From: Greg Kroah-Hartman Date: Thu, 6 Feb 2020 19:31:00 +0000 (+0100) Subject: 4.4-stable patches X-Git-Tag: v4.19.103~117 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=c59ef9948d056557c4b3833e76014c7de931db5a;p=thirdparty%2Fkernel%2Fstable-queue.git 4.4-stable patches added patches: mmc-spi-toggle-spi-polarity-do-not-hardcode-it.patch --- diff --git a/queue-4.4/mmc-spi-toggle-spi-polarity-do-not-hardcode-it.patch b/queue-4.4/mmc-spi-toggle-spi-polarity-do-not-hardcode-it.patch new file mode 100644 index 00000000000..c8c37d65537 --- /dev/null +++ b/queue-4.4/mmc-spi-toggle-spi-polarity-do-not-hardcode-it.patch @@ -0,0 +1,64 @@ +From af3ed119329cf9690598c5a562d95dfd128e91d6 Mon Sep 17 00:00:00 2001 +From: Linus Walleij +Date: Wed, 4 Dec 2019 16:27:49 +0100 +Subject: mmc: spi: Toggle SPI polarity, do not hardcode it + +From: Linus Walleij + +commit af3ed119329cf9690598c5a562d95dfd128e91d6 upstream. + +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 +Reported-by: Mark Brown +Signed-off-by: Linus Walleij +Reviewed-by: Mark Brown +Link: https://lore.kernel.org/r/20191204152749.12652-1-linus.walleij@linaro.org +Cc: stable@vger.kernel.org +Signed-off-by: Ulf Hansson +Signed-off-by: Greg Kroah-Hartman + +--- + drivers/mmc/host/mmc_spi.c | 11 ++++++++--- + 1 file changed, 8 insertions(+), 3 deletions(-) + +--- a/drivers/mmc/host/mmc_spi.c ++++ b/drivers/mmc/host/mmc_spi.c +@@ -1153,17 +1153,22 @@ static void mmc_spi_initsequence(struct + * 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, diff --git a/queue-4.4/series b/queue-4.4/series index 02193d456df..23019ebfbdc 100644 --- a/queue-4.4/series +++ b/queue-4.4/series @@ -16,3 +16,4 @@ usb-gadget-f_ecm-use-atomic_t-to-track-in-flight-request.patch alsa-dummy-fix-pcm-format-loop-in-proc-output.patch lib-test_kasan.c-fix-memory-leak-in-kmalloc_oob_krealloc_more.patch powerpc-pseries-advance-pfn-if-section-is-not-present-in-lmb_is_removable.patch +mmc-spi-toggle-spi-polarity-do-not-hardcode-it.patch