Hi John,
On Thu, Jun 19, 2025 at 5:34 AM John Madieu
<john.madieu.xa@xxxxxxxxxxxxxx> wrote:
>
> Hi Geert,
>
> > -----Original Message-----
> > From: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
> > Sent: Wednesday, June 18, 2025 1:02 PM
> > To: John Madieu <john.madieu.xa@xxxxxxxxxxxxxx>
> > Subject: Re: [PATCH v2 1/3] clk: renesas: r9a09g047: Add clock and reset
> > signals for the GBETH IPs
> >
> > Hi John,
> >
> > On Wed, 18 Jun 2025 at 12:04, John Madieu <john.madieu.xa@xxxxxxxxxxxxxx>
> > wrote:
> > > > From: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx> On Wed, 11 Jun 2025
> > > > at 11:02, John Madieu <john.madieu.xa@xxxxxxxxxxxxxx>
> > > > wrote:
> > > > > Add clock and reset entries for the Gigabit Ethernet Interfaces
> > > > > (GBETH
> > > > > 0-1) IPs found on the RZ/G3E SoC. This includes various PLLs,
> > > > > dividers, and mux clocks needed by these two GBETH IPs.
> > > > >
> > > > > Reviewed-by: Biju Das <biju.das.jz@xxxxxxxxxxxxxx>
> > > > > Tested-by: Biju Das <biju.das.jz@xxxxxxxxxxxxxx>
> > > > > Signed-off-by: John Madieu <john.madieu.xa@xxxxxxxxxxxxxx>
> > > >
> > > > Thanks for your patch!
> > > >
> > > > > --- a/drivers/clk/renesas/r9a09g047-cpg.c
> > > > > +++ b/drivers/clk/renesas/r9a09g047-cpg.c
> >
> > > > > @@ -214,6 +252,30 @@ static const struct rzv2h_mod_clk
> > > > r9a09g047_mod_clks[] __initconst = {
> > > > > BUS_MSTOP(8,
> > BIT(4))),
> > > > > DEF_MOD("sdhi_2_aclk",
> > CLK_PLLDTY_ACPU_DIV4,
> > > > 10, 14, 5, 14,
> > > > > BUS_MSTOP(8,
> > > > > BIT(4))),
> > > > > + DEF_MOD("gbeth_0_clk_tx_i",
> > CLK_SMUX2_GBE0_TXCLK,
> > > > 11, 8, 5, 24,
> > > > > + BUS_MSTOP(8,
> > BIT(5))),
> > > > > + DEF_MOD("gbeth_0_clk_rx_i",
> > CLK_SMUX2_GBE0_RXCLK,
> > > > 11, 9, 5, 25,
> > > > > + BUS_MSTOP(8,
> > BIT(5))),
> > > > > + DEF_MOD("gbeth_0_clk_tx_180_i",
> > CLK_SMUX2_GBE0_TXCLK,
> > > > 11, 10, 5, 26,
> > > > > + BUS_MSTOP(8,
> > BIT(5))),
> > > > > + DEF_MOD("gbeth_0_clk_rx_180_i",
> > CLK_SMUX2_GBE0_RXCLK,
> > > > 11, 11, 5, 27,
> > > > > + BUS_MSTOP(8,
> > BIT(5))),
> > > > > + DEF_MOD("gbeth_0_aclk_csr_i", CLK_PLLDTY_DIV8, 11,
> > 12,
> > > > 5, 28,
> > > > > + BUS_MSTOP(8,
> > BIT(5))),
> > > > > + DEF_MOD("gbeth_0_aclk_i", CLK_PLLDTY_DIV8, 11,
> > 13,
> > > > 5, 29,
> > > > > + BUS_MSTOP(8,
> > BIT(5))),
> > > > > + DEF_MOD("gbeth_1_clk_tx_i",
> > CLK_SMUX2_GBE1_TXCLK,
> > > > 11, 14, 5, 30,
> > > > > + BUS_MSTOP(8,
> > BIT(6))),
> > > > > + DEF_MOD("gbeth_1_clk_rx_i",
> > CLK_SMUX2_GBE1_RXCLK,
> > > > 11, 15, 5, 31,
> > > > > + BUS_MSTOP(8,
> > BIT(6))),
> > > > > + DEF_MOD("gbeth_1_clk_tx_180_i",
> > CLK_SMUX2_GBE1_TXCLK,
> > > > 12, 0, 6, 0,
> > > >
> > > > scripts/checkpatch.pl says:
> > > >
> > > > WARNING: please, no space before tabs
> > > >
> > >
> > > Noted.
> > >
> > > > > + BUS_MSTOP(8,
> > BIT(6))),
> > > > > + DEF_MOD("gbeth_1_clk_rx_180_i",
> > CLK_SMUX2_GBE1_RXCLK,
> > > > 12, 1, 6, 1,
> > > > > + BUS_MSTOP(8,
> > BIT(6))),
> > > > > + DEF_MOD("gbeth_1_aclk_csr_i", CLK_PLLDTY_DIV8, 12,
> > 2,
> > > > 6, 2,
> > > > > + BUS_MSTOP(8,
> > BIT(6))),
> > > > > + DEF_MOD("gbeth_1_aclk_i", CLK_PLLDTY_DIV8, 12,
> > 3,
> > > > 6, 3,
> > > > > + BUS_MSTOP(8,
> > > > > + BIT(6))),
> > > >
> > > > Shouldn't all of these use DEF_MOD_MUX_EXTERNAL() instead of
> > > > DEF_MOD(), like on RZ/V2H and RZ/V2N?
> > > >
> > >
> > > Do we really need to use DEF_MOD_MUX_EXTERNAL? Unlike for the RZ/V2H,
> > > On G3E, unbind/bind works with DEF_MOD. I can however switch to
> > > DEF_MOD_MUX_EXTERNAL for consistency if required.
> > >
> > > Please let me know.
> >
> > Does that mean the monitor bits on RZ/G3E do reflect the correct state of
> > external clocks? If yes, then DEF_MOD() is fine.
> >
> > Gr{oetje,eeting}s,
> >
> > Geert
> >
>
> Checked DEF_MOD() and had expected result. I'll then it and send v3.
>
Can you please share the devmem logs for external clocks please. I ask
because the HW team mentioned the below information will be added in
the RZ/V2H(P) HW manual. We need to check if below is not needed on
RZ/G3E.
"The clock gating cells require source clocks to operate correctly. If
the source clocks are stopped, these registers cannot be used."
Cheers,
Prabhakar
