RDMA/core: Add memory management extensions support

This patch adds support for the IB "base memory management extension"
(BMME) and the equivalent iWARP operations (which the iWARP verbs
mandates all devices must implement).  The new operations are:

 - Allocate an ib_mr for use in fast register work requests.

 - Allocate/free a physical buffer lists for use in fast register work
   requests.  This allows device drivers to allocate this memory as
   needed for use in posting send requests (eg via dma_alloc_coherent).

 - New send queue work requests:
   * send with remote invalidate
   * fast register memory region
   * local invalidate memory region
   * RDMA read with invalidate local memory region (iWARP only)

Consumer interface details:

 - A new device capability flag IB_DEVICE_MEM_MGT_EXTENSIONS is added
   to indicate device support for these features.

 - New send work request opcodes IB_WR_FAST_REG_MR, IB_WR_LOCAL_INV,
   IB_WR_RDMA_READ_WITH_INV are added.

 - A new consumer API function, ib_alloc_mr() is added to allocate
   fast register memory regions.

 - New consumer API functions, ib_alloc_fast_reg_page_list() and
   ib_free_fast_reg_page_list() are added to allocate and free
   device-specific memory for fast registration page lists.

 - A new consumer API function, ib_update_fast_reg_key(), is added to
   allow the key portion of the R_Key and L_Key of a fast registration
   MR to be updated.  Consumers call this if desired before posting
   a IB_WR_FAST_REG_MR work request.

Consumers can use this as follows:

 - MR is allocated with ib_alloc_mr().

 - Page list memory is allocated with ib_alloc_fast_reg_page_list().

 - MR R_Key/L_Key "key" field is updated with ib_update_fast_reg_key().

 - MR made VALID and bound to a specific page list via
   ib_post_send(IB_WR_FAST_REG_MR)

 - MR made INVALID via ib_post_send(IB_WR_LOCAL_INV),
   ib_post_send(IB_WR_RDMA_READ_WITH_INV) or an incoming send with
   invalidate operation.

 - MR is deallocated with ib_dereg_mr()

 - page lists dealloced via ib_free_fast_reg_page_list().

Applications can allocate a fast register MR once, and then can
repeatedly bind the MR to different physical block lists (PBLs) via
posting work requests to a send queue (SQ).  For each outstanding
MR-to-PBL binding in the SQ pipe, a fast_reg_page_list needs to be
allocated (the fast_reg_page_list is owned by the low-level driver
from the consumer posting a work request until the request completes).
Thus pipelining can be achieved while still allowing device-specific
page_list processing.

The 32-bit fast register memory key/STag is composed of a 24-bit index
and an 8-bit key.  The application can change the key each time it
fast registers thus allowing more control over the peer's use of the
key/STag (ie it can effectively be changed each time the rkey is
rebound to a page list).

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

drivers/infiniband/core/uverbs_cmd.c

@@ -917,7 +917,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file,
 		resp->wc[i].opcode 	   = wc[i].opcode;
 		resp->wc[i].vendor_err 	   = wc[i].vendor_err;
 		resp->wc[i].byte_len 	   = wc[i].byte_len;
-		resp->wc[i].imm_data 	   = (__u32 __force) wc[i].imm_data;
+		resp->wc[i].ex.imm_data    = (__u32 __force) wc[i].ex.imm_data;
 		resp->wc[i].qp_num 	   = wc[i].qp->qp_num;
 		resp->wc[i].src_qp 	   = wc[i].src_qp;
 		resp->wc[i].wc_flags 	   = wc[i].wc_flags;

drivers/infiniband/core/verbs.c

@@ -753,6 +753,52 @@ int ib_dereg_mr(struct ib_mr *mr)
 }
 EXPORT_SYMBOL(ib_dereg_mr);
 
+struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len)
+{
+	struct ib_mr *mr;
+
+	if (!pd->device->alloc_fast_reg_mr)
+		return ERR_PTR(-ENOSYS);
+
+	mr = pd->device->alloc_fast_reg_mr(pd, max_page_list_len);
+
+	if (!IS_ERR(mr)) {
+		mr->device  = pd->device;
+		mr->pd      = pd;
+		mr->uobject = NULL;
+		atomic_inc(&pd->usecnt);
+		atomic_set(&mr->usecnt, 0);
+	}
+
+	return mr;
+}
+EXPORT_SYMBOL(ib_alloc_fast_reg_mr);
+
+struct ib_fast_reg_page_list *ib_alloc_fast_reg_page_list(struct ib_device *device,
+							  int max_page_list_len)
+{
+	struct ib_fast_reg_page_list *page_list;
+
+	if (!device->alloc_fast_reg_page_list)
+		return ERR_PTR(-ENOSYS);
+
+	page_list = device->alloc_fast_reg_page_list(device, max_page_list_len);
+
+	if (!IS_ERR(page_list)) {
+		page_list->device = device;
+		page_list->max_page_list_len = max_page_list_len;
+	}
+
+	return page_list;
+}
+EXPORT_SYMBOL(ib_alloc_fast_reg_page_list);
+
+void ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
+{
+	page_list->device->free_fast_reg_page_list(page_list);
+}
+EXPORT_SYMBOL(ib_free_fast_reg_page_list);
+
 /* Memory windows */
 
 struct ib_mw *ib_alloc_mw(struct ib_pd *pd)

drivers/infiniband/hw/ehca/ehca_reqs.c

@@ -681,7 +681,7 @@ poll_cq_one_read_cqe:
 	wc->dlid_path_bits = cqe->dlid;
 	wc->src_qp = cqe->remote_qp_number;
 	wc->wc_flags = cqe->w_completion_flags;
-	wc->imm_data = cpu_to_be32(cqe->immediate_data);
+	wc->ex.imm_data = cpu_to_be32(cqe->immediate_data);
 	wc->sl = cqe->service_level;
 
 poll_cq_one_exit0:

drivers/infiniband/hw/ipath/ipath_cq.c

@@ -82,7 +82,7 @@ void ipath_cq_enter(struct ipath_cq *cq, struct ib_wc *entry, int solicited)
 		wc->uqueue[head].opcode = entry->opcode;
 		wc->uqueue[head].vendor_err = entry->vendor_err;
 		wc->uqueue[head].byte_len = entry->byte_len;
-		wc->uqueue[head].imm_data = (__u32 __force)entry->imm_data;
+		wc->uqueue[head].ex.imm_data = (__u32 __force) entry->ex.imm_data;
 		wc->uqueue[head].qp_num = entry->qp->qp_num;
 		wc->uqueue[head].src_qp = entry->src_qp;
 		wc->uqueue[head].wc_flags = entry->wc_flags;

drivers/infiniband/hw/ipath/ipath_rc.c

@@ -1703,11 +1703,11 @@ void ipath_rc_rcv(struct ipath_ibdev *dev, struct ipath_ib_header *hdr,
 	case OP(SEND_LAST_WITH_IMMEDIATE):
 	send_last_imm:
 		if (header_in_data) {
-			wc.imm_data = *(__be32 *) data;
+			wc.ex.imm_data = *(__be32 *) data;
 			data += sizeof(__be32);
 		} else {
 			/* Immediate data comes after BTH */
-			wc.imm_data = ohdr->u.imm_data;
+			wc.ex.imm_data = ohdr->u.imm_data;
 		}
 		hdrsize += 4;
 		wc.wc_flags = IB_WC_WITH_IMM;

drivers/infiniband/hw/ipath/ipath_ruc.c

@@ -331,7 +331,7 @@ again:
 	switch (wqe->wr.opcode) {
 	case IB_WR_SEND_WITH_IMM:
 		wc.wc_flags = IB_WC_WITH_IMM;
-		wc.imm_data = wqe->wr.ex.imm_data;
+		wc.ex.imm_data = wqe->wr.ex.imm_data;
 		/* FALLTHROUGH */
 	case IB_WR_SEND:
 		if (!ipath_get_rwqe(qp, 0))
@@ -342,7 +342,7 @@ again:
 		if (unlikely(!(qp->qp_access_flags & IB_ACCESS_REMOTE_WRITE)))
 			goto inv_err;
 		wc.wc_flags = IB_WC_WITH_IMM;
-		wc.imm_data = wqe->wr.ex.imm_data;
+		wc.ex.imm_data = wqe->wr.ex.imm_data;
 		if (!ipath_get_rwqe(qp, 1))
 			goto rnr_nak;
 		/* FALLTHROUGH */

drivers/infiniband/hw/ipath/ipath_uc.c

@@ -379,11 +379,11 @@ void ipath_uc_rcv(struct ipath_ibdev *dev, struct ipath_ib_header *hdr,
 	case OP(SEND_LAST_WITH_IMMEDIATE):
 	send_last_imm:
 		if (header_in_data) {
-			wc.imm_data = *(__be32 *) data;
+			wc.ex.imm_data = *(__be32 *) data;
 			data += sizeof(__be32);
 		} else {
 			/* Immediate data comes after BTH */
-			wc.imm_data = ohdr->u.imm_data;
+			wc.ex.imm_data = ohdr->u.imm_data;
 		}
 		hdrsize += 4;
 		wc.wc_flags = IB_WC_WITH_IMM;
@@ -483,11 +483,11 @@ void ipath_uc_rcv(struct ipath_ibdev *dev, struct ipath_ib_header *hdr,
 	case OP(RDMA_WRITE_LAST_WITH_IMMEDIATE):
 	rdma_last_imm:
 		if (header_in_data) {
-			wc.imm_data = *(__be32 *) data;
+			wc.ex.imm_data = *(__be32 *) data;
 			data += sizeof(__be32);
 		} else {
 			/* Immediate data comes after BTH */
-			wc.imm_data = ohdr->u.imm_data;
+			wc.ex.imm_data = ohdr->u.imm_data;
 		}
 		hdrsize += 4;
 		wc.wc_flags = IB_WC_WITH_IMM;

drivers/infiniband/hw/ipath/ipath_ud.c

@@ -96,7 +96,7 @@ static void ipath_ud_loopback(struct ipath_qp *sqp, struct ipath_swqe *swqe)
 
 	if (swqe->wr.opcode == IB_WR_SEND_WITH_IMM) {
 		wc.wc_flags = IB_WC_WITH_IMM;
-		wc.imm_data = swqe->wr.ex.imm_data;
+		wc.ex.imm_data = swqe->wr.ex.imm_data;
 	}
 
 	/*
@@ -492,14 +492,14 @@ void ipath_ud_rcv(struct ipath_ibdev *dev, struct ipath_ib_header *hdr,
 	if (qp->ibqp.qp_num > 1 &&
 	    opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) {
 		if (header_in_data) {
-			wc.imm_data = *(__be32 *) data;
+			wc.ex.imm_data = *(__be32 *) data;
 			data += sizeof(__be32);
 		} else
-			wc.imm_data = ohdr->u.ud.imm_data;
+			wc.ex.imm_data = ohdr->u.ud.imm_data;
 		wc.wc_flags = IB_WC_WITH_IMM;
 		hdrsize += sizeof(u32);
 	} else if (opcode == IB_OPCODE_UD_SEND_ONLY) {
-		wc.imm_data = 0;
+		wc.ex.imm_data = 0;
 		wc.wc_flags = 0;
 	} else {
 		dev->n_pkt_drops++;

drivers/infiniband/hw/mlx4/cq.c

@@ -663,18 +663,18 @@ repoll:
 
 		switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) {
 		case MLX4_RECV_OPCODE_RDMA_WRITE_IMM:
-			wc->opcode   = IB_WC_RECV_RDMA_WITH_IMM;
+			wc->opcode	= IB_WC_RECV_RDMA_WITH_IMM;
-			wc->wc_flags = IB_WC_WITH_IMM;
+			wc->wc_flags	= IB_WC_WITH_IMM;
-			wc->imm_data = cqe->immed_rss_invalid;
+			wc->ex.imm_data = cqe->immed_rss_invalid;
 			break;
 		case MLX4_RECV_OPCODE_SEND:
 			wc->opcode   = IB_WC_RECV;
 			wc->wc_flags = 0;
 			break;
 		case MLX4_RECV_OPCODE_SEND_IMM:
-			wc->opcode   = IB_WC_RECV;
+			wc->opcode	= IB_WC_RECV;
-			wc->wc_flags = IB_WC_WITH_IMM;
+			wc->wc_flags	= IB_WC_WITH_IMM;
-			wc->imm_data = cqe->immed_rss_invalid;
+			wc->ex.imm_data = cqe->immed_rss_invalid;
 			break;
 		}
 

