From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
When reworking the code to move the eviction fence to the object, the best code is removed code.
Remove some functions that are unused, and change the function definition if it's only used in 1 place.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Niranjana Vishwanathapura niranjana.vishwanathapura@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/i915_active.c | 28 +++------------------------- drivers/gpu/drm/i915/i915_active.h | 17 +---------------- drivers/gpu/drm/i915/i915_vma.c | 2 +- drivers/gpu/drm/i915/i915_vma.h | 2 -- 4 files changed, 5 insertions(+), 44 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 3103c1e1fd14..ee2b3a375362 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -426,8 +426,9 @@ replace_barrier(struct i915_active *ref, struct i915_active_fence *active) return true; }
-int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) +int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) { + struct dma_fence *fence = &rq->fence; struct i915_active_fence *active; int err;
@@ -436,7 +437,7 @@ int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) if (err) return err;
- active = active_instance(ref, idx); + active = active_instance(ref, i915_request_timeline(rq)->fence_context); if (!active) { err = -ENOMEM; goto out; @@ -477,29 +478,6 @@ __i915_active_set_fence(struct i915_active *ref, return prev; }
-static struct i915_active_fence * -__active_fence(struct i915_active *ref, u64 idx) -{ - struct active_node *it; - - it = __active_lookup(ref, idx); - if (unlikely(!it)) { /* Contention with parallel tree builders! */ - spin_lock_irq(&ref->tree_lock); - it = __active_lookup(ref, idx); - spin_unlock_irq(&ref->tree_lock); - } - GEM_BUG_ON(!it); /* slot must be preallocated */ - - return &it->base; -} - -struct dma_fence * -__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) -{ - /* Only valid while active, see i915_active_acquire_for_context() */ - return __i915_active_set_fence(ref, __active_fence(ref, idx), fence); -} - struct dma_fence * i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f) { diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h index 5fcdb0e2bc9e..7eb44132183a 100644 --- a/drivers/gpu/drm/i915/i915_active.h +++ b/drivers/gpu/drm/i915/i915_active.h @@ -164,26 +164,11 @@ void __i915_active_init(struct i915_active *ref, __i915_active_init(ref, active, retire, flags, &__mkey, &__wkey); \ } while (0)
-struct dma_fence * -__i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence); -int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence); - -static inline int -i915_active_add_request(struct i915_active *ref, struct i915_request *rq) -{ - return i915_active_ref(ref, - i915_request_timeline(rq)->fence_context, - &rq->fence); -} +int i915_active_add_request(struct i915_active *ref, struct i915_request *rq);
struct dma_fence * i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f);
-static inline bool i915_active_has_exclusive(struct i915_active *ref) -{ - return rcu_access_pointer(ref->excl.fence); -} - int __i915_active_wait(struct i915_active *ref, int state); static inline int i915_active_wait(struct i915_active *ref) { diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 90546fa58fc1..1187f1956c20 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1220,7 +1220,7 @@ __i915_request_await_bind(struct i915_request *rq, struct i915_vma *vma) return __i915_request_await_exclusive(rq, &vma->active); }
-int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq) +static int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq) { int err;
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 648dbe744c96..b882fd7b5f99 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -55,8 +55,6 @@ static inline bool i915_vma_is_active(const struct i915_vma *vma) /* do not reserve memory to prevent deadlocks */ #define __EXEC_OBJECT_NO_RESERVE BIT(31)
-int __must_check __i915_vma_move_to_active(struct i915_vma *vma, - struct i915_request *rq); int __must_check _i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq, struct dma_fence *fence,
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
Use a single null-terminated array for simplicity instead of a linked list. This might slightly speed up execbuf when many vma's may be marked as capture, but definitely removes an allocation from a signaling path.
We are not allowed to allocate memory in eb_move_to_gpu, but we can't enforce it yet through annotations.
Changes since v1: - Rebase on top of multi-batchbuffer changes.
v2: - Fix up checkpatch warnings
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Niranjana Vishwanathapura niranjana.vishwanathapura@intel.com #v1 Signed-off-by: Matthew Auld matthew.auld@intel.com --- .../gpu/drm/i915/gem/i915_gem_execbuffer.c | 28 +++++++++++-------- drivers/gpu/drm/i915/i915_gpu_error.c | 9 +++--- drivers/gpu/drm/i915/i915_request.c | 9 ++---- drivers/gpu/drm/i915/i915_request.h | 7 +---- 4 files changed, 25 insertions(+), 28 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index ea5b7b2a4d70..37b9f7ddc409 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -265,6 +265,9 @@ struct i915_execbuffer { /* number of batches in execbuf IOCTL */ unsigned int num_batches;
+ /* Number of objects with EXEC_OBJECT_CAPTURE set */ + unsigned int capture_count; + /** list of vma not yet bound during reservation phase */ struct list_head unbound;
@@ -909,6 +912,9 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) goto err; }
+ if (eb->exec[i].flags & EXEC_OBJECT_CAPTURE) + eb->capture_count++; + err = eb_validate_vma(eb, &eb->exec[i], vma); if (unlikely(err)) { i915_vma_put(vma); @@ -1906,19 +1912,11 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) assert_vma_held(vma);
if (flags & EXEC_OBJECT_CAPTURE) { - struct i915_capture_list *capture; + eb->capture_count--;
for_each_batch_create_order(eb, j) { - if (!eb->requests[j]) - break; - - capture = kmalloc(sizeof(*capture), GFP_KERNEL); - if (capture) { - capture->next = - eb->requests[j]->capture_list; - capture->vma = vma; - eb->requests[j]->capture_list = capture; - } + if (eb->requests[j]->capture_list) + eb->requests[j]->capture_list[eb->capture_count] = vma; } }
@@ -3130,6 +3128,13 @@ eb_requests_create(struct i915_execbuffer *eb, struct dma_fence *in_fence, return out_fence; }
+ if (eb->capture_count) { + eb->requests[i]->capture_list = + kvcalloc(eb->capture_count + 1, + sizeof(*eb->requests[i]->capture_list), + GFP_KERNEL | __GFP_NOWARN); + } + /* * Only the first request added (committed to backend) has to * take the in fences into account as all subsequent requests @@ -3197,6 +3202,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
eb.fences = NULL; eb.num_fences = 0; + eb.capture_count = 0;
memset(eb.requests, 0, sizeof(struct i915_request *) * ARRAY_SIZE(eb.requests)); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2a2d7643b551..45104bb12a98 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1356,10 +1356,10 @@ capture_user(struct intel_engine_capture_vma *capture, const struct i915_request *rq, gfp_t gfp) { - struct i915_capture_list *c; + int i;
- for (c = rq->capture_list; c; c = c->next) - capture = capture_vma(capture, c->vma, "user", gfp); + for (i = 0; rq->capture_list[i]; i++) + capture = capture_vma(capture, rq->capture_list[i], "user", gfp);
return capture; } @@ -1407,7 +1407,8 @@ intel_engine_coredump_add_request(struct intel_engine_coredump *ee, * by userspace. */ vma = capture_vma(vma, rq->batch, "batch", gfp); - vma = capture_user(vma, rq, gfp); + if (rq->capture_list) + vma = capture_user(vma, rq, gfp); vma = capture_vma(vma, rq->ring->vma, "ring", gfp); vma = capture_vma(vma, rq->context->state, "HW context", gfp);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 820a1f38b271..808632337832 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -188,15 +188,10 @@ void i915_request_notify_execute_cb_imm(struct i915_request *rq)
static void free_capture_list(struct i915_request *request) { - struct i915_capture_list *capture; + struct i915_vma **capture;
capture = fetch_and_zero(&request->capture_list); - while (capture) { - struct i915_capture_list *next = capture->next; - - kfree(capture); - capture = next; - } + kvfree(capture); }
static void __i915_request_fill(struct i915_request *rq, u8 val) diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index dc359242d1ae..49c87b160a6a 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -48,11 +48,6 @@ struct drm_i915_gem_object; struct drm_printer; struct i915_request;
-struct i915_capture_list { - struct i915_capture_list *next; - struct i915_vma *vma; -}; - #define RQ_TRACE(rq, fmt, ...) do { \ const struct i915_request *rq__ = (rq); \ ENGINE_TRACE(rq__->engine, "fence %llx:%lld, current %d " fmt, \ @@ -299,7 +294,7 @@ struct i915_request { * active reference - all objects on this list must also be * on the active_list (of their final request). */ - struct i915_capture_list *capture_list; + struct i915_vma **capture_list;
/** Time at which this request was emitted, in jiffies. */ unsigned long emitted_jiffies;
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
gen6_ppgtt_unpin_all is unused, kill it.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 11 ----------- drivers/gpu/drm/i915/gt/gen6_ppgtt.h | 1 - 2 files changed, 12 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index baea9770200a..ae693bf88ef0 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -404,17 +404,6 @@ void gen6_ppgtt_unpin(struct i915_ppgtt *base) i915_vma_unpin(ppgtt->vma); }
-void gen6_ppgtt_unpin_all(struct i915_ppgtt *base) -{ - struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base); - - if (!atomic_read(&ppgtt->pin_count)) - return; - - i915_vma_unpin(ppgtt->vma); - atomic_set(&ppgtt->pin_count, 0); -} - struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) { struct i915_ggtt * const ggtt = gt->ggtt; diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h index 6a61a5c3a85a..ab0eecb086dd 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h @@ -71,7 +71,6 @@ static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base)
int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww); void gen6_ppgtt_unpin(struct i915_ppgtt *base); -void gen6_ppgtt_unpin_all(struct i915_ppgtt *base); void gen6_ppgtt_enable(struct intel_gt *gt); void gen7_ppgtt_enable(struct intel_gt *gt); struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt);
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
We currently have to special case vma->obj being NULL because of gen6 ppgtt and mock_engine. Fix gen6 ppgtt, so we may soon be able to remove a few checks. As the object only exists as a fake object pointing to ggtt, we have no backing storage, so no real object is created. It just has to look real enough.
Also kill pin_mutex, it's not compatible with ww locking, and we can use the vm lock instead.
v2: - Drop IS_SHRINKABLE and shorten overly long line
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_internal.c | 44 ++++--- drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 123 +++++++++++-------- drivers/gpu/drm/i915/gt/gen6_ppgtt.h | 1 - drivers/gpu/drm/i915/i915_drv.h | 4 + 4 files changed, 100 insertions(+), 72 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index a57a6b7013c2..c5150a1ee3d2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -145,24 +145,10 @@ static const struct drm_i915_gem_object_ops i915_gem_object_internal_ops = { .put_pages = i915_gem_object_put_pages_internal, };
-/** - * i915_gem_object_create_internal: create an object with volatile pages - * @i915: the i915 device - * @size: the size in bytes of backing storage to allocate for the object - * - * Creates a new object that wraps some internal memory for private use. - * This object is not backed by swappable storage, and as such its contents - * are volatile and only valid whilst pinned. If the object is reaped by the - * shrinker, its pages and data will be discarded. Equally, it is not a full - * GEM object and so not valid for access from userspace. This makes it useful - * for hardware interfaces like ringbuffers (which are pinned from the time - * the request is written to the time the hardware stops accessing it), but - * not for contexts (which need to be preserved when not active for later - * reuse). Note that it is not cleared upon allocation. - */ struct drm_i915_gem_object * -i915_gem_object_create_internal(struct drm_i915_private *i915, - phys_addr_t size) +__i915_gem_object_create_internal(struct drm_i915_private *i915, + const struct drm_i915_gem_object_ops *ops, + phys_addr_t size) { static struct lock_class_key lock_class; struct drm_i915_gem_object *obj; @@ -179,7 +165,7 @@ i915_gem_object_create_internal(struct drm_i915_private *i915, return ERR_PTR(-ENOMEM);
drm_gem_private_object_init(&i915->drm, &obj->base, size); - i915_gem_object_init(obj, &i915_gem_object_internal_ops, &lock_class, 0); + i915_gem_object_init(obj, ops, &lock_class, 0); obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
/* @@ -199,3 +185,25 @@ i915_gem_object_create_internal(struct drm_i915_private *i915,
return obj; } + +/** + * i915_gem_object_create_internal: create an object with volatile pages + * @i915: the i915 device + * @size: the size in bytes of backing storage to allocate for the object + * + * Creates a new object that wraps some internal memory for private use. + * This object is not backed by swappable storage, and as such its contents + * are volatile and only valid whilst pinned. If the object is reaped by the + * shrinker, its pages and data will be discarded. Equally, it is not a full + * GEM object and so not valid for access from userspace. This makes it useful + * for hardware interfaces like ringbuffers (which are pinned from the time + * the request is written to the time the hardware stops accessing it), but + * not for contexts (which need to be preserved when not active for later + * reuse). Note that it is not cleared upon allocation. + */ +struct drm_i915_gem_object * +i915_gem_object_create_internal(struct drm_i915_private *i915, + phys_addr_t size) +{ + return __i915_gem_object_create_internal(i915, &i915_gem_object_internal_ops, size); +} diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index ae693bf88ef0..904c048953d6 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -261,13 +261,10 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm) { struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
- __i915_vma_put(ppgtt->vma); - gen6_ppgtt_free_pd(ppgtt); free_scratch(vm);
mutex_destroy(&ppgtt->flush); - mutex_destroy(&ppgtt->pin_mutex);
free_pd(&ppgtt->base.vm, ppgtt->base.pd); } @@ -330,37 +327,6 @@ static const struct i915_vma_ops pd_vma_ops = { .unbind_vma = pd_vma_unbind, };
-static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size) -{ - struct i915_ggtt *ggtt = ppgtt->base.vm.gt->ggtt; - struct i915_vma *vma; - - GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE)); - GEM_BUG_ON(size > ggtt->vm.total); - - vma = i915_vma_alloc(); - if (!vma) - return ERR_PTR(-ENOMEM); - - i915_active_init(&vma->active, NULL, NULL, 0); - - kref_init(&vma->ref); - mutex_init(&vma->pages_mutex); - vma->vm = i915_vm_get(&ggtt->vm); - vma->ops = &pd_vma_ops; - vma->private = ppgtt; - - vma->size = size; - vma->fence_size = size; - atomic_set(&vma->flags, I915_VMA_GGTT); - vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */ - - INIT_LIST_HEAD(&vma->obj_link); - INIT_LIST_HEAD(&vma->closed_link); - - return vma; -} - int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww) { struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base); @@ -377,24 +343,85 @@ int gen6_ppgtt_pin(struct i915_ppgtt *base, struct i915_gem_ww_ctx *ww) if (atomic_add_unless(&ppgtt->pin_count, 1, 0)) return 0;
- if (mutex_lock_interruptible(&ppgtt->pin_mutex)) - return -EINTR; + /* grab the ppgtt resv to pin the object */ + err = i915_vm_lock_objects(&ppgtt->base.vm, ww); + if (err) + return err;
/* * PPGTT PDEs reside in the GGTT and consists of 512 entries. The * allocator works in address space sizes, so it's multiplied by page * size. We allocate at the top of the GTT to avoid fragmentation. */ - err = 0; - if (!atomic_read(&ppgtt->pin_count)) + if (!atomic_read(&ppgtt->pin_count)) { err = i915_ggtt_pin(ppgtt->vma, ww, GEN6_PD_ALIGN, PIN_HIGH); + + GEM_BUG_ON(ppgtt->vma->fence); + clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(ppgtt->vma)); + } if (!err) atomic_inc(&ppgtt->pin_count); - mutex_unlock(&ppgtt->pin_mutex);
return err; }
+static int pd_dummy_obj_get_pages(struct drm_i915_gem_object *obj) +{ + obj->mm.pages = ZERO_SIZE_PTR; + return 0; +} + +static void pd_dummy_obj_put_pages(struct drm_i915_gem_object *obj, + struct sg_table *pages) +{ +} + +static const struct drm_i915_gem_object_ops pd_dummy_obj_ops = { + .name = "pd_dummy_obj", + .get_pages = pd_dummy_obj_get_pages, + .put_pages = pd_dummy_obj_put_pages, +}; + +static struct i915_page_directory * +gen6_alloc_top_pd(struct gen6_ppgtt *ppgtt) +{ + struct i915_ggtt * const ggtt = ppgtt->base.vm.gt->ggtt; + struct i915_page_directory *pd; + int err; + + pd = __alloc_pd(I915_PDES); + if (unlikely(!pd)) + return ERR_PTR(-ENOMEM); + + pd->pt.base = __i915_gem_object_create_internal(ppgtt->base.vm.gt->i915, + &pd_dummy_obj_ops, + I915_PDES * SZ_4K); + if (IS_ERR(pd->pt.base)) { + err = PTR_ERR(pd->pt.base); + pd->pt.base = NULL; + goto err_pd; + } + + pd->pt.base->base.resv = i915_vm_resv_get(&ppgtt->base.vm); + pd->pt.base->shares_resv_from = &ppgtt->base.vm; + + ppgtt->vma = i915_vma_instance(pd->pt.base, &ggtt->vm, NULL); + if (IS_ERR(ppgtt->vma)) { + err = PTR_ERR(ppgtt->vma); + ppgtt->vma = NULL; + goto err_pd; + } + + /* The dummy object we create is special, override ops.. */ + ppgtt->vma->ops = &pd_vma_ops; + ppgtt->vma->private = ppgtt; + return pd; + +err_pd: + free_pd(&ppgtt->base.vm, pd); + return ERR_PTR(err); +} + void gen6_ppgtt_unpin(struct i915_ppgtt *base) { struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base); @@ -415,7 +442,6 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) return ERR_PTR(-ENOMEM);
mutex_init(&ppgtt->flush); - mutex_init(&ppgtt->pin_mutex);
ppgtt_init(&ppgtt->base, gt, 0); ppgtt->base.vm.pd_shift = ilog2(SZ_4K * SZ_4K / sizeof(gen6_pte_t)); @@ -430,19 +456,13 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) ppgtt->base.vm.alloc_pt_dma = alloc_pt_dma; ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
- ppgtt->base.pd = __alloc_pd(I915_PDES); - if (!ppgtt->base.pd) { - err = -ENOMEM; - goto err_free; - } - err = gen6_ppgtt_init_scratch(ppgtt); if (err) - goto err_pd; + goto err_free;
- ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE); - if (IS_ERR(ppgtt->vma)) { - err = PTR_ERR(ppgtt->vma); + ppgtt->base.pd = gen6_alloc_top_pd(ppgtt); + if (IS_ERR(ppgtt->base.pd)) { + err = PTR_ERR(ppgtt->base.pd); goto err_scratch; }
@@ -450,10 +470,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
err_scratch: free_scratch(&ppgtt->base.vm); -err_pd: - free_pd(&ppgtt->base.vm, ppgtt->base.pd); err_free: - mutex_destroy(&ppgtt->pin_mutex); kfree(ppgtt); return ERR_PTR(err); } diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h index ab0eecb086dd..5e5cf2ec3309 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h @@ -19,7 +19,6 @@ struct gen6_ppgtt { u32 pp_dir;
atomic_t pin_count; - struct mutex pin_mutex;
bool scan_for_unused_pt; }; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 19e6700a4315..57f2f8da931e 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1932,6 +1932,10 @@ int i915_gem_evict_vm(struct i915_address_space *vm); struct drm_i915_gem_object * i915_gem_object_create_internal(struct drm_i915_private *dev_priv, phys_addr_t size); +struct drm_i915_gem_object * +__i915_gem_object_create_internal(struct drm_i915_private *dev_priv, + const struct drm_i915_gem_object_ops *ops, + phys_addr_t size);
/* i915_gem_tiling.c */ static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
This allows us to finally get rid of all the assumptions that vma->obj is NULL.
Changes since v1: - Ensure the mock_ring vma is pinned to prevent a fault. - Pin it high to avoid failure in evict_for_vma selftest.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/mock_engine.c | 38 ++++++++++++++++++++------- 1 file changed, 28 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index 8b89215afe46..bb99fc03f503 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -35,9 +35,31 @@ static void mock_timeline_unpin(struct intel_timeline *tl) atomic_dec(&tl->pin_count); }
+static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size) +{ + struct i915_address_space *vm = &ggtt->vm; + struct drm_i915_private *i915 = vm->i915; + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + + obj = i915_gem_object_create_internal(i915, size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + + vma = i915_vma_instance(obj, vm, NULL); + if (IS_ERR(vma)) + goto err; + + return vma; + +err: + i915_gem_object_put(obj); + return vma; +} + static struct intel_ring *mock_ring(struct intel_engine_cs *engine) { - const unsigned long sz = PAGE_SIZE / 2; + const unsigned long sz = PAGE_SIZE; struct intel_ring *ring;
ring = kzalloc(sizeof(*ring) + sz, GFP_KERNEL); @@ -50,15 +72,11 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) ring->vaddr = (void *)(ring + 1); atomic_set(&ring->pin_count, 1);
- ring->vma = i915_vma_alloc(); - if (!ring->vma) { + ring->vma = create_ring_vma(engine->gt->ggtt, PAGE_SIZE); + if (IS_ERR(ring->vma)) { kfree(ring); return NULL; } - i915_active_init(&ring->vma->active, NULL, NULL, 0); - __set_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(ring->vma)); - __set_bit(DRM_MM_NODE_ALLOCATED_BIT, &ring->vma->node.flags); - ring->vma->node.size = sz;
intel_ring_update_space(ring);
@@ -67,8 +85,7 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine)
static void mock_ring_free(struct intel_ring *ring) { - i915_active_fini(&ring->vma->active); - i915_vma_free(ring->vma); + i915_vma_put(ring->vma);
kfree(ring); } @@ -125,6 +142,7 @@ static void mock_context_unpin(struct intel_context *ce)
static void mock_context_post_unpin(struct intel_context *ce) { + i915_vma_unpin(ce->ring->vma); }
static void mock_context_destroy(struct kref *ref) @@ -169,7 +187,7 @@ static int mock_context_alloc(struct intel_context *ce) static int mock_context_pre_pin(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **unused) { - return 0; + return i915_vma_pin_ww(ce->ring->vma, ww, 0, 0, PIN_GLOBAL | PIN_HIGH); }
static int mock_context_pin(struct intel_context *ce, void *unused)
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
vma->obj and vma->resv are now never NULL, and some checks can be removed.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/intel_context.c | 2 +- .../gpu/drm/i915/gt/intel_ring_submission.c | 2 +- drivers/gpu/drm/i915/i915_vma.c | 48 ++++++++----------- drivers/gpu/drm/i915/i915_vma.h | 3 -- 4 files changed, 22 insertions(+), 33 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 5634d14052bc..e0220ac0e9b6 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -219,7 +219,7 @@ int __intel_context_do_pin_ww(struct intel_context *ce, */
err = i915_gem_object_lock(ce->timeline->hwsp_ggtt->obj, ww); - if (!err && ce->ring->vma->obj) + if (!err) err = i915_gem_object_lock(ce->ring->vma->obj, ww); if (!err && ce->state) err = i915_gem_object_lock(ce->state->obj, ww); diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 586dca1731ce..3e6fac0340ef 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -1357,7 +1357,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine) err = i915_gem_object_lock(timeline->hwsp_ggtt->obj, &ww); if (!err && gen7_wa_vma) err = i915_gem_object_lock(gen7_wa_vma->obj, &ww); - if (!err && engine->legacy.ring->vma->obj) + if (!err) err = i915_gem_object_lock(engine->legacy.ring->vma->obj, &ww); if (!err) err = intel_timeline_pin(timeline, &ww); diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 1187f1956c20..aebfc232b58b 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -40,12 +40,12 @@
static struct kmem_cache *slab_vmas;
-struct i915_vma *i915_vma_alloc(void) +static struct i915_vma *i915_vma_alloc(void) { return kmem_cache_zalloc(slab_vmas, GFP_KERNEL); }
-void i915_vma_free(struct i915_vma *vma) +static void i915_vma_free(struct i915_vma *vma) { return kmem_cache_free(slab_vmas, vma); } @@ -426,10 +426,8 @@ int i915_vma_bind(struct i915_vma *vma,
work->base.dma.error = 0; /* enable the queue_work() */
- if (vma->obj) { - __i915_gem_object_pin_pages(vma->obj); - work->pinned = i915_gem_object_get(vma->obj); - } + __i915_gem_object_pin_pages(vma->obj); + work->pinned = i915_gem_object_get(vma->obj); } else { vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags); } @@ -670,7 +668,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags) }
color = 0; - if (vma->obj && i915_vm_has_cache_coloring(vma->vm)) + if (i915_vm_has_cache_coloring(vma->vm)) color = vma->obj->cache_level;
if (flags & PIN_OFFSET_FIXED) { @@ -795,17 +793,14 @@ static bool try_qad_pin(struct i915_vma *vma, unsigned int flags) static int vma_get_pages(struct i915_vma *vma) { int err = 0; - bool pinned_pages = false; + bool pinned_pages = true;
if (atomic_add_unless(&vma->pages_count, 1, 0)) return 0;
- if (vma->obj) { - err = i915_gem_object_pin_pages(vma->obj); - if (err) - return err; - pinned_pages = true; - } + err = i915_gem_object_pin_pages(vma->obj); + if (err) + return err;
/* Allocations ahoy! */ if (mutex_lock_interruptible(&vma->pages_mutex)) { @@ -838,8 +833,8 @@ static void __vma_put_pages(struct i915_vma *vma, unsigned int count) if (atomic_sub_return(count, &vma->pages_count) == 0) { vma->ops->clear_pages(vma); GEM_BUG_ON(vma->pages); - if (vma->obj) - i915_gem_object_unpin_pages(vma->obj); + + i915_gem_object_unpin_pages(vma->obj); } mutex_unlock(&vma->pages_mutex); } @@ -875,7 +870,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, int err;
#ifdef CONFIG_PROVE_LOCKING - if (debug_locks && !WARN_ON(!ww) && vma->resv) + if (debug_locks && !WARN_ON(!ww)) assert_vma_held(vma); #endif
@@ -983,7 +978,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
GEM_BUG_ON(!vma->pages); err = i915_vma_bind(vma, - vma->obj ? vma->obj->cache_level : 0, + vma->obj->cache_level, flags, work); if (err) goto err_remove; @@ -1037,7 +1032,7 @@ int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, GEM_BUG_ON(!i915_vma_is_ggtt(vma));
#ifdef CONFIG_LOCKDEP - WARN_ON(!ww && vma->resv && dma_resv_held(vma->resv)); + WARN_ON(!ww && dma_resv_held(vma->resv)); #endif
do { @@ -1116,6 +1111,7 @@ void i915_vma_reopen(struct i915_vma *vma) void i915_vma_release(struct kref *ref) { struct i915_vma *vma = container_of(ref, typeof(*vma), ref); + struct drm_i915_gem_object *obj = vma->obj;
if (drm_mm_node_allocated(&vma->node)) { mutex_lock(&vma->vm->mutex); @@ -1126,15 +1122,11 @@ void i915_vma_release(struct kref *ref) } GEM_BUG_ON(i915_vma_is_active(vma));
- if (vma->obj) { - struct drm_i915_gem_object *obj = vma->obj; - - spin_lock(&obj->vma.lock); - list_del(&vma->obj_link); - if (!RB_EMPTY_NODE(&vma->obj_node)) - rb_erase(&vma->obj_node, &obj->vma.tree); - spin_unlock(&obj->vma.lock); - } + spin_lock(&obj->vma.lock); + list_del(&vma->obj_link); + if (!RB_EMPTY_NODE(&vma->obj_node)) + rb_erase(&vma->obj_node, &obj->vma.tree); + spin_unlock(&obj->vma.lock);
__i915_vma_remove_closed(vma); i915_vm_put(vma->vm); diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index b882fd7b5f99..423e0df81c87 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -416,9 +416,6 @@ static inline void i915_vma_clear_scanout(struct i915_vma *vma) list_for_each_entry(V, &(OBJ)->vma.list, obj_link) \ for_each_until(!i915_vma_is_ggtt(V))
-struct i915_vma *i915_vma_alloc(void); -void i915_vma_free(struct i915_vma *vma); - struct i915_vma *i915_vma_make_unshrinkable(struct i915_vma *vma); void i915_vma_make_shrinkable(struct i915_vma *vma); void i915_vma_make_purgeable(struct i915_vma *vma);
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
Resetting will clear the CONTEXT_VALID_BIT, so wait until after that to test.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Niranjana Vishwanathapura niranjana.vishwanathapura@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/intel_engine_pm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index a1334b48dde7..849fbb229bd3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -52,8 +52,6 @@ static int __engine_unpark(struct intel_wakeref *wf) /* Discard stale context state from across idling */ ce = engine->kernel_context; if (ce) { - GEM_BUG_ON(test_bit(CONTEXT_VALID_BIT, &ce->flags)); - /* Flush all pending HW writes before we touch the context */ while (unlikely(intel_context_inflight(ce))) intel_engine_flush_submission(engine); @@ -68,6 +66,9 @@ static int __engine_unpark(struct intel_wakeref *wf) ce->timeline->seqno, READ_ONCE(*ce->timeline->hwsp_seqno), ce->ring->emit); + + GEM_BUG_ON(test_bit(CONTEXT_VALID_BIT, &ce->flags)); + GEM_BUG_ON(ce->timeline->seqno != READ_ONCE(*ce->timeline->hwsp_seqno)); }
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
It's just an alias to vma->obj->base.resv, no need to duplicate it.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Niranjana Vishwanathapura niranjana.vishwanathapura@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 4 ++-- drivers/gpu/drm/i915/i915_vma.c | 9 ++++----- drivers/gpu/drm/i915/i915_vma.h | 6 +++--- drivers/gpu/drm/i915/i915_vma_types.h | 1 - 4 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 37b9f7ddc409..e29205bbc45f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -1007,7 +1007,7 @@ static int eb_validate_vmas(struct i915_execbuffer *eb) }
if (!(ev->flags & EXEC_OBJECT_WRITE)) { - err = dma_resv_reserve_shared(vma->resv, 1); + err = dma_resv_reserve_shared(vma->obj->base.resv, 1); if (err) return err; } @@ -2173,7 +2173,7 @@ static int eb_parse(struct i915_execbuffer *eb) goto err_trampoline; }
- err = dma_resv_reserve_shared(shadow->resv, 1); + err = dma_resv_reserve_shared(shadow->obj->base.resv, 1); if (err) goto err_trampoline;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index aebfc232b58b..ac09b685678a 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -116,7 +116,6 @@ vma_create(struct drm_i915_gem_object *obj, vma->vm = i915_vm_get(vm); vma->ops = &vm->vma_ops; vma->obj = obj; - vma->resv = obj->base.resv; vma->size = obj->base.size; vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
@@ -1032,7 +1031,7 @@ int i915_ggtt_pin(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, GEM_BUG_ON(!i915_vma_is_ggtt(vma));
#ifdef CONFIG_LOCKDEP - WARN_ON(!ww && dma_resv_held(vma->resv)); + WARN_ON(!ww && dma_resv_held(vma->obj->base.resv)); #endif
do { @@ -1251,19 +1250,19 @@ int _i915_vma_move_to_active(struct i915_vma *vma, }
if (fence) { - dma_resv_add_excl_fence(vma->resv, fence); + dma_resv_add_excl_fence(vma->obj->base.resv, fence); obj->write_domain = I915_GEM_DOMAIN_RENDER; obj->read_domains = 0; } } else { if (!(flags & __EXEC_OBJECT_NO_RESERVE)) { - err = dma_resv_reserve_shared(vma->resv, 1); + err = dma_resv_reserve_shared(vma->obj->base.resv, 1); if (unlikely(err)) return err; }
if (fence) { - dma_resv_add_shared_fence(vma->resv, fence); + dma_resv_add_shared_fence(vma->obj->base.resv, fence); obj->write_domain = 0; } } diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 423e0df81c87..9a931ecb09e5 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -232,16 +232,16 @@ static inline void __i915_vma_put(struct i915_vma *vma) kref_put(&vma->ref, i915_vma_release); }
-#define assert_vma_held(vma) dma_resv_assert_held((vma)->resv) +#define assert_vma_held(vma) dma_resv_assert_held((vma)->obj->base.resv)
static inline void i915_vma_lock(struct i915_vma *vma) { - dma_resv_lock(vma->resv, NULL); + dma_resv_lock(vma->obj->base.resv, NULL); }
static inline void i915_vma_unlock(struct i915_vma *vma) { - dma_resv_unlock(vma->resv); + dma_resv_unlock(vma->obj->base.resv); }
int __must_check diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h index 80e93bf00f2e..8a0decb19bcc 100644 --- a/drivers/gpu/drm/i915/i915_vma_types.h +++ b/drivers/gpu/drm/i915/i915_vma_types.h @@ -178,7 +178,6 @@ struct i915_vma { const struct i915_vma_ops *ops;
struct drm_i915_gem_object *obj; - struct dma_resv *resv; /** Alias of obj->resv */
struct sg_table *pages; void __iomem *iomap;
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
In the next commit, we don't evict when refcount = 0, so we need to call drain freed objects, because we want to pin new bo's in the same place, causing a test failure.
Furthermore, since each subtest is separated, it's a lot better to use i915_live_selftests, so each subtest starts with a clean slate, and a clean address space.
v2: - Make hugepage_ctx static. Reported-by: kernel test robot lkp@intel.com
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- .../gpu/drm/i915/gem/selftests/huge_pages.c | 128 +++++++++++------- 1 file changed, 80 insertions(+), 48 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index b2003133deaf..257588b68adc 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -22,6 +22,22 @@ #include "selftests/mock_region.h" #include "selftests/i915_random.h"
+static struct i915_gem_context *hugepage_ctx(struct drm_i915_private *i915, + struct file *file) +{ + struct i915_gem_context *ctx = live_context(i915, file); + struct i915_address_space *vm; + + if (IS_ERR(ctx)) + return ctx; + + vm = ctx->vm; + if (vm) + WRITE_ONCE(vm->scrub_64K, true); + + return ctx; +} + static const unsigned int page_sizes[] = { I915_GTT_PAGE_SIZE_2M, I915_GTT_PAGE_SIZE_64K, @@ -959,6 +975,8 @@ static int igt_mock_ppgtt_64K(void *arg) __i915_gem_object_put_pages(obj); i915_gem_object_unlock(obj); i915_gem_object_put(obj); + + i915_gem_drain_freed_objects(i915); } }
@@ -1080,10 +1098,6 @@ static int __igt_write_huge(struct intel_context *ce, if (IS_ERR(vma)) return PTR_ERR(vma);
- err = i915_vma_unbind(vma); - if (err) - return err; - err = i915_vma_pin(vma, size, 0, flags | offset); if (err) { /* @@ -1117,7 +1131,7 @@ static int __igt_write_huge(struct intel_context *ce, return err; }
-static int igt_write_huge(struct i915_gem_context *ctx, +static int igt_write_huge(struct drm_i915_private *i915, struct drm_i915_gem_object *obj) { struct i915_gem_engines *engines; @@ -1127,6 +1141,8 @@ static int igt_write_huge(struct i915_gem_context *ctx, IGT_TIMEOUT(end_time); unsigned int max_page_size; unsigned int count; + struct i915_gem_context *ctx; + struct file *file; u64 max; u64 num; u64 size; @@ -1134,6 +1150,16 @@ static int igt_write_huge(struct i915_gem_context *ctx, int i, n; int err = 0;
+ file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + ctx = hugepage_ctx(i915, file); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; + } + GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
size = obj->base.size; @@ -1153,7 +1179,7 @@ static int igt_write_huge(struct i915_gem_context *ctx, } i915_gem_context_unlock_engines(ctx); if (!n) - return 0; + goto out;
/* * To keep things interesting when alternating between engines in our @@ -1215,6 +1241,8 @@ static int igt_write_huge(struct i915_gem_context *ctx,
kfree(order);
+out: + fput(file); return err; }
@@ -1277,8 +1305,7 @@ static u32 igt_random_size(struct rnd_state *prng,
static int igt_ppgtt_smoke_huge(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; + struct drm_i915_private *i915 = arg; struct drm_i915_gem_object *obj; I915_RND_STATE(prng); struct { @@ -1302,6 +1329,7 @@ static int igt_ppgtt_smoke_huge(void *arg) u32 min = backends[i].min; u32 max = backends[i].max; u32 size = max; + try_again: size = igt_random_size(&prng, min, rounddown_pow_of_two(size));
@@ -1336,7 +1364,7 @@ static int igt_ppgtt_smoke_huge(void *arg) goto out_unpin; }
- err = igt_write_huge(ctx, obj); + err = igt_write_huge(i915, obj); if (err) { pr_err("%s write-huge failed with size=%u, i=%d\n", __func__, size, i); @@ -1363,8 +1391,7 @@ static int igt_ppgtt_smoke_huge(void *arg)
static int igt_ppgtt_sanity_check(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; + struct drm_i915_private *i915 = arg; unsigned int supported = INTEL_INFO(i915)->page_sizes; struct { igt_create_fn fn; @@ -1431,7 +1458,7 @@ static int igt_ppgtt_sanity_check(void *arg) if (pages) obj->mm.page_sizes.sg = pages;
- err = igt_write_huge(ctx, obj); + err = igt_write_huge(i915, obj);
i915_gem_object_lock(obj, NULL); i915_gem_object_unpin_pages(obj); @@ -1458,15 +1485,27 @@ static int igt_ppgtt_sanity_check(void *arg)
static int igt_tmpfs_fallback(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; + struct drm_i915_private *i915 = arg; + struct i915_address_space *vm; + struct i915_gem_context *ctx; struct vfsmount *gemfs = i915->mm.gemfs; - struct i915_address_space *vm = i915_gem_context_get_eb_vm(ctx); struct drm_i915_gem_object *obj; struct i915_vma *vma; + struct file *file; u32 *vaddr; int err = 0;
+ file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + ctx = hugepage_ctx(i915, file); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; + } + vm = i915_gem_context_get_eb_vm(ctx); + /* * Make sure that we don't burst into a ball of flames upon falling back * to tmpfs, which we rely on if on the off-chance we encouter a failure @@ -1510,33 +1549,47 @@ static int igt_tmpfs_fallback(void *arg) i915->mm.gemfs = gemfs;
i915_vm_put(vm); +out: + fput(file); return err; }
static int igt_shrink_thp(void *arg) { - struct i915_gem_context *ctx = arg; - struct drm_i915_private *i915 = ctx->i915; - struct i915_address_space *vm = i915_gem_context_get_eb_vm(ctx); + struct drm_i915_private *i915 = arg; + struct i915_address_space *vm; + struct i915_gem_context *ctx; struct drm_i915_gem_object *obj; struct i915_gem_engines_iter it; struct intel_context *ce; struct i915_vma *vma; + struct file *file; unsigned int flags = PIN_USER; unsigned int n; bool should_swap; - int err = 0; + int err; + + if (!igt_can_allocate_thp(i915)) { + pr_info("missing THP support, skipping\n"); + return 0; + } + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + ctx = hugepage_ctx(i915, file); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; + } + vm = i915_gem_context_get_eb_vm(ctx);
/* * Sanity check shrinking huge-paged object -- make sure nothing blows * up. */
- if (!igt_can_allocate_thp(i915)) { - pr_info("missing THP support, skipping\n"); - goto out_vm; - } - obj = i915_gem_object_create_shmem(i915, SZ_2M); if (IS_ERR(obj)) { err = PTR_ERR(obj); @@ -1626,7 +1679,8 @@ static int igt_shrink_thp(void *arg) i915_gem_object_put(obj); out_vm: i915_vm_put(vm); - +out: + fput(file); return err; }
@@ -1687,10 +1741,6 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_ppgtt_smoke_huge), SUBTEST(igt_ppgtt_sanity_check), }; - struct i915_gem_context *ctx; - struct i915_address_space *vm; - struct file *file; - int err;
if (!HAS_PPGTT(i915)) { pr_info("PPGTT not supported, skipping live-selftests\n"); @@ -1700,23 +1750,5 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915) if (intel_gt_is_wedged(&i915->gt)) return 0;
- file = mock_file(i915); - if (IS_ERR(file)) - return PTR_ERR(file); - - ctx = live_context(i915, file); - if (IS_ERR(ctx)) { - err = PTR_ERR(ctx); - goto out_file; - } - - vm = ctx->vm; - if (vm) - WRITE_ONCE(vm->scrub_64K, true); - - err = i915_subtests(tests, ctx); - -out_file: - fput(file); - return err; + return i915_live_subtests(tests, i915); }
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
Lets be thorough here. Users of the TTM backend would likely expect this behaviour.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/i915_drv.h | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 57f2f8da931e..1dc30ee26771 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1818,6 +1818,7 @@ static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915) */ while (atomic_read(&i915->mm.free_count)) { flush_work(&i915->mm.free_work); + flush_delayed_work(&i915->bdev.wq); rcu_barrier(); } }
From: Maarten Lankhorst maarten.lankhorst@linux.intel.com
TTM already requires this, and we require it for delayed destroy.
Signed-off-by: Maarten Lankhorst maarten.lankhorst@linux.intel.com Reviewed-by: Matthew Auld matthew.auld@intel.com Signed-off-by: Matthew Auld matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_object.c | 5 +++++ 1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 55b0f1df3192..6e5412e2b5ad 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -257,6 +257,8 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) */ void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj) { + assert_object_held(obj); + if (!list_empty(&obj->vma.list)) { struct i915_vma *vma;
@@ -323,7 +325,10 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, obj->ops->delayed_free(obj); continue; } + + i915_gem_object_lock(obj, NULL); __i915_gem_object_pages_fini(obj); + i915_gem_object_unlock(obj); __i915_gem_free_object(obj);
/* But keep the pointer alive for RCU-protected lookups */
dri-devel@lists.freedesktop.org
-
Matthew Auld