IB/uverbs: Export ib_umem_get()/ib_umem_release() to modules
Export ib_umem_get()/ib_umem_release() and put low-level drivers in
control of when to call ib_umem_get() to pin and DMA map userspace,
rather than always calling it in ib_uverbs_reg_mr() before calling the
low-level driver's reg_user_mr method.
Also move these functions to be in the ib_core module instead of
ib_uverbs, so that driver modules using them do not depend on
ib_uverbs.
This has a number of advantages:
- It is better design from the standpoint of making generic code a
library that can be used or overridden by device-specific code as
the details of specific devices dictate.
- Drivers that do not need to pin userspace memory regions do not
need to take the performance hit of calling ib_mem_get(). For
example, although I have not tried to implement it in this patch,
the ipath driver should be able to avoid pinning memory and just
use copy_{to,from}_user() to access userspace memory regions.
- Buffers that need special mapping treatment can be identified by
the low-level driver. For example, it may be possible to solve
some Altix-specific memory ordering issues with mthca CQs in
userspace by mapping CQ buffers with extra flags.
- Drivers that need to pin and DMA map userspace memory for things
other than memory regions can use ib_umem_get() directly, instead
of hacks using extra parameters to their reg_phys_mr method. For
example, the mlx4 driver that is pending being merged needs to pin
and DMA map QP and CQ buffers, but it does not need to create a
memory key for these buffers. So the cleanest solution is for mlx4
to call ib_umem_get() in the create_qp and create_cq methods.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/infiniband/hw/ehca/ehca_classes.h
index 10fb8fb..f64d42b 100644
--- a/drivers/infiniband/hw/ehca/ehca_classes.h
+++ b/drivers/infiniband/hw/ehca/ehca_classes.h
@@ -176,6 +176,7 @@
struct ib_mr ib_mr; /* must always be first in ehca_mr */
struct ib_fmr ib_fmr; /* must always be first in ehca_mr */
} ib;
+ struct ib_umem *umem;
spinlock_t mrlock;
enum ehca_mr_flag flags;
diff --git a/drivers/infiniband/hw/ehca/ehca_iverbs.h b/drivers/infiniband/hw/ehca/ehca_iverbs.h
index e14b029..37e7fe0 100644
--- a/drivers/infiniband/hw/ehca/ehca_iverbs.h
+++ b/drivers/infiniband/hw/ehca/ehca_iverbs.h
@@ -78,8 +78,7 @@
int num_phys_buf,
int mr_access_flags, u64 *iova_start);
-struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd,
- struct ib_umem *region,
+struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt,
int mr_access_flags, struct ib_udata *udata);
int ehca_rereg_phys_mr(struct ib_mr *mr,
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c b/drivers/infiniband/hw/ehca/ehca_mrmw.c
index d22ab56..84c5bb4 100644
--- a/drivers/infiniband/hw/ehca/ehca_mrmw.c
+++ b/drivers/infiniband/hw/ehca/ehca_mrmw.c
@@ -39,6 +39,8 @@
* POSSIBILITY OF SUCH DAMAGE.
*/
+#include <rdma/ib_umem.h>
+
#include <asm/current.h>
#include "ehca_iverbs.h"
@@ -238,10 +240,8 @@
/*----------------------------------------------------------------------*/
-struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd,
- struct ib_umem *region,
- int mr_access_flags,
- struct ib_udata *udata)
+struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt,
+ int mr_access_flags, struct ib_udata *udata)
{
struct ib_mr *ib_mr;
struct ehca_mr *e_mr;
@@ -257,11 +257,7 @@
ehca_gen_err("bad pd=%p", pd);
return ERR_PTR(-EFAULT);
}
- if (!region) {
- ehca_err(pd->device, "bad input values: region=%p", region);
- ib_mr = ERR_PTR(-EINVAL);
- goto reg_user_mr_exit0;
- }
+
if (((mr_access_flags & IB_ACCESS_REMOTE_WRITE) &&
!(mr_access_flags & IB_ACCESS_LOCAL_WRITE)) ||
((mr_access_flags & IB_ACCESS_REMOTE_ATOMIC) &&
@@ -275,17 +271,10 @@
ib_mr = ERR_PTR(-EINVAL);
goto reg_user_mr_exit0;
}
- if (region->page_size != PAGE_SIZE) {
- ehca_err(pd->device, "page size not supported, "
- "region->page_size=%x", region->page_size);
- ib_mr = ERR_PTR(-EINVAL);
- goto reg_user_mr_exit0;
- }
- if ((region->length == 0) ||
- ((region->virt_base + region->length) < region->virt_base)) {
+ if (length == 0 || virt + length < virt) {
ehca_err(pd->device, "bad input values: length=%lx "
- "virt_base=%lx", region->length, region->virt_base);
+ "virt_base=%lx", length, virt);
ib_mr = ERR_PTR(-EINVAL);
goto reg_user_mr_exit0;
}
@@ -297,40 +286,55 @@
goto reg_user_mr_exit0;
}
+ e_mr->umem = ib_umem_get(pd->uobject->context, start, length,
+ mr_access_flags);
+ if (IS_ERR(e_mr->umem)) {
+ ib_mr = (void *) e_mr->umem;
+ goto reg_user_mr_exit1;
+ }
+
+ if (e_mr->umem->page_size != PAGE_SIZE) {
+ ehca_err(pd->device, "page size not supported, "
+ "e_mr->umem->page_size=%x", e_mr->umem->page_size);
+ ib_mr = ERR_PTR(-EINVAL);
+ goto reg_user_mr_exit2;
+ }
+
/* determine number of MR pages */
- num_pages_mr = (((region->virt_base % PAGE_SIZE) + region->length +
- PAGE_SIZE - 1) / PAGE_SIZE);
- num_pages_4k = (((region->virt_base % EHCA_PAGESIZE) + region->length +
- EHCA_PAGESIZE - 1) / EHCA_PAGESIZE);
+ num_pages_mr = (((virt % PAGE_SIZE) + length + PAGE_SIZE - 1) /
+ PAGE_SIZE);
+ num_pages_4k = (((virt % EHCA_PAGESIZE) + length + EHCA_PAGESIZE - 1) /
+ EHCA_PAGESIZE);
/* register MR on HCA */
pginfo.type = EHCA_MR_PGI_USER;
pginfo.num_pages = num_pages_mr;
pginfo.num_4k = num_pages_4k;
- pginfo.region = region;
- pginfo.next_4k = region->offset / EHCA_PAGESIZE;
+ pginfo.region = e_mr->umem;
+ pginfo.next_4k = e_mr->umem->offset / EHCA_PAGESIZE;
pginfo.next_chunk = list_prepare_entry(pginfo.next_chunk,
- (®ion->chunk_list),
+ (&e_mr->umem->chunk_list),
list);
- ret = ehca_reg_mr(shca, e_mr, (u64*)region->virt_base,
- region->length, mr_access_flags, e_pd, &pginfo,
- &e_mr->ib.ib_mr.lkey, &e_mr->ib.ib_mr.rkey);
+ ret = ehca_reg_mr(shca, e_mr, (u64*) virt, length, mr_access_flags, e_pd,
+ &pginfo, &e_mr->ib.ib_mr.lkey, &e_mr->ib.ib_mr.rkey);
if (ret) {
ib_mr = ERR_PTR(ret);
- goto reg_user_mr_exit1;
+ goto reg_user_mr_exit2;
}
/* successful registration of all pages */
return &e_mr->ib.ib_mr;
+reg_user_mr_exit2:
+ ib_umem_release(e_mr->umem);
reg_user_mr_exit1:
ehca_mr_delete(e_mr);
reg_user_mr_exit0:
if (IS_ERR(ib_mr))
- ehca_err(pd->device, "rc=%lx pd=%p region=%p mr_access_flags=%x"
+ ehca_err(pd->device, "rc=%lx pd=%p mr_access_flags=%x"
" udata=%p",
- PTR_ERR(ib_mr), pd, region, mr_access_flags, udata);
+ PTR_ERR(ib_mr), pd, mr_access_flags, udata);
return ib_mr;
} /* end ehca_reg_user_mr() */
@@ -596,6 +600,9 @@
goto dereg_mr_exit0;
}
+ if (e_mr->umem)
+ ib_umem_release(e_mr->umem);
+
/* successful deregistration */
ehca_mr_delete(e_mr);