Merge branch 'copy_user' of git://git.marvell.com/orion into devel

arch/arm/Kconfig

@@ -1091,6 +1091,22 @@ config ALIGNMENT_TRAP
 	  correct operation of some network protocols. With an IP-only
 	  configuration it is safe to say N, otherwise say Y.
 
+config UACCESS_WITH_MEMCPY
+	bool "Use kernel mem{cpy,set}() for {copy_to,clear}_user() (EXPERIMENTAL)"
+	depends on MMU && EXPERIMENTAL
+	default y if CPU_FEROCEON
+	help
+	  Implement faster copy_to_user and clear_user methods for CPU
+	  cores where a 8-word STM instruction give significantly higher
+	  memory write throughput than a sequence of individual 32bit stores.
+
+	  A possible side effect is a slight increase in scheduling latency
+	  between threads sharing the same address space if they invoke
+	  such copy operations with large buffers.
+
+	  However, if the CPU data cache is using a write-allocate mode,
+	  this option is unlikely to provide any performance gain.
+
 endmenu
 
 menu "Boot options"

arch/arm/include/asm/uaccess.h

@@ -386,7 +386,9 @@ do {									\
 #ifdef CONFIG_MMU
 extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
 extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n);
 extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n);
 #else
 #define __copy_from_user(to,from,n)	(memcpy(to, (void __force *)from, n), 0)
 #define __copy_to_user(to,from,n)	(memcpy((void __force *)to, from, n), 0)

arch/arm/lib/Makefile

@@ -29,6 +29,9 @@ else
 endif
 endif
 
+# using lib_ here won't override already available weak symbols
+obj-$(CONFIG_UACCESS_WITH_MEMCPY) += uaccess_with_memcpy.o
+
 lib-$(CONFIG_MMU) += $(mmu-y)
 
 ifeq ($(CONFIG_CPU_32v3),y)

arch/arm/lib/clear_user.S

@@ -18,7 +18,8 @@
  *          : sz   - number of bytes to clear
  * Returns  : number of bytes NOT cleared
  */
-ENTRY(__clear_user)
+ENTRY(__clear_user_std)
+WEAK(__clear_user)
 		stmfd	sp!, {r1, lr}
 		mov	r2, #0
 		cmp	r1, #4

arch/arm/lib/copy_to_user.S

@@ -86,7 +86,8 @@
 
 	.text
 
-ENTRY(__copy_to_user)
+ENTRY(__copy_to_user_std)
+WEAK(__copy_to_user)
 
 #include "copy_template.S"
 

arch/arm/lib/uaccess_with_memcpy.c

+/*
+ *  linux/arch/arm/lib/uaccess_with_memcpy.c
+ *
+ *  Written by: Lennert Buytenhek and Nicolas Pitre
+ *  Copyright (C) 2009 Marvell Semiconductor
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/uaccess.h>
+#include <linux/rwsem.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/hardirq.h> /* for in_atomic() */
+#include <asm/current.h>
+#include <asm/page.h>
+
+static int
+pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
+{
+	unsigned long addr = (unsigned long)_addr;
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	pgd = pgd_offset(current->mm, addr);
+	if (unlikely(pgd_none(*pgd) || pgd_bad(*pgd)))
+		return 0;
+
+	pmd = pmd_offset(pgd, addr);
+	if (unlikely(pmd_none(*pmd) || pmd_bad(*pmd)))
+		return 0;
+
+	pte = pte_offset_map_lock(current->mm, pmd, addr, &ptl);
+	if (unlikely(!pte_present(*pte) || !pte_young(*pte) ||
+	    !pte_write(*pte) || !pte_dirty(*pte))) {
+		pte_unmap_unlock(pte, ptl);
+		return 0;
+	}
+
+	*ptep = pte;
+	*ptlp = ptl;
+
+	return 1;
+}
+
+static unsigned long noinline
+__copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
+{
+	int atomic;
+
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
+		memcpy((void *)to, from, n);
+		return 0;
+	}
+
+	/* the mmap semaphore is taken only if not in an atomic context */
+	atomic = in_atomic();
+
+	if (!atomic)
+		down_read(&current->mm->mmap_sem);
+	while (n) {
+		pte_t *pte;
+		spinlock_t *ptl;
+		int tocopy;
+
+		while (!pin_page_for_write(to, &pte, &ptl)) {
+			if (!atomic)
+				up_read(&current->mm->mmap_sem);
+			if (__put_user(0, (char __user *)to))
+				goto out;
+			if (!atomic)
+				down_read(&current->mm->mmap_sem);
+		}
+
+		tocopy = (~(unsigned long)to & ~PAGE_MASK) + 1;
+		if (tocopy > n)
+			tocopy = n;
+
+		memcpy((void *)to, from, tocopy);
+		to += tocopy;
+		from += tocopy;
+		n -= tocopy;
+
+		pte_unmap_unlock(pte, ptl);
+	}
+	if (!atomic)
+		up_read(&current->mm->mmap_sem);
+
+out:
+	return n;
+}
+
+unsigned long
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	/*
+	 * This test is stubbed out of the main function above to keep
+	 * the overhead for small copies low by avoiding a large
+	 * register dump on the stack just to reload them right away.
+	 * With frame pointer disabled, tail call optimization kicks in
+	 * as well making this test almost invisible.
+	 */
+	if (n < 64)
+		return __copy_to_user_std(to, from, n);
+	return __copy_to_user_memcpy(to, from, n);
+}
+	
+static unsigned long noinline
+__clear_user_memset(void __user *addr, unsigned long n)
+{
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
+		memset((void *)addr, 0, n);
+		return 0;
+	}
+
+	down_read(&current->mm->mmap_sem);
+	while (n) {
+		pte_t *pte;
+		spinlock_t *ptl;
+		int tocopy;
+
+		while (!pin_page_for_write(addr, &pte, &ptl)) {
+			up_read(&current->mm->mmap_sem);
+			if (__put_user(0, (char __user *)addr))
+				goto out;
+			down_read(&current->mm->mmap_sem);
+		}
+
+		tocopy = (~(unsigned long)addr & ~PAGE_MASK) + 1;
+		if (tocopy > n)
+			tocopy = n;
+
+		memset((void *)addr, 0, tocopy);
+		addr += tocopy;
+		n -= tocopy;
+
+		pte_unmap_unlock(pte, ptl);
+	}
+	up_read(&current->mm->mmap_sem);
+
+out:
+	return n;
+}
+
+unsigned long __clear_user(void __user *addr, unsigned long n)
+{
+	/* See rational for this in __copy_to_user() above. */
+	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