All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
To: <xen-devel@lists.xensource.com>
Cc: <linux-kernel@vger.kernel.org>,
	<linux-arm-kernel@lists.infradead.org>, <konrad.wilk@oracle.com>,
	<Stefano.Stabellini@eu.citrix.com>, <Ian.Campbell@citrix.com>,
	Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Subject: [PATCH v6 12/19] swiotlb: don't assume that io_tlb_start-io_tlb_end is coherent
Date: Fri, 27 Sep 2013 17:10:00 +0100	[thread overview]
Message-ID: <1380298207-29151-12-git-send-email-stefano.stabellini@eu.citrix.com> (raw)
In-Reply-To: <alpine.DEB.2.02.1309271653420.5498@kaball.uk.xensource.com>

The swiotlb code has appropriate calls to dma_mark_clean in place for
buffers passed to swiotlb_map_page as an argument. However it assumes
that the swiotlb bounce buffer (io_tlb_start-io_tlb_end) is already
coherent and doesn't need any calls to dma_mark_clean.

On ARM the swiotlb bounce buffer is not coherent (the memory is
writealloc while it should be bufferable) and therefore we need to call
dma_mark_clean appropriately on the bounce buffer code paths too.

Note that most architecures have an empty dma_mark_clean implementation
anyway.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 lib/swiotlb.c |   13 ++++++++++---
 1 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 4e8686c..eb45d17 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -515,6 +515,7 @@ found:
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+	dma_mark_clean(phys_to_virt(tlb_addr), size);
 
 	return tlb_addr;
 }
@@ -547,7 +548,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * First, sync the memory before unmapping the entry
 	 */
 	if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+	{
+		dma_mark_clean(phys_to_virt(tlb_addr), size);
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+	}
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -587,17 +591,20 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 
 	switch (target) {
 	case SYNC_FOR_CPU:
-		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
+		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) {
+			dma_mark_clean(phys_to_virt(tlb_addr), size);
 			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_FROM_DEVICE);
+		}
 		else
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
-		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) {
 			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_TO_DEVICE);
-		else
+			dma_mark_clean(phys_to_virt(tlb_addr), size);
+		} else
 			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
 	default:
-- 
1.7.2.5


WARNING: multiple messages have this Message-ID (diff)
From: stefano.stabellini@eu.citrix.com (Stefano Stabellini)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v6 12/19] swiotlb: don't assume that io_tlb_start-io_tlb_end is coherent
Date: Fri, 27 Sep 2013 17:10:00 +0100	[thread overview]
Message-ID: <1380298207-29151-12-git-send-email-stefano.stabellini@eu.citrix.com> (raw)
In-Reply-To: <alpine.DEB.2.02.1309271653420.5498@kaball.uk.xensource.com>

The swiotlb code has appropriate calls to dma_mark_clean in place for
buffers passed to swiotlb_map_page as an argument. However it assumes
that the swiotlb bounce buffer (io_tlb_start-io_tlb_end) is already
coherent and doesn't need any calls to dma_mark_clean.

On ARM the swiotlb bounce buffer is not coherent (the memory is
writealloc while it should be bufferable) and therefore we need to call
dma_mark_clean appropriately on the bounce buffer code paths too.

Note that most architecures have an empty dma_mark_clean implementation
anyway.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 lib/swiotlb.c |   13 ++++++++++---
 1 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 4e8686c..eb45d17 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -515,6 +515,7 @@ found:
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+	dma_mark_clean(phys_to_virt(tlb_addr), size);
 
 	return tlb_addr;
 }
@@ -547,7 +548,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * First, sync the memory before unmapping the entry
 	 */
 	if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+	{
+		dma_mark_clean(phys_to_virt(tlb_addr), size);
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+	}
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -587,17 +591,20 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 
 	switch (target) {
 	case SYNC_FOR_CPU:
-		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
+		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) {
+			dma_mark_clean(phys_to_virt(tlb_addr), size);
 			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_FROM_DEVICE);
+		}
 		else
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
-		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) {
 			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_TO_DEVICE);
-		else
+			dma_mark_clean(phys_to_virt(tlb_addr), size);
+		} else
 			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
 	default:
-- 
1.7.2.5

WARNING: multiple messages have this Message-ID (diff)
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
To: xen-devel@lists.xensource.com
Cc: linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, konrad.wilk@oracle.com,
	Stefano.Stabellini@eu.citrix.com, Ian.Campbell@citrix.com,
	Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Subject: [PATCH v6 12/19] swiotlb: don't assume that io_tlb_start-io_tlb_end is coherent
Date: Fri, 27 Sep 2013 17:10:00 +0100	[thread overview]
Message-ID: <1380298207-29151-12-git-send-email-stefano.stabellini@eu.citrix.com> (raw)
In-Reply-To: <alpine.DEB.2.02.1309271653420.5498@kaball.uk.xensource.com>

The swiotlb code has appropriate calls to dma_mark_clean in place for
buffers passed to swiotlb_map_page as an argument. However it assumes
that the swiotlb bounce buffer (io_tlb_start-io_tlb_end) is already
coherent and doesn't need any calls to dma_mark_clean.

On ARM the swiotlb bounce buffer is not coherent (the memory is
writealloc while it should be bufferable) and therefore we need to call
dma_mark_clean appropriately on the bounce buffer code paths too.

Note that most architecures have an empty dma_mark_clean implementation
anyway.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 lib/swiotlb.c |   13 ++++++++++---
 1 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 4e8686c..eb45d17 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -515,6 +515,7 @@ found:
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+	dma_mark_clean(phys_to_virt(tlb_addr), size);
 
 	return tlb_addr;
 }
@@ -547,7 +548,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * First, sync the memory before unmapping the entry
 	 */
 	if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+	{
+		dma_mark_clean(phys_to_virt(tlb_addr), size);
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+	}
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -587,17 +591,20 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 
 	switch (target) {
 	case SYNC_FOR_CPU:
-		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
+		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) {
+			dma_mark_clean(phys_to_virt(tlb_addr), size);
 			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_FROM_DEVICE);
+		}
 		else
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
-		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) {
 			swiotlb_bounce(orig_addr, tlb_addr,
 				       size, DMA_TO_DEVICE);
-		else
+			dma_mark_clean(phys_to_virt(tlb_addr), size);
+		} else
 			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
 	default:
-- 
1.7.2.5

  parent reply	other threads:[~2013-09-27 16:36 UTC|newest]

Thread overview: 133+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-09-27 16:09 [PATCH v6 0/19] enable swiotlb-xen on arm and arm64 Stefano Stabellini
2013-09-27 16:09 ` Stefano Stabellini
2013-09-27 16:09 ` Stefano Stabellini
2013-09-27 16:09 ` [PATCH v6 01/19] arm: make SWIOTLB available Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09 ` [PATCH v6 02/19] arm64: define DMA_ERROR_CODE Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-30 10:47   ` Catalin Marinas
2013-09-30 10:47     ` Catalin Marinas
2013-09-30 10:47     ` Catalin Marinas
2013-09-27 16:09 ` [PATCH v6 03/19] xen: introduce XENMEM_exchange_and_pin and XENMEM_unpin Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-30 14:54   ` Konrad Rzeszutek Wilk
2013-09-30 14:54     ` Konrad Rzeszutek Wilk
2013-09-27 16:09 ` [PATCH v6 04/19] xen: make xen_create_contiguous_region return the dma address Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09 ` [PATCH v6 05/19] swiotlb-xen: support autotranslate guests Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09 ` [PATCH v6 06/19] xen/arm,arm64: enable SWIOTLB_XEN Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-30 15:14   ` Konrad Rzeszutek Wilk
2013-09-30 15:14     ` Konrad Rzeszutek Wilk
2013-09-27 16:09 ` [PATCH v6 07/19] swiotlb-xen: introduce xen_swiotlb_set_dma_mask Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09 ` [PATCH v6 08/19] arm/xen: get_dma_ops: return xen_dma_ops if we are running on Xen Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-30 15:17   ` Konrad Rzeszutek Wilk
2013-09-30 15:17     ` Konrad Rzeszutek Wilk
2013-09-30 15:17     ` Konrad Rzeszutek Wilk
2013-09-27 16:09 ` [PATCH v6 09/19] arm64/xen: " Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-30 10:48   ` Catalin Marinas
2013-09-30 10:48     ` Catalin Marinas
2013-09-30 10:48     ` Catalin Marinas
2013-09-27 16:09 ` [PATCH v6 10/19] xen: introduce xen_alloc/free_coherent_pages Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-30 15:31   ` Konrad Rzeszutek Wilk
2013-09-30 15:31     ` Konrad Rzeszutek Wilk
2013-10-01 13:40     ` Catalin Marinas
2013-10-01 13:40       ` Catalin Marinas
2013-10-01 13:40       ` Catalin Marinas
2013-10-02 17:03       ` Stefano Stabellini
2013-10-02 17:03         ` Stefano Stabellini
2013-10-02 17:03         ` Stefano Stabellini
2013-10-02 17:07         ` Catalin Marinas
2013-10-02 17:07           ` Catalin Marinas
2013-10-02 17:07           ` Catalin Marinas
2013-10-02 17:14           ` Stefano Stabellini
2013-10-02 17:14             ` Stefano Stabellini
2013-10-02 17:14             ` Stefano Stabellini
2013-09-27 16:09 ` [PATCH v6 11/19] swiotlb-xen: use xen_alloc/free_coherent_pages Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-27 16:09   ` Stefano Stabellini
2013-09-30 15:34   ` Konrad Rzeszutek Wilk
2013-09-30 15:34     ` Konrad Rzeszutek Wilk
2013-09-27 16:10 ` Stefano Stabellini [this message]
2013-09-27 16:10   ` [PATCH v6 12/19] swiotlb: don't assume that io_tlb_start-io_tlb_end is coherent Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-30 15:56   ` Konrad Rzeszutek Wilk
2013-09-30 15:56     ` Konrad Rzeszutek Wilk
2013-10-02 17:31     ` Stefano Stabellini
2013-10-02 17:31       ` Stefano Stabellini
2013-10-02 17:31       ` Stefano Stabellini
2013-10-04 13:23       ` Konrad Rzeszutek Wilk
2013-10-04 13:23         ` Konrad Rzeszutek Wilk
2013-09-27 16:10 ` [PATCH v6 13/19] ASoC: Samsung: Rename dma_ops by samsung_dma_ops Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10 ` [PATCH v6 14/19] swiotlb: print a warning when the swiotlb is full Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-30 15:58   ` Konrad Rzeszutek Wilk
2013-09-30 15:58     ` Konrad Rzeszutek Wilk
2013-10-09 17:31     ` Stefano Stabellini
2013-10-09 17:31       ` Stefano Stabellini
2013-10-09 17:31       ` Stefano Stabellini
2013-09-27 16:10 ` [PATCH v6 15/19] swiotlb-xen: call dma_capable only if dev->dma_mask is allocated Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-30 16:02   ` Konrad Rzeszutek Wilk
2013-09-30 16:02     ` Konrad Rzeszutek Wilk
2013-10-02 17:13     ` Stefano Stabellini
2013-10-02 17:13       ` Stefano Stabellini
2013-10-02 17:13       ` Stefano Stabellini
2013-10-02 17:22       ` Konrad Rzeszutek Wilk
2013-10-02 17:22         ` Konrad Rzeszutek Wilk
2013-10-02 17:22         ` Konrad Rzeszutek Wilk
2013-10-03 18:35         ` Rob Herring
2013-10-03 18:35           ` Rob Herring
2013-10-03 18:35           ` Rob Herring
2013-09-27 16:10 ` [PATCH v6 16/19] arm,arm64: do not always merge biovec if we are running on Xen Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10   ` [PATCH v6 16/19] arm, arm64: " Stefano Stabellini
2013-09-30 16:06   ` [PATCH v6 16/19] arm,arm64: " Konrad Rzeszutek Wilk
2013-09-30 16:06     ` [PATCH v6 16/19] arm, arm64: " Konrad Rzeszutek Wilk
2013-09-30 16:06     ` Konrad Rzeszutek Wilk
2013-10-09 17:54     ` [PATCH v6 16/19] arm,arm64: " Stefano Stabellini
2013-10-09 17:54       ` Stefano Stabellini
2013-10-09 17:54       ` Stefano Stabellini
2013-09-27 16:10 ` [PATCH v6 17/19] xen: introduce XENMEM_pin Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-30 17:22   ` Konrad Rzeszutek Wilk
2013-09-30 17:22     ` Konrad Rzeszutek Wilk
2013-09-27 16:10 ` [PATCH v6 18/19] swiotlb-xen: introduce a rbtree to track phys to bus mappings Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-30 17:27   ` Konrad Rzeszutek Wilk
2013-09-30 17:27     ` Konrad Rzeszutek Wilk
2013-10-02 17:23     ` Stefano Stabellini
2013-10-02 17:23       ` Stefano Stabellini
2013-10-02 17:23       ` Stefano Stabellini
2013-10-09 17:25     ` Stefano Stabellini
2013-10-09 17:25       ` Stefano Stabellini
2013-10-09 17:25       ` Stefano Stabellini
2013-09-27 16:10 ` [PATCH v6 19/19] swiotlb-xen: instead of bouncing on the swiotlb, pin single pages Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-27 16:10   ` Stefano Stabellini
2013-09-30 17:39   ` Konrad Rzeszutek Wilk
2013-09-30 17:39     ` Konrad Rzeszutek Wilk
2013-10-09 17:27     ` Stefano Stabellini
2013-10-09 17:27       ` Stefano Stabellini
2013-10-09 17:27       ` Stefano Stabellini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1380298207-29151-12-git-send-email-stefano.stabellini@eu.citrix.com \
    --to=stefano.stabellini@eu.citrix.com \
    --cc=Ian.Campbell@citrix.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=xen-devel@lists.xensource.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.