arm64: lib: Implement optimized memcmp routine

This patch, based on Linaro's Cortex Strings library, adds
an assembly optimized memcmp() function.

Signed-off-by: Zhichang Yuan <zhichang.yuan@linaro.org>
Signed-off-by: Deepak Saxena <dsaxena@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

4 files changed, 263 insertions, 1 deletions

diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index 3ee8b303d9a9..3a43305cda71 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -34,4 +34,7 @@ extern void *memchr(const void *, int, __kernel_size_t);
 #define __HAVE_ARCH_MEMSET
 extern void *memset(void *, int, __kernel_size_t);
 
+#define __HAVE_ARCH_MEMCMP
+extern int memcmp(const void *, const void *, size_t);
+
 #endif
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 338b568cd8ae..909c18e155ea 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -48,6 +48,7 @@ EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
+EXPORT_SYMBOL(memcmp);
 
         /* atomic bitops */
 EXPORT_SYMBOL(set_bit);
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 328ce1a99daa..112c67f2b109 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,4 +1,4 @@
 lib-y           := bitops.o clear_user.o delay.o copy_from_user.o       \
                    copy_to_user.o copy_in_user.o copy_page.o            \
                    clear_page.o memchr.o memcpy.o memmove.o memset.o    \
-                   strchr.o strrchr.o
+                   memcmp.o strchr.o strrchr.o
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
new file mode 100644
index 000000000000..6ea0776ba6de
--- /dev/null
+++ b/arch/arm64/lib/memcmp.S
@@ -0,0 +1,258 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+* compare memory areas(when two memory areas' offset are different,
+* alignment handled by the hardware)
+*
+* Parameters:
+*  x0 - const memory area 1 pointer
+*  x1 - const memory area 2 pointer
+*  x2 - the maximal compare byte length
+* Returns:
+*  x0 - a compare result, maybe less than, equal to, or greater than ZERO
+*/
+
+/* Parameters and result.  */
+src1            .req    x0
+src2            .req    x1
+limit           .req    x2
+result          .req    x0
+
+/* Internal variables.  */
+data1           .req    x3
+data1w          .req    w3
+data2           .req    x4
+data2w          .req    w4
+has_nul         .req    x5
+diff            .req    x6
+endloop         .req    x7
+tmp1            .req    x8
+tmp2            .req    x9
+tmp3            .req    x10
+pos             .req    x11
+limit_wd        .req    x12
+mask            .req    x13
+
+ENTRY(memcmp)
+        cbz     limit, .Lret0
+        eor     tmp1, src1, src2
+        tst     tmp1, #7
+        b.ne    .Lmisaligned8
+        ands    tmp1, src1, #7
+        b.ne    .Lmutual_align
+        sub     limit_wd, limit, #1 /* limit != 0, so no underflow.  */
+        lsr     limit_wd, limit_wd, #3 /* Convert to Dwords.  */
+        /*
+        * The input source addresses are at alignment boundary.
+        * Directly compare eight bytes each time.
+        */
+.Lloop_aligned:
+        ldr     data1, [src1], #8
+        ldr     data2, [src2], #8
+.Lstart_realigned:
+        subs    limit_wd, limit_wd, #1
+        eor     diff, data1, data2      /* Non-zero if differences found.  */
+        csinv   endloop, diff, xzr, cs  /* Last Dword or differences.  */
+        cbz     endloop, .Lloop_aligned
+
+        /* Not reached the limit, must have found a diff.  */
+        tbz     limit_wd, #63, .Lnot_limit
+
+        /* Limit % 8 == 0 => the diff is in the last 8 bytes. */
+        ands    limit, limit, #7
+        b.eq    .Lnot_limit
+        /*
+        * The remained bytes less than 8. It is needed to extract valid data
+        * from last eight bytes of the intended memory range.
+        */
+        lsl     limit, limit, #3        /* bytes-> bits.  */
+        mov     mask, #~0
+CPU_BE( lsr     mask, mask, limit )
+CPU_LE( lsl     mask, mask, limit )
+        bic     data1, data1, mask
+        bic     data2, data2, mask
+
+        orr     diff, diff, mask
+        b       .Lnot_limit
+
+.Lmutual_align:
+        /*
+        * Sources are mutually aligned, but are not currently at an
+        * alignment boundary. Round down the addresses and then mask off
+        * the bytes that precede the start point.
+        */
+        bic     src1, src1, #7
+        bic     src2, src2, #7
+        ldr     data1, [src1], #8
+        ldr     data2, [src2], #8
+        /*
+        * We can not add limit with alignment offset(tmp1) here. Since the
+        * addition probably make the limit overflown.
+        */
+        sub     limit_wd, limit, #1/*limit != 0, so no underflow.*/
+        and     tmp3, limit_wd, #7
+        lsr     limit_wd, limit_wd, #3
+        add     tmp3, tmp3, tmp1
+        add     limit_wd, limit_wd, tmp3, lsr #3
+        add     limit, limit, tmp1/* Adjust the limit for the extra.  */
+
+        lsl     tmp1, tmp1, #3/* Bytes beyond alignment -> bits.*/
+        neg     tmp1, tmp1/* Bits to alignment -64.  */
+        mov     tmp2, #~0
+        /*mask off the non-intended bytes before the start address.*/
+CPU_BE( lsl     tmp2, tmp2, tmp1 )/*Big-endian.Early bytes are at MSB*/
+        /* Little-endian.  Early bytes are at LSB.  */
+CPU_LE( lsr     tmp2, tmp2, tmp1 )
+
+        orr     data1, data1, tmp2
+        orr     data2, data2, tmp2
+        b       .Lstart_realigned
+
+        /*src1 and src2 have different alignment offset.*/
+.Lmisaligned8:
+        cmp     limit, #8
+        b.lo    .Ltiny8proc /*limit < 8: compare byte by byte*/
+
+        and     tmp1, src1, #7
+        neg     tmp1, tmp1
+        add     tmp1, tmp1, #8/*valid length in the first 8 bytes of src1*/
+        and     tmp2, src2, #7
+        neg     tmp2, tmp2
+        add     tmp2, tmp2, #8/*valid length in the first 8 bytes of src2*/
+        subs    tmp3, tmp1, tmp2
+        csel    pos, tmp1, tmp2, hi /*Choose the maximum.*/
+
+        sub     limit, limit, pos
+        /*compare the proceeding bytes in the first 8 byte segment.*/
+.Ltinycmp:
+        ldrb    data1w, [src1], #1
+        ldrb    data2w, [src2], #1
+        subs    pos, pos, #1
+        ccmp    data1w, data2w, #0, ne  /* NZCV = 0b0000.  */
+        b.eq    .Ltinycmp
+        cbnz    pos, 1f /*diff occurred before the last byte.*/
+        cmp     data1w, data2w
+        b.eq    .Lstart_align
+1:
+        sub     result, data1, data2
+        ret
+
+.Lstart_align:
+        lsr     limit_wd, limit, #3
+        cbz     limit_wd, .Lremain8
+
+        ands    xzr, src1, #7
+        b.eq    .Lrecal_offset
+        /*process more leading bytes to make src1 aligned...*/
+        add     src1, src1, tmp3 /*backwards src1 to alignment boundary*/
+        add     src2, src2, tmp3
+        sub     limit, limit, tmp3
+        lsr     limit_wd, limit, #3
+        cbz     limit_wd, .Lremain8
+        /*load 8 bytes from aligned SRC1..*/
+        ldr     data1, [src1], #8
+        ldr     data2, [src2], #8
+
+        subs    limit_wd, limit_wd, #1
+        eor     diff, data1, data2  /*Non-zero if differences found.*/
+        csinv   endloop, diff, xzr, ne
+        cbnz    endloop, .Lunequal_proc
+        /*How far is the current SRC2 from the alignment boundary...*/
+        and     tmp3, tmp3, #7
+
+.Lrecal_offset:/*src1 is aligned now..*/
+        neg     pos, tmp3
+.Lloopcmp_proc:
+        /*
+        * Divide the eight bytes into two parts. First,backwards the src2
+        * to an alignment boundary,load eight bytes and compare from
+        * the SRC2 alignment boundary. If all 8 bytes are equal,then start
+        * the second part's comparison. Otherwise finish the comparison.
+        * This special handle can garantee all the accesses are in the
+        * thread/task space in avoid to overrange access.
+        */
+        ldr     data1, [src1,pos]
+        ldr     data2, [src2,pos]
+        eor     diff, data1, data2  /* Non-zero if differences found.  */
+        cbnz    diff, .Lnot_limit
+
+        /*The second part process*/
+        ldr     data1, [src1], #8
+        ldr     data2, [src2], #8
+        eor     diff, data1, data2  /* Non-zero if differences found.  */
+        subs    limit_wd, limit_wd, #1
+        csinv   endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
+        cbz     endloop, .Lloopcmp_proc
+.Lunequal_proc:
+        cbz     diff, .Lremain8
+
+/*There is differnence occured in the latest comparison.*/
+.Lnot_limit:
+/*
+* For little endian,reverse the low significant equal bits into MSB,then
+* following CLZ can find how many equal bits exist.
+*/
+CPU_LE( rev     diff, diff )
+CPU_LE( rev     data1, data1 )
+CPU_LE( rev     data2, data2 )
+
+        /*
+        * The MS-non-zero bit of DIFF marks either the first bit
+        * that is different, or the end of the significant data.
+        * Shifting left now will bring the critical information into the
+        * top bits.
+        */
+        clz     pos, diff
+        lsl     data1, data1, pos
+        lsl     data2, data2, pos
+        /*
+        * We need to zero-extend (char is unsigned) the value and then
+        * perform a signed subtraction.
+        */
+        lsr     data1, data1, #56
+        sub     result, data1, data2, lsr #56
+        ret
+
+.Lremain8:
+        /* Limit % 8 == 0 =>. all data are equal.*/
+        ands    limit, limit, #7
+        b.eq    .Lret0
+
+.Ltiny8proc:
+        ldrb    data1w, [src1], #1
+        ldrb    data2w, [src2], #1
+        subs    limit, limit, #1
+
+        ccmp    data1w, data2w, #0, ne  /* NZCV = 0b0000. */
+        b.eq    .Ltiny8proc
+        sub     result, data1, data2
+        ret
+.Lret0:
+        mov     result, #0
+        ret
+ENDPROC(memcmp)