Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "This is the powerpc changes for the 3.11 merge window.  In addition to
  the usual bug fixes and small updates, the main highlights are:

   - Support for transparent huge pages by Aneesh Kumar for 64-bit
     server processors.  This allows the use of 16M pages as transparent
     huge pages on kernels compiled with a 64K base page size.

   - Base VFIO support for KVM on power by Alexey Kardashevskiy

   - Wiring up of our nvram to the pstore infrastructure, including
     putting compressed oopses in there by Aruna Balakrishnaiah

   - Move, rework and improve our "EEH" (basically PCI error handling
     and recovery) infrastructure.  It is no longer specific to pseries
     but is now usable by the new "powernv" platform as well (no
     hypervisor) by Gavin Shan.

   - I fixed some bugs in our math-emu instruction decoding and made it
     usable to emulate some optional FP instructions on processors with
     hard FP that lack them (such as fsqrt on Freescale embedded
     processors).

   - Support for Power8 "Event Based Branch" facility by Michael
     Ellerman.  This facility allows what is basically "userspace
     interrupts" for performance monitor events.

   - A bunch of Transactional Memory vs.  Signals bug fixes and HW
     breakpoint/watchpoint fixes by Michael Neuling.

  And more ...  I appologize in advance if I've failed to highlight
  something that somebody deemed worth it."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  pstore: Add hsize argument in write_buf call of pstore_ftrace_call
  powerpc/fsl: add MPIC timer wakeup support
  powerpc/mpic: create mpic subsystem object
  powerpc/mpic: add global timer support
  powerpc/mpic: add irq_set_wake support
  powerpc/85xx: enable coreint for all the 64bit boards
  powerpc/8xx: Erroneous double irq_eoi() on CPM IRQ in MPC8xx
  powerpc/fsl: Enable CONFIG_E1000E in mpc85xx_smp_defconfig
  powerpc/mpic: Add get_version API both for internal and external use
  powerpc: Handle both new style and old style reserve maps
  powerpc/hw_brk: Fix off by one error when validating DAWR region end
  powerpc/pseries: Support compression of oops text via pstore
  powerpc/pseries: Re-organise the oops compression code
  pstore: Pass header size in the pstore write callback
  powerpc/powernv: Fix iommu initialization again
  powerpc/pseries: Inform the hypervisor we are using EBB regs
  powerpc/perf: Add power8 EBB support
  powerpc/perf: Core EBB support for 64-bit book3s
  powerpc/perf: Drop MMCRA from thread_struct
  powerpc/perf: Don't enable if we have zero events
  ...

2 files changed, 224 insertions, 39 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 29c6482..a3985ae 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -75,6 +75,11 @@ static unsigned int freeze_events_kernel = MMCR0_FCS;
 
 #define MMCR0_FCHV		0
 #define MMCR0_PMCjCE		MMCR0_PMCnCE
+#define MMCR0_FC56		0
+#define MMCR0_PMAO		0
+#define MMCR0_EBE		0
+#define MMCR0_PMCC		0
+#define MMCR0_PMCC_U6		0
 
 #define SPRN_MMCRA		SPRN_MMCR2
 #define MMCRA_SAMPLE_ENABLE	0
@@ -102,6 +107,15 @@ static inline int siar_valid(struct pt_regs *regs)
 	return 1;
 }
 
+static bool is_ebb_event(struct perf_event *event) { return false; }
+static int ebb_event_check(struct perf_event *event) { return 0; }
+static void ebb_event_add(struct perf_event *event) { }
+static void ebb_switch_out(unsigned long mmcr0) { }
+static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
+{
+	return mmcr0;
+}
+
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
 void power_pmu_flush_branch_stack(void) {}
@@ -462,6 +476,89 @@ void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
 	return;
 }
 
