of_alias_get_id() may return -ENODEV which leads to illegal access to
the cmdq->clocks array.
Adding a check over alias_id to prevent the unexpected behavior.
Fixes: 85dfdbfc13ea ("mailbox: cmdq: add multi-gce clocks support for
mt8195")
Signed-off-by: Fei Shao <[email protected]>
---
drivers/mailbox/mtk-cmdq-mailbox.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 64175a893312..f3e52dddd422 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -573,7 +573,7 @@ static int cmdq_probe(struct platform_device *pdev)
char clk_id[8];
alias_id = of_alias_get_id(node, clk_name);
- if (alias_id < cmdq->gce_num) {
+ 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].clk = of_clk_get(node, 0);
--
2.33.0.882.g93a45727a2-goog
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 <[email protected]>
---
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
On Thu, Oct 14, 2021 at 05:31:10PM +0800, Fei Shao wrote:
> of_alias_get_id() may return -ENODEV which leads to illegal access to
> the cmdq->clocks array.
> Adding a check over alias_id to prevent the unexpected behavior.
>
> Fixes: 85dfdbfc13ea ("mailbox: cmdq: add multi-gce clocks support for
> mt8195")
> Signed-off-by: Fei Shao <[email protected]>
Reviewed-by: Tzung-Bi Shih <[email protected]>
On Thu, Oct 14, 2021 at 05:31:11PM +0800, Fei Shao wrote:
> +const char *clk_name = "gce";
> +const char *clk_names[] = { "gce0", "gce1" };
Does letting them static make more sense?
On Thu, Oct 14, 2021 at 7:33 PM Fei Shao <[email protected]> wrote:
>
> On Thu, Oct 14, 2021 at 6:47 PM Tzung-Bi Shih <[email protected]> wrote:
> >
> > On Thu, Oct 14, 2021 at 05:31:11PM +0800, Fei Shao wrote:
> > > +const char *clk_name = "gce";
> > > +const char *clk_names[] = { "gce0", "gce1" };
> > Does letting them static make more sense?
> Yes, I'll send a v2 later. Thanks!
Probably better to keep their scope in probe function but extend the
lifecycle by using static.
On Thu, Oct 14, 2021 at 6:47 PM Tzung-Bi Shih <[email protected]> wrote:
>
> On Thu, Oct 14, 2021 at 05:31:11PM +0800, Fei Shao wrote:
> > +const char *clk_name = "gce";
> > +const char *clk_names[] = { "gce0", "gce1" };
> Does letting them static make more sense?
Yes, I'll send a v2 later. Thanks!