HWPM driver uses nested structures and arrays of structures. The IP
structure setup logic allocates pointer arrays based on dynamic list of
IPs and aperture addresses. This dynamic list is required to search
given regops address in less amount of time.
However, there is a chance that the number of pointers computed
dynamically is huge. And huge amount of memory will be required for the
dynamic pointers array, which is impractical.
This, this patch modifies ip structure setup and address to aperture
conversion logic to use static indexes if the pointer array size is
huge.
This patch modifies relevant functions to always use static arrays
to access instance and aperture structures.
If dynamic pointers array is allocated, the patch adds logic to
translate dynamic index to static index using inst_index_mask for
instances and new added aperture_index for element level structures.
Add/update few log message to improve relayed information.
Bug 4707244
Change-Id: Ib4847e6575f82b628a3ce838ad69196a4bc08fed
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3186843
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: buildbot_gerritrpt <buildbot_gerritrpt@nvidia.com>
This patch fixes issues found during testing
and guidance provided by devtools. The following
is changed in this patch:
1. mcf_iobhx and mcf_ocu are merged into a single mcf_soc IP.
2a. c2c is changed from 2 instances to 1.
2b. Remove C2CS0/1 which are the broadcast apertures.
Also remove the allowlist offset specific to broadcast
aperture.
3. mss_hub is changed from 1 instance to 8.
4. mss_channel is changed from 1 instance to 32.
5. mc0 perfmux is added to mcf_clink.
6. mcf_core is changed from 1 instance to 8.
7. License headers updated where necessary.
8. c2c allowlist updated to have just the offsets common
to all links.
9. Added a verbose comment explaining the design of
th500_hwpm_force_enable_ips()
10. Added back validate_current_config module parameter
as many systems still don't support fuses.
11. If all F's are read back for a regop in ip_readl(),
return -ENODEV.
There is a corresponding patch to update the python scripts
that generated many of the C and header files.
Bug 4287384
Change-Id: I8e14b0165dfa1abb9f5e04de577a41f0eb278246
Signed-off-by: Vishal Aslot <vaslot@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3134365
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-by: Eric Lu <ericlu@nvidia.com>
GVS: buildbot_gerritrpt <buildbot_gerritrpt@nvidia.com>
Currently, conditions to compile HWPM driver based on build config is
not defined well in the Makefiles. Update Makefiles to
- use external chip specific flags to include chip source files
- add copyright information
- revise IP force enablement logic, remove unused MINIMAL_IP_ENABLE flag
- follow a standard way of including source files and config flags.
Jira THWPM-109
Change-Id: I6d32b5b67d34c65b56fb9cb9d6a1c4cca7b11cc6
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3121175
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: buildbot_gerritrpt <buildbot_gerritrpt@nvidia.com>
A recent change has led to EMC fuse mask calculation regression.
This is being corrected in this patch. The emc_fuse_disable mask
is set in such a way that, each bit corresponds to 4 MSS Channels.
For example, emc_fuse_disable mask=1100, corresponds to MSS_Channel0
to MSS_Channel7 being present, while MSS_Channel8 to MSS_Channel15
are floorswept. However, in HWPM Driver, the logic to represent a
floorswept IP element is indicated by '1'. Correct the logic to
indicate this.
Bug 4490868
Change-Id: Id83d9e1d983c3fbf8f58cef3a1ff45334d7eadd6
Signed-off-by: vasukis <vasukis@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3122752
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
A recent change has led to EMC fuse mask calculation regression.
This is being corrected in this patch. The emc_fuse_disable mask is
set in such a way that, each bit corresponds to 4 MSS Channels.
For example, emc_fuse_disable mask=1100, corresponds to MSS_Channel0
to MSS_Channel7 being present, while MSS_Channel8 to MSS_Channel15
are floorswept. However, in HWPM Driver, the logic to represent
a floorswept IP element is indicated by '1'. Correct the logic to
indicate this.
Bug 4490868
Signed-off-by: vasukis <vasukis@nvidia.com>
Change-Id: Ia3825db29715e04aa43822283b160252d00f0a81
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3099298
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
ACPI configs are not required for aaos as
aaos is booted with dtb and not acpi.
