From mboxrd@z Thu Jan 1 00:00:00 1970 From: akpm@linux-foundation.org Subject: - iommu-sg-merging-ia64-make-sba_iommu-respect-the-segment-size-limits.patch removed from -mm tree Date: Tue, 05 Feb 2008 14:28:08 -0800 Message-ID: <200802052227.m15MRn76011832@imap1.linux-foundation.org> Reply-To: linux-kernel@vger.kernel.org Return-path: Received: from smtp2.linux-foundation.org ([207.189.120.14]:59779 "EHLO smtp2.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1762722AbYBEWoR (ORCPT ); Tue, 5 Feb 2008 17:44:17 -0500 Sender: mm-commits-owner@vger.kernel.org List-Id: mm-commits@vger.kernel.org To: tomof@acm.org, James.Bottomley@steeleye.com, fujita.tomonori@lab.ntt.co.jp, jeff@garzik.org, jens.axboe@oracle.com, tony.luck@intel.com, mm-commits@vger.kernel.org The patch titled iommu sg merging: IA64: make sba_iommu respect the segment size limits has been removed from the -mm tree. Its filename was iommu-sg-merging-ia64-make-sba_iommu-respect-the-segment-size-limits.patch This patch was dropped because it was merged into mainline or a subsystem tree The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: iommu sg merging: IA64: make sba_iommu respect the segment size limits From: FUJITA Tomonori This patch makes sba iommu respect segment size limits when merging sg lists. Signed-off-by: FUJITA Tomonori Cc: Jeff Garzik Cc: James Bottomley Acked-by: Jens Axboe Cc: "Luck, Tony" Signed-off-by: Andrew Morton --- arch/ia64/hp/common/sba_iommu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff -puN arch/ia64/hp/common/sba_iommu.c~iommu-sg-merging-ia64-make-sba_iommu-respect-the-segment-size-limits arch/ia64/hp/common/sba_iommu.c --- a/arch/ia64/hp/common/sba_iommu.c~iommu-sg-merging-ia64-make-sba_iommu-respect-the-segment-size-limits +++ a/arch/ia64/hp/common/sba_iommu.c @@ -1265,7 +1265,7 @@ sba_fill_pdir( * the sglist do both. */ static SBA_INLINE int -sba_coalesce_chunks( struct ioc *ioc, +sba_coalesce_chunks(struct ioc *ioc, struct device *dev, struct scatterlist *startsg, int nents) { @@ -1275,6 +1275,7 @@ sba_coalesce_chunks( struct ioc *ioc, struct scatterlist *dma_sg; /* next DMA stream head */ unsigned long dma_offset, dma_len; /* start/len of DMA stream */ int n_mappings = 0; + unsigned int max_seg_size = dma_get_max_seg_size(dev); while (nents > 0) { unsigned long vaddr = (unsigned long) sba_sg_address(startsg); @@ -1314,6 +1315,9 @@ sba_coalesce_chunks( struct ioc *ioc, > DMA_CHUNK_SIZE) break; + if (dma_len + startsg->length > max_seg_size) + break; + /* ** Then look for virtually contiguous blocks. ** @@ -1441,7 +1445,7 @@ int sba_map_sg(struct device *dev, struc ** w/o this association, we wouldn't have coherent DMA! ** Access to the virtual address is what forces a two pass algorithm. */ - coalesced = sba_coalesce_chunks(ioc, sglist, nents); + coalesced = sba_coalesce_chunks(ioc, dev, sglist, nents); /* ** Program the I/O Pdir _ Patches currently in -mm which might be from tomof@acm.org are origin.patch