As a prelude to the next step where we want to perform all the object
allocations together under the same lock, we first must delay the
i915_vma_pin() as that implicitly does the allocations for us, one by
one. As it only does the allocations one by one, it is not allowed to
wait/evict, whereas pulling all the allocations together the entire set
can be scheduled as one.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
.../gpu/drm/i915/gem/i915_gem_execbuffer.c | 70 +++++++++++--------
1 file changed, 39 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index bf8193d9e279..35a57c1fc9c3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -33,6 +33,8 @@ struct eb_vma {
/** This vma's place in the execbuf reservation list */
struct drm_i915_gem_exec_object2 *exec;
+
+ struct list_head bind_link;
struct list_head unbound_link;
struct list_head reloc_link;
@@ -240,8 +242,8 @@ struct i915_execbuffer {
/** actual size of execobj[] as we may extend it for the cmdparser */
unsigned int buffer_count;
- /** list of vma not yet bound during reservation phase */
- struct list_head unbound;
+ /** list of all vma required to bound for this execbuf */
+ struct list_head bind_list;
/** list of vma that have execobj.relocation_count */
struct list_head relocs;
@@ -565,6 +567,8 @@ eb_add_vma(struct i915_execbuffer *eb,
eb->lut_size)]);
}
+ list_add_tail(&ev->bind_link, &eb->bind_list);
+
if (entry->relocation_count)
list_add_tail(&ev->reloc_link, &eb->relocs);
@@ -586,16 +590,6 @@ eb_add_vma(struct i915_execbuffer *eb,
eb->batch = ev;
}
-
- if (eb_pin_vma(eb, entry, ev)) {
- if (entry->offset != vma->node.start) {
- entry->offset = vma->node.start | UPDATE;
- eb->args->flags |= __EXEC_HAS_RELOC;
- }
- } else {
- eb_unreserve_vma(ev);
- list_add_tail(&ev->unbound_link, &eb->unbound);
- }
}
static int eb_reserve_vma(const struct i915_execbuffer *eb,
@@ -670,13 +664,31 @@ static int wait_for_timeline(struct intel_timeline *tl)
} while (1);
}
-static int eb_reserve(struct i915_execbuffer *eb)
+static int eb_reserve_vm(struct i915_execbuffer *eb)
{
- const unsigned int count = eb->buffer_count;
unsigned int pin_flags = PIN_USER | PIN_NONBLOCK;
- struct list_head last;
+ struct list_head last, unbound;
struct eb_vma *ev;
- unsigned int i, pass;
+ unsigned int pass;
+
+ INIT_LIST_HEAD(&unbound);
+ list_for_each_entry(ev, &eb->bind_list, bind_link) {
+ struct drm_i915_gem_exec_object2 *entry = ev->exec;
+ struct i915_vma *vma = ev->vma;
+
+ if (eb_pin_vma(eb, entry, ev)) {
+ if (entry->offset != vma->node.start) {
+ entry->offset = vma->node.start | UPDATE;
+ eb->args->flags |= __EXEC_HAS_RELOC;
+ }
+ } else {
+ eb_unreserve_vma(ev);
+ list_add_tail(&ev->unbound_link, &unbound);
+ }
+ }
+
+ if (list_empty(&unbound))
+ return 0;
/*
* Attempt to pin all of the buffers into the GTT.
@@ -699,7 +711,7 @@ static int eb_reserve(struct i915_execbuffer *eb)
if (mutex_lock_interruptible(&eb->i915->drm.struct_mutex))
return -EINTR;
- list_for_each_entry(ev, &eb->unbound, unbound_link) {
+ list_for_each_entry(ev, &unbound, unbound_link) {
err = eb_reserve_vma(eb, ev, pin_flags);
if (err)
break;
@@ -710,13 +722,11 @@ static int eb_reserve(struct i915_execbuffer *eb)
}
/* Resort *all* the objects into priority order */
- INIT_LIST_HEAD(&eb->unbound);
+ INIT_LIST_HEAD(&unbound);
INIT_LIST_HEAD(&last);
- for (i = 0; i < count; i++) {
- unsigned int flags;
+ list_for_each_entry(ev, &eb->bind_list, bind_link) {
+ unsigned int flags = ev->flags;
- ev = &eb->vma[i];
- flags = ev->flags;
if (flags & EXEC_OBJECT_PINNED &&
flags & __EXEC_OBJECT_HAS_PIN)
continue;
@@ -725,17 +735,17 @@ static int eb_reserve(struct i915_execbuffer *eb)
if (flags & EXEC_OBJECT_PINNED)
/* Pinned must have their slot */
- list_add(&ev->unbound_link, &eb->unbound);
+ list_add(&ev->unbound_link, &unbound);
else if (flags & __EXEC_OBJECT_NEEDS_MAP)
/* Map require the lowest 256MiB (aperture) */
- list_add_tail(&ev->unbound_link, &eb->unbound);
+ list_add_tail(&ev->unbound_link, &unbound);
else if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS))
/* Prioritise 4GiB region for restricted bo */
list_add(&ev->unbound_link, &last);
else
list_add_tail(&ev->unbound_link, &last);
}
- list_splice_tail(&last, &eb->unbound);
+ list_splice_tail(&last, &unbound);
mutex_unlock(&eb->i915->drm.struct_mutex);
if (err == -EAGAIN) {
@@ -891,8 +901,8 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
unsigned int i;
int err = 0;
+ INIT_LIST_HEAD(&eb->bind_list);
INIT_LIST_HEAD(&eb->relocs);
- INIT_LIST_HEAD(&eb->unbound);
for (i = 0; i < eb->buffer_count; i++) {
struct i915_vma *vma;
@@ -1539,11 +1549,9 @@ static int eb_relocate(struct i915_execbuffer *eb)
if (err)
return err;
- if (!list_empty(&eb->unbound)) {
- err = eb_reserve(eb);
- if (err)
- return err;
- }
+ err = eb_reserve_vm(eb);
+ if (err)
+ return err;
/* The objects are in their final locations, apply the relocations. */
if (eb->args->flags & __EXEC_HAS_RELOC) {
