From 69111bac42f5ceacdd22e30947837ceb2c4493ed Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Tue, 21 Oct 2014 15:23:25 -0500
Subject: powerpc: Replace __get_cpu_var uses

This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.

V2->V2
  - Fix up to work against 3.18-rc1

__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x).  This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.

Other use cases are for storing and retrieving data from the current
processors percpu area.  __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.

__get_cpu_var() is defined as :

__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.

This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset.  Thereby address calculations are avoided and less registers
are used when code is generated.

At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.

The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e.  using a global
register that may be set to the per cpu base.

Transformations done to __get_cpu_var()

1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);

2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);

3. Retrieve the content of the current processors instance of a per cpu
variable.

	DEFINE_PER_CPU(int, y);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);

4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(&x, this_cpu_ptr(&y), sizeof(x));

5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	__this_cpu_write(y, x);

6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	__this_cpu_inc(y)

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
      assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/dbell.c         |  2 +-
 arch/powerpc/kernel/hw_breakpoint.c |  6 +++---
 arch/powerpc/kernel/iommu.c         |  2 +-
 arch/powerpc/kernel/irq.c           |  4 ++--
 arch/powerpc/kernel/kgdb.c          |  2 +-
 arch/powerpc/kernel/kprobes.c       |  6 +++---
 arch/powerpc/kernel/mce.c           | 24 ++++++++++++------------
 arch/powerpc/kernel/process.c       | 10 +++++-----
 arch/powerpc/kernel/smp.c           |  6 +++---
 arch/powerpc/kernel/sysfs.c         |  4 ++--
 arch/powerpc/kernel/time.c          | 22 +++++++++++-----------
 arch/powerpc/kernel/traps.c         |  8 ++++----
 12 files changed, 48 insertions(+), 48 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index d55c76c571f3..f4217819cc31 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -41,7 +41,7 @@ void doorbell_exception(struct pt_regs *regs)
 
 	may_hard_irq_enable();
 
-	__get_cpu_var(irq_stat).doorbell_irqs++;
+	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux();
 
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 1f7d84e2e8b2..05e804cdecaa 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -63,7 +63,7 @@ int hw_breakpoint_slots(int type)
 int arch_install_hw_breakpoint(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
 
 	*slot = bp;
 
@@ -88,7 +88,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
  */
 void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 {
-	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
 
 	if (*slot != bp) {
 		WARN_ONCE(1, "Can't find the breakpoint");
@@ -226,7 +226,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	 */
 	rcu_read_lock();
 
-	bp = __get_cpu_var(bp_per_reg);
+	bp = __this_cpu_read(bp_per_reg);
 	if (!bp)
 		goto out;
 	info = counter_arch_bp(bp);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index a10642a0d861..71e60bfb89e2 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -208,7 +208,7 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	 * We don't need to disable preemption here because any CPU can
 	 * safely use any IOMMU pool.
 	 */
-	pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1);
+	pool_nr = __this_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1);
 
 	if (largealloc)
 		pool = &(tbl->large_pool);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c14383575fe8..8d87bb162ecd 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -114,7 +114,7 @@ static inline notrace void set_soft_enabled(unsigned long enable)
 static inline notrace int decrementer_check_overflow(void)
 {
  	u64 now = get_tb_or_rtc();
- 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
  
 	return now >= *next_tb;
 }
@@ -499,7 +499,7 @@ void __do_irq(struct pt_regs *regs)
 
 	/* And finally process it */
 	if (unlikely(irq == NO_IRQ))
-		__get_cpu_var(irq_stat).spurious_irqs++;
+		__this_cpu_inc(irq_stat.spurious_irqs);
 	else
 		generic_handle_irq(irq);
 
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 8504657379f1..e77c3ccf8dcf 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -155,7 +155,7 @@ static int kgdb_singlestep(struct pt_regs *regs)
 {
 	struct thread_info *thread_info, *exception_thread_info;
 	struct thread_info *backup_current_thread_info =
-		&__get_cpu_var(kgdb_thread_info);
+		this_cpu_ptr(&kgdb_thread_info);
 
 	if (user_mode(regs))
 		return 0;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 2f72af82513c..7c053f281406 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -119,7 +119,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
 }
@@ -127,7 +127,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 				struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_msr = regs->msr;
 }
 
@@ -192,7 +192,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs)) {
 				goto ss_probe;
 			}
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index a7fd4cb78b78..15c99b649b04 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -73,8 +73,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
 		    uint64_t nip, uint64_t addr)
 {
 	uint64_t srr1;
-	int index = __get_cpu_var(mce_nest_count)++;
-	struct machine_check_event *mce = &__get_cpu_var(mce_event[index]);
+	int index = __this_cpu_inc_return(mce_nest_count);
+	struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
 
 	/*
 	 * Return if we don't have enough space to log mce event.
@@ -143,7 +143,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
  */
 int get_mce_event(struct machine_check_event *mce, bool release)
 {
-	int index = __get_cpu_var(mce_nest_count) - 1;
+	int index = __this_cpu_read(mce_nest_count) - 1;
 	struct machine_check_event *mc_evt;
 	int ret = 0;
 
@@ -153,7 +153,7 @@ int get_mce_event(struct machine_check_event *mce, bool release)
 
 	/* Check if we have MCE info to process. */
 	if (index < MAX_MC_EVT) {
-		mc_evt = &__get_cpu_var(mce_event[index]);
+		mc_evt = this_cpu_ptr(&mce_event[index]);
 		/* Copy the event structure and release the original */
 		if (mce)
 			*mce = *mc_evt;
@@ -163,7 +163,7 @@ int get_mce_event(struct machine_check_event *mce, bool release)
 	}
 	/* Decrement the count to free the slot. */
 	if (release)
-		__get_cpu_var(mce_nest_count)--;
+		__this_cpu_dec(mce_nest_count);
 
 	return ret;
 }
@@ -184,13 +184,13 @@ void machine_check_queue_event(void)
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
 
-	index = __get_cpu_var(mce_queue_count)++;
+	index = __this_cpu_inc_return(mce_queue_count);
 	/* If queue is full, just return for now. */
 	if (index >= MAX_MC_EVT) {
-		__get_cpu_var(mce_queue_count)--;
+		__this_cpu_dec(mce_queue_count);
 		return;
 	}
-	__get_cpu_var(mce_event_queue[index]) = evt;
+	memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt));
 
 	/* Queue irq work to process this event later. */
 	irq_work_queue(&mce_event_process_work);
@@ -208,11 +208,11 @@ static void machine_check_process_queued_event(struct irq_work *work)
 	 * For now just print it to console.
 	 * TODO: log this error event to FSP or nvram.
 	 */
-	while (__get_cpu_var(mce_queue_count) > 0) {
-		index = __get_cpu_var(mce_queue_count) - 1;
+	while (__this_cpu_read(mce_queue_count) > 0) {
+		index = __this_cpu_read(mce_queue_count) - 1;
 		machine_check_print_event_info(
-				&__get_cpu_var(mce_event_queue[index]));
-		__get_cpu_var(mce_queue_count)--;
+				this_cpu_ptr(&mce_event_queue[index]));
+		__this_cpu_dec(mce_queue_count);
 	}
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 923cd2daba89..91e132b495bf 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -499,7 +499,7 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk)
 
 void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
-	__get_cpu_var(current_brk) = *brk;
+	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
 	if (cpu_has_feature(CPU_FTR_DAWR))
 		set_dawr(brk);
@@ -842,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
  * schedule DABR
  */
 #ifndef CONFIG_HAVE_HW_BREAKPOINT
-	if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk)))
+	if (unlikely(!hw_brk_match(this_cpu_ptr(&current_brk), &new->thread.hw_brk)))
 		__set_breakpoint(&new->thread.hw_brk);
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 #endif
@@ -856,7 +856,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	 * Collect processor utilization data per process
 	 */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
 		long unsigned start_tb, current_tb;
 		start_tb = old_thread->start_tb;
 		cu->current_tb = current_tb = mfspr(SPRN_PURR);
@@ -866,7 +866,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	batch = &__get_cpu_var(ppc64_tlb_batch);
+	batch = this_cpu_ptr(&ppc64_tlb_batch);
 	if (batch->active) {
 		current_thread_info()->local_flags |= _TLF_LAZY_MMU;
 		if (batch->index)
@@ -889,7 +889,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
 		current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
-		batch = &__get_cpu_var(ppc64_tlb_batch);
+		batch = this_cpu_ptr(&ppc64_tlb_batch);
 		batch->active = 1;
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 71e186d5f331..8b2d2dc8ef10 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -243,7 +243,7 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 
 irqreturn_t smp_ipi_demux(void)
 {
-	struct cpu_messages *info = &__get_cpu_var(ipi_message);
+	struct cpu_messages *info = this_cpu_ptr(&ipi_message);
 	unsigned int all;
 
 	mb();	/* order any irq clear */
@@ -442,9 +442,9 @@ void generic_mach_cpu_die(void)
 	idle_task_exit();
 	cpu = smp_processor_id();
 	printk(KERN_DEBUG "CPU%d offline\n", cpu);
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	__this_cpu_write(cpu_state, CPU_DEAD);
 	smp_wmb();
-	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
+	while (__this_cpu_read(cpu_state) != CPU_UP_PREPARE)
 		cpu_relax();
 }
 
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 67fd2fd2620a..fa1fd8a0c867 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -394,10 +394,10 @@ void ppc_enable_pmcs(void)
 	ppc_set_pmu_inuse(1);
 
 	/* Only need to enable them once */
-	if (__get_cpu_var(pmcs_enabled))
+	if (__this_cpu_read(pmcs_enabled))
 		return;
 
-	__get_cpu_var(pmcs_enabled) = 1;
+	__this_cpu_write(pmcs_enabled, 1);
 
 	if (ppc_md.enable_pmcs)
 		ppc_md.enable_pmcs();
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 7505599c2593..9f8ea617ff2c 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -458,9 +458,9 @@ static inline void clear_irq_work_pending(void)
 
 DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
-#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
-#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
+#define set_irq_work_pending_flag()	__this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
 #endif /* 32 vs 64 bit */
 
@@ -482,8 +482,8 @@ void arch_irq_work_raise(void)
 static void __timer_interrupt(void)
 {
 	struct pt_regs *regs = get_irq_regs();
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+	struct clock_event_device *evt = this_cpu_ptr(&decrementers);
 	u64 now;
 
 	trace_timer_interrupt_entry(regs);
@@ -498,7 +498,7 @@ static void __timer_interrupt(void)
 		*next_tb = ~(u64)0;
 		if (evt->event_handler)
 			evt->event_handler(evt);
-		__get_cpu_var(irq_stat).timer_irqs_event++;
+		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
 		if (now <= DECREMENTER_MAX)
@@ -506,13 +506,13 @@ static void __timer_interrupt(void)
 		/* We may have raced with new irq work */
 		if (test_irq_work_pending())
 			set_dec(1);
-		__get_cpu_var(irq_stat).timer_irqs_others++;
+		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}
 
 #ifdef CONFIG_PPC64
 	/* collect purr register values often, for accurate calculations */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
 		cu->current_tb = mfspr(SPRN_PURR);
 	}
 #endif
@@ -527,7 +527,7 @@ static void __timer_interrupt(void)
 void timer_interrupt(struct pt_regs * regs)
 {
 	struct pt_regs *old_regs;
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
@@ -813,7 +813,7 @@ static void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
+	__this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt);
 	set_dec(evt);
 
 	/* We may have raced with new irq work */
@@ -833,7 +833,7 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 /* Interrupt handler for the timer broadcast IPI */
 void tick_broadcast_ipi_handler(void)
 {
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	*next_tb = get_tb_or_rtc();
 	__timer_interrupt();
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 0dc43f9932cf..e6595b72269b 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -295,7 +295,7 @@ long machine_check_early(struct pt_regs *regs)
 {
 	long handled = 0;
 
-	__get_cpu_var(irq_stat).mce_exceptions++;
+	__this_cpu_inc(irq_stat.mce_exceptions);
 
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
@@ -304,7 +304,7 @@ long machine_check_early(struct pt_regs *regs)
 
 long hmi_exception_realmode(struct pt_regs *regs)
 {
-	__get_cpu_var(irq_stat).hmi_exceptions++;
+	__this_cpu_inc(irq_stat.hmi_exceptions);
 
 	if (ppc_md.hmi_exception_early)
 		ppc_md.hmi_exception_early(regs);
@@ -700,7 +700,7 @@ void machine_check_exception(struct pt_regs *regs)
 	enum ctx_state prev_state = exception_enter();
 	int recover = 0;
 
-	__get_cpu_var(irq_stat).mce_exceptions++;
+	__this_cpu_inc(irq_stat.mce_exceptions);
 
 	/* See if any machine dependent calls. In theory, we would want
 	 * to call the CPU first, and call the ppc_md. one if the CPU
@@ -1519,7 +1519,7 @@ void vsx_unavailable_tm(struct pt_regs *regs)
 
 void performance_monitor_exception(struct pt_regs *regs)
 {
-	__get_cpu_var(irq_stat).pmu_irqs++;
+	__this_cpu_inc(irq_stat.pmu_irqs);
 
 	perf_irq(regs);
 }
-- 
cgit v1.2.3


From 9178ba294b6839eeff1a91bed95515d783f3ee6c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 13 Oct 2014 16:01:09 +0200
Subject: powerpc: Convert power off logic to pm_power_off

The generic Linux framework to power off the machine is a function pointer
called pm_power_off. The trick about this pointer is that device drivers can
potentially implement it rather than board files.

Today on powerpc we set pm_power_off to invoke our generic full machine power
off logic which then calls ppc_md.power_off to invoke machine specific power
off.

However, when we want to add a power off GPIO via the "gpio-poweroff" driver,
this card house falls apart. That driver only registers itself if pm_power_off
is NULL to ensure it doesn't override board specific logic. However, since we
always set pm_power_off to the generic power off logic (which will just not
power off the machine if no ppc_md.power_off call is implemented), we can't
implement power off via the generic GPIO power off driver.

To fix this up, let's get rid of the ppc_md.power_off logic and just always use
pm_power_off as was intended. Then individual drivers such as the GPIO power off
driver can implement power off logic via that function pointer.

With this patch set applied and a few patches on top of QEMU that implement a
power off GPIO on the virt e500 machine, I can successfully turn off my virtual
machine after halt.

Signed-off-by: Alexander Graf <agraf@suse.de>
[mpe: Squash into one patch and update changelog based on cover letter]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/machdep.h               |  1 -
 arch/powerpc/kernel/setup-common.c               |  6 +--
 arch/powerpc/platforms/44x/ppc476.c              |  2 +-
 arch/powerpc/platforms/52xx/efika.c              |  3 +-
 arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c   |  8 ++--
 arch/powerpc/platforms/85xx/corenet_generic.c    |  2 +-
 arch/powerpc/platforms/85xx/sgy_cts1000.c        |  4 +-
 arch/powerpc/platforms/cell/celleb_setup.c       |  4 +-
 arch/powerpc/platforms/cell/qpace_setup.c        |  2 +-
 arch/powerpc/platforms/cell/setup.c              |  2 +-
 arch/powerpc/platforms/chrp/setup.c              |  3 +-
 arch/powerpc/platforms/embedded6xx/gamecube.c    |  3 +-
 arch/powerpc/platforms/embedded6xx/linkstation.c |  4 +-
 arch/powerpc/platforms/embedded6xx/wii.c         |  3 +-
 arch/powerpc/platforms/maple/setup.c             |  4 +-
 arch/powerpc/platforms/powermac/setup.c          |  3 +-
 arch/powerpc/platforms/powernv/setup.c           |  4 +-
 arch/powerpc/platforms/ps3/setup.c               |  2 +-
 arch/powerpc/platforms/pseries/setup.c           | 59 ++++++++++++------------
 arch/powerpc/sysdev/fsl_soc.c                    |  2 +-
 arch/powerpc/xmon/xmon.c                         |  3 +-
 21 files changed, 66 insertions(+), 58 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 307347f8ddbd..f15f15c92544 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -142,7 +142,6 @@ struct machdep_calls {
 #endif
 
 	void		(*restart)(char *cmd);
-	void		(*power_off)(void);
 	void		(*halt)(void);
 	void		(*panic)(char *str);
 	void		(*cpu_die)(void);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 1362cd62b3fa..44c8d03558ac 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -139,8 +139,8 @@ void machine_restart(char *cmd)
 void machine_power_off(void)
 {
 	machine_shutdown();
-	if (ppc_md.power_off)
-		ppc_md.power_off();
+	if (pm_power_off)
+		pm_power_off();
 #ifdef CONFIG_SMP
 	smp_send_stop();
 #endif
@@ -151,7 +151,7 @@ void machine_power_off(void)
 /* Used by the G5 thermal driver */
 EXPORT_SYMBOL_GPL(machine_power_off);
 
-void (*pm_power_off)(void) = machine_power_off;
+void (*pm_power_off)(void);
 EXPORT_SYMBOL_GPL(pm_power_off);
 
 void machine_halt(void)
diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c
index 58db9d083969..c11ce6516c8f 100644
--- a/arch/powerpc/platforms/44x/ppc476.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -94,7 +94,7 @@ static int avr_probe(struct i2c_client *client,
 {
 	avr_i2c_client = client;
 	ppc_md.restart = avr_reset_system;
-	ppc_md.power_off = avr_power_off_system;
+	pm_power_off = avr_power_off_system;
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 3feffde9128d..6af651e69129 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -212,6 +212,8 @@ static int __init efika_probe(void)
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 
+	pm_power_off = rtas_power_off;
+
 	return 1;
 }
 
@@ -225,7 +227,6 @@ define_machine(efika)
 	.init_IRQ		= mpc52xx_init_irq,
 	.get_irq		= mpc52xx_get_irq,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.set_rtc_time		= rtas_set_rtc_time,
 	.get_rtc_time		= rtas_get_rtc_time,
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 463fa91ee5b6..15e8021ddef9 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -167,10 +167,10 @@ static int mcu_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (ret)
 		goto err;
 
-	/* XXX: this is potentially racy, but there is no lock for ppc_md */
-	if (!ppc_md.power_off) {
+	/* XXX: this is potentially racy, but there is no lock for pm_power_off */
+	if (!pm_power_off) {
 		glob_mcu = mcu;
-		ppc_md.power_off = mcu_power_off;
+		pm_power_off = mcu_power_off;
 		dev_info(&client->dev, "will provide power-off service\n");
 	}
 
@@ -197,7 +197,7 @@ static int mcu_remove(struct i2c_client *client)
 	device_remove_file(&client->dev, &dev_attr_status);
 
 	if (glob_mcu == mcu) {
-		ppc_md.power_off = NULL;
+		pm_power_off = NULL;
 		glob_mcu = NULL;
 	}
 
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index e56b89a792ed..1f309ccb096e 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -170,7 +170,7 @@ static int __init corenet_generic_probe(void)
 
 			ppc_md.get_irq = ehv_pic_get_irq;
 			ppc_md.restart = fsl_hv_restart;
-			ppc_md.power_off = fsl_hv_halt;
+			pm_power_off = fsl_hv_halt;
 			ppc_md.halt = fsl_hv_halt;
 #ifdef CONFIG_SMP
 			/*
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index 8162b0412117..e149c9ec26ae 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -120,7 +120,7 @@ static int gpio_halt_probe(struct platform_device *pdev)
 
 	/* Register our halt function */
 	ppc_md.halt = gpio_halt_cb;
-	ppc_md.power_off = gpio_halt_cb;
+	pm_power_off = gpio_halt_cb;
 
 	printk(KERN_INFO "gpio-halt: registered GPIO %d (%d trigger, %d"
 	       " irq).\n", gpio, trigger, irq);
@@ -137,7 +137,7 @@ static int gpio_halt_remove(struct platform_device *pdev)
 		free_irq(irq, halt_node);
 
 		ppc_md.halt = NULL;
-		ppc_md.power_off = NULL;
+		pm_power_off = NULL;
 
 		gpio_free(gpio);
 
diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c
index 34e8ce2976aa..90be8ec51686 100644
--- a/arch/powerpc/platforms/cell/celleb_setup.c
+++ b/arch/powerpc/platforms/cell/celleb_setup.c
@@ -142,6 +142,7 @@ static int __init celleb_probe_beat(void)
 	powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS
 		| FW_FEATURE_BEAT | FW_FEATURE_LPAR;
 	hpte_init_beat_v3();
+	pm_power_off = beat_power_off;
 
 	return 1;
 }
@@ -190,6 +191,7 @@ static int __init celleb_probe_native(void)
 
 	powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS;
 	hpte_init_native();
+	pm_power_off = rtas_power_off;
 
 	return 1;
 }
@@ -204,7 +206,6 @@ define_machine(celleb_beat) {
 	.setup_arch		= celleb_setup_arch_beat,
 	.show_cpuinfo		= celleb_show_cpuinfo,
 	.restart		= beat_restart,
-	.power_off		= beat_power_off,
 	.halt			= beat_halt,
 	.get_rtc_time		= beat_get_rtc_time,
 	.set_rtc_time		= beat_set_rtc_time,
@@ -230,7 +231,6 @@ define_machine(celleb_native) {
 	.setup_arch		= celleb_setup_arch_native,
 	.show_cpuinfo		= celleb_show_cpuinfo,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,
diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c
index 6e3409d590ac..d328140dc6f5 100644
--- a/arch/powerpc/platforms/cell/qpace_setup.c
+++ b/arch/powerpc/platforms/cell/qpace_setup.c
@@ -127,6 +127,7 @@ static int __init qpace_probe(void)
 		return 0;
 
 	hpte_init_native();
+	pm_power_off = rtas_power_off;
 
 	return 1;
 }
@@ -137,7 +138,6 @@ define_machine(qpace) {
 	.setup_arch		= qpace_setup_arch,
 	.show_cpuinfo		= qpace_show_cpuinfo,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index 6ae25fb62015..d62aa982d530 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -259,6 +259,7 @@ static int __init cell_probe(void)
 		return 0;
 
 	hpte_init_native();
+	pm_power_off = rtas_power_off;
 
 	return 1;
 }
@@ -269,7 +270,6 @@ define_machine(cell) {
 	.setup_arch		= cell_setup_arch,
 	.show_cpuinfo		= cell_show_cpuinfo,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 5b77b1919fd2..860a59eb8ea2 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -585,6 +585,8 @@ static int __init chrp_probe(void)
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 
+	pm_power_off = rtas_power_off;
+
 	return 1;
 }
 
@@ -597,7 +599,6 @@ define_machine(chrp) {
 	.show_cpuinfo		= chrp_show_cpuinfo,
 	.init_IRQ		= chrp_init_IRQ,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
 	.halt			= rtas_halt,
 	.time_init		= chrp_time_init,
 	.set_rtc_time		= chrp_set_rtc_time,
diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c
index bd4ba5d7d568..fe0ed6ee285e 100644
--- a/arch/powerpc/platforms/embedded6xx/gamecube.c
+++ b/arch/powerpc/platforms/embedded6xx/gamecube.c
@@ -67,6 +67,8 @@ static int __init gamecube_probe(void)
 	if (!of_flat_dt_is_compatible(dt_root, "nintendo,gamecube"))
 		return 0;
 
+	pm_power_off = gamecube_power_off;
+
 	return 1;
 }
 
@@ -80,7 +82,6 @@ define_machine(gamecube) {
 	.probe			= gamecube_probe,
 	.init_early		= gamecube_init_early,
 	.restart		= gamecube_restart,
-	.power_off		= gamecube_power_off,
 	.halt			= gamecube_halt,
 	.init_IRQ		= flipper_pic_probe,
 	.get_irq		= flipper_pic_get_irq,
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c
index 168e1d80b2e5..540eeb58d3f0 100644
--- a/arch/powerpc/platforms/embedded6xx/linkstation.c
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -147,6 +147,9 @@ static int __init linkstation_probe(void)
 
 	if (!of_flat_dt_is_compatible(root, "linkstation"))
 		return 0;
+
+	pm_power_off = linkstation_power_off;
+
 	return 1;
 }
 
