| xf.li | bdd93d5 | 2023-05-12 07:10:14 -0700 | [diff] [blame] | 1 | /* strrchr (str, ch) -- Return pointer to last occurrence of CH in STR. | 
 | 2 |    For Intel 80x86, x>=3. | 
 | 3 |    Copyright (C) 1994-2016 Free Software Foundation, Inc. | 
 | 4 |    This file is part of the GNU C Library. | 
 | 5 |    Contributed by Ulrich Drepper <drepper@gnu.ai.mit.edu> | 
 | 6 |    Some optimisations by Alan Modra <Alan@SPRI.Levels.UniSA.Edu.Au> | 
 | 7 |  | 
 | 8 |    The GNU C Library is free software; you can redistribute it and/or | 
 | 9 |    modify it under the terms of the GNU Lesser General Public | 
 | 10 |    License as published by the Free Software Foundation; either | 
 | 11 |    version 2.1 of the License, or (at your option) any later version. | 
 | 12 |  | 
 | 13 |    The GNU C Library is distributed in the hope that it will be useful, | 
 | 14 |    but WITHOUT ANY WARRANTY; without even the implied warranty of | 
 | 15 |    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU | 
 | 16 |    Lesser General Public License for more details. | 
 | 17 |  | 
 | 18 |    You should have received a copy of the GNU Lesser General Public | 
 | 19 |    License along with the GNU C Library; if not, see | 
 | 20 |    <http://www.gnu.org/licenses/>.  */ | 
 | 21 |  | 
 | 22 | #include <sysdep.h> | 
 | 23 | #include "asm-syntax.h" | 
 | 24 |  | 
 | 25 | #define PARMS	4+8	/* space for 2 saved regs */ | 
 | 26 | #define RTN	PARMS | 
 | 27 | #define STR	RTN | 
 | 28 | #define CHR	STR+4 | 
 | 29 |  | 
 | 30 | 	.text | 
 | 31 | ENTRY (strrchr) | 
 | 32 |  | 
 | 33 | 	pushl %edi		/* Save callee-safe registers used here.  */ | 
 | 34 | 	cfi_adjust_cfa_offset (4) | 
 | 35 | 	cfi_rel_offset (edi, 0) | 
 | 36 | 	pushl %esi | 
 | 37 | 	cfi_adjust_cfa_offset (4) | 
 | 38 |  | 
 | 39 | 	xorl %eax, %eax | 
 | 40 | 	movl STR(%esp), %esi | 
 | 41 | 	cfi_rel_offset (esi, 0) | 
 | 42 | 	movl CHR(%esp), %ecx | 
 | 43 |  | 
 | 44 | 	/* At the moment %ecx contains C.  What we need for the | 
 | 45 | 	   algorithm is C in all bytes of the dword.  Avoid | 
 | 46 | 	   operations on 16 bit words because these require an | 
 | 47 | 	   prefix byte (and one more cycle).  */ | 
 | 48 | 	movb %cl, %ch		/* now it is 0|0|c|c */ | 
 | 49 | 	movl %ecx, %edx | 
 | 50 | 	shll $16, %ecx		/* now it is c|c|0|0 */ | 
 | 51 | 	movw %dx, %cx		/* and finally c|c|c|c */ | 
 | 52 |  | 
 | 53 | 	/* Before we start with the main loop we process single bytes | 
 | 54 | 	   until the source pointer is aligned.  This has two reasons: | 
 | 55 | 	   1. aligned 32-bit memory access is faster | 
 | 56 | 	   and (more important) | 
 | 57 | 	   2. we process in the main loop 32 bit in one step although | 
 | 58 | 	      we don't know the end of the string.  But accessing at | 
 | 59 | 	      4-byte alignment guarantees that we never access illegal | 
 | 60 | 	      memory if this would not also be done by the trivial | 
 | 61 | 	      implementation (this is because all processor inherent | 
 | 62 | 	      boundaries are multiples of 4.  */ | 
 | 63 |  | 
 | 64 | 	testl $3, %esi		/* correctly aligned ? */ | 
 | 65 | 	jz L(19)		/* yes => begin loop */ | 
 | 66 | 	movb (%esi), %dl	/* load byte in question (we need it twice) */ | 
 | 67 | 	cmpb %dl, %cl		/* compare byte */ | 
 | 68 | 	jne L(11)			/* target found => return */ | 
 | 69 | 	movl %esi, %eax		/* remember pointer as possible result */ | 
