RDMA/rxe: Allow registering persistent flag for pmem MR only

Memory region could  support at most 2 flush access flags:
IB_ACCESS_FLUSH_PERSISTENT and IB_ACCESS_FLUSH_GLOBAL

But we only allow user to register persistent flush flags to the pmem MR
where it has the ability of persisting data across power cycles.

So registering a persistent access flag to a non-pmem MR will be rejected.

Link: https://lore.kernel.org/r/20221206130201.30986-5-lizhijian@fujitsu.com
CC: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index b7c9ff1..81a438e 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -111,6 +111,15 @@ void rxe_mr_init_dma(int access, struct rxe_mr *mr)
        mr->ibmr.type = IB_MR_TYPE_DMA;
 }
 
+static bool is_pmem_page(struct page *pg)
+{
+       unsigned long paddr = page_to_phys(pg);
+
+       return REGION_INTERSECTS ==
+              region_intersects(paddr, PAGE_SIZE, IORESOURCE_MEM,
+                                IORES_DESC_PERSISTENT_MEMORY);
+}
+
 int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova,
                     int access, struct rxe_mr *mr)
 {
@@ -146,16 +155,25 @@ int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova,
        num_buf                 = 0;
        map = mr->map;
        if (length > 0) {
-               buf = map[0]->buf;
+               bool persistent_access = access & IB_ACCESS_FLUSH_PERSISTENT;
 
+               buf = map[0]->buf;
                for_each_sgtable_page (&umem->sgt_append.sgt, &sg_iter, 0) {
+                       struct page *pg = sg_page_iter_page(&sg_iter);
+
+                       if (persistent_access && !is_pmem_page(pg)) {
+                               rxe_dbg_mr(mr, "Unable to register persistent access to non-pmem device\n");
+                               err = -EINVAL;
+                               goto err_release_umem;
+                       }
+
                        if (num_buf >= RXE_BUF_PER_MAP) {
                                map++;
                                buf = map[0]->buf;
                                num_buf = 0;
                        }
 
-                       vaddr = page_address(sg_page_iter_page(&sg_iter));
+                       vaddr = page_address(pg);
                        if (!vaddr) {
                                rxe_dbg_mr(mr, "Unable to get virtual address\n");
                                err = -ENOMEM;