Disabling CONFIG_ACPI results in a build failure as
it's undefined in the #if directive
so adding this check to see whether it is defined
resolves the issue and allows aaos to build
successfully with CONFIG_ACPI disabled
Bug 4559177
Change-Id: I9f068c373d6dc57acb610a107eb8a2e90a0e944b
Signed-off-by: Ahmad Chaudhry <ahmadc@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3115456
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
- Modify condition to include TH500 files for correct config. Since
TH500 is only supported with BaseOS and TinyLinux, the TH500 HWPM
config flag will be defined as part of the BaseOS/TinyLinux builds.
- Add new debug log mask for active debugs. This will allow us to enable
debug messages related to active debugs reducing amount of logs.
- Add condition to check ARCH_TEGRA config required for kernel specific
APIs.
Jira THWPM-69
Change-Id: I637bdbd2e5d72808611f63f4f719e5072f85ca34
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2978365
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
Tested-by: Vasuki Shankar <vasukis@nvidia.com>
HWPM code from HWPM repo is not currently used to compile with kernel
5.10. However, CL to compile HWPM repo for kernel 5.10 is required to
validate latest changes on Pre-Si.
Since conftest is only available for kernel version later than 5.10.
Add condition to include conftest only if HWPM is used as OOT module.
Bug 4119327
Change-Id: I760164447ff5c340884212f83966af72f1ee27da
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3011333
Tested-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Jonathan Hunter <jonathanh@nvidia.com>
Reviewed-by: Vishal Aslot <vaslot@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
The conftest script already has a test for checking which variant of the
get_user_pages() function is present in the kernel. So use the
definition generated by conftest to select which function variant is
used.
Bug 4276500
Change-Id: I29d216c8cead657c1daca4ce11b3dc3f74928467
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3015357
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Currently, HWPM requires raw readl/writel functions
to access sticky bits and as workaround for IP registers.
- Move the raw readl/writel logic along with IO mapping
of the address to a static function.
- Implement the wrapper functions to access sticky bits
and IP registers to use the created static functions.
Jira THWPM-86
Change-Id: Ib0b3229d4b8795d19aca142233622a166436e3bd
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/3014028
Reviewed-by: Adeel Raza <araza@nvidia.com>
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
This patch adds support for MCF SOC performance
monitoring in the driver. MCF SOC has two different
types of perfmuxes connected to the same perfmon:
one is the OCU type and the other is IBHX and OBHX.
IBHX is only accessible via MC16 aperture. Therefore,
this patch adds two separate IPs: OCU and IOBHX.
However, both are tied to the MCF SOC perfmon (mcfsoc0).
Bug 4287384
Signed-off-by: Vishal Aslot <vaslot@nvidia.com>
Change-Id: If15498a44e02270f9106337078931edbe043c254
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2986232
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
This patch adds support for C-NVLINK performance
monitoring in the driver. C-NVLINK consists of
RX, TX, and CTRL apertures, each with its own
perfmux signals and perfmons. So this patch
breaks them up into three sets of perfmux-perfmon
data structures.
Bug 4287384
Signed-off-by: Vishal Aslot <vaslot@nvidia.com>
Change-Id: Id8be4c965018125765f75a7b8bc8ab809bb7f976
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2999166
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
In Linux v6.2, the 'struct class.devnode()' function was updated to take
a 'const struct device *' instead of a 'struct device *'. A test has
been added to the conftest script to check for this and so instead of
relying on kernel version, use the definition generated by conftest to
select the appropriate function to use.
This is beneficial for working with 3rd party Linux kernels that may
have back-ported upstream changes into their kernel and so the kernel
version checks do not work.
Bug 4119327
Change-Id: I751b7401adee7b337192e255253b974cbd803642
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2991966
(cherry picked from commit 4b2fd8250d)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2995574
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
HWPM resource manager in QNX will query register read/write
ops to the IP debug node exposed. This is done via devctl
calls from the HWPM Res Mgr. Hence, update the NVDEC debug
node name in ip source file.
Bug 4170733
DOS-SHR-7601
Change-Id: I817aa18be43534907d761c992b9953918a39525d
Signed-off-by: vasukis <vasukis@nvidia.com>
(cherry picked from commit 7ed60c287e1253b834bfe050952240e97549e320)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2991341
Reviewed-by: Vishal Aslot <vaslot@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
- Set the 'CONFIG_T234_HWPM_IP_NVDEC' defconfig in HWPM
Makefile, so that nvdec IP related code can be compiled
alongside HWPM driver. This is required for enabling
NVDEC IP for profiling by HWPM.
- This change affects both L4T and AV+L configs.
DOS-SHR-7601
Change-Id: I654fc3024731660d20c874b1e31659bc28627191
Signed-off-by: vasukis <vasukis@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2983399
Reviewed-by: Vishal Aslot <vaslot@nvidia.com>
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
- HALs get_rtr_int_idx and get_ip_max_idx return the chip specific
router index and number of IPs. This information is static for a chip
and doesn't require any input. Hence, update the HAL definition to not
require hwpm pointer as an argument. Update definition and references
for these HALs.
- Add new HAL to get PMA and RTR structure pointers. Implement and
update other chip specific functions to use new HAL.
- Add new timer macro to check a condition and timeout after given
retries. Update necessary code to use new timer macro.
- Correct validate_emc_config function to compute correct available mss
channel mask based on fuse value.
- Update tegra_hwpm_readl and tegra_hwpm_writel macros to assert error
value. This way error checks are added at one spot and not sprinkled all
over the driver code.
- Update get_mem_bytes_put_ptr() and membuf_overflow_status() to return
error as function return and accept arguments to return mem_head pointer
and overflow status respectively. Add overflow status macros to use
throughout driver. Update HAL definition and references accordingly.
- conftest is only compiled for OOT config atm. Add OOT config check to
include conftest header.
Jira THWPM-109
Change-Id: I77d150e860fa344a1604d241e27718150fdb8647
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2982555
Reviewed-by: Adeel Raza <araza@nvidia.com>
Reviewed-by: Vishal Aslot <vaslot@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
HWPM resource manager in QNX will query register read/write
ops to the IP debug nodes exposed. This is done via devctl
calls from the HWPM Res Mgr. Hence, update the IP debug node
names in ip souce files.
Bug 4170733
DOS-SHR-7601
Change-Id: I58a39305aa8d6fcbbe01494d1e18069a369ee46f
Signed-off-by: vasukis <vasukis@nvidia.com>
(cherry picked from commit d37297cb494bb6bfc3b531e38302de18d0fddfc5)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2985248
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Determining whether the header file iosys-map.h is present in the kernel
is currently determine by kernel version. However, for Linux v5.15,
iosys-map.h has been backported in order to support simple-framebuffer
for early display. Therefore, we cannot rely on the kernel version to
indicate whether iosys-map is present. This is also true for 3rd party
Linux kernels that backport changes as well. Fix this by adding a
compile time flag, that will be set accordingly by the conftest script
if this header is present.
Bug 4119327
Bug 4228080
Change-Id: I9de07a4615a6c9da504b36750c48e73e200da301
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2974080
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove unused vmas parameter from get_user_pages() based
on following change in core kernel.
=====
Upstream commit "54d020692b34"
mm/gup: remove unused vmas parameter from get_user_pages()
Patch series "remove the vmas parameter from GUP APIs", v6.
(pin_/get)_user_pages[_remote]() each provide an optional output parameter
for an array of VMA objects associated with each page in the input range.
These provide the means for VMAs to be returned, as long as mm->mmap_lock
is never released during the GUP operation (i.e. the internal flag
FOLL_UNLOCKABLE is not specified).
In addition, these VMAs can only be accessed with the mmap_lock held and
become invalidated the moment it is released.
The vast majority of invocations do not use this functionality and of
those that do, all but one case retrieve a single VMA to perform checks
upon.
It is not egregious in the single VMA cases to simply replace the
operation with a vma_lookup(). In these cases we duplicate the (fast)
lookup on a slow path already under the mmap_lock, abstracted to a new
get_user_page_vma_remote() inline helper function which also performs
error checking and reference count maintenance.
The special case is io_uring, where io_pin_pages() specifically needs to
assert that the VMAs underlying the range do not result in broken
long-term GUP file-backed mappings.
As GUP now internally asserts that FOLL_LONGTERM mappings are not
file-backed in a broken fashion (i.e. requiring dirty tracking) - as
implemented in "mm/gup: disallow FOLL_LONGTERM GUP-nonfast writing to
file-backed mappings" - this logic is no longer required and so we can
simply remove it altogether from io_uring.
Eliminating the vmas parameter eliminates an entire class of danging
pointer errors that might have occured should the lock have been
incorrectly released.
In addition, the API is simplified and now clearly expresses what it is
intended for - applying the specified GUP flags and (if pinning) returning
pinned pages.
This change additionally opens the door to further potential improvements
in GUP and the possible marrying of disparate code paths.
I have run this series against gup_test with no issues.
Thanks to Matthew Wilcox for suggesting this refactoring!
This patch (of 6):
No invocation of get_user_pages() use the vmas parameter, so remove it.
The GUP API is confusing and caveated. Recent changes have done much to
improve that, however there is more we can do. Exporting vmas is a prime
target as the caller has to be extremely careful to preclude their use
after the mmap_lock has expired or otherwise be left with dangling
pointers.
Removing the vmas parameter focuses the GUP functions upon their primary
purpose - pinning (and outputting) pages as well as performing the actions
implied by the input flags.
This is part of a patch series aiming to remove the vmas parameter
altogether.
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
=====
Bug 4276500
Change-Id: Ie2833b7aa4e8fef1362694de6e8a27bba553e3d4
Signed-off-by: Shardar Mohammed <smohammed@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2978634
Reviewed-by: Laxman Dewangan <ldewangan@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
Kernel 5.10 support
- Use code from HWPM repo with kernel 5.10 builds.
- Add HWPM source files as built-in driver as IP drivers like PVA,
DLA are built-in and dependent on HWPM for IP registration.
HWPM next chips support
- Currently, only HWPM code in the current (public) repo is included in
compilation on TOT. This patch includes Makefile from HWPM next repo for
next/future chips.
Jira THWPM-69
Change-Id: I8f2bbcabf0c01f2b2cbc722c481a1fe83490c76b
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2921358
Reviewed-by: Adeel Raza <araza@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
- CONFIG_TEGRA_LINUX_PROD is used to indicate if the build belongs
to that of Prod or Prod_Debug. Use the Config to compile mock
hwpm driver in case of Prod builds. The reason being, IPs like
PVA and NVDLA are dependent on tegra_soc_hwpm_ip_register and
tegra_soc_hwpm_ip_unregister Symbols during boot.
- The packaging files only look for the nvhwpm drivers on
all build flavor. Hence, keep the same name HWPM driver
regardless of how it is build, fully supported or mock.
Bug 4206386
Change-Id: Ic554a7e7a22d55adb802636fd669c7d1fcb82830
Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
(cherry picked from commit e2f7b1a75312cfe486d9b256aefa263c151ccb68)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2948941
Tested-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Vedashree Vidwans <vvidwans@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
The config flags defined in Kconfig file are not available/used with
OOT kernel builds. To support all kernel versions, HWPM compiles
independent of CONFIG_TEGRA_SOC_HWPM flag. This also applies to
IP config flags which are not supported as well. Hence,
include HWPM IP files irrespective of the IP config flag status.
For OOT builds, use tegra_is_hypervisor_mode() instead of using
static function defined in HWPM driver.
Bug 4061775
Change-Id: Ifab4ad5c7c652a4ad17820a82b363e92280fdd1a
Signed-off-by: Vedashree Vidwans <vvidwans@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-hwpm/+/2918870
Reviewed-by: Vasuki Shankar <vasukis@nvidia.com>
Reviewed-by: Adeel Raza <araza@nvidia.com>
GVS: Gerrit_Virtual_Submit <buildbot_gerritrpt@nvidia.com>