+static bool is_ebb_event(struct perf_event *event)
+{
+	/*
+	 * This could be a per-PMU callback, but we'd rather avoid the cost. We
+	 * check that the PMU supports EBB, meaning those that don't can still
+	 * use bit 63 of the event code for something else if they wish.
+	 */
+	return (ppmu->flags & PPMU_EBB) &&
+	       ((event->attr.config >> EVENT_CONFIG_EBB_SHIFT) & 1);
+}
+
+static int ebb_event_check(struct perf_event *event)
+{
+	struct perf_event *leader = event->group_leader;
+
+	/* Event and group leader must agree on EBB */
+	if (is_ebb_event(leader) != is_ebb_event(event))
+		return -EINVAL;
+
+	if (is_ebb_event(event)) {
+		if (!(event->attach_state & PERF_ATTACH_TASK))
+			return -EINVAL;
+
+		if (!leader->attr.pinned || !leader->attr.exclusive)
+			return -EINVAL;
+
+		if (event->attr.inherit || event->attr.sample_period ||
+		    event->attr.enable_on_exec || event->attr.freq)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void ebb_event_add(struct perf_event *event)
+{
+	if (!is_ebb_event(event) || current->thread.used_ebb)
+		return;
+
+	/*
+	 * IFF this is the first time we've added an EBB event, set
+	 * PMXE in the user MMCR0 so we can detect when it's cleared by
+	 * userspace. We need this so that we can context switch while
+	 * userspace is in the EBB handler (where PMXE is 0).
+	 */
+	current->thread.used_ebb = 1;
+	current->thread.mmcr0 |= MMCR0_PMXE;
+}
+
+static void ebb_switch_out(unsigned long mmcr0)
+{
+	if (!(mmcr0 & MMCR0_EBE))
+		return;
+
+	current->thread.siar  = mfspr(SPRN_SIAR);
+	current->thread.sier  = mfspr(SPRN_SIER);
+	current->thread.sdar  = mfspr(SPRN_SDAR);
+	current->thread.mmcr0 = mmcr0 & MMCR0_USER_MASK;
+	current->thread.mmcr2 = mfspr(SPRN_MMCR2) & MMCR2_USER_MASK;
+}
+
+static unsigned long ebb_switch_in(bool ebb, unsigned long mmcr0)
+{
+	if (!ebb)
+		goto out;
+
+	/* Enable EBB and read/write to all 6 PMCs for userspace */
+	mmcr0 |= MMCR0_EBE | MMCR0_PMCC_U6;
+
+	/* Add any bits from the user reg, FC or PMAO */
+	mmcr0 |= current->thread.mmcr0;
+
+	/* Be careful not to set PMXE if userspace had it cleared */
+	if (!(current->thread.mmcr0 & MMCR0_PMXE))
+		mmcr0 &= ~MMCR0_PMXE;
+
+	mtspr(SPRN_SIAR, current->thread.siar);
+	mtspr(SPRN_SIER, current->thread.sier);
+	mtspr(SPRN_SDAR, current->thread.sdar);
+	mtspr(SPRN_MMCR2, current->thread.mmcr2);
+out:
+	return mmcr0;
+}
 #endif /* CONFIG_PPC64 */
 
 static void perf_event_interrupt(struct pt_regs *regs);
@@ -732,6 +829,13 @@ static void power_pmu_read(struct perf_event *event)
 
 	if (!event->hw.idx)
 		return;
+
+	if (is_ebb_event(event)) {
+		val = read_pmc(event->hw.idx);
+		local64_set(&event->hw.prev_count, val);
+		return;
+	}
+
 	/*
 	 * Performance monitor interrupts come even when interrupts
 	 * are soft-disabled, as long as interrupts are hard-enabled.
@@ -852,7 +956,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0)
 static void power_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
-	unsigned long flags;
+	unsigned long flags, mmcr0, val;
 
 	if (!ppmu)
 		return;
@@ -860,9 +964,6 @@ static void power_pmu_disable(struct pmu *pmu)
 	cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	if (!cpuhw->disabled) {
-		cpuhw->disabled = 1;
-		cpuhw->n_added = 0;
-
 		/*
 		 * Check if we ever enabled the PMU on this cpu.
 		 */
@@ -872,6 +973,21 @@ static void power_pmu_disable(struct pmu *pmu)
 		}
 
 		/*
+		 * Set the 'freeze counters' bit, clear EBE/PMCC/PMAO/FC56.
+		 */
+		val  = mmcr0 = mfspr(SPRN_MMCR0);
+		val |= MMCR0_FC;
+		val &= ~(MMCR0_EBE | MMCR0_PMCC | MMCR0_PMAO | MMCR0_FC56);
+
+		/*
+		 * The barrier is to make sure the mtspr has been
+		 * executed and the PMU has frozen the events etc.
+		 * before we return.
+		 */
+		write_mmcr0(cpuhw, val);
+		mb();
+
+		/*
 		 * Disable instruction sampling if it was enabled
 		 */
 		if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
@@ -880,15 +996,12 @@ static void power_pmu_disable(struct pmu *pmu)
 			mb();
 		}
 
-		/*
-		 * Set the 'freeze counters' bit.
-		 * The barrier is to make sure the mtspr has been
-		 * executed and the PMU has frozen the events
-		 * before we return.
-		 */
-		write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC);
-		mb();
+		cpuhw->disabled = 1;
+		cpuhw->n_added = 0;
+
+		ebb_switch_out(mmcr0);
 	}
+
 	local_irq_restore(flags);
 }
 