 | 70 | L(11):	orb %dl, %dl		/* is NUL? */ | 
 | 71 | 	jz L(2)			/* yes => return NULL */ | 
 | 72 | 	incl %esi		/* increment pointer */ | 
 | 73 |  | 
 | 74 | 	testl $3, %esi		/* correctly aligned ? */ | 
 | 75 | 	jz L(19)		/* yes => begin loop */ | 
 | 76 | 	movb (%esi), %dl	/* load byte in question (we need it twice) */ | 
 | 77 | 	cmpb %dl, %cl		/* compare byte */ | 
 | 78 | 	jne L(12)			/* target found => return */ | 
 | 79 | 	movl %esi, %eax		/* remember pointer as result */ | 
 | 80 | L(12):	orb %dl, %dl		/* is NUL? */ | 
 | 81 | 	jz L(2)			/* yes => return NULL */ | 
 | 82 | 	incl %esi		/* increment pointer */ | 
 | 83 |  | 
 | 84 | 	testl $3, %esi		/* correctly aligned ? */ | 
 | 85 | 	jz L(19)		/* yes => begin loop */ | 
 | 86 | 	movb (%esi), %dl	/* load byte in question (we need it twice) */ | 
 | 87 | 	cmpb %dl, %cl		/* compare byte */ | 
 | 88 | 	jne L(13)			/* target found => return */ | 
 | 89 | 	movl %esi, %eax		/* remember pointer as result */ | 
 | 90 | L(13):	orb %dl, %dl		/* is NUL? */ | 
 | 91 | 	jz L(2)			/* yes => return NULL */ | 
 | 92 | 	incl %esi		/* increment pointer */ | 
 | 93 |  | 
 | 94 | 	/* No we have reached alignment.  */ | 
 | 95 | 	jmp L(19)		/* begin loop */ | 
 | 96 |  | 
 | 97 |       /* We exit the loop if adding MAGIC_BITS to LONGWORD fails to | 
 | 98 | 	 change any of the hole bits of LONGWORD. | 
 | 99 |  | 
 | 100 | 	 1) Is this safe?  Will it catch all the zero bytes? | 
 | 101 | 	 Suppose there is a byte with all zeros.  Any carry bits | 
 | 102 | 	 propagating from its left will fall into the hole at its | 
 | 103 | 	 least significant bit and stop.  Since there will be no | 
 | 104 | 	 carry from its most significant bit, the LSB of the | 
 | 105 | 	 byte to the left will be unchanged, and the zero will be | 
 | 106 | 	 detected. | 
 | 107 |  | 
 | 108 | 	 2) Is this worthwhile?  Will it ignore everything except | 
 | 109 | 	 zero bytes?  Suppose every byte of LONGWORD has a bit set | 
 | 110 | 	 somewhere.  There will be a carry into bit 8.	If bit 8 | 
 | 111 | 	 is set, this will carry into bit 16.  If bit 8 is clear, | 
 | 112 | 	 one of bits 9-15 must be set, so there will be a carry | 
 | 113 | 	 into bit 16.  Similarly, there will be a carry into bit | 
 | 114 | 	 24.  If one of bits 24-31 is set, there will be a carry | 
 | 115 | 	 into bit 32 (=carry flag), so all of the hole bits will | 
 | 116 | 	 be changed. | 
 | 117 |  | 
 | 118 | 	 3) But wait!  Aren't we looking for C, not zero? | 
 | 119 | 	 Good point.  So what we do is XOR LONGWORD with a longword, | 
 | 120 | 	 each of whose bytes is C.  This turns each byte that is C | 
 | 121 | 	 into a zero.  */ | 
 | 122 |  | 
 | 123 | 	/* Each round the main loop processes 16 bytes.  */ | 
 | 124 |  | 
 | 125 | 	/* Jump to here when the character is detected.  We chose this | 
 | 126 | 	   way around because the character one is looking for is not | 
 | 127 | 	   as frequent as the rest and taking a conditional jump is more | 
 | 128 | 	   expensive than ignoring it. | 
 | 129 |  | 
 | 130 | 	   Some more words to the code below: it might not be obvious why | 
 | 131 | 	   we decrement the source pointer here.  In the loop the pointer | 
 | 132 | 	   is not pre-incremented and so it still points before the word | 
 | 133 | 	   we are looking at.  But you should take a look at the instruction | 
 | 134 | 	   which gets executed before we get into the loop: `addl $16, %esi'. | 
 | 135 | 	   This makes the following subs into adds.  */ | 
 | 136 |  | 
 | 137 | 	/* These fill bytes make the main loop be correctly aligned. | 
 | 138 | 	   We cannot use align because it is not the following instruction | 
 | 139 | 	   which should be aligned.  */ | 
 | 140 | 	.byte 0, 0 | 
 | 141 | #ifndef	PROF | 
 | 142 | 	/* Profiling adds some code and so changes the alignment.  */ | 
 | 143 | 	.byte 0 | 
 | 144 | #endif | 
 | 145 |  | 
 | 146 | L(4):	subl $4, %esi		/* adjust pointer */ | 
 | 147 | L(41):	subl $4, %esi | 
 | 148 | L(42):	subl $4, %esi | 
 | 149 | L(43):	testl $0xff000000, %edx	/* is highest byte == C? */ | 
 | 150 | 	jnz L(33)		/* no => try other bytes */ | 
 | 151 | 	leal 15(%esi), %eax	/* store address as result */ | 
 | 152 | 	jmp L(1)		/* and start loop again */ | 
 | 153 |  | 
 | 154 | L(3):	subl $4, %esi		/* adjust pointer */ | 
 | 155 | L(31):	subl $4, %esi | 
 | 156 | L(32):	subl $4, %esi | 
 | 157 | L(33):	testl $0xff0000, %edx	/* is C in third byte? */ | 
 | 158 | 	jnz L(51)		/* no => try other bytes */ | 
 | 159 | 	leal 14(%esi), %eax	/* store address as result */ | 
 | 160 | 	jmp L(1)		/* and start loop again */ | 
 | 161 |  | 
 | 162 | L(51): | 
 | 163 | 	/* At this point we know that the byte is in one of the lower bytes. | 
 | 164 | 	   We make a guess and correct it if necessary.  This reduces the | 
 | 165 | 	   number of necessary jumps.  */ | 
 | 166 | 	leal 12(%esi), %eax	/* guess address of lowest byte as result */ | 
 | 167 | 	testb %dh, %dh		/* is guess correct? */ | 
 | 168 | 	jnz L(1)		/* yes => start loop */ | 
 | 169 | 	leal 13(%esi), %eax	/* correct guess to second byte */ | 
 | 170 |  | 
 | 171 | L(1):	addl $16, %esi		/* increment pointer for full round */ | 
 | 172 |  | 
 | 173 | L(19):	movl (%esi), %edx	/* get word (= 4 bytes) in question */ | 
 | 174 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 175 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 176 | 				   carry bits reported for each byte which | 
 | 177 | 				   is *not* 0 */ | 
 | 178 |  | 
 | 179 | 	/* According to the algorithm we had to reverse the effect of the | 
 | 180 | 	   XOR first and then test the overflow bits.  But because the | 
 | 181 | 	   following XOR would destroy the carry flag and it would (in a | 
 | 182 | 	   representation with more than 32 bits) not alter then last | 
 | 183 | 	   overflow, we can now test this condition.  If no carry is signaled | 
 | 184 | 	   no overflow must have occurred in the last byte => it was 0.	*/ | 
 | 185 |  | 
 | 186 | 	jnc L(20)			/* found NUL => check last word */ | 
 | 187 |  | 
 | 188 | 	/* We are only interested in carry bits that change due to the | 
 | 189 | 	   previous add, so remove original bits */ | 
 | 190 | 	xorl %edx, %edi		/* (word+magic)^word */ | 
 | 191 |  | 
 | 192 | 	/* Now test for the other three overflow bits.  */ | 
 | 193 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 194 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 195 | 				   the addition will not result in 0.  */ | 
 | 196 |  | 
 | 197 | 	/* If at least one byte of the word is C we don't get 0 in %edi.  */ | 
 | 198 | 	jnz L(20)			/* found NUL => check last word */ | 
 | 199 |  | 
 | 200 | 	/* Now we made sure the dword does not contain the character we are | 
 | 201 | 	   looking for.  But because we deal with strings we have to check | 
