* [PATCH 2/2] gpmi-nand: Add ERR007117 protection for nfc_apply_timings
@ 2021-11-02 20:20 ` Christian Eggers
0 siblings, 0 replies; 12+ messages in thread
From: Christian Eggers @ 2021-11-02 20:20 UTC (permalink / raw)
To: Michael Trimarchi, Miquel Raynal, Stefan Riedmueller, Han Xu,
Greg Ungerer
Cc: Sascha Hauer, Christian Hemp, Boris Brezillon,
Richard Weinberger, Vignesh Raghavendra, linux-mtd, linux-kernel,
Christian Eggers, Stefan Riedmueller, stable
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@phytec.de>
Signed-off-by: Stefan Riedmueller <s.riedmueller@phytec.de>
Signed-off-by: Christian Eggers <ceggers@arri.de>
Cc: stable@vger.kernel.org
---
Changelog:
-----------
RFC --> v1
- added comment about clock divider behavior on the different i.MX series
- perform clock gating also on i.MX6SX
- only gate gpmi_io clock. Other GPMI/BCH clocks are not affected when
ENFC_CLK_ROOT divides are changes
- add error checking for clk_set_rate()
- Cc: stable@vger.kernel.org
drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 28 +++++++++++++++++++---
1 file changed, 25 insertions(+), 3 deletions(-)
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index a1f7000f033e..6e9f7d80ef8b 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -713,14 +713,32 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
(use_half_period ? BM_GPMI_CTRL1_HALF_PERIOD : 0);
}
-static void gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
+static int gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
{
struct gpmi_nfc_hardware_timing *hw = &this->hw;
struct resources *r = &this->resources;
void __iomem *gpmi_regs = r->gpmi_regs;
unsigned int dll_wait_time_us;
+ int ret;
+
+ /* Clock dividers do NOT guarantee a clean clock signal on its output
+ * during the change of the divide factor on i.MX6Q/UL/SX. On i.MX7/8,
+ * all clock dividers provide these guarantee.
+ */
+ if (GPMI_IS_MX6Q(this) || GPMI_IS_MX6SX(this))
+ clk_disable_unprepare(r->clock[0]);
+
+ ret = clk_set_rate(r->clock[0], hw->clk_rate);
+ if (ret) {
+ dev_err(this->dev, "cannot set clock rate to %lu Hz: %d\n", hw->clk_rate, ret);
+ return ret;
+ }
- clk_set_rate(r->clock[0], hw->clk_rate);
+ if (GPMI_IS_MX6Q(this) || GPMI_IS_MX6SX(this)) {
+ ret = clk_prepare_enable(r->clock[0]);
+ if (ret)
+ return ret;
+ }
writel(hw->timing0, gpmi_regs + HW_GPMI_TIMING0);
writel(hw->timing1, gpmi_regs + HW_GPMI_TIMING1);
@@ -739,6 +757,8 @@ static void gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
/* Wait for the DLL to settle. */
udelay(dll_wait_time_us);
+
+ return 0;
}
static int gpmi_setup_interface(struct nand_chip *chip, int chipnr,
@@ -2271,7 +2291,9 @@ static int gpmi_nfc_exec_op(struct nand_chip *chip,
*/
if (this->hw.must_apply_timings) {
this->hw.must_apply_timings = false;
- gpmi_nfc_apply_timings(this);
+ ret = gpmi_nfc_apply_timings(this);
+ if (ret)
+ return ret;
}
dev_dbg(this->dev, "%s: %d instructions\n", __func__, op->ninstrs);
--
Christian Eggers
Embedded software developer
Arnold & Richter Cine Technik GmbH & Co. Betriebs KG
Sitz: Muenchen - Registergericht: Amtsgericht Muenchen - Handelsregisternummer: HRA 57918
Persoenlich haftender Gesellschafter: Arnold & Richter Cine Technik GmbH
Sitz: Muenchen - Registergericht: Amtsgericht Muenchen - Handelsregisternummer: HRB 54477
Geschaeftsfuehrer: Dr. Michael Neuhaeuser; Stephan Schenk; Walter Trauninger; Markus Zeiler
^ permalink raw reply related [flat|nested] 12+ messages in thread
* Re: [PATCH 2/2] gpmi-nand: Add ERR007117 protection for nfc_apply_timings
2021-11-02 20:20 ` Christian Eggers
@ 2021-11-03 16:14 ` Han Xu
-1 siblings, 0 replies; 12+ messages in thread
From: Han Xu @ 2021-11-03 16:14 UTC (permalink / raw)
To: Christian Eggers
Cc: Michael Trimarchi, Miquel Raynal, Stefan Riedmueller,
Greg Ungerer, Sascha Hauer, Christian Hemp, Boris Brezillon,
Richard Weinberger, Vignesh Raghavendra, linux-mtd, linux-kernel,
stable
On 21/11/02 09:20PM, 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@phytec.de>
> Signed-off-by: Stefan Riedmueller <s.riedmueller@phytec.de>
> Signed-off-by: Christian Eggers <ceggers@arri.de>
> Cc: stable@vger.kernel.org
> ---
> Changelog:
> -----------
> RFC --> v1
> - added comment about clock divider behavior on the different i.MX series
> - perform clock gating also on i.MX6SX
> - only gate gpmi_io clock. Other GPMI/BCH clocks are not affected when
> ENFC_CLK_ROOT divides are changes
> - add error checking for clk_set_rate()
> - Cc: stable@vger.kernel.org
>
> drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 28 +++++++++++++++++++---
> 1 file changed, 25 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
> index a1f7000f033e..6e9f7d80ef8b 100644
> --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
> +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
> @@ -713,14 +713,32 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
> (use_half_period ? BM_GPMI_CTRL1_HALF_PERIOD : 0);
> }
>
> -static void gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
> +static int gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
> {
> struct gpmi_nfc_hardware_timing *hw = &this->hw;
> struct resources *r = &this->resources;
> void __iomem *gpmi_regs = r->gpmi_regs;
> unsigned int dll_wait_time_us;
> + int ret;
> +
> + /* Clock dividers do NOT guarantee a clean clock signal on its output
> + * during the change of the divide factor on i.MX6Q/UL/SX. On i.MX7/8,
> + * all clock dividers provide these guarantee.
