From d6d55f0b9d900673548515614b56ab55aa2c51f8 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Thu, 29 May 2014 17:26:50 +0200 Subject: [PATCH 1/4] perf/x86/amd: AMD support for bp_len > HW_BREAKPOINT_LEN_8 Implement hardware breakpoint address mask for AMD Family 16h and above processors. CPUID feature bit indicates hardware support for DRn_ADDR_MASK MSRs. These masks further qualify DRn/DR7 hardware breakpoint addresses to allow matching of larger addresses ranges. Valuable advice and pseudo code from Oleg Nesterov Signed-off-by: Jacob Shin Signed-off-by: Suravee Suthikulpanit Acked-by: Jiri Olsa Reviewed-by: Oleg Nesterov Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: xiakaixu Signed-off-by: Frederic Weisbecker --- arch/x86/include/asm/cpufeature.h | 2 ++ arch/x86/include/asm/debugreg.h | 5 +++++ arch/x86/include/asm/hw_breakpoint.h | 1 + arch/x86/include/uapi/asm/msr-index.h | 4 ++++ arch/x86/kernel/cpu/amd.c | 19 +++++++++++++++++++ arch/x86/kernel/hw_breakpoint.c | 20 ++++++++++++++++---- 6 files changed, 47 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 0bb1335313b2..53966d65591e 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 */ /* @@ -383,6 +384,7 @@ 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 8f02f6990759..b1fb4fae03d3 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -212,6 +212,10 @@ /* 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 813d29d00a17..abe4ec760db3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -870,3 +870,22 @@ 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..b5cb0c59ea87 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; } @@ -161,6 +163,8 @@ void arch_uninstall_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(0, i); } static int get_hbp_len(u8 hbp_len) @@ -277,6 +281,8 @@ 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 +299,17 @@ 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 +324,11 @@ 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 +342,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) break; #endif default: - return ret; + WARN_ON_ONCE(1); } /* From 3741eb9f8c3be3ec59583881c1f49980dad844e0 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Thu, 29 May 2014 17:26:51 +0200 Subject: [PATCH 2/4] perf tools: allow user to specify hardware breakpoint bp_len Currently bp_len is given a default value of 4. Allow user to override it: $ perf stat -e mem:0x1000/8 ^ bp_len If no value is given, it will default to 4 as it did before. Signed-off-by: Jacob Shin Signed-off-by: Suravee Suthikulpanit Acked-by: Jiri Olsa Reviewed-by: Oleg Nesterov Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: xiakaixu Signed-off-by: Frederic Weisbecker --- tools/perf/Documentation/perf-record.txt | 7 +++++-- tools/perf/util/parse-events.c | 21 ++++++++++--------- tools/perf/util/parse-events.h | 2 +- tools/perf/util/parse-events.l | 1 + tools/perf/util/parse-events.y | 26 ++++++++++++++++++++++-- 5 files changed, 42 insertions(+), 15 deletions(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index af9a54ece024..81a20f21a3e6 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -33,12 +33,15 @@ OPTIONS - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. - - 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=:: Event filter. diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c659a3ca1283..efa1ff4cca63 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; @@ -1364,7 +1365,7 @@ void print_events(const char *event_glob, bool name_only) printf("\n"); printf(" %-50s [%s]\n", - "mem:[:access]", + "mem:[/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 db2cf78ff0f3..a19fbeb80943 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -104,7 +104,7 @@ 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 { {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; } From ec32398c231a019d39017afee490728ab3b60b92 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Thu, 29 May 2014 17:26:52 +0200 Subject: [PATCH 3/4] perf tools: add hardware breakpoint bp_len test cases Signed-off-by: Jacob Shin Signed-off-by: Suravee Suthikulpanit Acked-by: Jiri Olsa Reviewed-by: Oleg Nesterov Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: xiakaixu Signed-off-by: Frederic Weisbecker --- tools/perf/tests/parse-events.c | 58 +++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7f2f51f93619..4169f460efa1 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", From 36748b9518a2437beffe861b47dff6d12b736b3f Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Thu, 29 May 2014 17:26:53 +0200 Subject: [PATCH 4/4] perf/x86: Remove get_hbp_len and replace with bp_len Clean up the logic for determining the breakpoint length Signed-off-by: Jacob Shin Signed-off-by: Suravee Suthikulpanit Acked-by: Jiri Olsa Reviewed-by: Oleg Nesterov Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: xiakaixu Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/hw_breakpoint.c | 25 +------------------------ 1 file changed, 1 insertion(+), 24 deletions(-) diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index b5cb0c59ea87..7114ba220fd4 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -167,29 +167,6 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) set_dr_addr_mask(0, i); } -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; -} - /* * Check for virtual address in kernel space. */ @@ -200,7 +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); }