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

Pull perf fixes from Thomas Gleixner:
 "A couple of small fixes to x86 perf drivers:

   - Measure L2 for HW_CACHE* events on AMD

   - Fix the address filter handling in the intel/pt driver

   - Handle the BTS disabling at the proper place"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/amd: Make HW_CACHE_REFERENCES and HW_CACHE_MISSES measure L2
  perf/x86/intel/pt: Do validate the size of a kernel address filter
  perf/x86/intel/pt: Fix kernel address filter's offset validation
  perf/x86/intel/pt: Fix an off-by-one in address filter configuration
  perf/x86/intel: Don't disable "intel_bts" around "intel" event batching

Author: torvalds

arch/x86/events/amd/core.c

@@ -119,8 +119,8 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
   [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
   [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x0080,
-  [PERF_COUNT_HW_CACHE_MISSES]			= 0x0081,
+  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x077d,
+  [PERF_COUNT_HW_CACHE_MISSES]			= 0x077e,
   [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]		= 0x00c2,
   [PERF_COUNT_HW_BRANCH_MISSES]			= 0x00c3,
   [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */

arch/x86/events/intel/core.c

@@ -1730,9 +1730,11 @@ static __initconst const u64 knl_hw_cache_extra_regs
  * disabled state if called consecutively.
  *
  * During consecutive calls, the same disable value will be written to related
- * registers, so the PMU state remains unchanged. hw.state in
- * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
- * calls.
+ * registers, so the PMU state remains unchanged.
+ *
+ * intel_bts events don't coexist with intel PMU's BTS events because of
+ * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
+ * disabled around intel PMU's event batching etc, only inside the PMI handler.
  */
 static void __intel_pmu_disable_all(void)
 {
@@ -1742,8 +1744,6 @@ static void __intel_pmu_disable_all(void)
 
 	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
-	else
-		intel_bts_disable_local();
 
 	intel_pmu_pebs_disable_all();
 }
@@ -1771,8 +1771,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 			return;
 
 		intel_pmu_enable_bts(event->hw.config);
-	} else
-		intel_bts_enable_local();
+	}
 }
 
 static void intel_pmu_enable_all(int added)
@@ -2073,6 +2072,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	 */
 	if (!x86_pmu.late_ack)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
+	intel_bts_disable_local();
 	__intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	handled += intel_bts_interrupt();
@@ -2172,6 +2172,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
 	if (cpuc->enabled)
 		__intel_pmu_enable_all(0, true);
+	intel_bts_enable_local();
 
 	/*
 	 * Only unmask the NMI after the overflow counters

arch/x86/events/intel/pt.c

@@ -1074,18 +1074,28 @@ static void pt_addr_filters_fini(struct perf_event *event)
 	event->hw.addr_filters = NULL;
 }
 
+static inline bool valid_kernel_ip(unsigned long ip)
+{
+	return virt_addr_valid(ip) && kernel_ip(ip);
+}
+
 static int pt_event_addr_filters_validate(struct list_head *filters)
 {
 	struct perf_addr_filter *filter;
 	int range = 0;
 
 	list_for_each_entry(filter, filters, entry) {
 		/* PT doesn't support single address triggers */
-		if (!filter->range)
+		if (!filter->range || !filter->size)
 			return -EOPNOTSUPP;
 
-		if (!filter->inode && !kernel_ip(filter->offset))
-			return -EINVAL;
+		if (!filter->inode) {
+			if (!valid_kernel_ip(filter->offset))
+				return -EINVAL;
+
+			if (!valid_kernel_ip(filter->offset + filter->size))
+				return -EINVAL;
+		}
 
 		if (++range > pt_cap_get(PT_CAP_num_address_ranges))
 			return -EOPNOTSUPP;
@@ -1111,7 +1121,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		} else {
 			/* apply the offset */
 			msr_a = filter->offset + offs[range];
-			msr_b = filter->size + msr_a;
+			msr_b = filter->size + msr_a - 1;
 		}
 
 		filters->filter[range].msr_a  = msr_a;

arch/x86/kvm/pmu_amd.c

@@ -23,8 +23,8 @@
 static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
 	[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
 	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
-	[2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
-	[3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+	[2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
+	[3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
 	[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
 	[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },