powerpc: introduce CONFIG_CACHE_FLUSH_WATCHDOG_THRESHOLD

When flush_cache() is called during boot on our ~7M kernel image, the
hundreds of thousands of WATCHDOG_RESET calls end up adding
significantly to boottime. Flushing a single cache line doesn't take
many microseconds, so doing these calls for every cache line is
complete overkill.

The generic watchdog_reset() provided by wdt-uclass.c actually
contains some rate-limiting logic that should in theory mitigate this,
but alas, that rate-limiting must be disabled on powerpc because of
its get_timer() implementation - get_timer() works just fine until
interrupts are disabled, but it just so happens that the "big"
flush_cache() call happens in the part of bootm where interrupts are
indeed disabled. [1] [2] [3]

I have checked with objdump that the generated code doesn't change
when this option is left at its default value of 0: gcc is smart
enough to see that the ">=" comparison is tautologically true, hence
all assignments to "flushed" are eliminated as dead stores.

On our board, setting the option to something like 65536 ends up
reducing total boottime by about 0.8 seconds.

[1] https://patchwork.ozlabs.org/project/uboot/patch/20200605111657.28773-1-rasmus.villemoes@prevas.dk/
[2] https://lists.denx.de/pipermail/u-boot/2021-April/446906.html
[3] https://lists.denx.de/pipermail/u-boot/2021-April/447280.html

Reviewed-by: Stefan Roese <sr@denx.de>
Signed-off-by: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
diff --git a/arch/powerpc/lib/cache.c b/arch/powerpc/lib/cache.c
index 3e487f5..1916251 100644
--- a/arch/powerpc/lib/cache.c
+++ b/arch/powerpc/lib/cache.c
@@ -9,9 +9,20 @@
 #include <asm/cache.h>
 #include <watchdog.h>
 
+static ulong maybe_watchdog_reset(ulong flushed)
+{
+	flushed += CONFIG_SYS_CACHELINE_SIZE;
+	if (flushed >= CONFIG_CACHE_FLUSH_WATCHDOG_THRESHOLD) {
+		WATCHDOG_RESET();
+		flushed = 0;
+	}
+	return flushed;
+}
+
 void flush_cache(ulong start_addr, ulong size)
 {
 	ulong addr, start, end;
+	ulong flushed = 0;
 
 	start = start_addr & ~(CONFIG_SYS_CACHELINE_SIZE - 1);
 	end = start_addr + size - 1;
@@ -19,7 +30,7 @@
 	for (addr = start; (addr <= end) && (addr >= start);
 			addr += CONFIG_SYS_CACHELINE_SIZE) {
 		asm volatile("dcbst 0,%0" : : "r" (addr) : "memory");
-		WATCHDOG_RESET();
+		flushed = maybe_watchdog_reset(flushed);
 	}
 	/* wait for all dcbst to complete on bus */
 	asm volatile("sync" : : : "memory");
@@ -27,7 +38,7 @@
 	for (addr = start; (addr <= end) && (addr >= start);
 			addr += CONFIG_SYS_CACHELINE_SIZE) {
 		asm volatile("icbi 0,%0" : : "r" (addr) : "memory");
-		WATCHDOG_RESET();
+		flushed = maybe_watchdog_reset(flushed);
 	}
 	asm volatile("sync" : : : "memory");
 	/* flush prefetch queue */