summaryrefslogtreecommitdiffstats
path: root/drivers/nvme/target
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:35:05 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:39:31 +0000
commit85c675d0d09a45a135bddd15d7b385f8758c32fb (patch)
tree76267dbc9b9a130337be3640948fe397b04ac629 /drivers/nvme/target
parentAdding upstream version 6.6.15. (diff)
downloadlinux-85c675d0d09a45a135bddd15d7b385f8758c32fb.tar.xz
linux-85c675d0d09a45a135bddd15d7b385f8758c32fb.zip
Adding upstream version 6.7.7.upstream/6.7.7
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'drivers/nvme/target')
-rw-r--r--drivers/nvme/target/Kconfig27
-rw-r--r--drivers/nvme/target/auth.c31
-rw-r--r--drivers/nvme/target/configfs.c128
-rw-r--r--drivers/nvme/target/fabrics-cmd-auth.c2
-rw-r--r--drivers/nvme/target/fc.c140
-rw-r--r--drivers/nvme/target/fcloop.c6
-rw-r--r--drivers/nvme/target/io-cmd-bdev.c20
-rw-r--r--drivers/nvme/target/loop.c4
-rw-r--r--drivers/nvme/target/nvmet.h12
-rw-r--r--drivers/nvme/target/tcp.c344
10 files changed, 581 insertions, 133 deletions
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 79fc64035e..872dd1a0ac 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -4,6 +4,8 @@ config NVME_TARGET
tristate "NVMe Target support"
depends on BLOCK
depends on CONFIGFS_FS
+ select NVME_KEYRING if NVME_TARGET_TCP_TLS
+ select KEYS if NVME_TARGET_TCP_TLS
select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
select SGL_ALLOC
help
@@ -84,17 +86,24 @@ config NVME_TARGET_TCP
If unsure, say N.
+config NVME_TARGET_TCP_TLS
+ bool "NVMe over Fabrics TCP target TLS encryption support"
+ depends on NVME_TARGET_TCP
+ select NET_HANDSHAKE
+ help
+ Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
+
+ The TLS handshake daemon is available at
+ https://github.com/oracle/ktls-utils.
+
+ If unsure, say N.
+
config NVME_TARGET_AUTH
- bool "NVMe over Fabrics In-band Authentication support"
+ bool "NVMe over Fabrics In-band Authentication in target side"
depends on NVME_TARGET
- select NVME_COMMON
- select CRYPTO
- select CRYPTO_HMAC
- select CRYPTO_SHA256
- select CRYPTO_SHA512
- select CRYPTO_DH
- select CRYPTO_DH_RFC7919_GROUPS
+ select NVME_AUTH
help
- This enables support for NVMe over Fabrics In-band Authentication
+ This enables support for NVMe over Fabrics In-band Authentication in
+ target side.
If unsure, say N.
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index 4dcddcf952..3ddbc3880c 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -267,7 +267,8 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
struct shash_desc *shash;
struct nvmet_ctrl *ctrl = req->sq->ctrl;
const char *hash_name;
- u8 *challenge = req->sq->dhchap_c1, *host_response;
+ u8 *challenge = req->sq->dhchap_c1;
+ struct nvme_dhchap_key *transformed_key;
u8 buf[4];
int ret;
@@ -291,14 +292,15 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
goto out_free_tfm;
}
- host_response = nvme_auth_transform_key(ctrl->host_key, ctrl->hostnqn);
- if (IS_ERR(host_response)) {
- ret = PTR_ERR(host_response);
+ transformed_key = nvme_auth_transform_key(ctrl->host_key,
+ ctrl->hostnqn);
+ if (IS_ERR(transformed_key)) {
+ ret = PTR_ERR(transformed_key);
goto out_free_tfm;
}
- ret = crypto_shash_setkey(shash_tfm, host_response,
- ctrl->host_key->len);
+ ret = crypto_shash_setkey(shash_tfm, transformed_key->key,
+ transformed_key->len);
if (ret)
goto out_free_response;
@@ -365,7 +367,7 @@ out:
kfree(challenge);
kfree(shash);
out_free_response:
- kfree_sensitive(host_response);
+ nvme_auth_free_key(transformed_key);
out_free_tfm:
crypto_free_shash(shash_tfm);
return 0;
@@ -378,7 +380,8 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
struct shash_desc *shash;
struct nvmet_ctrl *ctrl = req->sq->ctrl;
const char *hash_name;
- u8 *challenge = req->sq->dhchap_c2, *ctrl_response;
+ u8 *challenge = req->sq->dhchap_c2;
+ struct nvme_dhchap_key *transformed_key;
u8 buf[4];
int ret;
@@ -402,15 +405,15 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
goto out_free_tfm;
}
- ctrl_response = nvme_auth_transform_key(ctrl->ctrl_key,
+ transformed_key = nvme_auth_transform_key(ctrl->ctrl_key,
ctrl->subsysnqn);
- if (IS_ERR(ctrl_response)) {
- ret = PTR_ERR(ctrl_response);
+ if (IS_ERR(transformed_key)) {
+ ret = PTR_ERR(transformed_key);
goto out_free_tfm;
}
- ret = crypto_shash_setkey(shash_tfm, ctrl_response,
- ctrl->ctrl_key->len);
+ ret = crypto_shash_setkey(shash_tfm, transformed_key->key,
+ transformed_key->len);
if (ret)
goto out_free_response;
@@ -474,7 +477,7 @@ out:
kfree(challenge);
kfree(shash);
out_free_response:
- kfree_sensitive(ctrl_response);
+ nvme_auth_free_key(transformed_key);
out_free_tfm:
crypto_free_shash(shash_tfm);
return 0;
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 01b2a3d1a5..d937fe0512 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -15,6 +15,7 @@
#ifdef CONFIG_NVME_TARGET_AUTH
#include <linux/nvme-auth.h>
#endif
+#include <linux/nvme-keyring.h>
#include <crypto/hash.h>
#include <crypto/kpp.h>
#include <linux/nospec.h>
@@ -160,10 +161,14 @@ static const struct nvmet_type_name_map nvmet_addr_treq[] = {
{ NVMF_TREQ_NOT_REQUIRED, "not required" },
};
+static inline u8 nvmet_port_disc_addr_treq_mask(struct nvmet_port *port)
+{
+ return (port->disc_addr.treq & ~NVME_TREQ_SECURE_CHANNEL_MASK);
+}
+
static ssize_t nvmet_addr_treq_show(struct config_item *item, char *page)
{
- u8 treq = to_nvmet_port(item)->disc_addr.treq &
- NVME_TREQ_SECURE_CHANNEL_MASK;
+ u8 treq = nvmet_port_disc_addr_treq_secure_channel(to_nvmet_port(item));
int i;
for (i = 0; i < ARRAY_SIZE(nvmet_addr_treq); i++) {
@@ -179,7 +184,7 @@ static ssize_t nvmet_addr_treq_store(struct config_item *item,
const char *page, size_t count)
{
struct nvmet_port *port = to_nvmet_port(item);
- u8 treq = port->disc_addr.treq & ~NVME_TREQ_SECURE_CHANNEL_MASK;
+ u8 treq = nvmet_port_disc_addr_treq_mask(port);
int i;
if (nvmet_is_port_enabled(port, __func__))
@@ -194,6 +199,20 @@ static ssize_t nvmet_addr_treq_store(struct config_item *item,
return -EINVAL;
found:
+ if (port->disc_addr.trtype == NVMF_TRTYPE_TCP &&
+ port->disc_addr.tsas.tcp.sectype == NVMF_TCP_SECTYPE_TLS13) {
+ switch (nvmet_addr_treq[i].type) {
+ case NVMF_TREQ_NOT_SPECIFIED:
+ pr_debug("treq '%s' not allowed for TLS1.3\n",
+ nvmet_addr_treq[i].name);
+ return -EINVAL;
+ case NVMF_TREQ_NOT_REQUIRED:
+ pr_warn("Allow non-TLS connections while TLS1.3 is enabled\n");
+ break;
+ default:
+ break;
+ }
+ }
treq |= nvmet_addr_treq[i].type;
port->disc_addr.treq = treq;
return count;
@@ -304,6 +323,11 @@ static void nvmet_port_init_tsas_rdma(struct nvmet_port *port)
port->disc_addr.tsas.rdma.cms = NVMF_RDMA_CMS_RDMA_CM;
}
+static void nvmet_port_init_tsas_tcp(struct nvmet_port *port, int sectype)
+{
+ port->disc_addr.tsas.tcp.sectype = sectype;
+}
+
static ssize_t nvmet_addr_trtype_store(struct config_item *item,
const char *page, size_t count)
{
@@ -326,11 +350,99 @@ found:
port->disc_addr.trtype = nvmet_transport[i].type;
if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA)
nvmet_port_init_tsas_rdma(port);
+ else if (port->disc_addr.trtype == NVMF_TRTYPE_TCP)
+ nvmet_port_init_tsas_tcp(port, NVMF_TCP_SECTYPE_NONE);
return count;
}
CONFIGFS_ATTR(nvmet_, addr_trtype);
+static const struct nvmet_type_name_map nvmet_addr_tsas_tcp[] = {
+ { NVMF_TCP_SECTYPE_NONE, "none" },
+ { NVMF_TCP_SECTYPE_TLS13, "tls1.3" },
+};
+
+static const struct nvmet_type_name_map nvmet_addr_tsas_rdma[] = {
+ { NVMF_RDMA_QPTYPE_CONNECTED, "connected" },
+ { NVMF_RDMA_QPTYPE_DATAGRAM, "datagram" },
+};
+
+static ssize_t nvmet_addr_tsas_show(struct config_item *item,
+ char *page)
+{
+ struct nvmet_port *port = to_nvmet_port(item);
+ int i;
+
+ if (port->disc_addr.trtype == NVMF_TRTYPE_TCP) {
+ for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) {
+ if (port->disc_addr.tsas.tcp.sectype == nvmet_addr_tsas_tcp[i].type)
+ return sprintf(page, "%s\n", nvmet_addr_tsas_tcp[i].name);
+ }
+ } else if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA) {
+ for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_rdma); i++) {
+ if (port->disc_addr.tsas.rdma.qptype == nvmet_addr_tsas_rdma[i].type)
+ return sprintf(page, "%s\n", nvmet_addr_tsas_rdma[i].name);
+ }
+ }
+ return sprintf(page, "reserved\n");
+}
+
+static ssize_t nvmet_addr_tsas_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct nvmet_port *port = to_nvmet_port(item);
+ u8 treq = nvmet_port_disc_addr_treq_mask(port);
+ u8 sectype;
+ int i;
+
+ if (nvmet_is_port_enabled(port, __func__))
+ return -EACCES;
+
+ if (port->disc_addr.trtype != NVMF_TRTYPE_TCP)
+ return -EINVAL;
+
+ for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) {
+ if (sysfs_streq(page, nvmet_addr_tsas_tcp[i].name)) {
+ sectype = nvmet_addr_tsas_tcp[i].type;
+ goto found;
+ }
+ }
+
+ pr_err("Invalid value '%s' for tsas\n", page);
+ return -EINVAL;
+
+found:
+ if (sectype == NVMF_TCP_SECTYPE_TLS13) {
+ if (!IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS)) {
+ pr_err("TLS is not supported\n");
+ return -EINVAL;
+ }
+ if (!port->keyring) {
+ pr_err("TLS keyring not configured\n");
+ return -EINVAL;
+ }
+ }
+
+ nvmet_port_init_tsas_tcp(port, sectype);
+ /*
+ * If TLS is enabled TREQ should be set to 'required' per default
+ */
+ if (sectype == NVMF_TCP_SECTYPE_TLS13) {
+ u8 sc = nvmet_port_disc_addr_treq_secure_channel(port);
+
+ if (sc == NVMF_TREQ_NOT_SPECIFIED)
+ treq |= NVMF_TREQ_REQUIRED;
+ else
+ treq |= sc;
+ } else {
+ treq |= NVMF_TREQ_NOT_SPECIFIED;
+ }
+ port->disc_addr.treq = treq;
+ return count;
+}
+
+CONFIGFS_ATTR(nvmet_, addr_tsas);
+
/*
* Namespace structures & file operation functions below
*/
@@ -1734,6 +1846,7 @@ static void nvmet_port_release(struct config_item *item)
flush_workqueue(nvmet_wq);
list_del(&port->global_entry);
+ key_put(port->keyring);
kfree(port->ana_state);
kfree(port);
}
@@ -1744,6 +1857,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
&nvmet_attr_addr_traddr,
&nvmet_attr_addr_trsvcid,
&nvmet_attr_addr_trtype,
+ &nvmet_attr_addr_tsas,
&nvmet_attr_param_inline_data_size,
#ifdef CONFIG_BLK_DEV_INTEGRITY
&nvmet_attr_param_pi_enable,
@@ -1782,6 +1896,14 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
return ERR_PTR(-ENOMEM);
}
+ if (IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS) && nvme_keyring_id()) {
+ port->keyring = key_lookup(nvme_keyring_id());
+ if (IS_ERR(port->keyring)) {
+ pr_warn("NVMe keyring not available, disabling TLS\n");
+ port->keyring = NULL;
+ }
+ }
+
for (i = 1; i <= NVMET_MAX_ANAGRPS; i++) {
if (i == NVMET_DEFAULT_ANA_GRPID)
port->ana_state[1] = NVME_ANA_OPTIMIZED;
diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c
index 1d9854484e..eb7785be0c 100644
--- a/drivers/nvme/target/fabrics-cmd-auth.c
+++ b/drivers/nvme/target/fabrics-cmd-auth.c
@@ -163,11 +163,11 @@ static u16 nvmet_auth_reply(struct nvmet_req *req, void *d)
pr_debug("%s: ctrl %d qid %d challenge %*ph\n",
__func__, ctrl->cntlid, req->sq->qid, data->hl,
req->sq->dhchap_c2);
- req->sq->dhchap_s2 = le32_to_cpu(data->seqnum);
} else {
req->sq->authenticated = true;
req->sq->dhchap_c2 = NULL;
}
+ req->sq->dhchap_s2 = le32_to_cpu(data->seqnum);
return 0;
}
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 1ab6601fdd..666130878e 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -111,6 +111,8 @@ struct nvmet_fc_tgtport {
struct nvmet_fc_port_entry *pe;
struct kref ref;
u32 max_sg_cnt;
+
+ struct work_struct put_work;
};
struct nvmet_fc_port_entry {
@@ -145,8 +147,8 @@ struct nvmet_fc_tgt_queue {
struct list_head avail_defer_list;
struct workqueue_struct *work_q;
struct kref ref;
- struct rcu_head rcu;
- struct nvmet_fc_fcp_iod fod[]; /* array of fcp_iods */
+ /* array of fcp_iods */
+ struct nvmet_fc_fcp_iod fod[] __counted_by(sqsize);
} __aligned(sizeof(unsigned long long));
struct nvmet_fc_hostport {
@@ -165,10 +167,9 @@ struct nvmet_fc_tgt_assoc {
struct nvmet_fc_hostport *hostport;
struct nvmet_fc_ls_iod *rcv_disconn;
struct list_head a_list;
- struct nvmet_fc_tgt_queue __rcu *queues[NVMET_NR_QUEUES + 1];
+ struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1];
struct kref ref;
struct work_struct del_work;
- struct rcu_head rcu;
};
@@ -248,6 +249,13 @@ static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue);
static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue);
static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport);
+static void nvmet_fc_put_tgtport_work(struct work_struct *work)
+{
+ struct nvmet_fc_tgtport *tgtport =
+ container_of(work, struct nvmet_fc_tgtport, put_work);
+
+ nvmet_fc_tgtport_put(tgtport);
+}
static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport);
static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
struct nvmet_fc_fcp_iod *fod);
@@ -359,7 +367,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
if (!lsop->req_queued) {
spin_unlock_irqrestore(&tgtport->lock, flags);
- return;
+ goto out_putwork;
}
list_del(&lsop->lsreq_list);
@@ -372,7 +380,8 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
(lsreq->rqstlen + lsreq->rsplen),
DMA_BIDIRECTIONAL);
- nvmet_fc_tgtport_put(tgtport);
+out_putwork:
+ queue_work(nvmet_wq, &tgtport->put_work);
}
static int
@@ -801,14 +810,11 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
if (!queue)
return NULL;
- if (!nvmet_fc_tgt_a_get(assoc))
- goto out_free_queue;
-
queue->work_q = alloc_workqueue("ntfc%d.%d.%d", 0, 0,
assoc->tgtport->fc_target_port.port_num,
assoc->a_id, qid);
if (!queue->work_q)
- goto out_a_put;
+ goto out_free_queue;
queue->qid = qid;
queue->sqsize = sqsize;
@@ -830,15 +836,13 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
goto out_fail_iodlist;
WARN_ON(assoc->queues[qid]);
- rcu_assign_pointer(assoc->queues[qid], queue);
+ assoc->queues[qid] = queue;
return queue;
out_fail_iodlist:
nvmet_fc_destroy_fcp_iodlist(assoc->tgtport, queue);
destroy_workqueue(queue->work_q);
-out_a_put:
- nvmet_fc_tgt_a_put(assoc);
out_free_queue:
kfree(queue);
return NULL;
@@ -851,15 +855,11 @@ nvmet_fc_tgt_queue_free(struct kref *ref)
struct nvmet_fc_tgt_queue *queue =
container_of(ref, struct nvmet_fc_tgt_queue, ref);
- rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL);
-
nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue);
- nvmet_fc_tgt_a_put(queue->assoc);
-
destroy_workqueue(queue->work_q);
- kfree_rcu(queue, rcu);
+ kfree(queue);
}
static void
@@ -968,7 +968,7 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport,
rcu_read_lock();
list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
if (association_id == assoc->association_id) {
- queue = rcu_dereference(assoc->queues[qid]);
+ queue = assoc->queues[qid];
if (queue &&
(!atomic_read(&queue->connected) ||
!nvmet_fc_tgt_q_get(queue)))
@@ -1077,8 +1077,6 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
/* new allocation not needed */
kfree(newhost);
newhost = match;
- /* no new allocation - release reference */
- nvmet_fc_tgtport_put(tgtport);
} else {
newhost->tgtport = tgtport;
newhost->hosthandle = hosthandle;
@@ -1093,13 +1091,28 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
}
static void
-nvmet_fc_delete_assoc(struct work_struct *work)
+nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+ nvmet_fc_delete_target_assoc(assoc);
+ nvmet_fc_tgt_a_put(assoc);
+}
+
+static void
+nvmet_fc_delete_assoc_work(struct work_struct *work)
{
struct nvmet_fc_tgt_assoc *assoc =
container_of(work, struct nvmet_fc_tgt_assoc, del_work);
+ struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
- nvmet_fc_delete_target_assoc(assoc);
- nvmet_fc_tgt_a_put(assoc);
+ nvmet_fc_delete_assoc(assoc);
+ nvmet_fc_tgtport_put(tgtport);
+}
+
+static void
+nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+ nvmet_fc_tgtport_get(assoc->tgtport);
+ queue_work(nvmet_wq, &assoc->del_work);
}
static struct nvmet_fc_tgt_assoc *
@@ -1111,6 +1124,9 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
int idx;
bool needrandom = true;
+ if (!tgtport->pe)
+ return NULL;
+
assoc = kzalloc(sizeof(*assoc), GFP_KERNEL);
if (!assoc)
return NULL;
@@ -1130,7 +1146,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
assoc->a_id = idx;
INIT_LIST_HEAD(&assoc->a_list);
kref_init(&assoc->ref);
- INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc);
+ INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work);
atomic_set(&assoc->terminating, 0);
while (needrandom) {
@@ -1171,13 +1187,18 @@ nvmet_fc_target_assoc_free(struct kref *ref)
struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
struct nvmet_fc_ls_iod *oldls;
unsigned long flags;
+ int i;
+
+ for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+ if (assoc->queues[i])
+ nvmet_fc_delete_target_queue(assoc->queues[i]);
+ }
/* Send Disconnect now that all i/o has completed */
nvmet_fc_xmt_disconnect_assoc(assoc);
nvmet_fc_free_hostport(assoc->hostport);
spin_lock_irqsave(&tgtport->lock, flags);
- list_del_rcu(&assoc->a_list);
oldls = assoc->rcv_disconn;
spin_unlock_irqrestore(&tgtport->lock, flags);
/* if pending Rcv Disconnect Association LS, send rsp now */
@@ -1187,8 +1208,8 @@ nvmet_fc_target_assoc_free(struct kref *ref)
dev_info(tgtport->dev,
"{%d:%d} Association freed\n",
tgtport->fc_target_port.port_num, assoc->a_id);
- kfree_rcu(assoc, rcu);
nvmet_fc_tgtport_put(tgtport);
+ kfree(assoc);
}
static void
@@ -1207,7 +1228,7 @@ static void
nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
{
struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
- struct nvmet_fc_tgt_queue *queue;
+ unsigned long flags;
int i, terminating;
terminating = atomic_xchg(&assoc->terminating, 1);
@@ -1216,29 +1237,21 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
if (terminating)
return;
+ spin_lock_irqsave(&tgtport->lock, flags);
+ list_del_rcu(&assoc->a_list);
+ spin_unlock_irqrestore(&tgtport->lock, flags);
- for (i = NVMET_NR_QUEUES; i >= 0; i--) {
- rcu_read_lock();
- queue = rcu_dereference(assoc->queues[i]);
- if (!queue) {
- rcu_read_unlock();
- continue;
- }
+ synchronize_rcu();
- if (!nvmet_fc_tgt_q_get(queue)) {
- rcu_read_unlock();
- continue;
- }
- rcu_read_unlock();
- nvmet_fc_delete_target_queue(queue);
- nvmet_fc_tgt_q_put(queue);
+ /* ensure all in-flight I/Os have been processed */
+ for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+ if (assoc->queues[i])
+ flush_workqueue(assoc->queues[i]->work_q);
}
dev_info(tgtport->dev,
"{%d:%d} Association deleted\n",
tgtport->fc_target_port.port_num, assoc->a_id);
-
- nvmet_fc_tgt_a_put(assoc);
}
static struct nvmet_fc_tgt_assoc *
@@ -1414,6 +1427,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
kref_init(&newrec->ref);
ida_init(&newrec->assoc_cnt);
newrec->max_sg_cnt = template->max_sgl_segments;
+ INIT_WORK(&newrec->put_work, nvmet_fc_put_tgtport_work);
ret = nvmet_fc_alloc_ls_iodlist(newrec);
if (ret) {
@@ -1491,9 +1505,8 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport)
list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
if (!nvmet_fc_tgt_a_get(assoc))
continue;
- if (!queue_work(nvmet_wq, &assoc->del_work))
- /* already deleting - release local reference */
- nvmet_fc_tgt_a_put(assoc);
+ nvmet_fc_schedule_delete_assoc(assoc);
+ nvmet_fc_tgt_a_put(assoc);
}
rcu_read_unlock();
}
@@ -1546,9 +1559,8 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
continue;
assoc->hostport->invalid = 1;
noassoc = false;
- if (!queue_work(nvmet_wq, &assoc->del_work))
- /* already deleting - release local reference */
- nvmet_fc_tgt_a_put(assoc);
+ nvmet_fc_schedule_delete_assoc(assoc);
+ nvmet_fc_tgt_a_put(assoc);
}
spin_unlock_irqrestore(&tgtport->lock, flags);
@@ -1580,7 +1592,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
rcu_read_lock();
list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
- queue = rcu_dereference(assoc->queues[0]);
+ queue = assoc->queues[0];
if (queue && queue->nvme_sq.ctrl == ctrl) {
if (nvmet_fc_tgt_a_get(assoc))
found_ctrl = true;
@@ -1592,9 +1604,8 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
nvmet_fc_tgtport_put(tgtport);
if (found_ctrl) {
- if (!queue_work(nvmet_wq, &assoc->del_work))
- /* already deleting - release local reference */
- nvmet_fc_tgt_a_put(assoc);
+ nvmet_fc_schedule_delete_assoc(assoc);
+ nvmet_fc_tgt_a_put(assoc);
return;
}
@@ -1624,6 +1635,8 @@ nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port)
/* terminate any outstanding associations */
__nvmet_fc_free_assocs(tgtport);
+ flush_workqueue(nvmet_wq);
+
/*
* should terminate LS's as well. However, LS's will be generated
* at the tail end of association termination, so they likely don't
@@ -1869,9 +1882,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
sizeof(struct fcnvme_ls_disconnect_assoc_acc)),
FCNVME_LS_DISCONNECT_ASSOC);
- /* release get taken in nvmet_fc_find_target_assoc */
- nvmet_fc_tgt_a_put(assoc);
-
/*
