CoreSight

coresight@lists.linaro.org

5 participants
2501 discussions

[PATCH v1] coresight: tmc-etr: Speed up for bounce buffer in flat mode

by Leo Yan

The AUX bounce buffer is allocated with API dma_alloc_coherent(), in the low level's architecture code, e.g. for Arm64, it maps the memory with the attribution "Normal non-cacheable"; this can be concluded from the definition for pgprot_dmacoherent() in arch/arm64/include/asm/pgtable.h. Later when access the AUX bounce buffer, since the memory mapping is non-cacheable, it's low efficiency due to every load instruction must reach out DRAM. This patch changes to allocate pages with alloc_pages_node(), thus the driver can access the memory with cacheable mapping in the kernel linear virtual address; therefore, because load instructions can fetch data from cache lines rather than always read data from DRAM, the driver can boost memory coping performance. After using the cacheable mapping, the driver uses dma_sync_single_for_cpu() to invalidate cacheline prior to read bounce buffer so can avoid read stale trace data. By measurement the duration for function tmc_update_etr_buffer() with ftrace function_graph tracer, it shows the performance significant improvement for copying 4MiB data from bounce buffer: # echo tmc_etr_get_data_flat_buf > set_graph_notrace // avoid noise # echo tmc_update_etr_buffer > set_graph_function # echo function_graph > current_tracer before: # CPU DURATION FUNCTION CALLS # | | | | | | | 2) | tmc_update_etr_buffer() { ... 2) # 8148.320 us | } after: # CPU DURATION FUNCTION CALLS # | | | | | | | 2) | tmc_update_etr_buffer() { ... 2) # 2463.980 us | } Signed-off-by: Leo Yan <leo.yan(a)linaro.org> --- .../hwtracing/coresight/coresight-tmc-etr.c | 58 ++++++++++++++++--- 1 file changed, 49 insertions(+), 9 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index acdb59e0e661..94558dc5bcf4 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -21,6 +21,7 @@ struct etr_flat_buf { struct device *dev; + struct page *pages; dma_addr_t daddr; void *vaddr; size_t size; @@ -600,6 +601,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, { struct etr_flat_buf *flat_buf; struct device *real_dev = drvdata->csdev->dev.parent; + ssize_t aligned_size; /* We cannot reuse existing pages for flat buf */ if (pages) @@ -609,12 +611,17 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, if (!flat_buf) return -ENOMEM; - flat_buf->vaddr = dma_alloc_coherent(real_dev, etr_buf->size, - &flat_buf->daddr, GFP_KERNEL); - if (!flat_buf->vaddr) { - kfree(flat_buf); - return -ENOMEM; - } + aligned_size = PAGE_ALIGN(etr_buf->size); + flat_buf->pages = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, + get_order(aligned_size)); + if (!flat_buf->pages) + goto fail_alloc_pages; + + flat_buf->vaddr = page_address(flat_buf->pages); + flat_buf->daddr = dma_map_page(real_dev, flat_buf->pages, 0, + aligned_size, DMA_FROM_DEVICE); + if (dma_mapping_error(real_dev, flat_buf->daddr)) + goto fail_dma_map_page; flat_buf->size = etr_buf->size; flat_buf->dev = &drvdata->csdev->dev; @@ -622,23 +629,34 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, etr_buf->mode = ETR_MODE_FLAT; etr_buf->private = flat_buf; return 0; + +fail_dma_map_page: + __free_pages(flat_buf->pages, get_order(aligned_size)); +fail_alloc_pages: + kfree(flat_buf); + return -ENOMEM; } static void tmc_etr_free_flat_buf(struct etr_buf *etr_buf) { struct etr_flat_buf *flat_buf = etr_buf->private; - if (flat_buf && flat_buf->daddr) { + if (flat_buf && flat_buf->vaddr) { struct device *real_dev = flat_buf->dev->parent; + ssize_t aligned_size = PAGE_ALIGN(etr_buf->size); - dma_free_coherent(real_dev, flat_buf->size, - flat_buf->vaddr, flat_buf->daddr); + dma_unmap_page(real_dev, flat_buf->daddr, aligned_size, + DMA_FROM_DEVICE); + __free_pages(flat_buf->pages, get_order(aligned_size)); } kfree(flat_buf); } static void tmc_etr_sync_flat_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp) { + struct etr_flat_buf *flat_buf = etr_buf->private; + struct device *real_dev = flat_buf->dev->parent; + /* * Adjust the buffer to point to the beginning of the trace data * and update the available trace data. @@ -648,6 +666,28 @@ static void tmc_etr_sync_flat_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp) etr_buf->len = etr_buf->size; else etr_buf->len = rwp - rrp; + + if (etr_buf->offset + etr_buf->len > etr_buf->size) { + int len1, len2; + + /* + * If trace data is wrapped around, sync AUX bounce buffer + * for two chunks: "len1" is for the trace date length at + * the tail of bounce buffer, and "len2" is the length from + * the start of the buffer after wrapping around. + */ + len1 = etr_buf->size - etr_buf->offset; + len2 = etr_buf->len - len1; + dma_sync_single_for_cpu(real_dev, + flat_buf->daddr + etr_buf->offset, + len1, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(real_dev, flat_buf->daddr, + len2, DMA_FROM_DEVICE); + } else { + dma_sync_single_for_cpu(real_dev, + flat_buf->daddr + etr_buf->offset, + etr_buf->len, DMA_FROM_DEVICE); + } } static ssize_t tmc_etr_get_data_flat_buf(struct etr_buf *etr_buf, -- 2.25.1

4 years, 3 months

[RFC PATCH 0/8] coresight: syscfg: dynamic load, resource management

by Mike Leach

This patchset represents the second phase of CoreSight configuration management. 1) API updated to allow dynamic load and unload of configurations and features. Dependency management between loaded sets is added. 2) New configuration and feature sets can be added using a loadable module. An example in /samples/coresight is provided to demonstrate this. 3) Resource management API is added. This allows the system to ensure that loaded configurations and features are only loaded onto devices that can support them. Further - it ensures that configurations with multiple features cannot over allocate resources. 4) configfs can be used to activate a configuration which will then be used when controlling tracing using sysfs. 5) Resource management is added to ETMv4 configurations. This allows current and future features and configurations to be defined in terms of resources used as well as registers to be programmed. Defining features in this way allows the resource management to operate correctly. The perf event parsing is also adjusted to allow the ETM resources requested on the command line (e.g. address filters, etc) to be correctly handled using resoruce management alongside the complex configurations such as autofdo. Applies to coresight/next - which is 5.13-rc1 + initial Coresight configuration patchset. To follow in future revisions / sets:- a) load of additional config and features by configfs b) ECT and CTI and other Coresight components support for configuration and features. Mike Leach (8): coresight: syscfg: Update API to allow dynamic load and unload coresight: syscfg: Update load API for config loadable modules coresight: syscfg: Example CoreSight configuration loadable module coresight: configfs: Allow configfs to activate configuration. coresight: syscfg: Add API to check and validate device resources. coresight: etm4x: syscfg: Add resource management to etm4x. coresight: etm4x: Update perf event resource handling. coresight: etm4x: Update configuration example. MAINTAINERS | 1 + .../hwtracing/coresight/coresight-cfg-afdo.c | 38 +- .../coresight/coresight-cfg-preload.c | 9 +- .../hwtracing/coresight/coresight-config.c | 71 ++- .../hwtracing/coresight/coresight-config.h | 45 +- .../hwtracing/coresight/coresight-etm4x-cfg.c | 533 ++++++++++++++++++ .../hwtracing/coresight/coresight-etm4x-cfg.h | 196 ++++++- .../coresight/coresight-etm4x-core.c | 250 +++----- .../coresight/coresight-syscfg-configfs.c | 87 +++ .../coresight/coresight-syscfg-configfs.h | 4 + .../hwtracing/coresight/coresight-syscfg.c | 390 +++++++++++-- .../hwtracing/coresight/coresight-syscfg.h | 38 +- include/linux/coresight.h | 2 + samples/Kconfig | 9 + samples/Makefile | 1 + samples/coresight/Makefile | 4 + samples/coresight/coresight-cfg-sample.c | 73 +++ 17 files changed, 1511 insertions(+), 240 deletions(-) create mode 100644 samples/coresight/Makefile create mode 100644 samples/coresight/coresight-cfg-sample.c -- 2.17.1

