Question

In the Code below I am trying to recreate scanf to read everything from the stdin and break on the new line character returning all the characters read in a string.

But the problem is that the code leaks some memory especially when realloc gets invoked.

I would also like to know why is gets a dangerous function to use

test.c: warning: the 'gets' function is dangerous and should not be used.

My Code:-

#include <stdio.h>
#include <string.h>
#include <stdlib.h>

#define MAX_BUF_LEN 128
#define __cdecl

//0 - Success
//-1 - Error in input
//1 - Error
__cdecl int read_input(char *s,int len){

char c,*t;
int l,i=0;

if(s==NULL || len < 1)
    return -1;

while((c=getchar()) != '\n'){

    //check if sufficient memory
    //required + used > assigned 
    l=strlen(s);
    if(l + 2 > len){

        len += l + MAX_BUF_LEN;     //realloc max to avoid subsequent realloc as its costly!

        t = realloc(s,len);
        if(t!=NULL)
            s = t;
        else
            return 1;               //No space to store content
    }

    s[i++] = c;

}

s[i++] = '\0';      //Null terminate the Buffer
return 0;   
}

int main(int argc,char* argv[]){

int len = 5+1;
char *s = calloc(len,sizeof(char));

printf("Enter your name\n");

if(!read_input(s,len))
    printf("Hi %s\n",s);

free(s);

return 0;
}

Valgrind :

nimish:~/Desktop$ gcc -g -Wall test.c -o test
nimish~/Desktop$ clear && valgrind ./test  --leak-check=full

==3670== Memcheck, a memory error detector
==3670== Copyright (C) 2002-2010, and GNU GPL'd, by Julian Seward et al.
==3670== Using Valgrind-3.6.1 and LibVEX; rerun with -h for copyright info
==3670== Command: ./test --leak-check=full
==3670== 
Enter your name
Nimish Nicolus
==3670== Conditional jump or move depends on uninitialised value(s)
==3670==    at 0x4027029: strlen (mc_replace_strmem.c:282)
==3670==    by 0x804850E: read_input (test.c:23)
==3670==    by 0x80485CD: main (test.c:51)
==3670== 
==3670== Invalid read of size 1
==3670==    at 0x40831BF: vfprintf (vfprintf.c:1623)
==3670==    by 0x40891BF: printf (printf.c:35)
==3670==    by 0x80485E6: main (test.c:52)
==3670==  Address 0x41a5028 is 0 bytes inside a block of size 6 free'd
==3670==    at 0x402695A: realloc (vg_replace_malloc.c:525)
==3670==    by 0x8048537: read_input (test.c:28)
==3670==    by 0x80485CD: main (test.c:51)
==3670== 
==3670== Invalid read of size 1
==3670==    at 0x40A93A8: _IO_file_xsputn@@GLIBC_2.1 (fileops.c:1317)
==3670==    by 0x408346F: vfprintf (vfprintf.c:1623)
==3670==    by 0x40891BF: printf (printf.c:35)
==3670==    by 0x80485E6: main (test.c:52)
==3670==  Address 0x41a502c is 4 bytes inside a block of size 6 free'd
==3670==    at 0x402695A: realloc (vg_replace_malloc.c:525)
==3670==    by 0x8048537: read_input (test.c:28)
==3670==    by 0x80485CD: main (test.c:51)
==3670== 
==3670== Invalid read of size 1
==3670==    at 0x40A93BF: _IO_file_xsputn@@GLIBC_2.1 (fileops.c:1317)
==3670==    by 0x408346F: vfprintf (vfprintf.c:1623)
==3670==    by 0x40891BF: printf (printf.c:35)
==3670==    by 0x80485E6: main (test.c:52)
==3670==  Address 0x41a502b is 3 bytes inside a block of size 6 free'd
==3670==    at 0x402695A: realloc (vg_replace_malloc.c:525)
==3670==    by 0x8048537: read_input (test.c:28)
==3670==    by 0x80485CD: main (test.c:51)
==3670== 
==3670== Invalid read of size 1
==3670==    at 0x40A9330: _IO_file_xsputn@@GLIBC_2.1 (fileops.c:1349)
==3670==    by 0x408346F: vfprintf (vfprintf.c:1623)
==3670==    by 0x40891BF: printf (printf.c:35)
==3670==    by 0x80485E6: main (test.c:52)
==3670==  Address 0x41a5028 is 0 bytes inside a block of size 6 free'd
==3670==    at 0x402695A: realloc (vg_replace_malloc.c:525)
==3670==    by 0x8048537: read_input (test.c:28)
==3670==    by 0x80485CD: main (test.c:51)
==3670== 
==3670== Invalid read of size 1
==3670==    at 0x40A933C: _IO_file_xsputn@@GLIBC_2.1 (fileops.c:1348)
==3670==    by 0x408346F: vfprintf (vfprintf.c:1623)
==3670==    by 0x40891BF: printf (printf.c:35)
==3670==    by 0x80485E6: main (test.c:52)
==3670==  Address 0x41a502a is 2 bytes inside a block of size 6 free'd
==3670==    at 0x402695A: realloc (vg_replace_malloc.c:525)
==3670==    by 0x8048537: read_input (test.c:28)
==3670==    by 0x80485CD: main (test.c:51)
==3670== 
Hi Nimis
==3670== Invalid free() / delete / delete[]
==3670==    at 0x4025BF0: free (vg_replace_malloc.c:366)
==3670==    by 0x80485F2: main (test.c:54)
==3670==  Address 0x41a5028 is 0 bytes inside a block of size 6 free'd
==3670==    at 0x402695A: realloc (vg_replace_malloc.c:525)
==3670==    by 0x8048537: read_input (test.c:28)
==3670==    by 0x80485CD: main (test.c:51)
==3670== 
==3670== 
==3670== HEAP SUMMARY:
==3670==     in use at exit: 139 bytes in 1 blocks
==3670==   total heap usage: 2 allocs, 2 frees, 145 bytes allocated
==3670== 
==3670== LEAK SUMMARY:
==3670==    definitely lost: 139 bytes in 1 blocks
==3670==    indirectly lost: 0 bytes in 0 blocks
==3670==      possibly lost: 0 bytes in 0 blocks
==3670==    still reachable: 0 bytes in 0 blocks
==3670==         suppressed: 0 bytes in 0 blocks
==3670== Rerun with --leak-check=full to see details of leaked memory
==3670== 
==3670== For counts of detected and suppressed errors, rerun with: -v
==3670== Use --track-origins=yes to see where uninitialised values come from
==3670== ERROR SUMMARY: 23 errors from 7 contexts (suppressed: 11 from 6)

