* [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it
@ 2019-12-04 15:27 Linus Walleij
2019-12-04 17:20 ` Mark Brown
2019-12-10 9:51 ` Ulf Hansson
0 siblings, 2 replies; 5+ messages in thread
From: Linus Walleij @ 2019-12-04 15:27 UTC (permalink / raw)
To: linux-mmc, Ulf Hansson; +Cc: Linus Walleij, Phil Elwell, Mark Brown
The code in mmc_spi_initsequence() tries to send a burst with
high chipselect and for this reason hardcodes the device into
SPI_CS_HIGH.
This is not good because the SPI_CS_HIGH flag indicates
logical "asserted" CS not always the physical level. In
some cases the signal is inverted in the GPIO library and
in that case SPI_CS_HIGH is already set, and enforcing
SPI_CS_HIGH again will actually drive it low.
Instead of hard-coding this, toggle the polarity so if the
default is LOW it goes high to assert chipselect but if it
is already high then toggle it low instead.
Cc: Phil Elwell <phil@raspberrypi.org>
Reported-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
drivers/mmc/host/mmc_spi.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 74c6cfbf9172..1f02f54f09c0 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1134,17 +1134,22 @@ static void mmc_spi_initsequence(struct mmc_spi_host *host)
* SPI protocol. Another is that when chipselect is released while
* the card returns BUSY status, the clock must issue several cycles
* with chipselect high before the card will stop driving its output.
+ *
+ * SPI_CS_HIGH means "asserted" here. In some cases like when using
+ * GPIOs for chip select, SPI_CS_HIGH is set but this will be logically
+ * inverted by gpiolib, so if we want to ascertain to drive it high
+ * we should toggle the default with an XOR as we do here.
*/
- host->spi->mode |= SPI_CS_HIGH;
+ host->spi->mode ^= SPI_CS_HIGH;
if (spi_setup(host->spi) != 0) {
/* Just warn; most cards work without it. */
dev_warn(&host->spi->dev,
"can't change chip-select polarity\n");
- host->spi->mode &= ~SPI_CS_HIGH;
+ host->spi->mode ^= SPI_CS_HIGH;
} else {
mmc_spi_readbytes(host, 18);
- host->spi->mode &= ~SPI_CS_HIGH;
+ host->spi->mode ^= SPI_CS_HIGH;
if (spi_setup(host->spi) != 0) {
/* Wot, we can't get the same setup we had before? */
dev_err(&host->spi->dev,
--
2.23.0
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it
2019-12-04 15:27 [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it Linus Walleij
@ 2019-12-04 17:20 ` Mark Brown
2019-12-10 9:51 ` Ulf Hansson
1 sibling, 0 replies; 5+ messages in thread
From: Mark Brown @ 2019-12-04 17:20 UTC (permalink / raw)
To: Linus Walleij; +Cc: linux-mmc, Ulf Hansson, Phil Elwell
[-- Attachment #1: Type: text/plain, Size: 252 bytes --]
On Wed, Dec 04, 2019 at 04:27:49PM +0100, Linus Walleij wrote:
> The code in mmc_spi_initsequence() tries to send a burst with
> high chipselect and for this reason hardcodes the device into
> SPI_CS_HIGH.
Reviewed-by: Mark Brown <broonie@kernel.org>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it
2019-12-04 15:27 [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it Linus Walleij
2019-12-04 17:20 ` Mark Brown
@ 2019-12-10 9:51 ` Ulf Hansson
2019-12-10 23:10 ` Linus Walleij
1 sibling, 1 reply; 5+ messages in thread
From: Ulf Hansson @ 2019-12-10 9:51 UTC (permalink / raw)
To: Linus Walleij; +Cc: linux-mmc, Phil Elwell, Mark Brown
On Wed, 4 Dec 2019 at 16:29, Linus Walleij <linus.walleij@linaro.org> wrote:
>
> The code in mmc_spi_initsequence() tries to send a burst with
> high chipselect and for this reason hardcodes the device into
> SPI_CS_HIGH.
>
> This is not good because the SPI_CS_HIGH flag indicates
> logical "asserted" CS not always the physical level. In
> some cases the signal is inverted in the GPIO library and
> in that case SPI_CS_HIGH is already set, and enforcing
> SPI_CS_HIGH again will actually drive it low.
>
> Instead of hard-coding this, toggle the polarity so if the
> default is LOW it goes high to assert chipselect but if it
> is already high then toggle it low instead.
>
> Cc: Phil Elwell <phil@raspberrypi.org>
> Reported-by: Mark Brown <broonie@kernel.org>
> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Seems like we should add a stable tag, right?
In any case, I have applied this for next to let it cook for a while, thanks!
Kind regards
Uffe
> ---
> drivers/mmc/host/mmc_spi.c | 11 ++++++++---
> 1 file changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
> index 74c6cfbf9172..1f02f54f09c0 100644
> --- a/drivers/mmc/host/mmc_spi.c
> +++ b/drivers/mmc/host/mmc_spi.c
> @@ -1134,17 +1134,22 @@ static void mmc_spi_initsequence(struct mmc_spi_host *host)
> * SPI protocol. Another is that when chipselect is released while
> * the card returns BUSY status, the clock must issue several cycles
> * with chipselect high before the card will stop driving its output.