@@ -158,7 +161,6 @@ define_machine(linkstation){
 	.show_cpuinfo 		= linkstation_show_cpuinfo,
 	.get_irq 		= mpic_get_irq,
 	.restart 		= linkstation_restart,
-	.power_off 		= linkstation_power_off,
 	.halt	 		= linkstation_halt,
 	.calibrate_decr 	= generic_calibrate_decr,
 };
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 388e29bab8f6..352592d3e44e 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -211,6 +211,8 @@ static int __init wii_probe(void)
 	if (!of_flat_dt_is_compatible(dt_root, "nintendo,wii"))
 		return 0;
 
+	pm_power_off = wii_power_off;
+
 	return 1;
 }
 
@@ -226,7 +228,6 @@ define_machine(wii) {
 	.init_early		= wii_init_early,
 	.setup_arch		= wii_setup_arch,
 	.restart		= wii_restart,
-	.power_off		= wii_power_off,
 	.halt			= wii_halt,
 	.init_IRQ		= wii_pic_probe,
 	.get_irq		= flipper_pic_get_irq,
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index cb1b0b35a0c6..56b85cd61aaf 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -169,7 +169,7 @@ static void __init maple_use_rtas_reboot_and_halt_if_present(void)
 	if (rtas_service_present("system-reboot") &&
 	    rtas_service_present("power-off")) {
 		ppc_md.restart = rtas_restart;
-		ppc_md.power_off = rtas_power_off;
+		pm_power_off = rtas_power_off;
 		ppc_md.halt = rtas_halt;
 	}
 }
@@ -312,6 +312,7 @@ static int __init maple_probe(void)
 	alloc_dart_table();
 
 	hpte_init_native();
+	pm_power_off = maple_power_off;
 
 	return 1;
 }
@@ -325,7 +326,6 @@ define_machine(maple) {
 	.pci_irq_fixup		= maple_pci_irq_fixup,
 	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
 	.restart		= maple_restart,
-	.power_off		= maple_power_off,
 	.halt			= maple_halt,
        	.get_boot_time		= maple_get_boot_time,
        	.set_rtc_time		= maple_set_rtc_time,
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index b127a29ac526..713d36d45d1d 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -632,6 +632,8 @@ static int __init pmac_probe(void)
 	smu_cmdbuf_abs = memblock_alloc_base(4096, 4096, 0x80000000UL);
 #endif /* CONFIG_PMAC_SMU */
 
+	pm_power_off = pmac_power_off;
+
 	return 1;
 }
 
@@ -663,7 +665,6 @@ define_machine(powermac) {
 	.get_irq		= NULL,	/* changed later */
 	.pci_irq_fixup		= pmac_pci_irq_fixup,
 	.restart		= pmac_restart,
-	.power_off		= pmac_power_off,
 	.halt			= pmac_halt,
 	.time_init		= pmac_time_init,
 	.get_boot_time		= pmac_get_boot_time,
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 3f9546d8a51f..941831d67cb2 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -268,7 +268,7 @@ static void __init pnv_setup_machdep_opal(void)
 	ppc_md.get_rtc_time = opal_get_rtc_time;
 	ppc_md.set_rtc_time = opal_set_rtc_time;
 	ppc_md.restart = pnv_restart;
-	ppc_md.power_off = pnv_power_off;
+	pm_power_off = pnv_power_off;
 	ppc_md.halt = pnv_halt;
 	ppc_md.machine_check_exception = opal_machine_check;
 	ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery;
@@ -285,7 +285,7 @@ static void __init pnv_setup_machdep_rtas(void)
 		ppc_md.set_rtc_time = rtas_set_rtc_time;
 	}
 	ppc_md.restart = rtas_restart;
-	ppc_md.power_off = rtas_power_off;
+	pm_power_off = rtas_power_off;
 	ppc_md.halt = rtas_halt;
 }
 #endif /* CONFIG_PPC_POWERNV_RTAS */
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 3f509f86432c..009a2004b876 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -248,6 +248,7 @@ static int __init ps3_probe(void)
 	ps3_mm_init();
 	ps3_mm_vas_create(&htab_size);
 	ps3_hpte_init(htab_size);
+	pm_power_off = ps3_power_off;
 
 	DBG(" <- %s:%d\n", __func__, __LINE__);
 	return 1;
@@ -278,7 +279,6 @@ define_machine(ps3) {
 	.calibrate_decr			= ps3_calibrate_decr,
 	.progress			= ps3_progress,
 	.restart			= ps3_restart,
-	.power_off			= ps3_power_off,
 	.halt				= ps3_halt,
 #if defined(CONFIG_KEXEC)
 	.kexec_cpu_down			= ps3_kexec_cpu_down,
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 125c589eeef5..db0fc0c07568 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -659,6 +659,34 @@ static void __init pSeries_init_early(void)
 	pr_debug(" <- pSeries_init_early()\n");
 }
 
+/**
+ * pseries_power_off - tell firmware about how to power off the system.
+ *
+ * This function calls either the power-off rtas token in normal cases
+ * or the ibm,power-off-ups token (if present & requested) in case of
+ * a power failure. If power-off token is used, power on will only be
+ * possible with power button press. If ibm,power-off-ups token is used
+ * it will allow auto poweron after power is restored.
+ */
+static void pseries_power_off(void)
+{
+	int rc;
+	int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups");
+
+	if (rtas_flash_term_hook)
+		rtas_flash_term_hook(SYS_POWER_OFF);
+
+	if (rtas_poweron_auto == 0 ||
+		rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) {
+		rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1);
+		printk(KERN_INFO "RTAS power-off returned %d\n", rc);
+	} else {
+		rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL);
+		printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc);
+	}
+	for (;;);
+}
+
 /*
  * Called very early, MMU is off, device-tree isn't unflattened
  */
@@ -741,6 +769,8 @@ static int __init pSeries_probe(void)
 	else
 		hpte_init_native();
 
+	pm_power_off = pseries_power_off;
+
 	pr_debug("Machine is%s LPAR !\n",
 	         (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
 
@@ -754,34 +784,6 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus)
 	return PCI_PROBE_NORMAL;
 }
 
-/**
- * pSeries_power_off - tell firmware about how to power off the system.
- *
- * This function calls either the power-off rtas token in normal cases
- * or the ibm,power-off-ups token (if present & requested) in case of
- * a power failure. If power-off token is used, power on will only be
- * possible with power button press. If ibm,power-off-ups token is used
- * it will allow auto poweron after power is restored.
- */
-static void pSeries_power_off(void)
-{
-	int rc;
-	int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups");
-
-	if (rtas_flash_term_hook)
-		rtas_flash_term_hook(SYS_POWER_OFF);
-
-	if (rtas_poweron_auto == 0 ||
-		rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) {
-		rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1);
-		printk(KERN_INFO "RTAS power-off returned %d\n", rc);
-	} else {
-		rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL);
-		printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc);
-	}
-	for (;;);
-}
-
 #ifndef CONFIG_PCI
 void pSeries_final_fixup(void) { }
 #endif
@@ -796,7 +798,6 @@ define_machine(pseries) {
 	.pcibios_fixup		= pSeries_final_fixup,
 	.pci_probe_mode		= pSeries_pci_probe_mode,
 	.restart		= rtas_restart,
-	.power_off		= pSeries_power_off,
 	.halt			= rtas_halt,
 	.panic			= rtas_os_term,
 	.get_boot_time		= rtas_get_boot_time,
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index ffd1169ebaab..1e04568da3b9 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -238,7 +238,7 @@ void fsl_hv_restart(char *cmd)
 /*
  * Halt the current partition
  *
- * This function should be assigned to the ppc_md.power_off and ppc_md.halt
+ * This function should be assigned to the pm_power_off and ppc_md.halt
  * function pointers, to shut down the partition when we're running under
  * the Freescale hypervisor.
  */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index b988b5addf86..506d25681fe3 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -981,7 +981,8 @@ static void bootcmds(void)
 	else if (cmd == 'h')
 		ppc_md.halt();
 	else if (cmd == 'p')
-		ppc_md.power_off();
+		if (pm_power_off)
+			pm_power_off();
 }
 
 static int cpu_cmd(void)
-- 
cgit v1.2.3


From 7b051f665c32db3339ac9b6d9806ef508d09647f Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Mon, 13 Oct 2014 20:27:15 +1100
Subject: powerpc: Use probe_kernel_address in show_instructions

We really don't want to take a pagefault in show_instructions,
so use probe_kernel_address instead of __get_user.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/process.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 91e132b495bf..8c2691e445bd 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -37,9 +37,9 @@
 #include <linux/personality.h>
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
@@ -921,12 +921,8 @@ static void show_instructions(struct pt_regs *regs)
 			pc = (unsigned long)phys_to_virt(pc);
 #endif
 
-		/* We use __get_user here *only* to avoid an OOPS on a
-		 * bad address because the pc *should* only be a
-		 * kernel address.
-		 */
 		if (!__kernel_text_address(pc) ||
-		     __get_user(instr, (unsigned int __user *)pc)) {
+		     probe_kernel_address((unsigned int __user *)pc, instr)) {
 			printk(KERN_CONT "XXXXXXXX ");
 		} else {
 			if (regs->nip == pc)
-- 
cgit v1.2.3


From adb7cd732292b06ee964d9f6090b17c70bd8bd3d Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 14 Oct 2014 11:40:26 +1100
Subject: powerpc/pci: Quieten unset I/O resource warning

Newer POWER designs do not implement PCI I/O space, so we
expect to see a number of these.

Reduce the severity of the warning so it doesn't mask other
real issues.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index e5dad9a9edc0..bc2dab52a991 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1464,7 +1464,7 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
 	res = &hose->io_resource;
 
 	if (!res->flags) {
-		printk(KERN_WARNING "PCI: I/O resource not set for host"
+		pr_info("PCI: I/O resource not set for host"
 		       " bridge %s (domain %d)\n",
 		       hose->dn->full_name, hose->global_number);
 	} else {
-- 
cgit v1.2.3


From 64ff91ff85b56321e65b476e335955af9bed2c66 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 14 Oct 2014 12:24:35 +1100
Subject: powerpc: Remove ppc64_boot_msg

ppc64_boot_msg is meant to be a boot debug aid, but
is only used in one spot. Get rid of it, and save
ourseleves a couple of lines in the kernel log
buffer.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/machdep.h | 10 ----------
 arch/powerpc/kernel/setup_64.c     | 29 -----------------------------
 2 files changed, 39 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index f15f15c92544..4a6511f94258 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -342,16 +342,6 @@ extern sys_ctrler_t sys_ctrler;
 
 #endif /* CONFIG_PPC_PMAC */
 
-
-/* Functions to produce codes on the leds.
- * The SRC code should be unique for the message category and should
- * be limited to the lower 24 bits (the upper 8 are set by these funcs),
- * and (for boot & dump) should be sorted numerically in the order
- * the events occur.
- */
-/* Print a boot progress message. */
-void ppc64_boot_msg(unsigned int src, const char *msg);
-
 static inline void log_error(char *buf, unsigned int err_type, int fatal)
 {
 	if (ppc_md.log_error)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4f3cfe1b6a33..615aa904b216 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -665,8 +665,6 @@ static void __init emergency_stack_init(void)
  */
 void __init setup_arch(char **cmdline_p)
 {
-	ppc64_boot_msg(0x12, "Setup Arch");
-
 	*cmdline_p = boot_command_line;
 
 	/*
@@ -711,33 +709,6 @@ void __init setup_arch(char **cmdline_p)
 	if ((unsigned long)_stext & 0xffff)
 		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
 		      (unsigned long)_stext);
-
-	ppc64_boot_msg(0x15, "Setup Done");
-}
-
-
-/* ToDo: do something useful if ppc_md is not yet setup. */
-#define PPC64_LINUX_FUNCTION 0x0f000000
-#define PPC64_IPL_MESSAGE 0xc0000000
-#define PPC64_TERM_MESSAGE 0xb0000000
-
-static void ppc64_do_msg(unsigned int src, const char *msg)
-{
-	if (ppc_md.progress) {
-		char buf[128];
-
-		sprintf(buf, "%08X\n", src);
-		ppc_md.progress(buf, 0);
-		snprintf(buf, 128, "%s", msg);
-		ppc_md.progress(buf, 0);
-	}
-}
-
-/* Print a boot progress message. */
-void ppc64_boot_msg(unsigned int src, const char *msg)
-{
-	ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_IPL_MESSAGE|src, msg);
-	printk("[boot]%04x %s\n", src, msg);
 }
 
 #ifdef CONFIG_SMP
-- 
cgit v1.2.3


From 7439b37e7579543226cb30eeefdf989bed391997 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:06 +0200
Subject: powerpc/8xx: exception InstructionAccess does not exist on MPC8xx

Exception InstructionAccess does not exist on MPC8xx. No need to branch there from somewhere else.
Handling can be done directly in InstructionTLBError Exception.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index fafff8dbd5d9..d30f703790f4 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -234,15 +234,10 @@ DataAccess:
 	EXC_XFER_LITE(0x300, handle_page_fault)
 
 /* Instruction access exception.
- * This is "never generated" by the MPC8xx.  We jump to it for other
- * translation errors.
+ * This is "never generated" by the MPC8xx.
  */
 	. = 0x400
 InstructionAccess:
-	EXCEPTION_PROLOG
-	mr	r4,r12
-	mr	r5,r9
-	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* External interrupt */
 	EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
@@ -382,7 +377,7 @@ InstructionTLBMiss:
 #endif
 	mfspr	r10, SPRN_SPRG_SCRATCH2
 	EXCEPTION_EPILOG_0
-	b	InstructionAccess
+	b	InstructionTLBError
 
 	. = 0x1200
 DataStoreTLBMiss:
@@ -477,7 +472,11 @@ DataStoreTLBMiss:
  */
 	. = 0x1300
 InstructionTLBError:
-	b	InstructionAccess
+	EXCEPTION_PROLOG
+	mr	r4,r12
+	mr	r5,r9
+	/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
+	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
  * many reasons, including a dirty update to a pte.  We bail out to
-- 
cgit v1.2.3


From 749137a2516aea627cbdd49140e60bb60d80f18e Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:07 +0200
Subject: powerpc/8xx: DataAccess exception not generated by MPC8xx

DataAccess exception is never generated by MPC8xx so do the job directly where
it is used to avoid an unnecessary branching.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index d30f703790f4..464be24fd3eb 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -219,19 +219,10 @@ MachineCheck:
 	EXC_XFER_STD(0x200, machine_check_exception)
 
 /* Data access exception.
- * This is "never generated" by the MPC8xx.  We jump to it for other
- * translation errors.
+ * This is "never generated" by the MPC8xx.
  */
 	. = 0x300
 DataAccess:
-	EXCEPTION_PROLOG
-	mfspr	r10,SPRN_DSISR
-	stw	r10,_DSISR(r11)
-	mr	r5,r10
-	mfspr	r4,SPRN_DAR
-	li	r10,0x00f0
-	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
-	EXC_XFER_LITE(0x300, handle_page_fault)
 
 /* Instruction access exception.
  * This is "never generated" by the MPC8xx.
@@ -491,7 +482,15 @@ DataTLBError:
 	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
 	EXCEPTION_EPILOG_0
-	b	DataAccess
+	EXCEPTION_PROLOG
+	mfspr	r10,SPRN_DSISR
+	stw	r10,_DSISR(r11)
+	mr	r5,r10
+	mfspr	r4,SPRN_DAR
+	li	r10,0x00f0
+	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
+	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
+	EXC_XFER_LITE(0x300, handle_page_fault)
 
 	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE)
 	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE)
-- 
cgit v1.2.3


From 6cde2b6f399e7d68a4b482680850a077104f9068 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:08 +0200
Subject: powerpc/8xx: No need to restore registers and save them again.

In DTLBError handler there is not need to restore r10, r11 and cr registers
after fixing DAR as they are saved again to the same place just after.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 464be24fd3eb..c061bc8d9045 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -481,8 +481,8 @@ DataTLBError:
 	cmpwi	cr0, r11, 0x00f0
 	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
-	EXCEPTION_EPILOG_0
-	EXCEPTION_PROLOG
+	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_2
 	mfspr	r10,SPRN_DSISR
 	stw	r10,_DSISR(r11)
 	mr	r5,r10
-- 
cgit v1.2.3


From cbc130f120d5e180a70a0fa4a8b4191e44548a87 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:08 +0200
Subject: powerpc/8xx: Use M_TW instead of M_TWB

Use M_TW instead of M_TWB for storing Level 1 table address as M_TWB requires
4k aligned tables, which is only the case with 4k pages.
Consequently, we have to calculate the level 1 table index by ourselves.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 48 +++++++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index c061bc8d9045..c78f7fd342cb 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -278,8 +278,8 @@ SystemCall:
 	. = 0x1100
 /*
  * For the MPC8xx, this is a software tablewalk to load the instruction
- * TLB.  It is modelled after the example in the Motorola manual.  The task
- * switch loads the M_TWB register with the pointer to the first level table.
+ * TLB.  The task switch loads the M_TW register with the pointer to the first
+ * level table.
  * If we discover there is no second level table (value is zero) or if there
  * is an invalid pte, we load that into the TLB, which causes another fault
  * into the TLB Error interrupt where we can handle such problems.
@@ -301,7 +301,6 @@ InstructionTLBMiss:
 #endif
 	DO_8xx_CPU6(0x3780, r3)
 	mtspr	SPRN_MD_EPN, r10	/* Have to use MD_EPN for walk, MI_EPN can't */
-	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
@@ -309,14 +308,17 @@ InstructionTLBMiss:
 #ifdef CONFIG_MODULES
 	/* Only modules will cause ITLB Misses as we always
 	 * pin the first 8MB of kernel memory */
-	andi.	r11, r10, 0x0800	/* Address >= 0x80000000 */
+	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
+#endif
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
+#ifdef CONFIG_MODULES
 	beq	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	rlwimi	r10, r11, 0, 2, 19
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
+	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
 3:
 #endif
-	lwz	r11, 0(r10)	/* Get the level 1 entry */
+	rlwinm	r10, r10, 12, 20, 29	/* Extract level 1 index */
+	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
 	beq	2f		/* If zero, don't try to find a pte */
 
@@ -377,18 +379,19 @@ DataStoreTLBMiss:
 #endif
 	EXCEPTION_PROLOG_0
 	mtspr	SPRN_SPRG_SCRATCH2, r10
-	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
+	mfspr	r10, SPRN_MD_EPN
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
-	andi.	r11, r10, 0x0800
+	andis.	r11, r10, 0x8000
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
 	beq	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	rlwimi	r10, r11, 0, 2, 19
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
+	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
 3:
-	lwz	r11, 0(r10)	/* Get the level 1 entry */
+	rlwinm	r10, r10, 12, 20, 29	/* Extract level 1 index */
+	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
 	beq	2f		/* If zero, don't try to find a pte */
 
@@ -527,12 +530,12 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
 	DO_8xx_CPU6(0x3780, r3)
 	mtspr	SPRN_MD_EPN, r10
-	mfspr	r11, SPRN_M_TWB	/* Get level 1 table entry address */
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
 	beq-	3f		/* Branch if user space */
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
 	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
-	rlwimi	r11, r10, 32-20, 0xffc /* r11 = r11&~0xffc|(r10>>20)&0xffc */
-3:	lwz	r11, 0(r11)	/* Get the level 1 entry */
+3:	rlwinm	r10, r10, 12, 20, 29	/* Extract level 1 index */
+	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
 	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
@@ -541,6 +544,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	lwz	r3, 8(r0)	/* restore r3 from memory */
 #endif
 	/* concat physical page address(r11) and page offset(r10) */
+	mfspr	r10, SPRN_SRR0
 	rlwimi	r11, r10, 0, 20, 31
 	lwz	r11,0(r11)
 /* Check if it really is a dcbx instruction. */
@@ -696,11 +700,11 @@ start_here:
 #ifdef CONFIG_8xx_CPU6
 	lis	r4, cpu6_errata_word@h
 	ori	r4, r4, cpu6_errata_word@l
-	li	r3, 0x3980
+	li	r3, 0x3f80
 	stw	r3, 12(r4)
 	lwz	r3, 12(r4)
 #endif
-	mtspr	SPRN_M_TWB, r6
+	mtspr	SPRN_M_TW, r6
 	lis	r4,2f@h
 	ori	r4,r4,2f@l
 	tophys(r4,r4)
@@ -874,10 +878,10 @@ _GLOBAL(set_context)
 	lis	r6, cpu6_errata_word@h
 	ori	r6, r6, cpu6_errata_word@l
 	tophys	(r4, r4)
-	li	r7, 0x3980
+	li	r7, 0x3f80
 	stw	r7, 12(r6)
 	lwz	r7, 12(r6)
-        mtspr   SPRN_M_TWB, r4               /* Update MMU base address */
+        mtspr   SPRN_M_TW, r4               /* Update MMU base address */
 	li	r7, 0x3380
 	stw	r7, 12(r6)
 	lwz	r7, 12(r6)
@@ -885,7 +889,7 @@ _GLOBAL(set_context)
 #else
         mtspr   SPRN_M_CASID,r3		/* Update context */
 	tophys	(r4, r4)
-	mtspr	SPRN_M_TWB, r4		/* and pgd */
+	mtspr	SPRN_M_TW, r4		/* and pgd */
 #endif
 	SYNC
 	blr
-- 
cgit v1.2.3


From 33fb845a6f019001b8ca3f532eb1a4de34547f42 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:08 +0200
Subject: powerpc/8xx: Don't use MD_TWC for walk

MD_TWC can only be used properly with 4k pages.
So lets calculate level 2 table index by ourselves.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 28 ++++++++++++----------------
 1 file changed, 12 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index c78f7fd342cb..3eea29ad1fcf 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -299,8 +299,6 @@ InstructionTLBMiss:
 	addi	r11, r10, -0x1000
 	tlbie	r11
 #endif
-	DO_8xx_CPU6(0x3780, r3)
-	mtspr	SPRN_MD_EPN, r10	/* Have to use MD_EPN for walk, MI_EPN can't */
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
@@ -328,10 +326,9 @@ InstructionTLBMiss:
 	ori	r11,r11,1		/* Set valid bit */
 	DO_8xx_CPU6(0x2b80, r3)
 	mtspr	SPRN_MI_TWC, r11	/* Set segment attributes */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
-	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
-	lwz	r10, 0(r11)	/* Get the pte */
+	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
+	rlwinm	r11, r11, 22, 20, 29	/* Extract level 2 index */
+	lwzx	r10, r10, r11	/* Get the pte */
 
 #ifdef CONFIG_SWAP
 	andi.	r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT
@@ -397,12 +394,13 @@ DataStoreTLBMiss:
 
 	/* We have a pte table, so load fetch the pte from the table.
 	 */
-	ori	r11, r11, 1	/* Set valid bit in physical L2 page */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
-	mfspr	r10, SPRN_MD_TWC	/* ....and get the pte address */
+	mfspr	r10, SPRN_MD_EPN	/* Get address of fault */
+	/* Extract level 2 index */
+	rlwinm	r10, r10, 22, 20, 29
+	rlwimi	r10, r11, 0, 0, 19	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
 
+	ori	r11, r11, 1	/* Set valid bit in physical L2 page */
 	/* Insert the Guarded flag into the TWC from the Linux PTE.
 	 * It is bit 27 of both the Linux PTE and the TWC (at least
 	 * I got that right :-).  It will be better when we can put
@@ -528,18 +526,16 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	/* fetch instruction from memory. */
 	mfspr	r10, SPRN_SRR0
 	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
-	DO_8xx_CPU6(0x3780, r3)
-	mtspr	SPRN_MD_EPN, r10
 	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
 	beq-	3f		/* Branch if user space */
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
 	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
 3:	rlwinm	r10, r10, 12, 20, 29	/* Extract level 1 index */
 	lwzx	r11, r10, r11	/* Get the level 1 entry */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
-	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
-	lwz	r11, 0(r11)	/* Get the pte */
+	rlwinm	r10, r11,0,0,19	/* Extract page descriptor page address */
+	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
+	rlwinm	r11, r11, 22, 20, 29	/* Extract level 2 index */
+	lwzx	r11, r10, r11	/* Get the pte */
 #ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)	/* restore r3 from memory */
 #endif
-- 
cgit v1.2.3


From d14068035c3f6fd0d6514e061e4324a277be83e2 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:09 +0200
Subject: powerpc/8xx: Use PAGE size related consts

For PAGE size related operations, use PAGE size consts in order to be able to
use different page size in the futur.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 3eea29ad1fcf..e126adf15528 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -294,9 +294,9 @@ InstructionTLBMiss:
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
 #ifdef CONFIG_8xx_CPU15
-	addi	r11, r10, 0x1000
+	addi	r11, r10, PAGE_SIZE
 	tlbie	r11
-	addi	r11, r10, -0x1000
+	addi	r11, r10, -PAGE_SIZE
 	tlbie	r11
 #endif
 
@@ -315,7 +315,8 @@ InstructionTLBMiss:
 	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
 3:
 #endif
-	rlwinm	r10, r10, 12, 20, 29	/* Extract level 1 index */
+	/* Extract level 1 index */
+	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
 	beq	2f		/* If zero, don't try to find a pte */
@@ -327,7 +328,8 @@ InstructionTLBMiss:
 	DO_8xx_CPU6(0x2b80, r3)
 	mtspr	SPRN_MI_TWC, r11	/* Set segment attributes */
 	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
-	rlwinm	r11, r11, 22, 20, 29	/* Extract level 2 index */
+	/* Extract level 2 index */
+	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
 	lwzx	r10, r10, r11	/* Get the pte */
 
 #ifdef CONFIG_SWAP
@@ -387,7 +389,8 @@ DataStoreTLBMiss:
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
 	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
 3:
-	rlwinm	r10, r10, 12, 20, 29	/* Extract level 1 index */
+	/* Extract level 1 index */
+	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
 	beq	2f		/* If zero, don't try to find a pte */
@@ -396,8 +399,8 @@ DataStoreTLBMiss:
 	 */
 	mfspr	r10, SPRN_MD_EPN	/* Get address of fault */
 	/* Extract level 2 index */
-	rlwinm	r10, r10, 22, 20, 29
-	rlwimi	r10, r11, 0, 0, 19	/* Add level 2 base */
+	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
 
 	ori	r11, r11, 1	/* Set valid bit in physical L2 page */
@@ -530,18 +533,20 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	beq-	3f		/* Branch if user space */
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
 	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
-3:	rlwinm	r10, r10, 12, 20, 29	/* Extract level 1 index */
+	/* Extract level 1 index */
+3:	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwzx	r11, r10, r11	/* Get the level 1 entry */
 	rlwinm	r10, r11,0,0,19	/* Extract page descriptor page address */
 	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
-	rlwinm	r11, r11, 22, 20, 29	/* Extract level 2 index */
+	/* Extract level 2 index */
+	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
 	lwzx	r11, r10, r11	/* Get the pte */
 #ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)	/* restore r3 from memory */
 #endif
 	/* concat physical page address(r11) and page offset(r10) */
 	mfspr	r10, SPRN_SRR0
-	rlwimi	r11, r10, 0, 20, 31
+	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT, 31
 	lwz	r11,0(r11)
 /* Check if it really is a dcbx instruction. */
 /* dcbt and dcbtst does not generate DTLB Misses/Errors,
@@ -917,12 +922,13 @@ set_dec_cpu6:
 	.globl	sdata
 sdata:
 	.globl	empty_zero_page
+	.align	PAGE_SHIFT
 empty_zero_page:
-	.space	4096
+	.space	PAGE_SIZE
 
 	.globl	swapper_pg_dir
 swapper_pg_dir:
-	.space	4096
+	.space	PGD_TABLE_SIZE
 
 /* Room for two PTE table poiners, usually the kernel and current user
  * pointer to their respective root page table (pgdir).
-- 
cgit v1.2.3


From ac21951fa8a356e2aab6e93a61aa99b561100e67 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:09 +0200
Subject: powerpc/8xx: Const for TLB RPN forced value

Value 0x00f0 is used to force bits in TLB level 2 entry. This value is linked
to the page size and will vary when we change the page size. Lets define a const
for it in order to have it at only one place.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index e126adf15528..38efa8622176 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -40,6 +40,13 @@
 #else
 #define DO_8xx_CPU6(val, reg)
 #endif
+
+/*
+ * Value for the bits that have fixed value in RPN entries.
+ * Also used for tagging DAR for DTLBerror.
+ */
+#define RPN_PATTERN	0x00f0
+
 	__HEAD
 _ENTRY(_stext);
 _ENTRY(_start);
@@ -211,7 +218,7 @@ MachineCheck:
 	EXCEPTION_PROLOG
 	mfspr r4,SPRN_DAR
 	stw r4,_DAR(r11)
-	li r5,0x00f0
+	li r5,RPN_PATTERN
 	mtspr SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr r5,SPRN_DSISR
 	stw r5,_DSISR(r11)
@@ -239,7 +246,7 @@ Alignment:
 	EXCEPTION_PROLOG
 	mfspr	r4,SPRN_DAR
 	stw	r4,_DAR(r11)
-	li	r5,0x00f0
+	li	r5,RPN_PATTERN
 	mtspr	SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr	r5,SPRN_DSISR
 	stw	r5,_DSISR(r11)
@@ -343,7 +350,7 @@ InstructionTLBMiss:
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-	li	r11, 0x00f0
+	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 0x07f8	/* Set 24-27, clear 21-23,28 */
 	DO_8xx_CPU6(0x2d80, r3)
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
@@ -447,7 +454,7 @@ DataStoreTLBMiss:
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-2:	li	r11, 0x00f0
+2:	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
@@ -482,7 +489,7 @@ DataTLBError:
 	EXCEPTION_PROLOG_0
 
 	mfspr	r11, SPRN_DAR
-	cmpwi	cr0, r11, 0x00f0
+	cmpwi	cr0, r11, RPN_PATTERN
 	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
 	EXCEPTION_PROLOG_1
@@ -491,7 +498,7 @@ DARFixed:/* Return from dcbx instruction bug workaround */
 	stw	r10,_DSISR(r11)
 	mr	r5,r10
 	mfspr	r4,SPRN_DAR
-	li	r10,0x00f0
+	li	r10,RPN_PATTERN
 	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
 	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
 	EXC_XFER_LITE(0x300, handle_page_fault)
-- 
cgit v1.2.3


From 959d6173b5cccceff47cc2d25feeaac2f96df0e0 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:09 +0200
Subject: powerpc/8xx: Implement 16k pages

This patch activates the handling of 16k pages on the MPC8xx.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/Kconfig               | 2 +-
 arch/powerpc/include/asm/mmu-8xx.h | 2 ++
 arch/powerpc/kernel/head_8xx.S     | 4 ++++
 3 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 88eace4e28c3..abb8709d8b2a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -549,7 +549,7 @@ config PPC_4K_PAGES
 	bool "4k page size"
 
 config PPC_16K_PAGES
-	bool "16k page size" if 44x
+	bool "16k page size" if 44x || PPC_8xx
 
 config PPC_64K_PAGES
 	bool "64k page size" if 44x || PPC_STD_MMU_64 || PPC_BOOK3E_64
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 3d11d3ce79ec..986b9e1e1044 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -56,6 +56,7 @@
  * additional information from the MI_EPN, and MI_TWC registers.
  */
 #define SPRN_MI_RPN	790
+#define MI_SPS16K	0x00000008	/* Small page size (0 = 4k, 1 = 16k) */
 
 /* Define an RPN value for mapping kernel memory to large virtual
  * pages for boot initialization.  This has real page number of 0,
@@ -129,6 +130,7 @@
  * additional information from the MD_EPN, and MD_TWC registers.
  */
 #define SPRN_MD_RPN	798
+#define MD_SPS16K	0x00000008	/* Small page size (0 = 4k, 1 = 16k) */
 
 /* This is a temporary storage register that could be used to save
  * a processor working register during a tablewalk.
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 38efa8622176..84b0b9778065 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -45,7 +45,11 @@
  * Value for the bits that have fixed value in RPN entries.
  * Also used for tagging DAR for DTLBerror.
  */
+#ifdef CONFIG_PPC_16K_PAGES
+#define RPN_PATTERN	(0x00f0 | MD_SPS16K)
+#else
 #define RPN_PATTERN	0x00f0
+#endif
 
 	__HEAD
 _ENTRY(_stext);
-- 
cgit v1.2.3


From d3e40262e7d05236bf4c2c4fdf007589ba8af97a Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:09 +0200
Subject: powerpc/8xx: Better readibility of ERRATA CPU6 handling

This patch hiddes that SPR address needed for CPU6 ERRATA handling in the macro.
Then we don't have to worry about this address directly in the code.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 84b0b9778065..6e9124177f19 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -33,12 +33,19 @@
 
 /* Macro to make the code more readable. */
 #ifdef CONFIG_8xx_CPU6
-#define DO_8xx_CPU6(val, reg)	\
-	li	reg, val;	\
-	stw	reg, 12(r0);	\
-	lwz	reg, 12(r0);
+#define SPRN_MI_TWC_ADDR	0x2b80
+#define SPRN_MI_RPN_ADDR	0x2d80
+#define SPRN_MD_TWC_ADDR	0x3b80
+#define SPRN_MD_RPN_ADDR	0x3d80
+
+#define MTSPR_CPU6(spr, reg, treg)	\
+	li	treg, spr##_ADDR;	\
+	stw	treg, 12(r0);		\
+	lwz	treg, 12(r0);		\
+	mtspr	spr, reg
 #else
-#define DO_8xx_CPU6(val, reg)
+#define MTSPR_CPU6(spr, reg, treg)	\
+	mtspr	spr, reg
 #endif
 
 /*
@@ -336,8 +343,7 @@ InstructionTLBMiss:
 	 * for this "segment."
 	 */
 	ori	r11,r11,1		/* Set valid bit */
-	DO_8xx_CPU6(0x2b80, r3)
-	mtspr	SPRN_MI_TWC, r11	/* Set segment attributes */
+	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
 	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
 	/* Extract level 2 index */
 	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
@@ -356,8 +362,7 @@ InstructionTLBMiss:
 	 */
 	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 0x07f8	/* Set 24-27, clear 21-23,28 */
-	DO_8xx_CPU6(0x2d80, r3)
-	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
+	MTSPR_CPU6(SPRN_MI_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
@@ -426,8 +431,7 @@ DataStoreTLBMiss:
 	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
 	 */
 	rlwimi	r11, r10, 32-5, 30, 30
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11
+	MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
 
 	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
 	 * We also need to know if the insn is a load/store, so:
@@ -460,8 +464,7 @@ DataStoreTLBMiss:
 	 */
 2:	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
-	DO_8xx_CPU6(0x3d80, r3)
-	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
+	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-- 
cgit v1.2.3


From 4094f28f90adab007eca9babf28f606a40a83032 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:09 +0200
Subject: powerpc/8xx: set PTE bit 22 off TLBmiss

No need to re-set this bit at each TLB miss. Let's set it in the PTE.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/include/asm/pgtable-ppc32.h | 20 ++++++++++++++++++++
 arch/powerpc/include/asm/pte-8xx.h       |  7 +++++--
 arch/powerpc/kernel/head_8xx.S           | 10 ++--------
 3 files changed, 27 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h
index 945e47adf7db..234e07c47803 100644
--- a/arch/powerpc/include/asm/pgtable-ppc32.h
+++ b/arch/powerpc/include/asm/pgtable-ppc32.h
@@ -170,6 +170,25 @@ static inline unsigned long pte_update(pte_t *p,
 #ifdef PTE_ATOMIC_UPDATES
 	unsigned long old, tmp;
 
+#ifdef CONFIG_PPC_8xx
+	unsigned long tmp2;
+
+	__asm__ __volatile__("\
+1:	lwarx	%0,0,%4\n\
+	andc	%1,%0,%5\n\
+	or	%1,%1,%6\n\
+	/* 0x200 == Extended encoding, bit 22 */ \
+	/* Bit 22 has to be 1 if neither _PAGE_USER nor _PAGE_RW are set */ \
+	rlwimi	%1,%1,32-2,0x200\n /* get _PAGE_USER */ \
+	rlwinm	%3,%1,32-1,0x200\n /* get _PAGE_RW */ \
+	or	%1,%3,%1\n\
+	xori	%1,%1,0x200\n"
+"	stwcx.	%1,0,%4\n\
+	bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*p), "=&r" (tmp2)
+	: "r" (p), "r" (clr), "r" (set), "m" (*p)
+	: "cc" );
+#else /* CONFIG_PPC_8xx */
 	__asm__ __volatile__("\
 1:	lwarx	%0,0,%3\n\
 	andc	%1,%0,%4\n\
@@ -180,6 +199,7 @@ static inline unsigned long pte_update(pte_t *p,
 	: "=&r" (old), "=&r" (tmp), "=m" (*p)
 	: "r" (p), "r" (clr), "r" (set), "m" (*p)
 	: "cc" );
+#endif /* CONFIG_PPC_8xx */
 #else /* PTE_ATOMIC_UPDATES */
 	unsigned long old = pte_val(*p);
 	*p = __pte((old & ~clr) | set);
diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index d44826e4ff97..daa4616e61c4 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -48,19 +48,22 @@
  */
 #define _PAGE_RW	0x0400	/* lsb PP bits, inverted in HW */
 #define _PAGE_USER	0x0800	/* msb PP bits */
+/* set when neither _PAGE_USER nor _PAGE_RW are set */
+#define _PAGE_KNLRO	0x0200
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_BAD	0x0ff0
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
 
-#define _PTE_NONE_MASK _PAGE_ACCESSED
+#define _PTE_NONE_MASK _PAGE_KNLRO
 
 /* Until my rework is finished, 8xx still needs atomic PTE updates */
 #define PTE_ATOMIC_UPDATES	1
 
 /* We need to add _PAGE_SHARED to kernel pages */
-#define _PAGE_KERNEL_RO	(_PAGE_SHARED)
+#define _PAGE_KERNEL_RO	(_PAGE_SHARED | _PAGE_KNLRO)
+#define _PAGE_KERNEL_ROX	(_PAGE_EXEC | _PAGE_KNLRO)
 #define _PAGE_KERNEL_RW	(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE)
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 6e9124177f19..8d6e6830a675 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -447,14 +447,8 @@ DataStoreTLBMiss:
 	and	r11, r11, r10
 	rlwimi	r10, r11, 0, _PAGE_PRESENT
 #endif
-	/* Honour kernel RO, User NA */
-	/* 0x200 == Extended encoding, bit 22 */
-	rlwimi	r10, r10, 32-2, 0x200 /* Copy USER to bit 22, 0x200 */
-	/* r11 =  (r10 & _PAGE_RW) >> 1 */
-	rlwinm	r11, r10, 32-1, 0x200
-	or	r10, r11, r10
-	/* invert RW and 0x200 bits */
-	xori	r10, r10, _PAGE_RW | 0x200
+	/* invert RW */
+	xori	r10, r10, _PAGE_RW
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 22 and 28 must be clear.
-- 
cgit v1.2.3


From c9a803fb17bcec0e7527dc8fa055e56a9691abbb Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:09 +0200
Subject: powerpc/8xx: _PMD_PRESENT already set in level 1 entries

When a PMD entry is valid, _PMD_PRESENT is set. Therefore, forcing that bit
during TLB loading is useless.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 8d6e6830a675..46b47e1fe2a9 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -342,7 +342,6 @@ InstructionTLBMiss:
 	/* We have a pte table, so load the MI_TWC with the attributes
 	 * for this "segment."
 	 */
-	ori	r11,r11,1		/* Set valid bit */
 	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
 	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
 	/* Extract level 2 index */
@@ -419,7 +418,6 @@ DataStoreTLBMiss:
 	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
 
-	ori	r11, r11, 1	/* Set valid bit in physical L2 page */
 	/* Insert the Guarded flag into the TWC from the Linux PTE.
 	 * It is bit 27 of both the Linux PTE and the TWC (at least
 	 * I got that right :-).  It will be better when we can put
-- 
cgit v1.2.3


From b0168eb97b8b02594f47ce44faf1502f79e540df Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:10 +0200
Subject: powerpc/8xx: Don't restore regs to save them again.

There is not need to restore r10, r11 and cr registers at this end of ITLBmiss
handler as they are saved again to the same place in ITLBError handler we are
jumping to.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 46b47e1fe2a9..330d54418494 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -383,8 +383,7 @@ InstructionTLBMiss:
 	lwz	r3, 8(r0)
 #endif
 	mfspr	r10, SPRN_SPRG_SCRATCH2
-	EXCEPTION_EPILOG_0
-	b	InstructionTLBError
+	b	InstructionTLBError1
 
 	. = 0x1200
 DataStoreTLBMiss:
@@ -473,7 +472,10 @@ DataStoreTLBMiss:
  */
 	. = 0x1300
 InstructionTLBError:
-	EXCEPTION_PROLOG
+	EXCEPTION_PROLOG_0
+InstructionTLBError1:
+	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_2
 	mr	r4,r12
 	mr	r5,r9
 	/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
-- 
cgit v1.2.3


From 83c17ba35e0306e671b5c9ab622535f23a9a3e78 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:10 +0200
Subject: powerpc/8xx: Use DAR to save r3 for CPU6 ERRATA

As we are not using anymore DAR to save registers, it is now available for
saving the r3 register used for CPU6 ERRATA handling. Therefore we can
remove the major hack which was to use memory location 0 to save r3.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 33 +++++++++++++++------------------
 1 file changed, 15 insertions(+), 18 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 330d54418494..acf6d7eab6d5 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -83,13 +83,6 @@ _ENTRY(_start);
  * 8M 1:1.  I also mapped an additional I/O space 1:1 so we can get to
  * the "internal" processor registers before MMU_init is called.
  *
- * The TLB code currently contains a major hack.  Since I use the condition
- * code register, I have to save and restore it.  I am out of registers, so
- * I just store it in memory location 0 (the TLB handlers are not reentrant).
- * To avoid making any decisions, I need to use the "segment" valid bit
- * in the first level table, but that would require many changes to the
- * Linux page directory/table functions that I don't want to do right now.
- *
  *	-- Dan
  */
 	.globl	__start
@@ -306,7 +299,7 @@ SystemCall:
  */
 InstructionTLBMiss:
 #ifdef CONFIG_8xx_CPU6
-	stw	r3, 8(r0)
+	mtspr	SPRN_DAR, r3
 #endif
 	EXCEPTION_PROLOG_0
 	mtspr	SPRN_SPRG_SCRATCH2, r10
@@ -351,7 +344,10 @@ InstructionTLBMiss:
 #ifdef CONFIG_SWAP
 	andi.	r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT
 	cmpwi	cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT
+	li	r11, RPN_PATTERN
 	bne-	cr0, 2f
+#else
+	li	r11, RPN_PATTERN
 #endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 21 and 28 must be clear.
@@ -359,28 +355,29 @@ InstructionTLBMiss:
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 0x07f8	/* Set 24-27, clear 21-23,28 */
 	MTSPR_CPU6(SPRN_MI_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
+	mfspr	r3, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
 #endif
 	mfspr	r10, SPRN_SPRG_SCRATCH2
 	EXCEPTION_EPILOG_0
 	rfi
 2:
-	mfspr	r11, SPRN_SRR1
+	mfspr	r10, SPRN_SRR1
 	/* clear all error bits as TLB Miss
 	 * sets a few unconditionally
 	*/
-	rlwinm	r11, r11, 0, 0xffff
-	mtspr	SPRN_SRR1, r11
+	rlwinm	r10, r10, 0, 0xffff
+	mtspr	SPRN_SRR1, r10
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
+	mfspr	r3, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
 #endif
 	mfspr	r10, SPRN_SPRG_SCRATCH2
 	b	InstructionTLBError1
@@ -388,7 +385,7 @@ InstructionTLBMiss:
 	. = 0x1200
 DataStoreTLBMiss:
 #ifdef CONFIG_8xx_CPU6
-	stw	r3, 8(r0)
+	mtspr	SPRN_DAR, r3
 #endif
 	EXCEPTION_PROLOG_0
 	mtspr	SPRN_SPRG_SCRATCH2, r10
@@ -459,7 +456,7 @@ DataStoreTLBMiss:
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
+	mfspr	r3, SPRN_DAR
 #endif
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
 	mfspr	r10, SPRN_SPRG_SCRATCH2
@@ -531,7 +528,7 @@ DARFixed:/* Return from dcbx instruction bug workaround */
 #define NO_SELF_MODIFYING_CODE
 FixupDAR:/* Entry point for dcbx workaround. */
 #ifdef CONFIG_8xx_CPU6
-	stw	r3, 8(r0)
+	mtspr	SPRN_DAR, r3
 #endif
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	/* fetch instruction from memory. */
@@ -550,7 +547,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
 	lwzx	r11, r10, r11	/* Get the pte */
 #ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)	/* restore r3 from memory */
+	mfspr	r3, SPRN_DAR
 #endif
 	/* concat physical page address(r11) and page offset(r10) */
 	mfspr	r10, SPRN_SRR0
-- 
cgit v1.2.3


From c51a6821bdbc9068adda93b3b8ee65df8e4642a6 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Fri, 19 Sep 2014 10:36:10 +0200
Subject: powerpc/8xx: Invalidate non present TLB as early as possible

8xx sometimes need to load a invalid/non-present TLBs in
it DTLB asm handler.

These must be invalidated separaly as linux mm doesn't.

Commit 5efab4a02c89c252fb4cce097aafde5f8208dbfe was invalidating them in
arch/powerpc/mm/fault.c.
This patch does the invalidation earlier in order to free the TLB as soon as
possible. This also has the advantage of removing some 8xx specific code from
fault.c

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 arch/powerpc/kernel/head_8xx.S | 15 ++++++++++-----
 arch/powerpc/mm/fault.c        |  7 -------
 2 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index acf6d7eab6d5..d99aac0d69f1 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -475,8 +475,11 @@ InstructionTLBError1:
 	EXCEPTION_PROLOG_2
 	mr	r4,r12
 	mr	r5,r9
+	andis.	r10,r5,0x4000
+	beq+	1f
+	tlbie	r4
 	/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
-	EXC_XFER_LITE(0x400, handle_page_fault)
+1:	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
  * many reasons, including a dirty update to a pte.  We bail out to
@@ -492,11 +495,13 @@ DataTLBError:
 DARFixed:/* Return from dcbx instruction bug workaround */
 	EXCEPTION_PROLOG_1
 	EXCEPTION_PROLOG_2
-	mfspr	r10,SPRN_DSISR
-	stw	r10,_DSISR(r11)
-	mr	r5,r10
+	mfspr	r5,SPRN_DSISR
+	stw	r5,_DSISR(r11)
 	mfspr	r4,SPRN_DAR
-	li	r10,RPN_PATTERN
+	andis.	r10,r5,0x4000
+	beq+	1f
+	tlbie	r4
+1:	li	r10,RPN_PATTERN
 	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
 	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
 	EXC_XFER_LITE(0x300, handle_page_fault)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 08d659a9fcdb..eb79907f34fa 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -43,7 +43,6 @@
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
-#include <mm/mmu_decl.h>
 
 #include "icswx.h"
 
@@ -380,12 +379,6 @@ good_area:
 		goto bad_area;
 #endif /* CONFIG_6xx */
 #if defined(CONFIG_8xx)
-	/* 8xx sometimes need to load a invalid/non-present TLBs.
-	 * These must be invalidated separately as linux mm don't.
-	 */
-	if (error_code & 0x40000000) /* no translation? */
-		_tlbil_va(address, 0, 0, 0);
-
         /* The MPC8xx seems to always set 0x80000000, which is
          * "undefined".  Of those that can be set, this is the only
          * one which seems bad.
-- 
cgit v1.2.3


From 10239733ee8617bac3f1c1769af43a88ed979324 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Wed, 17 Sep 2014 22:15:33 +1000
Subject: powerpc: Remove bootmem allocator

At the moment we transition from the memblock alloctor to the bootmem
allocator. Gitting rid of the bootmem allocator removes a bunch of
complicated code (most of which I owe the dubious honour of being
responsible for writing).

