Merge branch 'perf/core' into perf/probes

Resolved merge conflict in tools/perf/Makefile

Merge reason: we want to queue up a dependent patch.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

9 files changed, 200 insertions, 98 deletions

diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index c31e5b534f0..d45be5b5ad4 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -51,6 +51,8 @@ static void __init mpc5200_simple_setup_arch(void)
 /* list of the supported boards */
 static char *board[] __initdata = {
 	"intercontrol,digsy-mtc",
+	"manroland,mucmc52",
+	"manroland,uc101",
 	"phytec,pcm030",
 	"phytec,pcm032",
 	"promess,motionpro",
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index 51fcae41f08..f9aee182e6f 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -132,12 +132,25 @@ static int __devinit ep8248e_mdio_probe(struct of_device *ofdev,
 		return -ENOMEM;
 
 	bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL);
+	if (bus->irq == NULL) {
+		ret = -ENOMEM;
+		goto err_free_bus;
+	}
 
 	bus->name = "ep8248e-mdio-bitbang";
 	bus->parent = &ofdev->dev;
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%x", res.start);
 
-	return of_mdiobus_register(bus, ofdev->node);
+	ret = of_mdiobus_register(bus, ofdev->node);
+	if (ret)
+		goto err_free_irq;
+
+	return 0;
+err_free_irq:
+	kfree(bus->irq);
+err_free_bus:
+	free_mdio_bitbang(bus);
+	return ret;
 }
 
 static int ep8248e_mdio_remove(struct of_device *ofdev)
diff --git a/arch/powerpc/platforms/iseries/Makefile b/arch/powerpc/platforms/iseries/Makefile
index cc7161ff166..ce014928d46 100644
--- a/arch/powerpc/platforms/iseries/Makefile
+++ b/arch/powerpc/platforms/iseries/Makefile
@@ -1,18 +1,9 @@
 EXTRA_CFLAGS	+= -mno-minimal-toc
 
-extra-y += dt.o
-
 obj-y += exception.o
-obj-y += hvlog.o hvlpconfig.o lpardata.o setup.o dt_mod.o mf.o lpevents.o \
+obj-y += hvlog.o hvlpconfig.o lpardata.o setup.o dt.o mf.o lpevents.o \
 	hvcall.o proc.o htab.o iommu.o misc.o irq.o
 obj-$(CONFIG_PCI) += pci.o
 obj-$(CONFIG_SMP) += smp.o
 obj-$(CONFIG_VIOPATH) += viopath.o vio.o
 obj-$(CONFIG_MODULES) += ksyms.o
-
-quiet_cmd_dt_strings = DT_STR  $@
-      cmd_dt_strings = $(OBJCOPY) --rename-section .rodata.str1.8=.dt_strings \
-				$< $@
-
-$(obj)/dt_mod.o:	$(obj)/dt.o
-	$(call if_changed,dt_strings)
diff --git a/arch/powerpc/platforms/iseries/dt.c b/arch/powerpc/platforms/iseries/dt.c
index c5a87a72057..7f45a51fe79 100644
--- a/arch/powerpc/platforms/iseries/dt.c
+++ b/arch/powerpc/platforms/iseries/dt.c
@@ -51,11 +51,16 @@
 
 /*
  * These are created by the linker script at the start and end
- * of the section containing all the strings from this file.
+ * of the section containing all the strings marked with the DS macro.
  */
 extern char __dt_strings_start[];
 extern char __dt_strings_end[];
 
+#define DS(s)	({	\
+	static const char __s[] __attribute__((section(".dt_strings"))) = s; \
+	__s;		\
+})
+
 struct iseries_flat_dt {
 	struct boot_param_header header;
 	u64 reserve_map[2];
@@ -64,9 +69,8 @@ struct iseries_flat_dt {
 static void * __initdata dt_data;
 
 /*
- * Putting these strings here keeps them out of the section
- * that we rename to .dt_strings using objcopy and capture
- * for the strings blob of the flattened device tree.
+ * Putting these strings here keeps them out of the .dt_strings section
+ * that we capture for the strings blob of the flattened device tree.
  */
 static char __initdata device_type_cpu[] = "cpu";
 static char __initdata device_type_memory[] = "memory";
@@ -173,7 +177,7 @@ static void __init dt_start_node(struct iseries_flat_dt *dt, const char *name)
 
 #define dt_end_node(dt) dt_push_u32(dt, OF_DT_END_NODE)
 
-static void __init dt_prop(struct iseries_flat_dt *dt, const char *name,
+static void __init __dt_prop(struct iseries_flat_dt *dt, const char *name,
 		const void *data, int len)
 {
 	unsigned long offset;
@@ -191,44 +195,32 @@ static void __init dt_prop(struct iseries_flat_dt *dt, const char *name,
 	/* The actual data. */
 	dt_push_bytes(dt, data, len);
 }
+#define dt_prop(dt, name, data, len)	__dt_prop((dt), DS(name), (data), (len))
 
-static void __init dt_prop_str(struct iseries_flat_dt *dt, const char *name,
-		const char *data)
-{
-	dt_prop(dt, name, data, strlen(data) + 1); /* + 1 for NULL */
-}
+#define dt_prop_str(dt, name, data)	\
+	dt_prop((dt), name, (data), strlen((data)) + 1); /* + 1 for NULL */
 
-static void __init dt_prop_u32(struct iseries_flat_dt *dt, const char *name,
+static void __init __dt_prop_u32(struct iseries_flat_dt *dt, const char *name,
 		u32 data)
 {
-	dt_prop(dt, name, &data, sizeof(u32));
+	__dt_prop(dt, name, &data, sizeof(u32));
 }
+#define dt_prop_u32(dt, name, data)	__dt_prop_u32((dt), DS(name), (data))
 
-static void __init __maybe_unused dt_prop_u64(struct iseries_flat_dt *dt,
-					      const char *name,
-		u64 data)
+static void __init __maybe_unused __dt_prop_u64(struct iseries_flat_dt *dt,
+		const char *name, u64 data)
 {
-	dt_prop(dt, name, &data, sizeof(u64));
+	__dt_prop(dt, name, &data, sizeof(u64));
 }
+#define dt_prop_u64(dt, name, data)	__dt_prop_u64((dt), DS(name), (data))
 
-static void __init dt_prop_u64_list(struct iseries_flat_dt *dt,
-		const char *name, u64 *data, int n)
-{
-	dt_prop(dt, name, data, sizeof(u64) * n);
-}
+#define dt_prop_u64_list(dt, name, data, n)	\
+	dt_prop((dt), name, (data), sizeof(u64) * (n))
 
-static void __init dt_prop_u32_list(struct iseries_flat_dt *dt,
-		const char *name, u32 *data, int n)
-{
-	dt_prop(dt, name, data, sizeof(u32) * n);
-}
+#define dt_prop_u32_list(dt, name, data, n)	\
+	dt_prop((dt), name, (data), sizeof(u32) * (n))
 
-#ifdef notyet
-static void __init dt_prop_empty(struct iseries_flat_dt *dt, const char *name)
-{
-	dt_prop(dt, name, NULL, 0);
-}
-#endif
+#define dt_prop_empty(dt, name)		dt_prop((dt), name, NULL, 0)
 
 static void __init dt_cpus(struct iseries_flat_dt *dt)
 {
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index c1427b3634e..383a5d0e981 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -14,68 +14,94 @@
 	
 #define STK_PARM(i)     (48 + ((i)-3)*8)
 
-#ifdef CONFIG_HCALL_STATS
+#ifdef CONFIG_TRACEPOINTS
+
+	.section	".toc","aw"
+
+	.globl hcall_tracepoint_refcount
+hcall_tracepoint_refcount:
+	.llong	0
+
+	.section	".text"
+
 /*
  * precall must preserve all registers.  use unused STK_PARM()
- * areas to save snapshots and opcode.
+ * areas to save snapshots and opcode. We branch around this
+ * in early init (eg when populating the MMU hashtable) by using an
+ * unconditional cpu feature.
  */
-#define HCALL_INST_PRECALL					\
-	std	r3,STK_PARM(r3)(r1);	/* save opcode */	\
-	mftb	r0;			/* get timebase and */	\
-	std     r0,STK_PARM(r5)(r1);	/* save for later */	\
+#define HCALL_INST_PRECALL(FIRST_REG)				\
 BEGIN_FTR_SECTION;						\
-	mfspr	r0,SPRN_PURR;		/* get PURR and */	\
-	std	r0,STK_PARM(r6)(r1);	/* save for later */	\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);
-	
+	b	1f;						\
+END_FTR_SECTION(0, 1);						\
+	ld      r12,hcall_tracepoint_refcount@toc(r2);		\
+	cmpdi	r12,0;						\
+	beq+	1f;						\
+	mflr	r0;						\
+	std	r3,STK_PARM(r3)(r1);				\
+	std	r4,STK_PARM(r4)(r1);				\
+	std	r5,STK_PARM(r5)(r1);				\
+	std	r6,STK_PARM(r6)(r1);				\
+	std	r7,STK_PARM(r7)(r1);				\
+	std	r8,STK_PARM(r8)(r1);				\
+	std	r9,STK_PARM(r9)(r1);				\
+	std	r10,STK_PARM(r10)(r1);				\
+	std	r0,16(r1);					\
+	addi	r4,r1,STK_PARM(FIRST_REG);			\
+	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
+	bl	.__trace_hcall_entry;				\
+	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
+	ld	r0,16(r1);					\
+	ld	r3,STK_PARM(r3)(r1);				\
+	ld	r4,STK_PARM(r4)(r1);				\
+	ld	r5,STK_PARM(r5)(r1);				\
+	ld	r6,STK_PARM(r6)(r1);				\
+	ld	r7,STK_PARM(r7)(r1);				\
+	ld	r8,STK_PARM(r8)(r1);				\
+	ld	r9,STK_PARM(r9)(r1);				\
+	ld	r10,STK_PARM(r10)(r1);				\
+	mtlr	r0;						\
+1:
+
 /*
  * postcall is performed immediately before function return which
  * allows liberal use of volatile registers.  We branch around this
  * in early init (eg when populating the MMU hashtable) by using an
  * unconditional cpu feature.
  */
-#define HCALL_INST_POSTCALL					\
+#define __HCALL_INST_POSTCALL					\
 BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
-	ld	r4,STK_PARM(r3)(r1);	/* validate opcode */	\
-	cmpldi	cr7,r4,MAX_HCALL_OPCODE;			\
-	bgt-	cr7,1f;						\
-								\
-	/* get time and PURR snapshots after hcall */		\
-	mftb	r7;			/* timebase after */	\
-BEGIN_FTR_SECTION;						\
-	mfspr	r8,SPRN_PURR;		/* PURR after */	\
-	ld	r6,STK_PARM(r6)(r1);	/* PURR before */	\
-	subf	r6,r6,r8;		/* delta */		\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
-	ld	r5,STK_PARM(r5)(r1);	/* timebase before */	\
-	subf	r5,r5,r7;		/* time delta */	\
-								\
-	/* calculate address of stat structure r4 = opcode */	\
-	srdi	r4,r4,2;		/* index into array */	\
-	mulli	r4,r4,HCALL_STAT_SIZE;				\
-	LOAD_REG_ADDR(r7, per_cpu__hcall_stats);		\
-	add	r4,r4,r7;					\
-	ld	r7,PACA_DATA_OFFSET(r13); /* per cpu offset */	\
-	add	r4,r4,r7;					\
-								\
-	/* update stats	*/					\
-	ld	r7,HCALL_STAT_CALLS(r4); /* count */		\
-	addi	r7,r7,1;					\
-	std	r7,HCALL_STAT_CALLS(r4);			\
-	ld      r7,HCALL_STAT_TB(r4);	/* timebase */		\
-	add	r7,r7,r5;					\
-	std	r7,HCALL_STAT_TB(r4);				\
-BEGIN_FTR_SECTION;						\
-	ld	r7,HCALL_STAT_PURR(r4);	/* PURR */		\
-	add	r7,r7,r6;					\
-	std	r7,HCALL_STAT_PURR(r4);				\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
+	ld      r12,hcall_tracepoint_refcount@toc(r2);		\
+	cmpdi	r12,0;						\
+	beq+	1f;						\
+	mflr	r0;						\
+	ld	r6,STK_PARM(r3)(r1);				\
+	std	r3,STK_PARM(r3)(r1);				\
+	mr	r4,r3;						\
+	mr	r3,r6;						\
+	std	r0,16(r1);					\
+	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
+	bl	.__trace_hcall_exit;				\
+	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
+	ld	r0,16(r1);					\
+	ld	r3,STK_PARM(r3)(r1);				\
+	mtlr	r0;						\
 1:
+
+#define HCALL_INST_POSTCALL_NORETS				\
+	li	r5,0;						\
+	__HCALL_INST_POSTCALL
+
+#define HCALL_INST_POSTCALL(BUFREG)				\
+	mr	r5,BUFREG;					\
+	__HCALL_INST_POSTCALL
+
 #else
-#define HCALL_INST_PRECALL
-#define HCALL_INST_POSTCALL
+#define HCALL_INST_PRECALL(FIRST_ARG)
+#define HCALL_INST_POSTCALL_NORETS
+#define HCALL_INST_POSTCALL(BUFREG)
 #endif
 
 	.text
@@ -86,11 +112,11 @@ _GLOBAL(plpar_hcall_norets)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r4)
 
 	HVSC				/* invoke the hypervisor */
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL_NORETS
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
@@ -102,7 +128,7 @@ _GLOBAL(plpar_hcall)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r5)
 