* The rules for LS response says the response cannot
* go back until ABTS's have been sent for all outstanding
@@ -1886,8 +1896,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
assoc->rcv_disconn = iod;
spin_unlock_irqrestore(&tgtport->lock, flags);
- nvmet_fc_delete_target_assoc(assoc);
-
if (oldls) {
dev_info(tgtport->dev,
"{%d:%d} Multiple Disconnect Association LS's "
@@ -1903,6 +1911,9 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
nvmet_fc_xmt_ls_rsp(tgtport, oldls);
}
+ nvmet_fc_schedule_delete_assoc(assoc);
+ nvmet_fc_tgt_a_put(assoc);
+
return false;
}
@@ -2539,8 +2550,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
fod->req.cmd = &fod->cmdiubuf.sqe;
fod->req.cqe = &fod->rspiubuf.cqe;
- if (tgtport->pe)
- fod->req.port = tgtport->pe->port;
+ if (!tgtport->pe)
+ goto transport_error;
+ fod->req.port = tgtport->pe->port;
/* clear any response payload */
memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));
@@ -2901,6 +2913,9 @@ nvmet_fc_remove_port(struct nvmet_port *port)
nvmet_fc_portentry_unbind(pe);
+ /* terminate any outstanding associations */
+ __nvmet_fc_free_assocs(pe->tgtport);
+
kfree(pe);
}
@@ -2932,6 +2947,9 @@ static int __init nvmet_fc_init_module(void)
static void __exit nvmet_fc_exit_module(void)
{
+ /* ensure any shutdown operation, e.g. delete ctrls have finished */
+ flush_workqueue(nvmet_wq);
+
/* sanity check - all lports should be removed */
if (!list_empty(&nvmet_fc_target_list))
pr_warn("%s: targetport list not empty\n", __func__);
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index c65a73433c..e6d4226827 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport,
if (!rport->targetport) {
tls_req->status = -ECONNREFUSED;
spin_lock(&rport->lock);
- list_add_tail(&rport->ls_list, &tls_req->ls_list);
+ list_add_tail(&tls_req->ls_list, &rport->ls_list);
spin_unlock(&rport->lock);
queue_work(nvmet_wq, &rport->ls_work);
return ret;
@@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport,
if (remoteport) {
rport = remoteport->private;
spin_lock(&rport->lock);
- list_add_tail(&rport->ls_list, &tls_req->ls_list);
+ list_add_tail(&tls_req->ls_list, &rport->ls_list);
spin_unlock(&rport->lock);
queue_work(nvmet_wq, &rport->ls_work);
}
@@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle,
if (!tport->remoteport) {
tls_req->status = -ECONNREFUSED;
spin_lock(&tport->lock);
- list_add_tail(&tport->ls_list, &tls_req->ls_list);
+ list_add_tail(&tls_req->ls_list, &tport->ls_list);
spin_unlock(&tport->lock);
queue_work(nvmet_wq, &tport->ls_work);
return ret;
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 468833675c..f11400a908 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -50,9 +50,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
{
- if (ns->bdev) {
- blkdev_put(ns->bdev, NULL);
+ if (ns->bdev_handle) {
+ bdev_release(ns->bdev_handle);
ns->bdev = NULL;
+ ns->bdev_handle = NULL;
}
}
@@ -84,17 +85,18 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
if (ns->buffered_io)
return -ENOTBLK;
- ns->bdev = blkdev_get_by_path(ns->device_path,
- BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
- if (IS_ERR(ns->bdev)) {
- ret = PTR_ERR(ns->bdev);
+ ns->bdev_handle = bdev_open_by_path(ns->device_path,
+ BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
+ if (IS_ERR(ns->bdev_handle)) {
+ ret = PTR_ERR(ns->bdev_handle);
if (ret != -ENOTBLK) {
- pr_err("failed to open block device %s: (%ld)\n",
- ns->device_path, PTR_ERR(ns->bdev));
+ pr_err("failed to open block device %s: (%d)\n",
+ ns->device_path, ret);
}
- ns->bdev = NULL;
+ ns->bdev_handle = NULL;
return ret;
}
+ ns->bdev = ns->bdev_handle->bdev;
ns->size = bdev_nr_bytes(ns->bdev);
ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 48d5df054c..9cb434c580 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -466,6 +466,8 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
out_destroy_io:
nvme_loop_destroy_io_queues(ctrl);
out_destroy_admin:
+ nvme_quiesce_admin_queue(&ctrl->ctrl);
+ nvme_cancel_admin_tagset(&ctrl->ctrl);
nvme_loop_destroy_admin_queue(ctrl);
out_disable:
dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
@@ -600,6 +602,8 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
return &ctrl->ctrl;
out_remove_admin_queue:
+ nvme_quiesce_admin_queue(&ctrl->ctrl);
+ nvme_cancel_admin_tagset(&ctrl->ctrl);
nvme_loop_destroy_admin_queue(ctrl);
out_free_queues:
kfree(ctrl->queues);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 8cfd60f3b5..6c8acebe1a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -58,6 +58,7 @@
struct nvmet_ns {
struct percpu_ref ref;
+ struct bdev_handle *bdev_handle;
struct block_device *bdev;
struct file *file;
bool readonly;
@@ -158,6 +159,7 @@ struct nvmet_port {
struct config_group ana_groups_group;
struct nvmet_ana_group ana_default_group;
enum nvme_ana_state *ana_state;
+ struct key *keyring;
void *priv;
bool enabled;
int inline_data_size;
@@ -178,6 +180,16 @@ static inline struct nvmet_port *ana_groups_to_port(
ana_groups_group);
}
+static inline u8 nvmet_port_disc_addr_treq_secure_channel(struct nvmet_port *port)
+{
+ return (port->disc_addr.treq & NVME_TREQ_SECURE_CHANNEL_MASK);
+}
+
+static inline bool nvmet_port_secure_channel_required(struct nvmet_port *port)
