Hi,
On Tue, Jun 21, 2022 at 10:57 AM Vijaya Krishna Nivarthi
<quic_vnivarth@xxxxxxxxxxx> wrote:
>
> In the logic around call to clk_round_rate, for some corner conditions,
> get_clk_div_rate() could return an sub-optimal clock rate. Also, if an
> exact clock rate was not found lowest clock was being returned.
>
> Search for suitable clock rate in 2 steps
> a) exact match or within 2% tolerance
> b) within 5% tolerance
> This also takes care of corner conditions.
>
> Fixes: c2194bc999d4 ("tty: serial: qcom-geni-serial: Remove uart frequency table. Instead, find suitable frequency with call to clk_round_rate")
> Signed-off-by: Vijaya Krishna Nivarthi <quic_vnivarth@xxxxxxxxxxx>
> ---
> drivers/tty/serial/qcom_geni_serial.c | 134 ++++++++++++++++++++++++++--------
> 1 file changed, 102 insertions(+), 32 deletions(-)
>
> diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
> index 2e23b65..8d247c1 100644
> --- a/drivers/tty/serial/qcom_geni_serial.c
> +++ b/drivers/tty/serial/qcom_geni_serial.c
> @@ -943,52 +943,123 @@ static int qcom_geni_serial_startup(struct uart_port *uport)
> return 0;
> }
>
> -static unsigned long get_clk_div_rate(struct clk *clk, unsigned int baud,
> - unsigned int sampling_rate, unsigned int *clk_div)
> +static unsigned long find_clk_rate_in_tol(struct clk *clk, unsigned int desired_clk,
> + unsigned int *clk_div, unsigned int percent_tol, bool *exact_match)
> {
> + unsigned long freq;
> + unsigned long div, maxdiv, new_div;
> + unsigned long long mult;
> unsigned long ser_clk;
> - unsigned long desired_clk;
> - unsigned long freq, prev;
> - unsigned long div, maxdiv;
> - int64_t mult;
> -
> - desired_clk = baud * sampling_rate;
> - if (!desired_clk) {
> - pr_err("%s: Invalid frequency\n", __func__);
> - return 0;
> - }
> + unsigned long test_freq, offset, new_freq;
>
> + ser_clk = 0;
> maxdiv = CLK_DIV_MSK >> CLK_DIV_SHFT;
> - prev = 0;
> + div = 1;
>
> - for (div = 1; div <= maxdiv; div++) {
> - mult = div * desired_clk;
> - if (mult > ULONG_MAX)
> + while (div <= maxdiv) {
> + mult = (unsigned long long)div * desired_clk;
> + if (mult != (unsigned long)mult)
> break;
>
> - freq = clk_round_rate(clk, (unsigned long)mult);
> - if (!(freq % desired_clk)) {
> - ser_clk = freq;
> - break;
> + /*
> + * Loop requesting a freq within tolerance and possibly exact freq.
> + *
> + * We'll keep track of the lowest freq inexact match we found
> + * but always try to find a perfect match. NOTE: this algorithm
> + * could miss a slightly better freq if there's more than one
> + * freq between (freq - offset) and (freq) but (freq) can't be made
> + * exactly, but that's OK.
> + *
> + * This absolutely relies on the fact that the Qualcomm clock
> + * driver always rounds up.
> + * We make use of exact_match as an I/O param.
> + */
> +
> + /* look only for exact match if within tolerance is already found */
> + if (ser_clk)
> + offset = 0;
> + else
> + offset = (mult * percent_tol) / 100;
> +
> + test_freq = mult - offset;
> + freq = clk_round_rate(clk, test_freq);
> +
> + /*
> + * A dead-on freq is an insta-win, look for it only in 1st run
> + */
> + if (*exact_match) {
> + if (!(freq % desired_clk)) {
> + ser_clk = freq;
> + *clk_div = freq / desired_clk;
> + return ser_clk;
> + }
> + }
The "*exact_match" if test isn't needed here. It's not saving you any
significant amount of time. You're still doing an "if" test, right?
...so you're basically saving a mod operation by adding a pointer
dereference and complexity? I don't think that's the right tradeoff.
> + if (!ser_clk) {
> + new_div = DIV_ROUND_CLOSEST(freq, desired_clk);
> + new_freq = new_div * desired_clk;
> + offset = (new_freq * percent_tol) / 100;
> +
> + if (new_freq - offset <= freq && freq <= new_freq + offset) {
> + /* Save the first (lowest freq) within tolerance */
> + ser_clk = freq;
> + *clk_div = new_div;
> + /* no more search for exact match required in 2nd run */
> + if (!(*exact_match))
> + break;
> + }
> }
>
> - if (!prev)
> - ser_clk = freq;
> - else if (prev == freq)
> + div = freq / desired_clk + 1;
> +
> + /*
> + * Only time clock framework doesn't round up is if
> + * we're past the max clock rate. We're done searching
> + * if that's the case.
> + */
> + if (freq < test_freq)
> break;
> + }
> +
> + *exact_match = false;
> + return ser_clk;
> +}
> +
> +static unsigned long get_clk_div_rate(struct clk *clk, unsigned int baud,
> + unsigned int sampling_rate, unsigned int *clk_div)
> +{
> + unsigned long ser_clk;
> + unsigned long desired_clk;
> + unsigned long desired_tol;
> + bool exact_match;
>
> - prev = freq;
> + desired_clk = baud * sampling_rate;
> + if (!desired_clk) {
> + pr_err("%s: Invalid frequency\n", __func__);
> + return 0;
> }
>
> - if (!ser_clk) {
> - pr_err("%s: Can't find matching DFS entry for baud %d\n",
> - __func__, baud);
> + /* try to find exact clock rate or within 2% tolerance */
> + ser_clk = 0;
> + exact_match = true;
> + desired_tol = 2;
Don't need a "desired_tol" variable. Just pass 2 into the function.
> + ser_clk = find_clk_rate_in_tol(clk, desired_clk, clk_div, desired_tol, &exact_match);
> + if (ser_clk) {
> + if (!exact_match)
> + pr_warn("Cannot find exact match clk_rate, using one within 2 percent tolerance\n");
IMO get rid of this printout. Just return what you found if it's not
0. It's perfectly fine. ...that means you can fully get rid of the
"exact_match" variable.
> return ser_clk;
> }
>
> - *clk_div = ser_clk / desired_clk;
> - if (!(*clk_div))
> - *clk_div = 1;
> + /* try within 5% tolerance now, no need to look for exact match */
> + exact_match = false;
> + desired_tol = 5;
> +
> + ser_clk = find_clk_rate_in_tol(clk, desired_clk, clk_div, desired_tol, &exact_match);
> + if (ser_clk)
> + pr_warn("Cannot find exact match clk_rate, using one within 5 percent tolerance\n");
> + else
> + pr_err("Cannot find suitable clk_rate, giving up\n");
Just keep the error message but not the warning. ...and ideally use
"dev_err" and print out the clock you were trying to achieve.
