summaryrefslogtreecommitdiff
path: root/drivers/nvme
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/common/auth.c2
-rw-r--r--drivers/nvme/common/keyring.c58
-rw-r--r--drivers/nvme/host/Kconfig4
-rw-r--r--drivers/nvme/host/apple.c101
-rw-r--r--drivers/nvme/host/auth.c8
-rw-r--r--drivers/nvme/host/constants.c2
-rw-r--r--drivers/nvme/host/core.c1170
-rw-r--r--drivers/nvme/host/fabrics.c108
-rw-r--r--drivers/nvme/host/fabrics.h10
-rw-r--r--drivers/nvme/host/fault_inject.c3
-rw-r--r--drivers/nvme/host/fc.c132
-rw-r--r--drivers/nvme/host/hwmon.c2
-rw-r--r--drivers/nvme/host/ioctl.c98
-rw-r--r--drivers/nvme/host/multipath.c245
-rw-r--r--drivers/nvme/host/nvme.h160
-rw-r--r--drivers/nvme/host/pci.c476
-rw-r--r--drivers/nvme/host/pr.c131
-rw-r--r--drivers/nvme/host/rdma.c97
-rw-r--r--drivers/nvme/host/sysfs.c104
-rw-r--r--drivers/nvme/host/tcp.c341
-rw-r--r--drivers/nvme/host/trace.c153
-rw-r--r--drivers/nvme/host/zns.c40
-rw-r--r--drivers/nvme/target/Kconfig21
-rw-r--r--drivers/nvme/target/Makefile5
-rw-r--r--drivers/nvme/target/admin-cmd.c732
-rw-r--r--drivers/nvme/target/auth.c61
-rw-r--r--drivers/nvme/target/configfs.c229
-rw-r--r--drivers/nvme/target/core.c499
-rw-r--r--drivers/nvme/target/debugfs.c202
-rw-r--r--drivers/nvme/target/debugfs.h42
-rw-r--r--drivers/nvme/target/discovery.c33
-rw-r--r--drivers/nvme/target/fabrics-cmd-auth.c82
-rw-r--r--drivers/nvme/target/fabrics-cmd.c144
-rw-r--r--drivers/nvme/target/fc.c52
-rw-r--r--drivers/nvme/target/fcloop.c28
-rw-r--r--drivers/nvme/target/io-cmd-bdev.c49
-rw-r--r--drivers/nvme/target/loop.c18
-rw-r--r--drivers/nvme/target/nvmet.h208
-rw-r--r--drivers/nvme/target/passthru.c44
-rw-r--r--drivers/nvme/target/pci-epf.c2610
-rw-r--r--drivers/nvme/target/pr.c1155
-rw-r--r--drivers/nvme/target/rdma.c167
-rw-r--r--drivers/nvme/target/tcp.c53
-rw-r--r--drivers/nvme/target/trace.c208
-rw-r--r--drivers/nvme/target/zns.c65
45 files changed, 8531 insertions, 1621 deletions
diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c
index a3455f1d67fa..9b7126e1a19d 100644
--- a/drivers/nvme/common/auth.c
+++ b/drivers/nvme/common/auth.c
@@ -8,7 +8,7 @@
#include <linux/base64.h>
#include <linux/prandom.h>
#include <linux/scatterlist.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/hash.h>
#include <crypto/dh.h>
#include <linux/nvme.h>
diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c
index 6f7e7a8fa5ae..ed5167f942d8 100644
--- a/drivers/nvme/common/keyring.c
+++ b/drivers/nvme/common/keyring.c
@@ -20,6 +20,28 @@ key_serial_t nvme_keyring_id(void)
}
EXPORT_SYMBOL_GPL(nvme_keyring_id);
+static bool nvme_tls_psk_revoked(struct key *psk)
+{
+ return test_bit(KEY_FLAG_REVOKED, &psk->flags) ||
+ test_bit(KEY_FLAG_INVALIDATED, &psk->flags);
+}
+
+struct key *nvme_tls_key_lookup(key_serial_t key_id)
+{
+ struct key *key = key_lookup(key_id);
+
+ if (IS_ERR(key)) {
+ pr_err("key id %08x not found\n", key_id);
+ return key;
+ }
+ if (nvme_tls_psk_revoked(key)) {
+ pr_err("key id %08x revoked\n", key_id);
+ return ERR_PTR(-EKEYREVOKED);
+ }
+ return key;
+}
+EXPORT_SYMBOL_GPL(nvme_tls_key_lookup);
+
static void nvme_tls_psk_describe(const struct key *key, struct seq_file *m)
{
seq_puts(m, key->description);
@@ -36,14 +58,12 @@ static bool nvme_tls_psk_match(const struct key *key,
pr_debug("%s: no key description\n", __func__);
return false;
}
- match_len = strlen(key->description);
- pr_debug("%s: id %s len %zd\n", __func__, key->description, match_len);
-
if (!match_data->raw_data) {
pr_debug("%s: no match data\n", __func__);
return false;
}
match_id = match_data->raw_data;
+ match_len = strlen(match_id);
pr_debug("%s: match '%s' '%s' len %zd\n",
__func__, match_id, key->description, match_len);
return !memcmp(key->description, match_id, match_len);
@@ -71,7 +91,7 @@ static struct key_type nvme_tls_psk_key_type = {
static struct key *nvme_tls_psk_lookup(struct key *keyring,
const char *hostnqn, const char *subnqn,
- int hmac, bool generated)
+ u8 hmac, u8 psk_ver, bool generated)
{
char *identity;
size_t identity_len = (NVMF_NQN_SIZE) * 2 + 11;
@@ -82,8 +102,8 @@ static struct key *nvme_tls_psk_lookup(struct key *keyring,
if (!identity)
return ERR_PTR(-ENOMEM);
- snprintf(identity, identity_len, "NVMe0%c%02d %s %s",
- generated ? 'G' : 'R', hmac, hostnqn, subnqn);
+ snprintf(identity, identity_len, "NVMe%u%c%02u %s %s",
+ psk_ver, generated ? 'G' : 'R', hmac, hostnqn, subnqn);
if (!keyring)
keyring = nvme_keyring;
@@ -107,21 +127,38 @@ static struct key *nvme_tls_psk_lookup(struct key *keyring,
/*
* NVMe PSK priority list
*
- * 'Retained' PSKs (ie 'generated == false')
- * should be preferred to 'generated' PSKs,
- * and SHA-384 should be preferred to SHA-256.
+ * 'Retained' PSKs (ie 'generated == false') should be preferred to 'generated'
+ * PSKs, PSKs with hash (psk_ver 1) should be preferred to PSKs without hash
+ * (psk_ver 0), and SHA-384 should be preferred to SHA-256.
*/
static struct nvme_tls_psk_priority_list {
bool generated;
+ u8 psk_ver;
enum nvme_tcp_tls_cipher cipher;
} nvme_tls_psk_prio[] = {
{ .generated = false,
+ .psk_ver = 1,
+ .cipher = NVME_TCP_TLS_CIPHER_SHA384, },
+ { .generated = false,
+ .psk_ver = 1,
+ .cipher = NVME_TCP_TLS_CIPHER_SHA256, },
+ { .generated = false,
+ .psk_ver = 0,
.cipher = NVME_TCP_TLS_CIPHER_SHA384, },
{ .generated = false,
+ .psk_ver = 0,
+ .cipher = NVME_TCP_TLS_CIPHER_SHA256, },
+ { .generated = true,
+ .psk_ver = 1,
+ .cipher = NVME_TCP_TLS_CIPHER_SHA384, },
+ { .generated = true,
+ .psk_ver = 1,
.cipher = NVME_TCP_TLS_CIPHER_SHA256, },
{ .generated = true,
+ .psk_ver = 0,
.cipher = NVME_TCP_TLS_CIPHER_SHA384, },
{ .generated = true,
+ .psk_ver = 0,
.cipher = NVME_TCP_TLS_CIPHER_SHA256, },
};
@@ -137,10 +174,11 @@ key_serial_t nvme_tls_psk_default(struct key *keyring,
for (prio = 0; prio < ARRAY_SIZE(nvme_tls_psk_prio); prio++) {
bool generated = nvme_tls_psk_prio[prio].generated;
+ u8 ver = nvme_tls_psk_prio[prio].psk_ver;
enum nvme_tcp_tls_cipher cipher = nvme_tls_psk_prio[prio].cipher;
tls_key = nvme_tls_psk_lookup(keyring, hostnqn, subnqn,
- cipher, generated);
+ cipher, ver, generated);
if (!IS_ERR(tls_key)) {
tls_key_id = tls_key->serial;
key_put(tls_key);
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index b309c8be720f..486afe598184 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
config NVME_CORE
tristate
- select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
config BLK_DEV_NVME
tristate "NVM Express block device"
@@ -42,6 +41,7 @@ config NVME_HWMON
config NVME_FABRICS
select NVME_CORE
+ select NVME_KEYRING if NVME_TCP_TLS
tristate
config NVME_RDMA
@@ -95,7 +95,6 @@ config NVME_TCP
config NVME_TCP_TLS
bool "NVMe over Fabrics TCP TLS encryption support"
depends on NVME_TCP
- select NVME_KEYRING
select NET_HANDSHAKE
select KEYS
help
@@ -110,6 +109,7 @@ config NVME_HOST_AUTH
bool "NVMe over Fabrics In-Band Authentication in host side"
depends on NVME_CORE
select NVME_AUTH
+ select NVME_KEYRING if NVME_TCP_TLS
help
This provides support for NVMe over Fabrics In-Band Authentication in
host side.
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index c727cd1f264b..8971aca41e63 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -599,7 +599,8 @@ static inline void apple_nvme_handle_cqe(struct apple_nvme_queue *q,
}
if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
- !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
+ !blk_mq_add_to_batch(req, iob,
+ nvme_req(req)->status != NVME_SC_SUCCESS,
apple_nvme_complete_batch))
apple_nvme_complete_rq(req);
}
@@ -649,7 +650,7 @@ static bool apple_nvme_handle_cq(struct apple_nvme_queue *q, bool force)
found = apple_nvme_poll_cq(q, &iob);
- if (!rq_list_empty(iob.req_list))
+ if (!rq_list_empty(&iob.req_list))
apple_nvme_complete_batch(&iob);
return found;
@@ -1011,25 +1012,37 @@ static void apple_nvme_reset_work(struct work_struct *work)
ret = apple_rtkit_shutdown(anv->rtk);
if (ret)
goto out;
+
+ writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
}
- writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+ /*
+ * Only do the soft-reset if the CPU is not running, which means either we
+ * or the previous stage shut it down cleanly.
+ */
+ if (!(readl(anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL) &
+ APPLE_ANS_COPROC_CPU_CONTROL_RUN)) {
- ret = reset_control_assert(anv->reset);
- if (ret)
- goto out;
+ ret = reset_control_assert(anv->reset);
+ if (ret)
+ goto out;
- ret = apple_rtkit_reinit(anv->rtk);
- if (ret)
- goto out;
+ ret = apple_rtkit_reinit(anv->rtk);
+ if (ret)
+ goto out;
- ret = reset_control_deassert(anv->reset);
- if (ret)
- goto out;
+ ret = reset_control_deassert(anv->reset);
+ if (ret)
+ goto out;
+
+ writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN,
+ anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+
+ ret = apple_rtkit_boot(anv->rtk);
+ } else {
+ ret = apple_rtkit_wake(anv->rtk);
+ }
- writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN,
- anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
- ret = apple_rtkit_boot(anv->rtk);
if (ret) {
dev_err(anv->dev, "ANS did not boot");
goto out;
@@ -1251,7 +1264,6 @@ static int apple_nvme_alloc_tagsets(struct apple_nvme *anv)
anv->admin_tagset.timeout = NVME_ADMIN_TIMEOUT;
anv->admin_tagset.numa_node = NUMA_NO_NODE;
anv->admin_tagset.cmd_size = sizeof(struct apple_nvme_iod);
- anv->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
anv->admin_tagset.driver_data = &anv->adminq;
ret = blk_mq_alloc_tag_set(&anv->admin_tagset);
@@ -1275,7 +1287,6 @@ static int apple_nvme_alloc_tagsets(struct apple_nvme *anv)
anv->tagset.timeout = NVME_IO_TIMEOUT;
anv->tagset.numa_node = NUMA_NO_NODE;
anv->tagset.cmd_size = sizeof(struct apple_nvme_iod);
- anv->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
anv->tagset.driver_data = &anv->ioq;
ret = blk_mq_alloc_tag_set(&anv->tagset);
@@ -1388,7 +1399,7 @@ static void devm_apple_nvme_mempool_destroy(void *data)
mempool_destroy(data);
}
-static int apple_nvme_probe(struct platform_device *pdev)
+static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct apple_nvme *anv;
@@ -1396,7 +1407,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
anv = devm_kzalloc(dev, sizeof(*anv), GFP_KERNEL);
if (!anv)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
anv->dev = get_device(dev);
anv->adminq.is_adminq = true;
@@ -1516,10 +1527,31 @@ static int apple_nvme_probe(struct platform_device *pdev)
goto put_dev;
}
- anv->ctrl.admin_q = blk_mq_init_queue(&anv->admin_tagset);
+ return anv;
+put_dev:
+ apple_nvme_detach_genpd(anv);
+ put_device(anv->dev);
+ return ERR_PTR(ret);
+}
+
+static int apple_nvme_probe(struct platform_device *pdev)
+{
+ struct apple_nvme *anv;
+ int ret;
+
+ anv = apple_nvme_alloc(pdev);
+ if (IS_ERR(anv))
+ return PTR_ERR(anv);
+
+ ret = nvme_add_ctrl(&anv->ctrl);
+ if (ret)
+ goto out_put_ctrl;
+
+ anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL);
if (IS_ERR(anv->ctrl.admin_q)) {
ret = -ENOMEM;
- goto put_dev;
+ anv->ctrl.admin_q = NULL;
+ goto out_uninit_ctrl;
}
nvme_reset_ctrl(&anv->ctrl);
@@ -1527,12 +1559,15 @@ static int apple_nvme_probe(struct platform_device *pdev)
return 0;
-put_dev:
- put_device(anv->dev);
+out_uninit_ctrl:
+ nvme_uninit_ctrl(&anv->ctrl);
+out_put_ctrl:
+ nvme_put_ctrl(&anv->ctrl);
+ apple_nvme_detach_genpd(anv);
return ret;
}
-static int apple_nvme_remove(struct platform_device *pdev)
+static void apple_nvme_remove(struct platform_device *pdev)
{
struct apple_nvme *anv = platform_get_drvdata(pdev);
@@ -1543,12 +1578,13 @@ static int apple_nvme_remove(struct platform_device *pdev)
apple_nvme_disable(anv, true);
nvme_uninit_ctrl(&anv->ctrl);
- if (apple_rtkit_is_running(anv->rtk))
+ if (apple_rtkit_is_running(anv->rtk)) {
apple_rtkit_shutdown(anv->rtk);
- apple_nvme_detach_genpd(anv);
+ writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+ }
- return 0;
+ apple_nvme_detach_genpd(anv);
}
static void apple_nvme_shutdown(struct platform_device *pdev)
@@ -1556,8 +1592,11 @@ static void apple_nvme_shutdown(struct platform_device *pdev)
struct apple_nvme *anv = platform_get_drvdata(pdev);
apple_nvme_disable(anv, true);
- if (apple_rtkit_is_running(anv->rtk))
+ if (apple_rtkit_is_running(anv->rtk)) {
apple_rtkit_shutdown(anv->rtk);
+
+ writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+ }
}
static int apple_nvme_resume(struct device *dev)
@@ -1574,10 +1613,11 @@ static int apple_nvme_suspend(struct device *dev)
apple_nvme_disable(anv, true);
- if (apple_rtkit_is_running(anv->rtk))
+ if (apple_rtkit_is_running(anv->rtk)) {
ret = apple_rtkit_shutdown(anv->rtk);
- writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+ writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+ }
return ret;
}
@@ -1604,4 +1644,5 @@ static struct platform_driver apple_nvme_driver = {
module_platform_driver(apple_nvme_driver);
MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
+MODULE_DESCRIPTION("Apple ANS NVM Express device driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index a264b3ae078b..5ea0e21709da 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -6,7 +6,7 @@
#include <linux/crc32.h>
#include <linux/base64.h>
#include <linux/prandom.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/hash.h>
#include <crypto/dh.h>
#include "nvme.h"
@@ -730,7 +730,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE);
if (ret) {
chap->status = ret;
- chap->error = -ECONNREFUSED;
+ chap->error = -EKEYREJECTED;
return;
}
@@ -797,7 +797,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1);
if (ret) {
chap->status = ret;
- chap->error = -ECONNREFUSED;
+ chap->error = -EKEYREJECTED;
return;
}
@@ -818,7 +818,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
ret = nvme_auth_process_dhchap_success1(ctrl, chap);
if (ret) {
/* Controller authentication failed */
- chap->error = -ECONNREFUSED;
+ chap->error = -EKEYREJECTED;
goto fail2;
}
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 6f2ebb5fcdb0..2b9e6cfaf2a8 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -173,7 +173,7 @@ static const char * const nvme_statuses[] = {
const char *nvme_get_error_status_str(u16 status)
{
- status &= 0x7ff;
+ status &= NVME_SCT_SC_MASK;
if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
return nvme_statuses[status];
return "Unknown";
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0a96362912ce..8359d0aa0e44 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4,6 +4,7 @@
* Copyright (c) 2011-2014, Intel Corporation.
*/
+#include <linux/async.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-integrity.h>
@@ -21,7 +22,7 @@
#include <linux/nvme_ioctl.h>
#include <linux/pm_qos.h>
#include <linux/ratelimit.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "nvme.h"
#include "fabrics.h"
@@ -36,10 +37,13 @@ struct nvme_ns_info {
struct nvme_ns_ids ids;
u32 nsid;
__le32 anagrpid;
+ u8 pi_offset;
bool is_shared;
bool is_readonly;
bool is_ready;
bool is_removed;
+ bool is_rotational;
+ bool no_vwc;
};
unsigned int admin_timeout = 60;
@@ -90,6 +94,17 @@ MODULE_PARM_DESC(apst_secondary_latency_tol_us,
"secondary APST latency tolerance in us");
/*
+ * Older kernels didn't enable protection information if it was at an offset.
+ * Newer kernels do, so it breaks reads on the upgrade if such formats were
+ * used in prior kernels since the metadata written did not contain a valid
+ * checksum.
+ */
+static bool disable_pi_offsets = false;
+module_param(disable_pi_offsets, bool, 0444);
+MODULE_PARM_DESC(disable_pi_offsets,
+ "disable protection information if it has an offset");
+
+/*
* nvme_wq - hosts nvme related works that are not reset or delete
* nvme_reset_wq - hosts nvme reset works
* nvme_delete_wq - hosts nvme delete works
@@ -110,16 +125,25 @@ struct workqueue_struct *nvme_delete_wq;
EXPORT_SYMBOL_GPL(nvme_delete_wq);
static LIST_HEAD(nvme_subsystems);
-static DEFINE_MUTEX(nvme_subsystems_lock);
+DEFINE_MUTEX(nvme_subsystems_lock);
static DEFINE_IDA(nvme_instance_ida);
static dev_t nvme_ctrl_base_chr_devt;
-static struct class *nvme_class;
-static struct class *nvme_subsys_class;
+static int nvme_class_uevent(const struct device *dev, struct kobj_uevent_env *env);
+static const struct class nvme_class = {
+ .name = "nvme",
+ .dev_uevent = nvme_class_uevent,
+};
+
+static const struct class nvme_subsys_class = {
+ .name = "nvme-subsystem",
+};
static DEFINE_IDA(nvme_ns_chr_minor_ida);
static dev_t nvme_ns_chr_devt;
-static struct class *nvme_ns_chr_class;
+static const struct class nvme_ns_chr_class = {
+ .name = "nvme-generic",
+};
static void nvme_put_subsystem(struct nvme_subsystem *subsys);
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
@@ -252,7 +276,7 @@ void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
static blk_status_t nvme_error_status(u16 status)
{
- switch (status & 0x7ff) {
+ switch (status & NVME_SCT_SC_MASK) {
case NVME_SC_SUCCESS:
return BLK_STS_OK;
case NVME_SC_CAP_EXCEEDED:
@@ -298,7 +322,7 @@ static void nvme_retry_req(struct request *req)
u16 crd;
/* The mask and shift result must be <= 3 */
- crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
+ crd = (nvme_req(req)->status & NVME_STATUS_CRD) >> 11;
if (crd)
delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
@@ -320,10 +344,10 @@ static void nvme_log_error(struct request *req)
nvme_sect_to_lba(ns->head, blk_rq_pos(req)),
blk_rq_bytes(req) >> ns->head->lba_shift,
nvme_get_error_status_str(nr->status),
- nr->status >> 8 & 7, /* Status Code Type */
- nr->status & 0xff, /* Status Code */
- nr->status & NVME_SC_MORE ? "MORE " : "",
- nr->status & NVME_SC_DNR ? "DNR " : "");
+ NVME_SCT(nr->status), /* Status Code Type */
+ nr->status & NVME_SC_MASK, /* Status Code */
+ nr->status & NVME_STATUS_MORE ? "MORE " : "",
+ nr->status & NVME_STATUS_DNR ? "DNR " : "");
return;
}
@@ -332,10 +356,10 @@ static void nvme_log_error(struct request *req)
nvme_get_admin_opcode_str(nr->cmd->common.opcode),
nr->cmd->common.opcode,
nvme_get_error_status_str(nr->status),
- nr->status >> 8 & 7, /* Status Code Type */
- nr->status & 0xff, /* Status Code */
- nr->status & NVME_SC_MORE ? "MORE " : "",
- nr->status & NVME_SC_DNR ? "DNR " : "");
+ NVME_SCT(nr->status), /* Status Code Type */
+ nr->status & NVME_SC_MASK, /* Status Code */
+ nr->status & NVME_STATUS_MORE ? "MORE " : "",
+ nr->status & NVME_STATUS_DNR ? "DNR " : "");
}
static void nvme_log_err_passthru(struct request *req)
@@ -350,10 +374,10 @@ static void nvme_log_err_passthru(struct request *req)
nvme_get_admin_opcode_str(nr->cmd->common.opcode),
nr->cmd->common.opcode,
nvme_get_error_status_str(nr->status),
- nr->status >> 8 & 7, /* Status Code Type */
- nr->status & 0xff, /* Status Code */
- nr->status & NVME_SC_MORE ? "MORE " : "",
- nr->status & NVME_SC_DNR ? "DNR " : "",
+ NVME_SCT(nr->status), /* Status Code Type */
+ nr->status & NVME_SC_MASK, /* Status Code */
+ nr->status & NVME_STATUS_MORE ? "MORE " : "",
+ nr->status & NVME_STATUS_DNR ? "DNR " : "",
nr->cmd->common.cdw10,
nr->cmd->common.cdw11,
nr->cmd->common.cdw12,
@@ -374,14 +398,14 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
if (likely(nvme_req(req)->status == 0))
return COMPLETE;
- if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
- return AUTHENTICATE;
-
if (blk_noretry_request(req) ||
- (nvme_req(req)->status & NVME_SC_DNR) ||
+ (nvme_req(req)->status & NVME_STATUS_DNR) ||
nvme_req(req)->retries >= nvme_max_retries)
return COMPLETE;
+ if ((nvme_req(req)->status & NVME_SCT_SC_MASK) == NVME_SC_AUTH_REQUIRED)
+ return AUTHENTICATE;
+
if (req->cmd_flags & REQ_NVME_MPATH) {
if (nvme_is_path_error(nvme_req(req)->status) ||
blk_queue_dying(req->q))
@@ -405,10 +429,8 @@ static inline void nvme_end_req_zoned(struct request *req)
}
}
-static inline void nvme_end_req(struct request *req)
+static inline void __nvme_end_req(struct request *req)
{
- blk_status_t status = nvme_error_status(nvme_req(req)->status);
-
if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
if (blk_rq_is_passthrough(req))
nvme_log_err_passthru(req);
@@ -419,6 +441,13 @@ static inline void nvme_end_req(struct request *req)
nvme_trace_bio_complete(req);
if (req->cmd_flags & REQ_NVME_MPATH)
nvme_mpath_end_request(req);
+}
+
+void nvme_end_req(struct request *req)
+{
+ blk_status_t status = nvme_error_status(nvme_req(req)->status);
+
+ __nvme_end_req(req);
blk_mq_end_request(req, status);
}
@@ -467,7 +496,7 @@ void nvme_complete_batch_req(struct request *req)
{
trace_nvme_complete_rq(req);
nvme_cleanup_cmd(req);
- nvme_end_req_zoned(req);
+ __nvme_end_req(req);
}
EXPORT_SYMBOL_GPL(nvme_complete_batch_req);
@@ -535,8 +564,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
switch (new_state) {
case NVME_CTRL_LIVE:
switch (old_state) {
- case NVME_CTRL_NEW:
- case NVME_CTRL_RESETTING:
case NVME_CTRL_CONNECTING:
changed = true;
fallthrough;
@@ -620,27 +647,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
/*
- * Returns true for sink states that can't ever transition back to live.
- */
-static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
-{
- switch (nvme_ctrl_state(ctrl)) {
- case NVME_CTRL_NEW:
- case NVME_CTRL_LIVE:
- case NVME_CTRL_RESETTING:
- case NVME_CTRL_CONNECTING:
- return false;
- case NVME_CTRL_DELETING:
- case NVME_CTRL_DELETING_NOIO:
- case NVME_CTRL_DEAD:
- return true;
- default:
- WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
- return true;
- }
-}
-
-/*
* Waits for the controller state to be resetting, or returns false if it is
* not possible to ever transition to that state.
*/
@@ -685,7 +691,7 @@ static void nvme_free_ns(struct kref *kref)
kfree(ns);
}
-static inline bool nvme_get_ns(struct nvme_ns *ns)
+bool nvme_get_ns(struct nvme_ns *ns)
{
return kref_get_unless_zero(&ns->kref);
}
@@ -694,7 +700,7 @@ void nvme_put_ns(struct nvme_ns *ns)
{
kref_put(&ns->kref, nvme_free_ns);
}
-EXPORT_SYMBOL_NS_GPL(nvme_put_ns, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_put_ns, "NVME_TARGET_PASSTHRU");
static inline void nvme_clear_nvme_request(struct request *req)
{
@@ -877,6 +883,12 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
return BLK_STS_OK;
}
+static void nvme_set_app_tag(struct request *req, struct nvme_command *cmnd)
+{
+ cmnd->rw.lbat = cpu_to_le16(bio_integrity(req->bio)->app_tag);
+ cmnd->rw.lbatm = cpu_to_le16(0xffff);
+}
+
static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
struct request *req)
{
@@ -934,6 +946,36 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
return BLK_STS_OK;
}
+/*
+ * NVMe does not support a dedicated command to issue an atomic write. A write
+ * which does adhere to the device atomic limits will silently be executed
+ * non-atomically. The request issuer should ensure that the write is within
+ * the queue atomic writes limits, but just validate this in case it is not.
+ */
+static bool nvme_valid_atomic_write(struct request *req)
+{
+ struct request_queue *q = req->q;
+ u32 boundary_bytes = queue_atomic_write_boundary_bytes(q);
+
+ if (blk_rq_bytes(req) > queue_atomic_write_unit_max_bytes(q))
+ return false;
+
+ if (boundary_bytes) {
+ u64 mask = boundary_bytes - 1, imask = ~mask;
+ u64 start = blk_rq_pos(req) << SECTOR_SHIFT;
+ u64 end = start + blk_rq_bytes(req) - 1;
+
+ /* If greater then must be crossing a boundary */
+ if (blk_rq_bytes(req) > boundary_bytes)
+ return false;
+
+ if ((start & imask) != (end & imask))
+ return false;
+ }
+
+ return true;
+}
+
static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd,
enum nvme_opcode op)
@@ -949,6 +991,9 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
if (req->cmd_flags & REQ_RAHEAD)
dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
+ if (req->cmd_flags & REQ_ATOMIC && !nvme_valid_atomic_write(req))
+ return BLK_STS_INVAL;
+
cmnd->rw.opcode = op;
cmnd->rw.flags = 0;
cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
@@ -960,8 +1005,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
cmnd->rw.length =
cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1);
cmnd->rw.reftag = 0;
- cmnd->rw.apptag = 0;
- cmnd->rw.appmask = 0;
+ cmnd->rw.lbat = 0;
+ cmnd->rw.lbatm = 0;
if (ns->head->ms) {
/*
@@ -976,18 +1021,17 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
control |= NVME_RW_PRINFO_PRACT;
}
- switch (ns->head->pi_type) {
- case NVME_NS_DPS_PI_TYPE3:
+ if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD))
control |= NVME_RW_PRINFO_PRCHK_GUARD;
- break;
- case NVME_NS_DPS_PI_TYPE1:
- case NVME_NS_DPS_PI_TYPE2:
- control |= NVME_RW_PRINFO_PRCHK_GUARD |
- NVME_RW_PRINFO_PRCHK_REF;
+ if (bio_integrity_flagged(req->bio, BIP_CHECK_REFTAG)) {
+ control |= NVME_RW_PRINFO_PRCHK_REF;
if (op == nvme_cmd_zone_append)
control |= NVME_RW_APPEND_PIREMAP;
nvme_set_ref_tag(ns, cmnd, req);
- break;
+ }
+ if (bio_integrity_flagged(req->bio, BIP_CHECK_APPTAG)) {
+ control |= NVME_RW_PRINFO_PRCHK_APP;
+ nvme_set_app_tag(req, cmnd);
}
}
@@ -1005,6 +1049,7 @@ void nvme_cleanup_cmd(struct request *req)
clear_bit_unlock(0, &ctrl->discard_page_busy);
else
kfree(bvec_virt(&req->special_vec));
+ req->rq_flags &= ~RQF_SPECIAL_PAYLOAD;
}
}
EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
@@ -1081,7 +1126,7 @@ int nvme_execute_rq(struct request *rq, bool at_head)
return nvme_req(rq)->status;
return blk_status_to_errno(status);
}
-EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, "NVME_TARGET_PASSTHRU");
/*
* Returns 0 on success. If the result is negative, it's a Linux error code;
@@ -1161,7 +1206,7 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
return effects;
}
-EXPORT_SYMBOL_NS_GPL(nvme_command_effects, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_command_effects, "NVME_TARGET_PASSTHRU");
u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
{
@@ -1181,7 +1226,7 @@ u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
}
return effects;
}
-EXPORT_SYMBOL_NS_GPL(nvme_passthru_start, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_passthru_start, "NVME_TARGET_PASSTHRU");
void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects,
struct nvme_command *cmd, int status)
@@ -1226,11 +1271,11 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects,
break;
}
}
-EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, "NVME_TARGET_PASSTHRU");
/*
* Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1:
- *
+ *
* The host should send Keep Alive commands at half of the Keep Alive Timeout
* accounting for transport roundtrip times [..].
*/
@@ -1267,10 +1312,9 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
blk_status_t status)
{
struct nvme_ctrl *ctrl = rq->end_io_data;
- unsigned long flags;
- bool startka = false;
unsigned long rtt = jiffies - (rq->deadline - rq->timeout);
unsigned long delay = nvme_keep_alive_work_period(ctrl);
+ enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
/*
* Subtract off the keepalive RTT so nvme_keep_alive_work runs
@@ -1295,12 +1339,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
ctrl->ka_last_check_time = jiffies;
ctrl->comp_seen = false;
- spin_lock_irqsave(&ctrl->lock, flags);
- if (ctrl->state == NVME_CTRL_LIVE ||
- ctrl->state == NVME_CTRL_CONNECTING)
- startka = true;
- spin_unlock_irqrestore(&ctrl->lock, flags);
- if (startka)
+ if (state == NVME_CTRL_LIVE || state == NVME_CTRL_CONNECTING)
queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
return RQ_END_IO_NONE;
}
@@ -1370,17 +1409,30 @@ static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
nvme_start_keep_alive(ctrl);
}
-/*
- * In NVMe 1.0 the CNS field was just a binary controller or namespace
- * flag, thus sending any new CNS opcodes has a big chance of not working.
- * Qemu unfortunately had that bug after reporting a 1.1 version compliance
- * (but not for any later version).
- */
-static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl)
+static bool nvme_id_cns_ok(struct nvme_ctrl *ctrl, u8 cns)
{
- if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)
- return ctrl->vs < NVME_VS(1, 2, 0);
- return ctrl->vs < NVME_VS(1, 1, 0);
+ /*
+ * The CNS field occupies a full byte starting with NVMe 1.2
+ */
+ if (ctrl->vs >= NVME_VS(1, 2, 0))
+ return true;
+
+ /*
+ * NVMe 1.1 expanded the CNS value to two bits, which means values
+ * larger than that could get truncated and treated as an incorrect
+ * value.
+ *
+ * Qemu implemented 1.0 behavior for controllers claiming 1.1
+ * compliance, so they need to be quirked here.
+ */
+ if (ctrl->vs >= NVME_VS(1, 1, 0) &&
+ !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS))
+ return cns <= 3;
+
+ /*
+ * NVMe 1.0 used a single bit for the CNS value.
+ */
+ return cns <= 1;
}
static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
@@ -1398,8 +1450,10 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
sizeof(struct nvme_id_ctrl));
- if (error)
+ if (error) {
kfree(*id);
+ *id = NULL;
+ }
return error;
}
@@ -1528,6 +1582,7 @@ int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
if (error) {
dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
kfree(*id);
+ *id = NULL;
}
return error;
}
@@ -1592,6 +1647,8 @@ static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
info->is_shared = id->nmic & NVME_NS_NMIC_SHARED;
info->is_readonly = id->nsattr & NVME_NS_ATTR_RO;
info->is_ready = id->nstat & NVME_NSTAT_NRDY;
+ info->is_rotational = id->nsfeat & NVME_NS_ROTATIONAL;
+ info->no_vwc = id->nsfeat & NVME_NS_VWC_NOT_PRESENT;
}
kfree(id);
return ret;
@@ -1641,7 +1698,13 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0,
&result);
- if (status < 0)
+
+ /*
+ * It's either a kernel error or the host observed a connection
+ * lost. In either case it's not possible communicate with the
+ * controller and thus enter the error code path.
+ */
+ if (status < 0 || status == NVME_SC_HOST_PATH_ERROR)
return status;
/*
@@ -1727,27 +1790,38 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
return 0;
}
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk,
- struct nvme_ns_head *head, u32 max_integrity_segments)
+static bool nvme_init_integrity(struct nvme_ns_head *head,
+ struct queue_limits *lim, struct nvme_ns_info *info)
{
- struct blk_integrity integrity = { };
+ struct blk_integrity *bi = &lim->integrity;
+
+ memset(bi, 0, sizeof(*bi));
+
+ if (!head->ms)
+ return true;
+
+ /*
+ * PI can always be supported as we can ask the controller to simply
+ * insert/strip it, which is not possible for other kinds of metadata.
+ */
+ if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) ||
+ !(head->features & NVME_NS_METADATA_SUPPORTED))
+ return nvme_ns_has_pi(head);
switch (head->pi_type) {
case NVME_NS_DPS_PI_TYPE3:
switch (head->guard_type) {
case NVME_NVM_NS_16B_GUARD:
- integrity.profile = &t10_pi_type3_crc;
- integrity.tag_size = sizeof(u16) + sizeof(u32);
- integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+ bi->csum_type = BLK_INTEGRITY_CSUM_CRC;
+ bi->tag_size = sizeof(u16) + sizeof(u32);
+ bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
case NVME_NVM_NS_64B_GUARD:
- integrity.profile = &ext_pi_type3_crc64;
- integrity.tag_size = sizeof(u16) + 6;
- integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+ bi->csum_type = BLK_INTEGRITY_CSUM_CRC64;
+ bi->tag_size = sizeof(u16) + 6;
+ bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
break;
default:
- integrity.profile = NULL;
break;
}
break;
@@ -1755,73 +1829,48 @@ static void nvme_init_integrity(struct gendisk *disk,
case NVME_NS_DPS_PI_TYPE2:
switch (head->guard_type) {
case NVME_NVM_NS_16B_GUARD:
- integrity.profile = &t10_pi_type1_crc;
- integrity.tag_size = sizeof(u16);
- integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+ bi->csum_type = BLK_INTEGRITY_CSUM_CRC;
+ bi->tag_size = sizeof(u16);
+ bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE |
+ BLK_INTEGRITY_REF_TAG;
break;
case NVME_NVM_NS_64B_GUARD:
- integrity.profile = &ext_pi_type1_crc64;
- integrity.tag_size = sizeof(u16);
- integrity.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+ bi->csum_type = BLK_INTEGRITY_CSUM_CRC64;
+ bi->tag_size = sizeof(u16);
+ bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE |
+ BLK_INTEGRITY_REF_TAG;
break;
default:
- integrity.profile = NULL;
break;
}
break;
default:
- integrity.profile = NULL;
break;
}
- integrity.tuple_size = head->ms;
- blk_integrity_register(disk, &integrity);
- blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
-}
-#else
-static void nvme_init_integrity(struct gendisk *disk,
- struct nvme_ns_head *head, u32 max_integrity_segments)
-{
+ bi->tuple_size = head->ms;
+ bi->pi_offset = info->pi_offset;
+ return true;
}
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
- struct nvme_ns_head *head)
+static void nvme_config_discard(struct nvme_ns *ns, struct queue_limits *lim)
{
- struct request_queue *queue = disk->queue;
- u32 max_discard_sectors;
-
- if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) {
- max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl);
- } else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
- max_discard_sectors = UINT_MAX;
- } else {
- blk_queue_max_discard_sectors(queue, 0);
- return;
- }
+ struct nvme_ctrl *ctrl = ns->ctrl;
- BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
- NVME_DSM_MAX_RANGES);
+ if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns->head, UINT_MAX))
+ lim->max_hw_discard_sectors =
+ nvme_lba_to_sect(ns->head, ctrl->dmrsl);
+ else if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
+ lim->max_hw_discard_sectors = UINT_MAX;
+ else
+ lim->max_hw_discard_sectors = 0;
- /*
- * If discard is already enabled, don't reset queue limits.
- *
- * This works around the fact that the block layer can't cope well with
- * updating the hardware limits when overridden through sysfs. This is
- * harmless because discard limits in NVMe are purely advisory.
- */
- if (queue->limits.max_discard_sectors)
- return;
+ lim->discard_granularity = lim->logical_block_size;
- blk_queue_max_discard_sectors(queue, max_discard_sectors);
if (ctrl->dmrl)
- blk_queue_max_discard_segments(queue, ctrl->dmrl);
+ lim->max_discard_segments = ctrl->dmrl;
else
- blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
- queue->limits.discard_granularity = queue_logical_block_size(queue);
-
- if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
- blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
+ lim->max_discard_segments = NVME_DSM_MAX_RANGES;
}
static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
@@ -1832,44 +1881,46 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
a->csi == b->csi;
}
-static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
- struct nvme_id_ns *id)
+static int nvme_identify_ns_nvm(struct nvme_ctrl *ctrl, unsigned int nsid,
+ struct nvme_id_ns_nvm **nvmp)
{
- bool first = id->dps & NVME_NS_DPS_PI_FIRST;
- unsigned lbaf = nvme_lbaf_index(id->flbas);
- struct nvme_command c = { };
+ struct nvme_command c = {
+ .identify.opcode = nvme_admin_identify,
+ .identify.nsid = cpu_to_le32(nsid),
+ .identify.cns = NVME_ID_CNS_CS_NS,
+ .identify.csi = NVME_CSI_NVM,
+ };
struct nvme_id_ns_nvm *nvm;
- int ret = 0;
- u32 elbaf;
-
- head->pi_size = 0;
- head->ms = le16_to_cpu(id->lbaf[lbaf].ms);
- if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
- head->pi_size = sizeof(struct t10_pi_tuple);
- head->guard_type = NVME_NVM_NS_16B_GUARD;
- goto set_pi;
- }
+ int ret;
nvm = kzalloc(sizeof(*nvm), GFP_KERNEL);
if (!nvm)
return -ENOMEM;
- c.identify.opcode = nvme_admin_identify;
- c.identify.nsid = cpu_to_le32(head->ns_id);
- c.identify.cns = NVME_ID_CNS_CS_NS;
- c.identify.csi = NVME_CSI_NVM;
-
ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm));
if (ret)
- goto free_data;
+ kfree(nvm);
+ else
+ *nvmp = nvm;
+ return ret;
+}
- elbaf = le32_to_cpu(nvm->elbaf[lbaf]);
+static void nvme_configure_pi_elbas(struct nvme_ns_head *head,
+ struct nvme_id_ns *id, struct nvme_id_ns_nvm *nvm)
+{
+ u32 elbaf = le32_to_cpu(nvm->elbaf[nvme_lbaf_index(id->flbas)]);
+ u8 guard_type;
/* no support for storage tag formats right now */
if (nvme_elbaf_sts(elbaf))
- goto free_data;
+ return;
+
+ guard_type = nvme_elbaf_guard_type(elbaf);
+ if ((nvm->pic & NVME_ID_NS_NVM_QPIFS) &&
+ guard_type == NVME_NVM_NS_QTYPE_GUARD)
+ guard_type = nvme_elbaf_qualified_guard_type(elbaf);
- head->guard_type = nvme_elbaf_guard_type(elbaf);
+ head->guard_type = guard_type;
switch (head->guard_type) {
case NVME_NVM_NS_64B_GUARD:
head->pi_size = sizeof(struct crc64_pi_tuple);
@@ -1880,30 +1931,34 @@ static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
default:
break;
}
-
-free_data:
- kfree(nvm);
-set_pi:
- if (head->pi_size && (first || head->ms == head->pi_size))
- head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
- else
- head->pi_type = 0;
-
- return ret;
}
-static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
- struct nvme_ns_head *head, struct nvme_id_ns *id)
+static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
+ struct nvme_ns_head *head, struct nvme_id_ns *id,
+ struct nvme_id_ns_nvm *nvm, struct nvme_ns_info *info)
{
- int ret;
-
- ret = nvme_init_ms(ctrl, head, id);
- if (ret)
- return ret;
-
head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+ head->pi_type = 0;
+ head->pi_size = 0;
+ head->ms = le16_to_cpu(id->lbaf[nvme_lbaf_index(id->flbas)].ms);
if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
- return 0;
+ return;
+
+ if (nvm && (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
+ nvme_configure_pi_elbas(head, id, nvm);
+ } else {
+ head->pi_size = sizeof(struct t10_pi_tuple);
+ head->guard_type = NVME_NVM_NS_16B_GUARD;
+ }
+
+ if (head->pi_size && head->ms >= head->pi_size)
+ head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+ if (!(id->dps & NVME_NS_DPS_PI_FIRST)) {
+ if (disable_pi_offsets)
+ head->pi_type = 0;
+ else
+ info->pi_offset = head->ms - head->pi_size;
+ }
if (ctrl->ops->flags & NVME_F_FABRICS) {
/*
@@ -1912,7 +1967,7 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
* remap the separate metadata buffer from the block layer.
*/
if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
- return 0;
+ return;
head->features |= NVME_NS_EXT_LBAS;
@@ -1939,46 +1994,61 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
else
head->features |= NVME_NS_METADATA_SUPPORTED;
}
- return 0;
}
-static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
- struct request_queue *q)
-{
- bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT;
- if (ctrl->max_hw_sectors) {
- u32 max_segments =
- (ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
+static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns,
+ struct nvme_id_ns *id, struct queue_limits *lim,
+ u32 bs, u32 atomic_bs)
+{
+ unsigned int boundary = 0;
- max_segments = min_not_zero(max_segments, ctrl->max_segments);
- blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
- blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
+ if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) {
+ if (le16_to_cpu(id->nabspf))
+ boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
}
- blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
- blk_queue_dma_alignment(q, 3);
- blk_queue_write_cache(q, vwc, vwc);
+ lim->atomic_write_hw_max = atomic_bs;
+ lim->atomic_write_hw_boundary = boundary;
+ lim->atomic_write_hw_unit_min = bs;
+ lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs);
+ lim->features |= BLK_FEAT_ATOMIC_WRITES;
+}
+
+static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
+{
+ return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1;
+}
+
+static void nvme_set_ctrl_limits(struct nvme_ctrl *ctrl,
+ struct queue_limits *lim)
+{
+ lim->max_hw_sectors = ctrl->max_hw_sectors;
+ lim->max_segments = min_t(u32, USHRT_MAX,
+ min_not_zero(nvme_max_drv_segments(ctrl), ctrl->max_segments));
+ lim->max_integrity_segments = ctrl->max_integrity_segments;
+ lim->virt_boundary_mask = NVME_CTRL_PAGE_SIZE - 1;
+ lim->max_segment_size = UINT_MAX;
+ lim->dma_alignment = 3;
}
-static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
- struct nvme_ns_head *head, struct nvme_id_ns *id)
+static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
+ struct queue_limits *lim)
{
- sector_t capacity = nvme_lba_to_sect(head, le64_to_cpu(id->nsze));
+ struct nvme_ns_head *head = ns->head;
u32 bs = 1U << head->lba_shift;
u32 atomic_bs, phys_bs, io_opt = 0;
+ bool valid = true;
/*
* The block layer can't support LBA sizes larger than the page size
* or smaller than a sector size yet, so catch this early and don't
* allow block I/O.
*/
- if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) {
- capacity = 0;
+ if (blk_validate_block_size(bs)) {
bs = (1 << 9);
+ valid = false;
}
- blk_integrity_unregister(disk);
-
atomic_bs = phys_bs = bs;
if (id->nabo == 0) {
/*
@@ -1989,46 +2059,34 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
else
- atomic_bs = (1 + ctrl->subsys->awupf) * bs;
+ atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+
+ nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
}
if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
/* NPWG = Namespace Preferred Write Granularity */
phys_bs = bs * (1 + le16_to_cpu(id->npwg));
/* NOWS = Namespace Optimal Write Size */
- io_opt = bs * (1 + le16_to_cpu(id->nows));
+ if (id->nows)
+ io_opt = bs * (1 + le16_to_cpu(id->nows));
}
- blk_queue_logical_block_size(disk->queue, bs);
/*
* Linux filesystems assume writing a single physical block is
* an atomic operation. Hence limit the physical block size to the
* value of the Atomic Write Unit Power Fail parameter.
*/
- blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
- blk_queue_io_min(disk->queue, phys_bs);
- blk_queue_io_opt(disk->queue, io_opt);
-
- /*
- * Register a metadata profile for PI, or the plain non-integrity NVMe
- * metadata masquerading as Type 0 if supported, otherwise reject block
- * I/O to namespaces with metadata except when the namespace supports
- * PI, as it can strip/insert in that case.
- */
- if (head->ms) {
- if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
- (head->features & NVME_NS_METADATA_SUPPORTED))
- nvme_init_integrity(disk, head,
- ctrl->max_integrity_segments);
- else if (!nvme_ns_has_pi(head))
- capacity = 0;
- }
-
- set_capacity_and_notify(disk, capacity);
-
- nvme_config_discard(ctrl, disk, head);
- blk_queue_max_write_zeroes_sectors(disk->queue,
- ctrl->max_zeroes_sectors);
+ lim->logical_block_size = bs;
+ lim->physical_block_size = min(phys_bs, atomic_bs);
+ lim->io_min = phys_bs;
+ lim->io_opt = io_opt;
+ if ((ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) &&
+ (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM))
+ lim->max_write_zeroes_sectors = UINT_MAX;
+ else
+ lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors;
+ return valid;
}
static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info)
@@ -2042,7 +2100,8 @@ static inline bool nvme_first_scan(struct gendisk *disk)
return !disk_live(disk);
}
-static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id,
+ struct queue_limits *lim)
{
struct nvme_ctrl *ctrl = ns->ctrl;
u32 iob;
@@ -2070,38 +2129,39 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
return;
}
- blk_queue_chunk_sectors(ns->queue, iob);
+ lim->chunk_sectors = iob;
}
static int nvme_update_ns_info_generic(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
- blk_mq_freeze_queue(ns->disk->queue);
- nvme_set_queue_limits(ns->ctrl, ns->queue);
- set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
- blk_mq_unfreeze_queue(ns->disk->queue);
+ struct queue_limits lim;
+ unsigned int memflags;
+ int ret;
- if (nvme_ns_head_multipath(ns->head)) {
- blk_mq_freeze_queue(ns->head->disk->queue);
- set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
- nvme_mpath_revalidate_paths(ns);
- blk_stack_limits(&ns->head->disk->queue->limits,
- &ns->queue->limits, 0);
- ns->head->disk->flags |= GENHD_FL_HIDDEN;
- blk_mq_unfreeze_queue(ns->head->disk->queue);
- }
+ lim = queue_limits_start_update(ns->disk->queue);
+ nvme_set_ctrl_limits(ns->ctrl, &lim);
- /* Hide the block-interface for these devices */
- ns->disk->flags |= GENHD_FL_HIDDEN;
- set_bit(NVME_NS_READY, &ns->flags);
+ memflags = blk_mq_freeze_queue(ns->disk->queue);
+ ret = queue_limits_commit_update(ns->disk->queue, &lim);
+ set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
+ blk_mq_unfreeze_queue(ns->disk->queue, memflags);
- return 0;
+ /* Hide the block-interface for these devices */
+ if (!ret)
+ ret = -ENODEV;
+ return ret;
}
static int nvme_update_ns_info_block(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
+ struct queue_limits lim;
+ struct nvme_id_ns_nvm *nvm = NULL;
+ struct nvme_zone_info zi = {};
struct nvme_id_ns *id;
+ unsigned int memflags;
+ sector_t capacity;
unsigned lbaf;
int ret;
@@ -2112,31 +2172,64 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
if (id->ncap == 0) {
/* namespace not allocated or attached */
info->is_removed = true;
- ret = -ENODEV;
- goto error;
+ ret = -ENXIO;
+ goto out;
}
-
- blk_mq_freeze_queue(ns->disk->queue);
lbaf = nvme_lbaf_index(id->flbas);
+
+ if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) {
+ ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm);
+ if (ret < 0)
+ goto out;
+ }
+
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ ns->head->ids.csi == NVME_CSI_ZNS) {
+ ret = nvme_query_zone_info(ns, lbaf, &zi);
+ if (ret < 0)
+ goto out;
+ }
+
+ lim = queue_limits_start_update(ns->disk->queue);
+
+ memflags = blk_mq_freeze_queue(ns->disk->queue);
ns->head->lba_shift = id->lbaf[lbaf].ds;
ns->head->nuse = le64_to_cpu(id->nuse);
- nvme_set_queue_limits(ns->ctrl, ns->queue);
+ capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
+ nvme_set_ctrl_limits(ns->ctrl, &lim);
+ nvme_configure_metadata(ns->ctrl, ns->head, id, nvm, info);
+ nvme_set_chunk_sectors(ns, id, &lim);
+ if (!nvme_update_disk_info(ns, id, &lim))
+ capacity = 0;
+ nvme_config_discard(ns, &lim);
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ ns->head->ids.csi == NVME_CSI_ZNS)
+ nvme_update_zone_info(ns, &lim, &zi);
- ret = nvme_configure_metadata(ns->ctrl, ns->head, id);
- if (ret < 0) {
- blk_mq_unfreeze_queue(ns->disk->queue);
+ if ((ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) && !info->no_vwc)
+ lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
+ else
+ lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
+
+ if (info->is_rotational)
+ lim.features |= BLK_FEAT_ROTATIONAL;
+
+ /*
+ * Register a metadata profile for PI, or the plain non-integrity NVMe
+ * metadata masquerading as Type 0 if supported, otherwise reject block
+ * I/O to namespaces with metadata except when the namespace supports
+ * PI, as it can strip/insert in that case.
+ */
+ if (!nvme_init_integrity(ns->head, &lim, info))
+ capacity = 0;
+
+ ret = queue_limits_commit_update(ns->disk->queue, &lim);
+ if (ret) {
+ blk_mq_unfreeze_queue(ns->disk->queue, memflags);
goto out;
}
- nvme_set_chunk_sectors(ns, id);
- nvme_update_disk_info(ns->ctrl, ns->disk, ns->head, id);
- if (ns->head->ids.csi == NVME_CSI_ZNS) {
- ret = nvme_update_zone_info(ns, lbaf);
- if (ret) {
- blk_mq_unfreeze_queue(ns->disk->queue);
- goto out;
- }
- }
+ set_capacity_and_notify(ns->disk, capacity);
/*
* Only set the DEAC bit if the device guarantees that reads from
@@ -2148,61 +2241,127 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
ns->head->features |= NVME_NS_DEAC;
set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
set_bit(NVME_NS_READY, &ns->flags);
- blk_mq_unfreeze_queue(ns->disk->queue);
+ blk_mq_unfreeze_queue(ns->disk->queue, memflags);
if (blk_queue_is_zoned(ns->queue)) {
- ret = nvme_revalidate_zones(ns);
+ ret = blk_revalidate_disk_zones(ns->disk);
if (ret && !nvme_first_scan(ns->disk))
goto out;
}
- if (nvme_ns_head_multipath(ns->head)) {
- blk_mq_freeze_queue(ns->head->disk->queue);
- nvme_update_disk_info(ns->ctrl, ns->head->disk, ns->head, id);
- set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
- nvme_mpath_revalidate_paths(ns);
- blk_stack_limits(&ns->head->disk->queue->limits,
- &ns->queue->limits, 0);
- disk_update_readahead(ns->head->disk);
- blk_mq_unfreeze_queue(ns->head->disk->queue);
- }
-
ret = 0;
out:
- /*
- * If probing fails due an unsupported feature, hide the block device,
- * but still allow other access.
- */
- if (ret == -ENODEV) {
- ns->disk->flags |= GENHD_FL_HIDDEN;
- set_bit(NVME_NS_READY, &ns->flags);
- ret = 0;
- }
-
-error:
+ kfree(nvm);
kfree(id);
return ret;
}
static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
{
+ bool unsupported = false;
+ int ret;
+
switch (info->ids.csi) {
case NVME_CSI_ZNS:
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
dev_info(ns->ctrl->device,
"block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n",
info->nsid);
- return nvme_update_ns_info_generic(ns, info);
+ ret = nvme_update_ns_info_generic(ns, info);
+ break;
}
- return nvme_update_ns_info_block(ns, info);
+ ret = nvme_update_ns_info_block(ns, info);
+ break;
case NVME_CSI_NVM:
- return nvme_update_ns_info_block(ns, info);
+ ret = nvme_update_ns_info_block(ns, info);
+ break;
default:
dev_info(ns->ctrl->device,
"block device for nsid %u not supported (csi %u)\n",
info->nsid, info->ids.csi);
- return nvme_update_ns_info_generic(ns, info);
+ ret = nvme_update_ns_info_generic(ns, info);
+ break;
+ }
+
+ /*
+ * If probing fails due an unsupported feature, hide the block device,
+ * but still allow other access.
+ */
+ if (ret == -ENODEV) {
+ ns->disk->flags |= GENHD_FL_HIDDEN;
+ set_bit(NVME_NS_READY, &ns->flags);
+ unsupported = true;
+ ret = 0;
+ }
+
+ if (!ret && nvme_ns_head_multipath(ns->head)) {
+ struct queue_limits *ns_lim = &ns->disk->queue->limits;
+ struct queue_limits lim;
+ unsigned int memflags;
+
+ lim = queue_limits_start_update(ns->head->disk->queue);
+ memflags = blk_mq_freeze_queue(ns->head->disk->queue);
+ /*
+ * queue_limits mixes values that are the hardware limitations
+ * for bio splitting with what is the device configuration.
+ *
+ * For NVMe the device configuration can change after e.g. a
+ * Format command, and we really want to pick up the new format
+ * value here. But we must still stack the queue limits to the
+ * least common denominator for multipathing to split the bios
+ * properly.
+ *
+ * To work around this, we explicitly set the device
+ * configuration to those that we just queried, but only stack
+ * the splitting limits in to make sure we still obey possibly
+ * lower limitations of other controllers.
+ */
+ lim.logical_block_size = ns_lim->logical_block_size;
+ lim.physical_block_size = ns_lim->physical_block_size;
+ lim.io_min = ns_lim->io_min;
+ lim.io_opt = ns_lim->io_opt;
+ queue_limits_stack_bdev(&lim, ns->disk->part0, 0,
+ ns->head->disk->disk_name);
+ if (unsupported)
+ ns->head->disk->flags |= GENHD_FL_HIDDEN;
+ else
+ nvme_init_integrity(ns->head, &lim, info);
+ ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
+
+ set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
+ set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
+ nvme_mpath_revalidate_paths(ns);
+
+ blk_mq_unfreeze_queue(ns->head->disk->queue, memflags);
+ }
+
+ return ret;
+}
+
+int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16],
+ enum blk_unique_id type)
+{
+ struct nvme_ns_ids *ids = &ns->head->ids;
+
+ if (type != BLK_UID_EUI64)
+ return -EINVAL;
+
+ if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) {
+ memcpy(id, &ids->nguid, sizeof(ids->nguid));
+ return sizeof(ids->nguid);
+ }
+ if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) {
+ memcpy(id, &ids->eui64, sizeof(ids->eui64));
+ return sizeof(ids->eui64);
}
+
+ return -EINVAL;
+}
+
+static int nvme_get_unique_id(struct gendisk *disk, u8 id[16],
+ enum blk_unique_id type)
+{
+ return nvme_ns_get_unique_id(disk->private_data, id, type);
}
#ifdef CONFIG_BLK_SED_OPAL
@@ -2260,6 +2419,7 @@ const struct block_device_operations nvme_bdev_ops = {
.open = nvme_open,
.release = nvme_release,
.getgeo = nvme_getgeo,
+ .get_unique_id = nvme_get_unique_id,
.report_zones = nvme_report_zones,
.pr_ops = &nvme_pr_ops,
};
@@ -2342,8 +2502,13 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
else
ctrl->ctrl_config = NVME_CC_CSS_NVM;
- if (ctrl->cap & NVME_CAP_CRMS_CRWMS && ctrl->cap & NVME_CAP_CRMS_CRIMS)
- ctrl->ctrl_config |= NVME_CC_CRIME;
+ /*
+ * Setting CRIME results in CSTS.RDY before the media is ready. This
+ * makes it possible for media related commands to return the error
+ * NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY. Until the driver is
+ * restructured to handle retries, disable CC.CRIME.
+ */
+ ctrl->ctrl_config &= ~NVME_CC_CRIME;
ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
@@ -2352,11 +2517,6 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
if (ret)
return ret;
- /* Flush write to device (required if transport is PCI) */
- ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CC, &ctrl->ctrl_config);
- if (ret)
- return ret;
-
/* CAP value may change after initial CC write */
ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
if (ret)
@@ -2378,10 +2538,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
* devices are known to get this wrong. Use the larger of the
* two values.
*/
- if (ctrl->ctrl_config & NVME_CC_CRIME)
- ready_timeout = NVME_CRTO_CRIMT(crto);
- else
- ready_timeout = NVME_CRTO_CRWMT(crto);
+ ready_timeout = NVME_CRTO_CRWMT(crto);
if (ready_timeout < timeout)
dev_warn_once(ctrl->device, "bad crto:%x cap:%llx\n",
@@ -2877,7 +3034,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
subsys->awupf = le16_to_cpu(id->awupf);
nvme_mpath_default_iopolicy(subsys);
- subsys->dev.class = nvme_subsys_class;
+ subsys->dev.class = &nvme_subsys_class;
subsys->dev.release = nvme_release_subsystem;
subsys->dev.groups = nvme_subsys_attrs_groups;
dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance);
@@ -2949,7 +3106,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
struct nvme_effects_log **log)
{
- struct nvme_effects_log *cel = xa_load(&ctrl->cels, csi);
+ struct nvme_effects_log *old, *cel = xa_load(&ctrl->cels, csi);
int ret;
if (cel)
@@ -2966,7 +3123,11 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
return ret;
}
- xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
+ old = xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
+ if (xa_is_err(old)) {
+ kfree(cel);
+ return xa_err(old);
+ }
out:
*log = cel;
return 0;
@@ -3000,7 +3161,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
ctrl->max_zeroes_sectors = 0;
if (ctrl->subsys->subtype != NVME_NQN_NVME ||
- nvme_ctrl_limited_cns(ctrl) ||
+ !nvme_id_cns_ok(ctrl, NVME_ID_CNS_CS_CTRL) ||
test_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags))
return 0;
@@ -3028,6 +3189,25 @@ free_data:
return ret;
}
+static int nvme_init_effects_log(struct nvme_ctrl *ctrl,
+ u8 csi, struct nvme_effects_log **log)
+{
+ struct nvme_effects_log *effects, *old;
+
+ effects = kzalloc(sizeof(*effects), GFP_KERNEL);
+ if (!effects)
+ return -ENOMEM;
+
+ old = xa_store(&ctrl->cels, csi, effects, GFP_KERNEL);
+ if (xa_is_err(old)) {
+ kfree(effects);
+ return xa_err(old);
+ }
+
+ *log = effects;
+ return 0;
+}
+
static void nvme_init_known_nvm_effects(struct nvme_ctrl *ctrl)
{
struct nvme_effects_log *log = ctrl->effects;
@@ -3074,10 +3254,9 @@ static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
}
if (!ctrl->effects) {
- ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
- if (!ctrl->effects)
- return -ENOMEM;
- xa_store(&ctrl->cels, NVME_CSI_NVM, ctrl->effects, GFP_KERNEL);
+ ret = nvme_init_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
+ if (ret < 0)
+ return ret;
}
nvme_init_known_nvm_effects(ctrl);
@@ -3117,11 +3296,18 @@ static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ct
return -EINVAL;
}
+ if (!ctrl->maxcmd) {
+ dev_warn(ctrl->device,
+ "Firmware bug: maximum outstanding commands is 0\n");
+ ctrl->maxcmd = ctrl->sqsize + 1;
+ }
+
return 0;
}
static int nvme_init_identify(struct nvme_ctrl *ctrl)
{
+ struct queue_limits lim;
struct nvme_id_ctrl *id;
u32 max_hw_sectors;
bool prev_apst_enabled;
@@ -3188,7 +3374,12 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
ctrl->max_hw_sectors =
min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);
- nvme_set_queue_limits(ctrl, ctrl->admin_q);
+ lim = queue_limits_start_update(ctrl->admin_q);
+ nvme_set_ctrl_limits(ctrl, &lim);
+ ret = queue_limits_commit_update(ctrl->admin_q, &lim);
+ if (ret)
+ goto out_free;
+
ctrl->sgls = le32_to_cpu(id->sgls);
ctrl->kas = le16_to_cpu(id->kas);
ctrl->max_namespaces = le32_to_cpu(id->mnan);
@@ -3206,7 +3397,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
if (ctrl->shutdown_timeout != shutdown_timeout)
dev_info(ctrl->device,
- "Shutdown timeout set to %u seconds\n",
+ "D3 entry latency set to %u seconds\n",
ctrl->shutdown_timeout);
} else
ctrl->shutdown_timeout = shutdown_timeout;
@@ -3420,7 +3611,7 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
if (minor < 0)
return minor;
cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor);
- cdev_device->class = nvme_ns_chr_class;
+ cdev_device->class = &nvme_ns_chr_class;
cdev_device->release = nvme_cdev_rel;
device_initialize(cdev_device);
cdev_init(cdev, fops);
@@ -3493,6 +3684,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
head->ns_id = info->nsid;
head->ids = info->ids;
head->shared = info->is_shared;
+ head->rotational = info->is_rotational;
ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1);
ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE);
kref_init(&head->ref);
@@ -3630,7 +3822,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
"Found shared namespace %d, but multipathing not supported.\n",
info->nsid);
dev_warn_once(ctrl->device,
- "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0\n.");
+ "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0.\n");
}
}
@@ -3649,9 +3841,11 @@ out_unlock:
struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns *ns, *ret = NULL;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu)) {
if (ns->head->ns_id == nsid) {
if (!nvme_get_ns(ns))
continue;
@@ -3661,10 +3855,10 @@ struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
if (ns->head->ns_id > nsid)
break;
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return ret;
}
-EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, "NVME_TARGET_PASSTHRU");
/*
* Add the namespace to the controller list while keeping the list ordered.
@@ -3675,7 +3869,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
list_for_each_entry_reverse(tmp, &ns->ctrl->namespaces, list) {
if (tmp->head->ns_id < ns->head->ns_id) {
- list_add(&ns->list, &tmp->list);
+ list_add_rcu(&ns->list, &tmp->list);
return;
}
}
@@ -3684,6 +3878,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
{
+ struct queue_limits lim = { };
struct nvme_ns *ns;
struct gendisk *disk;
int node = ctrl->numa_node;
@@ -3692,7 +3887,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
if (!ns)
return;
- disk = blk_mq_alloc_disk(ctrl->tagset, ns);
+ if (ctrl->opts && ctrl->opts->data_digest)
+ lim.features |= BLK_FEAT_STABLE_WRITES;
+ if (ctrl->ops->supports_pci_p2pdma &&
+ ctrl->ops->supports_pci_p2pdma(ctrl))
+ lim.features |= BLK_FEAT_PCI_P2PDMA;
+
+ disk = blk_mq_alloc_disk(ctrl->tagset, &lim, ns);
if (IS_ERR(disk))
goto out_free_ns;
disk->fops = &nvme_bdev_ops;
@@ -3700,15 +3901,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
ns->disk = disk;
ns->queue = disk->queue;
-
- if (ctrl->opts && ctrl->opts->data_digest)
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
-
- blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
- if (ctrl->ops->supports_pci_p2pdma &&
- ctrl->ops->supports_pci_p2pdma(ctrl))
- blk_queue_flag_set(QUEUE_FLAG_PCI_P2PDMA, ns->queue);
-
ns->ctrl = ctrl;
kref_init(&ns->kref);
@@ -3741,17 +3933,18 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
if (nvme_update_ns_info(ns, info))
goto out_unlink_ns;
- down_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
/*
* Ensure that no namespaces are added to the ctrl list after the queues
* are frozen, thereby avoiding a deadlock between scan and reset.
*/
if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
- up_write(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->namespaces_lock);
goto out_unlink_ns;
}
nvme_ns_add_to_ctrl_list(ns);
- up_write(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->namespaces_lock);
+ synchronize_srcu(&ctrl->srcu);
nvme_get_ctrl(ctrl);
if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups))
@@ -3774,9 +3967,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
out_cleanup_ns_from_list:
nvme_put_ctrl(ctrl);
- down_write(&ctrl->namespaces_rwsem);
- list_del_init(&ns->list);
- up_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
+ list_del_rcu(&ns->list);
+ mutex_unlock(&ctrl->namespaces_lock);
+ synchronize_srcu(&ctrl->srcu);
out_unlink_ns:
mutex_lock(&ctrl->subsys->lock);
list_del_rcu(&ns->siblings);
@@ -3826,9 +4020,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
nvme_cdev_del(&ns->cdev, &ns->cdev_device);
del_gendisk(ns->disk);
- down_write(&ns->ctrl->namespaces_rwsem);
- list_del_init(&ns->list);
- up_write(&ns->ctrl->namespaces_rwsem);
+ mutex_lock(&ns->ctrl->namespaces_lock);
+ list_del_rcu(&ns->list);
+ mutex_unlock(&ns->ctrl->namespaces_lock);
+ synchronize_srcu(&ns->ctrl->srcu);
if (last_path)
nvme_mpath_shutdown_disk(ns->head);
@@ -3847,7 +4042,7 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info)
{
- int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
+ int ret = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) {
dev_err(ns->ctrl->device,
@@ -3863,7 +4058,7 @@ out:
*
* TODO: we should probably schedule a delayed retry here.
*/
- if (ret > 0 && (ret & NVME_SC_DNR))
+ if (ret > 0 && (ret & NVME_STATUS_DNR))
nvme_ns_remove(ns);
}
@@ -3871,7 +4066,7 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns_info info = { .nsid = nsid };
struct nvme_ns *ns;
- int ret;
+ int ret = 1;
if (nvme_identify_ns_descs(ctrl, &info))
return;
@@ -3888,9 +4083,10 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid)
* set up a namespace. If not fall back to the legacy version.
*/
if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) ||
- (info.ids.csi != NVME_CSI_NVM && info.ids.csi != NVME_CSI_ZNS))
+ (info.ids.csi != NVME_CSI_NVM && info.ids.csi != NVME_CSI_ZNS) ||
+ ctrl->vs >= NVME_VS(2, 0, 0))
ret = nvme_ns_info_from_id_cs_indep(ctrl, &info);
- else
+ if (ret > 0)
ret = nvme_ns_info_from_identify(ctrl, &info);
if (info.is_removed)
@@ -3912,22 +4108,53 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid)
}
}
+/**
+ * struct async_scan_info - keeps track of controller & NSIDs to scan
+ * @ctrl: Controller on which namespaces are being scanned
+ * @next_nsid: Index of next NSID to scan in ns_list
+ * @ns_list: Pointer to list of NSIDs to scan
+ *
+ * Note: There is a single async_scan_info structure shared by all instances
+ * of nvme_scan_ns_async() scanning a given controller, so the atomic
+ * operations on next_nsid are critical to ensure each instance scans a unique
+ * NSID.
+ */
+struct async_scan_info {
+ struct nvme_ctrl *ctrl;
+ atomic_t next_nsid;
+ __le32 *ns_list;
+};
+
+static void nvme_scan_ns_async(void *data, async_cookie_t cookie)
+{
+ struct async_scan_info *scan_info = data;
+ int idx;
+ u32 nsid;
+
+ idx = (u32)atomic_fetch_inc(&scan_info->next_nsid);
+ nsid = le32_to_cpu(scan_info->ns_list[idx]);
+
+ nvme_scan_ns(scan_info->ctrl, nsid);
+}
+
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
unsigned nsid)
{
struct nvme_ns *ns, *next;
LIST_HEAD(rm_list);
- down_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
- if (ns->head->ns_id > nsid)
- list_move_tail(&ns->list, &rm_list);
+ if (ns->head->ns_id > nsid) {
+ list_del_rcu(&ns->list);
+ synchronize_srcu(&ctrl->srcu);
+ list_add_tail_rcu(&ns->list, &rm_list);
+ }
}
- up_write(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->namespaces_lock);
list_for_each_entry_safe(ns, next, &rm_list, list)
nvme_ns_remove(ns);
-
}
static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
@@ -3936,11 +4163,15 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
__le32 *ns_list;
u32 prev = 0;
int ret = 0, i;
+ ASYNC_DOMAIN(domain);
+ struct async_scan_info scan_info;
ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
if (!ns_list)
return -ENOMEM;
+ scan_info.ctrl = ctrl;
+ scan_info.ns_list = ns_list;
for (;;) {
struct nvme_command cmd = {
.identify.opcode = nvme_admin_identify,
@@ -3956,19 +4187,23 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
goto free;
}
+ atomic_set(&scan_info.next_nsid, 0);
for (i = 0; i < nr_entries; i++) {
u32 nsid = le32_to_cpu(ns_list[i]);
if (!nsid) /* end of the list? */
goto out;
- nvme_scan_ns(ctrl, nsid);
+ async_schedule_domain(nvme_scan_ns_async, &scan_info,
+ &domain);
while (++prev < nsid)
nvme_ns_remove_by_nsid(ctrl, prev);
}
+ async_synchronize_full_domain(&domain);
}
out:
nvme_remove_invalid_namespaces(ctrl, prev);
free:
+ async_synchronize_full_domain(&domain);
kfree(ns_list);
return ret;
}
@@ -4044,7 +4279,7 @@ static void nvme_scan_work(struct work_struct *work)
}
mutex_lock(&ctrl->scan_lock);
- if (nvme_ctrl_limited_cns(ctrl)) {
+ if (!nvme_id_cns_ok(ctrl, NVME_ID_CNS_NS_ACTIVE_LIST)) {
nvme_scan_ns_sequential(ctrl);
} else {
/*
@@ -4053,7 +4288,7 @@ static void nvme_scan_work(struct work_struct *work)
* they report) but don't actually support it.
*/
ret = nvme_scan_ns_list(ctrl);
- if (ret > 0 && ret & NVME_SC_DNR)
+ if (ret > 0 && ret & NVME_STATUS_DNR)
nvme_scan_ns_sequential(ctrl);
}
mutex_unlock(&ctrl->scan_lock);
@@ -4097,9 +4332,10 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
/* this is a no-op when called from the controller reset handler */
nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
- down_write(&ctrl->namespaces_rwsem);
- list_splice_init(&ctrl->namespaces, &ns_list);
- up_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
+ list_splice_init_rcu(&ctrl->namespaces, &ns_list, synchronize_rcu);
+ mutex_unlock(&ctrl->namespaces_lock);
+ synchronize_srcu(&ctrl->srcu);
list_for_each_entry_safe(ns, next, &ns_list, list)
nvme_ns_remove(ns);
@@ -4306,7 +4542,8 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl)
{
- dev_warn(ctrl->device, "resetting controller due to AER\n");
+ dev_warn(ctrl->device,
+ "resetting controller due to persistent internal error\n");
nvme_reset_ctrl(ctrl);
}
@@ -4353,15 +4590,16 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
const struct blk_mq_ops *ops, unsigned int cmd_size)
{
+ struct queue_limits lim = {};
int ret;
memset(set, 0, sizeof(*set));
set->ops = ops;
set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
if (ctrl->ops->flags & NVME_F_FABRICS)
- set->reserved_tags = NVMF_RESERVED_TAGS;
+ /* Reserved for fabric connect and keep alive */
+ set->reserved_tags = 2;
set->numa_node = ctrl->numa_node;
- set->flags = BLK_MQ_F_NO_SCHED;
if (ctrl->ops->flags & NVME_F_BLOCKING)
set->flags |= BLK_MQ_F_BLOCKING;
set->cmd_size = cmd_size;
@@ -4372,14 +4610,14 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
if (ret)
return ret;
- ctrl->admin_q = blk_mq_init_queue(set);
+ ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
if (IS_ERR(ctrl->admin_q)) {
ret = PTR_ERR(ctrl->admin_q);
goto out_free_tagset;
}
if (ctrl->ops->flags & NVME_F_FABRICS) {
- ctrl->fabrics_q = blk_mq_init_queue(set);
+ ctrl->fabrics_q = blk_mq_alloc_queue(set, NULL, NULL);
if (IS_ERR(ctrl->fabrics_q)) {
ret = PTR_ERR(ctrl->fabrics_q);
goto out_cleanup_admin_q;
@@ -4402,6 +4640,11 @@ EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set);
void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl)
{
+ /*
+ * As we're about to destroy the queue and free tagset
+ * we can not have keep-alive work running.
+ */
+ nvme_stop_keep_alive(ctrl);
blk_mq_destroy_queue(ctrl->admin_q);
blk_put_queue(ctrl->admin_q);
if (ctrl->ops->flags & NVME_F_FABRICS) {
@@ -4428,12 +4671,12 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS)
set->reserved_tags = NVME_AQ_DEPTH;
else if (ctrl->ops->flags & NVME_F_FABRICS)
- set->reserved_tags = NVMF_RESERVED_TAGS;
+ /* Reserved for fabric connect */
+ set->reserved_tags = 1;
set->numa_node = ctrl->numa_node;
- set->flags = BLK_MQ_F_SHOULD_MERGE;
if (ctrl->ops->flags & NVME_F_BLOCKING)
set->flags |= BLK_MQ_F_BLOCKING;
- set->cmd_size = cmd_size,
+ set->cmd_size = cmd_size;
set->driver_data = ctrl;
set->nr_hw_queues = ctrl->queue_count - 1;
set->timeout = NVME_IO_TIMEOUT;
@@ -4443,13 +4686,15 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
return ret;
if (ctrl->ops->flags & NVME_F_FABRICS) {
- ctrl->connect_q = blk_mq_init_queue(set);
+ struct queue_limits lim = {
+ .features = BLK_FEAT_SKIP_TAGSET_QUIESCE,
+ };
+
+ ctrl->connect_q = blk_mq_alloc_queue(set, &lim, NULL);
if (IS_ERR(ctrl->connect_q)) {
ret = PTR_ERR(ctrl->connect_q);
goto out_free_tag_set;
}
- blk_queue_flag_set(QUEUE_FLAG_SKIP_TAGSET_QUIESCE,
- ctrl->connect_q);
}
ctrl->tagset = set;
@@ -4476,7 +4721,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
{
nvme_mpath_stop(ctrl);
nvme_auth_stop(ctrl);
- nvme_stop_keep_alive(ctrl);
nvme_stop_failfast_work(ctrl);
flush_work(&ctrl->async_event_work);
cancel_work_sync(&ctrl->fw_act_work);
@@ -4512,6 +4756,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
{
+ nvme_stop_keep_alive(ctrl);
nvme_hwmon_exit(ctrl);
nvme_fault_inject_fini(&ctrl->fault_inject);
dev_pm_qos_hide_latency_tolerance(ctrl->device);
@@ -4541,9 +4786,9 @@ static void nvme_free_ctrl(struct device *dev)
if (!subsys || ctrl->instance != subsys->instance)
ida_free(&nvme_instance_ida, ctrl->instance);
- key_put(ctrl->tls_key);
nvme_free_cels(ctrl);
nvme_mpath_uninit(ctrl);
+ cleanup_srcu_struct(&ctrl->srcu);
nvme_auth_stop(ctrl);
nvme_auth_free(ctrl);
__free_page(ctrl->discard_page);
@@ -4566,6 +4811,9 @@ static void nvme_free_ctrl(struct device *dev)
* Initialize a NVMe controller structures. This needs to be called during
* earliest initialization so that we have the initialized structured around
* during probing.
+ *
+ * On success, the caller must use the nvme_put_ctrl() to release this when
+ * needed, which also invokes the ops->free_ctrl() callback.
*/
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
const struct nvme_ctrl_ops *ops, unsigned long quirks)
@@ -4576,10 +4824,15 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
ctrl->passthru_err_log_enabled = false;
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
spin_lock_init(&ctrl->lock);
+ mutex_init(&ctrl->namespaces_lock);
+
+ ret = init_srcu_struct(&ctrl->srcu);
+ if (ret)
+ return ret;
+
mutex_init(&ctrl->scan_lock);
INIT_LIST_HEAD(&ctrl->namespaces);
xa_init(&ctrl->cels);
- init_rwsem(&ctrl->namespaces_rwsem);
ctrl->dev = dev;
ctrl->ops = ops;
ctrl->quirks = quirks;
@@ -4609,11 +4862,17 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
goto out;
ctrl->instance = ret;
+ ret = nvme_auth_init_ctrl(ctrl);
+ if (ret)
+ goto out_release_instance;
+
+ nvme_mpath_init_ctrl(ctrl);
+
device_initialize(&ctrl->ctrl_device);
ctrl->device = &ctrl->ctrl_device;
ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt),
ctrl->instance);
- ctrl->device->class = nvme_class;
+ ctrl->device->class = &nvme_class;
ctrl->device->parent = ctrl->dev;
if (ops->dev_attr_groups)
ctrl->device->groups = ops->dev_attr_groups;
@@ -4621,16 +4880,36 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
ctrl->device->groups = nvme_dev_attr_groups;
ctrl->device->release = nvme_free_ctrl;
dev_set_drvdata(ctrl->device, ctrl);
+
+ return ret;
+
+out_release_instance:
+ ida_free(&nvme_instance_ida, ctrl->instance);
+out:
+ if (ctrl->discard_page)
+ __free_page(ctrl->discard_page);
+ cleanup_srcu_struct(&ctrl->srcu);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nvme_init_ctrl);
+
+/*
+ * On success, returns with an elevated controller reference and caller must
+ * use nvme_uninit_ctrl() to properly free resources associated with the ctrl.
+ */
+int nvme_add_ctrl(struct nvme_ctrl *ctrl)
+{
+ int ret;
+
ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance);
if (ret)
- goto out_release_instance;
+ return ret;
- nvme_get_ctrl(ctrl);
cdev_init(&ctrl->cdev, &nvme_dev_fops);
- ctrl->cdev.owner = ops->module;
+ ctrl->cdev.owner = ctrl->ops->module;
ret = cdev_device_add(&ctrl->cdev, ctrl->device);
if (ret)
- goto out_free_name;
+ return ret;
/*
* Initialize latency tolerance controls. The sysfs files won't
@@ -4641,48 +4920,36 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
min(default_ps_max_latency_us, (unsigned long)S32_MAX));
nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device));
- nvme_mpath_init_ctrl(ctrl);
- ret = nvme_auth_init_ctrl(ctrl);
- if (ret)
- goto out_free_cdev;
+ nvme_get_ctrl(ctrl);
return 0;
-out_free_cdev:
- nvme_fault_inject_fini(&ctrl->fault_inject);
- dev_pm_qos_hide_latency_tolerance(ctrl->device);
- cdev_device_del(&ctrl->cdev, ctrl->device);
-out_free_name:
- nvme_put_ctrl(ctrl);
- kfree_const(ctrl->device->kobj.name);
-out_release_instance:
- ida_free(&nvme_instance_ida, ctrl->instance);
-out:
- if (ctrl->discard_page)
- __free_page(ctrl->discard_page);
- return ret;
}
-EXPORT_SYMBOL_GPL(nvme_init_ctrl);
+EXPORT_SYMBOL_GPL(nvme_add_ctrl);
/* let I/O to all namespaces fail in preparation for surprise removal */
void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu))
blk_mark_disk_dead(ns->disk);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_mark_namespaces_dead);
void nvme_unfreeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_mq_unfreeze_queue(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu))
+ blk_mq_unfreeze_queue_non_owner(ns->queue);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
}
EXPORT_SYMBOL_GPL(nvme_unfreeze);
@@ -4690,14 +4957,16 @@ EXPORT_SYMBOL_GPL(nvme_unfreeze);
int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu)) {
timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
if (timeout <= 0)
break;
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return timeout;
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
@@ -4705,23 +4974,32 @@ EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
void nvme_wait_freeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu))
blk_mq_freeze_queue_wait(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze);
void nvme_start_freeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_freeze_queue_start(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu))
+ /*
+ * Typical non_owner use case is from pci driver, in which
+ * start_freeze is called from timeout work function, but
+ * unfreeze is done in reset work context
+ */
+ blk_freeze_queue_start_non_owner(ns->queue);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_start_freeze);
@@ -4764,11 +5042,13 @@ EXPORT_SYMBOL_GPL(nvme_unquiesce_admin_queue);
void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu))
blk_sync_queue(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
@@ -4786,7 +5066,7 @@ struct nvme_ctrl *nvme_ctrl_from_file(struct file *file)
return NULL;
return file->private_data;
}
-EXPORT_SYMBOL_NS_GPL(nvme_ctrl_from_file, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_ctrl_from_file, "NVME_TARGET_PASSTHRU");
/*
* Check we didn't inadvertently grow the command structure sizes:
@@ -4814,6 +5094,8 @@ static inline void _nvme_check_size(void)
BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_nvm) != NVME_IDENTIFY_DATA_SIZE);
BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
+ BUILD_BUG_ON(sizeof(struct nvme_endurance_group_log) != 512);
+ BUILD_BUG_ON(sizeof(struct nvme_rotational_media_log) != 512);
BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
BUILD_BUG_ON(sizeof(struct nvme_directive_cmd) != 64);
BUILD_BUG_ON(sizeof(struct nvme_feat_host_behavior) != 512);
@@ -4822,22 +5104,20 @@ static inline void _nvme_check_size(void)
static int __init nvme_core_init(void)
{
+ unsigned int wq_flags = WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS;
int result = -ENOMEM;
_nvme_check_size();
- nvme_wq = alloc_workqueue("nvme-wq",
- WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+ nvme_wq = alloc_workqueue("nvme-wq", wq_flags, 0);
if (!nvme_wq)
goto out;
- nvme_reset_wq = alloc_workqueue("nvme-reset-wq",
- WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+ nvme_reset_wq = alloc_workqueue("nvme-reset-wq", wq_flags, 0);
if (!nvme_reset_wq)
goto destroy_wq;
- nvme_delete_wq = alloc_workqueue("nvme-delete-wq",
- WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+ nvme_delete_wq = alloc_workqueue("nvme-delete-wq", wq_flags, 0);
if (!nvme_delete_wq)
goto destroy_reset_wq;
@@ -4846,42 +5126,36 @@ static int __init nvme_core_init(void)
if (result < 0)
goto destroy_delete_wq;
- nvme_class = class_create("nvme");
- if (IS_ERR(nvme_class)) {
- result = PTR_ERR(nvme_class);
+ result = class_register(&nvme_class);
+ if (result)
goto unregister_chrdev;
- }
- nvme_class->dev_uevent = nvme_class_uevent;
- nvme_subsys_class = class_create("nvme-subsystem");
- if (IS_ERR(nvme_subsys_class)) {
- result = PTR_ERR(nvme_subsys_class);
+ result = class_register(&nvme_subsys_class);
+ if (result)
goto destroy_class;
- }
result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS,
"nvme-generic");
if (result < 0)
goto destroy_subsys_class;
- nvme_ns_chr_class = class_create("nvme-generic");
- if (IS_ERR(nvme_ns_chr_class)) {
- result = PTR_ERR(nvme_ns_chr_class);
+ result = class_register(&nvme_ns_chr_class);
+ if (result)
goto unregister_generic_ns;
- }
+
result = nvme_init_auth();
if (result)
goto destroy_ns_chr;
return 0;
destroy_ns_chr:
- class_destroy(nvme_ns_chr_class);
+ class_unregister(&nvme_ns_chr_class);
unregister_generic_ns:
unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
destroy_subsys_class:
- class_destroy(nvme_subsys_class);
+ class_unregister(&nvme_subsys_class);
destroy_class:
- class_destroy(nvme_class);
+ class_unregister(&nvme_class);
unregister_chrdev:
unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
destroy_delete_wq:
@@ -4897,9 +5171,9 @@ out:
static void __exit nvme_core_exit(void)
{
nvme_exit_auth();
- class_destroy(nvme_ns_chr_class);
- class_destroy(nvme_subsys_class);
- class_destroy(nvme_class);
+ class_unregister(&nvme_ns_chr_class);
+ class_unregister(&nvme_subsys_class);
+ class_unregister(&nvme_class);
unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
destroy_workqueue(nvme_delete_wq);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 495c171daead..432efcbf9e2f 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -180,14 +180,14 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
cmd.prop_get.offset = cpu_to_le32(off);
ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
- NVME_QID_ANY, 0);
+ NVME_QID_ANY, NVME_SUBMIT_RESERVED);
if (ret >= 0)
*val = le64_to_cpu(res.u64);
if (unlikely(ret != 0))
dev_err(ctrl->device,
"Property Get error: %d, offset %#x\n",
- ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+ ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
return ret;
}
@@ -226,14 +226,14 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
cmd.prop_get.offset = cpu_to_le32(off);
ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
- NVME_QID_ANY, 0);
+ NVME_QID_ANY, NVME_SUBMIT_RESERVED);
if (ret >= 0)
*val = le64_to_cpu(res.u64);
if (unlikely(ret != 0))
dev_err(ctrl->device,
"Property Get error: %d, offset %#x\n",
- ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+ ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
return ret;
}
EXPORT_SYMBOL_GPL(nvmf_reg_read64);
@@ -271,15 +271,30 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
cmd.prop_set.value = cpu_to_le64(val);
ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0,
- NVME_QID_ANY, 0);
+ NVME_QID_ANY, NVME_SUBMIT_RESERVED);
if (unlikely(ret))
dev_err(ctrl->device,
"Property Set error: %d, offset %#x\n",
- ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
+ ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
return ret;
}
EXPORT_SYMBOL_GPL(nvmf_reg_write32);
+int nvmf_subsystem_reset(struct nvme_ctrl *ctrl)
+{
+ int ret;
+
+ if (!nvme_wait_reset(ctrl))
+ return -EBUSY;
+
+ ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, NVME_SUBSYS_RESET);
+ if (ret)
+ return ret;
+
+ return nvme_try_sched_reset(ctrl);
+}
+EXPORT_SYMBOL_GPL(nvmf_subsystem_reset);
+
/**
* nvmf_log_connect_error() - Error-parsing-diagnostic print out function for
* connect() errors.
@@ -295,7 +310,7 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
int errval, int offset, struct nvme_command *cmd,
struct nvmf_connect_data *data)
{
- int err_sctype = errval & ~NVME_SC_DNR;
+ int err_sctype = errval & ~NVME_STATUS_DNR;
if (errval < 0) {
dev_err(ctrl->device,
@@ -428,12 +443,6 @@ static void nvmf_connect_cmd_prep(struct nvme_ctrl *ctrl, u16 qid,
* fabrics-protocol connection of the NVMe Admin queue between the
* host system device and the allocated NVMe controller on the
* target system via a NVMe Fabrics "Connect" command.
- *
- * Return:
- * 0: success
- * > 0: NVMe error status code
- * < 0: Linux errno error code
- *
*/
int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
{
@@ -467,7 +476,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
if (result & NVME_CONNECT_AUTHREQ_ASCR) {
dev_warn(ctrl->device,
"qid 0: secure concatenation is not supported\n");
- ret = NVME_SC_AUTH_REQUIRED;
+ ret = -EOPNOTSUPP;
goto out_free_data;
}
/* Authentication required */
@@ -475,14 +484,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
if (ret) {
dev_warn(ctrl->device,
"qid 0: authentication setup failed\n");
- ret = NVME_SC_AUTH_REQUIRED;
goto out_free_data;
}
ret = nvme_auth_wait(ctrl, 0);
- if (ret)
+ if (ret) {
dev_warn(ctrl->device,
- "qid 0: authentication failed\n");
- else
+ "qid 0: authentication failed, error %d\n",
+ ret);
+ } else
dev_info(ctrl->device,
"qid 0: authenticated\n");
}
@@ -542,7 +551,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
if (result & NVME_CONNECT_AUTHREQ_ASCR) {
dev_warn(ctrl->device,
"qid 0: secure concatenation is not supported\n");
- ret = NVME_SC_AUTH_REQUIRED;
+ ret = -EOPNOTSUPP;
goto out_free_data;
}
/* Authentication required */
@@ -550,12 +559,13 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
if (ret) {
dev_warn(ctrl->device,
"qid %d: authentication setup failed\n", qid);
- ret = NVME_SC_AUTH_REQUIRED;
- } else {
- ret = nvme_auth_wait(ctrl, qid);
- if (ret)
- dev_warn(ctrl->device,
- "qid %u: authentication failed\n", qid);
+ goto out_free_data;
+ }
+ ret = nvme_auth_wait(ctrl, qid);
+ if (ret) {
+ dev_warn(ctrl->device,
+ "qid %u: authentication failed, error %d\n",
+ qid, ret);
}
}
out_free_data:
@@ -564,8 +574,26 @@ out_free_data:
}
EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
-bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
+/*
+ * Evaluate the status information returned by the transport in order to decided
+ * if a reconnect attempt should be scheduled.
+ *
+ * Do not retry when:
+ *
+ * - the DNR bit is set and the specification states no further connect
+ * attempts with the same set of paramenters should be attempted.
+ *
+ * - when the authentication attempt fails, because the key was invalid.
+ * This error code is set on the host side.
+ */
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status)
{
+ if (status > 0 && (status & NVME_STATUS_DNR))
+ return false;
+
+ if (status == -EKEYREJECTED)
+ return false;
+
if (ctrl->opts->max_reconnects == -1 ||
ctrl->nr_reconnects < ctrl->opts->max_reconnects)
return true;
@@ -637,8 +665,8 @@ static struct key *nvmf_parse_key(int key_id)
return ERR_PTR(-EINVAL);
}
- key = key_lookup(key_id);
- if (!IS_ERR(key))
+ key = nvme_tls_key_lookup(key_id);
+ if (IS_ERR(key))
pr_err("key id %08x not found\n", key_id);
else
pr_debug("Using key id %08x\n", key_id);
@@ -1319,7 +1347,10 @@ out_free_opts:
return ERR_PTR(ret);
}
-static struct class *nvmf_class;
+static const struct class nvmf_class = {
+ .name = "nvme-fabrics",
+};
+
static struct device *nvmf_device;
static DEFINE_MUTEX(nvmf_dev_mutex);
@@ -1372,10 +1403,10 @@ static void __nvmf_concat_opt_tokens(struct seq_file *seq_file)
tok = &opt_tokens[idx];
if (tok->token == NVMF_OPT_ERR)
continue;
- seq_puts(seq_file, ",");
+ seq_putc(seq_file, ',');
seq_puts(seq_file, tok->pattern);
}
- seq_puts(seq_file, "\n");
+ seq_putc(seq_file, '\n');
}
static int nvmf_dev_show(struct seq_file *seq_file, void *private)
@@ -1439,15 +1470,14 @@ static int __init nvmf_init(void)
if (!nvmf_default_host)
return -ENOMEM;
- nvmf_class = class_create("nvme-fabrics");
- if (IS_ERR(nvmf_class)) {
+ ret = class_register(&nvmf_class);
+ if (ret) {
pr_err("couldn't register class nvme-fabrics\n");
- ret = PTR_ERR(nvmf_class);
goto out_free_host;
}
nvmf_device =
- device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
+ device_create(&nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
if (IS_ERR(nvmf_device)) {
pr_err("couldn't create nvme-fabrics device!\n");
ret = PTR_ERR(nvmf_device);
@@ -1463,9 +1493,9 @@ static int __init nvmf_init(void)
return 0;
out_destroy_device:
- device_destroy(nvmf_class, MKDEV(0, 0));
+ device_destroy(&nvmf_class, MKDEV(0, 0));
out_destroy_class:
- class_destroy(nvmf_class);
+ class_unregister(&nvmf_class);
out_free_host:
nvmf_host_put(nvmf_default_host);
return ret;
@@ -1474,8 +1504,8 @@ out_free_host:
static void __exit nvmf_exit(void)
{
misc_deregister(&nvmf_misc);
- device_destroy(nvmf_class, MKDEV(0, 0));
- class_destroy(nvmf_class);
+ device_destroy(&nvmf_class, MKDEV(0, 0));
+ class_unregister(&nvmf_class);
nvmf_host_put(nvmf_default_host);
BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 06cc54851b1b..21d75dc4a3a0 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -19,13 +19,6 @@
#define NVMF_DEF_FAIL_FAST_TMO -1
/*
- * Reserved one command for internal usage. This command is used for sending
- * the connect command, as well as for the keep alive command on the admin
- * queue once live.
- */
-#define NVMF_RESERVED_TAGS 1
-
-/*
* Define a host as seen by the target. We allocate one at boot, but also
* allow the override it when creating controllers. This is both to provide
* persistence of the Host NQN over multiple boots, and to allow using
@@ -224,13 +217,14 @@ static inline unsigned int nvmf_nr_io_queues(struct nvmf_ctrl_options *opts)
int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
+int nvmf_subsystem_reset(struct nvme_ctrl *ctrl);
int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl);
int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid);
int nvmf_register_transport(struct nvmf_transport_ops *ops);
void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
void nvmf_free_options(struct nvmf_ctrl_options *opts);
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
-bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status);
bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
struct nvmf_ctrl_options *opts);
void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues,
diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c
index 1ba10a5c656d..105d6cb41c72 100644
--- a/drivers/nvme/host/fault_inject.c
+++ b/drivers/nvme/host/fault_inject.c
@@ -6,6 +6,7 @@
*/
#include <linux/moduleparam.h>
+#include <linux/debugfs.h>
#include "nvme.h"
static DECLARE_FAULT_ATTR(fail_default_attr);
@@ -75,7 +76,7 @@ void nvme_should_fail(struct request *req)
/* inject status code and DNR bit */
status = fault_inject->status;
if (fault_inject->dont_retry)
- status |= NVME_SC_DNR;
+ status |= NVME_STATUS_DNR;
nvme_req(req)->status = status;
}
}
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 68a5d971657b..b9929a5a7f4e 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -16,7 +16,6 @@
#include <linux/nvme-fc.h>
#include "fc.h"
#include <scsi/scsi_transport_fc.h>
-#include <linux/blk-mq-pci.h>
/* *************************** Data Structures/Defines ****************** */
@@ -786,49 +785,8 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
"NVME-FC{%d}: controller connectivity lost. Awaiting "
"Reconnect", ctrl->cnum);
- switch (nvme_ctrl_state(&ctrl->ctrl)) {
- case NVME_CTRL_NEW:
- case NVME_CTRL_LIVE:
- /*
- * Schedule a controller reset. The reset will terminate the
- * association and schedule the reconnect timer. Reconnects
- * will be attempted until either the ctlr_loss_tmo
- * (max_retries * connect_delay) expires or the remoteport's
- * dev_loss_tmo expires.
- */
- if (nvme_reset_ctrl(&ctrl->ctrl)) {
- dev_warn(ctrl->ctrl.device,
- "NVME-FC{%d}: Couldn't schedule reset.\n",
- ctrl->cnum);
- nvme_delete_ctrl(&ctrl->ctrl);
- }
- break;
-
- case NVME_CTRL_CONNECTING:
- /*
- * The association has already been terminated and the
- * controller is attempting reconnects. No need to do anything
- * futher. Reconnects will be attempted until either the
- * ctlr_loss_tmo (max_retries * connect_delay) expires or the
- * remoteport's dev_loss_tmo expires.
- */
- break;
-
- case NVME_CTRL_RESETTING:
- /*
- * Controller is already in the process of terminating the
- * association. No need to do anything further. The reconnect
- * step will kick in naturally after the association is
- * terminated.
- */
- break;
-
- case NVME_CTRL_DELETING:
- case NVME_CTRL_DELETING_NOIO:
- default:
- /* no action to take - let it delete */
- break;
- }
+ set_bit(ASSOC_FAILED, &ctrl->flags);
+ nvme_reset_ctrl(&ctrl->ctrl);
}
/**
@@ -2080,7 +2038,8 @@ done:
nvme_fc_complete_rq(rq);
check_error:
- if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING)
+ if (terminate_assoc &&
+ nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_RESETTING)
queue_work(nvme_reset_wq, &ctrl->ioerr_work);
}
@@ -2428,7 +2387,7 @@ nvme_fc_ctrl_get(struct nvme_fc_ctrl *ctrl)
* controller. Called after last nvme_put_ctrl() call
*/
static void
-nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl)
+nvme_fc_free_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
@@ -2534,6 +2493,8 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
static void
nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
{
+ enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
/*
* if an error (io timeout, etc) while (re)connecting, the remote
* port requested terminating of the association (disconnect_ls)
@@ -2541,9 +2502,8 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
* the controller. Abort any ios on the association and let the
* create_association error path resolve things.
*/
- if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
+ if (state == NVME_CTRL_CONNECTING) {
__nvme_fc_abort_outstanding_ios(ctrl, true);
- set_bit(ASSOC_FAILED, &ctrl->flags);
dev_warn(ctrl->ctrl.device,
"NVME-FC{%d}: transport error during (re)connect\n",
ctrl->cnum);
@@ -2551,7 +2511,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
}
/* Otherwise, only proceed if in LIVE state - e.g. on first error */
- if (ctrl->ctrl.state != NVME_CTRL_LIVE)
+ if (state != NVME_CTRL_LIVE)
return;
dev_warn(ctrl->ctrl.device,
@@ -3062,7 +3022,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
struct nvmefc_ls_rcv_op *disls = NULL;
unsigned long flags;
int ret;
- bool changed;
++ctrl->ctrl.nr_reconnects;
@@ -3132,7 +3091,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
if (ctrl->ctrl.icdoff) {
dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
ctrl->ctrl.icdoff);
- ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out_stop_keep_alive;
}
@@ -3140,7 +3099,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) {
dev_err(ctrl->ctrl.device,
"Mandatory sgls are not supported!\n");
- ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out_stop_keep_alive;
}
@@ -3173,12 +3132,13 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
if (ret)
goto out_term_aen_ops;
- changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) {
+ ret = -EIO;
+ goto out_term_aen_ops;
+ }
ctrl->ctrl.nr_reconnects = 0;
-
- if (changed)
- nvme_start_ctrl(&ctrl->ctrl);
+ nvme_start_ctrl(&ctrl->ctrl);
return 0; /* Success */
@@ -3310,12 +3270,10 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
ctrl->cnum, status);
- if (status > 0 && (status & NVME_SC_DNR))
- recon = false;
} else if (time_after_eq(jiffies, rport->dev_loss_end))
recon = false;
- if (recon && nvmf_should_reconnect(&ctrl->ctrl)) {
+ if (recon && nvmf_should_reconnect(&ctrl->ctrl, status)) {
if (portptr->port_state == FC_OBJSTATE_ONLINE)
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: Reconnect attempt in %ld "
@@ -3327,7 +3285,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay);
} else {
if (portptr->port_state == FC_OBJSTATE_ONLINE) {
- if (status > 0 && (status & NVME_SC_DNR))
+ if (status > 0 && (status & NVME_STATUS_DNR))
dev_warn(ctrl->ctrl.device,
"NVME-FC{%d}: reconnect failure\n",
ctrl->cnum);
@@ -3384,7 +3342,8 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
- .free_ctrl = nvme_fc_nvme_ctrl_freed,
+ .subsystem_reset = nvmf_subsystem_reset,
+ .free_ctrl = nvme_fc_free_ctrl,
.submit_async_event = nvme_fc_submit_async_event,
.delete_ctrl = nvme_fc_delete_ctrl,
.get_address = nvmf_get_address,
@@ -3446,12 +3405,11 @@ nvme_fc_existing_controller(struct nvme_fc_rport *rport,
return found;
}
-static struct nvme_ctrl *
-nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
+static struct nvme_fc_ctrl *
+nvme_fc_alloc_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
struct nvme_fc_lport *lport, struct nvme_fc_rport *rport)
{
struct nvme_fc_ctrl *ctrl;
- unsigned long flags;
int ret, idx, ctrl_loss_tmo;
if (!(rport->remoteport.port_role &
@@ -3540,7 +3498,35 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
if (lport->dev)
ctrl->ctrl.numa_node = dev_to_node(lport->dev);
- /* at this point, teardown path changes to ref counting on nvme ctrl */
+ return ctrl;
+
+out_free_queues:
+ kfree(ctrl->queues);
+out_free_ida:
+ put_device(ctrl->dev);
+ ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum);
+out_free_ctrl:
+ kfree(ctrl);
+out_fail:
+ /* exit via here doesn't follow ctlr ref points */
+ return ERR_PTR(ret);
+}
+
+static struct nvme_ctrl *
+nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
+ struct nvme_fc_lport *lport, struct nvme_fc_rport *rport)
+{
+ struct nvme_fc_ctrl *ctrl;
+ unsigned long flags;
+ int ret;
+
+ ctrl = nvme_fc_alloc_ctrl(dev, opts, lport, rport);
+ if (IS_ERR(ctrl))
+ return ERR_CAST(ctrl);
+
+ ret = nvme_add_ctrl(&ctrl->ctrl);
+ if (ret)
+ goto out_put_ctrl;
ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set,
&nvme_fc_admin_mq_ops,
@@ -3553,8 +3539,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
spin_unlock_irqrestore(&rport->lock, flags);
- if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING) ||
- !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
dev_err(ctrl->ctrl.device,
"NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum);
goto fail_ctrl;
@@ -3586,6 +3571,7 @@ fail_ctrl:
/* initiate nvme ctrl ref counting teardown */
nvme_uninit_ctrl(&ctrl->ctrl);
+out_put_ctrl:
/* Remove core ctrl ref. */
nvme_put_ctrl(&ctrl->ctrl);
@@ -3599,20 +3585,8 @@ fail_ctrl:
nvme_fc_rport_get(rport);
return ERR_PTR(-EIO);
-
-out_free_queues:
- kfree(ctrl->queues);
-out_free_ida:
- put_device(ctrl->dev);
- ida_free(&nvme_fc_ctrl_cnt, ctrl->cnum);
-out_free_ctrl:
- kfree(ctrl);
-out_fail:
- /* exit via here doesn't follow ctlr ref points */
- return ERR_PTR(ret);
}
-
struct nvmet_fc_traddr {
u64 nn;
u64 pn;
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
index 8df73a0b3980..89a1a1043d63 100644
--- a/drivers/nvme/host/hwmon.c
+++ b/drivers/nvme/host/hwmon.c
@@ -6,7 +6,7 @@
#include <linux/hwmon.h>
#include <linux/units.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "nvme.h"
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 3dfd5ae99ae0..24e2c702da7a 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -3,6 +3,7 @@
* Copyright (c) 2011-2014, Intel Corporation.
* Copyright (c) 2017-2021 Christoph Hellwig.
*/
+#include <linux/blk-integrity.h>
#include <linux/ptrace.h> /* for force_successful_syscall_return */
#include <linux/nvme_ioctl.h>
#include <linux/io_uring/cmd.h>
@@ -113,20 +114,37 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
static int nvme_map_user_request(struct request *req, u64 ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
- u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
+ struct io_uring_cmd *ioucmd, unsigned int flags)
{
struct request_queue *q = req->q;
struct nvme_ns *ns = q->queuedata;
struct block_device *bdev = ns ? ns->disk->part0 : NULL;
+ bool supports_metadata = bdev && blk_get_integrity(bdev->bd_disk);
+ struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
+ bool has_metadata = meta_buffer && meta_len;
struct bio *bio = NULL;
int ret;
+ if (!nvme_ctrl_sgl_supported(ctrl))
+ dev_warn_once(ctrl->device, "using unchecked data buffer\n");
+ if (has_metadata) {
+ if (!supports_metadata) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!nvme_ctrl_meta_sgl_supported(ctrl))
+ dev_warn_once(ctrl->device,
+ "using unchecked metadata buffer\n");
+ }
+
if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
struct iov_iter iter;
/* fixedbufs is only for non-vectored io */
- if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
- return -EINVAL;
+ if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC)) {
+ ret = -EINVAL;
+ goto out;
+ }
ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
rq_data_dir(req), &iter, ioucmd);
if (ret < 0)
@@ -142,15 +160,13 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
goto out;
bio = req->bio;
- if (bdev) {
+ if (bdev)
bio_set_dev(bio, bdev);
- if (meta_buffer && meta_len) {
- ret = bio_integrity_map_user(bio, meta_buffer, meta_len,
- meta_seed);
- if (ret)
- goto out_unmap;
- req->cmd_flags |= REQ_INTEGRITY;
- }
+
+ if (has_metadata) {
+ ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len);
+ if (ret)
+ goto out_unmap;
}
return ret;
@@ -165,7 +181,7 @@ out:
static int nvme_submit_user_cmd(struct request_queue *q,
struct nvme_command *cmd, u64 ubuffer, unsigned bufflen,
- void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
+ void __user *meta_buffer, unsigned meta_len,
u64 *result, unsigned timeout, unsigned int flags)
{
struct nvme_ns *ns = q->queuedata;
@@ -182,7 +198,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
req->timeout = timeout;
if (ubuffer && bufflen) {
ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
- meta_len, meta_seed, NULL, flags);
+ meta_len, NULL, flags);
if (ret)
return ret;
}
@@ -259,11 +275,11 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
c.rw.control = cpu_to_le16(io.control);
c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
c.rw.reftag = cpu_to_le32(io.reftag);
- c.rw.apptag = cpu_to_le16(io.apptag);
- c.rw.appmask = cpu_to_le16(io.appmask);
+ c.rw.lbat = cpu_to_le16(io.apptag);
+ c.rw.lbatm = cpu_to_le16(io.appmask);
return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
- meta_len, lower_32_bits(io.slba), NULL, 0, 0);
+ meta_len, NULL, 0, 0);
}
static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
@@ -271,8 +287,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
{
if (ns && nsid != ns->head->ns_id) {
dev_err(ctrl->device,
- "%s: nsid (%u) in cmd does not match nsid (%u)"
- "of namespace\n",
+ "%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
current->comm, nsid, ns->head->ns_id);
return false;
}
@@ -318,7 +333,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
- cmd.metadata_len, 0, &result, timeout, 0);
+ cmd.metadata_len, &result, timeout, 0);
if (status >= 0) {
if (put_user(result, &ucmd->result))
@@ -365,7 +380,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
- cmd.metadata_len, 0, &cmd.result, timeout, flags);
+ cmd.metadata_len, &cmd.result, timeout, flags);
if (status >= 0) {
if (put_user(cmd.result, &ucmd->result))
@@ -397,7 +412,7 @@ struct nvme_uring_cmd_pdu {
static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
struct io_uring_cmd *ioucmd)
{
- return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
+ return io_uring_cmd_to_pdu(ioucmd, struct nvme_uring_cmd_pdu);
}
static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
@@ -416,20 +431,30 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
struct io_uring_cmd *ioucmd = req->end_io_data;
struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
- if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+ if (nvme_req(req)->flags & NVME_REQ_CANCELLED) {
pdu->status = -EINTR;
- else
+ } else {
pdu->status = nvme_req(req)->status;
+ if (!pdu->status)
+ pdu->status = blk_status_to_errno(err);
+ }
pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
/*
- * For iopoll, complete it directly.
+ * For iopoll, complete it directly. Note that using the uring_cmd
+ * helper for this is safe only because we check blk_rq_is_poll().
+ * As that returns false if we're NOT on a polled queue, then it's
+ * safe to use the polled completion helper.
+ *
* Otherwise, move the completion to task work.
*/
- if (blk_rq_is_poll(req))
- nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
- else
+ if (blk_rq_is_poll(req)) {
+ if (pdu->bio)
+ blk_rq_unmap_user(pdu->bio);
+ io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
+ } else {
io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
+ }
return RQ_END_IO_FREE;
}
@@ -492,7 +517,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
if (d.addr && d.data_len) {
ret = nvme_map_user_request(req, d.addr,
d.data_len, nvme_to_user_ptr(d.metadata),
- d.metadata_len, 0, ioucmd, vec);
+ d.metadata_len, ioucmd, vec);
if (ret)
return ret;
}
@@ -620,8 +645,6 @@ static int nvme_ns_uring_cmd(struct nvme_ns *ns, struct io_uring_cmd *ioucmd,
struct nvme_ctrl *ctrl = ns->ctrl;
int ret;
- BUILD_BUG_ON(sizeof(struct nvme_uring_cmd_pdu) > sizeof(ioucmd->pdu));
-
ret = nvme_uring_cmd_checks(issue_flags);
if (ret)
return ret;
@@ -782,15 +805,15 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
bool open_for_write)
{
struct nvme_ns *ns;
- int ret;
+ int ret, srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
if (list_empty(&ctrl->namespaces)) {
ret = -ENOTTY;
goto out_unlock;
}
- ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
+ ns = list_first_or_null_rcu(&ctrl->namespaces, struct nvme_ns, list);
if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
dev_warn(ctrl->device,
"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
@@ -800,15 +823,18 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
dev_warn(ctrl->device,
"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
- kref_get(&ns->kref);
- up_read(&ctrl->namespaces_rwsem);
+ if (!nvme_get_ns(ns)) {
+ ret = -ENXIO;
+ goto out_unlock;
+ }
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write);
nvme_put_ns(ns);
return ret;
out_unlock:
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return ret;
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 74de1e64aeea..2a7635565083 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -17,6 +17,7 @@ MODULE_PARM_DESC(multipath,
static const char *nvme_iopolicy_names[] = {
[NVME_IOPOLICY_NUMA] = "numa",
[NVME_IOPOLICY_RR] = "round-robin",
+ [NVME_IOPOLICY_QD] = "queue-depth",
};
static int iopolicy = NVME_IOPOLICY_NUMA;
@@ -29,6 +30,8 @@ static int nvme_set_iopolicy(const char *val, const struct kernel_param *kp)
iopolicy = NVME_IOPOLICY_NUMA;
else if (!strncmp(val, "round-robin", 11))
iopolicy = NVME_IOPOLICY_RR;
+ else if (!strncmp(val, "queue-depth", 11))
+ iopolicy = NVME_IOPOLICY_QD;
else
return -EINVAL;
@@ -43,7 +46,7 @@ static int nvme_get_iopolicy(char *buf, const struct kernel_param *kp)
module_param_call(iopolicy, nvme_set_iopolicy, nvme_get_iopolicy,
&iopolicy, 0644);
MODULE_PARM_DESC(iopolicy,
- "Default multipath I/O policy; 'numa' (default) or 'round-robin'");
+ "Default multipath I/O policy; 'numa' (default), 'round-robin' or 'queue-depth'");
void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
{
@@ -57,7 +60,7 @@ void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
lockdep_assert_held(&subsys->lock);
list_for_each_entry(h, &subsys->nsheads, entry)
if (h->disk)
- blk_mq_unfreeze_queue(h->disk->queue);
+ blk_mq_unfreeze_queue_nomemrestore(h->disk->queue);
}
void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
@@ -83,7 +86,7 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
void nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
- u16 status = nvme_req(req)->status & 0x7ff;
+ u16 status = nvme_req(req)->status & NVME_SCT_SC_MASK;
unsigned long flags;
struct bio *bio;
@@ -118,7 +121,8 @@ void nvme_failover_req(struct request *req)
blk_steal_bios(&ns->head->requeue_list, req);
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
- blk_mq_end_request(req, 0);
+ nvme_req(req)->status = 0;
+ nvme_end_req(req);
kblockd_schedule_work(&ns->head->requeue_work);
}
@@ -127,6 +131,11 @@ void nvme_mpath_start_request(struct request *rq)
struct nvme_ns *ns = rq->q->queuedata;
struct gendisk *disk = ns->head->disk;
+ if (READ_ONCE(ns->head->subsys->iopolicy) == NVME_IOPOLICY_QD) {
+ atomic_inc(&ns->ctrl->nr_active);
+ nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE;
+ }
+
if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq))
return;
@@ -140,6 +149,9 @@ void nvme_mpath_end_request(struct request *rq)
{
struct nvme_ns *ns = rq->q->queuedata;
+ if (nvme_req(rq)->flags & NVME_MPATH_CNT_ACTIVE)
+ atomic_dec_if_positive(&ns->ctrl->nr_active);
+
if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
return;
bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
@@ -150,16 +162,18 @@ void nvme_mpath_end_request(struct request *rq)
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu)) {
if (!ns->head->disk)
continue;
kblockd_schedule_work(&ns->head->requeue_work);
if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
disk_uevent(ns->head->disk, KOBJ_CHANGE);
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
static const char *nvme_ana_state_names[] = {
@@ -193,13 +207,15 @@ out:
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu)) {
nvme_mpath_clear_current_path(ns);
kblockd_schedule_work(&ns->head->requeue_work);
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -210,7 +226,8 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
int srcu_idx;
srcu_idx = srcu_read_lock(&head->srcu);
- list_for_each_entry_rcu(ns, &head->list, siblings) {
+ list_for_each_entry_srcu(ns, &head->list, siblings,
+ srcu_read_lock_held(&head->srcu)) {
if (capacity != get_capacity(ns->disk))
clear_bit(NVME_NS_READY, &ns->flags);
}
@@ -243,11 +260,13 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
int found_distance = INT_MAX, fallback_distance = INT_MAX, distance;
struct nvme_ns *found = NULL, *fallback = NULL, *ns;
- list_for_each_entry_rcu(ns, &head->list, siblings) {
+ list_for_each_entry_srcu(ns, &head->list, siblings,
+ srcu_read_lock_held(&head->srcu)) {
if (nvme_path_is_disabled(ns))
continue;
- if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
+ if (ns->ctrl->numa_node != NUMA_NO_NODE &&
+ READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
distance = node_distance(node, ns->ctrl->numa_node);
else
distance = LOCAL_DISTANCE;
@@ -287,10 +306,15 @@ static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head,
return list_first_or_null_rcu(&head->list, struct nvme_ns, siblings);
}
-static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
- int node, struct nvme_ns *old)
+static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head)
{
struct nvme_ns *ns, *found = NULL;
+ int node = numa_node_id();
+ struct nvme_ns *old = srcu_dereference(head->current_path[node],
+ &head->srcu);
+
+ if (unlikely(!old))
+ return __nvme_find_path(head, node);
if (list_is_singular(&head->list)) {
if (nvme_path_is_disabled(old))
@@ -330,13 +354,50 @@ out:
return found;
}
+static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
+{
+ struct nvme_ns *best_opt = NULL, *best_nonopt = NULL, *ns;
+ unsigned int min_depth_opt = UINT_MAX, min_depth_nonopt = UINT_MAX;
+ unsigned int depth;
+
+ list_for_each_entry_srcu(ns, &head->list, siblings,
+ srcu_read_lock_held(&head->srcu)) {
+ if (nvme_path_is_disabled(ns))
+ continue;
+
+ depth = atomic_read(&ns->ctrl->nr_active);
+
+ switch (ns->ana_state) {
+ case NVME_ANA_OPTIMIZED:
+ if (depth < min_depth_opt) {
+ min_depth_opt = depth;
+ best_opt = ns;
+ }
+ break;
+ case NVME_ANA_NONOPTIMIZED:
+ if (depth < min_depth_nonopt) {
+ min_depth_nonopt = depth;
+ best_nonopt = ns;
+ }
+ break;
+ default:
+ break;
+ }
+
+ if (min_depth_opt == 0)
+ return best_opt;
+ }
+
+ return best_opt ? best_opt : best_nonopt;
+}
+
static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
{
return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
ns->ana_state == NVME_ANA_OPTIMIZED;
}
-inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
+static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
{
int node = numa_node_id();
struct nvme_ns *ns;
@@ -344,26 +405,38 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
ns = srcu_dereference(head->current_path[node], &head->srcu);
if (unlikely(!ns))
return __nvme_find_path(head, node);
-
- if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR)
- return nvme_round_robin_path(head, node, ns);
if (unlikely(!nvme_path_is_optimized(ns)))
return __nvme_find_path(head, node);
return ns;
}
+inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
+{
+ switch (READ_ONCE(head->subsys->iopolicy)) {
+ case NVME_IOPOLICY_QD:
+ return nvme_queue_depth_path(head);
+ case NVME_IOPOLICY_RR:
+ return nvme_round_robin_path(head);
+ default:
+ return nvme_numa_path(head);
+ }
+}
+
static bool nvme_available_path(struct nvme_ns_head *head)
{
struct nvme_ns *ns;
- list_for_each_entry_rcu(ns, &head->list, siblings) {
+ if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
+ return NULL;
+
+ list_for_each_entry_srcu(ns, &head->list, siblings,
+ srcu_read_lock_held(&head->srcu)) {
if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
continue;
switch (nvme_ctrl_state(ns->ctrl)) {
case NVME_CTRL_LIVE:
case NVME_CTRL_RESETTING:
case NVME_CTRL_CONNECTING:
- /* fallthru */
return true;
default:
break;
@@ -423,6 +496,21 @@ static void nvme_ns_head_release(struct gendisk *disk)
nvme_put_ns_head(disk->private_data);
}
+static int nvme_ns_head_get_unique_id(struct gendisk *disk, u8 id[16],
+ enum blk_unique_id type)
+{
+ struct nvme_ns_head *head = disk->private_data;
+ struct nvme_ns *ns;
+ int srcu_idx, ret = -EWOULDBLOCK;
+
+ srcu_idx = srcu_read_lock(&head->srcu);
+ ns = nvme_find_path(head);
+ if (ns)
+ ret = nvme_ns_get_unique_id(ns, id, type);
+ srcu_read_unlock(&head->srcu, srcu_idx);
+ return ret;
+}
+
#ifdef CONFIG_BLK_DEV_ZONED
static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
@@ -450,6 +538,7 @@ const struct block_device_operations nvme_ns_head_ops = {
.ioctl = nvme_ns_head_ioctl,
.compat_ioctl = blkdev_compat_ptr_ioctl,
.getgeo = nvme_getgeo,
+ .get_unique_id = nvme_ns_head_get_unique_id,
.report_zones = nvme_ns_head_report_zones,
.pr_ops = &nvme_pr_ops,
};
@@ -496,6 +585,20 @@ static int nvme_add_ns_head_cdev(struct nvme_ns_head *head)
return ret;
}
+static void nvme_partition_scan_work(struct work_struct *work)
+{
+ struct nvme_ns_head *head =
+ container_of(work, struct nvme_ns_head, partition_scan_work);
+
+ if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN,
+ &head->disk->state)))
+ return;
+
+ mutex_lock(&head->disk->open_mutex);
+ bdev_disk_changed(head->disk, false);
+ mutex_unlock(&head->disk->open_mutex);
+}
+
static void nvme_requeue_work(struct work_struct *work)
{
struct nvme_ns_head *head =
@@ -516,12 +619,13 @@ static void nvme_requeue_work(struct work_struct *work)
int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
{
- bool vwc = false;
+ struct queue_limits lim;
mutex_init(&head->lock);
bio_list_init(&head->requeue_list);
spin_lock_init(&head->requeue_lock);
INIT_WORK(&head->requeue_work, nvme_requeue_work);
+ INIT_WORK(&head->partition_scan_work, nvme_partition_scan_work);
/*
* Add a multipath node if the subsystems supports multiple controllers.
@@ -532,36 +636,29 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
!nvme_is_unique_nsid(ctrl, head) || !multipath)
return 0;
- head->disk = blk_alloc_disk(ctrl->numa_node);
- if (!head->disk)
- return -ENOMEM;
+ blk_set_stacking_limits(&lim);
+ lim.dma_alignment = 3;
+ lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
+ if (head->ids.csi == NVME_CSI_ZNS)
+ lim.features |= BLK_FEAT_ZONED;
+
+ head->disk = blk_alloc_disk(&lim, ctrl->numa_node);
+ if (IS_ERR(head->disk))
+ return PTR_ERR(head->disk);
head->disk->fops = &nvme_ns_head_ops;
head->disk->private_data = head;
- sprintf(head->disk->disk_name, "nvme%dn%d",
- ctrl->subsys->instance, head->instance);
- blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
- blk_queue_flag_set(QUEUE_FLAG_IO_STAT, head->disk->queue);
/*
- * This assumes all controllers that refer to a namespace either
- * support poll queues or not. That is not a strict guarantee,
- * but if the assumption is wrong the effect is only suboptimal
- * performance but not correctness problem.
+ * We need to suppress the partition scan from occuring within the
+ * controller's scan_work context. If a path error occurs here, the IO
+ * will wait until a path becomes available or all paths are torn down,
+ * but that action also occurs within scan_work, so it would deadlock.
+ * Defer the partion scan to a different context that does not block
+ * scan_work.
*/
- if (ctrl->tagset->nr_maps > HCTX_TYPE_POLL &&
- ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
- blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
-
- /* set to a default value of 512 until the disk is validated */
- blk_queue_logical_block_size(head->disk->queue, 512);
- blk_set_stacking_limits(&head->disk->queue->limits);
- blk_queue_dma_alignment(head->disk->queue, 3);
-
- /* we need to propagate up the VMC settings */
- if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
- vwc = true;
- blk_queue_write_cache(head->disk->queue, vwc, vwc);
+ set_bit(GD_SUPPRESS_PART_SCAN, &head->disk->state);
+ sprintf(head->disk->disk_name, "nvme%dn%d",
+ ctrl->subsys->instance, head->instance);
return 0;
}
@@ -582,10 +679,11 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
rc = device_add_disk(&head->subsys->dev, head->disk,
nvme_ns_attr_groups);
if (rc) {
- clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
+ clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags);
return;
}
nvme_add_ns_head_cdev(head);
+ kblockd_schedule_work(&head->partition_scan_work);
}
mutex_lock(&head->lock);
@@ -593,7 +691,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
int node, srcu_idx;
srcu_idx = srcu_read_lock(&head->srcu);
- for_each_node(node)
+ for_each_online_node(node)
__nvme_find_path(head, node);
srcu_read_unlock(&head->srcu, srcu_idx);
}
@@ -678,6 +776,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
unsigned *nr_change_groups = data;
struct nvme_ns *ns;
+ int srcu_idx;
dev_dbg(ctrl->device, "ANA group %d: %s.\n",
le32_to_cpu(desc->grpid),
@@ -689,8 +788,9 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
if (!nr_nsids)
return 0;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
+ srcu_read_lock_held(&ctrl->srcu)) {
unsigned nsid;
again:
nsid = le32_to_cpu(desc->nsids[n]);
@@ -703,7 +803,7 @@ again:
if (ns->head->ns_id > nsid)
goto again;
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return 0;
}
@@ -797,6 +897,29 @@ static ssize_t nvme_subsys_iopolicy_show(struct device *dev,
nvme_iopolicy_names[READ_ONCE(subsys->iopolicy)]);
}
+static void nvme_subsys_iopolicy_update(struct nvme_subsystem *subsys,
+ int iopolicy)
+{
+ struct nvme_ctrl *ctrl;
+ int old_iopolicy = READ_ONCE(subsys->iopolicy);
+
+ if (old_iopolicy == iopolicy)
+ return;
+
+ WRITE_ONCE(subsys->iopolicy, iopolicy);
+
+ /* iopolicy changes clear the mpath by design */
+ mutex_lock(&nvme_subsystems_lock);
+ list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+ nvme_mpath_clear_ctrl_paths(ctrl);
+ mutex_unlock(&nvme_subsystems_lock);
+
+ pr_notice("subsysnqn %s iopolicy changed from %s to %s\n",
+ subsys->subnqn,
+ nvme_iopolicy_names[old_iopolicy],
+ nvme_iopolicy_names[iopolicy]);
+}
+
static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
@@ -806,7 +929,7 @@ static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) {
if (sysfs_streq(buf, nvme_iopolicy_names[i])) {
- WRITE_ONCE(subsys->iopolicy, i);
+ nvme_subsys_iopolicy_update(subsys, i);
return count;
}
}
@@ -869,9 +992,6 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid)
nvme_mpath_set_live(ns);
}
- if (blk_queue_stable_writes(ns->queue) && ns->head->disk)
- blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
- ns->head->disk->queue);
#ifdef CONFIG_BLK_DEV_ZONED
if (blk_queue_is_zoned(ns->queue) && ns->head->disk)
ns->head->disk->nr_zones = ns->disk->nr_zones;
@@ -882,9 +1002,14 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
{
if (!head->disk)
return;
- kblockd_schedule_work(&head->requeue_work);
- if (test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+ if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
nvme_cdev_del(&head->cdev, &head->cdev_device);
+ /*
+ * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared
+ * to allow multipath to fail all I/O.
+ */
+ synchronize_srcu(&head->srcu);
+ kblockd_schedule_work(&head->requeue_work);
del_gendisk(head->disk);
}
}
@@ -896,6 +1021,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
/* make sure all pending bios are cleaned up */
kblockd_schedule_work(&head->requeue_work);
flush_work(&head->requeue_work);
+ flush_work(&head->partition_scan_work);
put_disk(head->disk);
}
@@ -917,6 +1043,9 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
!(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA))
return 0;
+ /* initialize this in the identify path to cover controller resets */
+ atomic_set(&ctrl->nr_active, 0);
+
if (!ctrl->max_namespaces ||
ctrl->max_namespaces > le32_to_cpu(id->nn)) {
dev_err(ctrl->device,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 7b87763e2f8a..7be92d07430e 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -49,6 +49,7 @@ extern unsigned int admin_timeout;
extern struct workqueue_struct *nvme_wq;
extern struct workqueue_struct *nvme_reset_wq;
extern struct workqueue_struct *nvme_delete_wq;
+extern struct mutex nvme_subsystems_lock;
/*
* List of workarounds for devices that required behavior not specified in
@@ -90,6 +91,11 @@ enum nvme_quirks {
NVME_QUIRK_NO_DEEPEST_PS = (1 << 5),
/*
+ * Problems seen with concurrent commands
+ */
+ NVME_QUIRK_QDEPTH_ONE = (1 << 6),
+
+ /*
* Set MEDIUM priority on SQ creation
*/
NVME_QUIRK_MEDIUM_PRIO_SQ = (1 << 7),
@@ -162,6 +168,16 @@ enum nvme_quirks {
* Disables simple suspend/resume path.
*/
NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND = (1 << 20),
+
+ /*
+ * MSI (but not MSI-X) interrupts are broken and never fire.
+ */
+ NVME_QUIRK_BROKEN_MSI = (1 << 21),
+
+ /*
+ * Align dma pool segment size to 512 bytes
+ */
+ NVME_QUIRK_DMAPOOL_ALIGN_512 = (1 << 22),
};
/*
@@ -190,6 +206,7 @@ enum {
NVME_REQ_CANCELLED = (1 << 0),
NVME_REQ_USERCMD = (1 << 1),
NVME_MPATH_IO_STATS = (1 << 2),
+ NVME_MPATH_CNT_ACTIVE = (1 << 3),
};
static inline struct nvme_request *nvme_req(struct request *req)
@@ -277,7 +294,8 @@ struct nvme_ctrl {
struct blk_mq_tag_set *tagset;
struct blk_mq_tag_set *admin_tagset;
struct list_head namespaces;
- struct rw_semaphore namespaces_rwsem;
+ struct mutex namespaces_lock;
+ struct srcu_struct srcu;
struct device ctrl_device;
struct device *device; /* char device */
#ifdef CONFIG_NVME_HWMON
@@ -293,7 +311,6 @@ struct nvme_ctrl {
struct opal_dev *opal_dev;
- char name[12];
u16 cntlid;
u16 mtfa;
@@ -354,6 +371,7 @@ struct nvme_ctrl {
size_t ana_log_size;
struct timer_list anatt_timer;
struct work_struct ana_work;
+ atomic_t nr_active;
#endif
#ifdef CONFIG_NVME_HOST_AUTH
@@ -364,7 +382,7 @@ struct nvme_ctrl {
struct nvme_dhchap_key *ctrl_key;
u16 transaction;
#endif
- struct key *tls_key;
+ key_serial_t tls_pskid;
/* Power saving configuration */
u64 ps_max_latency_us;
@@ -402,6 +420,7 @@ static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
enum nvme_iopolicy {
NVME_IOPOLICY_NUMA,
NVME_IOPOLICY_RR,
+ NVME_IOPOLICY_QD,
};
struct nvme_subsystem {
@@ -452,21 +471,20 @@ struct nvme_ns_head {
struct srcu_struct srcu;
struct nvme_subsystem *subsys;
struct nvme_ns_ids ids;
+ u8 lba_shift;
+ u16 ms;
+ u16 pi_size;
+ u8 pi_type;
+ u8 guard_type;
struct list_head entry;
struct kref ref;
bool shared;
+ bool rotational;
bool passthru_err_log_enabled;
- int instance;
struct nvme_effects_log *effects;
u64 nuse;
unsigned ns_id;
- int lba_shift;
- u16 ms;
- u16 pi_size;
- u8 pi_type;
- u8 guard_type;
- u16 sgs;
- u32 sws;
+ int instance;
#ifdef CONFIG_BLK_DEV_ZONED
u64 zsze;
#endif
@@ -482,6 +500,7 @@ struct nvme_ns_head {
struct bio_list requeue_list;
spinlock_t requeue_lock;
struct work_struct requeue_work;
+ struct work_struct partition_scan_work;
struct mutex lock;
unsigned long flags;
#define NVME_NSHEAD_DISK_LIVE 0
@@ -497,7 +516,7 @@ static inline bool nvme_ns_head_multipath(struct nvme_ns_head *head)
enum nvme_ns_features {
NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
- NVME_NS_DEAC, /* DEAC bit in Write Zeores supported */
+ NVME_NS_DEAC = 1 << 2, /* DEAC bit in Write Zeores supported */
};
struct nvme_ns {
@@ -546,6 +565,7 @@ struct nvme_ctrl_ops {
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
void (*free_ctrl)(struct nvme_ctrl *ctrl);
void (*submit_async_event)(struct nvme_ctrl *ctrl);
+ int (*subsystem_reset)(struct nvme_ctrl *ctrl);
void (*delete_ctrl)(struct nvme_ctrl *ctrl);
void (*stop_ctrl)(struct nvme_ctrl *ctrl);
int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
@@ -644,18 +664,9 @@ int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
{
- int ret;
-
- if (!ctrl->subsystem)
+ if (!ctrl->subsystem || !ctrl->ops->subsystem_reset)
return -ENOTTY;
- if (!nvme_wait_reset(ctrl))
- return -EBUSY;
-
- ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65);
- if (ret)
- return ret;
-
- return nvme_try_sched_reset(ctrl);
+ return ctrl->ops->subsystem_reset(ctrl);
}
/*
@@ -684,7 +695,7 @@ static inline u32 nvme_bytes_to_numd(size_t len)
static inline bool nvme_is_ana_error(u16 status)
{
- switch (status & 0x7ff) {
+ switch (status & NVME_SCT_SC_MASK) {
case NVME_SC_ANA_TRANSITION:
case NVME_SC_ANA_INACCESSIBLE:
case NVME_SC_ANA_PERSISTENT_LOSS:
@@ -697,7 +708,7 @@ static inline bool nvme_is_ana_error(u16 status)
static inline bool nvme_is_path_error(u16 status)
{
/* check for a status code type of 'path related status' */
- return (status & 0x700) == 0x300;
+ return (status & NVME_SCT_MASK) == NVME_SCT_PATH;
}
/*
@@ -740,6 +751,28 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
nvme_tag_from_cid(command_id) >= NVME_AQ_BLK_MQ_DEPTH;
}
+/*
+ * Returns true for sink states that can't ever transition back to live.
+ */
+static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl)
+{
+ switch (nvme_ctrl_state(ctrl)) {
+ case NVME_CTRL_NEW:
+ case NVME_CTRL_LIVE:
+ case NVME_CTRL_RESETTING:
+ case NVME_CTRL_CONNECTING:
+ return false;
+ case NVME_CTRL_DELETING:
+ case NVME_CTRL_DELETING_NOIO:
+ case NVME_CTRL_DEAD:
+ return true;
+ default:
+ WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
+ return true;
+ }
+}
+
+void nvme_end_req(struct request *req);
void nvme_complete_rq(struct request *req);
void nvme_complete_batch_req(struct request *req);
@@ -765,6 +798,7 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, bool shutdown);
int nvme_enable_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
const struct nvme_ctrl_ops *ops, unsigned long quirks);
+int nvme_add_ctrl(struct nvme_ctrl *ctrl);
void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
void nvme_start_ctrl(struct nvme_ctrl *ctrl);
void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
@@ -850,7 +884,7 @@ enum {
NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1),
/* Set BLK_MQ_REQ_RESERVED when allocating request */
NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2),
- /* Retry command when NVME_SC_DNR is not set in the result */
+ /* Retry command when NVME_STATUS_DNR is not set in the result */
NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3),
};
@@ -1035,11 +1069,22 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
}
#endif /* CONFIG_NVME_MULTIPATH */
-int nvme_revalidate_zones(struct nvme_ns *ns);
+int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16],
+ enum blk_unique_id type);
+
+struct nvme_zone_info {
+ u64 zone_size;
+ unsigned int max_open_zones;
+ unsigned int max_active_zones;
+};
+
int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+ struct nvme_zone_info *zi);
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+ struct nvme_zone_info *zi);
#ifdef CONFIG_BLK_DEV_ZONED
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmnd,
enum nvme_zone_mgmt_action action);
@@ -1050,13 +1095,6 @@ static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
{
return BLK_STS_NOTSUPP;
}
-
-static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
-{
- dev_warn(ns->ctrl->device,
- "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
- return -EPROTONOSUPPORT;
-}
#endif
static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
@@ -1090,7 +1128,15 @@ static inline void nvme_start_request(struct request *rq)
static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl)
{
- return ctrl->sgls & ((1 << 0) | (1 << 1));
+ return ctrl->sgls & (NVME_CTRL_SGLS_BYTE_ALIGNED |
+ NVME_CTRL_SGLS_DWORD_ALIGNED);
+}
+
+static inline bool nvme_ctrl_meta_sgl_supported(struct nvme_ctrl *ctrl)
+{
+ if (ctrl->ops->flags & NVME_F_FABRICS)
+ return true;
+ return ctrl->sgls & NVME_CTRL_SGLS_MSDS;
}
#ifdef CONFIG_NVME_HOST_AUTH
@@ -1120,7 +1166,7 @@ static inline int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid)
}
static inline int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid)
{
- return NVME_SC_AUTH_REQUIRED;
+ return -EPROTONOSUPPORT;
}
static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {};
#endif
@@ -1133,6 +1179,7 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects,
struct nvme_command *cmd, int status);
struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
+bool nvme_get_ns(struct nvme_ns *ns);
void nvme_put_ns(struct nvme_ns *ns);
static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
@@ -1140,43 +1187,4 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
}
-#ifdef CONFIG_NVME_VERBOSE_ERRORS
-const char *nvme_get_error_status_str(u16 status);
-const char *nvme_get_opcode_str(u8 opcode);
-const char *nvme_get_admin_opcode_str(u8 opcode);
-const char *nvme_get_fabrics_opcode_str(u8 opcode);
-#else /* CONFIG_NVME_VERBOSE_ERRORS */
-static inline const char *nvme_get_error_status_str(u16 status)
-{
- return "I/O Error";
-}
-static inline const char *nvme_get_opcode_str(u8 opcode)
-{
- return "I/O Cmd";
-}
-static inline const char *nvme_get_admin_opcode_str(u8 opcode)
-{
- return "Admin Cmd";
-}
-
-static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
-{
- return "Fabrics Cmd";
-}
-#endif /* CONFIG_NVME_VERBOSE_ERRORS */
-
-static inline const char *nvme_opcode_str(int qid, u8 opcode)
-{
- return qid ? nvme_get_opcode_str(opcode) :
- nvme_get_admin_opcode_str(opcode);
-}
-
-static inline const char *nvme_fabrics_opcode_str(
- int qid, const struct nvme_command *cmd)
-{
- if (nvme_is_fabrics(cmd))
- return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype);
-
- return nvme_opcode_str(qid, cmd->common.opcode);
-}
#endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index e6267a6aa380..3ad7f197c808 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -8,7 +8,6 @@
#include <linux/async.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
-#include <linux/blk-mq-pci.h>
#include <linux/blk-integrity.h>
#include <linux/dmi.h>
#include <linux/init.h>
@@ -43,6 +42,7 @@
*/
#define NVME_MAX_KB_SZ 8192
#define NVME_MAX_SEGS 128
+#define NVME_MAX_META_SEGS 15
#define NVME_MAX_NR_ALLOCATIONS 5
static int use_threaded_interrupts;
@@ -141,8 +141,10 @@ struct nvme_dev {
struct nvme_ctrl ctrl;
u32 last_ps;
bool hmb;
+ struct sg_table *hmb_sgt;
mempool_t *iod_mempool;
+ mempool_t *iod_meta_mempool;
/* shadow doorbell buffer support: */
__le32 *dbbuf_dbs;
@@ -153,6 +155,7 @@ struct nvme_dev {
/* host memory buffer support: */
u64 host_mem_size;
u32 nr_host_mem_descs;
+ u32 host_mem_descs_size;
dma_addr_t host_mem_descs_dma;
struct nvme_host_mem_buf_desc *host_mem_descs;
void **host_mem_desc_bufs;
@@ -237,6 +240,8 @@ struct nvme_iod {
dma_addr_t first_dma;
dma_addr_t meta_dma;
struct sg_table sgt;
+ struct sg_table meta_sgt;
+ union nvme_descriptor meta_list;
union nvme_descriptor list[NVME_MAX_NR_ALLOCATIONS];
};
@@ -367,7 +372,7 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
/*
* Ensure that the doorbell is updated before reading the event
* index from memory. The controller needs to provide similar
- * ordering to ensure the envent index is updated before reading
+ * ordering to ensure the event index is updated before reading
* the doorbell.
*/
mb();
@@ -457,7 +462,7 @@ static void nvme_pci_map_queues(struct blk_mq_tag_set *set)
*/
map->queue_offset = qoff;
if (i != HCTX_TYPE_POLL && offset)
- blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
+ blk_mq_map_hw_queues(map, dev->dev, offset);
else
blk_mq_map_queues(map);
qoff += map->nr_queues;
@@ -504,6 +509,15 @@ static void nvme_commit_rqs(struct blk_mq_hw_ctx *hctx)
spin_unlock(&nvmeq->sq_lock);
}
+static inline bool nvme_pci_metadata_use_sgls(struct nvme_dev *dev,
+ struct request *req)
+{
+ if (!nvme_ctrl_meta_sgl_supported(&dev->ctrl))
+ return false;
+ return req->nr_integrity_segments > 1 ||
+ nvme_req(req)->flags & NVME_REQ_USERCMD;
+}
+
static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
int nseg)
{
@@ -516,8 +530,10 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req,
return false;
if (!nvmeq->qid)
return false;
+ if (nvme_pci_metadata_use_sgls(dev, req))
+ return true;
if (!sgl_threshold || avg_seg_size < sgl_threshold)
- return false;
+ return nvme_req(req)->flags & NVME_REQ_USERCMD;
return true;
}
@@ -778,7 +794,9 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
struct bio_vec bv = req_bvec(req);
if (!is_pci_p2pdma_page(bv.bv_page)) {
- if (bv.bv_offset + bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
+ if (!nvme_pci_metadata_use_sgls(dev, req) &&
+ (bv.bv_offset & (NVME_CTRL_PAGE_SIZE - 1)) +
+ bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
return nvme_setup_prp_simple(dev, req,
&cmnd->rw, &bv);
@@ -821,19 +839,84 @@ out_free_sg:
return ret;
}
-static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
- struct nvme_command *cmnd)
+static blk_status_t nvme_pci_setup_meta_sgls(struct nvme_dev *dev,
+ struct request *req)
+{
+ struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+ struct nvme_rw_command *cmnd = &iod->cmd.rw;
+ struct nvme_sgl_desc *sg_list;
+ struct scatterlist *sgl, *sg;
+ unsigned int entries;
+ dma_addr_t sgl_dma;
+ int rc, i;
+
+ iod->meta_sgt.sgl = mempool_alloc(dev->iod_meta_mempool, GFP_ATOMIC);
+ if (!iod->meta_sgt.sgl)
+ return BLK_STS_RESOURCE;
+
+ sg_init_table(iod->meta_sgt.sgl, req->nr_integrity_segments);
+ iod->meta_sgt.orig_nents = blk_rq_map_integrity_sg(req,
+ iod->meta_sgt.sgl);
+ if (!iod->meta_sgt.orig_nents)
+ goto out_free_sg;
+
+ rc = dma_map_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req),
+ DMA_ATTR_NO_WARN);
+ if (rc)
+ goto out_free_sg;
+
+ sg_list = dma_pool_alloc(dev->prp_small_pool, GFP_ATOMIC, &sgl_dma);
+ if (!sg_list)
+ goto out_unmap_sg;
+
+ entries = iod->meta_sgt.nents;
+ iod->meta_list.sg_list = sg_list;
+ iod->meta_dma = sgl_dma;
+
+ cmnd->flags = NVME_CMD_SGL_METASEG;
+ cmnd->metadata = cpu_to_le64(sgl_dma);
+
+ sgl = iod->meta_sgt.sgl;
+ if (entries == 1) {
+ nvme_pci_sgl_set_data(sg_list, sgl);
+ return BLK_STS_OK;
+ }
+
+ sgl_dma += sizeof(*sg_list);
+ nvme_pci_sgl_set_seg(sg_list, sgl_dma, entries);
+ for_each_sg(sgl, sg, entries, i)
+ nvme_pci_sgl_set_data(&sg_list[i + 1], sg);
+
+ return BLK_STS_OK;
+
+out_unmap_sg:
+ dma_unmap_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req), 0);
+out_free_sg:
+ mempool_free(iod->meta_sgt.sgl, dev->iod_meta_mempool);
+ return BLK_STS_RESOURCE;
+}
+
+static blk_status_t nvme_pci_setup_meta_mptr(struct nvme_dev *dev,
+ struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+ struct bio_vec bv = rq_integrity_vec(req);
+ struct nvme_command *cmnd = &iod->cmd;
- iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
- rq_dma_dir(req), 0);
+ iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0);
if (dma_mapping_error(dev->dev, iod->meta_dma))
return BLK_STS_IOERR;
cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
return BLK_STS_OK;
}
+static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req)
+{
+ if (nvme_pci_metadata_use_sgls(dev, req))
+ return nvme_pci_setup_meta_sgls(dev, req);
+ return nvme_pci_setup_meta_mptr(dev, req);
+}
+
static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
@@ -842,6 +925,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
iod->aborted = false;
iod->nr_allocations = -1;
iod->sgt.nents = 0;
+ iod->meta_sgt.nents = 0;
ret = nvme_setup_cmd(req->q->queuedata, req);
if (ret)
@@ -854,7 +938,7 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
}
if (blk_integrity_rq(req)) {
- ret = nvme_map_metadata(dev, req, &iod->cmd);
+ ret = nvme_map_metadata(dev, req);
if (ret)
goto out_unmap_data;
}
@@ -862,7 +946,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
nvme_start_request(req);
return BLK_STS_OK;
out_unmap_data:
- nvme_unmap_data(dev, req);
+ if (blk_rq_nr_phys_segments(req))
+ nvme_unmap_data(dev, req);
out_free_cmd:
nvme_cleanup_cmd(req);
return ret;
@@ -900,11 +985,12 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
return BLK_STS_OK;
}
-static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct request **rqlist)
+static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct rq_list *rqlist)
{
+ struct request *req;
+
spin_lock(&nvmeq->sq_lock);
- while (!rq_list_empty(*rqlist)) {
- struct request *req = rq_list_pop(rqlist);
+ while ((req = rq_list_pop(rqlist))) {
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
nvme_sq_copy_cmd(nvmeq, &iod->cmd);
@@ -927,34 +1013,45 @@ static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req)
return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK;
}
-static void nvme_queue_rqs(struct request **rqlist)
+static void nvme_queue_rqs(struct rq_list *rqlist)
{
- struct request *req, *next, *prev = NULL;
- struct request *requeue_list = NULL;
+ struct rq_list submit_list = { };
+ struct rq_list requeue_list = { };
+ struct nvme_queue *nvmeq = NULL;
+ struct request *req;
- rq_list_for_each_safe(rqlist, req, next) {
- struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
+ while ((req = rq_list_pop(rqlist))) {
+ if (nvmeq && nvmeq != req->mq_hctx->driver_data)
+ nvme_submit_cmds(nvmeq, &submit_list);
+ nvmeq = req->mq_hctx->driver_data;
- if (!nvme_prep_rq_batch(nvmeq, req)) {
- /* detach 'req' and add to remainder list */
- rq_list_move(rqlist, &requeue_list, req, prev);
+ if (nvme_prep_rq_batch(nvmeq, req))
+ rq_list_add_tail(&submit_list, req);
+ else
+ rq_list_add_tail(&requeue_list, req);
+ }
- req = prev;
- if (!req)
- continue;
- }
+ if (nvmeq)
+ nvme_submit_cmds(nvmeq, &submit_list);
+ *rqlist = requeue_list;
+}
- if (!next || req->mq_hctx != next->mq_hctx) {
- /* detach rest of list, and submit */
- req->rq_next = NULL;
- nvme_submit_cmds(nvmeq, rqlist);
- *rqlist = next;
- prev = NULL;
- } else
- prev = req;
+static __always_inline void nvme_unmap_metadata(struct nvme_dev *dev,
+ struct request *req)
+{
+ struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+ if (!iod->meta_sgt.nents) {
+ dma_unmap_page(dev->dev, iod->meta_dma,
+ rq_integrity_vec(req).bv_len,
+ rq_dma_dir(req));
+ return;
}
- *rqlist = requeue_list;
+ dma_pool_free(dev->prp_small_pool, iod->meta_list.sg_list,
+ iod->meta_dma);
+ dma_unmap_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req), 0);
+ mempool_free(iod->meta_sgt.sgl, dev->iod_meta_mempool);
}
static __always_inline void nvme_pci_unmap_rq(struct request *req)
@@ -962,12 +1059,8 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
struct nvme_dev *dev = nvmeq->dev;
- if (blk_integrity_rq(req)) {
- struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-
- dma_unmap_page(dev->dev, iod->meta_dma,
- rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
- }
+ if (blk_integrity_rq(req))
+ nvme_unmap_metadata(dev, req);
if (blk_rq_nr_phys_segments(req))
nvme_unmap_data(dev, req);
@@ -1037,8 +1130,9 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
- !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
- nvme_pci_complete_batch))
+ !blk_mq_add_to_batch(req, iob,
+ nvme_req(req)->status != NVME_SC_SUCCESS,
+ nvme_pci_complete_batch))
nvme_pci_complete_rq(req);
}
@@ -1054,13 +1148,13 @@ static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
}
}
-static inline int nvme_poll_cq(struct nvme_queue *nvmeq,
- struct io_comp_batch *iob)
+static inline bool nvme_poll_cq(struct nvme_queue *nvmeq,
+ struct io_comp_batch *iob)
{
- int found = 0;
+ bool found = false;
while (nvme_cqe_pending(nvmeq)) {
- found++;
+ found = true;
/*
* load-load control dependency between phase and the rest of
* the cqe requires a full read memory barrier
@@ -1081,7 +1175,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
DEFINE_IO_COMP_BATCH(iob);
if (nvme_poll_cq(nvmeq, &iob)) {
- if (!rq_list_empty(iob.req_list))
+ if (!rq_list_empty(&iob.req_list))
nvme_pci_complete_batch(&iob);
return IRQ_HANDLED;
}
@@ -1142,6 +1236,41 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
spin_unlock(&nvmeq->sq_lock);
}
+static int nvme_pci_subsystem_reset(struct nvme_ctrl *ctrl)
+{
+ struct nvme_dev *dev = to_nvme_dev(ctrl);
+ int ret = 0;
+
+ /*
+ * Taking the shutdown_lock ensures the BAR mapping is not being
+ * altered by reset_work. Holding this lock before the RESETTING state
+ * change, if successful, also ensures nvme_remove won't be able to
+ * proceed to iounmap until we're done.
+ */
+ mutex_lock(&dev->shutdown_lock);
+ if (!dev->bar_mapped_size) {
+ ret = -ENODEV;
+ goto unlock;
+ }
+
+ if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) {
+ ret = -EBUSY;
+ goto unlock;
+ }
+
+ writel(NVME_SUBSYS_RESET, dev->bar + NVME_REG_NSSR);
+ nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE);
+
+ /*
+ * Read controller status to flush the previous write and trigger a
+ * pcie read error.
+ */
+ readl(dev->bar + NVME_REG_CSTS);
+unlock:
+ mutex_unlock(&dev->shutdown_lock);
+ return ret;
+}
+
static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
{
struct nvme_command c = { };
@@ -1273,7 +1402,7 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
dev_warn(dev->ctrl.device,
"Does your device have a faulty power saving mode enabled?\n");
dev_warn(dev->ctrl.device,
- "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
+ "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off\" and report a bug\n");
}
static enum blk_eh_timer_return nvme_timeout(struct request *req)
@@ -1283,14 +1412,28 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
struct nvme_dev *dev = nvmeq->dev;
struct request *abort_req;
struct nvme_command cmd = { };
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
u32 csts = readl(dev->bar + NVME_REG_CSTS);
u8 opcode;
+ /*
+ * Shutdown the device immediately if we see it is disconnected. This
+ * unblocks PCIe error handling if the nvme driver is waiting in
+ * error_resume for a device that has been removed. We can't unbind the
+ * driver while the driver's error callback is waiting to complete, so
+ * we're relying on a timeout to break that deadlock if a removal
+ * occurs while reset work is running.
+ */
+ if (pci_dev_is_disconnected(pdev))
+ nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
+ if (nvme_state_terminal(&dev->ctrl))
+ goto disable;
+
/* If PCI error recovery process is happening, we cannot reset or
* the recovery mechanism will surely fail.
*/
mb();
- if (pci_channel_offline(to_pci_dev(dev->dev)))
+ if (pci_channel_offline(pdev))
return BLK_EH_RESET_TIMER;
/*
@@ -1390,8 +1533,11 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
return BLK_EH_RESET_TIMER;
disable:
- if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) {
+ if (nvme_state_terminal(&dev->ctrl))
+ nvme_dev_disable(dev, true);
return BLK_EH_DONE;
+ }
nvme_dev_disable(dev, false);
if (nvme_try_sched_reset(&dev->ctrl))
@@ -1849,6 +1995,18 @@ static void nvme_map_cmb(struct nvme_dev *dev)
return;
/*
+ * Controllers may support a CMB size larger than their BAR, for
+ * example, due to being behind a bridge. Reduce the CMB to the
+ * reported size of the BAR
+ */
+ size = min(size, bar_size - offset);
+
+ if (!IS_ALIGNED(size, memremap_compat_align()) ||
+ !IS_ALIGNED(pci_resource_start(pdev, bar),
+ memremap_compat_align()))
+ return;
+
+ /*
* Tell the controller about the host side address mapping the CMB,
* and enable CMB decoding for the NVMe 1.4+ scheme:
*/
@@ -1858,17 +2016,10 @@ static void nvme_map_cmb(struct nvme_dev *dev)
dev->bar + NVME_REG_CMBMSC);
}
- /*
- * Controllers may support a CMB size larger than their BAR,
- * for example, due to being behind a bridge. Reduce the CMB to
- * the reported size of the BAR
- */
- if (size > bar_size - offset)
- size = bar_size - offset;
-
if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
dev_warn(dev->ctrl.device,
"failed to register the CMB\n");
+ hi_lo_writeq(0, dev->bar + NVME_REG_CMBMSC);
return;
}
@@ -1908,7 +2059,7 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
return ret;
}
-static void nvme_free_host_mem(struct nvme_dev *dev)
+static void nvme_free_host_mem_multi(struct nvme_dev *dev)
{
int i;
@@ -1923,18 +2074,54 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
kfree(dev->host_mem_desc_bufs);
dev->host_mem_desc_bufs = NULL;
- dma_free_coherent(dev->dev,
- dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
+}
+
+static void nvme_free_host_mem(struct nvme_dev *dev)
+{
+ if (dev->hmb_sgt)
+ dma_free_noncontiguous(dev->dev, dev->host_mem_size,
+ dev->hmb_sgt, DMA_BIDIRECTIONAL);
+ else
+ nvme_free_host_mem_multi(dev);
+
+ dma_free_coherent(dev->dev, dev->host_mem_descs_size,
dev->host_mem_descs, dev->host_mem_descs_dma);
dev->host_mem_descs = NULL;
+ dev->host_mem_descs_size = 0;
dev->nr_host_mem_descs = 0;
}
-static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
+static int nvme_alloc_host_mem_single(struct nvme_dev *dev, u64 size)
+{
+ dev->hmb_sgt = dma_alloc_noncontiguous(dev->dev, size,
+ DMA_BIDIRECTIONAL, GFP_KERNEL, 0);
+ if (!dev->hmb_sgt)
+ return -ENOMEM;
+
+ dev->host_mem_descs = dma_alloc_coherent(dev->dev,
+ sizeof(*dev->host_mem_descs), &dev->host_mem_descs_dma,
+ GFP_KERNEL);
+ if (!dev->host_mem_descs) {
+ dma_free_noncontiguous(dev->dev, size, dev->hmb_sgt,
+ DMA_BIDIRECTIONAL);
+ dev->hmb_sgt = NULL;
+ return -ENOMEM;
+ }
+ dev->host_mem_size = size;
+ dev->host_mem_descs_size = sizeof(*dev->host_mem_descs);
+ dev->nr_host_mem_descs = 1;
+
+ dev->host_mem_descs[0].addr =
+ cpu_to_le64(dev->hmb_sgt->sgl->dma_address);
+ dev->host_mem_descs[0].size = cpu_to_le32(size / NVME_CTRL_PAGE_SIZE);
+ return 0;
+}
+
+static int nvme_alloc_host_mem_multi(struct nvme_dev *dev, u64 preferred,
u32 chunk_size)
{
struct nvme_host_mem_buf_desc *descs;
- u32 max_entries, len;
+ u32 max_entries, len, descs_size;
dma_addr_t descs_dma;
int i = 0;
void **bufs;
@@ -1947,8 +2134,9 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
max_entries = dev->ctrl.hmmaxd;
- descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs),
- &descs_dma, GFP_KERNEL);
+ descs_size = max_entries * sizeof(*descs);
+ descs = dma_alloc_coherent(dev->dev, descs_size, &descs_dma,
+ GFP_KERNEL);
if (!descs)
goto out;
@@ -1977,22 +2165,14 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
dev->host_mem_size = size;
dev->host_mem_descs = descs;
dev->host_mem_descs_dma = descs_dma;
+ dev->host_mem_descs_size = descs_size;
dev->host_mem_desc_bufs = bufs;
return 0;
out_free_bufs:
- while (--i >= 0) {
- size_t size = le32_to_cpu(descs[i].size) * NVME_CTRL_PAGE_SIZE;
-
- dma_free_attrs(dev->dev, size, bufs[i],
- le64_to_cpu(descs[i].addr),
- DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
- }
-
kfree(bufs);
out_free_descs:
- dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs,
- descs_dma);
+ dma_free_coherent(dev->dev, descs_size, descs, descs_dma);
out:
dev->host_mem_descs = NULL;
return -ENOMEM;
@@ -2000,13 +2180,23 @@ out:
static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
{
+ unsigned long dma_merge_boundary = dma_get_merge_boundary(dev->dev);
u64 min_chunk = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
u64 chunk_size;
+ /*
+ * If there is an IOMMU that can merge pages, try a virtually
+ * non-contiguous allocation for a single segment first.
+ */
+ if (dma_merge_boundary && (PAGE_SIZE & dma_merge_boundary) == 0) {
+ if (!nvme_alloc_host_mem_single(dev, preferred))
+ return 0;
+ }
+
/* start big and work our way down */
for (chunk_size = min_chunk; chunk_size >= hmminds; chunk_size /= 2) {
- if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
+ if (!nvme_alloc_host_mem_multi(dev, preferred, chunk_size)) {
if (!min || dev->host_mem_size >= min)
return 0;
nvme_free_host_mem(dev);
@@ -2054,8 +2244,10 @@ static int nvme_setup_host_mem(struct nvme_dev *dev)
}
dev_info(dev->ctrl.device,
- "allocated %lld MiB host memory buffer.\n",
- dev->host_mem_size >> ilog2(SZ_1M));
+ "allocated %lld MiB host memory buffer (%u segment%s).\n",
+ dev->host_mem_size >> ilog2(SZ_1M),
+ dev->nr_host_mem_descs,
+ str_plural(dev->nr_host_mem_descs));
}
ret = nvme_set_host_mem(dev, enable_bits);
@@ -2218,6 +2410,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
.priv = dev,
};
unsigned int irq_queues, poll_queues;
+ unsigned int flags = PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY;
/*
* Poll queues don't need interrupts, but we need at least one I/O queue
@@ -2241,8 +2434,10 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
irq_queues = 1;
if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR))
irq_queues += (nr_io_queues - poll_queues);
- return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
- PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
+ if (dev->ctrl.quirks & NVME_QUIRK_BROKEN_MSI)
+ flags &= ~PCI_IRQ_MSI;
+ return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues, flags,
+ &affd);
}
static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
@@ -2460,17 +2655,36 @@ static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev)
return 1;
}
-static void nvme_pci_update_nr_queues(struct nvme_dev *dev)
+static bool nvme_pci_update_nr_queues(struct nvme_dev *dev)
{
+ if (!dev->ctrl.tagset) {
+ nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops,
+ nvme_pci_nr_maps(dev), sizeof(struct nvme_iod));
+ return true;
+ }
+
+ /* Give up if we are racing with nvme_dev_disable() */
+ if (!mutex_trylock(&dev->shutdown_lock))
+ return false;
+
+ /* Check if nvme_dev_disable() has been executed already */
+ if (!dev->online_queues) {
+ mutex_unlock(&dev->shutdown_lock);
+ return false;
+ }
+
blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
/* free previously allocated queues that are no longer usable */
nvme_free_queues(dev, dev->online_queues);
+ mutex_unlock(&dev->shutdown_lock);
+ return true;
}
static int nvme_pci_enable(struct nvme_dev *dev)
{
int result = -ENOMEM;
struct pci_dev *pdev = to_pci_dev(dev->dev);
+ unsigned int flags = PCI_IRQ_ALL_TYPES;
if (pci_enable_device_mem(pdev))
return result;
@@ -2487,7 +2701,9 @@ static int nvme_pci_enable(struct nvme_dev *dev)
* interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
* adjust this later.
*/
- result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+ if (dev->ctrl.quirks & NVME_QUIRK_BROKEN_MSI)
+ flags &= ~PCI_IRQ_MSI;
+ result = pci_alloc_irq_vectors(pdev, 1, 1, flags);
if (result < 0)
goto disable;
@@ -2508,15 +2724,8 @@ static int nvme_pci_enable(struct nvme_dev *dev)
else
dev->io_sqes = NVME_NVM_IOSQES;
- /*
- * Temporary fix for the Apple controller found in the MacBook8,1 and
- * some MacBook7,1 to avoid controller resets and data loss.
- */
- if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
+ if (dev->ctrl.quirks & NVME_QUIRK_QDEPTH_ONE) {
dev->q_depth = 2;
- dev_warn(dev->ctrl.device, "detected Apple NVMe controller, "
- "set queue depth=%u to work around controller resets\n",
- dev->q_depth);
} else if (pdev->vendor == PCI_VENDOR_ID_SAMSUNG &&
(pdev->device == 0xa821 || pdev->device == 0xa822) &&
NVME_CAP_MQES(dev->ctrl.cap) == 0) {
@@ -2633,15 +2842,20 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
static int nvme_setup_prp_pools(struct nvme_dev *dev)
{
+ size_t small_align = 256;
+
dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
NVME_CTRL_PAGE_SIZE,
NVME_CTRL_PAGE_SIZE, 0);
if (!dev->prp_page_pool)
return -ENOMEM;
+ if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512)
+ small_align = 512;
+
/* Optimisation for I/Os between 4k and 128k */
dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev,
- 256, 256, 0);
+ 256, small_align, 0);
if (!dev->prp_small_pool) {
dma_pool_destroy(dev->prp_page_pool);
return -ENOMEM;
@@ -2657,6 +2871,7 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)
static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev)
{
+ size_t meta_size = sizeof(struct scatterlist) * (NVME_MAX_META_SEGS + 1);
size_t alloc_size = sizeof(struct scatterlist) * NVME_MAX_SEGS;
dev->iod_mempool = mempool_create_node(1,
@@ -2665,7 +2880,18 @@ static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev)
dev_to_node(dev->dev));
if (!dev->iod_mempool)
return -ENOMEM;
+
+ dev->iod_meta_mempool = mempool_create_node(1,
+ mempool_kmalloc, mempool_kfree,
+ (void *)meta_size, GFP_KERNEL,
+ dev_to_node(dev->dev));
+ if (!dev->iod_meta_mempool)
+ goto free;
+
return 0;
+free:
+ mempool_destroy(dev->iod_mempool);
+ return -ENOMEM;
}
static void nvme_free_tagset(struct nvme_dev *dev)
@@ -2730,6 +2956,11 @@ static void nvme_reset_work(struct work_struct *work)
if (result)
goto out;
+ if (nvme_ctrl_meta_sgl_supported(&dev->ctrl))
+ dev->ctrl.max_integrity_segments = NVME_MAX_META_SEGS;
+ else
+ dev->ctrl.max_integrity_segments = 1;
+
nvme_dbbuf_dma_alloc(dev);
result = nvme_setup_host_mem(dev);
@@ -2749,7 +2980,8 @@ static void nvme_reset_work(struct work_struct *work)
nvme_dbbuf_set(dev);
nvme_unquiesce_io_queues(&dev->ctrl);
nvme_wait_freeze(&dev->ctrl);
- nvme_pci_update_nr_queues(dev);
+ if (!nvme_pci_update_nr_queues(dev))
+ goto out;
nvme_unfreeze(&dev->ctrl);
} else {
dev_warn(dev->ctrl.device, "IO queues lost\n");
@@ -2846,6 +3078,7 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
.reg_read64 = nvme_pci_reg_read64,
.free_ctrl = nvme_pci_free_ctrl,
.submit_async_event = nvme_pci_submit_async_event,
+ .subsystem_reset = nvme_pci_subsystem_reset,
.get_address = nvme_pci_get_address,
.print_device_info = nvme_pci_print_device_info,
.supports_pci_p2pdma = nvme_pci_supports_pci_p2pdma,
@@ -2917,8 +3150,28 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
dmi_match(DMI_BOARD_NAME, "NS5x_7xPU") ||
dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1"))
return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
+ } else if (pdev->vendor == 0x144d && pdev->device == 0xa80d) {
+ /*
+ * Exclude Samsung 990 Evo from NVME_QUIRK_SIMPLE_SUSPEND
+ * because of high power consumption (> 2 Watt) in s2idle
+ * sleep. Only some boards with Intel CPU are affected.
+ */
+ if (dmi_match(DMI_BOARD_NAME, "DN50Z-140HC-YD") ||
+ dmi_match(DMI_BOARD_NAME, "GMxPXxx") ||
+ dmi_match(DMI_BOARD_NAME, "GXxMRXx") ||
+ dmi_match(DMI_BOARD_NAME, "PH4PG31") ||
+ dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1") ||
+ dmi_match(DMI_BOARD_NAME, "PH6PG01_PH6PG71"))
+ return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
}
+ /*
+ * NVMe SSD drops off the PCIe bus after system idle
+ * for 10 hours on a Lenovo N60z board.
+ */
+ if (dmi_match(DMI_BOARD_NAME, "LXKT-ZXEG-N6"))
+ return NVME_QUIRK_NO_APST;
+
return 0;
}
@@ -2977,11 +3230,6 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
dev->ctrl.max_hw_sectors = min_t(u32,
NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9);
dev->ctrl.max_segments = NVME_MAX_SEGS;
-
- /*
- * There is no support for SGLs for metadata (yet), so we are limited to
- * a single integrity segment for the separate metadata pointer.
- */
dev->ctrl.max_integrity_segments = 1;
return dev;
@@ -3002,6 +3250,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (IS_ERR(dev))
return PTR_ERR(dev);
+ result = nvme_add_ctrl(&dev->ctrl);
+ if (result)
+ goto out_put_ctrl;
+
result = nvme_dev_map(dev);
if (result)
goto out_uninit_ctrl;
@@ -3040,6 +3292,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (result)
goto out_disable;
+ if (nvme_ctrl_meta_sgl_supported(&dev->ctrl))
+ dev->ctrl.max_integrity_segments = NVME_MAX_META_SEGS;
+ else
+ dev->ctrl.max_integrity_segments = 1;
+
nvme_dbbuf_dma_alloc(dev);
result = nvme_setup_host_mem(dev);
@@ -3082,12 +3339,14 @@ out_disable:
nvme_free_queues(dev, 0);
out_release_iod_mempool:
mempool_destroy(dev->iod_mempool);
+ mempool_destroy(dev->iod_meta_mempool);
out_release_prp_pools:
nvme_release_prp_pools(dev);
out_dev_unmap:
nvme_dev_unmap(dev);
out_uninit_ctrl:
nvme_uninit_ctrl(&dev->ctrl);
+out_put_ctrl:
nvme_put_ctrl(&dev->ctrl);
return result;
}
@@ -3146,6 +3405,7 @@ static void nvme_remove(struct pci_dev *pdev)
nvme_dbbuf_dma_free(dev);
nvme_free_queues(dev, 0);
mempool_destroy(dev->iod_mempool);
+ mempool_destroy(dev->iod_meta_mempool);
nvme_release_prp_pools(dev);
nvme_dev_unmap(dev);
nvme_uninit_ctrl(&dev->ctrl);
@@ -3344,12 +3604,10 @@ static const struct pci_device_id nvme_id_table[] = {
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a54), /* Intel P4500/P4600 */
.driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DEALLOCATE_ZEROES |
NVME_QUIRK_IGNORE_DEV_SUBNQN |
NVME_QUIRK_BOGUS_NID, },
{ PCI_VDEVICE(INTEL, 0x0a55), /* Dell Express Flash P4600 */
- .driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DEALLOCATE_ZEROES, },
+ .driver_data = NVME_QUIRK_STRIPE_SIZE, },
{ PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */
.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
NVME_QUIRK_MEDIUM_PRIO_SQ |
@@ -3363,6 +3621,11 @@ static const struct pci_device_id nvme_id_table[] = {
NVME_QUIRK_BOGUS_NID, },
{ PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */
.driver_data = NVME_QUIRK_BOGUS_NID, },
+ { PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */
+ .driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, },
+ { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */
.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
NVME_QUIRK_BOGUS_NID, },
@@ -3381,6 +3644,8 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
NVME_QUIRK_DISABLE_WRITE_ZEROES|
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+ { PCI_DEVICE(0x15b7, 0x5008), /* Sandisk SN530 */
+ .driver_data = NVME_QUIRK_BROKEN_MSI },
{ PCI_DEVICE(0x1987, 0x5012), /* Phison E12 */
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */
@@ -3458,6 +3723,8 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1cc1, 0x5350), /* ADATA XPG GAMMIX S50 */
.driver_data = NVME_QUIRK_BOGUS_NID, },
+ { PCI_DEVICE(0x1dbe, 0x5216), /* Acer/INNOGRIT FA100/5216 NVMe SSD */
+ .driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1dbe, 0x5236), /* ADATA XPG GAMMIX S70 */
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e49, 0x0021), /* ZHITAI TiPro5000 NVMe SSD */
@@ -3492,7 +3759,12 @@ static const struct pci_device_id nvme_id_table[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd02),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
- .driver_data = NVME_QUIRK_SINGLE_VECTOR },
+ /*
+ * Fix for the Apple controller found in the MacBook8,1 and
+ * some MacBook7,1 to avoid controller resets and data loss.
+ */
+ .driver_data = NVME_QUIRK_SINGLE_VECTOR |
+ NVME_QUIRK_QDEPTH_ONE },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005),
.driver_data = NVME_QUIRK_SINGLE_VECTOR |
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index fc3eed00f9ff..cf2d2c5039dd 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -5,7 +5,7 @@
*/
#include <linux/blkdev.h>
#include <linux/pr.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "nvme.h"
@@ -72,12 +72,12 @@ static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
return nvme_submit_sync_cmd(ns->queue, c, data, data_len);
}
-static int nvme_sc_to_pr_err(int nvme_sc)
+static int nvme_status_to_pr_err(int status)
{
- if (nvme_is_path_error(nvme_sc))
+ if (nvme_is_path_error(status))
return PR_STS_PATH_FAILED;
- switch (nvme_sc) {
+ switch (status & NVME_SCT_SC_MASK) {
case NVME_SC_SUCCESS:
return PR_STS_SUCCESS;
case NVME_SC_RESERVATION_CONFLICT:
@@ -94,110 +94,137 @@ static int nvme_sc_to_pr_err(int nvme_sc)
}
}
-static int nvme_send_pr_command(struct block_device *bdev,
- struct nvme_command *c, void *data, unsigned int data_len)
+static int __nvme_send_pr_command(struct block_device *bdev, u32 cdw10,
+ u32 cdw11, u8 op, void *data, unsigned int data_len)
{
- if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
- nvme_disk_is_ns_head(bdev->bd_disk))
- return nvme_send_ns_head_pr_command(bdev, c, data, data_len);
+ struct nvme_command c = { 0 };
+
+ c.common.opcode = op;
+ c.common.cdw10 = cpu_to_le32(cdw10);
+ c.common.cdw11 = cpu_to_le32(cdw11);
- return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,
- data_len);
+ if (nvme_disk_is_ns_head(bdev->bd_disk))
+ return nvme_send_ns_head_pr_command(bdev, &c, data, data_len);
+ return nvme_send_ns_pr_command(bdev->bd_disk->private_data, &c,
+ data, data_len);
}
-static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
- u64 key, u64 sa_key, u8 op)
+static int nvme_send_pr_command(struct block_device *bdev, u32 cdw10, u32 cdw11,
+ u8 op, void *data, unsigned int data_len)
{
- struct nvme_command c = { };
- u8 data[16] = { 0, };
int ret;
- put_unaligned_le64(key, &data[0]);
- put_unaligned_le64(sa_key, &data[8]);
-
- c.common.opcode = op;
- c.common.cdw10 = cpu_to_le32(cdw10);
-
- ret = nvme_send_pr_command(bdev, &c, data, sizeof(data));
- if (ret < 0)
- return ret;
-
- return nvme_sc_to_pr_err(ret);
+ ret = __nvme_send_pr_command(bdev, cdw10, cdw11, op, data, data_len);
+ return ret < 0 ? ret : nvme_status_to_pr_err(ret);
}
-static int nvme_pr_register(struct block_device *bdev, u64 old,
- u64 new, unsigned flags)
+static int nvme_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+ unsigned int flags)
{
+ struct nvmet_pr_register_data data = { 0 };
u32 cdw10;
if (flags & ~PR_FL_IGNORE_KEY)
return -EOPNOTSUPP;
- cdw10 = old ? 2 : 0;
- cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
- cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
- return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
+ data.crkey = cpu_to_le64(old_key);
+ data.nrkey = cpu_to_le64(new_key);
+
+ cdw10 = old_key ? NVME_PR_REGISTER_ACT_REPLACE :
+ NVME_PR_REGISTER_ACT_REG;
+ cdw10 |= (flags & PR_FL_IGNORE_KEY) ? NVME_PR_IGNORE_KEY : 0;
+ cdw10 |= NVME_PR_CPTPL_PERSIST;
+
+ return nvme_send_pr_command(bdev, cdw10, 0, nvme_cmd_resv_register,
+ &data, sizeof(data));
}
static int nvme_pr_reserve(struct block_device *bdev, u64 key,
enum pr_type type, unsigned flags)
{
+ struct nvmet_pr_acquire_data data = { 0 };
u32 cdw10;
if (flags & ~PR_FL_IGNORE_KEY)
return -EOPNOTSUPP;
- cdw10 = nvme_pr_type_from_blk(type) << 8;
- cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
- return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
+ data.crkey = cpu_to_le64(key);
+
+ cdw10 = NVME_PR_ACQUIRE_ACT_ACQUIRE;
+ cdw10 |= nvme_pr_type_from_blk(type) << 8;
+ cdw10 |= (flags & PR_FL_IGNORE_KEY) ? NVME_PR_IGNORE_KEY : 0;
+
+ return nvme_send_pr_command(bdev, cdw10, 0, nvme_cmd_resv_acquire,
+ &data, sizeof(data));
}
static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
enum pr_type type, bool abort)
{
- u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (abort ? 2 : 1);
+ struct nvmet_pr_acquire_data data = { 0 };
+ u32 cdw10;
+
+ data.crkey = cpu_to_le64(old);
+ data.prkey = cpu_to_le64(new);
- return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
+ cdw10 = abort ? NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT :
+ NVME_PR_ACQUIRE_ACT_PREEMPT;
+ cdw10 |= nvme_pr_type_from_blk(type) << 8;
+
+ return nvme_send_pr_command(bdev, cdw10, 0, nvme_cmd_resv_acquire,
+ &data, sizeof(data));
}
static int nvme_pr_clear(struct block_device *bdev, u64 key)
{
- u32 cdw10 = 1 | (key ? 0 : 1 << 3);
+ struct nvmet_pr_release_data data = { 0 };
+ u32 cdw10;
+
+ data.crkey = cpu_to_le64(key);
- return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
+ cdw10 = NVME_PR_RELEASE_ACT_CLEAR;
+ cdw10 |= key ? 0 : NVME_PR_IGNORE_KEY;
+
+ return nvme_send_pr_command(bdev, cdw10, 0, nvme_cmd_resv_release,
+ &data, sizeof(data));
}
static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
- u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (key ? 0 : 1 << 3);
+ struct nvmet_pr_release_data data = { 0 };
+ u32 cdw10;
+
+ data.crkey = cpu_to_le64(key);
- return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
+ cdw10 = NVME_PR_RELEASE_ACT_RELEASE;
+ cdw10 |= nvme_pr_type_from_blk(type) << 8;
+ cdw10 |= key ? 0 : NVME_PR_IGNORE_KEY;
+
+ return nvme_send_pr_command(bdev, cdw10, 0, nvme_cmd_resv_release,
+ &data, sizeof(data));
}
static int nvme_pr_resv_report(struct block_device *bdev, void *data,
u32 data_len, bool *eds)
{
- struct nvme_command c = { };
+ u32 cdw10, cdw11;
int ret;
- c.common.opcode = nvme_cmd_resv_report;
- c.common.cdw10 = cpu_to_le32(nvme_bytes_to_numd(data_len));
- c.common.cdw11 = cpu_to_le32(NVME_EXTENDED_DATA_STRUCT);
+ cdw10 = nvme_bytes_to_numd(data_len);
+ cdw11 = NVME_EXTENDED_DATA_STRUCT;
*eds = true;
retry:
- ret = nvme_send_pr_command(bdev, &c, data, data_len);
+ ret = __nvme_send_pr_command(bdev, cdw10, cdw11, nvme_cmd_resv_report,
+ data, data_len);
if (ret == NVME_SC_HOST_ID_INCONSIST &&
- c.common.cdw11 == cpu_to_le32(NVME_EXTENDED_DATA_STRUCT)) {
- c.common.cdw11 = 0;
+ cdw11 == NVME_EXTENDED_DATA_STRUCT) {
+ cdw11 = 0;
*eds = false;
goto retry;
}
- if (ret < 0)
- return ret;
-
- return nvme_sc_to_pr_err(ret);
+ return ret < 0 ? ret : nvme_status_to_pr_err(ret);
}
static int nvme_pr_read_keys(struct block_device *bdev,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 20fdd40b1879..86a2891d9bcc 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -18,7 +18,7 @@
#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/nvme.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
@@ -982,7 +982,8 @@ free_ctrl:
kfree(ctrl);
}
-static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
+static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl,
+ int status)
{
enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
@@ -992,7 +993,7 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
return;
}
- if (nvmf_should_reconnect(&ctrl->ctrl)) {
+ if (nvmf_should_reconnect(&ctrl->ctrl, status)) {
dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
ctrl->ctrl.opts->reconnect_delay);
queue_delayed_work(nvme_wq, &ctrl->reconnect_work,
@@ -1006,6 +1007,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
{
int ret;
bool changed;
+ u16 max_queue_size;
ret = nvme_rdma_configure_admin_queue(ctrl, new);
if (ret)
@@ -1017,7 +1019,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
goto destroy_admin;
}
- if (!(ctrl->ctrl.sgls & (1 << 2))) {
+ if (!(ctrl->ctrl.sgls & NVME_CTRL_SGLS_KSDBDS)) {
ret = -EOPNOTSUPP;
dev_err(ctrl->ctrl.device,
"Mandatory keyed sgls are not supported!\n");
@@ -1030,11 +1032,16 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
}
- if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) {
+ if (ctrl->ctrl.max_integrity_segments)
+ max_queue_size = NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
+ else
+ max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+
+ if (ctrl->ctrl.sqsize + 1 > max_queue_size) {
dev_warn(ctrl->ctrl.device,
- "ctrl sqsize %u > max queue size %u, clamping down\n",
- ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE);
- ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1;
+ "ctrl sqsize %u > max queue size %u, clamping down\n",
+ ctrl->ctrl.sqsize + 1, max_queue_size);
+ ctrl->ctrl.sqsize = max_queue_size - 1;
}
if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
@@ -1044,7 +1051,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
}
- if (ctrl->ctrl.sgls & (1 << 20))
+ if (ctrl->ctrl.sgls & NVME_CTRL_SGLS_SAOS)
ctrl->use_inline_data = true;
if (ctrl->ctrl.queue_count > 1) {
@@ -1084,13 +1091,7 @@ destroy_io:
}
destroy_admin:
nvme_stop_keep_alive(&ctrl->ctrl);
- nvme_quiesce_admin_queue(&ctrl->ctrl);
- blk_sync_queue(ctrl->ctrl.admin_q);
- nvme_rdma_stop_queue(&ctrl->queues[0]);
- nvme_cancel_admin_tagset(&ctrl->ctrl);
- if (new)
- nvme_remove_admin_tag_set(&ctrl->ctrl);
- nvme_rdma_destroy_admin_queue(ctrl);
+ nvme_rdma_teardown_admin_queue(ctrl, new);
return ret;
}
@@ -1098,10 +1099,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
struct nvme_rdma_ctrl, reconnect_work);
+ int ret;
++ctrl->ctrl.nr_reconnects;
- if (nvme_rdma_setup_ctrl(ctrl, false))
+ ret = nvme_rdma_setup_ctrl(ctrl, false);
+ if (ret)
goto requeue;
dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
@@ -1112,9 +1115,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
return;
requeue:
- dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
- ctrl->ctrl.nr_reconnects);
- nvme_rdma_reconnect_or_remove(ctrl);
+ dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d/%d\n",
+ ctrl->ctrl.nr_reconnects, ctrl->ctrl.opts->max_reconnects);
+ nvme_rdma_reconnect_or_remove(ctrl, ret);
}
static void nvme_rdma_error_recovery_work(struct work_struct *work)
@@ -1139,7 +1142,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
return;
}
- nvme_rdma_reconnect_or_remove(ctrl);
+ nvme_rdma_reconnect_or_remove(ctrl, 0);
}
static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
@@ -1354,8 +1357,8 @@ static void nvme_rdma_set_sig_domain(struct blk_integrity *bi,
if (control & NVME_RW_PRINFO_PRCHK_REF)
domain->sig.dif.ref_remap = true;
- domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.apptag);
- domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.appmask);
+ domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.lbat);
+ domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.lbatm);
domain->sig.dif.app_escape = true;
if (pi_type == NVME_NS_DPS_PI_TYPE3)
domain->sig.dif.ref_escape = true;
@@ -1487,7 +1490,7 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
req->metadata_sgl->sg_table.sgl =
(struct scatterlist *)(req->metadata_sgl + 1);
ret = sg_alloc_table_chained(&req->metadata_sgl->sg_table,
- blk_rq_count_integrity_sg(rq->q, rq->bio),
+ rq->nr_integrity_segments,
req->metadata_sgl->sg_table.sgl,
NVME_INLINE_METADATA_SG_CNT);
if (unlikely(ret)) {
@@ -1495,8 +1498,8 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq,
goto out_unmap_sg;
}
- req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq->q,
- rq->bio, req->metadata_sgl->sg_table.sgl);
+ req->metadata_sgl->nents = blk_rq_map_integrity_sg(rq,
+ req->metadata_sgl->sg_table.sgl);
*pi_count = ib_dma_map_sg(ibdev,
req->metadata_sgl->sg_table.sgl,
req->metadata_sgl->nents,
@@ -1867,6 +1870,8 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
*/
priv.hrqsize = cpu_to_le16(queue->queue_size);
priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
+ /* cntlid should only be set when creating an I/O queue */
+ priv.cntlid = cpu_to_le16(ctrl->ctrl.cntlid);
}
ret = rdma_connect_locked(queue->cm_id, &param);
@@ -2163,6 +2168,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl =
container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
+ int ret;
nvme_stop_ctrl(&ctrl->ctrl);
nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -2173,14 +2179,15 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
return;
}
- if (nvme_rdma_setup_ctrl(ctrl, false))
+ ret = nvme_rdma_setup_ctrl(ctrl, false);
+ if (ret)
goto out_fail;
return;
out_fail:
++ctrl->ctrl.nr_reconnects;
- nvme_rdma_reconnect_or_remove(ctrl);
+ nvme_rdma_reconnect_or_remove(ctrl, ret);
}
static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
@@ -2190,6 +2197,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
+ .subsystem_reset = nvmf_subsystem_reset,
.free_ctrl = nvme_rdma_free_ctrl,
.submit_async_event = nvme_rdma_submit_async_event,
.delete_ctrl = nvme_rdma_delete_ctrl,
@@ -2226,12 +2234,11 @@ nvme_rdma_existing_controller(struct nvmf_ctrl_options *opts)
return found;
}
-static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
+static struct nvme_rdma_ctrl *nvme_rdma_alloc_ctrl(struct device *dev,
struct nvmf_ctrl_options *opts)
{
struct nvme_rdma_ctrl *ctrl;
int ret;
- bool changed;
ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
if (!ctrl)
@@ -2293,6 +2300,30 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
if (ret)
goto out_kfree_queues;
+ return ctrl;
+
+out_kfree_queues:
+ kfree(ctrl->queues);
+out_free_ctrl:
+ kfree(ctrl);
+ return ERR_PTR(ret);
+}
+
+static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
+ struct nvmf_ctrl_options *opts)
+{
+ struct nvme_rdma_ctrl *ctrl;
+ bool changed;
+ int ret;
+
+ ctrl = nvme_rdma_alloc_ctrl(dev, opts);
+ if (IS_ERR(ctrl))
+ return ERR_CAST(ctrl);
+
+ ret = nvme_add_ctrl(&ctrl->ctrl);
+ if (ret)
+ goto out_put_ctrl;
+
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
WARN_ON_ONCE(!changed);
@@ -2311,15 +2342,11 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
out_uninit_ctrl:
nvme_uninit_ctrl(&ctrl->ctrl);
+out_put_ctrl:
nvme_put_ctrl(&ctrl->ctrl);
if (ret > 0)
ret = -EIO;
return ERR_PTR(ret);
-out_kfree_queues:
- kfree(ctrl->queues);
-out_free_ctrl:
- kfree(ctrl);
- return ERR_PTR(ret);
}
static struct nvmf_transport_ops nvme_rdma_transport = {
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index f2832f70e7e0..3a41b9ab0f13 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -221,14 +221,11 @@ static int ns_update_nuse(struct nvme_ns *ns)
ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id);
if (ret)
- goto out_free_id;
+ return ret;
ns->head->nuse = le64_to_cpu(id->nuse);
-
-out_free_id:
kfree(id);
-
- return ret;
+ return 0;
}
static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
@@ -236,14 +233,12 @@ static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
{
struct nvme_ns_head *head = dev_to_ns_head(dev);
struct gendisk *disk = dev_to_disk(dev);
- struct block_device *bdev = disk->part0;
int ret;
- if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
- bdev->bd_disk->fops == &nvme_ns_head_ops)
+ if (nvme_disk_is_ns_head(disk))
ret = ns_head_update_nuse(head);
else
- ret = ns_update_nuse(bdev->bd_disk->private_data);
+ ret = ns_update_nuse(disk->private_data);
if (ret)
return ret;
@@ -669,19 +664,6 @@ static DEVICE_ATTR(dhchap_ctrl_secret, S_IRUGO | S_IWUSR,
nvme_ctrl_dhchap_ctrl_secret_show, nvme_ctrl_dhchap_ctrl_secret_store);
#endif
-#ifdef CONFIG_NVME_TCP_TLS
-static ssize_t tls_key_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
-
- if (!ctrl->tls_key)
- return 0;
- return sysfs_emit(buf, "%08x", key_serial(ctrl->tls_key));
-}
-static DEVICE_ATTR_RO(tls_key);
-#endif
-
static struct attribute *nvme_dev_attrs[] = {
&dev_attr_reset_controller.attr,
&dev_attr_rescan_controller.attr,
@@ -709,9 +691,6 @@ static struct attribute *nvme_dev_attrs[] = {
&dev_attr_dhchap_secret.attr,
&dev_attr_dhchap_ctrl_secret.attr,
#endif
-#ifdef CONFIG_NVME_TCP_TLS
- &dev_attr_tls_key.attr,
-#endif
&dev_attr_adm_passthru_err_log_enabled.attr,
NULL
};
@@ -742,11 +721,6 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts)
return 0;
#endif
-#ifdef CONFIG_NVME_TCP_TLS
- if (a == &dev_attr_tls_key.attr &&
- (!ctrl->opts || strcmp(ctrl->opts->transport, "tcp")))
- return 0;
-#endif
return a->mode;
}
@@ -757,8 +731,78 @@ const struct attribute_group nvme_dev_attrs_group = {
};
EXPORT_SYMBOL_GPL(nvme_dev_attrs_group);
+#ifdef CONFIG_NVME_TCP_TLS
+static ssize_t tls_key_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+ if (!ctrl->tls_pskid)
+ return 0;
+ return sysfs_emit(buf, "%08x\n", ctrl->tls_pskid);
+}
+static DEVICE_ATTR_RO(tls_key);
+
+static ssize_t tls_configured_key_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+ struct key *key = ctrl->opts->tls_key;
+
+ return sysfs_emit(buf, "%08x\n", key_serial(key));
+}
+static DEVICE_ATTR_RO(tls_configured_key);
+
+static ssize_t tls_keyring_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+ struct key *keyring = ctrl->opts->keyring;
+
+ return sysfs_emit(buf, "%s\n", keyring->description);
+}
+static DEVICE_ATTR_RO(tls_keyring);
+
+static struct attribute *nvme_tls_attrs[] = {
+ &dev_attr_tls_key.attr,
+ &dev_attr_tls_configured_key.attr,
+ &dev_attr_tls_keyring.attr,
+ NULL,
+};
+
+static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj,
+ struct attribute *a, int n)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+ if (!ctrl->opts || strcmp(ctrl->opts->transport, "tcp"))
+ return 0;
+
+ if (a == &dev_attr_tls_key.attr &&
+ !ctrl->opts->tls)
+ return 0;
+ if (a == &dev_attr_tls_configured_key.attr &&
+ !ctrl->opts->tls_key)
+ return 0;
+ if (a == &dev_attr_tls_keyring.attr &&
+ !ctrl->opts->keyring)
+ return 0;
+
+ return a->mode;
+}
+
+static const struct attribute_group nvme_tls_attrs_group = {
+ .attrs = nvme_tls_attrs,
+ .is_visible = nvme_tls_attrs_are_visible,
+};
+#endif
+
const struct attribute_group *nvme_dev_attr_groups[] = {
&nvme_dev_attrs_group,
+#ifdef CONFIG_NVME_TCP_TLS
+ &nvme_tls_attrs_group,
+#endif
NULL,
};
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a6d596e05602..327f3f2f5399 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -37,6 +37,14 @@ module_param(so_priority, int, 0644);
MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
/*
+ * Use the unbound workqueue for nvme_tcp_wq, then we can set the cpu affinity
+ * from sysfs.
+ */
+static bool wq_unbound;
+module_param(wq_unbound, bool, 0644);
+MODULE_PARM_DESC(wq_unbound, "Use unbound workqueue for nvme-tcp IO context (default false)");
+
+/*
* TLS handshake timeout
*/
static int tls_handshake_timeout = 10;
@@ -46,6 +54,8 @@ MODULE_PARM_DESC(tls_handshake_timeout,
"nvme TLS handshake timeout in seconds (default 10)");
#endif
+static atomic_t nvme_tcp_cpu_queues[NR_CPUS];
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/* lockdep can detect a circular dependency of the form
* sk_lock -> mmap_lock (page fault) -> fs locks -> sk_lock
@@ -119,6 +129,7 @@ enum nvme_tcp_queue_flags {
NVME_TCP_Q_ALLOCATED = 0,
NVME_TCP_Q_LIVE = 1,
NVME_TCP_Q_POLLING = 2,
+ NVME_TCP_Q_IO_CPU_SET = 3,
};
enum nvme_tcp_recv_state {
@@ -157,6 +168,7 @@ struct nvme_tcp_queue {
bool hdr_digest;
bool data_digest;
+ bool tls_enabled;
struct ahash_request *rcv_hash;
struct ahash_request *snd_hash;
__le32 exp_ddgst;
@@ -205,7 +217,34 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
return queue - queue->ctrl->queues;
}
-static inline bool nvme_tcp_tls(struct nvme_ctrl *ctrl)
+static inline bool nvme_tcp_recv_pdu_supported(enum nvme_tcp_pdu_type type)
+{
+ switch (type) {
+ case nvme_tcp_c2h_term:
+ case nvme_tcp_c2h_data:
+ case nvme_tcp_r2t:
+ case nvme_tcp_rsp:
+ return true;
+ default:
+ return false;
+ }
+}
+
+/*
+ * Check if the queue is TLS encrypted
+ */
+static inline bool nvme_tcp_queue_tls(struct nvme_tcp_queue *queue)
+{
+ if (!IS_ENABLED(CONFIG_NVME_TCP_TLS))
+ return 0;
+
+ return queue->tls_enabled;
+}
+
+/*
+ * Check if TLS is configured for the controller.
+ */
+static inline bool nvme_tcp_tls_configured(struct nvme_ctrl *ctrl)
{
if (!IS_ENABLED(CONFIG_NVME_TCP_TLS))
return 0;
@@ -352,12 +391,18 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
} while (ret > 0);
}
-static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+static inline bool nvme_tcp_queue_has_pending(struct nvme_tcp_queue *queue)
{
return !list_empty(&queue->send_list) ||
!llist_empty(&queue->req_list);
}
+static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+{
+ return !nvme_tcp_queue_tls(queue) &&
+ nvme_tcp_queue_has_pending(queue);
+}
+
static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
bool sync, bool last)
{
@@ -378,7 +423,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
mutex_unlock(&queue->send_mutex);
}
- if (last && nvme_tcp_queue_more(queue))
+ if (last && nvme_tcp_queue_has_pending(queue))
queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
}
@@ -731,6 +776,40 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
return 0;
}
+static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue,
+ struct nvme_tcp_term_pdu *pdu)
+{
+ u16 fes;
+ const char *msg;
+ u32 plen = le32_to_cpu(pdu->hdr.plen);
+
+ static const char * const msg_table[] = {
+ [NVME_TCP_FES_INVALID_PDU_HDR] = "Invalid PDU Header Field",
+ [NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error",
+ [NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error",
+ [NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range",
+ [NVME_TCP_FES_DATA_LIMIT_EXCEEDED] = "Data Transfer Limit Exceeded",
+ [NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter",
+ };
+
+ if (plen < NVME_TCP_MIN_C2HTERM_PLEN ||
+ plen > NVME_TCP_MAX_C2HTERM_PLEN) {
+ dev_err(queue->ctrl->ctrl.device,
+ "Received a malformed C2HTermReq PDU (plen = %u)\n",
+ plen);
+ return;
+ }
+
+ fes = le16_to_cpu(pdu->fes);
+ if (fes && fes < ARRAY_SIZE(msg_table))
+ msg = msg_table[fes];
+ else
+ msg = "Unknown";
+
+ dev_err(queue->ctrl->ctrl.device,
+ "Received C2HTermReq (FES = %s)\n", msg);
+}
+
static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
unsigned int *offset, size_t *len)
{
@@ -752,6 +831,25 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
return 0;
hdr = queue->pdu;
+ if (unlikely(hdr->hlen != sizeof(struct nvme_tcp_rsp_pdu))) {
+ if (!nvme_tcp_recv_pdu_supported(hdr->type))
+ goto unsupported_pdu;
+
+ dev_err(queue->ctrl->ctrl.device,
+ "pdu type %d has unexpected header length (%d)\n",
+ hdr->type, hdr->hlen);
+ return -EPROTO;
+ }
+
+ if (unlikely(hdr->type == nvme_tcp_c2h_term)) {
+ /*
+ * C2HTermReq never includes Header or Data digests.
+ * Skip the checks.
+ */
+ nvme_tcp_handle_c2h_term(queue, (void *)queue->pdu);
+ return -EINVAL;
+ }
+
if (queue->hdr_digest) {
ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen);
if (unlikely(ret))
@@ -775,10 +873,13 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
nvme_tcp_init_recv_ctx(queue);
return nvme_tcp_handle_r2t(queue, (void *)queue->pdu);
default:
- dev_err(queue->ctrl->ctrl.device,
- "unsupported pdu type (%d)\n", hdr->type);
- return -EINVAL;
+ goto unsupported_pdu;
}
+
+unsupported_pdu:
+ dev_err(queue->ctrl->ctrl.device,
+ "unsupported pdu type (%d)\n", hdr->type);
+ return -EINVAL;
}
static inline void nvme_tcp_end_request(struct request *rq, u16 status)
@@ -1037,7 +1138,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
else
msg.msg_flags |= MSG_MORE;
- if (!sendpage_ok(page))
+ if (!sendpages_ok(page, len, offset))
msg.msg_flags &= ~MSG_SPLICE_PAGES;
bvec_set_page(&bvec, page, len, offset);
@@ -1344,7 +1445,6 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl)
static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
{
- struct page *page;
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
struct nvme_tcp_queue *queue = &ctrl->queues[qid];
unsigned int noreclaim_flag;
@@ -1355,11 +1455,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
if (queue->hdr_digest || queue->data_digest)
nvme_tcp_free_crypto(queue);
- if (queue->pf_cache.va) {
- page = virt_to_head_page(queue->pf_cache.va);
- __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
- queue->pf_cache.va = NULL;
- }
+ page_frag_cache_drain(&queue->pf_cache);
noreclaim_flag = memalloc_noreclaim_save();
/* ->sock will be released by fput() */
@@ -1418,19 +1514,22 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
memset(&msg, 0, sizeof(msg));
iov.iov_base = icresp;
iov.iov_len = sizeof(*icresp);
- if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
+ if (nvme_tcp_queue_tls(queue)) {
msg.msg_control = cbuf;
msg.msg_controllen = sizeof(cbuf);
}
+ msg.msg_flags = MSG_WAITALL;
ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
iov.iov_len, msg.msg_flags);
+ if (ret >= 0 && ret < sizeof(*icresp))
+ ret = -ECONNRESET;
if (ret < 0) {
pr_warn("queue %d: failed to receive icresp, error %d\n",
nvme_tcp_queue_id(queue), ret);
goto free_icresp;
}
ret = -ENOTCONN;
- if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
+ if (nvme_tcp_queue_tls(queue)) {
ctype = tls_get_record_type(queue->sock->sk,
(struct cmsghdr *)cbuf);
if (ctype != TLS_RECORD_TYPE_DATA) {
@@ -1538,20 +1637,56 @@ static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue)
ctrl->io_queues[HCTX_TYPE_POLL];
}
+/*
+ * Track the number of queues assigned to each cpu using a global per-cpu
+ * counter and select the least used cpu from the mq_map. Our goal is to spread
+ * different controllers I/O threads across different cpu cores.
+ *
+ * Note that the accounting is not 100% perfect, but we don't need to be, we're
+ * simply putting our best effort to select the best candidate cpu core that we
+ * find at any given point.
+ */
static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_ctrl *ctrl = queue->ctrl;
- int qid = nvme_tcp_queue_id(queue);
- int n = 0;
+ struct blk_mq_tag_set *set = &ctrl->tag_set;
+ int qid = nvme_tcp_queue_id(queue) - 1;
+ unsigned int *mq_map = NULL;
+ int cpu, min_queues = INT_MAX, io_cpu;
+
+ if (wq_unbound)
+ goto out;
if (nvme_tcp_default_queue(queue))
- n = qid - 1;
+ mq_map = set->map[HCTX_TYPE_DEFAULT].mq_map;
else if (nvme_tcp_read_queue(queue))
- n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] - 1;
+ mq_map = set->map[HCTX_TYPE_READ].mq_map;
else if (nvme_tcp_poll_queue(queue))
- n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] -
- ctrl->io_queues[HCTX_TYPE_READ] - 1;
- queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
+ mq_map = set->map[HCTX_TYPE_POLL].mq_map;
+
+ if (WARN_ON(!mq_map))
+ goto out;
+
+ /* Search for the least used cpu from the mq_map */
+ io_cpu = WORK_CPU_UNBOUND;
+ for_each_online_cpu(cpu) {
+ int num_queues = atomic_read(&nvme_tcp_cpu_queues[cpu]);
+
+ if (mq_map[cpu] != qid)
+ continue;
+ if (num_queues < min_queues) {
+ io_cpu = cpu;
+ min_queues = num_queues;
+ }
+ }
+ if (io_cpu != WORK_CPU_UNBOUND) {
+ queue->io_cpu = io_cpu;
+ atomic_inc(&nvme_tcp_cpu_queues[io_cpu]);
+ set_bit(NVME_TCP_Q_IO_CPU_SET, &queue->flags);
+ }
+out:
+ dev_dbg(ctrl->ctrl.device, "queue %d: using cpu %d\n",
+ qid, queue->io_cpu);
}
static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
@@ -1569,13 +1704,16 @@ static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
goto out_complete;
}
- tls_key = key_lookup(pskid);
+ tls_key = nvme_tls_key_lookup(pskid);
if (IS_ERR(tls_key)) {
dev_warn(ctrl->ctrl.device, "queue %d: Invalid key %x\n",
qid, pskid);
queue->tls_err = -ENOKEY;
} else {
- ctrl->ctrl.tls_key = tls_key;
+ queue->tls_enabled = true;
+ if (qid == 0)
+ ctrl->ctrl.tls_pskid = key_serial(tls_key);
+ key_put(tls_key);
queue->tls_err = 0;
}
@@ -1692,7 +1830,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
queue->sock->sk->sk_allocation = GFP_ATOMIC;
queue->sock->sk->sk_use_task_frag = false;
- nvme_tcp_set_queue_io_cpu(queue);
+ queue->io_cpu = WORK_CPU_UNBOUND;
queue->request = NULL;
queue->data_remaining = 0;
queue->ddgst_remaining = 0;
@@ -1756,7 +1894,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
}
/* If PSKs are configured try to start TLS */
- if (IS_ENABLED(CONFIG_NVME_TCP_TLS) && pskid) {
+ if (nvme_tcp_tls_configured(nctrl) && pskid) {
ret = nvme_tcp_start_tls(nctrl, queue, pskid);
if (ret)
goto err_init_connect;
@@ -1814,9 +1952,14 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags))
return;
+ if (test_and_clear_bit(NVME_TCP_Q_IO_CPU_SET, &queue->flags))
+ atomic_dec(&nvme_tcp_cpu_queues[queue->io_cpu]);
+
mutex_lock(&queue->queue_lock);
if (test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
__nvme_tcp_stop_queue(queue);
+ /* Stopping the queue will disable TLS */
+ queue->tls_enabled = false;
mutex_unlock(&queue->queue_lock);
}
@@ -1846,9 +1989,10 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
nvme_tcp_init_recv_ctx(queue);
nvme_tcp_setup_sock_ops(queue);
- if (idx)
+ if (idx) {
+ nvme_tcp_set_queue_io_cpu(queue);
ret = nvmf_connect_io_queue(nctrl, idx);
- else
+ } else
ret = nvmf_connect_admin_queue(nctrl);
if (!ret) {
@@ -1913,16 +2057,17 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
int ret;
key_serial_t pskid = 0;
- if (nvme_tcp_tls(ctrl)) {
+ if (nvme_tcp_tls_configured(ctrl)) {
if (ctrl->opts->tls_key)
pskid = key_serial(ctrl->opts->tls_key);
- else
+ else {
pskid = nvme_tls_psk_default(ctrl->opts->keyring,
ctrl->opts->host->nqn,
ctrl->opts->subsysnqn);
- if (!pskid) {
- dev_err(ctrl->device, "no valid PSK found\n");
- return -ENOKEY;
+ if (!pskid) {
+ dev_err(ctrl->device, "no valid PSK found\n");
+ return -ENOKEY;
+ }
}
}
@@ -1945,13 +2090,14 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
{
int i, ret;
- if (nvme_tcp_tls(ctrl) && !ctrl->tls_key) {
+ if (nvme_tcp_tls_configured(ctrl) && !ctrl->tls_pskid) {
dev_err(ctrl->device, "no PSK negotiated\n");
return -ENOKEY;
}
+
for (i = 1; i < ctrl->queue_count; i++) {
ret = nvme_tcp_alloc_queue(ctrl, i,
- key_serial(ctrl->tls_key));
+ ctrl->tls_pskid);
if (ret)
goto out_free_queues;
}
@@ -1990,14 +2136,6 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
return __nvme_tcp_alloc_io_queues(ctrl);
}
-static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove)
-{
- nvme_tcp_stop_io_queues(ctrl);
- if (remove)
- nvme_remove_io_tag_set(ctrl);
- nvme_tcp_free_io_queues(ctrl);
-}
-
static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
{
int ret, nr_queues;
@@ -2067,14 +2205,6 @@ out_free_io_queues:
return ret;
}
-static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove)
-{
- nvme_tcp_stop_queue(ctrl, 0);
- if (remove)
- nvme_remove_admin_tag_set(ctrl);
- nvme_tcp_free_admin_queue(ctrl);
-}
-
static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
{
int error;
@@ -2129,9 +2259,16 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
blk_sync_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
nvme_cancel_admin_tagset(ctrl);
- if (remove)
+ if (remove) {
nvme_unquiesce_admin_queue(ctrl);
- nvme_tcp_destroy_admin_queue(ctrl, remove);
+ nvme_remove_admin_tag_set(ctrl);
+ }
+ nvme_tcp_free_admin_queue(ctrl);
+ if (ctrl->tls_pskid) {
+ dev_dbg(ctrl->device, "Wipe negotiated TLS_PSK %08x\n",
+ ctrl->tls_pskid);
+ ctrl->tls_pskid = 0;
+ }
}
static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
@@ -2139,17 +2276,19 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
{
if (ctrl->queue_count <= 1)
return;
- nvme_quiesce_admin_queue(ctrl);
nvme_quiesce_io_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
nvme_cancel_tagset(ctrl);
- if (remove)
+ if (remove) {
nvme_unquiesce_io_queues(ctrl);
- nvme_tcp_destroy_io_queues(ctrl, remove);
+ nvme_remove_io_tag_set(ctrl);
+ }
+ nvme_tcp_free_io_queues(ctrl);
}
-static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
+static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl,
+ int status)
{
enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
@@ -2159,13 +2298,14 @@ static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
return;
}
- if (nvmf_should_reconnect(ctrl)) {
+ if (nvmf_should_reconnect(ctrl, status)) {
dev_info(ctrl->device, "Reconnecting in %d seconds...\n",
ctrl->opts->reconnect_delay);
queue_delayed_work(nvme_wq, &to_tcp_ctrl(ctrl)->connect_work,
ctrl->opts->reconnect_delay * HZ);
} else {
- dev_info(ctrl->device, "Removing controller...\n");
+ dev_info(ctrl->device, "Removing controller (%d)...\n",
+ status);
nvme_delete_ctrl(ctrl);
}
}
@@ -2233,11 +2373,13 @@ destroy_io:
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
nvme_cancel_tagset(ctrl);
- nvme_tcp_destroy_io_queues(ctrl, new);
+ if (new)
+ nvme_remove_io_tag_set(ctrl);
+ nvme_tcp_free_io_queues(ctrl);
}
destroy_admin:
nvme_stop_keep_alive(ctrl);
- nvme_tcp_teardown_admin_queue(ctrl, false);
+ nvme_tcp_teardown_admin_queue(ctrl, new);
return ret;
}
@@ -2246,23 +2388,25 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work)
struct nvme_tcp_ctrl *tcp_ctrl = container_of(to_delayed_work(work),
struct nvme_tcp_ctrl, connect_work);
struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;
+ int ret;
++ctrl->nr_reconnects;
- if (nvme_tcp_setup_ctrl(ctrl, false))
+ ret = nvme_tcp_setup_ctrl(ctrl, false);
+ if (ret)
goto requeue;
- dev_info(ctrl->device, "Successfully reconnected (%d attempt)\n",
- ctrl->nr_reconnects);
+ dev_info(ctrl->device, "Successfully reconnected (attempt %d/%d)\n",
+ ctrl->nr_reconnects, ctrl->opts->max_reconnects);
ctrl->nr_reconnects = 0;
return;
requeue:
- dev_info(ctrl->device, "Failed reconnect attempt %d\n",
- ctrl->nr_reconnects);
- nvme_tcp_reconnect_or_remove(ctrl);
+ dev_info(ctrl->device, "Failed reconnect attempt %d/%d\n",
+ ctrl->nr_reconnects, ctrl->opts->max_reconnects);
+ nvme_tcp_reconnect_or_remove(ctrl, ret);
}
static void nvme_tcp_error_recovery_work(struct work_struct *work)
@@ -2289,7 +2433,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
return;
}
- nvme_tcp_reconnect_or_remove(ctrl);
+ nvme_tcp_reconnect_or_remove(ctrl, 0);
}
static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
@@ -2309,6 +2453,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl =
container_of(work, struct nvme_ctrl, reset_work);
+ int ret;
nvme_stop_ctrl(ctrl);
nvme_tcp_teardown_ctrl(ctrl, false);
@@ -2322,14 +2467,15 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
return;
}
- if (nvme_tcp_setup_ctrl(ctrl, false))
+ ret = nvme_tcp_setup_ctrl(ctrl, false);
+ if (ret)
goto out_fail;
return;
out_fail:
++ctrl->nr_reconnects;
- nvme_tcp_reconnect_or_remove(ctrl);
+ nvme_tcp_reconnect_or_remove(ctrl, ret);
}
static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)
@@ -2579,6 +2725,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
{
struct nvme_tcp_queue *queue = hctx->driver_data;
struct sock *sk = queue->sock->sk;
+ int ret;
if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
return 0;
@@ -2586,9 +2733,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
set_bit(NVME_TCP_Q_POLLING, &queue->flags);
if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue))
sk_busy_loop(sk, true);
- nvme_tcp_try_recv(queue);
+ ret = nvme_tcp_try_recv(queue);
clear_bit(NVME_TCP_Q_POLLING, &queue->flags);
- return queue->nr_cqe;
+ return ret < 0 ? ret : queue->nr_cqe;
}
static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
@@ -2599,10 +2746,11 @@ static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
len = nvmf_get_address(ctrl, buf, size);
+ if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
+ return len;
+
mutex_lock(&queue->queue_lock);
- if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
- goto done;
ret = kernel_getsockname(queue->sock, (struct sockaddr *)&src_addr);
if (ret > 0) {
if (len > 0)
@@ -2610,7 +2758,7 @@ static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
len += scnprintf(buf + len, size - len, "%ssrc_addr=%pISc\n",
(len) ? "," : "", &src_addr);
}
-done:
+
mutex_unlock(&queue->queue_lock);
return len;
@@ -2644,6 +2792,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
+ .subsystem_reset = nvmf_subsystem_reset,
.free_ctrl = nvme_tcp_free_ctrl,
.submit_async_event = nvme_tcp_submit_async_event,
.delete_ctrl = nvme_tcp_delete_ctrl,
@@ -2668,7 +2817,7 @@ nvme_tcp_existing_controller(struct nvmf_ctrl_options *opts)
return found;
}
-static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
+static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(struct device *dev,
struct nvmf_ctrl_options *opts)
{
struct nvme_tcp_ctrl *ctrl;
@@ -2743,6 +2892,28 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
if (ret)
goto out_kfree_queues;
+ return ctrl;
+out_kfree_queues:
+ kfree(ctrl->queues);
+out_free_ctrl:
+ kfree(ctrl);
+ return ERR_PTR(ret);
+}
+
+static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
+ struct nvmf_ctrl_options *opts)
+{
+ struct nvme_tcp_ctrl *ctrl;
+ int ret;
+
+ ctrl = nvme_tcp_alloc_ctrl(dev, opts);
+ if (IS_ERR(ctrl))
+ return ERR_CAST(ctrl);
+
+ ret = nvme_add_ctrl(&ctrl->ctrl);
+ if (ret)
+ goto out_put_ctrl;
+
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
WARN_ON_ONCE(1);
ret = -EINTR;
@@ -2764,15 +2935,11 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
out_uninit_ctrl:
nvme_uninit_ctrl(&ctrl->ctrl);
+out_put_ctrl:
nvme_put_ctrl(&ctrl->ctrl);
if (ret > 0)
ret = -EIO;
return ERR_PTR(ret);
-out_kfree_queues:
- kfree(ctrl->queues);
-out_free_ctrl:
- kfree(ctrl);
- return ERR_PTR(ret);
}
static struct nvmf_transport_ops nvme_tcp_transport = {
@@ -2790,6 +2957,9 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
static int __init nvme_tcp_init_module(void)
{
+ unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS;
+ int cpu;
+
BUILD_BUG_ON(sizeof(struct nvme_tcp_hdr) != 8);
BUILD_BUG_ON(sizeof(struct nvme_tcp_cmd_pdu) != 72);
BUILD_BUG_ON(sizeof(struct nvme_tcp_data_pdu) != 24);
@@ -2799,11 +2969,16 @@ static int __init nvme_tcp_init_module(void)
BUILD_BUG_ON(sizeof(struct nvme_tcp_icresp_pdu) != 128);
BUILD_BUG_ON(sizeof(struct nvme_tcp_term_pdu) != 24);
- nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq",
- WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+ if (wq_unbound)
+ wq_flags |= WQ_UNBOUND;
+
+ nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq", wq_flags, 0);
if (!nvme_tcp_wq)
return -ENOMEM;
+ for_each_possible_cpu(cpu)
+ atomic_set(&nvme_tcp_cpu_queues[cpu], 0);
+
nvmf_register_transport(&nvme_tcp_transport);
return 0;
}
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 1c36fcedea20..ad25ad1e4041 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -4,7 +4,7 @@
* Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "trace.h"
static const char *nvme_trace_delete_sq(struct trace_seq *p, u8 *cdw10)
@@ -119,7 +119,10 @@ static const char *nvme_trace_get_lba_status(struct trace_seq *p,
static const char *nvme_trace_admin_format_nvm(struct trace_seq *p, u8 *cdw10)
{
const char *ret = trace_seq_buffer_ptr(p);
- u8 lbaf = cdw10[0] & 0xF;
+ /*
+ * lbafu(bit 13:12) is already in the upper 4 bits, lbafl: bit 03:00.
+ */
+ u8 lbaf = (cdw10[1] & 0x30) | (cdw10[0] & 0xF);
u8 mset = (cdw10[0] >> 4) & 0x1;
u8 pi = (cdw10[0] >> 5) & 0x7;
u8 pil = cdw10[1] & 0x1;
@@ -164,12 +167,27 @@ static const char *nvme_trace_dsm(struct trace_seq *p, u8 *cdw10)
static const char *nvme_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10)
{
+ static const char * const zsa_strs[] = {
+ [0x01] = "close zone",
+ [0x02] = "finish zone",
+ [0x03] = "open zone",
+ [0x04] = "reset zone",
+ [0x05] = "offline zone",
+ [0x10] = "set zone descriptor extension"
+ };
const char *ret = trace_seq_buffer_ptr(p);
u64 slba = get_unaligned_le64(cdw10);
+ const char *zsa_str;
u8 zsa = cdw10[12];
u8 all = cdw10[13];
- trace_seq_printf(p, "slba=%llu, zsa=%u, all=%u", slba, zsa, all);
+ if (zsa < ARRAY_SIZE(zsa_strs) && zsa_strs[zsa])
+ zsa_str = zsa_strs[zsa];
+ else
+ zsa_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, zsa=%u:%s, all=%u",
+ slba, zsa, zsa_str, all);
trace_seq_putc(p, 0);
return ret;
@@ -177,15 +195,132 @@ static const char *nvme_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10)
static const char *nvme_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10)
{
+ static const char * const zrasf_strs[] = {
+ [0x00] = "list all zones",
+ [0x01] = "list the zones in the ZSE: Empty state",
+ [0x02] = "list the zones in the ZSIO: Implicitly Opened state",
+ [0x03] = "list the zones in the ZSEO: Explicitly Opened state",
+ [0x04] = "list the zones in the ZSC: Closed state",
+ [0x05] = "list the zones in the ZSF: Full state",
+ [0x06] = "list the zones in the ZSRO: Read Only state",
+ [0x07] = "list the zones in the ZSO: Offline state",
+ [0x09] = "list the zones that have the zone attribute"
+ };
const char *ret = trace_seq_buffer_ptr(p);
u64 slba = get_unaligned_le64(cdw10);
u32 numd = get_unaligned_le32(cdw10 + 8);
u8 zra = cdw10[12];
u8 zrasf = cdw10[13];
+ const char *zrasf_str;
u8 pr = cdw10[14];
- trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u, pr=%u",
- slba, numd, zra, zrasf, pr);
+ if (zrasf < ARRAY_SIZE(zrasf_strs) && zrasf_strs[zrasf])
+ zrasf_str = zrasf_strs[zrasf];
+ else
+ zrasf_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u:%s, pr=%u",
+ slba, numd, zra, zrasf, zrasf_str, pr);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvme_trace_resv_reg(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const rrega_strs[] = {
+ [0x00] = "register",
+ [0x01] = "unregister",
+ [0x02] = "replace",
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 rrega = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 ptpl = (cdw10[3] >> 6) & 0x3;
+ const char *rrega_str;
+
+ if (rrega < ARRAY_SIZE(rrega_strs) && rrega_strs[rrega])
+ rrega_str = rrega_strs[rrega];
+ else
+ rrega_str = "reserved";
+
+ trace_seq_printf(p, "rrega=%u:%s, iekey=%u, ptpl=%u",
+ rrega, rrega_str, iekey, ptpl);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char * const rtype_strs[] = {
+ [0x00] = "reserved",
+ [0x01] = "write exclusive",
+ [0x02] = "exclusive access",
+ [0x03] = "write exclusive registrants only",
+ [0x04] = "exclusive access registrants only",
+ [0x05] = "write exclusive all registrants",
+ [0x06] = "exclusive access all registrants",
+};
+
+static const char *nvme_trace_resv_acq(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const racqa_strs[] = {
+ [0x00] = "acquire",
+ [0x01] = "preempt",
+ [0x02] = "preempt and abort",
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 racqa = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 rtype = cdw10[1];
+ const char *racqa_str = "reserved";
+ const char *rtype_str = "reserved";
+
+ if (racqa < ARRAY_SIZE(racqa_strs) && racqa_strs[racqa])
+ racqa_str = racqa_strs[racqa];
+
+ if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype])
+ rtype_str = rtype_strs[rtype];
+
+ trace_seq_printf(p, "racqa=%u:%s, iekey=%u, rtype=%u:%s",
+ racqa, racqa_str, iekey, rtype, rtype_str);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvme_trace_resv_rel(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const rrela_strs[] = {
+ [0x00] = "release",
+ [0x01] = "clear",
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 rrela = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 rtype = cdw10[1];
+ const char *rrela_str = "reserved";
+ const char *rtype_str = "reserved";
+
+ if (rrela < ARRAY_SIZE(rrela_strs) && rrela_strs[rrela])
+ rrela_str = rrela_strs[rrela];
+
+ if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype])
+ rtype_str = rtype_strs[rtype];
+
+ trace_seq_printf(p, "rrela=%u:%s, iekey=%u, rtype=%u:%s",
+ rrela, rrela_str, iekey, rtype, rtype_str);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvme_trace_resv_report(struct trace_seq *p, u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u32 numd = get_unaligned_le32(cdw10);
+ u8 eds = cdw10[4] & 0x1;
+
+ trace_seq_printf(p, "numd=%u, eds=%u", numd, eds);
trace_seq_putc(p, 0);
return ret;
@@ -243,6 +378,14 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
return nvme_trace_zone_mgmt_send(p, cdw10);
case nvme_cmd_zone_mgmt_recv:
return nvme_trace_zone_mgmt_recv(p, cdw10);
+ case nvme_cmd_resv_register:
+ return nvme_trace_resv_reg(p, cdw10);
+ case nvme_cmd_resv_acquire:
+ return nvme_trace_resv_acq(p, cdw10);
+ case nvme_cmd_resv_release:
+ return nvme_trace_resv_rel(p, cdw10);
+ case nvme_cmd_resv_report:
+ return nvme_trace_resv_report(p, cdw10);
default:
return nvme_trace_common(p, cdw10);
}
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 499bbb0eee8d..382949e18c6a 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -7,16 +7,6 @@
#include <linux/vmalloc.h>
#include "nvme.h"
-int nvme_revalidate_zones(struct nvme_ns *ns)
-{
- struct request_queue *q = ns->queue;
-
- blk_queue_chunk_sectors(q, ns->head->zsze);
- blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
-
- return blk_revalidate_disk_zones(ns->disk, NULL);
-}
-
static int nvme_set_max_append(struct nvme_ctrl *ctrl)
{
struct nvme_command c = { };
@@ -45,10 +35,10 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
return 0;
}
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+ struct nvme_zone_info *zi)
{
struct nvme_effects_log *log = ns->head->effects;
- struct request_queue *q = ns->queue;
struct nvme_command c = { };
struct nvme_id_ns_zns *id;
int status;
@@ -99,25 +89,33 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
goto free_data;
}
- ns->head->zsze =
- nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
- if (!is_power_of_2(ns->head->zsze)) {
+ zi->zone_size = le64_to_cpu(id->lbafe[lbaf].zsze);
+ if (!is_power_of_2(zi->zone_size)) {
dev_warn(ns->ctrl->device,
- "invalid zone size:%llu for namespace:%u\n",
- ns->head->zsze, ns->head->ns_id);
+ "invalid zone size: %llu for namespace: %u\n",
+ zi->zone_size, ns->head->ns_id);
status = -ENODEV;
goto free_data;
}
+ zi->max_open_zones = le32_to_cpu(id->mor) + 1;
+ zi->max_active_zones = le32_to_cpu(id->mar) + 1;
- disk_set_zoned(ns->disk);
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
- disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
- disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
free_data:
kfree(id);
return status;
}
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+ struct nvme_zone_info *zi)
+{
+ lim->features |= BLK_FEAT_ZONED;
+ lim->max_open_zones = zi->max_open_zones;
+ lim->max_active_zones = zi->max_active_zones;
+ lim->max_hw_zone_append_sectors = ns->ctrl->max_zone_append;
+ lim->chunk_sectors = ns->head->zsze =
+ nvme_lba_to_sect(ns->head, zi->zone_size);
+}
+
static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
unsigned int nr_zones, size_t *buflen)
{
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 872dd1a0acd8..fb7446d6d682 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -6,7 +6,6 @@ config NVME_TARGET
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
This enabled target side support for the NVMe protocol, that is
@@ -18,6 +17,15 @@ config NVME_TARGET
To configure the NVMe target you probably want to use the nvmetcli
tool from http://git.infradead.org/users/hch/nvmetcli.git.
+config NVME_TARGET_DEBUGFS
+ bool "NVMe Target debugfs support"
+ depends on NVME_TARGET
+ help
+ This enables debugfs support to display the connected controllers
+ to each subsystem
+
+ If unsure, say N.
+
config NVME_TARGET_PASSTHRU
bool "NVMe Target Passthrough support"
depends on NVME_TARGET
@@ -107,3 +115,14 @@ config NVME_TARGET_AUTH
target side.
If unsure, say N.
+
+config NVME_TARGET_PCI_EPF
+ tristate "NVMe PCI Endpoint Function target support"
+ depends on NVME_TARGET && PCI_ENDPOINT
+ depends on NVME_CORE=y || NVME_CORE=NVME_TARGET
+ help
+ This enables the NVMe PCI Endpoint Function target driver support,
+ which allows creating a NVMe PCI controller using an endpoint mode
+ capable PCI controller.
+
+ If unsure, say N.
diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile
index c66820102493..ed8522911d1f 100644
--- a/drivers/nvme/target/Makefile
+++ b/drivers/nvme/target/Makefile
@@ -8,9 +8,11 @@ obj-$(CONFIG_NVME_TARGET_RDMA) += nvmet-rdma.o
obj-$(CONFIG_NVME_TARGET_FC) += nvmet-fc.o
obj-$(CONFIG_NVME_TARGET_FCLOOP) += nvme-fcloop.o
obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o
+obj-$(CONFIG_NVME_TARGET_PCI_EPF) += nvmet-pci-epf.o
nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \
- discovery.o io-cmd-file.o io-cmd-bdev.o
+ discovery.o io-cmd-file.o io-cmd-bdev.o pr.o
+nvmet-$(CONFIG_NVME_TARGET_DEBUGFS) += debugfs.o
nvmet-$(CONFIG_NVME_TARGET_PASSTHRU) += passthru.o
nvmet-$(CONFIG_BLK_DEV_ZONED) += zns.o
nvmet-$(CONFIG_NVME_TARGET_AUTH) += fabrics-cmd-auth.o auth.o
@@ -19,4 +21,5 @@ nvmet-rdma-y += rdma.o
nvmet-fc-y += fc.o
nvme-fcloop-y += fcloop.o
nvmet-tcp-y += tcp.o
+nvmet-pci-epf-y += pci-epf.o
nvmet-$(CONFIG_TRACING) += trace.o
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 39cb570f833d..acc138bbf8f2 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -9,9 +9,145 @@
#include <linux/part_stat.h>
#include <generated/utsrelease.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "nvmet.h"
+static void nvmet_execute_delete_sq(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ u16 sqid = le16_to_cpu(req->cmd->delete_queue.qid);
+ u16 status;
+
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ status = nvmet_report_invalid_opcode(req);
+ goto complete;
+ }
+
+ if (!sqid) {
+ status = NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ status = nvmet_check_sqid(ctrl, sqid, false);
+ if (status != NVME_SC_SUCCESS)
+ goto complete;
+
+ status = ctrl->ops->delete_sq(ctrl, sqid);
+
+complete:
+ nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_create_sq(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvme_command *cmd = req->cmd;
+ u16 sqid = le16_to_cpu(cmd->create_sq.sqid);
+ u16 cqid = le16_to_cpu(cmd->create_sq.cqid);
+ u16 sq_flags = le16_to_cpu(cmd->create_sq.sq_flags);
+ u16 qsize = le16_to_cpu(cmd->create_sq.qsize);
+ u64 prp1 = le64_to_cpu(cmd->create_sq.prp1);
+ u16 status;
+
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ status = nvmet_report_invalid_opcode(req);
+ goto complete;
+ }
+
+ if (!sqid) {
+ status = NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ status = nvmet_check_sqid(ctrl, sqid, true);
+ if (status != NVME_SC_SUCCESS)
+ goto complete;
+
+ /*
+ * Note: The NVMe specification allows multiple SQs to use the same CQ.
+ * However, the target code does not really support that. So for now,
+ * prevent this and fail the command if sqid and cqid are different.
+ */
+ if (!cqid || cqid != sqid) {
+ pr_err("SQ %u: Unsupported CQID %u\n", sqid, cqid);
+ status = NVME_SC_CQ_INVALID | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ if (!qsize || qsize > NVME_CAP_MQES(ctrl->cap)) {
+ status = NVME_SC_QUEUE_SIZE | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ status = ctrl->ops->create_sq(ctrl, sqid, sq_flags, qsize, prp1);
+
+complete:
+ nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_delete_cq(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ u16 cqid = le16_to_cpu(req->cmd->delete_queue.qid);
+ u16 status;
+
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ status = nvmet_report_invalid_opcode(req);
+ goto complete;
+ }
+
+ if (!cqid) {
+ status = NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ status = nvmet_check_cqid(ctrl, cqid);
+ if (status != NVME_SC_SUCCESS)
+ goto complete;
+
+ status = ctrl->ops->delete_cq(ctrl, cqid);
+
+complete:
+ nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_create_cq(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvme_command *cmd = req->cmd;
+ u16 cqid = le16_to_cpu(cmd->create_cq.cqid);
+ u16 cq_flags = le16_to_cpu(cmd->create_cq.cq_flags);
+ u16 qsize = le16_to_cpu(cmd->create_cq.qsize);
+ u16 irq_vector = le16_to_cpu(cmd->create_cq.irq_vector);
+ u64 prp1 = le64_to_cpu(cmd->create_cq.prp1);
+ u16 status;
+
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ status = nvmet_report_invalid_opcode(req);
+ goto complete;
+ }
+
+ if (!cqid) {
+ status = NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ status = nvmet_check_cqid(ctrl, cqid);
+ if (status != NVME_SC_SUCCESS)
+ goto complete;
+
+ if (!qsize || qsize > NVME_CAP_MQES(ctrl->cap)) {
+ status = NVME_SC_QUEUE_SIZE | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ status = ctrl->ops->create_cq(ctrl, cqid, cq_flags, qsize,
+ prp1, irq_vector);
+
+complete:
+ nvmet_req_complete(req, status);
+}
+
u32 nvmet_get_log_page_len(struct nvme_command *cmd)
{
u32 len = le16_to_cpu(cmd->get_log_page.numdu);
@@ -71,6 +207,35 @@ static void nvmet_execute_get_log_page_error(struct nvmet_req *req)
nvmet_req_complete(req, 0);
}
+static void nvmet_execute_get_supported_log_pages(struct nvmet_req *req)
+{
+ struct nvme_supported_log *logs;
+ u16 status;
+
+ logs = kzalloc(sizeof(*logs), GFP_KERNEL);
+ if (!logs) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ logs->lids[NVME_LOG_SUPPORTED] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_ERROR] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_SMART] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_FW_SLOT] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_CHANGED_NS] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_CMD_EFFECTS] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_ENDURANCE_GROUP] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_ANA] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_FEATURES] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_RMI] = cpu_to_le32(NVME_LIDS_LSUPP);
+ logs->lids[NVME_LOG_RESERVATION] = cpu_to_le32(NVME_LIDS_LSUPP);
+
+ status = nvmet_copy_to_sgl(req, 0, logs, sizeof(*logs));
+ kfree(logs);
+out:
+ nvmet_req_complete(req, status);
+}
+
static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
struct nvme_smart_log *slog)
{
@@ -110,7 +275,7 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
unsigned long idx;
ctrl = req->sq->ctrl;
- xa_for_each(&ctrl->subsys->namespaces, idx, ns) {
+ nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) {
/* we don't have the right data for file backed ns */
if (!ns->bdev)
continue;
@@ -130,6 +295,45 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
return NVME_SC_SUCCESS;
}
+static void nvmet_execute_get_log_page_rmi(struct nvmet_req *req)
+{
+ struct nvme_rotational_media_log *log;
+ struct gendisk *disk;
+ u16 status;
+
+ req->cmd->common.nsid = cpu_to_le32(le16_to_cpu(
+ req->cmd->get_log_page.lsi));
+ status = nvmet_req_find_ns(req);
+ if (status)
+ goto out;
+
+ if (!req->ns->bdev || bdev_nonrot(req->ns->bdev)) {
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ if (req->transfer_len != sizeof(*log)) {
+ status = NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ log = kzalloc(sizeof(*log), GFP_KERNEL);
+ if (!log)
+ goto out;
+
+ log->endgid = req->cmd->get_log_page.lsi;
+ disk = req->ns->bdev->bd_disk;
+ if (disk && disk->ia_ranges)
+ log->numa = cpu_to_le16(disk->ia_ranges->nr_ia_ranges);
+ else
+ log->numa = cpu_to_le16(1);
+
+ status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+ kfree(log);
+out:
+ nvmet_req_complete(req, status);
+}
+
static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
{
struct nvme_smart_log *log;
@@ -162,8 +366,18 @@ out:
nvmet_req_complete(req, status);
}
-static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
+static void nvmet_get_cmd_effects_admin(struct nvmet_ctrl *ctrl,
+ struct nvme_effects_log *log)
{
+ /* For a PCI target controller, advertize support for the . */
+ if (nvmet_is_pci_ctrl(ctrl)) {
+ log->acs[nvme_admin_delete_sq] =
+ log->acs[nvme_admin_create_sq] =
+ log->acs[nvme_admin_delete_cq] =
+ log->acs[nvme_admin_create_cq] =
+ cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+ }
+
log->acs[nvme_admin_get_log_page] =
log->acs[nvme_admin_identify] =
log->acs[nvme_admin_abort_cmd] =
@@ -172,10 +386,17 @@ static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
log->acs[nvme_admin_async_event] =
log->acs[nvme_admin_keep_alive] =
cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+}
+static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
+{
log->iocs[nvme_cmd_read] =
log->iocs[nvme_cmd_flush] =
log->iocs[nvme_cmd_dsm] =
+ log->iocs[nvme_cmd_resv_acquire] =
+ log->iocs[nvme_cmd_resv_register] =
+ log->iocs[nvme_cmd_resv_release] =
+ log->iocs[nvme_cmd_resv_report] =
cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
log->iocs[nvme_cmd_write] =
log->iocs[nvme_cmd_write_zeroes] =
@@ -193,6 +414,7 @@ static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log)
static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_effects_log *log;
u16 status = NVME_SC_SUCCESS;
@@ -204,6 +426,7 @@ static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
switch (req->cmd->get_log_page.csi) {
case NVME_CSI_NVM:
+ nvmet_get_cmd_effects_admin(ctrl, log);
nvmet_get_cmd_effects_nvm(log);
break;
case NVME_CSI_ZNS:
@@ -211,6 +434,7 @@ static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
status = NVME_SC_INVALID_IO_CMD_SET;
goto free;
}
+ nvmet_get_cmd_effects_admin(ctrl, log);
nvmet_get_cmd_effects_nvm(log);
nvmet_get_cmd_effects_zns(log);
break;
@@ -259,9 +483,10 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
u32 count = 0;
if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
- xa_for_each(&ctrl->subsys->namespaces, idx, ns)
+ nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) {
if (ns->anagrpid == grpid)
desc->nsids[count++] = cpu_to_le32(ns->nsid);
+ }
}
desc->grpid = cpu_to_le32(grpid);
@@ -272,6 +497,49 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
return struct_size(desc, nsids, count);
}
+static void nvmet_execute_get_log_page_endgrp(struct nvmet_req *req)
+{
+ u64 host_reads, host_writes, data_units_read, data_units_written;
+ struct nvme_endurance_group_log *log;
+ u16 status;
+
+ /*
+ * The target driver emulates each endurance group as its own
+ * namespace, reusing the nsid as the endurance group identifier.
+ */
+ req->cmd->common.nsid = cpu_to_le32(le16_to_cpu(
+ req->cmd->get_log_page.lsi));
+ status = nvmet_req_find_ns(req);
+ if (status)
+ goto out;
+
+ log = kzalloc(sizeof(*log), GFP_KERNEL);
+ if (!log) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ if (!req->ns->bdev)
+ goto copy;
+
+ host_reads = part_stat_read(req->ns->bdev, ios[READ]);
+ data_units_read =
+ DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[READ]), 1000);
+ host_writes = part_stat_read(req->ns->bdev, ios[WRITE]);
+ data_units_written =
+ DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[WRITE]), 1000);
+
+ put_unaligned_le64(host_reads, &log->hrc[0]);
+ put_unaligned_le64(data_units_read, &log->dur[0]);
+ put_unaligned_le64(host_writes, &log->hwc[0]);
+ put_unaligned_le64(data_units_written, &log->duw[0]);
+copy:
+ status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+ kfree(log);
+out:
+ nvmet_req_complete(req, status);
+}
+
static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
{
struct nvme_ana_rsp_hdr hdr = { 0, };
@@ -317,12 +585,44 @@ out:
nvmet_req_complete(req, status);
}
+static void nvmet_execute_get_log_page_features(struct nvmet_req *req)
+{
+ struct nvme_supported_features_log *features;
+ u16 status;
+
+ features = kzalloc(sizeof(*features), GFP_KERNEL);
+ if (!features) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ features->fis[NVME_FEAT_NUM_QUEUES] =
+ cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE);
+ features->fis[NVME_FEAT_KATO] =
+ cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE);
+ features->fis[NVME_FEAT_ASYNC_EVENT] =
+ cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE);
+ features->fis[NVME_FEAT_HOST_ID] =
+ cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_CSCPE);
+ features->fis[NVME_FEAT_WRITE_PROTECT] =
+ cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_NSCPE);
+ features->fis[NVME_FEAT_RESV_MASK] =
+ cpu_to_le32(NVME_FIS_FSUPP | NVME_FIS_NSCPE);
+
+ status = nvmet_copy_to_sgl(req, 0, features, sizeof(*features));
+ kfree(features);
+out:
+ nvmet_req_complete(req, status);
+}
+
static void nvmet_execute_get_log_page(struct nvmet_req *req)
{
if (!nvmet_check_transfer_len(req, nvmet_get_log_page_len(req->cmd)))
return;
switch (req->cmd->get_log_page.lid) {
+ case NVME_LOG_SUPPORTED:
+ return nvmet_execute_get_supported_log_pages(req);
case NVME_LOG_ERROR:
return nvmet_execute_get_log_page_error(req);
case NVME_LOG_SMART:
@@ -338,13 +638,21 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
return nvmet_execute_get_log_changed_ns(req);
case NVME_LOG_CMD_EFFECTS:
return nvmet_execute_get_log_cmd_effects_ns(req);
+ case NVME_LOG_ENDURANCE_GROUP:
+ return nvmet_execute_get_log_page_endgrp(req);
case NVME_LOG_ANA:
return nvmet_execute_get_log_page_ana(req);
+ case NVME_LOG_FEATURES:
+ return nvmet_execute_get_log_page_features(req);
+ case NVME_LOG_RMI:
+ return nvmet_execute_get_log_page_rmi(req);
+ case NVME_LOG_RESERVATION:
+ return nvmet_execute_get_log_page_resv(req);
}
pr_debug("unhandled lid %d on qid %d\n",
req->cmd->get_log_page.lid, req->sq->qid);
req->error_loc = offsetof(struct nvme_get_log_page_command, lid);
- nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+ nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_STATUS_DNR);
}
static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
@@ -352,7 +660,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmet_subsys *subsys = ctrl->subsys;
struct nvme_id_ctrl *id;
- u32 cmd_capsule_size;
+ u32 cmd_capsule_size, ctratt;
u16 status = 0;
if (!subsys->subsys_discovered) {
@@ -367,9 +675,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
goto out;
}
- /* XXX: figure out how to assign real vendors IDs. */
- id->vid = 0;
- id->ssvid = 0;
+ id->vid = cpu_to_le16(subsys->vendor_id);
+ id->ssvid = cpu_to_le16(subsys->subsys_vendor_id);
memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE);
memcpy_and_pad(id->mn, sizeof(id->mn), subsys->model_number,
@@ -401,8 +708,10 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
/* XXX: figure out what to do about RTD3R/RTD3 */
id->oaes = cpu_to_le32(NVMET_AEN_CFG_OPTIONAL);
- id->ctratt = cpu_to_le32(NVME_CTRL_ATTR_HID_128_BIT |
- NVME_CTRL_ATTR_TBKAS);
+ ctratt = NVME_CTRL_ATTR_HID_128_BIT | NVME_CTRL_ATTR_TBKAS;
+ if (nvmet_is_pci_ctrl(ctrl))
+ ctratt |= NVME_CTRL_ATTR_RHII;
+ id->ctratt = cpu_to_le32(ctratt);
id->oacs = 0;
@@ -428,12 +737,13 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->cqes = (0x4 << 4) | 0x4;
/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
- id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+ id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
- NVME_CTRL_ONCS_WRITE_ZEROES);
+ NVME_CTRL_ONCS_WRITE_ZEROES |
+ NVME_CTRL_ONCS_RESERVATIONS);
/* XXX: don't report vwc if the underlying device is write through */
id->vwc = NVME_CTRL_VWC_PRESENT;
@@ -445,11 +755,12 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->awun = 0;
id->awupf = 0;
- id->sgls = cpu_to_le32(1 << 0); /* we always support SGLs */
+ /* we always support SGLs */
+ id->sgls = cpu_to_le32(NVME_CTRL_SGLS_BYTE_ALIGNED);
if (ctrl->ops->flags & NVMF_KEYED_SGLS)
- id->sgls |= cpu_to_le32(1 << 2);
+ id->sgls |= cpu_to_le32(NVME_CTRL_SGLS_KSDBDS);
if (req->port->inline_data_size)
- id->sgls |= cpu_to_le32(1 << 20);
+ id->sgls |= cpu_to_le32(NVME_CTRL_SGLS_SAOS);
strscpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn));
@@ -467,6 +778,13 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->msdbd = ctrl->ops->msdbd;
+ /*
+ * Endurance group identifier is 16 bits, so we can't let namespaces
+ * overflow that since we reuse the nsid
+ */
+ BUILD_BUG_ON(NVMET_MAX_NAMESPACES > USHRT_MAX);
+ id->endgidmax = cpu_to_le16(NVMET_MAX_NAMESPACES);
+
id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4);
id->anatt = 10; /* random value */
id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS);
@@ -496,7 +814,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
req->error_loc = offsetof(struct nvme_identify, nsid);
- status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
goto out;
}
@@ -551,6 +869,21 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
id->nmic = NVME_NS_NMIC_SHARED;
id->anagrpid = cpu_to_le32(req->ns->anagrpid);
+ if (req->ns->pr.enable)
+ id->rescap = NVME_PR_SUPPORT_WRITE_EXCLUSIVE |
+ NVME_PR_SUPPORT_EXCLUSIVE_ACCESS |
+ NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY |
+ NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY |
+ NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS |
+ NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS |
+ NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF;
+
+ /*
+ * Since we don't know any better, every namespace is its own endurance
+ * group.
+ */
+ id->endgid = cpu_to_le16(req->ns->nsid);
+
memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid));
id->lbaf[0].ds = req->ns->blksize_shift;
@@ -576,7 +909,40 @@ out:
nvmet_req_complete(req, status);
}
-static void nvmet_execute_identify_nslist(struct nvmet_req *req)
+static void nvmet_execute_identify_endgrp_list(struct nvmet_req *req)
+{
+ u16 min_endgid = le16_to_cpu(req->cmd->identify.cnssid);
+ static const int buf_size = NVME_IDENTIFY_DATA_SIZE;
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_ns *ns;
+ unsigned long idx;
+ __le16 *list;
+ u16 status;
+ int i = 1;
+
+ list = kzalloc(buf_size, GFP_KERNEL);
+ if (!list) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) {
+ if (ns->nsid <= min_endgid)
+ continue;
+
+ list[i++] = cpu_to_le16(ns->nsid);
+ if (i == buf_size / sizeof(__le16))
+ break;
+ }
+
+ list[0] = cpu_to_le16(i - 1);
+ status = nvmet_copy_to_sgl(req, 0, list, buf_size);
+ kfree(list);
+out:
+ nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_identify_nslist(struct nvmet_req *req, bool match_css)
{
static const int buf_size = NVME_IDENTIFY_DATA_SIZE;
struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -587,15 +953,27 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req)
u16 status = 0;
int i = 0;
+ /*
+ * NSID values 0xFFFFFFFE and NVME_NSID_ALL are invalid
+ * See NVMe Base Specification, Active Namespace ID list (CNS 02h).
+ */
+ if (min_nsid == 0xFFFFFFFE || min_nsid == NVME_NSID_ALL) {
+ req->error_loc = offsetof(struct nvme_identify, nsid);
+ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
+ goto out;
+ }
+
list = kzalloc(buf_size, GFP_KERNEL);
if (!list) {
status = NVME_SC_INTERNAL;
goto out;
}
- xa_for_each(&ctrl->subsys->namespaces, idx, ns) {
+ nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) {
if (ns->nsid <= min_nsid)
continue;
+ if (match_css && req->ns->csi != req->cmd->identify.csi)
+ continue;
list[i++] = cpu_to_le32(ns->nsid);
if (i == buf_size / sizeof(__le32))
break;
@@ -662,7 +1040,7 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req)
if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off,
off) != NVME_IDENTIFY_DATA_SIZE - off)
- status = NVME_SC_INTERNAL | NVME_SC_DNR;
+ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
out:
nvmet_req_complete(req, status);
@@ -675,6 +1053,62 @@ static void nvmet_execute_identify_ctrl_nvm(struct nvmet_req *req)
nvmet_zero_sgl(req, 0, sizeof(struct nvme_id_ctrl_nvm)));
}
+static void nvme_execute_identify_ns_nvm(struct nvmet_req *req)
+{
+ u16 status;
+ struct nvme_id_ns_nvm *id;
+
+ status = nvmet_req_find_ns(req);
+ if (status)
+ goto out;
+
+ id = kzalloc(sizeof(*id), GFP_KERNEL);
+ if (!id) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+ status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+ kfree(id);
+out:
+ nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_id_cs_indep(struct nvmet_req *req)
+{
+ struct nvme_id_ns_cs_indep *id;
+ u16 status;
+
+ status = nvmet_req_find_ns(req);
+ if (status)
+ goto out;
+
+ id = kzalloc(sizeof(*id), GFP_KERNEL);
+ if (!id) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ id->nstat = NVME_NSTAT_NRDY;
+ id->anagrpid = cpu_to_le32(req->ns->anagrpid);
+ id->nmic = NVME_NS_NMIC_SHARED;
+ if (req->ns->readonly)
+ id->nsattr |= NVME_NS_ATTR_RO;
+ if (req->ns->bdev && !bdev_nonrot(req->ns->bdev))
+ id->nsfeat |= NVME_NS_ROTATIONAL;
+ /*
+ * We need flush command to flush the file's metadata,
+ * so report supporting vwc if backend is file, even
+ * though buffered_io is disable.
+ */
+ if (req->ns->bdev && !bdev_write_cache(req->ns->bdev))
+ id->nsfeat |= NVME_NS_VWC_NOT_PRESENT;
+
+ status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+ kfree(id);
+out:
+ nvmet_req_complete(req, status);
+}
+
static void nvmet_execute_identify(struct nvmet_req *req)
{
if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE))
@@ -688,7 +1122,7 @@ static void nvmet_execute_identify(struct nvmet_req *req)
nvmet_execute_identify_ctrl(req);
return;
case NVME_ID_CNS_NS_ACTIVE_LIST:
- nvmet_execute_identify_nslist(req);
+ nvmet_execute_identify_nslist(req, false);
return;
case NVME_ID_CNS_NS_DESC_LIST:
nvmet_execute_identify_desclist(req);
@@ -696,8 +1130,8 @@ static void nvmet_execute_identify(struct nvmet_req *req)
case NVME_ID_CNS_CS_NS:
switch (req->cmd->identify.csi) {
case NVME_CSI_NVM:
- /* Not supported */
- break;
+ nvme_execute_identify_ns_nvm(req);
+ return;
case NVME_CSI_ZNS:
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
nvmet_execute_identify_ns_zns(req);
@@ -719,12 +1153,21 @@ static void nvmet_execute_identify(struct nvmet_req *req)
break;
}
break;
+ case NVME_ID_CNS_NS_ACTIVE_LIST_CS:
+ nvmet_execute_identify_nslist(req, true);
+ return;
+ case NVME_ID_CNS_NS_CS_INDEP:
+ nvmet_execute_id_cs_indep(req);
+ return;
+ case NVME_ID_CNS_ENDGRP_LIST:
+ nvmet_execute_identify_endgrp_list(req);
+ return;
}
pr_debug("unhandled identify cns %d on qid %d\n",
req->cmd->identify.cns, req->sq->qid);
req->error_loc = offsetof(struct nvme_identify, cns);
- nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+ nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_STATUS_DNR);
}
/*
@@ -807,7 +1250,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
if (val32 & ~mask) {
req->error_loc = offsetof(struct nvme_common_command, cdw11);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
@@ -816,6 +1259,92 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
return 0;
}
+static u16 nvmet_set_feat_host_id(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+
+ if (!nvmet_is_pci_ctrl(ctrl))
+ return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
+
+ /*
+ * The NVMe base specifications v2.1 recommends supporting 128-bits host
+ * IDs (section 5.1.25.1.28.1). However, that same section also says
+ * that "The controller may support a 64-bit Host Identifier and/or an
+ * extended 128-bit Host Identifier". So simplify this support and do
+ * not support 64-bits host IDs to avoid needing to check that all
+ * controllers associated with the same subsystem all use the same host
+ * ID size.
+ */
+ if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw11);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ return nvmet_copy_from_sgl(req, 0, &req->sq->ctrl->hostid,
+ sizeof(req->sq->ctrl->hostid));
+}
+
+static u16 nvmet_set_feat_irq_coalesce(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
+ struct nvmet_feat_irq_coalesce irqc = {
+ .time = (cdw11 >> 8) & 0xff,
+ .thr = cdw11 & 0xff,
+ };
+
+ /*
+ * This feature is not supported for fabrics controllers and mandatory
+ * for PCI controllers.
+ */
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ return ctrl->ops->set_feature(ctrl, NVME_FEAT_IRQ_COALESCE, &irqc);
+}
+
+static u16 nvmet_set_feat_irq_config(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
+ struct nvmet_feat_irq_config irqcfg = {
+ .iv = cdw11 & 0xffff,
+ .cd = (cdw11 >> 16) & 0x1,
+ };
+
+ /*
+ * This feature is not supported for fabrics controllers and mandatory
+ * for PCI controllers.
+ */
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ return ctrl->ops->set_feature(ctrl, NVME_FEAT_IRQ_CONFIG, &irqcfg);
+}
+
+static u16 nvmet_set_feat_arbitration(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
+ struct nvmet_feat_arbitration arb = {
+ .hpw = (cdw11 >> 24) & 0xff,
+ .mpw = (cdw11 >> 16) & 0xff,
+ .lpw = (cdw11 >> 8) & 0xff,
+ .ab = cdw11 & 0x3,
+ };
+
+ if (!ctrl->ops->set_feature) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ return ctrl->ops->set_feature(ctrl, NVME_FEAT_ARBITRATION, &arb);
+}
+
void nvmet_execute_set_features(struct nvmet_req *req)
{
struct nvmet_subsys *subsys = nvmet_req_subsys(req);
@@ -829,16 +1358,25 @@ void nvmet_execute_set_features(struct nvmet_req *req)
return;
switch (cdw10 & 0xff) {
+ case NVME_FEAT_ARBITRATION:
+ status = nvmet_set_feat_arbitration(req);
+ break;
case NVME_FEAT_NUM_QUEUES:
ncqr = (cdw11 >> 16) & 0xffff;
nsqr = cdw11 & 0xffff;
if (ncqr == 0xffff || nsqr == 0xffff) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
nvmet_set_result(req,
(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
break;
+ case NVME_FEAT_IRQ_COALESCE:
+ status = nvmet_set_feat_irq_coalesce(req);
+ break;
+ case NVME_FEAT_IRQ_CONFIG:
+ status = nvmet_set_feat_irq_config(req);
+ break;
case NVME_FEAT_KATO:
status = nvmet_set_feat_kato(req);
break;
@@ -846,14 +1384,17 @@ void nvmet_execute_set_features(struct nvmet_req *req)
status = nvmet_set_feat_async_event(req, NVMET_AEN_CFG_ALL);
break;
case NVME_FEAT_HOST_ID:
- status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ status = nvmet_set_feat_host_id(req);
break;
case NVME_FEAT_WRITE_PROTECT:
status = nvmet_set_feat_write_protect(req);
break;
+ case NVME_FEAT_RESV_MASK:
+ status = nvmet_set_feat_resv_notif_mask(req, cdw11);
+ break;
default:
req->error_loc = offsetof(struct nvme_common_command, cdw10);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
@@ -880,6 +1421,79 @@ static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
return 0;
}
+static u16 nvmet_get_feat_irq_coalesce(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_feat_irq_coalesce irqc = { };
+ u16 status;
+
+ /*
+ * This feature is not supported for fabrics controllers and mandatory
+ * for PCI controllers.
+ */
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ status = ctrl->ops->get_feature(ctrl, NVME_FEAT_IRQ_COALESCE, &irqc);
+ if (status != NVME_SC_SUCCESS)
+ return status;
+
+ nvmet_set_result(req, ((u32)irqc.time << 8) | (u32)irqc.thr);
+
+ return NVME_SC_SUCCESS;
+}
+
+static u16 nvmet_get_feat_irq_config(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ u32 iv = le32_to_cpu(req->cmd->common.cdw11) & 0xffff;
+ struct nvmet_feat_irq_config irqcfg = { .iv = iv };
+ u16 status;
+
+ /*
+ * This feature is not supported for fabrics controllers and mandatory
+ * for PCI controllers.
+ */
+ if (!nvmet_is_pci_ctrl(ctrl)) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ status = ctrl->ops->get_feature(ctrl, NVME_FEAT_IRQ_CONFIG, &irqcfg);
+ if (status != NVME_SC_SUCCESS)
+ return status;
+
+ nvmet_set_result(req, ((u32)irqcfg.cd << 16) | iv);
+
+ return NVME_SC_SUCCESS;
+}
+
+static u16 nvmet_get_feat_arbitration(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_feat_arbitration arb = { };
+ u16 status;
+
+ if (!ctrl->ops->get_feature) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ status = ctrl->ops->get_feature(ctrl, NVME_FEAT_ARBITRATION, &arb);
+ if (status != NVME_SC_SUCCESS)
+ return status;
+
+ nvmet_set_result(req,
+ ((u32)arb.hpw << 24) |
+ ((u32)arb.mpw << 16) |
+ ((u32)arb.lpw << 8) |
+ (arb.ab & 0x3));
+
+ return NVME_SC_SUCCESS;
+}
+
void nvmet_get_feat_kato(struct nvmet_req *req)
{
nvmet_set_result(req, req->sq->ctrl->kato * 1000);
@@ -906,21 +1520,24 @@ void nvmet_execute_get_features(struct nvmet_req *req)
* need to come up with some fake values for these.
*/
#if 0
- case NVME_FEAT_ARBITRATION:
- break;
case NVME_FEAT_POWER_MGMT:
break;
case NVME_FEAT_TEMP_THRESH:
break;
case NVME_FEAT_ERR_RECOVERY:
break;
+ case NVME_FEAT_WRITE_ATOMIC:
+ break;
+#endif
+ case NVME_FEAT_ARBITRATION:
+ status = nvmet_get_feat_arbitration(req);
+ break;
case NVME_FEAT_IRQ_COALESCE:
+ status = nvmet_get_feat_irq_coalesce(req);
break;
case NVME_FEAT_IRQ_CONFIG:
+ status = nvmet_get_feat_irq_config(req);
break;
- case NVME_FEAT_WRITE_ATOMIC:
- break;
-#endif
case NVME_FEAT_ASYNC_EVENT:
nvmet_get_feat_async_event(req);
break;
@@ -939,7 +1556,7 @@ void nvmet_execute_get_features(struct nvmet_req *req)
if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) {
req->error_loc =
offsetof(struct nvme_common_command, cdw11);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
@@ -949,10 +1566,13 @@ void nvmet_execute_get_features(struct nvmet_req *req)
case NVME_FEAT_WRITE_PROTECT:
status = nvmet_get_feat_write_protect(req);
break;
+ case NVME_FEAT_RESV_MASK:
+ status = nvmet_get_feat_resv_notif_mask(req);
+ break;
default:
req->error_loc =
offsetof(struct nvme_common_command, cdw10);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
@@ -969,7 +1589,7 @@ void nvmet_execute_async_event(struct nvmet_req *req)
mutex_lock(&ctrl->lock);
if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) {
mutex_unlock(&ctrl->lock);
- nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_SC_DNR);
+ nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_STATUS_DNR);
return;
}
ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
@@ -998,6 +1618,27 @@ out:
nvmet_req_complete(req, status);
}
+u32 nvmet_admin_cmd_data_len(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+
+ if (nvme_is_fabrics(cmd))
+ return nvmet_fabrics_admin_cmd_data_len(req);
+ if (nvmet_is_disc_subsys(nvmet_req_subsys(req)))
+ return nvmet_discovery_cmd_data_len(req);
+
+ switch (cmd->common.opcode) {
+ case nvme_admin_get_log_page:
+ return nvmet_get_log_page_len(cmd);
+ case nvme_admin_identify:
+ return NVME_IDENTIFY_DATA_SIZE;
+ case nvme_admin_get_features:
+ return nvmet_feat_data_len(req, le32_to_cpu(cmd->common.cdw10));
+ default:
+ return 0;
+ }
+}
+
u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
@@ -1005,8 +1646,6 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
if (nvme_is_fabrics(cmd))
return nvmet_parse_fabrics_admin_cmd(req);
- if (unlikely(!nvmet_check_auth_status(req)))
- return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR;
if (nvmet_is_disc_subsys(nvmet_req_subsys(req)))
return nvmet_parse_discovery_cmd(req);
@@ -1014,13 +1653,30 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
if (unlikely(ret))
return ret;
+ /* For PCI controllers, admin commands shall not use SGL. */
+ if (nvmet_is_pci_ctrl(req->sq->ctrl) && !req->sq->qid &&
+ cmd->common.flags & NVME_CMD_SGL_ALL)
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+
if (nvmet_is_passthru_req(req))
return nvmet_parse_passthru_admin_cmd(req);
switch (cmd->common.opcode) {
+ case nvme_admin_delete_sq:
+ req->execute = nvmet_execute_delete_sq;
+ return 0;
+ case nvme_admin_create_sq:
+ req->execute = nvmet_execute_create_sq;
+ return 0;
case nvme_admin_get_log_page:
req->execute = nvmet_execute_get_log_page;
return 0;
+ case nvme_admin_delete_cq:
+ req->execute = nvmet_execute_delete_cq;
+ return 0;
+ case nvme_admin_create_cq:
+ req->execute = nvmet_execute_create_cq;
+ return 0;
case nvme_admin_identify:
req->execute = nvmet_execute_identify;
return 0;
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index 3ddbc3880cac..b47d675232d2 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -15,7 +15,7 @@
#include <linux/ctype.h>
#include <linux/random.h>
#include <linux/nvme-auth.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "nvmet.h"
@@ -25,6 +25,18 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret,
unsigned char key_hash;
char *dhchap_secret;
+ if (!strlen(secret)) {
+ if (set_ctrl) {
+ kfree(host->dhchap_ctrl_secret);
+ host->dhchap_ctrl_secret = NULL;
+ host->dhchap_ctrl_key_hash = 0;
+ } else {
+ kfree(host->dhchap_secret);
+ host->dhchap_secret = NULL;
+ host->dhchap_key_hash = 0;
+ }
+ return 0;
+ }
if (sscanf(secret, "DHHC-1:%hhd:%*s", &key_hash) != 1)
return -EINVAL;
if (key_hash > 3) {
@@ -44,6 +56,7 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret,
dhchap_secret = kstrdup(secret, GFP_KERNEL);
if (!dhchap_secret)
return -ENOMEM;
+ down_write(&nvmet_config_sem);
if (set_ctrl) {
kfree(host->dhchap_ctrl_secret);
host->dhchap_ctrl_secret = strim(dhchap_secret);
@@ -53,6 +66,7 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret,
host->dhchap_secret = strim(dhchap_secret);
host->dhchap_key_hash = key_hash;
}
+ up_write(&nvmet_config_sem);
return 0;
}
@@ -101,6 +115,7 @@ int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id)
pr_debug("%s: ctrl %d failed to generate private key, err %d\n",
__func__, ctrl->cntlid, ret);
kfree_sensitive(ctrl->dh_key);
+ ctrl->dh_key = NULL;
return ret;
}
ctrl->dh_keysize = crypto_kpp_maxsize(ctrl->dh_tfm);
@@ -124,12 +139,11 @@ int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id)
return ret;
}
-int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
+u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl)
{
int ret = 0;
struct nvmet_host_link *p;
struct nvmet_host *host = NULL;
- const char *hash_name;
down_read(&nvmet_config_sem);
if (nvmet_is_disc_subsys(ctrl->subsys))
@@ -147,13 +161,16 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
}
if (!host) {
pr_debug("host %s not found\n", ctrl->hostnqn);
- ret = -EPERM;
+ ret = NVME_AUTH_DHCHAP_FAILURE_FAILED;
goto out_unlock;
}
ret = nvmet_setup_dhgroup(ctrl, host->dhchap_dhgroup_id);
- if (ret < 0)
+ if (ret < 0) {
pr_warn("Failed to setup DH group");
+ ret = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE;
+ goto out_unlock;
+ }
if (!host->dhchap_secret) {
pr_debug("No authentication provided\n");
@@ -164,12 +181,6 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
pr_debug("Re-use existing hash ID %d\n",
ctrl->shash_id);
} else {
- hash_name = nvme_auth_hmac_name(host->dhchap_hash_id);
- if (!hash_name) {
- pr_warn("Hash ID %d invalid\n", host->dhchap_hash_id);
- ret = -EINVAL;
- goto out_unlock;
- }
ctrl->shash_id = host->dhchap_hash_id;
}
@@ -178,7 +189,7 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
ctrl->host_key = nvme_auth_extract_key(host->dhchap_secret + 10,
host->dhchap_key_hash);
if (IS_ERR(ctrl->host_key)) {
- ret = PTR_ERR(ctrl->host_key);
+ ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE;
ctrl->host_key = NULL;
goto out_free_hash;
}
@@ -196,7 +207,7 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
ctrl->ctrl_key = nvme_auth_extract_key(host->dhchap_ctrl_secret + 10,
host->dhchap_ctrl_key_hash);
if (IS_ERR(ctrl->ctrl_key)) {
- ret = PTR_ERR(ctrl->ctrl_key);
+ ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE;
ctrl->ctrl_key = NULL;
goto out_free_hash;
}
@@ -285,9 +296,9 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
}
if (shash_len != crypto_shash_digestsize(shash_tfm)) {
- pr_debug("%s: hash len mismatch (len %d digest %d)\n",
- __func__, shash_len,
- crypto_shash_digestsize(shash_tfm));
+ pr_err("%s: hash len mismatch (len %d digest %d)\n",
+ __func__, shash_len,
+ crypto_shash_digestsize(shash_tfm));
ret = -EINVAL;
goto out_free_tfm;
}
@@ -316,7 +327,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
req->sq->dhchap_c1,
challenge, shash_len);
if (ret)
- goto out_free_response;
+ goto out_free_challenge;
}
pr_debug("ctrl %d qid %d host response seq %u transaction %d\n",
@@ -327,7 +338,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
GFP_KERNEL);
if (!shash) {
ret = -ENOMEM;
- goto out_free_response;
+ goto out_free_challenge;
}
shash->tfm = shash_tfm;
ret = crypto_shash_init(shash);
@@ -363,14 +374,15 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
goto out;
ret = crypto_shash_final(shash, response);
out:
+ kfree(shash);
+out_free_challenge:
if (challenge != req->sq->dhchap_c1)
kfree(challenge);
- kfree(shash);
out_free_response:
nvme_auth_free_key(transformed_key);
out_free_tfm:
crypto_free_shash(shash_tfm);
- return 0;
+ return ret;
}
int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
@@ -429,14 +441,14 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
req->sq->dhchap_c2,
challenge, shash_len);
if (ret)
- goto out_free_response;
+ goto out_free_challenge;
}
shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(shash_tfm),
GFP_KERNEL);
if (!shash) {
ret = -ENOMEM;
- goto out_free_response;
+ goto out_free_challenge;
}
shash->tfm = shash_tfm;
@@ -473,14 +485,15 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
goto out;
ret = crypto_shash_final(shash, response);
out:
+ kfree(shash);
+out_free_challenge:
if (challenge != req->sq->dhchap_c2)
kfree(challenge);
- kfree(shash);
out_free_response:
nvme_auth_free_key(transformed_key);
out_free_tfm:
crypto_free_shash(shash_tfm);
- return 0;
+ return ret;
}
int nvmet_auth_ctrl_exponential(struct nvmet_req *req,
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 2482a0db2504..e44ef69dffc2 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -37,6 +37,7 @@ static struct nvmet_type_name_map nvmet_transport[] = {
{ NVMF_TRTYPE_RDMA, "rdma" },
{ NVMF_TRTYPE_FC, "fc" },
{ NVMF_TRTYPE_TCP, "tcp" },
+ { NVMF_TRTYPE_PCI, "pci" },
{ NVMF_TRTYPE_LOOP, "loop" },
};
@@ -46,6 +47,7 @@ static const struct nvmet_type_name_map nvmet_addr_family[] = {
{ NVMF_ADDR_FAMILY_IP6, "ipv6" },
{ NVMF_ADDR_FAMILY_IB, "ib" },
{ NVMF_ADDR_FAMILY_FC, "fc" },
+ { NVMF_ADDR_FAMILY_PCI, "pci" },
{ NVMF_ADDR_FAMILY_LOOP, "loop" },
};
@@ -273,6 +275,32 @@ static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
CONFIGFS_ATTR(nvmet_, param_inline_data_size);
+static ssize_t nvmet_param_max_queue_size_show(struct config_item *item,
+ char *page)
+{
+ struct nvmet_port *port = to_nvmet_port(item);
+
+ return snprintf(page, PAGE_SIZE, "%d\n", port->max_queue_size);
+}
+
+static ssize_t nvmet_param_max_queue_size_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct nvmet_port *port = to_nvmet_port(item);
+ int ret;
+
+ if (nvmet_is_port_enabled(port, __func__))
+ return -EACCES;
+ ret = kstrtoint(page, 0, &port->max_queue_size);
+ if (ret) {
+ pr_err("Invalid value '%s' for max_queue_size\n", page);
+ return -EINVAL;
+ }
+ return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_max_queue_size);
+
#ifdef CONFIG_BLK_DEV_INTEGRITY
static ssize_t nvmet_param_pi_enable_show(struct config_item *item,
char *page)
@@ -384,7 +412,29 @@ static ssize_t nvmet_addr_tsas_show(struct config_item *item,
return sprintf(page, "%s\n", nvmet_addr_tsas_rdma[i].name);
}
}
- return sprintf(page, "reserved\n");
+ return sprintf(page, "\n");
+}
+
+static u8 nvmet_addr_tsas_rdma_store(const char *page)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_rdma); i++) {
+ if (sysfs_streq(page, nvmet_addr_tsas_rdma[i].name))
+ return nvmet_addr_tsas_rdma[i].type;
+ }
+ return NVMF_RDMA_QPTYPE_INVALID;
+}
+
+static u8 nvmet_addr_tsas_tcp_store(const char *page)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) {
+ if (sysfs_streq(page, nvmet_addr_tsas_tcp[i].name))
+ return nvmet_addr_tsas_tcp[i].type;
+ }
+ return NVMF_TCP_SECTYPE_INVALID;
}
static ssize_t nvmet_addr_tsas_store(struct config_item *item,
@@ -392,20 +442,19 @@ static ssize_t nvmet_addr_tsas_store(struct config_item *item,
{
struct nvmet_port *port = to_nvmet_port(item);
u8 treq = nvmet_port_disc_addr_treq_mask(port);
- u8 sectype;
- int i;
+ u8 sectype, qptype;
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;
+ if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA) {
+ qptype = nvmet_addr_tsas_rdma_store(page);
+ if (qptype == port->disc_addr.tsas.rdma.qptype)
+ return count;
+ } else if (port->disc_addr.trtype == NVMF_TRTYPE_TCP) {
+ sectype = nvmet_addr_tsas_tcp_store(page);
+ if (sectype != NVMF_TCP_SECTYPE_INVALID)
goto found;
- }
}
pr_err("Invalid value '%s' for tsas\n", page);
@@ -650,10 +699,18 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item,
if (kstrtobool(page, &enable))
return -EINVAL;
+ /*
+ * take a global nvmet_config_sem because the disable routine has a
+ * window where it releases the subsys-lock, giving a chance to
+ * a parallel enable to concurrently execute causing the disable to
+ * have a misaccounting of the ns percpu_ref.
+ */
+ down_write(&nvmet_config_sem);
if (enable)
ret = nvmet_ns_enable(ns);
else
nvmet_ns_disable(ns);
+ up_write(&nvmet_config_sem);
return ret ? ret : count;
}
@@ -714,6 +771,32 @@ static ssize_t nvmet_ns_revalidate_size_store(struct config_item *item,
CONFIGFS_ATTR_WO(nvmet_ns_, revalidate_size);
+static ssize_t nvmet_ns_resv_enable_show(struct config_item *item, char *page)
+{
+ return sysfs_emit(page, "%d\n", to_nvmet_ns(item)->pr.enable);
+}
+
+static ssize_t nvmet_ns_resv_enable_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct nvmet_ns *ns = to_nvmet_ns(item);
+ bool val;
+
+ if (kstrtobool(page, &val))
+ return -EINVAL;
+
+ mutex_lock(&ns->subsys->lock);
+ if (ns->enabled) {
+ pr_err("the ns:%d is already enabled.\n", ns->nsid);
+ mutex_unlock(&ns->subsys->lock);
+ return -EINVAL;
+ }
+ ns->pr.enable = val;
+ mutex_unlock(&ns->subsys->lock);
+ return count;
+}
+CONFIGFS_ATTR(nvmet_ns_, resv_enable);
+
static struct configfs_attribute *nvmet_ns_attrs[] = {
&nvmet_ns_attr_device_path,
&nvmet_ns_attr_device_nguid,
@@ -722,6 +805,7 @@ static struct configfs_attribute *nvmet_ns_attrs[] = {
&nvmet_ns_attr_enable,
&nvmet_ns_attr_buffered_io,
&nvmet_ns_attr_revalidate_size,
+ &nvmet_ns_attr_resv_enable,
#ifdef CONFIG_PCI_P2PDMA
&nvmet_ns_attr_p2pmem,
#endif
@@ -1318,6 +1402,49 @@ out_unlock:
}
CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_max);
+static ssize_t nvmet_subsys_attr_vendor_id_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "0x%x\n", to_subsys(item)->vendor_id);
+}
+
+static ssize_t nvmet_subsys_attr_vendor_id_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ u16 vid;
+
+ if (kstrtou16(page, 0, &vid))
+ return -EINVAL;
+
+ down_write(&nvmet_config_sem);
+ to_subsys(item)->vendor_id = vid;
+ up_write(&nvmet_config_sem);
+ return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_vendor_id);
+
+static ssize_t nvmet_subsys_attr_subsys_vendor_id_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "0x%x\n",
+ to_subsys(item)->subsys_vendor_id);
+}
+
+static ssize_t nvmet_subsys_attr_subsys_vendor_id_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ u16 ssvid;
+
+ if (kstrtou16(page, 0, &ssvid))
+ return -EINVAL;
+
+ down_write(&nvmet_config_sem);
+ to_subsys(item)->subsys_vendor_id = ssvid;
+ up_write(&nvmet_config_sem);
+ return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_subsys_vendor_id);
+
static ssize_t nvmet_subsys_attr_model_show(struct config_item *item,
char *page)
{
@@ -1546,6 +1673,8 @@ static struct configfs_attribute *nvmet_subsys_attrs[] = {
&nvmet_subsys_attr_attr_serial,
&nvmet_subsys_attr_attr_cntlid_min,
&nvmet_subsys_attr_attr_cntlid_max,
+ &nvmet_subsys_attr_attr_vendor_id,
+ &nvmet_subsys_attr_attr_subsys_vendor_id,
&nvmet_subsys_attr_attr_model,
&nvmet_subsys_attr_attr_qid_max,
&nvmet_subsys_attr_attr_ieee_oui,
@@ -1587,6 +1716,11 @@ static struct config_group *nvmet_subsys_make(struct config_group *group,
return ERR_PTR(-EINVAL);
}
+ if (sysfs_streq(name, nvmet_disc_subsys->subsysnqn)) {
+ pr_err("can't create subsystem using unique discovery NQN\n");
+ return ERR_PTR(-EINVAL);
+ }
+
subsys = nvmet_subsys_alloc(name, NVME_NQN_NVME);
if (IS_ERR(subsys))
return ERR_CAST(subsys);
@@ -1695,6 +1829,7 @@ static struct config_group *nvmet_referral_make(
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&port->entry);
+ port->disc_addr.trtype = NVMF_TRTYPE_MAX;
config_group_init_type_name(&port->group, name, &nvmet_referral_type);
return &port->group;
@@ -1859,6 +1994,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
&nvmet_attr_addr_trtype,
&nvmet_attr_addr_tsas,
&nvmet_attr_param_inline_data_size,
+ &nvmet_attr_param_max_queue_size,
#ifdef CONFIG_BLK_DEV_INTEGRITY
&nvmet_attr_param_pi_enable,
#endif
@@ -1917,7 +2053,9 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
INIT_LIST_HEAD(&port->subsystems);
INIT_LIST_HEAD(&port->referrals);
port->inline_data_size = -1; /* < 0 == let the transport choose */
+ port->max_queue_size = -1; /* < 0 == let the transport choose */
+ port->disc_addr.trtype = NVMF_TRTYPE_MAX;
port->disc_addr.portid = cpu_to_le16(portid);
port->disc_addr.adrfam = NVMF_ADDR_FAMILY_MAX;
port->disc_addr.treq = NVMF_TREQ_DISABLE_SQFLOW;
@@ -1962,11 +2100,17 @@ static struct config_group nvmet_ports_group;
static ssize_t nvmet_host_dhchap_key_show(struct config_item *item,
char *page)
{
- u8 *dhchap_secret = to_host(item)->dhchap_secret;
+ u8 *dhchap_secret;
+ ssize_t ret;
+ down_read(&nvmet_config_sem);
+ dhchap_secret = to_host(item)->dhchap_secret;
if (!dhchap_secret)
- return sprintf(page, "\n");
- return sprintf(page, "%s\n", dhchap_secret);
+ ret = sprintf(page, "\n");
+ else
+ ret = sprintf(page, "%s\n", dhchap_secret);
+ up_read(&nvmet_config_sem);
+ return ret;
}
static ssize_t nvmet_host_dhchap_key_store(struct config_item *item,
@@ -1990,10 +2134,16 @@ static ssize_t nvmet_host_dhchap_ctrl_key_show(struct config_item *item,
char *page)
{
u8 *dhchap_secret = to_host(item)->dhchap_ctrl_secret;
+ ssize_t ret;
+ down_read(&nvmet_config_sem);
+ dhchap_secret = to_host(item)->dhchap_ctrl_secret;
if (!dhchap_secret)
- return sprintf(page, "\n");
- return sprintf(page, "%s\n", dhchap_secret);
+ ret = sprintf(page, "\n");
+ else
+ ret = sprintf(page, "%s\n", dhchap_secret);
+ up_read(&nvmet_config_sem);
+ return ret;
}
static ssize_t nvmet_host_dhchap_ctrl_key_store(struct config_item *item,
@@ -2131,7 +2281,56 @@ static const struct config_item_type nvmet_hosts_type = {
static struct config_group nvmet_hosts_group;
+static ssize_t nvmet_root_discovery_nqn_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%s\n", nvmet_disc_subsys->subsysnqn);
+}
+
+static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct list_head *entry;
+ char *old_nqn, *new_nqn;
+ size_t len;
+
+ len = strcspn(page, "\n");
+ if (!len || len > NVMF_NQN_FIELD_LEN - 1)
+ return -EINVAL;
+
+ new_nqn = kstrndup(page, len, GFP_KERNEL);
+ if (!new_nqn)
+ return -ENOMEM;
+
+ down_write(&nvmet_config_sem);
+ list_for_each(entry, &nvmet_subsystems_group.cg_children) {
+ struct config_item *item =
+ container_of(entry, struct config_item, ci_entry);
+
+ if (!strncmp(config_item_name(item), page, len)) {
+ pr_err("duplicate NQN %s\n", config_item_name(item));
+ up_write(&nvmet_config_sem);
+ kfree(new_nqn);
+ return -EINVAL;
+ }
+ }
+ old_nqn = nvmet_disc_subsys->subsysnqn;
+ nvmet_disc_subsys->subsysnqn = new_nqn;
+ up_write(&nvmet_config_sem);
+
+ kfree(old_nqn);
+ return len;
+}
+
+CONFIGFS_ATTR(nvmet_root_, discovery_nqn);
+
+static struct configfs_attribute *nvmet_root_attrs[] = {
+ &nvmet_root_attr_discovery_nqn,
+ NULL,
+};
+
static const struct config_item_type nvmet_root_type = {
+ .ct_attrs = nvmet_root_attrs,
.ct_owner = THIS_MODULE,
};
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 8658e9c08534..2e741696f371 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -16,6 +16,7 @@
#include "trace.h"
#include "nvmet.h"
+#include "debugfs.h"
struct kmem_cache *nvmet_bvec_cache;
struct workqueue_struct *buffered_io_wq;
@@ -55,18 +56,18 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
return NVME_SC_SUCCESS;
case -ENOSPC:
req->error_loc = offsetof(struct nvme_rw_command, length);
- return NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
+ return NVME_SC_CAP_EXCEEDED | NVME_STATUS_DNR;
case -EREMOTEIO:
req->error_loc = offsetof(struct nvme_rw_command, slba);
- return NVME_SC_LBA_RANGE | NVME_SC_DNR;
+ return NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
case -EOPNOTSUPP:
req->error_loc = offsetof(struct nvme_common_command, opcode);
switch (req->cmd->common.opcode) {
case nvme_cmd_dsm:
case nvme_cmd_write_zeroes:
- return NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
+ return NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
default:
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
break;
case -ENODATA:
@@ -76,7 +77,7 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
fallthrough;
default:
req->error_loc = offsetof(struct nvme_common_command, opcode);
- return NVME_SC_INTERNAL | NVME_SC_DNR;
+ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
}
}
@@ -86,7 +87,7 @@ u16 nvmet_report_invalid_opcode(struct nvmet_req *req)
req->sq->qid);
req->error_loc = offsetof(struct nvme_common_command, opcode);
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
@@ -97,7 +98,7 @@ u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
{
if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
req->error_loc = offsetof(struct nvme_common_command, dptr);
- return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+ return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR;
}
return 0;
}
@@ -106,7 +107,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
{
if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
req->error_loc = offsetof(struct nvme_common_command, dptr);
- return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+ return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR;
}
return 0;
}
@@ -115,7 +116,7 @@ u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
{
if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len) {
req->error_loc = offsetof(struct nvme_common_command, dptr);
- return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+ return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR;
}
return 0;
}
@@ -126,7 +127,7 @@ static u32 nvmet_max_nsid(struct nvmet_subsys *subsys)
unsigned long idx;
u32 nsid = 0;
- xa_for_each(&subsys->namespaces, idx, cur)
+ nvmet_for_each_enabled_ns(&subsys->namespaces, idx, cur)
nsid = cur->nsid;
return nsid;
@@ -145,7 +146,7 @@ static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl)
while (ctrl->nr_async_event_cmds) {
req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
mutex_unlock(&ctrl->lock);
- nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
+ nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_STATUS_DNR);
mutex_lock(&ctrl->lock);
}
mutex_unlock(&ctrl->lock);
@@ -358,6 +359,18 @@ int nvmet_enable_port(struct nvmet_port *port)
if (port->inline_data_size < 0)
port->inline_data_size = 0;
+ /*
+ * If the transport didn't set the max_queue_size properly, then clamp
+ * it to the target limits. Also set default values in case the
+ * transport didn't set it at all.
+ */
+ if (port->max_queue_size < 0)
+ port->max_queue_size = NVMET_MAX_QUEUE_SIZE;
+ else
+ port->max_queue_size = clamp_t(int, port->max_queue_size,
+ NVMET_MIN_QUEUE_SIZE,
+ NVMET_MAX_QUEUE_SIZE);
+
port->enabled = true;
port->tr_ops = ops;
return 0;
@@ -425,11 +438,17 @@ void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
u16 nvmet_req_find_ns(struct nvmet_req *req)
{
u32 nsid = le32_to_cpu(req->cmd->common.nsid);
+ struct nvmet_subsys *subsys = nvmet_req_subsys(req);
- req->ns = xa_load(&nvmet_req_subsys(req)->namespaces, nsid);
- if (unlikely(!req->ns)) {
+ req->ns = xa_load(&subsys->namespaces, nsid);
+ if (unlikely(!req->ns || !req->ns->enabled)) {
req->error_loc = offsetof(struct nvme_common_command, nsid);
- return NVME_SC_INVALID_NS | NVME_SC_DNR;
+ if (!req->ns) /* ns doesn't exist! */
+ return NVME_SC_INVALID_NS | NVME_STATUS_DNR;
+
+ /* ns exists but it's disabled */
+ req->ns = NULL;
+ return NVME_SC_INTERNAL_PATH_ERROR;
}
percpu_ref_get(&req->ns->ref);
@@ -567,8 +586,6 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
goto out_unlock;
ret = -EMFILE;
- if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
- goto out_unlock;
ret = nvmet_bdev_ns_enable(ns);
if (ret == -ENOTBLK)
@@ -583,30 +600,25 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
nvmet_p2pmem_ns_add_p2p(ctrl, ns);
- ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace,
- 0, GFP_KERNEL);
- if (ret)
- goto out_dev_put;
-
- if (ns->nsid > subsys->max_nsid)
- subsys->max_nsid = ns->nsid;
-
- ret = xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL);
- if (ret)
- goto out_restore_subsys_maxnsid;
+ if (ns->pr.enable) {
+ ret = nvmet_pr_init_ns(ns);
+ if (ret)
+ goto out_dev_put;
+ }
- subsys->nr_namespaces++;
+ if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL))
+ goto out_pr_exit;
nvmet_ns_changed(subsys, ns->nsid);
ns->enabled = true;
+ xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED);
ret = 0;
out_unlock:
mutex_unlock(&subsys->lock);
return ret;
-
-out_restore_subsys_maxnsid:
- subsys->max_nsid = nvmet_max_nsid(subsys);
- percpu_ref_exit(&ns->ref);
+out_pr_exit:
+ if (ns->pr.enable)
+ nvmet_pr_exit_ns(ns);
out_dev_put:
list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
@@ -625,9 +637,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
goto out_unlock;
ns->enabled = false;
- xa_erase(&ns->subsys->namespaces, ns->nsid);
- if (ns->nsid == subsys->max_nsid)
- subsys->max_nsid = nvmet_max_nsid(subsys);
+ xa_clear_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED);
list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
@@ -647,9 +657,10 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
wait_for_completion(&ns->disable_done);
percpu_ref_exit(&ns->ref);
- mutex_lock(&subsys->lock);
+ if (ns->pr.enable)
+ nvmet_pr_exit_ns(ns);
- subsys->nr_namespaces--;
+ mutex_lock(&subsys->lock);
nvmet_ns_changed(subsys, ns->nsid);
nvmet_ns_dev_disable(ns);
out_unlock:
@@ -658,8 +669,19 @@ out_unlock:
void nvmet_ns_free(struct nvmet_ns *ns)
{
+ struct nvmet_subsys *subsys = ns->subsys;
+
nvmet_ns_disable(ns);
+ mutex_lock(&subsys->lock);
+
+ xa_erase(&subsys->namespaces, ns->nsid);
+ if (ns->nsid == subsys->max_nsid)
+ subsys->max_nsid = nvmet_max_nsid(subsys);
+
+ subsys->nr_namespaces--;
+ mutex_unlock(&subsys->lock);
+
down_write(&nvmet_ana_sem);
nvmet_ana_group_enabled[ns->anagrpid]--;
up_write(&nvmet_ana_sem);
@@ -672,15 +694,30 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
{
struct nvmet_ns *ns;
+ mutex_lock(&subsys->lock);
+
+ if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
+ goto out_unlock;
+
ns = kzalloc(sizeof(*ns), GFP_KERNEL);
if (!ns)
- return NULL;
+ goto out_unlock;
init_completion(&ns->disable_done);
ns->nsid = nsid;
ns->subsys = subsys;
+ if (ns->nsid > subsys->max_nsid)
+ subsys->max_nsid = nsid;
+
+ if (xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL))
+ goto out_exit;
+
+ subsys->nr_namespaces++;
+
+ mutex_unlock(&subsys->lock);
+
down_write(&nvmet_ana_sem);
ns->anagrpid = NVMET_DEFAULT_ANA_GRPID;
nvmet_ana_group_enabled[ns->anagrpid]++;
@@ -691,6 +728,12 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
ns->csi = NVME_CSI_NVM;
return ns;
+out_exit:
+ subsys->max_nsid = nvmet_max_nsid(subsys);
+ kfree(ns);
+out_unlock:
+ mutex_unlock(&subsys->lock);
+ return NULL;
}
static void nvmet_update_sq_head(struct nvmet_req *req)
@@ -738,6 +781,7 @@ static void nvmet_set_error(struct nvmet_req *req, u16 status)
static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
{
struct nvmet_ns *ns = req->ns;
+ struct nvmet_pr_per_ctrl_ref *pc_ref = req->pc_ref;
if (!req->sq->sqhd_disabled)
nvmet_update_sq_head(req);
@@ -750,6 +794,9 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
trace_nvmet_req_complete(req);
req->ops->queue_response(req);
+
+ if (pc_ref)
+ nvmet_pr_put_ns_pc_ref(pc_ref);
if (ns)
nvmet_put_namespace(ns);
}
@@ -787,6 +834,89 @@ static void nvmet_confirm_sq(struct percpu_ref *ref)
complete(&sq->confirm_done);
}
+u16 nvmet_check_cqid(struct nvmet_ctrl *ctrl, u16 cqid)
+{
+ if (!ctrl->sqs)
+ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
+
+ if (cqid > ctrl->subsys->max_qid)
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ /*
+ * Note: For PCI controllers, the NVMe specifications allows multiple
+ * SQs to share a single CQ. However, we do not support this yet, so
+ * check that there is no SQ defined for a CQ. If one exist, then the
+ * CQ ID is invalid for creation as well as when the CQ is being
+ * deleted (as that would mean that the SQ was not deleted before the
+ * CQ).
+ */
+ if (ctrl->sqs[cqid])
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ return NVME_SC_SUCCESS;
+}
+
+u16 nvmet_cq_create(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq,
+ u16 qid, u16 size)
+{
+ u16 status;
+
+ status = nvmet_check_cqid(ctrl, qid);
+ if (status != NVME_SC_SUCCESS)
+ return status;
+
+ nvmet_cq_setup(ctrl, cq, qid, size);
+
+ return NVME_SC_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(nvmet_cq_create);
+
+u16 nvmet_check_sqid(struct nvmet_ctrl *ctrl, u16 sqid,
+ bool create)
+{
+ if (!ctrl->sqs)
+ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
+
+ if (sqid > ctrl->subsys->max_qid)
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ if ((create && ctrl->sqs[sqid]) ||
+ (!create && !ctrl->sqs[sqid]))
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ return NVME_SC_SUCCESS;
+}
+
+u16 nvmet_sq_create(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
+ u16 sqid, u16 size)
+{
+ u16 status;
+ int ret;
+
+ if (!kref_get_unless_zero(&ctrl->ref))
+ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
+
+ status = nvmet_check_sqid(ctrl, sqid, true);
+ if (status != NVME_SC_SUCCESS)
+ return status;
+
+ ret = nvmet_sq_init(sq);
+ if (ret) {
+ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ goto ctrl_put;
+ }
+
+ nvmet_sq_setup(ctrl, sq, sqid, size);
+ sq->ctrl = ctrl;
+
+ return NVME_SC_SUCCESS;
+
+ctrl_put:
+ nvmet_ctrl_put(ctrl);
+ return status;
+}
+EXPORT_SYMBOL_GPL(nvmet_sq_create);
+
void nvmet_sq_destroy(struct nvmet_sq *sq)
{
struct nvmet_ctrl *ctrl = sq->ctrl;
@@ -803,6 +933,15 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
percpu_ref_exit(&sq->ref);
nvmet_auth_sq_free(sq);
+ /*
+ * we must reference the ctrl again after waiting for inflight IO
+ * to complete. Because admin connect may have sneaked in after we
+ * store sq->ctrl locally, but before we killed the percpu_ref. the
+ * admin connect allocates and assigns sq->ctrl, which now needs a
+ * final ref put, as this ctrl is going away.
+ */
+ ctrl = sq->ctrl;
+
if (ctrl) {
/*
* The teardown flow may take some time, and the host may not
@@ -871,6 +1010,33 @@ static inline u16 nvmet_io_cmd_check_access(struct nvmet_req *req)
return 0;
}
+static u32 nvmet_io_cmd_transfer_len(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+ u32 metadata_len = 0;
+
+ if (nvme_is_fabrics(cmd))
+ return nvmet_fabrics_io_cmd_data_len(req);
+
+ if (!req->ns)
+ return 0;
+
+ switch (req->cmd->common.opcode) {
+ case nvme_cmd_read:
+ case nvme_cmd_write:
+ case nvme_cmd_zone_append:
+ if (req->sq->ctrl->pi_support && nvmet_ns_has_pi(req->ns))
+ metadata_len = nvmet_rw_metadata_len(req);
+ return nvmet_rw_data_len(req) + metadata_len;
+ case nvme_cmd_dsm:
+ return nvmet_dsm_len(req);
+ case nvme_cmd_zone_mgmt_recv:
+ return (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2;
+ default:
+ return 0;
+ }
+}
+
static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
@@ -880,7 +1046,7 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
return nvmet_parse_fabrics_io_cmd(req);
if (unlikely(!nvmet_check_auth_status(req)))
- return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR;
+ return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR;
ret = nvmet_check_ctrl_status(req);
if (unlikely(ret))
@@ -904,18 +1070,39 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
return ret;
}
+ if (req->ns->pr.enable) {
+ ret = nvmet_parse_pr_cmd(req);
+ if (!ret)
+ return ret;
+ }
+
switch (req->ns->csi) {
case NVME_CSI_NVM:
if (req->ns->file)
- return nvmet_file_parse_io_cmd(req);
- return nvmet_bdev_parse_io_cmd(req);
+ ret = nvmet_file_parse_io_cmd(req);
+ else
+ ret = nvmet_bdev_parse_io_cmd(req);
+ break;
case NVME_CSI_ZNS:
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
- return nvmet_bdev_zns_parse_io_cmd(req);
- return NVME_SC_INVALID_IO_CMD_SET;
+ ret = nvmet_bdev_zns_parse_io_cmd(req);
+ else
+ ret = NVME_SC_INVALID_IO_CMD_SET;
+ break;
default:
- return NVME_SC_INVALID_IO_CMD_SET;
+ ret = NVME_SC_INVALID_IO_CMD_SET;
+ }
+ if (ret)
+ return ret;
+
+ if (req->ns->pr.enable) {
+ ret = nvmet_pr_check_cmd_access(req);
+ if (ret)
+ return ret;
+
+ ret = nvmet_pr_get_ns_pc_ref(req);
}
+ return ret;
}
bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
@@ -933,28 +1120,33 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
req->metadata_sg_cnt = 0;
req->transfer_len = 0;
req->metadata_len = 0;
+ req->cqe->result.u64 = 0;
req->cqe->status = 0;
req->cqe->sq_head = 0;
req->ns = NULL;
req->error_loc = NVMET_NO_ERROR_LOC;
req->error_slba = 0;
+ req->pc_ref = NULL;
/* no support for fused commands yet */
if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
req->error_loc = offsetof(struct nvme_common_command, flags);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto fail;
}
/*
* For fabrics, PSDT field shall describe metadata pointer (MPTR) that
* contains an address of a single contiguous physical buffer that is
- * byte aligned.
+ * byte aligned. For PCI controllers, this is optional so not enforced.
*/
if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) {
- req->error_loc = offsetof(struct nvme_common_command, flags);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
- goto fail;
+ if (!req->sq->ctrl || !nvmet_is_pci_ctrl(req->sq->ctrl)) {
+ req->error_loc =
+ offsetof(struct nvme_common_command, flags);
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto fail;
+ }
}
if (unlikely(!req->sq->ctrl))
@@ -971,7 +1163,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
trace_nvmet_req_init(req, req->cmd);
if (unlikely(!percpu_ref_tryget_live(&sq->ref))) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto fail;
}
@@ -989,16 +1181,34 @@ EXPORT_SYMBOL_GPL(nvmet_req_init);
void nvmet_req_uninit(struct nvmet_req *req)
{
percpu_ref_put(&req->sq->ref);
+ if (req->pc_ref)
+ nvmet_pr_put_ns_pc_ref(req->pc_ref);
if (req->ns)
nvmet_put_namespace(req->ns);
}
EXPORT_SYMBOL_GPL(nvmet_req_uninit);
+size_t nvmet_req_transfer_len(struct nvmet_req *req)
+{
+ if (likely(req->sq->qid != 0))
+ return nvmet_io_cmd_transfer_len(req);
+ if (unlikely(!req->sq->ctrl))
+ return nvmet_connect_cmd_data_len(req);
+ return nvmet_admin_cmd_data_len(req);
+}
+EXPORT_SYMBOL_GPL(nvmet_req_transfer_len);
+
bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len)
{
if (unlikely(len != req->transfer_len)) {
+ u16 status;
+
req->error_loc = offsetof(struct nvme_common_command, dptr);
- nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
+ if (req->cmd->common.flags & NVME_CMD_SGL_ALL)
+ status = NVME_SC_SGL_INVALID_DATA;
+ else
+ status = NVME_SC_INVALID_FIELD;
+ nvmet_req_complete(req, status | NVME_STATUS_DNR);
return false;
}
@@ -1009,8 +1219,14 @@ EXPORT_SYMBOL_GPL(nvmet_check_transfer_len);
bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len)
{
if (unlikely(data_len > req->transfer_len)) {
+ u16 status;
+
req->error_loc = offsetof(struct nvme_common_command, dptr);
- nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
+ if (req->cmd->common.flags & NVME_CMD_SGL_ALL)
+ status = NVME_SC_SGL_INVALID_DATA;
+ else
+ status = NVME_SC_INVALID_FIELD;
+ nvmet_req_complete(req, status | NVME_STATUS_DNR);
return false;
}
@@ -1101,41 +1317,6 @@ void nvmet_req_free_sgls(struct nvmet_req *req)
}
EXPORT_SYMBOL_GPL(nvmet_req_free_sgls);
-static inline bool nvmet_cc_en(u32 cc)
-{
- return (cc >> NVME_CC_EN_SHIFT) & 0x1;
-}
-
-static inline u8 nvmet_cc_css(u32 cc)
-{
- return (cc >> NVME_CC_CSS_SHIFT) & 0x7;
-}
-
-static inline u8 nvmet_cc_mps(u32 cc)
-{
- return (cc >> NVME_CC_MPS_SHIFT) & 0xf;
-}
-
-static inline u8 nvmet_cc_ams(u32 cc)
-{
- return (cc >> NVME_CC_AMS_SHIFT) & 0x7;
-}
-
-static inline u8 nvmet_cc_shn(u32 cc)
-{
- return (cc >> NVME_CC_SHN_SHIFT) & 0x3;
-}
-
-static inline u8 nvmet_cc_iosqes(u32 cc)
-{
- return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf;
-}
-
-static inline u8 nvmet_cc_iocqes(u32 cc)
-{
- return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf;
-}
-
static inline bool nvmet_css_supported(u8 cc_css)
{
switch (cc_css << NVME_CC_CSS_SHIFT) {
@@ -1212,6 +1393,7 @@ void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new)
ctrl->csts &= ~NVME_CSTS_SHST_CMPLT;
mutex_unlock(&ctrl->lock);
}
+EXPORT_SYMBOL_GPL(nvmet_update_cc);
static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
{
@@ -1223,9 +1405,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
ctrl->cap |= (15ULL << 24);
/* maximum queue entries supported: */
if (ctrl->ops->get_max_queue_size)
- ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1;
+ ctrl->cap |= min_t(u16, ctrl->ops->get_max_queue_size(ctrl),
+ ctrl->port->max_queue_size) - 1;
else
- ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+ ctrl->cap |= ctrl->port->max_queue_size - 1;
if (nvmet_is_passthru_subsys(ctrl->subsys))
nvmet_passthrough_override_cap(ctrl);
@@ -1278,18 +1461,18 @@ u16 nvmet_check_ctrl_status(struct nvmet_req *req)
if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
pr_err("got cmd %d while CC.EN == 0 on qid = %d\n",
req->cmd->common.opcode, req->sq->qid);
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
}
if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
pr_err("got cmd %d while CSTS.RDY == 0 on qid = %d\n",
req->cmd->common.opcode, req->sq->qid);
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
}
if (unlikely(!nvmet_check_auth_status(req))) {
pr_warn("qid %d not authenticated\n", req->sq->qid);
- return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR;
+ return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR;
}
return 0;
}
@@ -1318,17 +1501,17 @@ bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn)
* Note: ctrl->subsys->lock should be held when calling this function
*/
static void nvmet_setup_p2p_ns_map(struct nvmet_ctrl *ctrl,
- struct nvmet_req *req)
+ struct device *p2p_client)
{
struct nvmet_ns *ns;
unsigned long idx;
- if (!req->p2p_client)
+ if (!p2p_client)
return;
- ctrl->p2p_client = get_device(req->p2p_client);
+ ctrl->p2p_client = get_device(p2p_client);
- xa_for_each(&ctrl->subsys->namespaces, idx, ns)
+ nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns)
nvmet_p2pmem_ns_add_p2p(ctrl, ns);
}
@@ -1355,44 +1538,44 @@ static void nvmet_fatal_error_handler(struct work_struct *work)
ctrl->ops->delete_ctrl(ctrl);
}
-u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
- struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp)
+struct nvmet_ctrl *nvmet_alloc_ctrl(struct nvmet_alloc_ctrl_args *args)
{
struct nvmet_subsys *subsys;
struct nvmet_ctrl *ctrl;
+ u32 kato = args->kato;
+ u8 dhchap_status;
int ret;
- u16 status;
- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
- subsys = nvmet_find_get_subsys(req->port, subsysnqn);
+ args->status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ subsys = nvmet_find_get_subsys(args->port, args->subsysnqn);
if (!subsys) {
pr_warn("connect request for invalid subsystem %s!\n",
- subsysnqn);
- req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn);
- req->error_loc = offsetof(struct nvme_common_command, dptr);
- goto out;
+ args->subsysnqn);
+ args->result = IPO_IATTR_CONNECT_DATA(subsysnqn);
+ args->error_loc = offsetof(struct nvme_common_command, dptr);
+ return NULL;
}
down_read(&nvmet_config_sem);
- if (!nvmet_host_allowed(subsys, hostnqn)) {
+ if (!nvmet_host_allowed(subsys, args->hostnqn)) {
pr_info("connect by host %s for subsystem %s not allowed\n",
- hostnqn, subsysnqn);
- req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn);
+ args->hostnqn, args->subsysnqn);
+ args->result = IPO_IATTR_CONNECT_DATA(hostnqn);
up_read(&nvmet_config_sem);
- status = NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR;
- req->error_loc = offsetof(struct nvme_common_command, dptr);
+ args->status = NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR;
+ args->error_loc = offsetof(struct nvme_common_command, dptr);
goto out_put_subsystem;
}
up_read(&nvmet_config_sem);
- status = NVME_SC_INTERNAL;
+ args->status = NVME_SC_INTERNAL;
ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
if (!ctrl)
goto out_put_subsystem;
mutex_init(&ctrl->lock);
- ctrl->port = req->port;
- ctrl->ops = req->ops;
+ ctrl->port = args->port;
+ ctrl->ops = args->ops;
#ifdef CONFIG_NVME_TARGET_PASSTHRU
/* By default, set loop targets to clear IDS by default */
@@ -1406,11 +1589,12 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler);
INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer);
- memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
- memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);
+ memcpy(ctrl->subsysnqn, args->subsysnqn, NVMF_NQN_SIZE);
+ memcpy(ctrl->hostnqn, args->hostnqn, NVMF_NQN_SIZE);
kref_init(&ctrl->ref);
ctrl->subsys = subsys;
+ ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
nvmet_init_cap(ctrl);
WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
@@ -1429,11 +1613,13 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
subsys->cntlid_min, subsys->cntlid_max,
GFP_KERNEL);
if (ret < 0) {
- status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
+ args->status = NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR;
goto out_free_sqs;
}
ctrl->cntlid = ret;
+ uuid_copy(&ctrl->hostid, args->hostid);
+
/*
* Discovery controllers may use some arbitrary high value
* in order to cleanup stale discovery sessions
@@ -1450,13 +1636,44 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
nvmet_start_keep_alive_timer(ctrl);
mutex_lock(&subsys->lock);
+ ret = nvmet_ctrl_init_pr(ctrl);
+ if (ret)
+ goto init_pr_fail;
list_add_tail(&ctrl->subsys_entry, &subsys->ctrls);
- nvmet_setup_p2p_ns_map(ctrl, req);
+ nvmet_setup_p2p_ns_map(ctrl, args->p2p_client);
+ nvmet_debugfs_ctrl_setup(ctrl);
mutex_unlock(&subsys->lock);
- *ctrlp = ctrl;
- return 0;
+ if (args->hostid)
+ uuid_copy(&ctrl->hostid, args->hostid);
+
+ dhchap_status = nvmet_setup_auth(ctrl);
+ if (dhchap_status) {
+ pr_err("Failed to setup authentication, dhchap status %u\n",
+ dhchap_status);
+ nvmet_ctrl_put(ctrl);
+ if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED)
+ args->status =
+ NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR;
+ else
+ args->status = NVME_SC_INTERNAL;
+ return NULL;
+ }
+
+ args->status = NVME_SC_SUCCESS;
+
+ pr_info("Created %s controller %d for subsystem %s for NQN %s%s%s.\n",
+ nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm",
+ ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn,
+ ctrl->pi_support ? " T10-PI is enabled" : "",
+ nvmet_has_auth(ctrl) ? " with DH-HMAC-CHAP" : "");
+
+ return ctrl;
+init_pr_fail:
+ mutex_unlock(&subsys->lock);
+ nvmet_stop_keep_alive_timer(ctrl);
+ ida_free(&cntlid_ida, ctrl->cntlid);
out_free_sqs:
kfree(ctrl->sqs);
out_free_changed_ns_list:
@@ -1465,9 +1682,9 @@ out_free_ctrl:
kfree(ctrl);
out_put_subsystem:
nvmet_subsys_put(subsys);
-out:
- return status;
+ return NULL;
}
+EXPORT_SYMBOL_GPL(nvmet_alloc_ctrl);
static void nvmet_ctrl_free(struct kref *ref)
{
@@ -1475,6 +1692,7 @@ static void nvmet_ctrl_free(struct kref *ref)
struct nvmet_subsys *subsys = ctrl->subsys;
mutex_lock(&subsys->lock);
+ nvmet_ctrl_destroy_pr(ctrl);
nvmet_release_p2p_ns_map(ctrl);
list_del(&ctrl->subsys_entry);
mutex_unlock(&subsys->lock);
@@ -1486,6 +1704,8 @@ static void nvmet_ctrl_free(struct kref *ref)
nvmet_destroy_auth(ctrl);
+ nvmet_debugfs_ctrl_free(ctrl);
+
ida_free(&cntlid_ida, ctrl->cntlid);
nvmet_async_events_free(ctrl);
@@ -1500,6 +1720,7 @@ void nvmet_ctrl_put(struct nvmet_ctrl *ctrl)
{
kref_put(&ctrl->ref, nvmet_ctrl_free);
}
+EXPORT_SYMBOL_GPL(nvmet_ctrl_put);
void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl)
{
@@ -1512,6 +1733,14 @@ void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvmet_ctrl_fatal_error);
+ssize_t nvmet_ctrl_host_traddr(struct nvmet_ctrl *ctrl,
+ char *traddr, size_t traddr_len)
+{
+ if (!ctrl->ops->host_traddr)
+ return -EOPNOTSUPP;
+ return ctrl->ops->host_traddr(ctrl, traddr, traddr_len);
+}
+
static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
const char *subsysnqn)
{
@@ -1527,6 +1756,13 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
}
down_read(&nvmet_config_sem);
+ if (!strncmp(nvmet_disc_subsys->subsysnqn, subsysnqn,
+ NVMF_NQN_SIZE)) {
+ if (kref_get_unless_zero(&nvmet_disc_subsys->ref)) {
+ up_read(&nvmet_config_sem);
+ return nvmet_disc_subsys;
+ }
+ }
list_for_each_entry(p, &port->subsystems, entry) {
if (!strncmp(p->subsys->subsysnqn, subsysnqn,
NVMF_NQN_SIZE)) {
@@ -1599,8 +1835,14 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
INIT_LIST_HEAD(&subsys->ctrls);
INIT_LIST_HEAD(&subsys->hosts);
+ ret = nvmet_debugfs_subsys_setup(subsys);
+ if (ret)
+ goto free_subsysnqn;
+
return subsys;
+free_subsysnqn:
+ kfree(subsys->subsysnqn);
free_fr:
kfree(subsys->firmware_rev);
free_mn:
@@ -1617,6 +1859,8 @@ static void nvmet_subsys_free(struct kref *ref)
WARN_ON_ONCE(!xa_empty(&subsys->namespaces));
+ nvmet_debugfs_subsys_free(subsys);
+
xa_destroy(&subsys->namespaces);
nvmet_passthru_subsys_free(subsys);
@@ -1662,7 +1906,8 @@ static int __init nvmet_init(void)
if (!buffered_io_wq)
goto out_free_zbd_work_queue;
- nvmet_wq = alloc_workqueue("nvmet-wq", WQ_MEM_RECLAIM, 0);
+ nvmet_wq = alloc_workqueue("nvmet-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0);
if (!nvmet_wq)
goto out_free_buffered_work_queue;
@@ -1670,11 +1915,18 @@ static int __init nvmet_init(void)
if (error)
goto out_free_nvmet_work_queue;
- error = nvmet_init_configfs();
+ error = nvmet_init_debugfs();
if (error)
goto out_exit_discovery;
+
+ error = nvmet_init_configfs();
+ if (error)
+ goto out_exit_debugfs;
+
return 0;
+out_exit_debugfs:
+ nvmet_exit_debugfs();
out_exit_discovery:
nvmet_exit_discovery();
out_free_nvmet_work_queue:
@@ -1691,6 +1943,7 @@ out_destroy_bvec_cache:
static void __exit nvmet_exit(void)
{
nvmet_exit_configfs();
+ nvmet_exit_debugfs();
nvmet_exit_discovery();
ida_destroy(&cntlid_ida);
destroy_workqueue(nvmet_wq);
diff --git a/drivers/nvme/target/debugfs.c b/drivers/nvme/target/debugfs.c
new file mode 100644
index 000000000000..220c7391fc19
--- /dev/null
+++ b/drivers/nvme/target/debugfs.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DebugFS interface for the NVMe target.
+ * Copyright (c) 2022-2024 Shadow
+ * Copyright (c) 2024 SUSE LLC
+ */
+
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+#include "nvmet.h"
+#include "debugfs.h"
+
+static struct dentry *nvmet_debugfs;
+
+#define NVMET_DEBUGFS_ATTR(field) \
+ static int field##_open(struct inode *inode, struct file *file) \
+ { return single_open(file, field##_show, inode->i_private); } \
+ \
+ static const struct file_operations field##_fops = { \
+ .open = field##_open, \
+ .read = seq_read, \
+ .release = single_release, \
+ }
+
+#define NVMET_DEBUGFS_RW_ATTR(field) \
+ static int field##_open(struct inode *inode, struct file *file) \
+ { return single_open(file, field##_show, inode->i_private); } \
+ \
+ static const struct file_operations field##_fops = { \
+ .open = field##_open, \
+ .read = seq_read, \
+ .write = field##_write, \
+ .release = single_release, \
+ }
+
+static int nvmet_ctrl_hostnqn_show(struct seq_file *m, void *p)
+{
+ struct nvmet_ctrl *ctrl = m->private;
+
+ seq_puts(m, ctrl->hostnqn);
+ return 0;
+}
+NVMET_DEBUGFS_ATTR(nvmet_ctrl_hostnqn);
+
+static int nvmet_ctrl_kato_show(struct seq_file *m, void *p)
+{
+ struct nvmet_ctrl *ctrl = m->private;
+
+ seq_printf(m, "%d\n", ctrl->kato);
+ return 0;
+}
+NVMET_DEBUGFS_ATTR(nvmet_ctrl_kato);
+
+static int nvmet_ctrl_port_show(struct seq_file *m, void *p)
+{
+ struct nvmet_ctrl *ctrl = m->private;
+
+ seq_printf(m, "%d\n", le16_to_cpu(ctrl->port->disc_addr.portid));
+ return 0;
+}
+NVMET_DEBUGFS_ATTR(nvmet_ctrl_port);
+
+static const char *const csts_state_names[] = {
+ [NVME_CSTS_RDY] = "ready",
+ [NVME_CSTS_CFS] = "fatal",
+ [NVME_CSTS_NSSRO] = "reset",
+ [NVME_CSTS_SHST_OCCUR] = "shutdown",
+ [NVME_CSTS_SHST_CMPLT] = "completed",
+ [NVME_CSTS_PP] = "paused",
+};
+
+static int nvmet_ctrl_state_show(struct seq_file *m, void *p)
+{
+ struct nvmet_ctrl *ctrl = m->private;
+ bool sep = false;
+ int i;
+
+ for (i = 0; i < 7; i++) {
+ int state = BIT(i);
+
+ if (!(ctrl->csts & state))
+ continue;
+ if (sep)
+ seq_puts(m, "|");
+ sep = true;
+ if (csts_state_names[state])
+ seq_puts(m, csts_state_names[state]);
+ else
+ seq_printf(m, "%d", state);
+ }
+ if (sep)
+ seq_printf(m, "\n");
+ return 0;
+}
+
+static ssize_t nvmet_ctrl_state_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct seq_file *m = file->private_data;
+ struct nvmet_ctrl *ctrl = m->private;
+ char reset[16];
+
+ if (count >= sizeof(reset))
+ return -EINVAL;
+ if (copy_from_user(reset, buf, count))
+ return -EFAULT;
+ if (!memcmp(reset, "fatal", 5))
+ nvmet_ctrl_fatal_error(ctrl);
+ else
+ return -EINVAL;
+ return count;
+}
+NVMET_DEBUGFS_RW_ATTR(nvmet_ctrl_state);
+
+static int nvmet_ctrl_host_traddr_show(struct seq_file *m, void *p)
+{
+ struct nvmet_ctrl *ctrl = m->private;
+ ssize_t size;
+ char buf[NVMF_TRADDR_SIZE + 1];
+
+ size = nvmet_ctrl_host_traddr(ctrl, buf, NVMF_TRADDR_SIZE);
+ if (size < 0) {
+ buf[0] = '\0';
+ size = 0;
+ }
+ buf[size] = '\0';
+ seq_printf(m, "%s\n", buf);
+ return 0;
+}
+NVMET_DEBUGFS_ATTR(nvmet_ctrl_host_traddr);
+
+int nvmet_debugfs_ctrl_setup(struct nvmet_ctrl *ctrl)
+{
+ char name[32];
+ struct dentry *parent = ctrl->subsys->debugfs_dir;
+ int ret;
+
+ if (!parent)
+ return -ENODEV;
+ snprintf(name, sizeof(name), "ctrl%d", ctrl->cntlid);
+ ctrl->debugfs_dir = debugfs_create_dir(name, parent);
+ if (IS_ERR(ctrl->debugfs_dir)) {
+ ret = PTR_ERR(ctrl->debugfs_dir);
+ ctrl->debugfs_dir = NULL;
+ return ret;
+ }
+ debugfs_create_file("port", S_IRUSR, ctrl->debugfs_dir, ctrl,
+ &nvmet_ctrl_port_fops);
+ debugfs_create_file("hostnqn", S_IRUSR, ctrl->debugfs_dir, ctrl,
+ &nvmet_ctrl_hostnqn_fops);
+ debugfs_create_file("kato", S_IRUSR, ctrl->debugfs_dir, ctrl,
+ &nvmet_ctrl_kato_fops);
+ debugfs_create_file("state", S_IRUSR | S_IWUSR, ctrl->debugfs_dir, ctrl,
+ &nvmet_ctrl_state_fops);
+ debugfs_create_file("host_traddr", S_IRUSR, ctrl->debugfs_dir, ctrl,
+ &nvmet_ctrl_host_traddr_fops);
+ return 0;
+}
+
+void nvmet_debugfs_ctrl_free(struct nvmet_ctrl *ctrl)
+{
+ debugfs_remove_recursive(ctrl->debugfs_dir);
+}
+
+int nvmet_debugfs_subsys_setup(struct nvmet_subsys *subsys)
+{
+ int ret = 0;
+
+ subsys->debugfs_dir = debugfs_create_dir(subsys->subsysnqn,
+ nvmet_debugfs);
+ if (IS_ERR(subsys->debugfs_dir)) {
+ ret = PTR_ERR(subsys->debugfs_dir);
+ subsys->debugfs_dir = NULL;
+ }
+ return ret;
+}
+
+void nvmet_debugfs_subsys_free(struct nvmet_subsys *subsys)
+{
+ debugfs_remove_recursive(subsys->debugfs_dir);
+}
+
+int __init nvmet_init_debugfs(void)
+{
+ struct dentry *parent;
+
+ parent = debugfs_create_dir("nvmet", NULL);
+ if (IS_ERR(parent)) {
+ pr_warn("%s: failed to create debugfs directory\n", "nvmet");
+ return PTR_ERR(parent);
+ }
+ nvmet_debugfs = parent;
+ return 0;
+}
+
+void nvmet_exit_debugfs(void)
+{
+ debugfs_remove_recursive(nvmet_debugfs);
+}
diff --git a/drivers/nvme/target/debugfs.h b/drivers/nvme/target/debugfs.h
new file mode 100644
index 000000000000..cfb8bbf6a297
--- /dev/null
+++ b/drivers/nvme/target/debugfs.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DebugFS interface for the NVMe target.
+ * Copyright (c) 2022-2024 Shadow
+ * Copyright (c) 2024 SUSE LLC
+ */
+#ifndef NVMET_DEBUGFS_H
+#define NVMET_DEBUGFS_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_NVME_TARGET_DEBUGFS
+int nvmet_debugfs_subsys_setup(struct nvmet_subsys *subsys);
+void nvmet_debugfs_subsys_free(struct nvmet_subsys *subsys);
+int nvmet_debugfs_ctrl_setup(struct nvmet_ctrl *ctrl);
+void nvmet_debugfs_ctrl_free(struct nvmet_ctrl *ctrl);
+
+int __init nvmet_init_debugfs(void);
+void nvmet_exit_debugfs(void);
+#else
+static inline int nvmet_debugfs_subsys_setup(struct nvmet_subsys *subsys)
+{
+ return 0;
+}
+static inline void nvmet_debugfs_subsys_free(struct nvmet_subsys *subsys){}
+
+static inline int nvmet_debugfs_ctrl_setup(struct nvmet_ctrl *ctrl)
+{
+ return 0;
+}
+static inline void nvmet_debugfs_ctrl_free(struct nvmet_ctrl *ctrl) {}
+
+static inline int __init nvmet_init_debugfs(void)
+{
+ return 0;
+}
+
+static inline void nvmet_exit_debugfs(void) {}
+
+#endif
+
+#endif /* NVMET_DEBUGFS_H */
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 68e82ccc0e4e..df7207640506 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -179,7 +179,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
if (req->cmd->get_log_page.lid != NVME_LOG_DISC) {
req->error_loc =
offsetof(struct nvme_get_log_page_command, lid);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out;
}
@@ -187,7 +187,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
if (offset & 0x3) {
req->error_loc =
offsetof(struct nvme_get_log_page_command, lpo);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out;
}
@@ -224,6 +224,9 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
}
list_for_each_entry(r, &req->port->referrals, entry) {
+ if (r->disc_addr.trtype == NVMF_TRTYPE_PCI)
+ continue;
+
nvmet_format_discovery_entry(hdr, r,
NVME_DISC_SUBSYS_NAME,
r->disc_addr.traddr,
@@ -256,7 +259,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
if (req->cmd->identify.cns != NVME_ID_CNS_CTRL) {
req->error_loc = offsetof(struct nvme_identify, cns);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out;
}
@@ -282,7 +285,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
id->lpa = (1 << 2);
/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
- id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+ id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
id->sgls = cpu_to_le32(1 << 0); /* we always support SGLs */
if (ctrl->ops->flags & NVMF_KEYED_SGLS)
@@ -320,7 +323,7 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req)
default:
req->error_loc =
offsetof(struct nvme_common_command, cdw10);
- stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ stat = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
@@ -345,13 +348,27 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req)
default:
req->error_loc =
offsetof(struct nvme_common_command, cdw10);
- stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ stat = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
nvmet_req_complete(req, stat);
}
+u32 nvmet_discovery_cmd_data_len(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+
+ switch (cmd->common.opcode) {
+ case nvme_admin_get_log_page:
+ return nvmet_get_log_page_len(req->cmd);
+ case nvme_admin_identify:
+ return NVME_IDENTIFY_DATA_SIZE;
+ default:
+ return 0;
+ }
+}
+
u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
@@ -361,7 +378,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
cmd->common.opcode);
req->error_loc =
offsetof(struct nvme_common_command, opcode);
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
switch (cmd->common.opcode) {
@@ -386,7 +403,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
default:
pr_debug("unhandled cmd %d\n", cmd->common.opcode);
req->error_loc = offsetof(struct nvme_common_command, opcode);
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
}
diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c
index eb7785be0ca7..2022757f08dc 100644
--- a/drivers/nvme/target/fabrics-cmd-auth.c
+++ b/drivers/nvme/target/fabrics-cmd-auth.c
@@ -31,7 +31,7 @@ void nvmet_auth_sq_init(struct nvmet_sq *sq)
sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE;
}
-static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d)
+static u8 nvmet_auth_negotiate(struct nvmet_req *req, void *d)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmf_auth_dhchap_negotiate_data *data = d;
@@ -109,7 +109,7 @@ static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d)
return 0;
}
-static u16 nvmet_auth_reply(struct nvmet_req *req, void *d)
+static u8 nvmet_auth_reply(struct nvmet_req *req, void *d)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmf_auth_dhchap_reply_data *data = d;
@@ -172,13 +172,18 @@ static u16 nvmet_auth_reply(struct nvmet_req *req, void *d)
return 0;
}
-static u16 nvmet_auth_failure2(void *d)
+static u8 nvmet_auth_failure2(void *d)
{
struct nvmf_auth_dhchap_failure_data *data = d;
return data->rescode_exp;
}
+u32 nvmet_auth_send_data_len(struct nvmet_req *req)
+{
+ return le32_to_cpu(req->cmd->auth_send.tl);
+}
+
void nvmet_execute_auth_send(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -186,28 +191,29 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
void *d;
u32 tl;
u16 status = 0;
+ u8 dhchap_status;
if (req->cmd->auth_send.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_send_command, secp);
goto done;
}
if (req->cmd->auth_send.spsp0 != 0x01) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_send_command, spsp0);
goto done;
}
if (req->cmd->auth_send.spsp1 != 0x01) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_send_command, spsp1);
goto done;
}
- tl = le32_to_cpu(req->cmd->auth_send.tl);
+ tl = nvmet_auth_send_data_len(req);
if (!tl) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_send_command, tl);
goto done;
@@ -237,30 +243,32 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
if (data->auth_type == NVME_AUTH_COMMON_MESSAGES) {
if (data->auth_id == NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE) {
/* Restart negotiation */
- pr_debug("%s: ctrl %d qid %d reset negotiation\n", __func__,
- ctrl->cntlid, req->sq->qid);
+ pr_debug("%s: ctrl %d qid %d reset negotiation\n",
+ __func__, ctrl->cntlid, req->sq->qid);
if (!req->sq->qid) {
- if (nvmet_setup_auth(ctrl) < 0) {
- status = NVME_SC_INTERNAL;
- pr_err("ctrl %d qid 0 failed to setup"
- "re-authentication",
+ dhchap_status = nvmet_setup_auth(ctrl);
+ if (dhchap_status) {
+ pr_err("ctrl %d qid 0 failed to setup re-authentication\n",
ctrl->cntlid);
- goto done_failure1;
+ req->sq->dhchap_status = dhchap_status;
+ req->sq->dhchap_step =
+ NVME_AUTH_DHCHAP_MESSAGE_FAILURE1;
+ goto done_kfree;
}
}
- req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE;
+ req->sq->dhchap_step =
+ NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE;
} else if (data->auth_id != req->sq->dhchap_step)
goto done_failure1;
/* Validate negotiation parameters */
- status = nvmet_auth_negotiate(req, d);
- if (status == 0)
+ dhchap_status = nvmet_auth_negotiate(req, d);
+ if (dhchap_status == 0)
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE;
else {
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_FAILURE1;
- req->sq->dhchap_status = status;
- status = 0;
+ req->sq->dhchap_status = dhchap_status;
}
goto done_kfree;
}
@@ -284,15 +292,14 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
switch (data->auth_id) {
case NVME_AUTH_DHCHAP_MESSAGE_REPLY:
- status = nvmet_auth_reply(req, d);
- if (status == 0)
+ dhchap_status = nvmet_auth_reply(req, d);
+ if (dhchap_status == 0)
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1;
else {
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_FAILURE1;
- req->sq->dhchap_status = status;
- status = 0;
+ req->sq->dhchap_status = dhchap_status;
}
goto done_kfree;
case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2:
@@ -301,13 +308,12 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
__func__, ctrl->cntlid, req->sq->qid);
goto done_kfree;
case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2:
- status = nvmet_auth_failure2(d);
- if (status) {
+ dhchap_status = nvmet_auth_failure2(d);
+ if (dhchap_status) {
pr_warn("ctrl %d qid %d: authentication failed (%d)\n",
- ctrl->cntlid, req->sq->qid, status);
- req->sq->dhchap_status = status;
+ ctrl->cntlid, req->sq->qid, dhchap_status);
+ req->sq->dhchap_status = dhchap_status;
req->sq->authenticated = false;
- status = 0;
}
goto done_kfree;
default:
@@ -332,7 +338,6 @@ done:
pr_debug("%s: ctrl %d qid %d nvme status %x error loc %d\n",
__func__, ctrl->cntlid, req->sq->qid,
status, req->error_loc);
- req->cqe->result.u64 = 0;
if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 &&
req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) {
unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120;
@@ -429,6 +434,11 @@ static void nvmet_auth_failure1(struct nvmet_req *req, void *d, int al)
data->rescode_exp = req->sq->dhchap_status;
}
+u32 nvmet_auth_receive_data_len(struct nvmet_req *req)
+{
+ return le32_to_cpu(req->cmd->auth_receive.al);
+}
+
void nvmet_execute_auth_receive(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -437,26 +447,26 @@ void nvmet_execute_auth_receive(struct nvmet_req *req)
u16 status = 0;
if (req->cmd->auth_receive.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_receive_command, secp);
goto done;
}
if (req->cmd->auth_receive.spsp0 != 0x01) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_receive_command, spsp0);
goto done;
}
if (req->cmd->auth_receive.spsp1 != 0x01) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_receive_command, spsp1);
goto done;
}
- al = le32_to_cpu(req->cmd->auth_receive.al);
+ al = nvmet_auth_receive_data_len(req);
if (!al) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc =
offsetof(struct nvmf_auth_receive_command, al);
goto done;
@@ -515,8 +525,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req)
status = nvmet_copy_to_sgl(req, 0, d, al);
kfree(d);
done:
- req->cqe->result.u64 = 0;
-
if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2)
nvmet_auth_sq_free(req->sq);
else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) {
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 9964ffe347d2..eb406c90c167 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -18,7 +18,7 @@ static void nvmet_execute_prop_set(struct nvmet_req *req)
if (req->cmd->prop_set.attrib & 1) {
req->error_loc =
offsetof(struct nvmf_property_set_command, attrib);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out;
}
@@ -29,7 +29,7 @@ static void nvmet_execute_prop_set(struct nvmet_req *req)
default:
req->error_loc =
offsetof(struct nvmf_property_set_command, offset);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
out:
nvmet_req_complete(req, status);
@@ -50,7 +50,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
val = ctrl->cap;
break;
default:
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
} else {
@@ -64,8 +64,11 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
case NVME_REG_CSTS:
val = ctrl->csts;
break;
+ case NVME_REG_CRTO:
+ val = NVME_CAP_TIMEOUT(ctrl->csts);
+ break;
default:
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
break;
}
}
@@ -82,6 +85,22 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
nvmet_req_complete(req, status);
}
+u32 nvmet_fabrics_admin_cmd_data_len(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+
+ switch (cmd->fabrics.fctype) {
+#ifdef CONFIG_NVME_TARGET_AUTH
+ case nvme_fabrics_type_auth_send:
+ return nvmet_auth_send_data_len(req);
+ case nvme_fabrics_type_auth_receive:
+ return nvmet_auth_receive_data_len(req);
+#endif
+ default:
+ return 0;
+ }
+}
+
u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
@@ -105,12 +124,28 @@ u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req)
pr_debug("received unknown capsule type 0x%x\n",
cmd->fabrics.fctype);
req->error_loc = offsetof(struct nvmf_common_command, fctype);
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
return 0;
}
+u32 nvmet_fabrics_io_cmd_data_len(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+
+ switch (cmd->fabrics.fctype) {
+#ifdef CONFIG_NVME_TARGET_AUTH
+ case nvme_fabrics_type_auth_send:
+ return nvmet_auth_send_data_len(req);
+ case nvme_fabrics_type_auth_receive:
+ return nvmet_auth_receive_data_len(req);
+#endif
+ default:
+ return 0;
+ }
+}
+
u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
@@ -128,7 +163,7 @@ u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req)
pr_debug("received unknown capsule type 0x%x\n",
cmd->fabrics.fctype);
req->error_loc = offsetof(struct nvmf_common_command, fctype);
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
return 0;
@@ -147,29 +182,30 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
pr_warn("queue size zero!\n");
req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize);
- ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+ ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
goto err;
}
if (ctrl->sqs[qid] != NULL) {
pr_warn("qid %u has already been created\n", qid);
req->error_loc = offsetof(struct nvmf_connect_command, qid);
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
}
- if (sqsize > mqes) {
+ /* for fabrics, this value applies to only the I/O Submission Queues */
+ if (qid && sqsize > mqes) {
pr_warn("sqsize %u is larger than MQES supported %u cntlid %d\n",
sqsize, mqes, ctrl->cntlid);
req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize);
- return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+ return NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
}
old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
if (old) {
pr_warn("queue already connected!\n");
req->error_loc = offsetof(struct nvmf_connect_command, opcode);
- return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
+ return NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR;
}
/* note: convert queue size from 0's-based value to 1's-based value */
@@ -209,79 +245,67 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
struct nvmf_connect_command *c = &req->cmd->connect;
struct nvmf_connect_data *d;
struct nvmet_ctrl *ctrl = NULL;
- u16 status;
- int ret;
+ struct nvmet_alloc_ctrl_args args = {
+ .port = req->port,
+ .ops = req->ops,
+ .p2p_client = req->p2p_client,
+ .kato = le32_to_cpu(c->kato),
+ };
if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
return;
d = kmalloc(sizeof(*d), GFP_KERNEL);
if (!d) {
- status = NVME_SC_INTERNAL;
+ args.status = NVME_SC_INTERNAL;
goto complete;
}
- status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
- if (status)
+ args.status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (args.status)
goto out;
- /* zero out initial completion result, assign values as needed */
- req->cqe->result.u32 = 0;
-
if (c->recfmt != 0) {
pr_warn("invalid connect version (%d).\n",
le16_to_cpu(c->recfmt));
- req->error_loc = offsetof(struct nvmf_connect_command, recfmt);
- status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
+ args.error_loc = offsetof(struct nvmf_connect_command, recfmt);
+ args.status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR;
goto out;
}
if (unlikely(d->cntlid != cpu_to_le16(0xffff))) {
pr_warn("connect attempt for invalid controller ID %#x\n",
d->cntlid);
- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
- req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid);
+ args.status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ args.result = IPO_IATTR_CONNECT_DATA(cntlid);
goto out;
}
d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
- status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
- le32_to_cpu(c->kato), &ctrl);
- if (status)
- goto out;
- ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
+ args.subsysnqn = d->subsysnqn;
+ args.hostnqn = d->hostnqn;
+ args.hostid = &d->hostid;
+ args.kato = le32_to_cpu(c->kato);
- uuid_copy(&ctrl->hostid, &d->hostid);
-
- ret = nvmet_setup_auth(ctrl);
- if (ret < 0) {
- pr_err("Failed to setup authentication, error %d\n", ret);
- nvmet_ctrl_put(ctrl);
- if (ret == -EPERM)
- status = (NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR);
- else
- status = NVME_SC_INTERNAL;
+ ctrl = nvmet_alloc_ctrl(&args);
+ if (!ctrl)
goto out;
- }
- status = nvmet_install_queue(ctrl, req);
- if (status) {
+ args.status = nvmet_install_queue(ctrl, req);
+ if (args.status) {
nvmet_ctrl_put(ctrl);
goto out;
}
- pr_info("creating %s controller %d for subsystem %s for NQN %s%s%s.\n",
- nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm",
- ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn,
- ctrl->pi_support ? " T10-PI is enabled" : "",
- nvmet_has_auth(ctrl) ? " with DH-HMAC-CHAP" : "");
- req->cqe->result.u32 = cpu_to_le32(nvmet_connect_result(ctrl));
+ args.result = cpu_to_le32(nvmet_connect_result(ctrl));
out:
kfree(d);
complete:
- nvmet_req_complete(req, status);
+ req->error_loc = args.error_loc;
+ req->cqe->result.u32 = args.result;
+ nvmet_req_complete(req, args.status);
}
static void nvmet_execute_io_connect(struct nvmet_req *req)
@@ -305,13 +329,10 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
if (status)
goto out;
- /* zero out initial completion result, assign values as needed */
- req->cqe->result.u32 = 0;
-
if (c->recfmt != 0) {
pr_warn("invalid connect version (%d).\n",
le16_to_cpu(c->recfmt));
- status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
+ status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR;
goto out;
}
@@ -320,13 +341,13 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
ctrl = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
le16_to_cpu(d->cntlid), req);
if (!ctrl) {
- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+ status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
goto out;
}
if (unlikely(qid > ctrl->subsys->max_qid)) {
pr_warn("invalid queue id (%d)\n", qid);
- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+ status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(qid);
goto out_ctrl_put;
}
@@ -348,6 +369,17 @@ out_ctrl_put:
goto out;
}
+u32 nvmet_connect_cmd_data_len(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+
+ if (!nvme_is_fabrics(cmd) ||
+ cmd->fabrics.fctype != nvme_fabrics_type_connect)
+ return 0;
+
+ return sizeof(struct nvmf_connect_data);
+}
+
u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
@@ -356,13 +388,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
pr_debug("invalid command 0x%x on unconnected queue.\n",
cmd->fabrics.opcode);
req->error_loc = offsetof(struct nvme_common_command, opcode);
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
if (cmd->fabrics.fctype != nvme_fabrics_type_connect) {
pr_debug("invalid capsule type 0x%x on unconnected queue.\n",
cmd->fabrics.fctype);
req->error_loc = offsetof(struct nvmf_common_command, fctype);
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
if (cmd->connect.qid == 0)
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index fd229f310c93..3ef4beacde32 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -148,7 +148,7 @@ struct nvmet_fc_tgt_queue {
struct workqueue_struct *work_q;
struct kref ref;
/* array of fcp_iods */
- struct nvmet_fc_fcp_iod fod[] __counted_by(sqsize);
+ struct nvmet_fc_fcp_iod fod[] /* __counted_by(sqsize) */;
} __aligned(sizeof(unsigned long long));
struct nvmet_fc_hostport {
@@ -1115,16 +1115,21 @@ nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
}
static bool
-nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id)
+nvmet_fc_assoc_exists(struct nvmet_fc_tgtport *tgtport, u64 association_id)
{
struct nvmet_fc_tgt_assoc *a;
+ bool found = false;
+ rcu_read_lock();
list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) {
- if (association_id == a->association_id)
- return true;
+ if (association_id == a->association_id) {
+ found = true;
+ break;
+ }
}
+ rcu_read_unlock();
- return false;
+ return found;
}
static struct nvmet_fc_tgt_assoc *
@@ -1164,13 +1169,11 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
ran = ran << BYTES_FOR_QID_SHIFT;
spin_lock_irqsave(&tgtport->lock, flags);
- rcu_read_lock();
- if (!nvmet_fc_assoc_exits(tgtport, ran)) {
+ if (!nvmet_fc_assoc_exists(tgtport, ran)) {
assoc->association_id = ran;
list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list);
done = true;
}
- rcu_read_unlock();
spin_unlock_irqrestore(&tgtport->lock, flags);
} while (!done);
@@ -2931,6 +2934,38 @@ nvmet_fc_discovery_chg(struct nvmet_port *port)
tgtport->ops->discovery_event(&tgtport->fc_target_port);
}
+static ssize_t
+nvmet_fc_host_traddr(struct nvmet_ctrl *ctrl,
+ char *traddr, size_t traddr_size)
+{
+ struct nvmet_sq *sq = ctrl->sqs[0];
+ struct nvmet_fc_tgt_queue *queue =
+ container_of(sq, struct nvmet_fc_tgt_queue, nvme_sq);
+ struct nvmet_fc_tgtport *tgtport = queue->assoc ? queue->assoc->tgtport : NULL;
+ struct nvmet_fc_hostport *hostport = queue->assoc ? queue->assoc->hostport : NULL;
+ u64 wwnn, wwpn;
+ ssize_t ret = 0;
+
+ if (!tgtport || !nvmet_fc_tgtport_get(tgtport))
+ return -ENODEV;
+ if (!hostport || !nvmet_fc_hostport_get(hostport)) {
+ ret = -ENODEV;
+ goto out_put;
+ }
+
+ if (tgtport->ops->host_traddr) {
+ ret = tgtport->ops->host_traddr(hostport->hosthandle, &wwnn, &wwpn);
+ if (ret)
+ goto out_put_host;
+ ret = snprintf(traddr, traddr_size, "nn-0x%llx:pn-0x%llx", wwnn, wwpn);
+ }
+out_put_host:
+ nvmet_fc_hostport_put(hostport);
+out_put:
+ nvmet_fc_tgtport_put(tgtport);
+ return ret;
+}
+
static const struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_FC,
@@ -2940,6 +2975,7 @@ static const struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = {
.queue_response = nvmet_fc_fcp_nvme_cmd_done,
.delete_ctrl = nvmet_fc_delete_ctrl,
.discovery_chg = nvmet_fc_discovery_chg,
+ .host_traddr = nvmet_fc_host_traddr,
};
static int __init nvmet_fc_init_module(void)
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 1471af250ea6..e1abb27927ff 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -492,6 +492,16 @@ fcloop_t2h_host_release(void *hosthandle)
/* host handle ignored for now */
}
+static int
+fcloop_t2h_host_traddr(void *hosthandle, u64 *wwnn, u64 *wwpn)
+{
+ struct fcloop_rport *rport = hosthandle;
+
+ *wwnn = rport->lport->localport->node_name;
+ *wwpn = rport->lport->localport->port_name;
+ return 0;
+}
+
/*
* Simulate reception of RSCN and converting it to a initiator transport
* call to rescan a remote port.
