提交 4c67e2bf 编写于 作者: S Sagi Grimberg 提交者: Doug Ledford

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: NSagi Grimberg <sagig@mellanox.com>
Tested-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDoug Ledford <dledford@redhat.com>
上级 63e8790d
......@@ -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);
......@@ -738,6 +738,7 @@ enum ib_wc_opcode {
IB_WC_LSO,
IB_WC_LOCAL_INV,
IB_WC_FAST_REG_MR,
IB_WC_REG_MR,
IB_WC_MASKED_COMP_SWAP,
IB_WC_MASKED_FETCH_ADD,
/*
......@@ -1025,6 +1026,7 @@ enum ib_wr_opcode {
IB_WR_RDMA_READ_WITH_INV,
IB_WR_LOCAL_INV,
IB_WR_FAST_REG_MR,
IB_WR_REG_MR,
IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
IB_WR_BIND_MW,
......@@ -1157,6 +1159,18 @@ static inline struct ib_fast_reg_wr *fast_reg_wr(struct ib_send_wr *wr)
return container_of(wr, struct ib_fast_reg_wr, wr);
}
struct ib_reg_wr {
struct ib_send_wr wr;
struct ib_mr *mr;
u32 key;
int access;
};
static inline struct ib_reg_wr *reg_wr(struct ib_send_wr *wr)
{
return container_of(wr, struct ib_reg_wr, wr);
}
struct ib_bind_mw_wr {
struct ib_send_wr wr;
struct ib_mw *mw;
......@@ -1369,6 +1383,9 @@ struct ib_mr {
struct ib_uobject *uobject;
u32 lkey;
u32 rkey;
u64 iova;
u32 length;
unsigned int page_size;
atomic_t usecnt; /* count number of MWs */
};
......@@ -1753,6 +1770,9 @@ struct ib_device {
struct ib_mr * (*alloc_mr)(struct ib_pd *pd,
enum ib_mr_type mr_type,
u32 max_num_sg);
int (*map_mr_sg)(struct ib_mr *mr,
struct scatterlist *sg,
int sg_nents);
struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device,
int page_list_len);
void (*free_fast_reg_page_list)(struct ib_fast_reg_page_list *page_list);
......@@ -3059,4 +3079,28 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port,
u16 pkey, const union ib_gid *gid,
const struct sockaddr *addr);
int ib_map_mr_sg(struct ib_mr *mr,
struct scatterlist *sg,
int sg_nents,
unsigned int page_size);
static inline int
ib_map_mr_sg_zbva(struct ib_mr *mr,
struct scatterlist *sg,
int sg_nents,
unsigned int page_size)
{
int n;
n = ib_map_mr_sg(mr, sg, sg_nents, page_size);
mr->iova = 0;
return n;
}
int ib_sg_to_pages(struct ib_mr *mr,
struct scatterlist *sgl,
int sg_nents,
int (*set_page)(struct ib_mr *, u64));
#endif /* IB_VERBS_H */
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册