| Message ID | 20211206114542.45325-1-stephan@gerhold.net |
|---|---|
| State | Accepted |
| Commit | a7d9436a6c85fcb8843c910fd323dcd7f839bf63 |
| Headers | show |
| Series | interconnect: qcom: rpm: Prevent integer overflow in rate | expand |
diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index 6b918d082ab6..58894072adce 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -240,6 +240,7 @@ static int qcom_icc_set(struct icc_node *src, struct icc_node *dst) rate = max(sum_bw, max_peak_bw); do_div(rate, qn->buswidth); + rate = min_t(u64, rate, LONG_MAX); if (qn->rate == rate) return 0;
Using icc-rpm on ARM32 currently results in clk_set_rate() errors during boot, e.g. "bus clk_set_rate error: -22". This is very similar to commit 7381e27b1e56 ("interconnect: qcom: msm8974: Prevent integer overflow in rate") where the u64 is converted to a signed long during clock rate rounding, resulting in an overflow on 32-bit platforms. Let's fix it similarly by making sure that the rate does not exceed LONG_MAX. Such high clock rates will surely result in the maximum frequency of the bus anyway. Signed-off-by: Stephan Gerhold <stephan@gerhold.net> --- drivers/interconnect/qcom/icc-rpm.c | 1 + 1 file changed, 1 insertion(+)