<html><head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> </head> <body> <div class="moz-cite-prefix">On 2/21/20 2:19 AM, Luben Tuikov wrote: </div> <blockquote type="cite" cite="mid:9e26a27b-eeaa-39b3-dacc-9f3777f3cf92@amd.com"> <pre class="moz-quote-pre" wrap="">On 2020-02-19 08:53, Nirmoy Das wrote: </pre> <blockquote type="cite"> <pre class="moz-quote-pre" wrap="">Calculate GPU offset in radeon_bo_gpu_offset without depending on bo->offset Signed-off-by: Nirmoy Das <a class="moz-txt-link-rfc2396E" href="mailto:nirmoy.das@amd.com"><nirmoy.das@amd.com></a> Reviewed-and-tested-by: Christian König <a class="moz-txt-link-rfc2396E" href="mailto:christian.koenig@amd.com"><christian.koenig@amd.com></a> --- drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_object.h | 16 +++++++++++++++- drivers/gpu/drm/radeon/radeon_ttm.c | 4 +--- 3 files changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 30e32adc1fc6..b7c3fb2bfb54 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2828,6 +2828,7 @@ extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size extern void radeon_program_register_sequence(struct radeon_device *rdev, const u32 *registers, const u32 array_size); +struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev); /* * vm diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index d23f2ed4126e..4d37571c7ff5 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -90,7 +90,21 @@ static inline void radeon_bo_unreserve(struct radeon_bo *bo) */ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) { - return bo->tbo.offset; + struct radeon_device *rdev; + u64 start = 0; + + rdev = radeon_get_rdev(bo->tbo.bdev); + + switch(bo->tbo.mem.mem_type) { </pre> </blockquote> <pre class="moz-quote-pre" wrap=""> LKCS wants a space after a keyword, "switch (" .</pre> </blockquote> Thanks Luben, will fix that for both radeon and amdgpu. <blockquote type="cite" cite="mid:9e26a27b-eeaa-39b3-dacc-9f3777f3cf92@amd.com"> <pre class="moz-quote-pre" wrap=""> </pre> <blockquote type="cite"> <pre class="moz-quote-pre" wrap="">+ case TTM_PL_TT: + start = rdev->mc.gtt_start; + break; + case TTM_PL_VRAM: + start = rdev->mc.vram_start; + break; + } </pre> </blockquote> <pre class="moz-quote-pre" wrap=""> Could this lookup have been parameterized by "mem_type" to be looked up by an index (possibly "mem_type") to result in something new like (pseudo-code): start = rdev->mc.mem_start_table[bo->tbo.mem.mem_type]; Where "mem_start_table" is a new table holding memory starts of particular memories. Then you don't need the switch-case. </pre> </blockquote> That would look good but I am afraid, amdgpu_ttm_domain_start() and radeon_bo_gpu_offset() will be the only consumer of mem_start_table. I think it is not worth to do a intrusive change for this patch series. Regards, Nirmoy </body> </html>