Messages in this thread Patch in this message | | | Date | Mon, 21 May 2007 09:13:22 +0200 | From | Jens Axboe <> | Subject | Re: [PATCH 8/12] x86-64: update iommu/dma mapping functions to sg helpers |
| |
On Mon, May 21 2007, Benny Halevy wrote: > Jens Axboe wrote: > > On Thu, May 10 2007, Benny Halevy wrote: > >> @@ -411,12 +406,13 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) > >> boundary and the new one doesn't have an offset. */ > >> if (!iommu_merge || !nextneed || !need || s->offset || > >> (ps->offset + ps->length) % PAGE_SIZE) { > >> - if (dma_map_cont(sg, start, i, sg+out, pages, > >> - need) < 0) > >> + if (dma_map_cont(start_sg, i - start, sg+out, > >> + pages, need) < 0) > >> goto error; > >> out++; > >> pages = 0; > >> - start = i; > >> + start = i; > >> + start_sg = s; > >> } > >> } > >> > >> @@ -424,7 +420,7 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) > >> pages += to_pages(s->offset, s->length); > >> ps = s; > >> } > >> - if (dma_map_cont(sg, start, i, sg+out, pages, need) < 0) > >> + if (dma_map_cont(start_sg, i - start, sg+out, pages, need) < 0) > >> goto error; > >> out++; > >> flush_gart(); > > > > Your patch is (very) buggy, the whole premise of doing chained sg > > entries makes sg + int illegal! > > > > You're right. I'll send a fix asap.
Did you see this one, I cooked it up after sending that mail out. Please review :-)
diff --git a/arch/x86_64/kernel/pci-gart.c b/arch/x86_64/kernel/pci-gart.c index 2e22a3a..b16384f 100644 --- a/arch/x86_64/kernel/pci-gart.c +++ b/arch/x86_64/kernel/pci-gart.c @@ -381,7 +381,7 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) int start; unsigned long pages = 0; int need = 0, nextneed; - struct scatterlist *s, *ps, *start_sg; + struct scatterlist *s, *ps, *start_sg, *sgmap; if (nents == 0) return 0; @@ -391,7 +391,7 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) out = 0; start = 0; - start_sg = sg; + start_sg = sgmap = sg; ps = NULL; /* shut up gcc */ for_each_sg(sg, s, nents, i) { dma_addr_t addr = page_to_phys(s->page) + s->offset; @@ -405,11 +405,12 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) /* 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 || - (ps->offset + ps->length) % PAGE_SIZE) { - if (dma_map_cont(start_sg, i - start, sg+out, + (ps->offset + ps->length) % PAGE_SIZE) { + if (dma_map_cont(start_sg, i - start, sgmap, pages, need) < 0) goto error; out++; + sgmap = sg_next(sgmap); pages = 0; start = i; start_sg = s; @@ -420,7 +421,7 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) pages += to_pages(s->offset, s->length); ps = s; } - if (dma_map_cont(start_sg, i - start, sg+out, pages, need) < 0) + if (dma_map_cont(start_sg, i - start, sgmap, pages, need) < 0) goto error; out++; flush_gart(); -- Jens Axboe
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |