kernel/linux.git/drivers/gpu/drm/etnaviv, branch v5.10.257

drm/etnaviv: fix flush sequence logic

2025-12-06T21:08:07+00:00

[ Upstream commit a042beac6e6f8ac1e923784cfff98b47cbabb185 ] The current logic uses the flush sequence from the current address space. This is harmless when deducing the flush requirements for the current submit, as either the incoming address space is the same one as the currently active one or we switch context, in which case the flush is unconditional. However, this sequence is also stored as the current flush sequence of the GPU. If we switch context the stored flush sequence will no longer belong to the currently active address space. This incoherency can then cause missed flushes, resulting in translation errors. Fixes: 27b67278e007 ("drm/etnaviv: rework MMU handling") Signed-off-by: Tomeu Vizoso Signed-off-by: Lucas Stach Reviewed-by: Christian Gmeiner Link: https://lore.kernel.org/r/20251021093723.3887980-1-l.stach@pengutronix.de Signed-off-by: Sasha Levin

drm/etnaviv: Fix page property being used for non writecombine buffers

2025-03-13T11:46:45+00:00

[ Upstream commit 834f304192834d6f0941954f3277ae0ba11a9a86 ] In the etnaviv_gem_vmap_impl() function, the driver vmap whatever buffers with write combine(WC) page property, this is incorrect. Cached buffers should be mapped with the cached page property and uncached buffers should be mapped with the uncached page property. Fixes: a0a5ab3e99b8 ("drm/etnaviv: call correct function when trying to vmap a DMABUF") Signed-off-by: Sui Jingfeng Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin

drm/etnaviv: flush shader L1 cache after user commandstream

2024-12-14T18:48:18+00:00

commit 4f8dbadef085ab447a01a8d4806a3f629fea05ed upstream. The shader L1 cache is a writeback cache for shader loads/stores and thus must be flushed before any BOs backing the shader buffers are potentially freed. Cc: stable@vger.kernel.org Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Signed-off-by: Greg Kroah-Hartman

drm/etnaviv: hold GPU lock across perfmon sampling

2024-12-14T18:47:53+00:00

[ Upstream commit 37dc4737447a7667f8e9ec790dac251da057eb27 ] The perfmon sampling mutates shared GPU state (e.g. VIVS_HI_CLOCK_CONTROL to select the pipe for the perf counter reads). To avoid clashing with other functions mutating the same state (e.g. etnaviv_gpu_update_clock) the perfmon sampling needs to hold the GPU lock. Fixes: 68dc0b295dcb ("drm/etnaviv: use 'sync points' for performance monitor requests") Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin

drm/etnaviv: fix power register offset on GC300

2024-12-14T18:47:53+00:00

[ Upstream commit 61a6920bb604df3a0e389a2a9479e1e233e4461d ] Older GC300 revisions have their power registers at an offset of 0x200 rather than 0x100. Add new gpu_read_power and gpu_write_power functions to encapsulate accesses to the power addresses and fix the addresses. Signed-off-by: Doug Brown Signed-off-by: Lucas Stach Stable-dep-of: 37dc4737447a ("drm/etnaviv: hold GPU lock across perfmon sampling") Signed-off-by: Sasha Levin

drm/etnaviv: dump: fix sparse warnings

2024-12-14T18:47:53+00:00

[ Upstream commit 03a2753936e85beb8239fd20ae3fb2ce90209212 ] This patch fixes the following sparse warnings, by adding the missing endianess conversion functions. | etnaviv/etnaviv_dump.c:78:26: warning: restricted __le32 degrades to integer | etnaviv/etnaviv_dump.c:88:26: warning: incorrect type in assignment (different base types) | etnaviv/etnaviv_dump.c:88:26: expected restricted __le32 [usertype] reg | etnaviv/etnaviv_dump.c:88:26: got unsigned short const | etnaviv/etnaviv_dump.c:89:28: warning: incorrect type in assignment (different base types) | etnaviv/etnaviv_dump.c:89:28: expected restricted __le32 [usertype] value | etnaviv/etnaviv_dump.c:89:28: got unsigned int | etnaviv/etnaviv_dump.c:210:43: warning: incorrect type in assignment (different base types) | etnaviv/etnaviv_dump.c:210:43: expected restricted __le32 | etnaviv/etnaviv_dump.c:210:43: got long Signed-off-by: Marc Kleine-Budde Signed-off-by: Lucas Stach Stable-dep-of: 37dc4737447a ("drm/etnaviv: hold GPU lock across perfmon sampling") Signed-off-by: Sasha Levin

drm/etnaviv: Request pages from DMA32 zone on addressing_limited

2024-12-14T18:47:53+00:00

[ Upstream commit 13c96ac9a3f0f1c7ba1ff0656ea508e7fa065e7e ] Remove __GFP_HIGHMEM when requesting a page from DMA32 zone, and since all vivante GPUs in the system will share the same DMA constraints, move the check of whether to get a page from DMA32 to etnaviv_bind(). Fixes: b72af445cd38 ("drm/etnaviv: request pages from DMA32 zone when needed") Suggested-by: Sui Jingfeng Signed-off-by: Xiaolei Wang Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin

drm/etnaviv: rework linear window offset calculation

2024-12-14T18:47:53+00:00

[ Upstream commit 4bfdd2aa67fbfba09d7c32a4c7fd4c5eb1052bce ] The current calculation based on the required_dma mask can be significantly off, so that the linear window only overlaps a small part of the DRAM address space. This can lead to the command buffer being unmappable, which is obviously bad. Rework the linear window offset calculation to be based on the command buffer physical address, making sure that the command buffer is always mappable. Tested-by: Primoz Fiser Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Stable-dep-of: 13c96ac9a3f0 ("drm/etnaviv: Request pages from DMA32 zone on addressing_limited") Signed-off-by: Sasha Levin

drm/etnaviv: fix DMA direction handling for cached RW buffers

2024-08-19T03:40:49+00:00

[ Upstream commit 58979ad6330a70450ed78837be3095107d022ea9 ] The dma sync operation needs to be done with DMA_BIDIRECTIONAL when the BO is prepared for both read and write operations. Fixes: a8c21a5451d8 ("drm/etnaviv: add initial etnaviv DRM driver") Signed-off-by: Lucas Stach Reviewed-by: Philipp Zabel Reviewed-by: Christian Gmeiner Signed-off-by: Sasha Levin

drm/etnaviv: Restore some id values

2024-04-13T10:58:27+00:00

[ Upstream commit b735ee173f84d5d0d0733c53946a83c12d770d05 ] The hwdb selection logic as a feature that allows it to mark some fields as 'don't care'. If we match with such a field we memcpy(..) the current etnaviv_chip_identity into ident. This step can overwrite some id values read from the GPU with the 'don't care' value. Fix this issue by restoring the affected values after the memcpy(..). As this is crucial for user space to know when this feature works as expected increment the minor version too. Fixes: 4078a1186dd3 ("drm/etnaviv: update hwdb selection logic") Cc: stable@vger.kernel.org Signed-off-by: Christian Gmeiner Reviewed-by: Tomeu Vizoso Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin