Messages in this thread | | | From | Miquel Raynal <> | Subject | Re: [PATCH 3/4] mtd: rawnand: gpmi: validate controller clock rate | Date | Sun, 23 Jan 2022 16:39:41 +0100 |
| |
On Tue, 2022-01-18 at 09:54:33 UTC, Dario Binacchi wrote: > What to do when the real rate of the gpmi clock is not equal to the > required one? The solutions proposed in [1] did not lead to a conclusion > on how to validate the clock rate, so, inspired by the document [2], I > consider the rate correct only if not lower or equal to the rate of the > previous edo mode. In fact, in chapter 4.16.2 (NV-DDR) of the document [2], > it is written that "If the host selects timing mode n, then its clock > period shall be faster than the clock period of timing mode n-1 and > slower than or equal to the clock period of timing mode n.". I thought > that it could therefore also be used in this case, without therefore > having to define the valid rate ranges empirically. > > For example, suppose that gpmi_nfc_compute_timings() is called to set > edo mode 5 (100MHz) but the rate returned by clk_round_rate() is 80MHz > (edo mode 4). In this case gpmi_nfc_compute_timings() will return error, > and will be called again to set edo mode 4, which this time will be > successful. > > [1] https://lore.kernel.org/r/20210702065350.209646-5-ebiggers@kernel.org > [2] http://www.onfi.org/-/media/client/onfi/specs/onfi_3_0_gold.pdf?la=en > > Co-developed-by: Michael Trimarchi <michael@amarulasolutions.com> > Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com> > Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com> > Tested-by: Sascha Hauer <s.hauer@pengutronix.de> > Reviewed-by: Sascha Hauer <s.hauer@pengutronix.de>
Applied to https://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git nand/next, thanks.
Miquel
| |