Skip to content

Conversation

@keyonjie
Copy link
Contributor

back port memory management fixes from the main branch.

keyonjie and others added 13 commits July 30, 2021 16:48
Show heap status update with every pipeline going to be run, when
CONFIG_DEBUG_HEAP is enabled. This will help to monitor the heap memory
usage status.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Fix and log the information of block 0 also.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
No matter if CONFIG_DEBUG_HEAP selected or not, we need to print out
error message when allocation failed.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
The trace filtering will suppress useful logs and make debugging
difficult, disable it by default.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Add coverage to log out details during memory allocation, including
successful allocation, and all zone types heap.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Some minor corrections to the tigerlake HP SRAM organization.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Implementation of calculating the runtime heap size at run time, which
leverage the value of the _runtime_heap_size from platform linker script
at linking stage.

This will help to make full use of the HP SRAM banks for each cAVS
platforms, all of them available in .bss section will be used for
runtime heap allocation.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Define more runtime and runtime shared section counts to make full use
of the tigerlake platform.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Implementation of calculating the runtime heap size at run time for
Intel Tigerlake platforms.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Commit: 5aeb95b

Signed-off-by: Slawomir Blauciak <slawomir.blauciak@linux.intel.com>
9a26e45 config: apl: change image_size to the real SRAM size
8a2ea00 config: cnl: change image_size to the real SRAM size
1de9ccc config: jsl: change image_size to the real SRAM size
f52a078 config: icl: change image_size to the real SRAM size
8073ea3 config: tgl-h: change image_size to the real SRAM size
9e50a02 config: tgl: change image_size to the real SRAM size

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
246ea64 config: skl: change image_size to the real SRAM size
9c9e07c config: kbl: change image_size to the real SRAM size
44b37d1 config: sue: change image_size to the real SRAM size
580e4d6 config: tgl-cavs: change image_size to the real SRAM size

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
On platforms where we have plenty of SRAM banks, we can use a bigger
buffer zone to make running pipelines which ask for bigger
periods/buffers.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
@lgirdwood
Copy link
Member

@mwasko fyi - just to make sure this is on your radar.

@lgirdwood
Copy link
Member

@keyonjie are some of these back ported from main ? Do some still need merged into main ?

@keyonjie
Copy link
Contributor Author

keyonjie commented Aug 2, 2021

@keyonjie are some of these back ported from main ? Do some still need merged into main ?

yes, besides of #4521 and #4568, one new added commit (memory: tigerlake: use bigger buffer zone on TGL-U/LP) needed for the main branch also, I am waiting #4521 and #4568 got merged first, then the last PR to enlarge the buffer zone will be submitted on top of that on platforms including TGL-U/LP.

@lgirdwood
Copy link
Member

@mwasko @bkokoszx can you guys review here for tgl-013 ? Please merge if you approve for tgl 013.

@mwasko
Copy link
Contributor

mwasko commented Aug 4, 2021

@mwasko @bkokoszx can you guys review here for tgl-013 ? Please merge if you approve for tgl 013.

@lgirdwood we are waiting for FW full scope validation. As soon as we get the positive (hopefully) results I will proceed with the merge.

@mwasko mwasko merged commit f767a16 into thesofproject:tgl-013-drop-stable Sep 2, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants