* [PATCH v2] dmaengine: xgene-dma: Disable memcpy operation due to performance drop @ 2015-10-08 9:06 Rameshwar Prasad Sahu 2015-10-09 16:12 ` Vinod Koul 0 siblings, 1 reply; 5+ messages in thread From: Rameshwar Prasad Sahu @ 2015-10-08 9:06 UTC (permalink / raw) To: vinod.koul-ral2JQCrhuEAvxtiuMwx3w, dan.j.williams-ral2JQCrhuEAvxtiuMwx3w Cc: dmaengine-u79uwXL29TY76Z2rM5mHXA, arnd-r2nGTMty4D4, linux-kernel-u79uwXL29TY76Z2rM5mHXA, devicetree-u79uwXL29TY76Z2rM5mHXA, linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r, jcm-H+wXaHxf7aLQT0dZR+AlfA, patches-qTEPVZfXA3Y, Rameshwar Prasad Sahu The DMA engine supports memory copy, RAID5 XOR, RAID6 PQ, and other computations. But the bandwidth of the entire DMA engine is shared among all channels. This patch re-configures operations availability such that one can achieve maximum performance for XOR and PQ computation by removing the memory offload operations. Signed-off-by: Rameshwar Prasad Sahu <rsahu-qTEPVZfXA3Y@public.gmane.org> --- drivers/dma/xgene-dma.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c index 8d57b1b..cd38022 100644 --- a/drivers/dma/xgene-dma.c +++ b/drivers/dma/xgene-dma.c @@ -1707,7 +1707,6 @@ static void xgene_dma_set_caps(struct xgene_dma_chan *chan, dma_cap_zero(dma_dev->cap_mask); /* Set DMA device capability */ - dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); dma_cap_set(DMA_SG, dma_dev->cap_mask); /* Basically here, the X-Gene SoC DMA engine channel 0 supports XOR -- 1.8.2.1 -- To unsubscribe from this list: send the line "unsubscribe devicetree" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH v2] dmaengine: xgene-dma: Disable memcpy operation due to performance drop 2015-10-08 9:06 [PATCH v2] dmaengine: xgene-dma: Disable memcpy operation due to performance drop Rameshwar Prasad Sahu @ 2015-10-09 16:12 ` Vinod Koul [not found] ` <20151009161208.GJ3609-bQVUxfxUtC13uc1i7fC1zK2pdiUAq4bhAL8bYrjMMd8@public.gmane.org> 0 siblings, 1 reply; 5+ messages in thread From: Vinod Koul @ 2015-10-09 16:12 UTC (permalink / raw) To: Rameshwar Prasad Sahu Cc: dan.j.williams, dmaengine, arnd, linux-kernel, devicetree, linux-arm-kernel, jcm, patches On Thu, Oct 08, 2015 at 02:36:57PM +0530, Rameshwar Prasad Sahu wrote: > The DMA engine supports memory copy, RAID5 XOR, RAID6 PQ, and other > computations. But the bandwidth of the entire DMA engine is shared > among all channels. This patch re-configures operations availability > such that one can achieve maximum performance for XOR and PQ > computation by removing the memory offload operations. > > Signed-off-by: Rameshwar Prasad Sahu <rsahu@apm.com> > --- > drivers/dma/xgene-dma.c | 1 - > 1 file changed, 1 deletion(-) > > diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c > index 8d57b1b..cd38022 100644 > --- a/drivers/dma/xgene-dma.c > +++ b/drivers/dma/xgene-dma.c > @@ -1707,7 +1707,6 @@ static void xgene_dma_set_caps(struct xgene_dma_chan *chan, > dma_cap_zero(dma_dev->cap_mask); > > /* Set DMA device capability */ > - dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); > dma_cap_set(DMA_SG, dma_dev->cap_mask); This will not work. Still clients can invoke memcpy operation. You need to remove the callback -- ~Vinod ^ permalink raw reply [flat|nested] 5+ messages in thread
[parent not found: <20151009161208.GJ3609-bQVUxfxUtC13uc1i7fC1zK2pdiUAq4bhAL8bYrjMMd8@public.gmane.org>]
* Re: [PATCH v2] dmaengine: xgene-dma: Disable memcpy operation due to performance drop [not found] ` <20151009161208.GJ3609-bQVUxfxUtC13uc1i7fC1zK2pdiUAq4bhAL8bYrjMMd8@public.gmane.org> @ 2015-10-09 16:38 ` Rameshwar Sahu 2015-10-12 14:23 ` Vinod Koul 0 siblings, 1 reply; 5+ messages in thread From: Rameshwar Sahu @ 2015-10-09 16:38 UTC (permalink / raw) To: Vinod Koul Cc: dan.j.williams-ral2JQCrhuEAvxtiuMwx3w, dmaengine-u79uwXL29TY76Z2rM5mHXA, Arnd Bergmann, linux-kernel-u79uwXL29TY76Z2rM5mHXA, devicetree-u79uwXL29TY76Z2rM5mHXA, linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r, jcm-H+wXaHxf7aLQT0dZR+AlfA, patches-qTEPVZfXA3Y Hi Vinod, On Fri, Oct 9, 2015 at 9:42 PM, Vinod Koul <vinod.koul-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org> wrote: > On Thu, Oct 08, 2015 at 02:36:57PM +0530, Rameshwar Prasad Sahu wrote: >> The DMA engine supports memory copy, RAID5 XOR, RAID6 PQ, and other >> computations. But the bandwidth of the entire DMA engine is shared >> among all channels. This patch re-configures operations availability >> such that one can achieve maximum performance for XOR and PQ >> computation by removing the memory offload operations. >> >> Signed-off-by: Rameshwar Prasad Sahu <rsahu-qTEPVZfXA3Y@public.gmane.org> >> --- >> drivers/dma/xgene-dma.c | 1 - >> 1 file changed, 1 deletion(-) >> >> diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c >> index 8d57b1b..cd38022 100644 >> --- a/drivers/dma/xgene-dma.c >> +++ b/drivers/dma/xgene-dma.c >> @@ -1707,7 +1707,6 @@ static void xgene_dma_set_caps(struct xgene_dma_chan *chan, >> dma_cap_zero(dma_dev->cap_mask); >> >> /* Set DMA device capability */ >> - dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); >> dma_cap_set(DMA_SG, dma_dev->cap_mask); > > This will not work. Still clients can invoke memcpy operation. You need to > remove the callback Got it, instead of removing the callback registration can we keep it inside the condition like.. if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) dma_dev->device_prep_dma_memcpy = xgene_dma_prep_memcpy; > > -- > ~Vinod -- To unsubscribe from this list: send the line "unsubscribe devicetree" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH v2] dmaengine: xgene-dma: Disable memcpy operation due to performance drop 2015-10-09 16:38 ` Rameshwar Sahu @ 2015-10-12 14:23 ` Vinod Koul 2015-10-14 10:20 ` Rameshwar Sahu 0 siblings, 1 reply; 5+ messages in thread From: Vinod Koul @ 2015-10-12 14:23 UTC (permalink / raw) To: Rameshwar Sahu Cc: dan.j.williams, dmaengine, Arnd Bergmann, linux-kernel, devicetree, linux-arm-kernel, jcm, patches On Fri, Oct 09, 2015 at 10:08:32PM +0530, Rameshwar Sahu wrote: > Hi Vinod, > > On Fri, Oct 9, 2015 at 9:42 PM, Vinod Koul <vinod.koul@intel.com> wrote: > > On Thu, Oct 08, 2015 at 02:36:57PM +0530, Rameshwar Prasad Sahu wrote: > >> The DMA engine supports memory copy, RAID5 XOR, RAID6 PQ, and other > >> computations. But the bandwidth of the entire DMA engine is shared > >> among all channels. This patch re-configures operations availability > >> such that one can achieve maximum performance for XOR and PQ > >> computation by removing the memory offload operations. > >> > >> Signed-off-by: Rameshwar Prasad Sahu <rsahu@apm.com> > >> --- > >> drivers/dma/xgene-dma.c | 1 - > >> 1 file changed, 1 deletion(-) > >> > >> diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c > >> index 8d57b1b..cd38022 100644 > >> --- a/drivers/dma/xgene-dma.c > >> +++ b/drivers/dma/xgene-dma.c > >> @@ -1707,7 +1707,6 @@ static void xgene_dma_set_caps(struct xgene_dma_chan *chan, > >> dma_cap_zero(dma_dev->cap_mask); > >> > >> /* Set DMA device capability */ > >> - dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); > >> dma_cap_set(DMA_SG, dma_dev->cap_mask); > > > > This will