Commit d344b21b authored by Dan Carpenter's avatar Dan Carpenter Committed by Alex Deucher

drm/amd/amdgpu: Fix debugfs error handling

The error handling is wrong and "ent" could be NULL we when dereference
it to get "ent->d_inode".

The thing is that normally debugfs_create_file() is not supposed to
require (or have) any error handling.  That function does return error
pointers if debugfs is turned off but we know it's enable here.  When
it's enabled, then it returns NULL on error.

So what I did was I stripped out all the error handling except around
the i_size_write().  I could have just used a NULL check instead of an
IS_ERR_OR_NULL() but I figured this was more clear because that way you
don't have to look at the surrounding code to see whether debugfs is
enabled or not.
Signed-off-by: default avatarDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: default avatarChristian König <christian.koenig@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent c55045ad
...@@ -826,21 +826,13 @@ int amdgpu_debugfs_regs_init(struct amdgpu_device *adev) ...@@ -826,21 +826,13 @@ int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
{ {
struct drm_minor *minor = adev->ddev->primary; struct drm_minor *minor = adev->ddev->primary;
struct dentry *ent, *root = minor->debugfs_root; struct dentry *ent, *root = minor->debugfs_root;
unsigned i, j; unsigned int i;
for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) { for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) {
ent = debugfs_create_file(debugfs_regs_names[i], ent = debugfs_create_file(debugfs_regs_names[i],
S_IFREG | S_IRUGO, root, S_IFREG | S_IRUGO, root,
adev, debugfs_regs[i]); adev, debugfs_regs[i]);
if (IS_ERR(ent)) { if (!i && !IS_ERR_OR_NULL(ent))
for (j = 0; j < i; j++) {
debugfs_remove(adev->debugfs_regs[i]);
adev->debugfs_regs[i] = NULL;
}
return PTR_ERR(ent);
}
if (!i)
i_size_write(ent->d_inode, adev->rmmio_size); i_size_write(ent->d_inode, adev->rmmio_size);
adev->debugfs_regs[i] = ent; adev->debugfs_regs[i] = ent;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment