[PATCH 1/7] powerpc: Initialise PMU related regs on Power8

[PATCH 1/7] powerpc: Initialise PMU related regs on Power8

[Michael Ellerman]

For both HV and guest kernels, intialise PMU regs to something sane.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 arch/powerpc/include/asm/reg.h        |    6 ++++++
 arch/powerpc/kernel/cpu_setup_power.S |   21 ++++++++++++++++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4ae2d44..5735ebb 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -271,6 +271,7 @@
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
 #define   HFSCR_TAR	(1 << (63-55)) /* Enable Target Address Register */
 #define   HFSCR_TM	(1 << (63-58)) /* Enable Transactional Memory */
+#define   HFSCR_PM	(1 << (63-60)) /* Enable prob/priv access to PMU SPRs */
 #define   HFSCR_DSCR	(1 << (63-61)) /* Enable Data Stream Control Register */
 #define   HFSCR_VECVSX	(1 << (63-62)) /* Enable VMX/VSX  */
 #define   HFSCR_FP	(1 << (63-63)) /* Enable Floating Point */
@@ -637,6 +638,7 @@
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
+#define SPRN_MMCR2	769
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -655,6 +657,10 @@
 #define   POWER7P_MMCRA_SIAR_VALID 0x10000000	/* P7+ SIAR contents valid */
 #define   POWER7P_MMCRA_SDAR_VALID 0x08000000	/* P7+ SDAR contents valid */
 
+#define SPRN_MMCRH	316	/* Hypervisor monitor mode control register */
+#define SPRN_MMCRS	894	/* Supervisor monitor mode control register */
+#define SPRN_MMCRC	851	/* Core monitor mode control register */
+
 #define SPRN_PMC1	787
 #define SPRN_PMC2	788
 #define SPRN_PMC3	789
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 2e6ad11..02a6945 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -49,6 +49,7 @@ _GLOBAL(__restore_cpu_power7)
 _GLOBAL(__setup_cpu_power8)
 	mflr	r11
 	bl	__init_FSCR
+	bl	__init_PMU
 	bl	__init_hvmode_206
 	mtlr	r11
 	beqlr
@@ -59,12 +60,14 @@ _GLOBAL(__setup_cpu_power8)
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_TLB
+	bl	__init_PMU_HV
 	mtlr	r11
 	blr
 
 _GLOBAL(__restore_cpu_power8)
 	mflr	r11
 	bl	__init_FSCR
+	bl	__init_PMU
 	mfmsr	r3
 	rldicl.	r0,r3,4,63
 	beqlr
@@ -75,6 +78,7 @@ _GLOBAL(__restore_cpu_power8)
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_TLB
+	bl	__init_PMU_HV
 	mtlr	r11
 	blr
 
@@ -124,7 +128,7 @@ __init_FSCR:
 
 __init_HFSCR:
 	mfspr	r3,SPRN_HFSCR
-	ori	r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP
+	ori	r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_PM
 	mtspr	SPRN_HFSCR,r3
 	blr
 
@@ -139,3 +143,18 @@ __init_TLB:
 	bdnz	2b
 	ptesync
 1:	blr
+
+__init_PMU_HV:
+	li	r5,0
+	mtspr	SPRN_MMCRC,r5
+	mtspr	SPRN_MMCRH,r5
+	blr
+
+__init_PMU:
+	li	r5,0
+	mtspr	SPRN_MMCRS,r5
+	mtspr	SPRN_MMCRA,r5
+	mtspr	SPRN_MMCR0,r5
+	mtspr	SPRN_MMCR1,r5
+	mtspr	SPRN_MMCR2,r5
+	blr
-- 
1.7.10.4

[PATCH 2/7] powerpc/perf: Add an explict flag indicating presence of SLOT field

[Michael Ellerman]

In perf_ip_adjust() we potentially use the MMCRA[SLOT] field to adjust
the reported IP of a sampled instruction.

Currently the logic is written so that if the backend does NOT have
the PPMU_ALT_SIPR flag set then we assume MMCRA[SLOT] exists.

However on power8 we do not want to set ALT_SIPR (it's in a third
location), and we also do not have MMCRA[SLOT].

So add a new flag which only indicates whether MMCRA[SLOT] exists.

Naively we'd set it on everything except power6/7, because they set
ALT_SIPR, and we've reversed the polarity of the flag. But it's more
complicated than that.

mpc7450 is 32-bit, and uses its own version of perf_ip_adjust()
which doesn't use MMCRA[SLOT], so it doesn't need the new flag set and
the behaviour is unchanged.

