linux-sg2042/arch/alpha/lib/ev6-stxncpy.S

398 lines
11 KiB
ArmAsm

/*
* arch/alpha/lib/ev6-stxncpy.S
* 21264 version contributed by Rick Gorton <rick.gorton@api-networks.com>
*
* Copy no more than COUNT bytes of the null-terminated string from
* SRC to DST.
*
* This is an internal routine used by strncpy, stpncpy, and strncat.
* As such, it uses special linkage conventions to make implementation
* of these public functions more efficient.
*
* On input:
* t9 = return address
* a0 = DST
* a1 = SRC
* a2 = COUNT
*
* Furthermore, COUNT may not be zero.
*
* On output:
* t0 = last word written
* t10 = bitmask (with one bit set) indicating the byte position of
* the end of the range specified by COUNT
* t12 = bitmask (with one bit set) indicating the last byte written
* a0 = unaligned address of the last *word* written
* a2 = the number of full words left in COUNT
*
* Furthermore, v0, a3-a5, t11, and $at are untouched.
*
* 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
* ftp.digital.com/pub/Digital/info/semiconductor/literature/dsc-library.html
* Scheduling notation:
* E - either cluster
* U - upper subcluster; U0 - subcluster U0; U1 - subcluster U1
* L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
* Try not to change the actual algorithm if possible for consistency.
*/
#include <asm/regdef.h>
.set noat
.set noreorder
.text
/* There is a problem with either gdb (as of 4.16) or gas (as of 2.7) that
doesn't like putting the entry point for a procedure somewhere in the
middle of the procedure descriptor. Work around this by putting the
aligned copy in its own procedure descriptor */
.ent stxncpy_aligned
.align 4
stxncpy_aligned:
.frame sp, 0, t9, 0
.prologue 0
/* On entry to this basic block:
t0 == the first destination word for masking back in
t1 == the first source word. */
/* Create the 1st output word and detect 0's in the 1st input word. */
lda t2, -1 # E : build a mask against false zero
mskqh t2, a1, t2 # U : detection in the src word (stall)
mskqh t1, a1, t3 # U :
ornot t1, t2, t2 # E : (stall)
mskql t0, a1, t0 # U : assemble the first output word
cmpbge zero, t2, t8 # E : bits set iff null found
or t0, t3, t0 # E : (stall)
beq a2, $a_eoc # U :
bne t8, $a_eos # U :
nop
nop
nop
/* On entry to this basic block:
t0 == a source word not containing a null. */
/*
* nops here to:
* separate store quads from load quads
* limit of 1 bcond/quad to permit training
*/
$a_loop:
stq_u t0, 0(a0) # L :
addq a0, 8, a0 # E :
subq a2, 1, a2 # E :
nop
ldq_u t0, 0(a1) # L :
addq a1, 8, a1 # E :
cmpbge zero, t0, t8 # E :
beq a2, $a_eoc # U :
beq t8, $a_loop # U :
nop
nop
nop
/* Take care of the final (partial) word store. At this point
the end-of-count bit is set in t8 iff it applies.
On entry to this basic block we have:
t0 == the source word containing the null
t8 == the cmpbge mask that found it. */
$a_eos:
negq t8, t12 # E : find low bit set
and t8, t12, t12 # E : (stall)
/* For the sake of the cache, don't read a destination word
if we're not going to need it. */
and t12, 0x80, t6 # E : (stall)
bne t6, 1f # U : (stall)
/* We're doing a partial word store and so need to combine
our source and original destination words. */
ldq_u t1, 0(a0) # L :
subq t12, 1, t6 # E :
or t12, t6, t8 # E : (stall)
zapnot t0, t8, t0 # U : clear src bytes > null (stall)
zap t1, t8, t1 # .. e1 : clear dst bytes <= null
or t0, t1, t0 # e1 : (stall)
nop
nop
1: stq_u t0, 0(a0) # L :
ret (t9) # L0 : Latency=3
nop
nop
/* Add the end-of-count bit to the eos detection bitmask. */
$a_eoc:
or t10, t8, t8 # E :
br $a_eos # L0 : Latency=3
nop
nop
.end stxncpy_aligned
.align 4
.ent __stxncpy
.globl __stxncpy
__stxncpy:
.frame sp, 0, t9, 0
.prologue 0
/* Are source and destination co-aligned? */
xor a0, a1, t1 # E :
and a0, 7, t0 # E : find dest misalignment
and t1, 7, t1 # E : (stall)
addq a2, t0, a2 # E : bias count by dest misalignment (stall)
subq a2, 1, a2 # E :
and a2, 7, t2 # E : (stall)
srl a2, 3, a2 # U : a2 = loop counter = (count - 1)/8 (stall)
addq zero, 1, t10 # E :
sll t10, t2, t10 # U : t10 = bitmask of last count byte
bne t1, $unaligned # U :
/* We are co-aligned; take care of a partial first word. */
ldq_u t1, 0(a1) # L : load first src word
addq a1, 8, a1 # E :
beq t0, stxncpy_aligned # U : avoid loading dest word if not needed
ldq_u t0, 0(a0) # L :
nop
nop
br stxncpy_aligned # .. e1 :
nop
nop
nop
/* The source and destination are not co-aligned. Align the destination
and cope. We have to be very careful about not reading too much and
causing a SEGV. */
.align 4
$u_head:
/* We know just enough now to be able to assemble the first
full source word. We can still find a zero at the end of it
that prevents us from outputting the whole thing.
On entry to this basic block:
t0 == the first dest word, unmasked
t1 == the shifted low bits of the first source word
t6 == bytemask that is -1 in dest word bytes */
ldq_u t2, 8(a1) # L : Latency=3 load second src word
addq a1, 8, a1 # E :
mskql t0, a0, t0 # U : mask trailing garbage in dst
extqh t2, a1, t4 # U : (3 cycle stall on t2)
or t1, t4, t1 # E : first aligned src word complete (stall)
mskqh t1, a0, t1 # U : mask leading garbage in src (stall)
or t0, t1, t0 # E : first output word complete (stall)
or t0, t6, t6 # E : mask original data for zero test (stall)
cmpbge zero, t6, t8 # E :
beq a2, $u_eocfin # U :
lda t6, -1 # E :
nop
bne t8, $u_final # U :
mskql t6, a1, t6 # U : mask out bits already seen
stq_u t0, 0(a0) # L : store first output word
or t6, t2, t2 # E : (stall)
cmpbge zero, t2, t8 # E : find nulls in second partial
addq a0, 8, a0 # E :
subq a2, 1, a2 # E :
bne t8, $u_late_head_exit # U :
/* Finally, we've got all the stupid leading edge cases taken care
of and we can set up to enter the main loop. */
extql t2, a1, t1 # U : position hi-bits of lo word
beq a2, $u_eoc # U :
ldq_u t2, 8(a1) # L : read next high-order source word
addq a1, 8, a1 # E :
extqh t2, a1, t0 # U : position lo-bits of hi word (stall)
cmpbge zero, t2, t8 # E :
nop
bne t8, $u_eos # U :
/* Unaligned copy main loop. In order to avoid reading too much,
the loop is structured to detect zeros in aligned source words.
This has, unfortunately, effectively pulled half of a loop
iteration out into the head and half into the tail, but it does
prevent nastiness from accumulating in the very thing we want
to run as fast as possible.
On entry to this basic block:
t0 == the shifted low-order bits from the current source word
t1 == the shifted high-order bits from the previous source word
t2 == the unshifted current source word
We further know that t2 does not contain a null terminator. */
.align 4
$u_loop:
or t0, t1, t0 # E : current dst word now complete
subq a2, 1, a2 # E : decrement word count
extql t2, a1, t1 # U : extract low bits for next time
addq a0, 8, a0 # E :
stq_u t0, -8(a0) # U : save the current word
beq a2, $u_eoc # U :
ldq_u t2, 8(a1) # U : Latency=3 load high word for next time
addq a1, 8, a1 # E :
extqh t2, a1, t0 # U : extract low bits (2 cycle stall)
cmpbge zero, t2, t8 # E : test new word for eos
nop
beq t8, $u_loop # U :
/* We've found a zero somewhere in the source word we just read.
If it resides in the lower half, we have one (probably partial)
word to write out, and if it resides in the upper half, we
have one full and one partial word left to write out.