Signed-off-by: Anton Blanchard <anton@samba.org>
Tested-by: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/Kconfig                         |   1 +
 arch/powerpc/include/asm/setup.h             |   3 +-
 arch/powerpc/kernel/setup_32.c               |   5 +-
 arch/powerpc/kernel/setup_64.c               |   3 +-
 arch/powerpc/mm/init_32.c                    |   9 --
 arch/powerpc/mm/mem.c                        |  62 +-------
 arch/powerpc/mm/numa.c                       | 224 ++++-----------------------
 arch/powerpc/mm/pgtable_32.c                 |   3 +-
 arch/powerpc/mm/pgtable_64.c                 |   6 +-
 arch/powerpc/platforms/512x/mpc512x_shared.c |   9 +-
 10 files changed, 47 insertions(+), 278 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 88eace4e28c3..98e9c548bd75 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -148,6 +148,7 @@ config PPC
 	select HAVE_ARCH_AUDITSYSCALL
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
+	select NO_BOOTMEM
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 11ba86e17631..fbdf18cf954c 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -8,7 +8,6 @@ extern void ppc_printk_progress(char *s, unsigned short hex);
 
 extern unsigned int rtas_data;
 extern int mem_init_done;	/* set on boot once kmalloc can be called */
-extern int init_bootmem_done;	/* set once bootmem is available */
 extern unsigned long long memory_limit;
 extern unsigned long klimit;
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
@@ -24,7 +23,7 @@ extern void reloc_got2(unsigned long);
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
 void check_for_initrd(void);
-void do_init_bootmem(void);
+void initmem_init(void);
 void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
 
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 07831ed0d9ef..88a36e64bf9b 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -311,9 +311,8 @@ void __init setup_arch(char **cmdline_p)
 
 	irqstack_early_init();
 
-	/* set up the bootmem stuff with available memory */
-	do_init_bootmem();
-	if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab);
+	initmem_init();
+	if ( ppc_md.progress ) ppc_md.progress("setup_arch: initmem", 0x3eab);
 
 #ifdef CONFIG_DUMMY_CONSOLE
 	conswitchp = &dummy_con;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 615aa904b216..91d9cfaffe6c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -689,8 +689,7 @@ void __init setup_arch(char **cmdline_p)
 	exc_lvl_early_init();
 	emergency_stack_init();
 
-	/* set up the bootmem stuff with available memory */
-	do_init_bootmem();
+	initmem_init();
 	sparse_init();
 
 #ifdef CONFIG_DUMMY_CONSOLE
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 415a51b028b9..3b3100433c18 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -195,15 +195,6 @@ void __init MMU_init(void)
 	memblock_set_current_limit(lowmem_end_addr);
 }
 
-/* This is only called until mem_init is done. */
-void __init *early_get_page(void)
-{
-	if (init_bootmem_done)
-		return alloc_bootmem_pages(PAGE_SIZE);
-	else
-		return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
-}
-
 #ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 2add0b7b9f6d..e076d19c095b 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -61,7 +61,6 @@
 #define CPU_FTR_NOEXECUTE	0
 #endif
 
-int init_bootmem_done;
 int mem_init_done;
 unsigned long long memory_limit;
 
@@ -190,70 +189,22 @@ walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 }
 EXPORT_SYMBOL_GPL(walk_system_ram_range);
 
-/*
- * Initialize the bootmem system and give it all the memory we
- * have available.  If we are using highmem, we only put the
- * lowmem into the bootmem system.
- */
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init do_init_bootmem(void)
+void __init initmem_init(void)
 {
-	unsigned long start, bootmap_pages;
-	unsigned long total_pages;
-	struct memblock_region *reg;
-	int boot_mapsize;
-
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	total_pages = (memblock_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT;
+	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
 #ifdef CONFIG_HIGHMEM
-	total_pages = total_lowmem >> PAGE_SHIFT;
 	max_low_pfn = lowmem_end_addr >> PAGE_SHIFT;
 #endif
 
-	/*
-	 * Find an area to use for the bootmem bitmap.  Calculate the size of
-	 * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE.
-	 * Add 1 additional page in case the address isn't page-aligned.
-	 */
-	bootmap_pages = bootmem_bootmap_pages(total_pages);
-
-	start = memblock_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE);
-
-	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
-	boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
-
 	/* Place all memblock_regions in the same node and merge contiguous
 	 * memblock_regions
 	 */
 	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 
-	/* Add all physical memory to the bootmem map, mark each area
-	 * present.
-	 */
-#ifdef CONFIG_HIGHMEM
-	free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT);
-
-	/* reserve the sections we're already using */
-	for_each_memblock(reserved, reg) {
-		unsigned long top = reg->base + reg->size - 1;
-		if (top < lowmem_end_addr)
-			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-		else if (reg->base < lowmem_end_addr) {
-			unsigned long trunc_size = lowmem_end_addr - reg->base;
-			reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
-		}
-	}
-#else
-	free_bootmem_with_active_regions(0, max_pfn);
-
-	/* reserve the sections we're already using */
-	for_each_memblock(reserved, reg)
-		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-#endif
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
-
-	init_bootmem_done = 1;
 }
 
 /* mark pages that don't exist as nosave */
@@ -369,14 +320,6 @@ void __init paging_init(void)
 	mark_nonram_nosave();
 }
 
-static void __init register_page_bootmem_info(void)
-{
-	int i;
-
-	for_each_online_node(i)
-		register_page_bootmem_info_node(NODE_DATA(i));
-}
-
 void __init mem_init(void)
 {
 	/*
@@ -389,7 +332,6 @@ void __init mem_init(void)
 	swiotlb_init(0);
 #endif
 
-	register_page_bootmem_info();
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 	set_max_mapnr(max_pfn);
 	free_all_bootmem();
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b9d1dfdbe5bb..2e9ad2d76b75 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -134,28 +134,6 @@ static int __init fake_numa_create_new_node(unsigned long end_pfn,
 	return 0;
 }
 
-/*
- * get_node_active_region - Return active region containing pfn
- * Active range returned is empty if none found.
- * @pfn: The page to return the region for
- * @node_ar: Returned set to the active region containing @pfn
- */
-static void __init get_node_active_region(unsigned long pfn,
-					  struct node_active_region *node_ar)
-{
-	unsigned long start_pfn, end_pfn;
-	int i, nid;
-
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
-		if (pfn >= start_pfn && pfn < end_pfn) {
-			node_ar->nid = nid;
-			node_ar->start_pfn = start_pfn;
-			node_ar->end_pfn = end_pfn;
-			break;
-		}
-	}
-}
-
 static void reset_numa_cpu_lookup_table(void)
 {
 	unsigned int cpu;
@@ -928,134 +906,48 @@ static void __init dump_numa_memory_topology(void)
 	}
 }
 
-/*
- * Allocate some memory, satisfying the memblock or bootmem allocator where
- * required. nid is the preferred node and end is the physical address of
- * the highest address in the node.
- *
- * Returns the virtual address of the memory.
- */
-static void __init *careful_zallocation(int nid, unsigned long size,
-				       unsigned long align,
-				       unsigned long end_pfn)
-{
-	void *ret;
-	int new_nid;
-	unsigned long ret_paddr;
-
-	ret_paddr = __memblock_alloc_base(size, align, end_pfn << PAGE_SHIFT);
-
-	/* retry over all memory */
-	if (!ret_paddr)
-		ret_paddr = __memblock_alloc_base(size, align, memblock_end_of_DRAM());
-
-	if (!ret_paddr)
-		panic("numa.c: cannot allocate %lu bytes for node %d",
-		      size, nid);
-
-	ret = __va(ret_paddr);
-
-	/*
-	 * We initialize the nodes in numeric order: 0, 1, 2...
-	 * and hand over control from the MEMBLOCK allocator to the
-	 * bootmem allocator.  If this function is called for
-	 * node 5, then we know that all nodes <5 are using the
-	 * bootmem allocator instead of the MEMBLOCK allocator.
-	 *
-	 * So, check the nid from which this allocation came
-	 * and double check to see if we need to use bootmem
-	 * instead of the MEMBLOCK.  We don't free the MEMBLOCK memory
-	 * since it would be useless.
-	 */
-	new_nid = early_pfn_to_nid(ret_paddr >> PAGE_SHIFT);
-	if (new_nid < nid) {
-		ret = __alloc_bootmem_node(NODE_DATA(new_nid),
-				size, align, 0);
-
-		dbg("alloc_bootmem %p %lx\n", ret, size);
-	}
-
-	memset(ret, 0, size);
-	return ret;
-}
-
 static struct notifier_block ppc64_numa_nb = {
 	.notifier_call = cpu_numa_callback,
 	.priority = 1 /* Must run before sched domains notifier. */
 };
 
-static void __init mark_reserved_regions_for_nid(int nid)
+/* Initialize NODE_DATA for a node on the local memory */
+static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 {
-	struct pglist_data *node = NODE_DATA(nid);
-	struct memblock_region *reg;
-
-	for_each_memblock(reserved, reg) {
-		unsigned long physbase = reg->base;
-		unsigned long size = reg->size;
-		unsigned long start_pfn = physbase >> PAGE_SHIFT;
-		unsigned long end_pfn = PFN_UP(physbase + size);
-		struct node_active_region node_ar;
-		unsigned long node_end_pfn = pgdat_end_pfn(node);
-
-		/*
-		 * Check to make sure that this memblock.reserved area is
-		 * within the bounds of the node that we care about.
-		 * Checking the nid of the start and end points is not
-		 * sufficient because the reserved area could span the
-		 * entire node.
-		 */
-		if (end_pfn <= node->node_start_pfn ||
-		    start_pfn >= node_end_pfn)
-			continue;
-
-		get_node_active_region(start_pfn, &node_ar);
-		while (start_pfn < end_pfn &&
-			node_ar.start_pfn < node_ar.end_pfn) {
-			unsigned long reserve_size = size;
-			/*
-			 * if reserved region extends past active region
-			 * then trim size to active region
-			 */
-			if (end_pfn > node_ar.end_pfn)
-				reserve_size = (node_ar.end_pfn << PAGE_SHIFT)
-					- physbase;
-			/*
-			 * Only worry about *this* node, others may not
-			 * yet have valid NODE_DATA().
-			 */
-			if (node_ar.nid == nid) {
-				dbg("reserve_bootmem %lx %lx nid=%d\n",
-					physbase, reserve_size, node_ar.nid);
-				reserve_bootmem_node(NODE_DATA(node_ar.nid),
-						physbase, reserve_size,
-						BOOTMEM_DEFAULT);
-			}
-			/*
-			 * if reserved region is contained in the active region
-			 * then done.
-			 */
-			if (end_pfn <= node_ar.end_pfn)
-				break;
-
-			/*
-			 * reserved region extends past the active region
-			 *   get next active region that contains this
-			 *   reserved region
-			 */
-			start_pfn = node_ar.end_pfn;
-			physbase = start_pfn << PAGE_SHIFT;
-			size = size - reserve_size;
-			get_node_active_region(start_pfn, &node_ar);
-		}
-	}
+	u64 spanned_pages = end_pfn - start_pfn;
+	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
+	u64 nd_pa;
+	void *nd;
+	int tnid;
+
+	if (spanned_pages)
+		pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+			nid, start_pfn << PAGE_SHIFT,
+			(end_pfn << PAGE_SHIFT) - 1);
+	else
+		pr_info("Initmem setup node %d\n", nid);
+
+	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+	nd = __va(nd_pa);
+
+	/* report and initialize */
+	pr_info("  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+		nd_pa, nd_pa + nd_size - 1);
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (tnid != nid)
+		pr_info("    NODE_DATA(%d) on node %d\n", nid, tnid);
+
+	node_data[nid] = nd;
+	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+	NODE_DATA(nid)->node_id = nid;
+	NODE_DATA(nid)->node_start_pfn = start_pfn;
+	NODE_DATA(nid)->node_spanned_pages = spanned_pages;
 }
 
-
-void __init do_init_bootmem(void)
+void __init initmem_init(void)
 {
 	int nid, cpu;
 
-	min_low_pfn = 0;
 	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	max_pfn = max_low_pfn;
 
@@ -1064,64 +956,16 @@ void __init do_init_bootmem(void)
 	else
 		dump_numa_memory_topology();
 
+	memblock_dump_all();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
-		void *bootmem_vaddr;
-		unsigned long bootmap_pages;
 
 		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
-
-		/*
-		 * Allocate the node structure node local if possible
-		 *
-		 * Be careful moving this around, as it relies on all
-		 * previous nodes' bootmem to be initialized and have
-		 * all reserved areas marked.
-		 */
-		NODE_DATA(nid) = careful_zallocation(nid,
-					sizeof(struct pglist_data),
-					SMP_CACHE_BYTES, end_pfn);
-
-  		dbg("node %d\n", nid);
-		dbg("NODE_DATA() = %p\n", NODE_DATA(nid));
-
-		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
-		NODE_DATA(nid)->node_start_pfn = start_pfn;
-		NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
-
-		if (NODE_DATA(nid)->node_spanned_pages == 0)
-  			continue;
-
-  		dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT);
-  		dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT);
-
-		bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-		bootmem_vaddr = careful_zallocation(nid,
-					bootmap_pages << PAGE_SHIFT,
-					PAGE_SIZE, end_pfn);
-
-		dbg("bootmap_vaddr = %p\n", bootmem_vaddr);
-
-		init_bootmem_node(NODE_DATA(nid),
-				  __pa(bootmem_vaddr) >> PAGE_SHIFT,
-				  start_pfn, end_pfn);
-
-		free_bootmem_with_active_regions(nid, end_pfn);
-		/*
-		 * Be very careful about moving this around.  Future
-		 * calls to careful_zallocation() depend on this getting
-		 * done correctly.
-		 */
-		mark_reserved_regions_for_nid(nid);
+		setup_node_data(nid, start_pfn, end_pfn);
 		sparse_memory_present_with_active_regions(nid);
 	}
 
-	init_bootmem_done = 1;
-
-	/*
-	 * Now bootmem is initialised we can create the node to cpumask
-	 * lookup tables and setup the cpu callback to populate them.
-	 */
 	setup_node_to_cpumask_map();
 
 	reset_numa_cpu_lookup_table();
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index cf11342bf519..d545b1231594 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -100,12 +100,11 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
 {
 	pte_t *pte;
 	extern int mem_init_done;
-	extern void *early_get_page(void);
 
 	if (mem_init_done) {
 		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
 	} else {
-		pte = (pte_t *)early_get_page();
+		pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 		if (pte)
 			clear_page(pte);
 	}
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index c8d709ab489d..cdb19ab859d3 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -75,11 +75,7 @@ static __ref void *early_alloc_pgtable(unsigned long size)
 {
 	void *pt;
 
-	if (init_bootmem_done)
-		pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS));
-	else
-		pt = __va(memblock_alloc_base(size, size,
-					 __pa(MAX_DMA_ADDRESS)));
+	pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS)));
 	memset(pt, 0, size);
 
 	return pt;
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index e996e007bc44..711f3d352af7 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -18,7 +18,7 @@
 #include <linux/irq.h>
 #include <linux/of_platform.h>
 #include <linux/fsl-diu-fb.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <sysdev/fsl_soc.h>
 
 #include <asm/cacheflush.h>
@@ -297,14 +297,13 @@ static void __init mpc512x_setup_diu(void)
 	 * and so negatively affect boot time. Instead we reserve the
 	 * already configured frame buffer area so that it won't be
 	 * destroyed. The starting address of the area to reserve and
-	 * also it's length is passed to reserve_bootmem(). It will be
+	 * also it's length is passed to memblock_reserve(). It will be
 	 * freed later on first open of fbdev, when splash image is not
 	 * needed any more.
 	 */
 	if (diu_shared_fb.in_use) {
-		ret = reserve_bootmem(diu_shared_fb.fb_phys,
-				      diu_shared_fb.fb_len,
-				      BOOTMEM_EXCLUSIVE);
+		ret = memblock_reserve(diu_shared_fb.fb_phys,
+				       diu_shared_fb.fb_len);
 		if (ret) {
 			pr_err("%s: reserve bootmem failed\n", __func__);
 			diu_shared_fb.in_use = false;
-- 
cgit v1.2.3


From 14ed740957704e8768523899e0fa31972577bf65 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Wed, 17 Sep 2014 22:15:34 +1000
Subject: powerpc: Remove some old bootmem related comments

Now bootmem is gone from powerpc we can remove comments mentioning it.

Signed-off-by: Anton Blanchard <anton@samba.org>
Tested-by: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/prom.c           | 5 +----
 arch/powerpc/kernel/rtas.c           | 4 ++--
 arch/powerpc/kvm/book3s_hv_builtin.c | 2 +-
 arch/powerpc/mm/hugetlbpage.c        | 4 ++--
 arch/powerpc/mm/pgtable_64.c         | 4 ----
 5 files changed, 6 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 099f27e6d1b0..6af05fc1dec9 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -696,10 +696,7 @@ void __init early_init_devtree(void *params)
 		reserve_crashkernel();
 	early_reserve_mem();
 
-	/*
-	 * Ensure that total memory size is page-aligned, because otherwise
-	 * mark_bootmem() gets upset.
-	 */
+	/* Ensure that total memory size is page-aligned. */
 	limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
 	memblock_enforce_memory_limit(limit);
 
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 8b4c857c1421..4af905e81ab0 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1091,8 +1091,8 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 }
 
 /*
- * Call early during boot, before mem init or bootmem, to retrieve the RTAS
- * informations from the device-tree and allocate the RMO buffer for userland
+ * Call early during boot, before mem init, to retrieve the RTAS
+ * information from the device-tree and allocate the RMO buffer for userland
  * accesses.
  */
 void __init rtas_initialize(void)
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 4fdc27c80f4c..e64868c0b8de 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -154,7 +154,7 @@ EXPORT_SYMBOL_GPL(kvm_release_hpt);
  * kvm_cma_reserve() - reserve area for kvm hash pagetable
  *
  * This function reserves memory from early allocator. It should be
- * called by arch specific code once the early allocator (memblock or bootmem)
+ * called by arch specific code once the memblock allocator
  * has been activated and all other subsystems have already allocated/reserved
  * memory.
  */
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 8aa04f03fd31..b460e723f0ec 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -276,7 +276,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
 /* Build list of addresses of gigantic pages.  This function is used in early
- * boot before the buddy or bootmem allocator is setup.
+ * boot before the buddy allocator is setup.
  */
 void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 {
@@ -399,7 +399,7 @@ void __init reserve_hugetlb_gpages(void)
 #else /* !PPC_FSL_BOOK3E */
 
 /* Build list of addresses of gigantic pages.  This function is used in early
- * boot before the buddy or bootmem allocator is setup.
+ * boot before the buddy allocator is setup.
  */
 void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 {
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index cdb19ab859d3..aa9173745cf4 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -109,10 +109,6 @@ int map_kernel_page(unsigned long ea, unsigned long pa, int flags)
 							  __pgprot(flags)));
 	} else {
 #ifdef CONFIG_PPC_MMU_NOHASH
-		/* Warning ! This will blow up if bootmem is not initialized
-		 * which our ppc64 code is keen to do that, we'll need to
-		 * fix it and/or be more careful
-		 */
 		pgdp = pgd_offset_k(ea);
 #ifdef PUD_TABLE_SIZE
 		if (pgd_none(*pgdp)) {
-- 
cgit v1.2.3


From 68cf0d642f62267b960f947370539ff3582c4935 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Wed, 17 Sep 2014 22:15:35 +1000
Subject: powerpc: Remove superfluous bootmem includes

Lots of places included bootmem.h even when not using bootmem.

Signed-off-by: Anton Blanchard <anton@samba.org>
Tested-by: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/crash_dump.c               | 1 -
 arch/powerpc/kernel/irq.c                      | 1 -
 arch/powerpc/kernel/pci_64.c                   | 1 -
 arch/powerpc/kernel/rtas_pci.c                 | 1 -
 arch/powerpc/kernel/setup_32.c                 | 1 -
 arch/powerpc/kernel/vdso.c                     | 1 -
 arch/powerpc/kvm/book3s_hv_builtin.c           | 1 -
 arch/powerpc/mm/init_32.c                      | 1 -
 arch/powerpc/mm/init_64.c                      | 1 -
 arch/powerpc/mm/pgtable_64.c                   | 2 +-
 arch/powerpc/platforms/cell/celleb_scc_epci.c  | 1 -
 arch/powerpc/platforms/cell/celleb_scc_pciex.c | 1 -
 arch/powerpc/platforms/maple/pci.c             | 1 -
 arch/powerpc/platforms/powermac/pci.c          | 1 -
 arch/powerpc/platforms/powernv/eeh-ioda.c      | 1 -
 arch/powerpc/platforms/powernv/pci.c           | 1 -
 arch/powerpc/sysdev/fsl_msi.c                  | 1 -
 arch/powerpc/sysdev/ipic.c                     | 1 -
 arch/powerpc/sysdev/mpic.c                     | 1 -
 arch/powerpc/sysdev/mpic_pasemi_msi.c          | 1 -
 arch/powerpc/sysdev/mpic_u3msi.c               | 1 -
 arch/powerpc/sysdev/ppc4xx_msi.c               | 1 -
 arch/powerpc/sysdev/ppc4xx_pci.c               | 1 -
 arch/powerpc/sysdev/qe_lib/qe.c                | 1 -
 arch/powerpc/sysdev/qe_lib/qe_ic.c             | 1 -
 arch/powerpc/sysdev/uic.c                      | 1 -
 26 files changed, 1 insertion(+), 26 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index c78e6dac4d7d..cfa0f81a5bb0 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -12,7 +12,6 @@
 #undef DEBUG
 
 #include <linux/crash_dump.h>
-#include <linux/bootmem.h>
 #include <linux/io.h>
 #include <linux/memblock.h>
 #include <asm/code-patching.h>
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 8d87bb162ecd..45096033d37b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -50,7 +50,6 @@
 #include <linux/list.h>
 #include <linux/radix-tree.h>
 #include <linux/mutex.h>
-#include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 155013da27e0..ba0f2d6fc27f 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -17,7 +17,6 @@
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/list.h>
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 7c55b86206b3..ce230da2c015 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -26,7 +26,6 @@
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 
 #include <asm/io.h>
 #include <asm/pgtable.h>
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 88a36e64bf9b..ba3a3c3b8c66 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -11,7 +11,6 @@
 #include <linux/delay.h>
 #include <linux/initrd.h>
 #include <linux/tty.h>
-#include <linux/bootmem.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index f174351842cf..305eb0d9b768 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -20,7 +20,6 @@
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/security.h>
-#include <linux/bootmem.h>
 #include <linux/memblock.h>
 
 #include <asm/pgtable.h>
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index e64868c0b8de..3f1bb5a36c27 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -12,7 +12,6 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
-#include <linux/bootmem.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
 #include <linux/sizes.h>
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 3b3100433c18..a10be665b645 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -26,7 +26,6 @@
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 3481556a1880..10471f9bb63f 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -34,7 +34,6 @@
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <linux/bootmem.h>
 #include <linux/highmem.h>
 #include <linux/idr.h>
 #include <linux/nodemask.h>
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index aa9173745cf4..e0c718543174 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -33,7 +33,6 @@
 #include <linux/swap.h>
 #include <linux/stddef.h>
 #include <linux/vmalloc.h>
-#include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
 
@@ -51,6 +50,7 @@
 #include <asm/cputable.h>
 #include <asm/sections.h>
 #include <asm/firmware.h>
+#include <asm/dma.h>
 
 #include "mmu_decl.h"
 
diff --git a/arch/powerpc/platforms/cell/celleb_scc_epci.c b/arch/powerpc/platforms/cell/celleb_scc_epci.c
index 844c0facb4f7..9438bbed402f 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_epci.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_epci.c
@@ -25,7 +25,6 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/pci_regs.h>
-#include <linux/bootmem.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index 4278acfa2ede..f22387598040 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -25,7 +25,6 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
index f7136aae8bbf..d3a13067ec42 100644
--- a/arch/powerpc/platforms/maple/pci.c
+++ b/arch/powerpc/platforms/maple/pci.c
@@ -15,7 +15,6 @@
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 
 #include <asm/sections.h>
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 7e868ccf3b0d..04702db35d45 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -15,7 +15,6 @@
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 #include <linux/of_pci.h>
 
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index eba9cb10619c..db3803e21483 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -11,7 +11,6 @@
  * (at your option) any later version.
  */
 
-#include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/io.h>
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b2187d0068b8..ba7452708db3 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index de40b48b460e..8f37204bf94f 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -13,7 +13,6 @@
  *
  */
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/msi.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index b50f97811c25..b28733727ed3 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -20,7 +20,6 @@
 #include <linux/signal.h>
 #include <linux/syscore_ops.h>
 #include <linux/device.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/fsl_devices.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 89cec0ed6a58..c4648ad5c1f3 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -24,7 +24,6 @@
 #include <linux/irq.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c
index 15dccd35fa11..428de9d23120 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c
@@ -16,7 +16,6 @@
 #undef DEBUG
 
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/msi.h>
 #include <asm/mpic.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index 623d7fba15b4..4ce8f54f234c 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/msi.h>
 #include <asm/mpic.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 22b5200636e7..a59f2890897a 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -22,7 +22,6 @@
  */
 
 #include <linux/irq.h>
-#include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/msi.h>
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index df6e2fc4ff92..086aca69ecae 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -22,7 +22,6 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/of.h>
-#include <linux/bootmem.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 238a07b97f2c..b584debbcd9c 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -22,7 +22,6 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
-#include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/ioport.h>
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index b2b87c30e266..543765e1ef14 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -23,7 +23,6 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/device.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <asm/irq.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 92033936a8f7..7c37157d4c24 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -19,7 +19,6 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/device.h>
-#include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
-- 
cgit v1.2.3


From 21098b9e07476deb3f40acd7e51cffbffb4ef865 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Wed, 17 Sep 2014 22:15:36 +1000
Subject: powerpc: Move sparse_init() into initmem_init

We did part of sparse initialisation in setup_arch and part in
initmem_init. Put them together.

Signed-off-by: Anton Blanchard <anton@samba.org>
Tested-by: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup_64.c | 1 -
 arch/powerpc/mm/mem.c          | 1 +
 arch/powerpc/mm/numa.c         | 2 ++
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 91d9cfaffe6c..6e5310ddf8c7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -690,7 +690,6 @@ void __init setup_arch(char **cmdline_p)
 	emergency_stack_init();
 
 	initmem_init();
-	sparse_init();
 
 #ifdef CONFIG_DUMMY_CONSOLE
 	conswitchp = &dummy_con;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index e076d19c095b..b7285a5870f8 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -205,6 +205,7 @@ void __init initmem_init(void)
 
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
+	sparse_init();
 }
 
 /* mark pages that don't exist as nosave */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 2e9ad2d76b75..417b0a523a47 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -966,6 +966,8 @@ void __init initmem_init(void)
 		sparse_memory_present_with_active_regions(nid);
 	}
 
+	sparse_init();
+
 	setup_node_to_cpumask_map();
 
 	reset_numa_cpu_lookup_table();
-- 
cgit v1.2.3


From 7d56c65a6ff9065c459fc63c509950d8ea66e00c Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Wed, 17 Sep 2014 17:07:03 +1000
Subject: powerpc/ftrace: Remove mod_return_to_handler

mod_return_to_handler is the same as return_to_handler, except
it handles the change of the TOC (r2). Add this into
return_to_handler and remove mod_return_to_handler.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/entry_64.S | 24 +-----------------------
 arch/powerpc/kernel/ftrace.c   | 14 ++------------
 arch/powerpc/kernel/process.c  |  9 +--------
 3 files changed, 4 insertions(+), 43 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 0905c8da90f1..66f7ed32848f 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1240,28 +1240,6 @@ _GLOBAL(ftrace_graph_caller)
 	blr
 
 _GLOBAL(return_to_handler)
-	/* need to save return values */
-	std	r4,  -24(r1)
-	std	r3,  -16(r1)
-	std	r31, -8(r1)
-	mr	r31, r1
-	stdu	r1, -112(r1)
-
-	bl	ftrace_return_to_handler
-	nop
-
-	/* return value has real return address */
-	mtlr	r3
-
-	ld	r1, 0(r1)
-	ld	r4,  -24(r1)
-	ld	r3,  -16(r1)
-	ld	r31, -8(r1)
-
-	/* Jump back to real return address */
-	blr
-
-_GLOBAL(mod_return_to_handler)
 	/* need to save return values */
 	std	r4,  -32(r1)
 	std	r3,  -24(r1)
@@ -1272,7 +1250,7 @@ _GLOBAL(mod_return_to_handler)
 	stdu	r1, -112(r1)
 
 	/*
-	 * We are in a module using the module's TOC.
+	 * We might be called from a module.
 	 * Switch to our TOC to run inside the core kernel.
 	 */
 	ld	r2, PACATOC(r13)
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 390311c0f03d..abf79213c356 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -510,10 +510,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
-#ifdef CONFIG_PPC64
-extern void mod_return_to_handler(void);
-#endif
-
 /*
  * Hook the return address and push it in the stack of return addrs
  * in current thread info.
@@ -523,7 +519,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	unsigned long old;
 	int faulted;
 	struct ftrace_graph_ent trace;
-	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long return_hooker;
 
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
@@ -531,13 +527,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
-#ifdef CONFIG_PPC64
-	/* non core kernel code needs to save and restore the TOC */
-	if (REGION_ID(self_addr) != KERNEL_REGION_ID)
-		return_hooker = (unsigned long)&mod_return_to_handler;
-#endif
-
-	return_hooker = ppc_function_entry((void *)return_hooker);
+	return_hooker = ppc_function_entry(return_to_handler);
 
 	/*
 	 * Protect against fault, even if it shouldn't
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8c2691e445bd..f6b82152e7aa 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1527,13 +1527,6 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 	int curr_frame = current->curr_ret_stack;
 	extern void return_to_handler(void);
 	unsigned long rth = (unsigned long)return_to_handler;
-	unsigned long mrth = -1;
-#ifdef CONFIG_PPC64
-	extern void mod_return_to_handler(void);
-	rth = *(unsigned long *)rth;
-	mrth = (unsigned long)mod_return_to_handler;
-	mrth = *(unsigned long *)mrth;
-#endif
 #endif
 
 	sp = (unsigned long) stack;
@@ -1558,7 +1551,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 		if (!firstframe || ip != lr) {
 			printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-			if ((ip == rth || ip == mrth) && curr_frame >= 0) {
+			if ((ip == rth) && curr_frame >= 0) {
 				printk(" (%pS)",
 				       (void *)current->ret_stack[curr_frame].ret);
 				curr_frame--;
-- 
cgit v1.2.3


From b3c18725a0eb7ea2458e9ae3b7e5a477f52e361f Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Wed, 17 Sep 2014 17:07:04 +1000
Subject: powerpc/ftrace: simplify prepare_ftrace_return

Instead of passing in the stack address of the link register
to be modified, just pass in the old value and return the
new value and rely on ftrace_graph_caller to do the
modification.

This removes the exception handling around the stack update -
it isn't needed and we weren't consistent about it. Later on
we would do an unprotected modification:

       if (!ftrace_graph_entry(&trace)) {
               *parent = old;

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/entry_32.S | 10 +++++--
 arch/powerpc/kernel/entry_64.S | 11 ++++++--
 arch/powerpc/kernel/ftrace.c   | 59 ++++++++++--------------------------------
 3 files changed, 30 insertions(+), 50 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 22b45a4955cd..ad837d8a26d4 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1424,12 +1424,18 @@ _GLOBAL(ftrace_graph_caller)
 	lwz	r4, 44(r1)
 	subi	r4, r4, MCOUNT_INSN_SIZE
 
-	/* get the parent address */
-	addi	r3, r1, 52
+	/* Grab the LR out of the caller stack frame */
+	lwz	r3,52(r1)
 
 	bl	prepare_ftrace_return
 	nop
 
+        /*
+         * prepare_ftrace_return gives us the address we divert to.
+         * Change the LR in the callers stack frame to this.
+         */
+	stw	r3,52(r1)
+
 	MCOUNT_RESTORE_FRAME
 	/* old link register ends up in ctr reg */
 	bctr
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 66f7ed32848f..194e46dcf08d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1227,13 +1227,20 @@ _GLOBAL(ftrace_graph_caller)
 	ld	r4, 128(r1)
 	subi	r4, r4, MCOUNT_INSN_SIZE
 
-	/* get the parent address */
+	/* Grab the LR out of the caller stack frame */
 	ld	r11, 112(r1)
-	addi	r3, r11, 16
+	ld	r3, 16(r11)
 
 	bl	prepare_ftrace_return
 	nop
 
+	/*
+	 * prepare_ftrace_return gives us the address we divert to.
+	 * Change the LR in the callers stack frame to this.
+	 */
+	ld	r11, 112(r1)
+	std	r3, 16(r11)
+
 	ld	r0, 128(r1)
 	mtlr	r0
 	addi	r1, r1, 112
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index abf79213c356..d7950317d3a1 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -512,67 +512,34 @@ int ftrace_disable_ftrace_graph_caller(void)
 
 /*
  * Hook the return address and push it in the stack of return addrs
- * in current thread info.
+ * in current thread info. Return the address we want to divert to.
  */
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 {
-	unsigned long old;
-	int faulted;
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker;
 
 	if (unlikely(ftrace_graph_is_dead()))
-		return;
+		goto out;
 
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
-		return;
+		goto out;
 
 	return_hooker = ppc_function_entry(return_to_handler);
 
-	/*
-	 * Protect against fault, even if it shouldn't
-	 * happen. This tool is too much intrusive to
-	 * ignore such a protection.
-	 */
-	asm volatile(
-		"1: " PPC_LL "%[old], 0(%[parent])\n"
-		"2: " PPC_STL "%[return_hooker], 0(%[parent])\n"
-		"   li %[faulted], 0\n"
-		"3:\n"
-
-		".section .fixup, \"ax\"\n"
-		"4: li %[faulted], 1\n"
-		"   b 3b\n"
-		".previous\n"
-
-		".section __ex_table,\"a\"\n"
-			PPC_LONG_ALIGN "\n"
-			PPC_LONG "1b,4b\n"
-			PPC_LONG "2b,4b\n"
-		".previous"
-
-		: [old] "=&r" (old), [faulted] "=r" (faulted)
-		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
-		: "memory"
-	);
-
-	if (unlikely(faulted)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		return;
-	}
-
-	trace.func = self_addr;
+	trace.func = ip;
 	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		*parent = old;
-		return;
-	}
+	if (!ftrace_graph_entry(&trace))
+		goto out;
+
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+		goto out;
 
-	if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY)
-		*parent = old;
+	parent = return_hooker;
+out:
+	return parent;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-- 
cgit v1.2.3


From 60878dfb11d47a9029581543ee2d2101faa88072 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Tue, 29 Apr 2014 09:24:06 +0200
Subject: powerpc/ftrace: Fix obsolete comment

CONFIG_MCOUNT is not defined anymore, the corresponding #ifdef there
is CONFIG_FUNCTION_TRACER.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/entry_32.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index ad837d8a26d4..10a093579191 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1463,4 +1463,4 @@ _GLOBAL(return_to_handler)
 	blr
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-#endif /* CONFIG_MCOUNT */
+#endif /* CONFIG_FUNCTION_TRACER */
-- 
cgit v1.2.3


From e88f157de5e0b327b1b26e3260de4b16c07e2d19 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 27 Oct 2014 20:56:14 +1100
Subject: powerpc: Remove unused vgacon_remap_base & fix build break

The build is broken with CONFIG_PPC32=y, CONFIG_FB_VGA16=y and
CONFIG_VGA_CONSOLE=n.

The problem is that vgacon_remap_base is not defined. It's used in:

    #define VGA_MAP_MEM(x,s) (x + vgacon_remap_base)

Which is used in the vga16fb.c code.

Digging down it seems vgacon_remap_base is never initialised. It used to
be, back in arch/ppc (pplus.c and prep_setup.c), but none of that code
ever made it to arch/powerpc.

So given it's been unused for >6 years, remove it.

Whether vga16fb.c works on 32-bit is another question, but this patch
shouldn't affect it.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/vga.h | 4 +---
 arch/powerpc/kernel/setup_32.c | 5 -----
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/vga.h b/arch/powerpc/include/asm/vga.h
index a2eac409c1ec..e5f8dd366212 100644
--- a/arch/powerpc/include/asm/vga.h
+++ b/arch/powerpc/include/asm/vga.h
@@ -38,12 +38,10 @@ static inline u16 scr_readw(volatile const u16 *addr)
 
 #endif /* !CONFIG_VGA_CONSOLE && !CONFIG_MDA_CONSOLE */
 
-extern unsigned long vgacon_remap_base;
-
 #ifdef __powerpc64__
 #define VGA_MAP_MEM(x,s) ((unsigned long) ioremap((x), s))
 #else
-#define VGA_MAP_MEM(x,s) (x + vgacon_remap_base)
+#define VGA_MAP_MEM(x,s) (x)
 #endif
 
 #define vga_readb(x) (*(x))
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index ba3a3c3b8c66..bb02e9f6944e 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -52,11 +52,6 @@ unsigned long ISA_DMA_THRESHOLD;
 unsigned int DMA_MODE_READ;
 unsigned int DMA_MODE_WRITE;
 
-#ifdef CONFIG_VGA_CONSOLE
-unsigned long vgacon_remap_base;
-EXPORT_SYMBOL(vgacon_remap_base);
-#endif
-
 /*
  * These are used in binfmt_elf.c to put aux entries on the stack
  * for each elf executable being started.
-- 
cgit v1.2.3


From 6f791bef76d66923bc250cbbf4ddbf3f1c944686 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Fri, 31 Oct 2014 14:47:26 +1100
Subject: powerpc: Remove double braces in alignment code.

Looks like I introduced this when adding LE support.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/align.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 34f55524d456..86150fbb42c3 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -908,7 +908,7 @@ int fix_alignment(struct pt_regs *regs)
 		flush_fp_to_thread(current);
 	}
 
-	if ((nb == 16)) {
+	if (nb == 16) {
 		if (flags & F) {
 			/* Special case for 16-byte FP loads and stores */
 			PPC_WARN_ALIGNMENT(fp_pair, regs);
-- 
cgit v1.2.3


From ecaf5fa0a5096a237482ddc4b3c46becf531db1b Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Fri, 31 Oct 2014 14:47:27 +1100
Subject: powerpc: LLVM complains about forward declaration of struct
 rtas_sensors

Move the declaration up to silence the warning.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/rtas-proc.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 8777fb02349f..fb2fb3ea85e5 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -113,17 +113,6 @@
 #define SENSOR_PREFIX		"ibm,sensor-"
 #define cel_to_fahr(x)		((x*9/5)+32)
 
-
-/* Globals */
-static struct rtas_sensors sensors;
-static struct device_node *rtas_node = NULL;
-static unsigned long power_on_time = 0; /* Save the time the user set */
-static char progress_led[MAX_LINELENGTH];
-
-static unsigned long rtas_tone_frequency = 1000;
-static unsigned long rtas_tone_volume = 0;
-
-/* ****************STRUCTS******************************************* */
 struct individual_sensor {
 	unsigned int token;
 	unsigned int quant;
@@ -134,6 +123,15 @@ struct rtas_sensors {
 	unsigned int quant;
 };
 
+/* Globals */
+static struct rtas_sensors sensors;
+static struct device_node *rtas_node = NULL;
+static unsigned long power_on_time = 0; /* Save the time the user set */
+static char progress_led[MAX_LINELENGTH];
+
+static unsigned long rtas_tone_frequency = 1000;
+static unsigned long rtas_tone_volume = 0;
+
 /* ****************************************************************** */
 /* Declarations */
 static int ppc_rtas_sensors_show(struct seq_file *m, void *v);
-- 
cgit v1.2.3


From cd32e2dcc9de6c27ecbbfc0e2079fb64b42bad5f Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 11 Nov 2014 09:12:28 +1100
Subject: powerpc: Fix bad NULL pointer check in udbg_uart_getc_poll()

We have some code in udbg_uart_getc_poll() that tries to protect
against a NULL udbg_uart_in, but gets it all wrong.

Found with the LLVM static analyzer (scan-build).

Fixes: 309257484cc1 ("powerpc: Cleanup udbg_16550 and add support for LPC PIO-only UARTs")
Signed-off-by: Anton Blanchard <anton@samba.org>
[mpe: Add some newlines for readability while we're here]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/udbg_16550.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 6e7c4923b5ea..411116c38da4 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -69,8 +69,12 @@ static void udbg_uart_putc(char c)
 
 static int udbg_uart_getc_poll(void)
 {
-	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+	if (!udbg_uart_in)
+		return -1;
+
+	if (!(udbg_uart_in(UART_LSR) & LSR_DR))
 		return udbg_uart_in(UART_RBR);
+
 	return -1;
 }
 
-- 
cgit v1.2.3


From 8b91a2554610ac5e341de8fb0b5715fe90a0f2e2 Mon Sep 17 00:00:00 2001
From: "Suresh E. Warrier" <warrier@linux.vnet.ibm.com>
Date: Mon, 3 Nov 2014 15:46:42 +1100
Subject: powerpc: Save/restore PPR for KVM hypercalls

The system call FLIH (first-level interrupt handler) at 0xc00
unconditionally sets hardware priority to medium. For hypercalls, this
means we lose guest OS priority. The front end (do_kvm_0x**) to the
KVM interrupt handler always assumes that PPR priority is saved in
PACA exception save area, so it copies this to the kvm_hstate
structure. For hypercalls, this would be the saved priority from any
previous exception. Eventually, the guest gets resumed with an
incorrect priority.

The fix is to save the PPR priority in PACA exception save area before
switching HMT priorities in the FLIH so that existing code described above
in the KVM interrupt handler can copy it from there into the VCPU's saved
context.

Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
[mpe: Dropped HMT_MEDIUM_PPR_DISCARD and reworded comment]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/exceptions-64s.S | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 72e783ea0681..a1d45c161e24 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -292,15 +292,26 @@ decrementer_pSeries:
 	. = 0xc00
 	.globl	system_call_pSeries
 system_call_pSeries:
-	HMT_MEDIUM
+	 /*
+	  * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems
+	  * that support it) before changing to HMT_MEDIUM. That allows the KVM
+	  * code to save that value into the guest state (it is the guest's PPR
+	  * value). Otherwise just change to HMT_MEDIUM as userspace has
+	  * already saved the PPR.
+	  */
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	SET_SCRATCH0(r13)
 	GET_PACA(r13)
 	std	r9,PACA_EXGEN+EX_R9(r13)
+	OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);
+	HMT_MEDIUM;
 	std	r10,PACA_EXGEN+EX_R10(r13)
+	OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR);
 	mfcr	r9
 	KVMTEST(0xc00)
 	GET_SCRATCH0(r13)
+#else
+	HMT_MEDIUM;
 #endif
 	SYSCALL_PSERIES_1
 	SYSCALL_PSERIES_2_RFID
-- 
cgit v1.2.3


From 9e819963b45f79e87f5a8c44960a66c0727c80e6 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sun, 2 Nov 2014 20:02:42 +0530
Subject: powerpc: Disable CPU_FTR_TM if TM is disabled by firmware

Firmware is allowed to communicate to us via the "ibm,pa-features" property
that TM (Transactional Memory) support is disabled.

Currently this doesn't happen on any platform we're aware of, but we should
honor it anyway.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/prom.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 6af05fc1dec9..6a799b3cc6b4 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -160,6 +160,12 @@ static struct ibm_pa_feature {
 	{CPU_FTR_NODSISRALIGN, 0, 0,	1, 1, 1},
 	{0, MMU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
 	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
+	/*
+	 * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n),
+	 * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP
+	 * which is 0 if the kernel doesn't support TM.
+	 */
+	{CPU_FTR_TM_COMP, 0, 0,		22, 0, 0},
 };
 
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
-- 
cgit v1.2.3


From 59994fb01a102a448ba758c9b824a29b4a99cc1b Mon Sep 17 00:00:00 2001
From: Vineeth Vijayan <vvijayan@mvista.com>
Date: Fri, 14 Nov 2014 14:42:05 +0530
Subject: powerpc: Use generic PIE randomization

Back in 2009 we merged 501cb16d3cfd "Randomise PIEs", which added support for
randomizing PIE (Position Independent Executable) binaries.

That commit added randomize_et_dyn(), which correctly randomized the addresses,
but failed to honor PF_RANDOMIZE. That means it was not possible to disable PIE
randomization via the personality flag, or /proc/sys/kernel/randomize_va_space.

Since then there has been generic support for PIE randomization added to
binfmt_elf.c, selectable via ARCH_BINFMT_ELF_RANDOMIZE_PIE.

Enabling that allows us to drop randomize_et_dyn(), which means we start
honoring PF_RANDOMIZE correctly.

It also causes a fairly major change to how we layout PIE binaries.

Currently we will place the binary at 512MB-520MB for 32 bit binaries, or
512MB-1.5GB for 64 bit binaries, eg:

    $ cat /proc/$$/maps
    4e550000-4e580000 r-xp 00000000 08:02 129813       /bin/dash
    4e580000-4e590000 rw-p 00020000 08:02 129813       /bin/dash
    10014110000-10014140000 rw-p 00000000 00:00 0      [heap]
    3fffaa3f0000-3fffaa5a0000 r-xp 00000000 08:02 921  /lib/powerpc64le-linux-gnu/libc-2.19.so
    3fffaa5a0000-3fffaa5b0000 rw-p 001a0000 08:02 921  /lib/powerpc64le-linux-gnu/libc-2.19.so
    3fffaa5c0000-3fffaa5d0000 rw-p 00000000 00:00 0
    3fffaa5d0000-3fffaa5f0000 r-xp 00000000 00:00 0    [vdso]
    3fffaa5f0000-3fffaa620000 r-xp 00000000 08:02 1246 /lib/powerpc64le-linux-gnu/ld-2.19.so
    3fffaa620000-3fffaa630000 rw-p 00020000 08:02 1246 /lib/powerpc64le-linux-gnu/ld-2.19.so
    3ffffc340000-3ffffc370000 rw-p 00000000 00:00 0    [stack]

With this commit applied we don't do any special randomisation for the binary,
and instead rely on mmap randomisation. This means the binary ends up at high
addresses, eg:

    $ cat /proc/$$/maps
    3fff99820000-3fff999d0000 r-xp 00000000 08:02 921    /lib/powerpc64le-linux-gnu/libc-2.19.so
    3fff999d0000-3fff999e0000 rw-p 001a0000 08:02 921    /lib/powerpc64le-linux-gnu/libc-2.19.so
    3fff999f0000-3fff99a00000 rw-p 00000000 00:00 0
    3fff99a00000-3fff99a20000 r-xp 00000000 00:00 0      [vdso]
    3fff99a20000-3fff99a50000 r-xp 00000000 08:02 1246   /lib/powerpc64le-linux-gnu/ld-2.19.so
    3fff99a50000-3fff99a60000 rw-p 00020000 08:02 1246   /lib/powerpc64le-linux-gnu/ld-2.19.so
    3fff99a60000-3fff99a90000 r-xp 00000000 08:02 129813 /bin/dash
    3fff99a90000-3fff99aa0000 rw-p 00020000 08:02 129813 /bin/dash
    3fffc3de0000-3fffc3e10000 rw-p 00000000 00:00 0      [stack]
    3fffc55e0000-3fffc5610000 rw-p 00000000 00:00 0      [heap]

Although this should be OK, it's possible it might break badly written
binaries that make assumptions about the address space layout.

