diff --git a/arch/xtensa/include/asm/asmmacro.h b/arch/xtensa/include/asm/asmmacro.h index 746dcc8b5abc..d2a4415a4c08 100644 --- a/arch/xtensa/include/asm/asmmacro.h +++ b/arch/xtensa/include/asm/asmmacro.h @@ -150,5 +150,12 @@ __endl \ar \as .endm +/* Load or store instructions that may cause exceptions use the EX macro. */ + +#define EX(handler) \ + .section __ex_table, "a"; \ + .word 97f, handler; \ + .previous \ +97: #endif /* _XTENSA_ASMMACRO_H */ diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 5a2110bb5902..a27a9a65635b 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -14,6 +14,7 @@ #include #include +#include #include #include #include @@ -1094,35 +1095,12 @@ ENDPROC(fast_syscall_unrecoverable) * < VALID_DOUBLE_EXCEPTION_ADDRESS: regular exception * * Note: we don't have to save a2; a2 holds the return value - * - * We use the two macros TRY and CATCH: - * - * TRY adds an entry to the __ex_table fixup table for the immediately - * following instruction. - * - * CATCH catches any exception that occurred at one of the preceding TRY - * statements and continues from there - * - * Usage TRY l32i a0, a1, 0 - * - * done: rfe - * CATCH - * j done */ .literal_position #ifdef CONFIG_FAST_SYSCALL_XTENSA -#define TRY \ - .section __ex_table, "a"; \ - .word 66f, 67f; \ - .text; \ -66: - -#define CATCH \ -67: - ENTRY(fast_syscall_xtensa) s32i a7, a2, PT_AREG7 # we need an additional register @@ -1136,9 +1114,9 @@ ENTRY(fast_syscall_xtensa) .Lswp: /* Atomic compare and swap */ -TRY l32i a0, a3, 0 # read old value +EX(.Leac) l32i a0, a3, 0 # read old value bne a0, a4, 1f # same as old value? jump -TRY s32i a5, a3, 0 # different, modify value +EX(.Leac) s32i a5, a3, 0 # different, modify value l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, 1 # and return 1 @@ -1151,12 +1129,12 @@ TRY s32i a5, a3, 0 # different, modify value .Lnswp: /* Atomic set, add, and exg_add. */ -TRY l32i a7, a3, 0 # orig +EX(.Leac) l32i a7, a3, 0 # orig addi a6, a6, -SYS_XTENSA_ATOMIC_SET add a0, a4, a7 # + arg moveqz a0, a4, a6 # set addi a6, a6, SYS_XTENSA_ATOMIC_SET -TRY s32i a0, a3, 0 # write new value +EX(.Leac) s32i a0, a3, 0 # write new value mov a0, a2 mov a2, a7 @@ -1164,7 +1142,6 @@ TRY s32i a0, a3, 0 # write new value l32i a0, a0, PT_AREG0 # restore a0 rfe -CATCH .Leac: l32i a7, a2, PT_AREG7 # restore a7 l32i a0, a2, PT_AREG0 # restore a0 movi a2, -EFAULT diff --git a/arch/xtensa/lib/checksum.S b/arch/xtensa/lib/checksum.S index 4eb573d2720e..528fe0dd9339 