On Tue, 2021-11-02 at 20:20:22 UTC, Christian Eggers wrote: > gpmi_io clock needs to be gated off when changing the parent/dividers of > enfc_clk_root (i.MX6Q/i.MX6UL) respectively qspi2_clk_root (i.MX6SX). > Otherwise this rate change can lead to an unresponsive GPMI core which > results in DMA timeouts and failed driver probe: > > [ 4.072318] gpmi-nand 112000.gpmi-nand: DMA timeout, last DMA > ... > [ 4.370355] gpmi-nand 112000.gpmi-nand: Chip: 0, Error -110 > ... > [ 4.375988] gpmi-nand 112000.gpmi-nand: Chip: 0, Error -22 > [ 4.381524] gpmi-nand 112000.gpmi-nand: Error in ECC-based read: -22 > [ 4.387988] gpmi-nand 112000.gpmi-nand: Chip: 0, Error -22 > [ 4.393535] gpmi-nand 112000.gpmi-nand: Chip: 0, Error -22 > ... > > Other than stated in i.MX 6 erratum ERR007117, it should be sufficient > to gate only gpmi_io because all other bch/nand clocks are derived from > different clock roots. > > The i.MX6 reference manuals state that changing clock muxers can cause > glitches but are silent about changing dividers. But tests showed that > these glitches can definitely happen on i.MX6ULL. For i.MX7D/8MM in turn, > the manual guarantees that no glitches can happen when changing > dividers. > > Co-developed-by: Stefan Riedmueller <s.riedmueller@xxxxxxxxx> > Signed-off-by: Stefan Riedmueller <s.riedmueller@xxxxxxxxx> > Signed-off-by: Christian Eggers <ceggers@xxxxxxx> > Cc: stable@xxxxxxxxxxxxxxx > Acked-by: Han Xu <han.xu@xxxxxxx> Applied to https://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git nand/next, thanks. Miquel
