Port patches from u/mr0/master to main branch #115
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Program name for this pr is not compatable with other dependent prs, for more details please check tracked_on |
sysopenci
requested review from
feijiang1,
gkdeepa,
renchenglei,
yaoxinshi-intel,
YuanjunHuang and
yyao3
|
Improper Commit Message |
Additionally need read VIRTGPU_PARAM_RESOURCE_BLOB. Tracked-On: OAM-129380 Signed-off-by: lihaihong <[email protected]>
..., otherwise we are supposed to do atomic commit in this frame and the sleep is just a waste of time. Tracked-On: OAM-128362 Signed-off-by: Weifeng Liu <[email protected]>
Add hw min/max resolution support check for device
composition.
Test-done:
Android boot and gfxbench tested
Tracked-On: OAM-128410
Signed-off-by: Jia, Lin A <[email protected]>
|
Improper Commit Message |
Background: To get best performance we must guarantee that scan-out buffers used for composition in surfaceflinger reside in GPU local memory, but importing these buffers into virtio-GPU will migrate the buffers from local memory to system memory, which will highly impact the performance. To avoid migration of these client-composited buffers, allocate a shadow buffer for each of them and import the shadow buffers into virtio-GPU for scanning-out. Right before atomic commit, leverage GPU blit engine to copy content to shadow buffer. Use shadow buffers only when feature ALLOW_P2P of virtio-GPU is not present and dGPU exists. There are several GPU instructions to blit memory: - XY_FAST_COPY_BLT (BSpec: 47982), - XY_SRC_COPY_BLT (BSpec: 48002), - XY_BLOCK_COPY_BLT (BSpec: 3678). By experiment, XY_FAST_COPY is much faster than the other two instructions. Add class IntelBlitter to manage blitter resource, this makes the code more robust and readable. Open new fd for every blit context to avoid blocking the user space when copying multiple layers. Tracked-On: OAM-124505 Signed-off-by: Weifeng Liu <[email protected]>
Tracked-On: OAM-124505 Signed-off-by: lihaihong <[email protected]>
* Save first shadow buffer handle and fd for destroying. * Make i915_device local to avoid race condition. Tracked-On: OAM-129252 Signed-off-by: Weifeng Liu <[email protected]>
|
Improper Commit Message |
Add a flag to the HwcLayer which will be set when the layer is allowed to be shared as local memory objects without migrating to system memory, primarily used in the case that the layer is to be displayed on dGPU. If this flag is enabled, we will set the DMA BUF name to "p2p" via DMA_BUF_SET_NAME ioctl. The name acts as a hint in the KMD for local memory sharing. This feature cannot be achieved without the help from virtio-GPU KMD: now virtio-GPU will expose a bit mask (queried by ALLOW_P2P parameter) indicating whether local memory sharing is allowed for each scan-out. Change log: - v2: combine commit "Avoid dereferencing null pointer in headless mode" Tracked-On: OAM-129252 Signed-off-by: Weifeng Liu <[email protected]>
In current implementation, blitting happens in dGPU (PF) pass-through mode, which is not what we want. Tracked-On: OAM-130009 Signed-off-by: Weifeng Liu <[email protected]>
Tracked-On: OAM-130974 Signed-off-by: Weifeng Liu <[email protected]>
No logic is changed in this commit. Tracked-On: OAM-130974 Signed-off-by: Weifeng Liu <[email protected]>
virtio-GPU on PCI bus with * vendor id 0x1af4 * device id 0x1110 * subvendor id 0x8086 * subdevice id 0x201 is reserved for usage in Linux in Container (LIC). Skip this device when creating drm devices. Tracked-On: OAM-131266 Signed-off-by: Weifeng Liu <[email protected]>
sysopenci
removed request for
renchenglei,
yyao3,
gkdeepa,
YuanjunHuang and
yaoxinshi-intel
|
Android CI has started Engineering Build for this issue ,Please check the linked Tracked-On issue/Android CI Web for more details. |
|
SUCCESS: Android CI has completed Engineering Build for this issue.Please check the linked Tracked-On issue/Android CI Web for more details. |
|
Android CI has started MERGE Build for this pr ,Please check the linked Tracked-On issue/Android CI Web for more details. |
|
Android CI has completed MERGE Build for this pr, build is SUCCESS. Please check the linked Tracked-On issue/Android CI Web for more details. For Binaries: /cactus-absp-or-local/celadon-merge/1114 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.