 | 202 | 	   for the end of string before testing the next dword.  */ | 
 | 203 |  | 
 | 204 | 	xorl %ecx, %edx		/* XOR with word c|c|c|c => bytes of str == c | 
 | 205 | 				   are now 0 */ | 
 | 206 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 207 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 208 | 				   carry bits reported for each byte which | 
 | 209 | 				   is *not* 0 */ | 
 | 210 | 	jnc L(4)		/* highest byte is C => examine dword */ | 
 | 211 | 	xorl %edx, %edi		/* ((word^charmask)+magic)^(word^charmask) */ | 
 | 212 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 213 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 214 | 				   the addition will not result in 0.  */ | 
 | 215 | 	jnz L(3)		/* C is detected in the word => examine it */ | 
 | 216 |  | 
 | 217 | 	movl 4(%esi), %edx	/* get word (= 4 bytes) in question */ | 
 | 218 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 219 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 220 | 				   carry bits reported for each byte which | 
 | 221 | 				   is *not* 0 */ | 
 | 222 | 	jnc L(21)		/* found NUL => check last word */ | 
 | 223 | 	xorl %edx, %edi		/* (word+magic)^word */ | 
 | 224 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 225 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 226 | 				   the addition will not result in 0.  */ | 
 | 227 | 	jnz L(21)		/* found NUL => check last word */ | 
 | 228 | 	xorl %ecx, %edx		/* XOR with word c|c|c|c => bytes of str == c | 
 | 229 | 				   are now 0 */ | 
 | 230 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 231 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 232 | 				   carry bits reported for each byte which | 
 | 233 | 				   is *not* 0 */ | 
 | 234 | 	jnc L(41)		/* highest byte is C => examine dword */ | 
 | 235 | 	xorl %edx, %edi		/* ((word^charmask)+magic)^(word^charmask) */ | 
 | 236 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 237 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 238 | 				   the addition will not result in 0.  */ | 
 | 239 | 	jnz L(31)		/* C is detected in the word => examine it */ | 
 | 240 |  | 
 | 241 | 	movl 8(%esi), %edx	/* get word (= 4 bytes) in question */ | 
 | 242 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 243 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 244 | 				   carry bits reported for each byte which | 
 | 245 | 				   is *not* 0 */ | 
 | 246 | 	jnc L(22)		/* found NUL => check last word */ | 
 | 247 | 	xorl %edx, %edi		/* (word+magic)^word */ | 
 | 248 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 249 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 250 | 				   the addition will not result in 0.  */ | 
 | 251 | 	jnz L(22)		/* found NUL => check last word */ | 
 | 252 | 	xorl %ecx, %edx		/* XOR with word c|c|c|c => bytes of str == c | 
 | 253 | 				   are now 0 */ | 
 | 254 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 255 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 256 | 				   carry bits reported for each byte which | 
 | 257 | 				   is *not* 0 */ | 
 | 258 | 	jnc L(42)		/* highest byte is C => examine dword */ | 
 | 259 | 	xorl %edx, %edi		/* ((word^charmask)+magic)^(word^charmask) */ | 
 | 260 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 261 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 262 | 				   the addition will not result in 0.  */ | 