Signed-off-by: Vineeth Vijayan <vvijayan@mvista.com>
[mpe: Rewrite changelog]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/Kconfig           | 1 +
 arch/powerpc/include/asm/elf.h | 3 +--
 arch/powerpc/kernel/process.c  | 9 ---------
 3 files changed, 2 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 46227336aacb..421df5cc6d18 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -88,6 +88,7 @@ config PPC
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select BINFMT_ELF
+	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select OF
 	select OF_EARLY_FLATTREE
 	select OF_RESERVED_MEM
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 888d8f3f2524..57d289acb803 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -28,8 +28,7 @@
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk.  */
 
-extern unsigned long randomize_et_dyn(unsigned long base);
-#define ELF_ET_DYN_BASE		(randomize_et_dyn(0x20000000))
+#define ELF_ET_DYN_BASE	0x20000000
 
 #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index f6b82152e7aa..b4cc7bef6b16 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1654,12 +1654,3 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 	return ret;
 }
 
-unsigned long randomize_et_dyn(unsigned long base)
-{
-	unsigned long ret = PAGE_ALIGN(base + brk_rnd());
-
-	if (ret < base)
-		return base;
-
-	return ret;
-}
-- 
cgit v1.2.3


From 16b1d26e77b142546e2b9b6dc3b5aa5c44ae3b77 Mon Sep 17 00:00:00 2001
From: Neelesh Gupta <neelegup@linux.vnet.ibm.com>
Date: Tue, 14 Oct 2014 14:08:36 +0530
Subject: rtc/tpo: Driver to support rtc and wakeup on PowerNV platform

The patch implements the OPAL rtc driver that binds with the rtc
driver subsystem. The driver uses the platform device infrastructure
to probe the rtc device and register it to rtc class framework. The
'wakeup' is supported depending upon the property 'has-tpo' present
in the OF node. It provides a way to load the generic rtc driver in
in the absence of an OPAL driver.

The patch also moves the existing OPAL rtc get/set time interfaces to the
new driver and exposes the necessary OPAL calls using EXPORT_SYMBOL_GPL.

Test results:
-------------
Host:
[root@tul169p1 ~]# ls -l /sys/class/rtc/
total 0
lrwxrwxrwx 1 root root 0 Oct 14 03:07 rtc0 -> ../../devices/opal-rtc/rtc/rtc0
[root@tul169p1 ~]# cat /sys/devices/opal-rtc/rtc/rtc0/time
08:10:07
[root@tul169p1 ~]# echo `date '+%s' -d '+ 2 minutes'` > /sys/class/rtc/rtc0/wakealarm
[root@tul169p1 ~]# cat /sys/class/rtc/rtc0/wakealarm
1413274345
[root@tul169p1 ~]#

FSP:
$ smgr mfgState
standby
$ rtim timeofday

System time is valid: 2014/10/14 08:12:04.225115

$ smgr mfgState
ipling
$

CC: devicetree@vger.kernel.org
CC: tglx@linutronix.de
CC: rtc-linux@googlegroups.com
CC: a.zummo@towertech.it
Signed-off-by: Neelesh Gupta <neelegup@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 Documentation/devicetree/bindings/rtc/rtc-opal.txt |  16 ++
 arch/powerpc/include/asm/opal.h                    |   7 +-
 arch/powerpc/kernel/time.c                         |   1 +
 arch/powerpc/platforms/powernv/opal-async.c        |   3 +
 arch/powerpc/platforms/powernv/opal-rtc.c          |  65 ++---
 arch/powerpc/platforms/powernv/opal-wrappers.S     |   2 +
 arch/powerpc/platforms/powernv/opal.c              |   6 +
 arch/powerpc/platforms/powernv/setup.c             |   2 -
 drivers/rtc/Kconfig                                |  11 +
 drivers/rtc/Makefile                               |   1 +
 drivers/rtc/rtc-opal.c                             | 261 +++++++++++++++++++++
 11 files changed, 325 insertions(+), 50 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/rtc/rtc-opal.txt
 create mode 100644 drivers/rtc/rtc-opal.c

(limited to 'arch/powerpc/kernel')

diff --git a/Documentation/devicetree/bindings/rtc/rtc-opal.txt b/Documentation/devicetree/bindings/rtc/rtc-opal.txt
new file mode 100644
index 000000000000..af87e5ecac54
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/rtc-opal.txt
@@ -0,0 +1,16 @@
+IBM OPAL real-time clock
+------------------------
+
+Required properties:
+- comapatible: Should be "ibm,opal-rtc"
+
+Optional properties:
+- has-tpo: Decides if the wakeup is supported or not.
+
+Example:
+	rtc {
+		compatible = "ibm,opal-rtc";
+		has-tpo;
+		phandle = <0x10000029>;
+		linux,phandle = <0x10000029>;
+	};
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 5d073e50cac8..60250e2d1f0d 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -154,6 +154,8 @@ struct opal_sg_list {
 #define OPAL_HANDLE_HMI				98
 #define OPAL_REGISTER_DUMP_REGION		101
 #define OPAL_UNREGISTER_DUMP_REGION		102
+#define OPAL_WRITE_TPO				103
+#define OPAL_READ_TPO				104
 #define OPAL_IPMI_SEND				107
 #define OPAL_IPMI_RECV				108
 
@@ -832,6 +834,9 @@ int64_t opal_rtc_read(__be32 *year_month_day,
 		      __be64 *hour_minute_second_millisecond);
 int64_t opal_rtc_write(uint32_t year_month_day,
 		       uint64_t hour_minute_second_millisecond);
+int64_t opal_tpo_read(uint64_t token, __be32 *year_mon_day, __be32 *hour_min);
+int64_t opal_tpo_write(uint64_t token, uint32_t year_mon_day,
+		       uint32_t hour_min);
 int64_t opal_cec_power_down(uint64_t request);
 int64_t opal_cec_reboot(void);
 int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
@@ -1009,8 +1014,6 @@ extern int opal_async_wait_response(uint64_t token, struct opal_msg *msg);
 extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data);
 
 struct rtc_time;
-extern int opal_set_rtc_time(struct rtc_time *tm);
-extern void opal_get_rtc_time(struct rtc_time *tm);
 extern unsigned long opal_get_boot_time(void);
 extern void opal_nvram_init(void);
 extern void opal_flash_init(void);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 9f8ea617ff2c..fa7c4f12104f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -989,6 +989,7 @@ void GregorianDay(struct rtc_time * tm)
 
 	tm->tm_wday = day % 7;
 }
+EXPORT_SYMBOL_GPL(GregorianDay);
 
 void to_tm(int tim, struct rtc_time * tm)
 {
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index e462ab947d16..693b6cdac691 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -71,6 +71,7 @@ int opal_async_get_token_interruptible(void)
 
 	return token;
 }
+EXPORT_SYMBOL_GPL(opal_async_get_token_interruptible);
 
 int __opal_async_release_token(int token)
 {
@@ -102,6 +103,7 @@ int opal_async_release_token(int token)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opal_async_release_token);
 
 int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
 {
@@ -120,6 +122,7 @@ int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(opal_async_wait_response);
 
 static int opal_async_comp_event(struct notifier_block *nb,
 		unsigned long msg_type, void *msg)
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index 499707ddaa9c..37dbee15769f 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -15,6 +15,8 @@
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 #include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/of_platform.h>
 
 #include <asm/opal.h>
 #include <asm/firmware.h>
@@ -43,7 +45,7 @@ unsigned long __init opal_get_boot_time(void)
 	long rc = OPAL_BUSY;
 
 	if (!opal_check_token(OPAL_RTC_READ))
-		goto out;
+		return 0;
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
@@ -53,62 +55,33 @@ unsigned long __init opal_get_boot_time(void)
 			mdelay(10);
 	}
 	if (rc != OPAL_SUCCESS)
-		goto out;
+		return 0;
 
 	y_m_d = be32_to_cpu(__y_m_d);
 	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, &tm);
 	return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
 		      tm.tm_hour, tm.tm_min, tm.tm_sec);
-out:
-	ppc_md.get_rtc_time = NULL;
-	ppc_md.set_rtc_time = NULL;
-	return 0;
 }
 
-void opal_get_rtc_time(struct rtc_time *tm)
+static __init int opal_time_init(void)
 {
-	long rc = OPAL_BUSY;
-	u32 y_m_d;
-	u64 h_m_s_ms;
-	__be32 __y_m_d;
-	__be64 __h_m_s_ms;
+	struct platform_device *pdev;
+	struct device_node *rtc;
 
-	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
-			opal_poll_events(NULL);
+	rtc = of_find_node_by_path("/ibm,opal/rtc");
+	if (rtc) {
+		pdev = of_platform_device_create(rtc, "opal-rtc", NULL);
+		of_node_put(rtc);
+	} else {
+		if (opal_check_token(OPAL_RTC_READ) ||
+		    opal_check_token(OPAL_READ_TPO))
+			pdev = platform_device_register_simple("opal-rtc", -1,
+							       NULL, 0);
 		else
-			mdelay(10);
+			return -ENODEV;
 	}
-	if (rc != OPAL_SUCCESS)
-		return;
-	y_m_d = be32_to_cpu(__y_m_d);
-	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
-	opal_to_tm(y_m_d, h_m_s_ms, tm);
-}
-
-int opal_set_rtc_time(struct rtc_time *tm)
-{
-	long rc = OPAL_BUSY;
-	u32 y_m_d = 0;
-	u64 h_m_s_ms = 0;
-
-	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
-	y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
-	y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
-	y_m_d |= ((u32)bin2bcd(tm->tm_mday));
-
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
-	h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
 
-	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_rtc_write(y_m_d, h_m_s_ms);
-		if (rc == OPAL_BUSY_EVENT)
-			opal_poll_events(NULL);
-		else
-			mdelay(10);
-	}
-	return rc == OPAL_SUCCESS ? 0 : -EIO;
+	return PTR_ERR_OR_ZERO(pdev);
 }
+machine_subsys_initcall(powernv, opal_time_init);
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 59978af9babe..0a299be588af 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -250,5 +250,7 @@ OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
 OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
+OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
+OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
 OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
 OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 0297702e8ae9..a1c37f9d60d2 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -819,3 +819,9 @@ void opal_free_sg_list(struct opal_sg_list *sg)
 			sg = NULL;
 	}
 }
+
+EXPORT_SYMBOL_GPL(opal_poll_events);
+EXPORT_SYMBOL_GPL(opal_rtc_read);
+EXPORT_SYMBOL_GPL(opal_rtc_write);
+EXPORT_SYMBOL_GPL(opal_tpo_read);
+EXPORT_SYMBOL_GPL(opal_tpo_write);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 941831d67cb2..30b1c3e298a6 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -265,8 +265,6 @@ static unsigned long pnv_memory_block_size(void)
 static void __init pnv_setup_machdep_opal(void)
 {
 	ppc_md.get_boot_time = opal_get_boot_time;
-	ppc_md.get_rtc_time = opal_get_rtc_time;
-	ppc_md.set_rtc_time = opal_set_rtc_time;
 	ppc_md.restart = pnv_restart;
 	pm_power_off = pnv_power_off;
 	ppc_md.halt = pnv_halt;
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 6dd12ddbabc6..c8f0ec7464ce 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -979,6 +979,17 @@ config RTC_DRV_NUC900
 	  If you say yes here you get support for the RTC subsystem of the
 	  NUC910/NUC920 used in embedded systems.
 
+config RTC_DRV_OPAL
+	tristate "IBM OPAL RTC driver"
+	depends on PPC_POWERNV
+	default y
+	help
+	  If you say yes here you get support for the PowerNV platform RTC
+	  driver based on OPAL interfaces.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-opal.
+
 comment "on-CPU RTC drivers"
 
 config RTC_DRV_DAVINCI
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index b188323c096a..c8ef3e1e6ccd 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -92,6 +92,7 @@ obj-$(CONFIG_RTC_DRV_MSM6242)	+= rtc-msm6242.o
 obj-$(CONFIG_RTC_DRV_MPC5121)	+= rtc-mpc5121.o
 obj-$(CONFIG_RTC_DRV_MV)	+= rtc-mv.o
 obj-$(CONFIG_RTC_DRV_NUC900)	+= rtc-nuc900.o
+obj-$(CONFIG_RTC_DRV_OPAL)	+= rtc-opal.o
 obj-$(CONFIG_RTC_DRV_OMAP)	+= rtc-omap.o
 obj-$(CONFIG_RTC_DRV_PALMAS)	+= rtc-palmas.o
 obj-$(CONFIG_RTC_DRV_PCAP)	+= rtc-pcap.o
diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c
new file mode 100644
index 000000000000..95f652165fe9
--- /dev/null
+++ b/drivers/rtc/rtc-opal.c
@@ -0,0 +1,261 @@
+/*
+ * IBM OPAL RTC driver
+ * Copyright (C) 2014 IBM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ */
+
+#define DRVNAME		"rtc-opal"
+#define pr_fmt(fmt)	DRVNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+#include <linux/bcd.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
+{
+	tm->tm_year = ((bcd2bin(y_m_d >> 24) * 100) +
+		       bcd2bin((y_m_d >> 16) & 0xff)) - 1900;
+	tm->tm_mon  = bcd2bin((y_m_d >> 8) & 0xff) - 1;
+	tm->tm_mday = bcd2bin(y_m_d & 0xff);
+	tm->tm_hour = bcd2bin((h_m_s_ms >> 56) & 0xff);
+	tm->tm_min  = bcd2bin((h_m_s_ms >> 48) & 0xff);
+	tm->tm_sec  = bcd2bin((h_m_s_ms >> 40) & 0xff);
+
+	GregorianDay(tm);
+}
+
+static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms)
+{
+	*y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
+	*y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
+	*y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
+	*y_m_d |= ((u32)bin2bcd(tm->tm_mday));
+
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
+}
+
+static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d;
+	u64 h_m_s_ms;
+	__be32 __y_m_d;
+	__be64 __h_m_s_ms;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			msleep(10);
+	}
+
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
+	opal_to_tm(y_m_d, h_m_s_ms, tm);
+
+	return 0;
+}
+
+static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+	long rc = OPAL_BUSY;
+	u32 y_m_d = 0;
+	u64 h_m_s_ms = 0;
+
+	tm_to_opal(tm, &y_m_d, &h_m_s_ms);
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_write(y_m_d, h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT)
+			opal_poll_events(NULL);
+		else
+			msleep(10);
+	}
+
+	return rc == OPAL_SUCCESS ? 0 : -EIO;
+}
+
+/*
+ * TPO	Timed Power-On
+ *
+ * TPO get/set OPAL calls care about the hour and min and to make it consistent
+ * with the rtc utility time conversion functions, we use the 'u64' to store
+ * its value and perform bit shift by 32 before use..
+ */
+static int opal_get_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	__be32 __y_m_d, __h_m;
+	struct opal_msg msg;
+	int rc, token;
+	u64 h_m_s_ms;
+	u32 y_m_d;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			pr_err("Failed to get the async token\n");
+
+		return token;
+	}
+
+	rc = opal_tpo_read(token, &__y_m_d, &__h_m);
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	if (rc) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = be64_to_cpu(msg.params[1]);
+	if (rc != OPAL_SUCCESS) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = ((u64)be32_to_cpu(__h_m) << 32);
+	opal_to_tm(y_m_d, h_m_s_ms, &alarm->time);
+
+exit:
+	opal_async_release_token(token);
+	return rc;
+}
+
+/* Set Timed Power-On */
+static int opal_set_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	u64 h_m_s_ms = 0, token;
+	struct opal_msg msg;
+	u32 y_m_d = 0;
+	int rc;
+
+	tm_to_opal(&alarm->time, &y_m_d, &h_m_s_ms);
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			pr_err("Failed to get the async token\n");
+
+		return token;
+	}
+
+	/* TPO, we care about hour and minute */
+	rc = opal_tpo_write(token, y_m_d,
+			    (u32)((h_m_s_ms >> 32) & 0xffff0000));
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	if (rc) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = be64_to_cpu(msg.params[1]);
+	if (rc != OPAL_SUCCESS)
+		rc = -EIO;
+
+exit:
+	opal_async_release_token(token);
+	return rc;
+}
+
+static const struct rtc_class_ops opal_rtc_ops = {
+	.read_time	= opal_get_rtc_time,
+	.set_time	= opal_set_rtc_time,
+	.read_alarm	= opal_get_tpo_time,
+	.set_alarm	= opal_set_tpo_time,
+};
+
+static int opal_rtc_probe(struct platform_device *pdev)
+{
+	struct rtc_device *rtc;
+
+	if (pdev->dev.of_node && of_get_property(pdev->dev.of_node, "has-tpo",
+						 NULL))
+		device_set_wakeup_capable(&pdev->dev, true);
+
+	rtc = devm_rtc_device_register(&pdev->dev, DRVNAME, &opal_rtc_ops,
+				       THIS_MODULE);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	rtc->uie_unsupported = 1;
+
+	return 0;
+}
+
+static const struct of_device_id opal_rtc_match[] = {
+	{
+		.compatible	= "ibm,opal-rtc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, opal_rtc_match);
+
+static const struct platform_device_id opal_rtc_driver_ids[] = {
+	{
+		.name		= "opal-rtc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, opal_rtc_driver_ids);
+
+static struct platform_driver opal_rtc_driver = {
+	.probe		= opal_rtc_probe,
+	.id_table	= opal_rtc_driver_ids,
+	.driver		= {
+		.name		= DRVNAME,
+		.owner		= THIS_MODULE,
+		.of_match_table	= opal_rtc_match,
+	},
+};
+
+static int __init opal_rtc_init(void)
+{
+	if (!firmware_has_feature(FW_FEATURE_OPAL))
+		return -ENODEV;
+
+	return platform_driver_register(&opal_rtc_driver);
+}
+
+static void __exit opal_rtc_exit(void)
+{
+	platform_driver_unregister(&opal_rtc_driver);
+}
+
+MODULE_AUTHOR("Neelesh Gupta <neelegup@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("IBM OPAL RTC driver");
+MODULE_LICENSE("GPL");
+
+module_init(opal_rtc_init);
+module_exit(opal_rtc_exit);
-- 
cgit v1.2.3


From e39f223fc93580c86ccf6b3422033e349f57f0dd Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 18 Nov 2014 16:47:35 +1100
Subject: powerpc: Remove more traces of bootmem

Although we are now selecting NO_BOOTMEM, we still have some traces of
bootmem lying around. That is because even with NO_BOOTMEM there is
still a shim that converts bootmem calls into memblock calls, but
ultimately we want to remove all traces of bootmem.

Most of the patch is conversions from alloc_bootmem() to
memblock_virt_alloc(). In general a call such as:

  p = (struct foo *)alloc_bootmem(x);

Becomes:

  p = memblock_virt_alloc(x, 0);

We don't need the cast because memblock_virt_alloc() returns a void *.
The alignment value of zero tells memblock to use the default alignment,
which is SMP_CACHE_BYTES, the same value alloc_bootmem() uses.

We remove a number of NULL checks on the result of
memblock_virt_alloc(). That is because memblock_virt_alloc() will panic
if it can't allocate, in exactly the same way as alloc_bootmem(), so the
NULL checks are and always have been redundant.

The memory returned by memblock_virt_alloc() is already zeroed, so we
remove several memsets of the result of memblock_virt_alloc().

Finally we convert a few uses of __alloc_bootmem(x, y, MAX_DMA_ADDRESS)
to just plain memblock_virt_alloc(). We don't use memblock_alloc_base()
because MAX_DMA_ADDRESS is ~0ul on powerpc, so limiting the allocation
to that is pointless, 16XB ought to be enough for anyone.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c            |  1 -
 arch/powerpc/kernel/pci_32.c                |  4 +---
 arch/powerpc/kernel/setup_64.c              |  2 +-
 arch/powerpc/lib/alloc.c                    |  4 +---
 arch/powerpc/mm/hugetlbpage.c               |  2 +-
 arch/powerpc/mm/mmu_context_nohash.c        |  8 ++++----
 arch/powerpc/platforms/cell/celleb_pci.c    |  6 +++---
 arch/powerpc/platforms/powermac/nvram.c     |  6 +-----
 arch/powerpc/platforms/powernv/pci-ioda.c   | 12 +++---------
 arch/powerpc/platforms/powernv/pci-p5ioc2.c | 16 ++++------------
 arch/powerpc/platforms/ps3/setup.c          |  7 +------
 arch/powerpc/sysdev/fsl_pci.c               |  1 -
 12 files changed, 20 insertions(+), 49 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index bc2dab52a991..37d512d35943 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -20,7 +20,6 @@
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/of_address.h>
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 432459c817fa..1f7930037cb7 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -199,9 +199,7 @@ pci_create_OF_bus_map(void)
 	struct property* of_prop;
 	struct device_node *dn;
 
-	of_prop = (struct property*) alloc_bootmem(sizeof(struct property) + 256);
-	if (!of_prop)
-		return;
+	of_prop = memblock_virt_alloc(sizeof(struct property) + 256, 0);
 	dn = of_find_node_by_path("/");
 	if (dn) {
 		memset(of_prop, -1, sizeof(struct property) + 256);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 6e5310ddf8c7..49f553bbb360 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -660,7 +660,7 @@ static void __init emergency_stack_init(void)
 }
 
 /*
- * Called into from start_kernel this initializes bootmem, which is used
+ * Called into from start_kernel this initializes memblock, which is used
  * to manage page allocation until mem_init is called.
  */
 void __init setup_arch(char **cmdline_p)
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index da22c84a8fed..4a6c2cf890d9 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -13,9 +13,7 @@ void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask)
 	if (mem_init_done)
 		p = kzalloc(size, mask);
 	else {
-		p = alloc_bootmem(size);
-		if (p)
-			memset(p, 0, size);
+		p = memblock_virt_alloc(size, 0);
 	}
 	return p;
 }
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index af56de82375d..8c9b8115867c 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -315,7 +315,7 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 	 * If gpages can be in highmem we can't use the trick of storing the
 	 * data structure in the page; allocate space for this
 	 */
-	m = alloc_bootmem(sizeof(struct huge_bootmem_page));
+	m = memblock_virt_alloc(sizeof(struct huge_bootmem_page), 0);
 	m->phys = gpage_freearray[idx].gpage_list[--nr_gpages];
 #else
 	m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]);
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 928ebe79668b..9cba6cba2e50 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -421,12 +421,12 @@ void __init mmu_context_init(void)
 	/*
 	 * Allocate the maps used by context management
 	 */
-	context_map = alloc_bootmem(CTX_MAP_SIZE);
-	context_mm = alloc_bootmem(sizeof(void *) * (last_context + 1));
+	context_map = memblock_virt_alloc(CTX_MAP_SIZE, 0);
+	context_mm = memblock_virt_alloc(sizeof(void *) * (last_context + 1), 0);
 #ifndef CONFIG_SMP
-	stale_map[0] = alloc_bootmem(CTX_MAP_SIZE);
+	stale_map[0] = memblock_virt_alloc(CTX_MAP_SIZE, 0);
 #else
-	stale_map[boot_cpuid] = alloc_bootmem(CTX_MAP_SIZE);
+	stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0);
 
 	register_cpu_notifier(&mmu_context_cpu_nb);
 #endif
diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c
index 2b98a36ef8fb..3ce70ded2d6a 100644
--- a/arch/powerpc/platforms/cell/celleb_pci.c
+++ b/arch/powerpc/platforms/cell/celleb_pci.c
@@ -29,7 +29,7 @@
 #include <linux/pci.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/pci_regs.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -401,11 +401,11 @@ error:
 	} else {
 		if (config && *config) {
 			size = 256;
-			free_bootmem(__pa(*config), size);
+			memblock_free(__pa(*config), size);
 		}
 		if (res && *res) {
 			size = sizeof(struct celleb_pci_resource);
-			free_bootmem(__pa(*res), size);
+			memblock_free(__pa(*res), size);
 		}
 	}
 
