13 files changed, 97 insertions, 226 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f5808a35688c..83afacd3ba7b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -28,7 +28,7 @@ endif
 
 obj-y				:= cputable.o ptrace.o syscalls.o \
 				   irq.o align.o signal_32.o pmc.o vdso.o \
-				   init_task.o process.o systbl.o idle.o \
+				   process.o systbl.o idle.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o dma.o \
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 3e57a00b8cba..ba3aeb4bc06a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -206,40 +206,43 @@ reenable_mmu:				/* re-enable mmu so we can */
 	andi.	r10,r10,MSR_EE		/* Did EE change? */
 	beq	1f
 
-	/* Save handler and return address into the 2 unused words
-	 * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
-	 * else can be recovered from the pt_regs except r3 which for
-	 * normal interrupts has been set to pt_regs and for syscalls
-	 * is an argument, so we temporarily use ORIG_GPR3 to save it
-	 */
-	stw	r9,8(r1)
-	stw	r11,12(r1)
-	stw	r3,ORIG_GPR3(r1)
 	/*
 	 * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
 	 * If from user mode there is only one stack frame on the stack, and
 	 * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
 	 * stack frame to make trace_hardirqs_off happy.
+	 *
+	 * This is handy because we also need to save a bunch of GPRs,
+	 * r3 can be different from GPR3(r1) at this point, r9 and r11
+	 * contains the old MSR and handler address respectively,
+	 * r4 & r5 can contain page fault arguments that need to be passed
+	 * along as well. r12, CCR, CTR, XER etc... are left clobbered as
+	 * they aren't useful past this point (aren't syscall arguments),
+	 * the rest is restored from the exception frame.
 	 */
+	stwu	r1,-32(r1)
+	stw	r9,8(r1)
+	stw	r11,12(r1)
+	stw	r3,16(r1)
+	stw	r4,20(r1)
+	stw	r5,24(r1)
 	andi.	r12,r12,MSR_PR
-	beq	11f
-	stwu	r1,-16(r1)
+	b	11f
 	bl	trace_hardirqs_off
-	addi	r1,r1,16
 	b	12f
-
 11:
 	bl	trace_hardirqs_off
 12:
+	lwz	r5,24(r1)
+	lwz	r4,20(r1)
+	lwz	r3,16(r1)
+	lwz	r11,12(r1)
+	lwz	r9,8(r1)
+	addi	r1,r1,32
 	lwz	r0,GPR0(r1)
-	lwz	r3,ORIG_GPR3(r1)
-	lwz	r4,GPR4(r1)
-	lwz	r5,GPR5(r1)
 	lwz	r6,GPR6(r1)
 	lwz	r7,GPR7(r1)
 	lwz	r8,GPR8(r1)
-	lwz	r9,8(r1)
-	lwz	r11,12(r1)
 1:	mtctr	r11
 	mtlr	r9
 	bctr				/* jump to handler */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index f8a7a1a1a9f4..ef2074c3e906 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -588,23 +588,19 @@ _GLOBAL(ret_from_except_lite)
 fast_exc_return_irq:
 restore:
 	/*
-	 * This is the main kernel exit path, we first check if we
-	 * have to change our interrupt state.
+	 * This is the main kernel exit path. First we check if we
+	 * are about to re-enable interrupts
 	 */
 	ld	r5,SOFTE(r1)
 	lbz	r6,PACASOFTIRQEN(r13)
-	cmpwi	cr1,r5,0
-	cmpw	cr0,r5,r6
-	beq	cr0,4f
+	cmpwi	cr0,r5,0
+	beq	restore_irq_off
 
-	/* We do, handle disable first, which is easy */
-	bne	cr1,3f;
- 	li	r0,0
-	stb	r0,PACASOFTIRQEN(r13);
-	TRACE_DISABLE_INTS
-	b	4f
+	/* We are enabling, were we already enabled ? Yes, just return */
+	cmpwi	cr0,r6,1
+	beq	cr0,do_restore
 
