Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The biggest changes are Intel Nehalem-EX PMU uncore support, uprobes
  updates/cleanups/fixes from Oleg and diverse tooling updates (mostly
  fixes) now that Arnaldo is back from vacation."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  uprobes: __replace_page() needs munlock_vma_page()
  uprobes: Rename vma_address() and make it return "unsigned long"
  uprobes: Fix register_for_each_vma()->vma_address() check
  uprobes: Introduce vaddr_to_offset(vma, vaddr)
  uprobes: Teach build_probe_list() to consider the range
  uprobes: Remove insert_vm_struct()->uprobe_mmap()
  uprobes: Remove copy_vma()->uprobe_mmap()
  uprobes: Fix overflow in vma_address()/find_active_uprobe()
  uprobes: Suppress uprobe_munmap() from mmput()
  uprobes: Uprobe_mmap/munmap needs list_for_each_entry_safe()
  uprobes: Clean up and document write_opcode()->lock_page(old_page)
  uprobes: Kill write_opcode()->lock_page(new_page)
  uprobes: __replace_page() should not use page_address_in_vma()
  uprobes: Don't recheck vma/f_mapping in write_opcode()
  perf/x86: Fix missing struct before structure name
  perf/x86: Fix format definition of SNB-EP uncore QPI box
  perf/x86: Make bitfield unsigned
  perf/x86: Fix LLC-* and node-* events on Intel SandyBridge
  perf/x86: Add Intel Nehalem-EX uncore support
  perf/x86: Fix typo in format definition of uncore PCU filter
  ...

arch/x86/include/asm/perf_event.h

@@ -234,7 +234,7 @@ extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
 #else
-static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
 	*nr = 0;
 	return NULL;

arch/x86/kernel/cpu/perf_event.h

@@ -374,7 +374,7 @@ struct x86_pmu {
 	/*
 	 * Intel DebugStore bits
 	 */
-	int		bts		:1,
+	unsigned int	bts		:1,
 			bts_active	:1,
 			pebs		:1,
 			pebs_active	:1,

arch/x86/kernel/cpu/perf_event_intel.c

@@ -138,6 +138,84 @@ static u64 intel_pmu_event_map(int hw_event)
 	return intel_perfmon_event_map[hw_event];
 }
 
+#define SNB_DMND_DATA_RD	(1ULL << 0)
+#define SNB_DMND_RFO		(1ULL << 1)
+#define SNB_DMND_IFETCH		(1ULL << 2)
+#define SNB_DMND_WB		(1ULL << 3)
+#define SNB_PF_DATA_RD		(1ULL << 4)
+#define SNB_PF_RFO		(1ULL << 5)
+#define SNB_PF_IFETCH		(1ULL << 6)
+#define SNB_LLC_DATA_RD		(1ULL << 7)
+#define SNB_LLC_RFO		(1ULL << 8)
+#define SNB_LLC_IFETCH		(1ULL << 9)
+#define SNB_BUS_LOCKS		(1ULL << 10)
+#define SNB_STRM_ST		(1ULL << 11)
+#define SNB_OTHER		(1ULL << 15)
+#define SNB_RESP_ANY		(1ULL << 16)
+#define SNB_NO_SUPP		(1ULL << 17)
+#define SNB_LLC_HITM		(1ULL << 18)
+#define SNB_LLC_HITE		(1ULL << 19)
+#define SNB_LLC_HITS		(1ULL << 20)
+#define SNB_LLC_HITF		(1ULL << 21)
+#define SNB_LOCAL		(1ULL << 22)
+#define SNB_REMOTE		(0xffULL << 23)
+#define SNB_SNP_NONE		(1ULL << 31)
+#define SNB_SNP_NOT_NEEDED	(1ULL << 32)
+#define SNB_SNP_MISS		(1ULL << 33)
+#define SNB_NO_FWD		(1ULL << 34)
+#define SNB_SNP_FWD		(1ULL << 35)
+#define SNB_HITM		(1ULL << 36)
+#define SNB_NON_DRAM		(1ULL << 37)
+
+#define SNB_DMND_READ		(SNB_DMND_DATA_RD|SNB_LLC_DATA_RD)
+#define SNB_DMND_WRITE		(SNB_DMND_RFO|SNB_LLC_RFO)
+#define SNB_DMND_PREFETCH	(SNB_PF_DATA_RD|SNB_PF_RFO)
+
+#define SNB_SNP_ANY		(SNB_SNP_NONE|SNB_SNP_NOT_NEEDED| \
+				 SNB_SNP_MISS|SNB_NO_FWD|SNB_SNP_FWD| \
+				 SNB_HITM)
+
+#define SNB_DRAM_ANY		(SNB_LOCAL|SNB_REMOTE|SNB_SNP_ANY)
+#define SNB_DRAM_REMOTE		(SNB_REMOTE|SNB_SNP_ANY)
+
+#define SNB_L3_ACCESS		SNB_RESP_ANY
+#define SNB_L3_MISS		(SNB_DRAM_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 snb_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = SNB_DMND_READ|SNB_L3_MISS,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = SNB_DMND_WRITE|SNB_L3_MISS,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = SNB_DMND_PREFETCH|SNB_L3_MISS,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_DRAM_ANY,
+		[ C(RESULT_MISS)   ] = SNB_DMND_READ|SNB_DRAM_REMOTE,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_DRAM_ANY,
+		[ C(RESULT_MISS)   ] = SNB_DMND_WRITE|SNB_DRAM_REMOTE,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_DRAM_ANY,
+		[ C(RESULT_MISS)   ] = SNB_DMND_PREFETCH|SNB_DRAM_REMOTE,
+	},
+ },
+};
+
 static __initconst const u64 snb_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -235,16 +313,16 @@ static __initconst const u64 snb_hw_cache_event_ids
  },
  [ C(NODE) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
 
@@ -1964,6 +2042,8 @@ __init int intel_pmu_init(void)
 	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_snb();
 

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -18,6 +18,7 @@ static struct event_constraint constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
 DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -33,10 +34,81 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand0, filter_brand0, "config1:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand1, filter_brand1, "config1:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand2, filter_brand2, "config1:16-23");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand3, filter_brand3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+
+static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	u64 count;
+
+	rdmsrl(event->hw.event_base, count);
+
+	return count;
+}
+
+/*
+ * generic get constraint function for shared match/mask registers.
+ */
+static struct event_constraint *
+uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	unsigned long flags;
+	bool ok = false;
+
+	/*
+	 * reg->alloc can be set due to existing state, so for fake box we
+	 * need to ignore this, otherwise we might fail to allocate proper
+	 * fake state for this extra reg constraint.
+	 */
+	if (reg1->idx == EXTRA_REG_NONE ||
+	    (!uncore_box_is_fake(box) && reg1->alloc))
+		return NULL;
+
+	er = &box->shared_regs[reg1->idx];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (!atomic_read(&er->ref) ||
+	    (er->config1 == reg1->config && er->config2 == reg2->config)) {
+		atomic_inc(&er->ref);
+		er->config1 = reg1->config;
+		er->config2 = reg2->config;
+		ok = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (ok) {
+		if (!uncore_box_is_fake(box))
+			reg1->alloc = 1;
+		return NULL;
+	}
+
+	return &constraint_empty;
+}
+
+static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+
+	/*
+	 * Only put constraint if extra reg was actually allocated. Also
+	 * takes care of event which do not use an extra shared reg.
+	 *
+	 * Also, if this is a fake box we shouldn't touch any event state
+	 * (reg->alloc) and we don't care about leaving inconsistent box
+	 * state either since it will be thrown out.
+	 */
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	er = &box->shared_regs[reg1->idx];
+	atomic_dec(&er->ref);
+	reg1->alloc = 0;
+}
 
 /* Sandy Bridge-EP uncore support */
 static struct intel_uncore_type snbep_uncore_cbox;
@@ -64,18 +136,15 @@ static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
 	pci_write_config_dword(pdev, box_ctl, config);
 }
 
-static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
 
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config |
-				SNBEP_PMON_CTL_EN);
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
 
-static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
@@ -83,8 +152,7 @@ static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box,
 	pci_write_config_dword(pdev, hwc->config_base, hwc->config);
 }
 
-static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box,
-					struct perf_event *event)
+static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
@@ -92,14 +160,15 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box,
 
 	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
 	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
+
 	return count;
 }
 
 static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = box->pci_dev;
-	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL,
-				SNBEP_PMON_BOX_CTL_INT);
+
+	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
 }
 
 static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
@@ -112,7 +181,6 @@ static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
 		rdmsrl(msr, config);
 		config |= SNBEP_PMON_BOX_CTL_FRZ;
 		wrmsrl(msr, config);
-		return;
 	}
 }
 
@@ -126,12 +194,10 @@ static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
 		rdmsrl(msr, config);
 		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
 		wrmsrl(msr, config);
-		return;
 	}
 }
 
-static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
@@ -150,68 +216,15 @@ static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
 	wrmsrl(hwc->config_base, hwc->config);
 }
 
-static u64 snbep_uncore_msr_read_counter(struct intel_uncore_box *box,
-					struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	u64 count;
-
-	rdmsrl(hwc->event_base, count);
-	return count;
-}
-
 static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	unsigned msr = uncore_msr_box_ctl(box);
+
 	if (msr)
 		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
 }
 
-static struct event_constraint *
-snbep_uncore_get_constraint(struct intel_uncore_box *box,
-			    struct perf_event *event)
-{
-	struct intel_uncore_extra_reg *er;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	unsigned long flags;
-	bool ok = false;
-
-	if (reg1->idx == EXTRA_REG_NONE || (box->phys_id >= 0 && reg1->alloc))
-		return NULL;
-
-	er = &box->shared_regs[reg1->idx];
-	raw_spin_lock_irqsave(&er->lock, flags);
-	if (!atomic_read(&er->ref) || er->config1 == reg1->config) {
-		atomic_inc(&er->ref);
-		er->config1 = reg1->config;
-		ok = true;
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	if (ok) {
-		if (box->phys_id >= 0)
-			reg1->alloc = 1;
-		return NULL;
-	}
-	return &constraint_empty;
-}
-
-static void snbep_uncore_put_constraint(struct intel_uncore_box *box,
-					struct perf_event *event)
-{
-	struct intel_uncore_extra_reg *er;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-
-	if (box->phys_id < 0 || !reg1->alloc)
-		return;
-
-	er = &box->shared_regs[reg1->idx];
-	atomic_dec(&er->ref);
-	reg1->alloc = 0;
-}
-
-static int snbep_uncore_hw_config(struct intel_uncore_box *box,
-				  struct perf_event *event)
+static int snbep_uncore_hw_config(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
@@ -221,14 +234,16 @@ static int snbep_uncore_hw_config(struct intel_uncore_box *box,
 			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
 		reg1->config = event->attr.config1 &
 			SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK;
-	} else if (box->pmu->type == &snbep_uncore_pcu) {
-		reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
-		reg1->config = event->attr.config1 &
-			SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK;
 	} else {
-		return 0;
+		if (box->pmu->type == &snbep_uncore_pcu) {
+			reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+			reg1->config = event->attr.config1 & SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK;
+		} else {
+			return 0;
+		}
 	}
 	reg1->idx = 0;
+
 	return 0;
 }
 
@@ -272,10 +287,19 @@ static struct attribute *snbep_uncore_pcu_formats_attr[] = {
 	&format_attr_thresh5.attr,
 	&format_attr_occ_invert.attr,
 	&format_attr_occ_edge.attr,
-	&format_attr_filter_brand0.attr,
-	&format_attr_filter_brand1.attr,
-	&format_attr_filter_brand2.attr,
-	&format_attr_filter_brand3.attr,
+	&format_attr_filter_band0.attr,
+	&format_attr_filter_band1.attr,
+	&format_attr_filter_band2.attr,
+	&format_attr_filter_band3.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_qpi_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
 	NULL,
 };
 