+{
+ return nvmet_port_disc_addr_treq_secure_channel(port) == NVMF_TREQ_REQUIRED;
+}
+
struct nvmet_ctrl {
struct nvmet_subsys *subsys;
struct nvmet_sq **sqs;
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index a4f802790c..bb42ae42b1 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -8,9 +8,14 @@
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/err.h>
+#include <linux/key.h>
#include <linux/nvme-tcp.h>
+#include <linux/nvme-keyring.h>
#include <net/sock.h>
#include <net/tcp.h>
+#include <net/tls.h>
+#include <net/tls_prot.h>
+#include <net/handshake.h>
#include <linux/inet.h>
#include <linux/llist.h>
#include <crypto/hash.h>
@@ -67,6 +72,16 @@ device_param_cb(idle_poll_period_usecs, &set_param_ops,
MODULE_PARM_DESC(idle_poll_period_usecs,
"nvmet tcp io_work poll till idle time period in usecs: Default 0");
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
+/*
+ * TLS handshake timeout
+ */
+static int tls_handshake_timeout = 10;
+module_param(tls_handshake_timeout, int, 0644);
+MODULE_PARM_DESC(tls_handshake_timeout,
+ "nvme TLS handshake timeout in seconds (default 10)");
+#endif
+
#define NVMET_TCP_RECV_BUDGET 8
#define NVMET_TCP_SEND_BUDGET 8
#define NVMET_TCP_IO_WORK_BUDGET 64
@@ -105,6 +120,7 @@ struct nvmet_tcp_cmd {
u32 pdu_len;
u32 pdu_recv;
int sg_idx;
+ char recv_cbuf[CMSG_LEN(sizeof(char))];
struct msghdr recv_msg;
struct bio_vec *iov;
u32 flags;
@@ -123,8 +139,10 @@ struct nvmet_tcp_cmd {
enum nvmet_tcp_queue_state {
NVMET_TCP_Q_CONNECTING,
+ NVMET_TCP_Q_TLS_HANDSHAKE,
NVMET_TCP_Q_LIVE,
NVMET_TCP_Q_DISCONNECTING,
+ NVMET_TCP_Q_FAILED,
};
struct nvmet_tcp_queue {
@@ -133,6 +151,7 @@ struct nvmet_tcp_queue {
struct work_struct io_work;
struct nvmet_cq nvme_cq;
struct nvmet_sq nvme_sq;
+ struct kref kref;
/* send state */
struct nvmet_tcp_cmd *cmds;
@@ -156,6 +175,10 @@ struct nvmet_tcp_queue {
struct ahash_request *snd_hash;
struct ahash_request *rcv_hash;
+ /* TLS state */
+ key_serial_t tls_pskid;
+ struct delayed_work tls_handshake_tmo_work;
+
unsigned long poll_end;
spinlock_t state_lock;
@@ -911,8 +934,10 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
iov.iov_base = icresp;
iov.iov_len = sizeof(*icresp);
ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
- if (ret < 0)
+ if (ret < 0) {
+ queue->state = NVMET_TCP_Q_FAILED;
return ret; /* queue removal will cleanup */
+ }
queue->state = NVMET_TCP_Q_LIVE;
nvmet_prepare_receive_pdu(queue);
@@ -1110,20 +1135,65 @@ static inline bool nvmet_tcp_pdu_valid(u8 type)
return false;
}
+static int nvmet_tcp_tls_record_ok(struct nvmet_tcp_queue *queue,
+ struct msghdr *msg, char *cbuf)
+{
+ struct cmsghdr *cmsg = (struct cmsghdr *)cbuf;
+ u8 ctype, level, description;
+ int ret = 0;
+
+ ctype = tls_get_record_type(queue->sock->sk, cmsg);
+ switch (ctype) {
+ case 0:
+ break;
+ case TLS_RECORD_TYPE_DATA:
+ break;
+ case TLS_RECORD_TYPE_ALERT:
+ tls_alert_recv(queue->sock->sk, msg, &level, &description);
+ if (level == TLS_ALERT_LEVEL_FATAL) {
+ pr_err("queue %d: TLS Alert desc %u\n",
+ queue->idx, description);
+ ret = -ENOTCONN;
+ } else {
+ pr_warn("queue %d: TLS Alert desc %u\n",
+ queue->idx, description);
+ ret = -EAGAIN;
+ }
+ break;
+ default:
+ /* discard this record type */
+ pr_err("queue %d: TLS record %d unhandled\n",
+ queue->idx, ctype);
+ ret = -EAGAIN;
+ break;
+ }
+ return ret;
+}
+
static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue)
{
struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
- int len;
+ int len, ret;
struct kvec iov;
+ char cbuf[CMSG_LEN(sizeof(char))] = {};
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
recv:
iov.iov_base = (void *)&queue->pdu + queue->offset;
iov.iov_len = queue->left;
+ if (queue->tls_pskid) {
+ msg.msg_control = cbuf;
+ msg.msg_controllen = sizeof(cbuf);
+ }
len = kernel_recvmsg(queue->sock, &msg, &iov, 1,
iov.iov_len, msg.msg_flags);
if (unlikely(len < 0))
return len;
+ if (queue->tls_pskid) {
+ ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf);
+ if (ret < 0)
+ return ret;
+ }
queue->offset += len;
queue->left -= len;
@@ -1176,16 +1246,22 @@ static void nvmet_tcp_prep_recv_ddgst(struct nvmet_tcp_cmd *cmd)
static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue)
{
struct nvmet_tcp_cmd *cmd = queue->cmd;
- int ret;
+ int len, ret;
while (msg_data_left(&cmd->recv_msg)) {
- ret = sock_recvmsg(cmd->queue->sock, &cmd->recv_msg,
+ len = sock_recvmsg(cmd->queue->sock, &cmd->recv_msg,
cmd->recv_msg.msg_flags);
- if (ret <= 0)
- return ret;
+ if (len <= 0)
+ return len;
+ if (queue->tls_pskid) {
+ ret = nvmet_tcp_tls_record_ok(cmd->queue,
+ &cmd->recv_msg, cmd->recv_cbuf);
+ if (ret < 0)
+ return ret;
+ }
- cmd->pdu_recv += ret;
- cmd->rbytes_done += ret;
+ cmd->pdu_recv += len;
+ cmd->rbytes_done += len;
}
if (queue->data_digest) {
@@ -1203,20 +1279,30 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue)
static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue)
{
struct nvmet_tcp_cmd *cmd = queue->cmd;
- int ret;
+ int ret, len;
+ char cbuf[CMSG_LEN(sizeof(char))] = {};
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
struct kvec iov = {
.iov_base = (void *)&cmd->recv_ddgst + queue->offset,