100644 --- a/arch/xtensa/lib/checksum.S +++ b/arch/xtensa/lib/checksum.S @@ -14,9 +14,10 @@ * 2 of the License, or (at your option) any later version. */ -#include +#include #include #include +#include /* * computes a partial checksum, e.g. for TCP/UDP fragments @@ -175,23 +176,8 @@ ENDPROC(csum_partial) /* * Copy from ds while checksumming, otherwise like csum_partial - * - * The macros SRC and DST specify the type of access for the instruction. - * thus we can call a custom exception handler for each access type. */ -#define SRC(y...) \ - 9999: y; \ - .section __ex_table, "a"; \ - .long 9999b, 6001f ; \ - .previous - -#define DST(y...) \ - 9999: y; \ - .section __ex_table, "a"; \ - .long 9999b, 6002f ; \ - .previous - /* unsigned int csum_partial_copy_generic (const char *src, char *dst, int len, int sum, int *src_err_ptr, int *dst_err_ptr) @@ -244,28 +230,28 @@ ENTRY(csum_partial_copy_generic) add a10, a10, a2 /* a10 = end of last 32-byte src chunk */ .Loop5: #endif -SRC( l32i a9, a2, 0 ) -SRC( l32i a8, a2, 4 ) -DST( s32i a9, a3, 0 ) -DST( s32i a8, a3, 4 ) +EX(10f) l32i a9, a2, 0 +EX(10f) l32i a8, a2, 4 +EX(11f) s32i a9, a3, 0 +EX(11f) s32i a8, a3, 4 ONES_ADD(a5, a9) ONES_ADD(a5, a8) -SRC( l32i a9, a2, 8 ) -SRC( l32i a8, a2, 12 ) -DST( s32i a9, a3, 8 ) -DST( s32i a8, a3, 12 ) +EX(10f) l32i a9, a2, 8 +EX(10f) l32i a8, a2, 12 +EX(11f) s32i a9, a3, 8 +EX(11f) s32i a8, a3, 12 ONES_ADD(a5, a9) ONES_ADD(a5, a8) -SRC( l32i a9, a2, 16 ) -SRC( l32i a8, a2, 20 ) -DST( s32i a9, a3, 16 ) -DST( s32i a8, a3, 20 ) +EX(10f) l32i a9, a2, 16 +EX(10f) l32i a8, a2, 20 +EX(11f) s32i a9, a3, 16 +EX(11f) s32i a8, a3, 20 ONES_ADD(a5, a9) ONES_ADD(a5, a8) -SRC( l32i a9, a2, 24 ) -SRC( l32i a8, a2, 28 ) -DST( s32i a9, a3, 24 ) -DST( s32i a8, a3, 28 ) +EX(10f) l32i a9, a2, 24 +EX(10f) l32i a8, a2, 28 +EX(11f) s32i a9, a3, 24 +EX(11f) s32i a8, a3, 28 ONES_ADD(a5, a9) ONES_ADD(a5, a8) addi a2, a2, 32 @@ -284,8 +270,8 @@ DST( s32i a8, a3, 28 ) add a10, a10, a2 /* a10 = end of last 4-byte src chunk */ .Loop6: #endif -SRC( l32i a9, a2, 0 ) -DST( s32i a9, a3, 0 ) +EX(10f) l32i a9, a2, 0 +EX(11f) s32i a9, a3, 0 ONES_ADD(a5, a9) addi a2, a2, 4 addi a3, a3, 4 @@ -315,8 +301,8 @@ DST( s32i a9, a3, 0 ) add a10, a10, a2 /* a10 = end of last 2-byte src chunk */ .Loop7: #endif -SRC( l16ui a9, a2, 0 ) -DST( s16i a9, a3, 0 ) +EX(10f) l16ui a9, a2, 0 +EX(11f) s16i a9, a3, 0 ONES_ADD(a5, a9) addi a2, a2, 2 addi a3, a3, 2 @@ -326,8 +312,8 @@ DST( s16i a9, a3, 0 ) 4: /* This section processes a possible trailing odd byte. */ _bbci.l a4, 0, 8f /* 1-byte chunk */ -SRC( l8ui a9, a2, 0 ) -DST( s8i a9, a3, 0 ) +EX(10f) l8ui a9, a2, 0 +EX(11f) s8i a9, a3, 0 #ifdef __XTENSA_EB__ slli a9, a9, 8 /* shift byte to bits 8..15 */ #endif @@ -350,10 +336,10 @@ DST( s8i a9, a3, 0 ) add a10, a10, a2 /* a10 = end of last odd-aligned, 2-byte src chunk */ .Loop8: #endif -SRC( l8ui a9, a2, 0 ) -SRC( l8ui a8, a2, 1 ) -DST( s8i a9, a3, 0 ) -DST( s8i a8, a3, 1 ) +EX(10f) l8ui a9, a2, 0 +EX(10f) l8ui a8, a2, 1 +EX(11f) s8i a9, a3, 0 +EX(11f) s8i a8, a3, 1 #ifdef __XTENSA_EB__ slli a9, a9, 8 /* combine into a single 16-bit value */ #else /* for checksum computation */ @@ -381,7 +367,7 @@ ENDPROC(csum_partial_copy_generic) a12 = original dst for exception handling */ -6001: +10: _movi a2, -EFAULT s32i a2, a6, 0 /* src_err_ptr */ @@ -403,7 +389,7 @@ ENDPROC(csum_partial_copy_generic) 2: retw -6002: +11: movi a2, -EFAULT s32i a2, a7, 0 /* dst_err_ptr */ movi a2, 0 diff --git a/arch/xtensa/lib/memset.S b/arch/xtensa/lib/memset.S index 10b8c400f175..7a724edaf4f1 100644 --- a/arch/xtensa/lib/memset.S +++ b/arch/xtensa/lib/memset.S @@ -12,6 +12,7 @@ */ #include +#include /* * void *memset(void *dst, int c, size_t length) @@ -28,15 +29,6 @@ * the alignment labels). */ -/* Load or store instructions that may cause exceptions use the EX macro. */ - -#define EX(insn,reg1,reg2,offset,handler) \ -9: insn reg1, reg2, offset; \ - .section __ex_table, "a"; \ - .word 9b, handler; \ - .previous - - .text .align 4 .global memset @@ -73,10 +65,10 @@ memset: add a6, a6, a5 # a6 = end of last 16B chunk #endif /* !XCHAL_HAVE_LOOPS */ .Loop1: - EX(s32i, a3, a5, 0, memset_fixup) - EX(s32i, a3, a5, 4, memset_fixup) - EX(s32i, a3, a5, 8, memset_fixup) - EX(s32i, a3, a5, 12, memset_fixup) +EX(10f) s32i a3, a5, 0 +EX(10f) s32i a3, a5, 4 +EX(10f) s32i a3, a5, 8 +EX(10f) s32i a3, a5, 12 addi a5, a5, 16 #if !XCHAL_HAVE_LOOPS blt a5, a6, .Loop1 @@ -84,23 +76,23 @@ memset: .Loop1done: bbci.l a4, 3, .L2 # set 8 bytes - EX(s32i, a3, a5, 0, memset_fixup) - EX(s32i, a3, a5, 4, memset_fixup) +EX(10f) s32i a3, a5, 0 +EX(10f) s32i a3, a5, 4 addi a5, a5, 8 .L2: bbci.l a4, 2, .L3 # set 4 bytes - EX(s32i, a3, a5, 0, memset_fixup) +EX(10f) s32i a3, a5, 0 addi a5, a5, 4 .L3: bbci.l a4, 1, .L4 # set 2 bytes - EX(s16i, a3, a5, 0, memset_fixup) +EX(10f) s16i a3, a5, 0 addi a5, a5, 2 .L4: bbci.l a4, 0, .L5 # set 1 byte - EX(s8i, a3, a5, 0, memset_fixup) +EX(10f) s8i a3, a5, 0 .L5: .Lret1: retw @@ -114,7 +106,7 @@ memset: bbci.l a5, 0, .L20 # branch if dst alignment half-aligned # dst is only byte aligned # set 1 byte - EX(s8i, a3, a5, 0, memset_fixup) +EX(10f) s8i a3, a5, 0 addi a5, a5, 1 addi a4, a4, -1 # now retest if dst aligned @@ -122,7 +114,7 @@ memset: .L20: # dst half-aligned # set 2 bytes - EX(s16i, a3, a5, 0, memset_fixup) +EX(10f) s16i a3, a5, 0 addi a5, a5, 2 addi a4, a4, -2 j .L0 # dst is now aligned, return to main algorithm @@ -141,7 +133,7 @@ memset: add a6, a5, a4 # a6 = ending address #endif /* !XCHAL_HAVE_LOOPS */ .Lbyteloop: - EX(s8i, a3, a5, 0, memset_fixup) +EX(10f) s8i a3, a5, 0 addi a5, a5, 1 #if !XCHAL_HAVE_LOOPS blt a5, a6, .Lbyteloop @@ -155,6 +147,6 @@ memset: /* We return zero if a failure occurred. */ -memset_fixup: +10: movi a2, 0 retw diff --git a/arch/xtensa/lib/strncpy_user.S b/arch/xtensa/lib/strncpy_user.S index 1ad0ecf45368..827e1b393f3f 100644 --- a/arch/xtensa/lib/strncpy_user.S +++ b/arch/xtensa/lib/strncpy_user.S @@ -11,16 +11,9 @@ * Copyright (C) 2002 Tensilica Inc. */ -#include #include - -/* Load or store instructions that may cause exceptions use the EX macro. */ - -#define EX(insn,reg1,reg2,offset,handler) \ -9: insn reg1, reg2, offset; \ - .section __ex_table, "a"; \ - .word 9b, handler; \ - .previous +#include +#include /* * char *__strncpy_user(char *dst, const char *src, size_t len) @@ -75,9 +68,9 @@ __strncpy_user: j .Ldstunaligned .Lsrc1mod2: # src address is odd - EX(l8ui, a9, a3, 0, fixup_l) # get byte 0 +EX(11f) l8ui a9, a3, 0 # get byte 0 addi a3, a3, 1 # advance src pointer - EX(s8i, a9, a11, 0, fixup_s) # store byte 0 +EX(10f) s8i a9, a11, 0 # store byte 0 beqz a9, .Lret # if byte 0 is zero addi a11, a11, 1 # advance dst pointer addi a4, a4, -1 # decrement len @@ -85,16 +78,16 @@ __strncpy_user: bbci.l a3, 1, .Lsrcaligned # if src is now word-aligned .Lsrc2mod4: # src address is 2 mod 4 - EX(l8ui, a9, a3, 0, fixup_l) # get byte 0 +EX(11f) l8ui a9, a3, 0 # get byte 0 /* 1-cycle interlock */ - EX(s8i, a9, a11, 0, fixup_s) # store byte 0 +EX(10f) s8i a9, a11, 0 # store byte 0 beqz a9, .Lret # if byte 0 is zero addi a11, a11, 1 # advance dst pointer addi a4, a4, -1 # decrement len beqz a4, .Lret # if len is zero - EX(l8ui, a9, a3, 1, fixup_l) # get byte 0 +EX(11f) l8ui a9, a3, 1 # get byte 0 addi a3, a3, 2 # advance src pointer - EX(s8i, a9, a11, 0, fixup_s) # store byte 0 +EX(10f) s8i a9, a11, 0 # store byte 0 beqz a9, .Lret # if byte 0 is zero addi a11, a11, 1 # advance