* mtctr r11 */
+	entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */
+	entry->jump[1] = 0x398c0000 + (val&0xffff);     /* addi r12,r12,sym@l*/
+	entry->jump[2] = 0x7d8903a6;                    /* mtctr r12 */
 	entry->jump[3] = 0x4e800420;			/* bctr */
 
 	DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 1b488e5305c5..0794a3017b1b 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1312,7 +1312,7 @@ static struct opal_secondary_data {
 
 extern char opal_secondary_entry;
 
-static void prom_query_opal(void)
+static void __init prom_query_opal(void)
 {
 	long rc;
 
@@ -1436,7 +1436,7 @@ static void __init prom_opal_hold_cpus(void)
 	prom_debug("prom_opal_hold_cpus: end...\n");
 }
 
-static void prom_opal_takeover(void)
+static void __init prom_opal_takeover(void)
 {
 	struct opal_secondary_data *data = &RELOC(opal_secondary_data);
 	struct opal_takeover_args *args = &data->args;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 99a995c2a3f2..be171ee73bf8 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -475,6 +475,7 @@ void timer_interrupt(struct pt_regs * regs)
 	struct pt_regs *old_regs;
 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
 	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 now;
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
@@ -509,9 +510,16 @@ void timer_interrupt(struct pt_regs * regs)
 		irq_work_run();
 	}
 
-	*next_tb = ~(u64)0;
-	if (evt->event_handler)
-		evt->event_handler(evt);
+	now = get_tb_or_rtc();
+	if (now >= *next_tb) {
+		*next_tb = ~(u64)0;
+		if (evt->event_handler)
+			evt->event_handler(evt);
+	} else {
+		now = *next_tb - now;
+		if (now <= DECREMENTER_MAX)
+			set_dec((int)now);
+	}
 
 #ifdef CONFIG_PPC64
 	/* collect purr register values often, for accurate calculations */