PPC970 (and I assume power4) don't have MMCRA[SLOT], so shouldn't have
the new flag set. This is a behaviour change on those cpus, though we
were probably getting lucky and the bits in question were 0.

power5 and power5+ set the new flag, behaviour unchanged.

power6 & power7 do not set the new flag, behaviour unchanged.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 arch/powerpc/include/asm/perf_event_server.h |    1 +
 arch/powerpc/perf/core-book3s.c              |    3 ++-
 arch/powerpc/perf/power5+-pmu.c              |    2 +-
 arch/powerpc/perf/power5-pmu.c               |    1 +
 4 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index d0aec72..7074aec 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -52,6 +52,7 @@ struct power_pmu {
 #define PPMU_NO_SIPR		0x00000004 /* no SIPR/HV in MMCRA at all */
 #define PPMU_NO_CONT_SAMPLING	0x00000008 /* no continuous sampling */
 #define PPMU_SIAR_VALID		0x00000010 /* Processor has SIAR Valid bit */
+#define PPMU_HAS_SSLOT		0x00000020 /* Has sampled slot in MMCRA */
 
 /*
  * Values for flags to get_alternatives()
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 65362e9..eb64480 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -98,11 +98,12 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
 {
 	unsigned long mmcra = regs->dsisr;
 
-	if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) {
+	if ((ppmu->flags & PPMU_HAS_SSLOT) && (mmcra & MMCRA_SAMPLE_ENABLE)) {
 		unsigned long slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT;
 		if (slot > 1)
 			return 4 * (slot - 1);
 	}
+
 	return 0;
 }
 
diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index a8757ba..b03b6dc 100644
--- a/arch/powerpc/perf/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
@@ -671,7 +671,7 @@ static struct power_pmu power5p_pmu = {
 	.get_alternatives	= power5p_get_alternatives,
 	.disable_pmc		= power5p_disable_pmc,
 	.limited_pmc_event	= power5p_limited_pmc_event,
-	.flags			= PPMU_LIMITED_PMC5_6,
+	.flags			= PPMU_LIMITED_PMC5_6 | PPMU_HAS_SSLOT,
 	.n_generic		= ARRAY_SIZE(power5p_generic_events),
 	.generic_events		= power5p_generic_events,
 	.cache_events		= &power5p_cache_events,
diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index e7f06eb..1e8ce42 100644
--- a/arch/powerpc/perf/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
@@ -615,6 +615,7 @@ static struct power_pmu power5_pmu = {
 	.n_generic		= ARRAY_SIZE(power5_generic_events),
 	.generic_events		= power5_generic_events,
 	.cache_events		= &power5_cache_events,
+	.flags			= PPMU_HAS_SSLOT,
 };
 
 static int __init init_power5_pmu(void)
-- 
1.7.10.4

[PATCH 3/7] powerpc/perf: Convert mmcra_sipr/sihv() to regs_sipr/sihv()

[Michael Ellerman]

On power8 the SIPR and SIHV are not in MMCRA, so convert the routines
to take regs and change the names accordingly.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 arch/powerpc/perf/core-book3s.c |   20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index eb64480..2417fe2 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -131,24 +131,24 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 		*addrp = mfspr(SPRN_SDAR);
 }
 
-static bool mmcra_sihv(unsigned long mmcra)
+static bool regs_sihv(struct pt_regs *regs)
 {
 	unsigned long sihv = MMCRA_SIHV;
 
 	if (ppmu->flags & PPMU_ALT_SIPR)
 		sihv = POWER6_MMCRA_SIHV;
 
-	return !!(mmcra & sihv);
+	return !!(regs->dsisr & sihv);
 }
 
-static bool mmcra_sipr(unsigned long mmcra)
+static bool regs_sipr(struct pt_regs *regs)
 {
 	unsigned long sipr = MMCRA_SIPR;
 
 	if (ppmu->flags & PPMU_ALT_SIPR)
 		sipr = POWER6_MMCRA_SIPR;
 
-	return !!(mmcra & sipr);
+	return !!(regs->dsisr & sipr);
 }
 
 static inline u32 perf_flags_from_msr(struct pt_regs *regs)
@@ -162,7 +162,6 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
-	unsigned long mmcra = regs->dsisr;
 	unsigned long use_siar = regs->result;
 
 	if (!use_siar)
@@ -182,10 +181,12 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 	}
 
 	/* PR has priority over HV, so order below is important */
-	if (mmcra_sipr(mmcra))
+	if (regs_sipr(regs))
 		return PERF_RECORD_MISC_USER;
-	if (mmcra_sihv(mmcra) && (freeze_events_kernel != MMCR0_FCHV))
+
+	if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV))
 		return PERF_RECORD_MISC_HYPERVISOR;
+
 	return PERF_RECORD_MISC_KERNEL;
 }
 
@@ -201,6 +202,8 @@ static inline void perf_read_regs(struct pt_regs *regs)
 	int marked = mmcra & MMCRA_SAMPLE_ENABLE;
 	int use_siar;
 
+	regs->dsisr = mmcra;
+
 	/*
 	 * If this isn't a PMU exception (eg a software event) the SIAR is
 	 * not valid. Use pt_regs.
@@ -224,12 +227,11 @@ static inline void perf_read_regs(struct pt_regs *regs)
 		use_siar = 1;
 	else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
 		use_siar = 0;
-	else if (!(ppmu->flags & PPMU_NO_SIPR) && mmcra_sipr(mmcra))
+	else if (!(ppmu->flags & PPMU_NO_SIPR) && regs_sipr(regs))
 		use_siar = 0;
 	else
 		use_siar = 1;
 
-	regs->dsisr = mmcra;
 	regs->result = use_siar;
 }
 
-- 
1.7.10.4

[PATCH 4/7] powerpc/perf: Add an accessor for regs->result

[Michael Ellerman]

Add an accessor for regs->result so we can use it to store more flags in
future.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 arch/powerpc/perf/core-book3s.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 2417fe2..5d30001 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -89,6 +89,11 @@ static inline int siar_valid(struct pt_regs *regs)
 
 #endif /* CONFIG_PPC32 */
 
+static bool regs_use_siar(struct pt_regs *regs)
+{
+	return !!(regs->result & 1);
+}
+
 /*
  * Things that are specific to 64-bit implementations.
  */
@@ -162,7 +167,7 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
-	unsigned long use_siar = regs->result;
+	bool use_siar = regs_use_siar(regs);
 
 	if (!use_siar)
 		return perf_flags_from_msr(regs);
@@ -1425,7 +1430,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  */
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	unsigned long use_siar = regs->result;
+	bool use_siar = regs_use_siar(regs);
 
 	if (use_siar && siar_valid(regs))
 		return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
-- 
1.7.10.4

[PATCH 5/7] powerpc/perf: Add regs_no_sipr()

[Michael Ellerman]

On power8 the presence or absence of SIPR depends on settings at runtime,
so convert to using a dynamic flag for NO_SIPR. Existing backends that
set NO_SIPR unconditionally set the dynamic flag obviously.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 arch/powerpc/perf/core-book3s.c |   15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 5d30001..1c13c3d 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -156,6 +156,11 @@ static bool regs_sipr(struct pt_regs *regs)
 	return !!(regs->dsisr & sipr);
 }
 
+static bool regs_no_sipr(struct pt_regs *regs)
+{
+	return !!(regs->result & 2);
+}
+
 static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 {
 	if (regs->msr & MSR_PR)
@@ -178,7 +183,7 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 	 * SIAR which should give slightly more reliable
 	 * results
 	 */
-	if (ppmu->flags & PPMU_NO_SIPR) {
+	if (regs_no_sipr(regs)) {
 		unsigned long siar = mfspr(SPRN_SIAR);
 		if (siar >= PAGE_OFFSET)
 			return PERF_RECORD_MISC_KERNEL;
@@ -208,6 +213,10 @@ static inline void perf_read_regs(struct pt_regs *regs)
 	int use_siar;
 
 	regs->dsisr = mmcra;
+	regs->result = 0;
+
+	if (ppmu->flags & PPMU_NO_SIPR)
+		regs->result |= 2;
 
 	/*
 	 * If this isn't a PMU exception (eg a software event) the SIAR is
@@ -232,12 +241,12 @@ static inline void perf_read_regs(struct pt_regs *regs)
 		use_siar = 1;
 	else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
 		use_siar = 0;
-	else if (!(ppmu->flags & PPMU_NO_SIPR) && regs_sipr(regs))
+	else if (!regs_no_sipr(regs) && regs_sipr(regs))
 		use_siar = 0;
 	else
 		use_siar = 1;
 
-	regs->result = use_siar;
+	regs->result |= use_siar;
 }
 
 /*
-- 
1.7.10.4

[PATCH 6/7] powerpc/perf: Add support for SIER

[Michael Ellerman]

On power8 we have a new SIER (Sampled Instruction Event Register), which
captures information about instructions when we have random sampling
enabled.

Add support for loading the SIER into pt_regs, overloading regs->dar.
Also set the new NO_SIPR flag in regs->result if we don't have SIPR.

