IB/core: Add flags for on demand paging support

* Add a configuration option for enable on-demand paging support in
  the infiniband subsystem (CONFIG_INFINIBAND_ON_DEMAND_PAGING). In a
  later patch, this configuration option will select the MMU_NOTIFIER
  configuration option to enable mmu notifiers.
* Add a flag for on demand paging (ODP) support in the IB device capabilities.
* Add a flag to request ODP MR in the access flags to reg_mr.
* Fail registrations done with the ODP flag when the low-level driver
  doesn't support this.
* Change the conditions in which an MR will be writable to explicitly
  specify the access flags.  This is to avoid making an MR writable just
  because it is an ODP MR.
* Add a ODP capabilities to the extended query device verb.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

5 files changed, 81 insertions, 5 deletions

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 77089399359b..089a2c2af329 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -38,6 +38,16 @@ config INFINIBAND_USER_MEM
 	depends on INFINIBAND_USER_ACCESS != n
 	default y
 
+config INFINIBAND_ON_DEMAND_PAGING
+	bool "InfiniBand on-demand paging support"
+	depends on INFINIBAND_USER_MEM
+	default y
+	---help---
+	  On demand paging support for the InfiniBand subsystem.
+	  Together with driver support this allows registration of
+	  memory regions without pinning their pages, fetching the
+	  pages on demand instead.
+
 config INFINIBAND_ADDR_TRANS
 	bool
 	depends on INFINIBAND
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 6f152628e0d2..c328e4693d14 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -107,13 +107,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	umem->page_size = PAGE_SIZE;
 	umem->pid       = get_task_pid(current, PIDTYPE_PID);
 	/*
-	 * We ask for writable memory if any access flags other than
-	 * "remote read" are set.  "Local write" and "remote write"
+	 * We ask for writable memory if any of the following
+	 * access flags are set.  "Local write" and "remote write"
 	 * obviously require write access.  "Remote atomic" can do
 	 * things like fetch and add, which will modify memory, and
 	 * "MW bind" can change permissions by binding a window.
 	 */
-	umem->writable  = !!(access & ~IB_ACCESS_REMOTE_READ);
+	umem->writable  = !!(access &
+		(IB_ACCESS_LOCAL_WRITE   | IB_ACCESS_REMOTE_WRITE |
+		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
 
 	/* We assume the memory is from hugetlb until proved otherwise */
 	umem->hugetlb   = 1;
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index c7a43624c96b..f9326ccda4b5 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -953,6 +953,18 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 		goto err_free;
 	}
 
+	if (cmd.access_flags & IB_ACCESS_ON_DEMAND) {
+		struct ib_device_attr attr;
+
+		ret = ib_query_device(pd->device, &attr);
+		if (ret || !(attr.device_cap_flags &
+				IB_DEVICE_ON_DEMAND_PAGING)) {
+			pr_debug("ODP support not available\n");
+			ret = -EINVAL;
+			goto err_put;
+		}
+	}
+
 	mr = pd->device->reg_user_mr(pd, cmd.start, cmd.length, cmd.hca_va,
 				     cmd.access_flags, &udata);
 	if (IS_ERR(mr)) {
@@ -3289,6 +3301,19 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	copy_query_dev_fields(file, &resp.base, &attr);
 	resp.comp_mask = 0;
 
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	if (cmd.comp_mask & IB_USER_VERBS_EX_QUERY_DEVICE_ODP) {
+		resp.odp_caps.general_caps = attr.odp_caps.general_caps;
+		resp.odp_caps.per_transport_caps.rc_odp_caps =
+			attr.odp_caps.per_transport_caps.rc_odp_caps;
+		resp.odp_caps.per_transport_caps.uc_odp_caps =
+			attr.odp_caps.per_transport_caps.uc_odp_caps;
+		resp.odp_caps.per_transport_caps.ud_odp_caps =
+			attr.odp_caps.per_transport_caps.ud_odp_caps;
+		resp.comp_mask |= IB_USER_VERBS_EX_QUERY_DEVICE_ODP;
+	}
+#endif
+
 	err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
 	if (err)
 		return err;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 97a999f9e4d8..a41bc5a39ebf 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -123,7 +123,8 @@ enum ib_device_cap_flags {
 	IB_DEVICE_MEM_WINDOW_TYPE_2A	= (1<<23),
 	IB_DEVICE_MEM_WINDOW_TYPE_2B	= (1<<24),
 	IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29),
-	IB_DEVICE_SIGNATURE_HANDOVER	= (1<<30)
+	IB_DEVICE_SIGNATURE_HANDOVER	= (1<<30),
+	IB_DEVICE_ON_DEMAND_PAGING	= (1<<31),
 };
 
 enum ib_signature_prot_cap {
@@ -143,6 +144,27 @@ enum ib_atomic_cap {
 	IB_ATOMIC_GLOB
 };
 
+enum ib_odp_general_cap_bits {
+	IB_ODP_SUPPORT = 1 << 0,
+};
+
+enum ib_odp_transport_cap_bits {
+	IB_ODP_SUPPORT_SEND	= 1 << 0,
+	IB_ODP_SUPPORT_RECV	= 1 << 1,
+	IB_ODP_SUPPORT_WRITE	= 1 << 2,
+	IB_ODP_SUPPORT_READ	= 1 << 3,
+	IB_ODP_SUPPORT_ATOMIC	= 1 << 4,
+};
+
+struct ib_odp_caps {
+	uint64_t general_caps;
+	struct {
+		uint32_t  rc_odp_caps;
+		uint32_t  uc_odp_caps;
+		uint32_t  ud_odp_caps;
+	} per_transport_caps;
+};
+
 struct ib_device_attr {
 	u64			fw_ver;
 	__be64			sys_image_guid;
@@ -186,6 +208,7 @@ struct ib_device_attr {
 	u8			local_ca_ack_delay;
 	int			sig_prot_cap;
 	int			sig_guard_cap;
+	struct ib_odp_caps	odp_caps;
 };
 
 enum ib_mtu {
@@ -1073,7 +1096,8 @@ enum ib_access_flags {
 	IB_ACCESS_REMOTE_READ	= (1<<2),
 	IB_ACCESS_REMOTE_ATOMIC	= (1<<3),
 	IB_ACCESS_MW_BIND	= (1<<4),
-	IB_ZERO_BASED		= (1<<5)
+	IB_ZERO_BASED		= (1<<5),
+	IB_ACCESS_ON_DEMAND     = (1<<6),
 };
 
 struct ib_phys_buf {
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index e8a96071e352..4275b961bf60 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -202,15 +202,30 @@ struct ib_uverbs_query_device_resp {
 	__u8  reserved[4];
 };
 
+enum {
+	IB_USER_VERBS_EX_QUERY_DEVICE_ODP =		1ULL << 0,
+};
+
 struct ib_uverbs_ex_query_device {
 	__u32 comp_mask;
 	__u32 reserved;
 };
 
+struct ib_uverbs_odp_caps {
+	__u64 general_caps;
+	struct {
+		__u32 rc_odp_caps;
+		__u32 uc_odp_caps;
+		__u32 ud_odp_caps;
+	} per_transport_caps;
+	__u32 reserved;
+};
+
 struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_query_device_resp base;
 	__u32 comp_mask;
 	__u32 reserved;
+	struct ib_uverbs_odp_caps odp_caps;
 };
 
 struct ib_uverbs_query_port {