radeonsi: set a per-buffer flag that disables inter-process sharing
RFC PATCH 1/1 radeonsi: set a per-buffer flag that disables inter-process sharing
From: Marek Olšák <[email protected]>
for lower overhead in the CS ioctl
--- src/gallium/drivers/radeon/r600_buffer_common.c | 7 +++++++ src/gallium/drivers/radeon/radeon_winsys.h | 1 + src/gallium/winsys/amdgpu/drm/amdgpu_bo.c | 6 ++++++ 3 files changed, 14 insertions(+)
src/gallium/drivers/radeon/r600_buffer_common.c +7 -0
@@ -160,20 +160,27 @@ void r600_init_resource_fields(struct r600_common_screen *rscreen, }/* Tiled textures are unmappable. Always put them in VRAM. */ if ((res->b.b.target !=PIPE_BUFFER && !rtex->surface.is_linear) || res->flags &R600_RESOURCE_FLAG_UNMAPPABLE ) { res->domains =RADEON_DOMAIN_VRAM ; res->flags |=RADEON_FLAG_NO_CPU_ACCESS |RADEON_FLAG_GTT_WC ; } +/* Only displayable single-sample textures can be shared between +* processes. */ +if (res->b.b.target ==PIPE_BUFFER || + res->b.b.nr_samples >=2 || + rtex->surface.micro_tile_mode !=RADEON_MICRO_MODE_DISPLAY ) + res->flags |=RADEON_FLAG_NO_INTERPROCESS_SHARING ; +/* If VRAM is just stolen system memory, allow both VRAM and * GTT, whichever has free space. If a buffer is evicted from * VRAM to GTT, it will stay there. * * DRM 3.6.0 has good BO move throttling, so we can allow VRAM-only * placements even with a low amount of stolen VRAM. */ if (!rscreen->info.has_dedicated_vram && (rscreen->info.drm_major <3 || rscreen->info.drm_minor <6 ) && res->domains ==RADEON_DOMAIN_VRAM ) {
src/gallium/drivers/radeon/radeon_winsys.h +1 -0
@@ -47,20 +47,21 @@ enum radeon_bo_domain { /* bitfield */RADEON_DOMAIN_GTT =2 ,RADEON_DOMAIN_VRAM =4 ,RADEON_DOMAIN_VRAM_GTT =RADEON_DOMAIN_VRAM |RADEON_DOMAIN_GTT };enum radeon_bo_flag {/* bitfield */ RADEON_FLAG_GTT_WC = (1 <<0 ),RADEON_FLAG_NO_CPU_ACCESS = (1 <<1 ),RADEON_FLAG_NO_SUBALLOC = (1 <<2 ),RADEON_FLAG_SPARSE = (1 <<3 ), +RADEON_FLAG_NO_INTERPROCESS_SHARING = (1 <<4 ), };enum radeon_bo_usage {/* bitfield */ RADEON_USAGE_READ =2 ,RADEON_USAGE_WRITE =4 ,RADEON_USAGE_READWRITE =RADEON_USAGE_READ |RADEON_USAGE_WRITE ,/* The winsys ensures that the CS submission will be scheduled after * previously flushed CSs referencing this BO in a conflicting way. */
src/gallium/winsys/amdgpu/drm/amdgpu_bo.c +6 -0
@@ -31,20 +31,24 @@#include "amdgpu_cs.h" #include "os/os_time.h" #include "state_tracker/drm_driver.h" #include <amdgpu_drm.h> #include <xf86drm.h> #include <stdio.h> #include <inttypes.h> +#ifndef AMDGPU_GEM_CREATE_NO_INTERPROCESS_SHARING +#define AMDGPU_GEM_CREATE_NO_INTERPROCESS_SHARING (1 << 6) +#endif +/* Set to 1 for verbose output showing committed sparse buffer ranges. */ #define DEBUG_SPARSE_COMMITS 0struct amdgpu_sparse_backing_chunk {uint32_t begin, end; };static struct pb_buffer * amdgpu_bo_create(struct radeon_winsys *rws, uint64_t size,
@@ -395,20 +399,22 @@ static struct amdgpu_winsys_bo *amdgpu_create_bo(struct amdgpu_winsys *ws,if (initial_domain &RADEON_DOMAIN_VRAM ) request.preferred_heap |=AMDGPU_GEM_DOMAIN_VRAM ;if (initial_domain &RADEON_DOMAIN_GTT ) request.preferred_heap |=AMDGPU_GEM_DOMAIN_GTT ;if (flags &RADEON_FLAG_NO_CPU_ACCESS ) request.flags |=AMDGPU_GEM_CREATE_NO_CPU_ACCESS ;if (flags &RADEON_FLAG_GTT_WC ) request.flags |=AMDGPU_GEM_CREATE_CPU_GTT_USWC ; +if (flags &RADEON_FLAG_NO_INTERPROCESS_SHARING ) + request.flags |=AMDGPU_GEM_CREATE_NO_INTERPROCESS_SHARING ; r =amdgpu_bo_alloc (ws->dev, &request, &buf_handle);if (r) {fprintf (stderr,"amdgpu: Failed to allocate a buffer:\n" );fprintf (stderr,"amdgpu: size : %" PRIu64" bytes\n" , size);fprintf (stderr,"amdgpu: alignment : %u bytes\n" , alignment);fprintf (stderr,"amdgpu: domains : %u\n" , initial_domain); goto error_bo_alloc; }
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1500400020-11921-1-git-send-email-maraeo-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
For comments only. There are some assertion failures.
