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

Pull perf updates from Ingo Molnar:
 "With over 300 commits it's been a busy cycle - with most of the work
  concentrated on the tooling side (as it should).

  The main kernel side enhancements were:

   - Add per event callchain limit: Recently we introduced a sysctl to
     tune the max-stack for all events for which callchains were
     requested:

       $ sysctl kernel.perf_event_max_stack
       kernel.perf_event_max_stack = 127

     Now this patch introduces a way to configure this per event, i.e.
     this becomes possible:

       $ perf record -e sched:*/max-stack=2/ -e block:*/max-stack=10/ -a

     allowing finer tuning of how much buffer space callchains use.

     This uses an u16 from the reserved space at the end, leaving
     another u16 for future use.

     There has been interest in even finer tuning, namely to control the
     max stack for kernel and userspace callchains separately.  Further
     discussion is needed, we may for instance use the remaining u16 for
     that and when it is present, assume that the sample_max_stack
     introduced in this patch applies for the kernel, and the u16 left
     is used for limiting the userspace callchain (Arnaldo Carvalho de
     Melo)

   - Optimize AUX event (hardware assisted side-band event) delivery
     (Kan Liang)

   - Rework Intel family name macro usage (this is partially x86 arch
     work) (Dave Hansen)

   - Refine and fix Intel LBR support (David Carrillo-Cisneros)

   - Add support for Intel 'TopDown' events (Andi Kleen)

   - Intel uncore PMU driver fixes and enhancements (Kan Liang)

   - ... other misc changes.

  Here's an incomplete list of the tooling enhancements (but there's
  much more, see the shortlog and the git log for details):

   - Support cross unwinding, i.e.  collecting '--call-graph dwarf'
     perf.data files in one machine and then doing analysis in another
     machine of a different hardware architecture.  This enables, for
     instance, to do:

       $ perf record -a --call-graph dwarf

     on a x86-32 or aarch64 system and then do 'perf report' on it on a
     x86_64 workstation (He Kuang)

   - Allow reading from a backward ring buffer (one setup via
     sys_perf_event_open() with perf_event_attr.write_backward = 1)
     (Wang Nan)

   - Finish merging initial SDT (Statically Defined Traces) support, see
     cset comments for details about how it all works (Masami Hiramatsu)

   - Support attaching eBPF programs to tracepoints (Wang Nan)

   - Add demangling of symbols in programs written in the Rust language
     (David Tolnay)

   - Add support for tracepoints in the python binding, including an
     example, that sets up and parses sched:sched_switch events,
     tools/perf/python/tracepoint.py (Jiri Olsa)

   - Introduce --stdio-color to set up the color output mode selection
     in 'annotate' and 'report', allowing emit color escape sequences
     when redirecting the output of these tools (Arnaldo Carvalho de
     Melo)

   - Add 'callindent' option to 'perf script -F', to indent the Intel PT
     call stack, making this output more ftrace-like (Adrian Hunter,
     Andi Kleen)

   - Allow dumping the object files generated by llvm when processing
     eBPF scriptlet events (Wang Nan)

   - Add stackcollapse.py script to help generating flame graphs (Paolo
     Bonzini)

   - Add --ldlat option to 'perf mem' to specify load latency for loads
     event (e.g. cpu/mem-loads/ ) (Jiri Olsa)

   - Tooling support for Intel TopDown counters, recently added to the
     kernel (Andi Kleen)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (303 commits)
  perf tests: Add is_printable_array test
  perf tools: Make is_printable_array global
  perf script python: Fix string vs byte array resolving
  perf probe: Warn unmatched function filter correctly
  perf cpu_map: Add more helpers
  perf stat: Balance opening and reading events
  tools: Copy linux/{hash,poison}.h and check for drift
  perf tools: Remove include/linux/list.h from perf's MANIFEST
  tools: Copy the bitops files accessed from the kernel and check for drift
  Remove: kernel unistd*h files from perf's MANIFEST, not used
  perf tools: Remove tools/perf/util/include/linux/const.h
  perf tools: Remove tools/perf/util/include/asm/byteorder.h
  perf tools: Add missing linux/compiler.h include to perf-sys.h
  perf jit: Remove some no-op error handling
  perf jit: Add missing curly braces
  objtool: Initialize variable to silence old compiler
  objtool: Add -I$(srctree)/tools/arch/$(ARCH)/include/uapi
  perf record: Add --tail-synthesize option
  perf session: Don't warn about out of order event if write_backward is used
  perf tools: Enable overwrite settings
  ...

13 files changed, 608 insertions, 184 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 91eac39625be..dfebbde2a4cc 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1622,6 +1622,29 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, cha
 }
 EXPORT_SYMBOL_GPL(events_sysfs_show);
 
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct perf_pmu_events_ht_attr *pmu_attr =
+		container_of(attr, struct perf_pmu_events_ht_attr, attr);
+
+	/*
+	 * Report conditional events depending on Hyper-Threading.
+	 *
+	 * This is overly conservative as usually the HT special
+	 * handling is not needed if the other CPU thread is idle.
+	 *
+	 * Note this does not (and cannot) handle the case when thread
+	 * siblings are invisible, for example with virtualization
+	 * if they are owned by some other guest.  The user tool
+	 * has to re-read when a thread sibling gets onlined later.
+	 */
+	return sprintf(page, "%s",
+			topology_max_smt_threads() > 1 ?
+			pmu_attr->event_str_ht :
+			pmu_attr->event_str_noht);
+}
+
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
 EVENT_ATTR(cache-references,		CACHE_REFERENCES	);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9b4f9d3ce465..0974ba11e954 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -16,6 +16,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
+#include <asm/intel-family.h>
 #include <asm/apic.h>
 
 #include "../perf_event.h"
@@ -185,7 +186,7 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_skl_event_constraints[] = {
+static struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
@@ -204,10 +205,8 @@ struct event_constraint intel_skl_event_constraints[] = {
 };
 
 static struct extra_reg intel_knl_extra_regs[] __read_mostly = {
-	INTEL_UEVENT_EXTRA_REG(0x01b7,
-			       MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0),
-	INTEL_UEVENT_EXTRA_REG(0x02b7,
-			       MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1),
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x799ffbb6e7ull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x399ffbffe7ull, RSP_1),
 	EVENT_EXTRA_END
 };
 
@@ -243,14 +242,51 @@ 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[] = {
+static struct attribute *nhm_events_attrs[] = {
 	EVENT_PTR(mem_ld_nhm),
 	NULL,
 };
 
-struct attribute *snb_events_attrs[] = {
+/*
+ * topdown events for Intel Core CPUs.
+ *
+ * The events are all in slots, which is a free slot in a 4 wide
+ * pipeline. Some events are already reported in slots, for cycle
+ * events we multiply by the pipeline width (4).
+ *
+ * With Hyper Threading on, topdown metrics are either summed or averaged
+ * between the threads of a core: (count_t0 + count_t1).
+ *
+ * For the average case the metric is always scaled to pipeline width,
+ * so we use factor 2 ((count_t0 + count_t1) / 2 * 4)
+ */
+
+EVENT_ATTR_STR_HT(topdown-total-slots, td_total_slots,
+	"event=0x3c,umask=0x0",			/* cpu_clk_unhalted.thread */
+	"event=0x3c,umask=0x0,any=1");		/* cpu_clk_unhalted.thread_any */
+EVENT_ATTR_STR_HT(topdown-total-slots.scale, td_total_slots_scale, "4", "2");
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued,
+	"event=0xe,umask=0x1");			/* uops_issued.any */
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired,
+	"event=0xc2,umask=0x2");		/* uops_retired.retire_slots */
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles,
+	"event=0x9c,umask=0x1");		/* idq_uops_not_delivered_core */
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles,
+	"event=0xd,umask=0x3,cmask=1",		/* int_misc.recovery_cycles */
+	"event=0xd,umask=0x3,cmask=1,any=1");	/* int_misc.recovery_cycles_any */
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
+	"4", "2");
+
+static struct attribute *snb_events_attrs[] = {
 	EVENT_PTR(mem_ld_snb),
 	EVENT_PTR(mem_st_snb),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
 	NULL,
 };
 
@@ -280,7 +316,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_bdw_event_constraints[] = {
+static struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
@@ -1361,6 +1397,29 @@ static __initconst const u64 atom_hw_cache_event_ids
  },
 };
 
+EVENT_ATTR_STR(topdown-total-slots, td_total_slots_slm, "event=0x3c");
+EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_slm, "2");
+/* no_alloc_cycles.not_delivered */
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_slm,
+	       "event=0xca,umask=0x50");
+EVENT_ATTR_STR(topdown-fetch-bubbles.scale, td_fetch_bubbles_scale_slm, "2");
+/* uops_retired.all */
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_slm,
+	       "event=0xc2,umask=0x10");
+/* uops_retired.all */
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_slm,
+	       "event=0xc2,umask=0x10");
+
+static struct attribute *slm_events_attrs[] = {
+	EVENT_PTR(td_total_slots_slm),
+	EVENT_PTR(td_total_slots_scale_slm),
+	EVENT_PTR(td_fetch_bubbles_slm),
+	EVENT_PTR(td_fetch_bubbles_scale_slm),
+	EVENT_PTR(td_slots_issued_slm),
+	EVENT_PTR(td_slots_retired_slm),
+	NULL
+};
+
 static struct extra_reg intel_slm_extra_regs[] __read_mostly =
 {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
@@ -3290,11 +3349,11 @@ static int intel_snb_pebs_broken(int cpu)
 	u32 rev = UINT_MAX; /* default to broken for unknown models */
 
 	switch (cpu_data(cpu).x86_model) {
-	case 42: /* SNB */
+	case INTEL_FAM6_SANDYBRIDGE:
 		rev = 0x28;
 		break;
 
-	case 45: /* SNB-EP */
+	case INTEL_FAM6_SANDYBRIDGE_X:
 		switch (cpu_data(cpu).x86_mask) {
 		case 6: rev = 0x618; break;
 		case 7: rev = 0x70c; break;
@@ -3331,6 +3390,13 @@ static void intel_snb_check_microcode(void)
 	}
 }
 
+static bool is_lbr_from(unsigned long msr)
+{
+	unsigned long lbr_from_nr = x86_pmu.lbr_from + x86_pmu.lbr_nr;
+
+	return x86_pmu.lbr_from <= msr && msr < lbr_from_nr;
+}
+
 /*
  * Under certain circumstances, access certain MSR may cause #GP.
  * The function tests if the input MSR can be safely accessed.
@@ -3351,13 +3417,24 @@ static bool check_msr(unsigned long msr, u64 mask)
 	 * Only change the bits which can be updated by wrmsrl.
 	 */
 	val_tmp = val_old ^ mask;
+
+	if (is_lbr_from(msr))
+		val_tmp = lbr_from_signext_quirk_wr(val_tmp);
+
 	if (wrmsrl_safe(msr, val_tmp) ||
 	    rdmsrl_safe(msr, &val_new))
 		return false;
 
+	/*
+	 * Quirk only affects validation in wrmsr(), so wrmsrl()'s value
+	 * should equal rdmsrl()'s even with the quirk.
+	 */
 	if (val_new != val_tmp)
 		return false;
 
+	if (is_lbr_from(msr))
+		val_old = lbr_from_signext_quirk_wr(val_old);
+
 	/* Here it's sure that the MSR can be safely accessed.
 	 * Restore the old value and return.
 	 */
@@ -3466,6 +3543,13 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(cycles_ct),
 	EVENT_PTR(mem_ld_hsw),
 	EVENT_PTR(mem_st_hsw),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
 	NULL
 };
 
@@ -3537,15 +3621,15 @@ __init int intel_pmu_init(void)
 	 * Install the hw-cache-events table:
 	 */
 	switch (boot_cpu_data.x86_model) {
-	case 14: /* 65nm Core "Yonah" */
+	case INTEL_FAM6_CORE_YONAH:
 		pr_cont("Core events, ");
 		break;
 
-	case 15: /* 65nm Core2 "Merom"          */
+	case INTEL_FAM6_CORE2_MEROM:
 		x86_add_quirk(intel_clovertown_quirk);
-	case 22: /* 65nm Core2 "Merom-L"        */
-	case 23: /* 45nm Core2 "Penryn"         */
-	case 29: /* 45nm Core2 "Dunnington (MP) */
+	case INTEL_FAM6_CORE2_MEROM_L:
+	case INTEL_FAM6_CORE2_PENRYN:
+	case INTEL_FAM6_CORE2_DUNNINGTON:
 		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -3556,9 +3640,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Core2 events, ");
 		break;
 
-	case 30: /* 45nm Nehalem    */
-	case 26: /* 45nm Nehalem-EP */
-	case 46: /* 45nm Nehalem-EX */
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_EP:
+	case INTEL_FAM6_NEHALEM_EX:
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -3586,11 +3670,11 @@ __init int intel_pmu_init(void)
 		pr_cont("Nehalem events, ");
 		break;
 
-	case 28: /* 45nm Atom "Pineview"   */
-	case 38: /* 45nm Atom "Lincroft"   */
-	case 39: /* 32nm Atom "Penwell"    */
-	case 53: /* 32nm Atom "Cloverview" */
-	case 54: /* 32nm Atom "Cedarview"  */
+	case INTEL_FAM6_ATOM_PINEVIEW:
+	case INTEL_FAM6_ATOM_LINCROFT:
+	case INTEL_FAM6_ATOM_PENWELL:
+	case INTEL_FAM6_ATOM_CLOVERVIEW:
+	case INTEL_FAM6_ATOM_CEDARVIEW:
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -3602,9 +3686,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Atom events, ");
 		break;
 
-	case 55: /* 22nm Atom "Silvermont"                */
-	case 76: /* 14nm Atom "Airmont"                   */
-	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_AIRMONT:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -3616,11 +3700,12 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_slm_extra_regs;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.cpu_events = slm_events_attrs;
 		pr_cont("Silvermont events, ");
 		break;
 
-	case 92: /* 14nm Atom "Goldmont" */
-	case 95: /* 14nm Atom "Goldmont Denverton" */
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_DENVERTON:
 		memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -3643,9 +3728,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Goldmont events, ");
 		break;
 
-	case 37: /* 32nm Westmere    */
-	case 44: /* 32nm Westmere-EP */
-	case 47: /* 32nm Westmere-EX */
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_WESTMERE_EP:
+	case INTEL_FAM6_WESTMERE_EX:
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -3672,8 +3757,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Westmere events, ");
 		break;
 
-	case 42: /* 32nm SandyBridge         */
-	case 45: /* 32nm SandyBridge-E/EN/EP */
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_SANDYBRIDGE_X:
 		x86_add_quirk(intel_sandybridge_quirk);
 		x86_add_quirk(intel_ht_bug);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
@@ -3686,7 +3771,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		if (boot_cpu_data.x86_model == 45)
+		if (boot_cpu_data.x86_model == INTEL_FAM6_SANDYBRIDGE_X)
 			x86_pmu.extra_regs = intel_snbep_extra_regs;
 		else
 			x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -3708,8 +3793,8 @@ __init int intel_pmu_init(void)
 		pr_cont("SandyBridge events, ");
 		break;
 
-	case 58: /* 22nm IvyBridge       */
-	case 62: /* 22nm IvyBridge-EP/EX */
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE_X:
 		x86_add_quirk(intel_ht_bug);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -3725,7 +3810,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
 		x86_pmu.pebs_prec_dist = true;
-		if (boot_cpu_data.x86_model == 62)
+		if (boot_cpu_data.x86_model == INTEL_FAM6_IVYBRIDGE_X)
 			x86_pmu.extra_regs = intel_snbep_extra_regs;
 		else
 			x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -3743,10 +3828,10 @@ __init int intel_pmu_init(void)
 		break;
 
 
-	case 60: /* 22nm Haswell Core */
-	case 63: /* 22nm Haswell Server */
-	case 69: /* 22nm Haswell ULT */
-	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
+	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_X:
+	case INTEL_FAM6_HASWELL_ULT:
+	case INTEL_FAM6_HASWELL_GT3E:
 		x86_add_quirk(intel_ht_bug);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -3770,10 +3855,10 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
-	case 61: /* 14nm Broadwell Core-M */
-	case 86: /* 14nm Broadwell Xeon D */
-	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
-	case 79: /* 14nm Broadwell Server */
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_XEON_D:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_X:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -3806,7 +3891,7 @@ __init int intel_pmu_init(void)
 		pr_cont("Broadwell events, ");
 		break;
 
-	case 87: /* Knights Landing Xeon Phi */
+	case INTEL_FAM6_XEON_PHI_KNL:
 		memcpy(hw_cache_event_ids,
 		       slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs,
@@ -3824,16 +3909,22 @@ __init int intel_pmu_init(void)
 		pr_cont("Knights Landing events, ");
 		break;
 
-	case 142: /* 14nm Kabylake Mobile */
-	case 158: /* 14nm Kabylake Desktop */
-	case 78: /* 14nm Skylake Mobile */
-	case 94: /* 14nm Skylake Desktop */
-	case 85: /* 14nm Skylake Server */
+	case INTEL_FAM6_SKYLAKE_MOBILE:
+	case INTEL_FAM6_SKYLAKE_DESKTOP:
+	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_KABYLAKE_MOBILE:
+	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 		intel_pmu_lbr_init_skl();
 
+		/* INT_MISC.RECOVERY_CYCLES has umask 1 in Skylake */
+		event_attr_td_recovery_bubbles.event_str_noht =
+			"event=0xd,umask=0x1,cmask=1";
+		event_attr_td_recovery_bubbles.event_str_ht =
+			"event=0xd,umask=0x1,cmask=1,any=1";
+
 		x86_pmu.event_constraints = intel_skl_event_constraints;
 		x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_skl_extra_regs;
@@ -3914,6 +4005,8 @@ __init int intel_pmu_init(void)
 			x86_pmu.lbr_nr = 0;
 	}
 
+	if (x86_pmu.lbr_nr)
+		pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
 	/*
 	 * Access extra MSR may cause #GP under certain circumstances.
 	 * E.g. KVM doesn't support offcore event
@@ -3946,16 +4039,14 @@ __init int intel_pmu_init(void)
  */
 static __init int fixup_ht_bug(void)
 {
-	int cpu = smp_processor_id();
-	int w, c;
+	int c;
 	/*
 	 * problem not present on this CPU model, nothing to do
 	 */
 	if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED))
 		return 0;
 
-	w = cpumask_weight(topology_sibling_cpumask(cpu));
-	if (w > 1) {
+	if (topology_max_smt_threads() > 1) {
 		pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n");
 		return 0;
 	}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9ba4e4136a15..4c7638b91fa5 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -89,6 +89,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include "../perf_event.h"
 
 MODULE_LICENSE("GPL");
@@ -511,37 +512,37 @@ static const struct cstate_model slm_cstates __initconst = {
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
 
 static const struct x86_cpu_id intel_cstates_match[] __initconst = {
-	X86_CSTATES_MODEL(30, nhm_cstates),    /* 45nm Nehalem              */
-	X86_CSTATES_MODEL(26, nhm_cstates),    /* 45nm Nehalem-EP           */
-	X86_CSTATES_MODEL(46, nhm_cstates),    /* 45nm Nehalem-EX           */
+	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM,    nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EP, nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EX, nhm_cstates),
 
-	X86_CSTATES_MODEL(37, nhm_cstates),    /* 32nm Westmere             */
-	X86_CSTATES_MODEL(44, nhm_cstates),    /* 32nm Westmere-EP          */
-	X86_CSTATES_MODEL(47, nhm_cstates),    /* 32nm Westmere-EX          */
+	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE,    nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EP, nhm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EX, nhm_cstates),
 
-	X86_CSTATES_MODEL(42, snb_cstates),    /* 32nm SandyBridge          */
-	X86_CSTATES_MODEL(45, snb_cstates),    /* 32nm SandyBridge-E/EN/EP  */
+	X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE_X, snb_cstates),
 
-	X86_CSTATES_MODEL(58, snb_cstates),    /* 22nm IvyBridge            */
-	X86_CSTATES_MODEL(62, snb_cstates),    /* 22nm IvyBridge-EP/EX      */
+	X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_X, snb_cstates),
 
-	X86_CSTATES_MODEL(60, snb_cstates),    /* 22nm Haswell Core         */
-	X86_CSTATES_MODEL(63, snb_cstates),    /* 22nm Haswell Server       */
-	X86_CSTATES_MODEL(70, snb_cstates),    /* 22nm Haswell + GT3e       */
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_CORE, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X,	   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_GT3E, snb_cstates),
 
-	X86_CSTATES_MODEL(69, hswult_cstates), /* 22nm Haswell ULT          */
+	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates),
 
-	X86_CSTATES_MODEL(55, slm_cstates),    /* 22nm Atom Silvermont      */
-	X86_CSTATES_MODEL(77, slm_cstates),    /* 22nm Atom Avoton/Rangely  */
-	X86_CSTATES_MODEL(76, slm_cstates),    /* 22nm Atom Airmont         */
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT,     slm_cstates),
 
-	X86_CSTATES_MODEL(61, snb_cstates),    /* 14nm Broadwell Core-M     */
-	X86_CSTATES_MODEL(86, snb_cstates),    /* 14nm Broadwell Xeon D     */
-	X86_CSTATES_MODEL(71, snb_cstates),    /* 14nm Broadwell + GT3e     */
-	X86_CSTATES_MODEL(79, snb_cstates),    /* 14nm Broadwell Server     */
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_XEON_D, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_GT3E,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X,      snb_cstates),
 
-	X86_CSTATES_MODEL(78, snb_cstates),    /* 14nm Skylake Mobile       */
-	X86_CSTATES_MODEL(94, snb_cstates),    /* 14nm Skylake Desktop      */
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 9e2b40cdb05f..707d358e0dff 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -77,9 +77,11 @@ static enum {
 	 LBR_IND_JMP	|\
 	 LBR_FAR)
 
-#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
-#define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
-#define LBR_FROM_FLAG_ABORT    (1ULL << 61)
+#define LBR_FROM_FLAG_MISPRED	BIT_ULL(63)
+#define LBR_FROM_FLAG_IN_TX	BIT_ULL(62)
+#define LBR_FROM_FLAG_ABORT	BIT_ULL(61)
+
+#define LBR_FROM_SIGNEXT_2MSB	(BIT_ULL(60) | BIT_ULL(59))
 
 /*
  * x86control flow change classification
@@ -235,6 +237,97 @@ enum {
 	LBR_VALID,
 };
 
