From 0366a1c70b89efed4f9d590216bb004a16effbed Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Mon, 23 Sep 2013 14:29:11 +1000
Subject: powerpc/irq: Run softirqs off the top of the irq stack

Nowadays, irq_exit() calls __do_softirq() pretty much directly
instead of calling do_softirq() which switches to the decicated
softirq stack.

This has lead to observed stack overflows on powerpc since we call
irq_enter() and irq_exit() outside of the scope that switches to
the irq stack.

This fixes it by moving the stack switching up a level, making
irq_enter() and irq_exit() run off the irq stack.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h |   4 +-
 arch/powerpc/kernel/irq.c      | 104 ++++++++++++++++++++---------------------
 arch/powerpc/kernel/misc_32.S  |   9 ++--
 arch/powerpc/kernel/misc_64.S  |  10 ++--
 4 files changed, 62 insertions(+), 65 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 0e40843a1c6..41f13cec8a8 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -69,9 +69,9 @@ extern struct thread_info *softirq_ctx[NR_CPUS];
 
 extern void irq_ctx_init(void);
 extern void call_do_softirq(struct thread_info *tp);
-extern int call_handle_irq(int irq, void *p1,
-			   struct thread_info *tp, void *func);
+extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
 extern void do_IRQ(struct pt_regs *regs);
+extern void __do_irq(struct pt_regs *regs);
 
 int irq_choose_cpu(const struct cpumask *mask);
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c69440cef7a..2234a1276a7 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -441,50 +441,6 @@ void migrate_irqs(void)
 }
 #endif
 
-static inline void handle_one_irq(unsigned int irq)
-{
-	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit;
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	if (!desc)
-		return;
-
-	/* Switch to the irq stack to handle this */
-	curtp = current_thread_info();
-	irqtp = hardirq_ctx[smp_processor_id()];
-
-	if (curtp == irqtp) {
-		/* We're already on the irq stack, just handle it */
-		desc->handle_irq(irq, desc);
-		return;
-	}
-
-	saved_sp_limit = current->thread.ksp_limit;
-
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-
-	/* Copy the softirq bits in preempt_count so that the
-	 * softirq checks work in the hardirq context. */
-	irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
-			       (curtp->preempt_count & SOFTIRQ_MASK);
-
-	current->thread.ksp_limit = (unsigned long)irqtp +
-		_ALIGN_UP(sizeof(struct thread_info), 16);
-
-	call_handle_irq(irq, desc, irqtp, desc->handle_irq);
-	current->thread.ksp_limit = saved_sp_limit;
-	irqtp->task = NULL;
-
-	/* Set any flag that may have been set on the
-	 * alternate stack
-	 */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
-}
-
 static inline void check_stack_overflow(void)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -501,9 +457,9 @@ static inline void check_stack_overflow(void)
 #endif
 }
 
-void do_IRQ(struct pt_regs *regs)
+void __do_irq(struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct irq_desc *desc;
 	unsigned int irq;
 
 	irq_enter();
@@ -519,18 +475,64 @@ void do_IRQ(struct pt_regs *regs)
 	 */
 	irq = ppc_md.get_irq();
 
-	/* We can hard enable interrupts now */
+	/* We can hard enable interrupts now to allow perf interrupts */
 	may_hard_irq_enable();
 
 	/* And finally process it */
-	if (irq != NO_IRQ)
-		handle_one_irq(irq);
-	else
+	if (unlikely(irq == NO_IRQ))
 		__get_cpu_var(irq_stat).spurious_irqs++;
+	else {
+		desc = irq_to_desc(irq);
+		if (likely(desc))
+			desc->handle_irq(irq, desc);
+	}
 
 	trace_irq_exit(regs);
 
 	irq_exit();
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct thread_info *curtp, *irqtp;
+	unsigned long saved_sp_limit;
+
+	/* Switch to the irq stack to handle this */
+	curtp = current_thread_info();
+	irqtp = hardirq_ctx[raw_smp_processor_id()];
+
+	/* Already there ? */
+	if (unlikely(curtp == irqtp)) {
+		__do_irq(regs);
+		set_irq_regs(old_regs);
+		return;
+	}
+
+	/* Adjust the stack limit */
+	saved_sp_limit = current->thread.ksp_limit;
+	current->thread.ksp_limit = (unsigned long)irqtp +
+		_ALIGN_UP(sizeof(struct thread_info), 16);
+
+
+	/* Prepare the thread_info in the irq stack */
+	irqtp->task = curtp->task;
+	irqtp->flags = 0;
+
+	/* Copy the preempt_count so that the [soft]irq checks work. */
+	irqtp->preempt_count = curtp->preempt_count;
+
+	/* Switch stack and call */
+	call_do_irq(regs, irqtp);
+
+	/* Restore stack limit */
+	current->thread.ksp_limit = saved_sp_limit;
+	irqtp->task = NULL;
+
+	/* Copy back updates to the thread_info */
+	if (irqtp->flags)
+		set_bits(irqtp->flags, &curtp->flags);
+
 	set_irq_regs(old_regs);
 }
 
@@ -592,12 +594,10 @@ void irq_ctx_init(void)
 		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
 		tp = softirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = 0;
 
 		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
 		tp = hardirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = HARDIRQ_OFFSET;
 	}
 }
 
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 777d999f563..7da3882a362 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -47,13 +47,12 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
-	mtctr	r6
-	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	bl	__do_irq
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
 	mtlr	r0
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 971d7e78aff..e59caf874d0 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -40,14 +40,12 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
-	ld	r8,0(r6)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	std	r0,16(r1)
-	mtctr	r8
-	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	bl	.__do_irq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
-- 
cgit v1.2.3-70-g09d2


From cbc9565ee82694dec31d8137dec975b83175183b Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 24 Sep 2013 15:17:21 +1000
Subject: powerpc: Remove ksp_limit on ppc64

We've been keeping that field in thread_struct for a while, it contains
the "limit" of the current stack pointer and is meant to be used for
detecting stack overflows.

It has a few problems however:

 - First, it was never actually *used* on 64-bit. Set and updated but
not actually exploited

 - When switching stack to/from irq and softirq stacks, it's update
is racy unless we hard disable interrupts, which is costly. This
is fine on 32-bit as we don't soft-disable there but not on 64-bit.

Thus rather than fixing 2 in order to implement 1 in some hypothetical
future, let's remove the code completely from 64-bit. In order to avoid
a clutter of ifdef's, we remove the updates from C code completely
during interrupt stack switching, and instead maintain it from the
asm helper that is used to do the stack switching in the first place.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/processor.h |  4 +---
 arch/powerpc/kernel/asm-offsets.c    |  3 ++-
 arch/powerpc/kernel/irq.c            | 12 ------------
 arch/powerpc/kernel/misc_32.S        | 16 ++++++++++++++++
 arch/powerpc/kernel/process.c        |  3 ++-
 arch/powerpc/lib/sstep.c             |  3 ++-
 6 files changed, 23 insertions(+), 18 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index e378cccfca5..ce4de5aed7b 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -149,8 +149,6 @@ typedef struct {
 
 struct thread_struct {
 	unsigned long	ksp;		/* Kernel stack pointer */
-	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
-
 #ifdef CONFIG_PPC64
 	unsigned long	ksp_vsid;
 #endif
@@ -162,6 +160,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_PPC32
 	void		*pgdir;		/* root of page-table tree */
+	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
 #endif
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	/*
@@ -321,7 +320,6 @@ struct thread_struct {
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
-	.ksp_limit = INIT_SP_LIMIT, \
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
 	.fpr = {{0}}, \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d8958be5f31..502c7a4e73f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -80,10 +80,11 @@ int main(void)
 	DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
+	DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
+	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 #endif /* CONFIG_PPC64 */
 
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
-	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
 	DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2234a1276a7..57d286a78f8 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -496,7 +496,6 @@ void do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit;
 
 	/* Switch to the irq stack to handle this */
 	curtp = current_thread_info();
@@ -509,12 +508,6 @@ void do_IRQ(struct pt_regs *regs)
 		return;
 	}
 
-	/* Adjust the stack limit */
-	saved_sp_limit = current->thread.ksp_limit;
-	current->thread.ksp_limit = (unsigned long)irqtp +
-		_ALIGN_UP(sizeof(struct thread_info), 16);
-
-
 	/* Prepare the thread_info in the irq stack */
 	irqtp->task = curtp->task;
 	irqtp->flags = 0;
@@ -526,7 +519,6 @@ void do_IRQ(struct pt_regs *regs)
 	call_do_irq(regs, irqtp);
 
 	/* Restore stack limit */
-	current->thread.ksp_limit = saved_sp_limit;
 	irqtp->task = NULL;
 
 	/* Copy back updates to the thread_info */
@@ -604,16 +596,12 @@ void irq_ctx_init(void)
 static inline void do_softirq_onstack(void)
 {
 	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit = current->thread.ksp_limit;
 
 	curtp = current_thread_info();
 	irqtp = softirq_ctx[smp_processor_id()];
 	irqtp->task = curtp->task;
 	irqtp->flags = 0;
-	current->thread.ksp_limit = (unsigned long)irqtp +
-				    _ALIGN_UP(sizeof(struct thread_info), 16);
 	call_do_softirq(irqtp);
-	current->thread.ksp_limit = saved_sp_limit;
 	irqtp->task = NULL;
 
 	/* Set any flag that may have been set on the
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7da3882a362..2b0ad984536 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -36,25 +36,41 @@
 
 	.text
 
+/*
+ * We store the saved ksp_limit in the unused part
+ * of the STACK_FRAME_OVERHEAD
+ */
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_softirq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
 _GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
 	mr	r1,r4
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_irq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 6f428da53e2..96d2fdf3aa9 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1000,9 +1000,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	kregs = (struct pt_regs *) sp;
 	sp -= STACK_FRAME_OVERHEAD;
 	p->thread.ksp = sp;
+#ifdef CONFIG_PPC32
 	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
 				_ALIGN_UP(sizeof(struct thread_info), 16);
-
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	p->thread.ptrace_bps[0] = NULL;
 #endif
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index a7ee978fb86..b1faa1593c9 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1505,6 +1505,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		 */
 		if ((ra == 1) && !(regs->msr & MSR_PR) \
 			&& (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) {
+#ifdef CONFIG_PPC32
 			/*
 			 * Check if we will touch kernel sack overflow
 			 */
@@ -1513,7 +1514,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				err = -EINVAL;
 				break;
 			}
-
+#endif /* CONFIG_PPC32 */
 			/*
 			 * Check if we already set since that means we'll
 			 * lose the previous value.
-- 
cgit v1.2.3-70-g09d2


From 0c9fa29149d3726e14262aeb0c8461a948cc9d56 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 24 Sep 2013 16:10:38 +1000
Subject: powerpc/zImage: make the "OF" wrapper support ePAPR boot

This makes the "OF" zImage wrapper (zImage.pseries, zImage.pmac,
zImage.maple) work if booted via a flat device-tree (ePAPR boot
mode), and thus potentially usable with kexec.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/boot/Makefile        |  4 ++--
 arch/powerpc/boot/epapr-wrapper.c |  9 +++++++++
 arch/powerpc/boot/epapr.c         |  4 ++--
 arch/powerpc/boot/of.c            | 16 +++++++++++++++-
 arch/powerpc/boot/wrapper         |  9 +++++----
 5 files changed, 33 insertions(+), 9 deletions(-)
 create mode 100644 arch/powerpc/boot/epapr-wrapper.c

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 6a15c968d21..15ca2255f43 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -74,7 +74,7 @@ src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c
 src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
 src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c
 
-src-plat-y := of.c
+src-plat-y := of.c epapr.c
 src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \
 				treeboot-walnut.c cuboot-acadia.c \
 				cuboot-kilauea.c simpleboot.c \
@@ -97,7 +97,7 @@ src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \
 					prpmc2800.c
 src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c
 src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
-src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c
+src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
diff --git a/arch/powerpc/boot/epapr-wrapper.c b/arch/powerpc/boot/epapr-wrapper.c
new file mode 100644
index 00000000000..c1019100667
--- /dev/null
+++ b/arch/powerpc/boot/epapr-wrapper.c
@@ -0,0 +1,9 @@
+extern void epapr_platform_init(unsigned long r3, unsigned long r4,
+				unsigned long r5, unsigned long r6,
+				unsigned long r7);
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	epapr_platform_init(r3, r4, r5, r6, r7);
+}
diff --git a/arch/powerpc/boot/epapr.c b/arch/powerpc/boot/epapr.c
index 06c1961bd12..02e91aa2194 100644
--- a/arch/powerpc/boot/epapr.c
+++ b/arch/powerpc/boot/epapr.c
@@ -48,8 +48,8 @@ static void platform_fixups(void)
 		       fdt_addr, fdt_totalsize((void *)fdt_addr), ima_size);
 }
 
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
-		   unsigned long r6, unsigned long r7)
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7)
 {
 	epapr_magic = r6;
 	ima_size = r7;
diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c
index 61d9899aa0d..62e2f43ec1d 100644
--- a/arch/powerpc/boot/of.c
+++ b/arch/powerpc/boot/of.c
@@ -26,6 +26,9 @@
 
 static unsigned long claim_base;
 
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7);
+
 static void *of_try_claim(unsigned long size)
 {
 	unsigned long addr = 0;
@@ -61,7 +64,7 @@ static void of_image_hdr(const void *hdr)
 	}
 }
 
-void platform_init(unsigned long a1, unsigned long a2, void *promptr)
+static void of_platform_init(unsigned long a1, unsigned long a2, void *promptr)
 {
 	platform_ops.image_hdr = of_image_hdr;
 	platform_ops.malloc = of_try_claim;
@@ -81,3 +84,14 @@ void platform_init(unsigned long a1, unsigned long a2, void *promptr)
 		loader_info.initrd_size = a2;
 	}
 }
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	/* Detect OF vs. ePAPR boot */
+	if (r5)
+		of_platform_init(r3, r4, (void *)r5);
+	else
+		epapr_platform_init(r3, r4, r5, r6, r7);
+}
+
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 6761c746048..cd7af841ba0 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -148,18 +148,18 @@ make_space=y
 
 case "$platform" in
 pseries)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x4000000'
     ;;
 maple)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x400000'
     ;;
 pmac|chrp)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     ;;
 coff)
-    platformo="$object/crt0.o $object/of.o"
+    platformo="$object/crt0.o $object/of.o $object/epapr.o"
     lds=$object/zImage.coff.lds
     link_address='0x500000'
     pie=
@@ -253,6 +253,7 @@ treeboot-iss4xx-mpic)
     platformo="$object/treeboot-iss4xx.o"
     ;;
 epapr)
+    platformo="$object/epapr.o $object/epapr-wrapper.o"
     link_address='0x20000000'
     pie=-pie
     ;;
-- 
cgit v1.2.3-70-g09d2


From dbe78b40118636f2d5d276144239dd4bfd5f04f9 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 25 Sep 2013 14:02:50 +1000
Subject: powerpc/pseries: Do not start secondaries in Open Firmware

Starting secondary CPUs early on from Open Firmware and placing them
in a holding spin loop slows down the boot process significantly under
some hypervisors such as KVM.

This is also unnecessary when RTAS supports querying the CPU state

So let's not do it.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/prom_init.c      | 21 +++++++++++++++++++++
 arch/powerpc/platforms/pseries/smp.c | 26 ++++++++++++++++----------
 2 files changed, 37 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 12e656ffe60..5fe2842e8ba 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -196,6 +196,8 @@ static int __initdata mem_reserve_cnt;
 
 static cell_t __initdata regbuf[1024];
 
+static bool rtas_has_query_cpu_stopped;
+
 
 /*
  * Error results ... some OF calls will return "-1" on error, some
@@ -1574,6 +1576,11 @@ static void __init prom_instantiate_rtas(void)
 	prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
 		     &val, sizeof(val));
 
+	/* Check if it supports "query-cpu-stopped-state" */
+	if (prom_getprop(rtas_node, "query-cpu-stopped-state",
+			 &val, sizeof(val)) != PROM_ERROR)
+		rtas_has_query_cpu_stopped = true;
+
 #if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__)
 	/* PowerVN takeover hack */
 	prom_rtas_data = base;
@@ -1815,6 +1822,18 @@ static void __init prom_hold_cpus(void)
 		= (void *) LOW_ADDR(__secondary_hold_acknowledge);
 	unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
 
+	/*
+	 * On pseries, if RTAS supports "query-cpu-stopped-state",
+	 * we skip this stage, the CPUs will be started by the
+	 * kernel using RTAS.
+	 */
+	if ((of_platform == PLATFORM_PSERIES ||
+	     of_platform == PLATFORM_PSERIES_LPAR) &&
+	    rtas_has_query_cpu_stopped) {
+		prom_printf("prom_hold_cpus: skipped\n");
+		return;
+	}
+
 	prom_debug("prom_hold_cpus: start...\n");
 	prom_debug("    1) spinloop       = 0x%x\n", (unsigned long)spinloop);
 	prom_debug("    1) *spinloop      = 0x%x\n", *spinloop);
@@ -3011,6 +3030,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * On non-powermacs, put all CPUs in spin-loops.
 	 *
 	 * PowerMacs use a different mechanism to spin CPUs
+	 *
+	 * (This must be done after instanciating RTAS)
 	 */
 	if (of_platform != PLATFORM_POWERMAC &&
 	    of_platform != PLATFORM_OPAL)
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 1c1771a4025..24f58cb0a54 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -233,18 +233,24 @@ static void __init smp_init_pseries(void)
 
 	alloc_bootmem_cpumask_var(&of_spin_mask);
 
-	/* Mark threads which are still spinning in hold loops. */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		for_each_present_cpu(i) { 
-			if (cpu_thread_in_core(i) == 0)
-				cpumask_set_cpu(i, of_spin_mask);
-		}
-	} else {
-		cpumask_copy(of_spin_mask, cpu_present_mask);
+	/*
+	 * Mark threads which are still spinning in hold loops
+	 *
+	 * We know prom_init will not have started them if RTAS supports
+	 * query-cpu-stopped-state.
+	 */
+	if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) {
+		if (cpu_has_feature(CPU_FTR_SMT)) {
+			for_each_present_cpu(i) {
+				if (cpu_thread_in_core(i) == 0)
+					cpumask_set_cpu(i, of_spin_mask);
+			}
+		} else
+			cpumask_copy(of_spin_mask, cpu_present_mask);
+
+		cpumask_clear_cpu(boot_cpuid, of_spin_mask);
 	}
 
-	cpumask_clear_cpu(boot_cpuid, of_spin_mask);
-
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
 		smp_ops->give_timebase = rtas_give_timebase;
-- 
cgit v1.2.3-70-g09d2


From f7e3334a6bcb42e7295a9bd9cb36ca4e6e4e66b4 Mon Sep 17 00:00:00 2001
From: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Date: Fri, 27 Sep 2013 10:18:09 -0500
Subject: powerpc: Fix memory hotplug with sparse vmemmap

Previous commit 46723bfa540... introduced a new config option
HAVE_BOOTMEM_INFO_NODE that ended up breaking memory hot-remove for ppc
when sparse vmemmap is not defined.

This patch defines HAVE_BOOTMEM_INFO_NODE for ppc and adds the call to
register_page_bootmem_info_node. Without this we get a BUG_ON for memory
hot remove in put_page_bootmem().

This also adds a stub for register_page_bootmem_memmap to allow ppc to build
with sparse vmemmap defined. Leaving this as a stub is fine since the same
vmemmap addresses are also handled in vmemmap_populate and as such are
properly mapped.

Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org> [v3.9+]
---
 arch/powerpc/mm/init_64.c | 4 ++++
 arch/powerpc/mm/mem.c     | 9 +++++++++
 mm/Kconfig                | 2 +-
 3 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index d0cd9e4c683..8ed035d2edb 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -300,5 +300,9 @@ void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 
+void register_page_bootmem_memmap(unsigned long section_nr,
+				  struct page *start_page, unsigned long size)
+{
+}
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1cf9c5b67f2..3fa93dc7fe7 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -297,12 +297,21 @@ void __init paging_init(void)
 }
 #endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
+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)
 {
 #ifdef CONFIG_SWIOTLB
 	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/mm/Kconfig b/mm/Kconfig
index 026771a9b09..394838f489e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -183,7 +183,7 @@ config MEMORY_HOTPLUG_SPARSE
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
 	select MEMORY_ISOLATION
-	select HAVE_BOOTMEM_INFO_NODE if X86_64
+	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 
-- 
cgit v1.2.3-70-g09d2


From d9813c3681a36774b254c0cdc9cce53c9e22c756 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 Oct 2013 16:54:05 +1000
Subject: powerpc: Fix parameter clobber in csum_partial_copy_generic()

The csum_partial_copy_generic() uses register r7 to adjust the remaining
bytes to process.  Unfortunately, r7 also holds a parameter, namely the
address of the flag to set in case of access exceptions while reading
the source buffer.  Lacking a quantum implementation of PowerPC, this
commit instead uses register r9 to do the adjusting, leaving r7's
pointer uncorrupted.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: stable@vger.kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/lib/checksum_64.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 167f72555d6..609665aede7 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -269,8 +269,8 @@ _GLOBAL(csum_partial_copy_generic)
 	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 & 0x3) >> 1 */
 	beq	.Lcopy_aligned
 
-	li	r7,4
-	sub	r6,r7,r6
+	li	r9,4
+	sub	r6,r9,r6
 	mtctr	r6
 
 1:
-- 
cgit v1.2.3-70-g09d2


From 8f21bd0090052e740944f9397e2be5ac7957ded7 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 Oct 2013 17:11:35 +1000
Subject: powerpc: Restore registers on error exit from
 csum_partial_copy_generic()

The csum_partial_copy_generic() function saves the PowerPC non-volatile
r14, r15, and r16 registers for the main checksum-and-copy loop.
Unfortunately, it fails to restore them upon error exit from this loop,
which results in silent corruption of these registers in the presumably
rare event of an access exception within that loop.

This commit therefore restores these register on error exit from the loop.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: stable@vger.kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/lib/checksum_64.S | 54 +++++++++++++++++++++++++++++++-----------
 1 file changed, 40 insertions(+), 14 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 609665aede7..57a07206505 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -226,19 +226,35 @@ _GLOBAL(csum_partial)
 	blr
 
 
-	.macro source
+	.macro srcnr
 100:
 	.section __ex_table,"a"
 	.align 3
-	.llong 100b,.Lsrc_error
+	.llong 100b,.Lsrc_error_nr
 	.previous
 	.endm
 
-	.macro dest
+	.macro source
+150:
+	.section __ex_table,"a"
+	.align 3
+	.llong 150b,.Lsrc_error
+	.previous
+	.endm
+
+	.macro dstnr
 200:
 	.section __ex_table,"a"
 	.align 3
-	.llong 200b,.Ldest_error
+	.llong 200b,.Ldest_error_nr
+	.previous
+	.endm
+
+	.macro dest
+250:
+	.section __ex_table,"a"
+	.align 3
+	.llong 250b,.Ldest_error
 	.previous
 	.endm
 
@@ -274,11 +290,11 @@ _GLOBAL(csum_partial_copy_generic)
 	mtctr	r6
 
 1:
-source;	lhz	r6,0(r3)		/* align to doubleword */
+srcnr;	lhz	r6,0(r3)		/* align to doubleword */
 	subi	r5,r5,2
 	addi	r3,r3,2
 	adde	r0,r0,r6
-dest;	sth	r6,0(r4)
+dstnr;	sth	r6,0(r4)
 	addi	r4,r4,2
 	bdnz	1b
 
@@ -392,10 +408,10 @@ dest;	std	r16,56(r4)
 
 	mtctr	r6
 3:
-source;	ld	r6,0(r3)
+srcnr;	ld	r6,0(r3)
 	addi	r3,r3,8
 	adde	r0,r0,r6
-dest;	std	r6,0(r4)
+dstnr;	std	r6,0(r4)
 	addi	r4,r4,8
 	bdnz	3b
 
@@ -405,10 +421,10 @@ dest;	std	r6,0(r4)
 	srdi.	r6,r5,2
 	beq	.Lcopy_tail_halfword
 
-source;	lwz	r6,0(r3)
+srcnr;	lwz	r6,0(r3)
 	addi	r3,r3,4
 	adde	r0,r0,r6
-dest;	stw	r6,0(r4)
+dstnr;	stw	r6,0(r4)
 	addi	r4,r4,4
 	subi	r5,r5,4
 
@@ -416,10 +432,10 @@ dest;	stw	r6,0(r4)
 	srdi.	r6,r5,1
 	beq	.Lcopy_tail_byte
 
-source;	lhz	r6,0(r3)
+srcnr;	lhz	r6,0(r3)
 	addi	r3,r3,2
 	adde	r0,r0,r6
-dest;	sth	r6,0(r4)
+dstnr;	sth	r6,0(r4)
 	addi	r4,r4,2
 	subi	r5,r5,2
 
@@ -427,10 +443,10 @@ dest;	sth	r6,0(r4)
 	andi.	r6,r5,1
 	beq	.Lcopy_finish
 
-source;	lbz	r6,0(r3)
+srcnr;	lbz	r6,0(r3)
 	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
 	adde	r0,r0,r9
-dest;	stb	r6,0(r4)
+dstnr;	stb	r6,0(r4)
 
 .Lcopy_finish:
 	addze	r0,r0			/* add in final carry */
@@ -440,6 +456,11 @@ dest;	stb	r6,0(r4)
 	blr
 
 .Lsrc_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Lsrc_error_nr:
 	cmpdi	0,r7,0
 	beqlr
 	li	r6,-EFAULT
@@ -447,6 +468,11 @@ dest;	stb	r6,0(r4)
 	blr
 
 .Ldest_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldest_error_nr:
 	cmpdi	0,r8,0
 	beqlr
 	li	r6,-EFAULT
-- 
cgit v1.2.3-70-g09d2


