Message ID | 20211014120352.1506321-3-fshao@chromium.org (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | Fixups for mtk-cmdq multi-gce support | expand |
On Thu, Oct 14, 2021 at 08:03:52PM +0800, Fei Shao wrote: > 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 an use-after-free case. > > Since there are only limited variants of the gce clock names so far, we > can just declare them as static constants to fix the issue. > > Fixes: 85dfdbfc13ea ("mailbox: cmdq: add multi-gce clocks support for > mt8195") > Signed-off-by: Fei Shao <fshao@chromium.org> Reviewed-by: Tzung-Bi Shih <tzungbi@google.com>
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index f3e52dddd422..95ce7275641c 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -532,7 +532,8 @@ 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"; + static const char * const clk_name = "gce"; + static const char * const clk_names[] = { "gce0", "gce1" }; cmdq = devm_kzalloc(dev, sizeof(*cmdq), GFP_KERNEL); if (!cmdq) @@ -570,12 +571,9 @@ 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 an use-after-free case. Since there are only limited variants of the gce clock names so far, we can just declare them as static constants to fix the issue. Fixes: 85dfdbfc13ea ("mailbox: cmdq: add multi-gce clocks support for mt8195") Signed-off-by: Fei Shao <fshao@chromium.org> --- Changes in v2: - Make clock names static drivers/mailbox/mtk-cmdq-mailbox.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) -- 2.33.0.882.g93a45727a2-goog