+/*
+ * For formats with LBR_TSX flags (e.g. LBR_FORMAT_EIP_FLAGS2), bits 61:62 in
+ * MSR_LAST_BRANCH_FROM_x are the TSX flags when TSX is supported, but when
+ * TSX is not supported they have no consistent behavior:
+ *
+ *   - For wrmsr(), bits 61:62 are considered part of the sign extension.
+ *   - For HW updates (branch captures) bits 61:62 are always OFF and are not
+ *     part of the sign extension.
+ *
+ * Therefore, if:
+ *
+ *   1) LBR has TSX format
+ *   2) CPU has no TSX support enabled
+ *
+ * ... then any value passed to wrmsr() must be sign extended to 63 bits and any
+ * value from rdmsr() must be converted to have a 61 bits sign extension,
+ * ignoring the TSX flags.
+ */
+static inline bool lbr_from_signext_quirk_needed(void)
+{
+	int lbr_format = x86_pmu.intel_cap.lbr_format;
+	bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) ||
+			   boot_cpu_has(X86_FEATURE_RTM);
+
+	return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX);
+}
+
+DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key);
+
+/* If quirk is enabled, ensure sign extension is 63 bits: */
+inline u64 lbr_from_signext_quirk_wr(u64 val)
+{
+	if (static_branch_unlikely(&lbr_from_quirk_key)) {
+		/*
+		 * Sign extend into bits 61:62 while preserving bit 63.
+		 *
+		 * Quirk is enabled when TSX is disabled. Therefore TSX bits
+		 * in val are always OFF and must be changed to be sign
+		 * extension bits. Since bits 59:60 are guaranteed to be
+		 * part of the sign extension bits, we can just copy them
+		 * to 61:62.
+		 */
+		val |= (LBR_FROM_SIGNEXT_2MSB & val) << 2;
+	}
+	return val;
+}
+
+/*
+ * If quirk is needed, ensure sign extension is 61 bits:
+ */
+u64 lbr_from_signext_quirk_rd(u64 val)
+{
+	if (static_branch_unlikely(&lbr_from_quirk_key)) {
+		/*
+		 * Quirk is on when TSX is not enabled. Therefore TSX
+		 * flags must be read as OFF.
+		 */
+		val &= ~(LBR_FROM_FLAG_IN_TX | LBR_FROM_FLAG_ABORT);
+	}
+	return val;
+}
+
+static inline void wrlbr_from(unsigned int idx, u64 val)
+{
+	val = lbr_from_signext_quirk_wr(val);
+	wrmsrl(x86_pmu.lbr_from + idx, val);
+}
+
+static inline void wrlbr_to(unsigned int idx, u64 val)
+{
+	wrmsrl(x86_pmu.lbr_to + idx, val);
+}
+
+static inline u64 rdlbr_from(unsigned int idx)
+{
+	u64 val;
+
+	rdmsrl(x86_pmu.lbr_from + idx, val);
+
+	return lbr_from_signext_quirk_rd(val);
+}
+
+static inline u64 rdlbr_to(unsigned int idx)
+{
+	u64 val;
+
+	rdmsrl(x86_pmu.lbr_to + idx, val);
+
+	return val;
+}
+
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
 	int i;
@@ -251,8 +344,9 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 	tos = task_ctx->tos;
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
-		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
-		wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
+		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
+
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
@@ -262,9 +356,9 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
-	int i;
 	unsigned lbr_idx, mask;
 	u64 tos;
+	int i;
 
 	if (task_ctx->lbr_callstack_users == 0) {
 		task_ctx->lbr_stack_state = LBR_NONE;
@@ -275,8 +369,8 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 	tos = intel_pmu_lbr_tos();
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
-		rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
-		rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
+		task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
@@ -452,8 +546,8 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		u16 cycles = 0;
 		int lbr_flags = lbr_desc[lbr_format];
 
-		rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
-		rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
+		from = rdlbr_from(lbr_idx);
+		to   = rdlbr_to(lbr_idx);
 
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
@@ -956,7 +1050,6 @@ void __init intel_pmu_lbr_init_core(void)
 	 * SW branch filter usage:
 	 * - compensate for lack of HW filter
 	 */
-	pr_cont("4-deep LBR, ");
 }
 
 /* nehalem/westmere */
@@ -977,7 +1070,6 @@ void __init intel_pmu_lbr_init_nhm(void)
 	 *   That requires LBR_FAR but that means far
 	 *   jmp need to be filtered out
 	 */
-	pr_cont("16-deep LBR, ");
 }
 
 /* sandy bridge */
@@ -997,7 +1089,6 @@ void __init intel_pmu_lbr_init_snb(void)
 	 *   That requires LBR_FAR but that means far
 	 *   jmp need to be filtered out
 	 */
-	pr_cont("16-deep LBR, ");
 }
 
 /* haswell */
@@ -1011,7 +1102,8 @@ void intel_pmu_lbr_init_hsw(void)
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
 
-	pr_cont("16-deep LBR, ");
+	if (lbr_from_signext_quirk_needed())
+		static_branch_enable(&lbr_from_quirk_key);
 }
 
 /* skylake */
@@ -1031,7 +1123,6 @@ __init void intel_pmu_lbr_init_skl(void)
 	 *   That requires LBR_FAR but that means far
 	 *   jmp need to be filtered out
 	 */
-	pr_cont("32-deep LBR, ");
 }
 
 /* atom */
@@ -1057,7 +1148,6 @@ void __init intel_pmu_lbr_init_atom(void)
 	 * SW branch filter usage:
 	 * - compensate for lack of HW filter
 	 */
-	pr_cont("8-deep LBR, ");
 }
 
 /* slm */
@@ -1088,6 +1178,4 @@ void intel_pmu_lbr_init_knl(void)
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
-
-	pr_cont("8-deep LBR, ");
 }
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index e30eef4f29a6..d0c58b35155f 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -55,6 +55,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include "../perf_event.h"
 
 MODULE_LICENSE("GPL");
@@ -786,26 +787,27 @@ static const struct intel_rapl_init_fun skl_rapl_init __initconst = {
 };
 
 static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
-	X86_RAPL_MODEL_MATCH(42, snb_rapl_init),	/* Sandy Bridge */
-	X86_RAPL_MODEL_MATCH(45, snbep_rapl_init),	/* Sandy Bridge-EP */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE,   snb_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(58, snb_rapl_init),	/* Ivy Bridge */
-	X86_RAPL_MODEL_MATCH(62, snbep_rapl_init),	/* IvyTown */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE,   snb_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(60, hsw_rapl_init),	/* Haswell */
-	X86_RAPL_MODEL_MATCH(63, hsx_rapl_init),	/* Haswell-Server */
-	X86_RAPL_MODEL_MATCH(69, hsw_rapl_init),	/* Haswell-Celeron */
-	X86_RAPL_MODEL_MATCH(70, hsw_rapl_init),	/* Haswell GT3e */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X,    hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT,  hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(61, hsw_rapl_init),	/* Broadwell */
-	X86_RAPL_MODEL_MATCH(71, hsw_rapl_init),	/* Broadwell-H */
-	X86_RAPL_MODEL_MATCH(79, hsx_rapl_init),	/* Broadwell-Server */
-	X86_RAPL_MODEL_MATCH(86, hsx_rapl_init),	/* Broadwell Xeon D */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE,   hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E,   hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(87, knl_rapl_init),	/* Knights Landing */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(78, skl_rapl_init),	/* Skylake */
-	X86_RAPL_MODEL_MATCH(94, skl_rapl_init),	/* Skylake H/S */
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE,  skl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,	 hsx_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index fce74062d981..59b4974c697f 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1,4 +1,5 @@
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include "uncore.h"
 