-3:	/*
+	/*
 	 * We are about to soft-enable interrupts (we are hard disabled
 	 * at this point). We check if there's anything that needs to
 	 * be replayed first.
@@ -626,7 +622,7 @@ restore_no_replay:
 	/*
 	 * Final return path. BookE is handled in a different file
 	 */
-4:
+do_restore:
 #ifdef CONFIG_PPC_BOOK3E
 	b	.exception_return_book3e
 #else
@@ -700,6 +696,25 @@ fast_exception_return:
 #endif /* CONFIG_PPC_BOOK3E */
 
 	/*
+	 * We are returning to a context with interrupts soft disabled.
+	 *
+	 * However, we may also about to hard enable, so we need to
+	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+	 * or that bit can get out of sync and bad things will happen
+	 */
+restore_irq_off:
+	ld	r3,_MSR(r1)
+	lbz	r7,PACAIRQHAPPENED(r13)
+	andi.	r0,r3,MSR_EE
+	beq	1f
+	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
+	stb	r7,PACAIRQHAPPENED(r13)
+1:	li	r0,0
+	stb	r0,PACASOFTIRQEN(r13);
+	TRACE_DISABLE_INTS
+	b	do_restore
+
+	/*
 	 * Something did happen, check if a re-emit is needed
 	 * (this also clears paca->irq_happened)
 	 */
@@ -748,6 +763,9 @@ 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? */
@@ -767,16 +785,6 @@ do_work:
 	SOFT_DISABLE_INTS(r3,r4)
 1:	bl	.preempt_schedule_irq
 
-	/* Hard-disable interrupts again (and update PACA) */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	ld	r10,PACAKMSR(r13) /* Get kernel MSR without EE */
-	mtmsrd	r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-	li	r0,PACA_IRQ_HARD_DIS
-	stb	r0,PACAIRQHAPPENED(r13)
-
 	/* Re-test flags and eventually loop */
 	clrrdi	r9,r1,THREAD_SHIFT
 	ld	r4,TI_FLAGS(r9)
@@ -787,14 +795,6 @@ do_work:
 user_work:
 #endif /* CONFIG_PREEMPT */
 
-	/* Enable interrupts */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	ori	r10,r10,MSR_EE
-	mtmsrd	r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	1f
 	bl	.restore_interrupts
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index cb705fdbb458..8f880bc77c56 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -768,8 +768,8 @@ alignment_common:
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 	bl	.save_nvgprs
+	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ENABLE_INTS
 	bl	.alignment_exception
 	b	.ret_from_except
 
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 6d2209ac0c44..2099d9a879e8 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -113,29 +113,6 @@ void cpu_idle(void)
 	}
 }
 
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs come out of the old
- * idle loop and start using the new idle loop.
- * Required while changing idle handler on SMP systems.
- * Caller must have changed idle handler to the new value before the call.
- * This window may be larger on shared systems.
- */
-void cpu_idle_wait(void)
-{
-	int cpu;
-	smp_mb();
-
-	/* kick all the CPUs so that they exit out of old idle routine */
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (cpu != smp_processor_id())
-			smp_send_reschedule(cpu);
-	}
-	put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
 int powersave_nap;
 
 #ifdef CONFIG_SYSCTL
diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c
deleted file mode 100644
index d076d465dbd1..000000000000
--- a/arch/powerpc/kernel/init_task.c
+++ /dev/null
@@ -1,29 +0,0 @@
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/init_task.h>
-#include <linux/fs.h>
-#include <linux/mqueue.h>
-#include <asm/uaccess.h>
-
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-/*
- * Initial thread structure.
- *
- * We need to make sure that this is 16384-byte aligned due to the
- * way process stacks are handled. This is done by having a special
- * "init_task" linker map entry..
- */
-union thread_union init_thread_union __init_task_data =
-	{ INIT_THREAD_INFO(init_task) };
-
-/*
- * Initial task structure.
- *
- * All other task structs will be allocated on slabs in fork.c
- */
-struct task_struct init_task = INIT_TASK(init_task);
-
-EXPORT_SYMBOL(init_task);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 243dbabfe74d..641da9e868ce 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -229,6 +229,19 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
 		__hard_irq_disable();
+#ifdef CONFIG_TRACE_IRQFLAG
+	else {
+		/*
+		 * 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 (WARN_ON(mfmsr() & MSR_EE))
+			__hard_irq_disable();
+	}
+#endif /* CONFIG_TRACE_IRQFLAG */
+
 	set_soft_enabled(0);
 