4 years, 3 months

[RFC PATCH 0/4] Add support for Ultrasoc Trace Module

by Qi Liu

This patchset adds support for Ultrasoc Trace Module on Hip08 and Hip09 platform. It includes core layer framework, AXI Communicator(AXI-COM) and System Memory Buffer(SMB). Qi Liu (4): Documentation: tracing: Documentation for ultrasoc framework and drivers ultrasoc: add ultrasoc core layer framework ultrasoc: Add ultrasoc AXI Communicator driver ultrasoc: Add System Memory Buffer driver Documentation/trace/ultrasoc-trace.rst | 209 ++++++++ MAINTAINERS | 7 + drivers/Makefile | 1 + drivers/hwtracing/Kconfig | 2 + drivers/hwtracing/ultrasoc/Kconfig | 34 ++ drivers/hwtracing/ultrasoc/Makefile | 13 + drivers/hwtracing/ultrasoc/ultrasoc-axi-com.c | 334 +++++++++++++ drivers/hwtracing/ultrasoc/ultrasoc-axi-com.h | 66 +++ drivers/hwtracing/ultrasoc/ultrasoc-smb.c | 663 ++++++++++++++++++++++++++ drivers/hwtracing/ultrasoc/ultrasoc-smb.h | 182 +++++++ drivers/hwtracing/ultrasoc/ultrasoc.c | 518 ++++++++++++++++++++ drivers/hwtracing/ultrasoc/ultrasoc.h | 168 +++++++ 12 files changed, 2197 insertions(+) create mode 100644 Documentation/trace/ultrasoc-trace.rst create mode 100644 drivers/hwtracing/ultrasoc/Kconfig create mode 100644 drivers/hwtracing/ultrasoc/Makefile create mode 100644 drivers/hwtracing/ultrasoc/ultrasoc-axi-com.c create mode 100644 drivers/hwtracing/ultrasoc/ultrasoc-axi-com.h create mode 100644 drivers/hwtracing/ultrasoc/ultrasoc-smb.c create mode 100644 drivers/hwtracing/ultrasoc/ultrasoc-smb.h create mode 100644 drivers/hwtracing/ultrasoc/ultrasoc.c create mode 100644 drivers/hwtracing/ultrasoc/ultrasoc.h -- 2.7.4

4 years, 3 months

[PATCH v3 00/10] perf: Refine barriers for AUX ring buffer

by Leo Yan

This patch series is to refine the memory barriers for AUX ring buffer. Patches 01 ~ 04 to address the barriers usage in the kernel. The first patch is to make clear comment for how to use the barriers between the data store and aux_head store, this asks the driver to make sure the data is visible. Patches 02 ~ 04 is to refine the drivers for barriers after the data store. Patches 05 ~ 07 is to drop the legacy __sync functions, and polish for duplicate code and cleanup the build after SYNC_COMPARE_AND_SWAP is not used. Patch 08 is to use WRITE_ONCE() for updating aux_tail. Since the 64-bit value's atomicity is not promised on 32-bit perf, the last two patches tries to fixup for perf tool when it runs in compat mode. Patch 09 introduces a new global variable to indicate the kernel runs in 64-bit mode which can be used to confirm if in compat mode; patch 10 introduces variant functions for accessing AUX head/tail, it can resolve the aotmicity issue for reading head pointer, and for the tail write overflow issue it returns error to notify the tool to exit. Have testes the patches on Arm64 Juno platform. Changes from v2: - Removed auxtrace_mmap__read_snapshot_head(), which has the duplicated code with auxtrace_mmap__read_head(); - Cleanuped the build for HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT (Adrian); - Added global variable "kernel_is_64_bit" (Adrian); - Added compat variants compat_auxtrace_mmap__{read_head|write_tail} (Adrian). Leo Yan (10): perf/ring_buffer: Add comment for barriers on AUX ring buffer coresight: tmc-etr: Add barrier after updating AUX ring buffer coresight: tmc-etf: Add comment for store ordering perf/x86: Add barrier after updating bts perf auxtrace: Drop legacy __sync functions perf auxtrace: Remove auxtrace_mmap__read_snapshot_head() perf: Cleanup for HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT perf auxtrace: Use WRITE_ONCE() for updating aux_tail perf env: Set kernel bit mode perf auxtrace: Add compat_auxtrace_mmap__{read_head|write_tail} arch/x86/events/intel/bts.c | 3 + .../hwtracing/coresight/coresight-tmc-etf.c | 6 + .../hwtracing/coresight/coresight-tmc-etr.c | 8 ++ kernel/events/ring_buffer.c | 9 ++ tools/perf/Makefile.config | 4 - tools/perf/util/auxtrace.c | 19 ++- tools/perf/util/auxtrace.h | 109 ++++++++++++++---- tools/perf/util/env.c | 17 ++- tools/perf/util/env.h | 1 + 9 files changed, 136 insertions(+), 40 deletions(-) -- 2.25.1

4 years, 3 months

[PATCH v2 0/3] coresight: Fix for snapshot mode

by Leo Yan

This patch series is to correct the pointer usages for the snapshot mode. Patch 01 is to polish code, it removes the redundant header maintained in tmc-etr driver and directly uses pointer perf_output_handle::head. Patch 02 removes the callback cs_etm_find_snapshot() which wrongly calculates the buffer headers; we can simply use the perf's common function __auxtrace_mmap__read() for headers calculation. Patch 03 is to update comments in CoreSight drivers to reflect the changes introduced by patch 02. This patch can be cleanly applied on the mainline kernel with: commit dbe69e433722 ("Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next") And it has been tested on Arm64 Juno board. Changes from v1: - Dropped the patch "coresight: etm-perf: Correct buffer syncing for snapshot", after a long discussion, the patch doesn't really resolve any issues for snapshot mode. And another reason for unlike this patch is now the CoreSight and Intel-PT have the consistent behaviour (Suzuki/James/Mathieu); - Added the patch 03 to updates drivers' comments (James); - Added Suzuki's review tag for patch 01; - Added James' review and testing tags for patch 02. Leo Yan (3): coresight: tmc-etr: Use perf_output_handle::head for AUX ring buffer perf cs-etm: Remove callback cs_etm_find_snapshot() coresight: Update comments for removing cs_etm_find_snapshot() drivers/hwtracing/coresight/coresight-etb10.c | 2 +- .../hwtracing/coresight/coresight-tmc-etf.c | 2 +- .../hwtracing/coresight/coresight-tmc-etr.c | 12 +- tools/perf/arch/arm/util/cs-etm.c | 133 ------------------ 4 files changed, 6 insertions(+), 143 deletions(-) -- 2.25.1

4 years, 3 months

[PATCH] perf cs-etm: Delay decode of non-timeless data until cs_etm__flush_events()