.iov_len = queue->left
};
- ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
+ if (queue->tls_pskid) {
+ msg.msg_control = cbuf;
+ msg.msg_controllen = sizeof(cbuf);
+ }
+ len = kernel_recvmsg(queue->sock, &msg, &iov, 1,
iov.iov_len, msg.msg_flags);
- if (unlikely(ret < 0))
- return ret;
+ if (unlikely(len < 0))
+ return len;
+ if (queue->tls_pskid) {
+ ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf);
+ if (ret < 0)
+ return ret;
+ }
- queue->offset += ret;
- queue->left -= ret;
+ queue->offset += len;
+ queue->left -= len;
if (queue->left)
return -EAGAIN;
@@ -1294,14 +1380,27 @@ done:
return ret;
}
+static void nvmet_tcp_release_queue(struct kref *kref)
+{
+ struct nvmet_tcp_queue *queue =
+ container_of(kref, struct nvmet_tcp_queue, kref);
+
+ WARN_ON(queue->state != NVMET_TCP_Q_DISCONNECTING);
+ queue_work(nvmet_wq, &queue->release_work);
+}
+
static void nvmet_tcp_schedule_release_queue(struct nvmet_tcp_queue *queue)
{
- spin_lock(&queue->state_lock);
+ spin_lock_bh(&queue->state_lock);
+ if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
+ /* Socket closed during handshake */
+ tls_handshake_cancel(queue->sock->sk);
+ }
if (queue->state != NVMET_TCP_Q_DISCONNECTING) {
queue->state = NVMET_TCP_Q_DISCONNECTING;
- queue_work(nvmet_wq, &queue->release_work);
+ kref_put(&queue->kref, nvmet_tcp_release_queue);
}
- spin_unlock(&queue->state_lock);
+ spin_unlock_bh(&queue->state_lock);
}
static inline void nvmet_tcp_arm_queue_deadline(struct nvmet_tcp_queue *queue)
@@ -1383,6 +1482,10 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
if (!c->r2t_pdu)
goto out_free_data;
+ if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
+ c->recv_msg.msg_control = c->recv_cbuf;
+ c->recv_msg.msg_controllen = sizeof(c->recv_cbuf);
+ }
c->recv_msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
list_add_tail(&c->entry, &queue->free_list);
@@ -1496,6 +1599,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
mutex_unlock(&nvmet_tcp_queue_mutex);
nvmet_tcp_restore_socket_callbacks(queue);
+ cancel_delayed_work_sync(&queue->tls_handshake_tmo_work);
cancel_work_sync(&queue->io_work);
/* stop accepting incoming data */
queue->rcv_state = NVMET_TCP_RECV_ERR;
@@ -1504,12 +1608,12 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
nvmet_sq_destroy(&queue->nvme_sq);
cancel_work_sync(&queue->io_work);
nvmet_tcp_free_cmd_data_in_buffers(queue);
- sock_release(queue->sock);
+ /* ->sock will be released by fput() */
+ fput(queue->sock->file);
nvmet_tcp_free_cmds(queue);
if (queue->hdr_digest || queue->data_digest)
nvmet_tcp_free_crypto(queue);
ida_free(&nvmet_tcp_queue_ida, queue->idx);
-
page = virt_to_head_page(queue->pf_cache.va);
__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
kfree(queue);
@@ -1523,8 +1627,13 @@ static void nvmet_tcp_data_ready(struct sock *sk)
read_lock_bh(&sk->sk_callback_lock);
queue = sk->sk_user_data;
- if (likely(queue))
- queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
+ if (likely(queue)) {
+ if (queue->data_ready)
+ queue->data_ready(sk);
+ if (queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)
+ queue_work_on(queue_cpu(queue), nvmet_tcp_wq,
+ &queue->io_work);
+ }
read_unlock_bh(&sk->sk_callback_lock);
}
@@ -1632,31 +1741,176 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
return ret;
}
-static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
+static int nvmet_tcp_try_peek_pdu(struct nvmet_tcp_queue *queue)
+{
+ struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr;
+ int len, ret;
+ struct kvec iov = {
+ .iov_base = (u8 *)&queue->pdu + queue->offset,
+ .iov_len = sizeof(struct nvme_tcp_hdr),
+ };
+ char cbuf[CMSG_LEN(sizeof(char))] = {};
+ struct msghdr msg = {
+ .msg_control = cbuf,
+ .msg_controllen = sizeof(cbuf),
+ .msg_flags = MSG_PEEK,
+ };
+
+ if (nvmet_port_secure_channel_required(queue->port->nport))
+ return 0;
+
+ len = kernel_recvmsg(queue->sock, &msg, &iov, 1,
+ iov.iov_len, msg.msg_flags);
+ if (unlikely(len < 0)) {
+ pr_debug("queue %d: peek error %d\n",
+ queue->idx, len);
+ return len;
+ }
+
+ ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf);
+ if (ret < 0)
+ return ret;
+
+ if (len < sizeof(struct nvme_tcp_hdr)) {
+ pr_debug("queue %d: short read, %d bytes missing\n",
+ queue->idx, (int)iov.iov_len - len);
+ return -EAGAIN;
+ }
+ pr_debug("queue %d: hdr type %d hlen %d plen %d size %d\n",
+ queue->idx, hdr->type, hdr->hlen, hdr->plen,
+ (int)sizeof(struct nvme_tcp_icreq_pdu));
+ if (hdr->type == nvme_tcp_icreq &&
+ hdr->hlen == sizeof(struct nvme_tcp_icreq_pdu) &&
+ hdr->plen == cpu_to_le32(sizeof(struct nvme_tcp_icreq_pdu))) {
+ pr_debug("queue %d: icreq detected\n",
+ queue->idx);
+ return len;
+ }
+ return 0;
+}
+
+static void nvmet_tcp_tls_handshake_done(void *data, int status,
+ key_serial_t peerid)
+{
+ struct nvmet_tcp_queue *queue = data;
+
+ pr_debug("queue %d: TLS handshake done, key %x, status %d\n",
+ queue->idx, peerid, status);
+ spin_lock_bh(&queue->state_lock);
+ if (WARN_ON(queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)) {
+ spin_unlock_bh(&queue->state_lock);
+ return;
+ }
+ if (!status) {
+ queue->tls_pskid = peerid;
+ queue->state = NVMET_TCP_Q_CONNECTING;
