aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/ulp/iser
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/ulp/iser')
-rw-r--r--drivers/infiniband/ulp/iser/Kconfig2
-rw-r--r--drivers/infiniband/ulp/iser/iscsi_iser.c19
-rw-r--r--drivers/infiniband/ulp/iser/iscsi_iser.h8
-rw-r--r--drivers/infiniband/ulp/iser/iser_memory.c80
-rw-r--r--drivers/infiniband/ulp/iser/iser_verbs.c10
5 files changed, 78 insertions, 41 deletions
diff --git a/drivers/infiniband/ulp/iser/Kconfig b/drivers/infiniband/ulp/iser/Kconfig
index fead87d1eff..365a1b5f19e 100644
--- a/drivers/infiniband/ulp/iser/Kconfig
+++ b/drivers/infiniband/ulp/iser/Kconfig
@@ -1,6 +1,6 @@
config INFINIBAND_ISER
tristate "ISCSI RDMA Protocol"
- depends on INFINIBAND && SCSI
+ depends on INFINIBAND && SCSI && INET
select SCSI_ISCSI_ATTRS
---help---
Support for the ISCSI RDMA Protocol over InfiniBand. This
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 1437d7ee3b1..2a14fe2e322 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -141,18 +141,11 @@ iscsi_iser_cmd_init(struct iscsi_cmd_task *ctask)
if (sc->sc_data_direction == DMA_TO_DEVICE) {
BUG_ON(ctask->total_length == 0);
- /* bytes to be sent via RDMA operations */
- iser_ctask->rdma_data_count = ctask->total_length -
- ctask->imm_count -
- ctask->unsol_count;
- debug_scsi("cmd [itt %x total %d imm %d unsol_data %d "
- "rdma_data %d]\n",
+ debug_scsi("cmd [itt %x total %d imm %d unsol_data %d\n",
ctask->itt, ctask->total_length, ctask->imm_count,
- ctask->unsol_count, iser_ctask->rdma_data_count);
- } else
- /* bytes to be sent via RDMA operations */
- iser_ctask->rdma_data_count = ctask->total_length;
+ ctask->unsol_count);
+ }
iser_ctask_rdma_init(iser_ctask);
}
@@ -196,13 +189,10 @@ iscsi_iser_ctask_xmit_unsol_data(struct iscsi_conn *conn,
{
struct iscsi_data hdr;
int error = 0;
- struct iscsi_iser_cmd_task *iser_ctask = ctask->dd_data;
/* Send data-out PDUs while there's still unsolicited data to send */
while (ctask->unsol_count > 0) {
- iscsi_prep_unsolicit_data_pdu(ctask, &hdr,
- iser_ctask->rdma_data_count);
-
+ iscsi_prep_unsolicit_data_pdu(ctask, &hdr);
debug_scsi("Sending data-out: itt 0x%x, data count %d\n",
hdr.itt, ctask->data_count);
@@ -555,6 +545,7 @@ static struct scsi_host_template iscsi_iser_sht = {
.queuecommand = iscsi_queuecommand,
.can_queue = ISCSI_XMIT_CMDS_MAX - 1,
.sg_tablesize = ISCSI_ISER_SG_TABLESIZE,
+ .max_sectors = 1024,
.cmd_per_lun = ISCSI_MAX_CMD_PER_LUN,
.eh_abort_handler = iscsi_eh_abort,
.eh_host_reset_handler = iscsi_eh_host_reset,
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 3350ba690cf..2cf9ae0def1 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
@@ -171,6 +175,7 @@ struct iser_mem_reg {
u64 va;
u64 len;
void *mem_h;
+ int is_fmr;
};
struct iser_regd_buf {
@@ -257,7 +262,6 @@ struct iscsi_iser_conn {
struct iscsi_iser_cmd_task {
struct iser_desc desc;
struct iscsi_iser_conn *iser_conn;
- int rdma_data_count;/* RDMA bytes */
enum iser_task_status status;
int command_sent; /* set if command sent */
int dir[ISER_DIRS_NUM]; /* set if dir use*/
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 31950a522a1..d0b03f42658 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
@@ -55,7 +56,7 @@ int iser_regd_buff_release(struct iser_regd_buf *regd_buf)
if ((atomic_read(&regd_buf->ref_count) == 0) ||
atomic_dec_and_test(&regd_buf->ref_count)) {
/* if we used the dma mr, unreg is just NOP */
- if (regd_buf->reg.rkey != 0)
+ if (regd_buf->reg.is_fmr)
iser_unreg_mem(&regd_buf->reg);
if (regd_buf->dma_addr) {
@@ -90,9 +91,9 @@ void iser_reg_single(struct iser_device *device,
BUG_ON(dma_mapping_error(dma_addr));
regd_buf->reg.lkey = device->mr->lkey;
- regd_buf->reg.rkey = 0; /* indicate there's no need to unreg */
regd_buf->reg.len = regd_buf->data_size;
regd_buf->reg.va = dma_addr;
+ regd_buf->reg.is_fmr = 0;
regd_buf->dma_addr = dma_addr;
regd_buf->direction = direction;
