Problem statement: During the system boot time, an application request
for the bulk volume of cleared range bias memory when the clear_avail
is zero, we dont fallback into normal allocation method as we had an
unnecessary clear_avail check which prevents the fallback method leads
to fb allocation failure following system goes into unresponsive state.

Solution: Remove the unnecessary clear_avail check in the range bias
allocation function.

v2: add a kunit for this corner case (Daniel Vetter)

Signed-off-by: Arunpravin Paneer Selvam <arunpravin.paneersel...@amd.com>
Fixes: 96950929eb23 ("drm/buddy: Implement tracking clear page feature")
Reviewed-by: Matthew Auld <matthew.a...@intel.com>
---
 drivers/gpu/drm/drm_buddy.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 284ebae71cc4..1daf778cf6fa 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -249,6 +249,7 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 
chunk_size)
 
        mm->size = size;
        mm->avail = size;
+       mm->clear_avail = 0;
        mm->chunk_size = chunk_size;
        mm->max_order = ilog2(size) - ilog2(chunk_size);
 
@@ -574,7 +575,7 @@ __drm_buddy_alloc_range_bias(struct drm_buddy *mm,
 
        block = __alloc_range_bias(mm, start, end, order,
                                   flags, fallback);
-       if (IS_ERR(block) && mm->clear_avail)
+       if (IS_ERR(block))
                return __alloc_range_bias(mm, start, end, order,
                                          flags, !fallback);
 
-- 
2.25.1

Reply via email to