+ } else
+ queue->state = NVMET_TCP_Q_FAILED;
+ spin_unlock_bh(&queue->state_lock);
+
+ cancel_delayed_work_sync(&queue->tls_handshake_tmo_work);
+ if (status)
+ nvmet_tcp_schedule_release_queue(queue);
+ else
+ nvmet_tcp_set_queue_sock(queue);
+ kref_put(&queue->kref, nvmet_tcp_release_queue);
+}
+
+static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w)
+{
+ struct nvmet_tcp_queue *queue = container_of(to_delayed_work(w),
+ struct nvmet_tcp_queue, tls_handshake_tmo_work);
+
+ pr_warn("queue %d: TLS handshake timeout\n", queue->idx);
+ /*
+ * If tls_handshake_cancel() fails we've lost the race with
+ * nvmet_tcp_tls_handshake_done() */
+ if (!tls_handshake_cancel(queue->sock->sk))
+ return;
+ spin_lock_bh(&queue->state_lock);
+ if (WARN_ON(queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)) {
+ spin_unlock_bh(&queue->state_lock);
+ return;
+ }
+ queue->state = NVMET_TCP_Q_FAILED;
+ spin_unlock_bh(&queue->state_lock);
+ nvmet_tcp_schedule_release_queue(queue);
+ kref_put(&queue->kref, nvmet_tcp_release_queue);
+}
+
+static int nvmet_tcp_tls_handshake(struct nvmet_tcp_queue *queue)
+{
+ int ret = -EOPNOTSUPP;
+ struct tls_handshake_args args;
+
+ if (queue->state != NVMET_TCP_Q_TLS_HANDSHAKE) {
+ pr_warn("cannot start TLS in state %d\n", queue->state);
+ return -EINVAL;
+ }
+
+ kref_get(&queue->kref);
+ pr_debug("queue %d: TLS ServerHello\n", queue->idx);
+ memset(&args, 0, sizeof(args));
+ args.ta_sock = queue->sock;
+ args.ta_done = nvmet_tcp_tls_handshake_done;
+ args.ta_data = queue;
+ args.ta_keyring = key_serial(queue->port->nport->keyring);
+ args.ta_timeout_ms = tls_handshake_timeout * 1000;
+
+ ret = tls_server_hello_psk(&args, GFP_KERNEL);
+ if (ret) {
+ kref_put(&queue->kref, nvmet_tcp_release_queue);
+ pr_err("failed to start TLS, err=%d\n", ret);
+ } else {
+ queue_delayed_work(nvmet_wq, &queue->tls_handshake_tmo_work,
+ tls_handshake_timeout * HZ);
+ }
+ return ret;
+}
+#else
+static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w) {}
+#endif
+
+static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
struct socket *newsock)
{
struct nvmet_tcp_queue *queue;
+ struct file *sock_file = NULL;
int ret;
queue = kzalloc(sizeof(*queue), GFP_KERNEL);
- if (!queue)
- return -ENOMEM;
+ if (!queue) {
+ ret = -ENOMEM;
+ goto out_release;
+ }
INIT_WORK(&queue->release_work, nvmet_tcp_release_queue_work);
INIT_WORK(&queue->io_work, nvmet_tcp_io_work);
+ kref_init(&queue->kref);
queue->sock = newsock;
queue->port = port;
queue->nr_cmds = 0;
spin_lock_init(&queue->state_lock);
- queue->state = NVMET_TCP_Q_CONNECTING;
+ if (queue->port->nport->disc_addr.tsas.tcp.sectype ==
+ NVMF_TCP_SECTYPE_TLS13)
+ queue->state = NVMET_TCP_Q_TLS_HANDSHAKE;
+ else
+ queue->state = NVMET_TCP_Q_CONNECTING;
INIT_LIST_HEAD(&queue->free_list);
init_llist_head(&queue->resp_list);
INIT_LIST_HEAD(&queue->resp_send_list);
+ sock_file = sock_alloc_file(queue->sock, O_CLOEXEC, NULL);
+ if (IS_ERR(sock_file)) {
+ ret = PTR_ERR(sock_file);
+ goto out_free_queue;
+ }
+
queue->idx = ida_alloc(&nvmet_tcp_queue_ida, GFP_KERNEL);
if (queue->idx < 0) {
ret = queue->idx;
- goto out_free_queue;
+ goto out_sock;
}
ret = nvmet_tcp_alloc_cmd(queue, &queue->connect);
@@ -1673,11 +1927,33 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
list_add_tail(&queue->queue_list, &nvmet_tcp_queue_list);
mutex_unlock(&nvmet_tcp_queue_mutex);
+ INIT_DELAYED_WORK(&queue->tls_handshake_tmo_work,
+ nvmet_tcp_tls_handshake_timeout);
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
+ if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
+ struct sock *sk = queue->sock->sk;
+
+ /* Restore the default callbacks before starting upcall */
+ read_lock_bh(&sk->sk_callback_lock);
+ sk->sk_user_data = NULL;
+ sk->sk_data_ready = port->data_ready;
+ read_unlock_bh(&sk->sk_callback_lock);
+ if (!nvmet_tcp_try_peek_pdu(queue)) {
+ if (!nvmet_tcp_tls_handshake(queue))
+ return;
+ /* TLS handshake failed, terminate the connection */
+ goto out_destroy_sq;
+ }
+ /* Not a TLS connection, continue with normal processing */
+ queue->state = NVMET_TCP_Q_CONNECTING;
+ }
+#endif
+
ret = nvmet_tcp_set_queue_sock(queue);
if (ret)
goto out_destroy_sq;
- return 0;
+ return;
out_destroy_sq:
mutex_lock(&nvmet_tcp_queue_mutex);
list_del_init(&queue->queue_list);
@@ -1687,9 +1963,14 @@ out_free_connect:
nvmet_tcp_free_cmd(&queue->connect);
out_ida_remove:
ida_free(&nvmet_tcp_queue_ida, queue->idx);
+out_sock:
+ fput(queue->sock->file);
out_free_queue:
kfree(queue);
- return ret;
+out_release:
+ pr_err("failed to allocate queue, error %d\n", ret);
+ if (!sock_file)
+ sock_release(newsock);
}
static void nvmet_tcp_accept_work(struct work_struct *w)
@@ -1706,11 +1987,7 @@ static void nvmet_tcp_accept_work(struct work_struct *w)
pr_warn("failed to accept err=%d\n", ret);
return;
}
- ret = nvmet_tcp_alloc_queue(port, newsock);
- if (ret) {
- pr_err("failed to allocate queue\n");
- sock_release(newsock);
- }
+ nvmet_tcp_alloc_queue(port, newsock);
}
}
@@ -1927,6 +2204,7 @@ static void __exit nvmet_tcp_exit(void)
flush_workqueue(nvmet_wq);
destroy_workqueue(nvmet_tcp_wq);
+ ida_destroy(&nvmet_tcp_queue_ida);
}
module_init(nvmet_tcp_init);