Update regs_sihv/sipr() to look for SIPR/SIHV in SIER.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 arch/powerpc/include/asm/perf_event_server.h |    1 +
 arch/powerpc/include/asm/reg.h               |    5 +++++
 arch/powerpc/perf/core-book3s.c              |   19 +++++++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 7074aec..57b42da 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -53,6 +53,7 @@ struct power_pmu {
 #define PPMU_NO_CONT_SAMPLING	0x00000008 /* no continuous sampling */
 #define PPMU_SIAR_VALID		0x00000010 /* Processor has SIAR Valid bit */
 #define PPMU_HAS_SSLOT		0x00000020 /* Has sampled slot in MMCRA */
+#define PPMU_HAS_SIER		0x00000040 /* Has SIER */
 
 /*
  * Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 5735ebb..5c6fbe2 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -671,6 +671,11 @@
 #define SPRN_PMC8	794
 #define SPRN_SIAR	780
 #define SPRN_SDAR	781
+#define SPRN_SIER	784
+#define   SIER_SIPR		0x2000000	/* Sampled MSR_PR */
+#define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
+#define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
+#define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
 
 #define SPRN_PA6T_MMCR0 795
 #define   PA6T_MMCR0_EN0	0x0000000000000001UL
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 1c13c3d..4ac6e64 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -140,6 +140,9 @@ static bool regs_sihv(struct pt_regs *regs)
 {
 	unsigned long sihv = MMCRA_SIHV;
 
+	if (ppmu->flags & PPMU_HAS_SIER)
+		return !!(regs->dar & SIER_SIHV);
+
 	if (ppmu->flags & PPMU_ALT_SIPR)
 		sihv = POWER6_MMCRA_SIHV;
 
@@ -150,6 +153,9 @@ static bool regs_sipr(struct pt_regs *regs)
 {
 	unsigned long sipr = MMCRA_SIPR;
 
+	if (ppmu->flags & PPMU_HAS_SIER)
+		return !!(regs->dar & SIER_SIPR);
+
 	if (ppmu->flags & PPMU_ALT_SIPR)
 		sipr = POWER6_MMCRA_SIPR;
 
@@ -203,6 +209,7 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 /*
  * Overload regs->dsisr to store MMCRA so we only need to read it once
  * on each interrupt.
+ * Overload regs->dar to store SIER if we have it.
  * Overload regs->result to specify whether we should use the MSR (result
  * is zero) or the SIAR (result is non zero).
  */
@@ -219,6 +226,18 @@ static inline void perf_read_regs(struct pt_regs *regs)
 		regs->result |= 2;
 
 	/*
+	 * On power8 if we're in random sampling mode, the SIER is updated.
+	 * If we're in continuous sampling mode, we don't have SIPR.
+	 */
+	if (ppmu->flags & PPMU_HAS_SIER) {
+		if (marked)
+			regs->dar = mfspr(SPRN_SIER);
+		else
+			regs->result |= 2;
+	}
+
+
+	/*
 	 * If this isn't a PMU exception (eg a software event) the SIAR is
 	 * not valid. Use pt_regs.
 	 *
-- 
1.7.10.4

[PATCH 7/7] powerpc/perf: Power8 PMU support

[Michael Ellerman]

This patch adds support for the power8 PMU to perf.

Work is ongoing to add generic cache events.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 arch/powerpc/perf/Makefile     |    3 +-
 arch/powerpc/perf/power8-pmu.c |  537 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 539 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/perf/power8-pmu.c

diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index af3fac2..472db18 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -4,7 +4,8 @@ obj-$(CONFIG_PERF_EVENTS)	+= callchain.o
 
 obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
-				   power5+-pmu.o power6-pmu.o power7-pmu.o
+				   power5+-pmu.o power6-pmu.o power7-pmu.o \
+				   power8-pmu.o
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
new file mode 100644
index 0000000..c6aa713
--- /dev/null
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -0,0 +1,537 @@
+/*
+ * Performance counter support for POWER8 processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2013 Michael Ellerman, IBM Corporation.
+ *
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <asm/firmware.h>
+
+
+/*
+ * Some power8 event codes.
+ */
+#define PM_CYC				0x0001e
+#define PM_GCT_NOSLOT_CYC		0x100f8
+#define PM_CMPLU_STALL			0x4000a
+#define PM_INST_CMPL			0x00002
+#define PM_BRU_FIN			0x10068
+#define PM_BR_MPRED_CMPL		0x400f6
+
+
+/*
+ * Raw event encoding for POWER8:
+ *
+ *        60        56        52        48        44        40        36        32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *                                     [      thresh_cmp     ]   [  thresh_ctl   ]
+ *                                                                       |
+ *                                       thresh start/stop OR FAB match -*
+ *
+ *        28        24        20        16        12         8         4         0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *   [   ] [  sample ]   [cache]   [ pmc ]   [unit ]   c     m   [    pmcxsel    ]
+ *     |        |           |                          |     |
+ *     |        |           |                          |     *- mark
+ *     |        |           *- L1/L2/L3 cache_sel      |
+ *     |        |                                      |
+ *     |        *- sampling mode for marked events     *- combine
+ *     |
+ *     *- thresh_sel
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit    (PMCxUNIT)
+ * MMCR1[x]   = combine (PMCxCOMB)
+ *
+ * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011
+ *	# PM_MRK_FAB_RSP_MATCH
+ *	MMCR1[20:27] = thresh_ctl   (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
+ * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001
+ *	# PM_MRK_FAB_RSP_MATCH_CYC
+ *	MMCR1[20:27] = thresh_ctl   (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
+ * else
+ *	MMCRA[48:55] = thresh_ctl   (THRESH START/END)
+ *
+ * if thresh_sel:
+ *	MMCRA[45:47] = thresh_sel
+ *
+ * if thresh_cmp:
+ *	MMCRA[22:24] = thresh_cmp[0:2]
+ *	MMCRA[25:31] = thresh_cmp[3:9]
+ *
+ * if unit == 6 or unit == 7
+ *	MMCRC[53:55] = cache_sel[1:3]      (L2EVENT_SEL)
+ * else if unit == 8 or unit == 9:
+ *	if cache_sel[0] == 0: # L3 bank
+ *		MMCRC[47:49] = cache_sel[1:3]  (L3EVENT_SEL0)
+ *	else if cache_sel[0] == 1:
+ *		MMCRC[50:51] = cache_sel[2:3]  (L3EVENT_SEL1)
+ * else if cache_sel[1]: # L1 event
+ *	MMCR1[16] = cache_sel[2]
+ *	MMCR1[17] = cache_sel[3]
+ *
+ * if mark:
+ *	MMCRA[63]    = 1		(SAMPLE_ENABLE)
+ *	MMCRA[57:59] = sample[0:2]	(RAND_SAMP_ELIG)
+ *	MMCRA[61:62] = sample[3:4]	(RAND_SAMP_MODE)
+ *
+ */
+
+#define EVENT_THR_CMP_SHIFT	40	/* Threshold CMP value */
+#define EVENT_THR_CMP_MASK	0x3ff
+#define EVENT_THR_CTL_SHIFT	32	/* Threshold control value (start/stop) */
+#define EVENT_THR_CTL_MASK	0xffull
+#define EVENT_THR_SEL_SHIFT	29	/* Threshold select value */
+#define EVENT_THR_SEL_MASK	0x7
+#define EVENT_THRESH_SHIFT	29	/* All threshold bits */
+#define EVENT_THRESH_MASK	0x1fffffull
+#define EVENT_SAMPLE_SHIFT	24	/* Sampling mode & eligibility */
+#define EVENT_SAMPLE_MASK	0x1f
+#define EVENT_CACHE_SEL_SHIFT	20	/* L2/L3 cache select */
+#define EVENT_CACHE_SEL_MASK	0xf
+#define EVENT_IS_L1		(4 << EVENT_CACHE_SEL_SHIFT)
+#define EVENT_PMC_SHIFT		16	/* PMC number (1-based) */
+#define EVENT_PMC_MASK		0xf
+#define EVENT_UNIT_SHIFT	12	/* Unit */
+#define EVENT_UNIT_MASK		0xf
+#define EVENT_COMBINE_SHIFT	11	/* Combine bit */
+#define EVENT_COMBINE_MASK	0x1
+#define EVENT_MARKED_SHIFT	8	/* Marked bit */
+#define EVENT_MARKED_MASK	0x1
+#define EVENT_IS_MARKED		(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