From d1211af3049f4c9c1d8d4eb8f8098cc4f4f0d0c7 Mon Sep 17 00:00:00 2001
From: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Date: Wed, 2 Oct 2013 00:34:10 +0530
Subject: powerpc/sysfs: Disable writing to PURR in guest mode

arch/powerpc/kernel/sysfs.c exports PURR with write permission.
This may be valid for kernel in phyp mode. But writing to
the file in guest mode causes crash due to a priviledge violation

Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org>
---
 arch/powerpc/kernel/sysfs.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 27a90b99ef6..b4e667663d9 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,6 +17,7 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 #include <asm/pmc.h>
+#include <asm/firmware.h>
 
 #include "cacheinfo.h"
 
@@ -179,15 +180,25 @@ SYSFS_PMCSETUP(spurr, SPRN_SPURR);
 SYSFS_PMCSETUP(dscr, SPRN_DSCR);
 SYSFS_PMCSETUP(pir, SPRN_PIR);
 
+/*
+  Lets only enable read for phyp resources and
+  enable write when needed with a separate function.
+  Lets be conservative and default to pseries.
+*/
 static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
 static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
-static DEVICE_ATTR(purr, 0600, show_purr, store_purr);
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 
 unsigned long dscr_default = 0;
 EXPORT_SYMBOL(dscr_default);
 
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+	attr->attr.mode |= 0200;
+}
+
 static ssize_t show_dscr_default(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -394,8 +405,11 @@ static void register_cpu_online(unsigned int cpu)
 	if (cpu_has_feature(CPU_FTR_MMCRA))
 		device_create_file(s, &dev_attr_mmcra);
 
-	if (cpu_has_feature(CPU_FTR_PURR))
+	if (cpu_has_feature(CPU_FTR_PURR)) {
+		if (!firmware_has_feature(FW_FEATURE_LPAR))
+			add_write_permission_dev_attr(&dev_attr_purr);
 		device_create_file(s, &dev_attr_purr);
+	}
 
 	if (cpu_has_feature(CPU_FTR_SPURR))
 		device_create_file(s, &dev_attr_spurr);
-- 
cgit v1.2.3-70-g09d2


From 1cf389df090194a0976dc867b7fffe99d9d490cb Mon Sep 17 00:00:00 2001
From: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Date: Tue, 1 Oct 2013 14:04:53 -0700
Subject: powerpc/iommu: Use GFP_KERNEL instead of GFP_ATOMIC in
 iommu_init_table()

Under heavy (DLPAR?) stress, we tripped this panic() in
arch/powerpc/kernel/iommu.c::iommu_init_table():

	page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
	if (!page)
		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);

Before the panic() we got a page allocation failure for an order-2
allocation. There appears to be memory free, but perhaps not in the
ATOMIC context. I looked through all the call-sites of
iommu_init_table() and didn't see any obvious reason to need an ATOMIC
allocation. Most call-sites in fact have an explicit GFP_KERNEL
allocation shortly before the call to iommu_init_table(), indicating we
are not in an atomic context. There is some indirection for some paths,
but I didn't see any locks indicating that GFP_KERNEL is inappropriate.

With this change under the same conditions, we have not been able to
reproduce the panic.

Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org>
---
 arch/powerpc/kernel/iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0adab06ce5c..572bb5b95f3 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -661,7 +661,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	/* number of bytes needed for the bitmap */
 	sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
 
-	page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
+	page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz));
 	if (!page)
 		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
 	tbl->it_map = page_address(page);
-- 
cgit v1.2.3-70-g09d2


From e82b89a6f19bae73fb064d1b3dd91fcefbb478f4 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Mon, 23 Sep 2013 09:33:36 -0400
Subject: powerpc/vio: Fix modalias_show return values

modalias_show() should return an empty string on error, not -ENODEV.

This causes the following false and annoying error:

> find /sys/devices -name modalias -print0 | xargs -0 cat >/dev/null
cat: /sys/devices/vio/4000/modalias: No such device
cat: /sys/devices/vio/4001/modalias: No such device
cat: /sys/devices/vio/4002/modalias: No such device
cat: /sys/devices/vio/4004/modalias: No such device
cat: /sys/devices/vio/modalias: No such device

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org>
---
 arch/powerpc/kernel/vio.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 78a350670de..d38cc08b16c 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1530,11 +1530,15 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 	const char *cp;
 
 	dn = dev->of_node;
-	if (!dn)
-		return -ENODEV;
+	if (!dn) {
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
 	cp = of_get_property(dn, "compatible", NULL);
-	if (!cp)
-		return -ENODEV;
+	if (!cp) {
+		strcat(buf, "\n");
+		return strlen(buf);
+	}
 
 	return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp);
 }
-- 
cgit v1.2.3-70-g09d2


From a53b27b3abeef406de92a2bb0ceb6fb4c3fb8fc4 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Wed, 2 Oct 2013 18:04:06 +1000
Subject: powerpc/perf: Fix handling of FAB events

Commit 4df4899 "Add power8 EBB support" included a bug in the handling
of the FAB_CRESP_MATCH and FAB_TYPE_MATCH fields.

These values are pulled out of the event code using EVENT_THR_CTL_SHIFT,
however we were then or'ing that value directly into MMCR1.