@@ -903,23 +1016,36 @@ static void power_pmu_enable(struct pmu *pmu)
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
 	long i;
-	unsigned long val;
+	unsigned long val, mmcr0;
 	s64 left;
 	unsigned int hwc_index[MAX_HWEVENTS];
 	int n_lim;
 	int idx;
+	bool ebb;
 
 	if (!ppmu)
 		return;
 	local_irq_save(flags);
+
 	cpuhw = &__get_cpu_var(cpu_hw_events);
-	if (!cpuhw->disabled) {
-		local_irq_restore(flags);
-		return;
+	if (!cpuhw->disabled)
+		goto out;
+
+	if (cpuhw->n_events == 0) {
+		ppc_set_pmu_inuse(0);
+		goto out;
 	}
+
 	cpuhw->disabled = 0;
 
 	/*
+	 * EBB requires an exclusive group and all events must have the EBB
+	 * flag set, or not set, so we can just check a single event. Also we
+	 * know we have at least one event.
+	 */
+	ebb = is_ebb_event(cpuhw->event[0]);
+
+	/*
 	 * If we didn't change anything, or only removed events,
 	 * no need to recalculate MMCR* settings and reset the PMCs.
 	 * Just reenable the PMU with the current MMCR* settings
@@ -928,8 +1054,6 @@ static void power_pmu_enable(struct pmu *pmu)
 	if (!cpuhw->n_added) {
 		mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
 		mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
-		if (cpuhw->n_events == 0)
-			ppc_set_pmu_inuse(0);
 		goto out_enable;
 	}
 
@@ -996,25 +1120,34 @@ static void power_pmu_enable(struct pmu *pmu)
 			++n_lim;
 			continue;
 		}
-		val = 0;
-		if (event->hw.sample_period) {
-			left = local64_read(&event->hw.period_left);
-			if (left < 0x80000000L)
-				val = 0x80000000L - left;
+
+		if (ebb)
+			val = local64_read(&event->hw.prev_count);
+		else {
+			val = 0;
+			if (event->hw.sample_period) {
+				left = local64_read(&event->hw.period_left);
+				if (left < 0x80000000L)
+					val = 0x80000000L - left;
+			}
+			local64_set(&event->hw.prev_count, val);
 		}
-		local64_set(&event->hw.prev_count, val);
+
 		event->hw.idx = idx;
 		if (event->hw.state & PERF_HES_STOPPED)
 			val = 0;
 		write_pmc(idx, val);
+
 		perf_event_update_userpage(event);
 	}
 	cpuhw->n_limited = n_lim;
 	cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE;
 
  out_enable:
+	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
+
 	mb();
-	write_mmcr0(cpuhw, cpuhw->mmcr[0]);
+	write_mmcr0(cpuhw, mmcr0);
 
 	/*
 	 * Enable instruction sampling if necessary
@@ -1112,6 +1245,8 @@ static int power_pmu_add(struct perf_event *event, int ef_flags)
 	event->hw.config = cpuhw->events[n0];
 
 nocheck:
+	ebb_event_add(event);
+
 	++cpuhw->n_events;
 	++cpuhw->n_added;
 
@@ -1472,6 +1607,11 @@ static int power_pmu_event_init(struct perf_event *event)
 		}
 	}
 
+	/* Extra checks for EBB */
+	err = ebb_event_check(event);
+	if (err)
+		return err;
+
 	/*
 	 * If this is in a group, check if it can go on with all the
 	 * other hardware events in the group.  We assume the event
@@ -1511,6 +1651,13 @@ static int power_pmu_event_init(struct perf_event *event)
 	local64_set(&event->hw.period_left, event->hw.last_period);
 
 	/*
+	 * For EBB events we just context switch the PMC value, we don't do any
+	 * of the sample_period logic. We use hw.prev_count for this.
+	 */
+	if (is_ebb_event(event))
+		local64_set(&event->hw.prev_count, 0);
+
+	/*
 	 * See if we need to reserve the PMU.
 	 * If no events are currently in use, then we have to take a
 	 * mutex to ensure that we don't race with another task doing
@@ -1786,7 +1933,7 @@ static void power_pmu_setup(int cpu)
 	cpuhw->mmcr[0] = MMCR0_FC;
 }
 
-static int __cpuinit
+static int
 power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
@@ -1803,7 +1950,7 @@ power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu
 	return NOTIFY_OK;
 }
 
-int __cpuinit register_power_pmu(struct power_pmu *pmu)
+int register_power_pmu(struct power_pmu *pmu)
 {
 	if (ppmu)
 		return -EBUSY;		/* something's already registered */
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index f7d1c4f..96a64d6 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -31,9 +31,9 @@
  *
  *        60        56        52        48        44        40        36        32
  * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- *                                     [      thresh_cmp     ]   [  thresh_ctl   ]
- *                                                                       |
- *                                       thresh start/stop OR FAB match -*
+ *   |                                 [      thresh_cmp     ]   [  thresh_ctl   ]
+ *   |                                                                   |
+ *   *- EBB (Linux)                      thresh start/stop OR FAB match -*
  *
  *        28        24        20        16        12         8         4         0
  * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
@@ -85,6 +85,7 @@
  *
  */
 
