[Crash-utility] [PATCH] Improve error handling when architecture doesn't match

[Dave Anderson]

Bernhard Walle wrote:
> Currently, crash prints always
> 
>         crash: vmcore: not a supported file format
> 
> if you try to open a dump file which is not supported. However, it can be
> misleading if you have a valid ELF core dump, but just use crash for the wrong
> architecture. In the case I observed the user had a ELF64 x86 dump file and
> assumed it's x86-64. However, it just was a i386 core dump which was ELF64
> because kexec was called with --elf64-core-headers which makes sense
> if the i386 machine has PAE and possibly more than 4 GiB of physical RAM.
> 
> After that patch is applied, an example output is
> 
>         Looks like a valid ELF dump, but host architecture (X86_64) \
>         doesn't match dump architecture (IA64).
> 
> or if I try to open a PPC64 dump on x86-64:
> 
>         Looks like a valid ELF dump, but host endianess (LE) \
>         doesn't match target endianess (BE)
> 
> Please review and consider applying.

I like the addition of the machine-type verification error message.

But why bother with the endian check?  Using your ppc64/x86_64
example, an architecture check/error message would make far
more sense.  The "endianness" error message implies that if
they re-compiled their ppc64 kernel little-endian that things
would work.

Dave



> 
> 
> Signed-off-by: Bernhard Walle <bwalle at suse.de>
> 
> ---
>  defs.h    |    3 ++-
>  netdump.c |   48 +++++++++++++++++++++++++++++++++++++++++++-----
>  tools.c   |    9 ++++++++-
>  3 files changed, 53 insertions(+), 7 deletions(-)
> 
> --- a/defs.h
> +++ b/defs.h
> @@ -3198,7 +3198,8 @@ void stall(ulong);
>  char *pages_to_size(ulong, char *);
>  int clean_arg(void);
>  int empty_list(ulong);
> -int machine_type(char *);
> +int machine_type(const char *);
> +int is_big_endian(void);
>  void command_not_supported(void);
>  void option_not_supported(int);
>  void please_wait(char *);
> --- a/netdump.c
> +++ b/netdump.c
> @@ -36,6 +36,32 @@ static void check_dumpfile_size(char *);
>  #define ELFREAD  0
>  
>  #define MIN_PAGE_SIZE (4096)
> +
> +
> +/*
> + * Checks if the machine type of the host matches required_type.
> + * If not, it prints a short error message for the user.
> + */
> +static int machine_type_error(const char *required_type)
> +{
> +	if (machine_type(required_type))
> +		return 1;
> +	else {
> +		fprintf(stderr, "Looks like a valid ELF dump, but host "
> +				"architecture (%s) doesn't match dump "
> +				"architecture (%s).\n",
> +				MACHINE_TYPE, required_type);
> +		return 0;
> +	}
> +}
> +
> +/*
> + * Returns endianess in a string
> + */
> +static const char *endianess_to_string(int big_endian)
> +{
> +	return big_endian ? "BE" : "LE";
> +}
>  	
>  /*
>   *  Determine whether a file is a netdump/diskdump/kdump creation, 
> @@ -98,6 +124,18 @@ is_netdump(char *file, ulong source_quer
>  	 *  If either kdump difference is seen, presume kdump -- this
>  	 *  is obviously subject to change.
>  	 */
> +
> +	/* check endianess */
> +	if ((STRNEQ(elf32->e_ident, ELFMAG) || STRNEQ(elf64->e_ident, ELFMAG)) &&
> +			(elf32->e_type == ET_CORE || elf64->e_type == ET_CORE) &&
> +			(elf32->e_ident[EI_DATA] == ELFDATA2LSB && is_big_endian()) ||
> +			(elf32->e_ident[EI_DATA] == ELFDATA2MSB && !is_big_endian()))
> +		fprintf(stderr, "Looks like a valid ELF dump, but host "
> +				"endianess (%s) doesn't match target "
> +				"endianess (%s)\n",
> +			endianess_to_string(is_big_endian()),
> +			endianess_to_string(elf32->e_ident[EI_DATA] == ELFDATA2MSB));
> +
>          if (STRNEQ(elf32->e_ident, ELFMAG) && 
>  	    (elf32->e_ident[EI_CLASS] == ELFCLASS32) &&
>    	    (elf32->e_ident[EI_DATA] == ELFDATA2LSB) &&
> @@ -108,7 +146,7 @@ is_netdump(char *file, ulong source_quer
>  		switch (elf32->e_machine)
>  		{
>  		case EM_386:
> -			if (machine_type("X86"))
> +			if (machine_type_error("X86"))
>  				break;
>  		default:
>                  	goto bailout;
> @@ -133,28 +171,28 @@ is_netdump(char *file, ulong source_quer
>  		{
>  		case EM_IA_64:
>  			if ((elf64->e_ident[EI_DATA] == ELFDATA2LSB) &&
> -				machine_type("IA64"))
> +				machine_type_error("IA64"))
>  				break;
>  			else
>  				goto bailout;
>  
>  		case EM_PPC64:
>  			if ((elf64->e_ident[EI_DATA] == ELFDATA2MSB) &&
> -				machine_type("PPC64"))
> +				machine_type_error("PPC64"))
>  				break;
>  			else
>  				goto bailout;
>  
>  		case EM_X86_64:
>  			if ((elf64->e_ident[EI_DATA] == ELFDATA2LSB) &&
> -				machine_type("X86_64"))
> +				machine_type_error("X86_64"))
>  				break;
>  			else
>  				goto bailout;
>  
>  		case EM_386:
>  			if ((elf64->e_ident[EI_DATA] == ELFDATA2LSB) &&
> -				machine_type("X86"))
> +				machine_type_error("X86"))
>  				break;
>  			else
>  				goto bailout;
> --- a/tools.c
> +++ b/tools.c
> @@ -4518,11 +4518,18 @@ empty_list(ulong list_head_addr)
>  }
>  
>  int
> -machine_type(char *type)
> +machine_type(const char *type)
>  {
>  	return STREQ(MACHINE_TYPE, type);
>  }
>  
> +int
> +is_big_endian(void)
> +{
> +	unsigned short value = 0xff;
> +	return *((unsigned char *)&value) != 0xff;
> +}
> +
>  void
>  command_not_supported()
>  {
> 
> --
> Crash-utility mailing list
> Crash-utility at redhat.com
> https://www.redhat.com/mailman/listinfo/crash-utility