Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755640AbYJPGNx (ORCPT ); Thu, 16 Oct 2008 02:13:53 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755350AbYJPGMQ (ORCPT ); Thu, 16 Oct 2008 02:12:16 -0400 Received: from qmta08.emeryville.ca.mail.comcast.net ([76.96.30.80]:48489 "EHLO QMTA08.emeryville.ca.mail.comcast.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753100AbYJPGMO (ORCPT ); Thu, 16 Oct 2008 02:12:14 -0400 X-Authority-Analysis: v=1.0 c=1 a=CNcTrfTLiWAA:10 a=bx5Grbjpcb4A:10 a=l-ZSAgIrRNUgVz6KjyUA:9 a=KDWFIvr0pmJXXMCNE40A:7 a=Z_jyhY5sXCqWwpwD41YDapm4io8A:4 a=vNGxQsTWjH8A:10 Subject: [RFC PATCH 5/21] relay - Map the first sub-buffer at the end of the buffer, for temporary convenience. From: Tom Zanussi To: Linux Kernel Mailing List Cc: Martin Bligh , Peter Zijlstra , prasad@linux.vnet.ibm.com, Linus Torvalds , Thomas Gleixner , Mathieu Desnoyers , Steven Rostedt , od@suse.com, "Frank Ch. Eigler" , Andrew Morton , hch@lst.de, David Wilder , Jens Axboe , Pekka Enberg , Eduard - Gabriel Munteanu Content-Type: text/plain Date: Thu, 16 Oct 2008 01:05:47 -0500 Message-Id: <1224137148.16328.224.camel@charm-linux> Mime-Version: 1.0 X-Mailer: Evolution 2.12.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2720 Lines: 84 Make relay buffers 'circular' for writing by mapping the first subbuf at end of last subbuf. This is so we can do writes across last subbuf boundary without adding special write logic. This is a temporary state of affairs and it all goes away in a future patch, but it's here now so things will still work. --- kernel/relay.c | 26 +++++++++++++++----------- 1 files changed, 15 insertions(+), 11 deletions(-) diff --git a/kernel/relay.c b/kernel/relay.c index 6c7698a..e9dd976 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -125,20 +125,20 @@ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) /** * relay_alloc_buf - allocate a channel buffer * @buf: the buffer struct - * @size: total size of the buffer * * Returns a pointer to the resulting buffer, %NULL if unsuccessful. The * passed in size will get page aligned, if it isn't already. */ -static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size) +static void *relay_alloc_buf(struct rchan_buf *buf) { void *mem; - unsigned int i, j, n_pages; + unsigned int i, j, n_pages, n_subbuf_pages; - *size = PAGE_ALIGN(*size); - n_pages = *size >> PAGE_SHIFT; + buf->chan->alloc_size = PAGE_ALIGN(buf->chan->alloc_size); + n_pages = buf->chan->alloc_size >> PAGE_SHIFT; + n_subbuf_pages = PAGE_ALIGN(buf->chan->subbuf_size) >> PAGE_SHIFT; - buf->page_array = relay_alloc_page_array(n_pages); + buf->page_array = relay_alloc_page_array(n_pages + n_subbuf_pages); if (!buf->page_array) return NULL; @@ -148,11 +148,14 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size) goto depopulate; set_page_private(buf->page_array[i], (unsigned long)buf); } - mem = vmap(buf->page_array, n_pages, VM_MAP, PAGE_KERNEL); + for (i = 0; i < n_subbuf_pages; i++) + buf->page_array[n_pages + i] = buf->page_array[i]; + mem = vmap(buf->page_array, n_pages + n_subbuf_pages, VM_MAP, + PAGE_KERNEL); if (!mem) goto depopulate; - memset(mem, 0, *size); + memset(mem, 0, buf->chan->alloc_size); buf->page_count = n_pages; return mem; @@ -179,12 +182,13 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) if (!buf->padding) goto free_buf; - buf->start = relay_alloc_buf(buf, &chan->alloc_size); + buf->chan = chan; + kref_get(&buf->chan->kref); + + buf->start = relay_alloc_buf(buf); if (!buf->start) goto free_buf; - buf->chan = chan; - kref_get(&buf->chan->kref); return buf; free_buf: -- 1.5.3.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/