On 09/04/11(Sat) 09:19, Matthew Dempsky wrote:
> On Fri, Apr 8, 2011 at 11:04 PM, Martin Pieuchot <mpieuc...@nolizard.org>
> wrote:
> > Diff below add elf support to (bsd) strings(1) and make it usable for
> > architectures with ELF_TOOLCHAIN=Yes.
>
> Wait, why? I don't get it. This seems out of scope for strings(1).
Without the "-a" option strings(1) doesn't scan the file entirely [0].
In this case, for elf files it only looks for strings in non empty
sections flagged with SHF_ALLOC [1]. Maybe the manpage should be
updated.
>
> > +elf32.c: ${.CURDIR}/elf.c
> > + echo '#define ELFSIZE 32' | cat - $> > ${.TARGET}
> > +
> > +elf64.c: ${.CURDIR}/elf.c
> > + echo '#define ELFSIZE 64' | cat - $> > ${.TARGET}
>
> Why not just create elf32.c with:
>
> #define ELFSIZE 32
> #include "elf.c"
>
> and similar for elf64.c?
>
I would say to not create empty files, I just used the same method as
for nm.
The question here is more about *how* to reuse nm(1)'s elf.c in a smart
way (for nm, ranlib, strings...). I could have used the same file (diff
below) but that makes the binary twice bigger in size (but still less
than 5% of the size of the actual strings on amd64).
Martin
[0] http://pubs.opengroup.org/onlinepubs/9699919799/utilities/strings.html
[1] http://www.sco.com/developers/gabi/latest/ch4.sheader.html#special_sections
Index: Makefile
===================================================================
RCS file: /cvs/src/usr.bin/strings/Makefile,v
retrieving revision 1.3
diff -u -p -r1.3 Makefile
--- Makefile 21 Sep 1997 11:51:00 -0000 1.3
+++ Makefile 10 Apr 2011 10:54:50 -0000
@@ -1,5 +1,16 @@
# $OpenBSD: Makefile,v 1.3 1997/09/21 11:51:00 deraadt Exp $
PROG= strings
+SRCS= strings.c elf32.c elf64.c
+
+CLEANFILES+= elf32.c elf64.c
+
+CFLAGS+= -I${.CURDIR} -I${.CURDIR}/../nm
+
+elf32.c: ${.CURDIR}/../nm/elf.c
+ echo '#define ELFSIZE 32' | cat - $> > ${.TARGET}
+
+elf64.c: ${.CURDIR}/../nm/elf.c
+ echo '#define ELFSIZE 64' | cat - $> > ${.TARGET}
.include <bsd.prog.mk>
===================================================================
RCS file: /cvs/src/usr.bin/strings/strings.c,v
retrieving revision 1.15
diff -u -p -r1.15 strings.c
--- strings.c 27 Oct 2009 23:59:43 -0000 1.15
+++ strings.c 10 Apr 2011 10:57:01 -0000
@@ -34,46 +34,56 @@
#include <a.out.h>
#include <ctype.h>
+#include <elf_abi.h>
+#include <err.h>
#include <errno.h>
#include <fcntl.h>
+#include <locale.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-#include <locale.h>
#include <unistd.h>
-#include <err.h>
-#define FORMAT_DEC "%07ld "
-#define FORMAT_OCT "%07lo "
-#define FORMAT_HEX "%07lx "
+#include "elfuncs.h"
+
+#define FORMAT_DEC "%7lld "
+#define FORMAT_OCT "%7llo "
+#define FORMAT_HEX "%7llx "
#define DEF_LEN 4 /* default minimum string
length */
#define ISSTR(ch) (isascii(ch) && (isprint(ch) || ch == '\t'))
-typedef struct exec EXEC; /* struct exec cast */
-
-static long foff; /* offset in the file */
-static int hcnt, /* head count */
- head_len, /* length of header */
- read_len; /* length to read */
-static u_char hbfr[sizeof(EXEC)]; /* buffer for struct exec */
-
-static void usage(void);
-int getch(void);
+union hdr {
+ struct exec aout;
+ Elf32_Ehdr elf32;
+ Elf64_Ehdr elf64;
+};
+
+char *stab; /* Unsused, keep elf.c happy */
+int usemmap; /* Unsused, keep elf.c happy */
+
+static int hcnt, /* head count */
+ head_len; /* length of header */
+static u_char hbuf[sizeof(union hdr)]; /* buffer for header */
+
+short scan_entirely;
+short print_name;
+char *offset_format;
+int minlen, maxlen, buflen;
+
+static void usage(void);
+int getch(void);
+int process_file(const char *, u_char *);
+void find_strings(const char *, u_char *, off_t, off_t);
int
main(int argc, char *argv[])
{
- extern char *optarg;
- extern int optind;
- int ch, cnt;
- u_char *C;
- EXEC *head;
- int exitcode, minlen, maxlen, bfrlen;
- short asdata, fflg;
- u_char *bfr;
- char *file, *p;
- char *offset_format;
+ extern char *optarg;
+ extern int optind;
+ int ch, rval = 0;
+ u_char *buf;
+ char *file, *p;
setlocale(LC_ALL, "");
@@ -81,7 +91,7 @@ main(int argc, char *argv[])
* for backward compatibility, allow '-' to specify 'a' flag; no
* longer documented in the man page or usage string.
*/
- asdata = exitcode = fflg = 0;
+ scan_entirely = print_name = 0;
offset_format = NULL;
minlen = -1;
maxlen = -1;
@@ -103,10 +113,10 @@ main(int argc, char *argv[])
break;
case '-':
case 'a':
- asdata = 1;
+ scan_entirely = 1;
break;
case 'f':
- fflg = 1;
+ print_name = 1;
break;
case 'n':
minlen = atoi(optarg);
@@ -136,6 +146,7 @@ main(int argc, char *argv[])
case '?':
default:
usage();
+ /* NOTREACHED */
}
argc -= optind;
argv += optind;
@@ -146,85 +157,163 @@ main(int argc, char *argv[])
errx(1, "length less than 1");
if (maxlen != -1 && maxlen < minlen)
errx(1, "max length less than min");
- bfrlen = maxlen == -1 ? minlen : maxlen;
- bfr = malloc(bfrlen + 1);
- if (!bfr)
+
+ buflen = (maxlen == -1) ? minlen : maxlen;
+ if ((buf = malloc(buflen + 1)) == NULL)
err(1, "malloc");
- bfr[bfrlen] = '\0';
+ buf[buflen] = '\0';
+
file = "stdin";
do {
if (*argv) {
file = *argv++;
if (!freopen(file, "r", stdin)) {
warn("%s", file);
- exitcode = 1;
- goto nextfile;
+ rval = 1;
+ continue;
}
}
- foff = 0;
-#define DO_EVERYTHING() {read_len = -1; head_len = 0; goto
start;}
- read_len = -1;
- if (asdata)
- DO_EVERYTHING()
- else {
- head = (EXEC *)hbfr;
- if ((head_len =
- read(fileno(stdin), head, sizeof(EXEC))) == -1)
- DO_EVERYTHING()
- if (head_len == sizeof(EXEC) && !N_BADMAG(*head)) {
- foff = N_TXTOFF(*head);
- if (fseek(stdin, foff, SEEK_SET) == -1)
- DO_EVERYTHING()
- read_len = head->a_text + head->a_data;
- head_len = 0;
+ rval |= process_file(file, buf);
+ } while (*argv);
+
+ exit(rval);
+}
+
+int
+process_file(const char *file, u_char *buf)
+{
+ union hdr *head;
+ size_t bytes;
+ off_t foff = 0, offset = 0;
+ int i, rval = 0;
+
+ head_len = 0;
+
+ if (scan_entirely) {
+ find_strings(file, buf, 0, 0);
+ return (0);
+ }
+
+ head = (union hdr*)hbuf;
+ bzero(head, sizeof(*head));
+
+ bytes = fread((char *)head, 1, sizeof(*head), stdin);
+ if (bytes == -1) {
+ find_strings(file, buf, 0, 0);
+ return (1);
+ }
+
+ if (bytes >= sizeof(head->aout) && !N_BADMAG(head->aout)) {
+ foff = N_TXTOFF(head->aout);
+ if (fseeko(stdin, foff, SEEK_SET)) {
+ warn("%s: fseeko", file);
+ rval = errno;
+ find_strings(file, buf, 0, 0);
+ return (rval);
+ }
+ offset = head->aout.a_text + head->aout.a_data;
+ } else if (IS_ELF(head->elf32) &&
+ head->elf32.e_ident[EI_CLASS] == ELFCLASS32 &&
+ head->elf32.e_ident[EI_VERSION] == ELF_TARG_VER) {
+ Elf32_Shdr *shdrs;
+ Elf32_Ehdr *h = &head->elf32;
+
+ if ((shdrs = elf32_load_shdrs(file, stdin, 0, h)) == NULL)
+ return (1);
+
+ for (i = 1; i < h->e_shnum; i++) {
+ if (shdrs[i].sh_type != SHT_NOBITS &&
+ (shdrs[i].sh_flags & SHF_ALLOC)) {
+ foff = shdrs[i].sh_offset;
+ offset = foff + shdrs[i].sh_size;
+ if (fseeko(stdin, foff, SEEK_SET)) {
+ warn("%s: fseeko", file);
+ rval = errno;
+ break;
+ }
+ find_strings(file, buf, foff, offset);
}
- else
- hcnt = 0;
}
-start:
- for (cnt = 0, C = bfr; (ch = getch()) != EOF;) {
- if (ISSTR(ch)) {
- *C++ = ch;
- if (++cnt < minlen)
- continue;
- if (maxlen != -1) {
- while ((ch = getch()) != EOF &&
- ISSTR(ch) && cnt++ < maxlen)
- *C++ = ch;
- if (ch == EOF ||
- (ch != 0 && ch != '\n')) {
- /* get all of too big string */
- while ((ch = getch()) != EOF &&
- ISSTR(ch))
- ;
- ungetc(ch, stdin);
- goto out;
- }
- *C = 0;
+
+ free(shdrs);
+ return (rval);
+ } else if (IS_ELF(head->elf64) &&
+ head->elf64.e_ident[EI_CLASS] == ELFCLASS64 &&
+ head->elf64.e_ident[EI_VERSION] == ELF_TARG_VER) {
+ Elf64_Shdr *shdrs;
+ Elf64_Ehdr *h = &head->elf64;
+
+ if ((shdrs = elf64_load_shdrs(file, stdin, 0, h)) == NULL)
+ return (1);
+
+ for (i = 1; i < h->e_shnum; i++) {
+ if (shdrs[i].sh_type != SHT_NOBITS &&
+ (shdrs[i].sh_flags & SHF_ALLOC)) {
+ foff = shdrs[i].sh_offset;
+ offset = foff + shdrs[i].sh_size;
+ if (fseeko(stdin, foff, SEEK_SET)) {
+ warn("%s: fseeko", file);
+ rval = errno;
+ break;
}
+ find_strings(file, buf, foff, offset);
+ }
+ }
+
+ free(shdrs);
+ return (rval);
+ } else {
+ head_len = bytes;
+ hcnt = 0;
+ }
- if (fflg)
- printf("%s:", file);
+ find_strings(file, buf, foff, offset);
- if (offset_format)
- printf(offset_format, foff - minlen);
+ return (0);
+}
- printf("%s", bfr);
-
- if (maxlen == -1)
- while ((ch = getch()) != EOF &&
- ISSTR(ch))
- putchar((char)ch);
- putchar('\n');
- out:
- ;
- }
- cnt = 0;
- C = bfr;
+void
+find_strings(const char *filename, u_char *buf, off_t foff, off_t offset)
+{
+ int i, c = 0;
+
+ while (c != EOF && (foff < offset || !offset)) {
+ for (i = 0; i < buflen; i++) {
+ c = getch();
+ foff++;
+ if (!ISSTR(c) || foff == offset)
+ break;
+ buf[i] = c;
+ buf[i + 1] = '\0';
}
-nextfile: ;
- } while (*argv);
- exit(exitcode);
+
+ if (i >= minlen) {
+ if (print_name)
+ printf("%s: ", filename);
+
+ if (offset_format)
+ printf(offset_format, (foff - i));
+
+ printf("%s", buf);
+
+ if (maxlen == -1)
+ while (c != EOF && (foff < offset || !offset)) {
+ c = getch();
+ foff++;
+ if (!ISSTR(c) || foff == offset)
+ break;
+ putchar(c);
+ }
+ putchar('\n');
+
+ /* Eat all the string if it's too big */
+ if (i == maxlen && (c != '\n' || c != '\0'))
+ while ((foff < offset || !offset) && ISSTR(c)) {
+ c = getch();
+ foff++;
+ }
+ }
+ }
}
/*
@@ -234,21 +323,23 @@ nextfile: ;
int
getch(void)
{
- ++foff;
if (head_len) {
if (hcnt < head_len)
- return((int)hbfr[hcnt++]);
+ return ((int)hbuf[hcnt++]);
head_len = 0;
}
- if (read_len == -1 || read_len-- > 0)
- return(getchar());
- return(EOF);
+
+ return (getchar());
}
static void
usage(void)
{
+ extern char *__progname;
+
(void)fprintf(stderr,
- "usage: strings [-afo] [-m number] [-n number] [-t radix] [file
...]\n");
+ "usage: %s [-afo] [-m number] [-n number] [-t radix] [file ...]\n",
+ __progname);
+
exit(1);
}
