CoreSight

coresight@lists.linaro.org

9 participants
2379 discussions

[PATCH v5] perf: Support for Arm A32/T32 instruction sets in CoreSight trace

by Robert Walker

This patch adds support for generating instruction samples from trace of AArch32 programs using the A32 and T32 instruction sets. T32 has variable 2 or 4 byte instruction size, so the conversion between addresses and instruction counts requires extra information from the trace decoder, requiring version 0.10.0 of OpenCSD. A check for the OpenCSD library version has been added to the feature check for OpenCSD. Signed-off-by: Robert Walker <robert.walker(a)arm.com> --- Changes since v4: Formatting of comment block tools/build/feature/test-libopencsd.c | 8 +++ tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 29 ++++++++++ tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 10 ++++ tools/perf/util/cs-etm.c | 70 +++++++++++-------------- 4 files changed, 78 insertions(+), 39 deletions(-) diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c index 5ff1246..d68eb4f 100644 --- a/tools/build/feature/test-libopencsd.c +++ b/tools/build/feature/test-libopencsd.c @@ -1,6 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <opencsd/c_api/opencsd_c_api.h> +/* + * Check OpenCSD library version is sufficient to provide required features + */ +#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0)) +#if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER) +#error "OpenCSD >= 0.10.0 is required" +#endif + int main(void) { (void)ocsd_get_version(); diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 938def6..5efb616 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -263,9 +263,12 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder) decoder->tail = 0; decoder->packet_count = 0; for (i = 0; i < MAX_BUFFER; i++) { + decoder->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN; decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[i].instr_count = 0; decoder->packet_buffer[i].last_instr_taken_branch = false; + decoder->packet_buffer[i].last_instr_size = 0; decoder->packet_buffer[i].exc = false; decoder->packet_buffer[i].exc_ret = false; decoder->packet_buffer[i].cpu = INT_MIN; @@ -294,11 +297,15 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, decoder->packet_count++; decoder->packet_buffer[et].sample_type = sample_type; + decoder->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN; decoder->packet_buffer[et].exc = false; decoder->packet_buffer[et].exc_ret = false; decoder->packet_buffer[et].cpu = *((int *)inode->priv); decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[et].instr_count = 0; + decoder->packet_buffer[et].last_instr_taken_branch = false; + decoder->packet_buffer[et].last_instr_size = 0; if (decoder->packet_count == MAX_BUFFER - 1) return OCSD_RESP_WAIT; @@ -321,8 +328,28 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, packet = &decoder->packet_buffer[decoder->tail]; + switch (elem->isa) { + case ocsd_isa_aarch64: + packet->isa = CS_ETM_ISA_A64; + break; + case ocsd_isa_arm: + packet->isa = CS_ETM_ISA_A32; + break; + case ocsd_isa_thumb2: + packet->isa = CS_ETM_ISA_T32; + break; + case ocsd_isa_tee: + case ocsd_isa_jazelle: + case ocsd_isa_custom: + case ocsd_isa_unknown: + default: + packet->isa = CS_ETM_ISA_UNKNOWN; + } + packet->start_addr = elem->st_addr; packet->end_addr = elem->en_addr; + packet->instr_count = elem->num_instr_range; + switch (elem->last_i_type) { case OCSD_INSTR_BR: case OCSD_INSTR_BR_INDIRECT: @@ -336,6 +363,8 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, break; } + packet->last_instr_size = elem->last_instr_sz; + return ret; } diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 612b575..9351bd1 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -28,11 +28,21 @@ enum cs_etm_sample_type { CS_ETM_TRACE_ON = 1 << 1, }; +enum cs_etm_isa { + CS_ETM_ISA_UNKNOWN, + CS_ETM_ISA_A64, + CS_ETM_ISA_A32, + CS_ETM_ISA_T32, +}; + struct cs_etm_packet { enum cs_etm_sample_type sample_type; + enum cs_etm_isa isa; u64 start_addr; u64 end_addr; + u32 instr_count; u8 last_instr_taken_branch; + u8 last_instr_size; u8 exc; u8 exc_ret; int cpu; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 73430b7..48ad217 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -31,14 +31,6 @@ #define MAX_TIMESTAMP (~0ULL) -/* - * A64 instructions are always 4 bytes - * - * Only A64 is supported, so can use this constant for converting between - * addresses and instruction counts, calculting offsets etc - */ -#define A64_INSTR_SIZE 4 - struct cs_etm_auxtrace { struct auxtrace auxtrace; struct auxtrace_queues queues; @@ -510,21 +502,17 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) etmq->last_branch_rb->nr = 0; } -static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) -{ - /* Returns 0 for the CS_ETM_TRACE_ON packet */ - if (packet->sample_type == CS_ETM_TRACE_ON) - return 0; +static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq, + u64 addr) { + u8 instrBytes[2]; + cs_etm__mem_access(etmq, addr, ARRAY_SIZE(instrBytes), instrBytes); /* - * The packet records the execution range with an exclusive end address - * - * A64 instructions are constant size, so the last executed - * instruction is A64_INSTR_SIZE before the end address - * Will need to do instruction level decode for T32 instructions as - * they can be variable size (not yet supported). + * T32 instruction size is indicated by bits[15:11] of the first + * 16-bit word of the instruction: 0b11101, 0b11110 and 0b11111 + * denote a 32-bit instruction. */ - return packet->end_addr - A64_INSTR_SIZE; + return ((instrBytes[1] & 0xF8) >= 0xE8) ? 4 : 2; } static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) @@ -536,27 +524,32 @@ static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) return packet->start_addr; } -static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet) +static inline +u64 cs_etm__last_executed_instr(const struct cs_etm_packet *packet) { - /* - * Only A64 instructions are currently supported, so can get - * instruction count by dividing. - * Will need to do instruction level decode for T32 instructions as - * they can be variable size (not yet supported). - */ - return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE; + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + return packet->end_addr - packet->last_instr_size; } -static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet, +static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq, + const struct cs_etm_packet *packet, u64 offset) { - /* - * Only A64 instructions are currently supported, so can get - * instruction address by muliplying. - * Will need to do instruction level decode for T32 instructions as - * they can be variable size (not yet supported). - */ - return packet->start_addr + offset * A64_INSTR_SIZE; + if (packet->isa == CS_ETM_ISA_T32) { + u64 addr = packet->start_addr; + + while (offset > 0) { + addr += cs_etm__t32_instr_size(etmq, addr); + offset--; + } + return addr; + } + + /* Assume a 4 byte instruction size (A32/A64) */ + return packet->start_addr + offset * 4; } static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) @@ -888,9 +881,8 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; int ret; - u64 instrs_executed; + u64 instrs_executed = etmq->packet->instr_count; - instrs_executed = cs_etm__instr_count(etmq->packet); etmq->period_instructions += instrs_executed; /* @@ -920,7 +912,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) * executed, but PC has not advanced to next instruction) */ u64 offset = (instrs_executed - instrs_over - 1); - u64 addr = cs_etm__instr_addr(etmq->packet, offset); + u64 addr = cs_etm__instr_addr(etmq, etmq->packet, offset); ret = cs_etm__synth_instruction_sample( etmq, addr, etm->instructions_sample_period); -- 2.7.4

