diff options
Diffstat (limited to 'drivers/nvme')
48 files changed, 4338 insertions, 1755 deletions
diff --git a/drivers/nvme/Makefile b/drivers/nvme/Makefile index eedca8c72098..74f59ceed3d5 100644 --- a/drivers/nvme/Makefile +++ b/drivers/nvme/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_NVME_COMMON) += common/ +obj-y += common/ obj-y += host/ obj-y += target/ diff --git a/drivers/nvme/common/Kconfig b/drivers/nvme/common/Kconfig index 4514f44362dd..244432e0b73d 100644 --- a/drivers/nvme/common/Kconfig +++ b/drivers/nvme/common/Kconfig @@ -1,4 +1,14 @@ # SPDX-License-Identifier: GPL-2.0-only -config NVME_COMMON +config NVME_KEYRING tristate + select KEYS + +config NVME_AUTH + tristate + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_SHA256 + select CRYPTO_SHA512 + select CRYPTO_DH + select CRYPTO_DH_RFC7919_GROUPS diff --git a/drivers/nvme/common/Makefile b/drivers/nvme/common/Makefile index 720c625b8a52..681514cf2e2f 100644 --- a/drivers/nvme/common/Makefile +++ b/drivers/nvme/common/Makefile @@ -2,6 +2,8 @@ ccflags-y += -I$(src) -obj-$(CONFIG_NVME_COMMON) += nvme-common.o +obj-$(CONFIG_NVME_AUTH) += nvme-auth.o +obj-$(CONFIG_NVME_KEYRING) += nvme-keyring.o -nvme-common-y += auth.o +nvme-auth-y += auth.o +nvme-keyring-y += keyring.o diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c index d90e4f0c08b7..a3455f1d67fa 100644 --- a/drivers/nvme/common/auth.c +++ b/drivers/nvme/common/auth.c @@ -150,6 +150,14 @@ size_t nvme_auth_hmac_hash_len(u8 hmac_id) } EXPORT_SYMBOL_GPL(nvme_auth_hmac_hash_len); +u32 nvme_auth_key_struct_size(u32 key_len) +{ + struct nvme_dhchap_key key; + + return struct_size(&key, key, key_len); +} +EXPORT_SYMBOL_GPL(nvme_auth_key_struct_size); + struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, u8 key_hash) { @@ -163,14 +171,9 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, p = strrchr(secret, ':'); if (p) allocated_len = p - secret; - key = kzalloc(sizeof(*key), GFP_KERNEL); + key = nvme_auth_alloc_key(allocated_len, 0); if (!key) return ERR_PTR(-ENOMEM); - key->key = kzalloc(allocated_len, GFP_KERNEL); - if (!key->key) { - ret = -ENOMEM; - goto out_free_key; - } key_len = base64_decode(secret, allocated_len, key->key); if (key_len < 0) { @@ -187,14 +190,6 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, goto out_free_secret; } - if (key_hash > 0 && - (key_len - 4) != nvme_auth_hmac_hash_len(key_hash)) { - pr_err("Mismatched key len %d for %s\n", key_len, - nvme_auth_hmac_name(key_hash)); - ret = -EINVAL; - goto out_free_secret; - } - /* The last four bytes is the CRC in little-endian format */ key_len -= 4; /* @@ -213,37 +208,51 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, key->hash = key_hash; return key; out_free_secret: - kfree_sensitive(key->key); -out_free_key: - kfree(key); + nvme_auth_free_key(key); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(nvme_auth_extract_key); +struct nvme_dhchap_key *nvme_auth_alloc_key(u32 len, u8 hash) +{ + u32 num_bytes = nvme_auth_key_struct_size(len); + struct nvme_dhchap_key *key = kzalloc(num_bytes, GFP_KERNEL); + + if (key) { + key->len = len; + key->hash = hash; + } + return key; +} +EXPORT_SYMBOL_GPL(nvme_auth_alloc_key); + void nvme_auth_free_key(struct nvme_dhchap_key *key) { if (!key) return; - kfree_sensitive(key->key); - kfree(key); + kfree_sensitive(key); } EXPORT_SYMBOL_GPL(nvme_auth_free_key); -u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn) +struct nvme_dhchap_key *nvme_auth_transform_key( + struct nvme_dhchap_key *key, char *nqn) { const char *hmac_name; struct crypto_shash *key_tfm; struct shash_desc *shash; - u8 *transformed_key; - int ret; + struct nvme_dhchap_key *transformed_key; + int ret, key_len; - if (!key || !key->key) { + if (!key) { pr_warn("No key specified\n"); return ERR_PTR(-ENOKEY); } if (key->hash == 0) { - transformed_key = kmemdup(key->key, key->len, GFP_KERNEL); - return transformed_key ? transformed_key : ERR_PTR(-ENOMEM); + key_len = nvme_auth_key_struct_size(key->len); + transformed_key = kmemdup(key, key_len, GFP_KERNEL); + if (!transformed_key) + return ERR_PTR(-ENOMEM); + return transformed_key; } hmac_name = nvme_auth_hmac_name(key->hash); if (!hmac_name) { @@ -253,7 +262,7 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn) key_tfm = crypto_alloc_shash(hmac_name, 0, 0); if (IS_ERR(key_tfm)) - return (u8 *)key_tfm; + return ERR_CAST(key_tfm); shash = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(key_tfm), @@ -263,7 +272,8 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn) goto out_free_key; } - transformed_key = kzalloc(crypto_shash_digestsize(key_tfm), GFP_KERNEL); + key_len = crypto_shash_digestsize(key_tfm); + transformed_key = nvme_auth_alloc_key(key_len, key->hash); if (!transformed_key) { ret = -ENOMEM; goto out_free_shash; @@ -282,7 +292,7 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn) ret = crypto_shash_update(shash, "NVMe-over-Fabrics", 17); if (ret < 0) goto out_free_transformed_key; - ret = crypto_shash_final(shash, transformed_key); + ret = crypto_shash_final(shash, transformed_key->key); if (ret < 0) goto out_free_transformed_key; @@ -292,7 +302,7 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn) return transformed_key; out_free_transformed_key: - kfree_sensitive(transformed_key); + nvme_auth_free_key(transformed_key); out_free_shash: kfree(shash); out_free_key: @@ -331,7 +341,6 @@ int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len, u8 *challenge, u8 *aug, size_t hlen) { struct crypto_shash *tfm; - struct shash_desc *desc; u8 *hashed_key; const char *hmac_name; int ret; @@ -359,29 +368,11 @@ int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len, goto out_free_key; } - desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), - GFP_KERNEL); - if (!desc) { - ret = -ENOMEM; - goto out_free_hash; - } - desc->tfm = tfm; - ret = crypto_shash_setkey(tfm, hashed_key, hlen); if (ret) - goto out_free_desc; - - ret = crypto_shash_init(desc); - if (ret) - goto out_free_desc; - - ret = crypto_shash_update(desc, challenge, hlen); - if (ret) - goto out_free_desc; + goto out_free_hash; - ret = crypto_shash_final(desc, aug); -out_free_desc: - kfree_sensitive(desc); + ret = crypto_shash_tfm_digest(tfm, challenge, hlen, aug); out_free_hash: crypto_free_shash(tfm); out_free_key: @@ -480,4 +471,5 @@ int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key) } EXPORT_SYMBOL_GPL(nvme_auth_generate_key); +MODULE_DESCRIPTION("NVMe Authentication framework"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c new file mode 100644 index 000000000000..ed5167f942d8 --- /dev/null +++ b/drivers/nvme/common/keyring.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Hannes Reinecke, SUSE Labs + */ + +#include <linux/module.h> +#include <linux/seq_file.h> +#include <linux/key.h> +#include <linux/key-type.h> +#include <keys/user-type.h> +#include <linux/nvme.h> +#include <linux/nvme-tcp.h> +#include <linux/nvme-keyring.h> + +static struct key *nvme_keyring; + +key_serial_t nvme_keyring_id(void) +{ + return nvme_keyring->serial; +} +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); + seq_printf(m, ": %u", key->datalen); +} + +static bool nvme_tls_psk_match(const struct key *key, + const struct key_match_data *match_data) +{ + const char *match_id; + size_t match_len; + + if (!key->description) { + pr_debug("%s: no key description\n", __func__); + return false; + } + 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); +} + +static int nvme_tls_psk_match_preparse(struct key_match_data *match_data) +{ + match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE; + match_data->cmp = nvme_tls_psk_match; + return 0; +} + +static struct key_type nvme_tls_psk_key_type = { + .name = "psk", + .flags = KEY_TYPE_NET_DOMAIN, + .preparse = user_preparse, + .free_preparse = user_free_preparse, + .match_preparse = nvme_tls_psk_match_preparse, + .instantiate = generic_key_instantiate, + .revoke = user_revoke, + .destroy = user_destroy, + .describe = nvme_tls_psk_describe, + .read = user_read, +}; + +static struct key *nvme_tls_psk_lookup(struct key *keyring, + const char *hostnqn, const char *subnqn, + u8 hmac, u8 psk_ver, bool generated) +{ + char *identity; + size_t identity_len = (NVMF_NQN_SIZE) * 2 + 11; + key_ref_t keyref; + key_serial_t keyring_id; + + identity = kzalloc(identity_len, GFP_KERNEL); + if (!identity) + return ERR_PTR(-ENOMEM); + + snprintf(identity, identity_len, "NVMe%u%c%02u %s %s", + psk_ver, generated ? 'G' : 'R', hmac, hostnqn, subnqn); + + if (!keyring) + keyring = nvme_keyring; + keyring_id = key_serial(keyring); + pr_debug("keyring %x lookup tls psk '%s'\n", + keyring_id, identity); + keyref = keyring_search(make_key_ref(keyring, true), + &nvme_tls_psk_key_type, + identity, false); + if (IS_ERR(keyref)) { + pr_debug("lookup tls psk '%s' failed, error %ld\n", + identity, PTR_ERR(keyref)); + kfree(identity); + return ERR_PTR(-ENOKEY); + } + kfree(identity); + + return key_ref_to_ptr(keyref); +} + +/* + * NVMe PSK priority list + * + * '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, }, +}; + +/* + * nvme_tls_psk_default - Return the preferred PSK to use for TLS ClientHello + */ +key_serial_t nvme_tls_psk_default(struct key *keyring, + const char *hostnqn, const char *subnqn) +{ + struct key *tls_key; + key_serial_t tls_key_id; + int prio; + + 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, ver, generated); + if (!IS_ERR(tls_key)) { + tls_key_id = tls_key->serial; + key_put(tls_key); + return tls_key_id; + } + } + return 0; +} +EXPORT_SYMBOL_GPL(nvme_tls_psk_default); + +static int __init nvme_keyring_init(void) +{ + int err; + + nvme_keyring = keyring_alloc(".nvme", + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + current_cred(), + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + (KEY_USR_ALL & ~KEY_USR_SETATTR), + KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); + if (IS_ERR(nvme_keyring)) + return PTR_ERR(nvme_keyring); + + err = register_key_type(&nvme_tls_psk_key_type); + if (err) { + key_put(nvme_keyring); + return err; + } + return 0; +} + +static void __exit nvme_keyring_exit(void) +{ + unregister_key_type(&nvme_tls_psk_key_type); + key_revoke(nvme_keyring); + key_put(nvme_keyring); +} + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Hannes Reinecke <hare@suse.de>"); +MODULE_DESCRIPTION("NVMe Keyring implementation"); +module_init(nvme_keyring_init); +module_exit(nvme_keyring_exit); diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 2f6a7f8c94e8..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 @@ -92,18 +92,27 @@ config NVME_TCP If unsure, say N. -config NVME_AUTH - bool "NVM Express over Fabrics In-Band Authentication" +config NVME_TCP_TLS + bool "NVMe over Fabrics TCP TLS encryption support" + depends on NVME_TCP + select NET_HANDSHAKE + select KEYS + help + Enables TLS encryption for NVMe TCP using the netlink handshake API. + + The TLS handshake daemon is availble at + https://github.com/oracle/ktls-utils. + + If unsure, say N. + +config NVME_HOST_AUTH + bool "NVMe over Fabrics In-Band Authentication in host side" depends on NVME_CORE - select NVME_COMMON - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_SHA256 - select CRYPTO_SHA512 - select CRYPTO_DH - select CRYPTO_DH_RFC7919_GROUPS + select NVME_AUTH + select NVME_KEYRING if NVME_TCP_TLS help - This provides support for NVMe over Fabrics In-Band Authentication. + This provides support for NVMe over Fabrics In-Band Authentication in + host side. If unsure, say N. diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index c7c3cf202d12..6414ec968f99 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -17,7 +17,7 @@ nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o nvme-core-$(CONFIG_BLK_DEV_ZONED) += zns.o nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS) += fault_inject.o nvme-core-$(CONFIG_NVME_HWMON) += hwmon.o -nvme-core-$(CONFIG_NVME_AUTH) += auth.o +nvme-core-$(CONFIG_NVME_HOST_AUTH) += auth.o nvme-y += pci.o diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 596bb11eeba5..b1387dc459a3 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -797,6 +797,7 @@ static int apple_nvme_init_request(struct blk_mq_tag_set *set, static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown) { + enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl); u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS); bool dead = false, freeze = false; unsigned long flags; @@ -808,8 +809,8 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown) if (csts & NVME_CSTS_CFS) dead = true; - if (anv->ctrl.state == NVME_CTRL_LIVE || - anv->ctrl.state == NVME_CTRL_RESETTING) { + if (state == NVME_CTRL_LIVE || + state == NVME_CTRL_RESETTING) { freeze = true; nvme_start_freeze(&anv->ctrl); } @@ -881,7 +882,7 @@ static enum blk_eh_timer_return apple_nvme_timeout(struct request *req) unsigned long flags; u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS); - if (anv->ctrl.state != NVME_CTRL_LIVE) { + if (nvme_ctrl_state(&anv->ctrl) != NVME_CTRL_LIVE) { /* * From rdma.c: * If we are resetting, connecting or deleting we should @@ -985,10 +986,10 @@ static void apple_nvme_reset_work(struct work_struct *work) u32 boot_status, aqa; struct apple_nvme *anv = container_of(work, struct apple_nvme, ctrl.reset_work); + enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl); - if (anv->ctrl.state != NVME_CTRL_RESETTING) { - dev_warn(anv->dev, "ctrl state %d is not RESETTING\n", - anv->ctrl.state); + if (state != NVME_CTRL_RESETTING) { + dev_warn(anv->dev, "ctrl state %d is not RESETTING\n", state); ret = -ENODEV; goto out; } @@ -1387,7 +1388,7 @@ 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; @@ -1395,7 +1396,7 @@ 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; @@ -1515,10 +1516,30 @@ 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: + 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); @@ -1526,12 +1547,14 @@ 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); 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); @@ -1546,8 +1569,6 @@ static int apple_nvme_remove(struct platform_device *pdev) apple_rtkit_shutdown(anv->rtk); apple_nvme_detach_genpd(anv); - - return 0; } static void apple_nvme_shutdown(struct platform_device *pdev) @@ -1597,10 +1618,11 @@ static struct platform_driver apple_nvme_driver = { .pm = pm_sleep_ptr(&apple_nvme_pm_ops), }, .probe = apple_nvme_probe, - .remove = apple_nvme_remove, + .remove_new = apple_nvme_remove, .shutdown = apple_nvme_shutdown, }; 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 daf5d144a8ea..371e14f0a203 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -23,11 +23,13 @@ struct nvme_dhchap_queue_context { struct nvme_ctrl *ctrl; struct crypto_shash *shash_tfm; struct crypto_kpp *dh_tfm; + struct nvme_dhchap_key *transformed_key; void *buf; int qid; int error; u32 s1; u32 s2; + bool bi_directional; u16 transaction; u8 status; u8 dhgroup_id; @@ -36,7 +38,6 @@ struct nvme_dhchap_queue_context { u8 c1[64]; u8 c2[64]; u8 response[64]; - u8 *host_response; u8 *ctrl_key; u8 *host_key; u8 *sess_key; @@ -47,11 +48,6 @@ struct nvme_dhchap_queue_context { static struct workqueue_struct *nvme_auth_wq; -#define nvme_auth_flags_from_qid(qid) \ - (qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED -#define nvme_auth_queue_from_qid(ctrl, qid) \ - (qid == 0) ? (ctrl)->fabrics_q : (ctrl)->connect_q - static inline int ctrl_max_dhchaps(struct nvme_ctrl *ctrl) { return ctrl->opts->nr_io_queues + ctrl->opts->nr_write_queues + @@ -62,10 +58,15 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid, void *data, size_t data_len, bool auth_send) { struct nvme_command cmd = {}; - blk_mq_req_flags_t flags = nvme_auth_flags_from_qid(qid); - struct request_queue *q = nvme_auth_queue_from_qid(ctrl, qid); + nvme_submit_flags_t flags = NVME_SUBMIT_RETRY; + struct request_queue *q = ctrl->fabrics_q; int ret; + if (qid != 0) { + flags |= NVME_SUBMIT_NOWAIT | NVME_SUBMIT_RESERVED; + q = ctrl->connect_q; + } + cmd.auth_common.opcode = nvme_fabrics_command; cmd.auth_common.secp = NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER; cmd.auth_common.spsp0 = 0x01; @@ -79,8 +80,7 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid, } ret = __nvme_submit_sync_cmd(q, &cmd, NULL, data, data_len, - qid == 0 ? NVME_QID_ANY : qid, - 0, flags); + qid == 0 ? NVME_QID_ANY : qid, flags); if (ret > 0) dev_warn(ctrl->device, "qid %d auth_send failed with status %d\n", qid, ret); @@ -312,17 +312,17 @@ static int nvme_auth_set_dhchap_reply_data(struct nvme_ctrl *ctrl, data->dhvlen = cpu_to_le16(chap->host_key_len); memcpy(data->rval, chap->response, chap->hash_len); if (ctrl->ctrl_key) { + chap->bi_directional = true; get_random_bytes(chap->c2, chap->hash_len); data->cvalid = 1; - chap->s2 = nvme_auth_get_seqnum(); memcpy(data->rval + chap->hash_len, chap->c2, chap->hash_len); dev_dbg(ctrl->device, "%s: qid %d ctrl challenge %*ph\n", __func__, chap->qid, (int)chap->hash_len, chap->c2); } else { memset(chap->c2, 0, chap->hash_len); - chap->s2 = 0; } + chap->s2 = nvme_auth_get_seqnum(); data->seqnum = cpu_to_le32(chap->s2); if (chap->host_key_len) { dev_dbg(ctrl->device, "%s: qid %d host public key %*ph\n", @@ -339,10 +339,7 @@ static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl, struct nvme_dhchap_queue_context *chap) { struct nvmf_auth_dhchap_success1_data *data = chap->buf; - size_t size = sizeof(*data); - - if (chap->ctrl_key) - size += chap->hash_len; + size_t size = sizeof(*data) + chap->hash_len; if (size > CHAP_BUF_SIZE) { chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD; @@ -428,12 +425,12 @@ static int nvme_auth_dhchap_setup_host_response(struct nvme_ctrl *ctrl, dev_dbg(ctrl->device, "%s: qid %d host response seq %u transaction %d\n", __func__, chap->qid, chap->s1, chap->transaction); - if (!chap->host_response) { - chap->host_response = nvme_auth_transform_key(ctrl->host_key, + if (!chap->transformed_key) { + chap->transformed_key = nvme_auth_transform_key(ctrl->host_key, ctrl->opts->host->nqn); - if (IS_ERR(chap->host_response)) { - ret = PTR_ERR(chap->host_response); - chap->host_response = NULL; + if (IS_ERR(chap->transformed_key)) { + ret = PTR_ERR(chap->transformed_key); + chap->transformed_key = NULL; return ret; } } else { @@ -442,7 +439,7 @@ static int nvme_auth_dhchap_setup_host_response(struct nvme_ctrl *ctrl, } ret = crypto_shash_setkey(chap->shash_tfm, - chap->host_response, ctrl->host_key->len); + chap->transformed_key->key, chap->transformed_key->len); if (ret) { dev_warn(ctrl->device, "qid %d: failed to set key, error %d\n", chap->qid, ret); @@ -508,19 +505,19 @@ static int nvme_auth_dhchap_setup_ctrl_response(struct nvme_ctrl *ctrl, struct nvme_dhchap_queue_context *chap) { SHASH_DESC_ON_STACK(shash, chap->shash_tfm); - u8 *ctrl_response; + struct nvme_dhchap_key *transformed_key; u8 buf[4], *challenge = chap->c2; int ret; - ctrl_response = nvme_auth_transform_key(ctrl->ctrl_key, + transformed_key = nvme_auth_transform_key(ctrl->ctrl_key, ctrl->opts->subsysnqn); - if (IS_ERR(ctrl_response)) { - ret = PTR_ERR(ctrl_response); + if (IS_ERR(transformed_key)) { + ret = PTR_ERR(transformed_key); return ret; } ret = crypto_shash_setkey(chap->shash_tfm, - ctrl_response, ctrl->ctrl_key->len); + transformed_key->key, transformed_key->len); if (ret) { dev_warn(ctrl->device, "qid %d: failed to set key, error %d\n", chap->qid, ret); @@ -586,7 +583,7 @@ static int nvme_auth_dhchap_setup_ctrl_response(struct nvme_ctrl *ctrl, out: if (challenge != chap->c2) kfree(challenge); - kfree(ctrl_response); + nvme_auth_free_key(transformed_key); return ret; } @@ -648,8 +645,8 @@ gen_sesskey: static void nvme_auth_reset_dhchap(struct nvme_dhchap_queue_context *chap) { - kfree_sensitive(chap->host_response); - chap->host_response = NULL; + nvme_auth_free_key(chap->transformed_key); + chap->transformed_key = NULL; kfree_sensitive(chap->host_key); chap->host_key = NULL; chap->host_key_len = 0; @@ -663,6 +660,7 @@ static void nvme_auth_reset_dhchap(struct nvme_dhchap_queue_context *chap) chap->error = 0; chap->s1 = 0; chap->s2 = 0; + chap->bi_directional = false; chap->transaction = 0; memset(chap->c1, 0, sizeof(chap->c1)); memset(chap->c2, 0, sizeof(chap->c2)); @@ -732,7 +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; } @@ -758,12 +756,11 @@ static void nvme_queue_auth_work(struct work_struct *work) __func__, chap->qid); mutex_lock(&ctrl->dhchap_auth_mutex); ret = nvme_auth_dhchap_setup_host_response(ctrl, chap); + mutex_unlock(&ctrl->dhchap_auth_mutex); if (ret) { - mutex_unlock(&ctrl->dhchap_auth_mutex); chap->error = ret; goto fail2; } - mutex_unlock(&ctrl->dhchap_auth_mutex); /* DH-HMAC-CHAP Step 3: send reply */ dev_dbg(ctrl->device, "%s: qid %d send reply\n", @@ -800,7 +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; } @@ -821,11 +818,11 @@ 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; } - if (chap->ctrl_key) { + if (chap->bi_directional) { /* DH-HMAC-CHAP Step 5: send success2 */ dev_dbg(ctrl->device, "%s: qid %d send success2\n", __func__, chap->qid); @@ -840,6 +837,8 @@ static void nvme_queue_auth_work(struct work_struct *work) } fail2: + if (chap->status == 0) + chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; dev_dbg(ctrl->device, "%s: qid %d send failure2, status %x\n", __func__, chap->qid, chap->status); tl = nvme_auth_set_dhchap_failure2_data(ctrl, chap); @@ -897,7 +896,7 @@ static void nvme_ctrl_auth_work(struct work_struct *work) * If the ctrl is no connected, bail as reconnect will handle * authentication. */ - if (ctrl->state != NVME_CTRL_LIVE) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) return; /* Authenticate admin queue first */ diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index 20f46c230885..2b9e6cfaf2a8 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -171,15 +171,15 @@ static const char * const nvme_statuses[] = { [NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command", }; -const unsigned char *nvme_get_error_status_str(u16 status) +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 & 0x7ff]; + return nvme_statuses[status]; return "Unknown"; } -const unsigned char *nvme_get_opcode_str(u8 opcode) +const char *nvme_get_opcode_str(u8 opcode) { if (opcode < ARRAY_SIZE(nvme_ops) && nvme_ops[opcode]) return nvme_ops[opcode]; @@ -187,7 +187,7 @@ const unsigned char *nvme_get_opcode_str(u8 opcode) } EXPORT_SYMBOL_GPL(nvme_get_opcode_str); -const unsigned char *nvme_get_admin_opcode_str(u8 opcode) +const char *nvme_get_admin_opcode_str(u8 opcode) { if (opcode < ARRAY_SIZE(nvme_admin_ops) && nvme_admin_ops[opcode]) return nvme_admin_ops[opcode]; @@ -195,7 +195,7 @@ const unsigned char *nvme_get_admin_opcode_str(u8 opcode) } EXPORT_SYMBOL_GPL(nvme_get_admin_opcode_str); -const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) { +const char *nvme_get_fabrics_opcode_str(u8 opcode) { if (opcode < ARRAY_SIZE(nvme_fabrics_ops) && nvme_fabrics_ops[opcode]) return nvme_fabrics_ops[opcode]; return "Unknown"; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f3a01b79148c..ba6508455e18 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> @@ -20,6 +21,7 @@ #include <linux/ptrace.h> #include <linux/nvme_ioctl.h> #include <linux/pm_qos.h> +#include <linux/ratelimit.h> #include <asm/unaligned.h> #include "nvme.h" @@ -35,6 +37,7 @@ 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; @@ -109,16 +112,25 @@ 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, @@ -131,7 +143,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl) /* * Only new queue scan work when admin and IO queues are both alive */ - if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset) + if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE && ctrl->tagset) queue_work(nvme_wq, &ctrl->scan_work); } @@ -143,7 +155,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl) */ int nvme_try_sched_reset(struct nvme_ctrl *ctrl) { - if (ctrl->state != NVME_CTRL_RESETTING) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_RESETTING) return -EBUSY; if (!queue_work(nvme_reset_wq, &ctrl->reset_work)) return -EBUSY; @@ -156,7 +168,7 @@ static void nvme_failfast_work(struct work_struct *work) struct nvme_ctrl *ctrl = container_of(to_delayed_work(work), struct nvme_ctrl, failfast_work); - if (ctrl->state != NVME_CTRL_CONNECTING) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_CONNECTING) return; set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags); @@ -200,7 +212,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) ret = nvme_reset_ctrl(ctrl); if (!ret) { flush_work(&ctrl->reset_work); - if (ctrl->state != NVME_CTRL_LIVE) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) ret = -ENETRESET; } @@ -251,7 +263,7 @@ 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: @@ -297,7 +309,7 @@ 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; @@ -312,17 +324,17 @@ static void nvme_log_error(struct request *req) struct nvme_request *nr = nvme_req(req); if (ns) { - pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n", + pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %u blocks, %s (sct 0x%x / sc 0x%x) %s%s\n", ns->disk ? ns->disk->disk_name : "?", nvme_get_opcode_str(nr->cmd->common.opcode), nr->cmd->common.opcode, - (unsigned long long)nvme_sect_to_lba(ns, blk_rq_pos(req)), - (unsigned long long)blk_rq_bytes(req) >> ns->lba_shift, + 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; } @@ -331,10 +343,34 @@ 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) +{ + struct nvme_ns *ns = req->q->queuedata; + struct nvme_request *nr = nvme_req(req); + + pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s" + "cdw10=0x%x cdw11=0x%x cdw12=0x%x cdw13=0x%x cdw14=0x%x cdw15=0x%x\n", + ns ? ns->disk->disk_name : dev_name(nr->ctrl->device), + ns ? nvme_get_opcode_str(nr->cmd->common.opcode) : + nvme_get_admin_opcode_str(nr->cmd->common.opcode), + nr->cmd->common.opcode, + nvme_get_error_status_str(nr->status), + 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, + nr->cmd->common.cdw13, + nr->cmd->common.cdw14, + nr->cmd->common.cdw14); } enum nvme_disposition { @@ -349,14 +385,14 @@ 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)) @@ -372,21 +408,33 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req) static inline void nvme_end_req_zoned(struct request *req) { if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && - req_op(req) == REQ_OP_ZONE_APPEND) - req->__sector = nvme_lba_to_sect(req->q->queuedata, + req_op(req) == REQ_OP_ZONE_APPEND) { + struct nvme_ns *ns = req->q->queuedata; + + req->__sector = nvme_lba_to_sect(ns->head, le64_to_cpu(nvme_req(req)->result.u64)); + } } -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))) - nvme_log_error(req); nvme_end_req_zoned(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); + + if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) { + if (blk_rq_is_passthrough(req)) + nvme_log_err_passthru(req); + else + nvme_log_error(req); + } + __nvme_end_req(req); blk_mq_end_request(req, status); } @@ -420,7 +468,7 @@ void nvme_complete_rq(struct request *req) nvme_failover_req(req); return; case AUTHENTICATE: -#ifdef CONFIG_NVME_AUTH +#ifdef CONFIG_NVME_HOST_AUTH queue_work(nvme_wq, &ctrl->dhchap_auth_work); nvme_retry_req(req); #else @@ -435,7 +483,7 @@ 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); @@ -499,7 +547,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, spin_lock_irqsave(&ctrl->lock, flags); - old_state = ctrl->state; + old_state = nvme_ctrl_state(ctrl); switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { @@ -567,7 +615,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, } if (changed) { - ctrl->state = new_state; + WRITE_ONCE(ctrl->state, new_state); wake_up_all(&ctrl->state_wq); } @@ -575,11 +623,11 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, if (!changed) return false; - if (ctrl->state == NVME_CTRL_LIVE) { + if (new_state == NVME_CTRL_LIVE) { if (old_state == NVME_CTRL_CONNECTING) nvme_stop_failfast_work(ctrl); nvme_kick_requeue_lists(ctrl); - } else if (ctrl->state == NVME_CTRL_CONNECTING && + } else if (new_state == NVME_CTRL_CONNECTING && old_state == NVME_CTRL_RESETTING) { nvme_start_failfast_work(ctrl); } @@ -588,27 +636,6 @@ 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 (ctrl->state) { - 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. */ @@ -617,7 +644,7 @@ bool nvme_wait_reset(struct nvme_ctrl *ctrl) wait_event(ctrl->state_wq, nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) || nvme_state_terminal(ctrl)); - return ctrl->state == NVME_CTRL_RESETTING; + return nvme_ctrl_state(ctrl) == NVME_CTRL_RESETTING; } EXPORT_SYMBOL_GPL(nvme_wait_reset); @@ -653,7 +680,7 @@ 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); } @@ -675,10 +702,21 @@ static inline void nvme_clear_nvme_request(struct request *req) /* initialize a passthrough request */ void nvme_init_request(struct request *req, struct nvme_command *cmd) { - if (req->q->queuedata) + struct nvme_request *nr = nvme_req(req); + bool logging_enabled; + + if (req->q->queuedata) { + struct nvme_ns *ns = req->q->disk->private_data; + + logging_enabled = ns->head->passthru_err_log_enabled; req->timeout = NVME_IO_TIMEOUT; - else /* no queuedata implies admin queue */ + } else { /* no queuedata implies admin queue */ + logging_enabled = nr->ctrl->passthru_err_log_enabled; req->timeout = NVME_ADMIN_TIMEOUT; + } + + if (!logging_enabled) + req->rq_flags |= RQF_QUIET; /* passthru commands should let the driver set the SGL flags */ cmd->common.flags &= ~NVME_CMD_SGL_ALL; @@ -687,8 +725,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd) if (req->mq_hctx->type == HCTX_TYPE_POLL) req->cmd_flags |= REQ_POLLED; nvme_clear_nvme_request(req); - req->rq_flags |= RQF_QUIET; - memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd)); + memcpy(nr->cmd, cmd, sizeof(*cmd)); } EXPORT_SYMBOL_GPL(nvme_init_request); @@ -704,9 +741,11 @@ EXPORT_SYMBOL_GPL(nvme_init_request); blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, struct request *rq) { - if (ctrl->state != NVME_CTRL_DELETING_NOIO && - ctrl->state != NVME_CTRL_DELETING && - ctrl->state != NVME_CTRL_DEAD && + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); + + if (state != NVME_CTRL_DELETING_NOIO && + state != NVME_CTRL_DELETING && + state != NVME_CTRL_DEAD && !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) && !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; @@ -715,7 +754,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, EXPORT_SYMBOL_GPL(nvme_fail_nonready_command); bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, - bool queue_live) + bool queue_live, enum nvme_ctrl_state state) { struct nvme_request *req = nvme_req(rq); @@ -736,7 +775,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, * command, which is require to set the queue live in the * appropinquate states. */ - switch (ctrl->state) { + switch (state) { case NVME_CTRL_CONNECTING: if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) && (req->cmd->fabrics.fctype == nvme_fabrics_type_connect || @@ -791,8 +830,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, } if (queue_max_discard_segments(req->q) == 1) { - u64 slba = nvme_sect_to_lba(ns, blk_rq_pos(req)); - u32 nlb = blk_rq_sectors(req) >> (ns->lba_shift - 9); + u64 slba = nvme_sect_to_lba(ns->head, blk_rq_pos(req)); + u32 nlb = blk_rq_sectors(req) >> (ns->head->lba_shift - 9); range[0].cattr = cpu_to_le32(0); range[0].nlb = cpu_to_le32(nlb); @@ -800,8 +839,9 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, n = 1; } else { __rq_for_each_bio(bio, req) { - u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector); - u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; + u64 slba = nvme_sect_to_lba(ns->head, + bio->bi_iter.bi_sector); + u32 nlb = bio->bi_iter.bi_size >> ns->head->lba_shift; if (n < segments) { range[n].cattr = cpu_to_le32(0); @@ -839,7 +879,7 @@ static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd, u64 ref48; /* both rw and write zeroes share the same reftag format */ - switch (ns->guard_type) { + switch (ns->head->guard_type) { case NVME_NVM_NS_16B_GUARD: cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req)); break; @@ -867,17 +907,18 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes; cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id); cmnd->write_zeroes.slba = - cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); + cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req))); cmnd->write_zeroes.length = - cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); + cpu_to_le16((blk_rq_bytes(req) >> ns->head->lba_shift) - 1); - if (!(req->cmd_flags & REQ_NOUNMAP) && (ns->features & NVME_NS_DEAC)) + if (!(req->cmd_flags & REQ_NOUNMAP) && + (ns->head->features & NVME_NS_DEAC)) cmnd->write_zeroes.control |= cpu_to_le16(NVME_WZ_DEAC); - if (nvme_ns_has_pi(ns)) { + if (nvme_ns_has_pi(ns->head)) { cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT); - switch (ns->pi_type) { + switch (ns->head->pi_type) { case NVME_NS_DPS_PI_TYPE1: case NVME_NS_DPS_PI_TYPE2: nvme_set_ref_tag(ns, cmnd, req); @@ -888,6 +929,36 @@ 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) @@ -903,19 +974,24 @@ 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); cmnd->rw.cdw2 = 0; cmnd->rw.cdw3 = 0; cmnd->rw.metadata = 0; - cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); - cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); + cmnd->rw.slba = + cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req))); + 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->ms) { + if (ns->head->ms) { /* * If formated with metadata, the block layer always provides a * metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled. Else @@ -923,12 +999,12 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, * namespace capacity to zero to prevent any I/O. */ if (!blk_integrity_rq(req)) { - if (WARN_ON_ONCE(!nvme_ns_has_pi(ns))) + if (WARN_ON_ONCE(!nvme_ns_has_pi(ns->head))) return BLK_STS_NOTSUPP; control |= NVME_RW_PRINFO_PRACT; } - switch (ns->pi_type) { + switch (ns->head->pi_type) { case NVME_NS_DPS_PI_TYPE3: control |= NVME_RW_PRINFO_PRCHK_GUARD; break; @@ -957,6 +1033,7 @@ 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); @@ -1041,20 +1118,27 @@ EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, NVME_TARGET_PASSTHRU); */ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, union nvme_result *result, void *buffer, unsigned bufflen, - int qid, int at_head, blk_mq_req_flags_t flags) + int qid, nvme_submit_flags_t flags) { struct request *req; int ret; + blk_mq_req_flags_t blk_flags = 0; + if (flags & NVME_SUBMIT_NOWAIT) + blk_flags |= BLK_MQ_REQ_NOWAIT; + if (flags & NVME_SUBMIT_RESERVED) + blk_flags |= BLK_MQ_REQ_RESERVED; if (qid == NVME_QID_ANY) - req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags); + req = blk_mq_alloc_request(q, nvme_req_op(cmd), blk_flags); else - req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags, + req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), blk_flags, qid - 1); if (IS_ERR(req)) return PTR_ERR(req); nvme_init_request(req, cmd); + if (flags & NVME_SUBMIT_RETRY) + req->cmd_flags &= ~REQ_FAILFAST_DRIVER; if (buffer && bufflen) { ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); @@ -1062,7 +1146,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, goto out; } - ret = nvme_execute_rq(req, at_head); + ret = nvme_execute_rq(req, flags & NVME_SUBMIT_AT_HEAD); if (result && ret >= 0) *result = nvme_req(req)->result; out: @@ -1075,7 +1159,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buffer, unsigned bufflen) { return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, - NVME_QID_ANY, 0, 0); + NVME_QID_ANY, 0); } EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd); @@ -1098,6 +1182,10 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) effects &= ~NVME_CMD_EFFECTS_CSE_MASK; } else { effects = le32_to_cpu(ctrl->effects->acs[opcode]); + + /* Ignore execution restrictions if any relaxation bits are set */ + if (effects & NVME_CMD_EFFECTS_CSER_MASK) + effects &= ~NVME_CMD_EFFECTS_CSE_MASK; } return effects; @@ -1171,7 +1259,7 @@ 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 [..]. */ @@ -1192,8 +1280,16 @@ static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl) static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl) { - queue_delayed_work(nvme_wq, &ctrl->ka_work, - nvme_keep_alive_work_period(ctrl)); + unsigned long now = jiffies; + unsigned long delay = nvme_keep_alive_work_period(ctrl); + unsigned long ka_next_check_tm = ctrl->ka_last_check_time + delay; + + if (time_after(now, ka_next_check_tm)) + delay = 0; + else + delay = ka_next_check_tm - now; + + queue_delayed_work(nvme_wq, &ctrl->ka_work, delay); } static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, @@ -1331,8 +1427,10 @@ 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; } @@ -1442,7 +1540,7 @@ free_data: return status; } -static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, +int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, struct nvme_id_ns **id) { struct nvme_command c = { }; @@ -1461,6 +1559,7 @@ static 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; } @@ -1479,7 +1578,8 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl, if (id->ncap == 0) { /* namespace not allocated or attached */ info->is_removed = true; - return -ENODEV; + ret = -ENODEV; + goto error; } info->anagrpid = id->anagrpid; @@ -1497,8 +1597,10 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl, !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) memcpy(ids->nguid, id->nguid, sizeof(ids->nguid)); } + +error: kfree(id); - return 0; + return ret; } static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl, @@ -1539,7 +1641,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, c.features.dword11 = cpu_to_le32(dword11); ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res, - buffer, buflen, NVME_QID_ANY, 0, 0); + buffer, buflen, NVME_QID_ANY, 0); if (ret >= 0 && result) *result = le32_to_cpu(res.u32); return ret; @@ -1657,92 +1759,87 @@ 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 *ns, - 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 (ns->pi_type) { + switch (head->pi_type) { case NVME_NS_DPS_PI_TYPE3: - switch (ns->guard_type) { + 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; case NVME_NS_DPS_PI_TYPE1: case NVME_NS_DPS_PI_TYPE2: - switch (ns->guard_type) { + 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 = ns->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 *ns, - 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 gendisk *disk, struct nvme_ns *ns) +static void nvme_config_discard(struct nvme_ns *ns, struct queue_limits *lim) { struct nvme_ctrl *ctrl = ns->ctrl; - struct request_queue *queue = disk->queue; - u32 size = queue_logical_block_size(queue); - - if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX)) - ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl); - if (ctrl->max_discard_sectors == 0) { - blk_queue_max_discard_sectors(queue, 0); - return; - } - - BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < - NVME_DSM_MAX_RANGES); - - queue->limits.discard_granularity = size; - - /* If discard is already enabled, don't reset queue limits */ - if (queue->limits.max_discard_sectors) - return; + 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; - blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors); - blk_queue_max_discard_segments(queue, ctrl->max_discard_segments); + lim->discard_granularity = lim->logical_block_size; - if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) - blk_queue_max_write_zeroes_sectors(queue, UINT_MAX); + if (ctrl->dmrl) + lim->max_discard_segments = ctrl->dmrl; + else + lim->max_discard_segments = NVME_DSM_MAX_RANGES; } static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) @@ -1753,76 +1850,80 @@ 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_ns *ns, 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_ctrl *ctrl = ns->ctrl; - 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; - - ns->pi_size = 0; - ns->ms = le16_to_cpu(id->lbaf[lbaf].ms); - if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) { - ns->pi_size = sizeof(struct t10_pi_tuple); - ns->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(ns->head->ns_id); - c.identify.cns = NVME_ID_CNS_CS_NS; - c.identify.csi = NVME_CSI_NVM; - - ret = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, nvm, sizeof(*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; - ns->guard_type = nvme_elbaf_guard_type(elbaf); - switch (ns->guard_type) { + 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 = guard_type; + switch (head->guard_type) { case NVME_NVM_NS_64B_GUARD: - ns->pi_size = sizeof(struct crc64_pi_tuple); + head->pi_size = sizeof(struct crc64_pi_tuple); break; case NVME_NVM_NS_16B_GUARD: - ns->pi_size = sizeof(struct t10_pi_tuple); + head->pi_size = sizeof(struct t10_pi_tuple); break; default: break; } - -free_data: - kfree(nvm); -set_pi: - if (ns->pi_size && (first || ns->ms == ns->pi_size)) - ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK; - else - ns->pi_type = 0; - - return ret; } -static void nvme_configure_metadata(struct nvme_ns *ns, 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) { - struct nvme_ctrl *ctrl = ns->ctrl; - - if (nvme_init_ms(ns, id)) + 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; - ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS); - if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)) - 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)) + info->pi_offset = head->ms - head->pi_size; if (ctrl->ops->flags & NVME_F_FABRICS) { /* @@ -1833,7 +1934,7 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT))) return; - ns->features |= NVME_NS_EXT_LBAS; + head->features |= NVME_NS_EXT_LBAS; /* * The current fabrics transport drivers support namespace @@ -1844,8 +1945,8 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) * Note, this check will need to be modified if any drivers * gain the ability to use other metadata formats. */ - if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns)) - ns->features |= NVME_NS_METADATA_SUPPORTED; + if (ctrl->max_integrity_segments && nvme_ns_has_pi(head)) + head->features |= NVME_NS_METADATA_SUPPORTED; } else { /* * For PCIe controllers, we can't easily remap the separate @@ -1854,48 +1955,64 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) * We allow extended LBAs for the passthrough interface, though. */ if (id->flbas & NVME_NS_FLBAS_META_EXT) - ns->features |= NVME_NS_EXT_LBAS; + head->features |= NVME_NS_EXT_LBAS; else - ns->features |= NVME_NS_METADATA_SUPPORTED; + head->features |= NVME_NS_METADATA_SUPPORTED; } } -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); +} + +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 gendisk *disk, - struct nvme_ns *ns, 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(ns, le64_to_cpu(id->nsze)); - u32 bs = 1U << ns->lba_shift; + 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 - * yet, so catch this early and don't allow block I/O. + * or smaller than a sector size yet, so catch this early and don't + * allow block I/O. */ - if (ns->lba_shift > PAGE_SHIFT) { - capacity = 0; + if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) { bs = (1 << 9); + valid = false; } - blk_integrity_unregister(disk); - atomic_bs = phys_bs = bs; if (id->nabo == 0) { /* @@ -1907,45 +2024,32 @@ static void nvme_update_disk_info(struct gendisk *disk, atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; else 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 (ns->ms) { - if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && - (ns->features & NVME_NS_METADATA_SUPPORTED)) - nvme_init_integrity(disk, ns, - ns->ctrl->max_integrity_segments); - else if (!nvme_ns_has_pi(ns)) - capacity = 0; - } - - set_capacity_and_notify(disk, capacity); - - nvme_config_discard(disk, ns); - blk_queue_max_write_zeroes_sectors(disk->queue, - ns->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) + 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) @@ -1959,7 +2063,8 @@ 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; @@ -1968,7 +2073,7 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id) is_power_of_2(ctrl->max_hw_sectors)) iob = ctrl->max_hw_sectors; else - iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob)); + iob = nvme_lba_to_sect(ns->head, le16_to_cpu(id->noiob)); if (!iob) return; @@ -1987,38 +2092,36 @@ 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) { + struct queue_limits lim; + int ret; + blk_mq_freeze_queue(ns->disk->queue); - nvme_set_queue_limits(ns->ctrl, ns->queue); + lim = queue_limits_start_update(ns->disk->queue); + nvme_set_ctrl_limits(ns->ctrl, &lim); + 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); - 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); - } - /* Hide the block-interface for these devices */ - ns->disk->flags |= GENHD_FL_HIDDEN; - set_bit(NVME_NS_READY, &ns->flags); - - return 0; + 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; + sector_t capacity; unsigned lbaf; int ret; @@ -2026,23 +2129,65 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (ret) return ret; - blk_mq_freeze_queue(ns->disk->queue); + if (id->ncap == 0) { + /* namespace not allocated or attached */ + info->is_removed = true; + ret = -ENXIO; + goto out; + } lbaf = nvme_lbaf_index(id->flbas); - ns->lba_shift = id->lbaf[lbaf].ds; - nvme_set_queue_limits(ns->ctrl, ns->queue); - nvme_configure_metadata(ns, id); - nvme_set_chunk_sectors(ns, id); - nvme_update_disk_info(ns->disk, ns, id); + if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) { + ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm); + if (ret < 0) + goto out; + } - if (ns->head->ids.csi == NVME_CSI_ZNS) { - ret = nvme_update_zone_info(ns, lbaf); - if (ret) { - blk_mq_unfreeze_queue(ns->disk->queue); + 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; - } } + blk_mq_freeze_queue(ns->disk->queue); + ns->head->lba_shift = id->lbaf[lbaf].ds; + ns->head->nuse = le64_to_cpu(id->nuse); + capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze)); + + lim = queue_limits_start_update(ns->disk->queue); + 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); + + if (ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) + lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; + else + lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); + + /* + * 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); + goto out; + } + + set_capacity_and_notify(ns->disk, capacity); + /* * Only set the DEAC bit if the device guarantees that reads from * deallocated data return zeroes. While the DEAC bit does not @@ -2050,62 +2195,129 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, * do not return zeroes. */ if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3))) - ns->features |= NVME_NS_DEAC; + 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); 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->head->disk, ns, 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; - } + 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; + + 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 = queue_limits_start_update(ns->head->disk->queue); + 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); } + + 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 @@ -2124,7 +2336,7 @@ static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t l cmd.common.cdw11 = cpu_to_le32(len); return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len, - NVME_QID_ANY, 1, 0); + NVME_QID_ANY, NVME_SUBMIT_AT_HEAD); } static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended) @@ -2163,6 +2375,7 @@ 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, }; @@ -2245,25 +2458,8 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl) else ctrl->ctrl_config = NVME_CC_CSS_NVM; - if (ctrl->cap & NVME_CAP_CRMS_CRWMS) { - u32 crto; - - ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto); - if (ret) { - dev_err(ctrl->device, "Reading CRTO failed (%d)\n", - ret); - return ret; - } - - if (ctrl->cap & NVME_CAP_CRMS_CRIMS) { - ctrl->ctrl_config |= NVME_CC_CRIME; - timeout = NVME_CRTO_CRIMT(crto); - } else { - timeout = NVME_CRTO_CRWMT(crto); - } - } else { - timeout = NVME_CAP_TIMEOUT(ctrl->cap); - } + if (ctrl->cap & NVME_CAP_CRMS_CRWMS && ctrl->cap & NVME_CAP_CRMS_CRIMS) + 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; @@ -2272,11 +2468,39 @@ 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); + /* CAP value may change after initial CC write */ + ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap); if (ret) return ret; + timeout = NVME_CAP_TIMEOUT(ctrl->cap); + if (ctrl->cap & NVME_CAP_CRMS_CRWMS) { + u32 crto, ready_timeout; + + ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto); + if (ret) { + dev_err(ctrl->device, "Reading CRTO failed (%d)\n", + ret); + return ret; + } + + /* + * CRTO should always be greater or equal to CAP.TO, but some + * 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); + + if (ready_timeout < timeout) + dev_warn_once(ctrl->device, "bad crto:%x cap:%llx\n", + crto, ctrl->cap); + else + timeout = ready_timeout; + } + ctrl->ctrl_config |= NVME_CC_ENABLE; ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config); if (ret) @@ -2506,7 +2730,7 @@ static void nvme_set_latency_tolerance(struct device *dev, s32 val) if (ctrl->ps_max_latency_us != latency) { ctrl->ps_max_latency_us = latency; - if (ctrl->state == NVME_CTRL_LIVE) + if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE) nvme_configure_apst(ctrl); } } @@ -2764,7 +2988,7 @@ 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); @@ -2874,14 +3098,6 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) struct nvme_id_ctrl_nvm *id; int ret; - if (ctrl->oncs & NVME_CTRL_ONCS_DSM) { - ctrl->max_discard_sectors = UINT_MAX; - ctrl->max_discard_segments = NVME_DSM_MAX_RANGES; - } else { - ctrl->max_discard_sectors = 0; - ctrl->max_discard_segments = 0; - } - /* * Even though NVMe spec explicitly states that MDTS is not applicable * to the write-zeroes, we are cautious and limit the size to the @@ -2911,8 +3127,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) if (ret) goto free_data; - if (id->dmrl) - ctrl->max_discard_segments = id->dmrl; + ctrl->dmrl = id->dmrl; ctrl->dmrsl = le32_to_cpu(id->dmrsl); if (id->wzsl) ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl); @@ -2980,8 +3195,50 @@ static int nvme_init_effects(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) return 0; } +static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + /* + * In fabrics we need to verify the cntlid matches the + * admin connect + */ + if (ctrl->cntlid != le16_to_cpu(id->cntlid)) { + dev_err(ctrl->device, + "Mismatching cntlid: Connect %u vs Identify %u, rejecting\n", + ctrl->cntlid, le16_to_cpu(id->cntlid)); + return -EINVAL; + } + + if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) { + dev_err(ctrl->device, + "keep-alive support is mandatory for fabrics\n"); + return -EINVAL; + } + + if (!nvme_discovery_ctrl(ctrl) && ctrl->ioccsz < 4) { + dev_err(ctrl->device, + "I/O queue command capsule supported size %d < 4\n", + ctrl->ioccsz); + return -EINVAL; + } + + if (!nvme_discovery_ctrl(ctrl) && ctrl->iorcsz < 1) { + dev_err(ctrl->device, + "I/O queue response capsule supported size %d < 1\n", + ctrl->iorcsz); + return -EINVAL; + } + + if (!ctrl->maxcmd) { + dev_err(ctrl->device, "Maximum outstanding commands is 0\n"); + return -EINVAL; + } + + 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; @@ -3048,7 +3305,12 @@ 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); @@ -3066,7 +3328,7 @@ 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; @@ -3092,25 +3354,9 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->iorcsz = le32_to_cpu(id->iorcsz); ctrl->maxcmd = le16_to_cpu(id->maxcmd); - /* - * In fabrics we need to verify the cntlid matches the - * admin connect - */ - if (ctrl->cntlid != le16_to_cpu(id->cntlid)) { - dev_err(ctrl->device, - "Mismatching cntlid: Connect %u vs Identify " - "%u, rejecting\n", - ctrl->cntlid, le16_to_cpu(id->cntlid)); - ret = -EINVAL; - goto out_free; - } - - if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) { - dev_err(ctrl->device, - "keep-alive support is mandatory for fabrics\n"); - ret = -EINVAL; + ret = nvme_check_ctrl_fabric_info(ctrl, id); + if (ret) goto out_free; - } } else { ctrl->hmpre = le32_to_cpu(id->hmpre); ctrl->hmmin = le32_to_cpu(id->hmmin); @@ -3183,6 +3429,8 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl, bool was_suspended) clear_bit(NVME_CTRL_DIRTY_CAPABILITY, &ctrl->flags); ctrl->identified = true; + nvme_start_keep_alive(ctrl); + return 0; } EXPORT_SYMBOL_GPL(nvme_init_ctrl_finish); @@ -3192,7 +3440,7 @@ static int nvme_dev_open(struct inode *inode, struct file *file) struct nvme_ctrl *ctrl = container_of(inode->i_cdev, struct nvme_ctrl, cdev); - switch (ctrl->state) { + switch (nvme_ctrl_state(ctrl)) { case NVME_CTRL_LIVE: break; default: @@ -3294,7 +3542,7 @@ 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); @@ -3367,6 +3615,8 @@ 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; + ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1); + ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE); kref_init(&head->ref); if (head->ids.csi) { @@ -3502,7 +3752,7 @@ 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"); } } @@ -3521,9 +3771,10 @@ 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_rcu(ns, &ctrl->namespaces, list) { if (ns->head->ns_id == nsid) { if (!nvme_get_ns(ns)) continue; @@ -3533,7 +3784,7 @@ 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); @@ -3547,7 +3798,7 @@ 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; } } @@ -3556,6 +3807,7 @@ 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; @@ -3564,7 +3816,13 @@ 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; @@ -3572,15 +3830,6 @@ 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); @@ -3613,12 +3862,21 @@ 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)) { + 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_id_attr_groups)) + if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups)) goto out_cleanup_ns_from_list; if (!nvme_ns_head_multipath(ns->head)) @@ -3627,13 +3885,21 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) nvme_mpath_add_disk(ns, info->anagrpid); nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name); + /* + * Set ns->disk->device->driver_data to ns so we can access + * ns->head->passthru_err_log_enabled in + * nvme_io_passthru_err_log_enabled_[store | show](). + */ + dev_set_drvdata(disk_to_dev(ns->disk), ns); + return; 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); @@ -3683,9 +3949,10 @@ 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); @@ -3704,7 +3971,7 @@ 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, @@ -3720,7 +3987,7 @@ 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); } @@ -3769,22 +4036,53 @@ 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) @@ -3793,11 +4091,15 @@ 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, @@ -3813,19 +4115,23 @@ 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; } @@ -3878,7 +4184,7 @@ static void nvme_scan_work(struct work_struct *work) int ret; /* No tagset on a live ctrl means IO queues could not created */ - if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE || !ctrl->tagset) return; /* @@ -3910,7 +4216,7 @@ 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); @@ -3948,15 +4254,16 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) * removing the namespaces' disks; fail all the queues now to avoid * potentially having to clean up the failed sync later. */ - if (ctrl->state == NVME_CTRL_DEAD) + if (nvme_ctrl_state(ctrl) == NVME_CTRL_DEAD) nvme_mark_namespaces_dead(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); @@ -4030,7 +4337,7 @@ static void nvme_async_event_work(struct work_struct *work) * flushing ctrl async_event_work after changing the controller state * from LIVE and before freeing the admin queue. */ - if (ctrl->state == NVME_CTRL_LIVE) + if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE) ctrl->ops->submit_async_event(ctrl); } @@ -4051,14 +4358,30 @@ static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl) static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) { struct nvme_fw_slot_info_log *log; + u8 next_fw_slot, cur_fw_slot; log = kmalloc(sizeof(*log), GFP_KERNEL); if (!log) return; if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM, - log, sizeof(*log), 0)) + log, sizeof(*log), 0)) { dev_warn(ctrl->device, "Get FW SLOT INFO log error\n"); + goto out_free_log; + } + + cur_fw_slot = log->afi & 0x7; + next_fw_slot = (log->afi & 0x70) >> 4; + if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) { + dev_info(ctrl->device, + "Firmware is activated after next Controller Level Reset\n"); + goto out_free_log; + } + + memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1], + sizeof(ctrl->subsys->firmware_rev)); + +out_free_log: kfree(log); } @@ -4068,6 +4391,8 @@ static void nvme_fw_act_work(struct work_struct *work) struct nvme_ctrl, fw_act_work); unsigned long fw_act_timeout; + nvme_auth_stop(ctrl); + if (ctrl->mtfa) fw_act_timeout = jiffies + msecs_to_jiffies(ctrl->mtfa * 100); @@ -4123,7 +4448,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) * firmware activation. */ if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { - nvme_auth_stop(ctrl); requeue = false; queue_work(nvme_wq, &ctrl->fw_act_work); } @@ -4146,7 +4470,8 @@ 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); } @@ -4193,13 +4518,15 @@ 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) @@ -4212,14 +4539,14 @@ 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; @@ -4268,12 +4595,13 @@ 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; @@ -4283,13 +4611,15 @@ 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; @@ -4316,7 +4646,6 @@ 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); @@ -4327,8 +4656,6 @@ EXPORT_SYMBOL_GPL(nvme_stop_ctrl); void nvme_start_ctrl(struct nvme_ctrl *ctrl) { - nvme_start_keep_alive(ctrl); - nvme_enable_aen(ctrl); /* @@ -4354,6 +4681,7 @@ 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); @@ -4383,9 +4711,9 @@ static void nvme_free_ctrl(struct device *dev) if (!subsys || ctrl->instance != subsys->instance) ida_free(&nvme_instance_ida, ctrl->instance); - 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); @@ -4408,19 +4736,28 @@ 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) { int ret; - ctrl->state = NVME_CTRL_NEW; + WRITE_ONCE(ctrl->state, NVME_CTRL_NEW); + 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; @@ -4435,6 +4772,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work); memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd)); ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive; + ctrl->ka_last_check_time = jiffies; BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) > PAGE_SIZE); @@ -4449,11 +4787,17 @@ 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; @@ -4461,16 +4805,36 @@ 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 @@ -4481,62 +4845,50 @@ 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_rcu(ns, &ctrl->namespaces, list) 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) + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_rcu(ns, &ctrl->namespaces, list) blk_mq_unfreeze_queue(ns->queue); - up_read(&ctrl->namespaces_rwsem); + srcu_read_unlock(&ctrl->srcu, srcu_idx); + clear_bit(NVME_CTRL_FROZEN, &ctrl->flags); } 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_rcu(ns, &ctrl->namespaces, list) { 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); @@ -4544,22 +4896,25 @@ 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_rcu(ns, &ctrl->namespaces, list) 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; - down_read(&ctrl->namespaces_rwsem); - list_for_each_entry(ns, &ctrl->namespaces, list) + set_bit(NVME_CTRL_FROZEN, &ctrl->flags); + srcu_idx = srcu_read_lock(&ctrl->srcu); + list_for_each_entry_rcu(ns, &ctrl->namespaces, list) blk_freeze_queue_start(ns->queue); - up_read(&ctrl->namespaces_rwsem); + srcu_read_unlock(&ctrl->srcu, srcu_idx); } EXPORT_SYMBOL_GPL(nvme_start_freeze); @@ -4602,11 +4957,12 @@ 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_rcu(ns, &ctrl->namespaces, list) blk_sync_queue(ns->queue); - up_read(&ctrl->namespaces_rwsem); + srcu_read_unlock(&ctrl->srcu, srcu_idx); } EXPORT_SYMBOL_GPL(nvme_sync_io_queues); @@ -4684,29 +5040,22 @@ 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) @@ -4714,13 +5063,13 @@ static int __init nvme_core_init(void) 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: @@ -4736,9 +5085,9 @@ 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); @@ -4750,5 +5099,6 @@ static void __exit nvme_core_exit(void) MODULE_LICENSE("GPL"); MODULE_VERSION("1.0"); +MODULE_DESCRIPTION("NVMe host core framework"); module_init(nvme_core_init); module_exit(nvme_core_exit); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 8175d49f2909..432efcbf9e2f 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -12,6 +12,7 @@ #include <linux/seq_file.h> #include "nvme.h" #include "fabrics.h" +#include <linux/nvme-keyring.h> static LIST_HEAD(nvmf_transports); static DECLARE_RWSEM(nvmf_transports_rwsem); @@ -179,14 +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, 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; } @@ -225,14 +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, 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); @@ -270,15 +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, 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. @@ -294,7 +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, @@ -386,8 +402,8 @@ static struct nvmf_connect_data *nvmf_connect_data_prep(struct nvme_ctrl *ctrl, uuid_copy(&data->hostid, &ctrl->opts->host->id); data->cntlid = cpu_to_le16(cntlid); - strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); - strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); + strscpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); + strscpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); return data; } @@ -427,12 +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) { @@ -449,8 +459,10 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) return -ENOMEM; ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, - data, sizeof(*data), NVME_QID_ANY, 1, - BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); + data, sizeof(*data), NVME_QID_ANY, + NVME_SUBMIT_AT_HEAD | + NVME_SUBMIT_NOWAIT | + NVME_SUBMIT_RESERVED); if (ret) { nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32), &cmd, data); @@ -464,7 +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 */ @@ -472,14 +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"); } @@ -524,11 +536,14 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) return -ENOMEM; ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res, - data, sizeof(*data), qid, 1, - BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); + data, sizeof(*data), qid, + NVME_SUBMIT_AT_HEAD | + NVME_SUBMIT_RESERVED | + NVME_SUBMIT_NOWAIT); if (ret) { nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32), &cmd, data); + goto out_free_data; } result = le32_to_cpu(res.u32); if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) { @@ -536,7 +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 */ @@ -544,12 +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: @@ -558,8 +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; @@ -622,6 +656,23 @@ static struct nvmf_transport_ops *nvmf_lookup_transport( return NULL; } +static struct key *nvmf_parse_key(int key_id) +{ + struct key *key; + + if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) { + pr_err("TLS is not supported\n"); + return ERR_PTR(-EINVAL); + } + + 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); + return key; +} + static const match_table_t opt_tokens = { { NVMF_OPT_TRANSPORT, "transport=%s" }, { NVMF_OPT_TRADDR, "traddr=%s" }, @@ -643,10 +694,19 @@ static const match_table_t opt_tokens = { { NVMF_OPT_NR_WRITE_QUEUES, "nr_write_queues=%d" }, { NVMF_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" }, { NVMF_OPT_TOS, "tos=%d" }, +#ifdef CONFIG_NVME_TCP_TLS + { NVMF_OPT_KEYRING, "keyring=%d" }, + { NVMF_OPT_TLS_KEY, "tls_key=%d" }, +#endif { NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" }, { NVMF_OPT_DISCOVERY, "discovery" }, +#ifdef CONFIG_NVME_HOST_AUTH { NVMF_OPT_DHCHAP_SECRET, "dhchap_secret=%s" }, { NVMF_OPT_DHCHAP_CTRL_SECRET, "dhchap_ctrl_secret=%s" }, +#endif +#ifdef CONFIG_NVME_TCP_TLS + { NVMF_OPT_TLS, "tls" }, +#endif { NVMF_OPT_ERR, NULL } }; @@ -657,9 +717,10 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, char *options, *o, *p; int token, ret = 0; size_t nqnlen = 0; - int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO; + int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO, key_id; uuid_t hostid; char hostnqn[NVMF_NQN_SIZE]; + struct key *key; /* Set defaults */ opts->queue_size = NVMF_DEF_QUEUE_SIZE; @@ -671,6 +732,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->hdr_digest = false; opts->data_digest = false; opts->tos = -1; /* < 0 == use transport default */ + opts->tls = false; + opts->tls_key = NULL; + opts->keyring = NULL; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -924,6 +988,32 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } opts->tos = token; break; + case NVMF_OPT_KEYRING: + if (match_int(args, &key_id) || key_id <= 0) { + ret = -EINVAL; + goto out; + } + key = nvmf_parse_key(key_id); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto out; + } + key_put(opts->keyring); + opts->keyring = key; + break; + case NVMF_OPT_TLS_KEY: + if (match_int(args, &key_id) || key_id <= 0) { + ret = -EINVAL; + goto out; + } + key = nvmf_parse_key(key_id); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto out; + } + key_put(opts->tls_key); + opts->tls_key = key; + break; case NVMF_OPT_DISCOVERY: opts->discovery_nqn = true; break; @@ -955,6 +1045,14 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, kfree(opts->dhchap_ctrl_secret); opts->dhchap_ctrl_secret = p; break; + case NVMF_OPT_TLS: + if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) { + pr_err("TLS is not supported\n"); + ret = -EINVAL; + goto out; + } + opts->tls = true; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); @@ -1156,6 +1254,8 @@ static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts, void nvmf_free_options(struct nvmf_ctrl_options *opts) { nvmf_host_put(opts->host); + key_put(opts->keyring); + key_put(opts->tls_key); kfree(opts->transport); kfree(opts->traddr); kfree(opts->trsvcid); @@ -1247,7 +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); @@ -1300,10 +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) @@ -1367,15 +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); @@ -1391,9 +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; @@ -1402,8 +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); @@ -1421,6 +1523,7 @@ static void __exit nvmf_exit(void) } MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("NVMe host fabrics library"); module_init(nvmf_init); module_exit(nvmf_exit); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 82e7a27ffbde..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 @@ -70,6 +63,9 @@ enum { NVMF_OPT_DISCOVERY = 1 << 22, NVMF_OPT_DHCHAP_SECRET = 1 << 23, NVMF_OPT_DHCHAP_CTRL_SECRET = 1 << 24, + NVMF_OPT_TLS = 1 << 25, + NVMF_OPT_KEYRING = 1 << 26, + NVMF_OPT_TLS_KEY = 1 << 27, }; /** @@ -102,6 +98,9 @@ enum { * @dhchap_secret: DH-HMAC-CHAP secret * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional * authentication + * @keyring: Keyring to use for key lookups + * @tls_key: TLS key for encrypted connections (TCP) + * @tls: Start TLS encrypted connections (TCP) * @disable_sqflow: disable controller sq flow control * @hdr_digest: generate/verify header digest (TCP) * @data_digest: generate/verify data digest (TCP) @@ -128,6 +127,9 @@ struct nvmf_ctrl_options { struct nvmf_host *host; char *dhchap_secret; char *dhchap_ctrl_secret; + struct key *keyring; + struct key *tls_key; + bool tls; bool disable_sqflow; bool hdr_digest; bool data_digest; @@ -176,9 +178,11 @@ static inline bool nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl, struct nvmf_ctrl_options *opts) { - if (ctrl->state == NVME_CTRL_DELETING || - ctrl->state == NVME_CTRL_DELETING_NOIO || - ctrl->state == NVME_CTRL_DEAD || + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); + + if (state == NVME_CTRL_DELETING || + state == NVME_CTRL_DELETING_NOIO || + state == NVME_CTRL_DEAD || strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) || strcmp(opts->host->nqn, ctrl->opts->host->nqn) || !uuid_equal(&opts->host->id, &ctrl->opts->host->id)) @@ -213,13 +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 1cd2bf82319a..b81af7919e94 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -221,11 +221,6 @@ static LIST_HEAD(nvme_fc_lport_list); static DEFINE_IDA(nvme_fc_local_port_cnt); static DEFINE_IDA(nvme_fc_ctrl_cnt); -static struct workqueue_struct *nvme_fc_wq; - -static bool nvme_fc_waiting_to_unload; -static DECLARE_COMPLETION(nvme_fc_unload_proceed); - /* * These items are short-term. They will eventually be moved into * a generic FC class. See comments in module init. @@ -255,8 +250,6 @@ nvme_fc_free_lport(struct kref *ref) /* remove from transport list */ spin_lock_irqsave(&nvme_fc_lock, flags); list_del(&lport->port_list); - if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list)) - complete(&nvme_fc_unload_proceed); spin_unlock_irqrestore(&nvme_fc_lock, flags); ida_free(&nvme_fc_local_port_cnt, lport->localport.port_num); @@ -557,7 +550,7 @@ nvme_fc_rport_get(struct nvme_fc_rport *rport) static void nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl) { - switch (ctrl->ctrl.state) { + switch (nvme_ctrl_state(&ctrl->ctrl)) { case NVME_CTRL_NEW: case NVME_CTRL_CONNECTING: /* @@ -793,7 +786,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) "NVME-FC{%d}: controller connectivity lost. Awaiting " "Reconnect", ctrl->cnum); - switch (ctrl->ctrl.state) { + switch (nvme_ctrl_state(&ctrl->ctrl)) { case NVME_CTRL_NEW: case NVME_CTRL_LIVE: /* @@ -1218,10 +1211,10 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, /* Linux supports only Dynamic controllers */ assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff); uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id); - strncpy(assoc_rqst->assoc_cmd.hostnqn, ctrl->ctrl.opts->host->nqn, - min(FCNVME_ASSOC_HOSTNQN_LEN, NVMF_NQN_SIZE)); - strncpy(assoc_rqst->assoc_cmd.subnqn, ctrl->ctrl.opts->subsysnqn, - min(FCNVME_ASSOC_SUBNQN_LEN, NVMF_NQN_SIZE)); + strscpy(assoc_rqst->assoc_cmd.hostnqn, ctrl->ctrl.opts->host->nqn, + sizeof(assoc_rqst->assoc_cmd.hostnqn)); + strscpy(assoc_rqst->assoc_cmd.subnqn, ctrl->ctrl.opts->subsysnqn, + sizeof(assoc_rqst->assoc_cmd.subnqn)); lsop->queue = queue; lsreq->rqstaddr = assoc_rqst; @@ -1924,7 +1917,7 @@ char *nvme_fc_io_getuuid(struct nvmefc_fcp_req *req) struct nvme_fc_fcp_op *op = fcp_req_to_fcp_op(req); struct request *rq = op->rq; - if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !rq->bio) + if (!IS_ENABLED(CONFIG_BLK_CGROUP_FC_APPID) || !rq || !rq->bio) return NULL; return blkcg_get_fc_appid(rq->bio); } @@ -2435,7 +2428,7 @@ 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); @@ -2548,24 +2541,17 @@ 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. */ - enum nvme_ctrl_state state; - unsigned long flags; - - spin_lock_irqsave(&ctrl->lock, flags); - state = ctrl->ctrl.state; - if (state == NVME_CTRL_CONNECTING) { - set_bit(ASSOC_FAILED, &ctrl->flags); - spin_unlock_irqrestore(&ctrl->lock, flags); + if (ctrl->ctrl.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); return; } - spin_unlock_irqrestore(&ctrl->lock, flags); /* Otherwise, only proceed if in LIVE state - e.g. on first error */ - if (state != NVME_CTRL_LIVE) + if (ctrl->ctrl.state != NVME_CTRL_LIVE) return; dev_warn(ctrl->ctrl.device, @@ -2581,6 +2567,7 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq) { struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); struct nvme_fc_ctrl *ctrl = op->ctrl; + u16 qnum = op->queue->qnum; struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu; struct nvme_command *sqe = &cmdiu->sqe; @@ -2589,10 +2576,11 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq) * will detect the aborted io and will fail the connection. */ dev_info(ctrl->ctrl.device, - "NVME-FC{%d.%d}: io timeout: opcode %d fctype %d w10/11: " + "NVME-FC{%d.%d}: io timeout: opcode %d fctype %d (%s) w10/11: " "x%08x/x%08x\n", - ctrl->cnum, op->queue->qnum, sqe->common.opcode, - sqe->connect.fctype, sqe->common.cdw10, sqe->common.cdw11); + ctrl->cnum, qnum, sqe->common.opcode, sqe->fabrics.fctype, + nvme_fabrics_opcode_str(qnum, sqe), + sqe->common.cdw10, sqe->common.cdw11); if (__nvme_fc_abort_op(ctrl, op)) nvme_fc_error_recovery(ctrl, "io timeout abort failed"); @@ -3132,27 +3120,28 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) nvme_unquiesce_admin_queue(&ctrl->ctrl); ret = nvme_init_ctrl_finish(&ctrl->ctrl, false); - if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) - ret = -EIO; if (ret) goto out_disconnect_admin_queue; - + if (test_bit(ASSOC_FAILED, &ctrl->flags)) { + ret = -EIO; + goto out_stop_keep_alive; + } /* sanity checks */ /* FC-NVME does not have other data in the capsule */ 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; - goto out_disconnect_admin_queue; + ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out_stop_keep_alive; } /* FC-NVME supports normal SGL Data Block Descriptors */ 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; - goto out_disconnect_admin_queue; + ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out_stop_keep_alive; } if (opts->queue_size > ctrl->ctrl.maxcmd) { @@ -3179,16 +3168,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) else ret = nvme_fc_recreate_io_queues(ctrl); } - - spin_lock_irqsave(&ctrl->lock, flags); if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) ret = -EIO; - if (ret) { - spin_unlock_irqrestore(&ctrl->lock, flags); + if (ret) goto out_term_aen_ops; - } + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - spin_unlock_irqrestore(&ctrl->lock, flags); ctrl->ctrl.nr_reconnects = 0; @@ -3199,6 +3184,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) out_term_aen_ops: nvme_fc_term_aen_ops(ctrl); +out_stop_keep_alive: + nvme_stop_keep_alive(&ctrl->ctrl); out_disconnect_admin_queue: dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: create_assoc failed, assoc_id %llx ret %d\n", @@ -3316,19 +3303,17 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ; bool recon = true; - if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) + if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_CONNECTING) return; if (portptr->port_state == FC_OBJSTATE_ONLINE) { 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 " @@ -3340,7 +3325,7 @@ 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); @@ -3397,7 +3382,8 @@ 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, @@ -3459,12 +3445,11 @@ 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 & @@ -3506,10 +3491,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->ctrl.opts = opts; ctrl->ctrl.nr_reconnects = 0; - if (lport->dev) - ctrl->ctrl.numa_node = dev_to_node(lport->dev); - else - ctrl->ctrl.numa_node = NUMA_NO_NODE; INIT_LIST_HEAD(&ctrl->ctrl_list); ctrl->lport = lport; ctrl->rport = rport; @@ -3554,8 +3535,38 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0); if (ret) goto out_free_queues; + 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, @@ -3585,8 +3596,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, flush_delayed_work(&ctrl->connect_work); dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: new ctrl: NQN \"%s\"\n", - ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl)); + "NVME-FC{%d}: new ctrl: NQN \"%s\", hostnqn: %s\n", + ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl), opts->host->nqn); return &ctrl->ctrl; @@ -3601,6 +3612,7 @@ 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); @@ -3614,20 +3626,8 @@ 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; @@ -3904,10 +3904,6 @@ static int __init nvme_fc_init_module(void) { int ret; - nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0); - if (!nvme_fc_wq) - return -ENOMEM; - /* * NOTE: * It is expected that in the future the kernel will combine @@ -3925,7 +3921,7 @@ static int __init nvme_fc_init_module(void) ret = class_register(&fc_class); if (ret) { pr_err("couldn't register class fc\n"); - goto out_destroy_wq; + return ret; } /* @@ -3949,8 +3945,6 @@ out_destroy_device: device_destroy(&fc_class, MKDEV(0, 0)); out_destroy_class: class_unregister(&fc_class); -out_destroy_wq: - destroy_workqueue(nvme_fc_wq); return ret; } @@ -3970,48 +3964,27 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport) spin_unlock(&rport->lock); } -static void -nvme_fc_cleanup_for_unload(void) +static void __exit nvme_fc_exit_module(void) { struct nvme_fc_lport *lport; struct nvme_fc_rport *rport; - - list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { - list_for_each_entry(rport, &lport->endp_list, endp_list) { - nvme_fc_delete_controllers(rport); - } - } -} - -static void __exit nvme_fc_exit_module(void) -{ unsigned long flags; - bool need_cleanup = false; spin_lock_irqsave(&nvme_fc_lock, flags); - nvme_fc_waiting_to_unload = true; - if (!list_empty(&nvme_fc_lport_list)) { - need_cleanup = true; - nvme_fc_cleanup_for_unload(); - } + list_for_each_entry(lport, &nvme_fc_lport_list, port_list) + list_for_each_entry(rport, &lport->endp_list, endp_list) + nvme_fc_delete_controllers(rport); spin_unlock_irqrestore(&nvme_fc_lock, flags); - if (need_cleanup) { - pr_info("%s: waiting for ctlr deletes\n", __func__); - wait_for_completion(&nvme_fc_unload_proceed); - pr_info("%s: ctrl deletes complete\n", __func__); - } + flush_workqueue(nvme_delete_wq); nvmf_unregister_transport(&nvme_fc_transport); - ida_destroy(&nvme_fc_local_port_cnt); - ida_destroy(&nvme_fc_ctrl_cnt); - device_destroy(&fc_class, MKDEV(0, 0)); class_unregister(&fc_class); - destroy_workqueue(nvme_fc_wq); } module_init(nvme_fc_init_module); module_exit(nvme_fc_exit_module); +MODULE_DESCRIPTION("NVMe host FC transport driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 316f3e4ca7cc..8df73a0b3980 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -187,7 +187,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data, return 0; } -static const struct hwmon_channel_info *nvme_hwmon_info[] = { +static const struct hwmon_channel_info *const nvme_hwmon_info[] = { HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ), HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index d39f3219358b..b9b79ccfabf8 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -3,9 +3,10 @@ * 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.h> +#include <linux/io_uring/cmd.h> #include "nvme.h" enum { @@ -18,15 +19,12 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, { u32 effects; - if (capable(CAP_SYS_ADMIN)) - return true; - /* * Do not allow unprivileged passthrough on partitions, as that allows an * escape from the containment of the partition. */ if (flags & NVME_IOCTL_PARTITION) - return false; + goto admin; /* * Do not allow unprivileged processes to send vendor specific or fabrics @@ -34,7 +32,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, */ if (c->common.opcode >= nvme_cmd_vendor_start || c->common.opcode == nvme_fabrics_command) - return false; + goto admin; /* * Do not allow unprivileged passthrough of admin commands except @@ -53,7 +51,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, return true; } } - return false; + goto admin; } /* @@ -63,7 +61,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, */ effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode); if (!(effects & NVME_CMD_EFFECTS_CSUPP)) - return false; + goto admin; /* * Don't allow passthrough for command that have intrusive (or unknown) @@ -72,16 +70,20 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_UUID_SEL | NVME_CMD_EFFECTS_SCOPE_MASK)) - return false; + goto admin; /* * Only allow I/O commands that transfer data to the controller or that * change the logical block contents if the file descriptor is open for * writing. */ - if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) - return open_for_write; + if ((nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) && + !open_for_write) + goto admin; + return true; +admin: + return capable(CAP_SYS_ADMIN); } /* @@ -96,55 +98,6 @@ static void __user *nvme_to_user_ptr(uintptr_t ptrval) return (void __user *)ptrval; } -static void *nvme_add_user_metadata(struct request *req, void __user *ubuf, - unsigned len, u32 seed) -{ - struct bio_integrity_payload *bip; - int ret = -ENOMEM; - void *buf; - struct bio *bio = req->bio; - - buf = kmalloc(len, GFP_KERNEL); - if (!buf) - goto out; - - ret = -EFAULT; - if ((req_op(req) == REQ_OP_DRV_OUT) && copy_from_user(buf, ubuf, len)) - goto out_free_meta; - - bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); - if (IS_ERR(bip)) { - ret = PTR_ERR(bip); - goto out_free_meta; - } - - bip->bip_iter.bi_size = len; - bip->bip_iter.bi_sector = seed; - ret = bio_integrity_add_page(bio, virt_to_page(buf), len, - offset_in_page(buf)); - if (ret != len) { - ret = -ENOMEM; - goto out_free_meta; - } - - req->cmd_flags |= REQ_INTEGRITY; - return buf; -out_free_meta: - kfree(buf); -out: - return ERR_PTR(ret); -} - -static int nvme_finish_user_metadata(struct request *req, void __user *ubuf, - void *meta, unsigned len, int ret) -{ - if (!ret && req_op(req) == REQ_OP_DRV_IN && - copy_to_user(ubuf, meta, len)) - ret = -EFAULT; - kfree(meta); - return ret; -} - static struct request *nvme_alloc_user_request(struct request_queue *q, struct nvme_command *cmd, blk_opf_t rq_flags, blk_mq_req_flags_t blk_flags) @@ -161,16 +114,19 @@ 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, void **metap, struct io_uring_cmd *ioucmd, - unsigned int flags) + u32 meta_seed, 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); + bool has_metadata = meta_buffer && meta_len; struct bio *bio = NULL; - void *meta = NULL; int ret; + if (has_metadata && !supports_metadata) + return -EINVAL; + if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) { struct iov_iter iter; @@ -190,18 +146,16 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, if (ret) goto out; + bio = req->bio; if (bdev) bio_set_dev(bio, bdev); - if (bdev && meta_buffer && meta_len) { - meta = nvme_add_user_metadata(req, meta_buffer, meta_len, - meta_seed); - if (IS_ERR(meta)) { - ret = PTR_ERR(meta); + if (has_metadata) { + ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len, + meta_seed); + if (ret) goto out_unmap; - } - *metap = meta; } return ret; @@ -222,7 +176,6 @@ static int nvme_submit_user_cmd(struct request_queue *q, struct nvme_ns *ns = q->queuedata; struct nvme_ctrl *ctrl; struct request *req; - void *meta = NULL; struct bio *bio; u32 effects; int ret; @@ -234,7 +187,7 @@ 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, &meta, NULL, flags); + meta_len, meta_seed, NULL, flags); if (ret) return ret; } @@ -246,9 +199,6 @@ static int nvme_submit_user_cmd(struct request_queue *q, ret = nvme_execute_rq(req, false); if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); - if (meta) - ret = nvme_finish_user_metadata(req, meta_buffer, meta, - meta_len, ret); if (bio) blk_rq_unmap_user(bio); blk_mq_free_request(req); @@ -280,10 +230,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) return -EINVAL; } - length = (io.nblocks + 1) << ns->lba_shift; + length = (io.nblocks + 1) << ns->head->lba_shift; if ((io.control & NVME_RW_PRINFO_PRACT) && - ns->ms == sizeof(struct t10_pi_tuple)) { + (ns->head->ms == ns->head->pi_size)) { /* * Protection information is stripped/inserted by the * controller. @@ -293,11 +243,11 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) meta_len = 0; metadata = NULL; } else { - meta_len = (io.nblocks + 1) * ns->ms; + meta_len = (io.nblocks + 1) * ns->head->ms; metadata = nvme_to_user_ptr(io.metadata); } - if (ns->features & NVME_NS_EXT_LBAS) { + if (ns->head->features & NVME_NS_EXT_LBAS) { length += meta_len; meta_len = 0; } else if (meta_len) { @@ -314,8 +264,8 @@ 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); @@ -443,19 +393,10 @@ struct nvme_uring_data { * Expect build errors if this grows larger than that. */ struct nvme_uring_cmd_pdu { - union { - struct bio *bio; - struct request *req; - }; - u32 meta_len; - u32 nvme_status; - union { - struct { - void *meta; /* kernel-resident buffer */ - void __user *meta_buffer; - }; - u64 result; - } u; + struct request *req; + struct bio *bio; + u64 result; + int status; }; static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( @@ -464,31 +405,6 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; } -static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd, - unsigned issue_flags) -{ - struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); - struct request *req = pdu->req; - int status; - u64 result; - - if (nvme_req(req)->flags & NVME_REQ_CANCELLED) - status = -EINTR; - else - status = nvme_req(req)->status; - - result = le64_to_cpu(nvme_req(req)->result.u64); - - if (pdu->meta_len) - status = nvme_finish_user_metadata(req, pdu->u.meta_buffer, - pdu->u.meta, pdu->meta_len, status); - if (req->bio) - blk_rq_unmap_user(req->bio); - blk_mq_free_request(req); - - io_uring_cmd_done(ioucmd, status, result, issue_flags); -} - static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, unsigned issue_flags) { @@ -496,8 +412,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, if (pdu->bio) blk_rq_unmap_user(pdu->bio); - - io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags); + io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags); } static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, @@ -506,20 +421,24 @@ 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); - req->bio = pdu->bio; if (nvme_req(req)->flags & NVME_REQ_CANCELLED) - pdu->nvme_status = -EINTR; + pdu->status = -EINTR; else - pdu->nvme_status = nvme_req(req)->status; - pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64); + pdu->status = nvme_req(req)->status; + 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)) { - WRITE_ONCE(ioucmd->cookie, NULL); - nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED); + 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); } @@ -527,29 +446,6 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, return RQ_END_IO_FREE; } -static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req, - blk_status_t err) -{ - struct io_uring_cmd *ioucmd = req->end_io_data; - struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); - - req->bio = pdu->bio; - pdu->req = req; - - /* - * For iopoll, complete it directly. - * Otherwise, move the completion to task work. - */ - if (blk_rq_is_poll(req)) { - WRITE_ONCE(ioucmd->cookie, NULL); - nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED); - } else { - io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb); - } - - return RQ_END_IO_NONE; -} - static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec) { @@ -561,7 +457,6 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct request *req; blk_opf_t rq_flags = REQ_ALLOC_CACHE; blk_mq_req_flags_t blk_flags = 0; - void *meta = NULL; int ret; c.common.opcode = READ_ONCE(cmd->opcode); @@ -609,27 +504,16 @@ 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, &meta, ioucmd, vec); + d.metadata_len, 0, ioucmd, vec); if (ret) return ret; } - if (blk_rq_is_poll(req)) { - ioucmd->flags |= IORING_URING_CMD_POLLED; - WRITE_ONCE(ioucmd->cookie, req); - } - /* to free bio on completion, as req->bio will be null at that time */ pdu->bio = req->bio; - pdu->meta_len = d.metadata_len; + pdu->req = req; req->end_io_data = ioucmd; - if (pdu->meta_len) { - pdu->u.meta = meta; - pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata); - req->end_io = nvme_uring_cmd_end_io_meta; - } else { - req->end_io = nvme_uring_cmd_end_io; - } + req->end_io = nvme_uring_cmd_end_io; blk_execute_rq_nowait(req, false); return -EIOCBQUEUED; } @@ -780,16 +664,12 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd, struct io_comp_batch *iob, unsigned int poll_flags) { - struct request *req; - int ret = 0; - - if (!(ioucmd->flags & IORING_URING_CMD_POLLED)) - return 0; + struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); + struct request *req = pdu->req; - req = READ_ONCE(ioucmd->cookie); if (req && blk_rq_is_poll(req)) - ret = blk_rq_poll(req, iob, poll_flags); - return ret; + return blk_rq_poll(req, iob, poll_flags); + return 0; } #ifdef CONFIG_NVME_MULTIPATH static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, @@ -914,15 +794,15 @@ 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"); @@ -932,15 +812,18 @@ 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 0a88d7bdc5e3..48e7a8906d01 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) { @@ -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 +162,17 @@ 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_rcu(ns, &ctrl->namespaces, list) { if (!ns->head->disk) continue; kblockd_schedule_work(&ns->head->requeue_work); - if (ctrl->state == NVME_CTRL_LIVE) + 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 +206,14 @@ 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_rcu(ns, &ctrl->namespaces, list) { 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) @@ -223,13 +237,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns) static bool nvme_path_is_disabled(struct nvme_ns *ns) { + enum nvme_ctrl_state state = nvme_ctrl_state(ns->ctrl); + /* * We don't treat NVME_CTRL_DELETING as a disabled path as I/O should * still be able to complete assuming that the controller is connected. * Otherwise it will fail immediately and return to the requeue list. */ - if (ns->ctrl->state != NVME_CTRL_LIVE && - ns->ctrl->state != NVME_CTRL_DELETING) + if (state != NVME_CTRL_LIVE && state != NVME_CTRL_DELETING) return true; if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) || !test_bit(NVME_NS_READY, &ns->flags)) @@ -246,7 +261,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) 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; @@ -286,10 +302,15 @@ 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)) @@ -329,13 +350,49 @@ 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_rcu(ns, &head->list, siblings) { + 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 ns->ctrl->state == NVME_CTRL_LIVE && + 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; @@ -343,22 +400,34 @@ 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; + if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) + return NULL; + list_for_each_entry_rcu(ns, &head->list, siblings) { if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags)) continue; - switch (ns->ctrl->state) { + switch (nvme_ctrl_state(ns->ctrl)) { case NVME_CTRL_LIVE: case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: @@ -422,6 +491,21 @@ 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) @@ -449,6 +533,7 @@ 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, }; @@ -515,7 +600,7 @@ 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); @@ -531,36 +616,21 @@ 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; + else + lim.max_zone_append_sectors = 0; + + 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. - */ - 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); return 0; } @@ -579,9 +649,9 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) */ if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { rc = device_add_disk(&head->subsys->dev, head->disk, - nvme_ns_id_attr_groups); + 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); @@ -592,7 +662,7 @@ 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); } @@ -667,7 +737,7 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, * controller is ready. */ if (nvme_state_is_live(ns->ana_state) && - ns->ctrl->state == NVME_CTRL_LIVE) + nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE) nvme_mpath_set_live(ns); } @@ -677,6 +747,7 @@ 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), @@ -688,8 +759,8 @@ 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_rcu(ns, &ctrl->namespaces, list) { unsigned nsid; again: nsid = le32_to_cpu(desc->nsids[n]); @@ -702,7 +773,7 @@ again: if (ns->head->ns_id > nsid) goto again; } - up_read(&ctrl->namespaces_rwsem); + srcu_read_unlock(&ctrl->srcu, srcu_idx); return 0; } @@ -748,7 +819,7 @@ static void nvme_ana_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work); - if (ctrl->state != NVME_CTRL_LIVE) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) return; nvme_read_ana_log(ctrl); @@ -796,6 +867,29 @@ 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) { @@ -805,7 +899,7 @@ 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; } } @@ -868,9 +962,6 @@ 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; @@ -881,11 +972,16 @@ 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); del_gendisk(head->disk); } + /* + * 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); } void nvme_mpath_remove_disk(struct nvme_ns_head *head) @@ -916,6 +1012,9 @@ 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 f35647c470af..313a4f978a2c 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -16,6 +16,7 @@ #include <linux/rcupdate.h> #include <linux/wait.h> #include <linux/t10-pi.h> +#include <linux/ratelimit_types.h> #include <trace/events/block.h> @@ -48,6 +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 @@ -89,6 +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), @@ -156,6 +163,16 @@ enum nvme_quirks { * No temperature thresholds for channels other than 0 (Composite). */ NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), + + /* + * 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), }; /* @@ -184,6 +201,7 @@ 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) @@ -251,11 +269,13 @@ enum nvme_ctrl_flags { NVME_CTRL_STOPPED = 3, NVME_CTRL_SKIP_ID_CNS_CS = 4, NVME_CTRL_DIRTY_CAPABILITY = 5, + NVME_CTRL_FROZEN = 6, }; struct nvme_ctrl { bool comp_seen; bool identified; + bool passthru_err_log_enabled; enum nvme_ctrl_state state; spinlock_t lock; struct mutex scan_lock; @@ -269,7 +289,8 @@ 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 @@ -285,7 +306,6 @@ struct nvme_ctrl { struct opal_dev *opal_dev; - char name[12]; u16 cntlid; u16 mtfa; @@ -296,14 +316,13 @@ struct nvme_ctrl { u32 max_hw_sectors; u32 max_segments; u32 max_integrity_segments; - u32 max_discard_sectors; - u32 max_discard_segments; u32 max_zeroes_sectors; #ifdef CONFIG_BLK_DEV_ZONED u32 max_zone_append; #endif u16 crdt[3]; u16 oncs; + u8 dmrl; u32 dmrsl; u16 oacs; u16 sqsize; @@ -347,9 +366,10 @@ 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_AUTH +#ifdef CONFIG_NVME_HOST_AUTH struct work_struct dhchap_auth_work; struct mutex dhchap_auth_mutex; struct nvme_dhchap_queue_context *dhchap_ctxs; @@ -357,6 +377,7 @@ struct nvme_ctrl { struct nvme_dhchap_key *ctrl_key; u16 transaction; #endif + key_serial_t tls_pskid; /* Power saving configuration */ u64 ps_max_latency_us; @@ -386,9 +407,15 @@ struct nvme_ctrl { enum nvme_dctype dctype; }; +static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) +{ + return READ_ONCE(ctrl->state); +} + enum nvme_iopolicy { NVME_IOPOLICY_NUMA, NVME_IOPOLICY_RR, + NVME_IOPOLICY_QD, }; struct nvme_subsystem { @@ -438,13 +465,26 @@ struct nvme_ns_head { struct list_head list; struct srcu_struct srcu; struct nvme_subsystem *subsys; - unsigned ns_id; 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; - int instance; + bool passthru_err_log_enabled; struct nvme_effects_log *effects; + u64 nuse; + unsigned ns_id; + int instance; +#ifdef CONFIG_BLK_DEV_ZONED + u64 zsze; +#endif + unsigned long features; + + struct ratelimit_state rs_nuse; struct cdev cdev; struct device cdev_device; @@ -469,7 +509,7 @@ 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 { @@ -486,17 +526,6 @@ struct nvme_ns { struct kref kref; struct nvme_ns_head *head; - int lba_shift; - u16 ms; - u16 pi_size; - u16 sgs; - u32 sws; - u8 pi_type; - u8 guard_type; -#ifdef CONFIG_BLK_DEV_ZONED - u64 zsze; -#endif - unsigned long features; unsigned long flags; #define NVME_NS_REMOVING 0 #define NVME_NS_ANA_PENDING 2 @@ -507,13 +536,12 @@ struct nvme_ns { struct device cdev_device; struct nvme_fault_inject fault_inject; - }; /* NVMe ns supports metadata actions by the controller (generate/strip) */ -static inline bool nvme_ns_has_pi(struct nvme_ns *ns) +static inline bool nvme_ns_has_pi(struct nvme_ns_head *head) { - return ns->pi_type && ns->ms == ns->pi_size; + return head->pi_type && head->ms == head->pi_size; } struct nvme_ctrl_ops { @@ -530,6 +558,7 @@ 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); @@ -628,34 +657,25 @@ 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); } /* * Convert a 512B sector number to a device logical block number. */ -static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector) +static inline u64 nvme_sect_to_lba(struct nvme_ns_head *head, sector_t sector) { - return sector >> (ns->lba_shift - SECTOR_SHIFT); + return sector >> (head->lba_shift - SECTOR_SHIFT); } /* * Convert a device logical block number to a 512B sector number. */ -static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba) +static inline sector_t nvme_lba_to_sect(struct nvme_ns_head *head, u64 lba) { - return lba << (ns->lba_shift - SECTOR_SHIFT); + return lba << (head->lba_shift - SECTOR_SHIFT); } /* @@ -668,7 +688,7 @@ 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: @@ -681,7 +701,7 @@ 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; } /* @@ -724,6 +744,28 @@ 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); @@ -749,6 +791,7 @@ 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); @@ -790,17 +833,18 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req); blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, struct request *req); bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, - bool queue_live); + bool queue_live, enum nvme_ctrl_state state); static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live) { - if (likely(ctrl->state == NVME_CTRL_LIVE)) + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); + + if (likely(state == NVME_CTRL_LIVE)) return true; - if (ctrl->ops->flags & NVME_F_FABRICS && - ctrl->state == NVME_CTRL_DELETING) + if (ctrl->ops->flags & NVME_F_FABRICS && state == NVME_CTRL_DELETING) return queue_live; - return __nvme_check_ready(ctrl, rq, queue_live); + return __nvme_check_ready(ctrl, rq, queue_live, state); } /* @@ -821,12 +865,27 @@ static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl, (ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS); } +/* + * Flags for __nvme_submit_sync_cmd() + */ +typedef __u32 __bitwise nvme_submit_flags_t; + +enum { + /* Insert request at the head of the queue */ + NVME_SUBMIT_AT_HEAD = (__force nvme_submit_flags_t)(1 << 0), + /* Set BLK_MQ_REQ_NOWAIT when allocating request */ + 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_STATUS_DNR is not set in the result */ + NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3), +}; + int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buf, unsigned bufflen); int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, union nvme_result *result, void *buffer, unsigned bufflen, - int qid, int at_head, - blk_mq_req_flags_t flags); + int qid, nvme_submit_flags_t flags); int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, u32 *result); @@ -861,10 +920,12 @@ int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); +int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, + struct nvme_id_ns **id); int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo); int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags); -extern const struct attribute_group *nvme_ns_id_attr_groups[]; +extern const struct attribute_group *nvme_ns_attr_groups[]; extern const struct pr_ops nvme_pr_ops; extern const struct block_device_operations nvme_ns_head_ops; extern const struct attribute_group nvme_dev_attrs_group; @@ -914,6 +975,10 @@ extern struct device_attribute dev_attr_ana_grpid; extern struct device_attribute dev_attr_ana_state; extern struct device_attribute subsys_attr_iopolicy; +static inline bool nvme_disk_is_ns_head(struct gendisk *disk) +{ + return disk->fops == &nvme_ns_head_ops; +} #else #define multipath false static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) @@ -991,13 +1056,28 @@ static inline void nvme_mpath_start_request(struct request *rq) static inline void nvme_mpath_end_request(struct request *rq) { } +static inline bool nvme_disk_is_ns_head(struct gendisk *disk) +{ + return false; +} #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); @@ -1008,18 +1088,14 @@ 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) { - return dev_to_disk(dev)->private_data; + struct gendisk *disk = dev_to_disk(dev); + + WARN_ON(nvme_disk_is_ns_head(disk)); + return disk->private_data; } #ifdef CONFIG_NVME_HWMON @@ -1048,7 +1124,7 @@ static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl) return ctrl->sgls & ((1 << 0) | (1 << 1)); } -#ifdef CONFIG_NVME_AUTH +#ifdef CONFIG_NVME_HOST_AUTH int __init nvme_init_auth(void); void __exit nvme_exit_auth(void); int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl); @@ -1075,7 +1151,7 @@ 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 @@ -1088,6 +1164,7 @@ 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) @@ -1096,35 +1173,42 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl) } #ifdef CONFIG_NVME_VERBOSE_ERRORS -const unsigned char *nvme_get_error_status_str(u16 status); -const unsigned char *nvme_get_opcode_str(u8 opcode); -const unsigned char *nvme_get_admin_opcode_str(u8 opcode); -const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode); +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 unsigned char *nvme_get_error_status_str(u16 status) +static inline const char *nvme_get_error_status_str(u16 status) { return "I/O Error"; } -static inline const unsigned char *nvme_get_opcode_str(u8 opcode) +static inline const char *nvme_get_opcode_str(u8 opcode) { return "I/O Cmd"; } -static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode) +static inline const char *nvme_get_admin_opcode_str(u8 opcode) { return "Admin Cmd"; } -static inline const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) +static inline const char *nvme_get_fabrics_opcode_str(u8 opcode) { return "Fabrics Cmd"; } #endif /* CONFIG_NVME_VERBOSE_ERRORS */ -static inline const unsigned char *nvme_opcode_str(int qid, u8 opcode, u8 fctype) +static inline const char *nvme_opcode_str(int qid, u8 opcode) { - if (opcode == nvme_fabrics_command) - return nvme_get_fabrics_opcode_str(fctype); 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 2f57da12d983..7990c3f22ecf 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -778,7 +778,8 @@ 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 ((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); @@ -825,9 +826,9 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req, struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + struct bio_vec bv = rq_integrity_vec(req); - 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); @@ -862,7 +863,8 @@ 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; @@ -924,7 +926,6 @@ static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req) if (unlikely(!nvme_check_ready(&nvmeq->dev->ctrl, req, true))) return false; - req->mq_hctx->tags->rqs[req->tag] = req; return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK; } @@ -967,7 +968,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *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)); + rq_integrity_vec(req).bv_len, rq_dma_dir(req)); } if (blk_rq_nr_phys_segments(req)) @@ -1143,6 +1144,41 @@ 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 = { }; @@ -1234,7 +1270,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO); /* If there is a reset/reinit ongoing, we shouldn't reset again. */ - switch (dev->ctrl.state) { + switch (nvme_ctrl_state(&dev->ctrl)) { case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: return false; @@ -1274,7 +1310,7 @@ 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) @@ -1285,6 +1321,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) struct request *abort_req; struct nvme_command cmd = { }; u32 csts = readl(dev->bar + NVME_REG_CSTS); + u8 opcode; + + 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. @@ -1311,8 +1351,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) { dev_warn(dev->ctrl.device, - "I/O %d QID %d timeout, completion polled\n", - req->tag, nvmeq->qid); + "I/O tag %d (%04x) QID %d timeout, completion polled\n", + req->tag, nvme_cid(req), nvmeq->qid); return BLK_EH_DONE; } @@ -1322,14 +1362,14 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) * cancellation error. All outstanding requests are completed on * shutdown, so we return BLK_EH_DONE. */ - switch (dev->ctrl.state) { + switch (nvme_ctrl_state(&dev->ctrl)) { case NVME_CTRL_CONNECTING: nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING); fallthrough; case NVME_CTRL_DELETING: dev_warn_ratelimited(dev->ctrl.device, - "I/O %d QID %d timeout, disable controller\n", - req->tag, nvmeq->qid); + "I/O tag %d (%04x) QID %d timeout, disable controller\n", + req->tag, nvme_cid(req), nvmeq->qid); nvme_req(req)->flags |= NVME_REQ_CANCELLED; nvme_dev_disable(dev, true); return BLK_EH_DONE; @@ -1344,10 +1384,12 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) * command was already aborted once before and still hasn't been * returned to the driver, or if this is the admin queue. */ + opcode = nvme_req(req)->cmd->common.opcode; if (!nvmeq->qid || iod->aborted) { dev_warn(dev->ctrl.device, - "I/O %d QID %d timeout, reset controller\n", - req->tag, nvmeq->qid); + "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n", + req->tag, nvme_cid(req), opcode, + nvme_opcode_str(nvmeq->qid, opcode), nvmeq->qid); nvme_req(req)->flags |= NVME_REQ_CANCELLED; goto disable; } @@ -1363,10 +1405,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) cmd.abort.sqid = cpu_to_le16(nvmeq->qid); dev_warn(nvmeq->dev->ctrl.device, - "I/O %d (%s) QID %d timeout, aborting\n", - req->tag, - nvme_get_opcode_str(nvme_req(req)->cmd->common.opcode), - nvmeq->qid); + "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, aborting req_op:%s(%u) size:%u\n", + req->tag, nvme_cid(req), opcode, nvme_get_opcode_str(opcode), + nvmeq->qid, blk_op_str(req_op(req)), req_op(req), + blk_rq_bytes(req)); abort_req = blk_mq_alloc_request(dev->ctrl.admin_q, nvme_req_op(&cmd), BLK_MQ_REQ_NOWAIT); @@ -1388,8 +1430,11 @@ 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)) @@ -1594,7 +1639,7 @@ static int nvme_setup_io_queues_trylock(struct nvme_dev *dev) /* * Controller is in wrong state, fail early. */ - if (dev->ctrl.state != NVME_CTRL_CONNECTING) { + if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_CONNECTING) { mutex_unlock(&dev->shutdown_lock); return -ENODEV; } @@ -2216,6 +2261,7 @@ 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 @@ -2239,8 +2285,10 @@ 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) @@ -2460,6 +2508,12 @@ static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev) static void 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; + } + 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); @@ -2469,6 +2523,7 @@ 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; @@ -2485,7 +2540,9 @@ 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; @@ -2506,15 +2563,8 @@ 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) { @@ -2574,13 +2624,13 @@ static bool nvme_pci_ctrl_is_dead(struct nvme_dev *dev) static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) { + enum nvme_ctrl_state state = nvme_ctrl_state(&dev->ctrl); struct pci_dev *pdev = to_pci_dev(dev->dev); bool dead; mutex_lock(&dev->shutdown_lock); dead = nvme_pci_ctrl_is_dead(dev); - if (dev->ctrl.state == NVME_CTRL_LIVE || - dev->ctrl.state == NVME_CTRL_RESETTING) { + if (state == NVME_CTRL_LIVE || state == NVME_CTRL_RESETTING) { if (pci_is_enabled(pdev)) nvme_start_freeze(&dev->ctrl); /* @@ -2691,7 +2741,7 @@ static void nvme_reset_work(struct work_struct *work) bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result; - if (dev->ctrl.state != NVME_CTRL_RESETTING) { + if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_RESETTING) { dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n", dev->ctrl.state); result = -ENODEV; @@ -2744,10 +2794,10 @@ static void nvme_reset_work(struct work_struct *work) * controller around but remove all namespaces. */ if (dev->online_queues > 1) { + nvme_dbbuf_set(dev); nvme_unquiesce_io_queues(&dev->ctrl); nvme_wait_freeze(&dev->ctrl); nvme_pci_update_nr_queues(dev); - nvme_dbbuf_set(dev); nvme_unfreeze(&dev->ctrl); } else { dev_warn(dev->ctrl.device, "IO queues lost\n"); @@ -2844,6 +2894,7 @@ 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, @@ -2903,8 +2954,38 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) && dmi_match(DMI_BOARD_NAME, "LNVNB161216")) return NVME_QUIRK_SIMPLE_SUSPEND; + } else if (pdev->vendor == 0x2646 && (pdev->device == 0x2263 || + pdev->device == 0x500f)) { + /* + * Exclude some Kingston NV1 and A2000 devices from + * NVME_QUIRK_SIMPLE_SUSPEND. Do a full suspend to save a + * lot fo energy with s2idle sleep on some TUXEDO platforms. + */ + if (dmi_match(DMI_BOARD_NAME, "NS5X_NS7XAU") || + dmi_match(DMI_BOARD_NAME, "NS5x_7xAU") || + 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, "GMxPXxx") || + 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; } @@ -2916,9 +2997,6 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, struct nvme_dev *dev; int ret = -ENOMEM; - if (node == NUMA_NO_NODE) - set_dev_node(&pdev->dev, first_memory_node); - dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node); if (!dev) return ERR_PTR(-ENOMEM); @@ -2936,7 +3014,9 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, dev->dev = get_device(&pdev->dev); quirks |= check_vendor_combination_bug(pdev); - if (!noacpi && acpi_storage_d3(&pdev->dev)) { + if (!noacpi && + !(quirks & NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND) && + acpi_storage_d3(&pdev->dev)) { /* * Some systems use a bios work around to ask for D3 on * platforms that support kernel managed suspend. @@ -2989,6 +3069,10 @@ 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; @@ -3075,6 +3159,7 @@ 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; } @@ -3196,7 +3281,7 @@ static int nvme_suspend(struct device *dev) nvme_wait_freeze(ctrl); nvme_sync_queues(ctrl); - if (ctrl->state != NVME_CTRL_LIVE) + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) goto unfreeze; /* @@ -3332,7 +3417,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0x0a54), /* Intel P4500/P4600 */ .driver_data = NVME_QUIRK_STRIPE_SIZE | NVME_QUIRK_DEALLOCATE_ZEROES | - NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + 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, }, @@ -3349,6 +3435,11 @@ 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_QDEPTH_ONE }, + { 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, }, @@ -3367,6 +3458,8 @@ 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 */ @@ -3397,6 +3490,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1c5c, 0x174a), /* SK Hynix P31 SSD */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1c5c, 0x1D59), /* SK Hynix BC901 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x15b7, 0x2001), /* Sandisk Skyhawk */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1d97, 0x2263), /* SPCC */ @@ -3476,7 +3571,12 @@ 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 | @@ -3527,5 +3627,6 @@ static void __exit nvme_exit(void) MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>"); MODULE_LICENSE("GPL"); MODULE_VERSION("1.0"); +MODULE_DESCRIPTION("NVMe host PCIe transport driver"); module_init(nvme_init); module_exit(nvme_exit); diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index 391b1465ebfd..7347ddf85f00 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -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: @@ -97,8 +97,7 @@ 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) { - if (IS_ENABLED(CONFIG_NVME_MULTIPATH) && - bdev->bd_disk->fops == &nvme_ns_head_ops) + 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, @@ -122,7 +121,7 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10, if (ret < 0) return ret; - return nvme_sc_to_pr_err(ret); + return nvme_status_to_pr_err(ret); } static int nvme_pr_register(struct block_device *bdev, u64 old, @@ -197,7 +196,7 @@ retry: if (ret < 0) return ret; - return nvme_sc_to_pr_err(ret); + return 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 337a624a537c..c8fd0e8f0237 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -638,6 +638,9 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { + if (!test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) + return; + mutex_lock(&queue->queue_lock); if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) __nvme_rdma_stop_queue(queue); @@ -979,16 +982,18 @@ 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); + /* If we are resetting/deleting then do nothing */ - if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) { - WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW || - ctrl->ctrl.state == NVME_CTRL_LIVE); + if (state != NVME_CTRL_CONNECTING) { + WARN_ON_ONCE(state == NVME_CTRL_NEW || state == NVME_CTRL_LIVE); 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, @@ -1002,6 +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) @@ -1026,11 +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) { @@ -1056,8 +1067,10 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) * unless we're during creation of a new controller to * avoid races with teardown flow. */ - WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING && - ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO); + enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); + + WARN_ON_ONCE(state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO); WARN_ON_ONCE(new); ret = -EINVAL; goto destroy_io; @@ -1077,6 +1090,7 @@ destroy_io: nvme_rdma_free_io_queues(ctrl); } 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]); @@ -1091,10 +1105,12 @@ 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", @@ -1105,9 +1121,9 @@ 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) @@ -1125,12 +1141,14 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { /* state change failure is ok if we started ctrl delete */ - WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING && - ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO); + enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); + + WARN_ON_ONCE(state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO); 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) @@ -1158,7 +1176,7 @@ static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, struct nvme_rdma_queue *queue = wc->qp->qp_context; struct nvme_rdma_ctrl *ctrl = queue->ctrl; - if (ctrl->ctrl.state == NVME_CTRL_LIVE) + if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE) dev_info(ctrl->ctrl.device, "%s for CQE 0x%p failed with status %s (%d)\n", op, wc->wr_cqe, @@ -1345,8 +1363,8 @@ 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; @@ -1401,6 +1419,8 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue, struct nvme_ns *ns = rq->q->queuedata; struct bio *bio = rq->bio; struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl; + struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); + u32 xfer_len; int nr; req->mr = ib_mr_pool_get(queue->qp, &queue->qp->sig_mrs); @@ -1413,8 +1433,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue, if (unlikely(nr)) goto mr_put; - nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c, - req->mr->sig_attrs, ns->pi_type); + nvme_rdma_set_sig_attrs(bi, c, req->mr->sig_attrs, ns->head->pi_type); nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask); ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey)); @@ -1432,7 +1451,11 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue, IB_ACCESS_REMOTE_WRITE; sg->addr = cpu_to_le64(req->mr->iova); - put_unaligned_le24(req->mr->length, sg->length); + xfer_len = req->mr->length; + /* Check if PI is added by the HW */ + if (!pi_count) + xfer_len += (xfer_len >> bi->interval_exp) * ns->head->pi_size; + put_unaligned_le24(xfer_len, sg->length); put_unaligned_le32(req->mr->rkey, sg->key); sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4; @@ -1473,7 +1496,7 @@ 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)) { @@ -1481,8 +1504,8 @@ 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, @@ -1853,6 +1876,8 @@ 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, ¶m); @@ -1937,11 +1962,15 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq) struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); struct nvme_rdma_queue *queue = req->queue; struct nvme_rdma_ctrl *ctrl = queue->ctrl; + struct nvme_command *cmd = req->req.cmd; + int qid = nvme_rdma_queue_idx(queue); - dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", - rq->tag, nvme_rdma_queue_idx(queue)); + dev_warn(ctrl->ctrl.device, + "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n", + rq->tag, nvme_cid(rq), cmd->common.opcode, + nvme_fabrics_opcode_str(qid, cmd), qid); - if (ctrl->ctrl.state != NVME_CTRL_LIVE) { + if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) { /* * If we are resetting, connecting or deleting we should * complete immediately because we may block controller @@ -2008,7 +2037,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, queue->pi_support && (c->common.opcode == nvme_cmd_write || c->common.opcode == nvme_cmd_read) && - nvme_ns_has_pi(ns)) + nvme_ns_has_pi(ns->head)) req->use_sig_mr = true; else req->use_sig_mr = false; @@ -2145,6 +2174,7 @@ 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); @@ -2155,14 +2185,15 @@ 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 = { @@ -2172,6 +2203,7 @@ 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, @@ -2208,12 +2240,11 @@ 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) @@ -2275,6 +2306,30 @@ 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); @@ -2282,8 +2337,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, if (ret) goto out_uninit_ctrl; - dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n", - nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr); + dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs, hostnqn: %s\n", + nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn); mutex_lock(&nvme_rdma_ctrl_mutex); list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list); @@ -2293,15 +2348,11 @@ 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 = { @@ -2386,4 +2437,5 @@ static void __exit nvme_rdma_cleanup_module(void) module_init(nvme_rdma_init_module); module_exit(nvme_rdma_cleanup_module); +MODULE_DESCRIPTION("NVMe host RDMA transport driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 212e1b05d298..b68a9e5f1ea3 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -35,16 +35,71 @@ static ssize_t nvme_sysfs_rescan(struct device *dev, } static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan); +static ssize_t nvme_adm_passthru_err_log_enabled_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, + ctrl->passthru_err_log_enabled ? "on\n" : "off\n"); +} + +static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + bool passthru_err_log_enabled; + int err; + + err = kstrtobool(buf, &passthru_err_log_enabled); + if (err) + return -EINVAL; + + ctrl->passthru_err_log_enabled = passthru_err_log_enabled; + + return count; +} + static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); - if (disk->fops == &nvme_bdev_ops) - return nvme_get_ns_from_dev(dev)->head; - else + if (nvme_disk_is_ns_head(disk)) return disk->private_data; + return nvme_get_ns_from_dev(dev)->head; +} + +static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ns_head *head = dev_to_ns_head(dev); + + return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n"); } +static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ns_head *head = dev_to_ns_head(dev); + bool passthru_err_log_enabled; + int err; + + err = kstrtobool(buf, &passthru_err_log_enabled); + if (err) + return -EINVAL; + head->passthru_err_log_enabled = passthru_err_log_enabled; + + return count; +} + +static struct device_attribute dev_attr_adm_passthru_err_log_enabled = \ + __ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \ + nvme_adm_passthru_err_log_enabled_show, nvme_adm_passthru_err_log_enabled_store); + +static struct device_attribute dev_attr_io_passthru_err_log_enabled = \ + __ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \ + nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store); + static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -114,20 +169,101 @@ static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(nsid); -static struct attribute *nvme_ns_id_attrs[] = { +static ssize_t csi_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ids.csi); +} +static DEVICE_ATTR_RO(csi); + +static ssize_t metadata_bytes_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ms); +} +static DEVICE_ATTR_RO(metadata_bytes); + +static int ns_head_update_nuse(struct nvme_ns_head *head) +{ + struct nvme_id_ns *id; + struct nvme_ns *ns; + int srcu_idx, ret = -EWOULDBLOCK; + + /* Avoid issuing commands too often by rate limiting the update */ + if (!__ratelimit(&head->rs_nuse)) + return 0; + + srcu_idx = srcu_read_lock(&head->srcu); + ns = nvme_find_path(head); + if (!ns) + goto out_unlock; + + ret = nvme_identify_ns(ns->ctrl, head->ns_id, &id); + if (ret) + goto out_unlock; + + head->nuse = le64_to_cpu(id->nuse); + kfree(id); + +out_unlock: + srcu_read_unlock(&head->srcu, srcu_idx); + return ret; +} + +static int ns_update_nuse(struct nvme_ns *ns) +{ + struct nvme_id_ns *id; + int ret; + + /* Avoid issuing commands too often by rate limiting the update. */ + if (!__ratelimit(&ns->head->rs_nuse)) + return 0; + + ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id); + if (ret) + return ret; + + ns->head->nuse = le64_to_cpu(id->nuse); + kfree(id); + return 0; +} + +static ssize_t nuse_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns_head *head = dev_to_ns_head(dev); + struct gendisk *disk = dev_to_disk(dev); + int ret; + + if (nvme_disk_is_ns_head(disk)) + ret = ns_head_update_nuse(head); + else + ret = ns_update_nuse(disk->private_data); + if (ret) + return ret; + + return sysfs_emit(buf, "%llu\n", head->nuse); +} +static DEVICE_ATTR_RO(nuse); + +static struct attribute *nvme_ns_attrs[] = { &dev_attr_wwid.attr, &dev_attr_uuid.attr, &dev_attr_nguid.attr, &dev_attr_eui.attr, + &dev_attr_csi.attr, &dev_attr_nsid.attr, + &dev_attr_metadata_bytes.attr, + &dev_attr_nuse.attr, #ifdef CONFIG_NVME_MULTIPATH &dev_attr_ana_grpid.attr, &dev_attr_ana_state.attr, #endif + &dev_attr_io_passthru_err_log_enabled.attr, NULL, }; -static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj, +static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, struct device, kobj); @@ -148,7 +284,8 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj, } #ifdef CONFIG_NVME_MULTIPATH if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) { - if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */ + /* per-path attr */ + if (nvme_disk_is_ns_head(dev_to_disk(dev))) return 0; if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl)) return 0; @@ -157,13 +294,13 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj, return a->mode; } -static const struct attribute_group nvme_ns_id_attr_group = { - .attrs = nvme_ns_id_attrs, - .is_visible = nvme_ns_id_attrs_are_visible, +static const struct attribute_group nvme_ns_attr_group = { + .attrs = nvme_ns_attrs, + .is_visible = nvme_ns_attrs_are_visible, }; -const struct attribute_group *nvme_ns_id_attr_groups[] = { - &nvme_ns_id_attr_group, +const struct attribute_group *nvme_ns_attr_groups[] = { + &nvme_ns_attr_group, NULL, }; @@ -226,6 +363,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev, char *buf) { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + unsigned state = (unsigned)nvme_ctrl_state(ctrl); static const char *const state_name[] = { [NVME_CTRL_NEW] = "new", [NVME_CTRL_LIVE] = "live", @@ -236,9 +374,8 @@ static ssize_t nvme_sysfs_show_state(struct device *dev, [NVME_CTRL_DEAD] = "dead", }; - if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) && - state_name[ctrl->state]) - return sysfs_emit(buf, "%s\n", state_name[ctrl->state]); + if (state < ARRAY_SIZE(state_name) && state_name[state]) + return sysfs_emit(buf, "%s\n", state_name[state]); return sysfs_emit(buf, "unknown state\n"); } @@ -409,7 +546,7 @@ static ssize_t dctype_show(struct device *dev, } static DEVICE_ATTR_RO(dctype); -#ifdef CONFIG_NVME_AUTH +#ifdef CONFIG_NVME_HOST_AUTH static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -550,10 +687,11 @@ static struct attribute *nvme_dev_attrs[] = { &dev_attr_kato.attr, &dev_attr_cntrltype.attr, &dev_attr_dctype.attr, -#ifdef CONFIG_NVME_AUTH +#ifdef CONFIG_NVME_HOST_AUTH &dev_attr_dhchap_secret.attr, &dev_attr_dhchap_ctrl_secret.attr, #endif + &dev_attr_adm_passthru_err_log_enabled.attr, NULL }; @@ -577,7 +715,7 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, return 0; if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts) return 0; -#ifdef CONFIG_NVME_AUTH +#ifdef CONFIG_NVME_HOST_AUTH if (a == &dev_attr_dhchap_secret.attr && !ctrl->opts) return 0; if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts) @@ -593,8 +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; +} + +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 5b332d9f87fc..89c44413c593 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -8,9 +8,14 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/err.h> +#include <linux/key.h> #include <linux/nvme-tcp.h> +#include <linux/nvme-keyring.h> #include <net/sock.h> #include <net/tcp.h> +#include <net/tls.h> +#include <net/tls_prot.h> +#include <net/handshake.h> #include <linux/blk-mq.h> #include <crypto/hash.h> #include <net/busy_poll.h> @@ -31,6 +36,24 @@ static int so_priority; 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; +#ifdef CONFIG_NVME_TCP_TLS +module_param(tls_handshake_timeout, int, 0644); +MODULE_PARM_DESC(tls_handshake_timeout, + "nvme TLS handshake timeout in seconds (default 10)"); +#endif + #ifdef CONFIG_DEBUG_LOCK_ALLOC /* lockdep can detect a circular dependency of the form * sk_lock -> mmap_lock (page fault) -> fs locks -> sk_lock @@ -142,11 +165,13 @@ 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; __le32 recv_ddgst; - + struct completion tls_complete; + int tls_err; struct page_frag_cache pf_cache; void (*state_change)(struct sock *); @@ -189,6 +214,28 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue) return queue - queue->ctrl->queues; } +/* + * 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; + + return ctrl->opts->tls; +} + static inline struct blk_mq_tags *nvme_tcp_tagset(struct nvme_tcp_queue *queue) { u32 queue_idx = nvme_tcp_queue_id(queue); @@ -328,12 +375,18 @@ 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) { @@ -354,7 +407,7 @@ 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); } @@ -1013,7 +1066,7 @@ 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); @@ -1320,7 +1373,6 @@ 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; @@ -1331,14 +1383,12 @@ 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_release(queue->sock); + /* ->sock will be released by fput() */ + fput(queue->sock->file); + queue->sock = NULL; memalloc_noreclaim_restore(noreclaim_flag); kfree(queue->pdu); @@ -1350,6 +1400,8 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) { struct nvme_tcp_icreq_pdu *icreq; struct nvme_tcp_icresp_pdu *icresp; + char cbuf[CMSG_LEN(sizeof(char))] = {}; + u8 ctype; struct msghdr msg = {}; struct kvec iov; bool ctrl_hdgst, ctrl_ddgst; @@ -1381,17 +1433,36 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) iov.iov_base = icreq; iov.iov_len = sizeof(*icreq); ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); - if (ret < 0) + if (ret < 0) { + pr_warn("queue %d: failed to send icreq, error %d\n", + nvme_tcp_queue_id(queue), ret); goto free_icresp; + } memset(&msg, 0, sizeof(msg)); iov.iov_base = icresp; iov.iov_len = sizeof(*icresp); + if (nvme_tcp_queue_tls(queue)) { + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + } ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, iov.iov_len, msg.msg_flags); - if (ret < 0) + 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_queue_tls(queue)) { + ctype = tls_get_record_type(queue->sock->sk, + (struct cmsghdr *)cbuf); + if (ctype != TLS_RECORD_TYPE_DATA) { + pr_err("queue %d: unhandled TLS record %d\n", + nvme_tcp_queue_id(queue), ctype); + goto free_icresp; + } + } ret = -EINVAL; if (icresp->hdr.type != nvme_tcp_icresp) { pr_err("queue %d: bad type returned %d\n", @@ -1504,14 +1575,99 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue) 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); + if (wq_unbound) + queue->io_cpu = WORK_CPU_UNBOUND; + else + queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false); +} + +static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid) +{ + struct nvme_tcp_queue *queue = data; + struct nvme_tcp_ctrl *ctrl = queue->ctrl; + int qid = nvme_tcp_queue_id(queue); + struct key *tls_key; + + dev_dbg(ctrl->ctrl.device, "queue %d: TLS handshake done, key %x, status %d\n", + qid, pskid, status); + + if (status) { + queue->tls_err = -status; + goto out_complete; + } + + 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 { + queue->tls_enabled = true; + if (qid == 0) + ctrl->ctrl.tls_pskid = key_serial(tls_key); + key_put(tls_key); + queue->tls_err = 0; + } + +out_complete: + complete(&queue->tls_complete); } -static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid) +static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl, + struct nvme_tcp_queue *queue, + key_serial_t pskid) +{ + int qid = nvme_tcp_queue_id(queue); + int ret; + struct tls_handshake_args args; + unsigned long tmo = tls_handshake_timeout * HZ; + key_serial_t keyring = nvme_keyring_id(); + + dev_dbg(nctrl->device, "queue %d: start TLS with key %x\n", + qid, pskid); + memset(&args, 0, sizeof(args)); + args.ta_sock = queue->sock; + args.ta_done = nvme_tcp_tls_done; + args.ta_data = queue; + args.ta_my_peerids[0] = pskid; + args.ta_num_peerids = 1; + if (nctrl->opts->keyring) + keyring = key_serial(nctrl->opts->keyring); + args.ta_keyring = keyring; + args.ta_timeout_ms = tls_handshake_timeout * 1000; + queue->tls_err = -EOPNOTSUPP; + init_completion(&queue->tls_complete); + ret = tls_client_hello_psk(&args, GFP_KERNEL); + if (ret) { + dev_err(nctrl->device, "queue %d: failed to start TLS: %d\n", + qid, ret); + return ret; + } + ret = wait_for_completion_interruptible_timeout(&queue->tls_complete, tmo); + if (ret <= 0) { + if (ret == 0) + ret = -ETIMEDOUT; + + dev_err(nctrl->device, + "queue %d: TLS handshake failed, error %d\n", + qid, ret); + tls_handshake_cancel(queue->sock->sk); + } else { + dev_dbg(nctrl->device, + "queue %d: TLS handshake complete, error %d\n", + qid, queue->tls_err); + ret = queue->tls_err; + } + return ret; +} + +static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, + key_serial_t pskid) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; int ret, rcv_pdu_size; + struct file *sock_file; mutex_init(&queue->queue_lock); queue->ctrl = ctrl; @@ -1534,6 +1690,11 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid) goto err_destroy_mutex; } + sock_file = sock_alloc_file(queue->sock, O_CLOEXEC, NULL); + if (IS_ERR(sock_file)) { + ret = PTR_ERR(sock_file); + goto err_destroy_mutex; + } nvme_tcp_reclassify_socket(queue->sock); /* Single syn retry */ @@ -1624,6 +1785,13 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid) goto err_rcv_pdu; } + /* If PSKs are configured try to start TLS */ + if (nvme_tcp_tls_configured(nctrl) && pskid) { + ret = nvme_tcp_start_tls(nctrl, queue, pskid); + if (ret) + goto err_init_connect; + } + ret = nvme_tcp_init_connection(queue); if (ret) goto err_init_connect; @@ -1640,7 +1808,8 @@ err_crypto: if (queue->hdr_digest || queue->data_digest) nvme_tcp_free_crypto(queue); err_sock: - sock_release(queue->sock); + /* ->sock will be released by fput() */ + fput(queue->sock->file); queue->sock = NULL; err_destroy_mutex: mutex_destroy(&queue->send_mutex); @@ -1678,6 +1847,8 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) 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); } @@ -1772,8 +1943,23 @@ out_stop_queues: static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) { int ret; + key_serial_t pskid = 0; + + if (nvme_tcp_tls_configured(ctrl)) { + if (ctrl->opts->tls_key) + pskid = key_serial(ctrl->opts->tls_key); + 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; + } + } + } - ret = nvme_tcp_alloc_queue(ctrl, 0); + ret = nvme_tcp_alloc_queue(ctrl, 0, pskid); if (ret) return ret; @@ -1792,8 +1978,14 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) { int i, ret; + 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); + ret = nvme_tcp_alloc_queue(ctrl, i, + ctrl->tls_pskid); if (ret) goto out_free_queues; } @@ -1974,6 +2166,11 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, if (remove) nvme_unquiesce_admin_queue(ctrl); nvme_tcp_destroy_admin_queue(ctrl, remove); + 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, @@ -1991,22 +2188,25 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, nvme_tcp_destroy_io_queues(ctrl, remove); } -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); + /* If we are resetting/deleting then do nothing */ - if (ctrl->state != NVME_CTRL_CONNECTING) { - WARN_ON_ONCE(ctrl->state == NVME_CTRL_NEW || - ctrl->state == NVME_CTRL_LIVE); + if (state != NVME_CTRL_CONNECTING) { + WARN_ON_ONCE(state == NVME_CTRL_NEW || state == NVME_CTRL_LIVE); 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); } } @@ -2056,8 +2256,10 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new) * unless we're during creation of a new controller to * avoid races with teardown flow. */ - WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING && - ctrl->state != NVME_CTRL_DELETING_NOIO); + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); + + WARN_ON_ONCE(state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO); WARN_ON_ONCE(new); ret = -EINVAL; goto destroy_io; @@ -2075,11 +2277,8 @@ destroy_io: nvme_tcp_destroy_io_queues(ctrl, new); } destroy_admin: - nvme_quiesce_admin_queue(ctrl); - blk_sync_queue(ctrl->admin_q); - nvme_tcp_stop_queue(ctrl, 0); - nvme_cancel_admin_tagset(ctrl); - nvme_tcp_destroy_admin_queue(ctrl, new); + nvme_stop_keep_alive(ctrl); + nvme_tcp_teardown_admin_queue(ctrl, false); return ret; } @@ -2088,23 +2287,25 @@ 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) @@ -2124,12 +2325,14 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) { /* state change failure is ok if we started ctrl delete */ - WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING && - ctrl->state != NVME_CTRL_DELETING_NOIO); + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); + + WARN_ON_ONCE(state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO); 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) @@ -2149,25 +2352,29 @@ 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); if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) { /* state change failure is ok if we started ctrl delete */ - WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING && - ctrl->state != NVME_CTRL_DELETING_NOIO); + enum nvme_ctrl_state state = nvme_ctrl_state(ctrl); + + WARN_ON_ONCE(state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO); 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) @@ -2266,15 +2473,15 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq) struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req); - u8 opc = pdu->cmd.common.opcode, fctype = pdu->cmd.fabrics.fctype; + struct nvme_command *cmd = &pdu->cmd; int qid = nvme_tcp_queue_id(req->queue); dev_warn(ctrl->device, - "queue %d: timeout cid %#x type %d opcode %#x (%s)\n", - nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type, - opc, nvme_opcode_str(qid, opc, fctype)); + "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n", + rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode, + nvme_fabrics_opcode_str(qid, cmd), qid); - if (ctrl->state != NVME_CTRL_LIVE) { + if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) { /* * If we are resetting, connecting or deleting we should * complete immediately because we may block controller @@ -2482,6 +2689,7 @@ 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, @@ -2506,7 +2714,7 @@ 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; @@ -2581,6 +2789,28 @@ 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; @@ -2591,8 +2821,8 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, if (ret) goto out_uninit_ctrl; - dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n", - nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr); + dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp, hostnqn: %s\n", + nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn); mutex_lock(&nvme_tcp_ctrl_mutex); list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list); @@ -2602,15 +2832,11 @@ 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 = { @@ -2621,12 +2847,15 @@ static struct nvmf_transport_ops nvme_tcp_transport = { NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST | NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES | - NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE, + NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE | NVMF_OPT_TLS | + NVMF_OPT_KEYRING | NVMF_OPT_TLS_KEY, .create_ctrl = nvme_tcp_create_ctrl, }; static int __init nvme_tcp_init_module(void) { + unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS; + 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); @@ -2636,8 +2865,10 @@ 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; @@ -2663,4 +2894,5 @@ static void __exit nvme_tcp_cleanup_module(void) module_init(nvme_tcp_init_module); module_exit(nvme_tcp_cleanup_module); +MODULE_DESCRIPTION("NVMe host TCP transport driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 1c36fcedea20..0288315f0050 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -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 +195,86 @@ 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) +{ + 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; + + trace_seq_printf(p, "rrega=%u, iekey=%u, ptpl=%u", + rrega, iekey, ptpl); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvme_trace_resv_acq(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 racqa = cdw10[0] & 0x7; + u8 iekey = (cdw10[0] >> 3) & 0x1; + u8 rtype = cdw10[1]; + + trace_seq_printf(p, "racqa=%u, iekey=%u, rtype=%u", + racqa, iekey, rtype); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvme_trace_resv_rel(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 rrela = cdw10[0] & 0x7; + u8 iekey = (cdw10[0] >> 3) & 0x1; + u8 rtype = cdw10[1]; + + trace_seq_printf(p, "rrela=%u, iekey=%u, rtype=%u", + rrela, iekey, rtype); + 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 +332,14 @@ 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 ec8557810c21..9a06f9d98cd6 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->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; @@ -99,24 +89,33 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) goto free_data; } - ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze)); - if (!is_power_of_2(ns->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->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_ZONED_HM); - 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_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) { @@ -128,7 +127,7 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns, sizeof(struct nvme_zone_descriptor); nr_zones = min_t(unsigned int, nr_zones, - get_capacity(ns->disk) >> ilog2(ns->zsze)); + get_capacity(ns->disk) >> ilog2(ns->head->zsze)); bufsize = sizeof(struct nvme_zone_report) + nr_zones * sizeof(struct nvme_zone_descriptor); @@ -147,7 +146,8 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns, return NULL; } -static int nvme_zone_parse_entry(struct nvme_ns *ns, +static int nvme_zone_parse_entry(struct nvme_ctrl *ctrl, + struct nvme_ns_head *head, struct nvme_zone_descriptor *entry, unsigned int idx, report_zones_cb cb, void *data) @@ -155,20 +155,20 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns, struct blk_zone zone = { }; if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) { - dev_err(ns->ctrl->device, "invalid zone type %#x\n", + dev_err(ctrl->device, "invalid zone type %#x\n", entry->zt); return -EINVAL; } zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ; zone.cond = entry->zs >> 4; - zone.len = ns->zsze; - zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap)); - zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba)); + zone.len = head->zsze; + zone.capacity = nvme_lba_to_sect(head, le64_to_cpu(entry->zcap)); + zone.start = nvme_lba_to_sect(head, le64_to_cpu(entry->zslba)); if (zone.cond == BLK_ZONE_COND_FULL) zone.wp = zone.start + zone.len; else - zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp)); + zone.wp = nvme_lba_to_sect(head, le64_to_cpu(entry->wp)); return cb(&zone, idx, data); } @@ -196,11 +196,11 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL; c.zmr.pr = NVME_REPORT_ZONE_PARTIAL; - sector &= ~(ns->zsze - 1); + sector &= ~(ns->head->zsze - 1); while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) { memset(report, 0, buflen); - c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector)); + c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, sector)); ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen); if (ret) { if (ret > 0) @@ -213,14 +213,15 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, break; for (i = 0; i < nz && zone_idx < nr_zones; i++) { - ret = nvme_zone_parse_entry(ns, &report->entries[i], + ret = nvme_zone_parse_entry(ns->ctrl, ns->head, + &report->entries[i], zone_idx, cb, data); if (ret) goto out_free; zone_idx++; } - sector += ns->zsze * nz; + sector += ns->head->zsze * nz; } if (zone_idx > 0) @@ -239,7 +240,7 @@ blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, c->zms.opcode = nvme_cmd_zone_mgmt_send; c->zms.nsid = cpu_to_le32(ns->head->ns_id); - c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); + c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req))); c->zms.zsa = action; if (req_op(req) == REQ_OP_ZONE_RESET_ALL) diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index 79fc64035ee3..46be031f91b4 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -4,7 +4,8 @@ config NVME_TARGET tristate "NVMe Target support" depends on BLOCK depends on CONFIGFS_FS - select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY + select NVME_KEYRING if NVME_TARGET_TCP_TLS + select KEYS if NVME_TARGET_TCP_TLS select SGL_ALLOC help This enabled target side support for the NVMe protocol, that is @@ -16,6 +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 @@ -84,17 +94,24 @@ config NVME_TARGET_TCP If unsure, say N. +config NVME_TARGET_TCP_TLS + bool "NVMe over Fabrics TCP target TLS encryption support" + depends on NVME_TARGET_TCP + select NET_HANDSHAKE + help + Enables TLS encryption for the NVMe TCP target using the netlink handshake API. + + The TLS handshake daemon is available at + https://github.com/oracle/ktls-utils. + + If unsure, say N. + config NVME_TARGET_AUTH - bool "NVMe over Fabrics In-band Authentication support" + bool "NVMe over Fabrics In-band Authentication in target side" depends on NVME_TARGET - select NVME_COMMON - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_SHA256 - select CRYPTO_SHA512 - select CRYPTO_DH - select CRYPTO_DH_RFC7919_GROUPS + select NVME_AUTH help - This enables support for NVMe over Fabrics In-band Authentication + This enables support for NVMe over Fabrics In-band Authentication in + target side. If unsure, say N. diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index c66820102493..c402c44350b2 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \ discovery.o io-cmd-file.o io-cmd-bdev.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 diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 39cb570f833d..954d4c074770 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -344,7 +344,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *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) @@ -428,7 +428,7 @@ 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); @@ -496,7 +496,7 @@ 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; } @@ -587,6 +587,16 @@ 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; @@ -662,7 +672,7 @@ 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); @@ -724,7 +734,7 @@ static void nvmet_execute_identify(struct nvmet_req *req) 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 +817,7 @@ 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); @@ -833,7 +843,7 @@ void nvmet_execute_set_features(struct nvmet_req *req) 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, @@ -846,14 +856,14 @@ 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 = NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR; break; case NVME_FEAT_WRITE_PROTECT: status = nvmet_set_feat_write_protect(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; } @@ -939,7 +949,7 @@ 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; } @@ -952,7 +962,7 @@ void nvmet_execute_get_features(struct nvmet_req *req) 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 +979,7 @@ 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; @@ -1005,8 +1015,6 @@ 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); diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 4dcddcf95279..7897d02c681d 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -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; } @@ -124,12 +138,11 @@ 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 +160,16 @@ 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 +180,6 @@ 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 +188,7 @@ 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 +206,7 @@ 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; } @@ -267,7 +277,8 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, struct shash_desc *shash; struct nvmet_ctrl *ctrl = req->sq->ctrl; const char *hash_name; - u8 *challenge = req->sq->dhchap_c1, *host_response; + u8 *challenge = req->sq->dhchap_c1; + struct nvme_dhchap_key *transformed_key; u8 buf[4]; int ret; @@ -284,21 +295,22 @@ 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; } - host_response = nvme_auth_transform_key(ctrl->host_key, ctrl->hostnqn); - if (IS_ERR(host_response)) { - ret = PTR_ERR(host_response); + transformed_key = nvme_auth_transform_key(ctrl->host_key, + ctrl->hostnqn); + if (IS_ERR(transformed_key)) { + ret = PTR_ERR(transformed_key); goto out_free_tfm; } - ret = crypto_shash_setkey(shash_tfm, host_response, - ctrl->host_key->len); + ret = crypto_shash_setkey(shash_tfm, transformed_key->key, + transformed_key->len); if (ret) goto out_free_response; @@ -314,7 +326,7 @@ 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", @@ -325,7 +337,7 @@ 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); @@ -361,14 +373,15 @@ 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: - kfree_sensitive(host_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, @@ -378,7 +391,8 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, struct shash_desc *shash; struct nvmet_ctrl *ctrl = req->sq->ctrl; const char *hash_name; - u8 *challenge = req->sq->dhchap_c2, *ctrl_response; + u8 *challenge = req->sq->dhchap_c2; + struct nvme_dhchap_key *transformed_key; u8 buf[4]; int ret; @@ -402,15 +416,15 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, goto out_free_tfm; } - ctrl_response = nvme_auth_transform_key(ctrl->ctrl_key, + transformed_key = nvme_auth_transform_key(ctrl->ctrl_key, ctrl->subsysnqn); - if (IS_ERR(ctrl_response)) { - ret = PTR_ERR(ctrl_response); + if (IS_ERR(transformed_key)) { + ret = PTR_ERR(transformed_key); goto out_free_tfm; } - ret = crypto_shash_setkey(shash_tfm, ctrl_response, - ctrl->ctrl_key->len); + ret = crypto_shash_setkey(shash_tfm, transformed_key->key, + transformed_key->len); if (ret) goto out_free_response; @@ -426,14 +440,14 @@ 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; @@ -470,14 +484,15 @@ 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: - kfree_sensitive(ctrl_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 907143870da5..685e89b35d33 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -15,8 +15,10 @@ #ifdef CONFIG_NVME_TARGET_AUTH #include <linux/nvme-auth.h> #endif +#include <linux/nvme-keyring.h> #include <crypto/hash.h> #include <crypto/kpp.h> +#include <linux/nospec.h> #include "nvmet.h" @@ -159,10 +161,14 @@ static const struct nvmet_type_name_map nvmet_addr_treq[] = { { NVMF_TREQ_NOT_REQUIRED, "not required" }, }; +static inline u8 nvmet_port_disc_addr_treq_mask(struct nvmet_port *port) +{ + return (port->disc_addr.treq & ~NVME_TREQ_SECURE_CHANNEL_MASK); +} + static ssize_t nvmet_addr_treq_show(struct config_item *item, char *page) { - u8 treq = to_nvmet_port(item)->disc_addr.treq & - NVME_TREQ_SECURE_CHANNEL_MASK; + u8 treq = nvmet_port_disc_addr_treq_secure_channel(to_nvmet_port(item)); int i; for (i = 0; i < ARRAY_SIZE(nvmet_addr_treq); i++) { @@ -178,7 +184,7 @@ static ssize_t nvmet_addr_treq_store(struct config_item *item, const char *page, size_t count) { struct nvmet_port *port = to_nvmet_port(item); - u8 treq = port->disc_addr.treq & ~NVME_TREQ_SECURE_CHANNEL_MASK; + u8 treq = nvmet_port_disc_addr_treq_mask(port); int i; if (nvmet_is_port_enabled(port, __func__)) @@ -193,6 +199,20 @@ static ssize_t nvmet_addr_treq_store(struct config_item *item, return -EINVAL; found: + if (port->disc_addr.trtype == NVMF_TRTYPE_TCP && + port->disc_addr.tsas.tcp.sectype == NVMF_TCP_SECTYPE_TLS13) { + switch (nvmet_addr_treq[i].type) { + case NVMF_TREQ_NOT_SPECIFIED: + pr_debug("treq '%s' not allowed for TLS1.3\n", + nvmet_addr_treq[i].name); + return -EINVAL; + case NVMF_TREQ_NOT_REQUIRED: + pr_warn("Allow non-TLS connections while TLS1.3 is enabled\n"); + break; + default: + break; + } + } treq |= nvmet_addr_treq[i].type; port->disc_addr.treq = treq; return count; @@ -253,6 +273,32 @@ 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) @@ -303,6 +349,11 @@ static void nvmet_port_init_tsas_rdma(struct nvmet_port *port) port->disc_addr.tsas.rdma.cms = NVMF_RDMA_CMS_RDMA_CM; } +static void nvmet_port_init_tsas_tcp(struct nvmet_port *port, int sectype) +{ + port->disc_addr.tsas.tcp.sectype = sectype; +} + static ssize_t nvmet_addr_trtype_store(struct config_item *item, const char *page, size_t count) { @@ -325,11 +376,120 @@ found: port->disc_addr.trtype = nvmet_transport[i].type; if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA) nvmet_port_init_tsas_rdma(port); + else if (port->disc_addr.trtype == NVMF_TRTYPE_TCP) + nvmet_port_init_tsas_tcp(port, NVMF_TCP_SECTYPE_NONE); return count; } CONFIGFS_ATTR(nvmet_, addr_trtype); +static const struct nvmet_type_name_map nvmet_addr_tsas_tcp[] = { + { NVMF_TCP_SECTYPE_NONE, "none" }, + { NVMF_TCP_SECTYPE_TLS13, "tls1.3" }, +}; + +static const struct nvmet_type_name_map nvmet_addr_tsas_rdma[] = { + { NVMF_RDMA_QPTYPE_CONNECTED, "connected" }, + { NVMF_RDMA_QPTYPE_DATAGRAM, "datagram" }, +}; + +static ssize_t nvmet_addr_tsas_show(struct config_item *item, + char *page) +{ + struct nvmet_port *port = to_nvmet_port(item); + int i; + + if (port->disc_addr.trtype == NVMF_TRTYPE_TCP) { + for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) { + if (port->disc_addr.tsas.tcp.sectype == nvmet_addr_tsas_tcp[i].type) + return sprintf(page, "%s\n", nvmet_addr_tsas_tcp[i].name); + } + } else if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA) { + for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_rdma); i++) { + if (port->disc_addr.tsas.rdma.qptype == nvmet_addr_tsas_rdma[i].type) + return sprintf(page, "%s\n", nvmet_addr_tsas_rdma[i].name); + } + } + return sprintf(page, "\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, + const char *page, size_t count) +{ + struct nvmet_port *port = to_nvmet_port(item); + u8 treq = nvmet_port_disc_addr_treq_mask(port); + u8 sectype, qptype; + + if (nvmet_is_port_enabled(port, __func__)) + return -EACCES; + + 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); + return -EINVAL; + +found: + if (sectype == NVMF_TCP_SECTYPE_TLS13) { + if (!IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS)) { + pr_err("TLS is not supported\n"); + return -EINVAL; + } + if (!port->keyring) { + pr_err("TLS keyring not configured\n"); + return -EINVAL; + } + } + + nvmet_port_init_tsas_tcp(port, sectype); + /* + * If TLS is enabled TREQ should be set to 'required' per default + */ + if (sectype == NVMF_TCP_SECTYPE_TLS13) { + u8 sc = nvmet_port_disc_addr_treq_secure_channel(port); + + if (sc == NVMF_TREQ_NOT_SPECIFIED) + treq |= NVMF_TREQ_REQUIRED; + else + treq |= sc; + } else { + treq |= NVMF_TREQ_NOT_SPECIFIED; + } + port->disc_addr.treq = treq; + return count; +} + +CONFIGFS_ATTR(nvmet_, addr_tsas); + /* * Namespace structures & file operation functions below */ @@ -509,6 +669,7 @@ static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item, down_write(&nvmet_ana_sem); oldgrpid = ns->anagrpid; + newgrpid = array_index_nospec(newgrpid, NVMET_MAX_ANAGRPS); nvmet_ana_group_enabled[newgrpid]++; ns->anagrpid = newgrpid; nvmet_ana_group_enabled[oldgrpid]--; @@ -536,10 +697,18 @@ 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; } @@ -614,6 +783,18 @@ static struct configfs_attribute *nvmet_ns_attrs[] = { NULL, }; +bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid) +{ + struct config_item *ns_item; + char name[12]; + + snprintf(name, sizeof(name), "%u", nsid); + mutex_lock(&subsys->namespaces_group.cg_subsys->su_mutex); + ns_item = config_group_find_item(&subsys->namespaces_group, name); + mutex_unlock(&subsys->namespaces_group.cg_subsys->su_mutex); + return ns_item != NULL; +} + static void nvmet_ns_release(struct config_item *item) { struct nvmet_ns *ns = to_nvmet_ns(item); @@ -1162,7 +1343,7 @@ static ssize_t nvmet_subsys_attr_cntlid_min_store(struct config_item *item, return -EINVAL; down_write(&nvmet_config_sem); - if (cntlid_min >= to_subsys(item)->cntlid_max) + if (cntlid_min > to_subsys(item)->cntlid_max) goto out_unlock; to_subsys(item)->cntlid_min = cntlid_min; up_write(&nvmet_config_sem); @@ -1192,7 +1373,7 @@ static ssize_t nvmet_subsys_attr_cntlid_max_store(struct config_item *item, return -EINVAL; down_write(&nvmet_config_sem); - if (cntlid_max <= to_subsys(item)->cntlid_min) + if (cntlid_max < to_subsys(item)->cntlid_min) goto out_unlock; to_subsys(item)->cntlid_max = cntlid_max; up_write(&nvmet_config_sem); @@ -1473,6 +1654,11 @@ 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); @@ -1700,6 +1886,7 @@ static struct config_group *nvmet_ana_groups_make_group( grp->grpid = grpid; down_write(&nvmet_ana_sem); + grpid = array_index_nospec(grpid, NVMET_MAX_ANAGRPS); nvmet_ana_group_enabled[grpid]++; up_write(&nvmet_ana_sem); @@ -1731,6 +1918,7 @@ static void nvmet_port_release(struct config_item *item) flush_workqueue(nvmet_wq); list_del(&port->global_entry); + key_put(port->keyring); kfree(port->ana_state); kfree(port); } @@ -1741,7 +1929,9 @@ static struct configfs_attribute *nvmet_port_attrs[] = { &nvmet_attr_addr_traddr, &nvmet_attr_addr_trsvcid, &nvmet_attr_addr_trtype, + &nvmet_attr_addr_tsas, &nvmet_attr_param_inline_data_size, + &nvmet_attr_param_max_queue_size, #ifdef CONFIG_BLK_DEV_INTEGRITY &nvmet_attr_param_pi_enable, #endif @@ -1779,6 +1969,14 @@ static struct config_group *nvmet_ports_make(struct config_group *group, return ERR_PTR(-ENOMEM); } + if (IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS) && nvme_keyring_id()) { + port->keyring = key_lookup(nvme_keyring_id()); + if (IS_ERR(port->keyring)) { + pr_warn("NVMe keyring not available, disabling TLS\n"); + port->keyring = NULL; + } + } + for (i = 1; i <= NVMET_MAX_ANAGRPS; i++) { if (i == NVMET_DEFAULT_ANA_GRPID) port->ana_state[1] = NVME_ANA_OPTIMIZED; @@ -1792,6 +1990,7 @@ 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.portid = cpu_to_le16(portid); port->disc_addr.adrfam = NVMF_ADDR_FAMILY_MAX; @@ -1837,11 +2036,17 @@ 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, @@ -1865,10 +2070,16 @@ 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, @@ -2006,7 +2217,49 @@ 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; + size_t len; + + len = strcspn(page, "\n"); + if (!len || len > NVMF_NQN_FIELD_LEN - 1) + return -EINVAL; + + 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); + return -EINVAL; + } + } + memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN); + memcpy(nvmet_disc_subsys->subsysnqn, page, len); + up_write(&nvmet_config_sem); + + 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 3935165048e7..ed2424f8a396 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; } @@ -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); @@ -248,7 +249,7 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid) nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid)); if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR)) continue; - nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, + nvmet_add_async_event(ctrl, NVME_AER_NOTICE, NVME_AER_NOTICE_NS_CHANGED, NVME_LOG_CHANGED_NS); } @@ -265,7 +266,7 @@ void nvmet_send_ana_event(struct nvmet_subsys *subsys, continue; if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_ANA_CHANGE)) continue; - nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, + nvmet_add_async_event(ctrl, NVME_AER_NOTICE, NVME_AER_NOTICE_ANA, NVME_LOG_ANA); } mutex_unlock(&subsys->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 +438,14 @@ 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); + req->ns = xa_load(&subsys->namespaces, nsid); if (unlikely(!req->ns)) { req->error_loc = offsetof(struct nvme_common_command, nsid); - return NVME_SC_INVALID_NS | NVME_SC_DNR; + if (nvmet_subsys_nsid_exists(subsys, nsid)) + return NVME_SC_INTERNAL_PATH_ERROR; + return NVME_SC_INVALID_NS | NVME_STATUS_DNR; } percpu_ref_get(&req->ns->ref); @@ -803,6 +819,15 @@ 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 @@ -880,7 +905,7 @@ 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)) @@ -933,6 +958,7 @@ 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; @@ -942,7 +968,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, /* 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; } @@ -953,7 +979,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, */ 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; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; goto fail; } @@ -971,7 +997,7 @@ 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; } @@ -998,7 +1024,7 @@ bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len) { if (unlikely(len != req->transfer_len)) { req->error_loc = offsetof(struct nvme_common_command, dptr); - nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR); return false; } @@ -1010,7 +1036,7 @@ bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len) { if (unlikely(data_len > req->transfer_len)) { req->error_loc = offsetof(struct nvme_common_command, dptr); - nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR); + nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR); return false; } @@ -1223,9 +1249,10 @@ 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 +1305,18 @@ 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; } @@ -1363,7 +1390,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, int ret; u16 status; - status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; subsys = nvmet_find_get_subsys(req->port, subsysnqn); if (!subsys) { pr_warn("connect request for invalid subsystem %s!