OpenCloudOS-Kernel/arch/mips/cavium-octeon/octeon-memcpy.S

530 lines
13 KiB
ArmAsm

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Unified implementation of memcpy, memmove and the __copy_user backend.
*
* Copyright (C) 1998, 99, 2000, 01, 2002 Ralf Baechle (ralf@gnu.org)
* Copyright (C) 1999, 2000, 01, 2002 Silicon Graphics, Inc.
* Copyright (C) 2002 Broadcom, Inc.
* memcpy/copy_user author: Mark Vandevoorde
*
* Mnemonic names for arguments to memcpy/__copy_user
*/
#include <asm/asm.h>
#include <asm/asm-offsets.h>
#include <asm/regdef.h>
#define dst a0
#define src a1
#define len a2
/*
* Spec
*
* memcpy copies len bytes from src to dst and sets v0 to dst.
* It assumes that
* - src and dst don't overlap
* - src is readable
* - dst is writable
* memcpy uses the standard calling convention
*
* __copy_user copies up to len bytes from src to dst and sets a2 (len) to
* the number of uncopied bytes due to an exception caused by a read or write.
* __copy_user assumes that src and dst don't overlap, and that the call is
* implementing one of the following:
* copy_to_user
* - src is readable (no exceptions when reading src)
* copy_from_user
* - dst is writable (no exceptions when writing dst)
* __copy_user uses a non-standard calling convention; see
* arch/mips/include/asm/uaccess.h
*
* When an exception happens on a load, the handler must
# ensure that all of the destination buffer is overwritten to prevent
* leaking information to user mode programs.
*/
/*
* Implementation
*/
/*
* The exception handler for loads requires that:
* 1- AT contain the address of the byte just past the end of the source
* of the copy,
* 2- src_entry <= src < AT, and
* 3- (dst - src) == (dst_entry - src_entry),
* The _entry suffix denotes values when __copy_user was called.
*
* (1) is set up up by uaccess.h and maintained by not writing AT in copy_user
* (2) is met by incrementing src by the number of bytes copied
* (3) is met by not doing loads between a pair of increments of dst and src
*
* The exception handlers for stores adjust len (if necessary) and return.
* These handlers do not need to overwrite any data.
*
* For __rmemcpy and memmove an exception is always a kernel bug, therefore
* they're not protected.
*/
#define EXC(inst_reg,addr,handler) \
9: inst_reg, addr; \
.section __ex_table,"a"; \
PTR 9b, handler; \
.previous
/*
* Only on the 64-bit kernel we can made use of 64-bit registers.
*/
#ifdef CONFIG_64BIT
#define USE_DOUBLE
#endif
#ifdef USE_DOUBLE
#define LOAD ld
#define LOADL ldl
#define LOADR ldr
#define STOREL sdl
#define STORER sdr
#define STORE sd
#define ADD daddu
#define SUB dsubu
#define SRL dsrl
#define SRA dsra
#define SLL dsll
#define SLLV dsllv
#define SRLV dsrlv
#define NBYTES 8
#define LOG_NBYTES 3
/*
* As we are sharing code base with the mips32 tree (which use the o32 ABI
* register definitions). We need to redefine the register definitions from
* the n64 ABI register naming to the o32 ABI register naming.
*/
#undef t0
#undef t1
#undef t2
#undef t3
#define t0 $8
#define t1 $9
#define t2 $10
#define t3 $11
#define t4 $12
#define t5 $13
#define t6 $14
#define t7 $15
#else
#define LOAD lw
#define LOADL lwl
#define LOADR lwr
#define STOREL swl
#define STORER swr
#define STORE sw
#define ADD addu
#define SUB subu
#define SRL srl
#define SLL sll
#define SRA sra
#define SLLV sllv
#define SRLV srlv
#define NBYTES 4
#define LOG_NBYTES 2
#endif /* USE_DOUBLE */
#ifdef CONFIG_CPU_LITTLE_ENDIAN
#define LDFIRST LOADR
#define LDREST LOADL
#define STFIRST STORER
#define STREST STOREL
#define SHIFT_DISCARD SLLV
#else
#define LDFIRST LOADL
#define LDREST LOADR
#define STFIRST STOREL
#define STREST STORER
#define SHIFT_DISCARD SRLV
#endif
#define FIRST(unit) ((unit)*NBYTES)
#define REST(unit) (FIRST(unit)+NBYTES-1)
#define UNIT(unit) FIRST(unit)
#define ADDRMASK (NBYTES-1)
.text
.set noreorder
.set noat
/*
* t7 is used as a flag to note inatomic mode.
*/
LEAF(__copy_user_inatomic)
b __copy_user_common
li t7, 1
END(__copy_user_inatomic)
/*
* A combined memcpy/__copy_user
* __copy_user sets len to 0 for success; else to an upper bound of
* the number of uncopied bytes.
* memcpy sets v0 to dst.
*/
.align 5
LEAF(memcpy) /* a0=dst a1=src a2=len */
move v0, dst /* return value */
__memcpy:
FEXPORT(__copy_user)
li t7, 0 /* not inatomic */
__copy_user_common:
/*
* Note: dst & src may be unaligned, len may be 0
* Temps
*/
#
# Octeon doesn't care if the destination is unaligned. The hardware
# can fix it faster than we can special case the assembly.
#
pref 0, 0(src)
sltu t0, len, NBYTES # Check if < 1 word
bnez t0, copy_bytes_checklen
and t0, src, ADDRMASK # Check if src unaligned
bnez t0, src_unaligned
sltu t0, len, 4*NBYTES # Check if < 4 words
bnez t0, less_than_4units
sltu t0, len, 8*NBYTES # Check if < 8 words
bnez t0, less_than_8units
sltu t0, len, 16*NBYTES # Check if < 16 words
bnez t0, cleanup_both_aligned
sltu t0, len, 128+1 # Check if len < 129
bnez t0, 1f # Skip prefetch if len is too short
sltu t0, len, 256+1 # Check if len < 257
bnez t0, 1f # Skip prefetch if len is too short
pref 0, 128(src) # We must not prefetch invalid addresses
#
# This is where we loop if there is more than 128 bytes left
2: pref 0, 256(src) # We must not prefetch invalid addresses
#
# This is where we loop if we can't prefetch anymore
1:
EXC( LOAD t0, UNIT(0)(src), l_exc)
EXC( LOAD t1, UNIT(1)(src), l_exc_copy)
EXC( LOAD t2, UNIT(2)(src), l_exc_copy)
EXC( LOAD t3, UNIT(3)(src), l_exc_copy)
SUB len, len, 16*NBYTES
EXC( STORE t0, UNIT(0)(dst), s_exc_p16u)
EXC( STORE t1, UNIT(1)(dst), s_exc_p15u)
EXC( STORE t2, UNIT(2)(dst), s_exc_p14u)
EXC( STORE t3, UNIT(3)(dst), s_exc_p13u)
EXC( LOAD t0, UNIT(4)(src), l_exc_copy)
EXC( LOAD t1, UNIT(5)(src), l_exc_copy)
EXC( LOAD t2, UNIT(6)(src), l_exc_copy)
EXC( LOAD t3, UNIT(7)(src), l_exc_copy)
EXC( STORE t0, UNIT(4)(dst), s_exc_p12u)
EXC( STORE t1, UNIT(5)(dst), s_exc_p11u)
EXC( STORE t2, UNIT(6)(dst), s_exc_p10u)
ADD src, src, 16*NBYTES
EXC( STORE t3, UNIT(7)(dst), s_exc_p9u)
ADD dst, dst, 16*NBYTES
EXC( LOAD t0, UNIT(-8)(src), l_exc_copy)
EXC( LOAD t1, UNIT(-7)(src), l_exc_copy)
EXC( LOAD t2, UNIT(-6)(src), l_exc_copy)
EXC( LOAD t3, UNIT(-5)(src), l_exc_copy)
EXC( STORE t0, UNIT(-8)(dst), s_exc_p8u)
EXC( STORE t1, UNIT(-7)(dst), s_exc_p7u)
EXC( STORE t2, UNIT(-6)(dst), s_exc_p6u)
EXC( STORE t3, UNIT(-5)(dst), s_exc_p5u)
EXC( LOAD t0, UNIT(-4)(src), l_exc_copy)
EXC( LOAD t1, UNIT(-3)(src), l_exc_copy)
EXC( LOAD t2, UNIT(-2)(src), l_exc_copy)
EXC( LOAD t3, UNIT(-1)(src), l_exc_copy)
EXC( STORE t0, UNIT(-4)(dst), s_exc_p4u)
EXC( STORE t1, UNIT(-3)(dst), s_exc_p3u)
EXC( STORE t2, UNIT(-2)(dst), s_exc_p2u)
EXC( STORE t3, UNIT(-1)(dst), s_exc_p1u)
sltu t0, len, 256+1 # See if we can prefetch more
beqz t0, 2b
sltu t0, len, 128 # See if we can loop more time
beqz t0, 1b
nop
#
# Jump here if there are less than 16*NBYTES left.
#
cleanup_both_aligned:
beqz len, done
sltu t0, len, 8*NBYTES
bnez t0, less_than_8units
nop
EXC( LOAD t0, UNIT(0)(src), l_exc)
EXC( LOAD t1, UNIT(1)(src), l_exc_copy)
EXC( LOAD t2, UNIT(2)(src), l_exc_copy)
EXC( LOAD t3, UNIT(3)(src), l_exc_copy)
SUB len, len, 8*NBYTES
EXC( STORE t0, UNIT(0)(dst), s_exc_p8u)
EXC( STORE t1, UNIT(1)(dst), s_exc_p7u)
EXC( STORE t2, UNIT(2)(dst), s_exc_p6u)
EXC( STORE t3, UNIT(3)(dst), s_exc_p5u)
EXC( LOAD t0, UNIT(4)(src), l_exc_copy)
EXC( LOAD t1, UNIT(5)(src), l_exc_copy)
EXC( LOAD t2, UNIT(6)(src), l_exc_copy)
EXC( LOAD t3, UNIT(7)(src), l_exc_copy)
EXC( STORE t0, UNIT(4)(dst), s_exc_p4u)
EXC( STORE t1, UNIT(5)(dst), s_exc_p3u)
EXC( STORE t2, UNIT(6)(dst), s_exc_p2u)
EXC( STORE t3, UNIT(7)(dst), s_exc_p1u)
ADD src, src, 8*NBYTES
beqz len, done
ADD dst, dst, 8*NBYTES
#
# Jump here if there are less than 8*NBYTES left.
#
less_than_8units:
sltu t0, len, 4*NBYTES
bnez t0, less_than_4units
nop
EXC( LOAD t0, UNIT(0)(src), l_exc)
EXC( LOAD t1, UNIT(1)(src), l_exc_copy)
EXC( LOAD t2, UNIT(2)(src), l_exc_copy)
EXC( LOAD t3, UNIT(3)(src), l_exc_copy)
SUB len, len, 4*NBYTES
EXC( STORE t0, UNIT(0)(dst), s_exc_p4u)
EXC( STORE t1, UNIT(1)(dst), s_exc_p3u)
EXC( STORE t2, UNIT(2)(dst), s_exc_p2u)
EXC( STORE t3, UNIT(3)(dst), s_exc_p1u)
ADD src, src, 4*NBYTES
beqz len, done
ADD dst, dst, 4*NBYTES
#
# Jump here if there are less than 4*NBYTES left. This means
# we may need to copy up to 3 NBYTES words.
#
less_than_4units:
sltu t0, len, 1*NBYTES
bnez t0, copy_bytes_checklen
nop
#
# 1) Copy NBYTES, then check length again
#
EXC( LOAD t0, 0(src), l_exc)
SUB len, len, NBYTES
sltu t1, len, 8
EXC( STORE t0, 0(dst), s_exc_p1u)
ADD src, src, NBYTES
bnez t1, copy_bytes_checklen
ADD dst, dst, NBYTES
#
# 2) Copy NBYTES, then check length again
#
EXC( LOAD t0, 0(src), l_exc)
SUB len, len, NBYTES
sltu t1, len, 8
EXC( STORE t0, 0(dst), s_exc_p1u)
ADD src, src, NBYTES
bnez t1, copy_bytes_checklen
ADD dst, dst, NBYTES
#
# 3) Copy NBYTES, then check length again
#
EXC( LOAD t0, 0(src), l_exc)
SUB len, len, NBYTES
ADD src, src, NBYTES
ADD dst, dst, NBYTES
b copy_bytes_checklen
EXC( STORE t0, -8(dst), s_exc_p1u)
src_unaligned:
#define rem t8
SRL t0, len, LOG_NBYTES+2 # +2 for 4 units/iter
beqz t0, cleanup_src_unaligned
and rem, len, (4*NBYTES-1) # rem = len % 4*NBYTES
1:
/*
* Avoid consecutive LD*'s to the same register since some mips
* implementations can't issue them in the same cycle.
* It's OK to load FIRST(N+1) before REST(N) because the two addresses
* are to the same unit (unless src is aligned, but it's not).
*/
EXC( LDFIRST t0, FIRST(0)(src), l_exc)
EXC( LDFIRST t1, FIRST(1)(src), l_exc_copy)
SUB len, len, 4*NBYTES
EXC( LDREST t0, REST(0)(src), l_exc_copy)
EXC( LDREST t1, REST(1)(src), l_exc_copy)
EXC( LDFIRST t2, FIRST(2)(src), l_exc_copy)
EXC( LDFIRST t3, FIRST(3)(src), l_exc_copy)
EXC( LDREST t2, REST(2)(src), l_exc_copy)
EXC( LDREST t3, REST(3)(src), l_exc_copy)
ADD src, src, 4*NBYTES
EXC( STORE t0, UNIT(0)(dst), s_exc_p4u)
EXC( STORE t1, UNIT(1)(dst), s_exc_p3u)
EXC( STORE t2, UNIT(2)(dst), s_exc_p2u)
EXC( STORE t3, UNIT(3)(dst), s_exc_p1u)
bne len, rem, 1b
ADD dst, dst, 4*NBYTES
cleanup_src_unaligned:
beqz len, done
and rem, len, NBYTES-1 # rem = len % NBYTES
beq rem, len, copy_bytes
nop
1:
EXC( LDFIRST t0, FIRST(0)(src), l_exc)
EXC( LDREST t0, REST(0)(src), l_exc_copy)
SUB len, len, NBYTES
EXC( STORE t0, 0(dst), s_exc_p1u)
ADD src, src, NBYTES
bne len, rem, 1b
ADD dst, dst, NBYTES
copy_bytes_checklen:
beqz len, done
nop
copy_bytes:
/* 0 < len < NBYTES */
#define COPY_BYTE(N) \
EXC( lb t0, N(src), l_exc); \
SUB len, len, 1; \
beqz len, done; \
EXC( sb t0, N(dst), s_exc_p1)
COPY_BYTE(0)
COPY_BYTE(1)
#ifdef USE_DOUBLE
COPY_BYTE(2)
COPY_BYTE(3)
COPY_BYTE(4)
COPY_BYTE(5)
#endif
EXC( lb t0, NBYTES-2(src), l_exc)
SUB len, len, 1
jr ra
EXC( sb t0, NBYTES-2(dst), s_exc_p1)
done:
jr ra
nop
END(memcpy)
l_exc_copy:
/*
* Copy bytes from src until faulting load address (or until a
* lb faults)
*
* When reached by a faulting LDFIRST/LDREST, THREAD_BUADDR($28)
* may be more than a byte beyond the last address.
* Hence, the lb below may get an exception.
*
* Assumes src < THREAD_BUADDR($28)
*/
LOAD t0, TI_TASK($28)
LOAD t0, THREAD_BUADDR(t0)
1:
EXC( lb t1, 0(src), l_exc)
ADD src, src, 1
sb t1, 0(dst) # can't fault -- we're copy_from_user
bne src, t0, 1b
ADD dst, dst, 1
l_exc:
LOAD t0, TI_TASK($28)
LOAD t0, THREAD_BUADDR(t0) # t0 is just past last good address
SUB len, AT, t0 # len number of uncopied bytes
bnez t7, 2f /* Skip the zeroing out part if inatomic */
/*
* Here's where we rely on src and dst being incremented in tandem,
* See (3) above.
* dst += (fault addr - src) to put dst at first byte to clear
*/
ADD dst, t0 # compute start address in a1
SUB dst, src
/*
* Clear len bytes starting at dst. Can't call __bzero because it
* might modify len. An inefficient loop for these rare times...
*/
beqz len, done
SUB src, len, 1
1: sb zero, 0(dst)
ADD dst, dst, 1
bnez src, 1b
SUB src, src, 1
2: jr ra
nop
#define SEXC(n) \
s_exc_p ## n ## u: \
jr ra; \
ADD len, len, n*NBYTES
SEXC(16)
SEXC(15)
SEXC(14)
SEXC(13)
SEXC(12)
SEXC(11)
SEXC(10)
SEXC(9)
SEXC(8)
SEXC(7)
SEXC(6)
SEXC(5)
SEXC(4)
SEXC(3)
SEXC(2)
SEXC(1)
s_exc_p1:
jr ra
ADD len, len, 1
s_exc:
jr ra
nop
.align 5
LEAF(memmove)
ADD t0, a0, a2
ADD t1, a1, a2
sltu t0, a1, t0 # dst + len <= src -> memcpy
sltu t1, a0, t1 # dst >= src + len -> memcpy
and t0, t1
beqz t0, __memcpy
move v0, a0 /* return value */
beqz a2, r_out
END(memmove)
/* fall through to __rmemcpy */
LEAF(__rmemcpy) /* a0=dst a1=src a2=len */
sltu t0, a1, a0
beqz t0, r_end_bytes_up # src >= dst
nop
ADD a0, a2 # dst = dst + len
ADD a1, a2 # src = src + len
r_end_bytes:
lb t0, -1(a1)
SUB a2, a2, 0x1
sb t0, -1(a0)
SUB a1, a1, 0x1
bnez a2, r_end_bytes
SUB a0, a0, 0x1
r_out:
jr ra
move a2, zero
r_end_bytes_up:
lb t0, (a1)
SUB a2, a2, 0x1
sb t0, (a0)
ADD a1, a1, 0x1
bnez a2, r_end_bytes_up
ADD a0, a0, 0x1
jr ra
move a2, zero
END(__rmemcpy)