Resguardo inicial

linux-7.2.3/drivers/infiniband/ulp/rtrs/Kconfig

@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+config INFINIBAND_RTRS
+	tristate
+	depends on INFINIBAND_ADDR_TRANS
+
+config INFINIBAND_RTRS_CLIENT
+	tristate "RTRS client module"
+	depends on INFINIBAND_ADDR_TRANS
+	select INFINIBAND_RTRS
+	help
+	  RDMA transport client module.
+
+	  RDMA Transport (RTRS) client implements a reliable transport layer
+	  and also multipathing functionality and that it is intended to be
+	  the base layer for a block storage initiator over RDMA.
+
+config INFINIBAND_RTRS_SERVER
+	tristate "RTRS server module"
+	depends on INFINIBAND_ADDR_TRANS
+	select INFINIBAND_RTRS
+	help
+	  RDMA transport server module.
+
+	  RDMA Transport (RTRS) server module processing connection and IO
+	  requests received from the RTRS client module, it will pass the
+	  IO requests to its user eg. RNBD_server.

linux-7.2.3/drivers/infiniband/ulp/rtrs/Makefile

@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+CFLAGS_rtrs-clt-trace.o = -I$(src)
+
+rtrs-client-y := rtrs-clt.o \
+		  rtrs-clt-stats.o \
+		  rtrs-clt-sysfs.o \
+		  rtrs-clt-trace.o
+
+CFLAGS_rtrs-srv-trace.o = -I$(src)
+
+rtrs-server-y := rtrs-srv.o \
+		  rtrs-srv-stats.o \
+		  rtrs-srv-sysfs.o \
+		  rtrs-srv-trace.o
+
+rtrs-core-y := rtrs.o
+
+obj-$(CONFIG_INFINIBAND_RTRS)        += rtrs-core.o
+obj-$(CONFIG_INFINIBAND_RTRS_CLIENT) += rtrs-client.o
+obj-$(CONFIG_INFINIBAND_RTRS_SERVER) += rtrs-server.o

linux-7.2.3/drivers/infiniband/ulp/rtrs/README

@@ -0,0 +1,213 @@
+****************************
+RDMA Transport (RTRS)
+****************************
+
+RTRS (RDMA Transport) is a reliable high speed transport library
+which provides support to establish optimal number of connections
+between client and server machines using RDMA (InfiniBand, RoCE, iWarp)
+transport. It is optimized to transfer (read/write) IO blocks.
+
+In its core interface it follows the BIO semantics of providing the
+possibility to either write data from an sg list to the remote side
+or to request ("read") data transfer from the remote side into a given
+sg list.
+
+RTRS provides I/O fail-over and load-balancing capabilities by using
+multipath I/O (see "add_path" and "mp_policy" configuration entries in
+Documentation/ABI/testing/sysfs-class-rtrs-client).
+
+RTRS is used by the RNBD (RDMA Network Block Device) modules.
+
+==================
+Transport protocol
+==================
+
+Overview
+--------
+An established connection between a client and a server is called rtrs
+session. A session is associated with a set of memory chunks reserved on the
+server side for a given client for rdma transfer. A session
+consists of multiple paths, each representing a separate physical link
+between client and server. Those are used for load balancing and failover.
+Each path consists of as many connections (QPs) as there are cpus on
+the client.
+
+When processing an incoming write or read request, rtrs client uses memory
+chunks reserved for him on the server side. Their number, size and addresses
+need to be exchanged between client and server during the connection
+establishment phase. Apart from the memory related information client needs to
+inform the server about the session name and identify each path and connection
+individually.
+
+On an established session client sends to server write or read messages.
+Server uses immediate field to tell the client which request is being
+acknowledged and for errno. Client uses immediate field to tell the server
+which of the memory chunks has been accessed and at which offset the message
+can be found.
+
+Module parameter always_invalidate is introduced for the security problem
+discussed in LPC RDMA MC 2019. When always_invalidate=Y, on the server side we
+invalidate each rdma buffer before we hand it over to RNBD server and
+then pass it to the block layer. A new rkey is generated and registered for the
+buffer after it returns back from the block layer and RNBD server.
+The new rkey is sent back to the client along with the IO result.
+The procedure is the default behaviour of the driver. This invalidation and
+registration on each IO causes performance drop of up to 20%. A user of the
+driver may choose to load the modules with this mechanism switched off
+(always_invalidate=N), if he understands and can take the risk of a malicious
+client being able to corrupt memory of a server it is connected to. This might
+be a reasonable option in a scenario where all the clients and all the servers
+are located within a secure datacenter.
+
+
+Connection establishment
+------------------------
+
+1. Client starts establishing connections belonging to a path of a session one
+by one via attaching RTRS_MSG_CON_REQ messages to the rdma_connect requests.
+Those include uuid of the session and uuid of the path to be
+established. They are used by the server to find a persisting session/path or
+to create a new one when necessary. The message also contains the protocol
+version and magic for compatibility, total number of connections per session
+(as many as cpus on the client), the id of the current connection and
+the reconnect counter, which is used to resolve the situations where
+client is trying to reconnect a path, while server is still destroying the old
+one.
+
+2. Server accepts the connection requests one by one and attaches
+RTRS_MSG_CONN_RSP messages to the rdma_accept. Apart from magic and
+protocol version, the messages include error code, queue depth supported by
+the server (number of memory chunks which are going to be allocated for that
+session) and the maximum size of one io, RTRS_MSG_NEW_RKEY_F flags is set
+when always_invalidate=Y.
+
+3. After all connections of a path are established client sends to server the
+RTRS_MSG_INFO_REQ message, containing the name of the session. This message
+requests the address information from the server.
+
+4. Server replies to the session info request message with RTRS_MSG_INFO_RSP,
+which contains the addresses and keys of the RDMA buffers allocated for that
+session.
+
+5. Session becomes connected after all paths to be established are connected
+(i.e. steps 1-4 finished for all paths requested for a session)
+
+6. Server and client exchange periodically heartbeat messages (empty rdma
+messages with an immediate field) which are used to detect a crash on remote
+side or network outage in an absence of IO.
+
+7. On any RDMA related error or in the case of a heartbeat timeout, the
+corresponding path is disconnected, all the inflight IO are failed over to a
+healthy path, if any, and the reconnect mechanism is triggered.
+
+CLT                                     SRV
+*for each connection belonging to a path and for each path:
+RTRS_MSG_CON_REQ  ------------------->
+                   <------------------- RTRS_MSG_CON_RSP
+...
+*after all connections are established:
+RTRS_MSG_INFO_REQ ------------------->
+                   <------------------- RTRS_MSG_INFO_RSP
+*heartbeat is started from both sides:
+                   -------------------> [RTRS_HB_MSG_IMM]
+[RTRS_HB_MSG_ACK] <-------------------
+[RTRS_HB_MSG_IMM] <-------------------
+                   -------------------> [RTRS_HB_MSG_ACK]
+
+IO path
+-------
+
+* Write (always_invalidate=N) *
+
+1. When processing a write request client selects one of the memory chunks
+on the server side and rdma writes there the user data, user header and the
+RTRS_MSG_RDMA_WRITE message. Apart from the type (write), the message only
+contains size of the user header. The client tells the server which chunk has
+been accessed and at what offset the RTRS_MSG_RDMA_WRITE can be found by
+using the IMM field.
+
+2. When confirming a write request server sends an "empty" rdma message with
+an immediate field. The 32 bit field is used to specify the outstanding
+inflight IO and for the error code.
+
+CLT                                                          SRV
+usr_data + usr_hdr + rtrs_msg_rdma_write -----------------> [RTRS_IO_REQ_IMM]
+[RTRS_IO_RSP_IMM]                        <----------------- (id + errno)
+
+* Write (always_invalidate=Y) *
+
+1. When processing a write request client selects one of the memory chunks
+on the server side and rdma writes there the user data, user header and the
+RTRS_MSG_RDMA_WRITE message. Apart from the type (write), the message only
+contains size of the user header. The client tells the server which chunk has
+been accessed and at what offset the RTRS_MSG_RDMA_WRITE can be found by
+using the IMM field, Server invalidate rkey associated to the memory chunks
+first, when it finishes, pass the IO to RNBD server module.
+
+2. When confirming a write request server sends an "empty" rdma message with
+an immediate field. The 32 bit field is used to specify the outstanding
+inflight IO and for the error code. The new rkey is sent back using
+SEND_WITH_IMM WR, client When it recived new rkey message, it validates
+the message and finished IO after update rkey for the rbuffer, then post
+back the recv buffer for later use.
+
+CLT                                                          SRV
+usr_data + usr_hdr + rtrs_msg_rdma_write -----------------> [RTRS_IO_REQ_IMM]
+[RTRS_MSG_RKEY_RSP]                     <----------------- (RTRS_MSG_RKEY_RSP)
+[RTRS_IO_RSP_IMM]                        <----------------- (id + errno)
+
+
+* Read (always_invalidate=N)*
+
+1. When processing a read request client selects one of the memory chunks
+on the server side and rdma writes there the user header and the
+RTRS_MSG_RDMA_READ message. This message contains the type (read), size of
+the user header, flags (specifying if memory invalidation is necessary) and the
+list of addresses along with keys for the data to be read into.
+
+2. When confirming a read request server transfers the requested data first,
+attaches an invalidation message if requested and finally an "empty" rdma
+message with an immediate field. The 32 bit field is used to specify the
+outstanding inflight IO and the error code.
+
+CLT                                           SRV
+usr_hdr + rtrs_msg_rdma_read --------------> [RTRS_IO_REQ_IMM]
+[RTRS_IO_RSP_IMM]            <-------------- usr_data + (id + errno)
+or in case client requested invalidation:
+[RTRS_IO_RSP_IMM_W_INV]      <-------------- usr_data + (INV) + (id + errno)
+
+* Read (always_invalidate=Y)*
+
+1. When processing a read request client selects one of the memory chunks
+on the server side and rdma writes there the user header and the
+RTRS_MSG_RDMA_READ message. This message contains the type (read), size of
+the user header, flags (specifying if memory invalidation is necessary) and the
+list of addresses along with keys for the data to be read into.
+Server invalidate rkey associated to the memory chunks first, when it finishes,
+passes the IO to RNBD server module.
+
+2. When confirming a read request server transfers the requested data first,
+attaches an invalidation message if requested and finally an "empty" rdma
+message with an immediate field. The 32 bit field is used to specify the
+outstanding inflight IO and the error code. The new rkey is sent back using
+SEND_WITH_IMM WR, client When it recived new rkey message, it validates
+the message and finished IO after update rkey for the rbuffer, then post
+back the recv buffer for later use.
+
+CLT                                           SRV
+usr_hdr + rtrs_msg_rdma_read --------------> [RTRS_IO_REQ_IMM]
+[RTRS_IO_RSP_IMM]            <-------------- usr_data + (id + errno)
+[RTRS_MSG_RKEY_RSP]	     <----------------- (RTRS_MSG_RKEY_RSP)
+or in case client requested invalidation:
+[RTRS_IO_RSP_IMM_W_INV]      <-------------- usr_data + (INV) + (id + errno)
+=========================================
+Contributors List(in alphabetical order)
+=========================================
+Danil Kipnis <danil.kipnis@profitbricks.com>
+Fabian Holler <mail@fholler.de>
+Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
+Jack Wang <jinpu.wang@profitbricks.com>
+Kleber Souza <kleber.souza@profitbricks.com>
+Lutz Pogrell <lutz.pogrell@cloud.ionos.com>
+Milind Dumbare <Milind.dumbare@gmail.com>
+Roman Penyaev <roman.penyaev@profitbricks.com>

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c

@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
+
+#include "rtrs-clt.h"
+
+void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con)
+{
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
+	struct rtrs_clt_stats *stats = clt_path->stats;
+	struct rtrs_clt_stats_pcpu *s;
+	int cpu;
+
+	cpu = raw_smp_processor_id();
+	s = get_cpu_ptr(stats->pcpu_stats);
+	if (con->cpu != cpu) {
+		s->cpu_migr.to++;
+
+		/* Careful here, override s pointer */
+		s = per_cpu_ptr(stats->pcpu_stats, con->cpu);
+		atomic_inc(&s->cpu_migr.from);
+	}
+	put_cpu_ptr(stats->pcpu_stats);
+}
+
+void rtrs_clt_inc_failover_cnt(struct rtrs_clt_stats *stats)
+{
+	this_cpu_inc(stats->pcpu_stats->rdma.failover_cnt);
+}
+
+int rtrs_clt_stats_migration_from_cnt_to_str(struct rtrs_clt_stats *stats, char *buf)
+{
+	struct rtrs_clt_stats_pcpu *s;
+
+	size_t used;
+	int cpu;
+
+	used = 0;
+	for_each_possible_cpu(cpu) {
+		s = per_cpu_ptr(stats->pcpu_stats, cpu);
+		used += sysfs_emit_at(buf, used, "%d ",
+				  atomic_read(&s->cpu_migr.from));
+	}
+
+	used += sysfs_emit_at(buf, used, "\n");
+
+	return used;
+}
+
+int rtrs_clt_stats_migration_to_cnt_to_str(struct rtrs_clt_stats *stats, char *buf)
+{
+	struct rtrs_clt_stats_pcpu *s;
+
+	size_t used;
+	int cpu;
+
+	used = 0;
+	for_each_possible_cpu(cpu) {
+		s = per_cpu_ptr(stats->pcpu_stats, cpu);
+		used += sysfs_emit_at(buf, used, "%d ", s->cpu_migr.to);
+	}
+
+	used += sysfs_emit_at(buf, used, "\n");
+
+	return used;
+}
+
+int rtrs_clt_stats_reconnects_to_str(struct rtrs_clt_stats *stats, char *buf)
+{
+	return sysfs_emit(buf, "%d %d\n", stats->reconnects.successful_cnt,
+			  stats->reconnects.fail_cnt);
+}
+
+ssize_t rtrs_clt_stats_rdma_to_str(struct rtrs_clt_stats *stats, char *page)
+{
+	struct rtrs_clt_stats_rdma sum;
+	struct rtrs_clt_stats_rdma *r;
+	int cpu;
+
+	memset(&sum, 0, sizeof(sum));
+
+	for_each_possible_cpu(cpu) {
+		r = &per_cpu_ptr(stats->pcpu_stats, cpu)->rdma;
+
+		sum.dir[READ].cnt	  += r->dir[READ].cnt;
+		sum.dir[READ].size_total  += r->dir[READ].size_total;
+		sum.dir[WRITE].cnt	  += r->dir[WRITE].cnt;
+		sum.dir[WRITE].size_total += r->dir[WRITE].size_total;
+		sum.failover_cnt	  += r->failover_cnt;
+	}
+
+	return sysfs_emit(page, "%llu %llu %llu %llu %u %llu\n",
+			 sum.dir[READ].cnt, sum.dir[READ].size_total,
+			 sum.dir[WRITE].cnt, sum.dir[WRITE].size_total,
+			 atomic_read(&stats->inflight), sum.failover_cnt);
+}
+
+ssize_t rtrs_clt_reset_all_help(struct rtrs_clt_stats *s, char *page)
+{
+	return sysfs_emit(page, "echo 1 to reset all statistics\n");
+}
+
+int rtrs_clt_reset_rdma_stats(struct rtrs_clt_stats *stats, bool enable)
+{
+	struct rtrs_clt_stats_pcpu *s;
+	int cpu;
+
+	if (!enable)
+		return -EINVAL;
+
+	for_each_possible_cpu(cpu) {
+		s = per_cpu_ptr(stats->pcpu_stats, cpu);
+		memset(&s->rdma, 0, sizeof(s->rdma));
+	}
+
+	return 0;
+}
+
+int rtrs_clt_reset_cpu_migr_stats(struct rtrs_clt_stats *stats, bool enable)
+{
+	struct rtrs_clt_stats_pcpu *s;
+	int cpu;
+
+	if (!enable)
+		return -EINVAL;
+
+	for_each_possible_cpu(cpu) {
+		s = per_cpu_ptr(stats->pcpu_stats, cpu);
+		memset(&s->cpu_migr, 0, sizeof(s->cpu_migr));
+	}
+
+	return 0;
+}
+
+int rtrs_clt_reset_reconnects_stat(struct rtrs_clt_stats *stats, bool enable)
+{
+	if (!enable)
+		return -EINVAL;
+
+	memset(&stats->reconnects, 0, sizeof(stats->reconnects));
+
+	return 0;
+}
+
+int rtrs_clt_reset_all_stats(struct rtrs_clt_stats *s, bool enable)
+{
+	if (enable) {
+		rtrs_clt_reset_rdma_stats(s, enable);
+		rtrs_clt_reset_cpu_migr_stats(s, enable);
+		rtrs_clt_reset_reconnects_stat(s, enable);
+		atomic_set(&s->inflight, 0);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static inline void rtrs_clt_update_rdma_stats(struct rtrs_clt_stats *stats,
+					       size_t size, int d)
+{
+	this_cpu_inc(stats->pcpu_stats->rdma.dir[d].cnt);
+	this_cpu_add(stats->pcpu_stats->rdma.dir[d].size_total, size);
+}
+
+void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir)
+{
+	struct rtrs_clt_con *con = req->con;
+	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
+	struct rtrs_clt_stats *stats = clt_path->stats;
+	unsigned int len;
+
+	len = req->usr_len + req->data_len;
+	rtrs_clt_update_rdma_stats(stats, len, dir);
+	if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
+		atomic_inc(&stats->inflight);
+}
+
+int rtrs_clt_init_stats(struct rtrs_clt_stats *stats)
+{
+	stats->pcpu_stats = alloc_percpu(typeof(*stats->pcpu_stats));
+	if (!stats->pcpu_stats)
+		return -ENOMEM;
+
+	/*
+	 * successful_cnt will be set to 0 after session
+	 * is established for the first time
+	 */
+	stats->reconnects.successful_cnt = -1;
+
+	return 0;
+}

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c

@@ -0,0 +1,512 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
+
+#include "rtrs-pri.h"
+#include "rtrs-clt.h"
+#include "rtrs-log.h"
+
+#define MIN_MAX_RECONN_ATT -1
+#define MAX_MAX_RECONN_ATT 9999
+
+static void rtrs_clt_path_release(struct kobject *kobj)
+{
+	struct rtrs_clt_path *clt_path;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+
+	free_path(clt_path);
+}
+
+static struct kobj_type ktype_sess = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = rtrs_clt_path_release
+};
+
+static void rtrs_clt_path_stats_release(struct kobject *kobj)
+{
+	struct rtrs_clt_stats *stats;
+
+	stats = container_of(kobj, struct rtrs_clt_stats, kobj_stats);
+
+	free_percpu(stats->pcpu_stats);
+}
+
+static struct kobj_type ktype_stats = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = rtrs_clt_path_stats_release,
+};
+
+static ssize_t max_reconnect_attempts_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *page)
+{
+	struct rtrs_clt_sess *clt = container_of(dev, struct rtrs_clt_sess,
+						 dev);
+
+	return sysfs_emit(page, "%d\n",
+			  rtrs_clt_get_max_reconnect_attempts(clt));
+}
+
+static ssize_t max_reconnect_attempts_store(struct device *dev,
+					    struct device_attribute *attr,
+					    const char *buf,
+					    size_t count)
+{
+	int value;
+	int ret;
+	struct rtrs_clt_sess *clt  = container_of(dev, struct rtrs_clt_sess,
+						  dev);
+
+	ret = kstrtoint(buf, 10, &value);
+	if (ret) {
+		rtrs_err(clt, "%s: failed to convert string '%s' to int\n",
+			  attr->attr.name, buf);
+		return ret;
+	}
+	if (value > MAX_MAX_RECONN_ATT ||
+		     value < MIN_MAX_RECONN_ATT) {
+		rtrs_err(clt,
+			  "%s: invalid range (provided: '%s', accepted: min: %d, max: %d)\n",
+			  attr->attr.name, buf, MIN_MAX_RECONN_ATT,
+			  MAX_MAX_RECONN_ATT);
+		return -EINVAL;
+	}
+	rtrs_clt_set_max_reconnect_attempts(clt, value);
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(max_reconnect_attempts);
+
+static ssize_t mpath_policy_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *page)
+{
+	struct rtrs_clt_sess *clt;
+
+	clt = container_of(dev, struct rtrs_clt_sess, dev);
+
+	switch (clt->mp_policy) {
+	case MP_POLICY_RR:
+		return sysfs_emit(page, "round-robin (RR: %d)\n",
+				  clt->mp_policy);
+	case MP_POLICY_MIN_INFLIGHT:
+		return sysfs_emit(page, "min-inflight (MI: %d)\n",
+				  clt->mp_policy);
+	case MP_POLICY_MIN_LATENCY:
+		return sysfs_emit(page, "min-latency (ML: %d)\n",
+				  clt->mp_policy);
+	default:
+		return sysfs_emit(page, "Unknown (%d)\n", clt->mp_policy);
+	}
+}
+
+static ssize_t mpath_policy_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf,
+				  size_t count)
+{
+	struct rtrs_clt_sess *clt;
+	int value;
+	int ret;
+	size_t len = 0;
+
+	clt = container_of(dev, struct rtrs_clt_sess, dev);
+
+	ret = kstrtoint(buf, 10, &value);
+	if (!ret && (value == MP_POLICY_RR ||
+		     value == MP_POLICY_MIN_INFLIGHT ||
+		     value == MP_POLICY_MIN_LATENCY)) {
+		clt->mp_policy = value;
+		return count;
+	}
+
+	/* distinguish "mi" and "min-latency" with length */
+	len = strnlen(buf, NAME_MAX);
+	if (len && buf[len - 1] == '\n')
+		len--;
+
+	if (!strncasecmp(buf, "round-robin", 11) ||
+	    (len == 2 && !strncasecmp(buf, "rr", 2)))
+		clt->mp_policy = MP_POLICY_RR;
+	else if (!strncasecmp(buf, "min-inflight", 12) ||
+		 (len == 2 && !strncasecmp(buf, "mi", 2)))
+		clt->mp_policy = MP_POLICY_MIN_INFLIGHT;
+	else if (!strncasecmp(buf, "min-latency", 11) ||
+		 (len == 2 && !strncasecmp(buf, "ml", 2)))
+		clt->mp_policy = MP_POLICY_MIN_LATENCY;
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(mpath_policy);
+
+static ssize_t add_path_show(struct device *dev,
+			     struct device_attribute *attr, char *page)
+{
+	return sysfs_emit(page,
+		"Usage: echo [<source addr>@]<destination addr> > %s\n\n*addr ::= [ ip:<ipv4|ipv6> | gid:<gid> ]\n",
+		attr->attr.name);
+}
+
+static ssize_t add_path_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct sockaddr_storage srcaddr, dstaddr;
+	struct rtrs_addr addr = {
+		.src = &srcaddr,
+		.dst = &dstaddr
+	};
+	struct rtrs_clt_sess *clt;
+	const char *nl;
+	size_t len;
+	int err;
+
+	clt = container_of(dev, struct rtrs_clt_sess, dev);
+
+	nl = strchr(buf, '\n');
+	if (nl)
+		len = nl - buf;
+	else
+		len = count;
+	err = rtrs_addr_to_sockaddr(buf, len, clt->port, &addr);
+	if (err)
+		return -EINVAL;
+
+	err = rtrs_clt_create_path_from_sysfs(clt, &addr);
+	if (err)
+		return err;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(add_path);
+
+static ssize_t rtrs_clt_state_show(struct kobject *kobj,
+				    struct kobj_attribute *attr, char *page)
+{
+	struct rtrs_clt_path *clt_path;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	if (clt_path->state == RTRS_CLT_CONNECTED)
+		return sysfs_emit(page, "connected\n");
+
+	return sysfs_emit(page, "disconnected\n");
+}
+
+static struct kobj_attribute rtrs_clt_state_attr =
+	__ATTR(state, 0444, rtrs_clt_state_show, NULL);
+
+static ssize_t rtrs_clt_reconnect_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "Usage: echo 1 > %s\n", attr->attr.name);
+}
+
+static ssize_t rtrs_clt_reconnect_store(struct kobject *kobj,
+					 struct kobj_attribute *attr,
+					 const char *buf, size_t count)
+{
+	struct rtrs_clt_path *clt_path;
+	int ret;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	if (!sysfs_streq(buf, "1")) {
+		rtrs_err(clt_path->clt, "%s: unknown value: '%s'\n",
+			  attr->attr.name, buf);
+		return -EINVAL;
+	}
+	ret = rtrs_clt_reconnect_from_sysfs(clt_path);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static struct kobj_attribute rtrs_clt_reconnect_attr =
+	__ATTR(reconnect, 0644, rtrs_clt_reconnect_show,
+	       rtrs_clt_reconnect_store);
+
+static ssize_t rtrs_clt_disconnect_show(struct kobject *kobj,
+					struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "Usage: echo 1 > %s\n", attr->attr.name);
+}
+
+static ssize_t rtrs_clt_disconnect_store(struct kobject *kobj,
+					  struct kobj_attribute *attr,
+					  const char *buf, size_t count)
+{
+	struct rtrs_clt_path *clt_path;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	if (!sysfs_streq(buf, "1")) {
+		rtrs_err(clt_path->clt, "%s: unknown value: '%s'\n",
+			  attr->attr.name, buf);
+		return -EINVAL;
+	}
+	rtrs_clt_close_conns(clt_path, true);
+
+	return count;
+}
+
+static struct kobj_attribute rtrs_clt_disconnect_attr =
+	__ATTR(disconnect, 0644, rtrs_clt_disconnect_show,
+	       rtrs_clt_disconnect_store);
+
+static ssize_t rtrs_clt_remove_path_show(struct kobject *kobj,
+					 struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "Usage: echo 1 > %s\n", attr->attr.name);
+}
+
+static ssize_t rtrs_clt_remove_path_store(struct kobject *kobj,
+					   struct kobj_attribute *attr,
+					   const char *buf, size_t count)
+{
+	struct rtrs_clt_path *clt_path;
+	int ret;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	if (!sysfs_streq(buf, "1")) {
+		rtrs_err(clt_path->clt, "%s: unknown value: '%s'\n",
+			  attr->attr.name, buf);
+		return -EINVAL;
+	}
+	ret = rtrs_clt_remove_path_from_sysfs(clt_path, &attr->attr);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static struct kobj_attribute rtrs_clt_remove_path_attr =
+	__ATTR(remove_path, 0644, rtrs_clt_remove_path_show,
+	       rtrs_clt_remove_path_store);
+
+STAT_ATTR(struct rtrs_clt_stats, cpu_migration_from,
+	  rtrs_clt_stats_migration_from_cnt_to_str,
+	  rtrs_clt_reset_cpu_migr_stats);
+
+STAT_ATTR(struct rtrs_clt_stats, cpu_migration_to,
+	  rtrs_clt_stats_migration_to_cnt_to_str,
+	  rtrs_clt_reset_cpu_migr_stats);
+
+STAT_ATTR(struct rtrs_clt_stats, reconnects,
+	  rtrs_clt_stats_reconnects_to_str,
+	  rtrs_clt_reset_reconnects_stat);
+
+STAT_ATTR(struct rtrs_clt_stats, rdma,
+	  rtrs_clt_stats_rdma_to_str,
+	  rtrs_clt_reset_rdma_stats);
+
+STAT_ATTR(struct rtrs_clt_stats, reset_all,
+	  rtrs_clt_reset_all_help,
+	  rtrs_clt_reset_all_stats);
+
+static struct attribute *rtrs_clt_stats_attrs[] = {
+	&cpu_migration_from_attr.attr,
+	&cpu_migration_to_attr.attr,
+	&reconnects_attr.attr,
+	&rdma_attr.attr,
+	&reset_all_attr.attr,
+	NULL
+};
+
+static const struct attribute_group rtrs_clt_stats_attr_group = {
+	.attrs = rtrs_clt_stats_attrs,
+};
+
+static ssize_t rtrs_clt_hca_port_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_clt_path *clt_path;
+
+	clt_path = container_of(kobj, typeof(*clt_path), kobj);
+
+	return sysfs_emit(page, "%u\n", clt_path->hca_port);
+}
+
+static struct kobj_attribute rtrs_clt_hca_port_attr =
+	__ATTR(hca_port, 0444, rtrs_clt_hca_port_show, NULL);
+
+static ssize_t rtrs_clt_hca_name_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_clt_path *clt_path;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+
+	return sysfs_emit(page, "%s\n", clt_path->hca_name);
+}
+
+static struct kobj_attribute rtrs_clt_hca_name_attr =
+	__ATTR(hca_name, 0444, rtrs_clt_hca_name_show, NULL);
+
+static ssize_t rtrs_clt_cur_latency_show(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    char *page)
+{
+	struct rtrs_clt_path *clt_path;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+
+	return sysfs_emit(page, "%lld ns\n",
+			  ktime_to_ns(clt_path->s.hb_cur_latency));
+}
+
+static struct kobj_attribute rtrs_clt_cur_latency_attr =
+	__ATTR(cur_latency, 0444, rtrs_clt_cur_latency_show, NULL);
+
+static ssize_t rtrs_clt_src_addr_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_clt_path *clt_path;
+	int len;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	len = sockaddr_to_str((struct sockaddr *)&clt_path->s.src_addr, page,
+			      PAGE_SIZE);
+	len += sysfs_emit_at(page, len, "\n");
+	return len;
+}
+
+static struct kobj_attribute rtrs_clt_src_addr_attr =
+	__ATTR(src_addr, 0444, rtrs_clt_src_addr_show, NULL);
+
+static ssize_t rtrs_clt_dst_addr_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_clt_path *clt_path;
+	int len;
+
+	clt_path = container_of(kobj, struct rtrs_clt_path, kobj);
+	len = sockaddr_to_str((struct sockaddr *)&clt_path->s.dst_addr, page,
+			      PAGE_SIZE);
+	len += sysfs_emit_at(page, len, "\n");
+	return len;
+}
+
+static struct kobj_attribute rtrs_clt_dst_addr_attr =
+	__ATTR(dst_addr, 0444, rtrs_clt_dst_addr_show, NULL);
+
+static struct attribute *rtrs_clt_path_attrs[] = {
+	&rtrs_clt_hca_name_attr.attr,
+	&rtrs_clt_hca_port_attr.attr,
+	&rtrs_clt_src_addr_attr.attr,
+	&rtrs_clt_dst_addr_attr.attr,
+	&rtrs_clt_state_attr.attr,
+	&rtrs_clt_reconnect_attr.attr,
+	&rtrs_clt_disconnect_attr.attr,
+	&rtrs_clt_remove_path_attr.attr,
+	&rtrs_clt_cur_latency_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group rtrs_clt_path_attr_group = {
+	.attrs = rtrs_clt_path_attrs,
+};
+
+int rtrs_clt_create_path_files(struct rtrs_clt_path *clt_path)
+{
+	struct rtrs_clt_sess *clt = clt_path->clt;
+	char str[NAME_MAX];
+	int err;
+	struct rtrs_addr path = {
+		.src = &clt_path->s.src_addr,
+		.dst = &clt_path->s.dst_addr,
+	};
+
+	rtrs_addr_to_str(&path, str, sizeof(str));
+	err = kobject_init_and_add(&clt_path->kobj, &ktype_sess,
+				   clt->kobj_paths,
+				   "%s", str);
+	if (err) {
+		pr_err("kobject_init_and_add: %pe\n", ERR_PTR(err));
+		kobject_put(&clt_path->kobj);
+		return err;
+	}
+	err = sysfs_create_group(&clt_path->kobj, &rtrs_clt_path_attr_group);
+	if (err) {
+		pr_err("sysfs_create_group(): %pe\n", ERR_PTR(err));
+		goto put_kobj;
+	}
+	err = kobject_init_and_add(&clt_path->stats->kobj_stats, &ktype_stats,
+				   &clt_path->kobj, "stats");
+	if (err) {
+		pr_err("kobject_init_and_add: %pe\n", ERR_PTR(err));
+		kobject_put(&clt_path->stats->kobj_stats);
+		goto remove_group;
+	}
+
+	err = sysfs_create_group(&clt_path->stats->kobj_stats,
+				 &rtrs_clt_stats_attr_group);
+	if (err) {
+		pr_err("failed to create stats sysfs group, err: %pe\n", ERR_PTR(err));
+		goto put_kobj_stats;
+	}
+
+	return 0;
+
+put_kobj_stats:
+	kobject_del(&clt_path->stats->kobj_stats);
+	kobject_put(&clt_path->stats->kobj_stats);
+remove_group:
+	sysfs_remove_group(&clt_path->kobj, &rtrs_clt_path_attr_group);
+put_kobj:
+	kobject_del(&clt_path->kobj);
+	kobject_put(&clt_path->kobj);
+
+	return err;
+}
+
+void rtrs_clt_destroy_path_files(struct rtrs_clt_path *clt_path,
+				  const struct attribute *sysfs_self)
+{
+	kobject_del(&clt_path->stats->kobj_stats);
+	kobject_put(&clt_path->stats->kobj_stats);
+	if (sysfs_self)
+		sysfs_remove_file_self(&clt_path->kobj, sysfs_self);
+	kobject_del(&clt_path->kobj);
+}
+
+static struct attribute *rtrs_clt_attrs[] = {
+	&dev_attr_max_reconnect_attempts.attr,
+	&dev_attr_mpath_policy.attr,
+	&dev_attr_add_path.attr,
+	NULL,
+};
+
+static const struct attribute_group rtrs_clt_attr_group = {
+	.attrs = rtrs_clt_attrs,
+};
+
+int rtrs_clt_create_sysfs_root_files(struct rtrs_clt_sess *clt)
+{
+	return sysfs_create_group(&clt->dev.kobj, &rtrs_clt_attr_group);
+}
+
+void rtrs_clt_destroy_sysfs_root(struct rtrs_clt_sess *clt)
+{
+	sysfs_remove_group(&clt->dev.kobj, &rtrs_clt_attr_group);
+
+	if (clt->kobj_paths) {
+		kobject_del(clt->kobj_paths);
+		kobject_put(clt->kobj_paths);
+	}
+}

