1 /*- 2 * Copyright (c) 1993, David Greenman 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 24 * SUCH DAMAGE. 25 */ 26 27 #include <sys/cdefs.h> 28 __FBSDID("$FreeBSD$"); 29 30 #include <sys/param.h> 31 #include <sys/vnode.h> 32 #include <sys/proc.h> 33 #include <sys/systm.h> 34 #include <sys/sysproto.h> 35 #include <sys/exec.h> 36 #include <sys/imgact.h> 37 #include <sys/kernel.h> 38 39 #define KEEP_OLDCODE 1 40 #if BYTE_ORDER == LITTLE_ENDIAN /* temp for OLD_CODE kludge */ 41 #define DBG_MAGIC 0x2B23 /* #+ in "little-endian" */ 42 #define OLD_MAGIC 0x3C23 /* #< */ 43 #else 44 #define DBG_MAGIC 0x232B /* #+ in big-endian */ 45 #define OLD_MAGIC 0x233C /* #< */ 46 #endif 47 48 #if BYTE_ORDER == LITTLE_ENDIAN 49 #define SHELLMAGIC 0x2123 /* #! */ 50 #else 51 #define SHELLMAGIC 0x2321 52 #endif 53 54 /* 55 * At the time of this writing, MAXSHELLCMDLEN == PAGE_SIZE. This is 56 * significant because the caller has only mapped in one page of the 57 * file we're reading. This code should be changed to know how to 58 * read in the second page, but I'm not doing that just yet... 59 */ 60 #if MAXSHELLCMDLEN > PAGE_SIZE 61 #error "MAXSHELLCMDLEN is larger than a single page!" 62 #endif 63 64 /** 65 * Shell interpreter image activator. An interpreter name beginning at 66 * imgp->args->begin_argv is the minimal successful exit requirement. 67 * 68 * If the given file is a shell-script, then the first line will start 69 * with the two characters `#!' (aka SHELLMAGIC), followed by the name 70 * of the shell-interpreter to run, followed by zero or more tokens. 71 * 72 * The interpreter is then started up such that it will see: 73 * arg[0] -> The name of interpreter as specified after `#!' in the 74 * first line of the script. The interpreter name must 75 * not be longer than MAXSHELLCMDLEN bytes. 76 * arg[1] -> *If* there are any additional tokens on the first line, 77 * then we add a new arg[1], which is a copy of the rest of 78 * that line. The copy starts at the first token after the 79 * interpreter name. We leave it to the interpreter to 80 * parse the tokens in that value. 81 * arg[x] -> the full pathname of the script. This will either be 82 * arg[2] or arg[1], depending on whether or not tokens 83 * were found after the interpreter name. 84 * arg[x+1] -> all the arguments that were specified on the original 85 * command line. 86 * 87 * This processing is described in the execve(2) man page. 88 */ 89 90 /* 91 * HISTORICAL NOTE: From 1993 to mid-2005, FreeBSD parsed out the tokens as 92 * found on the first line of the script, and setup each token as a separate 93 * value in arg[]. This extra processing did not match the behavior of other 94 * OS's, and caused a few subtle problems. For one, it meant the kernel was 95 * deciding how those values should be parsed (wrt characters for quoting or 96 * comments, etc), while the interpreter might have other rules for parsing. 97 * It also meant the interpreter had no way of knowing which arguments came 98 * from the first line of the shell script, and which arguments were specified 99 * by the user on the command line. 100 * 101 * Only few things in the base system might depend on that non-standard 102 * processing (mainly /bin/sh and /usr/bin/env). And for programs which are 103 * not in the base system, the "newer" behavior matches how NetBSD, OpenBSD, 104 * Linux, Solaris, AIX, IRIX, and many other Unixes have set up the arg-list 105 * for the interpreter. So if a program can handle this behavior on those 106 * other OS's, it should be able to handle it for FreeBSD too. 107 */ 108 int 109 exec_shell_imgact(imgp) 110 struct image_params *imgp; 111 { 112 const char *image_header = imgp->image_header; 113 const char *ihp, *interpb, *interpe, *maxp, *optb, *opte; 114 int error, offset; 115 size_t length, clength; 116 struct vattr vattr; 117 118 /* a shell script? */ 119 if (((const short *) image_header)[0] != SHELLMAGIC) 120 return(-1); 121 122 /* 123 * Don't allow a shell script to be the shell for a shell 124 * script. :-) 125 */ 126 if (imgp->interpreted) 127 return(ENOEXEC); 128 129 imgp->interpreted = 1; 130 131 /* 132 * At this point we have the first page of the file mapped. 