| Message ID | 1424260217-7719-1-git-send-email-mika.westerberg@linux.intel.com (mailing list archive) |
|---|---|
| State | Accepted, archived |
| Delegated to: | Rafael Wysocki |
| Headers | show |
On Wed, Feb 18, 2015 at 01:50:16PM +0200, Mika Westerberg wrote: > On Baytrail and Braswell the BIOS might leave the I2C host controllers > enabled, probably because it uses them for its on purposes. This is fine in ^^^^^^^^^^^ As pointed out by Graham Whaley, it should say "own purposes". Rafael, do you want me to resend this patch? -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wednesday, February 18, 2015 02:54:08 PM Mika Westerberg wrote: > On Wed, Feb 18, 2015 at 01:50:16PM +0200, Mika Westerberg wrote: > > On Baytrail and Braswell the BIOS might leave the I2C host controllers > > enabled, probably because it uses them for its on purposes. This is fine in > ^^^^^^^^^^^ > As pointed out by Graham Whaley, it should say "own purposes". > > Rafael, do you want me to resend this patch? No need if the code changes are correct, I can fix up the changelog. :-)
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index e75737fd7eef..64ccc3bb0826 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -105,6 +105,8 @@ static void lpss_uart_setup(struct lpss_private_data *pdata) } } +#define LPSS_I2C_ENABLE 0x6c + static void byt_i2c_setup(struct lpss_private_data *pdata) { unsigned int offset; @@ -117,6 +119,8 @@ static void byt_i2c_setup(struct lpss_private_data *pdata) if (readl(pdata->mmio_base + pdata->dev_desc->prv_offset)) pdata->fixed_clk_rate = 133000000; + + writel(0, pdata->mmio_base + LPSS_I2C_ENABLE); } static struct lpss_device_desc lpt_dev_desc = {
On Baytrail and Braswell the BIOS might leave the I2C host controllers enabled, probably because it uses them for its on purposes. This is fine in normal cases because the I2C driver will disable the hardware when it is probed anyway. However, in case of suspend to disk it is different story. If the driver happens to be compiled as module the boot kernel never loads the driver thus leaving host controllers enabled upon loading the hibernation image. The I2C host controller interrupt mask register has default value of 0x8ff, in other words it has most of the interrupts unmasked. When combined with the fact that the host controller is enabled, the driver immediately starts getting interrupts even before its resume hook is called (once IO-APIC is resumed). Since the driver is not prepared for this it will crash the kernel due to NULL pointer derefence because dev->msgs is NULL. Unfortunately we were not able to get full backtrace to from the console which could be reproduced here. In order to fix this even when the driver is compiled as module, we disable the I2C host controllers in byt_i2c_setup() before devices are created. Reported-by: Yu Chen <yu.c.chen@intel.com> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com> --- drivers/acpi/acpi_lpss.c | 4 ++++ 1 file changed, 4 insertions(+)