 	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
 
@@ -121,7 +147,7 @@ _GLOBAL(plpar_hcall)
 	std	r6, 16(r12)
 	std	r7, 24(r12)
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL(r12)
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
@@ -168,7 +194,7 @@ _GLOBAL(plpar_hcall9)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r5)
 
 	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
 
@@ -196,7 +222,7 @@ _GLOBAL(plpar_hcall9)
 	std	r11,56(r12)
 	std	r0, 64(r12)
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL(r12)
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index 3631a4f277e..2f58c71b725 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -26,6 +26,7 @@
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
 #include <asm/cputable.h>
+#include <asm/trace.h>
 
 DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats);
 
@@ -100,6 +101,35 @@ static const struct file_operations hcall_inst_seq_fops = {
 #define	HCALL_ROOT_DIR		"hcall_inst"
 #define CPU_NAME_BUF_SIZE	32
 
+
+static void probe_hcall_entry(unsigned long opcode, unsigned long *args)
+{
+	struct hcall_stats *h;
+
+	if (opcode > MAX_HCALL_OPCODE)
+		return;
+
+	h = &get_cpu_var(hcall_stats)[opcode / 4];
+	h->tb_start = mftb();
+	h->purr_start = mfspr(SPRN_PURR);
+}
+
+static void probe_hcall_exit(unsigned long opcode, unsigned long retval,
+			     unsigned long *retbuf)
+{
+	struct hcall_stats *h;
+
+	if (opcode > MAX_HCALL_OPCODE)
+		return;
+
+	h = &__get_cpu_var(hcall_stats)[opcode / 4];
+	h->num_calls++;
+	h->tb_total = mftb() - h->tb_start;
+	h->purr_total = mfspr(SPRN_PURR) - h->purr_start;
+
+	put_cpu_var(hcall_stats);
+}
+
 static int __init hcall_inst_init(void)
 {
 	struct dentry *hcall_root;
@@ -110,6 +140,14 @@ static int __init hcall_inst_init(void)
 	if (!firmware_has_feature(FW_FEATURE_LPAR))
 		return 0;
 
+	if (register_trace_hcall_entry(probe_hcall_entry))
+		return -EINVAL;
+
+	if (register_trace_hcall_exit(probe_hcall_exit)) {
+		unregister_trace_hcall_entry(probe_hcall_entry);
+		return -EINVAL;
+	}
+
 	hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL);
 	if (!hcall_root)
 		return -ENOMEM;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 903eb9eec68..0707653612b 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -39,6 +39,7 @@
 #include <asm/cputable.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
+#include <asm/trace.h>
 
 #include "plpar_wrappers.h"
 #include "pseries.h"
@@ -661,3 +662,35 @@ void arch_free_page(struct page *page, int order)
 EXPORT_SYMBOL(arch_free_page);
 
 #endif
+
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * We optimise our hcall path by placing hcall_tracepoint_refcount
+ * directly in the TOC so we can check if the hcall tracepoints are
+ * enabled via a single load.
+ */
+
+/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
+extern long hcall_tracepoint_refcount;
+
+void hcall_tracepoint_regfunc(void)
+{
+	hcall_tracepoint_refcount++;
+}
+
+void hcall_tracepoint_unregfunc(void)
+{
+	hcall_tracepoint_refcount--;
+}
+
+void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
+{
+	trace_hcall_entry(opcode, args);
+}
+
+void __trace_hcall_exit(long opcode, unsigned long retval,
+			unsigned long *retbuf)
+{
+	trace_hcall_exit(opcode, retval, retbuf);
+}
+#endif
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index bf2e1ac4130..1164c3430f2 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -432,8 +432,6 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		/* Read config space back so we can restore after reset */
 		read_msi_msg(virq, &msg);
 		entry->msg = msg;
-
-		unmask_msi_irq(virq);
 	}
 
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 419f8a637ff..b9bf0eedccf 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/radix-tree.h>
 #include <linux/cpu.h>
+#include <linux/msi.h>
 #include <linux/of.h>
 
 #include <asm/firmware.h>
@@ -219,6 +220,14 @@ static void xics_unmask_irq(unsigned int virq)
 
 static unsigned int xics_startup(unsigned int virq)
 {
+	/*
+	 * The generic MSI code returns with the interrupt disabled on the
+	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
+	 * at that level, so we do it here by hand.
+	 */
+	if (irq_to_desc(virq)->msi_desc)
+		unmask_msi_irq(virq);
+
 	/* unmask it */
 	xics_unmask_irq(virq);
 	return 0;