drm/i915: don't do allocate_va_range again on PIN_UPDATE

If a vma is already bound to a ppgtt, we incorrectly call
allocate_va_range again when doing a PIN_UPDATE, which will result in
over accounting within our paging structures, such that when we do
unbind something we don't actually destroy the structures and end up
inadvertently recycling them. In reality this probably isn't too bad,
but once we start touching PDEs and PDPEs for 64K/2M/1G pages this
apparent recycling will manifest into lots of really, really subtle
bugs.

v2: Fix the testing of vma->flags for aliasing_ppgtt_bind_vma

Fixes: ff685975d9 ("drm/i915: Move allocate_va_range to GTT")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170512091423.26085-1-chris@chris-wilson.co.uk
(cherry picked from commit 1f23475c89)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
This commit is contained in:
Matthew Auld 2017-05-12 10:14:23 +01:00 committed by Jani Nikula
parent 82f2b4aca8
commit 2f720aac93

View file

@ -195,9 +195,12 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
u32 pte_flags;
int ret;
ret = vma->vm->allocate_va_range(vma->vm, vma->node.start, vma->size);
if (ret)
return ret;
if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
ret = vma->vm->allocate_va_range(vma->vm, vma->node.start,
vma->size);
if (ret)
return ret;
}
vma->pages = vma->obj->mm.pages;
@ -2306,7 +2309,8 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
if (flags & I915_VMA_LOCAL_BIND) {
struct i915_hw_ppgtt *appgtt = i915->mm.aliasing_ppgtt;
if (appgtt->base.allocate_va_range) {
if (!(vma->flags & I915_VMA_LOCAL_BIND) &&
appgtt->base.allocate_va_range) {
ret = appgtt->base.allocate_va_range(&appgtt->base,
vma->node.start,
vma->node.size);