From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Date: Wed, 23 Apr 2008 07:08:50 +0000 Subject: Re: blktrace/relay/s390: Oops in subbuf_splice_actor Message-Id: <20080423070850.GV12774@kernel.dk> List-Id: References: <20080314084337.GA9436@schmichrtp.de.ibm.com> <20080314115802.GK17940@kernel.dk> <20080314130552.GA9352@schmichrtp.de.ibm.com> <20080314131007.GQ17940@kernel.dk> <20080314132238.GA9815@schmichrtp.de.ibm.com> <1207628587.7535.8.camel@charm-linux> <20080423070605.GA5450@schmichrtp.de.ibm.com> In-Reply-To: <20080423070605.GA5450@schmichrtp.de.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Christof Schmitt Cc: Tom Zanussi , linux-btrace@vger.kernel.org, linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org, wilder@us.ibm.com On Wed, Apr 23 2008, Christof Schmitt wrote: > On Mon, Apr 07, 2008 at 11:23:07PM -0500, Tom Zanussi wrote: > > > Dave, can you have a look at this? I can easily reproduce the problem > > > on s390 Linux for testing and getting more debug information. > > > > > > > Not sure anyone's still looking into this, but it doesn't look like an > > s390 problem specifically. Apparently what happened was that some > > internal changes to splice seem to have broken the relay splice_read > > implementation. The above patch fixes part of the problem; the patch > > below should fix the rest, and AFAICT it doesn't break anything else. > > > > Signed-off-by: Tom Zanussi > > > > diff --git a/fs/splice.c b/fs/splice.c > > index a861bb3..068b210 100644 > > --- a/fs/splice.c > > +++ b/fs/splice.c > > @@ -1094,7 +1094,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, > > > > ret = splice_direct_to_actor(in, &sd, direct_splice_actor); > > if (ret > 0) > > - *ppos += ret; > > + *ppos = sd.pos; > > > > return ret; > > } > > diff --git a/kernel/relay.c b/kernel/relay.c > > index d6204a4..dc873fb 100644 > > --- a/kernel/relay.c > > +++ b/kernel/relay.c > > @@ -1162,7 +1162,7 @@ static ssize_t relay_file_splice_read(struct file *in, > > ret = 0; > > spliced = 0; > > > > - while (len) { > > + while (len && !spliced) { > > ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret); > > if (ret < 0) > > break; > > > > > > Sorry for the late response and yes, our tests on s390 are still > tracking the issue. I just ran a short test on 2.6.25 with the above > patch applied. With this patch, blktrace client/server mode works > again with the sendfile() call and returns valid data for blkparse. > > Thanks everybody for helping with this problem. > > Jens, will you pick up this patch for inclusion? Certainly, thanks to Tom for providing this and you for testing! -- Jens Axboe