+#define EVENT_PSEL_MASK		0xff	/* PMCxSEL value */
+
+/*
+ * Layout of constraint bits:
+ *
+ *        60        56        52        48        44        40        36        32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *   [   fab_match   ]         [       thresh_cmp      ] [   thresh_ctl    ] [   ]
+ *                                                                             |
+ *                                                                 thresh_sel -*
+ *
+ *        28        24        20        16        12         8         4         0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *                       [ ]   [  sample ]   [     ]   [6] [5]   [4] [3]   [2] [1]
+ *                        |                     |
+ *      L1 I/D qualifier -*                     |      Count of events for each PMC.
+ *                                              |        p1, p2, p3, p4, p5, p6.
+ *                     nc - number of counters -*
+ *
+ * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints
+ * we want the low bit of each field to be added to any existing value.
+ *
+ * Everything else is a value field.
+ */
+
+#define CNST_FAB_MATCH_VAL(v)	(((v) & EVENT_THR_CTL_MASK) << 56)
+#define CNST_FAB_MATCH_MASK	CNST_FAB_MATCH_VAL(EVENT_THR_CTL_MASK)
+
+/* We just throw all the threshold bits into the constraint */
+#define CNST_THRESH_VAL(v)	(((v) & EVENT_THRESH_MASK) << 32)
+#define CNST_THRESH_MASK	CNST_THRESH_VAL(EVENT_THRESH_MASK)
+
+#define CNST_L1_QUAL_VAL(v)	(((v) & 3) << 22)
+#define CNST_L1_QUAL_MASK	CNST_L1_QUAL_VAL(3)
+
+#define CNST_SAMPLE_VAL(v)	(((v) & EVENT_SAMPLE_MASK) << 16)
+#define CNST_SAMPLE_MASK	CNST_SAMPLE_VAL(EVENT_SAMPLE_MASK)
+
+/*
+ * For NC we are counting up to 4 events. This requires three bits, and we need
+ * the fifth event to overflow and set the 4th bit. To achieve that we bias the
+ * fields by 3 in test_adder.
+ */
+#define CNST_NC_SHIFT		12
+#define CNST_NC_VAL		(1 << CNST_NC_SHIFT)
+#define CNST_NC_MASK		(8 << CNST_NC_SHIFT)
+#define POWER8_TEST_ADDER	(3 << CNST_NC_SHIFT)
+
+/*
+ * For the per-PMC fields we have two bits. The low bit is added, so if two
+ * events ask for the same PMC the sum will overflow, setting the high bit,
+ * indicating an error. So our mask sets the high bit.
+ */
+#define CNST_PMC_SHIFT(pmc)	((pmc - 1) * 2)
+#define CNST_PMC_VAL(pmc)	(1 << CNST_PMC_SHIFT(pmc))
+#define CNST_PMC_MASK(pmc)	(2 << CNST_PMC_SHIFT(pmc))
+
+/* Our add_fields is defined as: */
+#define POWER8_ADD_FIELDS	\
+	CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \
+	CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL
+
+
+/* Bits in MMCR1 for POWER8 */
+#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_DC_QUAL_SHIFT		47
+#define MMCR1_IC_QUAL_SHIFT		46
+
+/* Bits in MMCRA for POWER8 */
+#define MMCRA_SAMP_MODE_SHIFT		1
+#define MMCRA_SAMP_ELIG_SHIFT		4
+#define MMCRA_THR_CTL_SHIFT		8
+#define MMCRA_THR_SEL_SHIFT		16
+#define MMCRA_THR_CMP_SHIFT		32
+#define MMCRA_SDAR_MODE_TLB		(1ull << 42)
+
+
+static inline bool event_is_fab_match(u64 event)
+{
+	/* Only check pmc, unit and pmcxsel, ignore the edge bit (0) */
+	event &= 0xff0fe;
+
+	/* PM_MRK_FAB_RSP_MATCH & PM_MRK_FAB_RSP_MATCH_CYC */
+	return (event == 0x30056 || event == 0x4f052);
+}
+
+static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
+{
+	unsigned int unit, pmc, cache;
+	unsigned long mask, value;
+
+	mask = value = 0;
+
+	pmc   = (event >> EVENT_PMC_SHIFT)       & EVENT_PMC_MASK;
+	unit  = (event >> EVENT_UNIT_SHIFT)      & EVENT_UNIT_MASK;
+	cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK;
+
+	if (pmc) {
+		if (pmc > 6)
+			return -1;
+
+		mask  |= CNST_PMC_MASK(pmc);
+		value |= CNST_PMC_VAL(pmc);
+
+		if (pmc >= 5 && event != 0x500fa && event != 0x600f4)
+			return -1;
+	}
+
+	if (pmc <= 4) {
+		/*
+		 * Add to number of counters in use. Note this includes events with
+		 * a PMC of 0 - they still need a PMC, it's just assigned later.
+		 * Don't count events on PMC 5 & 6, there is only one valid event
+		 * on each of those counters, and they are handled above.
+		 */
+		mask  |= CNST_NC_MASK;
+		value |= CNST_NC_VAL;
+	}
+
+	if (unit >= 6 && unit <= 9) {
+		/*
+		 * L2/L3 events contain a cache selector field, which is
+		 * supposed to be programmed into MMCRC. However MMCRC is only
+		 * HV writable, and there is no API for guest kernels to modify
+		 * it. The solution is for the hypervisor to initialise the
+		 * field to zeroes, and for us to only ever allow events that
+		 * have a cache selector of zero.
+		 */
+		if (cache)
+			return -1;
+
+	} else if (event & EVENT_IS_L1) {
+		mask  |= CNST_L1_QUAL_MASK;
+		value |= CNST_L1_QUAL_VAL(cache);
+	}
+
+	if (event & EVENT_IS_MARKED) {
+		mask  |= CNST_SAMPLE_MASK;
+		value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
+	}
+
+	/*
+	 * Special case for PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
+	 * the threshold control bits are used for the match value.
+	 */
+	if (event_is_fab_match(event)) {
+		mask  |= CNST_FAB_MATCH_MASK;
+		value |= CNST_FAB_MATCH_VAL(event >> EVENT_THR_CTL_SHIFT);
+	} else {
+		/*
+		 * Check the mantissa upper two bits are not zero, unless the
+		 * exponent is also zero. See the THRESH_CMP_MANTISSA doc.
+		 */
+		unsigned int cmp, exp;
+
+		cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
+		exp = cmp >> 7;
+
+		if (exp && (cmp & 0x60) == 0)
+			return -1;
+
+		mask  |= CNST_THRESH_MASK;
+		value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
+	}
+
+	*maskp = mask;
+	*valp = value;
+
+	return 0;
+}
+
+static int power8_compute_mmcr(u64 event[], int n_ev,
+			       unsigned int hwc[], unsigned long mmcr[])
+{
+	unsigned long mmcra, mmcr1, unit, combine, psel, cache, val;
+	unsigned int pmc, pmc_inuse;
+	int i;
+
+	pmc_inuse = 0;
+
+	/* First pass to count resource use */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
+		if (pmc)
+			pmc_inuse |= 1 << pmc;
+	}
+
+	/* In continous sampling mode, update SDAR on TLB miss */
+	mmcra = MMCRA_SDAR_MODE_TLB;
+	mmcr1 = 0;
+
+	/* Second pass: assign PMCs, set all MMCR1 fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc     = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
+		unit    = (event[i] >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
+		combine = (event[i] >> EVENT_COMBINE_SHIFT) & EVENT_COMBINE_MASK;
+		psel    =  event[i] & EVENT_PSEL_MASK;
+
+		if (!pmc) {
+			for (pmc = 1; pmc <= 4; ++pmc) {
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			}
+
+			pmc_inuse |= 1 << pmc;
+		}
+
+		if (pmc <= 4) {
+			mmcr1 |= unit << MMCR1_UNIT_SHIFT(pmc);
+			mmcr1 |= combine << MMCR1_COMBINE_SHIFT(pmc);
+			mmcr1 |= psel << MMCR1_PMCSEL_SHIFT(pmc);
+		}
+
+		if (event[i] & EVENT_IS_L1) {
+			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
+			mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT;
+			cache >>= 1;
+			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
+		}
+
+		if (event[i] & EVENT_IS_MARKED) {
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+
+			val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
+			if (val) {
+				mmcra |= (val &  3) << MMCRA_SAMP_MODE_SHIFT;
+				mmcra |= (val >> 2) << MMCRA_SAMP_ELIG_SHIFT;
+			}
+		}
+
+		/*
+		 * PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
+		 * 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;
+		} else {
+			val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
+			mmcra |= val << MMCRA_THR_CTL_SHIFT;
+			val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
+			mmcra |= val << MMCRA_THR_SEL_SHIFT;
+			val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
+			mmcra |= val << MMCRA_THR_CMP_SHIFT;
+		}
+
+		hwc[i] = pmc - 1;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+
+	/* pmc_inuse is 1-based */
+	if (pmc_inuse & 2)
+		mmcr[0] = MMCR0_PMC1CE;
+
+	if (pmc_inuse & 0x7c)
+		mmcr[0] |= MMCR0_PMCjCE;
+
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+
+	return 0;
+}
+
+#define MAX_ALT	2
+
+/* Table of alternatives, sorted by column 0 */
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x10134, 0x301e2 },		/* PM_MRK_ST_CMPL */
