Message ID | 20190205155251.18733-1-martin.kepplinger@ginzinger.com |
---|---|
State | Accepted |
Delegated to: | Boris Brezillon |
Headers | show |
Series | [v2] mtd: rawnand: gpmi: fix MX28 bus master lockup problem | expand |
> -----Original Message----- > From: Martin Kepplinger <martin.kepplinger@ginzinger.com> > Sent: Tuesday, February 5, 2019 9:53 AM > To: Han Xu <han.xu@nxp.com>; bbrezillon@kernel.org; > miquel.raynal@bootlin.com; richard@nod.at; dwmw2@infradead.org; > computersforpeace@gmail.com; marek.vasut@gmail.com; linux- > mtd@lists.infradead.org > Cc: linux-kernel@vger.kernel.org; stable@vger.kernel.org; Manfred Schlaegl > <manfred.schlaegl@ginzinger.com>; Fabio Estevam <festevam@gmail.com> > Subject: [PATCH v2] mtd: rawnand: gpmi: fix MX28 bus master lockup > problem > > Disable BCH soft reset according to MX23 erratum #2847 ("BCH soft > reset may cause bus master lock up") for MX28 too. It has the same > problem. > > Observed problem: once per 100,000+ MX28 reboots NAND read failed on > DMA timeout errors: > [ 1.770823] UBI: attaching mtd3 to ubi0 > [ 2.768088] gpmi_nand: DMA timeout, last DMA :1 > [ 3.958087] gpmi_nand: BCH timeout, last DMA :1 > [ 4.156033] gpmi_nand: Error in ECC-based read: -110 > [ 4.161136] UBI warning: ubi_io_read: error -110 while reading 64 > bytes from PEB 0:0, read only 0 bytes, retry > [ 4.171283] step 1 error > [ 4.173846] gpmi_nand: Chip: 0, Error -1 > > Without BCH soft reset we successfully executed 1,000,000 MX28 reboots. > > I have a quote from NXP regarding this problem, from July 18th 2016: > > "As the i.MX23 and i.MX28 are of the same generation, they share many > characteristics. Unfortunately, also the erratas may be shared. > In case of the documented erratas and the workarounds, you can also > apply the workaround solution of one device on the other one. This have > been reported, but I’m afraid that there are not an estimated date for > updating the Errata documents. > Please accept our apologies for any inconveniences this may cause." > > Fixes: 6f2a6a52560a ("mtd: nand: gpmi: reset BCH earlier, too, to avoid > NAND startup problems") > Cc: stable@vger.kernel.org > Signed-off-by: Manfred Schlaegl <manfred.schlaegl@ginzinger.com> > Signed-off-by: Martin Kepplinger <martin.kepplinger@ginzinger.com> > Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com> > Reviewed-by: Fabio Estevam <festevam@gmail.com> Acked-by: Han Xu <han.xu@nxp.com> > --- > > > revision history > ---------------- > v2: add Fixes tag, Cc stable and add recent Reviewed-by tags > > > drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c | 13 ++++++------- > 1 file changed, 6 insertions(+), 7 deletions(-) > > diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c > b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c > index bd4cfac6b5aa..a4768df5083f 100644 > --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c > +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c > @@ -155,9 +155,10 @@ int gpmi_init(struct gpmi_nand_data *this) > > /* > * Reset BCH here, too. We got failures otherwise :( > - * See later BCH reset for explanation of MX23 handling > + * See later BCH reset for explanation of MX23 and MX28 handling > */ > - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); > + ret = gpmi_reset_block(r->bch_regs, > + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); > if (ret) > goto err_out; > > @@ -263,12 +264,10 @@ int bch_set_geometry(struct gpmi_nand_data > *this) > /* > * Due to erratum #2847 of the MX23, the BCH cannot be soft reset on > this > * chip, otherwise it will lock up. So we skip resetting BCH on the > MX23. > - * On the other hand, the MX28 needs the reset, because one case > has been > - * seen where the BCH produced ECC errors constantly after 10000 > - * consecutive reboots. The latter case has not been seen on the > MX23 > - * yet, still we don't know if it could happen there as well. > + * and MX28. > */ > - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); > + ret = gpmi_reset_block(r->bch_regs, > + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); > if (ret) > goto err_out; > > -- > 2.20.1