drivers/infiniband/hw/mthca/mthca_cq.c

@@ -620,13 +620,13 @@ static inline int mthca_poll_one(struct mthca_dev *dev,
 		case IB_OPCODE_SEND_LAST_WITH_IMMEDIATE:
 		case IB_OPCODE_SEND_ONLY_WITH_IMMEDIATE:
 			entry->wc_flags = IB_WC_WITH_IMM;
-			entry->imm_data = cqe->imm_etype_pkey_eec;
+			entry->ex.imm_data = cqe->imm_etype_pkey_eec;
 			entry->opcode = IB_WC_RECV;
 			break;
 		case IB_OPCODE_RDMA_WRITE_LAST_WITH_IMMEDIATE:
 		case IB_OPCODE_RDMA_WRITE_ONLY_WITH_IMMEDIATE:
 			entry->wc_flags = IB_WC_WITH_IMM;
-			entry->imm_data = cqe->imm_etype_pkey_eec;
+			entry->ex.imm_data = cqe->imm_etype_pkey_eec;
 			entry->opcode = IB_WC_RECV_RDMA_WITH_IMM;
 			break;
 		default:

include/rdma/ib_user_verbs.h

@@ -289,7 +289,10 @@ struct ib_uverbs_wc {
 	__u32 opcode;
 	__u32 vendor_err;
 	__u32 byte_len;
-	__u32 imm_data;
+	union {
+		__u32 imm_data;
+		__u32 invalidate_rkey;
+	} ex;
 	__u32 qp_num;
 	__u32 src_qp;
 	__u32 wc_flags;

include/rdma/ib_verbs.h

@@ -103,6 +103,7 @@ enum ib_device_cap_flags {
 	 */
 	IB_DEVICE_UD_IP_CSUM		= (1<<18),
 	IB_DEVICE_UD_TSO		= (1<<19),
+	IB_DEVICE_MEM_MGT_EXTENSIONS	= (1<<21),
 };
 
 enum ib_atomic_cap {
@@ -148,6 +149,7 @@ struct ib_device_attr {
 	int			max_srq;
 	int			max_srq_wr;
 	int			max_srq_sge;
+	unsigned int		max_fast_reg_page_list_len;
 	u16			max_pkeys;
 	u8			local_ca_ack_delay;
 };
@@ -411,6 +413,8 @@ enum ib_wc_opcode {
 	IB_WC_FETCH_ADD,
 	IB_WC_BIND_MW,
 	IB_WC_LSO,
+	IB_WC_LOCAL_INV,
+	IB_WC_FAST_REG_MR,
 /*
  * Set value of IB_WC_RECV so consumers can test if a completion is a
  * receive by testing (opcode & IB_WC_RECV).
@@ -421,7 +425,8 @@ enum ib_wc_opcode {
 
 enum ib_wc_flags {
 	IB_WC_GRH		= 1,
-	IB_WC_WITH_IMM		= (1<<1)
+	IB_WC_WITH_IMM		= (1<<1),
+	IB_WC_WITH_INVALIDATE	= (1<<2),
 };
 
 struct ib_wc {
@@ -431,7 +436,10 @@ struct ib_wc {
 	u32			vendor_err;
 	u32			byte_len;
 	struct ib_qp	       *qp;
-	__be32			imm_data;
+	union {
+		__be32		imm_data;
+		u32		invalidate_rkey;
+	} ex;
 	u32			src_qp;
 	int			wc_flags;
 	u16			pkey_index;
@@ -625,6 +633,9 @@ enum ib_wr_opcode {
 	IB_WR_ATOMIC_FETCH_AND_ADD,
 	IB_WR_LSO,
 	IB_WR_SEND_WITH_INV,
+	IB_WR_RDMA_READ_WITH_INV,
+	IB_WR_LOCAL_INV,
+	IB_WR_FAST_REG_MR,
 };
 
 enum ib_send_flags {
@@ -641,6 +652,12 @@ struct ib_sge {
 	u32	lkey;
 };
 