@@ -314,15 +338,20 @@ static struct attribute_group snbep_uncore_pcu_format_group = {
 	.attrs = snbep_uncore_pcu_formats_attr,
 };
 
+static struct attribute_group snbep_uncore_qpi_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_qpi_formats_attr,
+};
+
 static struct intel_uncore_ops snbep_uncore_msr_ops = {
 	.init_box	= snbep_uncore_msr_init_box,
 	.disable_box	= snbep_uncore_msr_disable_box,
 	.enable_box	= snbep_uncore_msr_enable_box,
 	.disable_event	= snbep_uncore_msr_disable_event,
 	.enable_event	= snbep_uncore_msr_enable_event,
-	.read_counter	= snbep_uncore_msr_read_counter,
-	.get_constraint = snbep_uncore_get_constraint,
-	.put_constraint = snbep_uncore_put_constraint,
+	.read_counter	= uncore_msr_read_counter,
+	.get_constraint = uncore_get_constraint,
+	.put_constraint = uncore_put_constraint,
 	.hw_config	= snbep_uncore_hw_config,
 };
 
@@ -485,8 +514,13 @@ static struct intel_uncore_type snbep_uncore_qpi = {
 	.num_counters   = 4,
 	.num_boxes	= 2,
 	.perf_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,
+	.event_mask	= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,
+	.ops		= &snbep_uncore_pci_ops,
 	.event_descs	= snbep_uncore_qpi_events,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
+	.format_group	= &snbep_uncore_qpi_format_group,
 };
 
 
@@ -589,188 +623,1208 @@ static void snbep_pci2phy_map_init(void)
 		/* get the Node ID mapping */
 		pci_read_config_dword(ubox_dev, 0x54, &config);
 		/*
-		 * every three bits in the Node ID mapping register maps
-		 * to a particular node.
+		 * every three bits in the Node ID mapping register maps
+		 * to a particular node.
+		 */
+		for (i = 0; i < 8; i++) {
+			if (nodeid == ((config >> (3 * i)) & 0x7)) {
+				pcibus_to_physid[bus] = i;
+				break;
+			}
+		}
+	};
+	return;
+}
+/* end of Sandy Bridge-EP uncore support */
+
+/* Sandy Bridge uncore support */
+static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+	else
+		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+}
+
+static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	wrmsrl(event->hw.config_base, 0);
+}
+
+static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0) {
+		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+			SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+	}
+}
+
+static struct attribute *snb_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask5.attr,
+	NULL,
+};
+
+static struct attribute_group snb_uncore_format_group = {
+	.name		= "format",
+	.attrs		= snb_uncore_formats_attr,
+};
+
+static struct intel_uncore_ops snb_uncore_msr_ops = {
+	.init_box	= snb_uncore_msr_init_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= snb_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct event_constraint snb_uncore_cbox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snb_uncore_cbox = {
+	.name		= "cbox",
+	.num_counters   = 2,
+	.num_boxes	= 4,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
+	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
+	.fixed_ctr	= SNB_UNC_FIXED_CTR,
+	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
+	.single_fixed	= 1,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
+	.constraints	= snb_uncore_cbox_constraints,
+	.ops		= &snb_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+};
+
+static struct intel_uncore_type *snb_msr_uncores[] = {
+	&snb_uncore_cbox,
+	NULL,
+};
+/* end of Sandy Bridge uncore support */
+
+/* Nehalem uncore support */
+static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+}
+
+static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+	else
+		wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+}
+
+static struct attribute *nhm_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask8.attr,
+	NULL,
+};
+
+static struct attribute_group nhm_uncore_format_group = {
+	.name = "format",
+	.attrs = nhm_uncore_formats_attr,
+};
+
+static struct uncore_event_desc nhm_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,                "event=0xff,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any,       "event=0x2f,umask=0x0f"),
+	INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any,      "event=0x2c,umask=0x0f"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads,     "event=0x20,umask=0x01"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes,    "event=0x20,umask=0x02"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads,  "event=0x20,umask=0x04"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads,   "event=0x20,umask=0x10"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes,  "event=0x20,umask=0x20"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhm_uncore_msr_ops = {
+	.disable_box	= nhm_uncore_msr_disable_box,
+	.enable_box	= nhm_uncore_msr_enable_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= nhm_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type nhm_uncore = {
+	.name		= "",
+	.num_counters   = 8,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.event_ctl	= NHM_UNC_PERFEVTSEL0,
+	.perf_ctr	= NHM_UNC_UNCORE_PMC0,
+	.fixed_ctr	= NHM_UNC_FIXED_CTR,
+	.fixed_ctl	= NHM_UNC_FIXED_CTR_CTRL,
+	.event_mask	= NHM_UNC_RAW_EVENT_MASK,
+	.event_descs	= nhm_uncore_events,
+	.ops		= &nhm_uncore_msr_ops,
+	.format_group	= &nhm_uncore_format_group,
+};
+
+static struct intel_uncore_type *nhm_msr_uncores[] = {
+	&nhm_uncore,
+	NULL,
+};
+/* end of Nehalem uncore support */
+
+/* Nehalem-EX uncore support */
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+				((1ULL << (n)) - 1)))
+
+DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
+DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
+DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63");
+DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
+
+static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+}
+
+static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config &= ~((1ULL << uncore_num_counters(box)) - 1);
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config |= (1ULL << uncore_num_counters(box)) - 1;
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	wrmsrl(event->hw.config_base, 0);
+}
+
+static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+	else
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+#define NHMEX_UNCORE_OPS_COMMON_INIT()				\
+	.init_box	= nhmex_uncore_msr_init_box,		\
+	.disable_box	= nhmex_uncore_msr_disable_box,		\
+	.enable_box	= nhmex_uncore_msr_enable_box,		\
+	.disable_event	= nhmex_uncore_msr_disable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops nhmex_uncore_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_uncore_msr_enable_event,
+};
+
+static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_edge.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_ubox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters	= 1,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.event_ctl	= NHMEX_U_MSR_PMON_EV_SEL,
+	.perf_ctr	= NHMEX_U_MSR_PMON_CTR,
+	.event_mask	= NHMEX_U_PMON_RAW_EVENT_MASK,
+	.box_ctl	= NHMEX_U_MSR_PMON_GLOBAL_CTL,
+	.ops		= &nhmex_uncore_ops,
+	.format_group	= &nhmex_uncore_ubox_format_group
+};
+
+static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_cbox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 6,
+	.num_boxes		= 8,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
+	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_C_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type nhmex_uncore_wbox = {
+	.name			= "wbox",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_W_MSR_PMON_CNT0,
+	.perf_ctr		= NHMEX_W_MSR_PMON_EVT_SEL0,
+	.fixed_ctr		= NHMEX_W_MSR_PMON_FIXED_CTR,
+	.fixed_ctl		= NHMEX_W_MSR_PMON_FIXED_CTL,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_W_MSR_GLOBAL_CTL,
+	.pair_ctr_ctl		= 1,
+	.event_descs		= nhmex_uncore_wbox_events,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int ctr, ev_sel;
+
+	ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
+		NHMEX_B_PMON_CTR_SHIFT;
+	ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
+		  NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
+
+	/* events that do not use the match/mask registers */
+	if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
+	    (ctr == 2 && ev_sel != 0x4) || ctr == 3)
+		return 0;
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_B0_MSR_MATCH;
+	else
+		reg1->reg = NHMEX_B1_MSR_MATCH;
+	reg1->idx = 0;
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
+	return 0;
+}
+
+static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(reg1->reg + 1, reg2->config);
+	}
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
+}
+
+/*
+ * The Bbox has 4 counters, but each counter monitors different events.
+ * Use bits 6-7 in the event config to select counter.
+ */
+static struct event_constraint nhmex_uncore_bbox_constraints[] = {
+	EVENT_CONSTRAINT(0 , 1, 0xc0),
+	EVENT_CONSTRAINT(0x40, 2, 0xc0),
+	EVENT_CONSTRAINT(0x80, 4, 0xc0),
+	EVENT_CONSTRAINT(0xc0, 8, 0xc0),
+	EVENT_CONSTRAINT_END,
+};
+
+static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_counter.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_bbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_bbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_bbox_msr_enable_event,
+	.hw_config		= nhmex_bbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_bbox = {
+	.name			= "bbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_B0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_B0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_B_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_B0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_B_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.constraints		= nhmex_uncore_bbox_constraints,
+	.ops			= &nhmex_uncore_bbox_ops,
+	.format_group		= &nhmex_uncore_bbox_format_group
+};
+
+static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+
+	if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) {
+		reg1->config = event->attr.config1;
+		reg2->config = event->attr.config2;
+	} else {
+		reg1->config = ~0ULL;
+		reg2->config = ~0ULL;
+	}
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_S0_MSR_MM_CFG;
+	else
+		reg1->reg = NHMEX_S1_MSR_MM_CFG;
+
+	reg1->idx = 0;
+
+	return 0;
+}
+
+static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	wrmsrl(reg1->reg, 0);
+	if (reg1->config != ~0ULL || reg2->config != ~0ULL) {
+		wrmsrl(reg1->reg + 1, reg1->config);
+		wrmsrl(reg1->reg + 2, reg2->config);
+		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+	}
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+}
+
+static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_mm_cfg.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_sbox_format_group = {
+	.name			= "format",
+	.attrs			= nhmex_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_sbox_msr_enable_event,
+	.hw_config		= nhmex_sbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_S0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_S0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_S0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_S_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.ops			= &nhmex_uncore_sbox_ops,
+	.format_group		= &nhmex_uncore_sbox_format_group
+};
+
+enum {
+	EXTRA_REG_NHMEX_M_FILTER,
+	EXTRA_REG_NHMEX_M_DSP,
+	EXTRA_REG_NHMEX_M_ISS,
+	EXTRA_REG_NHMEX_M_MAP,
+	EXTRA_REG_NHMEX_M_MSC_THR,
+	EXTRA_REG_NHMEX_M_PGT,
+	EXTRA_REG_NHMEX_M_PLD,
+	EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
+};
+
+static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
+	MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
+	MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
+	/* event 0xa uses two extra registers */
+	MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
+	MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
+	MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
+	/* events 0xd ~ 0x10 use the same extra register */
+	MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
+	EVENT_EXTRA_END
+};
+
+static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	bool ret = false;
+	u64 mask;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		raw_spin_lock_irqsave(&er->lock, flags);
+		if (!atomic_read(&er->ref) || er->config == config) {
+			atomic_inc(&er->ref);
+			er->config = config;
+			ret = true;
+		}
+		raw_spin_unlock_irqrestore(&er->lock, flags);
+
+		return ret;
+	}
+	/*
+	 * The ZDP_CTL_FVC MSR has 4 fields which are used to control
+	 * events 0xd ~ 0x10. Besides these 4 fields, there are additional
+	 * fields which are shared.
+	 */
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	if (WARN_ON_ONCE(idx >= 4))
+		return false;
+
+	/* mask of the shared fields */
+	mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	/* add mask of the non-shared field if it's in use */
+	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8))
+		mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+
+	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
+		atomic_add(1 << (idx * 8), &er->ref);
+		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+			NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		er->config &= ~mask;
+		er->config |= (config & mask);
+		ret = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	return ret;
+}
+
+static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		atomic_dec(&er->ref);
+		return;
+	}
+
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	atomic_sub(1 << (idx * 8), &er->ref);
+}
+
+u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	int idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
+	u64 config = reg1->config;
+
+	/* get the non-shared control bits and shift them */
+	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (new_idx > orig_idx) {
+		idx = new_idx - orig_idx;
+		config <<= 3 * idx;
+	} else {
+		idx = orig_idx - new_idx;
+		config >>= 3 * idx;
+	}
+
+	/* add the shared control bits back */
+	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	if (modify) {
+		/* adjust the main event selector */
+		if (new_idx > orig_idx)
+			hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		else
+			hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		reg1->config = config;
+		reg1->idx = ~0xff | new_idx;
+	}
+	return config;
+}
+
+static struct event_constraint *
+nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int i, idx[2], alloc = 0;
+	u64 config1 = reg1->config;
+
+	idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
+	idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
+again:
+	for (i = 0; i < 2; i++) {
+		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+			idx[i] = 0xff;
+
+		if (idx[i] == 0xff)
+			continue;
+
+		if (!nhmex_mbox_get_shared_reg(box, idx[i],
+				__BITS_VALUE(config1, i, 32)))
+			goto fail;
+		alloc |= (0x1 << i);
+	}
+
+	/* for the match/mask registers */
+	if ((uncore_box_is_fake(box) || !reg2->alloc) &&
+	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
+		goto fail;
+
+	/*
+	 * If it's a fake box -- as per validate_{group,event}() we
+	 * shouldn't touch event state and we can avoid doing so
+	 * since both will only call get_event_constraints() once
+	 * on each event, this avoids the need for reg->alloc.
+	 */
+	if (!uncore_box_is_fake(box)) {
+		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
+			nhmex_mbox_alter_er(event, idx[0], true);
+		reg1->alloc |= alloc;
+		reg2->alloc = 1;
+	}
+	return NULL;
+fail:
+	if (idx[0] != 0xff && !(alloc & 0x1) &&
+	    idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		/*
+		 * events 0xd ~ 0x10 are functional identical, but are
+		 * controlled by different fields in the ZDP_CTL_FVC
+		 * register. If we failed to take one field, try the
+		 * rest 3 choices.
 		 */
-		for (i = 0; i < 8; i++) {
-			if (nodeid == ((config >> (3 * i)) & 0x7)) {
-				pcibus_to_physid[bus] = i;
-				break;
-			}
+		BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
+		idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		idx[0] = (idx[0] + 1) % 4;
+		idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
+			config1 = nhmex_mbox_alter_er(event, idx[0], false);
+			goto again;
 		}
-	};
-	return;
-}
-/* end of Sandy Bridge-EP uncore support */
+	}
 