+#define EVENT_EBB_MASK		1ull
 #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) */
@@ -109,6 +110,17 @@
 #define EVENT_IS_MARKED		(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
 #define EVENT_PSEL_MASK		0xff	/* PMCxSEL value */
 
+#define EVENT_VALID_MASK	\
+	((EVENT_THRESH_MASK    << EVENT_THRESH_SHIFT)		|	\
+	 (EVENT_SAMPLE_MASK    << EVENT_SAMPLE_SHIFT)		|	\
+	 (EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT)	|	\
+	 (EVENT_PMC_MASK       << EVENT_PMC_SHIFT)		|	\
+	 (EVENT_UNIT_MASK      << EVENT_UNIT_SHIFT)		|	\
+	 (EVENT_COMBINE_MASK   << EVENT_COMBINE_SHIFT)		|	\
+	 (EVENT_MARKED_MASK    << EVENT_MARKED_SHIFT)		|	\
+	 (EVENT_EBB_MASK       << EVENT_CONFIG_EBB_SHIFT)	|	\
+	  EVENT_PSEL_MASK)
+
 /* MMCRA IFM bits - POWER8 */
 #define	POWER8_MMCRA_IFM1		0x0000000040000000UL
 #define	POWER8_MMCRA_IFM2		0x0000000080000000UL
@@ -130,10 +142,10 @@
  *
  *        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.
+ *                   |   [ ]   [  sample ]   [     ]   [6] [5]   [4] [3]   [2] [1]
+ *              EBB -*    |                     |
+ *                        |                     |      Count of events for each PMC.
+ *      L1 I/D qualifier -*                     |        p1, p2, p3, p4, p5, p6.
  *                     nc - number of counters -*
  *
  * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints
@@ -149,6 +161,9 @@
 #define CNST_THRESH_VAL(v)	(((v) & EVENT_THRESH_MASK) << 32)
 #define CNST_THRESH_MASK	CNST_THRESH_VAL(EVENT_THRESH_MASK)
 
+#define CNST_EBB_VAL(v)		(((v) & EVENT_EBB_MASK) << 24)
+#define CNST_EBB_MASK		CNST_EBB_VAL(EVENT_EBB_MASK)
+
 #define CNST_L1_QUAL_VAL(v)	(((v) & 3) << 22)
 #define CNST_L1_QUAL_MASK	CNST_L1_QUAL_VAL(3)
 
@@ -207,14 +222,21 @@ static inline bool event_is_fab_match(u64 event)
 
 static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
 {
-	unsigned int unit, pmc, cache;
+	unsigned int unit, pmc, cache, ebb;
 	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 (event & ~EVENT_VALID_MASK)
+		return -1;
+
+	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;
+	ebb   = (event >> EVENT_CONFIG_EBB_SHIFT) & EVENT_EBB_MASK;
+
+	/* Clear the EBB bit in the event, so event checks work below */
+	event &= ~(EVENT_EBB_MASK << EVENT_CONFIG_EBB_SHIFT);
 
 	if (pmc) {
 		if (pmc > 6)
@@ -284,6 +306,18 @@ static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long
 		value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
 	}
 
+	if (!pmc && ebb)
+		/* EBB events must specify the PMC */
+		return -1;
+
+	/*
+	 * All events must agree on EBB, either all request it or none.
+	 * EBB events are pinned & exclusive, so this should never actually
+	 * hit, but we leave it as a fallback in case.
+	 */
+	mask  |= CNST_EBB_VAL(ebb);
+	value |= CNST_EBB_MASK;
+
 	*maskp = mask;
 	*valp = value;
 
@@ -378,6 +412,10 @@ static int power8_compute_mmcr(u64 event[], int n_ev,
 	if (pmc_inuse & 0x7c)
 		mmcr[0] |= MMCR0_PMCjCE;
 
+	/* If we're not using PMC 5 or 6, freeze them */
+	if (!(pmc_inuse & 0x60))
+		mmcr[0] |= MMCR0_FC56;
+
 	mmcr[1] = mmcr1;
 	mmcr[2] = mmcra;
 
@@ -574,7 +612,7 @@ static struct power_pmu power8_pmu = {
 	.get_constraint		= power8_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
 	.disable_pmc		= power8_disable_pmc,
-	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB,
+	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
 	.attr_groups		= power8_pmu_attr_groups,