by James Clark

Currently, timeless mode starts the decode on PERF_RECORD_EXIT, and non-timeless mode starts decoding on the fist PERF_RECORD_AUX record. This can cause the "data has no samples!" error if the first PERF_RECORD_AUX record comes before the first (or any relevant) PERF_RECORD_MMAP2 record because the mmaps are required by the decoder to access the binary data. This change pushes the start of non-timeless decoding to the very end of parsing the file. The PERF_RECORD_EXIT event can't be used because it might not exist in system-wide or snapshot modes. I have not been able to find the exact cause for the events to be intermittently in the wrong order in the basic scenario: perf record -e cs_etm/@tmc_etr0/u top But it can be made to happen every time with the --delay option. This is because "enable_on_exec" is disabled, which causes tracing to start before the process to be launched is exec'd. For example: perf record -e cs_etm/@tmc_etr0/u --delay=1 top perf report -D | grep 'AUX\|MAP' 0 16714475632740 0x520 [0x40]: PERF_RECORD_AUX offset: 0 size: 0x30 flags: 0 [] 0 16714476494960 0x5d0 [0x40]: PERF_RECORD_AUX offset: 0x30 size: 0x30 flags: 0 [] 0 16714478208900 0x660 [0x40]: PERF_RECORD_AUX offset: 0x60 size: 0x30 flags: 0 [] 4294967295 16714478293340 0x700 [0x70]: PERF_RECORD_MMAP2 8712/8712: [0x557a460000(0x54000) @ 0 00:17 5329258 0]: r-xp /usr/bin/top 4294967295 16714478353020 0x770 [0x88]: PERF_RECORD_MMAP2 8712/8712: [0x7f86f72000(0x34000) @ 0 00:17 5214354 0]: r-xp /usr/lib/aarch64-linux-gnu/ld-2.31.so Another scenario in which decoding from the first aux record fails is a workload that forks. Although the aux record comes after 'bash', it comes before 'top', which is what we are interested in. For example: perf record -e cs_etm/@tmc_etr0/u -- bash -c top perf report -D | grep 'AUX\|MAP' 4294967295 16853946421300 0x510 [0x70]: PERF_RECORD_MMAP2 8723/8723: [0x558f280000(0x142000) @ 0 00:17 5213953 0]: r-xp /usr/bin/bash 4294967295 16853946543560 0x580 [0x88]: PERF_RECORD_MMAP2 8723/8723: [0x7fbba6e000(0x34000) @ 0 00:17 5214354 0]: r-xp /usr/lib/aarch64-linux-gnu/ld-2.31.so 4294967295 16853946628420 0x608 [0x68]: PERF_RECORD_MMAP2 8723/8723: [0x7fbba9e000(0x1000) @ 0 00:00 0 0]: r-xp [vdso] 0 16853947067300 0x690 [0x40]: PERF_RECORD_AUX offset: 0 size: 0x3a60 flags: 0 [] ... 0 16853966602580 0x1758 [0x40]: PERF_RECORD_AUX offset: 0xc2470 size: 0x30 flags: 0 [] 4294967295 16853967119860 0x1818 [0x70]: PERF_RECORD_MMAP2 8723/8723: [0x5559e70000(0x54000) @ 0 00:17 5329258 0]: r-xp /usr/bin/top 4294967295 16853967181620 0x1888 [0x88]: PERF_RECORD_MMAP2 8723/8723: [0x7f9ed06000(0x34000) @ 0 00:17 5214354 0]: r-xp /usr/lib/aarch64-linux-gnu/ld-2.31.so 4294967295 16853967237180 0x1910 [0x68]: PERF_RECORD_MMAP2 8723/8723: [0x7f9ed36000(0x1000) @ 0 00:00 0 0]: r-xp [vdso] A third scenario is when the majority of time is spent in a shared library that is not loaded at startup. For example a dynamically loaded plugin. Testing ======= Testing was done by checking if any samples that are present in the old output are missing from the new output. Timestamps must be stripped out with awk because now they are set to the last AUX sample, rather than the first: ./perf script $4 | awk '!($4="")' > new.script ./perf-default script $4 | awk '!($4="")' > default.script comm -13 <(sort -u new.script) <(sort -u default.script) Testing showed that the new output is a superset of the old. When lines appear in the comm output, it is not because they are missing but because [unknown] is now resolved to sensible locations. For example last putp branch here now resolves to libtinfo, so it's not missing from the output, but is actually improved: Old: top 305 [001] 1 branches:uH: 402830 _init+0x30 (/usr/bin/top.procps) => 404a1c [unknown] (/usr/bin/top.procps) top 305 [001] 1 branches:uH: 404a20 [unknown] (/usr/bin/top.procps) => 402970 putp@plt+0x0 (/usr/bin/top.procps) top 305 [001] 1 branches:uH: 40297c putp@plt+0xc (/usr/bin/top.procps) => 0 [unknown] ([unknown]) New: top 305 [001] 1 branches:uH: 402830 _init+0x30 (/usr/bin/top.procps) => 404a1c [unknown] (/usr/bin/top.procps) top 305 [001] 1 branches:uH: 404a20 [unknown] (/usr/bin/top.procps) => 402970 putp@plt+0x0 (/usr/bin/top.procps) top 305 [001] 1 branches:uH: 40297c putp@plt+0xc (/usr/bin/top.procps) => 7f8ab39208 putp+0x0 (/lib/libtinfo.so.5.9) In the following two modes, decoding now works and the "data has no samples!" error is not displayed any more: perf record -e cs_etm/@tmc_etr0/u -- bash -c top perf record -e cs_etm/@tmc_etr0/u --delay=1 top In snapshot mode, there is also an improvement to decoding. Previously samples for the 'kill' process that was used to send SIGUSR2 were completely missing, because the process hadn't started yet. But now there are additional samples present: perf record -e cs_etm/@tmc_etr0/u --snapshot -a perf script stress 19380 [003] 161627.938153: 1000000 instructions:uH: aaaabb612fb4 [unknown] (/usr/bin/stress) kill 19644 [000] 161627.938153: 1000000 instructions:uH: ffffae0ef210 [unknown] (/lib/aarch64-linux-gnu/ld-2.27.so) stress 19380 [003] 161627.938153: 1000000 instructions:uH: ffff9e754d40 random_r+0x20 (/lib/aarch64-linux-gnu/libc-2.27.so) Also tested was the round trip of 'perf inject' followed by 'perf report' which has the same differences and improvements. Signed-off-by: James Clark <james.clark(a)arm.com> --- tools/perf/util/cs-etm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 57aea2c7fc77..ceed0b038796 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2407,6 +2407,11 @@ static int cs_etm__process_event(struct perf_session *session, return err; } + /* + * Don't wait for cs_etm__flush_events() in per-thread/timeless mode to start the decode. We + * need the tid of the PERF_RECORD_EXIT event to assign to the synthesised samples because + * ETM_OPT_CTXTID is not enabled. + */ if (etm->timeless_decoding && event->header.type == PERF_RECORD_EXIT) return cs_etm__process_timeless_queues(etm, @@ -2424,7 +2429,6 @@ static int cs_etm__process_event(struct perf_session *session, * onwards. */ etm->latest_kernel_timestamp = sample_kernel_timestamp; - return cs_etm__process_queues(etm); } return 0; -- 2.28.0

4 years, 3 months

Re: Re: following up again

by Aaron Lane

4 years, 3 months

ETM4 for Cortex-M7

by Jinnan Li A

Hi Linaro Coresight Team, We are debugging Arm ETB. We don't know how to dump the ETB data with the right method. Please give me some comments, thanks so much. * Let's me give a description for our ETB environment first. For the Core-sight components, after enabled ETM and ETB. We can dump the ETB data after a while. [cid:image004.jpg@01D76CF0.86E6C320] According to ARM_CoreSight_Architecture_Specification.pdf, then We think it works by changing the trace source ID. [cid:image005.jpg@01D76CF0.86E6C320] The following data is from the head of trace buffer. Before the trace source ID = 2: 00000005 = 00 | 0b10<<1+0b1 | 0x0 | 0x0 After the trace source ID = 4: 00000009 = 00 | 0b100<<1+0b1 | 0x0 | 0x0 0000000B 00000000 04000000 00800000 The registers about ETM are as follows. TRCCONFIGR(id:0x10)=0x31F07 TRCTRACEIDR(id:0x40)=0x2 TRCIDR8(id:0x180)=0x1 TRCIDR9(id:0x184)=0x20 TRCIDR10(id:0x188)=0x2 TRCIDR11(id:0x18c)=0x0 TRCIDR12(id:0x190)=0x1 TRCIDR13(id:0x194)=0x0 TRCIDR0(id:0x1e0)=0x8020EFF TRCIDR1(id:0x1e4)=0x4100F401 ARM ETM4.0.1 TRCIDR2(id:0x1e8)=0x420004 * How to use OpenCSD for M7? We also try to dump with your source code "OpenCSD" https://github.com/Linaro/OpenCSD, it's a useful tool. But maybe we lost some configuration, our ETB can't be dumped. Trace Packet Lister : Protocol printer ETMV4I on Trace ID 0x0 Idx:0; ID:0; I_NOT_SYNC : I Stream not synchronised Idx:285; ID:0; I_INCOMPLETE_EOT : Incomplete packet at end of trace.[I_NOT_SYNC] ID:0 END OF TRACE DATA Trace Packet Lister : Trace buffer done, processed 288 bytes. The attachments are the settings and trace buffer. So my question is: * Should we use ETM4D instead of ETMV4I? #define OCSD_BUILTIN_DCD_ETMV4D "ETMV4D" /**< ETMv4 data decoder */ * Does OpenCSD support ETMV4D and Cortex-M7? We can see the TODO from git repo. Support to be added: ETMv4 data trace - packet processing and decode. const char *decoderName = bDataChannel ? OCSD_BUILTIN_DCD_ETMV4D : OCSD_BUILTIN_DCD_ETMV4I; I didn't see the M7 support. 69 { "Cortex-M0", { ARCH_V7, profile_CortexM } }, 70 { "Cortex-M0+", { ARCH_V7, profile_CortexM } }, 71 { "Cortex-M3", { ARCH_V7, profile_CortexM } }, 72 { "Cortex-M4", { ARCH_V7, profile_CortexM } } * A stupid question, could you kindly tell me which ARM document introduce the data encoder? I debug test code step by step(see below lines), but it doesn't match with ETB trace buffer. I am not sure if there has more document about PEencoder/decoder. debug_count += 1; 4B11 ldr r3,0x604 681B ldr r3,[r3] 3301 adds r3,#0x1 4A0F ldr r2,0x604 6013 str r3,[r2] [cid:image011.jpg@01D76CF0.86E6C320] [PC-bas<f and trace analyzer p roaessng Element System bus System PE interface JTAG port Trae:e unit Control and trace flWing FIFO generatOn Cores i g ht core"ht Figure 1-2 Example SOC with a trace unit and a dedicated trace buffer] Looking forward to your feedback. Thank you so much. BR//Jinnan

4 years, 3 months

Re: following up on my last email

by Kayden Hopkins

4 years, 3 months

[PATCH v7 00/10] CoreSight configuration management; ETM strobing

by Mike Leach

This patchset introduces initial concepts in CoreSight system configuration management support. to allow more detailed and complex programming to be applied to CoreSight systems during trace capture. Configurations consist of 2 elements:- 1) Features - programming combinations for devices, applied to a class of device on the system (all ETMv4), or individual devices. 2) Configurations - a set of programmed features used when the named configuration is selected. Features and configurations are declared as a data table, a set of register, resource and parameter requirements. Features and configurations are loaded into the system by the virtual cs_syscfg device. This then matches features to any registered devices and loads the feature into them. Individual device classes that support feature and configuration register with cs_syscfg. Once loaded a configuration can be enabled for a specific trace run. Configurations are registered with the perf cs_etm event as entries in cs_etm/events. These can be selected on the perf command line as follows:- perf record -e cs_etm/<config_name>/ ... This patch set has one pre-loaded configuration and feature. A named "strobing" feature is provided for ETMv4. A named "autofdo" configuration is provided. This configuration enables strobing on any ETM in used. Thus the command: perf record -e cs_etm/autofdo/ ... will trace the supplied application while enabling the "autofdo" configuation on each ETM as it is enabled by perf. This in turn will enable strobing for the ETM - with default parameters. Parameters can be adjusted using configfs. The sink used in the trace run will be automatically selected. A configuration can supply up to 15 of preset parameter values, which will subsitute in parameter values for any feature used in the configuration. Selection of preset values as follows perf record -e cs_etm/autofdo,preset=1/ ... (valid presets 1-N, where N is the number supplied in the configuration, not exceeding 15. preset=0 is the same as not selecting a preset.) Applies to & tested against coresight/next-ETE-TRBE (5.12-rc3 base) Changes since v6: Fixed kernel test robot issues- Reported-by: kernel test robot <lkp(a)intel.com> Changes since v5: 1) Fix code style issues from auto-build reports, as Reported-by: kernel test robot <lkp(a)intel.com> 2) Update comments to get consistent docs for API functions. 3) remove unused #define from autofdo example. 4) fix perf code style issues from patch 4 (Mathieu) 5) fix configfs code style issues from patch 9. (Mathieu) Changes since v4: (based on comments from Matthieu and Suzuki). No large functional changes - primarily code improvements and naming schema. 1) Updated entire set to ensure a consistent naming scheme was used for variables and struct members that refer to the key objects in the system. Suffixes _desc used for all references to feature and configuraion descriptors, suffix _csdev used for all references to load feature and configs in the csdev instances. (Mathieu & Suzuki). 2) Dropped the 'configurations' sub dir in cs_etm perf directories as superfluous with the configfs containing the same information. (Mathieu). 3) Simplified perf handling code (suzuki) 4) Multiple simplifications and improvements for code readability (Matthieu and Suzuki) Changes since v3: (Primarily based on comments from Matthieu) 1) Locking mechanisms simplified. 2) Removed the possibility to enable features independently from configurations.Only configurations can be enabled now. Simplifies programming logic. 3) Configuration now uses an activate->enable mechanism. This means that perf will activate a selected configuration at the start of a session (during setup_aux), and disable at the end of a session (around free_aux) The active configuration and associated features will be programmed into the CoreSight device instances when they are enabled. This locks the configuration into the system while in use. Parameters cannot be altered while this is in place. This mechanism will be extended in future for dynamic load / unload of configurations to prevent removal while in use. 4) Removed the custom bus / driver as un-necessary. A single device is registered to own perf fs elements and configfs. 