diff options
Diffstat (limited to 'arch/alpha/lib/ev6-clear_user.S')
| -rw-r--r-- | arch/alpha/lib/ev6-clear_user.S | 84 |
1 files changed, 35 insertions, 49 deletions
diff --git a/arch/alpha/lib/ev6-clear_user.S b/arch/alpha/lib/ev6-clear_user.S index 05bef6b50598..e179e4757ef8 100644 --- a/arch/alpha/lib/ev6-clear_user.S +++ b/arch/alpha/lib/ev6-clear_user.S @@ -9,21 +9,6 @@ * a successful copy). There is also some rather minor exception setup * stuff. * - * NOTE! This is not directly C-callable, because the calling semantics - * are different: - * - * Inputs: - * length in $0 - * destination address in $6 - * exception pointer in $7 - * return address in $28 (exceptions expect it there) - * - * Outputs: - * bytes left to copy in $0 - * - * Clobbers: - * $1,$2,$3,$4,$5,$6 - * * Much of the information about 21264 scheduling/coding comes from: * Compiler Writer's Guide for the Alpha 21264 * abbreviated as 'CWG' in other comments here @@ -56,14 +41,15 @@ .set noreorder .align 4 - .globl __do_clear_user - .ent __do_clear_user - .frame $30, 0, $28 + .globl __clear_user + .ent __clear_user + .frame $30, 0, $26 .prologue 0 # Pipeline info : Slotting & Comments -__do_clear_user: - and $6, 7, $4 # .. E .. .. : find dest head misalignment +__clear_user: + and $17, $17, $0 + and $16, 7, $4 # .. E .. .. : find dest head misalignment beq $0, $zerolength # U .. .. .. : U L U L addq $0, $4, $1 # .. .. .. E : bias counter @@ -75,14 +61,14 @@ __do_clear_user: /* * Head is not aligned. Write (8 - $4) bytes to head of destination - * This means $6 is known to be misaligned + * This means $16 is known to be misaligned */ - EX( ldq_u $5, 0($6) ) # .. .. .. L : load dst word to mask back in + EX( ldq_u $5, 0($16) ) # .. .. .. L : load dst word to mask back in beq $1, $onebyte # .. .. U .. : sub-word store? - mskql $5, $6, $5 # .. U .. .. : take care of misaligned head - addq $6, 8, $6 # E .. .. .. : L U U L + mskql $5, $16, $5 # .. U .. .. : take care of misaligned head + addq $16, 8, $16 # E .. .. .. : L U U L - EX( stq_u $5, -8($6) ) # .. .. .. L : + EX( stq_u $5, -8($16) ) # .. .. .. L : subq $1, 1, $1 # .. .. E .. : addq $0, $4, $0 # .. E .. .. : bytes left -= 8 - misalignment subq $0, 8, $0 # E .. .. .. : U L U L @@ -93,11 +79,11 @@ __do_clear_user: * values upon initial entry to the loop * $1 is number of quadwords to clear (zero is a valid value) * $2 is number of trailing bytes (0..7) ($2 never used...) - * $6 is known to be aligned 0mod8 + * $16 is known to be aligned 0mod8 */ $headalign: subq $1, 16, $4 # .. .. .. E : If < 16, we can not use the huge loop - and $6, 0x3f, $2 # .. .. E .. : Forward work for huge loop + and $16, 0x3f, $2 # .. .. E .. : Forward work for huge loop subq $2, 0x40, $3 # .. E .. .. : bias counter (huge loop) blt $4, $trailquad # U .. .. .. : U L U L @@ -114,21 +100,21 @@ $headalign: beq $3, $bigalign # U .. .. .. : U L U L : Aligned 0mod64 $alignmod64: - EX( stq_u $31, 0($6) ) # .. .. .. L + EX( stq_u $31, 0($16) ) # .. .. .. L addq $3, 8, $3 # .. .. E .. subq $0, 8, $0 # .. E .. .. nop # E .. .. .. : U L U L nop # .. .. .. E subq $1, 1, $1 # .. .. E .. - addq $6, 8, $6 # .. E .. .. + addq $16, 8, $16 # .. E .. .. blt $3, $alignmod64 # U .. .. .. : U L U L $bigalign: /* * $0 is the number of bytes left * $1 is the number of quads left - * $6 is aligned 0mod64 + * $16 is aligned 0mod64 * we know that we'll be taking a minimum of one trip through * CWG Section 3.7.6: do not expect a sustained store rate of > 1/cycle * We are _not_ going to update $0 after every single store. That @@ -145,39 +131,39 @@ $bigalign: nop # E : nop # E : nop # E : - bis $6,$6,$3 # E : U L U L : Initial wh64 address is dest + bis $16,$16,$3 # E : U L U L : Initial wh64 address is dest /* This might actually help for the current trip... */ $do_wh64: wh64 ($3) # .. .. .. L1 : memory subsystem hint subq $1, 16, $4 # .. .. E .. : Forward calculation - repeat the loop? - EX( stq_u $31, 0($6) ) # .. L .. .. + EX( stq_u $31, 0($16) ) # .. L .. .. subq $0, 8, $0 # E .. .. .. : U L U L - addq $6, 128, $3 # E : Target address of wh64 - EX( stq_u $31, 8($6) ) # L : - EX( stq_u $31, 16($6) ) # L : + addq $16, 128, $3 # E : Target address of wh64 + EX( stq_u $31, 8($16) ) # L : + EX( stq_u $31, 16($16) ) # L : subq $0, 16, $0 # E : U L L U nop # E : - EX( stq_u $31, 24($6) ) # L : - EX( stq_u $31, 32($6) ) # L : + EX( stq_u $31, 24($16) ) # L : + EX( stq_u $31, 32($16) ) # L : subq $0, 168, $5 # E : U L L U : two trips through the loop left? /* 168 = 192 - 24, since we've already completed some stores */ subq $0, 16, $0 # E : - EX( stq_u $31, 40($6) ) # L : - EX( stq_u $31, 48($6) ) # L : - cmovlt $5, $6, $3 # E : U L L U : Latency 2, extra mapping cycle + EX( stq_u $31, 40($16) ) # L : + EX( stq_u $31, 48($16) ) # L : + cmovlt $5, $16, $3 # E : U L L U : Latency 2, extra mapping cycle subq $1, 8, $1 # E : subq $0, 16, $0 # E : - EX( stq_u $31, 56($6) ) # L : + EX( stq_u $31, 56($16) ) # L : nop # E : U L U L nop # E : subq $0, 8, $0 # E : - addq $6, 64, $6 # E : + addq $16, 64, $16 # E : bge $4, $do_wh64 # U : U L U L $trailquad: @@ -190,14 +176,14 @@ $trailquad: beq $1, $trailbytes # U .. .. .. : U L U L : Only 0..7 bytes to go $onequad: - EX( stq_u $31, 0($6) ) # .. .. .. L + EX( stq_u $31, 0($16) ) # .. .. .. L subq $1, 1, $1 # .. .. E .. subq $0, 8, $0 # .. E .. .. nop # E .. .. .. : U L U L nop # .. .. .. E nop # .. .. E .. - addq $6, 8, $6 # .. E .. .. + addq $16, 8, $16 # .. E .. .. bgt $1, $onequad # U .. .. .. : U L U L # We have an unknown number of bytes left to go. @@ -211,9 +197,9 @@ $trailbytes: # so we will use $0 as the loop counter # We know for a fact that $0 > 0 zero due to previous context $onebyte: - EX( stb $31, 0($6) ) # .. .. .. L + EX( stb $31, 0($16) ) # .. .. .. L subq $0, 1, $0 # .. .. E .. : - addq $6, 1, $6 # .. E .. .. : + addq $16, 1, $16 # .. E .. .. : bgt $0, $onebyte # U .. .. .. : U L U L $zerolength: @@ -221,6 +207,6 @@ $exception: # Destination for exception recovery(?) nop # .. .. .. E : nop # .. .. E .. : nop # .. E .. .. : - ret $31, ($28), 1 # L0 .. .. .. : L U L U - .end __do_clear_user - EXPORT_SYMBOL(__do_clear_user) + ret $31, ($26), 1 # L0 .. .. .. : L U L U + .end __clear_user + EXPORT_SYMBOL(__clear_user) |