summaryrefslogtreecommitdiffstats
path: root/drivers/nvme/target
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme/target')
-rw-r--r--drivers/nvme/target/Kconfig2
-rw-r--r--drivers/nvme/target/admin-cmd.c94
-rw-r--r--drivers/nvme/target/core.c4
-rw-r--r--drivers/nvme/target/io-cmd.c3
-rw-r--r--drivers/nvme/target/loop.c10
-rw-r--r--drivers/nvme/target/nvmet.h1
-rw-r--r--drivers/nvme/target/rdma.c107
7 files changed, 178 insertions, 43 deletions
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index a5c31cbeb481..3a5b9d0576cb 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -15,8 +15,8 @@ config NVME_TARGET
config NVME_TARGET_LOOP
tristate "NVMe loopback device support"
- depends on BLK_DEV_NVME
depends on NVME_TARGET
+ select NVME_CORE
select NVME_FABRICS
select SG_POOL
help
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 2fac17a5ad53..7ab9c9381b98 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -13,8 +13,8 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
-#include <linux/random.h>
#include <generated/utsrelease.h>
+#include <asm/unaligned.h>
#include "nvmet.h"
u32 nvmet_get_log_page_len(struct nvme_command *cmd)
@@ -30,8 +30,84 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
return len;
}
+static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
+ struct nvme_smart_log *slog)
+{
+ u16 status;
+ struct nvmet_ns *ns;
+ u64 host_reads, host_writes, data_units_read, data_units_written;
+
+ status = NVME_SC_SUCCESS;
+ ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->get_log_page.nsid);
+ if (!ns) {
+ status = NVME_SC_INVALID_NS;
+ pr_err("nvmet : Counld not find namespace id : %d\n",
+ le32_to_cpu(req->cmd->get_log_page.nsid));
+ goto out;
+ }
+
+ host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
+ data_units_read = part_stat_read(ns->bdev->bd_part, sectors[READ]);
+ host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
+ data_units_written = part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+
+ put_unaligned_le64(host_reads, &slog->host_reads[0]);
+ put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
+ put_unaligned_le64(host_writes, &slog->host_writes[0]);
+ put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
+ nvmet_put_namespace(ns);
+out:
+ return status;
+}
+
+static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
+ struct nvme_smart_log *slog)
+{
+ u16 status;
+ u64 host_reads = 0, host_writes = 0;
+ u64 data_units_read = 0, data_units_written = 0;
+ struct nvmet_ns *ns;
+ struct nvmet_ctrl *ctrl;
+
+ status = NVME_SC_SUCCESS;
+ ctrl = req->sq->ctrl;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+ host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
+ data_units_read +=
+ part_stat_read(ns->bdev->bd_part, sectors[READ]);
+ host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]);
+ data_units_written +=
+ part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+
+ }
+ rcu_read_unlock();
+
+ put_unaligned_le64(host_reads, &slog->host_reads[0]);
+ put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
+ put_unaligned_le64(host_writes, &slog->host_writes[0]);
+ put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
+
+ return status;
+}
+
+static u16 nvmet_get_smart_log(struct nvmet_req *req,
+ struct nvme_smart_log *slog)
+{
+ u16 status;
+
+ WARN_ON(req == NULL || slog == NULL);
+ if (req->cmd->get_log_page.nsid == 0xFFFFFFFF)
+ status = nvmet_get_smart_log_all(req, slog);
+ else
+ status = nvmet_get_smart_log_nsid(req, slog);
+ return status;
+}
+
static void nvmet_execute_get_log_page(struct nvmet_req *req)
{
+ struct nvme_smart_log *smart_log;
size_t data_len = nvmet_get_log_page_len(req->cmd);
void *buf;
u16 status = 0;
@@ -60,6 +136,16 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
* available (e.g. units or commands read/written) those aren't
* persistent over power loss.