+struct ib_fast_reg_page_list {
+	struct ib_device       *device;
+	u64		       *page_list;
+	unsigned int		max_page_list_len;
+};
+
 struct ib_send_wr {
 	struct ib_send_wr      *next;
 	u64			wr_id;
@@ -673,6 +690,15 @@ struct ib_send_wr {
 			u16	pkey_index; /* valid for GSI only */
 			u8	port_num;   /* valid for DR SMPs on switch only */
 		} ud;
+		struct {
+			u64				iova_start;
+			struct ib_fast_reg_page_list   *page_list;
+			unsigned int			page_shift;
+			unsigned int			page_list_len;
+			u32				length;
+			int				access_flags;
+			u32				rkey;
+		} fast_reg;
 	} wr;
 };
 
@@ -1011,6 +1037,11 @@ struct ib_device {
 	int                        (*query_mr)(struct ib_mr *mr,
 					       struct ib_mr_attr *mr_attr);
 	int                        (*dereg_mr)(struct ib_mr *mr);
+	struct ib_mr *		   (*alloc_fast_reg_mr)(struct ib_pd *pd,
+					       int max_page_list_len);
+	struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device,
+								   int page_list_len);
+	void			   (*free_fast_reg_page_list)(struct ib_fast_reg_page_list *page_list);
 	int                        (*rereg_phys_mr)(struct ib_mr *mr,
 						    int mr_rereg_mask,
 						    struct ib_pd *pd,
@@ -1804,6 +1835,54 @@ int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
  */
 int ib_dereg_mr(struct ib_mr *mr);
 
+/**
+ * ib_alloc_fast_reg_mr - Allocates memory region usable with the
+ *   IB_WR_FAST_REG_MR send work request.
+ * @pd: The protection domain associated with the region.
+ * @max_page_list_len: requested max physical buffer list length to be
+ *   used with fast register work requests for this MR.
+ */
+struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len);
+
+/**
+ * ib_alloc_fast_reg_page_list - Allocates a page list array
+ * @device - ib device pointer.
+ * @page_list_len - size of the page list array to be allocated.
+ *
+ * This allocates and returns a struct ib_fast_reg_page_list * and a
+ * page_list array that is at least page_list_len in size.  The actual
+ * size is returned in max_page_list_len.  The caller is responsible
+ * for initializing the contents of the page_list array before posting
+ * a send work request with the IB_WC_FAST_REG_MR opcode.
+ *
+ * The page_list array entries must be translated using one of the
+ * ib_dma_*() functions just like the addresses passed to
+ * ib_map_phys_fmr().  Once the ib_post_send() is issued, the struct
+ * ib_fast_reg_page_list must not be modified by the caller until the
+ * IB_WC_FAST_REG_MR work request completes.
+ */
+struct ib_fast_reg_page_list *ib_alloc_fast_reg_page_list(
+				struct ib_device *device, int page_list_len);
+
+/**
+ * ib_free_fast_reg_page_list - Deallocates a previously allocated
+ *   page list array.
+ * @page_list - struct ib_fast_reg_page_list pointer to be deallocated.
+ */
+void ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
+
+/**
+ * ib_update_fast_reg_key - updates the key portion of the fast_reg MR
+ *   R_Key and L_Key.
+ * @mr - struct ib_mr pointer to be updated.
+ * @newkey - new key to be used.
+ */
+static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey)
+{
+	mr->lkey = (mr->lkey & 0xffffff00) | newkey;
+	mr->rkey = (mr->rkey & 0xffffff00) | newkey;
+}
+
 /**
  * ib_alloc_mw - Allocates a memory window.
  * @pd: The protection domain associated with the memory window.