 | 263 | 	jnz L(32)		/* C is detected in the word => examine it */ | 
 | 264 |  | 
 | 265 | 	movl 12(%esi), %edx	/* get word (= 4 bytes) in question */ | 
 | 266 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 267 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 268 | 				   carry bits reported for each byte which | 
 | 269 | 				   is *not* 0 */ | 
 | 270 | 	jnc L(23)		/* found NUL => check last word */ | 
 | 271 | 	xorl %edx, %edi		/* (word+magic)^word */ | 
 | 272 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 273 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 274 | 				   the addition will not result in 0.  */ | 
 | 275 | 	jnz L(23)		/* found NUL => check last word */ | 
 | 276 | 	xorl %ecx, %edx		/* XOR with word c|c|c|c => bytes of str == c | 
 | 277 | 				   are now 0 */ | 
 | 278 | 	movl $0xfefefeff, %edi	/* magic value */ | 
 | 279 | 	addl %edx, %edi		/* add the magic value to the word.  We get | 
 | 280 | 				   carry bits reported for each byte which | 
 | 281 | 				   is *not* 0 */ | 
 | 282 | 	jnc L(43)		/* highest byte is C => examine dword */ | 
 | 283 | 	xorl %edx, %edi		/* ((word^charmask)+magic)^(word^charmask) */ | 
 | 284 | 	orl $0xfefefeff, %edi	/* set all non-carry bits */ | 
 | 285 | 	incl %edi		/* add 1: if one carry bit was *not* set | 
 | 286 | 				   the addition will not result in 0.  */ | 
 | 287 | 	jz L(1)			/* C is not detected => restart loop */ | 
 | 288 | 	jmp L(33)		/* examine word */ | 
 | 289 |  | 
 | 290 | L(23):	addl $4, %esi		/* adjust pointer */ | 
 | 291 | L(22):	addl $4, %esi | 
 | 292 | L(21):	addl $4, %esi | 
 | 293 |  | 
 | 294 | 	/* What remains to do is to test which byte the NUL char is and | 
 | 295 | 	   whether the searched character appears in one of the bytes | 
 | 296 | 	   before.  A special case is that the searched byte maybe NUL. | 
 | 297 | 	   In this case a pointer to the terminating NUL char has to be | 
 | 298 | 	   returned.  */ | 
 | 299 |  | 
 | 300 | L(20):	cmpb %cl, %dl		/* is first byte == C? */ | 
 | 301 | 	jne L(24)		/* no => skip */ | 
 | 302 | 	movl %esi, %eax		/* store address as result */ | 
 | 303 | L(24):	testb %dl, %dl		/* is first byte == NUL? */ | 
 | 304 | 	jz L(2)			/* yes => return */ | 
 | 305 |  | 
 | 306 | 	cmpb %cl, %dh		/* is second byte == C? */ | 
 | 307 | 	jne L(25)		/* no => skip */ | 
 | 308 | 	leal 1(%esi), %eax	/* store address as result */ | 
 | 309 | L(25):	testb %dh, %dh		/* is second byte == NUL? */ | 
 | 310 | 	jz L(2)			/* yes => return */ | 
 | 311 |  | 
 | 312 | 	shrl $16,%edx		/* make upper bytes accessible */ | 
 | 313 | 	cmpb %cl, %dl		/* is third byte == C */ | 
 | 314 | 	jne L(26)		/* no => skip */ | 
 | 315 | 	leal 2(%esi), %eax	/* store address as result */ | 
 | 316 | L(26):	testb %dl, %dl		/* is third byte == NUL */ | 
 | 317 | 	jz L(2)			/* yes => return */ | 
 | 318 |  | 
 | 319 | 	cmpb %cl, %dh		/* is fourth byte == C */ | 
 | 320 | 	jne L(2)		/* no => skip */ | 
 | 321 | 	leal 3(%esi), %eax	/* store address as result */ | 
 | 322 |  | 
 | 323 | L(2):	popl %esi		/* restore saved register content */ | 
 | 324 | 	cfi_adjust_cfa_offset (-4) | 
 | 325 | 	cfi_restore (esi) | 
 | 326 | 	popl %edi | 
 | 327 | 	cfi_adjust_cfa_offset (-4) | 
 | 328 | 	cfi_restore (edi) | 
 | 329 |  | 
 | 330 | 	ret | 
 | 331 | END (strrchr) | 
 | 332 |  | 
 | 333 | weak_alias (strrchr, rindex) | 
 | 334 | libc_hidden_builtin_def (strrchr) |