*/
+ if (data_len != sizeof(*smart_log)) {
+ status = NVME_SC_INTERNAL;
+ goto err;
+ }
+ smart_log = buf;
+ status = nvmet_get_smart_log(req, smart_log);
+ if (status) {
+ memset(buf, '\0', data_len);
+ goto err;
+ }
break;
case 0x03:
/*
@@ -74,6 +160,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
status = nvmet_copy_to_sgl(req, 0, buf, data_len);
+err:
kfree(buf);
out:
nvmet_req_complete(req, status);
@@ -83,7 +170,6 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_id_ctrl *id;
- u64 serial;
u16 status = 0;
id = kzalloc(sizeof(*id), GFP_KERNEL);
@@ -96,10 +182,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->vid = 0;
id->ssvid = 0;
- /* generate a random serial number as our controllers are ephemeral: */
- get_random_bytes(&serial, sizeof(serial));
memset(id->sn, ' ', sizeof(id->sn));
- snprintf(id->sn, sizeof(id->sn), "%llx", serial);
+ snprintf(id->sn, sizeof(id->sn), "%llx", ctrl->serial);
memset(id->mn, ' ', sizeof(id->mn));
strncpy((char *)id->mn, "Linux", sizeof(id->mn));
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 8a891ca53367..6559d5afa7bf 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -13,6 +13,7 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
+#include <linux/random.h>
#include "nvmet.h"
static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
@@ -728,6 +729,9 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);
+ /* generate a random serial number as our controllers are ephemeral: */
+ get_random_bytes(&ctrl->serial, sizeof(ctrl->serial));
+
kref_init(&ctrl->ref);
ctrl->subsys = subsys;
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
index 2cd069b691ae..4a96c2049b7b 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd.c
@@ -58,6 +58,7 @@ static void nvmet_execute_rw(struct nvmet_req *req)
if (req->cmd->rw.opcode == nvme_cmd_write) {
op = REQ_OP_WRITE;
+ op_flags = WRITE_ODIRECT;
if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
op_flags |= REQ_FUA;
} else {
@@ -205,7 +206,7 @@ int nvmet_parse_io_cmd(struct nvmet_req *req)
return 0;
case nvme_cmd_dsm:
req->execute = nvmet_execute_dsm;
- req->data_len = le32_to_cpu(cmd->dsm.nr) *
+ req->data_len = le32_to_cpu(cmd->dsm.nr + 1) *
sizeof(struct nvme_dsm_range);
return 0;
default:
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 94e782987cc9..d5df77d686b2 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -273,7 +273,6 @@ static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
static struct blk_mq_ops nvme_loop_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_loop_init_request,
.init_hctx = nvme_loop_init_hctx,
.timeout = nvme_loop_timeout,
@@ -282,7 +281,6 @@ static struct blk_mq_ops nvme_loop_mq_ops = {
static struct blk_mq_ops nvme_loop_admin_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_loop_init_admin_request,
.init_hctx = nvme_loop_init_admin_hctx,
.timeout = nvme_loop_timeout,
@@ -414,9 +412,8 @@ static void nvme_loop_del_ctrl_work(struct work_struct *work)
struct nvme_loop_ctrl *ctrl = container_of(work,
struct nvme_loop_ctrl, delete_work);
- nvme_remove_namespaces(&ctrl->ctrl);
- nvme_loop_shutdown_ctrl(ctrl);
nvme_uninit_ctrl(&ctrl->ctrl);
+ nvme_loop_shutdown_ctrl(ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
@@ -501,7 +498,6 @@ out_free_queues:
nvme_loop_destroy_admin_queue(ctrl);
out_disable:
dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
- nvme_remove_namespaces(&ctrl->ctrl);
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
@@ -558,7 +554,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
ctrl->tag_set.ops = &nvme_loop_mq_ops;
- ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize;
+ ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
ctrl->tag_set.reserved_tags = 1; /* fabric connect */
ctrl->tag_set.numa_node = NUMA_NO_NODE;
ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
@@ -622,7 +618,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
ret = -ENOMEM;
- ctrl->ctrl.sqsize = opts->queue_size;
+ ctrl->ctrl.sqsize = opts->queue_size - 1;
ctrl->ctrl.kato = opts->kato;
ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 57dd6d834c28..76b6eedccaf9 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -113,6 +113,7 @@ struct nvmet_ctrl {
struct mutex lock;
u64 cap;
+ u64 serial;
u32 cc;
u32 csts;
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index e06d504bdf0c..f8d23999e0f2 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -77,6 +77,7 @@ enum nvmet_rdma_queue_state {
NVMET_RDMA_Q_CONNECTING,
NVMET_RDMA_Q_LIVE,
NVMET_RDMA_Q_DISCONNECTING,
+ NVMET_RDMA_IN_DEVICE_REMOVAL,
};
struct nvmet_rdma_queue {
@@ -615,15 +616,10 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
if (!len)
return 0;
- /* use the already allocated data buffer if possible */
- if (len <= NVMET_RDMA_INLINE_DATA_SIZE && rsp->queue->host_qid) {
- nvmet_rdma_use_inline_sg(rsp, len, 0);
- } else {
- status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