From: Your Name <patch-notifications@your-domain.com> On Tue, 2019-02-05 at 15:52:51 UTC, Martin Kepplinger wrote: > Disable BCH soft reset according to MX23 erratum #2847 ("BCH soft > reset may cause bus master lock up") for MX28 too. It has the same > problem. > > Observed problem: once per 100,000+ MX28 reboots NAND read failed on > DMA timeout errors: > [ 1.770823] UBI: attaching mtd3 to ubi0 > [ 2.768088] gpmi_nand: DMA timeout, last DMA :1 > [ 3.958087] gpmi_nand: BCH timeout, last DMA :1 > [ 4.156033] gpmi_nand: Error in ECC-based read: -110 > [ 4.161136] UBI warning: ubi_io_read: error -110 while reading 64 > bytes from PEB 0:0, read only 0 bytes, retry > [ 4.171283] step 1 error > [ 4.173846] gpmi_nand: Chip: 0, Error -1 > > Without BCH soft reset we successfully executed 1,000,000 MX28 reboots. > > I have a quote from NXP regarding this problem, from July 18th 2016: > > "As the i.MX23 and i.MX28 are of the same generation, they share many > characteristics. Unfortunately, also the erratas may be shared. > In case of the documented erratas and the workarounds, you can also > apply the workaround solution of one device on the other one. This have > been reported, but I’m afraid that there are not an estimated date for > updating the Errata documents. > Please accept our apologies for any inconveniences this may cause." > > Fixes: 6f2a6a52560a ("mtd: nand: gpmi: reset BCH earlier, too, to avoid > NAND startup problems") > Cc: stable@vger.kernel.org > Signed-off-by: Manfred Schlaegl <manfred.schlaegl@ginzinger.com> > Signed-off-by: Martin Kepplinger <martin.kepplinger@ginzinger.com> > Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com> > Reviewed-by: Fabio Estevam <festevam@gmail.com> > Acked-by: Han Xu <han.xu@nxp.com> Applied to http://git.infradead.org/linux-mtd.git mtd/fixes, thanks. y'all come back now!
Hi Martin, On Tue, 5 Feb 2019 16:52:51 +0100 Martin Kepplinger <martin.kepplinger@ginzinger.com> wrote: > Disable BCH soft reset according to MX23 erratum #2847 ("BCH soft > reset may cause bus master lock up") for MX28 too. It has the same > problem. > > Observed problem: once per 100,000+ MX28 reboots NAND read failed on > DMA timeout errors: > [ 1.770823] UBI: attaching mtd3 to ubi0 > [ 2.768088] gpmi_nand: DMA timeout, last DMA :1 > [ 3.958087] gpmi_nand: BCH timeout, last DMA :1 > [ 4.156033] gpmi_nand: Error in ECC-based read: -110 > [ 4.161136] UBI warning: ubi_io_read: error -110 while reading 64 > bytes from PEB 0:0, read only 0 bytes, retry > [ 4.171283] step 1 error > [ 4.173846] gpmi_nand: Chip: 0, Error -1 > > Without BCH soft reset we successfully executed 1,000,000 MX28 reboots. > > I have a quote from NXP regarding this problem, from July 18th 2016: > > "As the i.MX23 and i.MX28 are of the same generation, they share many > characteristics. Unfortunately, also the erratas may be shared. > In case of the documented erratas and the workarounds, you can also > apply the workaround solution of one device on the other one. This have > been reported, but I’m afraid that there are not an estimated date for > updating the Errata documents. > Please accept our apologies for any inconveniences this may cause." > > Fixes: 6f2a6a52560a ("mtd: nand: gpmi: reset BCH earlier, too, to avoid > NAND startup problems") Please make sure this Fixes line is not wrapped next time. Thanks, Boris
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c index bd4cfac6b5aa..a4768df5083f 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c @@ -155,9 +155,10 @@ int gpmi_init(struct gpmi_nand_data *this) /* * Reset BCH here, too. We got failures otherwise :( - * See later BCH reset for explanation of MX23 handling + * See later BCH reset for explanation of MX23 and MX28 handling */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out; @@ -263,12 +264,10 @@ int bch_set_geometry(struct gpmi_nand_data *this) /* * Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this * chip, otherwise it will lock up. So we skip resetting BCH on the MX23. - * On the other hand, the MX28 needs the reset, because one case has been - * seen where the BCH produced ECC errors constantly after 10000 - * consecutive reboots. The latter case has not been seen on the MX23 - * yet, still we don't know if it could happen there as well. + * and MX28. */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out;