@@ -1074,6 +1084,7 @@ static struct nvmet_fc_target_template tgttemplate = {
.ls_req = fcloop_t2h_ls_req,
.ls_abort = fcloop_t2h_ls_abort,
.host_release = fcloop_t2h_host_release,
+ .host_traddr = fcloop_t2h_host_traddr,
.max_hw_queues = FCLOOP_HW_QUEUES,
.max_sgl_segments = FCLOOP_SGL_SEGS,
.max_dif_sgl_segments = FCLOOP_SGL_SEGS,
@@ -1556,7 +1567,9 @@ static const struct attribute_group *fcloop_dev_attr_groups[] = {
NULL,
};
-static struct class *fcloop_class;
+static const struct class fcloop_class = {
+ .name = "fcloop",
+};
static struct device *fcloop_device;
@@ -1564,15 +1577,14 @@ static int __init fcloop_init(void)
{
int ret;
- fcloop_class = class_create("fcloop");
- if (IS_ERR(fcloop_class)) {
+ ret = class_register(&fcloop_class);
+ if (ret) {
pr_err("couldn't register class fcloop\n");
- ret = PTR_ERR(fcloop_class);
return ret;
}
fcloop_device = device_create_with_groups(
- fcloop_class, NULL, MKDEV(0, 0), NULL,
+ &fcloop_class, NULL, MKDEV(0, 0), NULL,
fcloop_dev_attr_groups, "ctl");
if (IS_ERR(fcloop_device)) {
pr_err("couldn't create ctl device!\n");
@@ -1585,7 +1597,7 @@ static int __init fcloop_init(void)
return 0;
out_destroy_class:
- class_destroy(fcloop_class);
+ class_unregister(&fcloop_class);
return ret;
}
@@ -1643,8 +1655,8 @@ static void __exit fcloop_exit(void)
put_device(fcloop_device);
- device_destroy(fcloop_class, MKDEV(0, 0));
- class_destroy(fcloop_class);
+ device_destroy(&fcloop_class, MKDEV(0, 0));
+ class_unregister(&fcloop_class);
}
module_init(fcloop_init);
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index f11400a908f2..83be0657e6df 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
*/
id->nsfeat |= 1 << 4;
/* NPWG = Namespace Preferred Write Granularity. 0's based */
- id->npwg = lpp0b;
+ id->npwg = to0based(bdev_io_min(bdev) / bdev_logical_block_size(bdev));
/* NPWA = Namespace Preferred Write Alignment. 0's based */
id->npwa = id->npwg;
/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
@@ -50,10 +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_handle) {
- bdev_release(ns->bdev_handle);
+ if (ns->bdev_file) {
+ fput(ns->bdev_file);
ns->bdev = NULL;
- ns->bdev_handle = NULL;
+ ns->bdev_file = NULL;
}
}
@@ -61,15 +61,17 @@ static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns)
{
struct blk_integrity *bi = bdev_get_integrity(ns->bdev);
- if (bi) {
+ if (!bi)
+ return;
+
+ if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC) {
ns->metadata_size = bi->tuple_size;
- if (bi->profile == &t10_pi_type1_crc)
+ if (bi->flags & BLK_INTEGRITY_REF_TAG)
ns->pi_type = NVME_NS_DPS_PI_TYPE1;
- else if (bi->profile == &t10_pi_type3_crc)
- ns->pi_type = NVME_NS_DPS_PI_TYPE3;
else
- /* Unsupported metadata type */
- ns->metadata_size = 0;
+ ns->pi_type = NVME_NS_DPS_PI_TYPE3;
+ } else {
+ ns->metadata_size = 0;
}
}
@@ -85,24 +87,24 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
if (ns->buffered_io)
return -ENOTBLK;
- ns->bdev_handle = bdev_open_by_path(ns->device_path,
+ ns->bdev_file = bdev_file_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 (IS_ERR(ns->bdev_file)) {
+ ret = PTR_ERR(ns->bdev_file);
if (ret != -ENOTBLK) {
pr_err("failed to open block device %s: (%d)\n",
ns->device_path, ret);
}
- ns->bdev_handle = NULL;
+ ns->bdev_file = NULL;
return ret;
}
- ns->bdev = ns->bdev_handle->bdev;
+ ns->bdev = file_bdev(ns->bdev_file);
ns->size = bdev_nr_bytes(ns->bdev);
ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
ns->pi_type = 0;
ns->metadata_size = 0;
- if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY_T10))
+ if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY))
nvmet_bdev_ns_enable_integrity(ns);
if (bdev_is_zoned(ns->bdev)) {
@@ -135,11 +137,11 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
*/
switch (blk_sts) {
case BLK_STS_NOSPC:
- status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
+ status = NVME_SC_CAP_EXCEEDED | NVME_STATUS_DNR;
req->error_loc = offsetof(struct nvme_rw_command, length);
break;
case BLK_STS_TARGET:
- status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+ status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
req->error_loc = offsetof(struct nvme_rw_command, slba);
break;
case BLK_STS_NOTSUPP:
@@ -147,10 +149,10 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
switch (req->cmd->common.opcode) {
case nvme_cmd_dsm:
case nvme_cmd_write_zeroes:
- status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
+ status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
break;
default:
- status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
break;
case BLK_STS_MEDIUM:
@@ -159,7 +161,7 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
break;
case BLK_STS_IOERR:
default:
- status = NVME_SC_INTERNAL | NVME_SC_DNR;
+ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
req->error_loc = offsetof(struct nvme_common_command, opcode);
}
@@ -270,6 +272,9 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
iter_flags = SG_MITER_FROM_SG;
}
+ if (req->cmd->rw.control & cpu_to_le16(NVME_RW_LR))
+ opf |= REQ_FAILFAST_DEV;
+
if (is_pci_p2pdma_page(sg_page(req->sg)))
opf |= REQ_NOMERGE;
@@ -356,7 +361,7 @@ u16 nvmet_bdev_flush(struct nvmet_req *req)
return 0;
if (blkdev_issue_flush(req->ns->bdev))
- return NVME_SC_INTERNAL | NVME_SC_DNR;
+ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
return 0;
}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index e589915ddef8..a9d112d34d4f 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -265,6 +265,13 @@ static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
{
if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags))
return;
+ /*
+ * It's possible that some requests might have been added
+ * after admin queue is stopped/quiesced. So now start the
+ * queue to flush these requests to the completion.
+ */
+ nvme_unquiesce_admin_queue(&ctrl->ctrl);
+
nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
nvme_remove_admin_tag_set(&ctrl->ctrl);
}
@@ -297,6 +304,12 @@ static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
}
ctrl->ctrl.queue_count = 1;
+ /*
+ * It's possible that some requests might have been added
+ * after io queue is stopped/quiesced. So now start the
+ * queue to flush these requests to the completion.
+ */
+ nvme_unquiesce_io_queues(&ctrl->ctrl);
}
static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -555,6 +568,10 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
goto out;
}
+ ret = nvme_add_ctrl(&ctrl->ctrl);
+ if (ret)
+ goto out_put_ctrl;
+
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
WARN_ON_ONCE(1);
@@ -611,6 +628,7 @@ out_free_queues:
kfree(ctrl->queues);
out_uninit_ctrl:
nvme_uninit_ctrl(&ctrl->ctrl);
+out_put_ctrl:
nvme_put_ctrl(&ctrl->ctrl);
out:
if (ret > 0)
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 6c8acebe1a1a..fcf4f460dc9a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -20,9 +20,11 @@
#include <linux/blkdev.h>
#include <linux/radix-tree.h>
#include <linux/t10-pi.h>
+#include <linux/kfifo.h>
-#define NVMET_DEFAULT_VS NVME_VS(1, 3, 0)
+#define NVMET_DEFAULT_VS NVME_VS(2, 1, 0)
+#define NVMET_NS_ENABLED XA_MARK_1
#define NVMET_ASYNC_EVENTS 4
#define NVMET_ERROR_LOG_SLOTS 128
#define NVMET_NO_ERROR_LOC ((u16)-1)
@@ -30,6 +32,13 @@
#define NVMET_MN_MAX_SIZE 40
#define NVMET_SN_MAX_SIZE 20
#define NVMET_FR_MAX_SIZE 8
+#define NVMET_PR_LOG_QUEUE_SIZE 64
+
+#define nvmet_for_each_ns(xa, index, entry) \
+ xa_for_each(xa, index, entry)
+
+#define nvmet_for_each_enabled_ns(xa, index, entry) \
+ xa_for_each_marked(xa, index, entry, NVMET_NS_ENABLED)
/*
* Supported optional AENs:
@@ -56,9 +65,41 @@
#define IPO_IATTR_CONNECT_SQE(x) \
(cpu_to_le32(offsetof(struct nvmf_connect_command, x)))
+struct nvmet_pr_registrant {
+ u64 rkey;
+ uuid_t hostid;
+ enum nvme_pr_type rtype;
+ struct list_head entry;
+ struct rcu_head rcu;
+};
+
+struct nvmet_pr {
+ bool enable;
+ unsigned long notify_mask;
+ atomic_t generation;
+ struct nvmet_pr_registrant __rcu *holder;
+ /*
+ * During the execution of the reservation command, mutual
+ * exclusion is required throughout the process. However,
+ * while waiting asynchronously for the 'per controller
+ * percpu_ref' to complete before the 'preempt and abort'
+ * command finishes, a semaphore is needed to ensure mutual
+ * exclusion instead of a mutex.
+ */
+ struct semaphore pr_sem;
+ struct list_head registrant_list;
+};
+
+struct nvmet_pr_per_ctrl_ref {
+ struct percpu_ref ref;
+ struct completion free_done;
+ struct completion confirm_done;
+ uuid_t hostid;
+};
+
struct nvmet_ns {
struct percpu_ref ref;
- struct bdev_handle *bdev_handle;
+ struct file *bdev_file;
struct block_device *bdev;
struct file *file;
bool readonly;
@@ -85,6 +126,8 @@ struct nvmet_ns {
int pi_type;
int metadata_size;
u8 csi;
+ struct nvmet_pr pr;
+ struct xarray pr_per_ctrl_refs;
};
static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
@@ -113,8 +156,8 @@ struct nvmet_sq {
bool authenticated;
struct delayed_work auth_expired_work;
u16 dhchap_tid;
- u16 dhchap_status;
- int dhchap_step;
+ u8 dhchap_status;
+ u8 dhchap_step;
u8 *dhchap_c1;
u8 *dhchap_c2;
u32 dhchap_s1;
@@ -163,6 +206,7 @@ struct nvmet_port {
void *priv;
bool enabled;
int inline_data_size;
+ int max_queue_size;
const struct nvmet_fabrics_ops *tr_ops;
bool pi_enable;
};
@@ -190,10 +234,19 @@ 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_pr_log_mgr {
+ struct mutex lock;
+ u64 lost_count;
+ u64 counter;
+ DECLARE_KFIFO(log_queue, struct nvme_pr_log, NVMET_PR_LOG_QUEUE_SIZE);
+};
+
struct nvmet_ctrl {
struct nvmet_subsys *subsys;
struct nvmet_sq **sqs;
+ void *drvdata;
+
bool reset_tbkas;
struct mutex lock;
@@ -229,7 +282,9 @@ struct nvmet_ctrl {
struct device *p2p_client;
struct radix_tree_root p2p_ns_map;
-
+#ifdef CONFIG_NVME_TARGET_DEBUGFS
+ struct dentry *debugfs_dir;
+#endif
spinlock_t error_lock;
u64 err_counter;
struct nvme_error_slot slots[NVMET_ERROR_LOG_SLOTS];
@@ -243,6 +298,7 @@ struct nvmet_ctrl {
u8 *dh_key;
size_t dh_keysize;
#endif
+ struct nvmet_pr_log_mgr pr_log_mgr;
};
struct nvmet_subsys {
@@ -261,7 +317,9 @@ struct nvmet_subsys {
struct list_head hosts;
bool allow_any_host;
-
+#ifdef CONFIG_NVME_TARGET_DEBUGFS
+ struct dentry *debugfs_dir;
+#endif
u16 max_qid;
u64 ver;
@@ -275,6 +333,8 @@ struct nvmet_subsys {
struct config_group namespaces_group;
struct config_group allowed_hosts_group;
+ u16 vendor_id;
+ u16 subsys_vendor_id;
char *model_number;
u32 ieee_oui;
char *firmware_rev;
@@ -349,10 +409,24 @@ struct nvmet_fabrics_ops {
void (*delete_ctrl)(struct nvmet_ctrl *ctrl);
void (*disc_traddr)(struct nvmet_req *req,
struct nvmet_port *port, char *traddr);
+ ssize_t (*host_traddr)(struct nvmet_ctrl *ctrl,
+ char *traddr, size_t traddr_len);
u16 (*install_queue)(struct nvmet_sq *nvme_sq);
void (*discovery_chg)(struct nvmet_port *port);
u8 (*get_mdts)(const struct nvmet_ctrl *ctrl);
u16 (*get_max_queue_size)(const struct nvmet_ctrl *ctrl);
+
+ /* Operations mandatory for PCI target controllers */
+ u16 (*create_sq)(struct nvmet_ctrl *ctrl, u16 sqid, u16 flags,
+ u16 qsize, u64 prp1);
+ u16 (*delete_sq)(struct nvmet_ctrl *ctrl, u16 sqid);
+ u16 (*create_cq)(struct nvmet_ctrl *ctrl, u16 cqid, u16 flags,
+ u16 qsize, u64 prp1, u16 irq_vector);
+ u16 (*delete_cq)(struct nvmet_ctrl *ctrl, u16 cqid);
+ u16 (*set_feature)(const struct nvmet_ctrl *ctrl, u8 feat,
+ void *feat_data);
+ u16 (*get_feature)(const struct nvmet_ctrl *ctrl, u8 feat,
+ void *feat_data);
};
#define NVMET_MAX_INLINE_BIOVEC 8
@@ -389,6 +463,9 @@ struct nvmet_req {
struct work_struct zmgmt_work;
} z;
#endif /* CONFIG_BLK_DEV_ZONED */
+ struct {
+ struct work_struct abort_work;
+ } r;
};
int sg_cnt;
int metadata_sg_cnt;
@@ -405,6 +482,7 @@ struct nvmet_req {
struct device *p2p_client;
u16 error_loc;
u64 error_slba;
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
};
#define NVMET_MAX_MPOOL_BVEC 16
@@ -458,18 +536,24 @@ void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl);
void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl);
u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
+u32 nvmet_connect_cmd_data_len(struct nvmet_req *req);
void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id);
u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req);
u16 nvmet_file_parse_io_cmd(struct nvmet_req *req);
u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req);
+u32 nvmet_admin_cmd_data_len(struct nvmet_req *req);
u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
+u32 nvmet_discovery_cmd_data_len(struct nvmet_req *req);
u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req);
+u32 nvmet_fabrics_admin_cmd_data_len(struct nvmet_req *req);
u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req);
+u32 nvmet_fabrics_io_cmd_data_len(struct nvmet_req *req);
bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops);
void nvmet_req_uninit(struct nvmet_req *req);
+size_t nvmet_req_transfer_len(struct nvmet_req *req);
bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len);
bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len);
void nvmet_req_complete(struct nvmet_req *req, u16 status);
@@ -480,23 +564,44 @@ void nvmet_execute_set_features(struct nvmet_req *req);
void nvmet_execute_get_features(struct nvmet_req *req);
void nvmet_execute_keep_alive(struct nvmet_req *req);
+u16 nvmet_check_cqid(struct nvmet_ctrl *ctrl, u16 cqid);
void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
u16 size);
+u16 nvmet_cq_create(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, u16 qid,
+ u16 size);
+u16 nvmet_check_sqid(struct nvmet_ctrl *ctrl, u16 sqid, bool create);
void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid,
u16 size);
+u16 nvmet_sq_create(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid,
+ u16 size);
void nvmet_sq_destroy(struct nvmet_sq *sq);
int nvmet_sq_init(struct nvmet_sq *sq);
void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl);
void nvmet_update_cc(struct nvmet_ctrl *ctrl, u32 new);
-u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
- struct nvmet_req *req, u32 kato, struct nvmet_ctrl **ctrlp);
+
+struct nvmet_alloc_ctrl_args {
+ struct nvmet_port *port;
+ char *subsysnqn;
+ char *hostnqn;
+ uuid_t *hostid;
+ const struct nvmet_fabrics_ops *ops;
+ struct device *p2p_client;
+ u32 kato;
+ __le32 result;
+ u16 error_loc;
+ u16 status;
+};
+
+struct nvmet_ctrl *nvmet_alloc_ctrl(struct nvmet_alloc_ctrl_args *args);
struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn,
const char *hostnqn, u16 cntlid,
struct nvmet_req *req);
void nvmet_ctrl_put(struct nvmet_ctrl *ctrl);
u16 nvmet_check_ctrl_status(struct nvmet_req *req);
+ssize_t nvmet_ctrl_host_traddr(struct nvmet_ctrl *ctrl,
+ char *traddr, size_t traddr_len);
struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
enum nvme_subsys_type type);
@@ -543,9 +648,10 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
u8 event_info, u8 log_page);
-#define NVMET_QUEUE_SIZE 1024
+#define NVMET_MIN_QUEUE_SIZE 16
+#define NVMET_MAX_QUEUE_SIZE 1024
#define NVMET_NR_QUEUES 128
-#define NVMET_MAX_CMD NVMET_QUEUE_SIZE
+#define NVMET_MAX_CMD(ctrl) (NVME_CAP_MQES(ctrl->cap) + 1)
/*
* Nice round number that makes a list of nsids fit into a page.
@@ -629,6 +735,11 @@ static inline bool nvmet_is_disc_subsys(struct nvmet_subsys *subsys)
return subsys->type != NVME_NQN_NVME;
}
+static inline bool nvmet_is_pci_ctrl(struct nvmet_ctrl *ctrl)
+{
+ return ctrl->port->disc_addr.trtype == NVMF_TRTYPE_PCI;
+}
+
#ifdef CONFIG_NVME_TARGET_PASSTHRU
void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys);
int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys);
@@ -670,6 +781,41 @@ void nvmet_passthrough_override_cap(struct nvmet_ctrl *ctrl);
u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
u16 nvmet_report_invalid_opcode(struct nvmet_req *req);
+static inline bool nvmet_cc_en(u32 cc)
+{
+ return (cc & NVME_CC_ENABLE) >> NVME_CC_EN_SHIFT;
+}
+
+static inline u8 nvmet_cc_css(u32 cc)
+{
+ return (cc & NVME_CC_CSS_MASK) >> NVME_CC_CSS_SHIFT;
+}
+
+static inline u8 nvmet_cc_mps(u32 cc)
+{
+ return (cc & NVME_CC_MPS_MASK) >> NVME_CC_MPS_SHIFT;
+}
+
+static inline u8 nvmet_cc_ams(u32 cc)
+{
+ return (cc & NVME_CC_AMS_MASK) >> NVME_CC_AMS_SHIFT;
+}
+
+static inline u8 nvmet_cc_shn(u32 cc)
+{
+ return (cc & NVME_CC_SHN_MASK) >> NVME_CC_SHN_SHIFT;
+}
+
+static inline u8 nvmet_cc_iosqes(u32 cc)
+{
+ return (cc & NVME_CC_IOSQES_MASK) >> NVME_CC_IOSQES_SHIFT;
+}
+
+static inline u8 nvmet_cc_iocqes(u32 cc)
+{
+ return (cc & NVME_CC_IOCQES_MASK) >> NVME_CC_IOCQES_SHIFT;
+}
+
/* Convert a 32-bit number to a 16-bit 0's based number */
static inline __le16 to0based(u32 a)
{
@@ -706,12 +852,14 @@ static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio)
}
#ifdef CONFIG_NVME_TARGET_AUTH
+u32 nvmet_auth_send_data_len(struct nvmet_req *req);
void nvmet_execute_auth_send(struct nvmet_req *req);
+u32 nvmet_auth_receive_data_len(struct nvmet_req *req);
void nvmet_execute_auth_receive(struct nvmet_req *req);
int nvmet_auth_set_key(struct nvmet_host *host, const char *secret,
bool set_ctrl);
int nvmet_auth_set_host_hash(struct nvmet_host *host, const char *hash);
-int nvmet_setup_auth(struct nvmet_ctrl *ctrl);
+u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl);
void nvmet_auth_sq_init(struct nvmet_sq *sq);
void nvmet_destroy_auth(struct nvmet_ctrl *ctrl);
void nvmet_auth_sq_free(struct nvmet_sq *sq);
@@ -730,7 +878,7 @@ int nvmet_auth_ctrl_exponential(struct nvmet_req *req,
int nvmet_auth_ctrl_sesskey(struct nvmet_req *req,
u8 *buf, int buf_size);
#else
-static inline int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
+static inline u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl)
{
return 0;
}
@@ -750,4 +898,40 @@ static inline bool nvmet_has_auth(struct nvmet_ctrl *ctrl)
static inline const char *nvmet_dhchap_dhgroup_name(u8 dhgid) { return NULL; }
#endif
+int nvmet_pr_init_ns(struct nvmet_ns *ns);
+u16 nvmet_parse_pr_cmd(struct nvmet_req *req);
+u16 nvmet_pr_check_cmd_access(struct nvmet_req *req);
+int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl);
+void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl);
+void nvmet_pr_exit_ns(struct nvmet_ns *ns);
+void nvmet_execute_get_log_page_resv(struct nvmet_req *req);
+u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask);
+u16 nvmet_get_feat_resv_notif_mask(struct nvmet_req *req);
+u16 nvmet_pr_get_ns_pc_ref(struct nvmet_req *req);
+static inline void nvmet_pr_put_ns_pc_ref(struct nvmet_pr_per_ctrl_ref *pc_ref)
+{
+ percpu_ref_put(&pc_ref->ref);
+}
+
+/*
+ * Data for the get_feature() and set_feature() operations of PCI target
+ * controllers.
+ */
+struct nvmet_feat_irq_coalesce {
+ u8 thr;
+ u8 time;
+};
+
+struct nvmet_feat_irq_config {
+ u16 iv;
+ bool cd;
+};
+
+struct nvmet_feat_arbitration {
+ u8 hpw;
+ u8 mpw;
+ u8 lpw;
+ u8 ab;
+};
+
#endif /* _NVMET_H */
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index f2d963e1fe94..26e2907ce8bb 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -13,7 +13,7 @@
#include "../host/nvme.h"
#include "nvmet.h"
-MODULE_IMPORT_NS(NVME_TARGET_PASSTHRU);
+MODULE_IMPORT_NS("NVME_TARGET_PASSTHRU");
/*
* xarray to maintain one passthru subsystem per nvme controller.
@@ -132,7 +132,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
id->sqes = min_t(__u8, ((0x6 << 4) | 0x6), id->sqes);
id->cqes = min_t(__u8, ((0x4 << 4) | 0x4), id->cqes);
- id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+ id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
/* don't support fuse commands */
id->fuses = 0;
@@ -226,13 +226,13 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
req->cmd->common.opcode == nvme_admin_identify) {
switch (req->cmd->identify.cns) {
case NVME_ID_CNS_CTRL:
- nvmet_passthru_override_id_ctrl(req);
+ status = nvmet_passthru_override_id_ctrl(req);
break;
case NVME_ID_CNS_NS:
- nvmet_passthru_override_id_ns(req);
+ status = nvmet_passthru_override_id_ns(req);
break;
case NVME_ID_CNS_NS_DESC_LIST:
- nvmet_passthru_override_id_descs(req);
+ status = nvmet_passthru_override_id_descs(req);
break;
}
} else if (status < 0)
@@ -261,6 +261,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
{
struct scatterlist *sg;
struct bio *bio;
+ int ret = -EINVAL;
int i;
if (req->sg_cnt > BIO_MAX_VECS)
@@ -277,16 +278,19 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
}
for_each_sg(req->sg, sg, req->sg_cnt, i) {
- if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length,
- sg->offset) < sg->length) {
- nvmet_req_bio_put(req, bio);
- return -EINVAL;
- }
+ if (bio_add_page(bio, sg_page(sg), sg->length, sg->offset) <
+ sg->length)
+ goto out_bio_put;
}
- blk_rq_bio_prep(rq, bio, req->sg_cnt);
-
+ ret = blk_rq_append_bio(rq, bio);
+ if (ret)
+ goto out_bio_put;
return 0;
+
+out_bio_put:
+ nvmet_req_bio_put(req, bio);
+ return ret;
}
static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
@@ -306,7 +310,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
ns = nvme_find_get_ns(ctrl, nsid);
if (unlikely(!ns)) {
pr_err("failed to get passthru ns nsid:%u\n", nsid);
- status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
goto out;
}
@@ -426,7 +430,7 @@ u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
* emulated in the future if regular targets grow support for
* this feature.
*/
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
return nvmet_setup_passthru_command(req);
@@ -478,7 +482,7 @@ static u16 nvmet_passthru_get_set_features(struct nvmet_req *req)
case NVME_FEAT_RESV_PERSIST:
/* No reservations, see nvmet_parse_passthru_io_cmd() */
default:
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
}
}
@@ -535,10 +539,6 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
break;
case nvme_admin_identify:
switch (req->cmd->identify.cns) {
- case NVME_ID_CNS_CTRL:
- req->execute = nvmet_passthru_execute_cmd;
- req->p.use_workqueue = true;
- return NVME_SC_SUCCESS;
case NVME_ID_CNS_CS_CTRL:
switch (req->cmd->identify.csi) {
case NVME_CSI_ZNS:
@@ -546,8 +546,10 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
req->p.use_workqueue = true;
return NVME_SC_SUCCESS;
}
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ case NVME_ID_CNS_CTRL:
case NVME_ID_CNS_NS:
+ case NVME_ID_CNS_NS_DESC_LIST:
req->execute = nvmet_passthru_execute_cmd;
req->p.use_workqueue = true;
return NVME_SC_SUCCESS;
@@ -558,7 +560,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
req->p.use_workqueue = true;
return NVME_SC_SUCCESS;
}
- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
default:
return nvmet_setup_passthru_command(req);
}
diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
new file mode 100644
index 000000000000..b1e31483f157
--- /dev/null
+++ b/drivers/nvme/target/pci-epf.c
@@ -0,0 +1,2610 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe PCI Endpoint Function target driver.
+ *
+ * Copyright (c) 2024, Western Digital Corporation or its affiliates.
+ * Copyright (c) 2024, Rick Wertenbroek <rick.wertenbroek@gmail.com>
+ * REDS Institute, HEIG-VD, HES-SO, Switzerland
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/io.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/nvme.h>
+#include <linux/pci_ids.h>
+#include <linux/pci-epc.h>
+#include <linux/pci-epf.h>
+#include <linux/pci_regs.h>
+#include <linux/slab.h>
+
+#include "nvmet.h"
+
+static LIST_HEAD(nvmet_pci_epf_ports);
+static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex);
+
+/*
+ * Default and maximum allowed data transfer size. For the default,
+ * allow up to 128 page-sized segments. For the maximum allowed,
+ * use 4 times the default (which is completely arbitrary).
+ */
+#define NVMET_PCI_EPF_MAX_SEGS 128
+#define NVMET_PCI_EPF_MDTS_KB \
+ (NVMET_PCI_EPF_MAX_SEGS << (PAGE_SHIFT - 10))
+#define NVMET_PCI_EPF_MAX_MDTS_KB (NVMET_PCI_EPF_MDTS_KB * 4)
+
+/*
+ * IRQ vector coalescing threshold: by default, post 8 CQEs before raising an
+ * interrupt vector to the host. This default 8 is completely arbitrary and can
+ * be changed by the host with a nvme_set_features command.
+ */
+#define NVMET_PCI_EPF_IV_THRESHOLD 8
+
+/*
+ * BAR CC register and SQ polling intervals.
+ */
+#define NVMET_PCI_EPF_CC_POLL_INTERVAL msecs_to_jiffies(10)
+#define NVMET_PCI_EPF_SQ_POLL_INTERVAL msecs_to_jiffies(5)
+#define NVMET_PCI_EPF_SQ_POLL_IDLE msecs_to_jiffies(5000)
+
+/*
+ * SQ arbitration burst default: fetch at most 8 commands at a time from an SQ.
+ */
+#define NVMET_PCI_EPF_SQ_AB 8
+
+/*
+ * Handling of CQs is normally immediate, unless we fail to map a CQ or the CQ
+ * is full, in which case we retry the CQ processing after this interval.
+ */
+#define NVMET_PCI_EPF_CQ_RETRY_INTERVAL msecs_to_jiffies(1)
+
+enum nvmet_pci_epf_queue_flags {
+ NVMET_PCI_EPF_Q_IS_SQ = 0, /* The queue is a submission queue */
+ NVMET_PCI_EPF_Q_LIVE, /* The queue is live */
+ NVMET_PCI_EPF_Q_IRQ_ENABLED, /* IRQ is enabled for this queue */
+};
+
+/*
+ * IRQ vector descriptor.
+ */
+struct nvmet_pci_epf_irq_vector {
+ unsigned int vector;
+ unsigned int ref;
+ bool cd;
+ int nr_irqs;
+};
+
+struct nvmet_pci_epf_queue {
+ union {
+ struct nvmet_sq nvme_sq;
+ struct nvmet_cq nvme_cq;
+ };
+ struct nvmet_pci_epf_ctrl *ctrl;
+ unsigned long flags;
+
+ u64 pci_addr;
+ size_t pci_size;
+ struct pci_epc_map pci_map;
+
+ u16 qid;
+ u16 depth;
+ u16 vector;
+ u16 head;
+ u16 tail;
+ u16 phase;
+ u32 db;
+
+ size_t qes;
+
+ struct nvmet_pci_epf_irq_vector *iv;
+ struct workqueue_struct *iod_wq;
+ struct delayed_work work;
+ spinlock_t lock;
+ struct list_head list;
+};
+
+/*
+ * PCI Root Complex (RC) address data segment for mapping an admin or
+ * I/O command buffer @buf of @length bytes to the PCI address @pci_addr.
+ */
+struct nvmet_pci_epf_segment {
+ void *buf;
+ u64 pci_addr;
+ u32 length;
+};
+
+/*
+ * Command descriptors.
+ */
+struct nvmet_pci_epf_iod {
+ struct list_head link;
+
+ struct nvmet_req req;
+ struct nvme_command cmd;
+ struct nvme_completion cqe;
+ unsigned int status;
+
+ struct nvmet_pci_epf_ctrl *ctrl;
+
+ struct nvmet_pci_epf_queue *sq;
+ struct nvmet_pci_epf_queue *cq;
+
+ /* Data transfer size and direction for the command. */
+ size_t data_len;
+ enum dma_data_direction dma_dir;
+
+ /*
+ * PCI Root Complex (RC) address data segments: if nr_data_segs is 1, we
+ * use only @data_seg. Otherwise, the array of segments @data_segs is
+ * allocated to manage multiple PCI address data segments. @data_sgl and
+ * @data_sgt are used to setup the command request for execution by the
+ * target core.
+ */
+ unsigned int nr_data_segs;
+ struct nvmet_pci_epf_segment data_seg;
+ struct nvmet_pci_epf_segment *data_segs;
+ struct scatterlist data_sgl;
+ struct sg_table data_sgt;
+
+ struct work_struct work;
+ struct completion done;
+};
+
+/*
+ * PCI target controller private data.
+ */
+struct nvmet_pci_epf_ctrl {
+ struct nvmet_pci_epf *nvme_epf;
+ struct nvmet_port *port;
+ struct nvmet_ctrl *tctrl;
+ struct device *dev;
+
+ unsigned int nr_queues;
+ struct nvmet_pci_epf_queue *sq;
+ struct nvmet_pci_epf_queue *cq;
+ unsigned int sq_ab;
+
+ mempool_t iod_pool;
+ void *bar;
+ u64 cap;
+ u32 cc;
+ u32 csts;
+
+ size_t io_sqes;
+ size_t io_cqes;
+
+ size_t mps_shift;
+ size_t mps;
+ size_t mps_mask;
+
+ unsigned int mdts;
+
+ struct delayed_work poll_cc;
+ struct delayed_work poll_sqs;
+
+ struct mutex irq_lock;
+ struct nvmet_pci_epf_irq_vector *irq_vectors;
+ unsigned int irq_vector_threshold;
+
+ bool link_up;
+ bool enabled;
+};
+
+/*
+ * PCI EPF driver private data.
+ */
+struct nvmet_pci_epf {
+ struct pci_epf *epf;
+
+ const struct pci_epc_features *epc_features;
+
+ void *reg_bar;
+ size_t msix_table_offset;
+
+ unsigned int irq_type;
+ unsigned int nr_vectors;
+
+ struct nvmet_pci_epf_ctrl ctrl;
+
+ bool dma_enabled;
+ struct dma_chan *dma_tx_chan;
+ struct mutex dma_tx_lock;
+ struct dma_chan *dma_rx_chan;
+ struct mutex dma_rx_lock;
+
+ struct mutex mmio_lock;
+
+ /* PCI endpoint function configfs attributes. */
+ struct config_group group;
+ __le16 portid;
+ char subsysnqn[NVMF_NQN_SIZE];
+ unsigned int mdts_kb;
+};
+
+static inline u32 nvmet_pci_epf_bar_read32(struct nvmet_pci_epf_ctrl *ctrl,
+ u32 off)
+{
+ __le32 *bar_reg = ctrl->bar + off;
+
+ return le32_to_cpu(READ_ONCE(*bar_reg));
+}
+
+static inline void nvmet_pci_epf_bar_write32(struct nvmet_pci_epf_ctrl *ctrl,
+ u32 off, u32 val)
+{
+ __le32 *bar_reg = ctrl->bar + off;
+
+ WRITE_ONCE(*bar_reg, cpu_to_le32(val));
+}
+
+static inline u64 nvmet_pci_epf_bar_read64(struct nvmet_pci_epf_ctrl *ctrl,
+ u32 off)
+{
+ return (u64)nvmet_pci_epf_bar_read32(ctrl, off) |
+ ((u64)nvmet_pci_epf_bar_read32(ctrl, off + 4) << 32);
+}
+
+static inline void nvmet_pci_epf_bar_write64(struct nvmet_pci_epf_ctrl *ctrl,
+ u32 off, u64 val)
+{
+ nvmet_pci_epf_bar_write32(ctrl, off, val & 0xFFFFFFFF);
+ nvmet_pci_epf_bar_write32(ctrl, off + 4, (val >> 32) & 0xFFFFFFFF);
+}
+
+static inline int nvmet_pci_epf_mem_map(struct nvmet_pci_epf *nvme_epf,
+ u64 pci_addr, size_t size, struct pci_epc_map *map)
+{
+ struct pci_epf *epf = nvme_epf->epf;
+
+ return pci_epc_mem_map(epf->epc, epf->func_no, epf->vfunc_no,
+ pci_addr, size, map);
+}
+
+static inline void nvmet_pci_epf_mem_unmap(struct nvmet_pci_epf *nvme_epf,
+ struct pci_epc_map *map)
+{
+ struct pci_epf *epf = nvme_epf->epf;
+
+ pci_epc_mem_unmap(epf->epc, epf->func_no, epf->vfunc_no, map);
+}
+
+struct nvmet_pci_epf_dma_filter {
+ struct device *dev;
+ u32 dma_mask;
+};
+
+static bool nvmet_pci_epf_dma_filter(struct dma_chan *chan, void *arg)
+{
+ struct nvmet_pci_epf_dma_filter *filter = arg;
+ struct dma_slave_caps caps;
+
+ memset(&caps, 0, sizeof(caps));
+ dma_get_slave_caps(chan, &caps);
+
+ return chan->device->dev == filter->dev &&
+ (filter->dma_mask & caps.directions);
+}
+
+static void nvmet_pci_epf_init_dma(struct nvmet_pci_epf *nvme_epf)
+{
+ struct pci_epf *epf = nvme_epf->epf;
+ struct device *dev = &epf->dev;
+ struct nvmet_pci_epf_dma_filter filter;
+ struct dma_chan *chan;
+ dma_cap_mask_t mask;
+
+ mutex_init(&nvme_epf->dma_rx_lock);
+ mutex_init(&nvme_epf->dma_tx_lock);
+
+ dma_cap_zero(mask);
+ dma_cap_set(DMA_SLAVE, mask);
+
+ filter.dev = epf->epc->dev.parent;
+ filter.dma_mask = BIT(DMA_DEV_TO_MEM);
+
+ chan = dma_request_channel(mask, nvmet_pci_epf_dma_filter, &filter);
+ if (!chan)
+ goto out_dma_no_rx;
+
+ nvme_epf->dma_rx_chan = chan;
+
+ filter.dma_mask = BIT(DMA_MEM_TO_DEV);
+ chan = dma_request_channel(mask, nvmet_pci_epf_dma_filter, &filter);
+ if (!chan)
+ goto out_dma_no_tx;
+
+ nvme_epf->dma_tx_chan = chan;
+
+ nvme_epf->dma_enabled = true;
+
+ dev_dbg(dev, "Using DMA RX channel %s, maximum segment size %u B\n",
+ dma_chan_name(chan),
+ dma_get_max_seg_size(dmaengine_get_dma_device(chan)));
+
+ dev_dbg(dev, "Using DMA TX channel %s, maximum segment size %u B\n",
+ dma_chan_name(chan),
+ dma_get_max_seg_size(dmaengine_get_dma_device(chan)));
+
+ return;
+
+out_dma_no_tx:
+ dma_release_channel(nvme_epf->dma_rx_chan);
+ nvme_epf->dma_rx_chan = NULL;
+
+out_dma_no_rx:
+ mutex_destroy(&nvme_epf->dma_rx_lock);
+ mutex_destroy(&nvme_epf->dma_tx_lock);
+ nvme_epf->dma_enabled = false;
+
+ dev_info(&epf->dev, "DMA not supported, falling back to MMIO\n");
+}
+
+static void nvmet_pci_epf_deinit_dma(struct nvmet_pci_epf *nvme_epf)
+{
+ if (!nvme_epf->dma_enabled)
+ return;
+
+ dma_release_channel(nvme_epf->dma_tx_chan);
+ nvme_epf->dma_tx_chan = NULL;
+ dma_release_channel(nvme_epf->dma_rx_chan);
+ nvme_epf->dma_rx_chan = NULL;
+ mutex_destroy(&nvme_epf->dma_rx_lock);
+ mutex_destroy(&nvme_epf->dma_tx_lock);
+ nvme_epf->dma_enabled = false;
+}
+
+static int nvmet_pci_epf_dma_transfer(struct nvmet_pci_epf *nvme_epf,
+ struct nvmet_pci_epf_segment *seg, enum dma_data_direction dir)
+{
+ struct pci_epf *epf = nvme_epf->epf;
+ struct dma_async_tx_descriptor *desc;
+ struct dma_slave_config sconf = {};
+ struct device *dev = &epf->dev;
+ struct device *dma_dev;
+ struct dma_chan *chan;
+ dma_cookie_t cookie;
+ dma_addr_t dma_addr;
+ struct mutex *lock;
+ int ret;
+
+ switch (dir) {
+ case DMA_FROM_DEVICE:
+ lock = &nvme_epf->dma_rx_lock;
+ chan = nvme_epf->dma_rx_chan;
+ sconf.direction = DMA_DEV_TO_MEM;
+ sconf.src_addr = seg->pci_addr;
+ break;
+ case DMA_TO_DEVICE:
+ lock = &nvme_epf->dma_tx_lock;
+ chan = nvme_epf->dma_tx_chan;
+ sconf.direction = DMA_MEM_TO_DEV;
+ sconf.dst_addr = seg->pci_addr;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ mutex_lock(lock);
+
+ dma_dev = dmaengine_get_dma_device(chan);
+ dma_addr = dma_map_single(dma_dev, seg->buf, seg->length, dir);
+ ret = dma_mapping_error(dma_dev, dma_addr);
+ if (ret)
+ goto unlock;
+
+ ret = dmaengine_slave_config(chan, &sconf);
+ if (ret) {
+ dev_err(dev, "Failed to configure DMA channel\n");
+ goto unmap;
+ }
+
+ desc = dmaengine_prep_slave_single(chan, dma_addr, seg->length,
+ sconf.direction, DMA_CTRL_ACK);
+ if (!desc) {
+ dev_err(dev, "Failed to prepare DMA\n");
+ ret = -EIO;
+ goto unmap;
+ }
+
+ cookie = dmaengine_submit(desc);
+ ret = dma_submit_error(cookie);
+ if (ret) {
+ dev_err(dev, "Failed to do DMA submit (err=%d)\n", ret);
+ goto unmap;
+ }
+
+ if (dma_sync_wait(chan, cookie) != DMA_COMPLETE) {
+ dev_err(dev, "DMA transfer failed\n");
+ ret = -EIO;
+ }
+
+ dmaengine_terminate_sync(chan);
+
+unmap:
+ dma_unmap_single(dma_dev, dma_addr, seg->length, dir);
+
+unlock:
+ mutex_unlock(lock);
+
+ return ret;
+}
+
+static int nvmet_pci_epf_mmio_transfer(struct nvmet_pci_epf *nvme_epf,
+ struct nvmet_pci_epf_segment *seg, enum dma_data_direction dir)
+{
+ u64 pci_addr = seg->pci_addr;
+ u32 length = seg->length;
+ void *buf = seg->buf;
+ struct pci_epc_map map;
+ int ret = -EINVAL;
+
+ /*
+ * Note: MMIO transfers do not need serialization but this is a
+ * simple way to avoid using too many mapping windows.
+ */
+ mutex_lock(&nvme_epf->mmio_lock);
+
+ while (length) {
+ ret = nvmet_pci_epf_mem_map(nvme_epf, pci_addr, length, &map);
+ if (ret)
+ break;
+
+ switch (dir) {
+ case DMA_FROM_DEVICE:
+ memcpy_fromio(buf, map.virt_addr, map.pci_size);
+ break;
+ case DMA_TO_DEVICE:
+ memcpy_toio(map.virt_addr, buf, map.pci_size);
+ break;
+ default:
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ pci_addr += map.pci_size;
+ buf += map.pci_size;
+ length -= map.pci_size;
+
+ nvmet_pci_epf_mem_unmap(nvme_epf, &map);
+ }
+
+unlock:
+ mutex_unlock(&nvme_epf->mmio_lock);
+
+ return ret;
+}
+
+static inline int nvmet_pci_epf_transfer_seg(struct nvmet_pci_epf *nvme_epf,
+ struct nvmet_pci_epf_segment *seg, enum dma_data_direction dir)
+{
+ if (nvme_epf->dma_enabled)
+ return nvmet_pci_epf_dma_transfer(nvme_epf, seg, dir);
+
+ return nvmet_pci_epf_mmio_transfer(nvme_epf, seg, dir);
+}
+
+static inline int nvmet_pci_epf_transfer(struct nvmet_pci_epf_ctrl *ctrl,
+ void *buf, u64 pci_addr, u32 length,
+ enum dma_data_direction dir)
+{
+ struct nvmet_pci_epf_segment seg = {
+ .buf = buf,
+ .pci_addr = pci_addr,
+ .length = length,
+ };
+
+ return nvmet_pci_epf_transfer_seg(ctrl->nvme_epf, &seg, dir);
+}
+
+static int nvmet_pci_epf_alloc_irq_vectors(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ ctrl->irq_vectors = kcalloc(ctrl->nr_queues,
+ sizeof(struct nvmet_pci_epf_irq_vector),
+ GFP_KERNEL);
+ if (!ctrl->irq_vectors)
+ return -ENOMEM;
+
+ mutex_init(&ctrl->irq_lock);
+
+ return 0;
+}
+
+static void nvmet_pci_epf_free_irq_vectors(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ if (ctrl->irq_vectors) {
+ mutex_destroy(&ctrl->irq_lock);
+ kfree(ctrl->irq_vectors);
+ ctrl->irq_vectors = NULL;
+ }
+}
+
+static struct nvmet_pci_epf_irq_vector *
+nvmet_pci_epf_find_irq_vector(struct nvmet_pci_epf_ctrl *ctrl, u16 vector)
+{
+ struct nvmet_pci_epf_irq_vector *iv;
+ int i;
+
+ lockdep_assert_held(&ctrl->irq_lock);
+
+ for (i = 0; i < ctrl->nr_queues; i++) {
+ iv = &ctrl->irq_vectors[i];
+ if (iv->ref && iv->vector == vector)
+ return iv;
+ }
+
+ return NULL;
+}
+
+static struct nvmet_pci_epf_irq_vector *
+nvmet_pci_epf_add_irq_vector(struct nvmet_pci_epf_ctrl *ctrl, u16 vector)
+{
+ struct nvmet_pci_epf_irq_vector *iv;
+ int i;
+
+ mutex_lock(&ctrl->irq_lock);
+
+ iv = nvmet_pci_epf_find_irq_vector(ctrl, vector);
+ if (iv) {
+ iv->ref++;
+ goto unlock;
+ }
+
+ for (i = 0; i < ctrl->nr_queues; i++) {
+ iv = &ctrl->irq_vectors[i];
+ if (!iv->ref)
+ break;
+ }
+
+ if (WARN_ON_ONCE(!iv))
+ goto unlock;
+
+ iv->ref = 1;
+ iv->vector = vector;
+ iv->nr_irqs = 0;
+
+unlock:
+ mutex_unlock(&ctrl->irq_lock);
+
+ return iv;
+}
+
+static void nvmet_pci_epf_remove_irq_vector(struct nvmet_pci_epf_ctrl *ctrl,
+ u16 vector)
+{
+ struct nvmet_pci_epf_irq_vector *iv;
+
+ mutex_lock(&ctrl->irq_lock);
+
+ iv = nvmet_pci_epf_find_irq_vector(ctrl, vector);
+ if (iv) {
+ iv->ref--;
+ if (!iv->ref) {
+ iv->vector = 0;
+ iv->nr_irqs = 0;
+ }
+ }
+
+ mutex_unlock(&ctrl->irq_lock);
+}
+
+static bool nvmet_pci_epf_should_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_queue *cq, bool force)
+{
+ struct nvmet_pci_epf_irq_vector *iv = cq->iv;
+ bool ret;
+
+ if (!test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+ return false;
+
+ /* IRQ coalescing for the admin queue is not allowed. */
+ if (!cq->qid)
+ return true;
+
+ if (iv->cd)
+ return true;
+
+ if (force) {
+ ret = iv->nr_irqs > 0;
+ } else {
+ iv->nr_irqs++;
+ ret = iv->nr_irqs >= ctrl->irq_vector_threshold;
+ }
+ if (ret)
+ iv->nr_irqs = 0;
+
+ return ret;
+}
+
+static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_queue *cq, bool force)
+{
+ struct nvmet_pci_epf *nvme_epf = ctrl->nvme_epf;
+ struct pci_epf *epf = nvme_epf->epf;
+ int ret = 0;
+
+ if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
+ return;
+
+ mutex_lock(&ctrl->irq_lock);
+
+ if (!nvmet_pci_epf_should_raise_irq(ctrl, cq, force))
+ goto unlock;
+
+ switch (nvme_epf->irq_type) {
+ case PCI_IRQ_MSIX:
+ case PCI_IRQ_MSI:
+ ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
+ nvme_epf->irq_type, cq->vector + 1);
+ if (!ret)
+ break;
+ /*
+ * If we got an error, it is likely because the host is using
+ * legacy IRQs (e.g. BIOS, grub).
+ */
+ fallthrough;
+ case PCI_IRQ_INTX:
+ ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
+ PCI_IRQ_INTX, 0);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ ret = -EINVAL;
+ break;
+ }
+
+ if (ret)
+ dev_err(ctrl->dev, "Failed to raise IRQ (err=%d)\n", ret);
+
+unlock:
+ mutex_unlock(&ctrl->irq_lock);
+}
+
+static inline const char *nvmet_pci_epf_iod_name(struct nvmet_pci_epf_iod *iod)
+{
+ return nvme_opcode_str(iod->sq->qid, iod->cmd.common.opcode);
+}
+
+static void nvmet_pci_epf_exec_iod_work(struct work_struct *work);
+
+static struct nvmet_pci_epf_iod *
+nvmet_pci_epf_alloc_iod(struct nvmet_pci_epf_queue *sq)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = sq->ctrl;
+ struct nvmet_pci_epf_iod *iod;
+
+ iod = mempool_alloc(&ctrl->iod_pool, GFP_KERNEL);
+ if (unlikely(!iod))
+ return NULL;
+
+ memset(iod, 0, sizeof(*iod));
+ iod->req.cmd = &iod->cmd;
+ iod->req.cqe = &iod->cqe;
+ iod->req.port = ctrl->port;
+ iod->ctrl = ctrl;
+ iod->sq = sq;
+ iod->cq = &ctrl->cq[sq->qid];
+ INIT_LIST_HEAD(&iod->link);
+ iod->dma_dir = DMA_NONE;
+ INIT_WORK(&iod->work, nvmet_pci_epf_exec_iod_work);
+ init_completion(&iod->done);
+
+ return iod;
+}
+
+/*
+ * Allocate or grow a command table of PCI segments.
+ */
+static int nvmet_pci_epf_alloc_iod_data_segs(struct nvmet_pci_epf_iod *iod,
+ int nsegs)
+{
+ struct nvmet_pci_epf_segment *segs;
+ int nr_segs = iod->nr_data_segs + nsegs;
+
+ segs = krealloc(iod->data_segs,
+ nr_segs * sizeof(struct nvmet_pci_epf_segment),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!segs)
+ return -ENOMEM;
+
+ iod->nr_data_segs = nr_segs;
+ iod->data_segs = segs;
+
+ return 0;
+}
+
+static void nvmet_pci_epf_free_iod(struct nvmet_pci_epf_iod *iod)
+{
+ int i;
+
+ if (iod->data_segs) {
+ for (i = 0; i < iod->nr_data_segs; i++)
+ kfree(iod->data_segs[i].buf);
+ if (iod->data_segs != &iod->data_seg)
+ kfree(iod->data_segs);
+ }
+ if (iod->data_sgt.nents > 1)
+ sg_free_table(&iod->data_sgt);
+ mempool_free(iod, &iod->ctrl->iod_pool);
+}
+
+static int nvmet_pci_epf_transfer_iod_data(struct nvmet_pci_epf_iod *iod)
+{
+ struct nvmet_pci_epf *nvme_epf = iod->ctrl->nvme_epf;
+ struct nvmet_pci_epf_segment *seg = &iod->data_segs[0];
+ int i, ret;
+
+ /* Split the data transfer according to the PCI segments. */
+ for (i = 0; i < iod->nr_data_segs; i++, seg++) {
+ ret = nvmet_pci_epf_transfer_seg(nvme_epf, seg, iod->dma_dir);
+ if (ret) {
+ iod->status = NVME_SC_DATA_XFER_ERROR | NVME_STATUS_DNR;
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static inline u32 nvmet_pci_epf_prp_ofst(struct nvmet_pci_epf_ctrl *ctrl,
+ u64 prp)
+{
+ return prp & ctrl->mps_mask;
+}
+
+static inline size_t nvmet_pci_epf_prp_size(struct nvmet_pci_epf_ctrl *ctrl,
+ u64 prp)
+{
+ return ctrl->mps - nvmet_pci_epf_prp_ofst(ctrl, prp);
+}
+
+/*
+ * Transfer a PRP list from the host and return the number of prps.
+ */
+static int nvmet_pci_epf_get_prp_list(struct nvmet_pci_epf_ctrl *ctrl, u64 prp,
+ size_t xfer_len, __le64 *prps)
+{
+ size_t nr_prps = (xfer_len + ctrl->mps_mask) >> ctrl->mps_shift;
+ u32 length;
+ int ret;
+
+ /*
+ * Compute the number of PRPs required for the number of bytes to
+ * transfer (xfer_len). If this number overflows the memory page size
+ * with the PRP list pointer specified, only return the space available
+ * in the memory page, the last PRP in there will be a PRP list pointer
+ * to the remaining PRPs.
+ */
+ length = min(nvmet_pci_epf_prp_size(ctrl, prp), nr_prps << 3);
+ ret = nvmet_pci_epf_transfer(ctrl, prps, prp, length, DMA_FROM_DEVICE);
+ if (ret)
+ return ret;
+
+ return length >> 3;
+}
+
+static int nvmet_pci_epf_iod_parse_prp_list(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_iod *iod)
+{
+ struct nvme_command *cmd = &iod->cmd;
+ struct nvmet_pci_epf_segment *seg;
+ size_t size = 0, ofst, prp_size, xfer_len;
+ size_t transfer_len = iod->data_len;
+ int nr_segs, nr_prps = 0;
+ u64 pci_addr, prp;
+ int i = 0, ret;
+ __le64 *prps;
+
+ prps = kzalloc(ctrl->mps, GFP_KERNEL);
+ if (!prps)
+ goto err_internal;
+
+ /*
+ * Allocate PCI segments for the command: this considers the worst case
+ * scenario where all prps are discontiguous, so get as many segments
+ * as we can have prps. In practice, most of the time, we will have
+ * far less PCI segments than prps.
+ */
+ prp = le64_to_cpu(cmd->common.dptr.prp1);
+ if (!prp)
+ goto err_invalid_field;
+
+ ofst = nvmet_pci_epf_prp_ofst(ctrl, prp);
+ nr_segs = (transfer_len + ofst + ctrl->mps - 1) >> ctrl->mps_shift;
+
+ ret = nvmet_pci_epf_alloc_iod_data_segs(iod, nr_segs);
+ if (ret)
+ goto err_internal;
+
+ /* Set the first segment using prp1. */
+ seg = &iod->data_segs[0];
+ seg->pci_addr = prp;
+ seg->length = nvmet_pci_epf_prp_size(ctrl, prp);
+
+ size = seg->length;
+ pci_addr = prp + size;
+ nr_segs = 1;
+
+ /*
+ * Now build the PCI address segments using the PRP lists, starting
+ * from prp2.
+ */
+ prp = le64_to_cpu(cmd->common.dptr.prp2);
+ if (!prp)
+ goto err_invalid_field;
+
+ while (size < transfer_len) {
+ xfer_len = transfer_len - size;
+
+ if (!nr_prps) {
+ nr_prps = nvmet_pci_epf_get_prp_list(ctrl, prp,
+ xfer_len, prps);
+ if (nr_prps < 0)
+ goto err_internal;
+
+ i = 0;
+ ofst = 0;
+ }
+
+ /* Current entry */
+ prp = le64_to_cpu(prps[i]);
+ if (!prp)
+ goto err_invalid_field;
+
+ /* Did we reach the last PRP entry of the list? */
+ if (xfer_len > ctrl->mps && i == nr_prps - 1) {
+ /* We need more PRPs: PRP is a list pointer. */
+ nr_prps = 0;
+ continue;
+ }
+
+ /* Only the first PRP is allowed to have an offset. */
+ if (nvmet_pci_epf_prp_ofst(ctrl, prp))
+ goto err_invalid_offset;
+
+ if (prp != pci_addr) {
+ /* Discontiguous prp: new segment. */
+ nr_segs++;
+ if (WARN_ON_ONCE(nr_segs > iod->nr_data_segs))
+ goto err_internal;
+
+ seg++;
+ seg->pci_addr = prp;
+ seg->length = 0;
+ pci_addr = prp;
+ }
+
+ prp_size = min_t(size_t, ctrl->mps, xfer_len);
+ seg->length += prp_size;
+ pci_addr += prp_size;
+ size += prp_size;
+
+ i++;
+ }
+
+ iod->nr_data_segs = nr_segs;
+ ret = 0;
+
+ if (size != transfer_len) {
+ dev_err(ctrl->dev,
+ "PRPs transfer length mismatch: got %zu B, need %zu B\n",
+ size, transfer_len);
+ goto err_internal;
+ }
+
+ kfree(prps);
+
+ return 0;
+
+err_invalid_offset:
+ dev_err(ctrl->dev, "PRPs list invalid offset\n");
+ iod->status = NVME_SC_PRP_INVALID_OFFSET | NVME_STATUS_DNR;
+ goto err;
+
+err_invalid_field:
+ dev_err(ctrl->dev, "PRPs list invalid field\n");
+ iod->status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto err;
+
+err_internal:
+ dev_err(ctrl->dev, "PRPs list internal error\n");
+ iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+
+err:
+ kfree(prps);
+ return -EINVAL;
+}
+
+static int nvmet_pci_epf_iod_parse_prp_simple(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_iod *iod)
+{
+ struct nvme_command *cmd = &iod->cmd;
+ size_t transfer_len = iod->data_len;
+ int ret, nr_segs = 1;
+ u64 prp1, prp2 = 0;
+ size_t prp1_size;
+
+ prp1 = le64_to_cpu(cmd->common.dptr.prp1);
+ prp1_size = nvmet_pci_epf_prp_size(ctrl, prp1);
+
+ /* For commands crossing a page boundary, we should have prp2. */
+ if (transfer_len > prp1_size) {
+ prp2 = le64_to_cpu(cmd->common.dptr.prp2);
+ if (!prp2) {
+ iod->status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ return -EINVAL;
+ }
+ if (nvmet_pci_epf_prp_ofst(ctrl, prp2)) {
+ iod->status =
+ NVME_SC_PRP_INVALID_OFFSET | NVME_STATUS_DNR;
+ return -EINVAL;
+ }
+ if (prp2 != prp1 + prp1_size)
+ nr_segs = 2;
+ }
+
+ if (nr_segs == 1) {
+ iod->nr_data_segs = 1;
+ iod->data_segs = &iod->data_seg;
+ iod->data_segs[0].pci_addr = prp1;
+ iod->data_segs[0].length = transfer_len;
+ return 0;
+ }
+
+ ret = nvmet_pci_epf_alloc_iod_data_segs(iod, nr_segs);
+ if (ret) {
+ iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ return ret;
+ }
+
+ iod->data_segs[0].pci_addr = prp1;
+ iod->data_segs[0].length = prp1_size;
+ iod->data_segs[1].pci_addr = prp2;
+ iod->data_segs[1].length = transfer_len - prp1_size;
+
+ return 0;
+}
+
+static int nvmet_pci_epf_iod_parse_prps(struct nvmet_pci_epf_iod *iod)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = iod->ctrl;
+ u64 prp1 = le64_to_cpu(iod->cmd.common.dptr.prp1);
+ size_t ofst;
+
+ /* Get the PCI address segments for the command using its PRPs. */
+ ofst = nvmet_pci_epf_prp_ofst(ctrl, prp1);
+ if (ofst & 0x3) {
+ iod->status = NVME_SC_PRP_INVALID_OFFSET | NVME_STATUS_DNR;
+ return -EINVAL;
+ }
+
+ if (iod->data_len + ofst <= ctrl->mps * 2)
+ return nvmet_pci_epf_iod_parse_prp_simple(ctrl, iod);
+
+ return nvmet_pci_epf_iod_parse_prp_list(ctrl, iod);
+}
+
+/*
+ * Transfer an SGL segment from the host and return the number of data
+ * descriptors and the next segment descriptor, if any.
+ */
+static struct nvme_sgl_desc *
+nvmet_pci_epf_get_sgl_segment(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvme_sgl_desc *desc, unsigned int *nr_sgls)
+{
+ struct nvme_sgl_desc *sgls;
+ u32 length = le32_to_cpu(desc->length);
+ int nr_descs, ret;
+ void *buf;
+
+ buf = kmalloc(length, GFP_KERNEL);
+ if (!buf)
+ return NULL;
+
+ ret = nvmet_pci_epf_transfer(ctrl, buf, le64_to_cpu(desc->addr), length,
+ DMA_FROM_DEVICE);
+ if (ret) {
+ kfree(buf);
+ return NULL;
+ }
+
+ sgls = buf;
+ nr_descs = length / sizeof(struct nvme_sgl_desc);
+ if (sgls[nr_descs - 1].type == (NVME_SGL_FMT_SEG_DESC << 4) ||
+ sgls[nr_descs - 1].type == (NVME_SGL_FMT_LAST_SEG_DESC << 4)) {
+ /*
+ * We have another SGL segment following this one: do not count
+ * it as a regular data SGL descriptor and return it to the
+ * caller.
+ */
+ *desc = sgls[nr_descs - 1];
+ nr_descs--;
+ } else {
+ /* We do not have another SGL segment after this one. */
+ desc->length = 0;
+ }
+
+ *nr_sgls = nr_descs;
+
+ return sgls;
+}
+
+static int nvmet_pci_epf_iod_parse_sgl_segments(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_iod *iod)
+{
+ struct nvme_command *cmd = &iod->cmd;
+ struct nvme_sgl_desc seg = cmd->common.dptr.sgl;
+ struct nvme_sgl_desc *sgls = NULL;
+ int n = 0, i, nr_sgls;
+ int ret;
+
+ /*
+ * We do not support inline data nor keyed SGLs, so we should be seeing
+ * only segment descriptors.
+ */
+ if (seg.type != (NVME_SGL_FMT_SEG_DESC << 4) &&
+ seg.type != (NVME_SGL_FMT_LAST_SEG_DESC << 4)) {
+ iod->status = NVME_SC_SGL_INVALID_TYPE | NVME_STATUS_DNR;
+ return -EIO;
+ }
+
+ while (seg.length) {
+ sgls = nvmet_pci_epf_get_sgl_segment(ctrl, &seg, &nr_sgls);
+ if (!sgls) {
+ iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ return -EIO;
+ }
+
+ /* Grow the PCI segment table as needed. */
+ ret = nvmet_pci_epf_alloc_iod_data_segs(iod, nr_sgls);
+ if (ret) {
+ iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ /*
+ * Parse the SGL descriptors to build the PCI segment table,
+ * checking the descriptor type as we go.
+ */
+ for (i = 0; i < nr_sgls; i++) {
+ if (sgls[i].type != (NVME_SGL_FMT_DATA_DESC << 4)) {
+ iod->status = NVME_SC_SGL_INVALID_TYPE |
+ NVME_STATUS_DNR;
+ goto out;
+ }
+ iod->data_segs[n].pci_addr = le64_to_cpu(sgls[i].addr);
+ iod->data_segs[n].length = le32_to_cpu(sgls[i].length);
+ n++;
+ }
+
+ kfree(sgls);
+ }
+
+ out:
+ if (iod->status != NVME_SC_SUCCESS) {
+ kfree(sgls);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int nvmet_pci_epf_iod_parse_sgls(struct nvmet_pci_epf_iod *iod)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = iod->ctrl;
+ struct nvme_sgl_desc *sgl = &iod->cmd.common.dptr.sgl;
+
+ if (sgl->type == (NVME_SGL_FMT_DATA_DESC << 4)) {
+ /* Single data descriptor case. */
+ iod->nr_data_segs = 1;
+ iod->data_segs = &iod->data_seg;
+ iod->data_seg.pci_addr = le64_to_cpu(sgl->addr);
+ iod->data_seg.length = le32_to_cpu(sgl->length);
+ return 0;
+ }
+
+ return nvmet_pci_epf_iod_parse_sgl_segments(ctrl, iod);
+}
+
+static int nvmet_pci_epf_alloc_iod_data_buf(struct nvmet_pci_epf_iod *iod)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = iod->ctrl;
+ struct nvmet_req *req = &iod->req;
+ struct nvmet_pci_epf_segment *seg;
+ struct scatterlist *sg;
+ int ret, i;
+
+ if (iod->data_len > ctrl->mdts) {
+ iod->status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ return -EINVAL;
+ }
+
+ /*
+ * Get the PCI address segments for the command data buffer using either
+ * its SGLs or PRPs.
+ */
+ if (iod->cmd.common.flags & NVME_CMD_SGL_ALL)
+ ret = nvmet_pci_epf_iod_parse_sgls(iod);
+ else
+ ret = nvmet_pci_epf_iod_parse_prps(iod);
+ if (ret)
+ return ret;
+
+ /* Get a command buffer using SGLs matching the PCI segments. */
+ if (iod->nr_data_segs == 1) {
+ sg_init_table(&iod->data_sgl, 1);
+ iod->data_sgt.sgl = &iod->data_sgl;
+ iod->data_sgt.nents = 1;
+ iod->data_sgt.orig_nents = 1;
+ } else {
+ ret = sg_alloc_table(&iod->data_sgt, iod->nr_data_segs,
+ GFP_KERNEL);
+ if (ret)
+ goto err_nomem;
+ }
+
+ for_each_sgtable_sg(&iod->data_sgt, sg, i) {
+ seg = &iod->data_segs[i];
+ seg->buf = kmalloc(seg->length, GFP_KERNEL);
+ if (!seg->buf)
+ goto err_nomem;
+ sg_set_buf(sg, seg->buf, seg->length);
+ }
+
+ req->transfer_len = iod->data_len;
+ req->sg = iod->data_sgt.sgl;
+ req->sg_cnt = iod->data_sgt.nents;
+
+ return 0;
+
+err_nomem:
+ iod->status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ return -ENOMEM;
+}
+
+static void nvmet_pci_epf_complete_iod(struct nvmet_pci_epf_iod *iod)
+{
+ struct nvmet_pci_epf_queue *cq = iod->cq;
+ unsigned long flags;
+
+ /* Print an error message for failed commands, except AENs. */
+ iod->status = le16_to_cpu(iod->cqe.status) >> 1;
+ if (iod->status && iod->cmd.common.opcode != nvme_admin_async_event)
+ dev_err(iod->ctrl->dev,
+ "CQ[%d]: Command %s (0x%x) status 0x%0x\n",
+ iod->sq->qid, nvmet_pci_epf_iod_name(iod),
+ iod->cmd.common.opcode, iod->status);
+
+ /*
+ * Add the command to the list of completed commands and schedule the
+ * CQ work.
+ */
+ spin_lock_irqsave(&cq->lock, flags);
+ list_add_tail(&iod->link, &cq->list);
+ queue_delayed_work(system_highpri_wq, &cq->work, 0);
+ spin_unlock_irqrestore(&cq->lock, flags);
+}
+
+static void nvmet_pci_epf_drain_queue(struct nvmet_pci_epf_queue *queue)
+{
+ struct nvmet_pci_epf_iod *iod;
+ unsigned long flags;
+
+ spin_lock_irqsave(&queue->lock, flags);
+ while (!list_empty(&queue->list)) {
+ iod = list_first_entry(&queue->list, struct nvmet_pci_epf_iod,
+ link);
+ list_del_init(&iod->link);
+ nvmet_pci_epf_free_iod(iod);
+ }
+ spin_unlock_irqrestore(&queue->lock, flags);
+}
+
+static int nvmet_pci_epf_add_port(struct nvmet_port *port)
+{
+ mutex_lock(&nvmet_pci_epf_ports_mutex);
+ list_add_tail(&port->entry, &nvmet_pci_epf_ports);
+ mutex_unlock(&nvmet_pci_epf_ports_mutex);
+ return 0;
+}
+
+static void nvmet_pci_epf_remove_port(struct nvmet_port *port)
+{
+ mutex_lock(&nvmet_pci_epf_ports_mutex);
+ list_del_init(&port->entry);
+ mutex_unlock(&nvmet_pci_epf_ports_mutex);
+}
+
+static struct nvmet_port *
+nvmet_pci_epf_find_port(struct nvmet_pci_epf_ctrl *ctrl, __le16 portid)
+{
+ struct nvmet_port *p, *port = NULL;
+
+ mutex_lock(&nvmet_pci_epf_ports_mutex);
+ list_for_each_entry(p, &nvmet_pci_epf_ports, entry) {
+ if (p->disc_addr.portid == portid) {
+ port = p;
+ break;
+ }
+ }
+ mutex_unlock(&nvmet_pci_epf_ports_mutex);
+
+ return port;
+}
+
+static void nvmet_pci_epf_queue_response(struct nvmet_req *req)
+{
+ struct nvmet_pci_epf_iod *iod =
+ container_of(req, struct nvmet_pci_epf_iod, req);
+
+ iod->status = le16_to_cpu(req->cqe->status) >> 1;
+
+ /* If we have no data to transfer, directly complete the command. */
+ if (!iod->data_len || iod->dma_dir != DMA_TO_DEVICE) {
+ nvmet_pci_epf_complete_iod(iod);
+ return;
+ }
+
+ complete(&iod->done);
+}
+
+static u8 nvmet_pci_epf_get_mdts(const struct nvmet_ctrl *tctrl)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata;
+ int page_shift = NVME_CAP_MPSMIN(tctrl->cap) + 12;
+
+ return ilog2(ctrl->mdts) - page_shift;
+}
+
+static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
+ u16 cqid, u16 flags, u16 qsize, u64 pci_addr, u16 vector)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata;
+ struct nvmet_pci_epf_queue *cq = &ctrl->cq[cqid];
+ u16 status;
+
+ if (test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ if (!(flags & NVME_QUEUE_PHYS_CONTIG))
+ return NVME_SC_INVALID_QUEUE | NVME_STATUS_DNR;
+
+ cq->pci_addr = pci_addr;
+ cq->qid = cqid;
+ cq->depth = qsize + 1;
+ cq->vector = vector;
+ cq->head = 0;
+ cq->tail = 0;
+ cq->phase = 1;
+ cq->db = NVME_REG_DBS + (((cqid * 2) + 1) * sizeof(u32));
+ nvmet_pci_epf_bar_write32(ctrl, cq->db, 0);
+
+ if (!cqid)
+ cq->qes = sizeof(struct nvme_completion);
+ else
+ cq->qes = ctrl->io_cqes;
+ cq->pci_size = cq->qes * cq->depth;
+
+ if (flags & NVME_CQ_IRQ_ENABLED) {
+ cq->iv = nvmet_pci_epf_add_irq_vector(ctrl, vector);
+ if (!cq->iv)
+ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ set_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags);
+ }
+
+ status = nvmet_cq_create(tctrl, &cq->nvme_cq, cqid, cq->depth);
+ if (status != NVME_SC_SUCCESS)
+ goto err;
+
+ set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags);
+
+ dev_dbg(ctrl->dev, "CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
+ cqid, qsize, cq->qes, cq->vector);
+
+ return NVME_SC_SUCCESS;
+
+err:
+ if (test_and_clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+ nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
+ return status;
+}
+
+static u16 nvmet_pci_epf_delete_cq(struct nvmet_ctrl *tctrl, u16 cqid)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata;
+ struct nvmet_pci_epf_queue *cq = &ctrl->cq[cqid];
+
+ if (!test_and_clear_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ cancel_delayed_work_sync(&cq->work);
+ nvmet_pci_epf_drain_queue(cq);
+ nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
+
+ return NVME_SC_SUCCESS;
+}
+
+static u16 nvmet_pci_epf_create_sq(struct nvmet_ctrl *tctrl,
+ u16 sqid, u16 flags, u16 qsize, u64 pci_addr)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata;
+ struct nvmet_pci_epf_queue *sq = &ctrl->sq[sqid];
+ u16 status;
+
+ if (test_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags))
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ if (!(flags & NVME_QUEUE_PHYS_CONTIG))
+ return NVME_SC_INVALID_QUEUE | NVME_STATUS_DNR;
+
+ sq->pci_addr = pci_addr;
+ sq->qid = sqid;
+ sq->depth = qsize + 1;
+ sq->head = 0;
+ sq->tail = 0;
+ sq->phase = 0;
+ sq->db = NVME_REG_DBS + (sqid * 2 * sizeof(u32));
+ nvmet_pci_epf_bar_write32(ctrl, sq->db, 0);
+ if (!sqid)
+ sq->qes = 1UL << NVME_ADM_SQES;
+ else
+ sq->qes = ctrl->io_sqes;
+ sq->pci_size = sq->qes * sq->depth;
+
+ status = nvmet_sq_create(tctrl, &sq->nvme_sq, sqid, sq->depth);
+ if (status != NVME_SC_SUCCESS)
+ return status;
+
+ sq->iod_wq = alloc_workqueue("sq%d_wq", WQ_UNBOUND,
+ min_t(int, sq->depth, WQ_MAX_ACTIVE), sqid);
+ if (!sq->iod_wq) {
+ dev_err(ctrl->dev, "Failed to create SQ %d work queue\n", sqid);
+ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ goto out_destroy_sq;
+ }
+
+ set_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags);
+
+ dev_dbg(ctrl->dev, "SQ[%u]: %u entries of %zu B\n",
+ sqid, qsize, sq->qes);
+
+ return NVME_SC_SUCCESS;
+
+out_destroy_sq:
+ nvmet_sq_destroy(&sq->nvme_sq);
+ return status;
+}
+
+static u16 nvmet_pci_epf_delete_sq(struct nvmet_ctrl *tctrl, u16 sqid)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata;
+ struct nvmet_pci_epf_queue *sq = &ctrl->sq[sqid];
+
+ if (!test_and_clear_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags))
+ return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+
+ flush_workqueue(sq->iod_wq);
+ destroy_workqueue(sq->iod_wq);
+ sq->iod_wq = NULL;
+
+ nvmet_pci_epf_drain_queue(sq);
+
+ if (sq->nvme_sq.ctrl)
+ nvmet_sq_destroy(&sq->nvme_sq);
+
+ return NVME_SC_SUCCESS;
+}
+
+static u16 nvmet_pci_epf_get_feat(const struct nvmet_ctrl *tctrl,
+ u8 feat, void *data)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata;
+ struct nvmet_feat_arbitration *arb;
+ struct nvmet_feat_irq_coalesce *irqc;
+ struct nvmet_feat_irq_config *irqcfg;
+ struct nvmet_pci_epf_irq_vector *iv;
+ u16 status;
+
+ switch (feat) {
+ case NVME_FEAT_ARBITRATION:
+ arb = data;
+ if (!ctrl->sq_ab)
+ arb->ab = 0x7;
+ else
+ arb->ab = ilog2(ctrl->sq_ab);
+ return NVME_SC_SUCCESS;
+
+ case NVME_FEAT_IRQ_COALESCE:
+ irqc = data;
+ irqc->thr = ctrl->irq_vector_threshold;
+ irqc->time = 0;
+ return NVME_SC_SUCCESS;
+
+ case NVME_FEAT_IRQ_CONFIG:
+ irqcfg = data;
+ mutex_lock(&ctrl->irq_lock);
+ iv = nvmet_pci_epf_find_irq_vector(ctrl, irqcfg->iv);
+ if (iv) {
+ irqcfg->cd = iv->cd;
+ status = NVME_SC_SUCCESS;
+ } else {
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+ mutex_unlock(&ctrl->irq_lock);
+ return status;
+
+ default:
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+}
+
+static u16 nvmet_pci_epf_set_feat(const struct nvmet_ctrl *tctrl,
+ u8 feat, void *data)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = tctrl->drvdata;
+ struct nvmet_feat_arbitration *arb;
+ struct nvmet_feat_irq_coalesce *irqc;
+ struct nvmet_feat_irq_config *irqcfg;
+ struct nvmet_pci_epf_irq_vector *iv;
+ u16 status;
+
+ switch (feat) {
+ case NVME_FEAT_ARBITRATION:
+ arb = data;
+ if (arb->ab == 0x7)
+ ctrl->sq_ab = 0;
+ else
+ ctrl->sq_ab = 1 << arb->ab;
+ return NVME_SC_SUCCESS;
+
+ case NVME_FEAT_IRQ_COALESCE:
+ /*
+ * Since we do not implement precise IRQ coalescing timing,
+ * ignore the time field.
+ */
+ irqc = data;
+ ctrl->irq_vector_threshold = irqc->thr + 1;
+ return NVME_SC_SUCCESS;
+
+ case NVME_FEAT_IRQ_CONFIG:
+ irqcfg = data;
+ mutex_lock(&ctrl->irq_lock);
+ iv = nvmet_pci_epf_find_irq_vector(ctrl, irqcfg->iv);
+ if (iv) {
+ iv->cd = irqcfg->cd;
+ status = NVME_SC_SUCCESS;
+ } else {
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+ mutex_unlock(&ctrl->irq_lock);
+ return status;
+
+ default:
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+}
+
+static const struct nvmet_fabrics_ops nvmet_pci_epf_fabrics_ops = {
+ .owner = THIS_MODULE,
+ .type = NVMF_TRTYPE_PCI,
+ .add_port = nvmet_pci_epf_add_port,
+ .remove_port = nvmet_pci_epf_remove_port,
+ .queue_response = nvmet_pci_epf_queue_response,
+ .get_mdts = nvmet_pci_epf_get_mdts,
+ .create_cq = nvmet_pci_epf_create_cq,
+ .delete_cq = nvmet_pci_epf_delete_cq,
+ .create_sq = nvmet_pci_epf_create_sq,
+ .delete_sq = nvmet_pci_epf_delete_sq,
+ .get_feature = nvmet_pci_epf_get_feat,
+ .set_feature = nvmet_pci_epf_set_feat,
+};
+
+static void nvmet_pci_epf_cq_work(struct work_struct *work);
+
+static void nvmet_pci_epf_init_queue(struct nvmet_pci_epf_ctrl *ctrl,
+ unsigned int qid, bool sq)
+{
+ struct nvmet_pci_epf_queue *queue;
+
+ if (sq) {
+ queue = &ctrl->sq[qid];
+ set_bit(NVMET_PCI_EPF_Q_IS_SQ, &queue->flags);
+ } else {
+ queue = &ctrl->cq[qid];
+ INIT_DELAYED_WORK(&queue->work, nvmet_pci_epf_cq_work);
+ }
+ queue->ctrl = ctrl;
+ queue->qid = qid;
+ spin_lock_init(&queue->lock);
+ INIT_LIST_HEAD(&queue->list);
+}
+
+static int nvmet_pci_epf_alloc_queues(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ unsigned int qid;
+
+ ctrl->sq = kcalloc(ctrl->nr_queues,
+ sizeof(struct nvmet_pci_epf_queue), GFP_KERNEL);
+ if (!ctrl->sq)
+ return -ENOMEM;
+
+ ctrl->cq = kcalloc(ctrl->nr_queues,
+ sizeof(struct nvmet_pci_epf_queue), GFP_KERNEL);
+ if (!ctrl->cq) {
+ kfree(ctrl->sq);
+ ctrl->sq = NULL;
+ return -ENOMEM;
+ }
+
+ for (qid = 0; qid < ctrl->nr_queues; qid++) {
+ nvmet_pci_epf_init_queue(ctrl, qid, true);
+ nvmet_pci_epf_init_queue(ctrl, qid, false);
+ }
+
+ return 0;
+}
+
+static void nvmet_pci_epf_free_queues(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ kfree(ctrl->sq);
+ ctrl->sq = NULL;
+ kfree(ctrl->cq);
+ ctrl->cq = NULL;
+}
+
+static int nvmet_pci_epf_map_queue(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_queue *queue)
+{
+ struct nvmet_pci_epf *nvme_epf = ctrl->nvme_epf;
+ int ret;
+
+ ret = nvmet_pci_epf_mem_map(nvme_epf, queue->pci_addr,
+ queue->pci_size, &queue->pci_map);
+ if (ret) {
+ dev_err(ctrl->dev, "Failed to map queue %u (err=%d)\n",
+ queue->qid, ret);
+ return ret;
+ }
+
+ if (queue->pci_map.pci_size < queue->pci_size) {
+ dev_err(ctrl->dev, "Invalid partial mapping of queue %u\n",
+ queue->qid);
+ nvmet_pci_epf_mem_unmap(nvme_epf, &queue->pci_map);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static inline void nvmet_pci_epf_unmap_queue(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_queue *queue)
+{
+ nvmet_pci_epf_mem_unmap(ctrl->nvme_epf, &queue->pci_map);
+}
+
+static void nvmet_pci_epf_exec_iod_work(struct work_struct *work)
+{
+ struct nvmet_pci_epf_iod *iod =
+ container_of(work, struct nvmet_pci_epf_iod, work);
+ struct nvmet_req *req = &iod->req;
+ int ret;
+
+ if (!iod->ctrl->link_up) {
+ nvmet_pci_epf_free_iod(iod);
+ return;
+ }
+
+ if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &iod->sq->flags)) {
+ iod->status = NVME_SC_QID_INVALID | NVME_STATUS_DNR;
+ goto complete;
+ }
+
+ if (!nvmet_req_init(req, &iod->cq->nvme_cq, &iod->sq->nvme_sq,
+ &nvmet_pci_epf_fabrics_ops))
+ goto complete;
+
+ iod->data_len = nvmet_req_transfer_len(req);
+ if (iod->data_len) {
+ /*
+ * Get the data DMA transfer direction. Here "device" means the
+ * PCI root-complex host.
+ */
+ if (nvme_is_write(&iod->cmd))
+ iod->dma_dir = DMA_FROM_DEVICE;
+ else
+ iod->dma_dir = DMA_TO_DEVICE;
+
+ /*
+ * Setup the command data buffer and get the command data from
+ * the host if needed.
+ */
+ ret = nvmet_pci_epf_alloc_iod_data_buf(iod);
+ if (!ret && iod->dma_dir == DMA_FROM_DEVICE)
+ ret = nvmet_pci_epf_transfer_iod_data(iod);
+ if (ret) {
+ nvmet_req_uninit(req);
+ goto complete;
+ }
+ }
+
+ req->execute(req);
+
+ /*
+ * If we do not have data to transfer after the command execution
+ * finishes, nvmet_pci_epf_queue_response() will complete the command
+ * directly. No need to wait for the completion in this case.
+ */
+ if (!iod->data_len || iod->dma_dir != DMA_TO_DEVICE)
+ return;
+
+ wait_for_completion(&iod->done);
+
+ if (iod->status == NVME_SC_SUCCESS) {
+ WARN_ON_ONCE(!iod->data_len || iod->dma_dir != DMA_TO_DEVICE);
+ nvmet_pci_epf_transfer_iod_data(iod);
+ }
+
+complete:
+ nvmet_pci_epf_complete_iod(iod);
+}
+
+static int nvmet_pci_epf_process_sq(struct nvmet_pci_epf_ctrl *ctrl,
+ struct nvmet_pci_epf_queue *sq)
+{
+ struct nvmet_pci_epf_iod *iod;
+ int ret, n = 0;
+
+ sq->tail = nvmet_pci_epf_bar_read32(ctrl, sq->db);
+ while (sq->head != sq->tail && (!ctrl->sq_ab || n < ctrl->sq_ab)) {
+ iod = nvmet_pci_epf_alloc_iod(sq);
+ if (!iod)
+ break;
+
+ /* Get the NVMe command submitted by the host. */
+ ret = nvmet_pci_epf_transfer(ctrl, &iod->cmd,
+ sq->pci_addr + sq->head * sq->qes,
+ sq->qes, DMA_FROM_DEVICE);
+ if (ret) {
+ /* Not much we can do... */
+ nvmet_pci_epf_free_iod(iod);
+ break;
+ }
+
+ dev_dbg(ctrl->dev, "SQ[%u]: head %u, tail %u, command %s\n",
+ sq->qid, sq->head, sq->tail,
+ nvmet_pci_epf_iod_name(iod));
+
+ sq->head++;
+ if (sq->head == sq->depth)
+ sq->head = 0;
+ n++;
+
+ queue_work_on(WORK_CPU_UNBOUND, sq->iod_wq, &iod->work);
+
+ sq->tail = nvmet_pci_epf_bar_read32(ctrl, sq->db);
+ }
+
+ return n;
+}
+
+static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work)
+{
+ struct nvmet_pci_epf_ctrl *ctrl =
+ container_of(work, struct nvmet_pci_epf_ctrl, poll_sqs.work);
+ struct nvmet_pci_epf_queue *sq;
+ unsigned long limit = jiffies;
+ unsigned long last = 0;
+ int i, nr_sqs;
+
+ while (ctrl->link_up && ctrl->enabled) {
+ nr_sqs = 0;
+ /* Do round-robin arbitration. */
+ for (i = 0; i < ctrl->nr_queues; i++) {
+ sq = &ctrl->sq[i];
+ if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags))
+ continue;
+ if (nvmet_pci_epf_process_sq(ctrl, sq))
+ nr_sqs++;
+ }
+
+ /*
+ * If we have been running for a while, reschedule to let other
+ * tasks run and to avoid RCU stalls.
+ */
+ if (time_is_before_jiffies(limit + secs_to_jiffies(1))) {
+ cond_resched();
+ limit = jiffies;
+ continue;
+ }
+
+ if (nr_sqs) {
+ last = jiffies;
+ continue;
+ }
+
+ /*
+ * If we have not received any command on any queue for more
+ * than NVMET_PCI_EPF_SQ_POLL_IDLE, assume we are idle and
+ * reschedule. This avoids "burning" a CPU when the controller
+ * is idle for a long time.
+ */
+ if (time_is_before_jiffies(last + NVMET_PCI_EPF_SQ_POLL_IDLE))
+ break;
+
+ cpu_relax();
+ }
+
+ schedule_delayed_work(&ctrl->poll_sqs, NVMET_PCI_EPF_SQ_POLL_INTERVAL);
+}
+
+static void nvmet_pci_epf_cq_work(struct work_struct *work)
+{
+ struct nvmet_pci_epf_queue *cq =
+ container_of(work, struct nvmet_pci_epf_queue, work.work);
+ struct nvmet_pci_epf_ctrl *ctrl = cq->ctrl;
+ struct nvme_completion *cqe;
+ struct nvmet_pci_epf_iod *iod;
+ unsigned long flags;
+ int ret, n = 0;
+
+ ret = nvmet_pci_epf_map_queue(ctrl, cq);
+ if (ret)
+ goto again;
+
+ while (test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags) && ctrl->link_up) {
+
+ /* Check that the CQ is not full. */
+ cq->head = nvmet_pci_epf_bar_read32(ctrl, cq->db);
+ if (cq->head == cq->tail + 1) {
+ ret = -EAGAIN;
+ break;
+ }
+
+ spin_lock_irqsave(&cq->lock, flags);
+ iod = list_first_entry_or_null(&cq->list,
+ struct nvmet_pci_epf_iod, link);
+ if (iod)
+ list_del_init(&iod->link);
+ spin_unlock_irqrestore(&cq->lock, flags);
+
+ if (!iod)
+ break;
+
+ /* Post the IOD completion entry. */
+ cqe = &iod->cqe;
+ cqe->status = cpu_to_le16((iod->status << 1) | cq->phase);
+
+ dev_dbg(ctrl->dev,
+ "CQ[%u]: %s status 0x%x, result 0x%llx, head %u, tail %u, phase %u\n",
+ cq->qid, nvmet_pci_epf_iod_name(iod), iod->status,
+ le64_to_cpu(cqe->result.u64), cq->head, cq->tail,
+ cq->phase);
+
+ memcpy_toio(cq->pci_map.virt_addr + cq->tail * cq->qes,
+ cqe, cq->qes);
+
+ cq->tail++;
+ if (cq->tail >= cq->depth) {
+ cq->tail = 0;
+ cq->phase ^= 1;
+ }
+
+ nvmet_pci_epf_free_iod(iod);
+
+ /* Signal the host. */
+ nvmet_pci_epf_raise_irq(ctrl, cq, false);
+ n++;
+ }
+
+ nvmet_pci_epf_unmap_queue(ctrl, cq);
+
+ /*
+ * We do not support precise IRQ coalescing time (100ns units as per
+ * NVMe specifications). So if we have posted completion entries without
+ * reaching the interrupt coalescing threshold, raise an interrupt.
+ */
+ if (n)
+ nvmet_pci_epf_raise_irq(ctrl, cq, true);
+
+again:
+ if (ret < 0)
+ queue_delayed_work(system_highpri_wq, &cq->work,
+ NVMET_PCI_EPF_CQ_RETRY_INTERVAL);
+}
+
+static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ u64 pci_addr, asq, acq;
+ u32 aqa;
+ u16 status, qsize;
+
+ if (ctrl->enabled)
+ return 0;
+
+ dev_info(ctrl->dev, "Enabling controller\n");
+
+ ctrl->mps_shift = nvmet_cc_mps(ctrl->cc) + 12;
+ ctrl->mps = 1UL << ctrl->mps_shift;
+ ctrl->mps_mask = ctrl->mps - 1;
+
+ ctrl->io_sqes = 1UL << nvmet_cc_iosqes(ctrl->cc);
+ if (ctrl->io_sqes < sizeof(struct nvme_command)) {
+ dev_err(ctrl->dev, "Unsupported I/O SQES %zu (need %zu)\n",
+ ctrl->io_sqes, sizeof(struct nvme_command));
+ goto err;
+ }
+
+ ctrl->io_cqes = 1UL << nvmet_cc_iocqes(ctrl->cc);
+ if (ctrl->io_cqes < sizeof(struct nvme_completion)) {
+ dev_err(ctrl->dev, "Unsupported I/O CQES %zu (need %zu)\n",
+ ctrl->io_sqes, sizeof(struct nvme_completion));
+ goto err;
+ }
+
+ /* Create the admin queue. */
+ aqa = nvmet_pci_epf_bar_read32(ctrl, NVME_REG_AQA);
+ asq = nvmet_pci_epf_bar_read64(ctrl, NVME_REG_ASQ);
+ acq = nvmet_pci_epf_bar_read64(ctrl, NVME_REG_ACQ);
+
+ qsize = (aqa & 0x0fff0000) >> 16;
+ pci_addr = acq & GENMASK_ULL(63, 12);
+ status = nvmet_pci_epf_create_cq(ctrl->tctrl, 0,
+ NVME_CQ_IRQ_ENABLED | NVME_QUEUE_PHYS_CONTIG,
+ qsize, pci_addr, 0);
+ if (status != NVME_SC_SUCCESS) {
+ dev_err(ctrl->dev, "Failed to create admin completion queue\n");
+ goto err;
+ }
+
+ qsize = aqa & 0x00000fff;
+ pci_addr = asq & GENMASK_ULL(63, 12);
+ status = nvmet_pci_epf_create_sq(ctrl->tctrl, 0, NVME_QUEUE_PHYS_CONTIG,
+ qsize, pci_addr);
+ if (status != NVME_SC_SUCCESS) {
+ dev_err(ctrl->dev, "Failed to create admin submission queue\n");
+ nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
+ goto err;
+ }
+
+ ctrl->sq_ab = NVMET_PCI_EPF_SQ_AB;
+ ctrl->irq_vector_threshold = NVMET_PCI_EPF_IV_THRESHOLD;
+ ctrl->enabled = true;
+ ctrl->csts = NVME_CSTS_RDY;
+
+ /* Start polling the controller SQs. */
+ schedule_delayed_work(&ctrl->poll_sqs, 0);
+
+ return 0;
+
+err:
+ ctrl->csts = 0;
+ return -EINVAL;
+}
+
+static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ int qid;
+
+ if (!ctrl->enabled)
+ return;
+
+ dev_info(ctrl->dev, "Disabling controller\n");
+
+ ctrl->enabled = false;
+ cancel_delayed_work_sync(&ctrl->poll_sqs);
+
+ /* Delete all I/O queues first. */
+ for (qid = 1; qid < ctrl->nr_queues; qid++)
+ nvmet_pci_epf_delete_sq(ctrl->tctrl, qid);
+
+ for (qid = 1; qid < ctrl->nr_queues; qid++)
+ nvmet_pci_epf_delete_cq(ctrl->tctrl, qid);
+
+ /* Delete the admin queue last. */
+ nvmet_pci_epf_delete_sq(ctrl->tctrl, 0);
+ nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
+
+ ctrl->csts &= ~NVME_CSTS_RDY;
+}
+
+static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
+{
+ struct nvmet_pci_epf_ctrl *ctrl =
+ container_of(work, struct nvmet_pci_epf_ctrl, poll_cc.work);
+ u32 old_cc, new_cc;
+ int ret;
+
+ if (!ctrl->tctrl)
+ return;
+
+ old_cc = ctrl->cc;
+ new_cc = nvmet_pci_epf_bar_read32(ctrl, NVME_REG_CC);
+ if (new_cc == old_cc)
+ goto reschedule_work;
+
+ ctrl->cc = new_cc;
+
+ if (nvmet_cc_en(new_cc) && !nvmet_cc_en(old_cc)) {
+ ret = nvmet_pci_epf_enable_ctrl(ctrl);
+ if (ret)
+ goto reschedule_work;
+ }
+
+ if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc))
+ nvmet_pci_epf_disable_ctrl(ctrl);
+
+ if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) {
+ nvmet_pci_epf_disable_ctrl(ctrl);
+ ctrl->csts |= NVME_CSTS_SHST_CMPLT;
+ }
+
+ if (!nvmet_cc_shn(new_cc) && nvmet_cc_shn(old_cc))
+ ctrl->csts &= ~NVME_CSTS_SHST_CMPLT;
+
+ nvmet_update_cc(ctrl->tctrl, ctrl->cc);
+ nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
+
+reschedule_work:
+ schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL);
+}
+
+static void nvmet_pci_epf_init_bar(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ struct nvmet_ctrl *tctrl = ctrl->tctrl;
+
+ ctrl->bar = ctrl->nvme_epf->reg_bar;
+
+ /* Copy the target controller capabilities as a base. */
+ ctrl->cap = tctrl->cap;
+
+ /* Contiguous Queues Required (CQR). */
+ ctrl->cap |= 0x1ULL << 16;
+
+ /* Set Doorbell stride to 4B (DSTRB). */
+ ctrl->cap &= ~GENMASK_ULL(35, 32);
+
+ /* Clear NVM Subsystem Reset Supported (NSSRS). */
+ ctrl->cap &= ~(0x1ULL << 36);
+
+ /* Clear Boot Partition Support (BPS). */
+ ctrl->cap &= ~(0x1ULL << 45);
+
+ /* Clear Persistent Memory Region Supported (PMRS). */
+ ctrl->cap &= ~(0x1ULL << 56);
+
+ /* Clear Controller Memory Buffer Supported (CMBS). */
+ ctrl->cap &= ~(0x1ULL << 57);
+
+ /* Controller configuration. */
+ ctrl->cc = tctrl->cc & (~NVME_CC_ENABLE);
+
+ /* Controller status. */
+ ctrl->csts = ctrl->tctrl->csts;
+
+ nvmet_pci_epf_bar_write64(ctrl, NVME_REG_CAP, ctrl->cap);
+ nvmet_pci_epf_bar_write32(ctrl, NVME_REG_VS, tctrl->subsys->ver);
+ nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
+ nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CC, ctrl->cc);
+}
+
+static int nvmet_pci_epf_create_ctrl(struct nvmet_pci_epf *nvme_epf,
+ unsigned int max_nr_queues)
+{
+ struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
+ struct nvmet_alloc_ctrl_args args = {};
+ char hostnqn[NVMF_NQN_SIZE];
+ uuid_t id;
+ int ret;
+
+ memset(ctrl, 0, sizeof(*ctrl));
+ ctrl->dev = &nvme_epf->epf->dev;
+ mutex_init(&ctrl->irq_lock);
+ ctrl->nvme_epf = nvme_epf;
+ ctrl->mdts = nvme_epf->mdts_kb * SZ_1K;
+ INIT_DELAYED_WORK(&ctrl->poll_cc, nvmet_pci_epf_poll_cc_work);
+ INIT_DELAYED_WORK(&ctrl->poll_sqs, nvmet_pci_epf_poll_sqs_work);
+
+ ret = mempool_init_kmalloc_pool(&ctrl->iod_pool,
+ max_nr_queues * NVMET_MAX_QUEUE_SIZE,
+ sizeof(struct nvmet_pci_epf_iod));
+ if (ret) {
+ dev_err(ctrl->dev, "Failed to initialize IOD mempool\n");
+ return ret;
+ }
+
+ ctrl->port = nvmet_pci_epf_find_port(ctrl, nvme_epf->portid);
+ if (!ctrl->port) {
+ dev_err(ctrl->dev, "Port not found\n");
+ ret = -EINVAL;
+ goto out_mempool_exit;
+ }
+
+ /* Create the target controller. */
+ uuid_gen(&id);
+ snprintf(hostnqn, NVMF_NQN_SIZE,
+ "nqn.2014-08.org.nvmexpress:uuid:%pUb", &id);
+ args.port = ctrl->port;
+ args.subsysnqn = nvme_epf->subsysnqn;
+ memset(&id, 0, sizeof(uuid_t));
+ args.hostid = &id;
+ args.hostnqn = hostnqn;
+ args.ops = &nvmet_pci_epf_fabrics_ops;
+
+ ctrl->tctrl = nvmet_alloc_ctrl(&args);
+ if (!ctrl->tctrl) {
+ dev_err(ctrl->dev, "Failed to create target controller\n");
+ ret = -ENOMEM;
+ goto out_mempool_exit;
+ }
+ ctrl->tctrl->drvdata = ctrl;
+
+ /* We do not support protection information for now. */
+ if (ctrl->tctrl->pi_support) {
+ dev_err(ctrl->dev,
+ "Protection information (PI) is not supported\n");
+ ret = -ENOTSUPP;
+ goto out_put_ctrl;
+ }
+
+ /* Allocate our queues, up to the maximum number. */
+ ctrl->nr_queues = min(ctrl->tctrl->subsys->max_qid + 1, max_nr_queues);
+ ret = nvmet_pci_epf_alloc_queues(ctrl);
+ if (ret)
+ goto out_put_ctrl;
+
+ /*
+ * Allocate the IRQ vectors descriptors. We cannot have more than the
+ * maximum number of queues.
+ */
+ ret = nvmet_pci_epf_alloc_irq_vectors(ctrl);
+ if (ret)
+ goto out_free_queues;
+
+ dev_info(ctrl->dev,
+ "New PCI ctrl \"%s\", %u I/O queues, mdts %u B\n",
+ ctrl->tctrl->subsys->subsysnqn, ctrl->nr_queues - 1,
+ ctrl->mdts);
+
+ /* Initialize BAR 0 using the target controller CAP. */
+ nvmet_pci_epf_init_bar(ctrl);
+
+ return 0;
+
+out_free_queues:
+ nvmet_pci_epf_free_queues(ctrl);
+out_put_ctrl:
+ nvmet_ctrl_put(ctrl->tctrl);
+ ctrl->tctrl = NULL;
+out_mempool_exit:
+ mempool_exit(&ctrl->iod_pool);
+ return ret;
+}
+
+static void nvmet_pci_epf_start_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL);
+}
+
+static void nvmet_pci_epf_stop_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ cancel_delayed_work_sync(&ctrl->poll_cc);
+
+ nvmet_pci_epf_disable_ctrl(ctrl);
+}
+
+static void nvmet_pci_epf_destroy_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
+{
+ if (!ctrl->tctrl)
+ return;
+
+ dev_info(ctrl->dev, "Destroying PCI ctrl \"%s\"\n",
+ ctrl->tctrl->subsys->subsysnqn);
+
+ nvmet_pci_epf_stop_ctrl(ctrl);
+
+ nvmet_pci_epf_free_queues(ctrl);
+ nvmet_pci_epf_free_irq_vectors(ctrl);
+
+ nvmet_ctrl_put(ctrl->tctrl);
+ ctrl->tctrl = NULL;
+
+ mempool_exit(&ctrl->iod_pool);
+}
+
+static int nvmet_pci_epf_configure_bar(struct nvmet_pci_epf *nvme_epf)
+{
+ struct pci_epf *epf = nvme_epf->epf;
+ const struct pci_epc_features *epc_features = nvme_epf->epc_features;
+ size_t reg_size, reg_bar_size;
+ size_t msix_table_size = 0;
+
+ /*
+ * The first free BAR will be our register BAR and per NVMe
+ * specifications, it must be BAR 0.
+ */
+ if (pci_epc_get_first_free_bar(epc_features) != BAR_0) {
+ dev_err(&epf->dev, "BAR 0 is not free\n");
+ return -ENODEV;
+ }
+
+ if (epc_features->bar[BAR_0].only_64bit)
+ epf->bar[BAR_0].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64;
+
+ /*
+ * Calculate the size of the register bar: NVMe registers first with
+ * enough space for the doorbells, followed by the MSI-X table
+ * if supported.
+ */
+ reg_size = NVME_REG_DBS + (NVMET_NR_QUEUES * 2 * sizeof(u32));
+ reg_size = ALIGN(reg_size, 8);
+
+ if (epc_features->msix_capable) {
+ size_t pba_size;
+
+ msix_table_size = PCI_MSIX_ENTRY_SIZE * epf->msix_interrupts;
+ nvme_epf->msix_table_offset = reg_size;
+ pba_size = ALIGN(DIV_ROUND_UP(epf->msix_interrupts, 8), 8);
+
+ reg_size += msix_table_size + pba_size;
+ }
+
+ if (epc_features->bar[BAR_0].type == BAR_FIXED) {
+ if (reg_size > epc_features->bar[BAR_0].fixed_size) {
+ dev_err(&epf->dev,
+ "BAR 0 size %llu B too small, need %zu B\n",
+ epc_features->bar[BAR_0].fixed_size,
+ reg_size);
+ return -ENOMEM;
+ }
+ reg_bar_size = epc_features->bar[BAR_0].fixed_size;
+ } else {
+ reg_bar_size = ALIGN(reg_size, max(epc_features->align, 4096));
+ }
+
+ nvme_epf->reg_bar = pci_epf_alloc_space(epf, reg_bar_size, BAR_0,
+ epc_features, PRIMARY_INTERFACE);
+ if (!nvme_epf->reg_bar) {
+ dev_err(&epf->dev, "Failed to allocate BAR 0\n");
+ return -ENOMEM;
+ }
+ memset(nvme_epf->reg_bar, 0, reg_bar_size);
+
+ return 0;
+}
+
+static void nvmet_pci_epf_free_bar(struct nvmet_pci_epf *nvme_epf)
+{
+ struct pci_epf *epf = nvme_epf->epf;
+
+ if (!nvme_epf->reg_bar)
+ return;
+
+ pci_epf_free_space(epf, nvme_epf->reg_bar, BAR_0, PRIMARY_INTERFACE);
+ nvme_epf->reg_bar = NULL;
+}
+
+static void nvmet_pci_epf_clear_bar(struct nvmet_pci_epf *nvme_epf)
+{
+ struct pci_epf *epf = nvme_epf->epf;
+
+ pci_epc_clear_bar(epf->epc, epf->func_no, epf->vfunc_no,
+ &epf->bar[BAR_0]);
+}
+
+static int nvmet_pci_epf_init_irq(struct nvmet_pci_epf *nvme_epf)
+{
+ const struct pci_epc_features *epc_features = nvme_epf->epc_features;
+ struct pci_epf *epf = nvme_epf->epf;
+ int ret;
+
+ /* Enable MSI-X if supported, otherwise, use MSI. */
+ if (epc_features->msix_capable && epf->msix_interrupts) {
+ ret = pci_epc_set_msix(epf->epc, epf->func_no, epf->vfunc_no,
+ epf->msix_interrupts, BAR_0,
+ nvme_epf->msix_table_offset);
+ if (ret) {
+ dev_err(&epf->dev, "Failed to configure MSI-X\n");
+ return ret;
+ }
+
+ nvme_epf->nr_vectors = epf->msix_interrupts;
+ nvme_epf->irq_type = PCI_IRQ_MSIX;
+
+ return 0;
+ }
+
+ if (epc_features->msi_capable && epf->msi_interrupts) {
+ ret = pci_epc_set_msi(epf->epc, epf->func_no, epf->vfunc_no,
+ epf->msi_interrupts);
+ if (ret) {
+ dev_err(&epf->dev, "Failed to configure MSI\n");
+ return ret;
+ }
+
+ nvme_epf->nr_vectors = epf->msi_interrupts;
+ nvme_epf->irq_type = PCI_IRQ_MSI;
+
+ return 0;
+ }
+
+ /* MSI and MSI-X are not supported: fall back to INTx. */
+ nvme_epf->nr_vectors = 1;
+ nvme_epf->irq_type = PCI_IRQ_INTX;
+
+ return 0;
+}
+
+static int nvmet_pci_epf_epc_init(struct pci_epf *epf)
+{
+ struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
+ const struct pci_epc_features *epc_features = nvme_epf->epc_features;
+ struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
+ unsigned int max_nr_queues = NVMET_NR_QUEUES;
+ int ret;
+
+ /* For now, do not support virtual functions. */
+ if (epf->vfunc_no > 0) {
+ dev_err(&epf->dev, "Virtual functions are not supported\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Cap the maximum number of queues we can support on the controller
+ * with the number of IRQs we can use.
+ */
+ if (epc_features->msix_capable && epf->msix_interrupts) {
+ dev_info(&epf->dev,
+ "PCI endpoint controller supports MSI-X, %u vectors\n",
+ epf->msix_interrupts);
+ max_nr_queues = min(max_nr_queues, epf->msix_interrupts);
+ } else if (epc_features->msi_capable && epf->msi_interrupts) {
+ dev_info(&epf->dev,
+ "PCI endpoint controller supports MSI, %u vectors\n",
+ epf->msi_interrupts);
+ max_nr_queues = min(max_nr_queues, epf->msi_interrupts);
+ }
+
+ if (max_nr_queues < 2) {
+ dev_err(&epf->dev, "Invalid maximum number of queues %u\n",
+ max_nr_queues);
+ return -EINVAL;
+ }
+
+ /* Create the target controller. */
+ ret = nvmet_pci_epf_create_ctrl(nvme_epf, max_nr_queues);
+ if (ret) {
+ dev_err(&epf->dev,
+ "Failed to create NVMe PCI target controller (err=%d)\n",
+ ret);
+ return ret;
+ }
+
+ /* Set device ID, class, etc. */
+ epf->header->vendorid = ctrl->tctrl->subsys->vendor_id;
+ epf->header->subsys_vendor_id = ctrl->tctrl->subsys->subsys_vendor_id;
+ ret = pci_epc_write_header(epf->epc, epf->func_no, epf->vfunc_no,
+ epf->header);
+ if (ret) {
+ dev_err(&epf->dev,
+ "Failed to write configuration header (err=%d)\n", ret);
+ goto out_destroy_ctrl;
+ }
+
+ ret = pci_epc_set_bar(epf->epc, epf->func_no, epf->vfunc_no,
+ &epf->bar[BAR_0]);
+ if (ret) {
+ dev_err(&epf->dev, "Failed to set BAR 0 (err=%d)\n", ret);
+ goto out_destroy_ctrl;
+ }
+
+ /*
+ * Enable interrupts and start polling the controller BAR if we do not
+ * have a link up notifier.
+ */
+ ret = nvmet_pci_epf_init_irq(nvme_epf);
+ if (ret)
+ goto out_clear_bar;
+
+ if (!epc_features->linkup_notifier) {
+ ctrl->link_up = true;
+ nvmet_pci_epf_start_ctrl(&nvme_epf->ctrl);
+ }
+
+ return 0;
+
+out_clear_bar:
+ nvmet_pci_epf_clear_bar(nvme_epf);
+out_destroy_ctrl:
+ nvmet_pci_epf_destroy_ctrl(&nvme_epf->ctrl);
+ return ret;
+}
+
+static void nvmet_pci_epf_epc_deinit(struct pci_epf *epf)
+{
+ struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
+ struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
+
+ ctrl->link_up = false;
+ nvmet_pci_epf_destroy_ctrl(ctrl);
+
+ nvmet_pci_epf_deinit_dma(nvme_epf);
+ nvmet_pci_epf_clear_bar(nvme_epf);
+}
+
+static int nvmet_pci_epf_link_up(struct pci_epf *epf)
+{
+ struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
+ struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
+
+ ctrl->link_up = true;
+ nvmet_pci_epf_start_ctrl(ctrl);
+
+ return 0;
+}
+
+static int nvmet_pci_epf_link_down(struct pci_epf *epf)
+{
+ struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
+ struct nvmet_pci_epf_ctrl *ctrl = &nvme_epf->ctrl;
+
+ ctrl->link_up = false;
+ nvmet_pci_epf_stop_ctrl(ctrl);
+
+ return 0;
+}
+
+static const struct pci_epc_event_ops nvmet_pci_epf_event_ops = {
+ .epc_init = nvmet_pci_epf_epc_init,
+ .epc_deinit = nvmet_pci_epf_epc_deinit,
+ .link_up = nvmet_pci_epf_link_up,
+ .link_down = nvmet_pci_epf_link_down,
+};
+
+static int nvmet_pci_epf_bind(struct pci_epf *epf)
+{
+ struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
+ const struct pci_epc_features *epc_features;
+ struct pci_epc *epc = epf->epc;
+ int ret;
+
+ if (WARN_ON_ONCE(!epc))
+ return -EINVAL;
+
+ epc_features = pci_epc_get_features(epc, epf->func_no, epf->vfunc_no);
+ if (!epc_features) {
+ dev_err(&epf->dev, "epc_features not implemented\n");
+ return -EOPNOTSUPP;
+ }
+ nvme_epf->epc_features = epc_features;
+
+ ret = nvmet_pci_epf_configure_bar(nvme_epf);
+ if (ret)
+ return ret;
+
+ nvmet_pci_epf_init_dma(nvme_epf);
+
+ return 0;
+}
+
+static void nvmet_pci_epf_unbind(struct pci_epf *epf)
+{
+ struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
+ struct pci_epc *epc = epf->epc;
+
+ nvmet_pci_epf_destroy_ctrl(&nvme_epf->ctrl);
+
+ if (epc->init_complete) {
+ nvmet_pci_epf_deinit_dma(nvme_epf);
+ nvmet_pci_epf_clear_bar(nvme_epf);
+ }
+
+ nvmet_pci_epf_free_bar(nvme_epf);
+}
+
+static struct pci_epf_header nvme_epf_pci_header = {
+ .vendorid = PCI_ANY_ID,
+ .deviceid = PCI_ANY_ID,
+ .progif_code = 0x02, /* NVM Express */
+ .baseclass_code = PCI_BASE_CLASS_STORAGE,
+ .subclass_code = 0x08, /* Non-Volatile Memory controller */
+ .interrupt_pin = PCI_INTERRUPT_INTA,
+};
+
+static int nvmet_pci_epf_probe(struct pci_epf *epf,
+ const struct pci_epf_device_id *id)
+{
+ struct nvmet_pci_epf *nvme_epf;
+ int ret;
+
+ nvme_epf = devm_kzalloc(&epf->dev, sizeof(*nvme_epf), GFP_KERNEL);
+ if (!nvme_epf)
+ return -ENOMEM;
+
+ ret = devm_mutex_init(&epf->dev, &nvme_epf->mmio_lock);
+ if (ret)
+ return ret;
+
+ nvme_epf->epf = epf;
+ nvme_epf->mdts_kb = NVMET_PCI_EPF_MDTS_KB;
+
+ epf->event_ops = &nvmet_pci_epf_event_ops;
+ epf->header = &nvme_epf_pci_header;
+ epf_set_drvdata(epf, nvme_epf);
+
+ return 0;
+}
+
+#define to_nvme_epf(epf_group) \
+ container_of(epf_group, struct nvmet_pci_epf, group)
+
+static ssize_t nvmet_pci_epf_portid_show(struct config_item *item, char *page)
+{
+ struct config_group *group = to_config_group(item);
+ struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group);
+
+ return sysfs_emit(page, "%u\n", le16_to_cpu(nvme_epf->portid));
+}
+
+static ssize_t nvmet_pci_epf_portid_store(struct config_item *item,
+ const char *page, size_t len)
+{
+ struct config_group *group = to_config_group(item);
+ struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group);
+ u16 portid;
+
+ /* Do not allow setting this when the function is already started. */
+ if (nvme_epf->ctrl.tctrl)
+ return -EBUSY;
+
+ if (!len)
+ return -EINVAL;
+
+ if (kstrtou16(page, 0, &portid))
+ return -EINVAL;
+
+ nvme_epf->portid = cpu_to_le16(portid);
+
+ return len;
+}
+
+CONFIGFS_ATTR(nvmet_pci_epf_, portid);
+
+static ssize_t nvmet_pci_epf_subsysnqn_show(struct config_item *item,
+ char *page)
+{
+ struct config_group *group = to_config_group(item);
+ struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group);
+
+ return sysfs_emit(page, "%s\n", nvme_epf->subsysnqn);
+}
+
+static ssize_t nvmet_pci_epf_subsysnqn_store(struct config_item *item,
+ const char *page, size_t len)
+{
+ struct config_group *group = to_config_group(item);
+ struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group);
+
+ /* Do not allow setting this when the function is already started. */
+ if (nvme_epf->ctrl.tctrl)
+ return -EBUSY;
+
+ if (!len)
+ return -EINVAL;
+
+ strscpy(nvme_epf->subsysnqn, page, len);
+
+ return len;
+}
+
+CONFIGFS_ATTR(nvmet_pci_epf_, subsysnqn);
+
+static ssize_t nvmet_pci_epf_mdts_kb_show(struct config_item *item, char *page)
+{
+ struct config_group *group = to_config_group(item);
+ struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group);
+
+ return sysfs_emit(page, "%u\n", nvme_epf->mdts_kb);
+}
+
+static ssize_t nvmet_pci_epf_mdts_kb_store(struct config_item *item,
+ const char *page, size_t len)
+{
+ struct config_group *group = to_config_group(item);
+ struct nvmet_pci_epf *nvme_epf = to_nvme_epf(group);
+ unsigned long mdts_kb;
+ int ret;
+
+ if (nvme_epf->ctrl.tctrl)
+ return -EBUSY;
+
+ ret = kstrtoul(page, 0, &mdts_kb);
+ if (ret)
+ return ret;
+ if (!mdts_kb)
+ mdts_kb = NVMET_PCI_EPF_MDTS_KB;
+ else if (mdts_kb > NVMET_PCI_EPF_MAX_MDTS_KB)
+ mdts_kb = NVMET_PCI_EPF_MAX_MDTS_KB;
+
+ if (!is_power_of_2(mdts_kb))
+ return -EINVAL;
+
+ nvme_epf->mdts_kb = mdts_kb;
+
+ return len;
+}
+
+CONFIGFS_ATTR(nvmet_pci_epf_, mdts_kb);
+
+static struct configfs_attribute *nvmet_pci_epf_attrs[] = {
+ &nvmet_pci_epf_attr_portid,
+ &nvmet_pci_epf_attr_subsysnqn,
+ &nvmet_pci_epf_attr_mdts_kb,
+ NULL,
+};
+
+static const struct config_item_type nvmet_pci_epf_group_type = {
+ .ct_attrs = nvmet_pci_epf_attrs,
+ .ct_owner = THIS_MODULE,
+};
+
+static struct config_group *nvmet_pci_epf_add_cfs(struct pci_epf *epf,
+ struct config_group *group)
+{
+ struct nvmet_pci_epf *nvme_epf = epf_get_drvdata(epf);
+
+ config_group_init_type_name(&nvme_epf->group, "nvme",
+ &nvmet_pci_epf_group_type);
+
+ return &nvme_epf->group;
+}
+
+static const struct pci_epf_device_id nvmet_pci_epf_ids[] = {
+ { .name = "nvmet_pci_epf" },
+ {},
+};
+
+static struct pci_epf_ops nvmet_pci_epf_ops = {
+ .bind = nvmet_pci_epf_bind,
+ .unbind = nvmet_pci_epf_unbind,
+ .add_cfs = nvmet_pci_epf_add_cfs,
+};
+
+static struct pci_epf_driver nvmet_pci_epf_driver = {
+ .driver.name = "nvmet_pci_epf",
+ .probe = nvmet_pci_epf_probe,
+ .id_table = nvmet_pci_epf_ids,
+ .ops = &nvmet_pci_epf_ops,
+ .owner = THIS_MODULE,
+};
+
+static int __init nvmet_pci_epf_init_module(void)
+{
+ int ret;
+
+ ret = pci_epf_register_driver(&nvmet_pci_epf_driver);
+ if (ret)
+ return ret;
+
+ ret = nvmet_register_transport(&nvmet_pci_epf_fabrics_ops);
+ if (ret) {
+ pci_epf_unregister_driver(&nvmet_pci_epf_driver);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void __exit nvmet_pci_epf_cleanup_module(void)
+{
+ nvmet_unregister_transport(&nvmet_pci_epf_fabrics_ops);
+ pci_epf_unregister_driver(&nvmet_pci_epf_driver);
+}
+
+module_init(nvmet_pci_epf_init_module);
+module_exit(nvmet_pci_epf_cleanup_module);
+
+MODULE_DESCRIPTION("NVMe PCI Endpoint Function target driver");
+MODULE_AUTHOR("Damien Le Moal <dlemoal@kernel.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c
new file mode 100644
index 000000000000..cd22d8333314
--- /dev/null
+++ b/drivers/nvme/target/pr.c
@@ -0,0 +1,1155 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe over Fabrics Persist Reservation.
+ * Copyright (c) 2024 Guixin Liu, Alibaba Group.
+ * All rights reserved.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/unaligned.h>
+#include "nvmet.h"
+
+#define NVMET_PR_NOTIFI_MASK_ALL \
+ (1 << NVME_PR_NOTIFY_BIT_REG_PREEMPTED | \
+ 1 << NVME_PR_NOTIFY_BIT_RESV_RELEASED | \
+ 1 << NVME_PR_NOTIFY_BIT_RESV_PREEMPTED)
+
+static inline bool nvmet_pr_parse_ignore_key(u32 cdw10)
+{
+ /* Ignore existing key, bit 03. */
+ return (cdw10 >> 3) & 1;
+}
+
+static inline struct nvmet_ns *nvmet_pr_to_ns(struct nvmet_pr *pr)
+{
+ return container_of(pr, struct nvmet_ns, pr);
+}
+
+static struct nvmet_pr_registrant *
+nvmet_pr_find_registrant(struct nvmet_pr *pr, uuid_t *hostid)
+{
+ struct nvmet_pr_registrant *reg;
+
+ list_for_each_entry_rcu(reg, &pr->registrant_list, entry) {
+ if (uuid_equal(&reg->hostid, hostid))
+ return reg;
+ }
+ return NULL;
+}
+
+u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask)
+{
+ u32 nsid = le32_to_cpu(req->cmd->common.nsid);
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_ns *ns;
+ unsigned long idx;
+ u16 status;
+
+ if (mask & ~(NVMET_PR_NOTIFI_MASK_ALL)) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw11);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ if (nsid != U32_MAX) {
+ status = nvmet_req_find_ns(req);
+ if (status)
+ return status;
+ if (!req->ns->pr.enable)
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+
+ WRITE_ONCE(req->ns->pr.notify_mask, mask);
+ goto success;
+ }
+
+ nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) {
+ if (ns->pr.enable)
+ WRITE_ONCE(ns->pr.notify_mask, mask);
+ }
+
+success:
+ nvmet_set_result(req, mask);
+ return NVME_SC_SUCCESS;
+}
+
+u16 nvmet_get_feat_resv_notif_mask(struct nvmet_req *req)
+{
+ u16 status;
+
+ status = nvmet_req_find_ns(req);
+ if (status)
+ return status;
+
+ if (!req->ns->pr.enable)
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+
+ nvmet_set_result(req, READ_ONCE(req->ns->pr.notify_mask));
+ return status;
+}
+
+void nvmet_execute_get_log_page_resv(struct nvmet_req *req)
+{
+ struct nvmet_pr_log_mgr *log_mgr = &req->sq->ctrl->pr_log_mgr;
+ struct nvme_pr_log next_log = {0};
+ struct nvme_pr_log log = {0};
+ u16 status = NVME_SC_SUCCESS;
+ u64 lost_count;
+ u64 cur_count;
+ u64 next_count;
+
+ mutex_lock(&log_mgr->lock);
+ if (!kfifo_get(&log_mgr->log_queue, &log))
+ goto out;
+
+ /*
+ * We can't get the last in kfifo.
+ * Utilize the current count and the count from the next log to
+ * calculate the number of lost logs, while also addressing cases
+ * of overflow. If there is no subsequent log, the number of lost
+ * logs is equal to the lost_count within the nvmet_pr_log_mgr.
+ */
+ cur_count = le64_to_cpu(log.count);
+ if (kfifo_peek(&log_mgr->log_queue, &next_log)) {
+ next_count = le64_to_cpu(next_log.count);
+ if (next_count > cur_count)
+ lost_count = next_count - cur_count - 1;
+ else
+ lost_count = U64_MAX - cur_count + next_count - 1;
+ } else {
+ lost_count = log_mgr->lost_count;
+ }
+
+ log.count = cpu_to_le64((cur_count + lost_count) == 0 ?