5) Various other minor issues addressed. Changes since v2: 1) Added documentation file. 2) Altered cs_syscfg driver to no longer be coresight_device based, and moved to its own custom bus to remove it from the main coresight bus. (Mathieu) 3) Added configfs support to inspect and control loaded configurations and features. Allows listing of preset values (Yabin Cui) 4) Dropped sysfs support for adjusting feature parameters on the per device basis, in favour of a single point adjustment in configfs that is pushed to all device instances. 5) Altered how the config and preset command line options are handled in perf and the drivers. (Mathieu and Suzuki). 6) Fixes for various issues and technical points (Mathieu, Yabin) Changes since v1: 1) Moved preloaded configurations and features out of individual drivers. 2) Added cs_syscfg driver to manage configurations and features. Individual drivers register with cs_syscfg indicating support for config, and provide matching information that the system uses to load features into the drivers. This allows individual drivers to be updated on an as needed basis - and removes the need to consider devices that cannot benefit from configuration - static replicators, funnels, tpiu. 3) Added perf selection of configuarations. 4) Rebased onto the coresight module loading set. To follow in future revisions / sets:- a) load of additional config and features by loadable module. b) load of additional config and features by configfs c) enhanced resource management for ETMv4 and checking features have sufficient resources to be enabled. d) ECT and CTI support for configuration and features. Mike Leach (10): coresight: syscfg: Initial coresight system configuration coresight: syscfg: Add registration and feature loading for cs devices coresight: config: Add configuration and feature generic functions coresight: etm-perf: update to handle configuration selection coresight: syscfg: Add API to activate and enable configurations coresight: etm-perf: Update to activate selected configuration coresight: etm4x: Add complex configuration handlers to etmv4 coresight: config: Add preloaded configurations coresight: syscfg: Add initial configfs support Documentation: coresight: Add documentation for CoreSight config .../trace/coresight/coresight-config.rst | 244 ++++++ Documentation/trace/coresight/coresight.rst | 16 + drivers/hwtracing/coresight/Makefile | 7 +- .../hwtracing/coresight/coresight-cfg-afdo.c | 153 ++++ .../coresight/coresight-cfg-preload.c | 31 + .../coresight/coresight-cfg-preload.h | 13 + .../hwtracing/coresight/coresight-config.c | 275 ++++++ .../hwtracing/coresight/coresight-config.h | 253 ++++++ drivers/hwtracing/coresight/coresight-core.c | 12 +- .../hwtracing/coresight/coresight-etm-perf.c | 150 +++- .../hwtracing/coresight/coresight-etm-perf.h | 12 +- .../hwtracing/coresight/coresight-etm4x-cfg.c | 182 ++++ .../hwtracing/coresight/coresight-etm4x-cfg.h | 30 + .../coresight/coresight-etm4x-core.c | 38 +- .../coresight/coresight-etm4x-sysfs.c | 3 + .../coresight/coresight-syscfg-configfs.c | 396 +++++++++ .../coresight/coresight-syscfg-configfs.h | 45 + .../hwtracing/coresight/coresight-syscfg.c | 804 ++++++++++++++++++ .../hwtracing/coresight/coresight-syscfg.h | 81 ++ include/linux/coresight.h | 7 + 20 files changed, 2716 insertions(+), 36 deletions(-) create mode 100644 Documentation/trace/coresight/coresight-config.rst create mode 100644 drivers/hwtracing/coresight/coresight-cfg-afdo.c create mode 100644 drivers/hwtracing/coresight/coresight-cfg-preload.c create mode 100644 drivers/hwtracing/coresight/coresight-cfg-preload.h create mode 100644 drivers/hwtracing/coresight/coresight-config.c create mode 100644 drivers/hwtracing/coresight/coresight-config.h create mode 100644 drivers/hwtracing/coresight/coresight-etm4x-cfg.c create mode 100644 drivers/hwtracing/coresight/coresight-etm4x-cfg.h create mode 100644 drivers/hwtracing/coresight/coresight-syscfg-configfs.c create mode 100644 drivers/hwtracing/coresight/coresight-syscfg-configfs.h create mode 100644 drivers/hwtracing/coresight/coresight-syscfg.c create mode 100644 drivers/hwtracing/coresight/coresight-syscfg.h -- 2.17.1

4 years, 3 months

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight