Thomas Zimmermann
2020-Dec-09 14:25 UTC
[PATCH v3 2/8] drm/ast: Only map cursor BOs during updates
The HW cursor's BO used to be mapped permanently into the kernel's address space. GEM's vmap operation will be protected by locks, and we don't want to lock the BO's for an indefinate period of time. Change the cursor code to map the HW BOs only during updates. The vmap operation in VRAM helpers is cheap, as a once estabished mapping is being reused until the BO actually moves. As the HW cursor BOs are permanently pinned, they never move at all. v2: * fix typos in commit description Signed-off-by: Thomas Zimmermann <tzimmermann at suse.de> Acked-by: Christian K?nig <christian.koenig at amd.com> --- drivers/gpu/drm/ast/ast_cursor.c | 51 ++++++++++++++++++-------------- drivers/gpu/drm/ast/ast_drv.h | 2 -- 2 files changed, 28 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/ast/ast_cursor.c b/drivers/gpu/drm/ast/ast_cursor.c index 68bf3d33f1ed..fac1ee79c372 100644 --- a/drivers/gpu/drm/ast/ast_cursor.c +++ b/drivers/gpu/drm/ast/ast_cursor.c @@ -39,7 +39,6 @@ static void ast_cursor_fini(struct ast_private *ast) for (i = 0; i < ARRAY_SIZE(ast->cursor.gbo); ++i) { gbo = ast->cursor.gbo[i]; - drm_gem_vram_vunmap(gbo, &ast->cursor.map[i]); drm_gem_vram_unpin(gbo); drm_gem_vram_put(gbo); } @@ -53,14 +52,13 @@ static void ast_cursor_release(struct drm_device *dev, void *ptr) } /* - * Allocate cursor BOs and pins them at the end of VRAM. + * Allocate cursor BOs and pin them at the end of VRAM. */ int ast_cursor_init(struct ast_private *ast) { struct drm_device *dev = &ast->base; size_t size, i; struct drm_gem_vram_object *gbo; - struct dma_buf_map map; int ret; size = roundup(AST_HWC_SIZE + AST_HWC_SIGNATURE_SIZE, PAGE_SIZE); @@ -77,15 +75,7 @@ int ast_cursor_init(struct ast_private *ast) drm_gem_vram_put(gbo); goto err_drm_gem_vram_put; } - ret = drm_gem_vram_vmap(gbo, &map); - if (ret) { - drm_gem_vram_unpin(gbo); - drm_gem_vram_put(gbo); - goto err_drm_gem_vram_put; - } - ast->cursor.gbo[i] = gbo; - ast->cursor.map[i] = map; } return drmm_add_action_or_reset(dev, ast_cursor_release, NULL); @@ -94,7 +84,6 @@ int ast_cursor_init(struct ast_private *ast) while (i) { --i; gbo = ast->cursor.gbo[i]; - drm_gem_vram_vunmap(gbo, &ast->cursor.map[i]); drm_gem_vram_unpin(gbo); drm_gem_vram_put(gbo); } @@ -168,31 +157,38 @@ static void update_cursor_image(u8 __iomem *dst, const u8 *src, int width, int h int ast_cursor_blit(struct ast_private *ast, struct drm_framebuffer *fb) { struct drm_device *dev = &ast->base; - struct drm_gem_vram_object *gbo; - struct dma_buf_map map; - int ret; - void *src; + struct drm_gem_vram_object *dst_gbo = ast->cursor.gbo[ast->cursor.next_index]; + struct drm_gem_vram_object *src_gbo = drm_gem_vram_of_gem(fb->obj[0]); + struct dma_buf_map src_map, dst_map; void __iomem *dst; + void *src; + int ret; if (drm_WARN_ON_ONCE(dev, fb->width > AST_MAX_HWC_WIDTH) || drm_WARN_ON_ONCE(dev, fb->height > AST_MAX_HWC_HEIGHT)) return -EINVAL; - gbo = drm_gem_vram_of_gem(fb->obj[0]); - - ret = drm_gem_vram_vmap(gbo, &map); + ret = drm_gem_vram_vmap(src_gbo, &src_map); if (ret) return ret; - src = map.vaddr; /* TODO: Use mapping abstraction properly */ + src = src_map.vaddr; /* TODO: Use mapping abstraction properly */ - dst = ast->cursor.map[ast->cursor.next_index].vaddr_iomem; + ret = drm_gem_vram_vmap(dst_gbo, &dst_map); + if (ret) + goto err_drm_gem_vram_vunmap; + dst = dst_map.vaddr_iomem; /* TODO: Use mapping abstraction properly */ /* do data transfer to cursor BO */ update_cursor_image(dst, src, fb->width, fb->height); - drm_gem_vram_vunmap(gbo, &map); + drm_gem_vram_vunmap(dst_gbo, &dst_map); + drm_gem_vram_vunmap(src_gbo, &src_map); return 0; + +err_drm_gem_vram_vunmap: + drm_gem_vram_vunmap(src_gbo, &src_map); + return ret; } static void ast_cursor_set_base(struct ast_private *ast, u64 address) @@ -243,17 +239,26 @@ static void ast_cursor_set_location(struct ast_private *ast, u16 x, u16 y, void ast_cursor_show(struct ast_private *ast, int x, int y, unsigned int offset_x, unsigned int offset_y) { + struct drm_device *dev = &ast->base; + struct drm_gem_vram_object *gbo = ast->cursor.gbo[ast->cursor.next_index]; + struct dma_buf_map map; u8 x_offset, y_offset; u8 __iomem *dst; u8 __iomem *sig; u8 jreg; + int ret; - dst = ast->cursor.map[ast->cursor.next_index].vaddr; + ret = drm_gem_vram_vmap(gbo, &map); + if (drm_WARN_ONCE(dev, ret, "drm_gem_vram_vmap() failed, ret=%d\n", ret)) + return; + dst = map.vaddr_iomem; /* TODO: Use mapping abstraction properly */ sig = dst + AST_HWC_SIZE; writel(x, sig + AST_HWC_SIGNATURE_X); writel(y, sig + AST_HWC_SIGNATURE_Y); + drm_gem_vram_vunmap(gbo, &map); + if (x < 0) { x_offset = (-x) + offset_x; x = 0; diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index ccaff81924ee..f871fc36c2f7 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -28,7 +28,6 @@ #ifndef __AST_DRV_H__ #define __AST_DRV_H__ -#include <linux/dma-buf-map.h> #include <linux/i2c.h> #include <linux/i2c-algo-bit.h> #include <linux/io.h> @@ -133,7 +132,6 @@ struct ast_private { struct { struct drm_gem_vram_object *gbo[AST_DEFAULT_HWC_NUM]; - struct dma_buf_map map[AST_DEFAULT_HWC_NUM]; unsigned int next_index; } cursor; -- 2.29.2
Daniel Vetter
2020-Dec-11 10:18 UTC
[PATCH v3 2/8] drm/ast: Only map cursor BOs during updates
On Wed, Dec 09, 2020 at 03:25:21PM +0100, Thomas Zimmermann wrote:> The HW cursor's BO used to be mapped permanently into the kernel's > address space. GEM's vmap operation will be protected by locks, and > we don't want to lock the BO's for an indefinate period of time. > > Change the cursor code to map the HW BOs only during updates. The > vmap operation in VRAM helpers is cheap, as a once estabished mapping > is being reused until the BO actually moves. As the HW cursor BOs are > permanently pinned, they never move at all. > > v2: > * fix typos in commit description > > Signed-off-by: Thomas Zimmermann <tzimmermann at suse.de> > Acked-by: Christian K?nig <christian.koenig at amd.com>Acked-by: Daniel Vetter <daniel.vetter at ffwll.ch> Now there's a pretty big issue here though: We can't take dma_resv_lock in commit_tail, because of possible deadlocks on at least gpus that do real async rendering because of the dma_fences. Unfortunately my annotations patches got stuck a bit, I need to refresh them. Rules are you can pin and unpin stuff in prepare/cleanup_plane, and also take dma_resv_lock there, but not in commit_tail in-between. So I think our vmap_local needs to loose the unconditional assert_locked and require either that or a pin count. -Daniel> --- > drivers/gpu/drm/ast/ast_cursor.c | 51 ++++++++++++++++++-------------- > drivers/gpu/drm/ast/ast_drv.h | 2 -- > 2 files changed, 28 insertions(+), 25 deletions(-) > > diff --git a/drivers/gpu/drm/ast/ast_cursor.c b/drivers/gpu/drm/ast/ast_cursor.c > index 68bf3d33f1ed..fac1ee79c372 100644 > --- a/drivers/gpu/drm/ast/ast_cursor.c > +++ b/drivers/gpu/drm/ast/ast_cursor.c > @@ -39,7 +39,6 @@ static void ast_cursor_fini(struct ast_private *ast) > > for (i = 0; i < ARRAY_SIZE(ast->cursor.gbo); ++i) { > gbo = ast->cursor.gbo[i]; > - drm_gem_vram_vunmap(gbo, &ast->cursor.map[i]); > drm_gem_vram_unpin(gbo); > drm_gem_vram_put(gbo); > } > @@ -53,14 +52,13 @@ static void ast_cursor_release(struct drm_device *dev, void *ptr) > } > > /* > - * Allocate cursor BOs and pins them at the end of VRAM. > + * Allocate cursor BOs and pin them at the end of VRAM. > */ > int ast_cursor_init(struct ast_private *ast) > { > struct drm_device *dev = &ast->base; > size_t size, i; > struct drm_gem_vram_object *gbo; > - struct dma_buf_map map; > int ret; > > size = roundup(AST_HWC_SIZE + AST_HWC_SIGNATURE_SIZE, PAGE_SIZE); > @@ -77,15 +75,7 @@ int ast_cursor_init(struct ast_private *ast) > drm_gem_vram_put(gbo); > goto err_drm_gem_vram_put; > } > - ret = drm_gem_vram_vmap(gbo, &map); > - if (ret) { > - drm_gem_vram_unpin(gbo); > - drm_gem_vram_put(gbo); > - goto err_drm_gem_vram_put; > - } > - > ast->cursor.gbo[i] = gbo; > - ast->cursor.map[i] = map; > } > > return drmm_add_action_or_reset(dev, ast_cursor_release, NULL); > @@ -94,7 +84,6 @@ int ast_cursor_init(struct ast_private *ast) > while (i) { > --i; > gbo = ast->cursor.gbo[i]; > - drm_gem_vram_vunmap(gbo, &ast->cursor.map[i]); > drm_gem_vram_unpin(gbo); > drm_gem_vram_put(gbo); > } > @@ -168,31 +157,38 @@ static void update_cursor_image(u8 __iomem *dst, const u8 *src, int width, int h > int ast_cursor_blit(struct ast_private *ast, struct drm_framebuffer *fb) > { > struct drm_device *dev = &ast->base; > - struct drm_gem_vram_object *gbo; > - struct dma_buf_map map; > - int ret; > - void *src; > + struct drm_gem_vram_object *dst_gbo = ast->cursor.gbo[ast->cursor.next_index]; > + struct drm_gem_vram_object *src_gbo = drm_gem_vram_of_gem(fb->obj[0]); > + struct dma_buf_map src_map, dst_map; > void __iomem *dst; > + void *src; > + int ret; > > if (drm_WARN_ON_ONCE(dev, fb->width > AST_MAX_HWC_WIDTH) || > drm_WARN_ON_ONCE(dev, fb->height > AST_MAX_HWC_HEIGHT)) > return -EINVAL; > > - gbo = drm_gem_vram_of_gem(fb->obj[0]); > - > - ret = drm_gem_vram_vmap(gbo, &map); > + ret = drm_gem_vram_vmap(src_gbo, &src_map); > if (ret) > return ret; > - src = map.vaddr; /* TODO: Use mapping abstraction properly */ > + src = src_map.vaddr; /* TODO: Use mapping abstraction properly */ > > - dst = ast->cursor.map[ast->cursor.next_index].vaddr_iomem; > + ret = drm_gem_vram_vmap(dst_gbo, &dst_map); > + if (ret) > + goto err_drm_gem_vram_vunmap; > + dst = dst_map.vaddr_iomem; /* TODO: Use mapping abstraction properly */ > > /* do data transfer to cursor BO */ > update_cursor_image(dst, src, fb->width, fb->height); > > - drm_gem_vram_vunmap(gbo, &map); > + drm_gem_vram_vunmap(dst_gbo, &dst_map); > + drm_gem_vram_vunmap(src_gbo, &src_map); > > return 0; > + > +err_drm_gem_vram_vunmap: > + drm_gem_vram_vunmap(src_gbo, &src_map); > + return ret; > } > > static void ast_cursor_set_base(struct ast_private *ast, u64 address) > @@ -243,17 +239,26 @@ static void ast_cursor_set_location(struct ast_private *ast, u16 x, u16 y, > void ast_cursor_show(struct ast_private *ast, int x, int y, > unsigned int offset_x, unsigned int offset_y) > { > + struct drm_device *dev = &ast->base; > + struct drm_gem_vram_object *gbo = ast->cursor.gbo[ast->cursor.next_index]; > + struct dma_buf_map map; > u8 x_offset, y_offset; > u8 __iomem *dst; > u8 __iomem *sig; > u8 jreg; > + int ret; > > - dst = ast->cursor.map[ast->cursor.next_index].vaddr; > + ret = drm_gem_vram_vmap(gbo, &map); > + if (drm_WARN_ONCE(dev, ret, "drm_gem_vram_vmap() failed, ret=%d\n", ret)) > + return; > + dst = map.vaddr_iomem; /* TODO: Use mapping abstraction properly */ > > sig = dst + AST_HWC_SIZE; > writel(x, sig + AST_HWC_SIGNATURE_X); > writel(y, sig + AST_HWC_SIGNATURE_Y); > > + drm_gem_vram_vunmap(gbo, &map); > + > if (x < 0) { > x_offset = (-x) + offset_x; > x = 0; > diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h > index ccaff81924ee..f871fc36c2f7 100644 > --- a/drivers/gpu/drm/ast/ast_drv.h > +++ b/drivers/gpu/drm/ast/ast_drv.h > @@ -28,7 +28,6 @@ > #ifndef __AST_DRV_H__ > #define __AST_DRV_H__ > > -#include <linux/dma-buf-map.h> > #include <linux/i2c.h> > #include <linux/i2c-algo-bit.h> > #include <linux/io.h> > @@ -133,7 +132,6 @@ struct ast_private { > > struct { > struct drm_gem_vram_object *gbo[AST_DEFAULT_HWC_NUM]; > - struct dma_buf_map map[AST_DEFAULT_HWC_NUM]; > unsigned int next_index; > } cursor; > > -- > 2.29.2 >-- Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch