drm/etnaviv: lock MMU while dumping core

The devcoredump needs to operate on a stable state of the MMU while
it is writing the MMU state to the coredump. The missing lock
allowed both the userspace submit, as well as the GPU job finish
paths to mutate the MMU state while a coredump is under way.

Fixes: a8c21a5451 (drm/etnaviv: add initial etnaviv DRM driver)
Reported-by: David Jander <david@protonic.nl>
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Tested-by: David Jander <david@protonic.nl>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
This commit is contained in:
Lucas Stach 2019-05-21 14:53:40 +02:00
parent a188339ca5
commit 1396500d67
1 changed files with 5 additions and 0 deletions

View File

@ -125,6 +125,8 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu)
return;
etnaviv_dump_core = false;
mutex_lock(&gpu->mmu->lock);
mmu_size = etnaviv_iommu_dump_size(gpu->mmu);
/* We always dump registers, mmu, ring and end marker */
@ -167,6 +169,7 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu)
iter.start = __vmalloc(file_size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
PAGE_KERNEL);
if (!iter.start) {
mutex_unlock(&gpu->mmu->lock);
dev_warn(gpu->dev, "failed to allocate devcoredump file\n");
return;
}
@ -234,6 +237,8 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu)
obj->base.size);
}
mutex_unlock(&gpu->mmu->lock);
etnaviv_core_dump_header(&iter, ETDUMP_BUF_END, iter.data);
dev_coredumpv(gpu->dev, iter.start, iter.data - iter.start, GFP_KERNEL);