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-clt-trace.c

@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * RDMA Network Block Driver
+ *
+ * Copyright (c) 2022 1&1 IONOS SE. All rights reserved.
+ */
+#include "rtrs.h"
+#include "rtrs-clt.h"
+
+/*
+ * We include this last to have the helpers above available for the trace
+ * event implementations.
+ */
+#define CREATE_TRACE_POINTS
+#include "rtrs-clt-trace.h"

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-clt-trace.h

@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * RDMA Network Block Driver
+ *
+ * Copyright (c) 2022 1&1 IONOS SE. All rights reserved.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rtrs_clt
+
+#if !defined(_TRACE_RTRS_CLT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RTRS_CLT_H
+
+#include <linux/tracepoint.h>
+
+struct rtrs_clt_path;
+struct rtrs_clt_sess;
+
+TRACE_DEFINE_ENUM(RTRS_CLT_CONNECTING);
+TRACE_DEFINE_ENUM(RTRS_CLT_CONNECTING_ERR);
+TRACE_DEFINE_ENUM(RTRS_CLT_RECONNECTING);
+TRACE_DEFINE_ENUM(RTRS_CLT_CONNECTED);
+TRACE_DEFINE_ENUM(RTRS_CLT_CLOSING);
+TRACE_DEFINE_ENUM(RTRS_CLT_CLOSED);
+TRACE_DEFINE_ENUM(RTRS_CLT_DEAD);
+
+#define show_rtrs_clt_state(x) \
+	__print_symbolic(x, \
+		{ RTRS_CLT_CONNECTING,		"CONNECTING" }, \
+		{ RTRS_CLT_CONNECTING_ERR,	"CONNECTING_ERR" }, \
+		{ RTRS_CLT_RECONNECTING,	"RECONNECTING" }, \
+		{ RTRS_CLT_CONNECTED,		"CONNECTED" }, \
+		{ RTRS_CLT_CLOSING,		"CLOSING" }, \
+		{ RTRS_CLT_CLOSED,		"CLOSED" }, \
+		{ RTRS_CLT_DEAD,		"DEAD" })
+
+DECLARE_EVENT_CLASS(rtrs_clt_conn_class,
+	TP_PROTO(struct rtrs_clt_path *clt_path),
+
+	TP_ARGS(clt_path),
+
+	TP_STRUCT__entry(
+		__field(int, state)
+		__field(int, reconnect_attempts)
+		__field(int, max_reconnect_attempts)
+		__field(int, fail_cnt)
+		__field(int, success_cnt)
+		__array(char, sessname, NAME_MAX)
+	),
+
+	TP_fast_assign(
+		struct rtrs_clt_sess *clt = clt_path->clt;
+
+		__entry->state = clt_path->state;
+		__entry->reconnect_attempts = clt_path->reconnect_attempts;
+		__entry->max_reconnect_attempts = clt->max_reconnect_attempts;
+		__entry->fail_cnt = clt_path->stats->reconnects.fail_cnt;
+		__entry->success_cnt = clt_path->stats->reconnects.successful_cnt;
+		memcpy(__entry->sessname, kobject_name(&clt_path->kobj), NAME_MAX);
+	),
+
+	TP_printk("RTRS-CLT: sess='%s' state=%s attempts='%d' max-attempts='%d' fail='%d' success='%d'",
+		   __entry->sessname,
+		   show_rtrs_clt_state(__entry->state),
+		   __entry->reconnect_attempts,
+		   __entry->max_reconnect_attempts,
+		   __entry->fail_cnt,
+		   __entry->success_cnt
+	)
+);
+
+#define DEFINE_CLT_CONN_EVENT(name) \
+DEFINE_EVENT(rtrs_clt_conn_class, rtrs_##name, \
+	TP_PROTO(struct rtrs_clt_path *clt_path), \
+	TP_ARGS(clt_path))
+
+DEFINE_CLT_CONN_EVENT(clt_reconnect_work);
+DEFINE_CLT_CONN_EVENT(clt_close_conns);
+DEFINE_CLT_CONN_EVENT(rdma_error_recovery);
+
+#endif /* _TRACE_RTRS_CLT_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE rtrs-clt-trace
+#include <trace/define_trace.h>
+

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-clt.h

@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+
+#ifndef RTRS_CLT_H
+#define RTRS_CLT_H
+
+#include <linux/device.h>
+#include "rtrs-pri.h"
+
+/**
+ * enum rtrs_clt_state - Client states.
+ */
+enum rtrs_clt_state {
+	RTRS_CLT_CONNECTING,
+	RTRS_CLT_CONNECTING_ERR,
+	RTRS_CLT_RECONNECTING,
+	RTRS_CLT_CONNECTED,
+	RTRS_CLT_CLOSING,
+	RTRS_CLT_CLOSED,
+	RTRS_CLT_DEAD,
+};
+
+enum rtrs_mp_policy {
+	MP_POLICY_RR,
+	MP_POLICY_MIN_INFLIGHT,
+	MP_POLICY_MIN_LATENCY,
+};
+
+/* see Documentation/ABI/testing/sysfs-class-rtrs-client for details */
+struct rtrs_clt_stats_reconnects {
+	int successful_cnt;
+	int fail_cnt;
+};
+
+/* see Documentation/ABI/testing/sysfs-class-rtrs-client for details */
+struct rtrs_clt_stats_cpu_migr {
+	atomic_t from;
+	int to;
+};
+
+/* stats for Read and write operation.
+ * see Documentation/ABI/testing/sysfs-class-rtrs-client for details
+ */
+struct rtrs_clt_stats_rdma {
+	struct {
+		u64 cnt;
+		u64 size_total;
+	} dir[2];
+
+	u64 failover_cnt;
+};
+
+struct rtrs_clt_stats_pcpu {
+	struct rtrs_clt_stats_cpu_migr		cpu_migr;
+	struct rtrs_clt_stats_rdma		rdma;
+};
+
+struct rtrs_clt_stats {
+	struct kobject				kobj_stats;
+	struct rtrs_clt_stats_pcpu    __percpu	*pcpu_stats;
+	struct rtrs_clt_stats_reconnects	reconnects;
+	atomic_t				inflight;
+};
+
+struct rtrs_clt_con {
+	struct rtrs_con	c;
+	struct rtrs_iu		*rsp_ius;
+	u32			queue_num;
+	unsigned int		cpu;
+	struct mutex		con_mutex;
+	int			cm_err;
+};
+
+/**
+ * rtrs_permit - permits the memory allocation for future RDMA operation.
+ *		 Combine with irq pinning to keep IO on same CPU.
+ */
+struct rtrs_permit {
+	enum rtrs_clt_con_type con_type;
+	unsigned int cpu_id;
+	unsigned int mem_id;
+	unsigned int mem_off;
+};
+
+/**
+ * rtrs_clt_io_req - describes one inflight IO request
+ */
+struct rtrs_clt_io_req {
+	struct rtrs_iu		*iu;
+	struct scatterlist	*sglist; /* list holding user data */
+	unsigned int		sg_cnt;
+	unsigned int		sg_size;
+	unsigned int		data_len;
+	unsigned int		usr_len;
+	void			*priv;
+	bool			in_use;
+	enum rtrs_mp_policy     mp_policy;
+	struct rtrs_clt_con	*con;
+	struct ib_sge		*sge;
+	struct rtrs_permit	*permit;
+	enum dma_data_direction dir;
+	void			(*conf)(void *priv, int errno);
+
+	struct ib_mr		*mr;
+	struct ib_cqe		inv_cqe;
+	struct completion	inv_comp;
+	int			inv_errno;
+	bool			need_inv_comp;
+	refcount_t		ref;
+};
+
+struct rtrs_rbuf {
+	u64 addr;
+	u32 rkey;
+};
+
+struct rtrs_clt_path {
+	struct rtrs_path	s;
+	struct rtrs_clt_sess	*clt;
+	wait_queue_head_t	state_wq;
+	enum rtrs_clt_state	state;
+	atomic_t		connected_cnt;
+	struct mutex		init_mutex;
+	struct rtrs_clt_io_req	*reqs;
+	struct delayed_work	reconnect_dwork;
+	struct work_struct	close_work;
+	struct work_struct	err_recovery_work;
+	unsigned int		reconnect_attempts;
+	bool			established;
+	struct rtrs_rbuf	*rbufs;
+	size_t			max_io_size;
+	u32			max_hdr_size;
+	u32			chunk_size;
+	size_t			queue_depth;
+	u32			max_pages_per_mr;
+	u32			flags;
+	struct kobject		kobj;
+	u8			for_new_clt;
+	/* cache hca_port and hca_name to display in sysfs */
+	u8			hca_port;
+	char                    hca_name[IB_DEVICE_NAME_MAX];
+	struct list_head __percpu
+				*mp_skip_entry;
+	struct rtrs_clt_stats	stats[];
+};
+
+struct rtrs_clt_sess {
+	struct list_head	paths_list; /* rcu protected list */
+	size_t			paths_num;
+	struct rtrs_clt_path
+	__rcu * __percpu	*pcpu_path;
+	uuid_t			paths_uuid;
+	int			paths_up;
+	struct mutex		paths_mutex;
+	struct mutex		paths_ev_mutex;
+	char			sessname[NAME_MAX];
+	u16			port;
+	unsigned int		max_reconnect_attempts;
+	unsigned int		reconnect_delay_sec;
+	unsigned int		max_segments;
+	void			*permits;
+	unsigned long		*permits_map;
+	size_t			queue_depth;
+	size_t			max_io_size;
+	wait_queue_head_t	permits_wait;
+	size_t			pdu_sz;
+	void			*priv;
+	void			(*link_ev)(void *priv,
+					   enum rtrs_clt_link_ev ev);
+	struct device		dev;
+	struct kobject		*kobj_paths;
+	enum rtrs_mp_policy	mp_policy;
+};
+
+static inline struct rtrs_clt_con *to_clt_con(struct rtrs_con *c)
+{
+	return container_of(c, struct rtrs_clt_con, c);
+}
+
+static inline struct rtrs_clt_path *to_clt_path(struct rtrs_path *s)
+{
+	return container_of(s, struct rtrs_clt_path, s);
+}
+
+static inline int permit_size(struct rtrs_clt_sess *clt)
+{
+	return sizeof(struct rtrs_permit) + clt->pdu_sz;
+}
+
+static inline struct rtrs_permit *get_permit(struct rtrs_clt_sess *clt,
+					     int idx)
+{
+	return (struct rtrs_permit *)(clt->permits + permit_size(clt) * idx);
+}
+
+int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_path *path);
+void rtrs_clt_close_conns(struct rtrs_clt_path *clt_path, bool wait);
+int rtrs_clt_create_path_from_sysfs(struct rtrs_clt_sess *clt,
+				     struct rtrs_addr *addr);
+int rtrs_clt_remove_path_from_sysfs(struct rtrs_clt_path *path,
+				     const struct attribute *sysfs_self);
+
+void rtrs_clt_set_max_reconnect_attempts(struct rtrs_clt_sess *clt, int value);
+int rtrs_clt_get_max_reconnect_attempts(const struct rtrs_clt_sess *clt);
+void free_path(struct rtrs_clt_path *clt_path);
+void rtrs_clt_ib_event_handler(struct ib_event_handler *handler,
+			       struct ib_event *ibevent);
+
+/* rtrs-clt-stats.c */
+
+int rtrs_clt_init_stats(struct rtrs_clt_stats *stats);
+
+void rtrs_clt_inc_failover_cnt(struct rtrs_clt_stats *s);
+
+void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con);
+void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir);
+
+int rtrs_clt_reset_rdma_lat_distr_stats(struct rtrs_clt_stats *stats,
+					 bool enable);
+ssize_t rtrs_clt_stats_rdma_lat_distr_to_str(struct rtrs_clt_stats *stats,
+					      char *page);
+int rtrs_clt_reset_cpu_migr_stats(struct rtrs_clt_stats *stats, bool enable);
+int rtrs_clt_stats_migration_from_cnt_to_str(struct rtrs_clt_stats *stats, char *buf);
+int rtrs_clt_stats_migration_to_cnt_to_str(struct rtrs_clt_stats *stats, char *buf);
+int rtrs_clt_reset_reconnects_stat(struct rtrs_clt_stats *stats, bool enable);
+int rtrs_clt_stats_reconnects_to_str(struct rtrs_clt_stats *stats, char *buf);
+int rtrs_clt_reset_rdma_stats(struct rtrs_clt_stats *stats, bool enable);
+ssize_t rtrs_clt_stats_rdma_to_str(struct rtrs_clt_stats *stats,
+				    char *page);
+int rtrs_clt_reset_all_stats(struct rtrs_clt_stats *stats, bool enable);
+ssize_t rtrs_clt_reset_all_help(struct rtrs_clt_stats *stats,
+				 char *page);
+
+/* rtrs-clt-sysfs.c */
+
+int rtrs_clt_create_sysfs_root_files(struct rtrs_clt_sess *clt);
+void rtrs_clt_destroy_sysfs_root(struct rtrs_clt_sess *clt);
+
+int rtrs_clt_create_path_files(struct rtrs_clt_path *clt_path);
+void rtrs_clt_destroy_path_files(struct rtrs_clt_path *clt_path,
+				  const struct attribute *sysfs_self);
+
+#endif /* RTRS_CLT_H */

