arm: timer: sunxi: add Allwinner timer erratum workaround

The Allwinner A64 SoCs suffers from an arch timer implementation erratum,
where sometimes the lower 11 bits of the counter value erroneously
become all 0's or all 1's [1]. This leads to sudden jumps, both forwards and
backwards, with the latter one often showing weird behaviour.
Port the workaround proposed for Linux to U-Boot and activate it for all
A64 boards.
This fixes crashes when accessing MMC devices (SD cards), caused by a
recent change to actually use the counter value for timeout checks.

Fixes: 5ff8e54888 ("sunxi: improve throughput
in the sunxi_mmc driver")

[1] http://lists.infradead.org/pipermail/linux-arm-kernel/2018-May/576886.html

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Philipp Tomsich <philipp.tomsich@theobroma-systems.com>
Tested-by: Jagan Teki <jagan@amarulasolutions.com>
Tested-by: Andreas Färber <afaerber@suse.de>
Tested-by: Guillaume Gardet <guillaume.gardet@free.fr>

arch/arm/cpu/armv8/generic_timer.c

@@ -46,6 +46,30 @@ unsigned long timer_read_counter(void)
 
 	return cntpct;
 }
+#elif CONFIG_SUNXI_A64_TIMER_ERRATUM
+/*
+ * This erratum sometimes flips the lower 11 bits of the counter value
+ * to all 0's or all 1's, leading to jumps forwards or backwards.
+ * Backwards jumps might be interpreted all roll-overs and be treated as
+ * huge jumps forward.
+ * The workaround is to check whether the lower 11 bits of the counter are
+ * all 0 or all 1, then discard this value and read again.
+ * This occasionally discards valid values, but will catch all erroneous
+ * reads and fixes the problem reliably. Also this mostly requires only a
+ * single read, so does not have any significant overhead.
+ * The algorithm was conceived by Samuel Holland.
+ */
+unsigned long timer_read_counter(void)
+{
+	unsigned long cntpct;
+
+	isb();
+	do {
+		asm volatile("mrs %0, cntpct_el0" : "=r" (cntpct));
+	} while (((cntpct + 1) & GENMASK(10, 0)) <= 1);
+
+	return cntpct;
+}
 #else
 /*
  * timer_read_counter() using the Arm Generic Timer (aka arch timer).

arch/arm/mach-sunxi/Kconfig

@@ -84,6 +84,9 @@ config SUNXI_HIGH_SRAM
 	Chips using the latter setup are supposed to select this option to
 	adjust the addresses accordingly.
 
+config SUNXI_A64_TIMER_ERRATUM
+	bool
+
 # Note only one of these may be selected at a time! But hidden choices are
 # not supported by Kconfig
 config SUNXI_GEN_SUN4I
@@ -270,6 +273,7 @@ config MACH_SUN50I
 	select SUNXI_DRAM_DW_32BIT
 	select FIT
 	select SPL_LOAD_FIT
+	select SUNXI_A64_TIMER_ERRATUM
 
 config MACH_SUN50I_H5
 	bool "sun50i (Allwinner H5)"