6 years, 7 months

Question: perf dso support for /proc/kallsyms

by leo.yan＠linaro.org

Hi all, Now I found that if use the command 'perf script' for Arm CoreSight trace data, it fails to parse kernel symbols if we don't specify kernel vmlinux file. So when we don't specify kernel symbol files then perf tool will roll back to use /proc/kallsyms for kernel symbols parsing, as result it will run into below flow: thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al); map__load(al.map); dso__data_read_offset(al.map->dso, machine, offset, buffer, size); `-> data_read_offset() I can observe the function data_read_offset() returns failure, this is caused by checking the offset sanity "if (offset > dso->data.file_size)" (I pasted the whole function code at below in case you want to get more context for it), but if perf use "/proc/kallsyms" to load kernel symbols, the variable 'dso->data.file_size' will be set to zero thus the sanity checking always thinks the offset is out of the file size bound. Now I still don't understand how the dso/map support "/proc/kallsyms" and have no idea to fix this issue, though I spent some time to look into it. Could you give some suggestion for this? Or even better if you have fixing for this, I am glad to test at my side. static ssize_t data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size) { if (data_file_size(dso, machine)) return -1; /* Check the offset sanity. */ if (offset > dso->data.file_size) return -1; if (offset + size < offset) return -1; return cached_read(dso, machine, offset, data, size); } Thanks, Leo Yan

6 years, 7 months

[PATCH v4] perf: Support for Arm A32/T32 instruction sets in CoreSight trace

by Robert Walker

This patch adds support for generating instruction samples from trace of AArch32 programs using the A32 and T32 instruction sets. T32 has variable 2 or 4 byte instruction size, so the conversion between addresses and instruction counts requires extra information from the trace decoder, requiring version 0.10.0 of OpenCSD. A check for the OpenCSD library version has been added to the feature check for OpenCSD. Signed-off-by: Robert Walker <robert.walker(a)arm.com> --- tools/build/feature/test-libopencsd.c | 8 +++ tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 29 ++++++++++ tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 10 ++++ tools/perf/util/cs-etm.c | 71 +++++++++++-------------- 4 files changed, 78 insertions(+), 40 deletions(-) diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c index 5ff1246..d68eb4f 100644 --- a/tools/build/feature/test-libopencsd.c +++ b/tools/build/feature/test-libopencsd.c @@ -1,6 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <opencsd/c_api/opencsd_c_api.h> +/* + * Check OpenCSD library version is sufficient to provide required features + */ +#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0)) +#if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER) +#error "OpenCSD >= 0.10.0 is required" +#endif + int main(void) { (void)ocsd_get_version(); diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 938def6..5efb616 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -263,9 +263,12 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder) decoder->tail = 0; decoder->packet_count = 0; for (i = 0; i < MAX_BUFFER; i++) { + decoder->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN; decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[i].instr_count = 0; decoder->packet_buffer[i].last_instr_taken_branch = false; + decoder->packet_buffer[i].last_instr_size = 0; decoder->packet_buffer[i].exc = false; decoder->packet_buffer[i].exc_ret = false; decoder->packet_buffer[i].cpu = INT_MIN; @@ -294,11 +297,15 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, decoder->packet_count++; decoder->packet_buffer[et].sample_type = sample_type; + decoder->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN; decoder->packet_buffer[et].exc = false; decoder->packet_buffer[et].exc_ret = false; decoder->packet_buffer[et].cpu = *((int *)inode->priv); decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[et].instr_count = 0; + decoder->packet_buffer[et].last_instr_taken_branch = false; + decoder->packet_buffer[et].last_instr_size = 0; if (decoder->packet_count == MAX_BUFFER - 1) return OCSD_RESP_WAIT; @@ -321,8 +328,28 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, packet = &decoder->packet_buffer[decoder->tail]; + switch (elem->isa) { + case ocsd_isa_aarch64: + packet->isa = CS_ETM_ISA_A64; + break; + case ocsd_isa_arm: + packet->isa = CS_ETM_ISA_A32; + break; + case ocsd_isa_thumb2: + packet->isa = CS_ETM_ISA_T32; + break; + case ocsd_isa_tee: + case ocsd_isa_jazelle: + case ocsd_isa_custom: + case ocsd_isa_unknown: + default: + packet->isa = CS_ETM_ISA_UNKNOWN; + } + packet->start_addr = elem->st_addr; packet->end_addr = elem->en_addr; + packet->instr_count = elem->num_instr_range; + switch (elem->last_i_type) { case OCSD_INSTR_BR: case OCSD_INSTR_BR_INDIRECT: @@ -336,6 +363,8 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, break; } + packet->last_instr_size = elem->last_instr_sz; + return ret; } diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 612b575..9351bd1 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -28,11 +28,21 @@ enum cs_etm_sample_type { CS_ETM_TRACE_ON = 1 << 1, }; +enum cs_etm_isa { + CS_ETM_ISA_UNKNOWN, + CS_ETM_ISA_A64, + CS_ETM_ISA_A32, + CS_ETM_ISA_T32, +}; + struct cs_etm_packet { enum cs_etm_sample_type sample_type; + enum cs_etm_isa isa; u64 start_addr; u64 end_addr; + u32 instr_count; u8 last_instr_taken_branch; + u8 last_instr_size; u8 exc; u8 exc_ret; int cpu; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 73430b7..cad133c 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -31,14 +31,6 @@ #define MAX_TIMESTAMP (~0ULL) -/* - * A64 instructions are always 4 bytes - * - * Only A64 is supported, so can use this constant for converting between - * addresses and instruction counts, calculting offsets etc - */ -#define A64_INSTR_SIZE 4 - struct cs_etm_auxtrace { struct auxtrace auxtrace; struct auxtrace_queues queues; @@ -510,21 +502,16 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) etmq->last_branch_rb->nr = 0; } -static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) -{ - /* Returns 0 for the CS_ETM_TRACE_ON packet */ - if (packet->sample_type == CS_ETM_TRACE_ON) - return 0; +static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq, + u64 addr) { + u8 instrBytes[2]; - /* - * The packet records the execution range with an exclusive end address - * - * A64 instructions are constant size, so the last executed - * instruction is A64_INSTR_SIZE before the end address - * Will need to do instruction level decode for T32 instructions as - * they can be variable size (not yet supported). + cs_etm__mem_access(etmq, addr, ARRAY_SIZE(instrBytes), instrBytes); + /* T32 instruction size is indicated by bits[15:11] of the first + * 16-bit word of the instruction: 0b11101, 0b11110 and 0b11111 + * denote a 32-bit instruction. */ - return packet->end_addr - A64_INSTR_SIZE; + return ((instrBytes[1] & 0xF8) >= 0xE8) ? 4 : 2; } static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) @@ -536,27 +523,32 @@ static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) return packet->start_addr; } -static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet) +static inline +u64 cs_etm__last_executed_instr(const struct cs_etm_packet *packet) { - /* - * Only A64 instructions are currently supported, so can get - * instruction count by dividing. - * Will need to do instruction level decode for T32 instructions as - * they can be variable size (not yet supported). - */ - return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE; + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + return packet->end_addr - packet->last_instr_size; } -static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet, +static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq, + const struct cs_etm_packet *packet, u64 offset) { - /* - * Only A64 instructions are currently supported, so can get - * instruction address by muliplying. - * Will need to do instruction level decode for T32 instructions as - * they can be variable size (not yet supported). - */ - return packet->start_addr + offset * A64_INSTR_SIZE; + if (packet->isa == CS_ETM_ISA_T32) { + u64 addr = packet->start_addr; + + while (offset > 0) { + addr += cs_etm__t32_instr_size(etmq, addr); + offset--; + } + return addr; + } + + /* Assume a 4 byte instruction size (A32/A64) */ + return packet->start_addr + offset * 4; } static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) @@ -888,9 +880,8 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; int ret; - u64 instrs_executed; + u64 instrs_executed = etmq->packet->instr_count; - instrs_executed = cs_etm__instr_count(etmq->packet); etmq->period_instructions += instrs_executed; /* @@ -920,7 +911,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) * executed, but PC has not advanced to next instruction) */ u64 offset = (instrs_executed - instrs_over - 1); - u64 addr = cs_etm__instr_addr(etmq->packet, offset); + u64 addr = cs_etm__instr_addr(etmq, etmq->packet, offset); ret = cs_etm__synth_instruction_sample( etmq, addr, etm->instructions_sample_period); -- 2.7.4

6 years, 7 months

[PATCH 0/3] coresight: Fix miscellaneous problems with CLAIM tags

by Mathieu Poirier

This set addresses 3 problems observed with the CLAIM tag feature. The first patch adds support for CLAIM tags to the ETB10 drivers. The second and third patch deal with releasing the tags on ETF and ETM3x devices. Review and testing would be appreciated. Regards, Mathieu Mathieu Poirier (3): coresight: etb10: Add support for CLAIM tag coresight: etf: Release CLAIM tag after disabling the HW coresight: etm3x: Release CLAIM tag when operated from perf drivers/hwtracing/coresight/coresight-etb10.c | 23 +++++++++++++++++------ drivers/hwtracing/coresight/coresight-etm3x.c | 2 ++ drivers/hwtracing/coresight/coresight-tmc-etf.c | 2 +- 3 files changed, 20 insertions(+), 7 deletions(-) -- 2.7.4

6 years, 7 months

[PATCH v2 0/3] perf tools: Add support for ETMv3/PTM1.1 decoding

by Mathieu Poirier

This set adds support for ETMv3/PTM1.1 trace decoding. The work has been tested on TC2 and ST-Microelectronics' mp157c-ev1 board and applies cleanly on 4.20-rc1. Although not related to trace decoding, the following patches [1][2][3] are required for ETMv3/PTM1.1 traces to be generated properly on a 4.20-rc1 mainline kernel. I am planning to post this on the kernel mailing list in a week. Regards, Mathieu Changes since V1: * Address a problem with protocol identification in [3/3] [1]. https://lore.kernel.org/patchwork/patch/1007184/ [2]. https://lore.kernel.org/patchwork/patch/1007185/ [3]. https://lore.kernel.org/patchwork/patch/1007186/ Mathieu Poirier (3): perf tools: Add configuration for ETMv3 trace protocol perf tools: Add support for ETMv3 trace decoding perf tools: Add support for PTMv1.1 decoding tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 31 +++++++++++ tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 9 +++ tools/perf/util/cs-etm.c | 73 ++++++++++++++++++++----- 3 files changed, 99 insertions(+), 14 deletions(-) -- 2.7.4

6 years, 7 months

Release of library version 0.10.0

by Mike Leach

Changes this release. Functional update: Add additional information about the last instruction to the generic output packet & update docs for updated output packet. Bugfix: typecast removed from OCSD_VER_NUM in ocsd_if_version.h to allow use in C pre-processor. Bugfix: ETMV4: Interworking ISA change between A32-T32 occasionally missed during instruction decode. -- Mike Leach Principal Engineer, ARM Ltd. Manchester Design Centre. UK

6 years, 8 months

[GIT PULL 00/24] perf/urgent improvements and fixes

by Arnaldo Carvalho de Melo

Hi Ingo, Please consider pulling, next ones should be concentrating just on bug fixes, been busy with some, so some were left in the queue, flushing them now. - Arnaldo Test results at the end of this message, as usual. The following changes since commit 28fa741c27e6d57f6bf594ba3c444ce79e671e09: perf/core: Clean up inconsisent indentation (2018-10-30 09:51:58 +0100) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo-4.20-20181031 for you to fetch changes up to 5d4f0edaa3ac4f1844ed7c64cd2bae6f1912bac5: perf intel-pt/bts: Calculate cpumode for synthesized samples (2018-10-31 12:56:26 -0300) ---------------------------------------------------------------- perf/urgent improvements and fixes: - Fixes dealing with the removal of the fallback to looking up samples marked as userspace in the kernel maps, done recently: - For intel-pt, that was setting the synthesized header misc field as PERF_RECORD_MISC_USER, depending thus on the fallback to take place, now it sets as USER or KERNEL according to x86 specific knowledge. Also now it inserts the PERF_CONTEXT_{USER,KERNEL} into the PERF_SAMPLE_CALLCHAINs it synthesizes from hw traces (Adrian Hunter) - Similar fixes for the cs-etm ARM HW trace code, that used the Intel PT model as a starting point (Leo Yan) - For the "caller" callchain order, where the callchain returned by the kernel was simply reversed without taking into account the PERF_CONTEXT_{USER,KERNEL,etc} markers from where to define if an entry was for kernel or userspace, working just because the map lookup fallback was in place (David S. Miller) - Allow for selecting if 'overwrite' mode should be used in 'perf top' and make the default for it not to be used. This is due to problems with the current implementation where the pausing used ends up making 'perf top' miss PERF_RECORD_{MMAP,FORK,EXEC,etc} events, which with short lifetime threads workloads leads quickly to many "unknown" maps (and thus symbols) to appear in the UI. Workloads with long thread lifetimes and with few metadata events can still use --overwrite to take advantage of the overwrite mode (Arnaldo Carvalho de Melo) - Start 'perf top''s display thread earlier, so that the screen doesn't remain blank for too long at tool start (David S. Miller) - Don't clone maps from parent when synthesizing forks, to avoid the inevitable flurry of overlapping maps as we process the synthesized MMAP2 events that get delivered shortly thereafter. (David S. Miller) - Take pgoff into account when reporting elf to libdwfl, now the unwinding results are the same with elfutils's libdwfl and libunwind (Milian Wolff) - Update lotsa kernel ABI headers (Arnaldo Carvalho de Melo) - 'perf trace' syscall arg beautification improvements to allow for handling args such as mount's 'flags', where maks have to be ignored before considering what is left, that, if only zeroes, is suppressed like other args without such masks (Arnaldo Carvalho de Melo) - Beautify mount's 'source' and 'flags' args (Arnaldo Carvalho de Melo) - Generate mmap's flags bit constants from linux/mman.h and all the arch specific mman.h files, so that no changes in the main 'perf trace' source files is required when new flags get added (Arnaldo Carvalho de Melo) - Consider syscall aliases, so that 'perf trace -e umount' works and we don't have to use 'umount2' (that works as well, just not required) (Arnaldo Carvalho de Melo) Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> ---------------------------------------------------------------- Adrian Hunter (2): perf intel-pt: Insert callchain context into synthesized callchains perf intel-pt/bts: Calculate cpumode for synthesized samples Arnaldo Carvalho de Melo (21): tools include uapi: Grab a copy of linux/fs.h perf beauty: Add a generator for MS_ mount/umount's flag constants perf beauty: Switch from GPL v2.0 to LGPL v2.1 perf beauty: Introduce strarray__scnprintf_flags() perf trace beauty: Allow syscalls to mask an argument before considering it perf trace beauty: Beautify mount/umount's 'flags' argument perf trace: Consider syscall aliases too perf trace: Beautify the umount's 'name' argument perf trace: Beautify mount's first pathname arg perf top: Allow disabling the overwrite mode perf top: Do not use overwrite mode by default tools include uapi: Update linux/fs.h copy tools arch uapi: Update asm-generic/unistd.h and arm64 unistd.h copies tools include uapi: Update asound.h copy perf beauty: Add a generator for MAP_ mmap's flag constants perf beauty: Wire up the mmap flags table generator to the Makefile perf trace beauty: Use the mmap flags table generated from headers