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-log.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#ifndef RTRS_LOG_H
+#define RTRS_LOG_H
+
+#define rtrs_log(fn, obj, fmt, ...)				\
+	fn("<%s>: " fmt, obj->sessname, ##__VA_ARGS__)
+
+#define rtrs_err(obj, fmt, ...)	\
+	rtrs_log(pr_err, obj, fmt, ##__VA_ARGS__)
+#define rtrs_err_rl(obj, fmt, ...)	\
+	rtrs_log(pr_err_ratelimited, obj, fmt, ##__VA_ARGS__)
+#define rtrs_wrn(obj, fmt, ...)	\
+	rtrs_log(pr_warn, obj, fmt, ##__VA_ARGS__)
+#define rtrs_wrn_rl(obj, fmt, ...) \
+	rtrs_log(pr_warn_ratelimited, obj, fmt, ##__VA_ARGS__)
+#define rtrs_info(obj, fmt, ...) \
+	rtrs_log(pr_info, obj, fmt, ##__VA_ARGS__)
+#define rtrs_info_rl(obj, fmt, ...) \
+	rtrs_log(pr_info_ratelimited, obj, fmt, ##__VA_ARGS__)
+
+#endif /* RTRS_LOG_H */

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-pri.h

@@ -0,0 +1,418 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+
+#ifndef RTRS_PRI_H
+#define RTRS_PRI_H
+
+#include <linux/uuid.h>
+#include <rdma/rdma_cm.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib.h>
+
+#include "rtrs.h"
+
+#define RTRS_PROTO_VER_MAJOR 2
+#define RTRS_PROTO_VER_MINOR 0
+
+#define RTRS_PROTO_VER_STRING __stringify(RTRS_PROTO_VER_MAJOR) "." \
+			       __stringify(RTRS_PROTO_VER_MINOR)
+
+/*
+ * Max IB immediate data size is 2^28 (MAX_IMM_PAYL_BITS)
+ * and the minimum chunk size is 4096 (2^12).
+ * So the maximum sess_queue_depth is 65535 (2^16 - 1) in theory
+ * since queue_depth in rtrs_msg_conn_rsp is defined as le16.
+ * Therefore the pratical max value of sess_queue_depth is
+ * somewhere between 1 and 65535 and it depends on the system.
+ */
+#define MAX_SESS_QUEUE_DEPTH 65535
+
+enum rtrs_imm_const {
+	MAX_IMM_TYPE_BITS = 4,
+	MAX_IMM_TYPE_MASK = ((1 << MAX_IMM_TYPE_BITS) - 1),
+	MAX_IMM_PAYL_BITS = 28,
+	MAX_IMM_PAYL_MASK = ((1 << MAX_IMM_PAYL_BITS) - 1),
+};
+
+enum rtrs_imm_type {
+	RTRS_IO_REQ_IMM       = 0, /* client to server */
+	RTRS_IO_RSP_IMM       = 1, /* server to client */
+	RTRS_IO_RSP_W_INV_IMM = 2, /* server to client */
+
+	RTRS_HB_MSG_IMM = 8, /* HB: HeartBeat */
+	RTRS_HB_ACK_IMM = 9,
+
+	RTRS_LAST_IMM,
+};
+
+enum {
+	SERVICE_CON_QUEUE_DEPTH = 512,
+
+	MAX_PATHS_NUM = 128,
+
+	MIN_CHUNK_SIZE = 8192,
+
+	RTRS_HB_INTERVAL_MS = 5000,
+	RTRS_HB_MISSED_MAX = 5,
+
+	RTRS_MAGIC = 0x1BBD,
+	RTRS_PROTO_VER = (RTRS_PROTO_VER_MAJOR << 8) | RTRS_PROTO_VER_MINOR,
+};
+
+struct rtrs_ib_dev;
+
+struct rtrs_rdma_dev_pd_ops {
+	int (*init)(struct rtrs_ib_dev *dev);
+	void (*deinit)(struct rtrs_ib_dev *dev);
+};
+
+struct rtrs_rdma_dev_pd {
+	struct mutex		mutex;
+	struct list_head	list;
+	enum ib_pd_flags	pd_flags;
+	const struct rtrs_rdma_dev_pd_ops *ops;
+};
+
+struct rtrs_ib_dev {
+	struct ib_device	 *ib_dev;
+	struct ib_pd		 *ib_pd;
+	struct kref		 ref;
+	struct list_head	 entry;
+	struct rtrs_rdma_dev_pd *pool;
+	struct ib_event_handler	 event_handler;
+};
+
+struct rtrs_con {
+	struct rtrs_path	*path;
+	struct ib_qp		*qp;
+	struct ib_cq		*cq;
+	struct rdma_cm_id	*cm_id;
+	unsigned int		cid;
+	int                     nr_cqe;
+	atomic_t		wr_cnt;
+	atomic_t		sq_wr_avail;
+};
+
+struct rtrs_path {
+	struct list_head	entry;
+	struct sockaddr_storage dst_addr;
+	struct sockaddr_storage src_addr;
+	char			sessname[NAME_MAX];
+	uuid_t			uuid;
+	struct rtrs_con	**con;
+	unsigned int		con_num;
+	unsigned int		irq_con_num;
+	unsigned int		recon_cnt;
+	unsigned int		signal_interval;
+	struct rtrs_ib_dev	*dev;
+	int			dev_ref;
+	struct ib_cqe		*hb_cqe;
+	void			(*hb_err_handler)(struct rtrs_con *con);
+	struct workqueue_struct *hb_wq;
+	struct delayed_work	hb_dwork;
+	unsigned int		hb_interval_ms;
+	unsigned int		hb_missed_cnt;
+	unsigned int		hb_missed_max;
+	ktime_t			hb_last_sent;
+	ktime_t			hb_cur_latency;
+};
+
+/* rtrs information unit */
+struct rtrs_iu {
+	struct ib_cqe           cqe;
+	dma_addr_t              dma_addr;
+	void                    *buf;
+	size_t                  size;
+	enum dma_data_direction direction;
+};
+
+/**
+ * enum rtrs_msg_types - RTRS message types, see also rtrs/README
+ * @RTRS_MSG_INFO_REQ:		Client additional info request to the server
+ * @RTRS_MSG_INFO_RSP:		Server additional info response to the client
+ * @RTRS_MSG_WRITE:		Client writes data per RDMA to server
+ * @RTRS_MSG_READ:		Client requests data transfer from server
+ * @RTRS_MSG_RKEY_RSP:		Server refreshed rkey for rbuf
+ */
+enum rtrs_msg_types {
+	RTRS_MSG_INFO_REQ,
+	RTRS_MSG_INFO_RSP,
+	RTRS_MSG_WRITE,
+	RTRS_MSG_READ,
+	RTRS_MSG_RKEY_RSP,
+};
+
+/**
+ * enum rtrs_msg_flags - RTRS message flags.
+ * @RTRS_MSG_NEED_INVAL_F: Send invalidation in response.
+ * @RTRS_MSG_NEW_RKEY_F: Send refreshed rkey in response.
+ */
+enum rtrs_msg_flags {
+	RTRS_MSG_NEED_INVAL_F = 1 << 0,
+	RTRS_MSG_NEW_RKEY_F = 1 << 1,
+};
+
+/**
+ * struct rtrs_sg_desc - RDMA-Buffer entry description
+ * @addr:	Address of RDMA destination buffer
+ * @key:	Authorization rkey to write to the buffer
+ * @len:	Size of the buffer
+ */
+struct rtrs_sg_desc {
+	__le64			addr;
+	__le32			key;
+	__le32			len;
+};
+
+/**
+ * struct rtrs_msg_conn_req - Client connection request to the server
+ * @magic:	   RTRS magic
+ * @version:	   RTRS protocol version
+ * @cid:	   Current connection id
+ * @cid_num:	   Number of connections per session
+ * @recon_cnt:	   Reconnections counter
+ * @sess_uuid:	   UUID of a session (path)
+ * @paths_uuid:	   UUID of a group of sessions (paths)
+ * @first_conn:    %1 if the connection request is the first for that session,
+ *			otherwise %0
+ * NOTE: max size 56 bytes, see man rdma_connect().
+ */
+struct rtrs_msg_conn_req {
+	/**
+	 * @__cma_version: Is set to 0 by cma.c in case of AF_IB, do not touch
+	 * that. See https://www.spinics.net/lists/linux-rdma/msg22397.html
+	 */
+	u8		__cma_version;
+	/**
+	 * @__ip_version: On sender side that should be set to 0, or
+	 * cma_save_ip_info() extract garbage and will fail.
+	 */
+	u8		__ip_version;
+	__le16		magic;
+	__le16		version;
+	__le16		cid;
+	__le16		cid_num;
+	__le16		recon_cnt;
+	uuid_t		sess_uuid;
+	uuid_t		paths_uuid;
+	u8		first_conn : 1;
+	/* private: */
+	u8		reserved_bits : 7;
+	u8		reserved[11];
+};
+
+/**
+ * struct rtrs_msg_conn_rsp - Server connection response to the client
+ * @magic:	   RTRS magic
+ * @version:	   RTRS protocol version
+ * @errno:	   If rdma_accept() then 0, if rdma_reject() indicates error
+ * @queue_depth:   max inflight messages (queue-depth) in this session
+ * @max_io_size:   max io size server supports
+ * @max_hdr_size:  max msg header size server supports
+ * @flags:	   RTRS message flags for this message
+ *
+ * NOTE: size is 56 bytes, max possible is 136 bytes, see man rdma_accept().
+ */
+struct rtrs_msg_conn_rsp {
+	__le16		magic;
+	__le16		version;
+	__le16		errno;
+	__le16		queue_depth;
+	__le32		max_io_size;
+	__le32		max_hdr_size;
+	__le32		flags;
+	/* private: */
+	u8		reserved[36];
+};
+
+/**
+ * struct rtrs_msg_info_req - client additional info request
+ * @type:		@RTRS_MSG_INFO_REQ
+ * @pathname:		Path name chosen by client
+ */
+struct rtrs_msg_info_req {
+	__le16		type;
+	u8		pathname[NAME_MAX];
+	/* private: */
+	u8		reserved[15];
+};
+
+/**
+ * struct rtrs_msg_info_rsp - server additional info response
+ * @type:		@RTRS_MSG_INFO_RSP
+ * @sg_cnt:		Number of @desc entries
+ * @desc:		RDMA buffers where the client can write to server
+ */
+struct rtrs_msg_info_rsp {
+	__le16		type;
+	__le16          sg_cnt;
+	/* private: */
+	u8              reserved[4];
+	/* public: */
+	struct rtrs_sg_desc desc[];
+};
+
+/**
+ * struct rtrs_msg_rkey_rsp - server refreshed rkey response
+ * @type:		@RTRS_MSG_RKEY_RSP
+ * @buf_id:		RDMA buf_id of the new rkey
+ * @rkey:		new remote key for RDMA buffers id from server
+ */
+struct rtrs_msg_rkey_rsp {
+	__le16		type;
+	__le16          buf_id;
+	__le32		rkey;
+};
+
+/**
+ * struct rtrs_msg_rdma_read - RDMA data transfer request from client
+ * @type:		always @RTRS_MSG_READ
+ * @flags:		RTRS message flags (enum rtrs_msg_flags)
+ * @usr_len:		length of user payload
+ * @sg_cnt:		number of @desc entries
+ * @desc:		RDMA buffers where the server can write the result to
+ */
+struct rtrs_msg_rdma_read {
+	__le16			type;
+	__le16			usr_len;
+	__le16			flags;
+	__le16			sg_cnt;
+	struct rtrs_sg_desc    desc[];
+};
+
+/**
+ * struct rtrs_msg_rdma_write - Message transferred to server with RDMA-Write
+ * @type:		always @RTRS_MSG_WRITE
+ * @usr_len:		length of user payload
+ */
+struct rtrs_msg_rdma_write {
+	__le16			type;
+	__le16			usr_len;
+};
+
+/**
+ * struct rtrs_msg_rdma_hdr - header for read or write request
+ * @type:		@RTRS_MSG_WRITE | @RTRS_MSG_READ
+ */
+struct rtrs_msg_rdma_hdr {
+	__le16			type;
+};
+
+/* rtrs.c */
+
+struct rtrs_iu *rtrs_iu_alloc(u32 queue_num, size_t size, gfp_t t,
+			      struct ib_device *dev, enum dma_data_direction,
+			      void (*done)(struct ib_cq *cq, struct ib_wc *wc));
+void rtrs_iu_free(struct rtrs_iu *iu, struct ib_device *dev, u32 queue_num);
+int rtrs_iu_post_recv(struct rtrs_con *con, struct rtrs_iu *iu);
+int rtrs_iu_post_send(struct rtrs_con *con, struct rtrs_iu *iu, size_t size,
+		      struct ib_send_wr *head);
+int rtrs_iu_post_rdma_write_imm(struct rtrs_con *con, struct rtrs_iu *iu,
+				struct ib_sge *sge, unsigned int num_sge,
+				u32 rkey, u64 rdma_addr, u32 imm_data,
+				enum ib_send_flags flags,
+				struct ib_send_wr *head,
+				struct ib_send_wr *tail);
+
+int rtrs_post_recv_empty(struct rtrs_con *con, struct ib_cqe *cqe);
+
+int rtrs_cq_qp_create(struct rtrs_path *path, struct rtrs_con *con,
+		      u32 max_send_sge, int cq_vector, int nr_cqe,
+		      u32 max_send_wr, u32 max_recv_wr,
+		      enum ib_poll_context poll_ctx);
+void rtrs_cq_qp_destroy(struct rtrs_con *con);
+
+void rtrs_init_hb(struct rtrs_path *path, struct ib_cqe *cqe,
+		  unsigned int interval_ms, unsigned int missed_max,
+		  void (*err_handler)(struct rtrs_con *con),
+		  struct workqueue_struct *wq);
+void rtrs_start_hb(struct rtrs_path *path);
+void rtrs_stop_hb(struct rtrs_path *path);
+void rtrs_send_hb_ack(struct rtrs_path *path);
+
+void rtrs_rdma_dev_pd_init(enum ib_pd_flags pd_flags,
+			   struct rtrs_rdma_dev_pd *pool);
+void rtrs_rdma_dev_pd_deinit(struct rtrs_rdma_dev_pd *pool);
+
+struct rtrs_ib_dev *rtrs_ib_dev_find_or_add(struct ib_device *ib_dev,
+					    struct rtrs_rdma_dev_pd *pool);
+int rtrs_ib_dev_put(struct rtrs_ib_dev *dev);
+
+static inline u32 rtrs_to_imm(u32 type, u32 payload)
+{
+	BUILD_BUG_ON(MAX_IMM_PAYL_BITS + MAX_IMM_TYPE_BITS != 32);
+	BUILD_BUG_ON(RTRS_LAST_IMM > (1<<MAX_IMM_TYPE_BITS));
+	return ((type & MAX_IMM_TYPE_MASK) << MAX_IMM_PAYL_BITS) |
+		(payload & MAX_IMM_PAYL_MASK);
+}
+
+static inline void rtrs_from_imm(u32 imm, u32 *type, u32 *payload)
+{
+	*payload = imm & MAX_IMM_PAYL_MASK;
+	*type = imm >> MAX_IMM_PAYL_BITS;
+}
+
+static inline u32 rtrs_to_io_req_imm(u32 addr)
+{
+	return rtrs_to_imm(RTRS_IO_REQ_IMM, addr);
+}
+
+static inline u32 rtrs_to_io_rsp_imm(u32 msg_id, int errno, bool w_inval)
+{
+	enum rtrs_imm_type type;
+	u32 payload;
+
+	/* 9 bits for errno, 19 bits for msg_id */
+	payload = (abs(errno) & 0x1ff) << 19 | (msg_id & 0x7ffff);
+	type = w_inval ? RTRS_IO_RSP_W_INV_IMM : RTRS_IO_RSP_IMM;
+
+	return rtrs_to_imm(type, payload);
+}
+
+static inline void rtrs_from_io_rsp_imm(u32 payload, u32 *msg_id, int *errno)
+{
+	/* 9 bits for errno, 19 bits for msg_id */
+	*msg_id = payload & 0x7ffff;
+	*errno = -(int)((payload >> 19) & 0x1ff);
+}
+
+#define STAT_STORE_FUNC(type, set_value, reset)				\
+static ssize_t set_value##_store(struct kobject *kobj,			\
+			     struct kobj_attribute *attr,		\
+			     const char *buf, size_t count)		\
+{									\
+	int ret = -EINVAL;						\
+	type *stats = container_of(kobj, type, kobj_stats);		\
+									\
+	if (sysfs_streq(buf, "1"))					\
+		ret = reset(stats, true);			\
+	else if (sysfs_streq(buf, "0"))					\
+		ret = reset(stats, false);			\
+	if (ret)							\
+		return ret;						\
+									\
+	return count;							\
+}
+
+#define STAT_SHOW_FUNC(type, get_value, print)				\
+static ssize_t get_value##_show(struct kobject *kobj,			\
+			   struct kobj_attribute *attr,			\
+			   char *page)					\
+{									\
+	type *stats = container_of(kobj, type, kobj_stats);		\
+									\
+	return print(stats, page);			\
+}
+
+#define STAT_ATTR(type, stat, print, reset)				\
+STAT_STORE_FUNC(type, stat, reset)					\
+STAT_SHOW_FUNC(type, stat, print)					\
+static struct kobj_attribute stat##_attr = __ATTR_RW(stat)
+
+#endif /* RTRS_PRI_H */

