linux-kernel - [PATCH -mm 03/11] x86: make pci-gart iommu respect the segment size limits

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20071024165440D.tomof@acm.org>
Date:	Wed, 24 Oct 2007 19:48:10 +0900
From:	FUJITA Tomonori <tomof@....org>
To:	akpm@...ux-foundation.org
Cc:	linux-kernel@...r.kernel.org, linux-scsi@...r.kernel.org,
	muli@...ibm.com, fujita.tomonori@....ntt.co.jp
Subject: [PATCH -mm 03/11] x86: make pci-gart iommu respect the segment
 size limits

This patch makes pci-gart iommu respect segment size limits when
merging sg lists.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@....ntt.co.jp>
---
 arch/x86/kernel/pci-gart_64.c |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c56e9ee..dfe3828 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -384,6 +384,8 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	int start;
 	unsigned long pages = 0;
 	int need = 0, nextneed;
+	unsigned int seg_size;
+	unsigned int max_seg_size;
 	struct scatterlist *s, *ps, *start_sg, *sgmap;
 
 	if (nents == 0) 
@@ -395,6 +397,8 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	out = 0;
 	start = 0;
 	start_sg = sgmap = sg;
+	seg_size = 0;
+	max_seg_size = dma_get_max_seg_size(dev);
 	ps = NULL; /* shut up gcc */
 	for_each_sg(sg, s, nents, i) {
 		dma_addr_t addr = sg_phys(s);
@@ -408,11 +412,13 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 			/* Can only merge when the last chunk ends on a page 
 			   boundary and the new one doesn't have an offset. */
 			if (!iommu_merge || !nextneed || !need || s->offset ||
+			    (s->length + seg_size > max_seg_size) ||
 			    (ps->offset + ps->length) % PAGE_SIZE) {
 				if (dma_map_cont(start_sg, i - start, sgmap,
 						  pages, need) < 0)
 					goto error;
 				out++;
+				seg_size = 0;
 				sgmap = sg_next(sgmap);
 				pages = 0;
 				start = i;
@@ -420,6 +426,7 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 			}
 		}
 
+		seg_size += s->length;
 		need = nextneed;
 		pages += to_pages(s->offset, s->length);
 		ps = s;
-- 
1.5.2.4

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/