diff options
author | Hans Westgaard Ry <hans.westgaard.ry@oracle.com> | 2020-01-15 14:43:39 +0200 |
---|---|---|
committer | Leon Romanovsky <leonro@mellanox.com> | 2020-01-18 11:48:19 +0200 |
commit | 2eafa1746f17872483d1033b0116ec71435ea19d (patch) | |
tree | 4765b46e30a6c4418612109e6a42554d4c3c0a00 /net/rds/rdma.c | |
parent | c4c86abb3f9fb3d5bc113fb996298a30ec63e07b (diff) | |
download | linux-stable-2eafa1746f17872483d1033b0116ec71435ea19d.tar.gz linux-stable-2eafa1746f17872483d1033b0116ec71435ea19d.tar.bz2 linux-stable-2eafa1746f17872483d1033b0116ec71435ea19d.zip |
net/rds: Handle ODP mr registration/unregistration
On-Demand-Paging MRs are registered using ib_reg_user_mr and
unregistered with ib_dereg_mr.
Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Diffstat (limited to 'net/rds/rdma.c')
-rw-r--r-- | net/rds/rdma.c | 151 |
1 files changed, 113 insertions, 38 deletions
diff --git a/net/rds/rdma.c b/net/rds/rdma.c index eb23c38ce2b3..3341eee87bf9 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -177,13 +177,14 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; + struct scatterlist *sg = NULL; unsigned int nr_pages; struct page **pages = NULL; - struct scatterlist *sg; void *trans_private; unsigned long flags; rds_rdma_cookie_t cookie; - unsigned int nents; + unsigned int nents = 0; + int need_odp = 0; long i; int ret; @@ -197,6 +198,21 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, goto out; } + /* If the combination of the addr and size requested for this memory + * region causes an integer overflow, return error. + */ + if (((args->vec.addr + args->vec.bytes) < args->vec.addr) || + PAGE_ALIGN(args->vec.addr + args->vec.bytes) < + (args->vec.addr + args->vec.bytes)) { + ret = -EINVAL; + goto out; + } + + if (!can_do_mlock()) { + ret = -EPERM; + goto out; + } + nr_pages = rds_pages_in_vec(&args->vec); if (nr_pages == 0) { ret = -EINVAL; @@ -250,36 +266,44 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * the zero page. */ ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1); - if (ret < 0) - goto out; - - nents = ret; - sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL); - if (!sg) { - ret = -ENOMEM; + if (ret == -EOPNOTSUPP) { + need_odp = 1; + } else if (ret <= 0) { goto out; - } - WARN_ON(!nents); - sg_init_table(sg, nents); - - /* Stick all pages into the scatterlist */ - for (i = 0 ; i < nents; i++) - sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); + } else { + nents = ret; + sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL); + if (!sg) { + ret = -ENOMEM; + goto out; + } + WARN_ON(!nents); + sg_init_table(sg, nents); - rdsdebug("RDS: trans_private nents is %u\n", nents); + /* Stick all pages into the scatterlist */ + for (i = 0 ; i < nents; i++) + sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); + rdsdebug("RDS: trans_private nents is %u\n", nents); + } /* Obtain a transport specific MR. If this succeeds, the * s/g list is now owned by the MR. * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ - trans_private = rs->rs_transport->get_mr(sg, nents, rs, - &mr->r_key, - cp ? cp->cp_conn : NULL); + trans_private = rs->rs_transport->get_mr( + sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL, + args->vec.addr, args->vec.bytes, + need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED); if (IS_ERR(trans_private)) { - for (i = 0 ; i < nents; i++) - put_page(sg_page(&sg[i])); - kfree(sg); + /* In ODP case, we don't GUP pages, so don't need + * to release anything. + */ + if (!need_odp) { + for (i = 0 ; i < nents; i++) + put_page(sg_page(&sg[i])); + kfree(sg); + } ret = PTR_ERR(trans_private); goto out; } @@ -293,7 +317,11 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * map page aligned regions. So we keep the offset, and build * a 64bit cookie containing <R_Key, offset> and pass that * around. */ - cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK); + if (need_odp) + cookie = rds_rdma_make_cookie(mr->r_key, 0); + else + cookie = rds_rdma_make_cookie(mr->r_key, + args->vec.addr & ~PAGE_MASK); if (cookie_ret) *cookie_ret = cookie; @@ -458,22 +486,26 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) { unsigned int i; - for (i = 0; i < ro->op_nents; i++) { - struct page *page = sg_page(&ro->op_sg[i]); - - /* Mark page dirty if it was possibly modified, which - * is the case for a RDMA_READ which copies from remote - * to local memory */ - if (!ro->op_write) { - WARN_ON(!page->mapping && irqs_disabled()); - set_page_dirty(page); + if (ro->op_odp_mr) { + rds_mr_put(ro->op_odp_mr); + } else { + for (i = 0; i < ro->op_nents; i++) { + struct page *page = sg_page(&ro->op_sg[i]); + + /* Mark page dirty if it was possibly modified, which + * is the case for a RDMA_READ which copies from remote + * to local memory + */ + if (!ro->op_write) + set_page_dirty(page); + put_page(page); } - put_page(page); } kfree(ro->op_notifier); ro->op_notifier = NULL; ro->op_active = 0; + ro->op_odp_mr = NULL; } void rds_atomic_free_op(struct rm_atomic_op *ao) @@ -583,6 +615,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct rds_iovec *iovs; unsigned int i, j; int ret = 0; + bool odp_supported = true; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || rm->rdma.op_active) @@ -604,6 +637,9 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, ret = -EINVAL; goto out_ret; } + /* odp-mr is not supported for multiple requests within one message */ + if (args->nr_local != 1) + odp_supported = false; iovs = vec->iov; @@ -625,6 +661,8 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_silent = !!(args->flags & RDS_RDMA_SILENT); op->op_active = 1; op->op_recverr = rs->rs_recverr; + op->op_odp_mr = NULL; + WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); if (!op->op_sg) @@ -674,10 +712,44 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, * If it's a READ operation, we need to pin the pages for writing. */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); - if (ret < 0) + if ((!odp_supported && ret <= 0) || + (odp_supported && ret <= 0 && ret != -EOPNOTSUPP)) goto out_pages; - else - ret = 0; + + if (ret == -EOPNOTSUPP) { + struct rds_mr *local_odp_mr; + + if (!rs->rs_transport->get_mr) { + ret = -EOPNOTSUPP; + goto out_pages; + } + local_odp_mr = + kzalloc(sizeof(*local_odp_mr), GFP_KERNEL); + if (!local_odp_mr) { + ret = -ENOMEM; + goto out_pages; + } + RB_CLEAR_NODE(&local_odp_mr->r_rb_node); + refcount_set(&local_odp_mr->r_refcount, 1); + local_odp_mr->r_trans = rs->rs_transport; + local_odp_mr->r_sock = rs; + local_odp_mr->r_trans_private = + rs->rs_transport->get_mr( + NULL, 0, rs, &local_odp_mr->r_key, NULL, + iov->addr, iov->bytes, ODP_VIRTUAL); + if (IS_ERR(local_odp_mr->r_trans_private)) { + ret = IS_ERR(local_odp_mr->r_trans_private); + rdsdebug("get_mr ret %d %p\"", ret, + local_odp_mr->r_trans_private); + kfree(local_odp_mr); + ret = -EOPNOTSUPP; + goto out_pages; + } + rdsdebug("Need odp; local_odp_mr %p trans_private %p\n", + local_odp_mr, local_odp_mr->r_trans_private); + op->op_odp_mr = local_odp_mr; + op->op_odp_addr = iov->addr; + } rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); @@ -693,6 +765,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); + sg_dma_len(sg) = sg->length; rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", sg->offset, sg->length, iov->addr, iov->bytes); @@ -711,6 +784,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_pages; } op->op_bytes = nr_bytes; + ret = 0; out_pages: kfree(pages); @@ -757,7 +831,8 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { - mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE); + mr->r_trans->sync_mr(mr->r_trans_private, + DMA_TO_DEVICE); rm->rdma.op_rdma_mr = mr; } return err; |