 	/*
@@ -260,11 +273,17 @@ EXPORT_SYMBOL(arch_local_irq_restore);
  * 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 restore_interrupts(void)
 {
-	if (irqs_disabled())
+	if (irqs_disabled()) {
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 		local_irq_enable();
+	} else
+		__hard_irq_enable();
 }
 
 #endif /* CONFIG_PPC64 */
@@ -330,14 +349,10 @@ 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;
@@ -560,12 +575,6 @@ void do_softirq(void)
 	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);
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index c957b1202bdc..5df777794403 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -23,14 +23,11 @@
 
 void machine_kexec_mask_interrupts(void) {
 	unsigned int i;
+	struct irq_desc *desc;
 
-	for_each_irq(i) {
-		struct irq_desc *desc = irq_to_desc(i);
+	for_each_irq_desc(i, desc) {
 		struct irq_chip *chip;
 
-		if (!desc)
-			continue;
-
 		chip = irq_desc_get_chip(desc);
 		if (!chip)
 			continue;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index f88698c0f332..aa05935b6947 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1235,7 +1235,7 @@ void __ppc64_runlatch_on(void)
 	ctrl |= CTRL_RUNLATCH;
 	mtspr(SPRN_CTRLT, ctrl);
 
-	ti->local_flags |= TLF_RUNLATCH;
+	ti->local_flags |= _TLF_RUNLATCH;
 }
 
 /* Called with hard IRQs off */
@@ -1244,7 +1244,7 @@ void __ppc64_runlatch_off(void)
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
 
-	ti->local_flags &= ~TLF_RUNLATCH;
+	ti->local_flags &= ~_TLF_RUNLATCH;
 
 	ctrl = mfspr(SPRN_CTRLF);
 	ctrl &= ~CTRL_RUNLATCH;
@@ -1252,37 +1252,6 @@ void __ppc64_runlatch_off(void)
 }
 #endif /* CONFIG_PPC64 */
 
-#if THREAD_SHIFT < PAGE_SHIFT
-
-static struct kmem_cache *thread_info_cache;
-
-struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node)
-{
-	struct thread_info *ti;
-
-	ti = kmem_cache_alloc_node(thread_info_cache, GFP_KERNEL, node);
-	if (unlikely(ti == NULL))
-		return NULL;
-#ifdef CONFIG_DEBUG_STACK_USAGE
-	memset(ti, 0, THREAD_SIZE);
-#endif
-	return ti;
-}
-
-void free_thread_info(struct thread_info *ti)
-{
-	kmem_cache_free(thread_info_cache, ti);
-}
-
-void thread_info_cache_init(void)
-{
-	thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
-					      THREAD_SIZE, 0, NULL);
-	BUG_ON(thread_info_cache == NULL);
-}
-
-#endif /* THREAD_SHIFT < PAGE_SHIFT */
-
 unsigned long arch_align_stack(unsigned long sp)
 {
 	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 8d8e028893be..dd5e214cdf21 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1710,7 +1710,7 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
-	secure_computing(regs->gpr[0]);
+	secure_computing_strict(regs->gpr[0]);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
 	    tracehook_report_syscall_entry(regs))
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 9825f29d1faf..ec8a53fa9e8f 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -150,6 +150,9 @@ notrace void __init machine_init(u64 dt_ptr)
 }
 
