From c9b76548899cde2e729e3bca015d7e78ec5baad7 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Marek=20Ol=C5=A1=C3=A1k?= Date: Sun, 2 Mar 2014 00:56:21 +0100 Subject: [PATCH] drm/radeon: validate relocations in the order determined by userspace v3 MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Userspace should set the first 4 bits of drm_radeon_cs_reloc::flags to a number from 0 to 15. The higher the number, the higher the priority, which means a buffer with a higher number will be validated sooner. The old behavior is preserved: Buffers used for write are prioritized over read-only buffers if the userspace doesn't set the number. v2: add buffers to buckets directly, then concatenate them v3: use a stable sort Signed-off-by: Marek Olšák Reviewed-by: Christian König --- drivers/gpu/drm/radeon/radeon.h | 1 - drivers/gpu/drm/radeon/radeon_cs.c | 64 ++++++++++++++++++++++++-- drivers/gpu/drm/radeon/radeon_object.c | 10 ---- drivers/gpu/drm/radeon/radeon_object.h | 2 - 4 files changed, 61 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 7bb8fd96f3ce..efad56705e32 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -483,7 +483,6 @@ struct radeon_bo_list { struct ttm_validate_buffer tv; struct radeon_bo *bo; uint64_t gpu_offset; - bool written; unsigned domain; unsigned alt_domain; u32 tiling_flags; diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index d49a3f705e49..07e165128dbf 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -31,10 +31,52 @@ #include "radeon.h" #include "radeon_trace.h" +#define RADEON_CS_MAX_PRIORITY 32u +#define RADEON_CS_NUM_BUCKETS (RADEON_CS_MAX_PRIORITY + 1) + +/* This is based on the bucket sort with O(n) time complexity. + * An item with priority "i" is added to bucket[i]. The lists are then + * concatenated in descending order. + */ +struct radeon_cs_buckets { + struct list_head bucket[RADEON_CS_NUM_BUCKETS]; +}; + +static void radeon_cs_buckets_init(struct radeon_cs_buckets *b) +{ + unsigned i; + + for (i = 0; i < RADEON_CS_NUM_BUCKETS; i++) + INIT_LIST_HEAD(&b->bucket[i]); +} + +static void radeon_cs_buckets_add(struct radeon_cs_buckets *b, + struct list_head *item, unsigned priority) +{ + /* Since buffers which appear sooner in the relocation list are + * likely to be used more often than buffers which appear later + * in the list, the sort mustn't change the ordering of buffers + * with the same priority, i.e. it must be stable. + */ + list_add_tail(item, &b->bucket[min(priority, RADEON_CS_MAX_PRIORITY)]); +} + +static void radeon_cs_buckets_get_list(struct radeon_cs_buckets *b, + struct list_head *out_list) +{ + unsigned i; + + /* Connect the sorted buckets in the output list. */ + for (i = 0; i < RADEON_CS_NUM_BUCKETS; i++) { + list_splice(&b->bucket[i], out_list); + } +} + static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) { struct drm_device *ddev = p->rdev->ddev; struct radeon_cs_chunk *chunk; + struct radeon_cs_buckets buckets; unsigned i, j; bool duplicate; @@ -53,8 +95,12 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) if (p->relocs == NULL) { return -ENOMEM; } + + radeon_cs_buckets_init(&buckets); + for (i = 0; i < p->nrelocs; i++) { struct drm_radeon_cs_reloc *r; + unsigned priority; duplicate = false; r = (struct drm_radeon_cs_reloc *)&chunk->kdata[i*4]; @@ -80,7 +126,14 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) p->relocs_ptr[i] = &p->relocs[i]; p->relocs[i].robj = gem_to_radeon_bo(p->relocs[i].gobj); p->relocs[i].lobj.bo = p->relocs[i].robj; - p->relocs[i].lobj.written = !!r->write_domain; + + /* The userspace buffer priorities are from 0 to 15. A higher + * number means the buffer is more important. + * Also, the buffers used for write have a higher priority than + * the buffers used for read only, which doubles the range + * to 0 to 31. 32 is reserved for the kernel driver. + */ + priority = (r->flags & 0xf) * 2 + !!r->write_domain; /* the first reloc of an UVD job is the msg and that must be in VRAM, also but everything into VRAM on AGP cards to avoid @@ -94,6 +147,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) p->relocs[i].lobj.alt_domain = RADEON_GEM_DOMAIN_VRAM; + /* prioritize this over any other relocation */ + priority = RADEON_CS_MAX_PRIORITY; } else { uint32_t domain = r->write_domain ? r->write_domain : r->read_domains; @@ -107,9 +162,12 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) p->relocs[i].lobj.tv.bo = &p->relocs[i].robj->tbo; p->relocs[i].handle = r->handle; - radeon_bo_list_add_object(&p->relocs[i].lobj, - &p->validated); + radeon_cs_buckets_add(&buckets, &p->relocs[i].lobj.tv.head, + priority); } + + radeon_cs_buckets_get_list(&buckets, &p->validated); + return radeon_bo_list_validate(&p->ticket, &p->validated, p->ring); } diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 282d6a248396..8399fe021769 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -366,16 +366,6 @@ void radeon_bo_fini(struct radeon_device *rdev) arch_phys_wc_del(rdev->mc.vram_mtrr); } -void radeon_bo_list_add_object(struct radeon_bo_list *lobj, - struct list_head *head) -{ - if (lobj->written) { - list_add(&lobj->tv.head, head); - } else { - list_add_tail(&lobj->tv.head, head); - } -} - int radeon_bo_list_validate(struct ww_acquire_ctx *ticket, struct list_head *head, int ring) { diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index a9a8c11bd80d..6c3ca9edc2f4 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -138,8 +138,6 @@ extern int radeon_bo_evict_vram(struct radeon_device *rdev); extern void radeon_bo_force_delete(struct radeon_device *rdev); extern int radeon_bo_init(struct radeon_device *rdev); extern void radeon_bo_fini(struct radeon_device *rdev); -extern void radeon_bo_list_add_object(struct radeon_bo_list *lobj, - struct list_head *head); extern int radeon_bo_list_validate(struct ww_acquire_ctx *ticket, struct list_head *head, int ring); extern int radeon_bo_fbdev_mmap(struct radeon_bo *bo, -- 2.20.1