[PATCH] mtd: jedec_probe: Fix crash in jedec_read_mfr()

Richard Weinberger richard at nod.at
Tue Mar 27 12:02:08 PDT 2018


Am Samstag, 3. März 2018, 23:29:03 CEST schrieb Linus Walleij:
> It turns out that the loop where we read manufacturer
> jedec_read_mfd() can under some circumstances get a
> CFI_MFR_CONTINUATION repeatedly, making the loop go
> over all banks and eventually hit the end of the
> map and crash because of an access violation:
> 
> Unable to handle kernel paging request at virtual address c4980000
> pgd = (ptrval)
> [c4980000] *pgd=03808811, *pte=00000000, *ppte=00000000
> Internal error: Oops: 7 [#1] PREEMPT ARM
> CPU: 0 PID: 1 Comm: swapper Not tainted 4.16.0-rc1+ #150
> Hardware name: Gemini (Device Tree)
> PC is at jedec_probe_chip+0x6ec/0xcd0
> LR is at 0x4
> pc : [<c03a2bf4>]    lr : [<00000004>]    psr: 60000013
> sp : c382dd18  ip : 0000ffff  fp : 00000000
> r10: c0626388  r9 : 00020000  r8 : c0626340
> r7 : 00000000  r6 : 00000001  r5 : c3a71afc  r4 : c382dd70
> r3 : 00000001  r2 : c4900000  r1 : 00000002  r0 : 00080000
> Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
> Control: 0000397f  Table: 00004000  DAC: 00000053
> Process swapper (pid: 1, stack limit = 0x(ptrval))
> 
> Fix this by breaking the loop with a return 0 if
> the offset exceeds the map size.
> 
> Signed-off-by: Linus Walleij <linus.walleij at linaro.org>
> ---
>  drivers/mtd/chips/jedec_probe.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/drivers/mtd/chips/jedec_probe.c
> b/drivers/mtd/chips/jedec_probe.c index 7c0b27d132b1..b479bd81120b 100644
> --- a/drivers/mtd/chips/jedec_probe.c
> +++ b/drivers/mtd/chips/jedec_probe.c
> @@ -1889,6 +1889,8 @@ static inline u32 jedec_read_mfr(struct map_info *map,
> uint32_t base, do {
>  		uint32_t ofs = cfi_build_cmd_addr(0 + (bank << 8), map, cfi);
>  		mask = (1 << (cfi->device_type * 8)) - 1;
> +		if (ofs >= map->size)
> +			return 0;
>  		result = map_read(map, base + ofs);
>  		bank++;
>  	} while ((result.x[0] & mask) == CFI_MFR_CONTINUATION);

The fix is legit but I'm not sure whether we should emit a warning in this 
case too since something is obviously wrong.
Boris?

Thanks,
//richard



More information about the linux-mtd mailing list