Vectored AIO breakage for sockets and pipes ?

The call to aio_advance_iovec() in aio_rw_vect_retry() becomes problematic
when it comes to pipe and socket operations which internally modify/advance
the iovec themselves. As a result AIO writes to sockets fail to return
the correct result. 

I'm not sure what the best way to fix this is. One option is to always make
a copy of the iovec and pass that down. Any other thoughts ?

Regards
Suparna

-- 
Suparna Bhattacharya ([email protected])
Linux Technology Center
IBM Software Lab, India

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Follow-Ups:
- Re: Vectored AIO breakage for sockets and pipes ?
  - From: Zach Brown <[email protected]>

References:
- [PATCH -mm 0/10][RFC] aio: make struct kiocb private
  - From: Nate Diller <[email protected]>
- [PATCH -mm 3/10][RFC] aio: use iov_length instead of ki_left
  - From: Nate Diller <[email protected]>
- Re: [PATCH -mm 3/10][RFC] aio: use iov_length instead of ki_left
  - From: Christoph Hellwig <[email protected]>

Prev by Date: Re: problems with latest smbfs changes on 2.4.34 and security backports
Next by Date: Re: query related to serial console
Previous by thread: Re: [PATCH -mm 3/10][RFC] aio: use iov_length instead of ki_left
Next by thread: Re: Vectored AIO breakage for sockets and pipes ?
Index(es):
- Date
- Thread

[Index of Archives] [Kernel Newbies] [Netfilter] [Bugtraq] [Photo] [Stuff] [Gimp] [Yosemite News] [MIPS Linux] [ARM Linux] [Linux Security] [Linux RAID] [Video 4 Linux] [Linux for the blind] [Linux Resources]