| Message ID | 20211014093112.3852491-2-fshao@chromium.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [1/2] mailbox: mtk-cmdq: Validate alias_id on probe | expand |
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 6:47 PM Tzung-Bi Shih <tzungbi@google.com> 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!
On Thu, Oct 14, 2021 at 7:33 PM Fei Shao <fshao@chromium.org> wrote: > > On Thu, Oct 14, 2021 at 6:47 PM Tzung-Bi Shih <tzungbi@google.com> 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.
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);
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@chromium.org> --- drivers/mailbox/mtk-cmdq-mailbox.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)