CoreSight

coresight@lists.linaro.org

6 participants
2648 discussions

[PATCH v1 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 allows the AUX trace in the free run mode and only syncs the AUX ring buffer when taking snapshot. Patch 02 is to polish code, it removes the redundant header maintained in tmc-etr driver and directly uses pointer perf_output_handle::head. Patch 03 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. This patch can be cleanly applied on the mainline kernel with: commit 97e5bf604b7a ("Merge branch 'for-5.13-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu") And it has been tested on Arm64 Juno board. Leo Yan (3): coresight: etm-perf: Correct buffer syncing for snapshot coresight: tmc-etr: Use perf_output_handle::head for AUX ring buffer perf cs-etm: Remove callback cs_etm_find_snapshot() .../hwtracing/coresight/coresight-etm-perf.c | 30 +++- .../hwtracing/coresight/coresight-etm-perf.h | 2 + .../hwtracing/coresight/coresight-tmc-etr.c | 10 +- tools/perf/arch/arm/util/cs-etm.c | 133 ------------------ 4 files changed, 32 insertions(+), 143 deletions(-) -- 2.25.1

5 years, 3 months

data value tracing using CoreSight

by Farzam Dorostkar

Hello everyone, I'm interested in performing data value tracing using CoreSight. Do you know a board offering this feature? So far I know that data value tracing is supported by CoreSight in Cortex-A5 and Cortex-A7, although there might be other cores too (probably 32 bits). In case you have not dealt with data value tracing before, do you know a board with accessible CoreSight components featuring either Cortex-A5 or Cortex-A7? Any help will be greatly appreciated. Regards, Farzam

5 years, 3 months

Mail delivery failed: coresight@lists.linaro.org have 6 Pending incoming messages.

by Mail Delivery System

5 years, 3 months

[PATCH 0/8] Replace some bad characters on documents

by Mauro Carvalho Chehab

Hi Jon, This series contain the remaining 8 patches I submitted at v3 that weren't merged yet at -next. This series is rebased on the top of your docs-next branch. No changes here, except by some Reviewed/ack lines, and at the name of the final patch (per PCI maintainer's request). Mauro Carvalho Chehab (8): docs: admin-guide: reporting-issues.rst: replace some characters docs: trace: coresight: coresight-etm4x-reference.rst: replace some characters docs: driver-api: ioctl.rst: replace some characters docs: usb: replace some characters docs: vm: zswap.rst: replace some characters docs: filesystems: ext4: blockgroup.rst: replace some characters docs: networking: device_drivers: replace some characters docs: PCI: Replace non-breaking spaces to avoid PDF issues Documentation/PCI/acpi-info.rst | 18 +++++++++--------- Documentation/admin-guide/reporting-issues.rst | 2 +- Documentation/driver-api/ioctl.rst | 8 ++++---- Documentation/filesystems/ext4/blockgroup.rst | 2 +- .../device_drivers/ethernet/intel/i40e.rst | 6 +++--- .../device_drivers/ethernet/intel/iavf.rst | 2 +- .../coresight/coresight-etm4x-reference.rst | 2 +- Documentation/usb/ehci.rst | 2 +- Documentation/usb/gadget_printer.rst | 2 +- Documentation/vm/zswap.rst | 4 ++-- 10 files changed, 24 insertions(+), 24 deletions(-) -- 2.31.1