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index 014d06e6d46b..60b03a1703d1 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -513,11 +513,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr)
 		printk(KERN_ERR "nvram: no address\n");
 		return -EINVAL;
 	}
-	nvram_image = alloc_bootmem(NVRAM_SIZE);
-	if (nvram_image == NULL) {
-		printk(KERN_ERR "nvram: can't allocate ram image\n");
-		return -ENOMEM;
-	}
+	nvram_image = memblock_virt_alloc(NVRAM_SIZE, 0);
 	nvram_data = ioremap(addr, NVRAM_SIZE*2);
 	nvram_naddrs = 1; /* Make sure we get the correct case */
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index d03503515692..cc861c14840d 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1940,19 +1940,14 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb_id = be64_to_cpup(prop64);
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
-	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (!phb) {
-		pr_err("  Out of memory !\n");
-		return;
-	}
+	phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0);
 
 	/* Allocate PCI controller */
-	memset(phb, 0, sizeof(struct pnv_phb));
 	phb->hose = hose = pcibios_alloc_controller(np);
 	if (!phb->hose) {
 		pr_err("  Can't allocate PCI controller for %s\n",
 		       np->full_name);
-		free_bootmem((unsigned long)phb, sizeof(struct pnv_phb));
+		memblock_free(__pa(phb), sizeof(struct pnv_phb));
 		return;
 	}
 
@@ -2019,8 +2014,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	}
 	pemap_off = size;
 	size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
-	aux = alloc_bootmem(size);
-	memset(aux, 0, size);
+	aux = memblock_virt_alloc(size, 0);
 	phb->ioda.pe_alloc = aux;
 	phb->ioda.m32_segmap = aux + m32map_off;
 	if (phb->type == PNV_PHB_IODA1)
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 3336fcbdd08a..6ef6d4d8e7e2 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -122,12 +122,9 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 		return;
 	}
 
-	phb = alloc_bootmem(sizeof(struct pnv_phb));
-	if (phb) {
-		memset(phb, 0, sizeof(struct pnv_phb));
-		phb->hose = pcibios_alloc_controller(np);
-	}
-	if (!phb || !phb->hose) {
+	phb = memblock_virt_alloc(sizeof(struct pnv_phb), 0);
+	phb->hose = pcibios_alloc_controller(np);
+	if (!phb->hose) {
 		pr_err("  Failed to allocate PCI controller\n");
 		return;
 	}
@@ -216,12 +213,7 @@ void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
 	 *
 	 * XXX TODO: Make it chip local if possible
 	 */
-	tce_mem = __alloc_bootmem(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY,
-				  __pa(MAX_DMA_ADDRESS));
-	if (!tce_mem) {
-		pr_err(" Failed to allocate TCE Memory !\n");
-		return;
-	}
+	tce_mem = memblock_virt_alloc(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY);
 	pr_debug(" TCE    : 0x%016lx..0x%016lx\n",
 		__pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1);
 	rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem),
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 009a2004b876..799c8580ab09 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -125,12 +125,7 @@ static void __init prealloc(struct ps3_prealloc *p)
 	if (!p->size)
 		return;
 
-	p->address = __alloc_bootmem(p->size, p->align, __pa(MAX_DMA_ADDRESS));
-	if (!p->address) {
-		printk(KERN_ERR "%s: Cannot allocate %s\n", __func__,
-		       p->name);
-		return;
-	}
+	p->address = memblock_virt_alloc(p->size, p->align);
 
 	printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size,
 	       p->address);
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index d8484d7cffaa..6455c1eada1a 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -23,7 +23,6 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
-- 
cgit v1.2.3


From b85743ee95f3593ded82bca55cd3c38090ad001f Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Fri, 14 Nov 2014 10:47:28 +1100
Subject: powerpc/eeh: Refactor eeh_reset_pe()

The patch refactors eeh_reset_pe() in order for:

   * Varied return values for different failure cases.
   * Replace pr_err() with pr_warn() and print function name.
   * Coding style cleanup.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 2248a1999c64..967e4a08d824 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -758,30 +758,37 @@ static void eeh_reset_pe_once(struct eeh_pe *pe)
 int eeh_reset_pe(struct eeh_pe *pe)
 {
 	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
-	int i, rc;
+	int i, state, ret;
 
 	/* Take three shots at resetting the bus */
-	for (i=0; i<3; i++) {
+	for (i = 0; i < 3; i++) {
 		eeh_reset_pe_once(pe);
 
 		/*
 		 * EEH_PE_ISOLATED is expected to be removed after
 		 * BAR restore.
 		 */
-		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if ((rc & flags) == flags)
-			return 0;
+		state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+		if ((state & flags) == flags) {
+			ret = 0;
+			goto out;
+		}
 
-		if (rc < 0) {
-			pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+		if (state < 0) {
+			pr_warn("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
 				__func__, pe->phb->global_number, pe->addr);
-			return -1;
+			ret = -ENOTRECOVERABLE;
+			goto out;
 		}
-		pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n",
-			i+1, pe->phb->global_number, pe->addr, rc);
+
+		/* We might run out of credits */
+		ret = -EIO;
+		pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n",
+			__func__, state, pe->phb->global_number, pe->addr, (i + 1));
 	}
 
-	return -1;
+out:
+	return ret;
 }
 
 /**
-- 
cgit v1.2.3


From 28bf36f92afc6b22ba50ceaf36ba89afa9f5c1e8 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Fri, 14 Nov 2014 10:47:29 +1100
Subject: powerpc/eeh: Set EEH_PE_RESET on PE reset

The patch introduces additional flag EEH_PE_RESET to indicate the
corresponding PE is under reset. In turn, the PE retrieval bakcend
on PowerNV platform can return unfrozen state for the EEH core to
moving forward. Flag EEH_PE_CFG_BLOCKED isn't the correct one for
the purpose.

In PCI passthrou case, the problem is more worse: Guest doesn't
recover 6th EEH error. The PE is left in isolated (frozen) and
config blocked state on Broadcom adapters. We can't retrieve the
PE's state correctly any more, even from the host side via sysfs
/sys/bus/pci/devices/xxx/eeh_pe_state.

Reported-by: Rajeshkumar Subramanian <rajeshkumars@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h            |  1 +
 arch/powerpc/kernel/eeh.c                 |  4 ++++
 arch/powerpc/kernel/eeh_driver.c          | 10 ++--------
 arch/powerpc/platforms/powernv/eeh-ioda.c |  2 +-
 4 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index ca07f9c27335..2e633b41712a 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -72,6 +72,7 @@ struct device_node;
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
 #define EEH_PE_CFG_BLOCKED	(1 << 2)	/* Block config access	*/
+#define EEH_PE_RESET		(1 << 3)	/* PE reset in progress */
 
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 #define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 967e4a08d824..b372bfdbfb3a 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -760,6 +760,9 @@ int eeh_reset_pe(struct eeh_pe *pe)
 	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	int i, state, ret;
 
+	/* Mark as reset and block config space */
+	eeh_pe_state_mark(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+
 	/* Take three shots at resetting the bus */
 	for (i = 0; i < 3; i++) {
 		eeh_reset_pe_once(pe);
@@ -788,6 +791,7 @@ int eeh_reset_pe(struct eeh_pe *pe)
 	}
 
 out:
+	eeh_pe_state_clear(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
 	return ret;
 }
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 6535936bdf27..b17e793ba67e 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -528,13 +528,11 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
 
 	/* Issue reset */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	ret = eeh_reset_pe(pe);
 	if (ret) {
-		eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_CFG_BLOCKED);
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		return ret;
 	}
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Unfreeze the PE */
 	ret = eeh_clear_pe_frozen_state(pe, true);
@@ -601,19 +599,15 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * config accesses. So we prefer to block them. However, controlled
 	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	rc = eeh_reset_pe(pe);
-	if (rc) {
-		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+	if (rc)
 		return rc;
-	}
 
 	pci_lock_rescan_remove();
 
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index db3803e21483..fb38fe4dba89 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -372,7 +372,7 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 	 * moving forward, we have to return operational
 	 * state during PE reset.
 	 */
-	if (pe->state & EEH_PE_CFG_BLOCKED) {
+	if (pe->state & EEH_PE_RESET) {
 		result = (EEH_STATE_MMIO_ACTIVE  |
 			  EEH_STATE_DMA_ACTIVE   |
 			  EEH_STATE_MMIO_ENABLED |
-- 
cgit v1.2.3


From b1d76a7d57762332cd8e0c020470d43c5ad3948e Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Fri, 14 Nov 2014 10:47:30 +1100
Subject: powerpc/eeh: Recover EEH error on ownership change for BCM5719

In PCI passthrou scenario, we need simulate EEH recovery for Emulex
adapters when their ownership changes, as we did in commit 5cfb20b96
("powerpc/eeh: Emulate EEH recovery for VFIO devices"). Broadcom
BCM5719 adpaters are facing same problem and needs same cure.

Reported-by: Rajeshkumar Subramanian <rajeshkumars@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index b372bfdbfb3a..f1c6b115cb37 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1220,6 +1220,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state)
 static struct pci_device_id eeh_reset_ids[] = {
 	{ PCI_DEVICE(0x19a2, 0x0710) },	/* Emulex, BE     */
 	{ PCI_DEVICE(0x10df, 0xe220) },	/* Emulex, Lancer */
+	{ PCI_DEVICE(0x14e4, 0x1657) }, /* Broadcom BCM5719 */
 	{ 0 }
 };
 
-- 
cgit v1.2.3


From a450e8f55a57d049ac3afe218f06567e12d6b4f5 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Sat, 22 Nov 2014 21:58:09 +1100
Subject: powerpc/eeh: Dump PHB diag-data early

On PowerNV platform, PHB diag-data is dumped after stopping device
drivers. In case of recursive EEH errors, the kernel is usually
crashed before dumping PHB diag-data for the second EEH error. It's
hard to locate the root cause of the second EEH error without PHB
diag-data.

The patch adds one more EEH option "eeh=early_log", which helps
dumping PHB diag-data immediately once frozen PE is detected, in
order to get the PHB diag-data for the second EEH error.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h            |  1 +
 arch/powerpc/kernel/eeh.c                 |  2 ++
 arch/powerpc/platforms/powernv/eeh-ioda.c | 13 ++++++++++++-
 3 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 2e633b41712a..0652ebe117af 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -39,6 +39,7 @@ struct device_node;
 #define EEH_PROBE_MODE_DEV	0x04	/* From PCI device	*/
 #define EEH_PROBE_MODE_DEVTREE	0x08	/* From device tree	*/
 #define EEH_ENABLE_IO_FOR_LOG	0x10	/* Enable IO for log	*/
+#define EEH_EARLY_DUMP_LOG	0x20	/* Dump log immediately	*/
 
 /*
  * Delay for PE reset, all in ms
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index f1c6b115cb37..05be77d9ea0e 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -143,6 +143,8 @@ static int __init eeh_setup(char *str)
 {
 	if (!strcmp(str, "off"))
 		eeh_add_flag(EEH_FORCE_DISABLED);
+	else if (!strcmp(str, "early_log"))
+		eeh_add_flag(EEH_EARLY_DUMP_LOG);
 
 	return 1;
 }
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index fb38fe4dba89..2809c9895288 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -353,6 +353,9 @@ static int ioda_eeh_get_phb_state(struct eeh_pe *pe)
 	} else if (!(pe->state & EEH_PE_ISOLATED)) {
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
@@ -451,6 +454,9 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
@@ -730,7 +736,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
 			    char *drv_log, unsigned long len)
 {
-	pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+	if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
+		pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
 	return 0;
 }
@@ -1086,6 +1093,10 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		    !((*pe)->state & EEH_PE_ISOLATED)) {
 			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
 			ioda_eeh_phb_diag(*pe);
+
+			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+				pnv_pci_dump_phb_diag_data((*pe)->phb,
+							   (*pe)->data);
 		}
 
 		/*
-- 
cgit v1.2.3


From 6d626c5ea3d8411cc2a72d7cabe70f01dfc32d1d Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Mon, 24 Nov 2014 21:59:26 +0530
Subject: powerpc/powernv: Cleanup unused MCE definitions/declarations.

Cleanup OpalMCE_* definitions/declarations and other related code which
is not used anymore.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Benjamin Herrrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/opal.h       | 104 ----------------------------------
 arch/powerpc/include/asm/paca.h       |   7 ---
 arch/powerpc/kernel/asm-offsets.c     |   7 ---
 arch/powerpc/kernel/exceptions-64s.S  |  17 ------
 arch/powerpc/platforms/powernv/opal.c |   1 -
 5 files changed, 136 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 60250e2d1f0d..5cd8d2fddba9 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -288,62 +288,6 @@ enum OpalMessageType {
 	OPAL_MSG_TYPE_MAX,
 };
 
-/* Machine check related definitions */
-enum OpalMCE_Version {
-	OpalMCE_V1 = 1,
-};
-
-enum OpalMCE_Severity {
-	OpalMCE_SEV_NO_ERROR = 0,
-	OpalMCE_SEV_WARNING = 1,
-	OpalMCE_SEV_ERROR_SYNC = 2,
-	OpalMCE_SEV_FATAL = 3,
-};
-
-enum OpalMCE_Disposition {
-	OpalMCE_DISPOSITION_RECOVERED = 0,
-	OpalMCE_DISPOSITION_NOT_RECOVERED = 1,
-};
-
-enum OpalMCE_Initiator {
-	OpalMCE_INITIATOR_UNKNOWN = 0,
-	OpalMCE_INITIATOR_CPU = 1,
-};
-
-enum OpalMCE_ErrorType {
-	OpalMCE_ERROR_TYPE_UNKNOWN = 0,
-	OpalMCE_ERROR_TYPE_UE = 1,
-	OpalMCE_ERROR_TYPE_SLB = 2,
-	OpalMCE_ERROR_TYPE_ERAT = 3,
-	OpalMCE_ERROR_TYPE_TLB = 4,
-};
-
-enum OpalMCE_UeErrorType {
-	OpalMCE_UE_ERROR_INDETERMINATE = 0,
-	OpalMCE_UE_ERROR_IFETCH = 1,
-	OpalMCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
-	OpalMCE_UE_ERROR_LOAD_STORE = 3,
-	OpalMCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4,
-};
-
-enum OpalMCE_SlbErrorType {
-	OpalMCE_SLB_ERROR_INDETERMINATE = 0,
-	OpalMCE_SLB_ERROR_PARITY = 1,
-	OpalMCE_SLB_ERROR_MULTIHIT = 2,
-};
-
-enum OpalMCE_EratErrorType {
-	OpalMCE_ERAT_ERROR_INDETERMINATE = 0,
-	OpalMCE_ERAT_ERROR_PARITY = 1,
-	OpalMCE_ERAT_ERROR_MULTIHIT = 2,
-};
-
-enum OpalMCE_TlbErrorType {
-	OpalMCE_TLB_ERROR_INDETERMINATE = 0,
-	OpalMCE_TLB_ERROR_PARITY = 1,
-	OpalMCE_TLB_ERROR_MULTIHIT = 2,
-};
-
 enum OpalThreadStatus {
 	OPAL_THREAD_INACTIVE = 0x0,
 	OPAL_THREAD_STARTED = 0x1,
@@ -467,54 +411,6 @@ struct opal_ipmi_msg {
 	uint8_t		data[];
 };
 
-struct opal_machine_check_event {
-	enum OpalMCE_Version	version:8;	/* 0x00 */
-	uint8_t			in_use;		/* 0x01 */
-	enum OpalMCE_Severity	severity:8;	/* 0x02 */
-	enum OpalMCE_Initiator	initiator:8;	/* 0x03 */
-	enum OpalMCE_ErrorType	error_type:8;	/* 0x04 */
-	enum OpalMCE_Disposition disposition:8; /* 0x05 */
-	uint8_t			reserved_1[2];	/* 0x06 */
-	uint64_t		gpr3;		/* 0x08 */
-	uint64_t		srr0;		/* 0x10 */
-	uint64_t		srr1;		/* 0x18 */
-	union {					/* 0x20 */
-		struct {
-			enum OpalMCE_UeErrorType ue_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		physical_address_provided;
-			uint8_t		reserved_1[5];
-			uint64_t	effective_address;
-			uint64_t	physical_address;
-			uint8_t		reserved_2[8];
-		} ue_error;
-
-		struct {
-			enum OpalMCE_SlbErrorType slb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} slb_error;
-
-		struct {
-			enum OpalMCE_EratErrorType erat_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} erat_error;
-
-		struct {
-			enum OpalMCE_TlbErrorType tlb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} tlb_error;
-	} u;
-};
-
 /* FSP memory errors handling */
 enum OpalMemErr_Version {
 	OpalMemErr_V1 = 1,
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index a5139ea6910b..24a386cbb928 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -42,7 +42,6 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
-struct opal_machine_check_event;
 
 /*
  * Defines the layout of the paca.
@@ -153,12 +152,6 @@ struct paca_struct {
 	u64 tm_scratch;                 /* TM scratch area for reclaim */
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	/* Pointer to OPAL machine check event structure set by the
-	 * early exception handler for use by high level C handler
-	 */
-	struct opal_machine_check_event *opal_mc_evt;
-#endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Exclusive emergency stack pointer for machine check exception. */
 	void *mc_emergency_sp;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 9d7dede2847c..c161ef3f28a1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -726,12 +726,5 @@ int main(void)
 					arch.timing_last_enter.tv32.tbl));
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3));
-	DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0));
-	DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1));
-	DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt));
-#endif
-
 	return 0;
 }
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a1d45c161e24..ad62f4d6ce31 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1312,23 +1312,6 @@ hmi_exception_after_realmode:
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	hmi_exception_hv
 
-#ifdef CONFIG_PPC_POWERNV
-_GLOBAL(opal_mc_secondary_handler)
-	HMT_MEDIUM_PPR_DISCARD
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	clrldi	r3,r3,2
-	tovirt(r3,r3)
-	std	r3,PACA_OPAL_MC_EVT(r13)
-	ld	r13,OPAL_MC_SRR0(r3)
-	mtspr	SPRN_SRR0,r13
-	ld	r13,OPAL_MC_SRR1(r3)
-	mtspr	SPRN_SRR1,r13
-	ld	r3,OPAL_MC_GPR3(r3)
-	GET_SCRATCH0(r13)
-	b	machine_check_pSeries
-#endif /* CONFIG_PPC_POWERNV */
-
 
 #define MACHINE_CHECK_HANDLER_WINDUP			\
 	/* Clear MSR_RI before setting SRR0 and SRR1. */\
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index a1c37f9d60d2..cb0b6de79cd4 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -50,7 +50,6 @@ static int mc_recoverable_range_len;
 
 struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
-extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
 static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
-- 
cgit v1.2.3


From 221195fb80daa1a0c2fd54a023081c416fe93340 Mon Sep 17 00:00:00 2001
From: Greg Kurz <gkurz@linux.vnet.ibm.com>
Date: Tue, 25 Nov 2014 17:10:06 +0100
Subject: powerpc: Drop useless warning in eeh_init()

This is what we get in dmesg when booting a pseries guest and
the hypervisor doesn't provide EEH support.

[    0.166655] EEH functionality not supported
[    0.166778] eeh_init: Failed to call platform init function (-22)

Since both powernv_eeh_init() and pseries_eeh_init() already complain when
hitting an error, it is not needed to print more (especially such an
uninformative message).

Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 05be77d9ea0e..e1b6d8e17289 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -933,11 +933,8 @@ int eeh_init(void)
 		pr_warn("%s: Platform EEH operation not found\n",
 			__func__);
 		return -EEXIST;
-	} else if ((ret = eeh_ops->init())) {
-		pr_warn("%s: Failed to call platform init function (%d)\n",
-			__func__, ret);
+	} else if ((ret = eeh_ops->init()))
 		return ret;
-	}
 
 	/* Initialize EEH event */
 	ret = eeh_event_init();
-- 
cgit v1.2.3


From aefa5688c070727b8729de1aef85cad7b9933fc7 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Thu, 4 Dec 2014 11:00:14 +0530
Subject: powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault

upatepp can get called for a nohpte fault when we find from the linux
page table that the translation was hashed before. In that case
we are sure that there is no existing translation, hence we could
avoid doing tlbie.

We could possibly race with a parallel fault filling the TLB. But
that should be ok because updatepp is only ever relaxing permissions.
We also look at linux pte permission bits when filling hash pte
permission bits. We also hold the linux pte busy bits while
inserting/updating a hashpte entry, hence a paralle update of
linux pte is not possible. On the other hand mprotect involves
ptep_modify_prot_start which cause a hpte invalidate and not updatepp.

Performance number:
We use randbox_access_bench written by Anton.

Kernel with THP disabled and smaller hash page table size.

