- HWPM driver requires to know if an IP is available for performance
measurements. The ideal way is for IP driver registration with HWPM
driver. This way IP driver can share required power management and
register access function pointers.
- For IPs that do not have registration mechanism implemented, a
workaround to set an IP enabled is implemented in the HWPM driver.
- In the recent releases, MSS channel, PVA and DLA IPs are the only PORs
for production builds. Currently, this is acheived using the combination
of minimal build and force enable flags.
- However, this implementation limits the number of enabled IPs on TOT
to only minimal expected ones.
- This patch modifies the force enable IP logic implementation to make
force enable and minimal IP flag definition more clear.
- CONFIG_T234_HWPM_ALLOW_FORCE_ENABLE should be used to purposely enable
IPs that do not have registration mechanism implemented. This flag is
used for POR or non-POR IPs. Ideally, all IPs should implement HWPM
registration and force enable flag should not be required.
- CONFIG_TEGRA_HWPM_MINIMAL_IP_ENABLE should be used to implement logic
for POR IPs. In other words, if CONFIG_TEGRA_HWPM_MINIMAL_IP_ENABLE is
not defined, non-POR IPs should be included in the builds. This patch
sets MINIMAL IP config only for external non-safety builds.
- Fix include t234_perfmon_device_index.h error in t234_mss_mcf.c file.
- Add missing device index for PVA perfmon C0.
Jira THWPM-41
Change-Id: I20651eac14b6d42e5bf3cc5164d1f64ec208dc04
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2818735
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Property support-soc-tools was added mainly to provide user's control to
enable/disable HWPM feature. Since, the same functionality can be
achieved using "status" in device node, support-soc-tools property is
redundant. Hence, this property is removed from HWPM device node.
Update HWPM driver probe to not depend on support-soc-tools property.
JIRA THWPM-48
Change-Id: Ieaa5c77e6c62a59e938832f886c5a82031139ac6
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2797449
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
Add Device_index tag to read IP perfmon register address
index from ACPI or DTSI tables. Device_index will be
used to retrieve resource information from acpi tables
or device trees. This will replace current logic to
procure resource details using device names.
JIRA THWPM-71
Change-Id: I964546f2262dd77ec0acfb58f49d044c870deae6
Signed-off-by: vasukis <vasukis@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2797448
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Tested-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
Currently, dt_index aperture spec actually holds the element index of
the aperture within the IP instance. Hence, replace dt_index with
element_index to better indicate its purpose.
JIRA THWPM-71
Change-Id: Ic805da3281c60991e7966a80f442d84a2cfcf7cc
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2797447
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
- Make clock reset functions into HALs. This way we can control
clock-reset logic for any chip. Set clock-reset HAL pointers to
appropriate functions.
- Remove clock-reset function wrappers as these will not be required and
corresponding HAL pointers will be used.
- As clock reset init is defined as a HAL, modify probe logic to
initialize chip info before invoking any HALs.
- Move common/primary HAL validation logic to common code and implement
new HAL to validate chip specific HALs. This way we can ensure that HAL
pointers are set as expected.
- Keep only one definition for t234_hwpm_init_chip_info as t234 should
always be initialized and hence only single definition should be
available.
- Expected return value of 0 indicates success and any other value
(mostly negative in current logic) indicates error, compare function
returns with 0 to print error in tegra_hwpm_release().
- Since a build can support both ACPI and device tree, update
init_chip_info() to retrieve chip information from ACPI and device tree
in case of failure.
Jira THWPM-41
Bug 3583624
Change-Id: I03fefae0b3b0c8ce46d175d39e4fdbb45e2bb22f
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2789668
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2797445
- Zeroing of PMA trigger registers is unnecessary. Remove corresponding
logic from HWPM teardown function.
- During device open, add a check for PMA/RTR status. This will ensure
that PMA/RTR are ready to start new profiling session. Device open will
fail if RTR and PMA enginestatus is not ready(idle).
- SOC HWPM driver disables and releases all reserved IPs before teardown
steps. Update teardown logic to zero out IP allowlist registers during
teardown.
Jira THWPM-41
Bug 3714516
Change-Id: Iede5a5ed9860e2a73c8e4a04aeedfc061458c793
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2776229
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2797444
HWPM files are copied from the previous source in linux-nvidia repo
withgit history. Create folders and move files to obtain expected folder
structure.
Bug 3787076
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