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
@@ -882,7 +883,7 @@ uncore_types_init(struct intel_uncore_type **types, bool setid)
 static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct intel_uncore_type *type;
-	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_pmu *pmu = NULL;
 	struct intel_uncore_box *box;
 	int phys_id, pkg, ret;
 
@@ -903,20 +904,37 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	}
 
 	type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+
 	/*
-	 * for performance monitoring unit with multiple boxes,
-	 * each box has a different function id.
-	 */
-	pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
-	/* Knights Landing uses a common PCI device ID for multiple instances of
-	 * an uncore PMU device type. There is only one entry per device type in
-	 * the knl_uncore_pci_ids table inspite of multiple devices present for
-	 * some device types. Hence PCI device idx would be 0 for all devices.
-	 * So increment pmu pointer to point to an unused array element.
+	 * Some platforms, e.g.  Knights Landing, use a common PCI device ID
+	 * for multiple instances of an uncore PMU device type. We should check
+	 * PCI slot and func to indicate the uncore box.
 	 */
-	if (boot_cpu_data.x86_model == 87) {
-		while (pmu->func_id >= 0)
-			pmu++;
+	if (id->driver_data & ~0xffff) {
+		struct pci_driver *pci_drv = pdev->driver;
+		const struct pci_device_id *ids = pci_drv->id_table;
+		unsigned int devfn;
+
+		while (ids && ids->vendor) {
+			if ((ids->vendor == pdev->vendor) &&
+			    (ids->device == pdev->device)) {
+				devfn = PCI_DEVFN(UNCORE_PCI_DEV_DEV(ids->driver_data),
+						  UNCORE_PCI_DEV_FUNC(ids->driver_data));
+				if (devfn == pdev->devfn) {
+					pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)];
+					break;
+				}
+			}
+			ids++;
+		}
+		if (pmu == NULL)
+			return -ENODEV;
+	} else {
+		/*
+		 * for performance monitoring unit with multiple boxes,
+		 * each box has a different function id.
+		 */
+		pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
 	}
 
 	if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
@@ -956,7 +974,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 
 static void uncore_pci_remove(struct pci_dev *pdev)
 {
-	struct intel_uncore_box *box = pci_get_drvdata(pdev);
+	struct intel_uncore_box *box;
 	struct intel_uncore_pmu *pmu;
 	int i, phys_id, pkg;
 
@@ -1361,30 +1379,32 @@ static const struct intel_uncore_init_fun knl_uncore_init __initconst = {
 };
 
 static const struct intel_uncore_init_fun skl_uncore_init __initconst = {
+	.cpu_init = skl_uncore_cpu_init,
 	.pci_init = skl_uncore_pci_init,
 };
 
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
-	X86_UNCORE_MODEL_MATCH(26, nhm_uncore_init),	/* Nehalem */
-	X86_UNCORE_MODEL_MATCH(30, nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(37, nhm_uncore_init),	/* Westmere */
-	X86_UNCORE_MODEL_MATCH(44, nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(42, snb_uncore_init),	/* Sandy Bridge */
-	X86_UNCORE_MODEL_MATCH(58, ivb_uncore_init),	/* Ivy Bridge */
-	X86_UNCORE_MODEL_MATCH(60, hsw_uncore_init),	/* Haswell */
-	X86_UNCORE_MODEL_MATCH(69, hsw_uncore_init),	/* Haswell Celeron */
-	X86_UNCORE_MODEL_MATCH(70, hsw_uncore_init),	/* Haswell */
-	X86_UNCORE_MODEL_MATCH(61, bdw_uncore_init),	/* Broadwell */
-	X86_UNCORE_MODEL_MATCH(71, bdw_uncore_init),	/* Broadwell */
-	X86_UNCORE_MODEL_MATCH(45, snbep_uncore_init),	/* Sandy Bridge-EP */
-	X86_UNCORE_MODEL_MATCH(46, nhmex_uncore_init),	/* Nehalem-EX */
-	X86_UNCORE_MODEL_MATCH(47, nhmex_uncore_init),	/* Westmere-EX aka. Xeon E7 */
-	X86_UNCORE_MODEL_MATCH(62, ivbep_uncore_init),	/* Ivy Bridge-EP */
-	X86_UNCORE_MODEL_MATCH(63, hswep_uncore_init),	/* Haswell-EP */
-	X86_UNCORE_MODEL_MATCH(79, bdx_uncore_init),	/* BDX-EP */
-	X86_UNCORE_MODEL_MATCH(86, bdx_uncore_init),	/* BDX-DE */
-	X86_UNCORE_MODEL_MATCH(87, knl_uncore_init),	/* Knights Landing */
-	X86_UNCORE_MODEL_MATCH(94, skl_uncore_init),	/* SkyLake */
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EP,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE,	  snb_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE,	  ivb_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, bdw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, bdw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X,  snbep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EX,	  nhmex_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EX,	  nhmex_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X,	  ivbep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_X,	  hswep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  bdx_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, bdx_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL,	  knl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 79766b9a3580..d6063e438158 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -15,7 +15,11 @@
 #define UNCORE_PMC_IDX_FIXED		UNCORE_PMC_IDX_MAX_GENERIC
 #define UNCORE_PMC_IDX_MAX		(UNCORE_PMC_IDX_FIXED + 1)
 
+#define UNCORE_PCI_DEV_FULL_DATA(dev, func, type, idx)	\
+		((dev << 24) | (func << 16) | (type << 8) | idx)
 #define UNCORE_PCI_DEV_DATA(type, idx)	((type << 8) | idx)
+#define UNCORE_PCI_DEV_DEV(data)	((data >> 24) & 0xff)
+#define UNCORE_PCI_DEV_FUNC(data)	((data >> 16) & 0xff)
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
@@ -360,6 +364,7 @@ int bdw_uncore_pci_init(void);
 int skl_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
+void skl_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
 
 /* perf_event_intel_uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 96531d2b843f..97a69dbba649 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -1,4 +1,4 @@
-/* Nehalem/SandBridge/Haswell uncore support */
+/* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */
 #include "uncore.h"
 
 /* Uncore IMC PCI IDs */
@@ -9,6 +9,7 @@
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
 #define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
 #define PCI_DEVICE_ID_INTEL_SKL_IMC	0x191f
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x190c
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -64,6 +65,10 @@
 #define NHM_UNC_PERFEVTSEL0                     0x3c0
 #define NHM_UNC_UNCORE_PMC0                     0x3b0
 
+/* SKL uncore global control */
+#define SKL_UNC_PERF_GLOBAL_CTL			0xe01
+#define SKL_UNC_GLOBAL_CTL_CORE_ALL		((1 << 5) - 1)
+
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -179,6 +184,60 @@ void snb_uncore_cpu_init(void)
 		snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 }
 
+static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0) {
+		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+			SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
+	}
+}
+
+static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0)
+		wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static struct intel_uncore_ops skl_uncore_msr_ops = {
+	.init_box	= skl_uncore_msr_init_box,
+	.exit_box	= skl_uncore_msr_exit_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= snb_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type skl_uncore_cbox = {
+	.name		= "cbox",
+	.num_counters   = 4,
+	.num_boxes	= 5,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
+	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
+	.fixed_ctr	= SNB_UNC_FIXED_CTR,
+	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
+	.single_fixed	= 1,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
+	.ops		= &skl_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+	.event_descs	= snb_uncore_events,
+};
+
+static struct intel_uncore_type *skl_msr_uncores[] = {
+	&skl_uncore_cbox,
+	&snb_uncore_arb,
+	NULL,
+};
+
+void skl_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = skl_msr_uncores;
+	if (skl_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		skl_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
 enum {
 	SNB_PCI_UNCORE_IMC,
 };
@@ -544,6 +603,11 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+
 	{ /* end: all zeroes */ },
 };
 
@@ -587,6 +651,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
 	IMC_DEV(SKL_IMC, &skl_uncore_pci_driver),    /* 6th Gen Core */
+	IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core U */
 	{  /* end marker */ }
 };
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 874e8bd64d1d..824e54086e07 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2164,21 +2164,101 @@ static struct intel_uncore_type *knl_pci_uncores[] = {
 */
 
 static const struct pci_device_id knl_uncore_pci_ids[] = {
-	{ /* MC UClk */
+	{ /* MC0 UClk */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(10, 0, KNL_PCI_UNCORE_MC_UCLK, 0),
 	},
-	{ /* MC DClk Channel */
+	{ /* MC1 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(11, 0, KNL_PCI_UNCORE_MC_UCLK, 1),
+	},
+	{ /* MC0 DClk CH 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 2, KNL_PCI_UNCORE_MC_DCLK, 0),
+	},
+	{ /* MC0 DClk CH 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 3, KNL_PCI_UNCORE_MC_DCLK, 1),
+	},
+	{ /* MC0 DClk CH 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(8, 4, KNL_PCI_UNCORE_MC_DCLK, 2),
+	},
+	{ /* MC1 DClk CH 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 2, KNL_PCI_UNCORE_MC_DCLK, 3),
+	},
+	{ /* MC1 DClk CH 1 */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 3, KNL_PCI_UNCORE_MC_DCLK, 4),
+	},
+	{ /* MC1 DClk CH 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(9, 4, KNL_PCI_UNCORE_MC_DCLK, 5),
+	},
+	{ /* EDC0 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(15, 0, KNL_PCI_UNCORE_EDC_UCLK, 0),
+	},
+	{ /* EDC1 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(16, 0, KNL_PCI_UNCORE_EDC_UCLK, 1),
+	},
+	{ /* EDC2 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(17, 0, KNL_PCI_UNCORE_EDC_UCLK, 2),
+	},
+	{ /* EDC3 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, KNL_PCI_UNCORE_EDC_UCLK, 3),
 	},
-	{ /* EDC UClk */
+	{ /* EDC4 UClk */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(19, 0, KNL_PCI_UNCORE_EDC_UCLK, 4),
+	},
+	{ /* EDC5 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(20, 0, KNL_PCI_UNCORE_EDC_UCLK, 5),
+	},
+	{ /* EDC6 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 0, KNL_PCI_UNCORE_EDC_UCLK, 6),
+	},
+	{ /* EDC7 UClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(22, 0, KNL_PCI_UNCORE_EDC_UCLK, 7),
+	},
+	{ /* EDC0 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(24, 2, KNL_PCI_UNCORE_EDC_ECLK, 0),
+	},
+	{ /* EDC1 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(25, 2, KNL_PCI_UNCORE_EDC_ECLK, 1),
+	},
+	{ /* EDC2 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(26, 2, KNL_PCI_UNCORE_EDC_ECLK, 2),
+	},
+	{ /* EDC3 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(27, 2, KNL_PCI_UNCORE_EDC_ECLK, 3),
+	},
+	{ /* EDC4 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(28, 2, KNL_PCI_UNCORE_EDC_ECLK, 4),
+	},
+	{ /* EDC5 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(29, 2, KNL_PCI_UNCORE_EDC_ECLK, 5),
+	},
+	{ /* EDC6 EClk */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(30, 2, KNL_PCI_UNCORE_EDC_ECLK, 6),
 	},
-	{ /* EDC EClk */
+	{ /* EDC7 EClk */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835),
-		.driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(31, 2, KNL_PCI_UNCORE_EDC_ECLK, 7),
 	},
 	{ /* M2PCIe */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817),
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 85ef3c2e80e0..50b3a056f96b 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -1,4 +1,5 @@
 #include <linux/perf_event.h>
+#include <asm/intel-family.h>
 
