drm/amdkfd: Fix mmap write lock not release

[ Upstream commit 7574f30337e19045f03126b4c51f525b84e5049e ]

If mmap write lock is taken while draining retry fault, mmap write lock
is not released because svm_range_restore_pages calls mmap_read_unlock
then returns. This causes deadlock and system hangs later because mmap
read or write lock cannot be taken.

Downgrade mmap write lock to read lock if draining retry fault fix this
bug.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 155948dc3d07ae36872d42e131f475f731a364a0..0d950a20741d8f914b388531216374febbae289d 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3036,6 +3036,8 @@ retry_write_locked:
        if (svms->checkpoint_ts[gpuidx] != 0) {
                if (amdgpu_ih_ts_after_or_equal(ts,  svms->checkpoint_ts[gpuidx])) {
                        pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
+                       if (write_locked)
+                               mmap_write_downgrade(mm);
                        r = -EAGAIN;
                        goto out_unlock_svms;
                } else {