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

Pull perf updates from Ingo Molnar:
 "Features:

   - Add "uretprobes" - an optimization to uprobes, like kretprobes are
     an optimization to kprobes.  "perf probe -x file sym%return" now
     works like kretprobes.  By Oleg Nesterov.

   - Introduce per core aggregation in 'perf stat', from Stephane
     Eranian.

   - Add memory profiling via PEBS, from Stephane Eranian.

   - Event group view for 'annotate' in --stdio, --tui and --gtk, from
     Namhyung Kim.

   - Add support for AMD NB and L2I "uncore" counters, by Jacob Shin.

   - Add Ivy Bridge-EP uncore support, by Zheng Yan

   - IBM zEnterprise EC12 oprofile support patchlet from Robert Richter.

   - Add perf test entries for checking breakpoint overflow signal
     handler issues, from Jiri Olsa.

   - Add perf test entry for for checking number of EXIT events, from
     Namhyung Kim.

   - Add perf test entries for checking --cpu in record and stat, from
     Jiri Olsa.

   - Introduce perf stat --repeat forever, from Frederik Deweerdt.

   - Add --no-demangle to report/top, from Namhyung Kim.

   - PowerPC fixes plus a couple of cleanups/optimizations in uprobes
     and trace_uprobes, by Oleg Nesterov.

  Various fixes and refactorings:

   - Fix dependency of the python binding wrt libtraceevent, from
     Naohiro Aota.

   - Simplify some perf_evlist methods and to allow 'stat' to share code
     with 'record' and 'trace', by Arnaldo Carvalho de Melo.

   - Remove dead code in related to libtraceevent integration, from
     Namhyung Kim.

   - Revert "perf sched: Handle PERF_RECORD_EXIT events" to get 'perf
     sched lat' back working, by Arnaldo Carvalho de Melo

   - We don't use Newt anymore, just plain libslang, by Arnaldo Carvalho
     de Melo.

   - Kill a bunch of die() calls, from Namhyung Kim.

   - Fix build on non-glibc systems due to libio.h absence, from Cody P
     Schafer.

   - Remove some perf_session and tracing dead code, from David Ahern.

   - Honor parallel jobs, fix from Borislav Petkov

   - Introduce tools/lib/lk library, initially just removing duplication
     among tools/perf and tools/vm.  from Borislav Petkov

  ... and many more I missed to list, see the shortlog and git log for
  more details."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (136 commits)
  perf/x86/intel/P4: Robistify P4 PMU types
  perf/x86/amd: Fix AMD NB and L2I "uncore" support
  perf/x86/amd: Remove old-style NB counter support from perf_event_amd.c
  perf/x86: Check all MSRs before passing hw check
  perf/x86/amd: Add support for AMD NB and L2I "uncore" counters
  perf/x86/intel: Add Ivy Bridge-EP uncore support
  perf/x86/intel: Fix SNB-EP CBO and PCU uncore PMU filter management
  perf/x86: Avoid kfree() in CPU_{STARTING,DYING}
  uprobes/perf: Avoid perf_trace_buf_prepare/submit if ->perf_events is empty
  uprobes/tracing: Don't pass addr=ip to perf_trace_buf_submit()
  uprobes/tracing: Change create_trace_uprobe() to support uretprobes
  uprobes/tracing: Make seq_printf() code uretprobe-friendly
  uprobes/tracing: Make register_uprobe_event() paths uretprobe-friendly
  uprobes/tracing: Make uprobe_{trace,perf}_print() uretprobe-friendly
  uprobes/tracing: Introduce is_ret_probe() and uretprobe_dispatcher()
  uprobes/tracing: Introduce uprobe_{trace,perf}_print() helpers
  uprobes/tracing: Generalize struct uprobe_trace_entry_head
  uprobes/tracing: Kill the pointless local_save_flags/preempt_count calls
  uprobes/tracing: Kill the pointless seq_print_ip_sym() call
  uprobes/tracing: Kill the pointless task_pt_regs() calls
  ...

19 files changed, 1834 insertions, 303 deletions

diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h
index b532060d091..23016020915 100644
--- a/arch/powerpc/include/asm/uprobes.h
+++ b/arch/powerpc/include/asm/uprobes.h
@@ -51,4 +51,5 @@ extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
 extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif	/* _ASM_UPROBES_H */
diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
index bc77834dbf4..59f419b935f 100644
--- a/arch/powerpc/kernel/uprobes.c
+++ b/arch/powerpc/kernel/uprobes.c
@@ -31,6 +31,16 @@
 #define UPROBE_TRAP_NR	UINT_MAX
 
 /**
+ * is_trap_insn - check if the instruction is a trap variant
+ * @insn: instruction to be checked.
+ * Returns true if @insn is a trap variant.
+ */
+bool is_trap_insn(uprobe_opcode_t *insn)
+{
+	return (is_trap(*insn));
+}
+
+/**
  * arch_uprobe_analyze_insn
  * @mm: the probed address space.
  * @arch_uprobe: the probepoint information.
@@ -43,12 +53,6 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe,
 	if (addr & 0x03)
 		return -EINVAL;
 
-	/*
-	 * We currently don't support a uprobe on an already
-	 * existing breakpoint instruction underneath
-	 */
-	if (is_trap(auprobe->ainsn))
-		return -ENOTSUPP;
 	return 0;
 }
 
@@ -188,3 +192,16 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	return false;
 }
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+	unsigned long orig_ret_vaddr;
+
+	orig_ret_vaddr = regs->link;
+
+	/* Replace the return addr with trampoline addr */
+	regs->link = trampoline_vaddr;
+
+	return orig_ret_vaddr;
+}
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 584b93674ea..ffeb17ce7f3 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -440,6 +440,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 		switch (id.machine) {
 		case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
 		case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
+		case 0x2827:              ops->cpu_type = "s390/zEC12"; break;
 		default: return -ENODEV;
 		}
 	}
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 93fe929d1ce..ac10df72925 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,6 +168,7 @@
 #define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
 #define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
 #define X86_FEATURE_PERFCTR_NB  (6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_PERFCTR_L2	(6*32+28) /* L2 performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -311,6 +312,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 #define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
 #define cpu_has_perfctr_nb	boot_cpu_has(X86_FEATURE_PERFCTR_NB)
+#define cpu_has_perfctr_l2	boot_cpu_has(X86_FEATURE_PERFCTR_L2)
 #define cpu_has_cx8		boot_cpu_has(X86_FEATURE_CX8)
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
 #define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 4f7e67e2345..85e13ccf15c 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -24,45 +24,45 @@
 #define ARCH_P4_CNTRVAL_MASK	((1ULL << ARCH_P4_CNTRVAL_BITS) - 1)
 #define ARCH_P4_UNFLAGGED_BIT	((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1))
 
-#define P4_ESCR_EVENT_MASK	0x7e000000U
+#define P4_ESCR_EVENT_MASK	0x7e000000ULL
 #define P4_ESCR_EVENT_SHIFT	25
-#define P4_ESCR_EVENTMASK_MASK	0x01fffe00U
+#define P4_ESCR_EVENTMASK_MASK	0x01fffe00ULL
 #define P4_ESCR_EVENTMASK_SHIFT	9
-#define P4_ESCR_TAG_MASK	0x000001e0U
+#define P4_ESCR_TAG_MASK	0x000001e0ULL
 #define P4_ESCR_TAG_SHIFT	5
-#define P4_ESCR_TAG_ENABLE	0x00000010U
-#define P4_ESCR_T0_OS		0x00000008U
-#define P4_ESCR_T0_USR		0x00000004U
-#define P4_ESCR_T1_OS		0x00000002U
-#define P4_ESCR_T1_USR		0x00000001U
+#define P4_ESCR_TAG_ENABLE	0x00000010ULL
+#define P4_ESCR_T0_OS		0x00000008ULL
+#define P4_ESCR_T0_USR		0x00000004ULL
+#define P4_ESCR_T1_OS		0x00000002ULL
+#define P4_ESCR_T1_USR		0x00000001ULL
 
 #define P4_ESCR_EVENT(v)	((v) << P4_ESCR_EVENT_SHIFT)
 #define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
 
-#define P4_CCCR_OVF			0x80000000U
-#define P4_CCCR_CASCADE			0x40000000U
-#define P4_CCCR_OVF_PMI_T0		0x04000000U
-#define P4_CCCR_OVF_PMI_T1		0x08000000U
-#define P4_CCCR_FORCE_OVF		0x02000000U
-#define P4_CCCR_EDGE			0x01000000U
-#define P4_CCCR_THRESHOLD_MASK		0x00f00000U
+#define P4_CCCR_OVF			0x80000000ULL
+#define P4_CCCR_CASCADE			0x40000000ULL
+#define P4_CCCR_OVF_PMI_T0		0x04000000ULL
+#define P4_CCCR_OVF_PMI_T1		0x08000000ULL
+#define P4_CCCR_FORCE_OVF		0x02000000ULL
+#define P4_CCCR_EDGE			0x01000000ULL
+#define P4_CCCR_THRESHOLD_MASK		0x00f00000ULL
 #define P4_CCCR_THRESHOLD_SHIFT		20
-#define P4_CCCR_COMPLEMENT		0x00080000U
-#define P4_CCCR_COMPARE			0x00040000U
-#define P4_CCCR_ESCR_SELECT_MASK	0x0000e000U
+#define P4_CCCR_COMPLEMENT		0x00080000ULL
+#define P4_CCCR_COMPARE			0x00040000ULL
+#define P4_CCCR_ESCR_SELECT_MASK	0x0000e000ULL
 #define P4_CCCR_ESCR_SELECT_SHIFT	13
-#define P4_CCCR_ENABLE			0x00001000U
-#define P4_CCCR_THREAD_SINGLE		0x00010000U
-#define P4_CCCR_THREAD_BOTH		0x00020000U
-#define P4_CCCR_THREAD_ANY		0x00030000U
-#define P4_CCCR_RESERVED		0x00000fffU
+#define P4_CCCR_ENABLE			0x00001000ULL
+#define P4_CCCR_THREAD_SINGLE		0x00010000ULL
+#define P4_CCCR_THREAD_BOTH		0x00020000ULL
+#define P4_CCCR_THREAD_ANY		0x00030000ULL
+#define P4_CCCR_RESERVED		0x00000fffULL
 
 #define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
 
 #define P4_GEN_ESCR_EMASK(class, name, bit)	\
-	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
+	class##__##name = ((1ULL << bit) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_EMASK_BIT(class, name)		class##__##name
 
 /*
@@ -107,7 +107,7 @@
  * P4_PEBS_CONFIG_MASK and related bits on
  * modification.)
  */
-#define P4_CONFIG_ALIASABLE		(1 << 9)
+#define P4_CONFIG_ALIASABLE		(1ULL << 9)
 
 /*
  * The bits we allow to pass for RAW events
@@ -784,17 +784,17 @@ enum P4_ESCR_EMASKS {
  * Note we have UOP and PEBS bits reserved for now
  * just in case if we will need them once
  */
-#define P4_PEBS_CONFIG_ENABLE		(1 << 7)
-#define P4_PEBS_CONFIG_UOP_TAG		(1 << 8)
-#define P4_PEBS_CONFIG_METRIC_MASK	0x3f
-#define P4_PEBS_CONFIG_MASK		0xff
+#define P4_PEBS_CONFIG_ENABLE		(1ULL << 7)
+#define P4_PEBS_CONFIG_UOP_TAG		(1ULL << 8)
+#define P4_PEBS_CONFIG_METRIC_MASK	0x3FLL
+#define P4_PEBS_CONFIG_MASK		0xFFLL
 
 /*
  * mem: Only counters MSR_IQ_COUNTER4 (16) and
  * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling
  */
-#define P4_PEBS_ENABLE			0x02000000U
-#define P4_PEBS_ENABLE_UOP_TAG		0x01000000U
+#define P4_PEBS_ENABLE			0x02000000ULL
+#define P4_PEBS_ENABLE_UOP_TAG		0x01000000ULL
 
 #define p4_config_unpack_metric(v)	(((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK)
 #define p4_config_unpack_pebs(v)	(((u64)(v)) & P4_PEBS_CONFIG_MASK)
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 8ff8be7835a..6e5197910fd 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -55,4 +55,5 @@ extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
 extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif	/* _ASM_UPROBES_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 7a060f4b411..b5757885d7a 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -72,6 +72,7 @@
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
+#define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
 
 #define MSR_MTRRfix64K_00000		0x00000250
 #define MSR_MTRRfix16K_80000		0x00000258
@@ -195,6 +196,10 @@
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
 
+/* Fam 16h MSRs */
+#define MSR_F16H_L2I_PERF_CTL		0xc0010230
+#define MSR_F16H_L2I_PERF_CTR		0xc0010231
+
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL		0xc0010200
 #define MSR_F15H_PERF_CTR		0xc0010201
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index c9496313843..deef0399fc7 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -31,7 +31,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
 
 ifdef CONFIG_PERF_EVENTS
-obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd.o
+obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd.o perf_event_amd_uncore.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index bf0f01aea99..1025f3c99d2 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -180,8 +180,9 @@ static void release_pmc_hardware(void) {}
 
 static bool check_hw_exists(void)
 {
-	u64 val, val_new = ~0;
-	int i, reg, ret = 0;
+	u64 val, val_fail, val_new= ~0;
+	int i, reg, reg_fail, ret = 0;
+	int bios_fail = 0;
 
 	/*
 	 * Check to see if the BIOS enabled any of the counters, if so
@@ -192,8 +193,11 @@ static bool check_hw_exists(void)
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
 			goto msr_fail;
-		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
-			goto bios_fail;
+		if (val & ARCH_PERFMON_EVENTSEL_ENABLE) {
+			bios_fail = 1;
+			val_fail = val;
+			reg_fail = reg;
+		}
 	}
 
 	if (x86_pmu.num_counters_fixed) {
@@ -202,8 +206,11 @@ static bool check_hw_exists(void)
 		if (ret)
 			goto msr_fail;
 		for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
-			if (val & (0x03 << i*4))
-				goto bios_fail;
+			if (val & (0x03 << i*4)) {
+				bios_fail = 1;
+				val_fail = val;
+				reg_fail = reg;
+			}
 		}
 	}
 
@@ -221,14 +228,13 @@ static bool check_hw_exists(void)
 	if (ret || val != val_new)
 		goto msr_fail;
 
-	return true;
-
-bios_fail:
 	/*
 	 * We still allow the PMU driver to operate:
 	 */
-	printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
-	printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
+	if (bios_fail) {
+		printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
+		printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail);
+	}
 
 	return true;
 
@@ -1316,9 +1322,16 @@ static struct attribute_group x86_pmu_format_group = {
  */
 static void __init filter_events(struct attribute **attrs)
 {
+	struct device_attribute *d;
+	struct perf_pmu_events_attr *pmu_attr;
 	int i, j;
 
 	for (i = 0; attrs[i]; i++) {
+		d = (struct device_attribute *)attrs[i];
+		pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
+		/* str trumps id */
+		if (pmu_attr->event_str)
+			continue;
 		if (x86_pmu.event_map(i))
 			continue;
 
@@ -1330,22 +1343,45 @@ static void __init filter_events(struct attribute **attrs)
 	}
 }
 
-static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+/* Merge two pointer arrays */
+static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
+{
+	struct attribute **new;
+	int j, i;
+
+	for (j = 0; a[j]; j++)
+		;
+	for (i = 0; b[i]; i++)
+		j++;
+	j++;
+
+	new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	j = 0;
+	for (i = 0; a[i]; i++)
+		new[j++] = a[i];
+	for (i = 0; b[i]; i++)
+		new[j++] = b[i];
+	new[j] = NULL;
+
+	return new;
+}
+
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page)
 {
 	struct perf_pmu_events_attr *pmu_attr = \
 		container_of(attr, struct perf_pmu_events_attr, attr);
-
 	u64 config = x86_pmu.event_map(pmu_attr->id);
-	return x86_pmu.events_sysfs_show(page, config);
-}
 
-#define EVENT_VAR(_id)  event_attr_##_id
-#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+	/* string trumps id */
+	if (pmu_attr->event_str)
+		return sprintf(page, "%s", pmu_attr->event_str);
 
-#define EVENT_ATTR(_name, _id)						\
-	PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id,	\
-			events_sysfs_show)
+	return x86_pmu.events_sysfs_show(page, config);
+}
 
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
@@ -1459,16 +1495,27 @@ static int __init init_hw_perf_events(void)
 
 	unconstrained = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
-				   0, x86_pmu.num_counters, 0);
+				   0, x86_pmu.num_counters, 0, 0);
 
 	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
 	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
+	if (x86_pmu.event_attrs)
+		x86_pmu_events_group.attrs = x86_pmu.event_attrs;
+
 	if (!x86_pmu.events_sysfs_show)
 		x86_pmu_events_group.attrs = &empty_attrs;
 	else
 		filter_events(x86_pmu_events_group.attrs);
 
+	if (x86_pmu.cpu_events) {
+		struct attribute **tmp;
+
+		tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events);
+		if (!WARN_ON(!tmp))
+			x86_pmu_events_group.attrs = tmp;
+	}
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 7f5c75c2afd..ba9aadfa683 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -46,6 +46,7 @@ enum extra_reg_type {
 	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
 	EXTRA_REG_LBR   = 2,	/* lbr_select */
+	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
@@ -59,7 +60,13 @@ struct event_constraint {
 	u64	cmask;
 	int	weight;
 	int	overlap;
+	int	flags;
 };
+/*
+ * struct event_constraint flags
+ */
+#define PERF_X86_EVENT_PEBS_LDLAT	0x1 /* ld+ldlat data address sampling */
+#define PERF_X86_EVENT_PEBS_ST		0x2 /* st data address sampling */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -170,16 +177,17 @@ struct cpu_hw_events {
 	void				*kfree_on_online;
 };
 
-#define __EVENT_CONSTRAINT(c, n, m, w, o) {\
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
 	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
 	.cmask = (m),			\
 	.weight = (w),			\
 	.overlap = (o),			\
+	.flags = f,			\
 }
 
 #define EVENT_CONSTRAINT(c, n, m)	\
-	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0)
+	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
 
 /*
  * The overlap flag marks event constraints with overlapping counter
@@ -203,7 +211,7 @@ struct cpu_hw_events {
  * and its counter masks must be kept at a minimum.
  */
 #define EVENT_CONSTRAINT_OVERLAP(c, n, m)	\
-	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1)
+	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0)
 
 /*
  * Constraint on the Event code.
@@ -231,6 +239,14 @@ struct cpu_hw_events {
 #define INTEL_UEVENT_CONSTRAINT(c, n)	\
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
+#define INTEL_PLD_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
+
+#define INTEL_PST_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
+
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
 
@@ -260,12 +276,22 @@ struct extra_reg {
 	.msr = (ms),		\
 	.config_mask = (m),	\
 	.valid_mask = (vm),	\
-	.idx = EXTRA_REG_##i	\
+	.idx = EXTRA_REG_##i,	\
 	}
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\
 	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx)
 
+#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \
+	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \
+			ARCH_PERFMON_EVENTSEL_UMASK, vm, idx)
+
+#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \
+	INTEL_UEVENT_EXTRA_REG(c, \
+			       MSR_PEBS_LD_LAT_THRESHOLD, \
+			       0xffff, \
+			       LDLAT)
+
 #define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0)
 
 union perf_capabilities {
@@ -355,8 +381,10 @@ struct x86_pmu {
 	 */
 	int		attr_rdpmc;
 	struct attribute **format_attrs;
+	struct attribute **event_attrs;
 
 	ssize_t		(*events_sysfs_show)(char *page, u64 config);
+	struct attribute **cpu_events;
 
 	/*
 	 * CPU Hotplug hooks
@@ -421,6 +449,23 @@ do {									\
 #define ERF_NO_HT_SHARING	1
 #define ERF_HAS_RSP_1		2
 
+#define EVENT_VAR(_id)  event_attr_##_id
+#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+
+#define EVENT_ATTR(_name, _id)						\
+static struct perf_pmu_events_attr EVENT_VAR(_id) = {			\
+	.attr		= __ATTR(_name, 0444, events_sysfs_show, NULL),	\
+	.id		= PERF_COUNT_HW_##_id,				\
+	.event_str	= NULL,						\
+};
+
+#define EVENT_ATTR_STR(_name, v, str)					\
+static struct perf_pmu_events_attr event_attr_##v = {			\
+	.attr		= __ATTR(_name, 0444, events_sysfs_show, NULL),	\
+	.id		= 0,						\
+	.event_str	= str,						\
+};
+
 extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
@@ -628,6 +673,9 @@ int p6_pmu_init(void);
 
 int knc_pmu_init(void);
 
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page);
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index dfdab42aed2..7e28d9467bb 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -132,14 +132,11 @@ static u64 amd_pmu_event_map(int hw_event)
 	return amd_perfmon_event_map[hw_event];
 }
 
-static struct event_constraint *amd_nb_event_constraint;
-
 /*
  * Previously calculated offsets
  */
 static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly;
 static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly;
-static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly;
 
 /*
  * Legacy CPUs:
@@ -147,14 +144,10 @@ static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly;
  *
  * CPUs with core performance counter extensions:
  *   6 counters starting at 0xc0010200 each offset by 2
- *
- * CPUs with north bridge performance counter extensions:
- *   4 additional counters starting at 0xc0010240 each offset by 2
- *   (indexed right above either one of the above core counters)
  */
 static inline int amd_pmu_addr_offset(int index, bool eventsel)
 {
-	int offset, first, base;
+	int offset;
 
 	if (!index)
 		return index;
@@ -167,23 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel)
 	if (offset)
 		return offset;
 
-	if (amd_nb_event_constraint &&
-	    test_bit(index, amd_nb_event_constraint->idxmsk)) {
-		/*
-		 * calculate the offset of NB counters with respect to
-		 * base eventsel or perfctr
-		 */
-
-		first = find_first_bit(amd_nb_event_constraint->idxmsk,
-				       X86_PMC_IDX_MAX);
-
-		if (eventsel)
-			base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel;
-		else
-			base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr;
-
-		offset = base + ((index - first) << 1);
-	} else if (!cpu_has_perfctr_core)
+	if (!cpu_has_perfctr_core)
 		offset = index;
 	else
 		offset = index << 1;
@@ -196,36 +173,6 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel)
 	return offset;
 }
 
-static inline int amd_pmu_rdpmc_index(int index)
-{
-	int ret, first;
-
-	if (!index)
-		return index;
-
-	ret = rdpmc_indexes[index];
-
-	if (ret)
-		return ret;
-
-	if (amd_nb_event_constraint &&
-	    test_bit(index, amd_nb_event_constraint->idxmsk)) {
-		/*
-		 * according to the mnual, ECX value of the NB counters is
-		 * the index of the NB counter (0, 1, 2 or 3) plus 6
-		 */
-
-		first = find_first_bit(amd_nb_event_constraint->idxmsk,
-				       X86_PMC_IDX_MAX);
-		ret = index - first + 6;
-	} else
-		ret = index;
-
-	rdpmc_indexes[index] = ret;
-
-	return ret;
-}
-
 static int amd_core_hw_config(struct perf_event *event)
 {
 	if (event->attr.exclude_host && event->attr.exclude_guest)
@@ -245,34 +192,6 @@ static int amd_core_hw_config(struct perf_event *event)
 }
 
 /*
- * NB counters do not support the following event select bits:
- *   Host/Guest only
- *   Counter mask
- *   Invert counter mask
- *   Edge detect
- *   OS/User mode
- */
-static int amd_nb_hw_config(struct perf_event *event)
-{
-	/* for NB, we only allow system wide counting mode */
-	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
-		return -EINVAL;
-
-	if (event->attr.exclude_user || event->attr.exclude_kernel ||
-	    event->attr.exclude_host || event->attr.exclude_guest)
-		return -EINVAL;
-
-	event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
-			      ARCH_PERFMON_EVENTSEL_OS);
-
-	if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB |
-				 ARCH_PERFMON_EVENTSEL_INT))
-		return -EINVAL;
-
-	return 0;
-}
-
-/*
  * AMD64 events are detected based on their event codes.
  */
 static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
@@ -285,11 +204,6 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
-static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc)
-{
-	return amd_nb_event_constraint && amd_is_nb_event(hwc);
-}
-
 static inline int amd_has_nb(struct cpu_hw_events *cpuc)
 {
 	struct amd_nb *nb = cpuc->amd_nb;
@@ -315,9 +229,6 @@ static int amd_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == PERF_TYPE_RAW)
 		event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
 
-	if (amd_is_perfctr_nb_event(&event->hw))
-		return amd_nb_hw_config(event);
-
 	return amd_core_hw_config(event);
 }
 
@@ -341,19 +252,6 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
 	}
 }
 
-static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc)
-{
-	int core_id = cpu_data(smp_processor_id()).cpu_core_id;
-
-	/* deliver interrupts only to this core */
-	if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) {
-		hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE;
-		hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK;
-		hwc->config |= (u64)(core_id) <<
-			AMD64_EVENTSEL_INT_CORE_SEL_SHIFT;
-	}
-}
-
  /*
   * AMD64 NorthBridge events need special treatment because
   * counter access needs to be synchronized across all cores
@@ -441,9 +339,6 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
 	if (new == -1)
 		return &emptyconstraint;
 
-	if (amd_is_perfctr_nb_event(hwc))
-		amd_nb_interrupt_hw_config(hwc);
-
 	return &nb->event_constraints[new];
 }
 
@@ -543,8 +438,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw)))
 		return &unconstrained;
 
-	return __amd_get_nb_event_constraints(cpuc, event,
-					      amd_nb_event_constraint);
+	return __amd_get_nb_event_constraints(cpuc, event, NULL);
 }
 
 static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
@@ -643,9 +537,6 @@ static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09,
 static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
 static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 
-static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0);
-static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0);
-
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
@@ -711,8 +602,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
 			return &amd_f15_PMC20;
 		}
 	case AMD_EVENT_NB:
-		return __amd_get_nb_event_constraints(cpuc, event,
-						      amd_nb_event_constraint);
+		/* moved to perf_event_amd_uncore.c */
+		return &emptyconstraint;
 	default:
 		return &emptyconstraint;
 	}
@@ -738,7 +629,6 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.eventsel		= MSR_K7_EVNTSEL0,
 	.perfctr		= MSR_K7_PERFCTR0,
 	.addr_offset            = amd_pmu_addr_offset,
-	.rdpmc_index		= amd_pmu_rdpmc_index,
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
 	.num_counters		= AMD64_NUM_COUNTERS,
@@ -790,23 +680,6 @@ static int setup_perfctr_core(void)
 	return 0;
 }
 
-static int setup_perfctr_nb(void)
-{
-	if (!cpu_has_perfctr_nb)
-		return -ENODEV;
-
-	x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB;
-
-	if (cpu_has_perfctr_core)
-		amd_nb_event_constraint = &amd_NBPMC96;
-	else
-		amd_nb_event_constraint = &amd_NBPMC74;
-
-	printk(KERN_INFO "perf: AMD northbridge performance counters detected\n");
-
-	return 0;
-}
-
 __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
@@ -817,7 +690,6 @@ __init int amd_pmu_init(void)
 
 	setup_event_constraints();
 	setup_perfctr_core();
-	setup_perfctr_nb();
 
 	/* Events are common for all AMDs */
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
new file mode 100644
index 00000000000..c0c661adf03
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -0,0 +1,547 @@
+/*
+ * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ *
+ * Author: Jacob Shin <jacob.shin@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+
+#include <asm/cpufeature.h>
+#include <asm/perf_event.h>
+#include <asm/msr.h>
+
+#define NUM_COUNTERS_NB		4
+#define NUM_COUNTERS_L2		4
+#define MAX_COUNTERS		NUM_COUNTERS_NB
+
+#define RDPMC_BASE_NB		6
+#define RDPMC_BASE_L2		10
+
+#define COUNTER_SHIFT		16
+
+struct amd_uncore {
+	int id;
+	int refcnt;
+	int cpu;
+	int num_counters;
+	int rdpmc_base;
+	u32 msr_base;
+	cpumask_t *active_mask;
+	struct pmu *pmu;
+	struct perf_event *events[MAX_COUNTERS];
+	struct amd_uncore *free_when_cpu_online;
+};
+
+static struct amd_uncore * __percpu *amd_uncore_nb;
+static struct amd_uncore * __percpu *amd_uncore_l2;
+
+static struct pmu amd_nb_pmu;
+static struct pmu amd_l2_pmu;
+
+static cpumask_t amd_nb_active_mask;
+static cpumask_t amd_l2_active_mask;
+
+static bool is_nb_event(struct perf_event *event)
+{
+	return event->pmu->type == amd_nb_pmu.type;
+}
+
+static bool is_l2_event(struct perf_event *event)
+{
+	return event->pmu->type == amd_l2_pmu.type;
+}
+
+static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
+{
+	if (is_nb_event(event) && amd_uncore_nb)
+		return *per_cpu_ptr(amd_uncore_nb, event->cpu);
+	else if (is_l2_event(event) && amd_uncore_l2)
+		return *per_cpu_ptr(amd_uncore_l2, event->cpu);
+
+	return NULL;
+}
+
+static void amd_uncore_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev, new;
+	s64 delta;
+
+	/*
+	 * since we do not enable counter overflow interrupts,
+	 * we do not have to worry about prev_count changing on us
+	 */
+
+	prev = local64_read(&hwc->prev_count);
+	rdpmcl(hwc->event_base_rdpmc, new);
+	local64_set(&hwc->prev_count, new);
+	delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
+	delta >>= COUNTER_SHIFT;
+	local64_add(delta, &event->count);
+}
+
+static void amd_uncore_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (flags & PERF_EF_RELOAD)
+		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+
+	hwc->state = 0;
+	wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
+	perf_event_update_userpage(event);
+}
+
+static void amd_uncore_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	wrmsrl(hwc->config_base, hwc->config);
+	hwc->state |= PERF_HES_STOPPED;
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		amd_uncore_read(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+}
+
+static int amd_uncore_add(struct perf_event *event, int flags)
+{
+	int i;
+	struct amd_uncore *uncore = event_to_amd_uncore(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	/* are we already assigned? */
+	if (hwc->idx != -1 && uncore->events[hwc->idx] == event)
+		goto out;
+
+	for (i = 0; i < uncore->num_counters; i++) {
+		if (uncore->events[i] == event) {
+			hwc->idx = i;
+			goto out;
+		}
+	}
+
+	/* if not, take the first available counter */
+	hwc->idx = -1;
+	for (i = 0; i < uncore->num_counters; i++) {
+		if (cmpxchg(&uncore->events[i], NULL, event) == NULL) {
+			hwc->idx = i;
+			break;
+		}
+	}
+
+out:
+	if (hwc->idx == -1)
+		return -EBUSY;
+
+	hwc->config_base = uncore->msr_base + (2 * hwc->idx);
+	hwc->event_base = uncore->msr_base + 1 + (2 * hwc->idx);
+	hwc->event_base_rdpmc = uncore->rdpmc_base + hwc->idx;
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		amd_uncore_start(event, PERF_EF_RELOAD);
+
+	return 0;
+}
+
+static void amd_uncore_del(struct perf_event *event, int flags)
+{
+	int i;
+	struct amd_uncore *uncore = event_to_amd_uncore(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	amd_uncore_stop(event, PERF_EF_UPDATE);
+
+	for (i = 0; i < uncore->num_counters; i++) {
+		if (cmpxchg(&uncore->events[i], event, NULL) == event)
+			break;
+	}
+
+	hwc->idx = -1;
+}
+
+static int amd_uncore_event_init(struct perf_event *event)
+{
+	struct amd_uncore *uncore;
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/*
+	 * NB and L2 counters (MSRs) are shared across all cores that share the
+	 * same NB / L2 cache. Interrupts can be directed to a single target
+	 * core, however, event counts generated by processes running on other
+	 * cores cannot be masked out. So we do not support sampling and
+	 * per-thread events.
+	 */
+	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+		return -EINVAL;
+
+	/* NB and L2 counters do not have usr/os/guest/host bits */
+	if (event->attr.exclude_user || event->attr.exclude_kernel ||
+	    event->attr.exclude_host || event->attr.exclude_guest)
+		return -EINVAL;
+
+	/* and we do not enable counter overflow interrupts */
+	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
+	hwc->idx = -1;
+
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	uncore = event_to_amd_uncore(event);
+	if (!uncore)
+		return -ENODEV;
+
+	/*
+	 * since request can come in to any of the shared cores, we will remap
+	 * to a single common cpu.
+	 */
+	event->cpu = uncore->cpu;
+
+	return 0;
+}
+
+static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	int n;
+	cpumask_t *active_mask;
+	struct pmu *pmu = dev_get_drvdata(dev);
+
+	if (pmu->type == amd_nb_pmu.type)
+		active_mask = &amd_nb_active_mask;
+	else if (pmu->type == amd_l2_pmu.type)
+		active_mask = &amd_l2_active_mask;
+	else
+		return 0;
+
+	n = cpulist_scnprintf(buf, PAGE_SIZE - 2, active_mask);
+	buf[n++] = '\n';
+	buf[n] = '\0';
+	return n;
+}
+static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);
+
+static struct attribute *amd_uncore_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group amd_uncore_attr_group = {
+	.attrs = amd_uncore_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-7,32-35");
+PMU_FORMAT_ATTR(umask, "config:8-15");
+
+static struct attribute *amd_uncore_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	NULL,
+};
+
+static struct attribute_group amd_uncore_format_group = {
+	.name = "format",
+	.attrs = amd_uncore_format_attr,
+};
+
+static const struct attribute_group *amd_uncore_attr_groups[] = {
+	&amd_uncore_attr_group,
+	&amd_uncore_format_group,
+	NULL,
+};
+
+static struct pmu amd_nb_pmu = {
+	.attr_groups	= amd_uncore_attr_groups,
+	.name		= "amd_nb",
+	.event_init	= amd_uncore_event_init,
+	.add		= amd_uncore_add,
+	.del		= amd_uncore_del,
+	.start		= amd_uncore_start,
+	.stop		= amd_uncore_stop,
+	.read		= amd_uncore_read,
+};
+
+static struct pmu amd_l2_pmu = {
+	.attr_groups	= amd_uncore_attr_groups,
+	.name		= "amd_l2",
+	.event_init	= amd_uncore_event_init,
+	.add		= amd_uncore_add,
+	.del		= amd_uncore_del,
+	.start		= amd_uncore_start,
+	.stop		= amd_uncore_stop,
+	.read		= amd_uncore_read,
+};
+
+static struct amd_uncore * __cpuinit amd_uncore_alloc(unsigned int cpu)
+{
+	return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL,
+			cpu_to_node(cpu));
+}
+
+static void __cpuinit amd_uncore_cpu_up_prepare(unsigned int cpu)
+{
+	struct amd_uncore *uncore;
+
+	if (amd_uncore_nb) {
+		uncore = amd_uncore_alloc(cpu);
+		uncore->cpu = cpu;
+		uncore->num_counters = NUM_COUNTERS_NB;
+		uncore->rdpmc_base = RDPMC_BASE_NB;
+		uncore->msr_base = MSR_F15H_NB_PERF_CTL;
+		uncore->active_mask = &amd_nb_active_mask;
+		uncore->pmu = &amd_nb_pmu;
+		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+	}
+
+	if (amd_uncore_l2) {
+		uncore = amd_uncore_alloc(cpu);
+		uncore->cpu = cpu;
+		uncore->num_counters = NUM_COUNTERS_L2;
+		uncore->rdpmc_base = RDPMC_BASE_L2;
+		uncore->msr_base = MSR_F16H_L2I_PERF_CTL;
+		uncore->active_mask = &amd_l2_active_mask;
+		uncore->pmu = &amd_l2_pmu;
+		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+	}
+}
+
+static struct amd_uncore *
+__cpuinit amd_uncore_find_online_sibling(struct amd_uncore *this,
+					 struct amd_uncore * __percpu *uncores)
+{
+	unsigned int cpu;
+	struct amd_uncore *that;
+
+	for_each_online_cpu(cpu) {
+		that = *per_cpu_ptr(uncores, cpu);
+
+		if (!that)
+			continue;
+
+		if (this == that)
+			continue;
+
+		if (this->id == that->id) {
+			that->free_when_cpu_online = this;
+			this = that;
+			break;
+		}
+	}
+
+	this->refcnt++;
+	return this;
+}
+
+static void __cpuinit amd_uncore_cpu_starting(unsigned int cpu)
+{
+	unsigned int eax, ebx, ecx, edx;
+	struct amd_uncore *uncore;
+
+	if (amd_uncore_nb) {
+		uncore = *per_cpu_ptr(amd_uncore_nb, cpu);
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+		uncore->id = ecx & 0xff;
+
+		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_nb);
+		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+	}
+
+	if (amd_uncore_l2) {
+		unsigned int apicid = cpu_data(cpu).apicid;
+		unsigned int nshared;
+
+		uncore = *per_cpu_ptr(amd_uncore_l2, cpu);
+		cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
+		nshared = ((eax >> 14) & 0xfff) + 1;
+		uncore->id = apicid - (apicid % nshared);
+
+		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
+		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+	}
+}
+
+static void __cpuinit uncore_online(unsigned int cpu,
+				    struct amd_uncore * __percpu *uncores)
+{
+	struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+
+	kfree(uncore->free_when_cpu_online);
+	uncore->free_when_cpu_online = NULL;
+
+	if (cpu == uncore->cpu)
+		cpumask_set_cpu(cpu, uncore->active_mask);
+}
+
+static void __cpuinit amd_uncore_cpu_online(unsigned int cpu)
+{
+	if (amd_uncore_nb)
+		uncore_online(cpu, amd_uncore_nb);
+
+	if (amd_uncore_l2)
+		uncore_online(cpu, amd_uncore_l2);
+}
+
+static void __cpuinit uncore_down_prepare(unsigned int cpu,
+					  struct amd_uncore * __percpu *uncores)
+{
+	unsigned int i;
+	struct amd_uncore *this = *per_cpu_ptr(uncores, cpu);
+
+	if (this->cpu != cpu)
+		return;
+
+	/* this cpu is going down, migrate to a shared sibling if possible */
+	for_each_online_cpu(i) {
+		struct amd_uncore *that = *per_cpu_ptr(uncores, i);
+
+		if (cpu == i)
+			continue;
+
+		if (this == that) {
+			perf_pmu_migrate_context(this->pmu, cpu, i);
+			cpumask_clear_cpu(cpu, that->active_mask);
+			cpumask_set_cpu(i, that->active_mask);
+			that->cpu = i;
+			break;
+		}
+	}
+}
+
+static void __cpuinit amd_uncore_cpu_down_prepare(unsigned int cpu)
+{
+	if (amd_uncore_nb)
+		uncore_down_prepare(cpu, amd_uncore_nb);
+
+	if (amd_uncore_l2)
+		uncore_down_prepare(cpu, amd_uncore_l2);
+}
+
+static void __cpuinit uncore_dead(unsigned int cpu,
+				  struct amd_uncore * __percpu *uncores)
+{
+	struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+
+	if (cpu == uncore->cpu)
+		cpumask_clear_cpu(cpu, uncore->active_mask);
+
+	if (!--uncore->refcnt)
+		kfree(uncore);
+	*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
+}
+
+static void __cpuinit amd_uncore_cpu_dead(unsigned int cpu)
+{
+	if (amd_uncore_nb)
+		uncore_dead(cpu, amd_uncore_nb);
+
+	if (amd_uncore_l2)
+		uncore_dead(cpu, amd_uncore_l2);
+}
+
+static int __cpuinit
+amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action,
+			void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		amd_uncore_cpu_up_prepare(cpu);
+		break;
+
+	case CPU_STARTING:
+		amd_uncore_cpu_starting(cpu);
+		break;
+
+	case CPU_ONLINE:
+		amd_uncore_cpu_online(cpu);
+		break;
+
+	case CPU_DOWN_PREPARE:
+		amd_uncore_cpu_down_prepare(cpu);
+		break;
+
+	case CPU_UP_CANCELED:
+	case CPU_DEAD:
+		amd_uncore_cpu_dead(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block amd_uncore_cpu_notifier_block __cpuinitdata = {
+	.notifier_call	= amd_uncore_cpu_notifier,
+	.priority	= CPU_PRI_PERF + 1,
+};
+
+static void __init init_cpu_already_online(void *dummy)
+{
+	unsigned int cpu = smp_processor_id();
+
+	amd_uncore_cpu_starting(cpu);
+	amd_uncore_cpu_online(cpu);
+}
+
+static int __init amd_uncore_init(void)
+{
+	unsigned int cpu;
+	int ret = -ENODEV;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return -ENODEV;
+
+	if (!cpu_has_topoext)
+		return -ENODEV;
+
+	if (cpu_has_perfctr_nb) {
+		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
+		perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+
+		printk(KERN_INFO "perf: AMD NB counters detected\n");
+		ret = 0;
+	}
+
+	if (cpu_has_perfctr_l2) {
+		amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
+		perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+
+		printk(KERN_INFO "perf: AMD L2I counters detected\n");
+		ret = 0;
+	}
+
+	if (ret)
+		return -ENODEV;
+
+	get_online_cpus();
+	/* init cpus already online before registering for hotplug notifier */
+	for_each_online_cpu(cpu) {
+		amd_uncore_cpu_up_prepare(cpu);
+		smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
+	}
+
+	register_cpu_notifier(&amd_uncore_cpu_notifier_block);
+	put_online_cpus();
+
+	return 0;
+}
+device_initcall(amd_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index cc45deb791b..ffd6050a1de 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -81,6 +81,7 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
 static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
 {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
 	EVENT_EXTRA_END
 };
 
@@ -108,6 +109,8 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
 	EVENT_CONSTRAINT_END
 };
 
@@ -136,6 +139,7 @@ static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
 {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
 	EVENT_EXTRA_END
 };
 
@@ -155,6 +159,8 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
@@ -164,6 +170,21 @@ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
+EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
+
+struct attribute *nhm_events_attrs[] = {
+	EVENT_PTR(mem_ld_nhm),
+	NULL,
+};
+
+struct attribute *snb_events_attrs[] = {
+	EVENT_PTR(mem_ld_snb),
+	EVENT_PTR(mem_st_snb),
+	NULL,
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -1398,8 +1419,11 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if ((event->hw.config & c->cmask) == c->code)
+			if ((event->hw.config & c->cmask) == c->code) {
+				/* hw.flags zeroed at initialization */
+				event->hw.flags |= c->flags;
 				return c;
+			}
 		}
 	}
 
@@ -1444,6 +1468,7 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 					struct perf_event *event)
 {
+	event->hw.flags = 0;
 	intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
@@ -1767,6 +1792,8 @@ static void intel_pmu_flush_branch_stack(void)
 
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
+PMU_FORMAT_ATTR(ldlat, "config1:0-15");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -1777,6 +1804,7 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_cmask.attr,
 
 	&format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+	&format_attr_ldlat.attr, /* PEBS load latency */
 	NULL,
 };
 
@@ -2037,6 +2065,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
+		x86_pmu.cpu_events = nhm_events_attrs;
+
 		/* UOPS_ISSUED.STALLED_CYCLES */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2080,6 +2110,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.extra_regs = intel_westmere_extra_regs;
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 
+		x86_pmu.cpu_events = nhm_events_attrs;
+
 		/* UOPS_ISSUED.STALLED_CYCLES */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2111,6 +2143,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
+		x86_pmu.cpu_events = snb_events_attrs;
+
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2140,6 +2174,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
+		x86_pmu.cpu_events = snb_events_attrs;
+
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 26830f3af0d..60250f68705 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -24,6 +24,130 @@ struct pebs_record_32 {
 
  */
 
+union intel_x86_pebs_dse {
+	u64 val;
+	struct {
+		unsigned int ld_dse:4;
+		unsigned int ld_stlb_miss:1;
+		unsigned int ld_locked:1;
+		unsigned int ld_reserved:26;
+	};
+	struct {
+		unsigned int st_l1d_hit:1;
+		unsigned int st_reserved1:3;
+		unsigned int st_stlb_miss:1;
+		unsigned int st_locked:1;
+		unsigned int st_reserved2:26;
+	};
+};
+
+
+/*
+ * Map PEBS Load Latency Data Source encodings to generic
+ * memory data source information
+ */
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+static const u64 pebs_data_source[] = {
+	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
+	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
+	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */
+	OP_LH | P(LVL, L2)  | P(SNOOP, NONE),	/* 0x03: L2 hit */
+	OP_LH | P(LVL, L3)  | P(SNOOP, NONE),	/* 0x04: L3 hit */
+	OP_LH | P(LVL, L3)  | P(SNOOP, MISS),	/* 0x05: L3 hit, snoop miss */
+	OP_LH | P(LVL, L3)  | P(SNOOP, HIT),	/* 0x06: L3 hit, snoop hit */
+	OP_LH | P(LVL, L3)  | P(SNOOP, HITM),	/* 0x07: L3 hit, snoop hitm */
+	OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT),  /* 0x08: L3 miss snoop hit */
+	OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/
+	OP_LH | P(LVL, LOC_RAM)  | P(SNOOP, HIT),  /* 0x0a: L3 miss, shared */
+	OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT),  /* 0x0b: L3 miss, shared */
+	OP_LH | P(LVL, LOC_RAM)  | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */
+	OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */
+	OP_LH | P(LVL, IO)  | P(SNOOP, NONE), /* 0x0e: I/O */
+	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
+};
+
+static u64 precise_store_data(u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2);
+
+	dse.val = status;
+
+	/*
+	 * bit 4: TLB access
+	 * 1 = stored missed 2nd level TLB
+	 *
+	 * so it either hit the walker or the OS
+	 * otherwise hit 2nd level TLB
+	 */
+	if (dse.st_stlb_miss)
+		val |= P(TLB, MISS);
+	else
+		val |= P(TLB, HIT);
+
+	/*
+	 * bit 0: hit L1 data cache
+	 * if not set, then all we know is that
+	 * it missed L1D
+	 */
+	if (dse.st_l1d_hit)
+		val |= P(LVL, HIT);
+	else
+		val |= P(LVL, MISS);
+
+	/*
+	 * bit 5: Locked prefix
+	 */
+	if (dse.st_locked)
+		val |= P(LOCK, LOCKED);
+
+	return val;
+}
+
+static u64 load_latency_data(u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val;
+	int model = boot_cpu_data.x86_model;
+	int fam = boot_cpu_data.x86;
+
+	dse.val = status;
+
+	/*
+	 * use the mapping table for bit 0-3
+	 */
+	val = pebs_data_source[dse.ld_dse];
+
+	/*
+	 * Nehalem models do not support TLB, Lock infos
+	 */
+	if (fam == 0x6 && (model == 26 || model == 30
+	    || model == 31 || model == 46)) {
+		val |= P(TLB, NA) | P(LOCK, NA);
+		return val;
+	}
+	/*
+	 * bit 4: TLB access
+	 * 0 = did not miss 2nd level TLB
+	 * 1 = missed 2nd level TLB
+	 */
+	if (dse.ld_stlb_miss)
+		val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	/*
+	 * bit 5: locked prefix
+	 */
+	if (dse.ld_locked)
+		val |= P(LOCK, LOCKED);
+
+	return val;
+}
+
 struct pebs_record_core {
 	u64 flags, ip;
 	u64 ax, bx, cx, dx;
@@ -365,7 +489,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
-	INTEL_EVENT_CONSTRAINT(0x0b, 0xf),    /* MEM_INST_RETIRED.* */
+	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
 	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
@@ -380,7 +504,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_westmere_pebs_event_constraints[] = {
-	INTEL_EVENT_CONSTRAINT(0x0b, 0xf),    /* MEM_INST_RETIRED.* */
+	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
 	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
@@ -400,7 +524,8 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
+	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -414,7 +539,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
         INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
+        INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
+	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
         INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -431,8 +557,10 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
 	if (x86_pmu.pebs_constraints) {
 		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
-			if ((event->hw.config & c->cmask) == c->code)
+			if ((event->hw.config & c->cmask) == c->code) {
+				event->hw.flags |= c->flags;
 				return c;
+			}
 		}
 	}
 
@@ -447,6 +575,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
+
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
+		cpuc->pebs_enabled |= 1ULL << 63;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -559,20 +692,51 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 				   struct pt_regs *iregs, void *__pebs)
 {
 	/*
-	 * We cast to pebs_record_core since that is a subset of
-	 * both formats and we don't use the other fields in this
-	 * routine.
+	 * We cast to pebs_record_nhm to get the load latency data
+	 * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used
 	 */
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct pebs_record_core *pebs = __pebs;
+	struct pebs_record_nhm *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
+	u64 sample_type;
+	int fll, fst;
 
 	if (!intel_pmu_save_and_restart(event))
 		return;
 
+	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
+	fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST;
+
 	perf_sample_data_init(&data, 0, event->hw.last_period);
 
+	data.period = event->hw.last_period;
+	sample_type = event->attr.sample_type;
+
+	/*
+	 * if PEBS-LL or PreciseStore
+	 */
+	if (fll || fst) {
+		if (sample_type & PERF_SAMPLE_ADDR)
+			data.addr = pebs->dla;
+
+		/*
+		 * Use latency for weight (only avail with PEBS-LL)
+		 */
+		if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
+			data.weight = pebs->lat;
+
+		/*
+		 * data.data_src encodes the data source
+		 */
+		if (sample_type & PERF_SAMPLE_DATA_SRC) {
+			if (fll)
+				data.data_src.val = load_latency_data(pebs->dse);
+			else
+				data.data_src.val = precise_store_data(pebs->dse);
+		}
+	}
+
 	/*
 	 * We use the interrupt regs as a base because the PEBS record
 	 * does not contain a full regs set, specifically it seems to
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index b43200dbfe7..d0f9e5aa215 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -17,6 +17,9 @@ static struct event_constraint constraint_fixed =
 static struct event_constraint constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+				((1ULL << (n)) - 1)))
+
 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");
@@ -31,9 +34,13 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
 DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
 DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
 DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
 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");
@@ -110,6 +117,21 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even
 	reg1->alloc = 0;
 }
 
+static u64 uncore_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;
+}
+
 /* Sandy Bridge-EP uncore support */
 static struct intel_uncore_type snbep_uncore_cbox;
 static struct intel_uncore_type snbep_uncore_pcu;
@@ -205,7 +227,7 @@ static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
 
 	if (reg1->idx != EXTRA_REG_NONE)
-		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
 
 	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
@@ -226,29 +248,6 @@ static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
 		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
 }
 
-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;
-
-	if (box->pmu->type == &snbep_uncore_cbox) {
-		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
-			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;
-		}
-	}
-	reg1->idx = 0;
-
-	return 0;
-}
-
 static struct attribute *snbep_uncore_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -345,16 +344,16 @@ static struct attribute_group snbep_uncore_qpi_format_group = {
 	.attrs = snbep_uncore_qpi_formats_attr,
 };
 
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
+	.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	= uncore_msr_read_counter
+
 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	= uncore_msr_read_counter,
-	.get_constraint = uncore_get_constraint,
-	.put_constraint = uncore_put_constraint,
-	.hw_config	= snbep_uncore_hw_config,
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 };
 
 static struct intel_uncore_ops snbep_uncore_pci_ops = {
@@ -372,6 +371,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
 	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
@@ -421,6 +421,14 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
@@ -428,6 +436,8 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
 	EVENT_CONSTRAINT_END
 };
 
@@ -446,6 +456,145 @@ static struct intel_uncore_type snbep_uncore_ubox = {
 	.format_group	= &snbep_uncore_ubox_format_group,
 };
 
+static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
+	EVENT_EXTRA_END
+};
+
+static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	int i;
+
+	if (uncore_box_is_fake(box))
+		return;
+
+	for (i = 0; i < 5; i++) {
+		if (reg1->alloc & (0x1 << i))
+			atomic_sub(1 << (i * 6), &er->ref);
+	}
+	reg1->alloc = 0;
+}
+
+static struct event_constraint *
+__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
+			    u64 (*cbox_filter_mask)(int fields))
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	int i, alloc = 0;
+	unsigned long flags;
+	u64 mask;
+
+	if (reg1->idx == EXTRA_REG_NONE)
+		return NULL;
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	for (i = 0; i < 5; i++) {
+		if (!(reg1->idx & (0x1 << i)))
+			continue;
+		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+			continue;
+
+		mask = cbox_filter_mask(0x1 << i);
+		if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
+		    !((reg1->config ^ er->config) & mask)) {
+			atomic_add(1 << (i * 6), &er->ref);
+			er->config &= ~mask;
+			er->config |= reg1->config & mask;
+			alloc |= (0x1 << i);
+		} else {
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+	if (i < 5)
+		goto fail;
+
+	if (!uncore_box_is_fake(box))
+		reg1->alloc |= alloc;
+
+	return 0;
+fail:
+	for (; i >= 0; i--) {
+		if (alloc & (0x1 << i))
+			atomic_sub(1 << (i * 6), &er->ref);
+	}
+	return &constraint_empty;
+}
+
+static u64 snbep_cbox_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+	if (fields & 0x4)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+	return mask;
+}
+
+static struct event_constraint *
+snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
+}
+
+static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_cbox_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_cbox_hw_config,
+	.get_constraint		= snbep_cbox_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
 static struct intel_uncore_type snbep_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 4,
@@ -458,10 +607,104 @@ static struct intel_uncore_type snbep_uncore_cbox = {
 	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
 	.num_shared_regs	= 1,
 	.constraints		= snbep_uncore_cbox_constraints,
-	.ops			= &snbep_uncore_msr_ops,
+	.ops			= &snbep_uncore_cbox_ops,
 	.format_group		= &snbep_uncore_cbox_format_group,
 };
 
+static u64 snbep_pcu_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;
+	u64 config = reg1->config;
+
+	if (new_idx > reg1->idx)
+		config <<= 8 * (new_idx - reg1->idx);
+	else
+		config >>= 8 * (reg1->idx - new_idx);
+
+	if (modify) {
+		hwc->config += new_idx - reg1->idx;
+		reg1->config = config;
+		reg1->idx = new_idx;
+	}
+	return config;
+}
+
+static struct event_constraint *
+snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	unsigned long flags;
+	int idx = reg1->idx;
+	u64 mask, config1 = reg1->config;
+	bool ok = false;
+
+	if (reg1->idx == EXTRA_REG_NONE ||
+	    (!uncore_box_is_fake(box) && reg1->alloc))
+		return NULL;
+again:
+	mask = 0xff << (idx * 8);
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
+	    !((config1 ^ er->config) & mask)) {
+		atomic_add(1 << (idx * 8), &er->ref);
+		er->config &= ~mask;
+		er->config |= config1 & mask;
+		ok = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (!ok) {
+		idx = (idx + 1) % 4;
+		if (idx != reg1->idx) {
+			config1 = snbep_pcu_alter_er(event, idx, false);
+			goto again;
+		}
+		return &constraint_empty;
+	}
+
+	if (!uncore_box_is_fake(box)) {
+		if (idx != reg1->idx)
+			snbep_pcu_alter_er(event, idx, true);
+		reg1->alloc = 1;
+	}
+	return NULL;
+}
+
+static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	atomic_sub(1 << (reg1->idx * 8), &er->ref);
+	reg1->alloc = 0;
+}
+
+static int snbep_pcu_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;
+	int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+	if (ev_sel >= 0xb && ev_sel <= 0xe) {
+		reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+		reg1->idx = ev_sel - 0xb;
+		reg1->config = event->attr.config1 & (0xff << reg1->idx);
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_pcu_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
 static struct intel_uncore_type snbep_uncore_pcu = {
 	.name			= "pcu",
 	.num_counters		= 4,
@@ -472,7 +715,7 @@ static struct intel_uncore_type snbep_uncore_pcu = {
 	.event_mask		= SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
 	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
 	.num_shared_regs	= 1,
-	.ops			= &snbep_uncore_msr_ops,
+	.ops			= &snbep_uncore_pcu_ops,
 	.format_group		= &snbep_uncore_pcu_format_group,
 };
 
@@ -544,55 +787,63 @@ static struct intel_uncore_type snbep_uncore_r3qpi = {
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
 
+enum {
+	SNBEP_PCI_UNCORE_HA,
+	SNBEP_PCI_UNCORE_IMC,
+	SNBEP_PCI_UNCORE_QPI,
+	SNBEP_PCI_UNCORE_R2PCIE,
+	SNBEP_PCI_UNCORE_R3QPI,
+};
+
 static struct intel_uncore_type *snbep_pci_uncores[] = {
-	&snbep_uncore_ha,
-	&snbep_uncore_imc,
-	&snbep_uncore_qpi,
-	&snbep_uncore_r2pcie,
-	&snbep_uncore_r3qpi,
+	[SNBEP_PCI_UNCORE_HA]		= &snbep_uncore_ha,
+	[SNBEP_PCI_UNCORE_IMC]		= &snbep_uncore_imc,
+	[SNBEP_PCI_UNCORE_QPI]		= &snbep_uncore_qpi,
+	[SNBEP_PCI_UNCORE_R2PCIE]	= &snbep_uncore_r2pcie,
+	[SNBEP_PCI_UNCORE_R3QPI]	= &snbep_uncore_r3qpi,
 	NULL,
 };
 
 static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
 	{ /* Home Agent */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
-		.driver_data = (unsigned long)&snbep_uncore_ha,
+		.driver_data = SNBEP_PCI_UNCORE_HA,
 	},
 	{ /* MC Channel 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
-		.driver_data = (unsigned long)&snbep_uncore_imc,
+		.driver_data = SNBEP_PCI_UNCORE_IMC,
 	},
 	{ /* MC Channel 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
-		.driver_data = (unsigned long)&snbep_uncore_imc,
+		.driver_data = SNBEP_PCI_UNCORE_IMC,
 	},
 	{ /* MC Channel 2 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
-		.driver_data = (unsigned long)&snbep_uncore_imc,
+		.driver_data = SNBEP_PCI_UNCORE_IMC,
 	},
 	{ /* MC Channel 3 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
-		.driver_data = (unsigned long)&snbep_uncore_imc,
+		.driver_data = SNBEP_PCI_UNCORE_IMC,
 	},
 	{ /* QPI Port 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
-		.driver_data = (unsigned long)&snbep_uncore_qpi,
+		.driver_data = SNBEP_PCI_UNCORE_QPI,
 	},
 	{ /* QPI Port 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
-		.driver_data = (unsigned long)&snbep_uncore_qpi,
+		.driver_data = SNBEP_PCI_UNCORE_QPI,
 	},
-	{ /* P2PCIe */
+	{ /* R2PCIe */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
-		.driver_data = (unsigned long)&snbep_uncore_r2pcie,
+		.driver_data = SNBEP_PCI_UNCORE_R2PCIE,
 	},
 	{ /* R3QPI Link 0 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
-		.driver_data = (unsigned long)&snbep_uncore_r3qpi,
+		.driver_data = SNBEP_PCI_UNCORE_R3QPI,
 	},
 	{ /* R3QPI Link 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
-		.driver_data = (unsigned long)&snbep_uncore_r3qpi,
+		.driver_data = SNBEP_PCI_UNCORE_R3QPI,
 	},
 	{ /* end: all zeroes */ }
 };
@@ -605,7 +856,7 @@ static struct pci_driver snbep_uncore_pci_driver = {
 /*
  * build pci bus to socket mapping
  */
-static int snbep_pci2phy_map_init(void)
+static int snbep_pci2phy_map_init(int devid)
 {
 	struct pci_dev *ubox_dev = NULL;
 	int i, bus, nodeid;
@@ -614,9 +865,7 @@ static int snbep_pci2phy_map_init(void)
 
 	while (1) {
 		/* find the UBOX device */
-		ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL,
-					PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX,
-					ubox_dev);
+		ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
 		if (!ubox_dev)
 			break;
 		bus = ubox_dev->bus->number;
@@ -639,7 +888,7 @@ static int snbep_pci2phy_map_init(void)
 				break;
 			}
 		}
-	};
+	}
 
 	if (ubox_dev)
 		pci_dev_put(ubox_dev);
@@ -648,6 +897,440 @@ static int snbep_pci2phy_map_init(void)
 }
 /* end of Sandy Bridge-EP uncore support */
 
+/* IvyTown uncore support */
+static void ivt_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	if (msr)
+		wrmsrl(msr, IVT_PMON_BOX_CTL_INT);
+}
+
+static void ivt_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, IVT_PMON_BOX_CTL_INT);
+}
+
+#define IVT_UNCORE_MSR_OPS_COMMON_INIT()			\
+	.init_box	= ivt_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	= uncore_msr_read_counter
+
+static struct intel_uncore_ops ivt_uncore_msr_ops = {
+	IVT_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+static struct intel_uncore_ops ivt_uncore_pci_ops = {
+	.init_box	= ivt_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= snbep_uncore_pci_disable_event,
+	.enable_event	= snbep_uncore_pci_enable_event,
+	.read_counter	= snbep_uncore_pci_read_counter,
+};
+
+#define IVT_UNCORE_PCI_COMMON_INIT()				\
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
+	.event_mask	= IVT_PMON_RAW_EVENT_MASK,		\
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
+	.ops		= &ivt_uncore_pci_ops,			\
+	.format_group	= &ivt_uncore_format_group
+
+static struct attribute *ivt_uncore_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 *ivt_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	NULL,
+};
+
+static struct attribute *ivt_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid.attr,
+	&format_attr_filter_link.attr,
+	&format_attr_filter_state2.attr,
+	&format_attr_filter_nid2.attr,
+	&format_attr_filter_opc2.attr,
+	NULL,
+};
+
+static struct attribute *ivt_uncore_pcu_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_occ_sel.attr,
+	&format_attr_edge.attr,
+	&format_attr_thresh5.attr,
+	&format_attr_occ_invert.attr,
+	&format_attr_occ_edge.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 *ivt_uncore_qpi_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group ivt_uncore_format_group = {
+	.name = "format",
+	.attrs = ivt_uncore_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_ubox_format_group = {
+	.name = "format",
+	.attrs = ivt_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = ivt_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_pcu_format_group = {
+	.name = "format",
+	.attrs = ivt_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group ivt_uncore_qpi_format_group = {
+	.name = "format",
+	.attrs = ivt_uncore_qpi_formats_attr,
+};
+
+static struct intel_uncore_type ivt_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
+	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
+	.event_mask	= IVT_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.ops		= &ivt_uncore_msr_ops,
+	.format_group	= &ivt_uncore_ubox_format_group,
+};
+
+static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
+	EVENT_EXTRA_END
+};
+
+static u64 ivt_cbox_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK;
+	if (fields & 0x4)
+		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8)
+		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID;
+	if (fields & 0x10)
+		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+	return mask;
+}
+
+static struct event_constraint *
+ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask);
+}
+
+static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static void ivt_cbox_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;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		u64 filter = uncore_shared_reg_config(box, 0);
+		wrmsrl(reg1->reg, filter & 0xffffffff);
+		wrmsrl(reg1->reg + 6, filter >> 32);
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops ivt_uncore_cbox_ops = {
+	.init_box		= ivt_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		= ivt_cbox_enable_event,
+	.read_counter		= uncore_msr_read_counter,
+	.hw_config		= ivt_cbox_hw_config,
+	.get_constraint		= ivt_cbox_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type ivt_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 4,
+	.num_boxes		= 15,
+	.perf_ctr_bits		= 44,
+	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
+	.event_mask		= IVT_CBO_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= snbep_uncore_cbox_constraints,
+	.ops			= &ivt_uncore_cbox_ops,
+	.format_group		= &ivt_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_ops ivt_uncore_pcu_ops = {
+	IVT_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type ivt_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= IVT_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &ivt_uncore_pcu_ops,
+	.format_group		= &ivt_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *ivt_msr_uncores[] = {
+	&ivt_uncore_ubox,
+	&ivt_uncore_cbox,
+	&ivt_uncore_pcu,
+	NULL,
+};
+
+static struct intel_uncore_type ivt_uncore_ha = {
+	.name		= "ha",
+	.num_counters   = 4,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 48,
+	IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivt_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 4,
+	.num_boxes	= 8,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivt_uncore_qpi = {
+	.name		= "qpi",
+	.num_counters   = 4,
+	.num_boxes	= 3,
+	.perf_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,
+	.event_mask	= IVT_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,
+	.ops		= &ivt_uncore_pci_ops,
+	.format_group	= &ivt_uncore_qpi_format_group,
+};
+
+static struct intel_uncore_type ivt_uncore_r2pcie = {
+	.name		= "r2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r2pcie_constraints,
+	IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivt_uncore_r3qpi = {
+	.name		= "r3qpi",
+	.num_counters   = 3,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r3qpi_constraints,
+	IVT_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+	IVT_PCI_UNCORE_HA,
+	IVT_PCI_UNCORE_IMC,
+	IVT_PCI_UNCORE_QPI,
+	IVT_PCI_UNCORE_R2PCIE,
+	IVT_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *ivt_pci_uncores[] = {
+	[IVT_PCI_UNCORE_HA]	= &ivt_uncore_ha,
+	[IVT_PCI_UNCORE_IMC]	= &ivt_uncore_imc,
+	[IVT_PCI_UNCORE_QPI]	= &ivt_uncore_qpi,
+	[IVT_PCI_UNCORE_R2PCIE]	= &ivt_uncore_r2pcie,
+	[IVT_PCI_UNCORE_R3QPI]	= &ivt_uncore_r3qpi,
+	NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = {
+	{ /* Home Agent 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
+		.driver_data = IVT_PCI_UNCORE_HA,
+	},
+	{ /* Home Agent 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
+		.driver_data = IVT_PCI_UNCORE_HA,
+	},
+	{ /* MC0 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* MC0 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* MC0 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* MC0 Channel 4 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* MC1 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* MC1 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* MC1 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* MC1 Channel 4 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
+		.driver_data = IVT_PCI_UNCORE_IMC,
+	},
+	{ /* QPI0 Port 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
+		.driver_data = IVT_PCI_UNCORE_QPI,
+	},
+	{ /* QPI0 Port 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
+		.driver_data = IVT_PCI_UNCORE_QPI,
+	},
+	{ /* QPI1 Port 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
+		.driver_data = IVT_PCI_UNCORE_QPI,
+	},
+	{ /* R2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
+		.driver_data = IVT_PCI_UNCORE_R2PCIE,
+	},
+	{ /* R3QPI0 Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
+		.driver_data = IVT_PCI_UNCORE_R3QPI,
+	},
+	{ /* R3QPI0 Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
+		.driver_data = IVT_PCI_UNCORE_R3QPI,
+	},
+	{ /* R3QPI1 Link 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
+		.driver_data = IVT_PCI_UNCORE_R3QPI,
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver ivt_uncore_pci_driver = {
+	.name		= "ivt_uncore",
+	.id_table	= ivt_uncore_pci_ids,
+};
+/* end of IvyTown uncore support */
+
 /* Sandy Bridge uncore support */
 static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
@@ -808,9 +1491,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = {
 /* 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(match, match, "config1:0-63");
@@ -1161,7 +1841,7 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
 };
 
 /* Nehalem-EX or Westmere-EX ? */
-bool uncore_nhmex;
+static bool uncore_nhmex;
 
 static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
 {
@@ -1239,7 +1919,7 @@ static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
 	atomic_sub(1 << (idx * 8), &er->ref);
 }
 
-u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+static 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;
@@ -1554,7 +2234,7 @@ static struct intel_uncore_type nhmex_uncore_mbox = {
 	.format_group		= &nhmex_uncore_mbox_format_group,
 };
 
-void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
+static 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;
@@ -1724,21 +2404,6 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event
 	return 0;
 }
 
-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;
@@ -1759,7 +2424,7 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
 	case 2:
 	case 3:
 		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
-			nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5));
+			uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
 		break;
 	case 4:
 		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
@@ -2285,7 +2950,7 @@ out:
 	return ret;
 }
 
-int uncore_pmu_event_init(struct perf_event *event)
+static int uncore_pmu_event_init(struct perf_event *event)
 {
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
@@ -2438,7 +3103,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
 
 	type->unconstrainted = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
-				0, type->num_counters, 0);
+				0, type->num_counters, 0, 0);
 
 	for (i = 0; i < type->num_boxes; i++) {
 		pmus[i].func_id = -1;
@@ -2556,6 +3221,8 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 	if (WARN_ON_ONCE(phys_id != box->phys_id))
 		return;
 
+	pci_set_drvdata(pdev, NULL);
+
 	raw_spin_lock(&uncore_box_lock);
 	list_del(&box->list);
 	raw_spin_unlock(&uncore_box_lock);
@@ -2574,11 +3241,7 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 static int uncore_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *id)
 {
-	struct intel_uncore_type *type;
-
-	type = (struct intel_uncore_type *)id->driver_data;
-
-	return uncore_pci_add(type, pdev);
+	return uncore_pci_add(pci_uncores[id->driver_data], pdev);
 }
 
 static int __init uncore_pci_init(void)
@@ -2587,12 +3250,19 @@ static int __init uncore_pci_init(void)
 
 	switch (boot_cpu_data.x86_model) {
 	case 45: /* Sandy Bridge-EP */
-		ret = snbep_pci2phy_map_init();
+		ret = snbep_pci2phy_map_init(0x3ce0);
 		if (ret)
 			return ret;
 		pci_uncores = snbep_pci_uncores;
 		uncore_pci_driver = &snbep_uncore_pci_driver;
 		break;
+	case 62: /* IvyTown */
+		ret = snbep_pci2phy_map_init(0x0e1e);
+		if (ret)
+			return ret;
+		pci_uncores = ivt_pci_uncores;
+		uncore_pci_driver = &ivt_uncore_pci_driver;
+		break;
 	default:
 		return 0;
 	}
@@ -2622,6 +3292,21 @@ static void __init uncore_pci_exit(void)
 	}
 }
 
+/* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */
+static LIST_HEAD(boxes_to_free);
+
+static void __cpuinit uncore_kfree_boxes(void)
+{
+	struct intel_uncore_box *box;
+
+	while (!list_empty(&boxes_to_free)) {
+		box = list_entry(boxes_to_free.next,
+				 struct intel_uncore_box, list);
+		list_del(&box->list);
+		kfree(box);
+	}
+}
+
 static void __cpuinit uncore_cpu_dying(int cpu)
 {
 	struct intel_uncore_type *type;
@@ -2636,7 +3321,7 @@ static void __cpuinit uncore_cpu_dying(int cpu)
 			box = *per_cpu_ptr(pmu->box, cpu);
 			*per_cpu_ptr(pmu->box, cpu) = NULL;
 			if (box && atomic_dec_and_test(&box->refcnt))
-				kfree(box);
+				list_add(&box->list, &boxes_to_free);
 		}
 	}
 }
@@ -2666,8 +3351,11 @@ static int __cpuinit uncore_cpu_starting(int cpu)
 				if (exist && exist->phys_id == phys_id) {
 					atomic_inc(&exist->refcnt);
 					*per_cpu_ptr(pmu->box, cpu) = exist;
-					kfree(box);
-					box = NULL;
+					if (box) {
+						list_add(&box->list,
+							 &boxes_to_free);
+						box = NULL;
+					}
 					break;
 				}
 			}
@@ -2806,6 +3494,10 @@ static int
 	case CPU_DYING:
 		uncore_cpu_dying(cpu);
 		break;
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		uncore_kfree_boxes();
+		break;
 	default:
 		break;
 	}
@@ -2871,6 +3563,12 @@ static int __init uncore_cpu_init(void)
 			nhmex_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = nhmex_msr_uncores;
 		break;
+	case 62: /* IvyTown */
+		if (ivt_uncore_cbox.num_boxes > max_cores)
+			ivt_uncore_cbox.num_boxes = max_cores;
+		msr_uncores = ivt_msr_uncores;
+		break;
+
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index e68a4550e95..f9528917f6e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -76,7 +76,7 @@
 #define SNBEP_PMON_CTL_UMASK_MASK	0x0000ff00
 #define SNBEP_PMON_CTL_RST		(1 << 17)
 #define SNBEP_PMON_CTL_EDGE_DET		(1 << 18)
-#define SNBEP_PMON_CTL_EV_SEL_EXT	(1 << 21)	/* only for QPI */
+#define SNBEP_PMON_CTL_EV_SEL_EXT	(1 << 21)
 #define SNBEP_PMON_CTL_EN		(1 << 22)
 #define SNBEP_PMON_CTL_INVERT		(1 << 23)
 #define SNBEP_PMON_CTL_TRESH_MASK	0xff000000
@@ -148,9 +148,20 @@
 #define SNBEP_C0_MSR_PMON_CTL0			0xd10
 #define SNBEP_C0_MSR_PMON_BOX_CTL		0xd04
 #define SNBEP_C0_MSR_PMON_BOX_FILTER		0xd14
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK	0xfffffc1f
 #define SNBEP_CBO_MSR_OFFSET			0x20
 
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID	0x1f
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID	0x3fc00
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE	0x7c0000
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC	0xff800000
+
+#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) {	\
+	.event = (e),				\
+	.msr = SNBEP_C0_MSR_PMON_BOX_FILTER,	\
+	.config_mask = (m),			\
+	.idx = (i)				\
+}
+
 /* SNB-EP PCU register */
 #define SNBEP_PCU_MSR_PMON_CTR0			0xc36
 #define SNBEP_PCU_MSR_PMON_CTL0			0xc30
@@ -160,6 +171,55 @@
 #define SNBEP_PCU_MSR_CORE_C3_CTR		0x3fc
 #define SNBEP_PCU_MSR_CORE_C6_CTR		0x3fd
 
+/* IVT event control */
+#define IVT_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
+					 SNBEP_PMON_BOX_CTL_RST_CTRS)
+#define IVT_PMON_RAW_EVENT_MASK		(SNBEP_PMON_CTL_EV_SEL_MASK | \
+					 SNBEP_PMON_CTL_UMASK_MASK | \
+					 SNBEP_PMON_CTL_EDGE_DET | \
+					 SNBEP_PMON_CTL_TRESH_MASK)
+/* IVT Ubox */
+#define IVT_U_MSR_PMON_GLOBAL_CTL		0xc00
+#define IVT_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
+#define IVT_U_PMON_GLOBAL_UNFRZ_ALL		(1 << 29)
+
+#define IVT_U_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_UMASK_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+/* IVT Cbo */
+#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK		(IVT_PMON_RAW_EVENT_MASK | \
+						 SNBEP_CBO_PMON_CTL_TID_EN)
+
+#define IVT_CB0_MSR_PMON_BOX_FILTER_TID		(0x1fULL << 0)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 5)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE	(0x3fULL << 17)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_NID		(0xffffULL << 32)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC		(0x1ffULL << 52)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_C6		(0x1ULL << 61)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_NC		(0x1ULL << 62)
+#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC	(0x1ULL << 63)
+
+/* IVT home agent */
+#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST		(1 << 16)
+#define IVT_HA_PCI_PMON_RAW_EVENT_MASK		\
+				(IVT_PMON_RAW_EVENT_MASK | \
+				 IVT_HA_PCI_PMON_CTL_Q_OCC_RST)
+/* IVT PCU */
+#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+/* IVT QPI */
+#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK	\
+				(IVT_PMON_RAW_EVENT_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT)
+
 /* NHM-EX event control */
 #define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
 #define NHMEX_PMON_CTL_UMASK_MASK	0x0000ff00
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 92c7e39a079..3486e666035 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void)
 	 * So at moment let leave metrics turned on forever -- it's
 	 * ok for now but need to be revisited!
 	 *
-	 * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0);
-	 * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0);
+	 * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, 0);
+	 * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, 0);
 	 */
 }
 
@@ -910,8 +910,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
 	 * asserted again and again
 	 */
 	(void)wrmsrl_safe(hwc->config_base,
-		(u64)(p4_config_unpack_cccr(hwc->config)) &
-			~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
+		p4_config_unpack_cccr(hwc->config) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
 }
 
 static void p4_pmu_disable_all(void)
@@ -957,7 +956,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
 	u64 escr_addr, cccr;
 
 	bind = &p4_event_bind_map[idx];
-	escr_addr = (u64)bind->escr_msr[thread];
+	escr_addr = bind->escr_msr[thread];
 
 	/*
 	 * - we dont support cascaded counters yet
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 7bfe318d3d8..9895a9a4138 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -353,7 +353,11 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
 		 * have given.
 		 */
 		newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
-		BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check.  */
+		if ((s64) (s32) newdisp != newdisp) {
+			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
+			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value);
+			return 0;
+		}
 		disp = (u8 *) dest + insn_offset_displacement(&insn);
 		*(s32 *) disp = (s32) newdisp;
 	}
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 0ba4cfb4f41..2ed845928b5 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -697,3 +697,32 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		send_sig(SIGTRAP, current, 0);
 	return ret;
 }
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+	int rasize, ncopied;
+	unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
+
+	rasize = is_ia32_task() ? 4 : 8;
+	ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize);
+	if (unlikely(ncopied))
+		return -1;
+
+	/* check whether address has been already hijacked */
+	if (orig_ret_vaddr == trampoline_vaddr)
+		return orig_ret_vaddr;
+
+	ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
+	if (likely(!ncopied))
+		return orig_ret_vaddr;
+
+	if (ncopied != rasize) {
+		pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, "
+			"%%ip=%#lx\n", current->pid, regs->sp, regs->ip);
+
+		force_sig_info(SIGSEGV, SEND_SIG_FORCED, current);
+	}
+
+	return -1;
+}