> + */
> + if (GPMI_IS_MX6Q(this) || GPMI_IS_MX6SX(this))
> + clk_disable_unprepare(r->clock[0]);
> +
> + ret = clk_set_rate(r->clock[0], hw->clk_rate);
> + if (ret) {
> + dev_err(this->dev, "cannot set clock rate to %lu Hz: %d\n", hw->clk_rate, ret);
> + return ret;
> + }
>
> - clk_set_rate(r->clock[0], hw->clk_rate);
> + if (GPMI_IS_MX6Q(this) || GPMI_IS_MX6SX(this)) {
> + ret = clk_prepare_enable(r->clock[0]);
> + if (ret)
> + return ret;
> + }
>
> writel(hw->timing0, gpmi_regs + HW_GPMI_TIMING0);
> writel(hw->timing1, gpmi_regs + HW_GPMI_TIMING1);
> @@ -739,6 +757,8 @@ static void gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
>
> /* Wait for the DLL to settle. */
> udelay(dll_wait_time_us);
> +
> + return 0;
> }
>
> static int gpmi_setup_interface(struct nand_chip *chip, int chipnr,
> @@ -2271,7 +2291,9 @@ static int gpmi_nfc_exec_op(struct nand_chip *chip,
> */
> if (this->hw.must_apply_timings) {
> this->hw.must_apply_timings = false;
> - gpmi_nfc_apply_timings(this);
> + ret = gpmi_nfc_apply_timings(this);
> + if (ret)
> + return ret;
> }
>
> dev_dbg(this->dev, "%s: %d instructions\n", __func__, op->ninstrs);
Acked-by: Han Xu <han.xu@nxp.com>
> --
> Christian Eggers
> Embedded software developer
>
> Arnold & Richter Cine Technik GmbH & Co. Betriebs KG
> Sitz: Muenchen - Registergericht: Amtsgericht Muenchen - Handelsregisternummer: HRA 57918
> Persoenlich haftender Gesellschafter: Arnold & Richter Cine Technik GmbH
> Sitz: Muenchen - Registergericht: Amtsgericht Muenchen - Handelsregisternummer: HRB 54477
> Geschaeftsfuehrer: Dr. Michael Neuhaeuser; Stephan Schenk; Walter Trauninger; Markus Zeiler
>
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [PATCH 2/2] gpmi-nand: Add ERR007117 protection for nfc_apply_timings
@ 2021-11-03 16:14 ` Han Xu
0 siblings, 0 replies; 12+ messages in thread
From: Han Xu @ 2021-11-03 16:14 UTC (permalink / raw)
To: Christian Eggers
Cc: Michael Trimarchi, Miquel Raynal, Stefan Riedmueller,
Greg Ungerer, Sascha Hauer, Christian Hemp, Boris Brezillon,
Richard Weinberger, Vignesh Raghavendra, linux-mtd, linux-kernel,
stable
On 21/11/02 09:20PM, 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@phytec.de>
> Signed-off-by: Stefan Riedmueller <s.riedmueller@phytec.de>
> Signed-off-by: Christian Eggers <ceggers@arri.de>
> Cc: stable@vger.kernel.org
> ---
> Changelog:
> -----------
> RFC --> v1
> - added comment about clock divider behavior on the different i.MX series
> - perform clock gating also on i.MX6SX
> - only gate gpmi_io clock. Other GPMI/BCH clocks are not affected when
> ENFC_CLK_ROOT divides are changes
> - add error checking for clk_set_rate()
> - Cc: stable@vger.kernel.org
>
> drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 28 +++++++++++++++++++---
> 1 file changed, 25 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
> index a1f7000f033e..6e9f7d80ef8b 100644
> --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
> +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
> @@ -713,14 +713,32 @@ static void gpmi_nfc_compute_timings(struct gpmi_nand_data *this,
> (use_half_period ? BM_GPMI_CTRL1_HALF_PERIOD : 0);
> }
>
> -static void gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
> +static int gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
> {
> struct gpmi_nfc_hardware_timing *hw = &this->hw;
> struct resources *r = &this->resources;
> void __iomem *gpmi_regs = r->gpmi_regs;
> unsigned int dll_wait_time_us;
> + int ret;
> +
> + /* Clock dividers do NOT guarantee a clean clock signal on its output
> + * during the change of the divide factor on i.MX6Q/UL/SX. On i.MX7/8,
> + * all clock dividers provide these guarantee.
