[PATCH 2/2] mailbox: mtk-cmdq: Fix local clock ID usage

Fei Shao fshao at chromium.org
Thu Oct 14 02:31:11 PDT 2021


In the probe function, the clock IDs were pointed to local variables
which should only be used in the same code block, and any access to them
after the probing stage becomes a use-after-free case.

Since there are only limited variants of the gce clock names so far, we
can just declare them as global constants to fix the issue.

Fixes: 85dfdbfc13ea ("mailbox: cmdq: add multi-gce clocks support for
mt8195")
Signed-off-by: Fei Shao <fshao at chromium.org>

---

 drivers/mailbox/mtk-cmdq-mailbox.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index f3e52dddd422..27248b31cd51 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -90,6 +90,9 @@ struct gce_plat {
 	u32 gce_num;
 };
 
+const char *clk_name = "gce";
+const char *clk_names[] = { "gce0", "gce1" };
+
 u8 cmdq_get_shift_pa(struct mbox_chan *chan)
 {
 	struct cmdq *cmdq = container_of(chan->mbox, struct cmdq, mbox);
@@ -532,7 +535,6 @@ static int cmdq_probe(struct platform_device *pdev)
 	struct device_node *phandle = dev->of_node;
 	struct device_node *node;
 	int alias_id = 0;
-	char clk_name[4] = "gce";
 
 	cmdq = devm_kzalloc(dev, sizeof(*cmdq), GFP_KERNEL);
 	if (!cmdq)
@@ -570,12 +572,9 @@ static int cmdq_probe(struct platform_device *pdev)
 
 	if (cmdq->gce_num > 1) {
 		for_each_child_of_node(phandle->parent, node) {
-			char clk_id[8];
-
 			alias_id = of_alias_get_id(node, clk_name);
 			if (alias_id >= 0 && alias_id < cmdq->gce_num) {
-				snprintf(clk_id, sizeof(clk_id), "%s%d", clk_name, alias_id);
-				cmdq->clocks[alias_id].id = clk_id;
+				cmdq->clocks[alias_id].id = clk_names[alias_id];
 				cmdq->clocks[alias_id].clk = of_clk_get(node, 0);
 				if (IS_ERR(cmdq->clocks[alias_id].clk)) {
 					dev_err(dev, "failed to get gce clk: %d\n", alias_id);
-- 
2.33.0.882.g93a45727a2-goog




More information about the linux-arm-kernel mailing list