4.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Bjorn Andersson <[email protected]>

commit e7d5e412160c2143de1f818668774b33b3cdab0b upstream.

Upon failing to acquire regulator supplies the qcom-ufs driver calls
kfree() on the devm allocated memory used to store the name of the
regulator, leading to devres corruption.

Rather than switching to using the appropriate free function the patch
acknowledge the fact that "name" is always a constant string and we
don't actually need to create a local copy of it, but rather just
reference the constant string.

Fixes: add78fc05702 ("phy: qcom-ufs: Use devm sibling of kstrdup for regulator 
names")
Reviewed-by: Subhash Jadavani <[email protected]>
Signed-off-by: Bjorn Andersson <[email protected]>
Signed-off-by: Kishon Vijay Abraham I <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

---
 drivers/phy/phy-qcom-ufs.c |    9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

--- a/drivers/phy/phy-qcom-ufs.c
+++ b/drivers/phy/phy-qcom-ufs.c
@@ -217,12 +217,7 @@ static int __ufs_qcom_phy_init_vreg(stru
 
        char prop_name[MAX_PROP_NAME];
 
-       vreg->name = devm_kstrdup(dev, name, GFP_KERNEL);
-       if (!vreg->name) {
-               err = -ENOMEM;
-               goto out;
-       }
-
+       vreg->name = name;
        vreg->reg = devm_regulator_get(dev, name);
        if (IS_ERR(vreg->reg)) {
                err = PTR_ERR(vreg->reg);
@@ -265,8 +260,6 @@ static int __ufs_qcom_phy_init_vreg(stru
        }
 
 out:
-       if (err)
-               kfree(vreg->name);
        return err;
 }
 


Reply via email to