5 years, 3 months

[PATCH v2 00/29] docs: avoid using ReST :doc:`foo` tag

by Mauro Carvalho Chehab

(Maintainers bcc, to avoid too many recipient troubles) As discussed at: https://lore.kernel.org/linux-doc/871r9k6rmy.fsf@meer.lwn.net/ It is better to avoid using :doc:`foo` to refer to Documentation/foo.rst, as the automarkup.py extension should handle it automatically, on most cases. There are a couple of exceptions to this rule: 1. when :doc: tag is used to point to a kernel-doc DOC: markup; 2. when it is used with a named tag, e. g. :doc:`some name <foo>`; On this series: Patch 1 manually adjust the references inside driver-api/pm/devices.rst, as there it uses :file:`foo` to refer to some Documentation/ files; Patch 2 converts a table at Documentation/dev-tools/kunit/api/index.rst into a list, carefully avoiding the The remaining patches convert the other occurrences via a replace script. They were manually edited, in order to honour 80-columns where possible. This series based on docs-next branch. In order to avoid merge conflicts, I rebased it internally against yesterday's linux-next, dropping a patch and a hunk that would have caused conflicts there. I'll re-send the remaining patch (plus another patch) with conflicting changes, together with any other doc:`filename` reference that might still be upstream by 5.14-rc1. --- v2: - dropped media patches (as I merged via my own tree); - removed one patch that would conflict at linux-next (adm1177.rst); - removed one hunk fron kunit patch that would also conflict at linux-next. Mauro Carvalho Chehab (29): docs: devices.rst: better reference documentation docs docs: dev-tools: kunit: don't use a table for docs name docs: admin-guide: pm: avoid using ReST :doc:`foo` markup docs: admin-guide: hw-vuln: avoid using ReST :doc:`foo` markup docs: admin-guide: sysctl: avoid using ReST :doc:`foo` markup docs: block: biodoc.rst: avoid using ReST :doc:`foo` markup docs: bpf: bpf_lsm.rst: avoid using ReST :doc:`foo` markup docs: core-api: avoid using ReST :doc:`foo` markup docs: dev-tools: testing-overview.rst: avoid using ReST :doc:`foo` markup docs: dev-tools: kunit: avoid using ReST :doc:`foo` markup docs: devicetree: bindings: submitting-patches.rst: avoid using ReST :doc:`foo` markup docs: doc-guide: avoid using ReST :doc:`foo` markup docs: driver-api: avoid using ReST :doc:`foo` markup docs: driver-api: gpio: using-gpio.rst: avoid using ReST :doc:`foo` markup docs: driver-api: surface_aggregator: avoid using ReST :doc:`foo` markup docs: driver-api: usb: avoid using ReST :doc:`foo` markup docs: firmware-guide: acpi: avoid using ReST :doc:`foo` markup docs: i2c: avoid using ReST :doc:`foo` markup docs: kernel-hacking: hacking.rst: avoid using ReST :doc:`foo` markup docs: networking: devlink: avoid using ReST :doc:`foo` markup docs: PCI: endpoint: pci-endpoint-cfs.rst: avoid using ReST :doc:`foo` markup docs: PCI: pci.rst: avoid using ReST :doc:`foo` markup docs: process: submitting-patches.rst: avoid using ReST :doc:`foo` markup docs: security: landlock.rst: avoid using ReST :doc:`foo` markup docs: trace: coresight: coresight.rst: avoid using ReST :doc:`foo` markup docs: trace: ftrace.rst: avoid using ReST :doc:`foo` markup docs: userspace-api: landlock.rst: avoid using ReST :doc:`foo` markup docs: virt: kvm: s390-pv-boot.rst: avoid using ReST :doc:`foo` markup docs: x86: avoid using ReST :doc:`foo` markup .../PCI/endpoint/pci-endpoint-cfs.rst | 2 +- Documentation/PCI/pci.rst | 6 +-- .../special-register-buffer-data-sampling.rst | 3 +- Documentation/admin-guide/pm/intel_idle.rst | 16 +++++--- Documentation/admin-guide/pm/intel_pstate.rst | 9 +++-- Documentation/admin-guide/sysctl/abi.rst | 2 +- Documentation/admin-guide/sysctl/kernel.rst | 37 ++++++++++--------- Documentation/block/biodoc.rst | 2 +- Documentation/bpf/bpf_lsm.rst | 13 ++++--- .../core-api/bus-virt-phys-mapping.rst | 2 +- Documentation/core-api/dma-api.rst | 5 ++- Documentation/core-api/dma-isa-lpc.rst | 2 +- Documentation/core-api/index.rst | 4 +- Documentation/dev-tools/kunit/api/index.rst | 8 ++-- Documentation/dev-tools/kunit/faq.rst | 2 +- Documentation/dev-tools/kunit/index.rst | 14 +++---- Documentation/dev-tools/kunit/start.rst | 4 +- Documentation/dev-tools/kunit/tips.rst | 5 ++- Documentation/dev-tools/kunit/usage.rst | 8 ++-- Documentation/dev-tools/testing-overview.rst | 16 ++++---- .../bindings/submitting-patches.rst | 11 +++--- Documentation/doc-guide/contributing.rst | 8 ++-- Documentation/driver-api/gpio/using-gpio.rst | 4 +- Documentation/driver-api/ioctl.rst | 2 +- Documentation/driver-api/pm/devices.rst | 8 ++-- .../surface_aggregator/clients/index.rst | 3 +- .../surface_aggregator/internal.rst | 15 ++++---- .../surface_aggregator/overview.rst | 6 ++- Documentation/driver-api/usb/dma.rst | 6 +-- .../acpi/dsd/data-node-references.rst | 3 +- .../firmware-guide/acpi/dsd/graph.rst | 2 +- .../firmware-guide/acpi/enumeration.rst | 7 ++-- Documentation/i2c/instantiating-devices.rst | 2 +- Documentation/i2c/old-module-parameters.rst | 3 +- Documentation/i2c/smbus-protocol.rst | 4 +- Documentation/kernel-hacking/hacking.rst | 4 +- .../networking/devlink/devlink-region.rst | 2 +- .../networking/devlink/devlink-trap.rst | 4 +- Documentation/process/submitting-patches.rst | 32 ++++++++-------- Documentation/security/landlock.rst | 3 +- Documentation/trace/coresight/coresight.rst | 8 ++-- Documentation/trace/ftrace.rst | 2 +- Documentation/userspace-api/landlock.rst | 11 +++--- Documentation/virt/kvm/s390-pv-boot.rst | 2 +- Documentation/x86/boot.rst | 4 +- Documentation/x86/mtrr.rst | 2 +- 46 files changed, 171 insertions(+), 147 deletions(-) -- 2.31.1