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-srv-stats.c

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
+
+#include "rtrs-srv.h"
+
+int rtrs_srv_reset_rdma_stats(struct rtrs_srv_stats *stats, bool enable)
+{
+	if (enable) {
+		int cpu;
+		struct rtrs_srv_stats_rdma_stats *r;
+
+		for_each_possible_cpu(cpu) {
+			r = per_cpu_ptr(stats->rdma_stats, cpu);
+			memset(r, 0, sizeof(*r));
+		}
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+ssize_t rtrs_srv_stats_rdma_to_str(struct rtrs_srv_stats *stats, char *page)
+{
+	int cpu;
+	struct rtrs_srv_stats_rdma_stats sum;
+	struct rtrs_srv_stats_rdma_stats *r;
+
+	memset(&sum, 0, sizeof(sum));
+
+	for_each_possible_cpu(cpu) {
+		r = per_cpu_ptr(stats->rdma_stats, cpu);
+
+		sum.dir[READ].cnt	  += r->dir[READ].cnt;
+		sum.dir[READ].size_total  += r->dir[READ].size_total;
+		sum.dir[WRITE].cnt	  += r->dir[WRITE].cnt;
+		sum.dir[WRITE].size_total += r->dir[WRITE].size_total;
+	}
+
+	return sysfs_emit(page, "%llu %llu %llu %llu\n",
+			  sum.dir[READ].cnt, sum.dir[READ].size_total,
+			  sum.dir[WRITE].cnt, sum.dir[WRITE].size_total);
+}

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c

@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
+
+#include "rtrs-pri.h"
+#include "rtrs-srv.h"
+#include "rtrs-log.h"
+
+static void rtrs_srv_release(struct kobject *kobj)
+{
+	struct rtrs_srv_path *srv_path;
+
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	kfree(srv_path);
+}
+
+static struct kobj_type ktype = {
+	.sysfs_ops	= &kobj_sysfs_ops,
+	.release	= rtrs_srv_release,
+};
+
+static ssize_t rtrs_srv_disconnect_show(struct kobject *kobj,
+					struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "Usage: echo 1 > %s\n", attr->attr.name);
+}
+
+static ssize_t rtrs_srv_disconnect_store(struct kobject *kobj,
+					  struct kobj_attribute *attr,
+					  const char *buf, size_t count)
+{
+	struct rtrs_srv_path *srv_path;
+	struct rtrs_path *s;
+	char str[MAXHOSTNAMELEN];
+
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	s = &srv_path->s;
+	if (!sysfs_streq(buf, "1")) {
+		rtrs_err(s, "%s: invalid value: '%s'\n",
+			  attr->attr.name, buf);
+		return -EINVAL;
+	}
+
+	sockaddr_to_str((struct sockaddr *)&srv_path->s.dst_addr, str,
+			sizeof(str));
+
+	rtrs_info(s, "disconnect for path %s requested\n", str);
+	/* first remove sysfs itself to avoid deadlock */
+	sysfs_remove_file_self(&srv_path->kobj, &attr->attr);
+	close_path(srv_path);
+
+	return count;
+}
+
+static struct kobj_attribute rtrs_srv_disconnect_attr =
+	__ATTR(disconnect, 0644,
+	       rtrs_srv_disconnect_show, rtrs_srv_disconnect_store);
+
+static ssize_t rtrs_srv_hca_port_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_srv_path *srv_path;
+	struct rtrs_con *usr_con;
+
+	srv_path = container_of(kobj, typeof(*srv_path), kobj);
+	usr_con = srv_path->s.con[0];
+
+	return sysfs_emit(page, "%u\n", usr_con->cm_id->port_num);
+}
+
+static struct kobj_attribute rtrs_srv_hca_port_attr =
+	__ATTR(hca_port, 0444, rtrs_srv_hca_port_show, NULL);
+
+static ssize_t rtrs_srv_hca_name_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_srv_path *srv_path;
+
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+
+	return sysfs_emit(page, "%s\n", srv_path->s.dev->ib_dev->name);
+}
+
+static struct kobj_attribute rtrs_srv_hca_name_attr =
+	__ATTR(hca_name, 0444, rtrs_srv_hca_name_show, NULL);
+
+static ssize_t rtrs_srv_src_addr_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_srv_path *srv_path;
+	int cnt;
+
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	cnt = sockaddr_to_str((struct sockaddr *)&srv_path->s.dst_addr,
+			      page, PAGE_SIZE);
+	return cnt + sysfs_emit_at(page, cnt, "\n");
+}
+
+static struct kobj_attribute rtrs_srv_src_addr_attr =
+	__ATTR(src_addr, 0444, rtrs_srv_src_addr_show, NULL);
+
+static ssize_t rtrs_srv_dst_addr_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *page)
+{
+	struct rtrs_srv_path *srv_path;
+	int len;
+
+	srv_path = container_of(kobj, struct rtrs_srv_path, kobj);
+	len = sockaddr_to_str((struct sockaddr *)&srv_path->s.src_addr, page,
+			      PAGE_SIZE);
+	len += sysfs_emit_at(page, len, "\n");
+	return len;
+}
+
+static struct kobj_attribute rtrs_srv_dst_addr_attr =
+	__ATTR(dst_addr, 0444, rtrs_srv_dst_addr_show, NULL);
+
+static struct attribute *rtrs_srv_path_attrs[] = {
+	&rtrs_srv_hca_name_attr.attr,
+	&rtrs_srv_hca_port_attr.attr,
+	&rtrs_srv_src_addr_attr.attr,
+	&rtrs_srv_dst_addr_attr.attr,
+	&rtrs_srv_disconnect_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group rtrs_srv_path_attr_group = {
+	.attrs = rtrs_srv_path_attrs,
+};
+
+STAT_ATTR(struct rtrs_srv_stats, rdma,
+	  rtrs_srv_stats_rdma_to_str,
+	  rtrs_srv_reset_rdma_stats);
+
+static struct attribute *rtrs_srv_stats_attrs[] = {
+	&rdma_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group rtrs_srv_stats_attr_group = {
+	.attrs = rtrs_srv_stats_attrs,
+};
+
+static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_path *srv_path)
+{
+	struct rtrs_srv_sess *srv = srv_path->srv;
+	int err = 0;
+
+	mutex_lock(&srv->paths_mutex);
+	if (srv->dev_ref++) {
+		/*
+		 * Device needs to be registered only on the first session
+		 */
+		goto unlock;
+	}
+	srv->dev.class = &rtrs_dev_class;
+	err = dev_set_name(&srv->dev, "%s", srv_path->s.sessname);
+	if (err)
+		goto unlock;
+
+	/*
+	 * Suppress user space notification until
+	 * sysfs files are created
+	 */
+	dev_set_uevent_suppress(&srv->dev, true);
+	err = device_add(&srv->dev);
+	if (err) {
+		pr_err("device_add(): %pe\n", ERR_PTR(err));
+		put_device(&srv->dev);
+		goto unlock;
+	}
+	srv->kobj_paths = kobject_create_and_add("paths", &srv->dev.kobj);
+	if (!srv->kobj_paths) {
+		err = -ENOMEM;
+		pr_err("kobject_create_and_add(): %pe\n", ERR_PTR(err));
+		device_del(&srv->dev);
+		put_device(&srv->dev);
+		goto unlock;
+	}
+	dev_set_uevent_suppress(&srv->dev, false);
+	kobject_uevent(&srv->dev.kobj, KOBJ_ADD);
+unlock:
+	mutex_unlock(&srv->paths_mutex);
+
+	return err;
+}
+
+static void
+rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_path *srv_path)
+{
+	struct rtrs_srv_sess *srv = srv_path->srv;
+
+	mutex_lock(&srv->paths_mutex);
+	if (!--srv->dev_ref) {
+		kobject_put(srv->kobj_paths);
+		mutex_unlock(&srv->paths_mutex);
+		device_del(&srv->dev);
+		put_device(&srv->dev);
+	} else {
+		put_device(&srv->dev);
+		mutex_unlock(&srv->paths_mutex);
+	}
+}
+
+static void rtrs_srv_path_stats_release(struct kobject *kobj)
+{
+	struct rtrs_srv_stats *stats;
+
+	stats = container_of(kobj, struct rtrs_srv_stats, kobj_stats);
+
+	free_percpu(stats->rdma_stats);
+
+	kfree(stats);
+}
+
+static struct kobj_type ktype_stats = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = rtrs_srv_path_stats_release,
+};
+
+static int rtrs_srv_create_stats_files(struct rtrs_srv_path *srv_path)
+{
+	int err;
+	struct rtrs_path *s = &srv_path->s;
+
+	err = kobject_init_and_add(&srv_path->stats->kobj_stats, &ktype_stats,
+				   &srv_path->kobj, "stats");
+	if (err) {
+		rtrs_err(s, "kobject_init_and_add(): %pe\n", ERR_PTR(err));
+		kobject_put(&srv_path->stats->kobj_stats);
+		return err;
+	}
+	err = sysfs_create_group(&srv_path->stats->kobj_stats,
+				 &rtrs_srv_stats_attr_group);
+	if (err) {
+		rtrs_err(s, "sysfs_create_group(): %pe\n", ERR_PTR(err));
+		goto err;
+	}
+
+	return 0;
+
+err:
+	kobject_del(&srv_path->stats->kobj_stats);
+	kobject_put(&srv_path->stats->kobj_stats);
+
+	return err;
+}
+
+int rtrs_srv_create_path_files(struct rtrs_srv_path *srv_path)
+{
+	struct rtrs_srv_sess *srv = srv_path->srv;
+	struct rtrs_path *s = &srv_path->s;
+	char str[NAME_MAX];
+	int err;
+	struct rtrs_addr path = {
+		.src = &srv_path->s.dst_addr,
+		.dst = &srv_path->s.src_addr,
+	};
+
+	rtrs_addr_to_str(&path, str, sizeof(str));
+	err = rtrs_srv_create_once_sysfs_root_folders(srv_path);
+	if (err)
+		return err;
+
+	err = kobject_init_and_add(&srv_path->kobj, &ktype, srv->kobj_paths,
+				   "%s", str);
+	if (err) {
+		rtrs_err(s, "kobject_init_and_add(): %pe\n", ERR_PTR(err));
+		goto destroy_root;
+	}
+	err = sysfs_create_group(&srv_path->kobj, &rtrs_srv_path_attr_group);
+	if (err) {
+		rtrs_err(s, "sysfs_create_group(): %pe\n", ERR_PTR(err));
+		goto put_kobj;
+	}
+	err = rtrs_srv_create_stats_files(srv_path);
+	if (err)
+		goto remove_group;
+
+	return 0;
+
+remove_group:
+	sysfs_remove_group(&srv_path->kobj, &rtrs_srv_path_attr_group);
+put_kobj:
+	kobject_del(&srv_path->kobj);
+destroy_root:
+	rtrs_srv_destroy_once_sysfs_root_folders(srv_path);
+	kobject_put(&srv_path->kobj);
+
+	return err;
+}
+
+void rtrs_srv_destroy_path_files(struct rtrs_srv_path *srv_path)
+{
+	if (srv_path->stats->kobj_stats.state_in_sysfs) {
+		sysfs_remove_group(&srv_path->stats->kobj_stats,
+				   &rtrs_srv_stats_attr_group);
+		kobject_del(&srv_path->stats->kobj_stats);
+		kobject_put(&srv_path->stats->kobj_stats);
+	}
+
+	if (srv_path->kobj.state_in_sysfs) {
+		sysfs_remove_group(&srv_path->kobj, &rtrs_srv_path_attr_group);
+		kobject_put(&srv_path->kobj);
+		rtrs_srv_destroy_once_sysfs_root_folders(srv_path);
+	}
+
+}

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-srv-trace.c

@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * RDMA Network Block Driver
+ *
+ * Copyright (c) 2022 1&1 IONOS SE. All rights reserved.
+ */
+#include "rtrs.h"
+#include "rtrs-pri.h"
+#include "rtrs-srv.h"
+
+/*
+ * We include this last to have the helpers above available for the trace
+ * event implementations.
+ */
+#define CREATE_TRACE_POINTS
+#include "rtrs-srv-trace.h"

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-srv-trace.h

@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * RDMA Network Block Driver
+ *
+ * Copyright (c) 2022 1&1 IONOS SE. All rights reserved.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rtrs_srv
+
+#if !defined(_TRACE_RTRS_SRV_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RTRS_SRV_H
+
+#include <linux/tracepoint.h>
+
+struct rtrs_srv_op;
+struct rtrs_srv_con;
+struct rtrs_srv_path;
+
+TRACE_DEFINE_ENUM(RTRS_SRV_CONNECTING);
+TRACE_DEFINE_ENUM(RTRS_SRV_CONNECTED);
+TRACE_DEFINE_ENUM(RTRS_SRV_CLOSING);
+TRACE_DEFINE_ENUM(RTRS_SRV_CLOSED);
+
+#define show_rtrs_srv_state(x) \
+	__print_symbolic(x, \
+		{ RTRS_SRV_CONNECTING,	"CONNECTING" }, \
+		{ RTRS_SRV_CONNECTED,	"CONNECTED" }, \
+		{ RTRS_SRV_CLOSING,	"CLOSING" }, \
+		{ RTRS_SRV_CLOSED,	"CLOSED" })
+
+TRACE_EVENT(send_io_resp_imm,
+	TP_PROTO(struct rtrs_srv_op *id,
+		 bool need_inval,
+		 bool always_invalidate,
+		 int errno),
+
+	TP_ARGS(id, need_inval, always_invalidate, errno),
+
+	TP_STRUCT__entry(
+		__field(u8, dir)
+		__field(bool, need_inval)
+		__field(bool, always_invalidate)
+		__field(u32, msg_id)
+		__field(int, wr_cnt)
+		__field(u32, signal_interval)
+		__field(int, state)
+		__field(int, errno)
+		__array(char, sessname, NAME_MAX)
+	),
+
+	TP_fast_assign(
+		struct rtrs_srv_con *con = id->con;
+		struct rtrs_path *s = con->c.path;
+		struct rtrs_srv_path *srv_path = to_srv_path(s);
+
+		__entry->dir = id->dir;
+		__entry->state = srv_path->state;
+		__entry->errno = errno;
+		__entry->need_inval = need_inval;
+		__entry->always_invalidate = always_invalidate;
+		__entry->msg_id = id->msg_id;
+		__entry->wr_cnt = atomic_read(&con->c.wr_cnt);
+		__entry->signal_interval = s->signal_interval;
+		memcpy(__entry->sessname, kobject_name(&srv_path->kobj), NAME_MAX);
+	),
+
+	TP_printk("sess='%s' state='%s' dir=%s err='%d' inval='%d' glob-inval='%d' msgid='%u' wrcnt='%d' sig-interval='%u'",
+		   __entry->sessname,
+		   show_rtrs_srv_state(__entry->state),
+		   __print_symbolic(__entry->dir,
+			 { READ,  "READ" },
+			 { WRITE, "WRITE" }),
+		   __entry->errno,
+		   __entry->need_inval,
+		   __entry->always_invalidate,
+		   __entry->msg_id,
+		   __entry->wr_cnt,
+		   __entry->signal_interval
+	)
+);
+
+#endif /* _TRACE_RTRS_SRV_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE rtrs-srv-trace
+#include <trace/define_trace.h>
+

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs-srv.h

@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+
+#ifndef RTRS_SRV_H
+#define RTRS_SRV_H
+
+#include <linux/device.h>
+#include <linux/refcount.h>
+#include <linux/percpu.h>
+#include "rtrs-pri.h"
+
+/*
+ * enum rtrs_srv_state - Server states.
+ */
+enum rtrs_srv_state {
+	RTRS_SRV_CONNECTING,
+	RTRS_SRV_CONNECTED,
+	RTRS_SRV_CLOSING,
+	RTRS_SRV_CLOSED,
+};
+
+/* stats for Read and write operation.
+ * see Documentation/ABI/testing/sysfs-class-rtrs-server for details
+ */
+struct rtrs_srv_stats_rdma_stats {
+	struct {
+		u64 cnt;
+		u64 size_total;
+	} dir[2];
+};
+
+struct rtrs_srv_stats {
+	struct kobject					kobj_stats;
+	struct rtrs_srv_stats_rdma_stats __percpu	*rdma_stats;
+	struct rtrs_srv_path				*srv_path;
+};
+
+struct rtrs_srv_con {
+	struct rtrs_con		c;
+	struct list_head	rsp_wr_wait_list;
+	spinlock_t		rsp_wr_wait_lock;
+};
+
+/* IO context in rtrs_srv, each io has one */
+struct rtrs_srv_op {
+	struct rtrs_srv_con		*con;
+	u32				msg_id;
+	u8				dir;
+	struct rtrs_msg_rdma_read	*rd_msg;
+	struct ib_rdma_wr		tx_wr;
+	struct ib_sge			tx_sg;
+	struct list_head		wait_list;
+	int				status;
+};
+
+/*
+ * server side memory region context, when always_invalidate=Y, we need
+ * queue_depth of memory region to invalidate each memory region.
+ */
+struct rtrs_srv_mr {
+	struct ib_mr	*mr;
+	struct sg_table	sgt;
+	struct ib_cqe	inv_cqe;	/* only for always_invalidate=true */
+	u32		msg_id;		/* only for always_invalidate=true */
+	u32		msg_off;	/* only for always_invalidate=true */
+	struct rtrs_iu	*iu;		/* send buffer for new rkey msg */
+};
+
+struct rtrs_srv_path {
+	struct rtrs_path	s;
+	struct rtrs_srv_sess	*srv;
+	struct work_struct	close_work;
+	enum rtrs_srv_state	state;
+	spinlock_t		state_lock;
+	int			cur_cq_vector;
+	struct rtrs_srv_op	**ops_ids;
+	struct percpu_ref       ids_inflight_ref;
+	struct completion       complete_done;
+	struct rtrs_srv_mr	*mrs;
+	unsigned int		mrs_num;
+	dma_addr_t		*dma_addr;
+	bool			established;
+	unsigned int		mem_bits;
+	struct kobject		kobj;
+	struct rtrs_srv_stats	*stats;
+	unsigned long		connection_timeout;
+};
+
+static inline struct rtrs_srv_path *to_srv_path(struct rtrs_path *s)
+{
+	return container_of(s, struct rtrs_srv_path, s);
+}
+
+struct rtrs_srv_sess {
+	struct list_head	paths_list;
+	int			paths_up;
+	struct mutex		paths_ev_mutex;
+	size_t			paths_num;
+	struct mutex		paths_mutex;
+	uuid_t			paths_uuid;
+	refcount_t		refcount;
+	struct rtrs_srv_ctx	*ctx;
+	struct list_head	ctx_list;
+	void			*priv;
+	size_t			queue_depth;
+	struct page		**chunks;
+	struct device		dev;
+	unsigned int		dev_ref;
+	struct kobject		*kobj_paths;
+};
+
+struct rtrs_srv_ctx {
+	struct rtrs_srv_ops ops;
+	struct rdma_cm_id *cm_id_ip;
+	struct rdma_cm_id *cm_id_ib;
+	struct mutex srv_mutex;
+	struct list_head srv_list;
+};
+
+struct rtrs_srv_ib_ctx {
+	struct rtrs_srv_ctx	*srv_ctx;
+	u16			port;
+	struct mutex            ib_dev_mutex;
+	int			ib_dev_count;
+};
+
+extern const struct class rtrs_dev_class;
+
+void close_path(struct rtrs_srv_path *srv_path);
+void rtrs_srv_ib_event_handler(struct ib_event_handler *handler,
+			       struct ib_event *ibevent);
+
+static inline void rtrs_srv_update_rdma_stats(struct rtrs_srv_stats *s,
+					      size_t size, int d)
+{
+	this_cpu_inc(s->rdma_stats->dir[d].cnt);
+	this_cpu_add(s->rdma_stats->dir[d].size_total, size);
+}
+
+/* functions which are implemented in rtrs-srv-stats.c */
+int rtrs_srv_reset_rdma_stats(struct rtrs_srv_stats *stats, bool enable);
+ssize_t rtrs_srv_stats_rdma_to_str(struct rtrs_srv_stats *stats, char *page);
+int rtrs_srv_reset_all_stats(struct rtrs_srv_stats *stats, bool enable);
+ssize_t rtrs_srv_reset_all_help(struct rtrs_srv_stats *stats,
+				 char *page, size_t len);
+
+/* functions which are implemented in rtrs-srv-sysfs.c */
+int rtrs_srv_create_path_files(struct rtrs_srv_path *srv_path);
+void rtrs_srv_destroy_path_files(struct rtrs_srv_path *srv_path);
+
+#endif /* RTRS_SRV_H */

