lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <b62e658a-a35c-4fa8-9674-2d3a12266176@nvidia.com>
Date: Sun, 9 Nov 2025 19:05:25 +0000
From: Chaitanya Kulkarni <chaitanyak@...dia.com>
To: Ming Lei <ming.lei@...hat.com>, Caleb Sander Mateos
	<csander@...estorage.com>
CC: Jens Axboe <axboe@...nel.dk>, Damien Le Moal <dlemoal@...nel.org>,
	Christoph Hellwig <hch@....de>, "linux-block@...r.kernel.org"
	<linux-block@...r.kernel.org>, "linux-kernel@...r.kernel.org"
	<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 1/2] loop: use blk_rq_nr_phys_segments() instead of
 iterating bvecs

On 11/9/25 04:19, Ming Lei wrote:
> On Sat, Nov 08, 2025 at 04:01:00PM -0700, Caleb Sander Mateos wrote:
>> The number of bvecs can be obtained directly from struct request's
>> nr_phys_segments field via blk_rq_nr_phys_segments(), so use that
>> instead of iterating over the bvecs an extra time.
>>
>> Signed-off-by: Caleb Sander Mateos <csander@...estorage.com>
>> ---
>>   drivers/block/loop.c | 5 +----
>>   1 file changed, 1 insertion(+), 4 deletions(-)
>>
>> diff --git a/drivers/block/loop.c b/drivers/block/loop.c
>> index 13ce229d450c..8096478fad45 100644
>> --- a/drivers/block/loop.c
>> +++ b/drivers/block/loop.c
>> @@ -346,16 +346,13 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
>>   	struct request *rq = blk_mq_rq_from_pdu(cmd);
>>   	struct bio *bio = rq->bio;
>>   	struct file *file = lo->lo_backing_file;
>>   	struct bio_vec tmp;
>>   	unsigned int offset;
>> -	int nr_bvec = 0;
>> +	unsigned short nr_bvec = blk_rq_nr_phys_segments(rq);
>>   	int ret;
>>   
>> -	rq_for_each_bvec(tmp, rq, rq_iter)
>> -		nr_bvec++;
>> -
> The two may not be same, since one bvec can be splitted into multiple segments.
>
> Thanks,
> Ming
>
>

I had this patch only to realize this :-

bvec_split_segs():-
* When splitting a bio, it can happen that a bvec is encountered that is too
* big to fit in a single segment and hence that it has to be split in the
* middle. This function verifies whether or not that should happen. The 
value
* %true is returned if and only if appending the entire @bv to a bio with
* *@...gs segments and *@...tors sectors would make that bio 
unacceptable for
* the block driver.

if following messup the indentation after I send plz ignore :-

submit_bio()
   -> submit_bio_noacct()
     -> __submit_bio_noacct()
       -> __submit_bio()
         -> blk_mq_submit_bio()
           -> __bio_split_to_limits()
             -> bio_split_rw()
               -> bio_split_rw_at()
                 -> bio_split_io_at()

                   -- bio_for_each_bvec()   (iterate all bvecs)
                    -- [Fast path]
                         nsegs++             (1 bvec = 1 segment)
                         bytes += bv.bv_len
                    -- [Slow path]
                       /* one bv is passed from bio bvec list  */
                       -> bvec_split_segs(lim, &bv, &nsegs, &bytes,
                                          lim->max_segments, max_bytes)

                            /* working on one bvec and associated 
segments */
                            -- while (len && *nsegs < max_segs) {

                                 ...

                                 get_max_segment_size()
                                   -> min(len,
                                          seg_boundary_mask - offset,
                                          max_segment_size)

                                 (*nsegs)++
                                 total_len += seg_size
                                 len -= seg_size

                                 ...

                               }

                            -- *bytes += total_len
                            -- return (len > 0)

           -> blk_mq_bio_to_request()
                rq->nr_phys_segments = nr_segs

-ck



Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