[openib-general] [PATCH 3/5] IB/iser: make FMR "page size" be 4K and not PAGE_SIZE

[Erez Zilber]

As iser is able to use at most one rdma operation for the
execution of a scsi command, and registration of the sg
associated with scsi command has its restrictions, the code
checks if an sg is "aligned for rdma".

Alignment for rdma is measured in "fmr page" units whose
possible resolutions are different between HCAs and can be
smaller, equal or bigger to the system page size.

When the system page size is bigger than 4KB (eg the default
with ia64 kernels) there a bigger chance that an sg would be
aligned for rdma if the fmr page size is 4KB.

Change the code to create FMR whose pages are of size 4KB
and to take that into account when processing the sg.

Signed-off-by: Erez Zilber <erezz at voltaire.com>

---

 drivers/infiniband/ulp/iser/iscsi_iser.h  |    6 +++++-
 drivers/infiniband/ulp/iser/iser_memory.c |   31 +++++++++++++++++++----------
 drivers/infiniband/ulp/iser/iser_verbs.c  |    4 ++--
 3 files changed, 27 insertions(+), 14 deletions(-)

1f90243f796772fcaea6ad059876a0aad6a06d52
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 7c3d0c9..2c8bc67 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -82,8 +82,12 @@
 		       __func__ , ## arg);		\
 	} while (0)
 
+#define SHIFT_4K	12
+#define SIZE_4K	(1UL << SHIFT_4K)
+#define MASK_4K	(~(SIZE_4K-1))
+
 					/* support upto 512KB in one RDMA */
-#define ISCSI_ISER_SG_TABLESIZE         (0x80000 >> PAGE_SHIFT)
+#define ISCSI_ISER_SG_TABLESIZE         (0x80000 >> SHIFT_4K)
 #define ISCSI_ISER_MAX_LUN		256
 #define ISCSI_ISER_MAX_CMD_LEN		16
 
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 53af956..bcef0d3 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -42,6 +42,7 @@
 #include "iscsi_iser.h"
 
 #define ISER_KMALLOC_THRESHOLD 0x20000 /* 128K - kmalloc limit */
+
 /**
  * Decrements the reference count for the
  * registered buffer & releases it
@@ -239,7 +240,7 @@ static int iser_sg_to_page_vec(struct is
 	int i;
 
 	/* compute the offset of first element */
-	page_vec->offset = (u64) sg[0].offset;
+	page_vec->offset = (u64) sg[0].offset & ~MASK_4K;
 
 	for (i = 0; i < data->dma_nents; i++) {
 		total_sz += sg_dma_len(&sg[i]);
@@ -247,21 +248,30 @@ static int iser_sg_to_page_vec(struct is
 		first_addr = sg_dma_address(&sg[i]);
 		last_addr  = first_addr + sg_dma_len(&sg[i]);
 
-		start_aligned = !(first_addr & ~PAGE_MASK);
-		end_aligned   = !(last_addr  & ~PAGE_MASK);
+		start_aligned = !(first_addr & ~MASK_4K);
+		end_aligned   = !(last_addr  & ~MASK_4K);
 
 		/* continue to collect page fragments till aligned or SG ends */
 		while (!end_aligned && (i + 1 < data->dma_nents)) {
 			i++;
 			total_sz += sg_dma_len(&sg[i]);
 			last_addr = sg_dma_address(&sg[i]) + sg_dma_len(&sg[i]);
-			end_aligned = !(last_addr  & ~PAGE_MASK);
+			end_aligned = !(last_addr  & ~MASK_4K);
 		}
 
-		first_addr = first_addr & PAGE_MASK;
-
-		for (page = first_addr; page < last_addr; page += PAGE_SIZE)
-			page_vec->pages[cur_page++] = page;
+		/* handle the 1st page in the 1st DMA element */
+		if (cur_page == 0) {
+			page = first_addr & MASK_4K;
+			page_vec->pages[cur_page] = page;
+			cur_page++;
+			page += SIZE_4K;
+		} else
+			page = first_addr;
+
+		for (; page < last_addr; page += SIZE_4K) {
+			page_vec->pages[cur_page] = page;
+			cur_page++;
+		}
 
 	}
 	page_vec->data_size = total_sz;
@@ -269,8 +279,7 @@ static int iser_sg_to_page_vec(struct is
 	return cur_page;
 }
 
-#define MASK_4K			((1UL << 12) - 1) /* 0xFFF */
-#define IS_4K_ALIGNED(addr)	((((unsigned long)addr) & MASK_4K) == 0)
+#define IS_4K_ALIGNED(addr)	((((unsigned long)addr) & ~MASK_4K) == 0)
 
 /**
  * iser_data_buf_aligned_len - Tries to determine the maximal correctly aligned
@@ -352,7 +361,7 @@ static void iser_page_vec_build(struct i
 
 	page_vec->length = page_vec_len;
 
-	if (page_vec_len * PAGE_SIZE < page_vec->data_size) {
+	if (page_vec_len * SIZE_4K < page_vec->data_size) {
 		iser_err("page_vec too short to hold this SG\n");
 		iser_data_buf_dump(data);
 		iser_dump_page_vec(page_vec);
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 72febf1..9b27a7c 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -150,7 +150,7 @@ static int iser_create_ib_conn_res(struc
 	}
 	ib_conn->page_vec->pages = (u64 *) (ib_conn->page_vec + 1);
 
-	params.page_shift        = PAGE_SHIFT;
+	params.page_shift        = SHIFT_4K;
 	/* when the first/last SG element are not start/end *
 	 * page aligned, the map whould be of N+1 pages     */
 	params.max_pages_per_fmr = ISCSI_ISER_SG_TABLESIZE + 1;
@@ -604,7 +604,7 @@ int iser_reg_page_vec(struct iser_conn  
 
 	mem_reg->lkey  = mem->fmr->lkey;
 	mem_reg->rkey  = mem->fmr->rkey;
-	mem_reg->len   = page_vec->length * PAGE_SIZE;
+	mem_reg->len   = page_vec->length * SIZE_4K;
 	mem_reg->va    = io_addr;
 	mem_reg->mem_h = (void *)mem;
 
-- 
1.2.6