[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210609014822.GT3697498@iweiny-DESK2.sc.intel.com>
Date: Tue, 8 Jun 2021 18:48:22 -0700
From: Ira Weiny <ira.weiny@...el.com>
To: Christoph Hellwig <hch@....de>
Cc: Jens Axboe <axboe@...nel.dk>,
Thomas Bogendoerfer <tsbogend@...ha.franken.de>,
Geoff Levand <geoff@...radead.org>,
Ilya Dryomov <idryomov@...il.com>,
Dongsheng Yang <dongsheng.yang@...ystack.cn>,
Mike Snitzer <snitzer@...hat.com>, dm-devel@...hat.com,
linux-mips@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-block@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org,
ceph-devel@...r.kernel.org
Subject: Re: [PATCH 09/16] ps3disk: use memcpy_{from,to}_bvec
On Tue, Jun 08, 2021 at 06:05:56PM +0200, Christoph Hellwig wrote:
>
> rq_for_each_segment(bvec, req, iter) {
> - unsigned long flags;
> - dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %llu\n",
> - __func__, __LINE__, i, bio_sectors(iter.bio),
> - iter.bio->bi_iter.bi_sector);
> -
> - size = bvec.bv_len;
> - buf = bvec_kmap_irq(&bvec, &flags);
> if (gather)
> - memcpy(dev->bounce_buf+offset, buf, size);
> + memcpy_from_bvec(dev->bounce_buf + offset, &bvec);
> else
> - memcpy(buf, dev->bounce_buf+offset, size);
> - offset += size;
> - flush_kernel_dcache_page(bvec.bv_page);
I'm still not 100% sure that these flushes are needed but the are not no-ops on
every arch. Would it be best to preserve them after the memcpy_to/from_bvec()?
Same thing in patch 11 and 14.
Ira
Powered by blists - more mailing lists