Re: [PATCH v3 3/4] binfmt_elf: Provide prot bits as context for padzero() errors

["Eric W. Biederman" <ebiederm@xmission.com>]

Kees Cook <keescook@chromium.org> writes:

> Errors with padzero() should be caught unless we're expecting a
> pathological (non-writable) segment. Report -EFAULT only when PROT_WRITE
> is present.
>
> Additionally add some more documentation to padzero(), elf_map(), and
> elf_load().

I wonder if this might be easier to just perform the PROT_WRITE
test in elf_load, and to completely skip padzero of PROT_WRITE
is not present. 

Eric

> Cc: Eric Biederman <ebiederm@xmission.com>
> Cc: Alexander Viro <viro@zeniv.linux.org.uk>
> Cc: Christian Brauner <brauner@kernel.org>
> Cc: linux-fsdevel@vger.kernel.org
> Cc: linux-mm@kvack.org
> Suggested-by: Eric Biederman <ebiederm@xmission.com>
> Signed-off-by: Kees Cook <keescook@chromium.org>
> ---
>  fs/binfmt_elf.c | 33 +++++++++++++++++++++++----------
>  1 file changed, 23 insertions(+), 10 deletions(-)
>
> diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
> index 0214d5a949fc..b939cfe3215c 100644
> --- a/fs/binfmt_elf.c
> +++ b/fs/binfmt_elf.c
> @@ -110,19 +110,21 @@ static struct linux_binfmt elf_format = {
>  
>  #define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE))
>  
> -/* We need to explicitly zero any fractional pages
> -   after the data section (i.e. bss).  This would
> -   contain the junk from the file that should not
> -   be in memory
> +/*
> + * We need to explicitly zero any trailing portion of the page that follows
> + * p_filesz when it ends before the page ends (e.g. bss), otherwise this
> + * memory will contain the junk from the file that should not be present.
>   */
> -static int padzero(unsigned long elf_bss)
> +static int padzero(unsigned long address, int prot)
>  {
>  	unsigned long nbyte;
>  
> -	nbyte = ELF_PAGEOFFSET(elf_bss);
> +	nbyte = ELF_PAGEOFFSET(address);
>  	if (nbyte) {
>  		nbyte = ELF_MIN_ALIGN - nbyte;
> -		if (clear_user((void __user *) elf_bss, nbyte))
> +		/* Only report errors when the segment is writable. */
> +		if (clear_user((void __user *)address, nbyte) &&
> +		    prot & PROT_WRITE)
>  			return -EFAULT;
>  	}
>  	return 0;
> @@ -348,6 +350,11 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
>  	return 0;
>  }
>  
> +/*
> + * Map "eppnt->p_filesz" bytes from "filep" offset "eppnt->p_offset"
> + * into memory at "addr". (Note that p_filesz is rounded up to the
> + * next page, so any extra bytes from the file must be wiped.)
> + */
>  static unsigned long elf_map(struct file *filep, unsigned long addr,
>  		const struct elf_phdr *eppnt, int prot, int type,
>  		unsigned long total_size)
> @@ -387,6 +394,11 @@ static unsigned long elf_map(struct file *filep, unsigned long addr,
>  	return(map_addr);
>  }
>  
> +/*
> + * Map "eppnt->p_filesz" bytes from "filep" offset "eppnt->p_offset"
> + * into memory at "addr". Memory from "p_filesz" through "p_memsz"
> + * rounded up to the next page is zeroed.
> + */
>  static unsigned long elf_load(struct file *filep, unsigned long addr,
>  		const struct elf_phdr *eppnt, int prot, int type,
>  		unsigned long total_size)
> @@ -405,7 +417,8 @@ static unsigned long elf_load(struct file *filep, unsigned long addr,
>  				eppnt->p_memsz;
>  
>  			/* Zero the end of the last mapped page */
> -			padzero(zero_start);
> +			if (padzero(zero_start, prot))
> +				return -EFAULT;
>  		}
>  	} else {
>  		map_addr = zero_start = ELF_PAGESTART(addr);
> @@ -712,7 +725,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
>  	 * the file up to the page boundary, and zero it from elf_bss
>  	 * up to the end of the page.
>  	 */
> -	if (padzero(elf_bss)) {
> +	if (padzero(elf_bss, bss_prot)) {
>  		error = -EFAULT;
>  		goto out;
>  	}
> @@ -1407,7 +1420,7 @@ static int load_elf_library(struct file *file)
>  		goto out_free_ph;
>  
>  	elf_bss = eppnt->p_vaddr + eppnt->p_filesz;
> -	if (padzero(elf_bss)) {
> +	if (padzero(elf_bss, PROT_WRITE)) {
>  		error = -EFAULT;
>  		goto out_free_ph;
>  	}