Merge branch 'perf/hw_breakpoints' into perf/core

The new hw_breakpoint bits are now ready for v3.20, merge them
into the main branch, to avoid conflicts.

Conflicts:
	tools/perf/Documentation/perf-record.txt

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 148 insertions, 43 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aede2c347bde..90a54851aedc 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -174,6 +174,7 @@
 #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_BPEXT	(6*32+26) /* data breakpoint extension */
 #define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
 
 /*
@@ -388,6 +389,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
 #define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
 #define cpu_has_topoext		boot_cpu_has(X86_FEATURE_TOPOEXT)
+#define cpu_has_bpext		boot_cpu_has(X86_FEATURE_BPEXT)
 
 #if __GNUC__ >= 4
 extern void warn_pre_alternatives(void);
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 61fd18b83b6c..12cb66f6d3a5 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -114,5 +114,10 @@ static inline void debug_stack_usage_inc(void) { }
 static inline void debug_stack_usage_dec(void) { }
 #endif /* X86_64 */
 
+#ifdef CONFIG_CPU_SUP_AMD
+extern void set_dr_addr_mask(unsigned long mask, int dr);
+#else
+static inline void set_dr_addr_mask(unsigned long mask, int dr) { }
+#endif
 
 #endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index ef1c4d2d41ec..6c98be864a75 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -12,6 +12,7 @@
  */
 struct arch_hw_breakpoint {
 	unsigned long	address;
+	unsigned long	mask;
 	u8		len;
 	u8		type;
 };
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c8aa65d56027..d979e5abae55 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -251,6 +251,10 @@
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
+#define MSR_F16H_DR1_ADDR_MASK		0xc0011019
+#define MSR_F16H_DR2_ADDR_MASK		0xc001101a
+#define MSR_F16H_DR3_ADDR_MASK		0xc001101b
+#define MSR_F16H_DR0_ADDR_MASK		0xc0011027
 
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL		0xc0010200
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 15c5df92f74e..a220239cea65 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -869,3 +869,22 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 
 	return false;
 }
+
+void set_dr_addr_mask(unsigned long mask, int dr)
+{
+	if (!cpu_has_bpext)
+		return;
+
+	switch (dr) {
+	case 0:
+		wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
+		break;
+	case 1:
+	case 2:
+	case 3:
+		wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
+		break;
+	default:
+		break;
+	}
+}
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 3d5fb509bdeb..7114ba220fd4 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -126,6 +126,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	*dr7 |= encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
+	if (info->mask)
+		set_dr_addr_mask(info->mask, i);
 
 	return 0;
 }
@@ -161,29 +163,8 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	*dr7 &= ~__encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
-}
-
-static int get_hbp_len(u8 hbp_len)
-{
-	unsigned int len_in_bytes = 0;
-
-	switch (hbp_len) {
-	case X86_BREAKPOINT_LEN_1:
-		len_in_bytes = 1;
-		break;
-	case X86_BREAKPOINT_LEN_2:
-		len_in_bytes = 2;
-		break;
-	case X86_BREAKPOINT_LEN_4:
-		len_in_bytes = 4;
-		break;
-#ifdef CONFIG_X86_64
-	case X86_BREAKPOINT_LEN_8:
-		len_in_bytes = 8;
-		break;
-#endif
-	}
-	return len_in_bytes;
+	if (info->mask)
+		set_dr_addr_mask(0, i);
 }
 
 /*
@@ -196,7 +177,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
 	va = info->address;
-	len = get_hbp_len(info->len);
+	len = bp->attr.bp_len;
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -277,6 +258,8 @@ static int arch_build_bp_info(struct perf_event *bp)
 	}
 
 	/* Len */
+	info->mask = 0;
+
 	switch (bp->attr.bp_len) {
 	case HW_BREAKPOINT_LEN_1:
 		info->len = X86_BREAKPOINT_LEN_1;
@@ -293,11 +276,17 @@ static int arch_build_bp_info(struct perf_event *bp)
 		break;
 #endif
 	default:
-		return -EINVAL;
+		if (!is_power_of_2(bp->attr.bp_len))
+			return -EINVAL;
+		if (!cpu_has_bpext)
+			return -EOPNOTSUPP;
+		info->mask = bp->attr.bp_len - 1;
+		info->len = X86_BREAKPOINT_LEN_1;
 	}
 
 	return 0;
 }
+
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
@@ -312,11 +301,11 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	if (ret)
 		return ret;
 
-	ret = -EINVAL;
-
 	switch (info->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
+		if (info->mask)
+			align = info->mask;
 		break;
 	case X86_BREAKPOINT_LEN_2:
 		align = 1;
@@ -330,7 +319,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		break;
 #endif
 	default:
-		return ret;
+		WARN_ON_ONCE(1);
 	}
 
 	/*
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 7d8df2e5edd8..31e977459c51 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -45,12 +45,15 @@ OPTIONS
           param1 and param2 are defined as formats for the PMU in:
           /sys/bus/event_sources/devices/<pmu>/format/*
 
-        - a hardware breakpoint event in the form of '\mem:addr[:access]'
+        - a hardware breakpoint event in the form of '\mem:addr[/len][:access]'
           where addr is the address in memory you want to break in.
           Access is the memory access type (read, write, execute) it can
-          be passed as follows: '\mem:addr[:[r][w][x]]'.
+          be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range,
+          number of bytes from specified addr, which the breakpoint will cover.
           If you want to profile read-write accesses in 0x1000, just set
           'mem:0x1000:rw'.
+          If you want to profile write accesses in [0x1000~1008), just set
+          'mem:0x1000/8:w'.
 
 --filter=<filter>::
         Event filter.
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index d188e20d958f..1cdab0ce00e2 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1145,6 +1145,49 @@ static int test__pinned_group(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_breakpoint_len(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 ==
+					evsel->attr.bp_len);
+
+	return 0;
+}
+
+static int test__checkevent_breakpoint_len_w(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W ==
+					 evsel->attr.bp_type);
+	TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 ==
+					evsel->attr.bp_len);
+
+	return 0;
+}
+
+static int
+test__checkevent_breakpoint_len_rw_modifier(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+
+	return test__checkevent_breakpoint_rw(evlist);
+}
+
 static int count_tracepoints(void)
 {
 	char events_path[PATH_MAX];
@@ -1420,6 +1463,21 @@ static struct evlist_test test__events[] = {
 		.check = test__pinned_group,
 		.id    = 41,
 	},
+	{
+		.name  = "mem:0/1",
+		.check = test__checkevent_breakpoint_len,
+		.id    = 42,
+	},
+	{
+		.name  = "mem:0/2:w",
+		.check = test__checkevent_breakpoint_len_w,
+		.id    = 43,
+	},
+	{
+		.name  = "mem:0/4:rw:u",
+		.check = test__checkevent_breakpoint_len_rw_modifier,
+		.id    = 44
+	},
 #if defined(__s390x__)
 	{
 		.name  = "kvm-s390:kvm_s390_create_vm",
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f36b80ecaf52..7f8ec6ce2823 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -526,7 +526,7 @@ do {					\
 }
 
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
-				void *ptr, char *type)
+				void *ptr, char *type, u64 len)
 {
 	struct perf_event_attr attr;
 
@@ -536,14 +536,15 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 	if (parse_breakpoint_type(type, &attr))
 		return -EINVAL;
 
-	/*
-	 * We should find a nice way to override the access length
-	 * Provide some defaults for now
-	 */
-	if (attr.bp_type == HW_BREAKPOINT_X)
-		attr.bp_len = sizeof(long);
-	else
-		attr.bp_len = HW_BREAKPOINT_LEN_4;
+	/* Provide some defaults if len is not specified */
+	if (!len) {
+		if (attr.bp_type == HW_BREAKPOINT_X)
+			len = sizeof(long);
+		else
+			len = HW_BREAKPOINT_LEN_4;
+	}
+
+	attr.bp_len = len;
 
 	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.sample_period = 1;
@@ -1366,7 +1367,7 @@ void print_events(const char *event_glob, bool name_only)
 		printf("\n");
 
 		printf("  %-50s [%s]\n",
-		       "mem:<addr>[:access]",
+		       "mem:<addr>[/len][:access]",
 			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
 		printf("\n");
 	}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index ca226cef8460..ff6e1fa4111e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -105,7 +105,7 @@ int parse_events_add_numeric(struct list_head *list, int *idx,
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
-				void *ptr, char *type);
+				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct list_head *list, int *idx,
 			 char *pmu , struct list_head *head_config);
 enum perf_pmu_event_symbol_type
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 906630bbf8eb..94eacb6c1ef7 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -159,6 +159,7 @@ branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
 <mem>{
 {modifier_bp}		{ return str(yyscanner, PE_MODIFIER_BP); }
 :			{ return ':'; }
+"/"			{ return '/'; }
 {num_dec}		{ return value(yyscanner, 10); }
 {num_hex}		{ return value(yyscanner, 16); }
 	/*
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 93c4c9fbc922..72def077dbbf 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -326,6 +326,28 @@ PE_NAME_CACHE_TYPE
 }
 
 event_legacy_mem:
+PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+					     (void *) $2, $6, $4));
+	$$ = list;
+}
+|
+PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+					     (void *) $2, NULL, $4));
+	$$ = list;
+}
+|
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
 	struct parse_events_evlist *data = _data;
@@ -333,7 +355,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
-					     (void *) $2, $4));
+					     (void *) $2, $4, 0));
 	$$ = list;
 }
 |
@@ -344,7 +366,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
-					     (void *) $2, NULL));
+					     (void *) $2, NULL, 0));
 	$$ = list;
 }