This meant we were failing to set the FAB fields correctly, and also
potentially corrupting the value for PMC4SEL. Leading to no counts for
the FAB events and incorrect counts for PMC4.

The fix is simply to shift left the FAB value correctly before or'ing it
with MMCR1.

Reported-by: Sooraj Ravindran Nair <soonair3@in.ibm.com>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Cc: <stable@vger.kernel.org> # 3.10+
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/perf/power8-pmu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 2ee4a707f0d..a3f7abd2f13 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -199,6 +199,7 @@
 #define MMCR1_UNIT_SHIFT(pmc)		(60 - (4 * ((pmc) - 1)))
 #define MMCR1_COMBINE_SHIFT(pmc)	(35 - ((pmc) - 1))
 #define MMCR1_PMCSEL_SHIFT(pmc)		(24 - (((pmc) - 1)) * 8)
+#define MMCR1_FAB_SHIFT			36
 #define MMCR1_DC_QUAL_SHIFT		47
 #define MMCR1_IC_QUAL_SHIFT		46
 
@@ -388,8 +389,8 @@ static int power8_compute_mmcr(u64 event[], int n_ev,
 		 * the threshold bits are used for the match value.
 		 */
 		if (event_is_fab_match(event[i])) {
-			mmcr1 |= (event[i] >> EVENT_THR_CTL_SHIFT) &
-				  EVENT_THR_CTL_MASK;
+			mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) &
+				  EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT;
 		} else {
 			val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
 			mmcra |= val << MMCRA_THR_CTL_SHIFT;
-- 
cgit v1.2.3-70-g09d2


From c69e63b0f135fa51d6e1c38b5ac8a1def15ea3fa Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Wed, 2 Oct 2013 17:15:15 +1000
Subject: powerpc/tm: Turn interrupts hard off in tm_reclaim()

We can't take IRQs in tm_reclaim as we might have a bogus r13 and r1.

This turns IRQs hard off in this function.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Cc: <stable@vger.kernel.org> # 3.9+
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/tm.S | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 7b60b985146..8ece1908be1 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -123,6 +123,7 @@ _GLOBAL(tm_reclaim)
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
 	li	r16, MSR_RI
+	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
 #ifdef CONFIG_VSX
-- 
cgit v1.2.3-70-g09d2


From e9bdc3d6143d1c4b8d8ce5231fc958268331f983 Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Thu, 26 Sep 2013 13:29:09 +1000
Subject: powerpc/tm: Switch out userspace PPR and DSCR sooner

When we do a treclaim or trecheckpoint we end up running with userspace
PPR and DSCR values.  Currently we don't do anything special to avoid
running with user values which could cause a severe performance
degradation.

This patch moves the PPR and DSCR save and restore around treclaim and
trecheckpoint so that we run with user values for a much shorter period.
More care is taken with the PPR as it's impact is greater than the DSCR.

This is similar to user exceptions, where we run HTM_MEDIUM early to
ensure that we don't run with a userspace PPR values in the kernel.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Cc: <stable@vger.kernel.org> # 3.9+
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/tm.S | 94 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 63 insertions(+), 31 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 8ece1908be1..cd809eaa8b5 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -79,6 +79,11 @@ _GLOBAL(tm_abort)
 	TABORT(R3)
 	blr
 
+	.section	".toc","aw"
+DSCR_DEFAULT:
+	.tc dscr_default[TC],dscr_default
+
+	.section	".text"
 
 /* void tm_reclaim(struct thread_struct *thread,
  *                 unsigned long orig_msr,
@@ -188,11 +193,18 @@ dont_backup_fp:
 	std	r1, PACATMSCRATCH(r13)
 	ld	r1, PACAR1(r13)
 
+	/* Store the PPR in r11 and reset to decent value */
+	std	r11, GPR11(r1)			/* Temporary stash */
+	mfspr	r11, SPRN_PPR
+	HMT_MEDIUM
+
 	/* Now get some more GPRS free */
 	std	r7, GPR7(r1)			/* Temporary stash */
 	std	r12, GPR12(r1)			/* ''   ''    ''   */
 	ld	r12, STACK_PARAM(0)(r1)		/* Param 0, thread_struct * */
 
+	std	r11, THREAD_TM_PPR(r12)		/* Store PPR and free r11 */
+
 	addi	r7, r12, PT_CKPT_REGS		/* Thread's ckpt_regs */
 
 	/* Make r7 look like an exception frame so that we
@@ -204,15 +216,19 @@ dont_backup_fp:
 	SAVE_GPR(0, r7)				/* user r0 */
 	SAVE_GPR(2, r7)			/* user r2 */
 	SAVE_4GPRS(3, r7)			/* user r3-r6 */
-	SAVE_4GPRS(8, r7)			/* user r8-r11 */
+	SAVE_GPR(8, r7)				/* user r8 */
+	SAVE_GPR(9, r7)				/* user r9 */
+	SAVE_GPR(10, r7)			/* user r10 */
 	ld	r3, PACATMSCRATCH(r13)		/* user r1 */
 	ld	r4, GPR7(r1)			/* user r7 */
-	ld	r5, GPR12(r1)			/* user r12 */
-	GET_SCRATCH0(6)				/* user r13 */
+	ld	r5, GPR11(r1)			/* user r11 */
+	ld	r6, GPR12(r1)			/* user r12 */
+	GET_SCRATCH0(8)				/* user r13 */
 	std	r3, GPR1(r7)
 	std	r4, GPR7(r7)
-	std	r5, GPR12(r7)
-	std	r6, GPR13(r7)
+	std	r5, GPR11(r7)
+	std	r6, GPR12(r7)
+	std	r8, GPR13(r7)
 
