summaryrefslogtreecommitdiff
path: root/drivers/infiniband
diff options
context:
space:
mode:
authorSagi Grimberg <sagig@mellanox.com>2015-10-13 19:11:24 +0300
committerDoug Ledford <dledford@redhat.com>2015-10-29 05:27:17 +0300
commit4c67e2bfc8b7121d51434362fa7c2d012f8bcf1b (patch)
treed262b24e2c9fe18611816437acc9a7e3526eb64d /drivers/infiniband
parent63e8790d39a2d7c9a0ebeab987a6033d184bc6ba (diff)
downloadlinux-4c67e2bfc8b7121d51434362fa7c2d012f8bcf1b.tar.xz
IB/core: Introduce new fast registration API
The new fast registration verb ib_map_mr_sg receives a scatterlist and converts it to a page list under the verbs API thus hiding the specific HW mapping details away from the consumer. The provider drivers are provided with a generic helper ib_sg_to_pages that converts a scatterlist into a vector of page addresses. The drivers can still perform any HW specific page address setting by passing a set_page function pointer which will be invoked for each page address. This allows drivers to avoid keeping a shadow page vectors and convert them to HW specific translations by doing extra copies. This API will allow ULPs to remove the duplicated code of constructing a page vector from a given sg list. The send work request ib_reg_wr also shrinks as it will contain only mr, key and access flags in addition. Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Tested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Doug Ledford <dledford@redhat.com>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/core/verbs.c107
1 files changed, 107 insertions, 0 deletions
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 46d97f09fbae..5673df061213 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1496,3 +1496,110 @@ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
mr->device->check_mr_status(mr, check_mask, mr_status) : -ENOSYS;
}
EXPORT_SYMBOL(ib_check_mr_status);
+
+/**
+ * ib_map_mr_sg() - Map the largest prefix of a dma mapped SG list
+ * and set it the memory region.
+ * @mr: memory region
+ * @sg: dma mapped scatterlist
+ * @sg_nents: number of entries in sg
+ * @page_size: page vector desired page size
+ *
+ * Constraints:
+ * - The first sg element is allowed to have an offset.
+ * - Each sg element must be aligned to page_size (or physically
+ * contiguous to the previous element). In case an sg element has a
+ * non contiguous offset, the mapping prefix will not include it.
+ * - The last sg element is allowed to have length less than page_size.
+ * - If sg_nents total byte length exceeds the mr max_num_sge * page_size
+ * then only max_num_sg entries will be mapped.
+ *
+ * Returns the number of sg elements that were mapped to the memory region.
+ *
+ * After this completes successfully, the memory region
+ * is ready for registration.
+ */
+int ib_map_mr_sg(struct ib_mr *mr,
+ struct scatterlist *sg,
+ int sg_nents,
+ unsigned int page_size)
+{
+ if (unlikely(!mr->device->map_mr_sg))
+ return -ENOSYS;
+
+ mr->page_size = page_size;
+
+ return mr->device->map_mr_sg(mr, sg, sg_nents);
+}
+EXPORT_SYMBOL(ib_map_mr_sg);
+
+/**
+ * ib_sg_to_pages() - Convert the largest prefix of a sg list
+ * to a page vector
+ * @mr: memory region
+ * @sgl: dma mapped scatterlist
+ * @sg_nents: number of entries in sg
+ * @set_page: driver page assignment function pointer
+ *
+ * Core service helper for drivers to covert the largest
+ * prefix of given sg list to a page vector. The sg list
+ * prefix converted is the prefix that meet the requirements
+ * of ib_map_mr_sg.
+ *
+ * Returns the number of sg elements that were assigned to
+ * a page vector.
+ */
+int ib_sg_to_pages(struct ib_mr *mr,
+ struct scatterlist *sgl,
+ int sg_nents,
+ int (*set_page)(struct ib_mr *, u64))
+{
+ struct scatterlist *sg;
+ u64 last_end_dma_addr = 0, last_page_addr = 0;
+ unsigned int last_page_off = 0;
+ u64 page_mask = ~((u64)mr->page_size - 1);
+ int i;
+
+ mr->iova = sg_dma_address(&sgl[0]);
+ mr->length = 0;
+
+ for_each_sg(sgl, sg, sg_nents, i) {
+ u64 dma_addr = sg_dma_address(sg);
+ unsigned int dma_len = sg_dma_len(sg);
+ u64 end_dma_addr = dma_addr + dma_len;
+ u64 page_addr = dma_addr & page_mask;
+
+ if (i && page_addr != dma_addr) {
+ if (last_end_dma_addr != dma_addr) {
+ /* gap */
+ goto done;
+
+ } else if (last_page_off + dma_len <= mr->page_size) {
+ /* chunk this fragment with the last */
+ mr->length += dma_len;
+ last_end_dma_addr += dma_len;
+ last_page_off += dma_len;
+ continue;
+ } else {
+ /* map starting from the next page */
+ page_addr = last_page_addr + mr->page_size;
+ dma_len -= mr->page_size - last_page_off;
+ }
+ }
+
+ do {
+ if (unlikely(set_page(mr, page_addr)))
+ goto done;
+ page_addr += mr->page_size;
+ } while (page_addr < end_dma_addr);
+
+ mr->length += dma_len;
+ last_end_dma_addr = end_dma_addr;
+ last_page_addr = end_dma_addr & page_mask;
+ last_page_off = end_dma_addr & ~page_mask;
+ }
+
+done:
+ return i;
+}
+EXPORT_SYMBOL(ib_sg_to_pages);