+	if (alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, idx[0]);
+	if (alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, idx[1]);
+	return &constraint_empty;
+}
 
-/* Sandy Bridge uncore support */
-static void snb_uncore_msr_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
 
-	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
-	else
-		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+	if (uncore_box_is_fake(box))
+		return;
+
+	if (reg1->alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
+	if (reg1->alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
+	reg1->alloc = 0;
+
+	if (reg2->alloc) {
+		nhmex_mbox_put_shared_reg(box, reg2->idx);
+		reg2->alloc = 0;
+	}
 }
 
-static void snb_uncore_msr_disable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
 {
-	wrmsrl(event->hw.config_base, 0);
+	if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return er->idx;
+	return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
 }
 
-static u64 snb_uncore_msr_read_counter(struct intel_uncore_box *box,
-					struct perf_event *event)
+static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
 {
-	u64 count;
-	rdmsrl(event->hw.event_base, count);
-	return count;
+	struct intel_uncore_type *type = box->pmu->type;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	struct extra_reg *er;
+	unsigned msr;
+	int reg_idx = 0;
+
+	if (WARN_ON_ONCE(reg1->idx != -1))
+		return -EINVAL;
+	/*
+	 * The mbox events may require 2 extra MSRs at the most. But only
+	 * the lower 32 bits in these MSRs are significant, so we can use
+	 * config1 to pass two MSRs' config.
+	 */
+	for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		if (event->attr.config1 & ~er->valid_mask)
+			return -EINVAL;
+		if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) ||
+		    er->idx == __BITS_VALUE(reg1->idx, 1, 8))
+			continue;
+		if (WARN_ON_ONCE(reg_idx >= 2))
+			return -EINVAL;
+
+		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
+		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
+			return -EINVAL;
+
+		/* always use the 32~63 bits to pass the PLD config */
+		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
+			reg_idx = 1;
+
+		reg1->idx &= ~(0xff << (reg_idx * 8));
+		reg1->reg &= ~(0xffff << (reg_idx * 16));
+		reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
+		reg1->reg |= msr << (reg_idx * 16);
+		reg1->config = event->attr.config1;
+		reg_idx++;
+	}
+	/* use config2 to pass the filter config */
+	reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+	if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+		reg2->config = event->attr.config2;
+	else
+		reg2->config = ~0ULL;
+	if (box->pmu->pmu_idx == 0)
+		reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+	else
+		reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+
+	return 0;
 }
 
-static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
+static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
 {
-	if (box->pmu->pmu_idx == 0) {
-		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
-			SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
-	}
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	u64 config;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return box->shared_regs[idx].config;
+
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	config = er->config;
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+	return config;
 }
 
-static struct attribute *snb_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_cmask5.attr,
+static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx;
+
+	idx = __BITS_VALUE(reg1->idx, 0, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+	idx = __BITS_VALUE(reg1->idx, 1, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+
+	wrmsrl(reg2->reg, 0);
+	if (reg2->config != ~0ULL) {
+		wrmsrl(reg2->reg + 1,
+			reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+		wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+			(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+		wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(count_mode,	count_mode,	"config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode,	"config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,	wrap_mode,	"config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode,	flag_mode,	"config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel,	inc_sel,	"config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,	set_flag_sel,	"config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg,	filter_cfg,	"config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match,	filter_match,	"config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask,	filter_mask,	"config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp,		dsp,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr,		thr,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc,		fvc,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt,		pgt,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map,		map,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss,		iss,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld,		pld,		"config1:32-63");
+
+static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
+	&format_attr_count_mode.attr,
+	&format_attr_storage_mode.attr,
+	&format_attr_wrap_mode.attr,
+	&format_attr_flag_mode.attr,
+	&format_attr_inc_sel.attr,
+	&format_attr_set_flag_sel.attr,
+	&format_attr_filter_cfg.attr,
+	&format_attr_filter_match.attr,
+	&format_attr_filter_mask.attr,
+	&format_attr_dsp.attr,
+	&format_attr_thr.attr,
+	&format_attr_fvc.attr,
+	&format_attr_pgt.attr,
+	&format_attr_map.attr,
+	&format_attr_iss.attr,
+	&format_attr_pld.attr,
 	NULL,
 };
 
-static struct attribute_group snb_uncore_format_group = {
-	.name = "format",
-	.attrs = snb_uncore_formats_attr,
+static struct attribute_group nhmex_uncore_mbox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_mbox_formats_attr,
 };
 
-static struct intel_uncore_ops snb_uncore_msr_ops = {
-	.init_box	= snb_uncore_msr_init_box,
-	.disable_event	= snb_uncore_msr_disable_event,
-	.enable_event	= snb_uncore_msr_enable_event,
-	.read_counter	= snb_uncore_msr_read_counter,
+static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
+	{ /* end: all zeroes */ },
 };
 
-static struct event_constraint snb_uncore_cbox_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
-	EVENT_CONSTRAINT_END
+static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_mbox_msr_enable_event,
+	.hw_config	= nhmex_mbox_hw_config,
+	.get_constraint	= nhmex_mbox_get_constraint,
+	.put_constraint	= nhmex_mbox_put_constraint,
 };
 
-static struct intel_uncore_type snb_uncore_cbox = {
-	.name		= "cbox",
-	.num_counters   = 2,
-	.num_boxes	= 4,
-	.perf_ctr_bits	= 44,
-	.fixed_ctr_bits	= 48,
-	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
-	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
-	.fixed_ctr	= SNB_UNC_FIXED_CTR,
-	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
-	.single_fixed	= 1,
-	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
-	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
-	.constraints	= snb_uncore_cbox_constraints,
-	.ops		= &snb_uncore_msr_ops,
-	.format_group	= &snb_uncore_format_group,
+static struct intel_uncore_type nhmex_uncore_mbox = {
+	.name			= "mbox",
+	.num_counters		= 6,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_M0_MSR_PMU_CTL0,
+	.perf_ctr		= NHMEX_M0_MSR_PMU_CNT0,
+	.event_mask		= NHMEX_M_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_M0_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_M_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 8,
+	.event_descs		= nhmex_uncore_mbox_events,
+	.ops			= &nhmex_uncore_mbox_ops,
+	.format_group		= &nhmex_uncore_mbox_format_group,
 };
 
-static struct intel_uncore_type *snb_msr_uncores[] = {
-	&snb_uncore_cbox,
-	NULL,
-};
-/* end of Sandy Bridge uncore support */
+void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	int port;
 
-/* Nehalem uncore support */
-static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
+	/* adjust the main event selector */
+	if (reg1->idx % 2) {
+		reg1->idx--;
+		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	} else {
+		reg1->idx++;
+		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	}
+
+	/* adjust address or config of extra register */
+	port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
+	switch (reg1->idx % 6) {
+	case 0:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
+		break;
+	case 1:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
+		break;
+	case 2:
+		/* the 8~15 bits to the 0~7 bits */
+		reg1->config >>= 8;
+		break;
+	case 3:
+		/* the 0~7 bits to the 8~15 bits */
+		reg1->config <<= 8;
+		break;
+	case 4:
+		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
+		break;
+	case 5:
+		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
+		break;
+	};
+}
+
+/*
+ * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
+ * An event set consists of 6 events, the 3rd and 4th events in
+ * an event set use the same extra register. So an event set uses
+ * 5 extra registers.
+ */
+static struct event_constraint *
+nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	int idx, er_idx;
+	u64 config1;
+	bool ok = false;
+
+	if (!uncore_box_is_fake(box) && reg1->alloc)
+		return NULL;
+
+	idx = reg1->idx % 6;
+	config1 = reg1->config;
+again:
+	er_idx = idx;
+	/* the 3rd and 4th events use the same extra register */
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (idx < 2) {
+		if (!atomic_read(&er->ref) || er->config == reg1->config) {
+			atomic_inc(&er->ref);
+			er->config = reg1->config;
+			ok = true;
+		}
+	} else if (idx == 2 || idx == 3) {
+		/*
+		 * these two events use different fields in a extra register,
+		 * the 0~7 bits and the 8~15 bits respectively.
+		 */
+		u64 mask = 0xff << ((idx - 2) * 8);
+		if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
+				!((er->config ^ config1) & mask)) {
+			atomic_add(1 << ((idx - 2) * 8), &er->ref);
+			er->config &= ~mask;
+			er->config |= config1 & mask;
+			ok = true;
+		}
+	} else {
+		if (!atomic_read(&er->ref) ||
+				(er->config == (hwc->config >> 32) &&
+				 er->config1 == reg1->config &&
+				 er->config2 == reg2->config)) {
+			atomic_inc(&er->ref);
+			er->config = (hwc->config >> 32);
+			er->config1 = reg1->config;
+			er->config2 = reg2->config;
+			ok = true;
+		}
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (!ok) {
+		/*
+		 * The Rbox events are always in pairs. The paired
+		 * events are functional identical, but use different
+		 * extra registers. If we failed to take an extra
+		 * register, try the alternative.
+		 */
+		if (idx % 2)
+			idx--;
+		else
+			idx++;
+		if (idx != reg1->idx % 6) {
+			if (idx == 2)
+				config1 >>= 8;
+			else if (idx == 3)
+				config1 <<= 8;
+			goto again;
+		}
+	} else {
+		if (!uncore_box_is_fake(box)) {
+			if (idx != reg1->idx % 6)
+				nhmex_rbox_alter_er(box, event);
+			reg1->alloc = 1;
+		}
+		return NULL;
+	}
+	return &constraint_empty;
 }
 
-static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
+static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL,
-		NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	int idx, er_idx;
+
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	idx = reg1->idx % 6;
+	er_idx = idx;
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	if (idx == 2 || idx == 3)
+		atomic_sub(1 << ((idx - 2) * 8), &er->ref);
+	else
+		atomic_dec(&er->ref);
+
+	reg1->alloc = 0;
 }
 
-static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int port, idx;
 