 	SAVE_NVGPRS(r7)				/* user r14-r31 */
 
@@ -235,14 +251,12 @@ dont_backup_fp:
 	std	r6, _XER(r7)
 
 
-	/* ******************** TAR, PPR, DSCR ********** */
+	/* ******************** TAR, DSCR ********** */
 	mfspr	r3, SPRN_TAR
-	mfspr	r4, SPRN_PPR
-	mfspr	r5, SPRN_DSCR
+	mfspr	r4, SPRN_DSCR
 
 	std	r3, THREAD_TM_TAR(r12)
-	std	r4, THREAD_TM_PPR(r12)
-	std	r5, THREAD_TM_DSCR(r12)
+	std	r4, THREAD_TM_DSCR(r12)
 
 	/* MSR and flags:  We don't change CRs, and we don't need to alter
 	 * MSR.
@@ -259,7 +273,7 @@ dont_backup_fp:
 	std	r3, THREAD_TM_TFHAR(r12)
 	std	r4, THREAD_TM_TFIAR(r12)
 
-	/* AMR and PPR are checkpointed too, but are unsupported by Linux. */
+	/* AMR is checkpointed too, but is unsupported by Linux. */
 
 	/* Restore original MSR/IRQ state & clear TM mode */
 	ld	r14, TM_FRAME_L0(r1)		/* Orig MSR */
@@ -275,6 +289,12 @@ dont_backup_fp:
 	mtcr	r4
 	mtlr	r0
 	ld	r2, 40(r1)
+
+	/* Load system default DSCR */
+	ld	r4, DSCR_DEFAULT@toc(r2)
+	ld	r0, 0(r4)
+	mtspr	SPRN_DSCR, r0
+
 	blr
 
 
@@ -359,25 +379,24 @@ dont_restore_fp:
 
 restore_gprs:
 
-	/* ******************** TAR, PPR, DSCR ********** */
-	ld	r4, THREAD_TM_TAR(r3)
-	ld	r5, THREAD_TM_PPR(r3)
-	ld	r6, THREAD_TM_DSCR(r3)
+	/* ******************** CR,LR,CCR,MSR ********** */
+	ld	r4, _CTR(r7)
+	ld	r5, _LINK(r7)
+	ld	r6, _CCR(r7)
+	ld	r8, _XER(r7)
 
-	mtspr	SPRN_TAR,	r4
-	mtspr	SPRN_PPR,	r5
-	mtspr	SPRN_DSCR,	r6
+	mtctr	r4
+	mtlr	r5
+	mtcr	r6
+	mtxer	r8
 
-	/* ******************** CR,LR,CCR,MSR ********** */
-	ld	r3, _CTR(r7)
-	ld	r4, _LINK(r7)
-	ld	r5, _CCR(r7)
-	ld	r6, _XER(r7)
+	/* ******************** TAR ******************** */
+	ld	r4, THREAD_TM_TAR(r3)
+	mtspr	SPRN_TAR,	r4
 
-	mtctr	r3
-	mtlr	r4
-	mtcr	r5
-	mtxer	r6
+	/* Load up the PPR and DSCR in GPRs only at this stage */
+	ld	r5, THREAD_TM_DSCR(r3)
+	ld	r6, THREAD_TM_PPR(r3)
 
 	/* Clear the MSR RI since we are about to change R1.  EE is already off
 	 */
@@ -385,19 +404,26 @@ restore_gprs:
 	mtmsrd	r4, 1
 
 	REST_4GPRS(0, r7)			/* GPR0-3 */
-	REST_GPR(4, r7)				/* GPR4-6 */
-	REST_GPR(5, r7)
-	REST_GPR(6, r7)
+	REST_GPR(4, r7)				/* GPR4 */
 	REST_4GPRS(8, r7)			/* GPR8-11 */
 	REST_2GPRS(12, r7)			/* GPR12-13 */
 
 	REST_NVGPRS(r7)				/* GPR14-31 */
 
-	ld	r7, GPR7(r7)			/* GPR7 */
+	/* Load up PPR and DSCR here so we don't run with user values for long
+	 */
+	mtspr	SPRN_DSCR, r5
+	mtspr	SPRN_PPR, r6
+
+	REST_GPR(5, r7)				/* GPR5-7 */
+	REST_GPR(6, r7)
+	ld	r7, GPR7(r7)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
 
+	HMT_MEDIUM
+
 	/* Our transactional state has now changed.
 	 *
 	 * Now just get out of here.  Transactional (current) state will be
@@ -420,6 +446,12 @@ restore_gprs:
 	mtcr	r4
 	mtlr	r0
 	ld	r2, 40(r1)
+
+	/* Load system default DSCR */
+	ld	r4, DSCR_DEFAULT@toc(r2)
+	ld	r0, 0(r4)
+	mtspr	SPRN_DSCR, r0
+
 	blr
 
 	/* ****************************************************************** */
-- 
cgit v1.2.3-70-g09d2