After the suspend routine running in OCRAM puts DDR into self-refresh, it will access IOMUXC block to float DDR IO for power saving. A TLB missing of IOMUXC base address may happen in this case, and triggers an access to DDR, and thus hangs the system. The failure is discovered by running suspend/resume on a Cubox-i board. Though the issue is not Cubox-i specific, it can be hit the on the board quite easily with the 3.15 or 3.16 kernel. Fix the issue with a dummy access to IOMUXC block at the beginning of suspend routine, so that the address translation can be filled into TLB before DDR is put into self-refresh. Signed-off-by: Shawn Guo <shawn.guo@xxxxxxxxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> --- arch/arm/mach-imx/suspend-imx6.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index fe123b079c05..87bdf7a629a5 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -172,6 +172,8 @@ ENTRY(imx6_suspend) ldr r6, [r11, #0x0] ldr r11, [r0, #PM_INFO_MX6Q_GPC_V_OFFSET] ldr r6, [r11, #0x0] + ldr r11, [r0, #PM_INFO_MX6Q_IOMUXC_V_OFFSET] + ldr r6, [r11, #0x0] /* use r11 to store the IO address */ ldr r11, [r0, #PM_INFO_MX6Q_SRC_V_OFFSET] -- 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html