linux-kernel - Re: [PATCH] ASoC: fsl_asrc: Add an option to select internal ratio mode

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAA+D8APOd2MxO08nnK9UE03bMj25fyMfMnF-neBzdyoykbjAKA@mail.gmail.com>
Date:   Tue, 30 Jun 2020 13:31:15 +0800
From:   Shengjiu Wang <shengjiu.wang@...il.com>
To:     Nicolin Chen <nicoleotsuka@...il.com>
Cc:     Shengjiu Wang <shengjiu.wang@....com>,
        Linux-ALSA <alsa-devel@...a-project.org>,
        Timur Tabi <timur@...nel.org>, Xiubo Li <Xiubo.Lee@...il.com>,
        linuxppc-dev@...ts.ozlabs.org, Takashi Iwai <tiwai@...e.com>,
        Liam Girdwood <lgirdwood@...il.com>,
        Mark Brown <broonie@...nel.org>,
        Fabio Estevam <festevam@...il.com>,
        linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] ASoC: fsl_asrc: Add an option to select internal ratio mode

On Tue, Jun 30, 2020 at 4:09 AM Nicolin Chen <nicoleotsuka@...il.com> wrote:
>
> On Mon, Jun 29, 2020 at 09:58:35PM +0800, Shengjiu Wang wrote:
> > The ASRC not only supports ideal ratio mode, but also supports
> > internal ratio mode.
> >
> > For internal rato mode, the rate of clock source should be divided
> > with no remainder by sample rate, otherwise there is sound
> > distortion.
> >
> > Add function fsl_asrc_select_clk() to find proper clock source for
> > internal ratio mode, if the clock source is available then internal
> > ratio mode will be selected.
> >
> > With change, the ideal ratio mode is not the only option for user.
> >
> > Signed-off-by: Shengjiu Wang <shengjiu.wang@....com>
> > ---
>
> > +static int fsl_asrc_select_clk(struct fsl_asrc_priv *asrc_priv,
> > +                            struct fsl_asrc_pair *pair,
> > +                            int in_rate,
> > +                            int out_rate)
> > +{
> > +     struct fsl_asrc_pair_priv *pair_priv = pair->private;
> > +     struct asrc_config *config = pair_priv->config;
> > +     int rate[2], select_clk[2]; /* Array size 2 means IN and OUT */
> > +     int clk_rate, clk_index;
> > +     int i = 0, j = 0;
> > +     bool clk_sel[2];
> > +
> > +     rate[0] = in_rate;
> > +     rate[1] = out_rate;
> > +
> > +     /* Select proper clock source for internal ratio mode */
> > +     for (j = 0; j < 2; j++) {
> > +             for (i = 0; i < ASRC_CLK_MAP_LEN; i++) {
> > +                     clk_index = asrc_priv->clk_map[j][i];
> > +                     clk_rate = clk_get_rate(asrc_priv->asrck_clk[clk_index]);
>
> +                       /* Only match a perfect clock source with no remainder */
>
> > +                     if (clk_rate != 0 && (clk_rate / rate[j]) <= 1024 &&
> > +                         (clk_rate % rate[j]) == 0)
> > +                             break;
> > +             }
> > +
> > +             if (i == ASRC_CLK_MAP_LEN) {
> > +                     select_clk[j] = OUTCLK_ASRCK1_CLK;
> > +                     clk_sel[j] = false;
> > +             } else {
> > +                     select_clk[j] = i;
> > +                     clk_sel[j] = true;
> > +             }
> > +     }
> > +
> > +     /* Switch to ideal ratio mode if there is no proper clock source */
> > +     if (!clk_sel[IN] || !clk_sel[OUT])
> > +             select_clk[IN] = INCLK_NONE;
>
> Could get rid of clk_set:
>
>         for (j) {
>                 for (i) {
>                         if (match)
>                                 break;
>                 }
>
>                 clk[j] = i;
>         }
>
>         if (clk[IN] == ASRC_CLK_MAP_LEN || clk[OUT] == ASRC_CLK_MAP_LEN)
>
> And it only overrides clk[IN] setting but leaving clk[OUT] to
> to the searching result. This means that clk[OUT] may be using
> a clock source other than OUTCLK_ASRCK1_CLK if sel[IN] happens
> to be false while sel[OUT] happens to be true. Not sure if it
> is intended...but I feel it would probably be safer to use the
> previous settings: INCLK_NONE + OUTCLK_ASRCK1_CLK?

ok, will update the patch.

best regards
wang shengjiu