Handle persistent (VM_BIND) mappings during the request submission
in the execbuf3 path.
v2: Ensure requests wait for bindings to complete.
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@xxxxxxxxx>
Signed-off-by: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>
---
.../gpu/drm/i915/gem/i915_gem_execbuffer3.c | 214 +++++++++++++++++-
1 file changed, 213 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer3.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer3.c
index 66b723842e45..5cece16949d8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer3.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer3.c
@@ -19,6 +19,7 @@
#include "i915_gem_vm_bind.h"
#include "i915_trace.h"
+#define __EXEC3_HAS_PIN BIT_ULL(33)
#define __EXEC3_ENGINE_PINNED BIT_ULL(32)
#define __EXEC3_INTERNAL_FLAGS (~0ull << 32)
@@ -42,7 +43,9 @@
* execlist. Hence, no support for implicit sync.
*
* The new execbuf3 ioctl only works in VM_BIND mode and the VM_BIND mode only
- * works with execbuf3 ioctl for submission.
+ * works with execbuf3 ioctl for submission. All BOs mapped on that VM (through
+ * VM_BIND call) at the time of execbuf3 call are deemed required for that
+ * submission.
*
* The execbuf3 ioctl directly specifies the batch addresses instead of as
* object handles as in execbuf2 ioctl. The execbuf3 ioctl will also not
@@ -58,6 +61,13 @@
* So, a lot of code supporting execbuf2 ioctl, like relocations, VA evictions,
* vma lookup table, implicit sync, vma active reference tracking etc., are not
* applicable for execbuf3 ioctl.
+ *
+ * During each execbuf submission, request fence is added to all VM_BIND mapped
+ * objects with DMA_RESV_USAGE_BOOKKEEP. The DMA_RESV_USAGE_BOOKKEEP usage will
+ * prevent over sync (See enum dma_resv_usage). Note that DRM_I915_GEM_WAIT and
+ * DRM_I915_GEM_BUSY ioctls do not check for DMA_RESV_USAGE_BOOKKEEP usage and
+ * hence should not be used for end of batch check. Instead, the execbuf3
+ * timeline out fence should be used for end of batch check.
*/
/**
@@ -127,6 +137,23 @@ eb_find_vma(struct i915_address_space *vm, u64 addr)
return i915_gem_vm_bind_lookup_vma(vm, va);
}
+static void eb_scoop_unbound_vma_all(struct i915_address_space *vm)
+{
+ struct i915_vma *vma, *vn;
+
+ /**
+ * Move all unbound vmas back into vm_bind_list so that they are
+ * revalidated.
+ */
+ spin_lock(&vm->vm_rebind_lock);
+ list_for_each_entry_safe(vma, vn, &vm->vm_rebind_list, vm_rebind_link) {
+ list_del_init(&vma->vm_rebind_link);
+ if (!list_empty(&vma->vm_bind_link))
+ list_move_tail(&vma->vm_bind_link, &vm->vm_bind_list);
+ }
+ spin_unlock(&vm->vm_rebind_lock);
+}
+
static int eb_lookup_vma_all(struct i915_execbuffer *eb)
{
unsigned int i, current_batch = 0;
@@ -141,14 +168,121 @@ static int eb_lookup_vma_all(struct i915_execbuffer *eb)
++current_batch;
}
+ eb_scoop_unbound_vma_all(eb->context->vm);
+
return 0;
}
+static int eb_lock_vma_all(struct i915_execbuffer *eb)
+{
+ struct i915_address_space *vm = eb->context->vm;
+ struct i915_vma *vma;
+ int err;
+
+ err = i915_gem_object_lock(eb->context->vm->root_obj, &eb->ww);
+ if (err)
+ return err;
+
+ list_for_each_entry(vma, &vm->non_priv_vm_bind_list,
+ non_priv_vm_bind_link) {
+ err = i915_gem_object_lock(vma->obj, &eb->ww);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static void eb_release_persistent_vma_all(struct i915_execbuffer *eb,
+ bool final)
+{
+ struct i915_address_space *vm = eb->context->vm;
+ struct i915_vma *vma, *vn;
+
+ lockdep_assert_held(&vm->vm_bind_lock);
+
+ if (!(eb->args->flags & __EXEC3_HAS_PIN))
+ return;
+
+ assert_object_held(vm->root_obj);
+
+ list_for_each_entry(vma, &vm->vm_bind_list, vm_bind_link)
+ __i915_vma_unpin(vma);
+
+ eb->args->flags &= ~__EXEC3_HAS_PIN;
+ if (!final)
+ return;
+
+ list_for_each_entry_safe(vma, vn, &vm->vm_bind_list, vm_bind_link)
+ if (i915_vma_verify_bind_complete(vma))
+ list_move_tail(&vma->vm_bind_link, &vm->vm_bound_list);
+}
+
static void eb_release_vma_all(struct i915_execbuffer *eb, bool final)
{
+ eb_release_persistent_vma_all(eb, final);
eb_unpin_engine(eb);
}
+static int eb_reserve_fence_for_persistent_vma_all(struct i915_execbuffer *eb)
+{
+ struct i915_address_space *vm = eb->context->vm;
+ struct i915_vma *vma;
+ int ret;
+
+ ret = dma_resv_reserve_fences(vm->root_obj->base.resv, 1);
+ if (ret)
+ return ret;
+
+ list_for_each_entry(vma, &vm->non_priv_vm_bind_list,
+ non_priv_vm_bind_link) {
+ ret = dma_resv_reserve_fences(vma->obj->base.resv, 1);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int eb_validate_persistent_vma_all(struct i915_execbuffer *eb)
+{
+ struct i915_address_space *vm = eb->context->vm;
+ struct i915_vma *vma, *last_pinned_vma = NULL;
+ int ret = 0;
+
+ lockdep_assert_held(&vm->vm_bind_lock);
+ assert_object_held(vm->root_obj);
+
+ ret = eb_reserve_fence_for_persistent_vma_all(eb);
+ if (ret)
+ return ret;
+
+ if (list_empty(&vm->vm_bind_list))
+ return 0;
+
+ list_for_each_entry(vma, &vm->vm_bind_list, vm_bind_link) {
+ u64 pin_flags = vma->start | PIN_OFFSET_FIXED | PIN_USER;