[PATCH v2] cpufreq: qcom-hw: Fix reading "reg" with address/size-cells != 2

[PATCH v2] cpufreq: qcom-hw: Fix reading "reg" with address/size-cells != 2

[Konrad Dybcio]

Commit 054a3ef683a1 ("cpufreq: qcom-hw: Allocate qcom_cpufreq_data during
probe") assumed that every reg variable is 4*u32 wide (as most new qcom
SoCs set #address- and #size-cells to <2>. That is not the case for all of
them though. Check the cells values dynamically to ensure the proper
region of the DTB is being read.

Fixes: 054a3ef683a1 ("cpufreq: qcom-hw: Allocate qcom_cpufreq_data during probe")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
---
Changes in v2:
- remove the comment about 'i' reuse
- call of_node_put() on exit

 drivers/cpufreq/qcom-cpufreq-hw.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 340fed35e45d..9505a812d6a1 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -649,9 +649,10 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
 {
 	struct clk_hw_onecell_data *clk_data;
 	struct device *dev = &pdev->dev;
+	struct device_node *soc_node;
 	struct device *cpu_dev;
 	struct clk *clk;
-	int ret, i, num_domains;
+	int ret, i, num_domains, reg_sz;
 
 	clk = clk_get(dev, "xo");
 	if (IS_ERR(clk))
@@ -679,7 +680,21 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
 		return ret;
 
 	/* Allocate qcom_cpufreq_data based on the available frequency domains in DT */
-	num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * 4);
+	soc_node = of_get_parent(dev->of_node);
+	if (!soc_node)
+		return -EINVAL;
+
+	ret = of_property_read_u32(soc_node, "#address-cells", &reg_sz);
+	if (ret)
+		goto of_exit;
+
+	ret = of_property_read_u32(soc_node, "#size-cells", &i);
+	if (ret)
+		goto of_exit;
+
+	reg_sz += i;
+
+	num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * reg_sz);
 	if (num_domains <= 0)
 		return num_domains;
 
@@ -743,6 +758,9 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
 	else
 		dev_dbg(dev, "QCOM CPUFreq HW driver initialized\n");
 
+of_exit:
+	of_node_put(soc_node);
+
 	return ret;
 }
 
-- 
2.39.0

Re: [PATCH v2] cpufreq: qcom-hw: Fix reading "reg" with address/size-cells != 2

[Viresh Kumar]

On 20-12-22, 14:39, Konrad Dybcio wrote:
> Commit 054a3ef683a1 ("cpufreq: qcom-hw: Allocate qcom_cpufreq_data during
> probe") assumed that every reg variable is 4*u32 wide (as most new qcom
> SoCs set #address- and #size-cells to <2>. That is not the case for all of
> them though. Check the cells values dynamically to ensure the proper
> region of the DTB is being read.
> 
> Fixes: 054a3ef683a1 ("cpufreq: qcom-hw: Allocate qcom_cpufreq_data during probe")
> Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
> ---
> Changes in v2:
> - remove the comment about 'i' reuse
> - call of_node_put() on exit

Applied. Thanks.

-- 
viresh