Marek
Quoted 120 lines · Marek Olšák
From: Marek Olšák <[email protected]>
for lower overhead in the CS ioctl
--- src/gallium/drivers/radeon/r600_buffer_common.c | 7 +++++++ src/gallium/drivers/radeon/radeon_winsys.h | 1 + src/gallium/winsys/amdgpu/drm/amdgpu_bo.c | 6 ++++++ 3 files changed, 14 insertions(+)src/gallium/drivers/radeon/r600_buffer_common.c +7
-0@@ -160,20 +160,27 @@ void r600_init_resource_fields(struct r600_common_screen *rscreen, }/* Tiled textures are unmappable. Always put them in VRAM. */ if ((res->b.b.target !=PIPE_BUFFER && !rtex->surface.is_linear) || res->flags &R600_RESOURCE_FLAG_UNMAPPABLE ) { res->domains =RADEON_DOMAIN_VRAM ; res->flags |=RADEON_FLAG_NO_CPU_ACCESS |RADEON_FLAG_GTT_WC ; } +/* Only displayable single-sample textures can be shared between +* processes. */ +if (res->b.b.target ==PIPE_BUFFER || + res->b.b.nr_samples >=2 || + rtex->surface.micro_tile_mode !=RADEON_MICRO_MODE_DISPLAY ) + res->flags |=RADEON_FLAG_NO_INTERPROCESS_SHARING ; +/* If VRAM is just stolen system memory, allow both VRAM and * GTT, whichever has free space. If a buffer is evicted from * VRAM to GTT, it will stay there. * * DRM 3.6.0 has good BO move throttling, so we can allow VRAM-only * placements even with a low amount of stolen VRAM. */ if (!rscreen->info.has_dedicated_vram && (rscreen->info.drm_major <3 || rscreen->info.drm_minor <6 ) && res->domains ==RADEON_DOMAIN_VRAM ) {src/gallium/drivers/radeon/radeon_winsys.h +1
-0@@ -47,20 +47,21 @@ enum radeon_bo_domain { /* bitfield */RADEON_DOMAIN_GTT =2 ,RADEON_DOMAIN_VRAM =4 ,RADEON_DOMAIN_VRAM_GTT =RADEON_DOMAIN_VRAM |RADEON_DOMAIN_GTT };enum radeon_bo_flag {/* bitfield */ RADEON_FLAG_GTT_WC = (1 <<0 ),RADEON_FLAG_NO_CPU_ACCESS = (1 <<1 ),RADEON_FLAG_NO_SUBALLOC = (1 <<2 ),RADEON_FLAG_SPARSE = (1 <<3 ), +RADEON_FLAG_NO_INTERPROCESS_SHARING = (1 <<4 ), };enum radeon_bo_usage {/* bitfield */ RADEON_USAGE_READ =2 ,RADEON_USAGE_WRITE =4 ,RADEON_USAGE_READWRITE =RADEON_USAGE_READ |RADEON_USAGE_WRITE ,/* The winsys ensures that the CS submission will be scheduled after * previously flushed CSs referencing this BO in a conflicting way. */src/gallium/winsys/amdgpu/drm/amdgpu_bo.c +6
-1@@ -31,20 +31,24 @@#include "amdgpu_cs.h" #include "os/os_time.h" #include "state_tracker/drm_driver.h" #include <amdgpu_drm.h> #include <xf86drm.h> #include <stdio.h> #include <inttypes.h> +#ifndef AMDGPU_GEM_CREATE_NO_INTERPROCESS_SHARING +#define AMDGPU_GEM_CREATE_NO_INTERPROCESS_SHARING (1 << 6) +#endif +/* Set to 1 for verbose output showing committed sparse buffer ranges. */ #define DEBUG_SPARSE_COMMITS 0struct amdgpu_sparse_backing_chunk {uint32_t begin, end; };static struct pb_buffer * amdgpu_bo_create(struct radeon_winsys *rws, uint64_t size,@@ -395,20 +399,22 @@ static struct amdgpu_winsys_bo *amdgpu_create_bo(struct amdgpu_winsys *ws,if (initial_domain &RADEON_DOMAIN_VRAM ) request.preferred_heap |=AMDGPU_GEM_DOMAIN_VRAM ;if (initial_domain &RADEON_DOMAIN_GTT ) request.preferred_heap |=AMDGPU_GEM_DOMAIN_GTT ;if (flags &RADEON_FLAG_NO_CPU_ACCESS ) request.flags |=AMDGPU_GEM_CREATE_NO_CPU_ACCESS ;if (flags &RADEON_FLAG_GTT_WC ) request.flags |=AMDGPU_GEM_CREATE_CPU_GTT_USWC ; +if (flags &RADEON_FLAG_NO_INTERPROCESS_SHARING ) + request.flags |=AMDGPU_GEM_CREATE_NO_INTERPROCESS_SHARING ; r =amdgpu_bo_alloc (ws->dev, &request, &buf_handle);if (r) {fprintf (stderr,"amdgpu: Failed to allocate a buffer:\n" );fprintf (stderr,"amdgpu: size : %" PRIu64" bytes\n" , size);fprintf (stderr,"amdgpu: alignment : %u bytes\n" , alignment);fprintf (stderr,"amdgpu: domains : %u\n" , initial_domain); goto error_bo_alloc; } --
Quoted 2 lines
2.7.4
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx