[ARM] alternative copy_to_user: more precise fallback threshold

Previous size thresholds were guessed from various user space benchmarks
using a kernel with and without the alternative uaccess option.  This
is however not as precise as a kernel based test to measure the real
speed of each method.

This adds a simple test bench to show the time needed for each method.
With this, the optimal size treshold for the alternative implementation
can be determined with more confidence.  It appears that the optimal
threshold for both copy_to_user and clear_user is around 64 bytes. This
is not a surprise knowing that the memcpy and memset implementations
need at least 64 bytes to achieve maximum throughput.

One might suggest that such test be used to determine the optimal
threshold at run time instead, but results are near enough to 64 on
tested targets concerned by this alternative copy_to_user implementation,
so adding some overhead associated with a variable threshold is probably
not worth it for now.
Signed-off-by: Nicolas Pitre <nico@marvell.com>

arch/arm/lib/uaccess_with_memcpy.c

@@ -106,7 +106,7 @@ __copy_to_user(void __user *to, const void *from, unsigned long n)
 	 * With frame pointer disabled, tail call optimization kicks in
 	 * as well making this test almost invisible.
 	 */
-	if (n < 1024)
+	if (n < 64)
 		return __copy_to_user_std(to, from, n);
 	return __copy_to_user_memcpy(to, from, n);
 }
@@ -151,7 +151,78 @@ out:
 unsigned long __clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
-	if (n < 256)
+	if (n < 64)
 		return __clear_user_std(addr, n);
 	return __clear_user_memset(addr, n);
 }
+
+#if 0
+
+/*
+ * This code is disabled by default, but kept around in case the chosen
+ * thresholds need to be revalidated.  Some overhead (small but still)
+ * would be implied by a runtime determined variable threshold, and
+ * so far the measurement on concerned targets didn't show a worthwhile
+ * variation.
+ *
+ * Note that a fairly precise sched_clock() implementation is needed
+ * for results to make some sense.
+ */
+
+#include <linux/vmalloc.h>
+
+static int __init test_size_treshold(void)
+{
+	struct page *src_page, *dst_page;
+	void *user_ptr, *kernel_ptr;
+	unsigned long long t0, t1, t2;
+	int size, ret;
+
+	ret = -ENOMEM;
+	src_page = alloc_page(GFP_KERNEL);
+	if (!src_page)
+		goto no_src;
+	dst_page = alloc_page(GFP_KERNEL);
+	if (!dst_page)
+		goto no_dst;
+	kernel_ptr = page_address(src_page);
+	user_ptr = vmap(&dst_page, 1, VM_IOREMAP, __pgprot(__P010));
+	if (!user_ptr)
+		goto no_vmap;
+
+	/* warm up the src page dcache */
+	ret = __copy_to_user_memcpy(user_ptr, kernel_ptr, PAGE_SIZE);
+
+	for (size = PAGE_SIZE; size >= 4; size /= 2) {
+		t0 = sched_clock();
+		ret |= __copy_to_user_memcpy(user_ptr, kernel_ptr, size);
+		t1 = sched_clock();
+		ret |= __copy_to_user_std(user_ptr, kernel_ptr, size);
+		t2 = sched_clock();
+		printk("copy_to_user: %d %llu %llu\n", size, t1 - t0, t2 - t1);
+	}
+
+	for (size = PAGE_SIZE; size >= 4; size /= 2) {
+		t0 = sched_clock();
+		ret |= __clear_user_memset(user_ptr, size);
+		t1 = sched_clock();
+		ret |= __clear_user_std(user_ptr, size);
+		t2 = sched_clock();
+		printk("clear_user: %d %llu %llu\n", size, t1 - t0, t2 - t1);
+	}
+
+	if (ret)
+		ret = -EFAULT;
+
+	vunmap(user_ptr);
+no_vmap:
+	put_page(dst_page);
+no_dst:
+	put_page(src_page);
+no_src:
+	return ret;
+}
+
+subsys_initcall(test_size_treshold);
+
+#endif