From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755504Ab3HWMzx (ORCPT ); Fri, 23 Aug 2013 08:55:53 -0400 Received: from aserp1040.oracle.com ([141.146.126.69]:51031 "EHLO aserp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755445Ab3HWMzv (ORCPT ); Fri, 23 Aug 2013 08:55:51 -0400 Date: Fri, 23 Aug 2013 08:55:33 -0400 From: Konrad Rzeszutek Wilk To: Zoltan Kiss Cc: Jeremy Fitzhardinge , Steven Rostedt , Frederic Weisbecker , Ingo Molnar , linux-kernel@vger.kernel.org, xen-devel@lists.xensource.com, virtualization@lists.linux-foundation.org Subject: Re: [PATCH] tracing/events: Add bounce tracing to swiotbl-xen Message-ID: <20130823125533.GC14306@konrad-lan.dumpdata.com> References: <1377208048-8963-1-git-send-email-zoltan.kiss@citrix.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1377208048-8963-1-git-send-email-zoltan.kiss@citrix.com> User-Agent: Mutt/1.5.21 (2010-09-15) X-Source-IP: acsinet22.oracle.com [141.146.126.238] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Aug 22, 2013 at 10:47:28PM +0100, Zoltan Kiss wrote: > Ftrace is currently not able to detect when SWIOTLB has to do double buffering > under Xen. You can only see it indirectly in function_graph, when > xen_swiotlb_map_page() doesn't stop after range_straddles_page_boundary(), but > calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch > introduces the swiotlb-xen:bounced event, which also prints out the following > informations to help you find out why bouncing happened: > > dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768 > swiotlb_force=0 > > If (dev_addr + size + 1) > dma_mask, the buffer is out of the device's DMA > range. If swiotlb_force == 1, you should really change the kernel parameters. > Otherwise, the buffer is not contiguous in mfn space. Could this be in the lib/swiotlb.c instead? > > Signed-off-by: Zoltan Kiss > --- > drivers/xen/swiotlb-xen.c | 7 ++++++ > include/trace/events/swiotlb-xen.h | 46 ++++++++++++++++++++++++++++++++++++ > 2 files changed, 53 insertions(+) > create mode 100644 include/trace/events/swiotlb-xen.h > > diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c > index aadffcf..f08440d 100644 > --- a/drivers/xen/swiotlb-xen.c > +++ b/drivers/xen/swiotlb-xen.c > @@ -42,6 +42,10 @@ > #include > #include > #include > + > +#define CREATE_TRACE_POINTS > +#include > + > /* > * Used to do a quick range check in swiotlb_tbl_unmap_single and > * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this > @@ -358,6 +362,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, > /* > * Oh well, have to allocate and map a bounce buffer. > */ > + > + trace_bounced(dev, dev_addr, size, swiotlb_force); > + > map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir); > if (map == SWIOTLB_MAP_ERROR) > return DMA_ERROR_CODE; > diff --git a/include/trace/events/swiotlb-xen.h b/include/trace/events/swiotlb-xen.h > new file mode 100644 > index 0000000..cbe2dca > --- /dev/null > +++ b/include/trace/events/swiotlb-xen.h > @@ -0,0 +1,46 @@ > +#undef TRACE_SYSTEM > +#define TRACE_SYSTEM swiotlb-xen > + > +#if !defined(_TRACE_SWIOTLBXEN_H) || defined(TRACE_HEADER_MULTI_READ) > +#define _TRACE_SWIOTLBXEN_H > + > +#include > + > +TRACE_EVENT(bounced, > + > + TP_PROTO(struct device *dev, > + dma_addr_t dev_addr, > + size_t size, > + int swiotlb_force), > + > + TP_ARGS(dev, dev_addr, size, swiotlb_force), > + > + TP_STRUCT__entry( > + __string( dev_name, dev_name(dev) ) > + __field( u64, dma_mask ) > + __field( dma_addr_t, dev_addr ) > + __field( size_t, size ) > + __field( int, swiotlb_force ) > + ), > + > + TP_fast_assign( > + __assign_str(dev_name, dev_name(dev)); > + __entry->dma_mask = (dev->dma_mask ? *dev->dma_mask : 0); > + __entry->dev_addr = dev_addr; > + __entry->size = size; > + __entry->swiotlb_force = swiotlb_force; > + ), > + > + TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx " > + "size=%zu swiotlb_force=%x", > + __get_str(dev_name), > + __entry->dma_mask, > + (unsigned long long)__entry->dev_addr, > + __entry->size, > + __entry->swiotlb_force ) > +); > + > +#endif /* _TRACE_IRQ_H */ > + > +/* This part must be outside protection */ > +#include > -- > 1.7.9.5 >