@@ -239,7 +240,7 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data,
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 iser_data_buf *data,
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 iser_data_buf *data,
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
@@ -320,9 +329,9 @@ static void iser_data_buf_dump(struct iser_data_buf *data)
struct scatterlist *sg = (struct scatterlist *)data->buf;
int i;
- for (i = 0; i < data->size; i++)
+ for (i = 0; i < data->dma_nents; i++)
iser_err("sg[%d] dma_addr:0x%lX page:0x%p "
- "off:%d sz:%d dma_len:%d\n",
+ "off:0x%x sz:0x%x dma_len:0x%x\n",
i, (unsigned long)sg_dma_address(&sg[i]),
sg[i].page, sg[i].offset,
sg[i].length,sg_dma_len(&sg[i]));
@@ -352,7 +361,7 @@ static void iser_page_vec_build(struct iser_data_buf *data,
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);
@@ -370,15 +379,18 @@ int iser_reg_rdma_mem(struct iscsi_iser_cmd_task *iser_ctask,
enum iser_data_dir cmd_dir)
{
struct iser_conn *ib_conn = iser_ctask->iser_conn->ib_conn;
+ struct iser_device *device = ib_conn->device;
struct iser_data_buf *mem = &iser_ctask->data[cmd_dir];
struct iser_regd_buf *regd_buf;
int aligned_len;
int err;
+ int i;
+ struct scatterlist *sg;
regd_buf = &iser_ctask->rdma_regd[cmd_dir];
aligned_len = iser_data_buf_aligned_len(mem);
- if (aligned_len != mem->size) {
+ if (aligned_len != mem->dma_nents) {
iser_err("rdma alignment violation %d/%d aligned\n",
aligned_len, mem->size);
iser_data_buf_dump(mem);
@@ -389,10 +401,38 @@ int iser_reg_rdma_mem(struct iscsi_iser_cmd_task *iser_ctask,
mem = &iser_ctask->data_copy[cmd_dir];
}
- iser_page_vec_build(mem, ib_conn->page_vec);
- err = iser_reg_page_vec(ib_conn, ib_conn->page_vec, &regd_buf->reg);
- if (err)
- return err;
+ /* if there a single dma entry, FMR is not needed */
+ if (mem->dma_nents == 1) {
+ sg = (struct scatterlist *)mem->buf;
+
+ regd_buf->reg.lkey = device->mr->lkey;
+ regd_buf->reg.rkey = device->mr->rkey;
+ regd_buf->reg.len = sg_dma_len(&sg[0]);
+ regd_buf->reg.va = sg_dma_address(&sg[0]);
+ regd_buf->reg.is_fmr = 0;
+
+ iser_dbg("PHYSICAL Mem.register: lkey: 0x%08X rkey: 0x%08X "
+ "va: 0x%08lX sz: %ld]\n",
+ (unsigned int)regd_buf->reg.lkey,
+ (unsigned int)regd_buf->reg.rkey,
+ (unsigned long)regd_buf->reg.va,
+ (unsigned long)regd_buf->reg.len);
+ } else { /* use FMR for multiple dma entries */
+ iser_page_vec_build(mem, ib_conn->page_vec);
+ err = iser_reg_page_vec(ib_conn, ib_conn->page_vec, &regd_buf->reg);
+ if (err) {
+ iser_data_buf_dump(mem);
+ iser_err("mem->dma_nents = %d (dlength = 0x%x)\n", mem->dma_nents,
+ ntoh24(iser_ctask->desc.iscsi_header.dlength));
+ iser_err("page_vec: data_size = 0x%x, length = %d, offset = 0x%x\n",
+ ib_conn->page_vec->data_size, ib_conn->page_vec->length,
+ ib_conn->page_vec->offset);
+ for (i=0 ; i<ib_conn->page_vec->length ; i++)
+ iser_err("page_vec[%d] = 0x%llx\n", i,
+ (unsigned long long) ib_conn->page_vec->pages[i]);
+ return err;
+ }
+ }
/* take a reference on this regd buf such that it will not be released *
* (eg in send dto completion) before we get the scsi response */
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 72febf1f8ff..ecdca7fc1e4 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -88,8 +88,9 @@ static int iser_create_device_ib_res(struct iser_device *device)
iser_cq_tasklet_fn,
(unsigned long)device);
- device->mr = ib_get_dma_mr(device->pd,
- IB_ACCESS_LOCAL_WRITE);
+ device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE |
+ IB_ACCESS_REMOTE_WRITE |
+ IB_ACCESS_REMOTE_READ);
if (IS_ERR(device->mr))
goto dma_mr_err;
@@ -150,7 +151,7 @@ static int iser_create_ib_conn_res(struct iser_conn *ib_conn)
}
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;
@@ -604,8 +605,9 @@ int iser_reg_page_vec(struct iser_conn *ib_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->is_fmr = 1;
mem_reg->mem_h = (void *)mem;
mem_reg->va += page_vec->offset;