5 years, 3 months

Invitation to Project Monitoring and Evaluation with Data Management and Analysis July 2021 Workshop

by Jackson From FDC-K Africa

5 years, 3 months

Re: ThunderX2 and Coresight bring up

by Zhenghao Hu

Hi, We are a group of researchers from NYU trying to bring up Coresight ETM interfaces on ThunderX2. So we dug out this old thread ( https://lists.linaro.org/pipermail/coresight/2018-August/001626.html) and trying to get things spinning. We are current on Linux 5.12.9 kernel, but it seems some of the DTS entries are missing from the upstream. Just to be sure, would it be possible that you could share the DTS scripts? Thank you! Zhenghao

5 years, 3 months

[PATCH v6 0/1] perf cs-etm: Split Coresight decode by aux records

by James Clark

Changes since v5: * Fixed typo in commit message * Indentation fix James Clark (1): perf cs-etm: Split Coresight decode by aux records tools/perf/util/cs-etm.c | 156 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 155 insertions(+), 1 deletion(-) -- 2.28.0

5 years, 3 months

[PATCH v5 0/1] perf cs-etm: Split Coresight decode by aux records

by James Clark

Changes since RFC v4: * Style and indentation fixes * Add a warning when the buffer isn't found (suggested by Leo) * Undo change to set 'etm->data_queued' * Replace 'matchesCpuPid' with early exit when CPU/TID doesn't match * Check more return value errors * Remove TODOs from commit message and code * Add motivation to commit message James Clark (1): perf cs-etm: Split Coresight decode by aux records tools/perf/util/cs-etm.c | 158 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 157 insertions(+), 1 deletion(-) -- 2.28.0

5 years, 3 months

[PATCHv2 0/4] perf/core: Add support to exclude kernel mode PMU tracing

by Sai Prakash Ranjan

Hardware assisted tracing families such as ARM Coresight, Intel PT provides rich tracing capabilities including instruction level tracing and accurate timestamps which are very useful for profiling and also pose a significant security risk. One such example of security risk is when kernel mode tracing is not excluded and these hardware assisted tracing can be used to analyze cryptographic code execution. In this case, even the root user must not be able to infer anything. To explain it more clearly in the words of a security team member (credits: Mattias Nissler), "Consider a system where disk contents are encrypted and the encryption key is set up by the user when mounting the file system. From that point on the encryption key resides in the kernel. It seems reasonable to expect that the disk encryption key be protected from exfiltration even if the system later suffers a root compromise (or even against insiders that have root access), at least as long as the attacker doesn't manage to compromise the kernel." Here the idea is to protect such important information from all users including root users since root privileges does not have to mean full control over the kernel [1] and root compromise does not have to be the end of the world. But "Peter said even the regular counters can be used for full branch trace, the information isn't as accurate as PT and friends and not easier but is good enough to infer plenty". This would mean that a global tunable config for all kernel mode pmu tracing is more appropriate than the one targeting the hardware assisted instruction tracing. Currently we can exclude kernel mode tracing via perf_event_paranoid sysctl but it has following limitations, * No option to restrict kernel mode instruction tracing by the root user. * Not possible to restrict kernel mode instruction tracing when the hardware assisted tracing IPs like ARM Coresight ETMs use an additional interface via sysfs for tracing in addition to perf interface. So introduce a new config CONFIG_EXCLUDE_KERNEL_PMU_TRACE to exclude kernel mode pmu tracing for all users including root which will be generic and applicable to all hardware tracing families and which can also be used with other interfaces like sysfs in case of ETMs. Patch 1 adds this new config and the support in perf core to exclude all kernel mode PMU tracing. Patch 2 adds the perf evsel warning message when the perf tool users attempt to perform a kernel mode trace with the config enabled to exclude the kernel mode tracing. Patch 3 and Patch 4 adds the support for excluding kernel mode for ARM Coresight ETM{4,3}XX sysfs mode using the newly introduced generic config. [1] https://lwn.net/Articles/796866/ Changes in v2: * Move from kernel mode instruction tracing to all kernel level PMU tracing (Peter) * Move the check and warning to the caller mode_store() (Doug) Sai Prakash Ranjan (4): perf/core: Add support to exclude kernel mode PMU tracing perf evsel: Print warning for excluding kernel mode instruction tracing coresight: etm4x: Add support to exclude kernel mode tracing coresight: etm3x: Add support to exclude kernel mode tracing drivers/hwtracing/coresight/coresight-etm3x-core.c | 3 +++ drivers/hwtracing/coresight/coresight-etm3x-sysfs.c | 6 ++++++ drivers/hwtracing/coresight/coresight-etm4x-core.c | 6 +++++- drivers/hwtracing/coresight/coresight-etm4x-sysfs.c | 6 ++++++ init/Kconfig | 11 +++++++++++ kernel/events/core.c | 3 +++ tools/perf/util/evsel.c | 3 ++- 7 files changed, 36 insertions(+), 2 deletions(-) -- QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation

5 years, 3 months

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight