/* SPDX-License-Identifier: GPL-2.0 */ /* * arch/alpha/lib/stxncpy.S * Contributed by Richard Henderson (rth@tamu.edu) * * 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.
*/
#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 */
/* We are co-aligned; take care of a partial first word. */
ldq_u t1, 0(a1) # e0 : load first src word
addq a1, 8, a1 # .. e1 :
beq t0, stxncpy_aligned # avoid loading dest word if not needed
ldq_u t0, 0(a0) # e0 :
br stxncpy_aligned # .. e1 :
/* 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 3
$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) # e0 : load second src word
addq a1, 8, a1 # .. e1 :
mskql t0, a0, t0 # e0 : mask trailing garbage in dst
extqh t2, a1, t4 # e0 :
or t1, t4, t1 # e1 : first aligned src word complete
mskqh t1, a0, t1 # e0 : mask leading garbage in src
or t0, t1, t0 # e0 : first output word complete
or t0, t6, t6 # e1 : mask original data for zero test
cmpbge zero, t6, t8 # e0 :
beq a2, $u_eocfin # .. e1 : lda t6, -1 # e0 :
bne t8, $u_final # .. e1 :
mskql t6, a1, t6 # e0 : mask out bits already seen
nop # .. e1 :
stq_u t0, 0(a0) # e0 : store first output word
or t6, t2, t2 # .. e1 :
cmpbge zero, t2, t8 # e0 : find nulls in second partial
addq a0, 8, a0 # .. e1 :
subq a2, 1, a2 # e0 :
bne t8, $u_late_head_exit # .. e1 :
/* Finally, we've got all the stupid leading edge cases taken care
of and we can set up to enter the main loop. */
/* 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 3
$u_loop:
or t0, t1, t0 # e0 : current dst word now complete
subq a2, 1, a2 # .. e1 : decrement word count
stq_u t0, 0(a0) # e0 : save the current word
addq a0, 8, a0 # .. e1 :
extql t2, a1, t1 # e0 : extract high bits for next time
beq a2, $u_eoc # .. e1 :
ldq_u t2, 8(a1) # e0 : load high word for next time
addq a1, 8, a1 # .. e1 :
nop # e0 :
cmpbge zero, t2, t8 # e1 : test new word for eos (stall)
extqh t2, a1, t0 # e0 : extract low bits for current word
beq t8, $u_loop # .. e1 :
/* 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 # e0 : first (partial) source word complete
nop # .. e1 :
cmpbge zero, t0, t8 # e0 : is the null in this first bit?
bne t8, $u_final # .. e1 (zdb)
stq_u t0, 0(a0) # e0 : the null was in the high-order bits
addq a0, 8, a0 # .. e1 :
subq a2, 1, a2 # e1 :
/* 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 # e0 : isolate low bit set
and t6, t8, t12 # e1 :
and t12, 0x80, t6 # e0 : avoid dest word load if we can
bne t6, 1f # .. e1 (zdb)
/* 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 # e1 : sll t10, t6, t6 # e0 :
and t6, 0xff, t6 # e0 :
bne t6, 1f # .. e1 :
ldq_u t2, 8(a1) # e0 : load final src word
nop # .. e1 :
extqh t2, a1, t0 # e0 : extract low bits for last word
or t1, t0, t1 # e1 :
1: cmpbge zero, t1, t8
mov t1, t0
$u_eocfin: # end-of-count, final word
or t10, t8, t8
br $u_final
/* If source misalignment is larger than dest misalignment, we need
extra startup checks to avoid SEGV. */
1: cmplt t4, t5, t12 # e1 :
extql t1, a1, t1 # .. e0 : shift src into place lda t2, -1 # e0 : for creating masks later
beq t12, $u_head # .. e1 :
extql t2, a1, t2 # e0 :
cmpbge zero, t1, t8 # .. e1 : is there a zero?
andnot t2, t6, t2 # e0 : dest mask for a single word copy
or t8, t10, t5 # .. e1 : test for end-of-count too
cmpbge zero, t2, t3 # e0 :
cmoveq a2, t5, t8 # .. e1 :
andnot t8, t3, t8 # e0 :
beq t8, $u_head # .. e1 (zdb)
/* 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.) */
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.