> + */
> + if (GPMI_IS_MX6Q(this) || GPMI_IS_MX6SX(this))
> + clk_disable_unprepare(r->clock[0]);
> +
> + ret = clk_set_rate(r->clock[0], hw->clk_rate);
> + if (ret) {
> + dev_err(this->dev, "cannot set clock rate to %lu Hz: %d\n", hw->clk_rate, ret);
> + return ret;
> + }
>
> - clk_set_rate(r->clock[0], hw->clk_rate);
> + if (GPMI_IS_MX6Q(this) || GPMI_IS_MX6SX(this)) {
> + ret = clk_prepare_enable(r->clock[0]);
> + if (ret)
> + return ret;
> + }
>
> writel(hw->timing0, gpmi_regs + HW_GPMI_TIMING0);
> writel(hw->timing1, gpmi_regs + HW_GPMI_TIMING1);
> @@ -739,6 +757,8 @@ static void gpmi_nfc_apply_timings(struct gpmi_nand_data *this)
>
> /* Wait for the DLL to settle. */
> udelay(dll_wait_time_us);
> +
> + return 0;
> }
>
> static int gpmi_setup_interface(struct nand_chip *chip, int chipnr,
> @@ -2271,7 +2291,9 @@ static int gpmi_nfc_exec_op(struct nand_chip *chip,
> */
> if (this->hw.must_apply_timings) {
> this->hw.must_apply_timings = false;
> - gpmi_nfc_apply_timings(this);
> + ret = gpmi_nfc_apply_timings(this);
> + if (ret)
> + return ret;
> }
>
> dev_dbg(this->dev, "%s: %d instructions\n", __func__, op->ninstrs);
Acked-by: Han Xu <han.xu@nxp.com>
> --
> Christian Eggers
> Embedded software developer
>
> Arnold & Richter Cine Technik GmbH & Co. Betriebs KG
> Sitz: Muenchen - Registergericht: Amtsgericht Muenchen - Handelsregisternummer: HRA 57918
> Persoenlich haftender Gesellschafter: Arnold & Richter Cine Technik GmbH
> Sitz: Muenchen - Registergericht: Amtsgericht Muenchen - Handelsregisternummer: HRB 54477
> Geschaeftsfuehrer: Dr. Michael Neuhaeuser; Stephan Schenk; Walter Trauninger; Markus Zeiler
>
______________________________________________________
Linux MTD discussion mailing list
http://lists.infradead.org/mailman/listinfo/linux-mtd/
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [PATCH 2/2] gpmi-nand: Add ERR007117 protection for nfc_apply_timings
2021-11-02 20:20 ` Christian Eggers
@ 2021-11-19 18:43 ` Miquel Raynal
-1 siblings, 0 replies; 12+ messages in thread
From: Miquel Raynal @ 2021-11-19 18:43 UTC (permalink / raw)
To: Christian Eggers, Michael Trimarchi, Miquel Raynal,
Stefan Riedmueller, Han Xu, Greg Ungerer
Cc: Sascha Hauer, Christian Hemp, Boris Brezillon,
Richard Weinberger, Vignesh Raghavendra, linux-mtd, linux-kernel,
Stefan Riedmueller, stable
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@phytec.de>
> Signed-off-by: Stefan Riedmueller <s.riedmueller@phytec.de>
> Signed-off-by: Christian Eggers <ceggers@arri.de>
> Cc: stable@vger.kernel.org
> Acked-by: Han Xu <han.xu@nxp.com>
Applied to https://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git nand/next, thanks.
Miquel
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [PATCH 2/2] gpmi-nand: Add ERR007117 protection for nfc_apply_timings
@ 2021-11-19 18:43 ` Miquel Raynal
0 siblings, 0 replies; 12+ messages in thread
From: Miquel Raynal @ 2021-11-19 18:43 UTC (permalink / raw)
To: Christian Eggers, Michael Trimarchi, Miquel Raynal,
Stefan Riedmueller, Han Xu, Greg Ungerer
Cc: Sascha Hauer, Christian Hemp, Boris Brezillon,
Richard Weinberger, Vignesh Raghavendra, linux-mtd, linux-kernel,
Stefan Riedmueller, stable
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@phytec.de>
> Signed-off-by: Stefan Riedmueller <s.riedmueller@phytec.de>
> Signed-off-by: Christian Eggers <ceggers@arri.de>
> Cc: stable@vger.kernel.org
> Acked-by: Han Xu <han.xu@nxp.com>
Applied to https://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux.git nand/next, thanks.
Miquel
______________________________________________________
Linux MTD discussion mailing list
http://lists.infradead.org/mailman/listinfo/linux-mtd/
^ permalink raw reply [flat|nested] 12+ messages in thread