[ofa-general] [PATCH] ib_core: Use weak ordering for data registered memory

[Eli Cohen]

Some architectures support weak ordering in which case better
performance is possible. IB registered memory used for data can be
weakly ordered becuase the the completion queues' buffers are
registered as strongly ordered. This will result in flushing all data
related outstanding DMA requests by the HCA when a completion is DMAed
to a completion queue buffer.
This patch will allow weak ordering for data if ib_core is loaded with
the module parameter, allow_weak_ordering, set to a none zero value.

Signed-off-by: Eli Cohen <eli at mellanox.co.il>
Signed-off-by: Arnd Bergmann <arnd at arndb.de>
---

Roland,
this patch has a fix to bug inserted while I recreated the patch from
another one so please use this one.
Also, are you going to push this to 2.6.28?

 drivers/infiniband/core/umem.c |   12 ++++++++++--
 include/rdma/ib_umem.h         |    2 ++
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 6f7c096..da5e247 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -40,6 +40,10 @@
 
 #include "uverbs.h"
 
+static int allow_weak_ordering;
+module_param(allow_weak_ordering, bool, 0444);
+MODULE_PARM_DESC(allow_weak_ordering,  "Allow weak ordering for data registered memory");
+
 #define IB_UMEM_MAX_PAGE_CHUNK						\
 	((PAGE_SIZE - offsetof(struct ib_umem_chunk, page_list)) /	\
 	 ((void *) &((struct ib_umem_chunk *) 0)->page_list[1] -	\
@@ -51,8 +55,8 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 	int i;
 
 	list_for_each_entry_safe(chunk, tmp, &umem->chunk_list, list) {
-		ib_dma_unmap_sg(dev, chunk->page_list,
-				chunk->nents, DMA_BIDIRECTIONAL);
+		ib_dma_unmap_sg_attrs(dev, chunk->page_list,
+				      chunk->nents, DMA_BIDIRECTIONAL, &chunk->attrs);
 		for (i = 0; i < chunk->nents; ++i) {
 			struct page *page = sg_page(&chunk->page_list[i]);
 
@@ -91,6 +95,9 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	if (dmasync)
 		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
+	else if (allow_weak_ordering)
+		dma_set_attr(DMA_ATTR_WEAK_ORDERING, &attrs);
+
 
 	if (!can_do_mlock())
 		return ERR_PTR(-EPERM);
@@ -169,6 +176,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 				goto out;
 			}
 
+			chunk->attrs = attrs;
 			chunk->nents = min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK);
 			sg_init_table(chunk->page_list, chunk->nents);
 			for (i = 0; i < chunk->nents; ++i) {
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 9ee0d2e..90f3712 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -36,6 +36,7 @@
 #include <linux/list.h>
 #include <linux/scatterlist.h>
 #include <linux/workqueue.h>
+#include <linux/dma-attrs.h>
 
 struct ib_ucontext;
 
@@ -56,6 +57,7 @@ struct ib_umem_chunk {
 	struct list_head	list;
 	int                     nents;
 	int                     nmap;
+	struct dma_attrs	attrs;
 	struct scatterlist      page_list[0];
 };
 
-- 
1.6.0.2