    86.60%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_updatepp
     2.10%  random_access_b  random_access_bench              [.] doit
     1.99%  random_access_b  [kernel.kallsyms]                [k] .do_raw_spin_lock
     1.85%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_insert
     1.26%  random_access_b  [kernel.kallsyms]                [k] .native_flush_hash_range
     1.18%  random_access_b  [kernel.kallsyms]                [k] .__delay
     0.69%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_remove
     0.37%  random_access_b  [kernel.kallsyms]                [k] .clear_user_page
     0.34%  random_access_b  [kernel.kallsyms]                [k] .__hash_page_64K
     0.32%  random_access_b  [kernel.kallsyms]                [k] fast_exception_return
     0.30%  random_access_b  [kernel.kallsyms]                [k] .hash_page_mm

With Fix:

    27.54%  random_access_b  random_access_bench              [.] doit
    22.90%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_insert
     5.76%  random_access_b  [kernel.kallsyms]                [k] .native_hpte_remove
     5.20%  random_access_b  [kernel.kallsyms]                [k] fast_exception_return
     5.12%  random_access_b  [kernel.kallsyms]                [k] .__hash_page_64K
     4.80%  random_access_b  [kernel.kallsyms]                [k] .hash_page_mm
     3.31%  random_access_b  [kernel.kallsyms]                [k] data_access_common
     1.84%  random_access_b  [kernel.kallsyms]                [k] .trace_hardirqs_on_caller

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/machdep.h        |  2 +-
 arch/powerpc/include/asm/mmu-hash64.h     | 22 ++++++++++------
 arch/powerpc/include/asm/tlbflush.h       |  4 +--
 arch/powerpc/kernel/exceptions-64s.S      |  2 ++
 arch/powerpc/mm/hash_low_64.S             | 15 ++++++-----
 arch/powerpc/mm/hash_native_64.c          | 15 ++++++++---
 arch/powerpc/mm/hash_utils_64.c           | 44 ++++++++++++++++++++-----------
 arch/powerpc/mm/hugepage-hash64.c         |  8 +++---
 arch/powerpc/mm/hugetlbpage-hash64.c      |  6 ++---
 arch/powerpc/mm/pgtable_64.c              |  7 ++---
 arch/powerpc/platforms/cell/beat_htab.c   |  4 +--
 arch/powerpc/platforms/cell/spu_base.c    |  5 ++--
 arch/powerpc/platforms/cell/spufs/fault.c |  2 +-
 arch/powerpc/platforms/ps3/htab.c         |  2 +-
 arch/powerpc/platforms/pseries/lpar.c     |  2 +-
 drivers/misc/cxl/fault.c                  |  8 ++++--
 16 files changed, 91 insertions(+), 57 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index e5c0919acca4..c8175a3fe560 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -42,7 +42,7 @@ struct machdep_calls {
 					 unsigned long newpp, 
 					 unsigned long vpn,
 					 int bpsize, int apsize,
-					 int ssize, int local);
+					 int ssize, unsigned long flags);
 	void            (*hpte_updateboltedpp)(unsigned long newpp, 
 					       unsigned long ea,
 					       int psize, int ssize);
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index aeebc94b2bce..4f13c3ed7acf 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -316,27 +316,33 @@ static inline unsigned long hpt_hash(unsigned long vpn,
 	return hash & 0x7fffffffffUL;
 }
 
+#define HPTE_LOCAL_UPDATE	0x1
+#define HPTE_NOHPTE_UPDATE	0x2
+
 extern int __hash_page_4K(unsigned long ea, unsigned long access,
 			  unsigned long vsid, pte_t *ptep, unsigned long trap,
-			  unsigned int local, int ssize, int subpage_prot);
+			  unsigned long flags, int ssize, int subpage_prot);
 extern int __hash_page_64K(unsigned long ea, unsigned long access,
 			   unsigned long vsid, pte_t *ptep, unsigned long trap,
-			   unsigned int local, int ssize);
+			   unsigned long flags, int ssize);
 struct mm_struct;
 unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
-extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap);
-extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
+extern int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+			unsigned long access, unsigned long trap,
+			unsigned long flags);
+extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+		     unsigned long dsisr);
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
-		     pte_t *ptep, unsigned long trap, int local, int ssize,
-		     unsigned int shift, unsigned int mmu_psize);
+		     pte_t *ptep, unsigned long trap, unsigned long flags,
+		     int ssize, unsigned int shift, unsigned int mmu_psize);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern int __hash_page_thp(unsigned long ea, unsigned long access,
 			   unsigned long vsid, pmd_t *pmdp, unsigned long trap,
-			   int local, int ssize, unsigned int psize);
+			   unsigned long flags, int ssize, unsigned int psize);
 #else
 static inline int __hash_page_thp(unsigned long ea, unsigned long access,
 				  unsigned long vsid, pmd_t *pmdp,
-				  unsigned long trap, int local,
+				  unsigned long trap, unsigned long flags,
 				  int ssize, unsigned int psize)
 {
 	BUG();
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 4d3ecd8d8929..23d351ca0303 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -125,11 +125,11 @@ static inline void arch_leave_lazy_mmu_mode(void)
 
 
 extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
-			    int ssize, int local);
+			    int ssize, unsigned long flags);
 extern void flush_hash_range(unsigned long number, int local);
 extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
 				pmd_t *pmdp, unsigned int psize, int ssize,
-				int local);
+				unsigned long flags);
 
 static inline void local_flush_tlb_mm(struct mm_struct *mm)
 {
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ad62f4d6ce31..6213f494f40b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1565,9 +1565,11 @@ do_hash_page:
 	 * r3 contains the faulting address
 	 * r4 contains the required access permissions
 	 * r5 contains the trap number
+	 * r6 contains dsisr
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
+	ld      r6,_DSISR(r1)
 	bl	hash_page		/* build HPTE if possible */
 	cmpdi	r3,0			/* see if hash_page succeeded */
 
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 5094f32b706e..463174a4a647 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -46,7 +46,8 @@
 
 /*
  * _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
- *		 pte_t *ptep, unsigned long trap, int local, int ssize)
+ *		 pte_t *ptep, unsigned long trap, unsigned long flags,
+ *		 int ssize)
  *
  * Adds a 4K page to the hash table in a segment of 4K pages only
  */
@@ -298,7 +299,7 @@ htab_modify_pte:
 	li	r6,MMU_PAGE_4K		/* base page size */
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "flags" param */
 .globl htab_call_hpte_updatepp
 htab_call_hpte_updatepp:
 	bl	.			/* Patched by htab_finish_init() */
@@ -338,8 +339,8 @@ htab_pte_insert_failure:
  *****************************************************************************/
 
 /* _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
- *		 pte_t *ptep, unsigned long trap, int local, int ssize,
- *		 int subpg_prot)
+ *		 pte_t *ptep, unsigned long trap, unsigned local flags,
+ *		 int ssize, int subpg_prot)
  */
 
 /*
@@ -594,7 +595,7 @@ htab_inval_old_hpte:
 	li	r5,0			/* PTE.hidx */
 	li	r6,MMU_PAGE_64K		/* psize */
 	ld	r7,STK_PARAM(R9)(r1)	/* ssize */
-	ld	r8,STK_PARAM(R8)(r1)	/* local */
+	ld	r8,STK_PARAM(R8)(r1)	/* flags */
 	bl	flush_hash_page
 	/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
 	lis	r0,_PAGE_HPTE_SUB@h
@@ -666,7 +667,7 @@ htab_modify_pte:
 	li	r6,MMU_PAGE_4K		/* base page size */
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "flags" param */
 .globl htab_call_hpte_updatepp
 htab_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
@@ -962,7 +963,7 @@ ht64_modify_pte:
 	li	r6,MMU_PAGE_64K		/* base page size */
 	li	r7,MMU_PAGE_64K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "flags" param */
 .globl ht64_call_hpte_updatepp
 ht64_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 13700911b522..9c4880ddecd6 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -283,11 +283,11 @@ static long native_hpte_remove(unsigned long hpte_group)
 
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 				 unsigned long vpn, int bpsize,
-				 int apsize, int ssize, int local)
+				 int apsize, int ssize, unsigned long flags)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
-	int ret = 0;
+	int ret = 0, local = 0;
 
 	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 
@@ -322,8 +322,15 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		}
 		native_unlock_hpte(hptep);
 	}
-	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, bpsize, apsize, ssize, local);
+
+	if (flags & HPTE_LOCAL_UPDATE)
+		local = 1;
+	/*
+	 * Ensure it is out of the tlb too if it is not a nohpte fault
+	 */
+	if (!(flags & HPTE_NOHPTE_UPDATE))
+		tlbie(vpn, bpsize, apsize, ssize, local);
+
 	return ret;
 }
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 68211d398fdb..e56a307bc676 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -989,7 +989,9 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
  * -1 - critical hash insertion error
  * -2 - access not permitted by subpage protection mechanism
  */
-int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+		 unsigned long access, unsigned long trap,
+		 unsigned long flags)
 {
 	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
@@ -997,7 +999,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
 	pte_t *ptep;
 	unsigned hugeshift;
 	const struct cpumask *tmp;
-	int rc, user_region = 0, local = 0;
+	int rc, user_region = 0;
 	int psize, ssize;
 
 	DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
@@ -1049,7 +1051,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
 	/* Check CPU locality */
 	tmp = cpumask_of(smp_processor_id());
 	if (user_region && cpumask_equal(mm_cpumask(mm), tmp))
-		local = 1;
+		flags |= HPTE_LOCAL_UPDATE;
 
 #ifndef CONFIG_PPC_64K_PAGES
 	/* If we use 4K pages and our psize is not 4K, then we might
@@ -1086,11 +1088,11 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
 	if (hugeshift) {
 		if (pmd_trans_huge(*(pmd_t *)ptep))
 			rc = __hash_page_thp(ea, access, vsid, (pmd_t *)ptep,
-					     trap, local, ssize, psize);
+					     trap, flags, ssize, psize);
 #ifdef CONFIG_HUGETLB_PAGE
 		else
 			rc = __hash_page_huge(ea, access, vsid, ptep, trap,
-					      local, ssize, hugeshift, psize);
+					      flags, ssize, hugeshift, psize);
 #else
 		else {
 			/*
@@ -1149,7 +1151,8 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
 	if (psize == MMU_PAGE_64K)
-		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
+		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
+				     flags, ssize);
 	else
 #endif /* CONFIG_PPC_HAS_HASH_64K */
 	{
@@ -1158,7 +1161,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u
 			rc = -2;
 		else
 			rc = __hash_page_4K(ea, access, vsid, ptep, trap,
-					    local, ssize, spp);
+					    flags, ssize, spp);
 	}
 
 	/* Dump some info in case of hash insertion failure, they should
@@ -1181,14 +1184,19 @@ bail:
 }
 EXPORT_SYMBOL_GPL(hash_page_mm);
 
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+	      unsigned long dsisr)
 {
+	unsigned long flags = 0;
 	struct mm_struct *mm = current->mm;
 
 	if (REGION_ID(ea) == VMALLOC_REGION_ID)
 		mm = &init_mm;
 
-	return hash_page_mm(mm, ea, access, trap);
+	if (dsisr & DSISR_NOHPTE)
+		flags |= HPTE_NOHPTE_UPDATE;
+
+	return hash_page_mm(mm, ea, access, trap, flags);
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
@@ -1200,7 +1208,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	pgd_t *pgdir;
 	pte_t *ptep;
 	unsigned long flags;
-	int rc, ssize, local = 0;
+	int rc, ssize, update_flags = 0;
 
 	BUG_ON(REGION_ID(ea) != USER_REGION_ID);
 
@@ -1251,16 +1259,17 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 
 	/* Is that local to this CPU ? */
 	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
-		local = 1;
+		update_flags |= HPTE_LOCAL_UPDATE;
 
 	/* Hash it in */
 #ifdef CONFIG_PPC_HAS_HASH_64K
 	if (mm->context.user_psize == MMU_PAGE_64K)
-		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
+		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
+				     update_flags, ssize);
 	else
 #endif /* CONFIG_PPC_HAS_HASH_64K */
-		rc = __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize,
-				    subpage_protection(mm, ea));
+		rc = __hash_page_4K(ea, access, vsid, ptep, trap, update_flags,
+				    ssize, subpage_protection(mm, ea));
 
 	/* Dump some info in case of hash insertion failure, they should
 	 * never happen so it is really useful to know if/when they do
@@ -1278,9 +1287,10 @@ out_exit:
  *          do not forget to update the assembly call site !
  */
 void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
-		     int local)
+		     unsigned long flags)
 {
 	unsigned long hash, index, shift, hidx, slot;
+	int local = flags & HPTE_LOCAL_UPDATE;
 
 	DBG_LOW("flush_hash_page(vpn=%016lx)\n", vpn);
 	pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
@@ -1317,12 +1327,14 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
-			 pmd_t *pmdp, unsigned int psize, int ssize, int local)
+			 pmd_t *pmdp, unsigned int psize, int ssize,
+			 unsigned long flags)
 {
 	int i, max_hpte_count, valid;
 	unsigned long s_addr;
 	unsigned char *hpte_slot_array;
 	unsigned long hidx, shift, vpn, hash, slot;
+	int local = flags & HPTE_LOCAL_UPDATE;
 
 	s_addr = addr & HPAGE_PMD_MASK;
 	hpte_slot_array = get_hpte_slot_array(pmdp);
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 3a648cd363ae..86686514ae13 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -19,8 +19,8 @@
 #include <asm/machdep.h>
 
 int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
-		    pmd_t *pmdp, unsigned long trap, int local, int ssize,
-		    unsigned int psize)
+		    pmd_t *pmdp, unsigned long trap, unsigned long flags,
+		    int ssize, unsigned int psize)
 {
 	unsigned int index, valid;
 	unsigned char *hpte_slot_array;
@@ -95,7 +95,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		 */
 		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
 			flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
-					    ssize, local);
+					    ssize, flags);
 	}
 
 	valid = hpte_valid(hpte_slot_array, index);
@@ -108,7 +108,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot += hidx & _PTEIDX_GROUP_IX;
 
 		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
-					   psize, lpsize, ssize, local);
+					   psize, lpsize, ssize, flags);
 		/*
 		 * We failed to update, try to insert a new entry.
 		 */
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index a5bcf9301196..d94b1af53a93 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -19,8 +19,8 @@ extern long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
 				  unsigned long vflags, int psize, int ssize);
 
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
-		     pte_t *ptep, unsigned long trap, int local, int ssize,
-		     unsigned int shift, unsigned int mmu_psize)
+		     pte_t *ptep, unsigned long trap, unsigned long flags,
+		     int ssize, unsigned int shift, unsigned int mmu_psize)
 {
 	unsigned long vpn;
 	unsigned long old_pte, new_pte;
@@ -81,7 +81,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot += (old_pte & _PAGE_F_GIX) >> 12;
 
 		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
-					 mmu_psize, ssize, local) == -1)
+					 mmu_psize, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index eea9fa1f8ae7..4fe5f64cc179 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -739,9 +739,10 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 			    pmd_t *pmdp, unsigned long old_pmd)
 {
-	int ssize, local = 0;
+	int ssize;
 	unsigned int psize;
 	unsigned long vsid;
+	unsigned long flags = 0;
 	const struct cpumask *tmp;
 
 	/* get the base page size,vsid and segment size */
@@ -765,9 +766,9 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 
 	tmp = cpumask_of(smp_processor_id());
 	if (cpumask_equal(mm_cpumask(mm), tmp))
-		local = 1;
+		flags |= HPTE_LOCAL_UPDATE;
 
-	return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, local);
+	return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, flags);
 }
 
 static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index d4d245c0d787..bee9232fe619 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -186,7 +186,7 @@ static long beat_lpar_hpte_updatepp(unsigned long slot,
 				    unsigned long newpp,
 				    unsigned long vpn,
 				    int psize, int apsize,
-				    int ssize, int local)
+				    int ssize, unsigned long flags)
 {
 	unsigned long lpar_rc;
 	u64 dummy0, dummy1;
@@ -369,7 +369,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
 				       unsigned long newpp,
 				       unsigned long vpn,
 				       int psize, int apsize,
-				       int ssize, int local)
+				       int ssize, unsigned long flags)
 {
 	unsigned long lpar_rc;
 	unsigned long want_v;
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index ffcbd242e669..f7af74f83693 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -181,7 +181,8 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea)
 	return 0;
 }
 
-extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); //XXX
+extern int hash_page(unsigned long ea, unsigned long access,
+		     unsigned long trap, unsigned long dsisr); //XXX
 static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
 {
 	int ret;
@@ -196,7 +197,7 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
 	    (REGION_ID(ea) != USER_REGION_ID)) {
 
 		spin_unlock(&spu->register_lock);
-		ret = hash_page(ea, _PAGE_PRESENT, 0x300);
+		ret = hash_page(ea, _PAGE_PRESENT, 0x300, dsisr);
 		spin_lock(&spu->register_lock);
 
 		if (!ret) {
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index e45894a08118..d98f845ac777 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -144,7 +144,7 @@ int spufs_handle_class1(struct spu_context *ctx)
 	access = (_PAGE_PRESENT | _PAGE_USER);
 	access |= (dsisr & MFC_DSISR_ACCESS_PUT) ? _PAGE_RW : 0UL;
 	local_irq_save(flags);
-	ret = hash_page(ea, access, 0x300);
+	ret = hash_page(ea, access, 0x300, dsisr);
 	local_irq_restore(flags);
 
 	/* hashing failed, so try the actual fault handler */
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 3e270e3412ae..2f95d33cf34a 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -110,7 +110,7 @@ static long ps3_hpte_remove(unsigned long hpte_group)
 
 static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
 			      unsigned long vpn, int psize, int apsize,
-			      int ssize, int local)
+			      int ssize, unsigned long inv_flags)
 {
 	int result;
 	u64 hpte_v, want_v, hpte_rs;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 832f221840f2..469751d92004 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -284,7 +284,7 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot,
 				       unsigned long newpp,
 				       unsigned long vpn,
 				       int psize, int apsize,
-				       int ssize, int local)
+				       int ssize, unsigned long inv_flags)
 {
 	unsigned long lpar_rc;
 	unsigned long flags = (newpp & 7) | H_AVPN;
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index c99e896604ee..f8684bca2d79 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -133,7 +133,7 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
 {
 	unsigned flt = 0;
 	int result;
-	unsigned long access, flags;
+	unsigned long access, flags, inv_flags = 0;
 
 	if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
 		pr_devel("copro_handle_mm_fault failed: %#x\n", result);
@@ -149,8 +149,12 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
 		access |= _PAGE_RW;
 	if ((!ctx->kernel) || ~(dar & (1ULL << 63)))
 		access |= _PAGE_USER;
+
+	if (dsisr & DSISR_NOHPTE)
+		inv_flags |= HPTE_NOHPTE_UPDATE;
+
 	local_irq_save(flags);
-	hash_page_mm(mm, dar, access, 0x300);
+	hash_page_mm(mm, dar, access, 0x300, inv_flags);
 	local_irq_restore(flags);
 
 	pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);
-- 
cgit v1.2.3


From 682e77c861c4c60f79ffbeae5e1938ffed24a575 Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Fri, 5 Dec 2014 10:01:15 +0530
Subject: powerpc/book3s: Fix partial invalidation of TLBs in MCE code.

The existing MCE code calls flush_tlb hook with IS=0 (single page) resulting
in partial invalidation of TLBs which is not right. This patch fixes
that by passing IS=0xc00 to invalidate whole TLB for successful recovery
from TLB and ERAT errors.

Cc: stable@vger.kernel.org
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/mce_power.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index aa9aff3d6ad3..b6f123ab90ed 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -79,7 +79,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
@@ -110,7 +110,7 @@ static long mce_handle_common_ierror(uint64_t srr1)
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 			handled = 1;
 		}
 		break;
-- 
cgit v1.2.3


From 56548fc0e86cb9156af7a7e1f15ba78f251dafaf Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 3 Dec 2014 14:48:40 +1100
Subject: powerpc/powernv: Return to cpu offline loop when finished in KVM
 guest

When a secondary hardware thread has finished running a KVM guest, we
currently put that thread into nap mode using a nap instruction in
the KVM code.  This changes the code so that instead of doing a nap
instruction directly, we instead cause the call to power7_nap() that
put the thread into nap mode to return.  The reason for doing this is
to avoid having the KVM code having to know what low-power mode to
put the thread into.

In the case of a secondary thread used to run a KVM guest, the thread
will be offline from the point of view of the host kernel, and the
relevant power7_nap() call is the one in pnv_smp_cpu_disable().
In this case we don't want to clear pending IPIs in the offline loop
in that function, since that might cause us to miss the wakeup for
the next time the thread needs to run a guest.  To tell whether or
not to clear the interrupt, we use the SRR1 value returned from
power7_nap(), and check if it indicates an external interrupt.  We
arrange that the return from power7_nap() when we have finished running
a guest returns 0, so pending interrupts don't get flushed in that
case.

Note that it is important a secondary thread that has finished
executing in the guest, or that didn't have a guest to run, should
not return to power7_nap's caller while the kvm_hstate.hwthread_req
flag in the PACA is non-zero, because the return from power7_nap
will reenable the MMU, and the MMU might still be in guest context.
In this situation we spin at low priority in real mode waiting for
hwthread_req to become zero.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/processor.h    |  2 +-
 arch/powerpc/kernel/exceptions-64s.S    |  2 ++
 arch/powerpc/kernel/idle_power7.S       | 12 ++++++--
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 54 ++++++++++++++++++++++-----------
 arch/powerpc/platforms/powernv/smp.c    | 23 +++++++++++---
 5 files changed, 68 insertions(+), 25 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index dda7ac4c80bd..29c3798cf800 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -451,7 +451,7 @@ extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
-extern void power7_nap(int check_irq);
+extern unsigned long power7_nap(int check_irq);
 extern void power7_sleep(void);
 extern void flush_instruction_cache(void);
 extern void hard_reset_now(void);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6213f494f40b..db08382e19f1 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -131,6 +131,8 @@ BEGIN_FTR_SECTION
 1:
 #endif
 
+	/* Return SRR1 from power7_nap() */
+	mfspr	r3,SPRN_SRR1
 	beq	cr1,2f
 	b	power7_wakeup_noloss
 2:	b	power7_wakeup_loss
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index c0754bbf8118..18c0687e5ab3 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -212,6 +212,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	mtspr	SPRN_SRR0,r5
 	rfid
 
+/*
+ * R3 here contains the value that will be returned to the caller
+ * of power7_nap.
+ */
 _GLOBAL(power7_wakeup_loss)
 	ld	r1,PACAR1(r13)
 BEGIN_FTR_SECTION
@@ -219,15 +223,19 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	REST_NVGPRS(r1)
 	REST_GPR(2, r1)
-	ld	r3,_CCR(r1)
+	ld	r6,_CCR(r1)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)
 	addi	r1,r1,INT_FRAME_SIZE
-	mtcr	r3
+	mtcr	r6
 	mtspr	SPRN_SRR1,r4
 	mtspr	SPRN_SRR0,r5
 	rfid
 
+/*
+ * R3 here contains the value that will be returned to the caller
+ * of power7_nap.
+ */
 _GLOBAL(power7_wakeup_noloss)
 	lbz	r0,PACA_NAPSTATELOST(r13)
 	cmpwi	r0,0
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index edb2ccdbb2ba..65c105b17a25 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -201,8 +201,6 @@ kvmppc_primary_no_guest:
 	bge	kvm_novcpu_exit	/* another thread already exiting */
 	li	r3, NAPPING_NOVCPU
 	stb	r3, HSTATE_NAPPING(r13)
-	li	r3, 1
-	stb	r3, HSTATE_HWTHREAD_REQ(r13)
 
 	b	kvm_do_nap
 
@@ -293,6 +291,8 @@ kvm_start_guest:
 	/* if we have no vcpu to run, go back to sleep */
 	beq	kvm_no_guest
 
+kvm_secondary_got_guest:
+
 	/* Set HSTATE_DSCR(r13) to something sensible */
 	ld	r6, PACA_DSCR(r13)
 	std	r6, HSTATE_DSCR(r13)
@@ -318,27 +318,46 @@ kvm_start_guest:
 	stwcx.	r3, 0, r4
 	bne	51b
 
+/*
+ * At this point we have finished executing in the guest.
+ * We need to wait for hwthread_req to become zero, since
+ * we may not turn on the MMU while hwthread_req is non-zero.
+ * While waiting we also need to check if we get given a vcpu to run.
+ */
 kvm_no_guest:
-	li	r0, KVM_HWTHREAD_IN_NAP
+	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
+	cmpwi	r3, 0
+	bne	53f
+	HMT_MEDIUM
+	li	r0, KVM_HWTHREAD_IN_KERNEL
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
-kvm_do_nap:
-	/* Clear the runlatch bit before napping */
-	mfspr	r2, SPRN_CTRLF
-	clrrdi	r2, r2, 1
-	mtspr	SPRN_CTRLT, r2
-
+	/* need to recheck hwthread_req after a barrier, to avoid race */
+	sync
+	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
+	cmpwi	r3, 0
+	bne	54f
+/*
+ * We jump to power7_wakeup_loss, which will return to the caller
+ * of power7_nap in the powernv cpu offline loop.  The value we
+ * put in r3 becomes the return value for power7_nap.
+ */
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
-	isync
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
-	nap
-	b	.
+	li	r3, 0
+	b	power7_wakeup_loss
+
+53:	HMT_LOW
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	cmpdi	r4, 0
+	beq	kvm_no_guest
+	HMT_MEDIUM
+	b	kvm_secondary_got_guest
+
+54:	li	r0, KVM_HWTHREAD_IN_KVM
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	b	kvm_no_guest
 
 /******************************************************************************
  *                                                                            *
@@ -2172,6 +2191,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	 * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
 	 * runlatch bit before napping.
 	 */
+kvm_do_nap:
 	mfspr	r2, SPRN_CTRLF
 	clrrdi	r2, r2, 1
 	mtspr	SPRN_CTRLT, r2
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 4753958cd509..b716f666e48a 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -149,6 +149,7 @@ static int pnv_smp_cpu_disable(void)
 static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
+	unsigned long srr1;
 
 	/* Standard hot unplug procedure */
 	local_irq_disable();
@@ -165,13 +166,25 @@ static void pnv_smp_cpu_kill_self(void)
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
 		ppc64_runlatch_off();
-		power7_nap(1);
+		srr1 = power7_nap(1);
 		ppc64_runlatch_on();
 
-		/* Clear the IPI that woke us up */
-		icp_native_flush_interrupt();
-		local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
-		mb();
+		/*
+		 * If the SRR1 value indicates that we woke up due to
+		 * an external interrupt, then clear the interrupt.
+		 * We clear the interrupt before checking for the
+		 * reason, so as to avoid a race where we wake up for
+		 * some other reason, find nothing and clear the interrupt
+		 * just as some other cpu is sending us an interrupt.
+		 * If we returned from power7_nap as a result of
+		 * having finished executing in a KVM guest, then srr1
+		 * contains 0.
+		 */
+		if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) {
+			icp_native_flush_interrupt();
+			local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
+			smp_mb();
+		}
 
 		if (cpu_core_split_required())
 			continue;
-- 
cgit v1.2.3