EDIT :- PLEASE REFER TO THE NEW CODE ATTACHED BELOW

New Code :-

__cdecl int read_input(char **s,int len){

char c,*t;
int l,i=0;

if((*s)==NULL || len < 1)
    return -1;

while((c=getchar()) != '\n'){

    //check if sufficient memory
    //required + used > assigned 
    l=strlen((*s));
    if(l + 2 > len){

        len += l + MAX_BUF_LEN;     //realloc max to avoid subsequent realloc as its costly!

        t = realloc((*s),len);
        if(t!=NULL)
            (*s) = t;
        else
            return 1;               //No space to store content
    }

    *((*s)+i++) = c;

}

*((*s)+i) = '\0';       //Null terminate the Buffer
return 0;   
} 

Valgrind :

==4767== Memcheck, a memory error detector
==4767== Copyright (C) 2002-2010, and GNU GPL'd, by Julian Seward et al.
==4767== Using Valgrind-3.6.1 and LibVEX; rerun with -h for copyright info
==4767== Command: ./test --leak-check=full
==4767== 
Enter your name
Nimish Nicolus
==4767== Conditional jump or move depends on uninitialised value(s)
==4767==    at 0x4027029: strlen (mc_replace_strmem.c:282)
==4767==    by 0x8048516: read_input (test.c:23)
==4767==    by 0x80485DE: main (test.c:51)
==4767== 
Hi Nimish Nicolus
==4767== 
==4767== HEAP SUMMARY:
==4767==     in use at exit: 0 bytes in 0 blocks
==4767==   total heap usage: 2 allocs, 2 frees, 145 bytes allocated
==4767== 
==4767== All heap blocks were freed -- no leaks are possible
==4767== 
==4767== For counts of detected and suppressed errors, rerun with: -v
==4767== Use --track-origins=yes to see where uninitialised values come from
==4767== ERROR SUMMARY: 6 errors from 1 contexts (suppressed: 11 from 6)

It still gives some issue.

Answer 1

Here is what the manual has to say about gets problem:

Never use gets(). Because it is impossible to tell without knowing the data in advance how many characters gets() will read, and because gets() will continue to store characters past the end of the buffer, it is extremely dangerous to use. It has been used to break computer security. Use fgets() instead.

The leak problem happens because the pointer s is passed by value, so any changes, including assignments after reallocation, are done to its copy, not to the original pointer. As a consequence, freeing s frees only the memory that has been allocated originally, leaking the realloc-ed one. To fix this, change read_input to take a pointer to a pointer, like this:

int read_input(char **ps,int len)

Pass &s to read_input, and use (*ps) in place of s in the body of the function.