 #ifdef CONFIG_BOOKE_WDT
+extern u32 booke_wdt_enabled;
+extern u32 booke_wdt_period;
+
 /* Checks wdt=x and wdt_period=xx command-line option */
 notrace int __init early_parse_wdt(char *p)
 {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index d9f94410fd7f..e4cb34322de4 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -57,27 +57,9 @@
 #define DBG(fmt...)
 #endif
 
-
-/* Store all idle threads, this can be reused instead of creating
-* a new thread. Also avoids complicated thread destroy functionality
-* for idle threads.
-*/
 #ifdef CONFIG_HOTPLUG_CPU
-/*
- * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
- * removed after init for !CONFIG_HOTPLUG_CPU.
- */
-static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
-#define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
-#define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
-
 /* State of each CPU during hotplug phases */
 static DEFINE_PER_CPU(int, cpu_state) = { 0 };
-
-#else
-static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
-#define get_idle_for_cpu(x)      (idle_thread_array[(x)])
-#define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
 #endif
 
 struct thread_info *secondary_ti;
@@ -429,60 +411,19 @@ int generic_check_cpu_restart(unsigned int cpu)
 }
 #endif
 
-struct create_idle {
-	struct work_struct work;
-	struct task_struct *idle;
-	struct completion done;
-	int cpu;
-};
-
-static void __cpuinit do_fork_idle(struct work_struct *work)
+static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
 {
-	struct create_idle *c_idle =
-		container_of(work, struct create_idle, work);
-
-	c_idle->idle = fork_idle(c_idle->cpu);
-	complete(&c_idle->done);
-}
-
-static int __cpuinit create_idle(unsigned int cpu)
-{
-	struct thread_info *ti;
-	struct create_idle c_idle = {
-		.cpu	= cpu,
-		.done	= COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
-	};
-	INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
-
-	c_idle.idle = get_idle_for_cpu(cpu);
-
-	/* We can't use kernel_thread since we must avoid to
-	 * reschedule the child. We use a workqueue because
-	 * we want to fork from a kernel thread, not whatever
-	 * userspace process happens to be trying to online us.
-	 */
-	if (!c_idle.idle) {
-		schedule_work(&c_idle.work);
-		wait_for_completion(&c_idle.done);
-	} else
-		init_idle(c_idle.idle, cpu);
-	if (IS_ERR(c_idle.idle)) {		
-		pr_err("Failed fork for CPU %u: %li", cpu, PTR_ERR(c_idle.idle));
-		return PTR_ERR(c_idle.idle);
-	}
-	ti = task_thread_info(c_idle.idle);
+	struct thread_info *ti = task_thread_info(idle);
 
 #ifdef CONFIG_PPC64
-	paca[cpu].__current = c_idle.idle;
+	paca[cpu].__current = idle;
 	paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
 #endif
 	ti->cpu = cpu;
-	current_set[cpu] = ti;
-
-	return 0;
+	secondary_ti = current_set[cpu] = ti;
 }
 
-int __cpuinit __cpu_up(unsigned int cpu)
+int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc, c;
 
@@ -490,12 +431,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	    (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
 		return -EINVAL;
 
-	/* Make sure we have an idle thread */
-	rc = create_idle(cpu);
-	if (rc)
-		return rc;
-
-	secondary_ti = current_set[cpu];
+	cpu_idle_thread_init(cpu, tidle);
 
 	/* Make sure callin-map entry is 0 (can be leftover a CPU
 	 * hotplug
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6aa0c663e247..158972341a2d 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -248,7 +248,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 				   addr, regs->nip, regs->link, code);
 	}
 
-	if (!arch_irq_disabled_regs(regs))
+	if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
 	memset(&info, 0, sizeof(info));
@@ -1019,7 +1019,9 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		return;
 	}
 
-	local_irq_enable();
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
 
 #ifdef CONFIG_MATH_EMULATION
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
@@ -1069,6 +1071,10 @@ void alignment_exception(struct pt_regs *regs)
 {
 	int sig, code, fixed = 0;
 
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
+
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
 		fixed = fix_alignment(regs);