+	{ 0x10138, 0x40138 },		/* PM_BR_MRK_2PATH */
+	{ 0x18082, 0x3e05e },		/* PM_L3_CO_MEPF */
+	{ 0x1d14e, 0x401e8 },		/* PM_MRK_DATA_FROM_L2MISS */
+	{ 0x1e054, 0x4000a },		/* PM_CMPLU_STALL */
+	{ 0x20036, 0x40036 },		/* PM_BR_2PATH */
+	{ 0x200f2, 0x300f2 },		/* PM_INST_DISP */
+	{ 0x200f4, 0x600f4 },		/* PM_RUN_CYC */
+	{ 0x2013c, 0x3012e },		/* PM_MRK_FILT_MATCH */
+	{ 0x3e054, 0x400f0 },		/* PM_LD_MISS_L1 */
+	{ 0x400fa, 0x500fa },		/* PM_RUN_INST_CMPL */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(u64 event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+
+	return -1;
+}
+
+static int power8_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, num_alt = 0;
+	u64 alt_event;
+
+	alt[num_alt++] = event;
+
+	i = find_alternative(event);
+	if (i >= 0) {
+		/* Filter out the original event, it's already in alt[0] */
+		for (j = 0; j < MAX_ALT; ++j) {
+			alt_event = event_alternatives[i][j];
+			if (alt_event && alt_event != event)
+				alt[num_alt++] = alt_event;
+		}
+	}
+
+	if (flags & PPMU_ONLY_COUNT_RUN) {
+		/*
+		 * We're only counting in RUN state, so PM_CYC is equivalent to
+		 * PM_RUN_CYC and PM_INST_CMPL === PM_RUN_INST_CMPL.
+		 */
+		j = num_alt;
+		for (i = 0; i < num_alt; ++i) {
+			switch (alt[i]) {
+			case 0x1e:	/* PM_CYC */
+				alt[j++] = 0x600f4;	/* PM_RUN_CYC */
+				break;
+			case 0x600f4:	/* PM_RUN_CYC */
+				alt[j++] = 0x1e;
+				break;
+			case 0x2:	/* PM_PPC_CMPL */
+				alt[j++] = 0x500fa;	/* PM_RUN_INST_CMPL */
+				break;
+			case 0x500fa:	/* PM_RUN_INST_CMPL */
+				alt[j++] = 0x2;	/* PM_PPC_CMPL */
+				break;
+			}
+		}
+		num_alt = j;
+	}
+
+	return num_alt;
+}
+
+static void power8_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1));
+}
+
+PMU_FORMAT_ATTR(event,		"config:0-49");
+PMU_FORMAT_ATTR(pmcxsel,	"config:0-7");
+PMU_FORMAT_ATTR(mark,		"config:8");
+PMU_FORMAT_ATTR(combine,	"config:11");
+PMU_FORMAT_ATTR(unit,		"config:12-15");
+PMU_FORMAT_ATTR(pmc,		"config:16-19");
+PMU_FORMAT_ATTR(cache_sel,	"config:20-23");
+PMU_FORMAT_ATTR(sample_mode,	"config:24-28");
+PMU_FORMAT_ATTR(thresh_sel,	"config:29-31");
+PMU_FORMAT_ATTR(thresh_stop,	"config:32-35");
+PMU_FORMAT_ATTR(thresh_start,	"config:36-39");
+PMU_FORMAT_ATTR(thresh_cmp,	"config:40-49");
+
+static struct attribute *power8_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_pmcxsel.attr,
+	&format_attr_mark.attr,
+	&format_attr_combine.attr,
+	&format_attr_unit.attr,
+	&format_attr_pmc.attr,
+	&format_attr_cache_sel.attr,
+	&format_attr_sample_mode.attr,
+	&format_attr_thresh_sel.attr,
+	&format_attr_thresh_stop.attr,
+	&format_attr_thresh_start.attr,
+	&format_attr_thresh_cmp.attr,
+	NULL,
+};
+
+struct attribute_group power8_pmu_format_group = {
+	.name = "format",
+	.attrs = power8_pmu_format_attr,
+};
+
+static const struct attribute_group *power8_pmu_attr_groups[] = {
+	&power8_pmu_format_group,
+	NULL,
+};
+
+static int power8_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] =			PM_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PM_GCT_NOSLOT_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =	PM_CMPLU_STALL,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BRU_FIN,
+	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
+};
+
+static struct power_pmu power8_pmu = {
+	.name			= "POWER8",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT + 1,
+	.add_fields		= POWER8_ADD_FIELDS,
+	.test_adder		= POWER8_TEST_ADDER,
+	.compute_mmcr		= power8_compute_mmcr,
+	.get_constraint		= power8_get_constraint,
+	.get_alternatives	= power8_get_alternatives,
+	.disable_pmc		= power8_disable_pmc,
+	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER,
+	.n_generic		= ARRAY_SIZE(power8_generic_events),
+	.generic_events		= power8_generic_events,
+	.attr_groups		= power8_pmu_attr_groups,
+};
+
+static int __init init_power8_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power8"))
+		return -ENODEV;
+
+	return register_power_pmu(&power8_pmu);
+}
+early_initcall(init_power8_pmu);
-- 
1.7.10.4