-	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
-	else
-		wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
+		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	if (idx >= 0x18)
+		return -EINVAL;
+
+	reg1->idx = idx;
+	reg1->config = event->attr.config1;
+
+	port = idx / 6 + box->pmu->pmu_idx * 4;
+	idx %= 6;
+	switch (idx) {
+	case 0:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
+		break;
+	case 1:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
+		break;
+	case 2:
+	case 3:
+		reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port);
+		break;
+	case 4:
+	case 5:
+		if (idx == 4)
+			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
+		else
+			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
+		reg2->config = event->attr.config2;
+		hwc->config |= event->attr.config & (~0ULL << 32);
+		break;
+	};
+	return 0;
 }
 
-static struct attribute *nhm_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_cmask8.attr,
+static u64 nhmex_rbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	u64 config;
+
+	er = &box->shared_regs[idx];
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	config = er->config;
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	return config;
+}
+
+static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx, er_idx;
+
+	idx = reg1->idx % 6;
+	er_idx = idx;
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	switch (idx) {
+	case 0:
+	case 1:
+		wrmsrl(reg1->reg, reg1->config);
+		break;
+	case 2:
+	case 3:
+		wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx));
+		break;
+	case 4:
+	case 5:
+		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(reg1->reg + 1, hwc->config >> 32);
+		wrmsrl(reg1->reg + 2, reg2->config);
+		break;
+	};
+
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
+DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
+
+static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_xbr_mm_cfg.attr,
+	&format_attr_xbr_match.attr,
+	&format_attr_xbr_mask.attr,
+	&format_attr_qlx_cfg.attr,
+	&format_attr_iperf_cfg.attr,
 	NULL,
 };
 
-static struct attribute_group nhm_uncore_format_group = {
+static struct attribute_group nhmex_uncore_rbox_format_group = {
 	.name = "format",
-	.attrs = nhm_uncore_formats_attr,
+	.attrs = nhmex_uncore_rbox_formats_attr,
 };
 
-static struct uncore_event_desc nhm_uncore_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks,                "event=0xff,umask=0x00"),
-	INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any,       "event=0x2f,umask=0x0f"),
-	INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any,      "event=0x2c,umask=0x0f"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads,     "event=0x20,umask=0x01"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes,    "event=0x20,umask=0x02"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads,  "event=0x20,umask=0x04"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads,   "event=0x20,umask=0x10"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes,  "event=0x20,umask=0x20"),
+static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(qpi0_flit_send,		"event=0x0,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_filt_send,		"event=0x6,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt,		"event=0x0,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt,		"event=0x6,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_date_response,	"event=0x0,iperf_cfg=0xc4"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_date_response,	"event=0x6,iperf_cfg=0xc4"),
 	{ /* end: all zeroes */ },
 };
 
-static struct intel_uncore_ops nhm_uncore_msr_ops = {
-	.disable_box	= nhm_uncore_msr_disable_box,
-	.enable_box	= nhm_uncore_msr_enable_box,
-	.disable_event	= snb_uncore_msr_disable_event,
-	.enable_event	= nhm_uncore_msr_enable_event,
-	.read_counter	= snb_uncore_msr_read_counter,
+static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_rbox_msr_enable_event,
+	.hw_config		= nhmex_rbox_hw_config,
+	.get_constraint		= nhmex_rbox_get_constraint,
+	.put_constraint		= nhmex_rbox_put_constraint,
 };
 
-static struct intel_uncore_type nhm_uncore = {
-	.name		= "",
-	.num_counters   = 8,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	.fixed_ctr_bits	= 48,
-	.event_ctl	= NHM_UNC_PERFEVTSEL0,
-	.perf_ctr	= NHM_UNC_UNCORE_PMC0,
-	.fixed_ctr	= NHM_UNC_FIXED_CTR,
-	.fixed_ctl	= NHM_UNC_FIXED_CTR_CTRL,
-	.event_mask	= NHM_UNC_RAW_EVENT_MASK,
-	.event_descs	= nhm_uncore_events,
-	.ops		= &nhm_uncore_msr_ops,
-	.format_group	= &nhm_uncore_format_group,
+static struct intel_uncore_type nhmex_uncore_rbox = {
+	.name			= "rbox",
+	.num_counters		= 8,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_R_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_R_MSR_PMON_CNT0,
+	.event_mask		= NHMEX_R_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_R_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_R_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 20,
+	.event_descs		= nhmex_uncore_rbox_events,
+	.ops			= &nhmex_uncore_rbox_ops,
+	.format_group		= &nhmex_uncore_rbox_format_group
 };
 
-static struct intel_uncore_type *nhm_msr_uncores[] = {
-	&nhm_uncore,
+static struct intel_uncore_type *nhmex_msr_uncores[] = {
+	&nhmex_uncore_ubox,
+	&nhmex_uncore_cbox,
+	&nhmex_uncore_bbox,
+	&nhmex_uncore_sbox,
+	&nhmex_uncore_mbox,
+	&nhmex_uncore_rbox,
+	&nhmex_uncore_wbox,
 	NULL,
 };
-/* end of Nehalem uncore support */
+/* end of Nehalem-EX uncore support */
 
-static void uncore_assign_hw_event(struct intel_uncore_box *box,
-				struct perf_event *event, int idx)
+static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -787,8 +1841,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box,
 	hwc->event_base  = uncore_perf_ctr(box, hwc->idx);
 }
 
-static void uncore_perf_event_update(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 prev_count, new_count, delta;
 	int shift;
@@ -858,14 +1911,12 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
-					  int cpu)
+struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
 {
 	struct intel_uncore_box *box;
 	int i, size;
 
-	size = sizeof(*box) + type->num_shared_regs *
-		sizeof(struct intel_uncore_extra_reg);
+	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
 	box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu));
 	if (!box)
@@ -915,12 +1966,11 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 	 * perf core schedules event on the basis of cpu, uncore events are
 	 * collected by one of the cpus inside a physical package.
 	 */
-	return uncore_pmu_to_box(uncore_event_to_pmu(event),
-				 smp_processor_id());
+	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
 }
 
-static int uncore_collect_events(struct intel_uncore_box *box,
-				struct perf_event *leader, bool dogrp)
+static int
+uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
 	struct perf_event *event;
 	int n, max_count;
@@ -952,8 +2002,7 @@ static int uncore_collect_events(struct intel_uncore_box *box,
 }
 
 static struct event_constraint *
-uncore_get_event_constraint(struct intel_uncore_box *box,
-			    struct perf_event *event)
+uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct intel_uncore_type *type = box->pmu->type;
 	struct event_constraint *c;
@@ -977,15 +2026,13 @@ uncore_get_event_constraint(struct intel_uncore_box *box,
 	return &type->unconstrainted;
 }
 
-static void uncore_put_event_constraint(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void uncore_put_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	if (box->pmu->type->ops->put_constraint)
 		box->pmu->type->ops->put_constraint(box, event);
 }
 
-static int uncore_assign_events(struct intel_uncore_box *box,
-				int assign[], int n)
+static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n)
 {
 	unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
 	struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX];
@@ -1407,8 +2454,7 @@ static bool pcidrv_registered;
 /*
  * add a pci uncore device
  */
-static int __devinit uncore_pci_add(struct intel_uncore_type *type,
-				    struct pci_dev *pdev)
+static int __devinit uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
 {
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
@@ -1485,6 +2531,7 @@ static int __devinit uncore_pci_probe(struct pci_dev *pdev,
 	struct intel_uncore_type *type;
 
 	type = (struct intel_uncore_type *)id->driver_data;
+
 	return uncore_pci_add(type, pdev);
 }
 
@@ -1612,8 +2659,8 @@ static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id)
 	return 0;
 }
 
-static void __cpuinit uncore_change_context(struct intel_uncore_type **uncores,
-					    int old_cpu, int new_cpu)
+static void __cpuinit
+uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu)
 {
 	struct intel_uncore_type *type;
 	struct intel_uncore_pmu *pmu;
@@ -1694,8 +2741,8 @@ static void __cpuinit uncore_event_init_cpu(int cpu)
 	uncore_change_context(pci_uncores, -1, cpu);
 }
 
-static int __cpuinit uncore_cpu_notifier(struct notifier_block *self,
-					 unsigned long action, void *hcpu)
+static int
+ __cpuinit uncore_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
@@ -1732,12 +2779,12 @@ static int __cpuinit uncore_cpu_notifier(struct notifier_block *self,
 }
 
 static struct notifier_block uncore_cpu_nb __cpuinitdata = {
-	.notifier_call = uncore_cpu_notifier,
+	.notifier_call	= uncore_cpu_notifier,
 	/*
 	 * to migrate uncore events, our notifier should be executed
 	 * before perf core's notifier.
 	 */
-	.priority = CPU_PRI_PERF + 1,
+	.priority	= CPU_PRI_PERF + 1,
 };
 
 static void __init uncore_cpu_setup(void *dummy)
@@ -1767,6 +2814,9 @@ static int __init uncore_cpu_init(void)
 			snbep_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = snbep_msr_uncores;
 		break;
+	case 46:
+		msr_uncores = nhmex_msr_uncores;
+		break;
 	default:
 		return 0;
 	}

arch/x86/kernel/cpu/perf_event_intel_uncore.h

@@ -5,8 +5,6 @@
 #include "perf_event.h"
 
 #define UNCORE_PMU_NAME_LEN		32
-#define UNCORE_BOX_HASH_SIZE		8
-
 #define UNCORE_PMU_HRTIMER_INTERVAL	(60 * NSEC_PER_SEC)
 
 #define UNCORE_FIXED_EVENT		0xff
@@ -115,6 +113,10 @@
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
 
+#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_RAW_EVENT_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT)
+
 /* SNB-EP pci control register */
 #define SNBEP_PCI_PMON_BOX_CTL			0xf4
 #define SNBEP_PCI_PMON_CTL0			0xd8
@@ -158,6 +160,193 @@
 #define SNBEP_PCU_MSR_CORE_C3_CTR		0x3fc
 #define SNBEP_PCU_MSR_CORE_C6_CTR		0x3fd
 
+/* NHM-EX event control */
+#define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
+#define NHMEX_PMON_CTL_UMASK_MASK	0x0000ff00
+#define NHMEX_PMON_CTL_EN_BIT0		(1 << 0)
+#define NHMEX_PMON_CTL_EDGE_DET		(1 << 18)
+#define NHMEX_PMON_CTL_PMI_EN		(1 << 20)
+#define NHMEX_PMON_CTL_EN_BIT22		(1 << 22)
+#define NHMEX_PMON_CTL_INVERT		(1 << 23)
+#define NHMEX_PMON_CTL_TRESH_MASK	0xff000000
+#define NHMEX_PMON_RAW_EVENT_MASK	(NHMEX_PMON_CTL_EV_SEL_MASK | \
+					 NHMEX_PMON_CTL_UMASK_MASK | \
+					 NHMEX_PMON_CTL_EDGE_DET | \
+					 NHMEX_PMON_CTL_INVERT | \
+					 NHMEX_PMON_CTL_TRESH_MASK)
+
+/* NHM-EX Ubox */
+#define NHMEX_U_MSR_PMON_GLOBAL_CTL		0xc00
+#define NHMEX_U_MSR_PMON_CTR			0xc11
+#define NHMEX_U_MSR_PMON_EV_SEL			0xc10
+
+#define NHMEX_U_PMON_GLOBAL_EN			(1 << 0)
+#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL	0x0000001e
+#define NHMEX_U_PMON_GLOBAL_EN_ALL		(1 << 28)
+#define NHMEX_U_PMON_GLOBAL_RST_ALL		(1 << 29)
+#define NHMEX_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
+
+#define NHMEX_U_PMON_RAW_EVENT_MASK		\
+		(NHMEX_PMON_CTL_EV_SEL_MASK |	\
+		 NHMEX_PMON_CTL_EDGE_DET)
+
+/* NHM-EX Cbox */
+#define NHMEX_C0_MSR_PMON_GLOBAL_CTL		0xd00
+#define NHMEX_C0_MSR_PMON_CTR0			0xd11
+#define NHMEX_C0_MSR_PMON_EV_SEL0		0xd10
+#define NHMEX_C_MSR_OFFSET			0x20
+
+/* NHM-EX Bbox */
+#define NHMEX_B0_MSR_PMON_GLOBAL_CTL		0xc20
+#define NHMEX_B0_MSR_PMON_CTR0			0xc31
+#define NHMEX_B0_MSR_PMON_CTL0			0xc30
+#define NHMEX_B_MSR_OFFSET			0x40
+#define NHMEX_B0_MSR_MATCH			0xe45
+#define NHMEX_B0_MSR_MASK			0xe46
+#define NHMEX_B1_MSR_MATCH			0xe4d
+#define NHMEX_B1_MSR_MASK			0xe4e
+
+#define NHMEX_B_PMON_CTL_EN			(1 << 0)
+#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_B_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_B_PMON_CTR_SHIFT		6
+#define NHMEX_B_PMON_CTR_MASK		\
+		(0x3 << NHMEX_B_PMON_CTR_SHIFT)
+#define NHMEX_B_PMON_RAW_EVENT_MASK		\
+		(NHMEX_B_PMON_CTL_EV_SEL_MASK | \
+		 NHMEX_B_PMON_CTR_MASK)
+
+/* NHM-EX Sbox */
+#define NHMEX_S0_MSR_PMON_GLOBAL_CTL		0xc40
+#define NHMEX_S0_MSR_PMON_CTR0			0xc51
+#define NHMEX_S0_MSR_PMON_CTL0			0xc50
+#define NHMEX_S_MSR_OFFSET			0x80
+#define NHMEX_S0_MSR_MM_CFG			0xe48
+#define NHMEX_S0_MSR_MATCH			0xe49
+#define NHMEX_S0_MSR_MASK			0xe4a
+#define NHMEX_S1_MSR_MM_CFG			0xe58
+#define NHMEX_S1_MSR_MATCH			0xe59
+#define NHMEX_S1_MSR_MASK			0xe5a
+
+#define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
+
+/* NHM-EX Mbox */
+#define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
+#define NHMEX_M0_MSR_PMU_DSP			0xca5
+#define NHMEX_M0_MSR_PMU_ISS			0xca6
+#define NHMEX_M0_MSR_PMU_MAP			0xca7
+#define NHMEX_M0_MSR_PMU_MSC_THR		0xca8
+#define NHMEX_M0_MSR_PMU_PGT			0xca9
+#define NHMEX_M0_MSR_PMU_PLD			0xcaa
+#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC		0xcab
+#define NHMEX_M0_MSR_PMU_CTL0			0xcb0
+#define NHMEX_M0_MSR_PMU_CNT0			0xcb1
+#define NHMEX_M_MSR_OFFSET			0x40
+#define NHMEX_M0_MSR_PMU_MM_CFG			0xe54
+#define NHMEX_M1_MSR_PMU_MM_CFG			0xe5c
+
+#define NHMEX_M_PMON_MM_CFG_EN			(1ULL << 63)
+#define NHMEX_M_PMON_ADDR_MATCH_MASK		0x3ffffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_MASK		0x7ffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_SHIFT		34
+
+#define NHMEX_M_PMON_CTL_EN			(1 << 0)
+#define NHMEX_M_PMON_CTL_PMI_EN			(1 << 1)
+#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT	2
+#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT	4
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_WRAP_MODE		(1 << 6)
+#define NHMEX_M_PMON_CTL_FLAG_MODE		(1 << 7)
+#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT		9
+#define NHMEX_M_PMON_CTL_INC_SEL_MASK		\
+	(0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT	19
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK	\
+	(0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
+#define NHMEX_M_PMON_RAW_EVENT_MASK			\
+		(NHMEX_M_PMON_CTL_COUNT_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_STORAGE_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_WRAP_MODE |		\
+		 NHMEX_M_PMON_CTL_FLAG_MODE |		\
+		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
+		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
+
+
+#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK	0x1f
+#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK	(0x7 << 5)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK	(0x7 << 8)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR	(1 << 23)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK			\
+		(NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK |	\
+		 NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK |	\
+		 NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK  |	\
+		 NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (11 + 3 * (n)))
+
+/*
+ * use the 9~13 bits to select event If the 7th bit is not set,
+ * otherwise use the 19~21 bits to select event.
+ */
+#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+			   NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_EXTAR_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
+#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_SET_FLAG_SEL_MASK, \
+				(u64)-1, NHMEX_M_##r)
+
+/* NHM-EX Rbox */
+#define NHMEX_R_MSR_GLOBAL_CTL			0xe00
+#define NHMEX_R_MSR_PMON_CTL0			0xe10
+#define NHMEX_R_MSR_PMON_CNT0			0xe11
+#define NHMEX_R_MSR_OFFSET			0x20
+
+#define NHMEX_R_MSR_PORTN_QLX_CFG(n)		\
+		((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n)		(0xe04 + (n))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n)		(0xe24 + (n))
+#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n)		\
+		(((n) < 4 ? 0 : 0x10) + (n) * 4)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n)	\
+		(0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n)	\
+		(0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
+
+#define NHMEX_R_PMON_CTL_EN			(1 << 0)
+#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_R_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_R_PMON_CTL_PMI_EN			(1 << 6)
+#define NHMEX_R_PMON_RAW_EVENT_MASK		NHMEX_R_PMON_CTL_EV_SEL_MASK
+
+/* NHM-EX Wbox */
+#define NHMEX_W_MSR_GLOBAL_CTL			0xc80
+#define NHMEX_W_MSR_PMON_CNT0			0xc90
+#define NHMEX_W_MSR_PMON_EVT_SEL0		0xc91
+#define NHMEX_W_MSR_PMON_FIXED_CTR		0x394
+#define NHMEX_W_MSR_PMON_FIXED_CTL		0x395
+
+#define NHMEX_W_PMON_GLOBAL_FIXED_EN		(1ULL << 31)
+
 struct intel_uncore_ops;
 struct intel_uncore_pmu;
 struct intel_uncore_box;
@@ -178,6 +367,7 @@ struct intel_uncore_type {
 	unsigned msr_offset;
 	unsigned num_shared_regs:8;
 	unsigned single_fixed:1;
+	unsigned pair_ctr_ctl:1;
 	struct event_constraint unconstrainted;
 	struct event_constraint *constraints;
 	struct intel_uncore_pmu *pmus;
@@ -213,7 +403,7 @@ struct intel_uncore_pmu {
 
 struct intel_uncore_extra_reg {
 	raw_spinlock_t lock;
-	u64 config1;
+	u64 config, config1, config2;
 	atomic_t ref;
 };
 
@@ -323,14 +513,16 @@ unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
 static inline
 unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
-	return idx + box->pmu->type->event_ctl +
+	return box->pmu->type->event_ctl +
+		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
 		box->pmu->type->msr_offset * box->pmu->pmu_idx;
 }
 
 static inline
 unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
 {
-	return idx + box->pmu->type->perf_ctr +
+	return box->pmu->type->perf_ctr +
+		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
 		box->pmu->type->msr_offset * box->pmu->pmu_idx;
 }
 
@@ -422,3 +614,8 @@ static inline void uncore_box_init(struct intel_uncore_box *box)
 			box->pmu->type->ops->init_box(box);
 	}
 }
+
+static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
+{
+	return (box->phys_id < 0);
+}

kernel/events/uprobes.c

@@ -32,6 +32,7 @@
 #include <linux/swap.h>		/* try_to_free_swap */
 #include <linux/ptrace.h>	/* user_enable_single_step */
 #include <linux/kdebug.h>	/* notifier mechanism */
+#include "../../mm/internal.h"	/* munlock_vma_page */
 
 #include <linux/uprobes.h>
 
@@ -112,14 +113,14 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register)
 	return false;
 }
 
-static loff_t vma_address(struct vm_area_struct *vma, loff_t offset)
+static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset)
 {
-	loff_t vaddr;
-
-	vaddr = vma->vm_start + offset;
-	vaddr -= vma->vm_pgoff << PAGE_SHIFT;
+	return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+}
 
-	return vaddr;
+static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
+{
+	return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start);
 }
 
 /**
@@ -127,25 +128,27 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset)
  * based on replace_page in mm/ksm.c
  *
  * @vma:      vma that holds the pte pointing to page
+ * @addr:     address the old @page is mapped at
  * @page:     the cowed page we are replacing by kpage
  * @kpage:    the modified page we replace page by
  *
  * Returns 0 on success, -EFAULT on failure.
  */
-static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage)
+static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
+				struct page *page, struct page *kpage)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long addr;
 	spinlock_t *ptl;
 	pte_t *ptep;
+	int err;
 
-	addr = page_address_in_vma(page, vma);
-	if (addr == -EFAULT)
-		return -EFAULT;
+	/* For try_to_free_swap() and munlock_vma_page() below */
+	lock_page(page);
 
+	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
 	if (!ptep)
-		return -EAGAIN;
+		goto unlock;
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr);
@@ -162,10 +165,16 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct
 	page_remove_rmap(page);
 	if (!page_mapped(page))
 		try_to_free_swap(page);
-	put_page(page);
 	pte_unmap_unlock(ptep, ptl);
 
-	return 0;
+	if (vma->vm_flags & VM_LOCKED)
+		munlock_vma_page(page);
+	put_page(page);
+
+	err = 0;
+ unlock:
+	unlock_page(page);
+	return err;
 }
 
 /**
@@ -206,45 +215,23 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 			unsigned long vaddr, uprobe_opcode_t opcode)
 {
 	struct page *old_page, *new_page;
-	struct address_space *mapping;
 	void *vaddr_old, *vaddr_new;
 	struct vm_area_struct *vma;
-	struct uprobe *uprobe;
 	int ret;
+
 retry:
 	/* Read the page with vaddr into memory */
 	ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
 	if (ret <= 0)
 		return ret;
 
-	ret = -EINVAL;
-
-	/*
-	 * We are interested in text pages only. Our pages of interest
-	 * should be mapped for read and execute only. We desist from
-	 * adding probes in write mapped pages since the breakpoints
-	 * might end up in the file copy.
-	 */
-	if (!valid_vma(vma, is_swbp_insn(&opcode)))
-		goto put_out;
-
-	uprobe = container_of(auprobe, struct uprobe, arch);
-	mapping = uprobe->inode->i_mapping;
-	if (mapping != vma->vm_file->f_mapping)
-		goto put_out;
-
 	ret = -ENOMEM;
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 	if (!new_page)
-		goto put_out;
+		goto put_old;
 
 	__SetPageUptodate(new_page);
 
-	/*
-	 * lock page will serialize against do_wp_page()'s
-	 * PageAnon() handling
-	 */
-	lock_page(old_page);
 	/* copy the page now that we've got it stable */
 	vaddr_old = kmap_atomic(old_page);
 	vaddr_new = kmap_atomic(new_page);
@@ -257,17 +244,13 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 
 	ret = anon_vma_prepare(vma);
 	if (ret)
-		goto unlock_out;
+		goto put_new;
 
-	lock_page(new_page);
-	ret = __replace_page(vma, old_page, new_page);
-	unlock_page(new_page);
+	ret = __replace_page(vma, vaddr, old_page, new_page);
 
-unlock_out:
-	unlock_page(old_page);
+put_new:
 	page_cache_release(new_page);
-
-put_out:
+put_old:
 	put_page(old_page);
 
 	if (unlikely(ret == -EAGAIN))
@@ -791,7 +774,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 		curr = info;
 
 		info->mm = vma->vm_mm;
-		info->vaddr = vma_address(vma, offset);
+		info->vaddr = offset_to_vaddr(vma, offset);
 	}
 	mutex_unlock(&mapping->i_mmap_mutex);
 
@@ -839,12 +822,13 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 			goto free;
 
 		down_write(&mm->mmap_sem);
-		vma = find_vma(mm, (unsigned long)info->vaddr);
-		if (!vma || !valid_vma(vma, is_register))
+		vma = find_vma(mm, info->vaddr);
+		if (!vma || !valid_vma(vma, is_register) ||
+		    vma->vm_file->f_mapping->host != uprobe->inode)
 			goto unlock;
 
-		if (vma->vm_file->f_mapping->host != uprobe->inode ||
-		    vma_address(vma, uprobe->offset) != info->vaddr)
+		if (vma->vm_start > info->vaddr ||
+		    vaddr_to_offset(vma, info->vaddr) != uprobe->offset)
 			goto unlock;
 
 		if (is_register) {
@@ -960,59 +944,66 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume
 		put_uprobe(uprobe);
 }
 
-/*
- * Of all the nodes that correspond to the given inode, return the node
- * with the least offset.
- */
-static struct rb_node *find_least_offset_node(struct inode *inode)
+static struct rb_node *
+find_node_in_range(struct inode *inode, loff_t min, loff_t max)
 {
-	struct uprobe u = { .inode = inode, .offset = 0};
 	struct rb_node *n = uprobes_tree.rb_node;
-	struct rb_node *close_node = NULL;
-	struct uprobe *uprobe;
-	int match;
 
 	while (n) {
-		uprobe = rb_entry(n, struct uprobe, rb_node);
-		match = match_uprobe(&u, uprobe);
-
-		if (uprobe->inode == inode)
-			close_node = n;
-
-		if (!match)
-			return close_node;
+		struct uprobe *u = rb_entry(n, struct uprobe, rb_node);
 
-		if (match < 0)
+		if (inode < u->inode) {
 			n = n->rb_left;
-		else
+		} else if (inode > u->inode) {
 			n = n->rb_right;
+		} else {
+			if (max < u->offset)
+				n = n->rb_left;
+			else if (min > u->offset)
+				n = n->rb_right;
+			else
+				break;
+		}
 	}
 
-	return close_node;
+	return n;
 }
 
 /*
- * For a given inode, build a list of probes that need to be inserted.
+ * For a given range in vma, build a list of probes that need to be inserted.
  */
-static void build_probe_list(struct inode *inode, struct list_head *head)
+static void build_probe_list(struct inode *inode,
+				struct vm_area_struct *vma,
+				unsigned long start, unsigned long end,
+				struct list_head *head)
 {
-	struct uprobe *uprobe;
+	loff_t min, max;
 	unsigned long flags;
-	struct rb_node *n;
-
-	spin_lock_irqsave(&uprobes_treelock, flags);
-
-	n = find_least_offset_node(inode);
+	struct rb_node *n, *t;
+	struct uprobe *u;
 
-	for (; n; n = rb_next(n)) {
-		uprobe = rb_entry(n, struct uprobe, rb_node);
-		if (uprobe->inode != inode)
-			break;
+	INIT_LIST_HEAD(head);
+	min = vaddr_to_offset(vma, start);
+	max = min + (end - start) - 1;
 
-		list_add(&uprobe->pending_list, head);
-		atomic_inc(&uprobe->ref);
+	spin_lock_irqsave(&uprobes_treelock, flags);
+	n = find_node_in_range(inode, min, max);
+	if (n) {
+		for (t = n; t; t = rb_prev(t)) {
+			u = rb_entry(t, struct uprobe, rb_node);
+			if (u->inode != inode || u->offset < min)
+				break;
+			list_add(&u->pending_list, head);
+			atomic_inc(&u->ref);
+		}
+		for (t = n; (t = rb_next(t)); ) {
+			u = rb_entry(t, struct uprobe, rb_node);
+			if (u->inode != inode || u->offset > max)
+				break;
+			list_add(&u->pending_list, head);
+			atomic_inc(&u->ref);
+		}
 	}
-
 	spin_unlock_irqrestore(&uprobes_treelock, flags);
 }
 
@@ -1031,7 +1022,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head)
 int uprobe_mmap(struct vm_area_struct *vma)
 {
 	struct list_head tmp_list;
-	struct uprobe *uprobe;
+	struct uprobe *uprobe, *u;
 	struct inode *inode;
 	int ret, count;
 
@@ -1042,21 +1033,15 @@ int uprobe_mmap(struct vm_area_struct *vma)
 	if (!inode)
 		return 0;
 
-	INIT_LIST_HEAD(&tmp_list);
 	mutex_lock(uprobes_mmap_hash(inode));
-	build_probe_list(inode, &tmp_list);
+	build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list);
 
 	ret = 0;
 	count = 0;
 
-	list_for_each_entry(uprobe, &tmp_list, pending_list) {
+	list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
 		if (!ret) {
-			loff_t vaddr = vma_address(vma, uprobe->offset);
-
-			if (vaddr < vma->vm_start || vaddr >= vma->vm_end) {
-				put_uprobe(uprobe);
-				continue;
-			}
+			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
 
 			ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
 			/*
@@ -1097,12 +1082,15 @@ int uprobe_mmap(struct vm_area_struct *vma)
 void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 	struct list_head tmp_list;
-	struct uprobe *uprobe;
+	struct uprobe *uprobe, *u;
 	struct inode *inode;
 
 	if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
 		return;
 
+	if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
+		return;
+
 	if (!atomic_read(&vma->vm_mm->uprobes_state.count))
 		return;
 
@@ -1110,21 +1098,17 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
 	if (!inode)
 		return;
 
-	INIT_LIST_HEAD(&tmp_list);
 	mutex_lock(uprobes_mmap_hash(inode));
-	build_probe_list(inode, &tmp_list);
-
-	list_for_each_entry(uprobe, &tmp_list, pending_list) {
-		loff_t vaddr = vma_address(vma, uprobe->offset);
-
-		if (vaddr >= start && vaddr < end) {
-			/*
-			 * An unregister could have removed the probe before
-			 * unmap. So check before we decrement the count.
-			 */
-			if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1)
-				atomic_dec(&vma->vm_mm->uprobes_state.count);
-		}
+	build_probe_list(inode, vma, start, end, &tmp_list);
+
+	list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
+		unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
+		/*
+		 * An unregister could have removed the probe before
+		 * unmap. So check before we decrement the count.
+		 */
+		if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1)
+			atomic_dec(&vma->vm_mm->uprobes_state.count);
 		put_uprobe(uprobe);
 	}
 	mutex_unlock(uprobes_mmap_hash(inode));
@@ -1463,12 +1447,9 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 	vma = find_vma(mm, bp_vaddr);
 	if (vma && vma->vm_start <= bp_vaddr) {
 		if (valid_vma(vma, false)) {
-			struct inode *inode;
-			loff_t offset;
+			struct inode *inode = vma->vm_file->f_mapping->host;
+			loff_t offset = vaddr_to_offset(vma, bp_vaddr);
 
-			inode = vma->vm_file->f_mapping->host;
-			offset = bp_vaddr - vma->vm_start;
-			offset += (vma->vm_pgoff << PAGE_SHIFT);
 			uprobe = find_uprobe(inode, offset);
 		}
 

kernel/sched/core.c

@@ -1910,12 +1910,12 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
+	trace_sched_switch(prev, next);
 	sched_info_switch(prev, next);
 	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
 	prepare_lock_switch(rq, next);
 	prepare_arch_switch(next);
-	trace_sched_switch(prev, next);
 }
 
 /**

mm/mmap.c

@@ -2345,9 +2345,6 @@ int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
 	     security_vm_enough_memory_mm(mm, vma_pages(vma)))
 		return -ENOMEM;
 
-	if (vma->vm_file && uprobe_mmap(vma))
-		return -EINVAL;
-
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	return 0;
 }
@@ -2418,9 +2415,6 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			if (new_vma->vm_file) {
 				get_file(new_vma->vm_file);
 
-				if (uprobe_mmap(new_vma))
-					goto out_free_mempol;
-
 				if (vma->vm_flags & VM_EXECUTABLE)
 					added_exe_file_vma(mm);
 			}

tools/lib/traceevent/.gitignore

+TRACEEVENT-CFLAGS

tools/lib/traceevent/Makefile

@@ -207,7 +207,7 @@ libtraceevent.so: $(PEVENT_LIB_OBJS)
 libtraceevent.a: $(PEVENT_LIB_OBJS)
 	$(Q)$(do_build_static_lib)
 
-$(PEVENT_LIB_OBJS): %.o: $(src)/%.c
+$(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
 	$(Q)$(do_fpic_compile)
 
 define make_version.h
@@ -272,6 +272,16 @@ ifneq ($(dep_includes),)
  include $(dep_includes)
 endif
 
+### Detect environment changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
+
+TRACEEVENT-CFLAGS: force
+	@FLAGS='$(TRACK_CFLAGS)'; \
+	    if test x"$$FLAGS" != x"`cat TRACEEVENT-CFLAGS 2>/dev/null`" ; then \
+		echo 1>&2 "    * new build flags or cross compiler"; \
+		echo "$$FLAGS" >TRACEEVENT-CFLAGS; \
+            fi
+
 tags:	force
 	$(RM) tags
 	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
@@ -297,7 +307,7 @@ install: install_lib
 
 clean:
 	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
-	$(RM) tags TAGS
+	$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 endif # skip-makefile
 

tools/perf/Makefile

@@ -354,6 +354,7 @@ LIB_OBJS += $(OUTPUT)util/usage.o
 LIB_OBJS += $(OUTPUT)util/wrapper.o
 LIB_OBJS += $(OUTPUT)util/sigchain.o
 LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/dso-test-data.o
 LIB_OBJS += $(OUTPUT)util/color.o
 LIB_OBJS += $(OUTPUT)util/pager.o
 LIB_OBJS += $(OUTPUT)util/header.o
@@ -803,6 +804,9 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls $<
+
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 

tools/perf/builtin-test.c

@@ -1141,6 +1141,10 @@ static struct test {
 		.desc = "Test perf pmu format parsing",
 		.func = test__perf_pmu,
 	},
+	{
+		.desc = "Test dso data interface",
+		.func = dso__test_data,
+	},
 	{
 		.func = NULL,
 	},

tools/perf/builtin-top.c

@@ -125,7 +125,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 	/*
 	 * We can't annotate with just /proc/kallsyms
 	 */
-	if (map->dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		pr_err("Can't annotate %s: No vmlinux file was found in the "
 		       "path\n", sym->name);
 		sleep(1);

tools/perf/ui/browsers/hists.c

@@ -978,8 +978,8 @@ static int hist_browser__dump(struct hist_browser *browser)
 	fp = fopen(filename, "w");
 	if (fp == NULL) {
 		char bf[64];
-		strerror_r(errno, bf, sizeof(bf));
-		ui_helpline__fpush("Couldn't write to %s: %s", filename, bf);
+		const char *err = strerror_r(errno, bf, sizeof(bf));
+		ui_helpline__fpush("Couldn't write to %s: %s", filename, err);
 		return -1;
 	}
 

tools/perf/util/annotate.c

@@ -426,7 +426,18 @@ int symbol__alloc_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	const size_t size = symbol__size(sym);
-	size_t sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+	size_t sizeof_sym_hist;
+
+	/* Check for overflow when calculating sizeof_sym_hist */
+	if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64))
+		return -1;
+
+	sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+
+	/* Check for overflow in zalloc argument */
+	if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src))
+				/ symbol_conf.nr_events)
+		return -1;
 
 	notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
 	if (notes->src == NULL)
@@ -777,7 +788,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 		free_filename = false;
 	}
 
-	if (dso->symtab_type == SYMTAB__KALLSYMS) {
+	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
 		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
 		char *build_id_msg = NULL;
 

tools/perf/util/dso-test-data.c

+#include "util.h"
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include "symbol.h"
+
+#define TEST_ASSERT_VAL(text, cond) \
+do { \
+	if (!(cond)) { \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1; \
+	} \
+} while (0)
+
+static char *test_file(int size)
+{
+	static char buf_templ[] = "/tmp/test-XXXXXX";
+	char *templ = buf_templ;
+	int fd, i;
+	unsigned char *buf;
+
+	fd = mkostemp(templ, O_CREAT|O_WRONLY|O_TRUNC);
+
+	buf = malloc(size);
+	if (!buf) {
+		close(fd);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++)
+		buf[i] = (unsigned char) ((int) i % 10);
+
+	if (size != write(fd, buf, size))
+		templ = NULL;
+
+	close(fd);
+	return templ;
+}
+
+#define TEST_FILE_SIZE (DSO__DATA_CACHE_SIZE * 20)
+
+struct test_data_offset {
+	off_t offset;
+	u8 data[10];
+	int size;
+};
+
+struct test_data_offset offsets[] = {
+	/* Fill first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read first cache page. */
+	{
+		.offset = 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read cache boundary pages. */
+	{
+		.offset = DSO__DATA_CACHE_SIZE - DSO__DATA_CACHE_SIZE % 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Fill final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 10,
+		.data   = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 },
+		.size   = 10,
+	},
+	/* Read final cache page. */
+	{
+		.offset = TEST_FILE_SIZE - 3,
+		.data   = { 7, 8, 9, 0, 0, 0, 0, 0, 0, 0 },
+		.size   = 3,
+	},
+};
+
+int dso__test_data(void)
+{
+	struct machine machine;
+	struct dso *dso;
+	char *file = test_file(TEST_FILE_SIZE);
+	size_t i;
+
+	TEST_ASSERT_VAL("No test file", file);
+
+	memset(&machine, 0, sizeof(machine));
+
+	dso = dso__new((const char *)file);
+
+	/* Basic 10 bytes tests. */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		struct test_data_offset *data = &offsets[i];
+		ssize_t size;
+		u8 buf[10];
+
+		memset(buf, 0, 10);
+		size = dso__data_read_offset(dso, &machine, data->offset,
+				     buf, 10);
+
+		TEST_ASSERT_VAL("Wrong size", size == data->size);
+		TEST_ASSERT_VAL("Wrong data", !memcmp(buf, data->data, 10));
+	}
+
+	/* Read cross multiple cache pages. */
+	{
+		ssize_t size;
+		int c;
+		u8 *buf;
+
+		buf = malloc(TEST_FILE_SIZE);
+		TEST_ASSERT_VAL("ENOMEM\n", buf);
+
+		/* First iteration to fill caches, second one to read them. */
+		for (c = 0; c < 2; c++) {
+			memset(buf, 0, TEST_FILE_SIZE);
+			size = dso__data_read_offset(dso, &machine, 10,
+						     buf, TEST_FILE_SIZE);
+
+			TEST_ASSERT_VAL("Wrong size",
+				size == (TEST_FILE_SIZE - 10));
+
+			for (i = 0; i < (size_t)size; i++)
+				TEST_ASSERT_VAL("Wrong data",
+					buf[i] == (i % 10));
+		}
+
+		free(buf);
+	}
+
+	dso__delete(dso);
+	unlink(file);
+	return 0;
+}

tools/perf/util/evlist.c

@@ -214,7 +214,7 @@ int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
 		attrs[i].type	       = PERF_TYPE_TRACEPOINT;
 		attrs[i].config	       = err;
 	        attrs[i].sample_type   = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
-					  PERF_SAMPLE_CPU);
+					  PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD);
 		attrs[i].sample_period = 1;
 	}
 

tools/perf/util/header.c

@@ -1212,6 +1212,12 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 				attr.exclude_user,
 				attr.exclude_kernel);
 
+		fprintf(fp, ", excl_host = %d, excl_guest = %d",
+				attr.exclude_host,
+				attr.exclude_guest);
+
+		fprintf(fp, ", precise_ip = %d", attr.precise_ip);
+
 		if (nr)
 			fprintf(fp, ", id = {");
 

tools/perf/util/hist.c

@@ -708,7 +708,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	bool printed = false;
 	struct rb_node *node;
 	int i = 0;
-	int ret;
+	int ret = 0;
 
 	/*
 	 * If have one single callchain root, don't bother printing
@@ -747,8 +747,11 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		root = &cnode->rb_root;
 	}
 
-	return __callchain__fprintf_graph(fp, root, total_samples,
+	ret += __callchain__fprintf_graph(fp, root, total_samples,
 					  1, 1, left_margin);
+	ret += fprintf(fp, "\n");
+
+	return ret;
 }
 
 static size_t __callchain__fprintf_flat(FILE *fp,

tools/perf/util/map.c

@@ -7,6 +7,8 @@
 #include <stdio.h>
 #include <unistd.h>
 #include "map.h"
+#include "thread.h"
+#include "strlist.h"
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -585,7 +587,21 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid)
 	self->kmaps.machine = self;
 	self->pid	    = pid;
 	self->root_dir      = strdup(root_dir);
-	return self->root_dir == NULL ? -ENOMEM : 0;
+	if (self->root_dir == NULL)
+		return -ENOMEM;
+
+	if (pid != HOST_KERNEL_ID) {
+		struct thread *thread = machine__findnew_thread(self, pid);
+		char comm[64];
+
+		if (thread == NULL)
+			return -ENOMEM;
+
+		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
+		thread__set_comm(thread, comm);
+	}
+
+	return 0;
 }
 
 static void dsos__delete(struct list_head *self)
@@ -680,7 +696,15 @@ struct machine *machines__findnew(struct rb_root *self, pid_t pid)
 	    (symbol_conf.guestmount)) {
 		sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
 		if (access(path, R_OK)) {
-			pr_err("Can't access file %s\n", path);
+			static struct strlist *seen;
+
+			if (!seen)
+				seen = strlist__new(true, NULL);
+
+			if (!strlist__has_entry(seen, path)) {
+				pr_err("Can't access file %s\n", path);
+				strlist__add(seen, path);
+			}
 			machine = NULL;
 			goto out;
 		}
@@ -714,3 +738,16 @@ char *machine__mmap_name(struct machine *self, char *bf, size_t size)
 
 	return bf;
 }
+
+void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size)
+{
+	struct rb_node *node;
+	struct machine *machine;
+
+	for (node = rb_first(machines); node; node = rb_next(node)) {
+		machine = rb_entry(node, struct machine, rb_node);
+		machine->id_hdr_size = id_hdr_size;
+	}
+
+	return;
+}

tools/perf/util/map.h

@@ -151,6 +151,7 @@ struct machine *machines__add(struct rb_root *self, pid_t pid,
 struct machine *machines__find_host(struct rb_root *self);
 struct machine *machines__find(struct rb_root *self, pid_t pid);
 struct machine *machines__findnew(struct rb_root *self, pid_t pid);
+void machines__set_id_hdr_size(struct rb_root *self, u16 id_hdr_size);
 char *machine__mmap_name(struct machine *self, char *bf, size_t size);
 int machine__init(struct machine *self, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *self);

tools/perf/util/parse-events.c

@@ -377,6 +377,7 @@ static int add_tracepoint(struct list_head **list, int *idx,
 	attr.sample_type |= PERF_SAMPLE_RAW;
 	attr.sample_type |= PERF_SAMPLE_TIME;
 	attr.sample_type |= PERF_SAMPLE_CPU;
+	attr.sample_type |= PERF_SAMPLE_PERIOD;
 	attr.sample_period = 1;
 
 	snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name);
@@ -489,6 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx,
 		attr.bp_len = HW_BREAKPOINT_LEN_4;
 
 	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.sample_period = 1;
 
 	return add_event(list, idx, &attr, NULL);
 }

tools/perf/util/session.c

@@ -87,6 +87,7 @@ void perf_session__update_sample_type(struct perf_session *self)
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
 	self->host_machine.id_hdr_size = self->id_hdr_size;
+	machines__set_id_hdr_size(&self->machines, self->id_hdr_size);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -918,7 +919,9 @@ static struct machine *
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+	if (perf_guest &&
+	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
+	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
 		if (event->header.type == PERF_RECORD_MMAP)

tools/perf/util/symbol.c

@@ -29,6 +29,7 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
+static void dso_cache__free(struct rb_root *root);
 static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
 static int elf_read_build_id(Elf *elf, void *bf, size_t size);
 static void dsos__add(struct list_head *head, struct dso *dso);
@@ -48,6 +49,31 @@ struct symbol_conf symbol_conf = {
 	.symfs            = "",
 };
 
+static enum dso_binary_type binary_type_symtab[] = {
+	DSO_BINARY_TYPE__KALLSYMS,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__SYMTAB_CNT sizeof(binary_type_symtab)
+
+static enum dso_binary_type binary_type_data[] = {
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+#define DSO_BINARY_TYPE__DATA_CNT sizeof(binary_type_data)
+
 int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
@@ -318,7 +344,9 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->symtab_type = SYMTAB__NOT_FOUND;
+		dso->cache = RB_ROOT;
+		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
@@ -352,6 +380,7 @@ void dso__delete(struct dso *dso)
 		free((char *)dso->short_name);
 	if (dso->lname_alloc)
 		free(dso->long_name);
+	dso_cache__free(&dso->cache);
 	free(dso);
 }
 
@@ -806,9 +835,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	symbols__fixup_end(&dso->symbols[map->type]);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
 	else
-		dso->symtab_type = SYMTAB__KALLSYMS;
+		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
 	return dso__split_kallsyms(dso, map, filter);
 }
@@ -1660,32 +1689,110 @@ static int filename__read_debuglink(const char *filename,
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
-		[SYMTAB__KALLSYMS]	      = 'k',
-		[SYMTAB__JAVA_JIT]	      = 'j',
-		[SYMTAB__DEBUGLINK]           = 'l',
-		[SYMTAB__BUILD_ID_CACHE]      = 'B',
-		[SYMTAB__FEDORA_DEBUGINFO]    = 'f',
-		[SYMTAB__UBUNTU_DEBUGINFO]    = 'u',
-		[SYMTAB__BUILDID_DEBUGINFO]   = 'b',
-		[SYMTAB__SYSTEM_PATH_DSO]     = 'd',
-		[SYMTAB__SYSTEM_PATH_KMODULE] = 'K',
-		[SYMTAB__GUEST_KALLSYMS]      =  'g',
-		[SYMTAB__GUEST_KMODULE]	      =  'G',
+		[DSO_BINARY_TYPE__KALLSYMS]		= 'k',
+		[DSO_BINARY_TYPE__JAVA_JIT]		= 'j',
+		[DSO_BINARY_TYPE__DEBUGLINK]		= 'l',
+		[DSO_BINARY_TYPE__BUILD_ID_CACHE]	= 'B',
+		[DSO_BINARY_TYPE__FEDORA_DEBUGINFO]	= 'f',
+		[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]	= 'u',
+		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]	= 'b',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]	= 'd',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]	= 'K',
+		[DSO_BINARY_TYPE__GUEST_KALLSYMS]	= 'g',
+		[DSO_BINARY_TYPE__GUEST_KMODULE]	= 'G',
 	};
 
-	if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND)
+	if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
 		return '!';
 	return origin[dso->symtab_type];
 }
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size)
+{
+	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	int ret = 0;
+
+	switch (type) {
+	case DSO_BINARY_TYPE__DEBUGLINK: {
+		char *debuglink;
+
+		strncpy(file, dso->long_name, size);
+		debuglink = file + dso->long_name_len;
+		while (debuglink != file && *debuglink != '/')
+			debuglink--;
+		if (*debuglink == '/')
+			debuglink++;
+		filename__read_debuglink(dso->long_name, debuglink,
+					 size - (debuglink - file));
+		}
+		break;
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		/* skip the locally configured cache if a symfs is given */
+		if (symbol_conf.symfs[0] ||
+		    (dso__build_id_filename(dso, file, size) == NULL))
+			ret = -1;
+		break;
+
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s.debug",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+		snprintf(file, size, "%s/usr/lib/debug%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+		if (!dso->has_build_id) {
+			ret = -1;
+			break;
+		}
+
+		build_id__sprintf(dso->build_id,
+				  sizeof(dso->build_id),
+				  build_id_hex);
+		snprintf(file, size,
+			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+		snprintf(file, size, "%s%s",
+			 symbol_conf.symfs, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+		snprintf(file, size, "%s%s%s", symbol_conf.symfs,
+			 root_dir, dso->long_name);
+		break;
+
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		snprintf(file, size, "%s%s", symbol_conf.symfs,
+			 dso->long_name);
+		break;
+
+	default:
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__NOT_FOUND:
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
-	int size = PATH_MAX;
 	char *name;
 	int ret = -1;
 	int fd;
+	u_int i;
 	struct machine *machine;
-	const char *root_dir;
+	char *root_dir = (char *) "";
 	int want_symtab;
 
 	dso__set_loaded(dso, map->type);
@@ -1700,7 +1807,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	else
 		machine = NULL;
 
-	name = malloc(size);
+	name = malloc(PATH_MAX);
 	if (!name)
 		return -1;
 
@@ -1719,81 +1826,27 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
-		dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
-					      SYMTAB__NOT_FOUND;
+		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
+					     DSO_BINARY_TYPE__NOT_FOUND;
 		return ret;
 	}
 
+	if (machine)
+		root_dir = machine->root_dir;
+
 	/* Iterate over candidate debug images.
 	 * On the first pass, only load images if they have a full symtab.
 	 * Failing that, do a second pass where we accept .dynsym also
 	 */
 	want_symtab = 1;
 restart:
-	for (dso->symtab_type = SYMTAB__DEBUGLINK;
-	     dso->symtab_type != SYMTAB__NOT_FOUND;
-	     dso->symtab_type++) {
-		switch (dso->symtab_type) {
-		case SYMTAB__DEBUGLINK: {
-			char *debuglink;
-			strncpy(name, dso->long_name, size);
-			debuglink = name + dso->long_name_len;
-			while (debuglink != name && *debuglink != '/')
-				debuglink--;
-			if (*debuglink == '/')
-				debuglink++;
-			filename__read_debuglink(dso->long_name, debuglink,
-						 size - (debuglink - name));
-			}
-			break;
-		case SYMTAB__BUILD_ID_CACHE:
-			/* skip the locally configured cache if a symfs is given */
-			if (symbol_conf.symfs[0] ||
-			    (dso__build_id_filename(dso, name, size) == NULL)) {
-				continue;
-			}
-			break;
-		case SYMTAB__FEDORA_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s.debug",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__UBUNTU_DEBUGINFO:
-			snprintf(name, size, "%s/usr/lib/debug%s",
-				 symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__BUILDID_DEBUGINFO: {
-			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
+	for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
 
-			if (!dso->has_build_id)
-				continue;
+		dso->symtab_type = binary_type_symtab[i];
 
-			build_id__sprintf(dso->build_id,
-					  sizeof(dso->build_id),
-					  build_id_hex);
-			snprintf(name, size,
-				 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-				 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
-			}
-			break;
-		case SYMTAB__SYSTEM_PATH_DSO:
-			snprintf(name, size, "%s%s",
-			     symbol_conf.symfs, dso->long_name);
-			break;
-		case SYMTAB__GUEST_KMODULE:
-			if (map->groups && machine)
-				root_dir = machine->root_dir;
-			else
-				root_dir = "";
-			snprintf(name, size, "%s%s%s", symbol_conf.symfs,
-				 root_dir, dso->long_name);
-			break;
-
-		case SYMTAB__SYSTEM_PATH_KMODULE:
-			snprintf(name, size, "%s%s", symbol_conf.symfs,
-				 dso->long_name);
-			break;
-		default:;
-		}
+		if (dso__binary_type_file(dso, dso->symtab_type,
+					  root_dir, name, PATH_MAX))
+			continue;
 
 		/* Name is now the name of the next image to try */
 		fd = open(name, O_RDONLY);
@@ -2010,9 +2063,9 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 		return NULL;
 
 	if (machine__is_host(machine))
-		dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
 	else
-		dso->symtab_type = SYMTAB__GUEST_KMODULE;
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
 	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
@@ -2564,8 +2617,15 @@ int machine__create_kernel_maps(struct machine *machine)
 	    __machine__create_kernel_maps(machine, kernel) < 0)
 		return -1;
 
-	if (symbol_conf.use_modules && machine__create_modules(machine) < 0)
-		pr_debug("Problems creating module maps, continuing anyway...\n");
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
+		if (machine__is_host(machine))
+			pr_debug("Problems creating module maps, "
+				 "continuing anyway...\n");
+		else
+			pr_debug("Problems creating module maps for guest %d, "
+				 "continuing anyway...\n", machine->pid);
+	}
+
 	/*
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
@@ -2905,3 +2965,218 @@ struct map *dso__new_map(const char *name)
 
 	return map;
 }
+
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	char *root_dir = (char *) "";
+	char *name;
+	int fd;
+
+	name = malloc(PATH_MAX);
+	if (!name)
+		return -ENOMEM;
+
+	if (machine)
+		root_dir = machine->root_dir;
+
+	if (dso__binary_type_file(dso, dso->data_type,
+				  root_dir, name, PATH_MAX)) {
+		free(name);
+		return -EINVAL;
+	}
+
+	fd = open(name, O_RDONLY);
+	free(name);
+	return fd;
+}
+
+int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int i = 0;
+
+	if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
+		return open_dso(dso, machine);
+
+	do {
+		int fd;
+
+		dso->data_type = binary_type_data[i++];
+
+		fd = open_dso(dso, machine);
+		if (fd >= 0)
+			return fd;
+
+	} while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);
+
+	return -EINVAL;
+}
+
+static void
+dso_cache__free(struct rb_root *root)
+{
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct dso_cache *cache;
+
+		cache = rb_entry(next, struct dso_cache, rb_node);
+		next = rb_next(&cache->rb_node);
+		rb_erase(&cache->rb_node, root);
+		free(cache);
+	}
+}
+
+static struct dso_cache*
+dso_cache__find(struct rb_root *root, u64 offset)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+		else
+			return cache;
+	}
+	return NULL;
+}
+
+static void
+dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct dso_cache *cache;
+	u64 offset = new->offset;
+
+	while (*p != NULL) {
+		u64 end;
+
+		parent = *p;
+		cache = rb_entry(parent, struct dso_cache, rb_node);
+		end = cache->offset + DSO__DATA_CACHE_SIZE;
+
+		if (offset < cache->offset)
+			p = &(*p)->rb_left;
+		else if (offset >= end)
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&new->rb_node, parent, p);
+	rb_insert_color(&new->rb_node, root);
+}
+
+static ssize_t
+dso_cache__memcpy(struct dso_cache *cache, u64 offset,
+		  u8 *data, u64 size)
+{
+	u64 cache_offset = offset - cache->offset;
+	u64 cache_size   = min(cache->size - cache_offset, size);
+
+	memcpy(data, cache->data + cache_offset, cache_size);
+	return cache_size;
+}
+
+static ssize_t
+dso_cache__read(struct dso *dso, struct machine *machine,
+		 u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+	ssize_t ret;
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return -1;
+
+	do {
+		u64 cache_offset;
+
+		ret = -ENOMEM;
+
+		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+		if (!cache)
+			break;
+
+		cache_offset = offset & DSO__DATA_CACHE_MASK;
+		ret = -EINVAL;
+
+		if (-1 == lseek(fd, cache_offset, SEEK_SET))
+			break;
+
+		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		if (ret <= 0)
+			break;
+
+		cache->offset = cache_offset;
+		cache->size   = ret;
+		dso_cache__insert(&dso->cache, cache);
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+
+	} while (0);
+
+	if (ret <= 0)
+		free(cache);
+
+	close(fd);
+	return ret;
+}
+
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	struct dso_cache *cache;
+
+	cache = dso_cache__find(&dso->cache, offset);
+	if (cache)
+		return dso_cache__memcpy(cache, offset, data, size);
+	else
+		return dso_cache__read(dso, machine, offset, data, size);
+}
+
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	ssize_t r = 0;
+	u8 *p = data;
+
+	do {
+		ssize_t ret;
+
+		ret = dso_cache_read(dso, machine, offset, p, size);
+		if (ret < 0)
+			return ret;
+
+		/* Reached EOF, return what we have. */
+		if (!ret)
+			break;
+
+		BUG_ON(ret > size);
+
+		r      += ret;
+		p      += ret;
+		offset += ret;
+		size   -= ret;
+
+	} while (size);
+
+	return r;
+}
+
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size)
+{
+	u64 offset = map->map_ip(map, addr);
+	return dso__data_read_offset(dso, machine, offset, data, size);
+}

tools/perf/util/symbol.h

@@ -155,6 +155,21 @@ struct addr_location {
 	s32	      cpu;
 };
 
+enum dso_binary_type {
+	DSO_BINARY_TYPE__KALLSYMS = 0,
+	DSO_BINARY_TYPE__GUEST_KALLSYMS,
+	DSO_BINARY_TYPE__JAVA_JIT,
+	DSO_BINARY_TYPE__DEBUGLINK,
+	DSO_BINARY_TYPE__BUILD_ID_CACHE,
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
+	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
 enum dso_kernel_type {
 	DSO_TYPE_USER = 0,
 	DSO_TYPE_KERNEL,
@@ -167,19 +182,31 @@ enum dso_swap_type {
 	DSO_SWAP__YES,
 };
 
+#define DSO__DATA_CACHE_SIZE 4096
+#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1)
+
+struct dso_cache {
+	struct rb_node	rb_node;
+	u64 offset;
+	u64 size;
+	char data[0];
+};
+
 struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 cache;
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
+	enum dso_binary_type	symtab_type;
+	enum dso_binary_type	data_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
 	u8		 sname_alloc:1;
 	u8		 lname_alloc:1;
-	unsigned char	 symtab_type;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 build_id[BUILD_ID_SIZE];
@@ -253,21 +280,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 				    enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
-enum symtab_type {
-	SYMTAB__KALLSYMS = 0,
-	SYMTAB__GUEST_KALLSYMS,
-	SYMTAB__JAVA_JIT,
-	SYMTAB__DEBUGLINK,
-	SYMTAB__BUILD_ID_CACHE,
-	SYMTAB__FEDORA_DEBUGINFO,
-	SYMTAB__UBUNTU_DEBUGINFO,
-	SYMTAB__BUILDID_DEBUGINFO,
-	SYMTAB__SYSTEM_PATH_DSO,
-	SYMTAB__GUEST_KMODULE,
-	SYMTAB__SYSTEM_PATH_KMODULE,
-	SYMTAB__NOT_FOUND,
-};
-
 char dso__symtab_origin(const struct dso *dso);
 void dso__set_long_name(struct dso *dso, char *name);
 void dso__set_build_id(struct dso *dso, void *build_id);
@@ -304,4 +316,14 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
+int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+			  char *root_dir, char *file, size_t size);
+
+int dso__data_fd(struct dso *dso, struct machine *machine);
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size);
+ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
+			    struct machine *machine, u64 addr,
+			    u8 *data, ssize_t size);
+int dso__test_data(void);
 #endif /* __PERF_SYMBOL */

tools/perf/util/target.c

@@ -110,8 +110,17 @@ int perf_target__strerror(struct perf_target *target, int errnum,
 	int idx;
 	const char *msg;
 
+	BUG_ON(buflen > 0);
+
 	if (errnum >= 0) {
-		strerror_r(errnum, buf, buflen);
+		const char *err = strerror_r(errnum, buf, buflen);
+
+		if (err != buf) {
+			size_t len = strlen(err);
+			char *c = mempcpy(buf, err, min(buflen - 1, len));
+			*c = '\0';
+		}
+
 		return 0;
 	}