On entry to this basic block:
t0 == the shifted low-order bits from the current source word
t1 == the shifted high-order bits from the previous source word
t2 == the unshifted current source word. */
$u_eos:
or t0, t1, t0 # E : first (partial) source word complete
nop
cmpbge zero, t0, t8 # E : is the null in this first bit? (stall)
bne t8, $u_final # U : (stall)
stq_u t0, 0(a0) # L : the null was in the high-order bits
addq a0, 8, a0 # E :
subq a2, 1, a2 # E :
nop
$u_late_head_exit:
extql t2, a1, t0 # U :
cmpbge zero, t0, t8 # E :
or t8, t10, t6 # E : (stall)
cmoveq a2, t6, t8 # E : Latency=2, extra map slot (stall)
/* Take care of a final (probably partial) result word.
On entry to this basic block:
t0 == assembled source word
t8 == cmpbge mask that found the null. */
$u_final:
negq t8, t6 # E : isolate low bit set
and t6, t8, t12 # E : (stall)
and t12, 0x80, t6 # E : avoid dest word load if we can (stall)
bne t6, 1f # U : (stall)
ldq_u t1, 0(a0) # L :
subq t12, 1, t6 # E :
or t6, t12, t8 # E : (stall)
zapnot t0, t8, t0 # U : kill source bytes > null
zap t1, t8, t1 # U : kill dest bytes <= null
or t0, t1, t0 # E : (stall)
nop
nop
1: stq_u t0, 0(a0) # L :
ret (t9) # L0 : Latency=3
/* Got to end-of-count before end of string.
On entry to this basic block:
t1 == the shifted high-order bits from the previous source word */
$u_eoc:
and a1, 7, t6 # E : avoid final load if possible
sll t10, t6, t6 # U : (stall)
and t6, 0xff, t6 # E : (stall)
bne t6, 1f # U : (stall)
ldq_u t2, 8(a1) # L : load final src word
nop
extqh t2, a1, t0 # U : extract low bits for last word (stall)
or t1, t0, t1 # E : (stall)
1: cmpbge zero, t1, t8 # E :
mov t1, t0 # E :
$u_eocfin: # end-of-count, final word
or t10, t8, t8 # E :
br $u_final # L0 : Latency=3
/* Unaligned copy entry point. */
.align 4
$unaligned:
ldq_u t1, 0(a1) # L : load first source word
and a0, 7, t4 # E : find dest misalignment
and a1, 7, t5 # E : find src misalignment
/* Conditionally load the first destination word and a bytemask
with 0xff indicating that the destination byte is sacrosanct. */
mov zero, t0 # E :
mov zero, t6 # E :
beq t4, 1f # U :
ldq_u t0, 0(a0) # L :
lda t6, -1 # E :
mskql t6, a0, t6 # U :
nop
nop
subq a1, t4, a1 # E : sub dest misalignment from src addr
/* If source misalignment is larger than dest misalignment, we need
extra startup checks to avoid SEGV. */
1: cmplt t4, t5, t12 # E :
extql t1, a1, t1 # U : shift src into place
lda t2, -1 # E : for creating masks later
beq t12, $u_head # U : (stall)
extql t2, a1, t2 # U :
cmpbge zero, t1, t8 # E : is there a zero?
andnot t2, t6, t12 # E : dest mask for a single word copy
or t8, t10, t5 # E : test for end-of-count too
cmpbge zero, t12, t3 # E :
cmoveq a2, t5, t8 # E : Latency=2, extra map slot
nop # E : keep with cmoveq
andnot t8, t3, t8 # E : (stall)
beq t8, $u_head # U :
/* At this point we've found a zero in the first partial word of
the source. We need to isolate the valid source data and mask
it into the original destination data. (Incidentally, we know
that we'll need at least one byte of that original dest word.) */
ldq_u t0, 0(a0) # L :
negq t8, t6 # E : build bitmask of bytes <= zero
mskqh t1, t4, t1 # U :
and t6, t8, t2 # E :
subq t2, 1, t6 # E : (stall)
or t6, t2, t8 # E : (stall)
zapnot t12, t8, t12 # U : prepare source word; mirror changes (stall)
zapnot t1, t8, t1 # U : to source validity mask
andnot t0, t12, t0 # E : zero place for source to reside
or t0, t1, t0 # E : and put it there (stall both t0, t1)
stq_u t0, 0(a0) # L : (stall)
ret (t9) # L0 : Latency=3
nop
nop
nop
.end __stxncpy