[PATCH] Make copy_from_user_inatomic NOT zero the tail on i386

As described in a previous patch and documented in mm/filemap.h,
copy_from_user_inatomic* shouldn't zero out the tail of the buffer after an
incomplete copy.

This patch implements that change for i386.

For the _nocache version, a new __copy_user_intel_nocache is defined similar
to copy_user_zeroio_intel_nocache, and this is ultimately used for the copy.

For the regular version, __copy_from_user_ll_nozero is defined which uses
__copy_user and __copy_user_intel - the later needs casts to reposition the
__user annotations.

If copy_from_user_atomic is given a constant length of 1, 2, or 4, then we do
still zero the destintion on failure.  This didn't seem worth the effort of
fixing as the places where it is used really don't care.

Signed-off-by: Neil Brown <neilb@suse.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 119 insertions, 0 deletions

diff --git a/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c
index 6979297ce278..c5aa65f7c02a 100644
--- a/arch/i386/lib/usercopy.c
+++ b/arch/i386/lib/usercopy.c
@@ -528,6 +528,97 @@ static unsigned long __copy_user_zeroing_intel_nocache(void *to,
 	return size;
 }
 
+static unsigned long __copy_user_intel_nocache(void *to,
+				const void __user *from, unsigned long size)
+{
+        int d0, d1;
+
+	__asm__ __volatile__(
+	       "        .align 2,0x90\n"
+	       "0:      movl 32(%4), %%eax\n"
+	       "        cmpl $67, %0\n"
+	       "        jbe 2f\n"
+	       "1:      movl 64(%4), %%eax\n"
+	       "        .align 2,0x90\n"
+	       "2:      movl 0(%4), %%eax\n"
+	       "21:     movl 4(%4), %%edx\n"
+	       "        movnti %%eax, 0(%3)\n"
+	       "        movnti %%edx, 4(%3)\n"
+	       "3:      movl 8(%4), %%eax\n"
+	       "31:     movl 12(%4),%%edx\n"
+	       "        movnti %%eax, 8(%3)\n"
+	       "        movnti %%edx, 12(%3)\n"
+	       "4:      movl 16(%4), %%eax\n"
+	       "41:     movl 20(%4), %%edx\n"
+	       "        movnti %%eax, 16(%3)\n"
+	       "        movnti %%edx, 20(%3)\n"
+	       "10:     movl 24(%4), %%eax\n"
+	       "51:     movl 28(%4), %%edx\n"
+	       "        movnti %%eax, 24(%3)\n"
+	       "        movnti %%edx, 28(%3)\n"
+	       "11:     movl 32(%4), %%eax\n"
+	       "61:     movl 36(%4), %%edx\n"
+	       "        movnti %%eax, 32(%3)\n"
+	       "        movnti %%edx, 36(%3)\n"
+	       "12:     movl 40(%4), %%eax\n"
+	       "71:     movl 44(%4), %%edx\n"
+	       "        movnti %%eax, 40(%3)\n"
+	       "        movnti %%edx, 44(%3)\n"
+	       "13:     movl 48(%4), %%eax\n"
+	       "81:     movl 52(%4), %%edx\n"
+	       "        movnti %%eax, 48(%3)\n"
+	       "        movnti %%edx, 52(%3)\n"
+	       "14:     movl 56(%4), %%eax\n"
+	       "91:     movl 60(%4), %%edx\n"
+	       "        movnti %%eax, 56(%3)\n"
+	       "        movnti %%edx, 60(%3)\n"
+	       "        addl $-64, %0\n"
+	       "        addl $64, %4\n"
+	       "        addl $64, %3\n"
+	       "        cmpl $63, %0\n"
+	       "        ja  0b\n"
+	       "        sfence \n"
+	       "5:      movl  %0, %%eax\n"
+	       "        shrl  $2, %0\n"
+	       "        andl $3, %%eax\n"
+	       "        cld\n"
+	       "6:      rep; movsl\n"
+	       "        movl %%eax,%0\n"
+	       "7:      rep; movsb\n"
+	       "8:\n"
+	       ".section .fixup,\"ax\"\n"
+	       "9:      lea 0(%%eax,%0,4),%0\n"
+	       "16:     jmp 8b\n"
+	       ".previous\n"
+	       ".section __ex_table,\"a\"\n"
+	       "	.align 4\n"
+	       "	.long 0b,16b\n"
+	       "	.long 1b,16b\n"
+	       "	.long 2b,16b\n"
+	       "	.long 21b,16b\n"
+	       "	.long 3b,16b\n"
+	       "	.long 31b,16b\n"
+	       "	.long 4b,16b\n"
+	       "	.long 41b,16b\n"
+	       "	.long 10b,16b\n"
+	       "	.long 51b,16b\n"
+	       "	.long 11b,16b\n"
+	       "	.long 61b,16b\n"
+	       "	.long 12b,16b\n"
+	       "	.long 71b,16b\n"
+	       "	.long 13b,16b\n"
+	       "	.long 81b,16b\n"
+	       "	.long 14b,16b\n"
+	       "	.long 91b,16b\n"
+	       "	.long 6b,9b\n"
+	       "        .long 7b,16b\n"
+	       ".previous"
+	       : "=&c"(size), "=&D" (d0), "=&S" (d1)
+	       :  "1"(to), "2"(from), "0"(size)
+	       : "eax", "edx", "memory");
+	return size;
+}
+
 #else
 
 /*
@@ -694,6 +785,19 @@ unsigned long __copy_from_user_ll(void *to, const void __user *from,
 }
 EXPORT_SYMBOL(__copy_from_user_ll);
 
+unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
+					 unsigned long n)
+{
+	BUG_ON((long)n < 0);
+	if (movsl_is_ok(to, from, n))
+		__copy_user(to, from, n);
+	else
+		n = __copy_user_intel((void __user *)to,
+				      (const void *)from, n);
+	return n;
+}
+EXPORT_SYMBOL(__copy_from_user_ll_nozero);
+
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
@@ -709,6 +813,21 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 	return n;
 }
 
+unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
+					unsigned long n)
+{
+	BUG_ON((long)n < 0);
+#ifdef CONFIG_X86_INTEL_USERCOPY
+	if ( n > 64 && cpu_has_xmm2)
+                n = __copy_user_intel_nocache(to, from, n);
+	else
+		__copy_user(to, from, n);
+#else
+        __copy_user(to, from, n);
+#endif
+	return n;
+}
+
 /**
  * copy_to_user: - Copy a block of data into user space.
  * @to:   Destination address, in user space.