not work. Still clients can invoke memcpy operation. You need to > > remove the callback > > Got it, instead of removing the callback registration can we keep it > inside the condition like.. > > if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) > dma_dev->device_prep_dma_memcpy = xgene_dma_prep_memcpy; But the code is dead and will not be tested and hence not maintained. I do not see a reason to keep dead code in kernel -- ~Vinod ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH v2] dmaengine: xgene-dma: Disable memcpy operation due to performance drop 2015-10-12 14:23 ` Vinod Koul @ 2015-10-14 10:20 ` Rameshwar Sahu 0 siblings, 0 replies; 5+ messages in thread From: Rameshwar Sahu @ 2015-10-14 10:20 UTC (permalink / raw) To: Vinod Koul Cc: dan.j.williams-ral2JQCrhuEAvxtiuMwx3w, dmaengine-u79uwXL29TY76Z2rM5mHXA, Arnd Bergmann, linux-kernel-u79uwXL29TY76Z2rM5mHXA, devicetree-u79uwXL29TY76Z2rM5mHXA, linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r, jcm-H+wXaHxf7aLQT0dZR+AlfA, patches-qTEPVZfXA3Y Hi Vinod, On Mon, Oct 12, 2015 at 7:53 PM, Vinod Koul <vinod.koul-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org> wrote: > On Fri, Oct 09, 2015 at 10:08:32PM +0530, Rameshwar Sahu wrote: >> Hi Vinod, >> >> On Fri, Oct 9, 2015 at 9:42 PM, Vinod Koul <vinod.koul-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org> wrote: >> > On Thu, Oct 08, 2015 at 02:36:57PM +0530, Rameshwar Prasad Sahu wrote: >> >> The DMA engine supports memory copy, RAID5 XOR, RAID6 PQ, and other >> >> computations. But the bandwidth of the entire DMA engine is shared >> >> among all channels. This patch re-configures operations availability >> >> such that one can achieve maximum performance for XOR and PQ >> >> computation by removing the memory offload operations. >> >> >> >> Signed-off-by: Rameshwar Prasad Sahu <rsahu-qTEPVZfXA3Y@public.gmane.org> >> >> --- >> >> drivers/dma/xgene-dma.c | 1 - >> >> 1 file changed, 1 deletion(-) >> >> >> >> diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c >> >> index 8d57b1b..cd38022 100644 >> >> --- a/drivers/dma/xgene-dma.c >> >> +++ b/drivers/dma/xgene-dma.c >> >> @@ -1707,7 +1707,6 @@ static void xgene_dma_set_caps(struct xgene_dma_chan *chan, >> >> dma_cap_zero(dma_dev->cap_mask); >> >> >> >> /* Set DMA device capability */ >> >> - dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); >> >> dma_cap_set(DMA_SG, dma_dev->cap_mask); >> > >> > This will not work. Still clients can invoke memcpy operation. You need to >> > remove the callback >> >> Got it, instead of removing the callback registration can we keep it >> inside the condition like.. >> >> if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) >> dma_dev->device_prep_dma_memcpy = xgene_dma_prep_memcpy; > > But the code is dead and will not be tested and hence not maintained. I do > not see a reason to keep dead code in kernel Got it, I will remove the memcpy offload support and will send another patch for review. > > -- > ~Vinod -- To unsubscribe from this list: send the line "unsubscribe devicetree" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2015-10-14 10:20 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-10-08 9:06 [PATCH v2] dmaengine: xgene-dma: Disable memcpy operation due to performance drop Rameshwar Prasad Sahu
2015-10-09 16:12 ` Vinod Koul
[not found] ` <20151009161208.GJ3609-bQVUxfxUtC13uc1i7fC1zK2pdiUAq4bhAL8bYrjMMd8@public.gmane.org>
2015-10-09 16:38 ` Rameshwar Sahu
2015-10-12 14:23 ` Vinod Koul
2015-10-14 10:20 ` Rameshwar Sahu
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).