+ 1 : (cur_count + lost_count));
+ log_mgr->lost_count -= lost_count;
+
+ log.nr_pages = kfifo_len(&log_mgr->log_queue);
+
+out:
+ status = nvmet_copy_to_sgl(req, 0, &log, sizeof(log));
+ mutex_unlock(&log_mgr->lock);
+ nvmet_req_complete(req, status);
+}
+
+static void nvmet_pr_add_resv_log(struct nvmet_ctrl *ctrl, u8 log_type,
+ u32 nsid)
+{
+ struct nvmet_pr_log_mgr *log_mgr = &ctrl->pr_log_mgr;
+ struct nvme_pr_log log = {0};
+
+ mutex_lock(&log_mgr->lock);
+ log_mgr->counter++;
+ if (log_mgr->counter == 0)
+ log_mgr->counter = 1;
+
+ log.count = cpu_to_le64(log_mgr->counter);
+ log.type = log_type;
+ log.nsid = cpu_to_le32(nsid);
+
+ if (!kfifo_put(&log_mgr->log_queue, log)) {
+ pr_info("a reservation log lost, cntlid:%d, log_type:%d, nsid:%d\n",
+ ctrl->cntlid, log_type, nsid);
+ log_mgr->lost_count++;
+ }
+
+ mutex_unlock(&log_mgr->lock);
+}
+
+static void nvmet_pr_resv_released(struct nvmet_pr *pr, uuid_t *hostid)
+{
+ struct nvmet_ns *ns = nvmet_pr_to_ns(pr);
+ struct nvmet_subsys *subsys = ns->subsys;
+ struct nvmet_ctrl *ctrl;
+
+ if (test_bit(NVME_PR_NOTIFY_BIT_RESV_RELEASED, &pr->notify_mask))
+ return;
+
+ mutex_lock(&subsys->lock);
+ list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+ if (!uuid_equal(&ctrl->hostid, hostid) &&
+ nvmet_pr_find_registrant(pr, &ctrl->hostid)) {
+ nvmet_pr_add_resv_log(ctrl,
+ NVME_PR_LOG_RESERVATION_RELEASED, ns->nsid);
+ nvmet_add_async_event(ctrl, NVME_AER_CSS,
+ NVME_AEN_RESV_LOG_PAGE_AVALIABLE,
+ NVME_LOG_RESERVATION);
+ }
+ }
+ mutex_unlock(&subsys->lock);
+}
+
+static void nvmet_pr_send_event_to_host(struct nvmet_pr *pr, uuid_t *hostid,
+ u8 log_type)
+{
+ struct nvmet_ns *ns = nvmet_pr_to_ns(pr);
+ struct nvmet_subsys *subsys = ns->subsys;
+ struct nvmet_ctrl *ctrl;
+
+ mutex_lock(&subsys->lock);
+ list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+ if (uuid_equal(hostid, &ctrl->hostid)) {
+ nvmet_pr_add_resv_log(ctrl, log_type, ns->nsid);
+ nvmet_add_async_event(ctrl, NVME_AER_CSS,
+ NVME_AEN_RESV_LOG_PAGE_AVALIABLE,
+ NVME_LOG_RESERVATION);
+ }
+ }
+ mutex_unlock(&subsys->lock);
+}
+
+static void nvmet_pr_resv_preempted(struct nvmet_pr *pr, uuid_t *hostid)
+{
+ if (test_bit(NVME_PR_NOTIFY_BIT_RESV_PREEMPTED, &pr->notify_mask))
+ return;
+
+ nvmet_pr_send_event_to_host(pr, hostid,
+ NVME_PR_LOG_RESERVATOIN_PREEMPTED);
+}
+
+static void nvmet_pr_registration_preempted(struct nvmet_pr *pr,
+ uuid_t *hostid)
+{
+ if (test_bit(NVME_PR_NOTIFY_BIT_REG_PREEMPTED, &pr->notify_mask))
+ return;
+
+ nvmet_pr_send_event_to_host(pr, hostid,
+ NVME_PR_LOG_REGISTRATION_PREEMPTED);
+}
+
+static inline void nvmet_pr_set_new_holder(struct nvmet_pr *pr, u8 new_rtype,
+ struct nvmet_pr_registrant *reg)
+{
+ reg->rtype = new_rtype;
+ rcu_assign_pointer(pr->holder, reg);
+}
+
+static u16 nvmet_pr_register(struct nvmet_req *req,
+ struct nvmet_pr_register_data *d)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_pr_registrant *new, *reg;
+ struct nvmet_pr *pr = &req->ns->pr;
+ u16 status = NVME_SC_SUCCESS;
+ u64 nrkey = le64_to_cpu(d->nrkey);
+
+ new = kmalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
+ return NVME_SC_INTERNAL;
+
+ down(&pr->pr_sem);
+ reg = nvmet_pr_find_registrant(pr, &ctrl->hostid);
+ if (reg) {
+ if (reg->rkey != nrkey)
+ status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ kfree(new);
+ goto out;
+ }
+
+ memset(new, 0, sizeof(*new));
+ INIT_LIST_HEAD(&new->entry);
+ new->rkey = nrkey;
+ uuid_copy(&new->hostid, &ctrl->hostid);
+ list_add_tail_rcu(&new->entry, &pr->registrant_list);
+
+out:
+ up(&pr->pr_sem);
+ return status;
+}
+
+static void nvmet_pr_unregister_one(struct nvmet_pr *pr,
+ struct nvmet_pr_registrant *reg)
+{
+ struct nvmet_pr_registrant *first_reg;
+ struct nvmet_pr_registrant *holder;
+ u8 original_rtype;
+
+ list_del_rcu(&reg->entry);
+
+ holder = rcu_dereference_protected(pr->holder, 1);
+ if (reg != holder)
+ goto out;
+
+ original_rtype = holder->rtype;
+ if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS ||
+ original_rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) {
+ first_reg = list_first_or_null_rcu(&pr->registrant_list,
+ struct nvmet_pr_registrant, entry);
+ if (first_reg)
+ first_reg->rtype = original_rtype;
+ rcu_assign_pointer(pr->holder, first_reg);
+ } else {
+ rcu_assign_pointer(pr->holder, NULL);
+
+ if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_REG_ONLY ||
+ original_rtype == NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY)
+ nvmet_pr_resv_released(pr, &reg->hostid);
+ }
+out:
+ kfree_rcu(reg, rcu);
+}
+
+static u16 nvmet_pr_unregister(struct nvmet_req *req,
+ struct nvmet_pr_register_data *d,
+ bool ignore_key)
+{
+ u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_registrant *reg;
+
+ down(&pr->pr_sem);
+ list_for_each_entry_rcu(reg, &pr->registrant_list, entry) {
+ if (uuid_equal(&reg->hostid, &ctrl->hostid)) {
+ if (ignore_key || reg->rkey == le64_to_cpu(d->crkey)) {
+ status = NVME_SC_SUCCESS;
+ nvmet_pr_unregister_one(pr, reg);
+ }
+ break;
+ }
+ }
+ up(&pr->pr_sem);
+
+ return status;
+}
+
+static void nvmet_pr_update_reg_rkey(struct nvmet_pr_registrant *reg,
+ void *attr)
+{
+ reg->rkey = *(u64 *)attr;
+}
+
+static u16 nvmet_pr_update_reg_attr(struct nvmet_pr *pr,
+ struct nvmet_pr_registrant *reg,
+ void (*change_attr)(struct nvmet_pr_registrant *reg,
+ void *attr),
+ void *attr)
+{
+ struct nvmet_pr_registrant *holder;
+ struct nvmet_pr_registrant *new;
+
+ holder = rcu_dereference_protected(pr->holder, 1);
+ if (reg != holder) {
+ change_attr(reg, attr);
+ return NVME_SC_SUCCESS;
+ }
+
+ new = kmalloc(sizeof(*new), GFP_ATOMIC);
+ if (!new)
+ return NVME_SC_INTERNAL;
+
+ new->rkey = holder->rkey;
+ new->rtype = holder->rtype;
+ uuid_copy(&new->hostid, &holder->hostid);
+ INIT_LIST_HEAD(&new->entry);
+
+ change_attr(new, attr);
+ list_replace_rcu(&holder->entry, &new->entry);
+ rcu_assign_pointer(pr->holder, new);
+ kfree_rcu(holder, rcu);
+
+ return NVME_SC_SUCCESS;
+}
+
+static u16 nvmet_pr_replace(struct nvmet_req *req,
+ struct nvmet_pr_register_data *d,
+ bool ignore_key)
+{
+ u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_registrant *reg;
+ u64 nrkey = le64_to_cpu(d->nrkey);
+
+ down(&pr->pr_sem);
+ list_for_each_entry_rcu(reg, &pr->registrant_list, entry) {
+ if (uuid_equal(&reg->hostid, &ctrl->hostid)) {
+ if (ignore_key || reg->rkey == le64_to_cpu(d->crkey))
+ status = nvmet_pr_update_reg_attr(pr, reg,
+ nvmet_pr_update_reg_rkey,
+ &nrkey);
+ break;
+ }
+ }
+ up(&pr->pr_sem);
+ return status;
+}
+
+static void nvmet_execute_pr_register(struct nvmet_req *req)
+{
+ u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+ bool ignore_key = nvmet_pr_parse_ignore_key(cdw10);
+ struct nvmet_pr_register_data *d;
+ u8 reg_act = cdw10 & 0x07; /* Reservation Register Action, bit 02:00 */
+ u16 status;
+
+ d = kmalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (status)
+ goto free_data;
+
+ switch (reg_act) {
+ case NVME_PR_REGISTER_ACT_REG:
+ status = nvmet_pr_register(req, d);
+ break;
+ case NVME_PR_REGISTER_ACT_UNREG:
+ status = nvmet_pr_unregister(req, d, ignore_key);
+ break;
+ case NVME_PR_REGISTER_ACT_REPLACE:
+ status = nvmet_pr_replace(req, d, ignore_key);
+ break;
+ default:
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ break;
+ }
+free_data:
+ kfree(d);
+out:
+ if (!status)
+ atomic_inc(&req->ns->pr.generation);
+ nvmet_req_complete(req, status);
+}
+
+static u16 nvmet_pr_acquire(struct nvmet_req *req,
+ struct nvmet_pr_registrant *reg,
+ u8 rtype)
+{
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_registrant *holder;
+
+ holder = rcu_dereference_protected(pr->holder, 1);
+ if (holder && reg != holder)
+ return NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ if (holder && reg == holder) {
+ if (holder->rtype == rtype)
+ return NVME_SC_SUCCESS;
+ return NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ }
+
+ nvmet_pr_set_new_holder(pr, rtype, reg);
+ return NVME_SC_SUCCESS;
+}
+
+static void nvmet_pr_confirm_ns_pc_ref(struct percpu_ref *ref)
+{
+ struct nvmet_pr_per_ctrl_ref *pc_ref =
+ container_of(ref, struct nvmet_pr_per_ctrl_ref, ref);
+
+ complete(&pc_ref->confirm_done);
+}
+
+static void nvmet_pr_set_ctrl_to_abort(struct nvmet_req *req, uuid_t *hostid)
+{
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+ struct nvmet_ns *ns = req->ns;
+ unsigned long idx;
+
+ xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) {
+ if (uuid_equal(&pc_ref->hostid, hostid)) {
+ percpu_ref_kill_and_confirm(&pc_ref->ref,
+ nvmet_pr_confirm_ns_pc_ref);
+ wait_for_completion(&pc_ref->confirm_done);
+ }
+ }
+}
+
+static u16 nvmet_pr_unreg_all_host_by_prkey(struct nvmet_req *req, u64 prkey,
+ uuid_t *send_hostid,
+ bool abort)
+{
+ u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ struct nvmet_pr_registrant *reg, *tmp;
+ struct nvmet_pr *pr = &req->ns->pr;
+ uuid_t hostid;
+
+ list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) {
+ if (reg->rkey == prkey) {
+ status = NVME_SC_SUCCESS;
+ uuid_copy(&hostid, &reg->hostid);
+ if (abort)
+ nvmet_pr_set_ctrl_to_abort(req, &hostid);
+ nvmet_pr_unregister_one(pr, reg);
+ if (!uuid_equal(&hostid, send_hostid))
+ nvmet_pr_registration_preempted(pr, &hostid);
+ }
+ }
+ return status;
+}
+
+static void nvmet_pr_unreg_all_others_by_prkey(struct nvmet_req *req,
+ u64 prkey,
+ uuid_t *send_hostid,
+ bool abort)
+{
+ struct nvmet_pr_registrant *reg, *tmp;
+ struct nvmet_pr *pr = &req->ns->pr;
+ uuid_t hostid;
+
+ list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) {
+ if (reg->rkey == prkey &&
+ !uuid_equal(&reg->hostid, send_hostid)) {
+ uuid_copy(&hostid, &reg->hostid);
+ if (abort)
+ nvmet_pr_set_ctrl_to_abort(req, &hostid);
+ nvmet_pr_unregister_one(pr, reg);
+ nvmet_pr_registration_preempted(pr, &hostid);
+ }
+ }
+}
+
+static void nvmet_pr_unreg_all_others(struct nvmet_req *req,
+ uuid_t *send_hostid,
+ bool abort)
+{
+ struct nvmet_pr_registrant *reg, *tmp;
+ struct nvmet_pr *pr = &req->ns->pr;
+ uuid_t hostid;
+
+ list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) {
+ if (!uuid_equal(&reg->hostid, send_hostid)) {
+ uuid_copy(&hostid, &reg->hostid);
+ if (abort)
+ nvmet_pr_set_ctrl_to_abort(req, &hostid);
+ nvmet_pr_unregister_one(pr, reg);
+ nvmet_pr_registration_preempted(pr, &hostid);
+ }
+ }
+}
+
+static void nvmet_pr_update_holder_rtype(struct nvmet_pr_registrant *reg,
+ void *attr)
+{
+ u8 new_rtype = *(u8 *)attr;
+
+ reg->rtype = new_rtype;
+}
+
+static u16 nvmet_pr_preempt(struct nvmet_req *req,
+ struct nvmet_pr_registrant *reg,
+ u8 rtype,
+ struct nvmet_pr_acquire_data *d,
+ bool abort)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_registrant *holder;
+ enum nvme_pr_type original_rtype;
+ u64 prkey = le64_to_cpu(d->prkey);
+ u16 status;
+
+ holder = rcu_dereference_protected(pr->holder, 1);
+ if (!holder)
+ return nvmet_pr_unreg_all_host_by_prkey(req, prkey,
+ &ctrl->hostid, abort);
+
+ original_rtype = holder->rtype;
+ if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS ||
+ original_rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) {
+ if (!prkey) {
+ /*
+ * To prevent possible access from other hosts, and
+ * avoid terminate the holder, set the new holder
+ * first before unregistering.
+ */
+ nvmet_pr_set_new_holder(pr, rtype, reg);
+ nvmet_pr_unreg_all_others(req, &ctrl->hostid, abort);
+ return NVME_SC_SUCCESS;
+ }
+ return nvmet_pr_unreg_all_host_by_prkey(req, prkey,
+ &ctrl->hostid, abort);
+ }
+
+ if (holder == reg) {
+ status = nvmet_pr_update_reg_attr(pr, holder,
+ nvmet_pr_update_holder_rtype, &rtype);
+ if (!status && original_rtype != rtype)
+ nvmet_pr_resv_released(pr, &reg->hostid);
+ return status;
+ }
+
+ if (prkey == holder->rkey) {
+ /*
+ * Same as before, set the new holder first.
+ */
+ nvmet_pr_set_new_holder(pr, rtype, reg);
+ nvmet_pr_unreg_all_others_by_prkey(req, prkey, &ctrl->hostid,
+ abort);
+ if (original_rtype != rtype)
+ nvmet_pr_resv_released(pr, &reg->hostid);
+ return NVME_SC_SUCCESS;
+ }
+
+ if (prkey)
+ return nvmet_pr_unreg_all_host_by_prkey(req, prkey,
+ &ctrl->hostid, abort);
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+}
+
+static void nvmet_pr_do_abort(struct work_struct *w)
+{
+ struct nvmet_req *req = container_of(w, struct nvmet_req, r.abort_work);
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+ struct nvmet_ns *ns = req->ns;
+ unsigned long idx;
+
+ /*
+ * The target does not support abort, just wait per-controller ref to 0.
+ */
+ xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) {
+ if (percpu_ref_is_dying(&pc_ref->ref)) {
+ wait_for_completion(&pc_ref->free_done);
+ reinit_completion(&pc_ref->confirm_done);
+ reinit_completion(&pc_ref->free_done);
+ percpu_ref_resurrect(&pc_ref->ref);
+ }
+ }
+
+ up(&ns->pr.pr_sem);
+ nvmet_req_complete(req, NVME_SC_SUCCESS);
+}
+
+static u16 __nvmet_execute_pr_acquire(struct nvmet_req *req,
+ struct nvmet_pr_registrant *reg,
+ u8 acquire_act,
+ u8 rtype,
+ struct nvmet_pr_acquire_data *d)
+{
+ u16 status;
+
+ switch (acquire_act) {
+ case NVME_PR_ACQUIRE_ACT_ACQUIRE:
+ status = nvmet_pr_acquire(req, reg, rtype);
+ goto out;
+ case NVME_PR_ACQUIRE_ACT_PREEMPT:
+ status = nvmet_pr_preempt(req, reg, rtype, d, false);
+ goto inc_gen;
+ case NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT:
+ status = nvmet_pr_preempt(req, reg, rtype, d, true);
+ goto inc_gen;
+ default:
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ goto out;
+ }
+inc_gen:
+ if (!status)
+ atomic_inc(&req->ns->pr.generation);
+out:
+ return status;
+}
+
+static void nvmet_execute_pr_acquire(struct nvmet_req *req)
+{
+ u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+ bool ignore_key = nvmet_pr_parse_ignore_key(cdw10);
+ /* Reservation type, bit 15:08 */
+ u8 rtype = (u8)((cdw10 >> 8) & 0xff);
+ /* Reservation acquire action, bit 02:00 */
+ u8 acquire_act = cdw10 & 0x07;
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_pr_acquire_data *d = NULL;
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_registrant *reg;
+ u16 status = NVME_SC_SUCCESS;
+
+ if (ignore_key ||
+ rtype < NVME_PR_WRITE_EXCLUSIVE ||
+ rtype > NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) {
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ d = kmalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (status)
+ goto free_data;
+
+ status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ down(&pr->pr_sem);
+ list_for_each_entry_rcu(reg, &pr->registrant_list, entry) {
+ if (uuid_equal(&reg->hostid, &ctrl->hostid) &&
+ reg->rkey == le64_to_cpu(d->crkey)) {
+ status = __nvmet_execute_pr_acquire(req, reg,
+ acquire_act, rtype, d);
+ break;
+ }
+ }
+
+ if (!status && acquire_act == NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT) {
+ kfree(d);
+ INIT_WORK(&req->r.abort_work, nvmet_pr_do_abort);
+ queue_work(nvmet_wq, &req->r.abort_work);
+ return;
+ }
+
+ up(&pr->pr_sem);
+
+free_data:
+ kfree(d);
+out:
+ nvmet_req_complete(req, status);
+}
+
+static u16 nvmet_pr_release(struct nvmet_req *req,
+ struct nvmet_pr_registrant *reg,
+ u8 rtype)
+{
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_registrant *holder;
+ u8 original_rtype;
+
+ holder = rcu_dereference_protected(pr->holder, 1);
+ if (!holder || reg != holder)
+ return NVME_SC_SUCCESS;
+
+ original_rtype = holder->rtype;
+ if (original_rtype != rtype)
+ return NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+
+ rcu_assign_pointer(pr->holder, NULL);
+
+ if (original_rtype != NVME_PR_WRITE_EXCLUSIVE &&
+ original_rtype != NVME_PR_EXCLUSIVE_ACCESS)
+ nvmet_pr_resv_released(pr, &reg->hostid);
+
+ return NVME_SC_SUCCESS;
+}
+
+static void nvmet_pr_clear(struct nvmet_req *req)
+{
+ struct nvmet_pr_registrant *reg, *tmp;
+ struct nvmet_pr *pr = &req->ns->pr;
+
+ rcu_assign_pointer(pr->holder, NULL);
+
+ list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) {
+ list_del_rcu(&reg->entry);
+ if (!uuid_equal(&req->sq->ctrl->hostid, &reg->hostid))
+ nvmet_pr_resv_preempted(pr, &reg->hostid);
+ kfree_rcu(reg, rcu);
+ }
+
+ atomic_inc(&pr->generation);
+}
+
+static u16 __nvmet_execute_pr_release(struct nvmet_req *req,
+ struct nvmet_pr_registrant *reg,
+ u8 release_act, u8 rtype)
+{
+ switch (release_act) {
+ case NVME_PR_RELEASE_ACT_RELEASE:
+ return nvmet_pr_release(req, reg, rtype);
+ case NVME_PR_RELEASE_ACT_CLEAR:
+ nvmet_pr_clear(req);
+ return NVME_SC_SUCCESS;
+ default:
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+}
+
+static void nvmet_execute_pr_release(struct nvmet_req *req)
+{
+ u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+ bool ignore_key = nvmet_pr_parse_ignore_key(cdw10);
+ u8 rtype = (u8)((cdw10 >> 8) & 0xff); /* Reservation type, bit 15:08 */
+ u8 release_act = cdw10 & 0x07; /* Reservation release action, bit 02:00 */
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_release_data *d;
+ struct nvmet_pr_registrant *reg;
+ u16 status;
+
+ if (ignore_key) {
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ d = kmalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+
+ status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (status)
+ goto free_data;
+
+ status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ down(&pr->pr_sem);
+ list_for_each_entry_rcu(reg, &pr->registrant_list, entry) {
+ if (uuid_equal(&reg->hostid, &ctrl->hostid) &&
+ reg->rkey == le64_to_cpu(d->crkey)) {
+ status = __nvmet_execute_pr_release(req, reg,
+ release_act, rtype);
+ break;
+ }
+ }
+ up(&pr->pr_sem);
+free_data:
+ kfree(d);
+out:
+ nvmet_req_complete(req, status);
+}
+
+static void nvmet_execute_pr_report(struct nvmet_req *req)
+{
+ u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
+ u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+ u32 num_bytes = 4 * (cdw10 + 1); /* cdw10 is number of dwords */
+ u8 eds = cdw11 & 1; /* Extended data structure, bit 00 */
+ struct nvme_registered_ctrl_ext *ctrl_eds;
+ struct nvme_reservation_status_ext *data;
+ struct nvmet_pr *pr = &req->ns->pr;
+ struct nvmet_pr_registrant *holder;
+ struct nvmet_pr_registrant *reg;
+ u16 num_ctrls = 0;
+ u16 status;
+ u8 rtype;
+
+ /* nvmet hostid(uuid_t) is 128 bit. */
+ if (!eds) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw11);
+ status = NVME_SC_HOST_ID_INCONSIST | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ if (num_bytes < sizeof(struct nvme_reservation_status_ext)) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ data = kzalloc(num_bytes, GFP_KERNEL);
+ if (!data) {
+ status = NVME_SC_INTERNAL;
+ goto out;
+ }
+ data->gen = cpu_to_le32(atomic_read(&pr->generation));
+ data->ptpls = 0;
+ ctrl_eds = data->regctl_eds;
+
+ rcu_read_lock();
+ holder = rcu_dereference(pr->holder);
+ rtype = holder ? holder->rtype : 0;
+ data->rtype = rtype;
+
+ list_for_each_entry_rcu(reg, &pr->registrant_list, entry) {
+ num_ctrls++;
+ /*
+ * continue to get the number of all registrans.
+ */
+ if (((void *)ctrl_eds + sizeof(*ctrl_eds)) >
+ ((void *)data + num_bytes))
+ continue;
+ /*
+ * Dynamic controller, set cntlid to 0xffff.
+ */
+ ctrl_eds->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC);
+ if (rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS ||
+ rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS)
+ ctrl_eds->rcsts = 1;
+ if (reg == holder)
+ ctrl_eds->rcsts = 1;
+ uuid_copy((uuid_t *)&ctrl_eds->hostid, &reg->hostid);
+ ctrl_eds->rkey = cpu_to_le64(reg->rkey);
+ ctrl_eds++;
+ }
+ rcu_read_unlock();
+
+ put_unaligned_le16(num_ctrls, data->regctl);
+ status = nvmet_copy_to_sgl(req, 0, data, num_bytes);
+ kfree(data);
+out:
+ nvmet_req_complete(req, status);
+}
+
+u16 nvmet_parse_pr_cmd(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+
+ switch (cmd->common.opcode) {
+ case nvme_cmd_resv_register:
+ req->execute = nvmet_execute_pr_register;
+ break;
+ case nvme_cmd_resv_acquire:
+ req->execute = nvmet_execute_pr_acquire;
+ break;
+ case nvme_cmd_resv_release:
+ req->execute = nvmet_execute_pr_release;
+ break;
+ case nvme_cmd_resv_report:
+ req->execute = nvmet_execute_pr_report;
+ break;
+ default:
+ return 1;
+ }
+ return NVME_SC_SUCCESS;
+}
+
+static bool nvmet_is_req_write_cmd_group(struct nvmet_req *req)
+{
+ u8 opcode = req->cmd->common.opcode;
+
+ if (req->sq->qid) {
+ switch (opcode) {
+ case nvme_cmd_flush:
+ case nvme_cmd_write:
+ case nvme_cmd_write_zeroes:
+ case nvme_cmd_dsm:
+ case nvme_cmd_zone_append:
+ case nvme_cmd_zone_mgmt_send:
+ return true;
+ default:
+ return false;
+ }
+ }
+ return false;
+}
+
+static bool nvmet_is_req_read_cmd_group(struct nvmet_req *req)
+{
+ u8 opcode = req->cmd->common.opcode;
+
+ if (req->sq->qid) {
+ switch (opcode) {
+ case nvme_cmd_read:
+ case nvme_cmd_zone_mgmt_recv:
+ return true;
+ default:
+ return false;
+ }
+ }
+ return false;
+}
+
+u16 nvmet_pr_check_cmd_access(struct nvmet_req *req)
+{
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ struct nvmet_pr_registrant *holder;
+ struct nvmet_ns *ns = req->ns;
+ struct nvmet_pr *pr = &ns->pr;
+ u16 status = NVME_SC_SUCCESS;
+
+ rcu_read_lock();
+ holder = rcu_dereference(pr->holder);
+ if (!holder)
+ goto unlock;
+ if (uuid_equal(&ctrl->hostid, &holder->hostid))
+ goto unlock;
+
+ /*
+ * The Reservation command group is checked in executing,
+ * allow it here.
+ */
+ switch (holder->rtype) {
+ case NVME_PR_WRITE_EXCLUSIVE:
+ if (nvmet_is_req_write_cmd_group(req))
+ status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ break;
+ case NVME_PR_EXCLUSIVE_ACCESS:
+ if (nvmet_is_req_read_cmd_group(req) ||
+ nvmet_is_req_write_cmd_group(req))
+ status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ break;
+ case NVME_PR_WRITE_EXCLUSIVE_REG_ONLY:
+ case NVME_PR_WRITE_EXCLUSIVE_ALL_REGS:
+ if ((nvmet_is_req_write_cmd_group(req)) &&
+ !nvmet_pr_find_registrant(pr, &ctrl->hostid))
+ status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ break;
+ case NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY:
+ case NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS:
+ if ((nvmet_is_req_read_cmd_group(req) ||
+ nvmet_is_req_write_cmd_group(req)) &&
+ !nvmet_pr_find_registrant(pr, &ctrl->hostid))
+ status = NVME_SC_RESERVATION_CONFLICT | NVME_STATUS_DNR;
+ break;
+ default:
+ pr_warn("the reservation type is set wrong, type:%d\n",
+ holder->rtype);
+ break;
+ }
+
+unlock:
+ rcu_read_unlock();
+ if (status)
+ req->error_loc = offsetof(struct nvme_common_command, opcode);
+ return status;
+}
+
+u16 nvmet_pr_get_ns_pc_ref(struct nvmet_req *req)
+{
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+
+ pc_ref = xa_load(&req->ns->pr_per_ctrl_refs,
+ req->sq->ctrl->cntlid);
+ if (unlikely(!percpu_ref_tryget_live(&pc_ref->ref)))
+ return NVME_SC_INTERNAL;
+ req->pc_ref = pc_ref;
+ return NVME_SC_SUCCESS;
+}
+
+static void nvmet_pr_ctrl_ns_all_cmds_done(struct percpu_ref *ref)
+{
+ struct nvmet_pr_per_ctrl_ref *pc_ref =
+ container_of(ref, struct nvmet_pr_per_ctrl_ref, ref);
+
+ complete(&pc_ref->free_done);
+}
+
+static int nvmet_pr_alloc_and_insert_pc_ref(struct nvmet_ns *ns,
+ unsigned long idx,
+ uuid_t *hostid)
+{
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+ int ret;
+
+ pc_ref = kmalloc(sizeof(*pc_ref), GFP_ATOMIC);
+ if (!pc_ref)
+ return -ENOMEM;
+
+ ret = percpu_ref_init(&pc_ref->ref, nvmet_pr_ctrl_ns_all_cmds_done,
+ PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
+ if (ret)
+ goto free;
+
+ init_completion(&pc_ref->free_done);
+ init_completion(&pc_ref->confirm_done);
+ uuid_copy(&pc_ref->hostid, hostid);
+
+ ret = xa_insert(&ns->pr_per_ctrl_refs, idx, pc_ref, GFP_KERNEL);
+ if (ret)
+ goto exit;
+ return ret;
+exit:
+ percpu_ref_exit(&pc_ref->ref);
+free:
+ kfree(pc_ref);
+ return ret;
+}
+
+int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl)
+{
+ struct nvmet_subsys *subsys = ctrl->subsys;
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+ struct nvmet_ns *ns = NULL;
+ unsigned long idx;
+ int ret;
+
+ ctrl->pr_log_mgr.counter = 0;
+ ctrl->pr_log_mgr.lost_count = 0;
+ mutex_init(&ctrl->pr_log_mgr.lock);
+ INIT_KFIFO(ctrl->pr_log_mgr.log_queue);
+
+ /*
+ * Here we are under subsys lock, if an ns not in subsys->namespaces,
+ * we can make sure that ns is not enabled, and not call
+ * nvmet_pr_init_ns(), see more details in nvmet_ns_enable().
+ * So just check ns->pr.enable.
+ */
+ nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) {
+ if (ns->pr.enable) {
+ ret = nvmet_pr_alloc_and_insert_pc_ref(ns, ctrl->cntlid,
+ &ctrl->hostid);
+ if (ret)
+ goto free_per_ctrl_refs;
+ }
+ }
+ return 0;
+
+free_per_ctrl_refs:
+ nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) {
+ if (ns->pr.enable) {
+ pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid);
+ if (pc_ref)
+ percpu_ref_exit(&pc_ref->ref);
+ kfree(pc_ref);
+ }
+ }
+ return ret;
+}
+
+void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl)
+{
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+ struct nvmet_ns *ns;
+ unsigned long idx;
+
+ kfifo_free(&ctrl->pr_log_mgr.log_queue);
+ mutex_destroy(&ctrl->pr_log_mgr.lock);
+
+ nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) {
+ if (ns->pr.enable) {
+ pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid);
+ if (pc_ref)
+ percpu_ref_exit(&pc_ref->ref);
+ kfree(pc_ref);
+ }
+ }
+}
+
+int nvmet_pr_init_ns(struct nvmet_ns *ns)
+{
+ struct nvmet_subsys *subsys = ns->subsys;
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+ struct nvmet_ctrl *ctrl = NULL;
+ unsigned long idx;
+ int ret;
+
+ ns->pr.holder = NULL;
+ atomic_set(&ns->pr.generation, 0);
+ sema_init(&ns->pr.pr_sem, 1);
+ INIT_LIST_HEAD(&ns->pr.registrant_list);
+ ns->pr.notify_mask = 0;
+
+ xa_init(&ns->pr_per_ctrl_refs);
+
+ list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+ ret = nvmet_pr_alloc_and_insert_pc_ref(ns, ctrl->cntlid,
+ &ctrl->hostid);
+ if (ret)
+ goto free_per_ctrl_refs;
+ }
+ return 0;
+
+free_per_ctrl_refs:
+ xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) {
+ xa_erase(&ns->pr_per_ctrl_refs, idx);
+ percpu_ref_exit(&pc_ref->ref);
+ kfree(pc_ref);
+ }
+ return ret;
+}
+
+void nvmet_pr_exit_ns(struct nvmet_ns *ns)
+{
+ struct nvmet_pr_registrant *reg, *tmp;
+ struct nvmet_pr_per_ctrl_ref *pc_ref;
+ struct nvmet_pr *pr = &ns->pr;
+ unsigned long idx;
+
+ list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) {
+ list_del(&reg->entry);
+ kfree(reg);
+ }
+
+ xa_for_each(&ns->pr_per_ctrl_refs, idx, pc_ref) {
+ /*
+ * No command on ns here, we can safely free pc_ref.
+ */
+ pc_ref = xa_erase(&ns->pr_per_ctrl_refs, idx);
+ percpu_ref_exit(&pc_ref->ref);
+ kfree(pc_ref);
+ }
+
+ xa_destroy(&ns->pr_per_ctrl_refs);
+}
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 3a0f2c170f4c..2a4536ef6184 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -16,7 +16,7 @@
#include <linux/string.h>
#include <linux/wait.h>
#include <linux/inet.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
@@ -39,6 +39,8 @@
#define NVMET_RDMA_BACKLOG 128
+#define NVMET_RDMA_DISCRETE_RSP_TAG -1
+
struct nvmet_rdma_srq;
struct nvmet_rdma_cmd {
@@ -53,7 +55,6 @@ struct nvmet_rdma_cmd {
enum {
NVMET_RDMA_REQ_INLINE_DATA = (1 << 0),
- NVMET_RDMA_REQ_INVALIDATE_RKEY = (1 << 1),
};
struct nvmet_rdma_rsp {
@@ -76,7 +77,7 @@ struct nvmet_rdma_rsp {
u32 invalidate_rkey;
struct list_head wait_list;
- struct list_head free_list;
+ int tag;
};
enum nvmet_rdma_queue_state {
@@ -99,8 +100,7 @@ struct nvmet_rdma_queue {
struct nvmet_sq nvme_sq;
struct nvmet_rdma_rsp *rsps;
- struct list_head free_rsps;
- spinlock_t rsps_lock;
+ struct sbitmap rsp_tags;
struct nvmet_rdma_cmd *cmds;
struct work_struct release_work;
@@ -173,7 +173,8 @@ static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev,
struct nvmet_rdma_rsp *r);
static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
- struct nvmet_rdma_rsp *r);
+ struct nvmet_rdma_rsp *r,
+ int tag);
static const struct nvmet_fabrics_ops nvmet_rdma_ops;
@@ -211,15 +212,12 @@ static inline bool nvmet_rdma_need_data_out(struct nvmet_rdma_rsp *rsp)
static inline struct nvmet_rdma_rsp *
nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
{
- struct nvmet_rdma_rsp *rsp;
- unsigned long flags;
+ struct nvmet_rdma_rsp *rsp = NULL;
+ int tag;
- spin_lock_irqsave(&queue->rsps_lock, flags);
- rsp = list_first_entry_or_null(&queue->free_rsps,
- struct nvmet_rdma_rsp, free_list);
- if (likely(rsp))
- list_del(&rsp->free_list);
- spin_unlock_irqrestore(&queue->rsps_lock, flags);
+ tag = sbitmap_get(&queue->rsp_tags);
+ if (tag >= 0)
+ rsp = &queue->rsps[tag];
if (unlikely(!rsp)) {
int ret;
@@ -227,13 +225,12 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
rsp = kzalloc(sizeof(*rsp), GFP_KERNEL);
if (unlikely(!rsp))
return NULL;
- ret = nvmet_rdma_alloc_rsp(queue->dev, rsp);
+ ret = nvmet_rdma_alloc_rsp(queue->dev, rsp,
+ NVMET_RDMA_DISCRETE_RSP_TAG);
if (unlikely(ret)) {
kfree(rsp);
return NULL;
}
-
- rsp->allocated = true;
}
return rsp;
@@ -242,17 +239,13 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
static inline void
nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
{
- unsigned long flags;
-
- if (unlikely(rsp->allocated)) {
+ if (unlikely(rsp->tag == NVMET_RDMA_DISCRETE_RSP_TAG)) {
nvmet_rdma_free_rsp(rsp->queue->dev, rsp);
kfree(rsp);
return;
}
- spin_lock_irqsave(&rsp->queue->rsps_lock, flags);
- list_add_tail(&rsp->free_list, &rsp->queue->free_rsps);
- spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
+ sbitmap_clear_bit(&rsp->queue->rsp_tags, rsp->tag);
}
static void nvmet_rdma_free_inline_pages(struct nvmet_rdma_device *ndev,
@@ -405,7 +398,7 @@ static void nvmet_rdma_free_cmds(struct nvmet_rdma_device *ndev,
}
static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
- struct nvmet_rdma_rsp *r)
+ struct nvmet_rdma_rsp *r, int tag)
{
/* NVMe CQE / RDMA SEND */
r->req.cqe = kmalloc(sizeof(*r->req.cqe), GFP_KERNEL);
@@ -433,6 +426,7 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
r->read_cqe.done = nvmet_rdma_read_data_done;
/* Data Out / RDMA WRITE */
r->write_cqe.done = nvmet_rdma_write_data_done;
+ r->tag = tag;
return 0;
@@ -455,33 +449,33 @@ nvmet_rdma_alloc_rsps(struct nvmet_rdma_queue *queue)
{
struct nvmet_rdma_device *ndev = queue->dev;
int nr_rsps = queue->recv_queue_size * 2;
- int ret = -EINVAL, i;
+ int ret = -ENOMEM, i;
+
+ if (sbitmap_init_node(&queue->rsp_tags, nr_rsps, -1, GFP_KERNEL,
+ NUMA_NO_NODE, false, true))
+ goto out;
queue->rsps = kcalloc(nr_rsps, sizeof(struct nvmet_rdma_rsp),
GFP_KERNEL);
if (!queue->rsps)
- goto out;
+ goto out_free_sbitmap;
for (i = 0; i < nr_rsps; i++) {
struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
- ret = nvmet_rdma_alloc_rsp(ndev, rsp);
+ ret = nvmet_rdma_alloc_rsp(ndev, rsp, i);
if (ret)
goto out_free;
-
- list_add_tail(&rsp->free_list, &queue->free_rsps);
}
return 0;
out_free:
- while (--i >= 0) {
- struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
-
- list_del(&rsp->free_list);
- nvmet_rdma_free_rsp(ndev, rsp);
- }
+ while (--i >= 0)
+ nvmet_rdma_free_rsp(ndev, &queue->rsps[i]);
kfree(queue->rsps);
+out_free_sbitmap:
+ sbitmap_free(&queue->rsp_tags);
out:
return ret;
}
@@ -491,13 +485,10 @@ static void nvmet_rdma_free_rsps(struct nvmet_rdma_queue *queue)
struct nvmet_rdma_device *ndev = queue->dev;
int i, nr_rsps = queue->recv_queue_size * 2;
- for (i = 0; i < nr_rsps; i++) {
- struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
-
- list_del(&rsp->free_list);
- nvmet_rdma_free_rsp(ndev, rsp);
- }
+ for (i = 0; i < nr_rsps; i++)
+ nvmet_rdma_free_rsp(ndev, &queue->rsps[i]);
kfree(queue->rsps);
+ sbitmap_free(&queue->rsp_tags);
}
static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
@@ -587,8 +578,8 @@ static void nvmet_rdma_set_sig_domain(struct blk_integrity *bi,
if (control & NVME_RW_PRINFO_PRCHK_REF)
domain->sig.dif.ref_remap = true;
- domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.apptag);
- domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.appmask);
+ domain->sig.dif.app_tag = le16_to_cpu(cmd->rw.lbat);
+ domain->sig.dif.apptag_check_mask = le16_to_cpu(cmd->rw.lbatm);
domain->sig.dif.app_escape = true;
if (pi_type == NVME_NS_DPS_PI_TYPE3)
domain->sig.dif.ref_escape = true;
@@ -722,7 +713,7 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
struct rdma_cm_id *cm_id = rsp->queue->cm_id;
struct ib_send_wr *first_wr;
- if (rsp->flags & NVMET_RDMA_REQ_INVALIDATE_RKEY) {
+ if (rsp->invalidate_rkey) {
rsp->send_wr.opcode = IB_WR_SEND_WITH_INV;
rsp->send_wr.ex.invalidate_rkey = rsp->invalidate_rkey;
} else {
@@ -861,12 +852,12 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
if (!nvme_is_write(rsp->req.cmd)) {
rsp->req.error_loc =
offsetof(struct nvme_common_command, opcode);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
if (off + len > rsp->queue->dev->inline_data_size) {
pr_err("invalid inline data offset!\n");
- return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
+ return NVME_SC_SGL_INVALID_OFFSET | NVME_STATUS_DNR;
}
/* no data command? */
@@ -905,10 +896,8 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
goto error_out;
rsp->n_rdma += ret;
- if (invalidate) {
+ if (invalidate)
rsp->invalidate_rkey = key;
- rsp->flags |= NVMET_RDMA_REQ_INVALIDATE_RKEY;
- }
return 0;
@@ -930,7 +919,7 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
pr_err("invalid SGL subtype: %#x\n", sgl->type);
rsp->req.error_loc =
offsetof(struct nvme_common_command, dptr);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
case NVME_KEY_SGL_FMT_DATA_DESC:
switch (sgl->type & 0xf) {
@@ -942,12 +931,12 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
pr_err("invalid SGL subtype: %#x\n", sgl->type);
rsp->req.error_loc =
offsetof(struct nvme_common_command, dptr);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
default:
pr_err("invalid SGL type: %#x\n", sgl->type);
rsp->req.error_loc = offsetof(struct nvme_common_command, dptr);
- return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR;
+ return NVME_SC_SGL_INVALID_TYPE | NVME_STATUS_DNR;
}
}
@@ -1007,6 +996,27 @@ out_err:
nvmet_req_complete(&cmd->req, status);
}
+static bool nvmet_rdma_recv_not_live(struct nvmet_rdma_queue *queue,
+ struct nvmet_rdma_rsp *rsp)
+{
+ unsigned long flags;
+ bool ret = true;
+
+ spin_lock_irqsave(&queue->state_lock, flags);
+ /*
+ * recheck queue state is not live to prevent a race condition
+ * with RDMA_CM_EVENT_ESTABLISHED handler.
+ */
+ if (queue->state == NVMET_RDMA_Q_LIVE)
+ ret = false;
+ else if (queue->state == NVMET_RDMA_Q_CONNECTING)
+ list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
+ else
+ nvmet_rdma_put_rsp(rsp);
+ spin_unlock_irqrestore(&queue->state_lock, flags);
+ return ret;
+}
+
static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
{
struct nvmet_rdma_cmd *cmd =
@@ -1047,18 +1057,11 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
rsp->req.cmd = cmd->nvme_cmd;
rsp->req.port = queue->port;
rsp->n_rdma = 0;
+ rsp->invalidate_rkey = 0;
- if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
- unsigned long flags;
-
- spin_lock_irqsave(&queue->state_lock, flags);
- if (queue->state == NVMET_RDMA_Q_CONNECTING)
- list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
- else
- nvmet_rdma_put_rsp(rsp);
- spin_unlock_irqrestore(&queue->state_lock, flags);
+ if (unlikely(queue->state != NVMET_RDMA_Q_LIVE) &&
+ nvmet_rdma_recv_not_live(queue, rsp))
return;
- }
nvmet_rdma_handle_command(queue, rsp);
}
@@ -1457,8 +1460,6 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
INIT_LIST_HEAD(&queue->rsp_wait_list);
INIT_LIST_HEAD(&queue->rsp_wr_wait_list);
spin_lock_init(&queue->rsp_wr_wait_lock);
- INIT_LIST_HEAD(&queue->free_rsps);
- spin_lock_init(&queue->rsps_lock);
INIT_LIST_HEAD(&queue->queue_list);
queue->idx = ida_alloc(&nvmet_rdma_queue_ida, GFP_KERNEL);
@@ -1816,18 +1817,14 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
static void nvmet_rdma_delete_ctrl(struct nvmet_ctrl *ctrl)
{
- struct nvmet_rdma_queue *queue;
+ struct nvmet_rdma_queue *queue, *n;
-restart:
mutex_lock(&nvmet_rdma_queue_mutex);
- list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) {
- if (queue->nvme_sq.ctrl == ctrl) {
- list_del_init(&queue->queue_list);
- mutex_unlock(&nvmet_rdma_queue_mutex);
-
- __nvmet_rdma_queue_disconnect(queue);
- goto restart;
- }
+ list_for_each_entry_safe(queue, n, &nvmet_rdma_queue_list, queue_list) {
+ if (queue->nvme_sq.ctrl != ctrl)
+ continue;
+ list_del_init(&queue->queue_list);
+ __nvmet_rdma_queue_disconnect(queue);
}
mutex_unlock(&nvmet_rdma_queue_mutex);
}
@@ -1956,6 +1953,14 @@ static int nvmet_rdma_add_port(struct nvmet_port *nport)
nport->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
}
+ if (nport->max_queue_size < 0) {
+ nport->max_queue_size = NVME_RDMA_DEFAULT_QUEUE_SIZE;
+ } else if (nport->max_queue_size > NVME_RDMA_MAX_QUEUE_SIZE) {
+ pr_warn("max_queue_size %u is too large, reducing to %u\n",
+ nport->max_queue_size, NVME_RDMA_MAX_QUEUE_SIZE);
+ nport->max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+ }
+
ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr,
nport->disc_addr.trsvcid, &port->addr);
if (ret) {
@@ -2006,6 +2011,17 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
}
}
+static ssize_t nvmet_rdma_host_port_addr(struct nvmet_ctrl *ctrl,
+ char *traddr, size_t traddr_len)
+{
+ struct nvmet_sq *nvme_sq = ctrl->sqs[0];
+ struct nvmet_rdma_queue *queue =
+ container_of(nvme_sq, struct nvmet_rdma_queue, nvme_sq);
+
+ return snprintf(traddr, traddr_len, "%pISc",
+ (struct sockaddr *)&queue->cm_id->route.addr.dst_addr);
+}
+
static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
{
if (ctrl->pi_support)
@@ -2015,6 +2031,8 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl)
{
+ if (ctrl->pi_support)
+ return NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
return NVME_RDMA_MAX_QUEUE_SIZE;
}
@@ -2028,6 +2046,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.queue_response = nvmet_rdma_queue_response,
.delete_ctrl = nvmet_rdma_delete_ctrl,
.disc_traddr = nvmet_rdma_disc_port_addr,
+ .host_traddr = nvmet_rdma_host_port_addr,
.get_mdts = nvmet_rdma_get_mdts,
.get_max_queue_size = nvmet_rdma_get_max_queue_size,
};
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index c8655fc5aa5b..4f9cac8a5abe 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,6 +348,7 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu)
return 0;
}
+/* If cmd buffers are NULL, no operation is performed */
static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd)
{
kfree(cmd->iov);
@@ -415,10 +416,10 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) |
NVME_SGL_FMT_OFFSET)) {
if (!nvme_is_write(cmd->req.cmd))
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
if (len > cmd->req.port->inline_data_size)
- return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
+ return NVME_SC_SGL_INVALID_OFFSET | NVME_STATUS_DNR;
cmd->pdu_len = len;
}
cmd->req.transfer_len += len;
@@ -570,10 +571,16 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
struct nvmet_tcp_cmd *cmd =
container_of(req, struct nvmet_tcp_cmd, req);
struct nvmet_tcp_queue *queue = cmd->queue;
+ enum nvmet_tcp_recv_state queue_state;
+ struct nvmet_tcp_cmd *queue_cmd;
struct nvme_sgl_desc *sgl;
u32 len;
- if (unlikely(cmd == queue->cmd)) {
+ /* Pairs with store_release in nvmet_prepare_receive_pdu() */
+ queue_state = smp_load_acquire(&queue->rcv_state);
+ queue_cmd = READ_ONCE(queue->cmd);
+
+ if (unlikely(cmd == queue_cmd)) {
sgl = &cmd->req.cmd->common.dptr.sgl;
len = le32_to_cpu(sgl->length);
@@ -582,7 +589,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
* Avoid using helpers, this might happen before
* nvmet_req_init is completed.
*/
- if (queue->rcv_state == NVMET_TCP_RECV_PDU &&
+ if (queue_state == NVMET_TCP_RECV_PDU &&
len && len <= cmd->req.port->inline_data_size &&
nvme_is_write(cmd->req.cmd))
return;
@@ -846,8 +853,9 @@ static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue)
{
queue->offset = 0;
queue->left = sizeof(struct nvme_tcp_hdr);
- queue->cmd = NULL;
- queue->rcv_state = NVMET_TCP_RECV_PDU;
+ WRITE_ONCE(queue->cmd, NULL);
+ /* Ensure rcv_state is visible only after queue->cmd is set */
+ smp_store_release(&queue->rcv_state, NVMET_TCP_RECV_PDU);
}
static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue)
@@ -898,6 +906,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
pr_err("bad nvme-tcp pdu length (%d)\n",
le32_to_cpu(icreq->hdr.plen));
nvmet_tcp_fatal_error(queue);
+ return -EPROTO;
}
if (icreq->pfv != NVME_TCP_PFV_1_0) {
@@ -1580,18 +1589,13 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue)
struct nvmet_tcp_cmd *cmd = queue->cmds;
int i;
- for (i = 0; i < queue->nr_cmds; i++, cmd++) {
- if (nvmet_tcp_need_data_in(cmd))
- nvmet_tcp_free_cmd_buffers(cmd);
- }
-
- if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect))
- nvmet_tcp_free_cmd_buffers(&queue->connect);
+ for (i = 0; i < queue->nr_cmds; i++, cmd++)
+ nvmet_tcp_free_cmd_buffers(cmd);
+ nvmet_tcp_free_cmd_buffers(&queue->connect);
}
static void nvmet_tcp_release_queue_work(struct work_struct *w)
{
- struct page *page;
struct nvmet_tcp_queue *queue =
container_of(w, struct nvmet_tcp_queue, release_work);
@@ -1615,8 +1619,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
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);
+ page_frag_cache_drain(&queue->pf_cache);
kfree(queue);
}
@@ -2150,8 +2153,10 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq)
}
queue->nr_cmds = sq->size * 2;
- if (nvmet_tcp_alloc_cmds(queue))
+ if (nvmet_tcp_alloc_cmds(queue)) {
+ queue->nr_cmds = 0;
return NVME_SC_INTERNAL;
+ }
return 0;
}
@@ -2171,6 +2176,19 @@ static void nvmet_tcp_disc_port_addr(struct nvmet_req *req,
}
}
+static ssize_t nvmet_tcp_host_port_addr(struct nvmet_ctrl *ctrl,
+ char *traddr, size_t traddr_len)
+{
+ struct nvmet_sq *sq = ctrl->sqs[0];
+ struct nvmet_tcp_queue *queue =
+ container_of(sq, struct nvmet_tcp_queue, nvme_sq);
+
+ if (queue->sockaddr_peer.ss_family == AF_UNSPEC)
+ return -EINVAL;
+ return snprintf(traddr, traddr_len, "%pISc",
+ (struct sockaddr *)&queue->sockaddr_peer);
+}
+
static const struct nvmet_fabrics_ops nvmet_tcp_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_TCP,
@@ -2181,6 +2199,7 @@ static const struct nvmet_fabrics_ops nvmet_tcp_ops = {
.delete_ctrl = nvmet_tcp_delete_ctrl,
.install_queue = nvmet_tcp_install_queue,
.disc_traddr = nvmet_tcp_disc_port_addr,
+ .host_traddr = nvmet_tcp_host_port_addr,
};
static int __init nvmet_tcp_init(void)
diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c
index 6ee1f3db81d0..6dbc7036f2e4 100644
--- a/drivers/nvme/target/trace.c
+++ b/drivers/nvme/target/trace.c
@@ -4,7 +4,7 @@
* Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "trace.h"
static const char *nvmet_trace_admin_identify(struct trace_seq *p, u8 *cdw10)
@@ -119,6 +119,167 @@ const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p,
}
}
+static const char *nvmet_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const zsa_strs[] = {
+ [0x01] = "close zone",
+ [0x02] = "finish zone",
+ [0x03] = "open zone",
+ [0x04] = "reset zone",
+ [0x05] = "offline zone",
+ [0x10] = "set zone descriptor extension"
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u64 slba = get_unaligned_le64(cdw10);
+ const char *zsa_str;
+ u8 zsa = cdw10[12];
+ u8 all = cdw10[13];
+
+ if (zsa < ARRAY_SIZE(zsa_strs) && zsa_strs[zsa])
+ zsa_str = zsa_strs[zsa];
+ else
+ zsa_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, zsa=%u:%s, all=%u",
+ slba, zsa, zsa_str, all);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvmet_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const zrasf_strs[] = {
+ [0x00] = "list all zones",
+ [0x01] = "list the zones in the ZSE: Empty state",
+ [0x02] = "list the zones in the ZSIO: Implicitly Opened state",
+ [0x03] = "list the zones in the ZSEO: Explicitly Opened state",
+ [0x04] = "list the zones in the ZSC: Closed state",
+ [0x05] = "list the zones in the ZSF: Full state",
+ [0x06] = "list the zones in the ZSRO: Read Only state",
+ [0x07] = "list the zones in the ZSO: Offline state",
+ [0x09] = "list the zones that have the zone attribute"
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u64 slba = get_unaligned_le64(cdw10);
+ u32 numd = get_unaligned_le32(&cdw10[8]);
+ u8 zra = cdw10[12];
+ u8 zrasf = cdw10[13];
+ const char *zrasf_str;
+ u8 pr = cdw10[14];
+
+ if (zrasf < ARRAY_SIZE(zrasf_strs) && zrasf_strs[zrasf])
+ zrasf_str = zrasf_strs[zrasf];
+ else
+ zrasf_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u:%s, pr=%u",
+ slba, numd, zra, zrasf, zrasf_str, pr);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvmet_trace_resv_reg(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const rrega_strs[] = {
+ [0x00] = "register",
+ [0x01] = "unregister",
+ [0x02] = "replace",
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 rrega = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 ptpl = (cdw10[3] >> 6) & 0x3;
+ const char *rrega_str;
+
+ if (rrega < ARRAY_SIZE(rrega_strs) && rrega_strs[rrega])
+ rrega_str = rrega_strs[rrega];
+ else
+ rrega_str = "reserved";
+
+ trace_seq_printf(p, "rrega=%u:%s, iekey=%u, ptpl=%u",
+ rrega, rrega_str, iekey, ptpl);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char * const rtype_strs[] = {
+ [0x00] = "reserved",
+ [0x01] = "write exclusive",
+ [0x02] = "exclusive access",
+ [0x03] = "write exclusive registrants only",
+ [0x04] = "exclusive access registrants only",
+ [0x05] = "write exclusive all registrants",
+ [0x06] = "exclusive access all registrants",
+};
+
+static const char *nvmet_trace_resv_acq(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const racqa_strs[] = {
+ [0x00] = "acquire",
+ [0x01] = "preempt",
+ [0x02] = "preempt and abort",
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 racqa = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 rtype = cdw10[1];
+ const char *racqa_str = "reserved";
+ const char *rtype_str = "reserved";
+
+ if (racqa < ARRAY_SIZE(racqa_strs) && racqa_strs[racqa])
+ racqa_str = racqa_strs[racqa];
+
+ if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype])
+ rtype_str = rtype_strs[rtype];
+
+ trace_seq_printf(p, "racqa=%u:%s, iekey=%u, rtype=%u:%s",
+ racqa, racqa_str, iekey, rtype, rtype_str);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvmet_trace_resv_rel(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const rrela_strs[] = {
+ [0x00] = "release",
+ [0x01] = "clear",
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 rrela = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 rtype = cdw10[1];
+ const char *rrela_str = "reserved";
+ const char *rtype_str = "reserved";
+
+ if (rrela < ARRAY_SIZE(rrela_strs) && rrela_strs[rrela])
+ rrela_str = rrela_strs[rrela];
+
+ if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype])
+ rtype_str = rtype_strs[rtype];
+
+ trace_seq_printf(p, "rrela=%u:%s, iekey=%u, rtype=%u:%s",
+ rrela, rrela_str, iekey, rtype, rtype_str);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvmet_trace_resv_report(struct trace_seq *p, u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u32 numd = get_unaligned_le32(cdw10);
+ u8 eds = cdw10[4] & 0x1;
+
+ trace_seq_printf(p, "numd=%u, eds=%u", numd, eds);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p,
u8 opcode, u8 *cdw10)
{
@@ -126,9 +287,22 @@ const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p,
case nvme_cmd_read:
case nvme_cmd_write:
case nvme_cmd_write_zeroes:
+ case nvme_cmd_zone_append:
return nvmet_trace_read_write(p, cdw10);
case nvme_cmd_dsm:
return nvmet_trace_dsm(p, cdw10);
+ case nvme_cmd_zone_mgmt_send:
+ return nvmet_trace_zone_mgmt_send(p, cdw10);
+ case nvme_cmd_zone_mgmt_recv:
+ return nvmet_trace_zone_mgmt_recv(p, cdw10);
+ case nvme_cmd_resv_register:
+ return nvmet_trace_resv_reg(p, cdw10);
+ case nvme_cmd_resv_acquire:
+ return nvmet_trace_resv_acq(p, cdw10);
+ case nvme_cmd_resv_release:
+ return nvmet_trace_resv_rel(p, cdw10);
+ case nvme_cmd_resv_report:
+ return nvmet_trace_resv_report(p, cdw10);
default:
return nvmet_trace_common(p, cdw10);
}
@@ -176,6 +350,34 @@ static const char *nvmet_trace_fabrics_property_get(struct trace_seq *p,
return ret;
}
+static const char *nvmet_trace_fabrics_auth_send(struct trace_seq *p, u8 *spc)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 spsp0 = spc[1];
+ u8 spsp1 = spc[2];
+ u8 secp = spc[3];
+ u32 tl = get_unaligned_le32(spc + 4);
+
+ trace_seq_printf(p, "spsp0=%02x, spsp1=%02x, secp=%02x, tl=%u",
+ spsp0, spsp1, secp, tl);
+ trace_seq_putc(p, 0);
+ return ret;
+}
+
+static const char *nvmet_trace_fabrics_auth_receive(struct trace_seq *p, u8 *spc)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 spsp0 = spc[1];
+ u8 spsp1 = spc[2];
+ u8 secp = spc[3];
+ u32 al = get_unaligned_le32(spc + 4);
+
+ trace_seq_printf(p, "spsp0=%02x, spsp1=%02x, secp=%02x, al=%u",
+ spsp0, spsp1, secp, al);
+ trace_seq_putc(p, 0);
+ return ret;
+}
+
static const char *nvmet_trace_fabrics_common(struct trace_seq *p, u8 *spc)
{
const char *ret = trace_seq_buffer_ptr(p);
@@ -195,6 +397,10 @@ const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p,
return nvmet_trace_fabrics_connect(p, spc);
case nvme_fabrics_type_property_get:
return nvmet_trace_fabrics_property_get(p, spc);
+ case nvme_fabrics_type_auth_send:
+ return nvmet_trace_fabrics_auth_send(p, spc);
+ case nvme_fabrics_type_auth_receive:
+ return nvmet_trace_fabrics_auth_receive(p, spc);
default:
return nvmet_trace_fabrics_common(p, spc);
}
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 5b5c1e481722..29a60fabfcc8 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -52,14 +52,10 @@ bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
if (get_capacity(bd_disk) & (bdev_zone_sectors(ns->bdev) - 1))
return false;
/*
- * ZNS does not define a conventional zone type. If the underlying
- * device has a bitmap set indicating the existence of conventional
- * zones, reject the device. Otherwise, use report zones to detect if
- * the device has conventional zones.
+ * ZNS does not define a conventional zone type. Use report zones
+ * to detect if the device has conventional zones and reject it if
+ * it does.
*/
- if (ns->bdev->bd_disk->conv_zones_bitmap)
- return false;
-
ret = blkdev_report_zones(ns->bdev, 0, bdev_nr_zones(ns->bdev),
validate_conv_zones_cb, NULL);
if (ret < 0)
@@ -104,7 +100,7 @@ void nvmet_execute_identify_ns_zns(struct nvmet_req *req)
if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
req->error_loc = offsetof(struct nvme_identify, nsid);
- status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
goto out;
}
@@ -125,7 +121,7 @@ void nvmet_execute_identify_ns_zns(struct nvmet_req *req)
}
if (!bdev_is_zoned(req->ns->bdev)) {
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
req->error_loc = offsetof(struct nvme_identify, nsid);
goto out;
}
@@ -162,17 +158,17 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, slba);
- return NVME_SC_LBA_RANGE | NVME_SC_DNR;
+ return NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
}
if (out_bufsize < sizeof(struct nvme_zone_report)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, numd);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
if (req->cmd->zmr.zra != NVME_ZRA_ZONE_REPORT) {
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, zra);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
switch (req->cmd->zmr.pr) {
@@ -181,7 +177,7 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
break;
default:
req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, pr);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
switch (req->cmd->zmr.zrasf) {
@@ -197,7 +193,7 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
default:
req->error_loc =
offsetof(struct nvme_zone_mgmt_recv_cmd, zrasf);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
return NVME_SC_SUCCESS;
@@ -345,7 +341,7 @@ static u16 blkdev_zone_mgmt_errno_to_nvme_status(int ret)
return NVME_SC_SUCCESS;
case -EINVAL:
case -EIO:
- return NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
+ return NVME_SC_ZONE_INVALID_TRANSITION | NVME_STATUS_DNR;
default:
return NVME_SC_INTERNAL;
}
@@ -456,8 +452,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
switch (zsa_req_op(req->cmd->zms.zsa)) {
case REQ_OP_ZONE_RESET:
ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0,
- get_capacity(req->ns->bdev->bd_disk),
- GFP_KERNEL);
+ get_capacity(req->ns->bdev->bd_disk));
if (ret < 0)
return blkdev_zone_mgmt_errno_to_nvme_status(ret);
break;
@@ -468,7 +463,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
default:
/* this is needed to quiet compiler warning */
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
}
return NVME_SC_SUCCESS;
@@ -486,7 +481,7 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
if (op == REQ_OP_LAST) {
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
- status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
+ status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_STATUS_DNR;
goto out;
}
@@ -498,17 +493,17 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
if (sect >= get_capacity(bdev->bd_disk)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
- status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+ status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
goto out;
}
if (sect & (zone_sectors - 1)) {
req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out;
}
- ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL);
+ ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors);
if (ret < 0)
status = blkdev_zone_mgmt_errno_to_nvme_status(ret);
@@ -542,6 +537,7 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
u16 status = NVME_SC_SUCCESS;
unsigned int total_len = 0;
struct scatterlist *sg;
+ u32 data_len = nvmet_rw_data_len(req);
struct bio *bio;
int sg_cnt;
@@ -549,6 +545,13 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
if (!nvmet_check_transfer_len(req, nvmet_rw_data_len(req)))
return;
+ if (data_len >
+ bdev_max_zone_append_sectors(req->ns->bdev) << SECTOR_SHIFT) {
+ req->error_loc = offsetof(struct nvme_rw_command, length);
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
if (!req->sg_cnt) {
nvmet_req_complete(req, 0);
return;
@@ -556,13 +559,13 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
req->error_loc = offsetof(struct nvme_rw_command, slba);
- status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+ status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
goto out;
}
if (sect & (bdev_zone_sectors(req->ns->bdev) - 1)) {
req->error_loc = offsetof(struct nvme_rw_command, slba);
- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
goto out;
}
@@ -581,21 +584,17 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
bio->bi_opf |= REQ_FUA;
for_each_sg(req->sg, sg, req->sg_cnt, sg_cnt) {
- struct page *p = sg_page(sg);
- unsigned int l = sg->length;
- unsigned int o = sg->offset;
- unsigned int ret;
+ unsigned int len = sg->length;
- ret = bio_add_zone_append_page(bio, p, l, o);
- if (ret != sg->length) {
+ if (bio_add_page(bio, sg_page(sg), len, sg->offset) != len) {
status = NVME_SC_INTERNAL;
goto out_put_bio;
}
- total_len += sg->length;
+ total_len += len;
}
- if (total_len != nvmet_rw_data_len(req)) {
- status = NVME_SC_INTERNAL | NVME_SC_DNR;
+ if (total_len != data_len) {
+ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
goto out_put_bio;
}