user/sven/linux.git/include/linux/host1x.h, branch v4.19.259

gpu: host1x: Increase maximum DMA segment size

2019-07-31T05:26:59Z

[ Upstream commit 1e390478cfb527e34c9ab89ba57212cb05c33c51 ] Recent versions of the DMA API debug code have started to warn about violations of the maximum DMA segment size. This is because the segment size defaults to 64 KiB, which can easily be exceeded in large buffer allocations such as used in DRM/KMS for framebuffers. Technically the Tegra SMMU and ARM SMMU don't have a maximum segment size (they map individual pages irrespective of whether they are contiguous or not), so the choice of 4 MiB is a bit arbitrary here. The maximum segment size is a 32-bit unsigned integer, though, so we can't set it to the correct maximum size, which would be the size of the aperture. Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin

gpu: host1x: Use not explicitly sized types

2018-05-18T19:51:37Z

The number of words and the offset in a gather don't need to be explicitly sized, so make them unsigned int instead. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding

gpu: host1x: Rename relocarray -> relocs for consistency

2018-05-18T19:51:25Z

All other array variables use a plural, and this is the only one using the *array suffix. This is confusing, so rename it for consistency. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding

gpu: host1x: Store pointer to client in jobs

2018-05-18T19:50:24Z

Rather than storing some identifier derived from the application context that can't be used concretely anywhere, store a pointer to the client directly so that accesses can be made directly through that client object. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding

gpu: host1x: Remove wait check support

2018-05-18T19:50:04Z

The job submission userspace ABI doesn't support this and there are no plans to implement it, so all of this code is dead and can be removed. Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding

gpu: host1x: syncpt: Request syncpoints per client

2017-10-20T12:19:51Z

Rather than request syncpoints for a struct device *, request them for a struct host1x_client *. This is important because subsequent patches are going to break the assumption that host1x will always be the parent for devices requesting a syncpoint. It's also a more natural choice because host1x clients are really the only ones that will know how to deal with syncpoints. Note that host1x clients are always guaranteed to be children of host1x, regardless of their location in the device tree. Signed-off-by: Thierry Reding

gpu: host1x: Refactor channel allocation code

2017-06-15T12:25:38Z

This is largely a rewrite of the Host1x channel allocation code, bringing several changes: - The previous code could deadlock due to an interaction between the 'reflock' mutex and CDMA timeout handling. This gets rid of the mutex. - Support for more than 32 channels, required for Tegra186 - General refactoring, including better encapsulation of channel ownership handling into channel.c Signed-off-by: Mikko Perttunen Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding

gpu: host1x: Correct swapped arguments in the is_addr_reg() definition

2017-06-15T12:24:18Z

Arguments of the .is_addr_reg() are swapped in the definition of the function, that is quite confusing. Signed-off-by: Dmitry Osipenko Reviewed-by: Erik Faye-Lund Reviewed-by: Mikko Perttunen Signed-off-by: Thierry Reding

gpu: host1x: Forbid unrelated SETCLASS opcode in the firewall

2017-06-15T12:23:50Z

Several channels could be made to write the same unit concurrently via the SETCLASS opcode, trusting userspace is a bad idea. It should be possible to drop the per-client channel reservation and add a per-unit locking by inserting MLOCK's to the command stream to re-allow the SETCLASS opcode, but it will be much more work. Let's forbid the unit-unrelated class changes for now. Signed-off-by: Dmitry Osipenko Reviewed-by: Erik Faye-Lund Reviewed-by: Mikko Perttunen Signed-off-by: Thierry Reding

drm/tegra: Correct copying of waitchecks and disable them in the 'submit' IOCTL

2017-06-15T12:16:37Z

The waitchecks along with multiple syncpoints per submit are not ready for use yet, let's forbid them for now. Signed-off-by: Dmitry Osipenko Reviewed-by: Mikko Perttunen Signed-off-by: Thierry Reding