 enum perf_msr_id {
 	PERF_MSR_TSC			= 0,
@@ -34,39 +35,43 @@ static bool test_intel(int idx)
 		return false;
 
 	switch (boot_cpu_data.x86_model) {
-	case 30: /* 45nm Nehalem    */
-	case 26: /* 45nm Nehalem-EP */
-	case 46: /* 45nm Nehalem-EX */
-
-	case 37: /* 32nm Westmere    */
-	case 44: /* 32nm Westmere-EP */
-	case 47: /* 32nm Westmere-EX */
-
-	case 42: /* 32nm SandyBridge         */
-	case 45: /* 32nm SandyBridge-E/EN/EP */
-
-	case 58: /* 22nm IvyBridge       */
-	case 62: /* 22nm IvyBridge-EP/EX */
-
-	case 60: /* 22nm Haswell Core */
-	case 63: /* 22nm Haswell Server */
-	case 69: /* 22nm Haswell ULT */
-	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
-
-	case 61: /* 14nm Broadwell Core-M */
-	case 86: /* 14nm Broadwell Xeon D */
-	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
-	case 79: /* 14nm Broadwell Server */
-
-	case 55: /* 22nm Atom "Silvermont"                */
-	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
-	case 76: /* 14nm Atom "Airmont"                   */
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_EP:
+	case INTEL_FAM6_NEHALEM_EX:
+
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_WESTMERE2:
+	case INTEL_FAM6_WESTMERE_EP:
+	case INTEL_FAM6_WESTMERE_EX:
+
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_SANDYBRIDGE_X:
+
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE_X:
+
+	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_X:
+	case INTEL_FAM6_HASWELL_ULT:
+	case INTEL_FAM6_HASWELL_GT3E:
+
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_XEON_D:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_X:
+
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_AIRMONT:
 		if (idx == PERF_MSR_SMI)
 			return true;
 		break;
 
-	case 78: /* 14nm Skylake Mobile */
-	case 94: /* 14nm Skylake Desktop */
+	case INTEL_FAM6_SKYLAKE_MOBILE:
+	case INTEL_FAM6_SKYLAKE_DESKTOP:
+	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_KABYLAKE_MOBILE:
+	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8bd764df815d..8c4a47706296 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -668,6 +668,14 @@ static struct perf_pmu_events_attr event_attr_##v = {			\
 	.event_str	= str,						\
 };
 
+#define EVENT_ATTR_STR_HT(_name, v, noht, ht)				\
+static struct perf_pmu_events_ht_attr event_attr_##v = {		\
+	.attr		= __ATTR(_name, 0444, events_ht_sysfs_show, NULL),\
+	.id		= 0,						\
+	.event_str_noht	= noht,						\
+	.event_str_ht	= ht,						\
+}
+
 extern struct x86_pmu x86_pmu __read_mostly;
 
 static inline bool x86_pmu_has_lbr_callstack(void)
@@ -803,6 +811,8 @@ struct attribute **merge_attr(struct attribute **a, struct attribute **b);
 
 ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page);
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page);
 
 #ifdef CONFIG_CPU_SUP_AMD
 
@@ -892,6 +902,8 @@ void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
 
+u64 lbr_from_signext_quirk_wr(u64 val);
+
 void intel_pmu_lbr_reset(void);
 
 void intel_pmu_lbr_enable(struct perf_event *event);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 7f991bd5031b..e346572841a0 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -129,6 +129,14 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 extern unsigned int __max_logical_packages;
 #define topology_max_packages()			(__max_logical_packages)
+
+extern int __max_smt_threads;
+
+static inline int topology_max_smt_threads(void)
+{
+	return __max_smt_threads;
+}
+
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
 extern int topology_phys_to_logical_pkg(unsigned int pkg);
 #else
@@ -136,6 +144,7 @@ extern int topology_phys_to_logical_pkg(unsigned int pkg);
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
+static inline int topology_max_smt_threads(void) { return 1; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fafe8b923cac..2ed0ec1353f8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -105,6 +105,9 @@ static unsigned int max_physical_pkg_id __read_mostly;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 
+/* Maximum number of SMT threads on any online core */
+int __max_smt_threads __read_mostly;
+
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	unsigned long flags;
@@ -493,7 +496,7 @@ void set_cpu_sibling_map(int cpu)
 	bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct cpuinfo_x86 *o;
-	int i;
+	int i, threads;
 
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
@@ -550,6 +553,10 @@ void set_cpu_sibling_map(int cpu)
 		if (match_die(c, o) && !topology_same_node(c, o))
 			primarily_use_numa_for_topology();
 	}
+
+	threads = cpumask_weight(topology_sibling_cpumask(cpu));
+	if (threads > __max_smt_threads)
+		__max_smt_threads = threads;
 }
 
 /* maps the cpu to the sched domain representing multi-core */
@@ -1441,6 +1448,21 @@ __init void prefill_possible_map(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
+/* Recompute SMT state for all CPUs on offline */
+static void recompute_smt_state(void)
+{
+	int max_threads, cpu;
+
+	max_threads = 0;
+	for_each_online_cpu (cpu) {
+		int threads = cpumask_weight(topology_sibling_cpumask(cpu));
+
+		if (threads > max_threads)
+			max_threads = threads;
+	}
+	__max_smt_threads = max_threads;
+}
+
 static void remove_siblinginfo(int cpu)
 {
 	int sibling;
@@ -1465,6 +1487,7 @@ static void remove_siblinginfo(int cpu)
 	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
+	recompute_smt_state();
 }
 
 static void remove_cpu_from_maps(int cpu)