tools include uapi: Update linux/mmap.h copy tools headers: Sync the various kvm.h header copies tools headers uapi: Update linux/netlink.h header copy tools headers uapi: Update linux/if_link.h header copy David Miller (2): perf top: Start display thread earlier perf tools: Don't clone maps from parent when synthesizing forks David S. Miller (1): perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc} Leo Yan (1): perf cs-etm: Correct CPU mode for samples Milian Wolff (1): perf unwind: Take pgoff into account when reporting elf to libdwfl include/uapi/linux/perf_event.h | 2 + tools/arch/arm64/include/uapi/asm/unistd.h | 1 + tools/arch/powerpc/include/uapi/asm/kvm.h | 1 + tools/arch/s390/include/uapi/asm/kvm.h | 2 + tools/arch/x86/include/uapi/asm/kvm.h | 6 +- tools/include/uapi/asm-generic/unistd.h | 2 + tools/include/uapi/linux/fs.h | 393 +++++++++++++++++++++ tools/include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/kvm.h | 21 +- tools/include/uapi/linux/mman.h | 2 + tools/include/uapi/linux/netlink.h | 1 + tools/include/uapi/linux/perf_event.h | 2 + tools/include/uapi/sound/asound.h | 2 +- tools/perf/Documentation/perf-top.txt | 10 + tools/perf/Makefile.perf | 19 + tools/perf/builtin-top.c | 21 +- tools/perf/builtin-trace.c | 48 ++- tools/perf/check-headers.sh | 1 + tools/perf/trace/beauty/Build | 1 + tools/perf/trace/beauty/beauty.h | 7 + tools/perf/trace/beauty/clone.c | 3 +- tools/perf/trace/beauty/drm_ioctl.sh | 1 + tools/perf/trace/beauty/eventfd.c | 2 +- tools/perf/trace/beauty/fcntl.c | 3 +- tools/perf/trace/beauty/flock.c | 2 +- tools/perf/trace/beauty/futex_op.c | 2 +- tools/perf/trace/beauty/futex_val3.c | 2 +- tools/perf/trace/beauty/ioctl.c | 3 +- tools/perf/trace/beauty/kcmp.c | 3 +- tools/perf/trace/beauty/kcmp_type.sh | 1 + tools/perf/trace/beauty/kvm_ioctl.sh | 1 + tools/perf/trace/beauty/madvise_behavior.sh | 1 + tools/perf/trace/beauty/mmap.c | 50 +-- tools/perf/trace/beauty/mmap_flags.sh | 32 ++ tools/perf/trace/beauty/mode_t.c | 2 +- tools/perf/trace/beauty/mount_flags.c | 43 +++ tools/perf/trace/beauty/mount_flags.sh | 15 + tools/perf/trace/beauty/msg_flags.c | 2 +- tools/perf/trace/beauty/open_flags.c | 2 +- tools/perf/trace/beauty/perf_event_open.c | 2 +- tools/perf/trace/beauty/perf_ioctl.sh | 1 + tools/perf/trace/beauty/pid.c | 3 +- tools/perf/trace/beauty/pkey_alloc.c | 30 +- .../perf/trace/beauty/pkey_alloc_access_rights.sh | 1 + tools/perf/trace/beauty/prctl.c | 3 +- tools/perf/trace/beauty/prctl_option.sh | 1 + tools/perf/trace/beauty/sched_policy.c | 2 +- tools/perf/trace/beauty/seccomp.c | 2 +- tools/perf/trace/beauty/signum.c | 2 +- tools/perf/trace/beauty/sndrv_ctl_ioctl.sh | 1 + tools/perf/trace/beauty/sndrv_pcm_ioctl.sh | 1 + tools/perf/trace/beauty/sockaddr.c | 2 +- tools/perf/trace/beauty/socket.c | 2 +- tools/perf/trace/beauty/socket_ipproto.sh | 1 + tools/perf/trace/beauty/socket_type.c | 2 +- tools/perf/trace/beauty/statx.c | 3 +- tools/perf/trace/beauty/vhost_virtio_ioctl.sh | 1 + tools/perf/trace/beauty/waitid_options.c | 2 +- tools/perf/util/cs-etm.c | 39 +- tools/perf/util/event.c | 1 + tools/perf/util/intel-bts.c | 17 +- tools/perf/util/intel-pt.c | 28 +- tools/perf/util/machine.c | 54 ++- tools/perf/util/thread-stack.c | 44 ++- tools/perf/util/thread-stack.h | 2 +- tools/perf/util/thread.c | 13 +- tools/perf/util/thread.h | 2 +- tools/perf/util/unwind-libdw.c | 4 +- 68 files changed, 837 insertions(+), 142 deletions(-) create mode 100644 tools/include/uapi/linux/fs.h create mode 100755 tools/perf/trace/beauty/mmap_flags.sh create mode 100644 tools/perf/trace/beauty/mount_flags.c create mode 100755 tools/perf/trace/beauty/mount_flags.sh Test results: The first ones are container (docker) based builds of tools/perf with and without libelf support. Where clang is available, it is also used to build perf with/without libelf, and building with LIBCLANGLLVM=1 (built-in clang) with gcc and clang when clang and its devel libraries are installed. The objtool and samples/bpf/ builds are disabled now that I'm switching from using the sources in a local volume to fetching them from a http server to build it inside the container, to make it easier to build in a container cluster. Those will come back later. Several are cross builds, the ones with -x-ARCH and the android one, and those may not have all the features built, due to lack of multi-arch devel packages, available and being used so far on just a few, like debian:experimental-x-{arm64,mipsel}. The 'perf test' one will perform a variety of tests exercising tools/perf/util/, tools/lib/{bpf,traceevent,etc}, as well as run perf commands with a variety of command line event specifications to then intercept the sys_perf_event syscall to check that the perf_event_attr fields are set up as expected, among a variety of other unit tests. Then there is the 'make -C tools/perf build-test' ones, that build tools/perf/ with a variety of feature sets, exercising the build with an incomplete set of features as well as with a complete one. It is planned to have it run on each of the containers mentioned above, using some container orchestration infrastructure. Get in contact if interested in helping having this in place. The failures are minor and will be fixed soon. 50 6.21 ubuntu:16.04-x-arm64 : FAIL aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 This one is related to smp_load_{acquire,release} expansions in this specific gcc version, reported to Daniel Borkmann 60 3.70 ubuntu:18.04-x-m68k : FAIL m68k-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 64 3.48 ubuntu:18.04-x-riscv64 : FAIL riscv64-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 These two need mman.h files added to its directories in tools/arch/, will fix later. 66 3.84 ubuntu:18.04-x-sh4 : FAIL sh4-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 Needs to normalize sh4 -> sh so that it finds tools/arch/sh/include/uapi/asm/mman.h. # dm 1 alpine:3.4 : Ok gcc (Alpine 5.3.0) 5.3.0 2 alpine:3.5 : Ok gcc (Alpine 6.2.1) 6.2.1 20160822 3 alpine:3.6 : Ok gcc (Alpine 6.3.0) 6.3.0 4 alpine:3.7 : Ok gcc (Alpine 6.4.0) 6.4.0 5 alpine:3.8 : Ok gcc (Alpine 6.4.0) 6.4.0 6 alpine:edge : Ok gcc (Alpine 6.4.0) 6.4.0 7 amazonlinux:1 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28) 8 amazonlinux:2 : Ok gcc (GCC) 7.3.1 20180303 (Red Hat 7.3.1-5) 9 android-ndk:r12b-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 10 android-ndk:r15c-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 11 centos:5 : Ok gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55) 12 centos:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23) 13 centos:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28) 14 clearlinux:latest : Ok gcc (Clear Linux OS for Intel Architecture) 8.2.1 20180502 15 debian:7 : Ok gcc (Debian 4.7.2-5) 4.7.2 16 debian:8 : Ok gcc (Debian 4.9.2-10+deb8u1) 4.9.2 17 debian:9 : Ok gcc (Debian 6.3.0-18+deb9u1) 6.3.0 20170516 18 debian:experimental : Ok gcc (Debian 8.2.0-8) 8.2.0 19 debian:experimental-x-arm64 : Ok aarch64-linux-gnu-gcc (Debian 8.2.0-7) 8.2.0 20 debian:experimental-x-mips : Ok mips-linux-gnu-gcc (Debian 8.2.0-7) 8.2.0 21 debian:experimental-x-mips64 : Ok mips64-linux-gnuabi64-gcc (Debian 8.1.0-12) 8.1.0 22 debian:experimental-x-mipsel : Ok mipsel-linux-gnu-gcc (Debian 8.2.0-7) 8.2.0 23 fedora:20 : Ok gcc (GCC) 4.8.3 20140911 (Red Hat 4.8.3-7) 24 fedora:21 : Ok gcc (GCC) 4.9.2 20150212 (Red Hat 4.9.2-6) 25 fedora:22 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 26 fedora:23 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 27 fedora:24 : Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1) 28 fedora:24-x-ARC-uClibc : Ok arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 29 fedora:25 : Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1) 30 fedora:26 : Ok gcc (GCC) 7.3.1 20180130 (Red Hat 7.3.1-2) 31 fedora:27 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-6) 32 fedora:28 : Ok gcc (GCC) 8.1.1 20180712 (Red Hat 8.1.1-5) 33 fedora:29 : Ok gcc (GCC) 8.2.1 20181011 (Red Hat 8.2.1-4) 34 fedora:rawhide : Ok gcc (GCC) 8.2.1 20180905 (Red Hat 8.2.1-3) 35 gentoo-stage3-amd64:latest : Ok gcc (Gentoo 7.3.0-r3 p1.4) 7.3.0 36 mageia:5 : Ok gcc (GCC) 4.9.2 37 mageia:6 : Ok gcc (Mageia 5.5.0-1.mga6) 5.5.0 38 opensuse:13.2 : Ok gcc (SUSE Linux) 4.8.3 20140627 [gcc-4_8-branch revision 212064] 39 opensuse:42.1 : Ok gcc (SUSE Linux) 4.8.5 40 opensuse:42.2 : Ok gcc (SUSE Linux) 4.8.5 41 opensuse:42.3 : Ok gcc (SUSE Linux) 4.8.5 42 opensuse:tumbleweed : Ok gcc (SUSE Linux) 7.3.1 20180323 [gcc-7-branch revision 258812] 43 oraclelinux:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23.0.1) 44 oraclelinux:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28.0.1) 45 ubuntu:12.04.5 : Ok gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3 46 ubuntu:14.04.4 : Ok gcc (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4 47 ubuntu:14.04.4-x-linaro-arm64 : Ok aarch64-linux-gnu-gcc (Linaro GCC 5.5-2017.10) 5.5.0 48 ubuntu:16.04 : Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.10) 5.4.0 20160609 49 ubuntu:16.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 50 ubuntu:16.04-x-arm64 : FAIL aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 51 ubuntu:16.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 52 ubuntu:16.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 53 ubuntu:16.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 54 ubuntu:16.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 55 ubuntu:16.10 : Ok gcc (Ubuntu 6.2.0-5ubuntu12) 6.2.0 20161005 56 ubuntu:17.10 : Ok gcc (Ubuntu 7.2.0-8ubuntu3.2) 7.2.0 57 ubuntu:18.04 : Ok gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 58 ubuntu:18.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0 59 ubuntu:18.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0 60 ubuntu:18.04-x-m68k : FAIL m68k-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 61 ubuntu:17.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 62 ubuntu:18.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 63 ubuntu:18.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 64 ubuntu:18.04-x-riscv64 : FAIL riscv64-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 65 ubuntu:18.