0074-proc/readproc.c: Fix bugs and overflows in file2strvec().

Note: this is by far the most important and complex patch of the whole
series, please review it carefully; thank you very much!

For this patch, we decided to keep the original function's design and
skeleton, to avoid regressions and behavior changes, while fixing the
various bugs and overflows. And like the "Harden file2str()" patch, this
patch does not fail when about to overflow, but truncates instead: there
is information available about this process, so return it to the caller;
also, we used INT_MAX as a limit, but a lower limit could be used.

The easy changes:

- Replace sprintf() with snprintf() (and check for truncation).

- Replace "if (n == 0 && rbuf == 0)" with "if (n <= 0 && tot <= 0)" and
  do break instead of return: it simplifies the code (only one place to
  handle errors), and also guarantees that in the while loop either n or
  tot is > 0 (or both), even if n is reset to 0 when about to overflow.

- Remove the "if (n < 0)" block in the while loop: it is (and was) dead
  code, since we enter the while loop only if n >= 0.

- Rewrite the missing-null-terminator detection: in the original
  function, if the size of the file is a multiple of 2047, a null-
  terminator is appended even if the file is already null-terminated.

- Replace "if (n <= 0 && !end_of_file)" with "if (n < 0 || tot <= 0)":
  originally, it was equivalent to "if (n < 0)", but we added "tot <= 0"
  to handle the first break of the while loop, and to guarantee that in
  the rest of the function tot is > 0.

- Double-force ("belt and suspenders") the null-termination of rbuf:
  this is (and was) essential to the correctness of the function.

- Replace the final "while" loop with a "for" loop that behaves just
  like the preceding "for" loop: in the original function, this would
  lead to unexpected results (for example, if rbuf is |\0|A|\0|, this
  would return the array {"",NULL} but should return {"","A",NULL}; and
  if rbuf is |A|\0|B| (should never happen because rbuf should be null-
  terminated), this would make room for two pointers in ret, but would
  write three pointers to ret).

The hard changes:

- Prevent the integer overflow of tot in the while loop, but unlike
  file2str(), file2strvec() cannot let tot grow until it almost reaches
  INT_MAX, because it needs more space for the pointers: this is why we
  introduced ARG_LEN, which also guarantees that we can add "align" and
  a few sizeof(char*)s to tot without overflowing.

- Prevent the integer overflow of "tot + c + align": when INT_MAX is
  (almost) reached, we write the maximal safe amount of pointers to ret
  (ARG_LEN guarantees that there is always space for *ret = rbuf and the
  NULL terminator).

---------------------------- adapted for newlib branch
. there were many formatting differences
. i introduced several myself (especially comments)
. stdlib 'realloc' used, not that home grown xrealloc
. stdlib 'realloc' required extra 'return NULL' statement

Signed-off-by: Jim Warner <james.warner@comcast.net>

proc/readproc.c

@@ -686,25 +686,36 @@ static int file2str(const char *directory, const char *what, struct utlbuf_s *ub
 
 static char** file2strvec(const char* directory, const char* what) {
     char buf[2048];     /* read buf bytes at a time */
-    char *p, *rbuf = 0, *endbuf, **q, **ret;
+    char *p, *rbuf = 0, *endbuf, **q, **ret, *strp;
     int fd, tot = 0, n, c, end_of_file = 0;
     int align;
 
-    sprintf(buf, "%s/%s", directory, what);
+    const int len = snprintf(buf, sizeof buf, "%s/%s", directory, what);
+    if(len <= 0 || (size_t)len >= sizeof buf) return NULL;
     fd = open(buf, O_RDONLY, 0);
-    if(fd==-1)
+    if(fd==-1) return NULL;
-        return NULL;
 
     /* read whole file into a memory buffer, allocating as we go */
     while ((n = read(fd, buf, sizeof buf - 1)) >= 0) {
         if (n < (int)(sizeof buf - 1))
             end_of_file = 1;
-        if (n == 0 && rbuf == 0) {
+        if (n <= 0 && tot <= 0) {  /* nothing read now, nothing read before */
-            close(fd);
+            break;                 /* process died between our open and read */
-            return NULL;        /* process died between our open and read */
         }
-        if (end_of_file && (n == 0 || buf[n-1]))/* last read char not null */
+        /* ARG_LEN is our guesstimated median length of a command-line argument
+           or environment variable (the minimum is 1, the maximum is 131072) */
+        #define ARG_LEN 64
+        if (tot >= INT_MAX / (ARG_LEN + (int)sizeof(char*)) * ARG_LEN - n) {
+            end_of_file = 1;       /* integer overflow: null-terminate and break */
+            n = 0;                 /* but tot > 0 */
+        }
+        #undef ARG_LEN
+        if (end_of_file &&
+            ((n > 0 && buf[n-1] != '\0') ||     /* last read char not null */
+             (n <= 0 && rbuf[tot-1] != '\0')))  /* last read char not null */
             buf[n++] = '\0';                    /* so append null-terminator */
+
+        if (n <= 0) break;         /* unneeded (end_of_file = 1) but avoid realloc */
         rbuf = realloc(rbuf, tot + n);          /* allocate more memory */
         if (!rbuf) return NULL;
         memcpy(rbuf + tot, buf, n);             /* copy buffer into it */
@@ -713,31 +724,36 @@ static char** file2strvec(const char* directory, const char* what) {
             break;
     }
     close(fd);
-    if (n <= 0 && !end_of_file) {
+    if (n < 0 || tot <= 0) {       /* error, or nothing read */
-        if (rbuf)
+        if (rbuf) free(rbuf);
-            free(rbuf);
+        return NULL;               /* read error */
-        return NULL;            /* read error */
     }
-    endbuf = rbuf + tot;                        /* count space for pointers */
+
+    rbuf[tot-1] = '\0';            /* belt and suspenders (the while loop did it, too) */
+    endbuf = rbuf + tot;           /* count space for pointers */
     align = (sizeof(char*)-1) - ((tot + sizeof(char*)-1) & (sizeof(char*)-1));
-    for (c = 0, p = rbuf; p < endbuf; p++) {
+    c = sizeof(char*);             /* one extra for NULL term */
-        if (!*p || *p == '\n')
+    for (p = rbuf; p < endbuf; p++) {
+        if (!*p || *p == '\n') {
+            if (c >= INT_MAX - (tot + (int)sizeof(char*) + align)) break;
             c += sizeof(char*);
+        }
         if (*p == '\n')
             *p = 0;
     }
-    c += sizeof(char*);                         /* one extra for NULL term */
 
     rbuf = realloc(rbuf, tot + c + align);      /* make room for ptrs AT END */
     if (!rbuf) return NULL;
     endbuf = rbuf + tot;                        /* addr just past data buf */
     q = ret = (char**) (endbuf+align);          /* ==> free(*ret) to dealloc */
-    *q++ = p = rbuf;                            /* point ptrs to the strings */
+    for (strp = p = rbuf; p < endbuf; p++) {
-    endbuf--;                                   /* do not traverse final NUL */
+        if (!*p) {                              /* NUL char implies that */
-    while (++p < endbuf)
+            if (c < 2 * (int)sizeof(char*)) break;
-        if (!*p)                                /* NUL char implies that */
+            c -= sizeof(char*);
-            *q++ = p+1;                         /* next string -> next char */
+            *q++ = strp;                        /* point ptrs to the strings */
-
+            strp = p+1;                         /* next string -> next char */
+        }
+    }
     *q = 0;                                     /* null ptr list terminator */
     return ret;
 }