[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <Y+EhOHVZWLjTq26h@infradead.org>
Date: Mon, 6 Feb 2023 07:48:08 -0800
From: Christoph Hellwig <hch@...radead.org>
To: David Howells <dhowells@...hat.com>
Cc: Steve French <smfrench@...il.com>,
Al Viro <viro@...iv.linux.org.uk>,
Shyam Prasad N <nspmangalore@...il.com>,
Rohith Surabattula <rohiths.msft@...il.com>,
Tom Talpey <tom@...pey.com>,
Stefan Metzmacher <metze@...ba.org>,
Christoph Hellwig <hch@...radead.org>,
Matthew Wilcox <willy@...radead.org>,
Jeff Layton <jlayton@...nel.org>, linux-cifs@...r.kernel.org,
linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
Steve French <sfrench@...ba.org>
Subject: Re: [PATCH 03/11] cifs: Implement splice_read to pass down ITER_BVEC
not ITER_PIPE
On Fri, Feb 03, 2023 at 08:59:21PM +0000, David Howells wrote:
> Provide cifs_splice_read() to use a bvec rather than an pipe iterator as
> the latter cannot so easily be split and advanced, which is necessary to
> pass an iterator down to the bottom levels. Upstream cifs gets around this
> problem by using iov_iter_get_pages() to prefill the pipe and then passing
> the list of pages down.
Just as last time: if cifs has a problem with splitting these iters
so does everyone else. What about solving the root cause here?
If the splice isn't actually a splice you might as well not implement
it.
Powered by blists - more mailing lists