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 66 ubuntu:18.04-x-sh4 : FAIL sh4-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 67 ubuntu:18.04-x-sparc64 : Ok sparc64-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 68 ubuntu:18.10 : Ok gcc (Ubuntu 8.2.0-7ubuntu1) 8.2.0 # uname -a Linux seventh 4.19.0-rc8-00014-gc0cff31be705 #1 SMP Wed Oct 17 09:00:22 -03 2018 x86_64 x86_64 x86_64 GNU/Linux # git log --oneline -1 5d4f0edaa3ac perf intel-pt/bts: Calculate cpumode for synthesized samples # perf version --build-options perf version 4.19.g5d4f0e dwarf: [ on ] # HAVE_DWARF_SUPPORT dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT glibc: [ on ] # HAVE_GLIBC_SUPPORT gtk2: [ on ] # HAVE_GTK2_SUPPORT syscall_table: [ on ] # HAVE_SYSCALL_TABLE_SUPPORT libbfd: [ on ] # HAVE_LIBBFD_SUPPORT libelf: [ on ] # HAVE_LIBELF_SUPPORT libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT libperl: [ on ] # HAVE_LIBPERL_SUPPORT libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT libslang: [ on ] # HAVE_SLANG_SUPPORT libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT zlib: [ on ] # HAVE_ZLIB_SUPPORT lzma: [ on ] # HAVE_LZMA_SUPPORT get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT bpf: [ on ] # HAVE_LIBBPF_SUPPORT # perf test 1: vmlinux symtab matches kallsyms : Ok 2: Detect openat syscall event : Ok 3: Detect openat syscall event on all cpus : Ok 4: Read samples using the mmap interface : Ok 5: Test data source output : Ok 6: Parse event definition strings : Ok 7: Simple expression parser : Ok 8: PERF_RECORD_* events & perf_sample fields : Ok 9: Parse perf pmu format : Ok 10: DSO data read : Ok 11: DSO data cache : Ok 12: DSO data reopen : Ok 13: Roundtrip evsel->name : Ok 14: Parse sched tracepoints fields : Ok 15: syscalls:sys_enter_openat event fields : Ok 16: Setup struct perf_event_attr : Ok 17: Match and link multiple hists : Ok 18: 'import perf' in python : Ok 19: Breakpoint overflow signal handler : Ok 20: Breakpoint overflow sampling : Ok 21: Breakpoint accounting : Ok 22: Watchpoint : 22.1: Read Only Watchpoint : Skip 22.2: Write Only Watchpoint : Ok 22.3: Read / Write Watchpoint : Ok 22.4: Modify Watchpoint : Ok 23: Number of exit events of a simple workload : Ok 24: Software clock events period values : Ok 25: Object code reading : Ok 26: Sample parsing : Ok 27: Use a dummy software event to keep tracking : Ok 28: Parse with no sample_id_all bit set : Ok 29: Filter hist entries : Ok 30: Lookup mmap thread : Ok 31: Share thread mg : Ok 32: Sort output of hist entries : Ok 33: Cumulate child hist entries : Ok 34: Track with sched_switch : Ok 35: Filter fds with revents mask in a fdarray : Ok 36: Add fd to a fdarray, making it autogrow : Ok 37: kmod_path__parse : Ok 38: Thread map : Ok 39: LLVM search and compile : 39.1: Basic BPF llvm compile : Ok 39.2: kbuild searching : Ok 39.3: Compile source for BPF prologue generation : Ok 39.4: Compile source for BPF relocation : Ok 40: Session topology : Ok 41: BPF filter : 41.1: Basic BPF filtering : Ok 41.2: BPF pinning : Ok 41.3: BPF prologue generation : Ok 41.4: BPF relocation checker : Ok 42: Synthesize thread map : Ok 43: Remove thread map : Ok 44: Synthesize cpu map : Ok 45: Synthesize stat config : Ok 46: Synthesize stat : Ok 47: Synthesize stat round : Ok 48: Synthesize attr update : Ok 49: Event times : Ok 50: Read backward ring buffer : Ok 51: Print cpu map : Ok 52: Probe SDT events : Ok 53: is_printable_array : Ok 54: Print bitmap : Ok 55: perf hooks : Ok 56: builtin clang support : Skip (not compiled in) 57: unit_number__scnprintf : Ok 58: mem2node : Ok 59: x86 rdpmc : Ok 60: Convert perf time to TSC : Ok 61: DWARF unwind : Ok 62: x86 instruction decoder - new instructions : Ok 63: x86 bp modify : Ok 64: probe libc's inet_pton & backtrace it with ping : Ok 65: Check open filename arg using perf trace + vfs_getname: Ok 66: Use vfs_getname probe to get syscall args filenames : Ok 67: Add vfs_getname probe to get syscall args filenames : Ok $ make -C tools/perf build-test make: Entering directory '/home/acme/git/perf/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . make_with_clangllvm_O: make LIBCLANGLLVM=1 make_no_libperl_O: make NO_LIBPERL=1 make_install_prefix_O: make install prefix=/tmp/krava make_install_prefix_slash_O: make install prefix=/tmp/krava/ make_no_libpython_O: make NO_LIBPYTHON=1 make_perf_o_O: make perf.o make_static_O: make LDFLAGS=-static make_no_newt_O: make NO_NEWT=1 make_no_auxtrace_O: make NO_AUXTRACE=1 make_util_pmu_bison_o_O: make util/pmu-bison.o make_util_map_o_O: make util/map.o make_minimal_O: make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 make_no_libelf_O: make NO_LIBELF=1 make_no_backtrace_O: make NO_BACKTRACE=1 make_no_libbpf_O: make NO_LIBBPF=1 make_no_libunwind_O: make NO_LIBUNWIND=1 make_no_gtk2_O: make NO_GTK2=1 make_install_bin_O: make install-bin make_no_demangle_O: make NO_DEMANGLE=1 make_no_libbionic_O: make NO_LIBBIONIC=1 make_no_libnuma_O: make NO_LIBNUMA=1 make_with_babeltrace_O: make LIBBABELTRACE=1 make_pure_O: make make_tags_O: make tags make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1 make_install_O: make install make_clean_all_O: make clean all make_no_slang_O: make NO_SLANG=1 make_doc_O: make doc make_debug_O: make DEBUG=1 make_no_libaudit_O: make NO_LIBAUDIT=1 make_help_O: make help make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1 OK make: Leaving directory '/home/acme/git/perf/tools/perf' $

6 years, 8 months

[PATCH] perf cs-etm: Correct CPU mode for samples

by Leo Yan

Since commit 9042f5e3539e ("perf tools: Stop fallbacking to kallsyms for vdso symbols lookup"), the kernel address cannot be properly parsed to kernel symbol with command 'perf script -k vmlinux'. The reason is CoreSight samples is always to set CPU mode as PERF_RECORD_MISC_USER, thus it fails to find corresponding map/dso in below flows: process_sample_event() `-> machine__resolve() `-> thread__find_map(thread, sample->cpumode, sample->ip, al); In this flow it needs to pass argument 'sample->cpumode' to tell what's the CPU mode, before it always passed PERF_RECORD_MISC_USER but without any failure until the commit 9042f5e3539e ("perf tools: Stop fallbacking to kallsyms for vdso symbols lookup") has been merged. The reason is even with the wrong CPU mode the function thread__find_map() firstly fails to find map but it will rollback to find kernel map for vdso symbols lookup. In the latest code it has removed the fallback code, thus if CPU mode is PERF_RECORD_MISC_USER then it cannot find map anymore with kernel address. This patch is to correct samples CPU mode setting, it creates a new helper function cs_etm__cpu_mode() to tell what's the CPU mode based on the address with the info from machine structure; this patch has a bit extension to check not only kernel and user mode, but also check for host/guest and hypervisor mode. Finally this patch uses the function in instruction and branch samples and also apply in cs_etm__mem_access() for a minor polishing. Signed-off-by: Leo Yan <leo.yan(a)linaro.org> --- tools/perf/util/cs-etm.c | 39 ++++++++++++++++++++++++++++++--------- 1 file changed, 30 insertions(+), 9 deletions(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 3b37d66..73430b7 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -244,6 +244,27 @@ static void cs_etm__free(struct perf_session *session) zfree(&aux); } +static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address) +{ + struct machine *machine; + + machine = etmq->etm->machine; + + if (address >= etmq->etm->kernel_start) { + if (machine__is_host(machine)) + return PERF_RECORD_MISC_KERNEL; + else + return PERF_RECORD_MISC_GUEST_KERNEL; + } else { + if (machine__is_host(machine)) + return PERF_RECORD_MISC_USER; + else if (perf_guest) + return PERF_RECORD_MISC_GUEST_USER; + else + return PERF_RECORD_MISC_HYPERVISOR; + } +} + static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address, size_t size, u8 *buffer) { @@ -258,10 +279,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address, return -1; machine = etmq->etm->machine; - if (address >= etmq->etm->kernel_start) - cpumode = PERF_RECORD_MISC_KERNEL; - else - cpumode = PERF_RECORD_MISC_USER; + cpumode = cs_etm__cpu_mode(etmq, address); thread = etmq->thread; if (!thread) { @@ -653,7 +671,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, struct perf_sample sample = {.ip = 0,}; event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; + event->sample.header.misc = cs_etm__cpu_mode(etmq, addr); event->sample.header.size = sizeof(struct perf_event_header); sample.ip = addr; @@ -665,7 +683,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, sample.cpu = etmq->packet->cpu; sample.flags = 0; sample.insn_len = 1; - sample.cpumode = event->header.misc; + sample.cpumode = event->sample.header.misc; if (etm->synth_opts.last_branch) { cs_etm__copy_last_branch_rb(etmq); @@ -706,12 +724,15 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) u64 nr; struct branch_entry entries; } dummy_bs; + u64 ip; + + ip = cs_etm__last_executed_instr(etmq->prev_packet); event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; + event->sample.header.misc = cs_etm__cpu_mode(etmq, ip); event->sample.header.size = sizeof(struct perf_event_header); - sample.ip = cs_etm__last_executed_instr(etmq->prev_packet); + sample.ip = ip; sample.pid = etmq->pid; sample.tid = etmq->tid; sample.addr = cs_etm__first_executed_instr(etmq->packet); @@ -720,7 +741,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) sample.period = 1; sample.cpu = etmq->packet->cpu; sample.flags = 0; - sample.cpumode = PERF_RECORD_MISC_USER; + sample.cpumode = event->sample.header.misc; /* * perf report cannot handle events without a branch stack -- 2.7.4

6 years, 8 months

[PATCH v1 0/4] perf cs-etm: Add support for sample flags

by Leo Yan

This patch seris adds support for sample flags so can facilitate perf to print sample flags for branch instruction. The branch instructions also include exception taken and return related instructions, so the first patch is used to generate branch sample for exception packets; and the second patch is to track the exception number. The patch 0003 is to set branch instruction flags in packet, this patch has the core code in this series to set flags according to the decoding element type, and also based on the elements including instruction type, subtype and condition flag to help making decision to set flags value. The patch 0004 is to support sample flags by copying the flags value from packet structure to sample structure, and it includes two fixing up for TRACE_ON and exception packets. The patch series is based on OpenCSD v0.10.0 and Rob's patch 'perf: Support for Arm A32/T32 instruction sets in CoreSight trace' also is prerequisite to support A32/T32 ISAs. The patches can be applied on the acme core branch [1] and tested on Juno board with below commands for A64 and A32/T32 building: # perf script -F,-time,+flags,+ip,+sym,+addr -k vmlinux Leo Yan (4): perf cs-etm: Generate branch sample for exception packet perf cs-etm: Track exception number perf cs-etm: Set branch instruction flags in packet perf cs-etm: Add support sample flags tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 237 +++++++++++++++++++++++- tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 11 +- tools/perf/util/cs-etm.c | 44 ++++- 3 files changed, 277 insertions(+), 15 deletions(-) -- 2.7.4

6 years, 8 months

Open CSD

by Ajith Kurian Issac

Hi, We are trying to us the Open CSD for decoding a onchip trace in our ETB. The trace was enabled and is captured in the ETB. We read the trace back and dumped it into a text file. I am attaching it. How can I use the CSD tool to decode it? Thanks Ajith

6 years, 8 months

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight