amdgpu_device_ip_soft_reset() allocates an array of AMDGPU_MAX_RINGS
ring pointers on the stack. On 64-bit builds this consumes around 1280
bytes and triggers:
warning: stack frame size (1304) exceeds limit (1024)
Move the temporary ring pointer array to heap allocation to reduce stack
usage.
v2: (Alex)
- Avoid allocating memory in the reset path.
- Use a pre-allocated ring pointer array stored in amdgpu_device.
Fixes: a6319ac34a13 ("drm/amdgpu: Add IP block soft reset as a GPU recovery
method")
Cc: Alex Deucher <[email protected]>
Cc: Timur Kristóf <[email protected]>
Signed-off-by: Srinivasan Shanmugam <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_ip.c | 8 +++++---
2 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 4c3e933ff6d5..30053ca3b92b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -889,6 +889,8 @@ struct amdgpu_device {
u64 fence_context;
unsigned num_rings;
struct amdgpu_ring *rings[AMDGPU_MAX_RINGS];
+ /* Temporary ring list used during IP block soft reset. */
+ struct amdgpu_ring *ip_soft_reset_rings[AMDGPU_MAX_RINGS];
struct dma_fence __rcu *gang_submit;
bool ib_pool_ready;
struct amdgpu_sa_manager ib_pools[AMDGPU_IB_POOL_MAX];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ip.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ip.c
index 65505bc50399..c8af5a158cea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ip.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ip.c
@@ -524,7 +524,7 @@ int amdgpu_device_ip_soft_reset(struct amdgpu_ring
*guilty_ring,
struct amdgpu_fence *guilty_fence)
{
struct amdgpu_device *adev = guilty_ring->adev;
- struct amdgpu_ring *rings[AMDGPU_MAX_RINGS];
+ struct amdgpu_ring **rings = adev->ip_soft_reset_rings;
struct amdgpu_ip_block *ip_block;
enum amd_ip_block_type ip_type;
u32 num_rings, ring_type_mask;
@@ -546,11 +546,13 @@ int amdgpu_device_ip_soft_reset(struct amdgpu_ring
*guilty_ring,
amdgpu_filter_rings(adev, ring_type_mask, rings, &num_rings);
amdgpu_device_lock_reset_domain(adev->reset_domain);
- amdgpu_multi_ring_reset_helper_begin(rings, num_rings, guilty_ring,
guilty_fence);
+ amdgpu_multi_ring_reset_helper_begin(rings, num_rings, guilty_ring,
+ guilty_fence);
r = ip_block->version->funcs->soft_reset(ip_block);
- r = amdgpu_multi_ring_reset_helper_end(rings, num_rings, guilty_ring,
r);
+ r = amdgpu_multi_ring_reset_helper_end(rings, num_rings, guilty_ring,
+ r);
amdgpu_device_unlock_reset_domain(adev->reset_domain);
if (r) {
--
2.34.1