> + *
> + * SPI_CS_HIGH means "asserted" here. In some cases like when using
> + * GPIOs for chip select, SPI_CS_HIGH is set but this will be logically
> + * inverted by gpiolib, so if we want to ascertain to drive it high
> + * we should toggle the default with an XOR as we do here.
> */
> - host->spi->mode |= SPI_CS_HIGH;
> + host->spi->mode ^= SPI_CS_HIGH;
> if (spi_setup(host->spi) != 0) {
> /* Just warn; most cards work without it. */
> dev_warn(&host->spi->dev,
> "can't change chip-select polarity\n");
> - host->spi->mode &= ~SPI_CS_HIGH;
> + host->spi->mode ^= SPI_CS_HIGH;
> } else {
> mmc_spi_readbytes(host, 18);
>
> - host->spi->mode &= ~SPI_CS_HIGH;
> + host->spi->mode ^= SPI_CS_HIGH;
> if (spi_setup(host->spi) != 0) {
> /* Wot, we can't get the same setup we had before? */
> dev_err(&host->spi->dev,
> --
> 2.23.0
>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it
2019-12-10 9:51 ` Ulf Hansson
@ 2019-12-10 23:10 ` Linus Walleij
2019-12-16 12:09 ` Ulf Hansson
0 siblings, 1 reply; 5+ messages in thread
From: Linus Walleij @ 2019-12-10 23:10 UTC (permalink / raw)
To: Ulf Hansson; +Cc: linux-mmc, Phil Elwell, Mark Brown
On Tue, Dec 10, 2019 at 10:52 AM Ulf Hansson <ulf.hansson@linaro.org> wrote:
> On Wed, 4 Dec 2019 at 16:29, Linus Walleij <linus.walleij@linaro.org> wrote:
> >
> > The code in mmc_spi_initsequence() tries to send a burst with
> > high chipselect and for this reason hardcodes the device into
> > SPI_CS_HIGH.
> >
> > This is not good because the SPI_CS_HIGH flag indicates
> > logical "asserted" CS not always the physical level. In
> > some cases the signal is inverted in the GPIO library and
> > in that case SPI_CS_HIGH is already set, and enforcing
> > SPI_CS_HIGH again will actually drive it low.
> >
> > Instead of hard-coding this, toggle the polarity so if the
> > default is LOW it goes high to assert chipselect but if it
> > is already high then toggle it low instead.
> >
> > Cc: Phil Elwell <phil@raspberrypi.org>
> > Reported-by: Mark Brown <broonie@kernel.org>
> > Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
>
> Seems like we should add a stable tag, right?
Yeah I agree.
> In any case, I have applied this for next to let it cook for a while, thanks!
Good, thanks!
Yours,
Linus Walleij
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it
2019-12-10 23:10 ` Linus Walleij
@ 2019-12-16 12:09 ` Ulf Hansson
0 siblings, 0 replies; 5+ messages in thread
From: Ulf Hansson @ 2019-12-16 12:09 UTC (permalink / raw)
To: Linus Walleij; +Cc: linux-mmc, Phil Elwell, Mark Brown
On Wed, 11 Dec 2019 at 00:11, Linus Walleij <linus.walleij@linaro.org> wrote:
>
> On Tue, Dec 10, 2019 at 10:52 AM Ulf Hansson <ulf.hansson@linaro.org> wrote:
> > On Wed, 4 Dec 2019 at 16:29, Linus Walleij <linus.walleij@linaro.org> wrote:
> > >
> > > The code in mmc_spi_initsequence() tries to send a burst with
> > > high chipselect and for this reason hardcodes the device into
> > > SPI_CS_HIGH.
> > >
> > > This is not good because the SPI_CS_HIGH flag indicates
> > > logical "asserted" CS not always the physical level. In
> > > some cases the signal is inverted in the GPIO library and
> > > in that case SPI_CS_HIGH is already set, and enforcing
> > > SPI_CS_HIGH again will actually drive it low.
> > >
> > > Instead of hard-coding this, toggle the polarity so if the
> > > default is LOW it goes high to assert chipselect but if it
> > > is already high then toggle it low instead.
> > >
> > > Cc: Phil Elwell <phil@raspberrypi.org>
> > > Reported-by: Mark Brown <broonie@kernel.org>
> > > Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
> >
> > Seems like we should add a stable tag, right?
>
> Yeah I agree.
Alright. I have amended the patch to add the tag.
Kind regards
Uffe
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2019-12-16 12:09 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-12-04 15:27 [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it Linus Walleij
2019-12-04 17:20 ` Mark Brown
2019-12-10 9:51 ` Ulf Hansson
2019-12-10 23:10 ` Linus Walleij
2019-12-16 12:09 ` Ulf Hansson
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).