--- /dev/null
+/*
+ * Copyright (c) 2013, Applied Micro Circuits Corporation
+ * Copyright (c) 2012-2013, Linaro Limited
+ *
+ * Author: Feng Kan <fkan@apm.com>
+ * Author: Philipp Tomsich <philipp.tomsich@theobroma-systems.com>
+ *
+ * The code is adopted from the memcpy routine by Linaro Limited.
+ *
+ * This file is free software: you may copy, redistribute and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation, either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This file 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/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * 1 Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2 Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3 Neither the name of the Linaro nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <asm/assembler.h>
+
+dstin .req x0
+src .req x1
+count .req x2
+tmp1 .req x3
+tmp1w .req w3
+tmp2 .req x4
+tmp2w .req w4
+tmp3 .req x5
+tmp3w .req w5
+dst .req x6
+
+A_l .req x7
+A_h .req x8
+B_l .req x9
+B_h .req x10
+C_l .req x11
+C_h .req x12
+D_l .req x13
+D_h .req x14
+
+ mov dst, dstin
+ cmp count, #64
+ b.ge .Lcpy_not_short
+ cmp count, #15
+ b.le .Ltail15tiny
+
+ /*
+ * Deal with small copies quickly by dropping straight into the
+ * exit block.
+ */
+.Ltail63:
+ /*
+ * Copy up to 48 bytes of data. At this point we only need the
+ * bottom 6 bits of count to be accurate.
+ */
+ ands tmp1, count, #0x30
+ b.eq .Ltail15
+ add dst, dst, tmp1
+ add src, src, tmp1
+ cmp tmp1w, #0x20
+ b.eq 1f
+ b.lt 2f
+ USER(8f, ldp A_l, A_h, [src, #-48])
+ USER(8f, stp A_l, A_h, [dst, #-48])
+1:
+ USER(8f, ldp A_l, A_h, [src, #-32])
+ USER(8f, stp A_l, A_h, [dst, #-32])
+2:
+ USER(8f, ldp A_l, A_h, [src, #-16])
+ USER(8f, stp A_l, A_h, [dst, #-16])
+
+.Ltail15:
+ ands count, count, #15
+ beq 1f
+ add src, src, count
+ USER(9f, ldp A_l, A_h, [src, #-16])
+ add dst, dst, count
+ USER(9f, stp A_l, A_h, [dst, #-16])
+1:
+ b .Lsuccess
+
+.Ltail15tiny:
+ /*
+ * Copy up to 15 bytes of data. Does not assume additional data
+ * being copied.
+ */
+ tbz count, #3, 1f
+ USER(10f, ldr tmp1, [src], #8)
+ USER(10f, str tmp1, [dst], #8)
+1:
+ tbz count, #2, 1f
+ USER(10f, ldr tmp1w, [src], #4)
+ USER(10f, str tmp1w, [dst], #4)
+1:
+ tbz count, #1, 1f
+ USER(10f, ldrh tmp1w, [src], #2)
+ USER(10f, strh tmp1w, [dst], #2)
+1:
+ tbz count, #0, 1f
+ USER(10f, ldrb tmp1w, [src])
+ USER(10f, strb tmp1w, [dst])
+1:
+ b .Lsuccess
+
+.Lcpy_not_short:
+ /*
+ * We don't much care about the alignment of DST, but we want SRC
+ * to be 128-bit (16 byte) aligned so that we don't cross cache line
+ * boundaries on both loads and stores.
+ */
+ neg tmp2, src
+ ands tmp2, tmp2, #15 /* Bytes to reach alignment. */
+ b.eq 2f
+ sub count, count, tmp2
+ /*
+ * Copy more data than needed; it's faster than jumping
+ * around copying sub-Quadword quantities. We know that
+ * it can't overrun.
+ */
+ USER(11f, ldp A_l, A_h, [src])
+ add src, src, tmp2
+ USER(11f, stp A_l, A_h, [dst])
+ add dst, dst, tmp2
+ /* There may be less than 63 bytes to go now. */
+ cmp count, #63
+ b.le .Ltail63
+2:
+ subs count, count, #128
+ b.ge .Lcpy_body_large
+ /*
+ * Less than 128 bytes to copy, so handle 64 here and then jump
+ * to the tail.
+ */
+ USER(12f, ldp A_l, A_h, [src])
+ USER(12f, ldp B_l, B_h, [src, #16])
+ USER(12f, ldp C_l, C_h, [src, #32])
+ USER(12f, ldp D_l, D_h, [src, #48])
+ USER(12f, stp A_l, A_h, [dst])
+ USER(12f, stp B_l, B_h, [dst, #16])
+ USER(12f, stp C_l, C_h, [dst, #32])
+ USER(12f, stp D_l, D_h, [dst, #48])
+ tst count, #0x3f
+ add src, src, #64
+ add dst, dst, #64
+ b.ne .Ltail63
+ b .Lsuccess
+
+ /*
+ * Critical loop. Start at a new cache line boundary. Assuming
+ * 64 bytes per line this ensures the entire loop is in one line.
+ */
+ .p2align 6
+.Lcpy_body_large:
+ /* There are at least 128 bytes to copy. */
+ USER(12f, ldp A_l, A_h, [src, #0])
+ sub dst, dst, #16 /* Pre-bias. */
+ USER(13f, ldp B_l, B_h, [src, #16])
+ USER(13f, ldp C_l, C_h, [src, #32])
+ USER(13f, ldp D_l, D_h, [src, #48]!) /* src += 64 - Pre-bias. */
+1:
+ USER(13f, stp A_l, A_h, [dst, #16])
+ USER(13f, ldp A_l, A_h, [src, #16])
+ USER(13f, stp B_l, B_h, [dst, #32])
+ USER(13f, ldp B_l, B_h, [src, #32])
+ USER(13f, stp C_l, C_h, [dst, #48])
+ USER(13f, ldp C_l, C_h, [src, #48])
+ USER(13f, stp D_l, D_h, [dst, #64]!)
+ USER(13f, ldp D_l, D_h, [src, #64]!)
+ subs count, count, #64
+ b.ge 1b
+ USER(13f, stp A_l, A_h, [dst, #16])
+ USER(13f, stp B_l, B_h, [dst, #32])
+ USER(13f, stp C_l, C_h, [dst, #48])
+ USER(13f, stp D_l, D_h, [dst, #64])
+ add src, src, #16
+ add dst, dst, #64 + 16
+ tst count, #0x3f
+ b.ne .Ltail63
+.Lsuccess:
+ /* Nothing left to copy */
+ mov x0, #0
+ ret
projects / people / julieng / linux-arm.git / commitdiff