- len);
- if (status)
- return status;
- }
+ status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
+ len);
+ if (status)
+ return status;
ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
@@ -852,7 +848,7 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
ndev->device = cm_id->device;
kref_init(&ndev->ref);
- ndev->pd = ib_alloc_pd(ndev->device);
+ ndev->pd = ib_alloc_pd(ndev->device, 0);
if (IS_ERR(ndev->pd))
goto out_free_dev;
@@ -982,9 +978,13 @@ static void nvmet_rdma_release_queue_work(struct work_struct *w)
container_of(w, struct nvmet_rdma_queue, release_work);
struct rdma_cm_id *cm_id = queue->cm_id;
struct nvmet_rdma_device *dev = queue->dev;
+ enum nvmet_rdma_queue_state state = queue->state;
nvmet_rdma_free_queue(queue);
- rdma_destroy_id(cm_id);
+
+ if (state != NVMET_RDMA_IN_DEVICE_REMOVAL)
+ rdma_destroy_id(cm_id);
+
kref_put(&dev->ref, nvmet_rdma_free_dev);
}
@@ -1004,10 +1004,10 @@ nvmet_rdma_parse_cm_connect_req(struct rdma_conn_param *conn,
queue->host_qid = le16_to_cpu(req->qid);
/*
- * req->hsqsize corresponds to our recv queue size
+ * req->hsqsize corresponds to our recv queue size plus 1
* req->hrqsize corresponds to our send queue size
*/
- queue->recv_queue_size = le16_to_cpu(req->hsqsize);
+ queue->recv_queue_size = le16_to_cpu(req->hsqsize) + 1;
queue->send_queue_size = le16_to_cpu(req->hrqsize);
if (!queue->host_qid && queue->recv_queue_size > NVMF_AQ_DEPTH)
@@ -1233,8 +1233,9 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
switch (queue->state) {
case NVMET_RDMA_Q_CONNECTING:
case NVMET_RDMA_Q_LIVE:
- disconnect = true;
queue->state = NVMET_RDMA_Q_DISCONNECTING;
+ case NVMET_RDMA_IN_DEVICE_REMOVAL:
+ disconnect = true;
break;
case NVMET_RDMA_Q_DISCONNECTING:
break;
@@ -1272,6 +1273,62 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
schedule_work(&queue->release_work);
}
+/**
+ * nvme_rdma_device_removal() - Handle RDMA device removal
+ * @queue: nvmet rdma queue (cm id qp_context)
+ * @addr: nvmet address (cm_id context)
+ *
+ * DEVICE_REMOVAL event notifies us that the RDMA device is about
+ * to unplug so we should take care of destroying our RDMA resources.
+ * This event will be generated for each allocated cm_id.
+ *
+ * Note that this event can be generated on a normal queue cm_id
+ * and/or a device bound listener cm_id (where in this case
+ * queue will be null).
+ *
+ * we claim ownership on destroying the cm_id. For queues we move
+ * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port
+ * we nullify the priv to prevent double cm_id destruction and destroying
+ * the cm_id implicitely by returning a non-zero rc to the callout.
+ */
+static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id,
+ struct nvmet_rdma_queue *queue)
+{
+ unsigned long flags;
+
+ if (!queue) {
+ struct nvmet_port *port = cm_id->context;
+
+ /*
+ * This is a listener cm_id. Make sure that
+ * future remove_port won't invoke a double
+ * cm_id destroy. use atomic xchg to make sure
+ * we don't compete with remove_port.
+ */
+ if (xchg(&port->priv, NULL) != cm_id)
+ return 0;
+ } else {
+ /*
+ * This is a queue cm_id. Make sure that
+ * release queue will not destroy the cm_id
+ * and schedule all ctrl queues removal (only
+ * if the queue is not disconnecting already).
+ */
+ spin_lock_irqsave(&queue->state_lock, flags);
+ if (queue->state != NVMET_RDMA_Q_DISCONNECTING)
+ queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL;
+ spin_unlock_irqrestore(&queue->state_lock, flags);
+ nvmet_rdma_queue_disconnect(queue);
+ flush_scheduled_work();
+ }
+
+ /*
+ * We need to return 1 so that the core will destroy
+ * it's own ID. What a great API design..
+ */
+ return 1;
+}
+
static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event)
{
@@ -1294,20 +1351,11 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
break;
case RDMA_CM_EVENT_ADDR_CHANGE:
case RDMA_CM_EVENT_DISCONNECTED:
- case RDMA_CM_EVENT_DEVICE_REMOVAL:
case RDMA_CM_EVENT_TIMEWAIT_EXIT:
- /*
- * We can get the device removal callback even for a
- * CM ID that we aren't actually using. In that case
- * the context pointer is NULL, so we shouldn't try
- * to disconnect a non-existing queue. But we also
- * need to return 1 so that the core will destroy
- * it's own ID. What a great API design..
- */
- if (queue)
- nvmet_rdma_queue_disconnect(queue);
- else
- ret = 1;
+ nvmet_rdma_queue_disconnect(queue);
+ break;
+ case RDMA_CM_EVENT_DEVICE_REMOVAL:
+ ret = nvmet_rdma_device_removal(cm_id, queue);
break;
case RDMA_CM_EVENT_REJECTED:
case RDMA_CM_EVENT_UNREACHABLE:
@@ -1396,9 +1444,10 @@ out_destroy_id:
static void nvmet_rdma_remove_port(struct nvmet_port *port)
{
- struct rdma_cm_id *cm_id = port->priv;
+ struct rdma_cm_id *cm_id = xchg(&port->priv, NULL);
- rdma_destroy_id(cm_id);
+ if (cm_id)
+ rdma_destroy_id(cm_id);
}
static struct nvmet_fabrics_ops nvmet_rdma_ops = {
OpenPOWER on IntegriCloud