Coverity: iwl_dbg_tlv_alloc_fragment(): Control flow issues

Coverity: iwl_dbg_tlv_alloc_fragment(): Control flow issues

[coverity-bot]

Hello!

This is an experimental automated report about issues detected by Coverity
from a scan of next-20191031 as part of the linux-next weekly scan project:
https://scan.coverity.com/projects/linux-next-weekly-scan

You're getting this email because you were associated with the identified
lines of code (noted below) that were touched by recent commits:

14124b25780d ("iwlwifi: dbg_ini: implement monitor allocation flow")

Coverity reported the following:

*** CID 1487402:  Control flow issues  (DEADCODE)
/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c: 497 in iwl_dbg_tlv_alloc_fragment()
491     			 pages * PAGE_SIZE);
492
493     		pages = DIV_ROUND_UP(pages, 2);
494     	}
495
496     	if (!block)
vvv     CID 1487402:  Control flow issues  (DEADCODE)
vvv     Execution cannot reach this statement: "return -12;".
497     		return -ENOMEM;
498
499     	frag->physical = physical;
500     	frag->block = block;
501     	frag->size = pages * PAGE_SIZE;
502

If this is a false positive, please let us know so we can mark it as
such, or teach the Coverity rules to be smarter. If not, please make
sure fixes get into linux-next. :) For patches fixing this, please
include these lines (but double-check the "Fixes" first):

Reported-by: coverity-bot <keescook+coverity-bot@chromium.org>
Addresses-Coverity-ID: 1487402 ("Control flow issues")
Fixes: 14124b25780d ("iwlwifi: dbg_ini: implement monitor allocation flow")


Thanks for your attention!

-- 
Coverity-bot

Re: Coverity: iwl_dbg_tlv_alloc_fragment(): Control flow issues

[Luciano Coelho]

On Mon, 2019-11-04 at 09:37 -0800, coverity-bot wrote:
> Hello!
> 
> This is an experimental automated report about issues detected by Coverity
> from a scan of next-20191031 as part of the linux-next weekly scan project:
> https://scan.coverity.com/projects/linux-next-weekly-scan
> 
> You're getting this email because you were associated with the identified
> lines of code (noted below) that were touched by recent commits:
> 
> 14124b25780d ("iwlwifi: dbg_ini: implement monitor allocation flow")
> 
> Coverity reported the following:
> 
> *** CID 1487402:  Control flow issues  (DEADCODE)
> /drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c: 497 in iwl_dbg_tlv_alloc_fragment()
> 491     			 pages * PAGE_SIZE);
> 492
> 493     		pages = DIV_ROUND_UP(pages, 2);
> 494     	}
> 495
> 496     	if (!block)
> vvv     CID 1487402:  Control flow issues  (DEADCODE)
> vvv     Execution cannot reach this statement: "return -12;".
> 497     		return -ENOMEM;
> 498
> 499     	frag->physical = physical;
> 500     	frag->block = block;
> 501     	frag->size = pages * PAGE_SIZE;
> 502
> 
> If this is a false positive, please let us know so we can mark it as
> such, or teach the Coverity rules to be smarter. If not, please make
> sure fixes get into linux-next. :) For patches fixing this, please
> include these lines (but double-check the "Fixes" first):
> 
> Reported-by: coverity-bot <keescook+coverity-bot@chromium.org>
> Addresses-Coverity-ID: 1487402 ("Control flow issues")
> Fixes: 14124b25780d ("iwlwifi: dbg_ini: implement monitor allocation flow")
> 
> 
> Thanks for your attention!

Hi,

This is a good catch! We have a loop:

	while (pages) {
		block = dma_alloc_coherent(fwrt->dev, pages * PAGE_SIZE,
					   &physical,
					   GFP_KERNEL | __GFP_NOWARN);
		if (block)
			break;

		IWL_WARN(fwrt, "WRT: Failed to allocate fragment size %lu\n",
			 pages * PAGE_SIZE);

		pages = DIV_ROUND_UP(pages, 2);
	}

	if (!block)
		return -ENOMEM;

Which seems like it will keep trying allocate smaller and smaller
blocks until it succeeds.  But "pages" will never become zero (because
of the DIV_ROUND_UP), so if we can't allocate any size and pages
becomes 1, we will keep trying to allocate 1 page until it succeeds. 
And in that case, as coverity reported, block will never be NULL.

I'll add a fix to this in our internal tree and it will reach the
mainline following our normal upstream process.

--
Cheers,
Luca.