133 * However, we don't know how far into the page the contents are 134 * valid -- the actual file might be much shorter than the page. 135 * So find out the file size. 136 */ 137 error = VOP_GETATTR(imgp->vp, &vattr, imgp->proc->p_ucred, curthread); 138 if (error) 139 return (error); 140 141 /* 142 * Copy shell name and arguments from image_header into a string 143 * buffer. Remember that the caller has mapped only the 144 * first page of the file into memory. 145 */ 146 clength = (vattr.va_size > PAGE_SIZE) ? PAGE_SIZE : vattr.va_size; 147 148 maxp = &image_header[clength]; 149 ihp = &image_header[2]; 150 #if KEEP_OLDCODE 151 /* 152 * XXX - Temporarily provide a quick-and-dirty way to get the 153 * older, non-standard option-parsing behavior, just in case 154 * someone finds themselves in an emergency where they need it. 155 * This will not be documented. It is only for initial testing. 156 */ 157 if (*(const short *)ihp == OLD_MAGIC) 158 ihp += 2; 159 else 160 goto new_code; 161 interpb = ihp; 162 163 /* 164 * Figure out the number of bytes that need to be reserved in the 165 * argument string to copy the contents of the interpreter's command 166 * line into the argument string. 167 */ 168 ihp = interpb; 169 offset = 0; 170 while (ihp < &image_header[clength]) { 171 /* Skip any whitespace */ 172 if ((*ihp == ' ') || (*ihp == '\t')) { 173 ihp++; 174 continue; 175 } 176 177 /* End of line? */ 178 if ((*ihp == '\n') || (*ihp == '#') || (*ihp == '\0')) 179 break; 180 181 /* Found a token */ 182 do { 183 offset++; 184 ihp++; 185 } while ((*ihp != ' ') && (*ihp != '\t') && (*ihp != '\n') && 186 (*ihp != '#') && (*ihp != '\0') && 187 (ihp < &image_header[clength])); 188 /* Include terminating nulls in the offset */ 189 offset++; 190 } 191 192 /* If the script gives a null line as the interpreter, we bail */ 193 if (offset == 0) 194 return (ENOEXEC); 195 196 /* Check that we aren't too big */ 197 if (ihp == &image_header[MAXSHELLCMDLEN]) 198 return (ENAMETOOLONG); 199 200 /* 201 * The full path name of the original script file must be tagged 202 * onto the end, adjust the offset to deal with it. 203 * 204 * The original argv[0] is being replaced, set 'length' to the number 205 * of bytes being removed. So 'offset' is the number of bytes being 206 * added and 'length' is the number of bytes being removed. 207 */ 208 offset += strlen(imgp->args->fname) + 1; /* add fname */ 209 length = (imgp->args->argc == 0) ? 0 : 210 strlen(imgp->args->begin_argv) + 1; /* bytes to delete */ 211 212 if (offset - length > imgp->args->stringspace) 213 return (E2BIG); 214 215 bcopy(imgp->args->begin_argv + length, imgp->args->begin_argv + offset, 216 imgp->args->endp - (imgp->args->begin_argv + length)); 217 218 offset -= length; /* calculate actual adjustment */ 219 imgp->args->begin_envv += offset; 220 imgp->args->endp += offset; 221 imgp->args->stringspace -= offset; 222 223 /* 224 * If there were no arguments then we've added one, otherwise 225 * decr argc remove old argv[0], incr argc for fname add, net 0 226 */ 227 if (imgp->args->argc == 0) 228 imgp->args->argc = 1; 229 230 /* 231 * Loop through the interpreter name yet again, copying as 232 * we go. 233 */ 234 ihp = interpb; 235 offset = 0; 236 while (ihp < &image_header[clength]) { 237 /* Skip whitespace */ 238 if ((*ihp == ' ') || (*ihp == '\t')) { 239 ihp++; 240 continue; 241 } 242 243 /* End of line? */ 244 if ((*ihp == '\n') || (*ihp == '#') || (*ihp == '\0')) 245 break; 246 247 /* Found a token, copy it */ 248 do { 249 imgp->args->begin_argv[offset++] = *ihp++; 250 } while ((*ihp != ' ') && (*ihp != '\t') && (*ihp != '\n') && 251 (*ihp != '#') && (*ihp != '\0') && 252 (ihp < &image_header[MAXSHELLCMDLEN])); 253 imgp->args->begin_argv[offset++] = '\0'; 254 imgp->args->argc++; 255 } 256 goto common_end; 257 new_code: 258 #endif 259 /* 260 * Find the beginning and end of the interpreter_name. If the 261 * line does not include any interpreter, or if the name which 262 * was found is too long, we bail out. 263 */ 264 while (ihp < maxp && ((*ihp == ' ') || (*ihp == '\t'))) 265 ihp++; 266 interpb = ihp; 267 while (ihp < maxp && ((*ihp != ' ') && (*ihp != '\t') && (*ihp != '\n') 268 && (*ihp != '\0'))) 269 ihp++; 270 interpe = ihp; 271 if (interpb == interpe) 272 return (ENOEXEC); 273 if ((interpe - interpb) >= MAXSHELLCMDLEN) 274 return (ENAMETOOLONG); 275 276 /* 277 * Find the beginning of the options (if any), and the end-of-line. 278 * Then trim the trailing blanks off the value. Note that some 279 * other operating systems do *not* trim the trailing whitespace... 280 */ 281 while (ihp < maxp && ((*ihp == ' ') || (*ihp == '\t'))) 282 ihp++; 283 optb = ihp; 284 while (ihp < maxp && ((*ihp != '\n') && (*ihp != '\0'))) 285 ihp++; 286 opte = ihp; 287 while (--ihp > interpe && ((*ihp == ' ') || (*ihp == '\t'))) 288 opte = ihp; 289 290 /* 291 * We need to "pop" (remove) the present value of arg[0], and "push" 292 * either two or three new values in the arg[] list. To do this, 293 * we first shift all the other values in the `begin_argv' area to 294 * provide the exact amount of room for the values added. Set up 295 * `offset' as the number of bytes to be added to the `begin_argv' 296 * area, and 'length' as the number of bytes being removed. 297 */ 298 offset = interpe - interpb + 1; /* interpreter */ 299 if (opte != optb) /* options (if any) */ 300 offset += opte - optb + 1; 301 offset += strlen(imgp->args->fname) + 1; /* fname of script */ 302 length = (imgp->args->argc == 0) ? 0 : 303 strlen(imgp->args->begin_argv) + 1; /* bytes to delete */ 304 305 if (offset - length > imgp->args->stringspace) 306 return (E2BIG); 307 308 bcopy(imgp->args->begin_argv + length, imgp->args->begin_argv + offset, 309 imgp->args->endp - (imgp->args->begin_argv + length)); 310 311 offset -= length; /* calculate actual adjustment */ 312 imgp->args->begin_envv += offset; 313 imgp->args->endp += offset; 314 imgp->args->stringspace -= offset; 315 316 /* 317 * If there was no arg[0] when we started, then the interpreter_name 318 * is adding an argument (instead of replacing the arg[0] we started 319 * with). And we're always adding an argument when we include the 320 * full pathname of the original script. 321 */ 322 if (imgp->args->argc == 0) 323 imgp->args->argc = 1; 324 imgp->args->argc++; 325 326 /* 327 * The original arg[] list has been shifted appropriately. Copy in 328 * the interpreter name and options-string. 329 */ 330 length = interpe - interpb; 331 bcopy(interpb, imgp->args->buf, length); 332 *(imgp->args->buf + length) = '\0'; 333 offset = length + 1; 334 if (opte != optb) { 335 length = opte - optb; 336 bcopy(optb, imgp->args->buf + offset, length); 337 *(imgp->args->buf + offset + length) = '\0'; 338 offset += length + 1; 339 imgp->args->argc++; 340 } 341 342 #if KEEP_OLDCODE 343 common_end: 344 #endif 345 /* 346 * Finally, add the filename onto the end for the interpreter to 347 * use and copy the interpreter's name to imgp->interpreter_name 348 * for exec to use. 349 */ 350 error = copystr(imgp->args->fname, imgp->args->buf + offset, 351 imgp->args->stringspace, &length); 352 353 if (error == 0) 354 error = copystr(imgp->args->begin_argv, imgp->interpreter_name, 355 MAXSHELLCMDLEN, &length); 356 357 return (error); 358 } 359 360 /* 361 * Tell kern_execve.c about it, with a little help from the linker. 362 */ 363 static struct execsw shell_execsw = { exec_shell_imgact, "#!" }; 364 EXEC_SET(shell, shell_execsw); 365