dst pointer addi a4, a4, -1 # decrement len @@ -117,12 +110,12 @@ __strncpy_user: add a12, a12, a11 # a12 = end of last 4B chunck #endif .Loop1: - EX(l32i, a9, a3, 0, fixup_l) # get word from src +EX(11f) l32i a9, a3, 0 # get word from src addi a3, a3, 4 # advance src pointer bnone a9, a5, .Lz0 # if byte 0 is zero bnone a9, a6, .Lz1 # if byte 1 is zero bnone a9, a7, .Lz2 # if byte 2 is zero - EX(s32i, a9, a11, 0, fixup_s) # store word to dst +EX(10f) s32i a9, a11, 0 # store word to dst bnone a9, a8, .Lz3 # if byte 3 is zero addi a11, a11, 4 # advance dst pointer #if !XCHAL_HAVE_LOOPS @@ -132,7 +125,7 @@ __strncpy_user: .Loop1done: bbci.l a4, 1, .L100 # copy 2 bytes - EX(l16ui, a9, a3, 0, fixup_l) +EX(11f) l16ui a9, a3, 0 addi a3, a3, 2 # advance src pointer #ifdef __XTENSA_EB__ bnone a9, a7, .Lz0 # if byte 2 is zero @@ -141,13 +134,13 @@ __strncpy_user: bnone a9, a5, .Lz0 # if byte 0 is zero bnone a9, a6, .Lz1 # if byte 1 is zero #endif - EX(s16i, a9, a11, 0, fixup_s) +EX(10f) s16i a9, a11, 0 addi a11, a11, 2 # advance dst pointer .L100: bbci.l a4, 0, .Lret - EX(l8ui, a9, a3, 0, fixup_l) +EX(11f) l8ui a9, a3, 0 /* slot */ - EX(s8i, a9, a11, 0, fixup_s) +EX(10f) s8i a9, a11, 0 beqz a9, .Lret # if byte is zero addi a11, a11, 1-3 # advance dst ptr 1, but also cancel # the effect of adding 3 in .Lz3 code @@ -161,14 +154,14 @@ __strncpy_user: #ifdef __XTENSA_EB__ movi a9, 0 #endif /* __XTENSA_EB__ */ - EX(s8i, a9, a11, 0, fixup_s) +EX(10f) s8i a9, a11, 0 sub a2, a11, a2 # compute strlen retw .Lz1: # byte 1 is zero #ifdef __XTENSA_EB__ extui a9, a9, 16, 16 #endif /* __XTENSA_EB__ */ - EX(s16i, a9, a11, 0, fixup_s) +EX(10f) s16i a9, a11, 0 addi a11, a11, 1 # advance dst pointer sub a2, a11, a2 # compute strlen retw @@ -176,9 +169,9 @@ __strncpy_user: #ifdef __XTENSA_EB__ extui a9, a9, 16, 16 #endif /* __XTENSA_EB__ */ - EX(s16i, a9, a11, 0, fixup_s) +EX(10f) s16i a9, a11, 0 movi a9, 0 - EX(s8i, a9, a11, 2, fixup_s) +EX(10f) s8i a9, a11, 2 addi a11, a11, 2 # advance dst pointer sub a2, a11, a2 # compute strlen retw @@ -196,9 +189,9 @@ __strncpy_user: add a12, a11, a4 # a12 = ending address #endif /* XCHAL_HAVE_LOOPS */ .Lnextbyte: - EX(l8ui, a9, a3, 0, fixup_l) +EX(11f) l8ui a9, a3, 0 addi a3, a3, 1 - EX(s8i, a9, a11, 0, fixup_s) +EX(10f) s8i a9, a11, 0 beqz a9, .Lunalignedend addi a11, a11, 1 #if !XCHAL_HAVE_LOOPS @@ -218,8 +211,7 @@ __strncpy_user: * implementation in memset(). Thus, we differentiate between * load/store fixups. */ -fixup_s: -fixup_l: +10: +11: movi a2, -EFAULT retw - diff --git a/arch/xtensa/lib/strnlen_user.S b/arch/xtensa/lib/strnlen_user.S index 4c03b1e581e9..9404ac46ce4c 100644 --- a/arch/xtensa/lib/strnlen_user.S +++ b/arch/xtensa/lib/strnlen_user.S @@ -12,14 +12,7 @@ */ #include - -/* Load or store instructions that may cause exceptions use the EX macro. */ - -#define EX(insn,reg1,reg2,offset,handler) \ -9: insn reg1, reg2, offset; \ - .section __ex_table, "a"; \ - .word 9b, handler; \ - .previous +#include /* * size_t __strnlen_user(const char *s, size_t len) @@ -77,7 +70,7 @@ __strnlen_user: add a10, a10, a4 # a10 = end of last 4B chunk #endif /* XCHAL_HAVE_LOOPS */ .Loop: - EX(l32i, a9, a4, 4, lenfixup) # get next word of string +EX(10f) l32i a9, a4, 4 # get next word of string addi a4, a4, 4 # advance string pointer bnone a9, a5, .Lz0 # if byte 0 is zero bnone a9, a6, .Lz1 # if byte 1 is zero @@ -88,7 +81,7 @@ __strnlen_user: #endif .Ldone: - EX(l32i, a9, a4, 4, lenfixup) # load 4 bytes for remaining checks +EX(10f) l32i a9, a4, 4 # load 4 bytes for remaining checks bbci.l a3, 1, .L100 # check two more bytes (bytes 0, 1 of word) @@ -125,14 +118,14 @@ __strnlen_user: retw .L1mod2: # address is odd - EX(l8ui, a9, a4, 4, lenfixup) # get byte 0 +EX(10f) l8ui a9, a4, 4 # get byte 0 addi a4, a4, 1 # advance string pointer beqz a9, .Lz3 # if byte 0 is zero bbci.l a4, 1, .Laligned # if string pointer is now word-aligned .L2mod4: # address is 2 mod 4 addi a4, a4, 2 # advance ptr for aligned access - EX(l32i, a9, a4, 0, lenfixup) # get word with first two bytes of string +EX(10f) l32i a9, a4, 0 # get word with first two bytes of string bnone a9, a7, .Lz2 # if byte 2 (of word, not string) is zero bany a9, a8, .Laligned # if byte 3 (of word, not string) is nonzero # byte 3 is zero @@ -142,6 +135,6 @@ __strnlen_user: .section .fixup, "ax" .align 4 -lenfixup: +10: movi a2, 0 retw diff --git a/arch/xtensa/lib/usercopy.S b/arch/xtensa/lib/usercopy.S index d9cd766bde3e..4172b73b0364 100644 --- a/arch/xtensa/lib/usercopy.S +++ b/arch/xtensa/lib/usercopy.S @@ -54,6 +54,7 @@ */ #include +#include #ifdef __XTENSA_EB__ #define ALIGN(R, W0, W1) src R, W0, W1 @@ -63,15 +64,6 @@ #define SSA8(R) ssa8l R #endif -/* Load or store instructions that may cause exceptions use the EX macro. */ - -#define EX(insn,reg1,reg2,offset,handler) \ -9: insn reg1, reg2, offset; \ - .section __ex_table, "a"; \ - .word 9b, handler; \ - .previous - - .text .align 4 .global __xtensa_copy_user @@ -102,9 +94,9 @@ __xtensa_copy_user: bltui a4, 7, .Lbytecopy # do short copies byte by byte # copy 1 byte - EX(l8ui, a6, a3, 0, fixup) +EX(10f) l8ui a6, a3, 0 addi a3, a3, 1 - EX(s8i, a6, a5, 0, fixup) +EX(10f) s8i a6, a5, 0 addi a5, a5, 1 addi a4, a4, -1 bbci.l a5, 1, .Ldstaligned # if dst is now aligned, then @@ -112,11 +104,11 @@ __xtensa_copy_user: .Ldst2mod4: # dst 16-bit aligned # copy 2 bytes bltui a4, 6, .Lbytecopy # do short copies byte by byte - EX(l8ui, a6, a3, 0, fixup) - EX(l8ui, a7, a3, 1, fixup) +EX(10f) l8ui a6, a3, 0 +EX(10f) l8ui a7, a3, 1 addi a3, a3, 2 - EX(s8i, a6, a5, 0, fixup) - EX(s8i, a7, a5, 1, fixup) +EX(10f) s8i a6, a5, 0 +EX(10f) s8i a7, a5, 1 addi a5, a5, 2 addi a4, a4, -2 j .Ldstaligned # dst is now aligned, return to main algorithm @@ -135,9 +127,9 @@ __xtensa_copy_user: add a7, a3, a4 # a7 = end address for source #endif /* !XCHAL_HAVE_LOOPS */ .Lnextbyte: - EX(l8ui, a6, a3, 0, fixup) +EX(10f) l8ui a6, a3, 0 addi a3, a3, 1 - EX(s8i, a6, a5, 0, fixup) +EX(10f) s8i a6, a5, 0 addi a5, a5, 1 #if !XCHAL_HAVE_LOOPS blt a3, a7, .Lnextbyte @@ -161,15 +153,15 @@ __xtensa_copy_user: add a8, a8, a3 # a8 = end of last 16B source chunk #endif /* !XCHAL_HAVE_LOOPS */ .Loop1: - EX(l32i, a6, a3, 0, fixup) - EX(l32i, a7, a3, 4, fixup) - EX(s32i, a6, a5, 0, fixup) - EX(l32i, a6, a3, 8, fixup) - EX(s32i, a7, a5, 4, fixup) - EX(l32i, a7, a3, 12, fixup) - EX(s32i, a6, a5, 8, fixup) +EX(10f) l32i a6, a3, 0 +EX(10f) l32i a7, a3, 4 +EX(10f) s32i a6, a5, 0 +EX(10f) l32i a6, a3, 8 +EX(10f) s32i a7, a5, 4 +EX(10f) l32i a7, a3, 12 +EX(10f) s32i a6, a5, 8 addi a3, a3, 16 - EX(s32i, a7, a5, 12, fixup) +EX(10f) s32i a7, a5, 12 addi a5, a5, 16 #if !XCHAL_HAVE_LOOPS blt a3, a8, .Loop1 @@ -177,31 +169,31 @@ __xtensa_copy_user: .Loop1done: bbci.l a4, 3, .L2 # copy 8 bytes - EX(l32i, a6, a3, 0, fixup) - EX(l32i, a7, a3, 4, fixup) +EX(10f) l32i a6, a3, 0 +EX(10f) l32i a7, a3, 4 addi a3, a3, 8 - EX(s32i, a6, a5, 0, fixup) - EX(s32i, a7, a5, 4, fixup) +EX(10f) s32i a6, a5, 0 +EX(10f) s32i a7, a5, 4 addi a5, a5, 8 .L2: bbci.l a4, 2, .L3 # copy 4 bytes - EX(l32i, a6, a3, 0, fixup) +EX(10f) l32i a6, a3, 0 addi a3, a3, 4 - EX(s32i, a6, a5, 0, fixup) +EX(10f) s32i a6, a5, 0 addi a5, a5, 4 .L3: bbci.l a4, 1, .L4 # copy 2 bytes - EX(l16ui, a6, a3, 0, fixup) +EX(10f) l16ui a6, a3, 0 addi a3, a3, 2 - EX(s16i, a6, a5, 0, fixup) +EX(10f) s16i a6, a5, 0 addi a5, a5, 2 .L4: bbci.l a4, 0, .L5 # copy 1 byte - EX(l8ui, a6, a3, 0, fixup) - EX(s8i, a6, a5, 0, fixup) +EX(10f) l8ui a6, a3, 0 +EX(10f) s8i a6, a5, 0 .L5: movi a2, 0 # return success for len bytes copied retw @@ -217,7 +209,7 @@ __xtensa_copy_user: # copy 16 bytes per iteration for word-aligned dst and unaligned src and a10, a3, a8 # save unalignment offset for below sub a3, a3, a10 # align a3 (to avoid sim warnings only; not needed for hardware) - EX(l32i, a6, a3, 0, fixup) # load first word +EX(10f) l32i a6, a3, 0 # load first word #if XCHAL_HAVE_LOOPS loopnez a7, .Loop2done #else /* !XCHAL_HAVE_LOOPS */ @@ -226,19 +218,19 @@ __xtensa_copy_user: add a12, a12, a3 # a12 = end of last 16B source chunk #endif /* !XCHAL_HAVE_LOOPS */ .Loop2: - EX(l32i, a7, a3, 4, fixup) - EX(l32i, a8, a3, 8, fixup) +EX(10f) l32i a7, a3, 4 +EX(10f) l32i a8, a3, 8 ALIGN( a6, a6, a7) - EX(s32i, a6, a5, 0, fixup) - EX(l32i, a9, a3, 12, fixup) +EX(10f) s32i a6, a5, 0 +EX(10f) l32i a9, a3, 12 ALIGN( a7, a7, a8) - EX(s32i, a7, a5, 4, fixup) - EX(l32i, a6, a3, 16, fixup) +EX(10f) s32i a7, a5, 4 +EX(10f) l32i a6, a3, 16 ALIGN( a8, a8, a9) - EX(s32i, a8, a5, 8, fixup) +EX(10f) s32i a8, a5, 8 addi a3, a3, 16 ALIGN( a9, a9, a6) - EX(s32i, a9, a5, 12, fixup) +EX(10f) s32i a9, a5, 12 addi a5, a5, 16 #if !XCHAL_HAVE_LOOPS blt a3, a12, .Loop2 @@ -246,39 +238,39 @@ __xtensa_copy_user: .Loop2done: bbci.l a4, 3, .L12 # copy 8 bytes - EX(l32i, a7, a3, 4, fixup) - EX(l32i, a8, a3, 8, fixup) +EX(10f) l32i a7, a3, 4 +EX(10f) l32i a8, a3, 8 ALIGN( a6, a6, a7) - EX(s32i, a6, a5, 0, fixup) +EX(10f) s32i a6, a5, 0 addi a3, a3, 8 ALIGN( a7, a7, a8) - EX(s32i, a7, a5, 4, fixup) +EX(10f) s32i a7, a5, 4 addi a5, a5, 8 mov a6, a8 .L12: bbci.l a4, 2, .L13 # copy 4 bytes - EX(l32i, a7, a3, 4, fixup) +EX(10f) l32i a7, a3, 4 addi a3, a3, 4 ALIGN( a6, a6, a7) - EX(s32i, a6, a5, 0, fixup) +EX(10f) s32i a6, a5, 0 addi a5, a5, 4 mov a6, a7 .L13: add a3, a3, a10 # readjust a3 with correct misalignment bbci.l a4, 1, .L14 # copy 2 bytes - EX(l8ui, a6, a3, 0, fixup) - EX(l8ui, a7, a3, 1, fixup) +EX(10f) l8ui a6, a3, 0 +EX(10f) l8ui a7, a3, 1 addi a3, a3, 2 - EX(s8i, a6, a5, 0, fixup) - EX(s8i, a7, a5, 1, fixup) +EX(10f) s8i a6, a5, 0 +EX(10f) s8i a7, a5, 1 addi a5, a5, 2 .L14: bbci.l a4, 0, .L15 # copy 1 byte - EX(l8ui, a6, a3, 0, fixup) - EX(s8i, a6, a5, 0, fixup) +EX(10f) l8ui a6, a3, 0 +EX(10f) s8i a6, a5, 0 .L15: movi a2, 0 # return success for len bytes copied retw @@ -294,7 +286,7 @@ __xtensa_copy_user: */ -fixup: +10: sub a2, a5, a2 /* a2 <-- bytes copied */ sub a2, a11, a2 /* a2 <-- bytes not copied */ retw