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs.c

@@ -0,0 +1,648 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
+
+#include <linux/module.h>
+#include <linux/inet.h>
+
+#include "rtrs-pri.h"
+#include "rtrs-log.h"
+
+MODULE_DESCRIPTION("RDMA Transport Core");
+MODULE_LICENSE("GPL");
+
+struct rtrs_iu *rtrs_iu_alloc(u32 iu_num, size_t size, gfp_t gfp_mask,
+			      struct ib_device *dma_dev,
+			      enum dma_data_direction dir,
+			      void (*done)(struct ib_cq *cq, struct ib_wc *wc))
+{
+	struct rtrs_iu *ius, *iu;
+	int i;
+
+	ius = kzalloc_objs(*ius, iu_num, gfp_mask);
+	if (!ius)
+		return NULL;
+	for (i = 0; i < iu_num; i++) {
+		iu = &ius[i];
+		iu->direction = dir;
+		iu->buf = kzalloc(size, gfp_mask);
+		if (!iu->buf)
+			goto err;
+
+		iu->dma_addr = ib_dma_map_single(dma_dev, iu->buf, size, dir);
+		if (ib_dma_mapping_error(dma_dev, iu->dma_addr)) {
+			kfree(iu->buf);
+			goto err;
+		}
+
+		iu->cqe.done  = done;
+		iu->size      = size;
+	}
+	return ius;
+err:
+	rtrs_iu_free(ius, dma_dev, i);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(rtrs_iu_alloc);
+
+void rtrs_iu_free(struct rtrs_iu *ius, struct ib_device *ibdev, u32 queue_num)
+{
+	struct rtrs_iu *iu;
+	int i;
+
+	if (!ius)
+		return;
+
+	for (i = 0; i < queue_num; i++) {
+		iu = &ius[i];
+		ib_dma_unmap_single(ibdev, iu->dma_addr, iu->size, iu->direction);
+		kfree(iu->buf);
+	}
+	kfree(ius);
+}
+EXPORT_SYMBOL_GPL(rtrs_iu_free);
+
+int rtrs_iu_post_recv(struct rtrs_con *con, struct rtrs_iu *iu)
+{
+	struct rtrs_path *path = con->path;
+	struct ib_recv_wr wr;
+	struct ib_sge list;
+
+	list.addr   = iu->dma_addr;
+	list.length = iu->size;
+	list.lkey   = path->dev->ib_pd->local_dma_lkey;
+
+	if (list.length == 0) {
+		rtrs_wrn(con->path,
+			  "Posting receive work request failed, sg list is empty\n");
+		return -EINVAL;
+	}
+	wr = (struct ib_recv_wr) {
+		.wr_cqe  = &iu->cqe,
+		.sg_list = &list,
+		.num_sge = 1,
+	};
+
+	return ib_post_recv(con->qp, &wr, NULL);
+}
+EXPORT_SYMBOL_GPL(rtrs_iu_post_recv);
+
+int rtrs_post_recv_empty(struct rtrs_con *con, struct ib_cqe *cqe)
+{
+	struct ib_recv_wr wr;
+
+	wr = (struct ib_recv_wr) {
+		.wr_cqe  = cqe,
+	};
+
+	return ib_post_recv(con->qp, &wr, NULL);
+}
+EXPORT_SYMBOL_GPL(rtrs_post_recv_empty);
+
+static int rtrs_post_send(struct ib_qp *qp, struct ib_send_wr *head,
+			  struct ib_send_wr *wr, struct ib_send_wr *tail)
+{
+	if (head) {
+		struct ib_send_wr *next = head;
+
+		while (next->next)
+			next = next->next;
+		next->next = wr;
+	} else {
+		head = wr;
+	}
+
+	if (tail)
+		wr->next = tail;
+
+	return ib_post_send(qp, head, NULL);
+}
+
+int rtrs_iu_post_send(struct rtrs_con *con, struct rtrs_iu *iu, size_t size,
+		       struct ib_send_wr *head)
+{
+	struct rtrs_path *path = con->path;
+	struct ib_send_wr wr;
+	struct ib_sge list;
+
+	if (WARN_ON(size == 0))
+		return -EINVAL;
+
+	list.addr   = iu->dma_addr;
+	list.length = size;
+	list.lkey   = path->dev->ib_pd->local_dma_lkey;
+
+	wr = (struct ib_send_wr) {
+		.wr_cqe     = &iu->cqe,
+		.sg_list    = &list,
+		.num_sge    = 1,
+		.opcode     = IB_WR_SEND,
+		.send_flags = IB_SEND_SIGNALED,
+	};
+
+	return rtrs_post_send(con->qp, head, &wr, NULL);
+}
+EXPORT_SYMBOL_GPL(rtrs_iu_post_send);
+
+int rtrs_iu_post_rdma_write_imm(struct rtrs_con *con, struct rtrs_iu *iu,
+				struct ib_sge *sge, unsigned int num_sge,
+				u32 rkey, u64 rdma_addr, u32 imm_data,
+				enum ib_send_flags flags,
+				struct ib_send_wr *head,
+				struct ib_send_wr *tail)
+{
+	struct ib_rdma_wr wr;
+	int i;
+
+	wr = (struct ib_rdma_wr) {
+		.wr.wr_cqe	  = &iu->cqe,
+		.wr.sg_list	  = sge,
+		.wr.num_sge	  = num_sge,
+		.rkey		  = rkey,
+		.remote_addr	  = rdma_addr,
+		.wr.opcode	  = IB_WR_RDMA_WRITE_WITH_IMM,
+		.wr.ex.imm_data = cpu_to_be32(imm_data),
+		.wr.send_flags  = flags,
+	};
+
+	/*
+	 * If one of the sges has 0 size, the operation will fail with a
+	 * length error
+	 */
+	for (i = 0; i < num_sge; i++)
+		if (WARN_ONCE(sge[i].length == 0, "sg %d is zero length\n", i))
+			return -EINVAL;
+
+	return rtrs_post_send(con->qp, head, &wr.wr, tail);
+}
+EXPORT_SYMBOL_GPL(rtrs_iu_post_rdma_write_imm);
+
+static int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con,
+					  struct ib_cqe *cqe,
+					  u32 imm_data,
+					  struct ib_send_wr *head)
+{
+	struct ib_rdma_wr wr;
+	struct rtrs_path *path = con->path;
+	enum ib_send_flags sflags;
+
+	atomic_dec_if_positive(&con->sq_wr_avail);
+	sflags = (atomic_inc_return(&con->wr_cnt) % path->signal_interval) ?
+		0 : IB_SEND_SIGNALED;
+
+	wr = (struct ib_rdma_wr) {
+		.wr.wr_cqe	= cqe,
+		.wr.send_flags	= sflags,
+		.wr.opcode	= IB_WR_RDMA_WRITE_WITH_IMM,
+		.wr.ex.imm_data	= cpu_to_be32(imm_data),
+	};
+
+	return rtrs_post_send(con->qp, head, &wr.wr, NULL);
+}
+
+static void qp_event_handler(struct ib_event *ev, void *ctx)
+{
+	struct rtrs_con *con = ctx;
+
+	switch (ev->event) {
+	case IB_EVENT_COMM_EST:
+		rtrs_info(con->path, "QP event %s (%d) received\n",
+			   ib_event_msg(ev->event), ev->event);
+		rdma_notify(con->cm_id, IB_EVENT_COMM_EST);
+		break;
+	default:
+		rtrs_info(con->path, "Unhandled QP event %s (%d) received\n",
+			   ib_event_msg(ev->event), ev->event);
+		break;
+	}
+}
+
+static bool is_pollqueue(struct rtrs_con *con)
+{
+	return con->cid >= con->path->irq_con_num;
+}
+
+static int create_cq(struct rtrs_con *con, int cq_vector, int nr_cqe,
+		     enum ib_poll_context poll_ctx)
+{
+	struct rdma_cm_id *cm_id = con->cm_id;
+	struct ib_cq *cq;
+
+	if (is_pollqueue(con))
+		cq = ib_alloc_cq(cm_id->device, con, nr_cqe, cq_vector,
+				 poll_ctx);
+	else
+		cq = ib_cq_pool_get(cm_id->device, nr_cqe, cq_vector, poll_ctx);
+
+	if (IS_ERR(cq)) {
+		rtrs_err(con->path, "Creating completion queue failed, errno: %pe\n",
+			  cq);
+		return PTR_ERR(cq);
+	}
+	con->cq = cq;
+	con->nr_cqe = nr_cqe;
+
+	return 0;
+}
+
+static int create_qp(struct rtrs_con *con, struct ib_pd *pd,
+		     u32 max_send_wr, u32 max_recv_wr, u32 max_sge)
+{
+	struct ib_qp_init_attr init_attr = {};
+	struct rdma_cm_id *cm_id = con->cm_id;
+	int ret;
+
+	init_attr.cap.max_send_wr = max_send_wr;
+	init_attr.cap.max_recv_wr = max_recv_wr;
+	init_attr.cap.max_recv_sge = 1;
+	init_attr.event_handler = qp_event_handler;
+	init_attr.qp_context = con;
+	init_attr.cap.max_send_sge = max_sge;
+
+	init_attr.qp_type = IB_QPT_RC;
+	init_attr.send_cq = con->cq;
+	init_attr.recv_cq = con->cq;
+	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+
+	ret = rdma_create_qp(cm_id, pd, &init_attr);
+	if (ret) {
+		rtrs_err(con->path, "Creating QP failed, err: %pe\n",
+			 ERR_PTR(ret));
+		return ret;
+	}
+	con->qp = cm_id->qp;
+
+	return ret;
+}
+
+static void destroy_cq(struct rtrs_con *con)
+{
+	if (con->cq) {
+		if (is_pollqueue(con))
+			ib_free_cq(con->cq);
+		else
+			ib_cq_pool_put(con->cq, con->nr_cqe);
+	}
+	con->cq = NULL;
+}
+
+int rtrs_cq_qp_create(struct rtrs_path *path, struct rtrs_con *con,
+		       u32 max_send_sge, int cq_vector, int nr_cqe,
+		       u32 max_send_wr, u32 max_recv_wr,
+		       enum ib_poll_context poll_ctx)
+{
+	int err;
+
+	err = create_cq(con, cq_vector, nr_cqe, poll_ctx);
+	if (err)
+		return err;
+
+	err = create_qp(con, path->dev->ib_pd, max_send_wr, max_recv_wr,
+			max_send_sge);
+	if (err) {
+		destroy_cq(con);
+		return err;
+	}
+	con->path = path;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtrs_cq_qp_create);
+
+void rtrs_cq_qp_destroy(struct rtrs_con *con)
+{
+	if (con->qp) {
+		rdma_destroy_qp(con->cm_id);
+		con->qp = NULL;
+	}
+	destroy_cq(con);
+}
+EXPORT_SYMBOL_GPL(rtrs_cq_qp_destroy);
+
+static void schedule_hb(struct rtrs_path *path)
+{
+	queue_delayed_work(path->hb_wq, &path->hb_dwork,
+			   msecs_to_jiffies(path->hb_interval_ms));
+}
+
+void rtrs_send_hb_ack(struct rtrs_path *path)
+{
+	struct rtrs_con *usr_con = path->con[0];
+	u32 imm;
+	int err;
+
+	imm = rtrs_to_imm(RTRS_HB_ACK_IMM, 0);
+	err = rtrs_post_rdma_write_imm_empty(usr_con, path->hb_cqe, imm,
+					     NULL);
+	if (err) {
+		rtrs_err(path, "send HB ACK failed, errno: %pe\n",
+			 ERR_PTR(err));
+		path->hb_err_handler(usr_con);
+		return;
+	}
+}
+EXPORT_SYMBOL_GPL(rtrs_send_hb_ack);
+
+static void hb_work(struct work_struct *work)
+{
+	struct rtrs_con *usr_con;
+	struct rtrs_path *path;
+	u32 imm;
+	int err;
+
+	path = container_of(to_delayed_work(work), typeof(*path), hb_dwork);
+	usr_con = path->con[0];
+
+	if (path->hb_missed_cnt > path->hb_missed_max) {
+		rtrs_err(path, "HB missed max reached.\n");
+		path->hb_err_handler(usr_con);
+		return;
+	}
+	if (path->hb_missed_cnt++) {
+		/* Reschedule work without sending hb */
+		schedule_hb(path);
+		return;
+	}
+
+	path->hb_last_sent = ktime_get();
+
+	imm = rtrs_to_imm(RTRS_HB_MSG_IMM, 0);
+	err = rtrs_post_rdma_write_imm_empty(usr_con, path->hb_cqe, imm,
+					     NULL);
+	if (err) {
+		rtrs_err(path, "HB send failed, errno: %pe\n",
+			 ERR_PTR(err));
+		path->hb_err_handler(usr_con);
+		return;
+	}
+
+	schedule_hb(path);
+}
+
+void rtrs_init_hb(struct rtrs_path *path, struct ib_cqe *cqe,
+		  unsigned int interval_ms, unsigned int missed_max,
+		  void (*err_handler)(struct rtrs_con *con),
+		  struct workqueue_struct *wq)
+{
+	path->hb_cqe = cqe;
+	path->hb_interval_ms = interval_ms;
+	path->hb_err_handler = err_handler;
+	path->hb_wq = wq;
+	path->hb_missed_max = missed_max;
+	path->hb_missed_cnt = 0;
+	INIT_DELAYED_WORK(&path->hb_dwork, hb_work);
+}
+EXPORT_SYMBOL_GPL(rtrs_init_hb);
+
+void rtrs_start_hb(struct rtrs_path *path)
+{
+	schedule_hb(path);
+}
+EXPORT_SYMBOL_GPL(rtrs_start_hb);
+
+void rtrs_stop_hb(struct rtrs_path *path)
+{
+	cancel_delayed_work_sync(&path->hb_dwork);
+	path->hb_missed_cnt = 0;
+}
+EXPORT_SYMBOL_GPL(rtrs_stop_hb);
+
+static int rtrs_str_gid_to_sockaddr(const char *addr, size_t len,
+				     short port, struct sockaddr_storage *dst)
+{
+	struct sockaddr_ib *dst_ib = (struct sockaddr_ib *)dst;
+	int ret;
+
+	/*
+	 * We can use some of the IPv6 functions since GID is a valid
+	 * IPv6 address format
+	 */
+	ret = in6_pton(addr, len, dst_ib->sib_addr.sib_raw, '\0', NULL);
+	if (ret == 0)
+		return -EINVAL;
+
+	dst_ib->sib_family = AF_IB;
+	/*
+	 * Use the same TCP server port number as the IB service ID
+	 * on the IB port space range
+	 */
+	dst_ib->sib_sid = cpu_to_be64(RDMA_IB_IP_PS_IB | port);
+	dst_ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL);
+	dst_ib->sib_pkey = cpu_to_be16(0xffff);
+
+	return 0;
+}
+
+/**
+ * rtrs_str_to_sockaddr() - Convert rtrs address string to sockaddr
+ * @addr:	String representation of an addr (IPv4, IPv6 or IB GID):
+ *              - "ip:192.168.1.1"
+ *              - "ip:fe80::200:5aee:feaa:20a2"
+ *              - "gid:fe80::200:5aee:feaa:20a2"
+ * @len:        String address length
+ * @port:	Destination port
+ * @dst:	Destination sockaddr structure
+ *
+ * Returns 0 if conversion successful. Non-zero on error.
+ */
+static int rtrs_str_to_sockaddr(const char *addr, size_t len,
+				u16 port, struct sockaddr_storage *dst)
+{
+	if (strncmp(addr, "gid:", 4) == 0) {
+		return rtrs_str_gid_to_sockaddr(addr + 4, len - 4, port, dst);
+	} else if (strncmp(addr, "ip:", 3) == 0) {
+		char port_str[8];
+		char *cpy;
+		int err;
+
+		snprintf(port_str, sizeof(port_str), "%u", port);
+		cpy = kstrndup(addr + 3, len - 3, GFP_KERNEL);
+		err = cpy ? inet_pton_with_scope(&init_net, AF_UNSPEC,
+						 cpy, port_str, dst) : -ENOMEM;
+		kfree(cpy);
+
+		return err;
+	}
+	return -EPROTONOSUPPORT;
+}
+
+/**
+ * sockaddr_to_str() - convert sockaddr to a string.
+ * @addr:	the sockadddr structure to be converted.
+ * @buf:	string containing socket addr.
+ * @len:	string length.
+ *
+ * The return value is the number of characters written into buf not
+ * including the trailing '\0'. If len is == 0 the function returns 0..
+ */
+int sockaddr_to_str(const struct sockaddr *addr, char *buf, size_t len)
+{
+	switch (addr->sa_family) {
+	case AF_IB:
+		return scnprintf(buf, len, "gid:%pI6",
+			&((struct sockaddr_ib *)addr)->sib_addr.sib_raw);
+	case AF_INET:
+		return scnprintf(buf, len, "ip:%pI4",
+			&((struct sockaddr_in *)addr)->sin_addr);
+	case AF_INET6:
+		return scnprintf(buf, len, "ip:%pI6c",
+			  &((struct sockaddr_in6 *)addr)->sin6_addr);
+	}
+	return scnprintf(buf, len, "<invalid address family>");
+}
+EXPORT_SYMBOL(sockaddr_to_str);
+
+/**
+ * rtrs_addr_to_str() - convert rtrs_addr to a string "src@dst"
+ * @addr:	the rtrs_addr structure to be converted
+ * @buf:	string containing source and destination addr of a path
+ *		separated by '@' I.e. "ip:1.1.1.1@ip:1.1.1.2"
+ *		"ip:1.1.1.1@ip:1.1.1.2".
+ * @len:	string length
+ *
+ * The return value is the number of characters written into buf not
+ * including the trailing '\0'.
+ */
+int rtrs_addr_to_str(const struct rtrs_addr *addr, char *buf, size_t len)
+{
+	int cnt;
+
+	cnt = sockaddr_to_str((struct sockaddr *)addr->src,
+			      buf, len);
+	cnt += scnprintf(buf + cnt, len - cnt, "@");
+	sockaddr_to_str((struct sockaddr *)addr->dst,
+			buf + cnt, len - cnt);
+	return cnt;
+}
+EXPORT_SYMBOL(rtrs_addr_to_str);
+
+/**
+ * rtrs_addr_to_sockaddr() - convert path string "src,dst" or "src@dst"
+ * to sockaddreses
+ * @str:	string containing source and destination addr of a path
+ *		separated by ',' or '@' I.e. "ip:1.1.1.1,ip:1.1.1.2" or
+ *		"ip:1.1.1.1@ip:1.1.1.2". If str contains only one address it's
+ *		considered to be destination.
+ * @len:	string length
+ * @port:	Destination port number.
+ * @addr:	will be set to the source/destination address or to NULL
+ *		if str doesn't contain any source address.
+ *
+ * Returns zero if conversion successful. Non-zero otherwise.
+ */
+int rtrs_addr_to_sockaddr(const char *str, size_t len, u16 port,
+			  struct rtrs_addr *addr)
+{
+	const char *d;
+
+	d = strchr(str, ',');
+	if (!d)
+		d = strchr(str, '@');
+	if (d) {
+		if (rtrs_str_to_sockaddr(str, d - str, 0, addr->src))
+			return -EINVAL;
+		d += 1;
+		len -= d - str;
+		str  = d;
+
+	} else {
+		addr->src = NULL;
+	}
+	return rtrs_str_to_sockaddr(str, len, port, addr->dst);
+}
+EXPORT_SYMBOL(rtrs_addr_to_sockaddr);
+
+void rtrs_rdma_dev_pd_init(enum ib_pd_flags pd_flags,
+			    struct rtrs_rdma_dev_pd *pool)
+{
+	INIT_LIST_HEAD(&pool->list);
+	mutex_init(&pool->mutex);
+	pool->pd_flags = pd_flags;
+}
+EXPORT_SYMBOL(rtrs_rdma_dev_pd_init);
+
+void rtrs_rdma_dev_pd_deinit(struct rtrs_rdma_dev_pd *pool)
+{
+	mutex_destroy(&pool->mutex);
+	WARN_ON(!list_empty(&pool->list));
+}
+EXPORT_SYMBOL(rtrs_rdma_dev_pd_deinit);
+
+static void dev_free(struct kref *ref)
+{
+	struct rtrs_rdma_dev_pd *pool;
+	struct rtrs_ib_dev *dev;
+
+	dev = container_of(ref, typeof(*dev), ref);
+	pool = dev->pool;
+
+	mutex_lock(&pool->mutex);
+	list_del(&dev->entry);
+	mutex_unlock(&pool->mutex);
+
+	if (pool->ops && pool->ops->deinit)
+		pool->ops->deinit(dev);
+
+	ib_dealloc_pd(dev->ib_pd);
+	kfree(dev);
+}
+
+int rtrs_ib_dev_put(struct rtrs_ib_dev *dev)
+{
+	return kref_put(&dev->ref, dev_free);
+}
+EXPORT_SYMBOL(rtrs_ib_dev_put);
+
+static int rtrs_ib_dev_get(struct rtrs_ib_dev *dev)
+{
+	return kref_get_unless_zero(&dev->ref);
+}
+
+struct rtrs_ib_dev *
+rtrs_ib_dev_find_or_add(struct ib_device *ib_dev,
+			 struct rtrs_rdma_dev_pd *pool)
+{
+	struct rtrs_ib_dev *dev;
+
+	mutex_lock(&pool->mutex);
+	list_for_each_entry(dev, &pool->list, entry) {
+		if (dev->ib_dev->node_guid == ib_dev->node_guid &&
+		    rtrs_ib_dev_get(dev))
+			goto out_unlock;
+	}
+	mutex_unlock(&pool->mutex);
+	dev = kzalloc_obj(*dev);
+	if (!dev)
+		goto out_err;
+
+	kref_init(&dev->ref);
+	dev->pool = pool;
+	dev->ib_dev = ib_dev;
+	dev->ib_pd = ib_alloc_pd(ib_dev, pool->pd_flags);
+	if (IS_ERR(dev->ib_pd))
+		goto out_free_dev;
+
+	if (pool->ops && pool->ops->init && pool->ops->init(dev))
+		goto out_free_pd;
+
+	mutex_lock(&pool->mutex);
+	list_add(&dev->entry, &pool->list);
+out_unlock:
+	mutex_unlock(&pool->mutex);
+	return dev;
+
+out_free_pd:
+	ib_dealloc_pd(dev->ib_pd);
+out_free_dev:
+	kfree(dev);
+out_err:
+	return NULL;
+}
+EXPORT_SYMBOL(rtrs_ib_dev_find_or_add);

linux-7.2.3/drivers/infiniband/ulp/rtrs/rtrs.h

@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RDMA Transport Layer
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#ifndef RTRS_H
+#define RTRS_H
+
+#include <linux/socket.h>
+#include <linux/scatterlist.h>
+
+struct rtrs_permit;
+struct rtrs_clt_sess;
+struct rtrs_srv_ctx;
+struct rtrs_srv_sess;
+struct rtrs_srv_op;
+
+/*
+ * RDMA transport (RTRS) client API
+ */
+
+/**
+ * enum rtrs_clt_link_ev - Events about connectivity state of a client
+ * @RTRS_CLT_LINK_EV_RECONNECTED:	Client was reconnected.
+ * @RTRS_CLT_LINK_EV_DISCONNECTED:	Client was disconnected.
+ */
+enum rtrs_clt_link_ev {
+	RTRS_CLT_LINK_EV_RECONNECTED,
+	RTRS_CLT_LINK_EV_DISCONNECTED,
+};
+
+/**
+ * struct rtrs_addr - Source and destination address of a path to be established
+ * @src:	source address
+ * @dst:	destination address
+ */
+struct rtrs_addr {
+	struct sockaddr_storage *src;
+	struct sockaddr_storage *dst;
+};
+
+/**
+ * struct rtrs_clt_ops - it holds the link event callback and private pointer.
+ * @priv: User supplied private data.
+ * @link_ev: Event notification callback function for connection state changes
+ *	@priv: User supplied data that was passed to rtrs_clt_open()
+ *	@ev: Occurred event
+ */
+struct rtrs_clt_ops {
+	void	*priv;
+	void	(*link_ev)(void *priv, enum rtrs_clt_link_ev ev);
+};
+
+struct rtrs_clt_sess *rtrs_clt_open(struct rtrs_clt_ops *ops,
+				 const char *pathname,
+				 const struct rtrs_addr *paths,
+				 size_t path_cnt, u16 port,
+				 size_t pdu_sz, u8 reconnect_delay_sec,
+				 s16 max_reconnect_attempts, u32 nr_poll_queues);
+
+void rtrs_clt_close(struct rtrs_clt_sess *clt);
+
+enum wait_type {
+	RTRS_PERMIT_NOWAIT = 0,
+	RTRS_PERMIT_WAIT   = 1
+};
+
+/**
+ * enum rtrs_clt_con_type - type of ib connection to use with a given
+ * rtrs_permit
+ * @RTRS_ADMIN_CON: use connection reserved for "service" messages
+ * @RTRS_IO_CON: use a connection reserved for IO
+ */
+enum rtrs_clt_con_type {
+	RTRS_ADMIN_CON,
+	RTRS_IO_CON
+};
+
+struct rtrs_permit *rtrs_clt_get_permit(struct rtrs_clt_sess *sess,
+					enum rtrs_clt_con_type con_type,
+					enum wait_type wait);
+
+void rtrs_clt_put_permit(struct rtrs_clt_sess *sess,
+			 struct rtrs_permit *permit);
+
+/**
+ * struct rtrs_clt_req_ops - it holds the request confirmation callback
+ * and a private pointer.
+ * @priv: User supplied private data.
+ * @conf_fn:	callback function to be called as confirmation
+ *	@priv:	User provided data, passed back with corresponding
+ *		@(conf) confirmation.
+ *	@errno: error number.
+ */
+struct rtrs_clt_req_ops {
+	void	*priv;
+	void	(*conf_fn)(void *priv, int errno);
+};
+
+int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
+		     struct rtrs_clt_sess *sess, struct rtrs_permit *permit,
+		     const struct kvec *vec, size_t nr, size_t len,
+		     struct scatterlist *sg, unsigned int sg_cnt);
+int rtrs_clt_rdma_cq_direct(struct rtrs_clt_sess *clt, unsigned int index);
+
+/**
+ * struct rtrs_attrs - RTRS session attributes
+ * @queue_depth:	queue_depth saved from rtrs_clt_sess message
+ * @max_io_size:	max_io_size from rtrs_clt_sess message, capped to
+ *			  @max_segments * %SZ_4K
+ * @max_segments:	max_segments saved from rtrs_clt_sess message
+ */
+struct rtrs_attrs {
+	u32		queue_depth;
+	u32		max_io_size;
+	u32		max_segments;
+};
+
+int rtrs_clt_query(struct rtrs_clt_sess *sess, struct rtrs_attrs *attr);
+
+/*
+ * Here goes RTRS server API
+ */
+
+/**
+ * enum rtrs_srv_link_ev - Server link events
+ * @RTRS_SRV_LINK_EV_CONNECTED:	Connection from client established
+ * @RTRS_SRV_LINK_EV_DISCONNECTED:	Connection was disconnected, all
+ *					connection RTRS resources were freed.
+ */
+enum rtrs_srv_link_ev {
+	RTRS_SRV_LINK_EV_CONNECTED,
+	RTRS_SRV_LINK_EV_DISCONNECTED,
+};
+
+struct rtrs_srv_ops {
+	/**
+	 * rdma_ev():		Event notification for RDMA operations
+	 *			If the callback returns a value != 0, an error
+	 *			message for the data transfer will be sent to
+	 *			the client.
+
+	 *	@priv:		Private data set by rtrs_srv_set_sess_priv()
+	 *	@id:		internal RTRS operation id
+	 *	@data:		Pointer to (bidirectional) rdma memory area:
+	 *			- in case of %RTRS_SRV_RDMA_EV_RECV contains
+	 *			data sent by the client
+	 *			- in case of %RTRS_SRV_RDMA_EV_WRITE_REQ points
+	 *			to the memory area where the response is to be
+	 *			written to
+	 *	@datalen:	Size of the memory area in @data
+	 *	@usr:		The extra user message sent by the client (%vec)
+	 *	@usrlen:	Size of the user message
+	 */
+	int (*rdma_ev)(void *priv,
+		       struct rtrs_srv_op *id,
+		       void *data, size_t datalen, const void *usr,
+		       size_t usrlen);
+	/**
+	 * link_ev():		Events about connectivity state changes
+	 *			If the callback returns != 0 and the event
+	 *			%RTRS_SRV_LINK_EV_CONNECTED the corresponding
+	 *			session will be destroyed.
+	 *	@sess:		Session
+	 *	@ev:		event
+	 *	@priv:		Private data from user if previously set with
+	 *			rtrs_srv_set_sess_priv()
+	 */
+	int (*link_ev)(struct rtrs_srv_sess *sess, enum rtrs_srv_link_ev ev,
+		       void *priv);
+};
+
+struct rtrs_srv_ctx *rtrs_srv_open(struct rtrs_srv_ops *ops, u16 port);
+
+void rtrs_srv_close(struct rtrs_srv_ctx *ctx);
+
+bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int errno);
+
+void rtrs_srv_set_sess_priv(struct rtrs_srv_sess *sess, void *priv);
+
+int rtrs_srv_get_path_name(struct rtrs_srv_sess *sess, char *pathname,
+			   size_t len);
+
+int rtrs_srv_get_queue_depth(struct rtrs_srv_sess *sess);
+
+int rtrs_addr_to_sockaddr(const char *str, size_t len, u16 port,
+			  struct rtrs_addr *addr);
+
+int sockaddr_to_str(const struct sockaddr *addr, char *buf, size_t len);
+int rtrs_addr_to_str(const struct rtrs_addr *addr, char *buf, size_t len);
+#endif