\n", @@ -1379,7 +1406,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, hostnqn, subsysnqn); req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn); up_read(&nvmet_config_sem); - status = NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR; + status = NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR; req->error_loc = offsetof(struct nvme_common_command, dptr); goto out_put_subsystem; } @@ -1411,6 +1438,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, 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); @@ -1425,14 +1453,11 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, if (!ctrl->sqs) goto out_free_changed_ns_list; - if (subsys->cntlid_min > subsys->cntlid_max) - goto out_free_sqs; - ret = ida_alloc_range(&cntlid_ida, subsys->cntlid_min, subsys->cntlid_max, GFP_KERNEL); if (ret < 0) { - status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; + status = NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR; goto out_free_sqs; } ctrl->cntlid = ret; @@ -1455,6 +1480,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, mutex_lock(&subsys->lock); list_add_tail(&ctrl->subsys_entry, &subsys->ctrls); nvmet_setup_p2p_ns_map(ctrl, req); + nvmet_debugfs_ctrl_setup(ctrl); mutex_unlock(&subsys->lock); *ctrlp = ctrl; @@ -1489,6 +1515,8 @@ 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); @@ -1515,6 +1543,14 @@ 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) { @@ -1530,6 +1566,13 @@ 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)) { @@ -1602,8 +1645,14 @@ 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: @@ -1620,6 +1669,8 @@ 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); @@ -1665,7 +1716,8 @@ 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, 0); if (!nvmet_wq) goto out_free_buffered_work_queue; @@ -1673,11 +1725,18 @@ 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: @@ -1694,6 +1753,7 @@ 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); @@ -1708,4 +1768,5 @@ static void __exit nvmet_exit(void) module_init(nvmet_init); module_exit(nvmet_exit); +MODULE_DESCRIPTION("NVMe target core framework"); MODULE_LICENSE("GPL v2"); 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 668d257fa986..28843df5fa7c 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -21,7 +21,7 @@ static void __nvmet_disc_changed(struct nvmet_port *port, if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_DISC_CHANGE)) return; - nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, + nvmet_add_async_event(ctrl, NVME_AER_NOTICE, NVME_AER_NOTICE_DISC_CHANGED, NVME_LOG_DISC); } @@ -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; } @@ -256,7 +256,7 @@ 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 +282,7 @@ 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 +320,7 @@ 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; } @@ -345,7 +345,7 @@ 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; } @@ -361,7 +361,7 @@ 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 +386,7 @@ 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 586458f765f1..3f2857c17d95 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; @@ -163,16 +163,16 @@ static u16 nvmet_auth_reply(struct nvmet_req *req, void *d) pr_debug("%s: ctrl %d qid %d challenge %*ph\n", __func__, ctrl->cntlid, req->sq->qid, data->hl, req->sq->dhchap_c2); - req->sq->dhchap_s2 = le32_to_cpu(data->seqnum); } else { req->sq->authenticated = true; req->sq->dhchap_c2 = NULL; } + req->sq->dhchap_s2 = le32_to_cpu(data->seqnum); return 0; } -static u16 nvmet_auth_failure2(void *d) +static u8 nvmet_auth_failure2(void *d) { struct nvmf_auth_dhchap_failure_data *data = d; @@ -186,28 +186,29 @@ 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); 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 +238,32 @@ 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 +287,14 @@ 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 +303,12 @@ 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: @@ -332,20 +333,21 @@ 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; - nvmet_req_complete(req, status); 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; mod_delayed_work(system_wq, &req->sq->auth_expired_work, auth_expire_secs * HZ); - return; + goto complete; } /* Final states, clear up variables */ nvmet_auth_sq_free(req->sq); if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) nvmet_ctrl_fatal_error(ctrl); + +complete: + nvmet_req_complete(req, status); } static int nvmet_auth_challenge(struct nvmet_req *req, void *d, int al) @@ -435,26 +437,26 @@ 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); 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; @@ -513,12 +515,11 @@ 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; - nvmet_req_complete(req, status); 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) { nvmet_auth_sq_free(req->sq); nvmet_ctrl_fatal_error(ctrl); } + nvmet_req_complete(req, status); } diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 43b5bd8bb6a5..c4b2eddd5666 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 { @@ -65,7 +65,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) val = ctrl->csts; break; default: - status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; break; } } @@ -105,7 +105,7 @@ 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; @@ -128,7 +128,7 @@ 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 +147,30 @@ 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 */ @@ -209,8 +210,8 @@ 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 = 0; - int ret; + u16 status; + u8 dhchap_status; if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data))) return; @@ -225,40 +226,38 @@ static void nvmet_execute_admin_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)); req->error_loc = offsetof(struct nvmf_connect_command, recfmt); - status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR; + 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; + status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR; req->cqe->result.u32 = 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; - uuid_copy(&ctrl->hostid, &d->hostid); - ret = nvmet_setup_auth(ctrl); - if (ret < 0) { - pr_err("Failed to setup authentication, error %d\n", ret); + 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 (ret == -EPERM) - status = (NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR); + if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED) + status = (NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR); else status = NVME_SC_INTERNAL; goto out; @@ -288,7 +287,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) struct nvmf_connect_data *d; struct nvmet_ctrl *ctrl; u16 qid = le16_to_cpu(c->qid); - u16 status = 0; + u16 status; if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data))) return; @@ -303,26 +302,25 @@ 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; } + d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; + d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; 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; } @@ -352,13 +350,13 @@ 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 1ab6601fdd5c..3ef4beacde32 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -111,6 +111,8 @@ struct nvmet_fc_tgtport { struct nvmet_fc_port_entry *pe; struct kref ref; u32 max_sg_cnt; + + struct work_struct put_work; }; struct nvmet_fc_port_entry { @@ -145,8 +147,8 @@ struct nvmet_fc_tgt_queue { struct list_head avail_defer_list; struct workqueue_struct *work_q; struct kref ref; - struct rcu_head rcu; - struct nvmet_fc_fcp_iod fod[]; /* array of fcp_iods */ + /* array of fcp_iods */ + struct nvmet_fc_fcp_iod fod[] /* __counted_by(sqsize) */; } __aligned(sizeof(unsigned long long)); struct nvmet_fc_hostport { @@ -165,10 +167,9 @@ struct nvmet_fc_tgt_assoc { struct nvmet_fc_hostport *hostport; struct nvmet_fc_ls_iod *rcv_disconn; struct list_head a_list; - struct nvmet_fc_tgt_queue __rcu *queues[NVMET_NR_QUEUES + 1]; + struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; struct kref ref; struct work_struct del_work; - struct rcu_head rcu; }; @@ -248,6 +249,13 @@ static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc); static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue); static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue); static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport); +static void nvmet_fc_put_tgtport_work(struct work_struct *work) +{ + struct nvmet_fc_tgtport *tgtport = + container_of(work, struct nvmet_fc_tgtport, put_work); + + nvmet_fc_tgtport_put(tgtport); +} static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport); static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod); @@ -359,7 +367,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) if (!lsop->req_queued) { spin_unlock_irqrestore(&tgtport->lock, flags); - return; + goto out_putwork; } list_del(&lsop->lsreq_list); @@ -372,7 +380,8 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) (lsreq->rqstlen + lsreq->rsplen), DMA_BIDIRECTIONAL); - nvmet_fc_tgtport_put(tgtport); +out_putwork: + queue_work(nvmet_wq, &tgtport->put_work); } static int @@ -488,8 +497,7 @@ nvmet_fc_xmt_disconnect_assoc(struct nvmet_fc_tgt_assoc *assoc) * message is normal. Otherwise, send unless the hostport has * already been invalidated by the lldd. */ - if (!tgtport->ops->ls_req || !assoc->hostport || - assoc->hostport->invalid) + if (!tgtport->ops->ls_req || assoc->hostport->invalid) return; lsop = kzalloc((sizeof(*lsop) + @@ -801,14 +809,11 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, if (!queue) return NULL; - if (!nvmet_fc_tgt_a_get(assoc)) - goto out_free_queue; - queue->work_q = alloc_workqueue("ntfc%d.%d.%d", 0, 0, assoc->tgtport->fc_target_port.port_num, assoc->a_id, qid); if (!queue->work_q) - goto out_a_put; + goto out_free_queue; queue->qid = qid; queue->sqsize = sqsize; @@ -830,15 +835,13 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, goto out_fail_iodlist; WARN_ON(assoc->queues[qid]); - rcu_assign_pointer(assoc->queues[qid], queue); + assoc->queues[qid] = queue; return queue; out_fail_iodlist: nvmet_fc_destroy_fcp_iodlist(assoc->tgtport, queue); destroy_workqueue(queue->work_q); -out_a_put: - nvmet_fc_tgt_a_put(assoc); out_free_queue: kfree(queue); return NULL; @@ -851,15 +854,11 @@ nvmet_fc_tgt_queue_free(struct kref *ref) struct nvmet_fc_tgt_queue *queue = container_of(ref, struct nvmet_fc_tgt_queue, ref); - rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL); - nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue); - nvmet_fc_tgt_a_put(queue->assoc); - destroy_workqueue(queue->work_q); - kfree_rcu(queue, rcu); + kfree(queue); } static void @@ -968,7 +967,7 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, rcu_read_lock(); list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { - queue = rcu_dereference(assoc->queues[qid]); + queue = assoc->queues[qid]; if (queue && (!atomic_read(&queue->connected) || !nvmet_fc_tgt_q_get(queue))) @@ -1030,7 +1029,7 @@ nvmet_fc_match_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) list_for_each_entry(host, &tgtport->host_list, host_list) { if (host->hosthandle == hosthandle && !host->invalid) { if (nvmet_fc_hostport_get(host)) - return (host); + return host; } } @@ -1077,8 +1076,6 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) /* new allocation not needed */ kfree(newhost); newhost = match; - /* no new allocation - release reference */ - nvmet_fc_tgtport_put(tgtport); } else { newhost->tgtport = tgtport; newhost->hosthandle = hosthandle; @@ -1093,23 +1090,59 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle) } static void -nvmet_fc_delete_assoc(struct work_struct *work) +nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc) +{ + nvmet_fc_delete_target_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); +} + +static void +nvmet_fc_delete_assoc_work(struct work_struct *work) { struct nvmet_fc_tgt_assoc *assoc = container_of(work, struct nvmet_fc_tgt_assoc, del_work); + struct nvmet_fc_tgtport *tgtport = assoc->tgtport; - nvmet_fc_delete_target_assoc(assoc); - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_delete_assoc(assoc); + nvmet_fc_tgtport_put(tgtport); +} + +static void +nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc) +{ + nvmet_fc_tgtport_get(assoc->tgtport); + queue_work(nvmet_wq, &assoc->del_work); +} + +static bool +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) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; } static struct nvmet_fc_tgt_assoc * nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) { - struct nvmet_fc_tgt_assoc *assoc, *tmpassoc; + struct nvmet_fc_tgt_assoc *assoc; unsigned long flags; + bool done; u64 ran; int idx; - bool needrandom = true; + + if (!tgtport->pe) + return NULL; assoc = kzalloc(sizeof(*assoc), GFP_KERNEL); if (!assoc) @@ -1119,43 +1152,33 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) if (idx < 0) goto out_free_assoc; - if (!nvmet_fc_tgtport_get(tgtport)) - goto out_ida; - assoc->hostport = nvmet_fc_alloc_hostport(tgtport, hosthandle); if (IS_ERR(assoc->hostport)) - goto out_put; + goto out_ida; assoc->tgtport = tgtport; assoc->a_id = idx; INIT_LIST_HEAD(&assoc->a_list); kref_init(&assoc->ref); - INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc); + INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work); atomic_set(&assoc->terminating, 0); - while (needrandom) { + done = false; + do { get_random_bytes(&ran, sizeof(ran) - BYTES_FOR_QID); ran = ran << BYTES_FOR_QID_SHIFT; spin_lock_irqsave(&tgtport->lock, flags); - needrandom = false; - list_for_each_entry(tmpassoc, &tgtport->assoc_list, a_list) { - if (ran == tmpassoc->association_id) { - needrandom = true; - break; - } - } - if (!needrandom) { + if (!nvmet_fc_assoc_exists(tgtport, ran)) { assoc->association_id = ran; list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list); + done = true; } spin_unlock_irqrestore(&tgtport->lock, flags); - } + } while (!done); return assoc; -out_put: - nvmet_fc_tgtport_put(tgtport); out_ida: ida_free(&tgtport->assoc_cnt, idx); out_free_assoc: @@ -1171,13 +1194,18 @@ nvmet_fc_target_assoc_free(struct kref *ref) struct nvmet_fc_tgtport *tgtport = assoc->tgtport; struct nvmet_fc_ls_iod *oldls; unsigned long flags; + int i; + + for (i = NVMET_NR_QUEUES; i >= 0; i--) { + if (assoc->queues[i]) + nvmet_fc_delete_target_queue(assoc->queues[i]); + } /* Send Disconnect now that all i/o has completed */ nvmet_fc_xmt_disconnect_assoc(assoc); nvmet_fc_free_hostport(assoc->hostport); spin_lock_irqsave(&tgtport->lock, flags); - list_del_rcu(&assoc->a_list); oldls = assoc->rcv_disconn; spin_unlock_irqrestore(&tgtport->lock, flags); /* if pending Rcv Disconnect Association LS, send rsp now */ @@ -1187,8 +1215,7 @@ nvmet_fc_target_assoc_free(struct kref *ref) dev_info(tgtport->dev, "{%d:%d} Association freed\n", tgtport->fc_target_port.port_num, assoc->a_id); - kfree_rcu(assoc, rcu); - nvmet_fc_tgtport_put(tgtport); + kfree(assoc); } static void @@ -1207,7 +1234,7 @@ static void nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) { struct nvmet_fc_tgtport *tgtport = assoc->tgtport; - struct nvmet_fc_tgt_queue *queue; + unsigned long flags; int i, terminating; terminating = atomic_xchg(&assoc->terminating, 1); @@ -1216,29 +1243,21 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) if (terminating) return; + spin_lock_irqsave(&tgtport->lock, flags); + list_del_rcu(&assoc->a_list); + spin_unlock_irqrestore(&tgtport->lock, flags); - for (i = NVMET_NR_QUEUES; i >= 0; i--) { - rcu_read_lock(); - queue = rcu_dereference(assoc->queues[i]); - if (!queue) { - rcu_read_unlock(); - continue; - } + synchronize_rcu(); - if (!nvmet_fc_tgt_q_get(queue)) { - rcu_read_unlock(); - continue; - } - rcu_read_unlock(); - nvmet_fc_delete_target_queue(queue); - nvmet_fc_tgt_q_put(queue); + /* ensure all in-flight I/Os have been processed */ + for (i = NVMET_NR_QUEUES; i >= 0; i--) { + if (assoc->queues[i]) + flush_workqueue(assoc->queues[i]->work_q); } dev_info(tgtport->dev, "{%d:%d} Association deleted\n", tgtport->fc_target_port.port_num, assoc->a_id); - - nvmet_fc_tgt_a_put(assoc); } static struct nvmet_fc_tgt_assoc * @@ -1414,6 +1433,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); newrec->max_sg_cnt = template->max_sgl_segments; + INIT_WORK(&newrec->put_work, nvmet_fc_put_tgtport_work); ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1491,9 +1511,8 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport) list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (!nvmet_fc_tgt_a_get(assoc)) continue; - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); } rcu_read_unlock(); } @@ -1539,16 +1558,14 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port, spin_lock_irqsave(&tgtport->lock, flags); list_for_each_entry_safe(assoc, next, &tgtport->assoc_list, a_list) { - if (!assoc->hostport || - assoc->hostport->hosthandle != hosthandle) + if (assoc->hostport->hosthandle != hosthandle) continue; if (!nvmet_fc_tgt_a_get(assoc)) continue; assoc->hostport->invalid = 1; noassoc = false; - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); } spin_unlock_irqrestore(&tgtport->lock, flags); @@ -1580,7 +1597,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) rcu_read_lock(); list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { - queue = rcu_dereference(assoc->queues[0]); + queue = assoc->queues[0]; if (queue && queue->nvme_sq.ctrl == ctrl) { if (nvmet_fc_tgt_a_get(assoc)) found_ctrl = true; @@ -1592,9 +1609,8 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) nvmet_fc_tgtport_put(tgtport); if (found_ctrl) { - if (!queue_work(nvmet_wq, &assoc->del_work)) - /* already deleting - release local reference */ - nvmet_fc_tgt_a_put(assoc); + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); return; } @@ -1624,6 +1640,8 @@ nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port) /* terminate any outstanding associations */ __nvmet_fc_free_assocs(tgtport); + flush_workqueue(nvmet_wq); + /* * should terminate LS's as well. However, LS's will be generated * at the tail end of association termination, so they likely don't @@ -1869,9 +1887,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, sizeof(struct fcnvme_ls_disconnect_assoc_acc)), FCNVME_LS_DISCONNECT_ASSOC); - /* release get taken in nvmet_fc_find_target_assoc */ - nvmet_fc_tgt_a_put(assoc); - /* * The rules for LS response says the response cannot * go back until ABTS's have been sent for all outstanding @@ -1886,8 +1901,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, assoc->rcv_disconn = iod; spin_unlock_irqrestore(&tgtport->lock, flags); - nvmet_fc_delete_target_assoc(assoc); - if (oldls) { dev_info(tgtport->dev, "{%d:%d} Multiple Disconnect Association LS's " @@ -1903,6 +1916,9 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport, nvmet_fc_xmt_ls_rsp(tgtport, oldls); } + nvmet_fc_schedule_delete_assoc(assoc); + nvmet_fc_tgt_a_put(assoc); + return false; } @@ -2539,8 +2555,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, fod->req.cmd = &fod->cmdiubuf.sqe; fod->req.cqe = &fod->rspiubuf.cqe; - if (tgtport->pe) - fod->req.port = tgtport->pe->port; + if (!tgtport->pe) + goto transport_error; + fod->req.port = tgtport->pe->port; /* clear any response payload */ memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf)); @@ -2901,6 +2918,9 @@ nvmet_fc_remove_port(struct nvmet_port *port) nvmet_fc_portentry_unbind(pe); + /* terminate any outstanding associations */ + __nvmet_fc_free_assocs(pe->tgtport); + kfree(pe); } @@ -2914,6 +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, @@ -2923,6 +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) @@ -2932,6 +2985,9 @@ static int __init nvmet_fc_init_module(void) static void __exit nvmet_fc_exit_module(void) { + /* ensure any shutdown operation, e.g. delete ctrls have finished */ + flush_workqueue(nvmet_wq); + /* sanity check - all lports should be removed */ if (!list_empty(&nvmet_fc_target_list)) pr_warn("%s: targetport list not empty\n", __func__); @@ -2944,4 +3000,5 @@ static void __exit nvmet_fc_exit_module(void) module_init(nvmet_fc_init_module); module_exit(nvmet_fc_exit_module); +MODULE_DESCRIPTION("NVMe target FC transport driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index c65a73433c05..e1abb27927ff 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport, if (!rport->targetport) { tls_req->status = -ECONNREFUSED; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); queue_work(nvmet_wq, &rport->ls_work); return ret; @@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport, if (remoteport) { rport = remoteport->private; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); queue_work(nvmet_wq, &rport->ls_work); } @@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle, if (!tport->remoteport) { tls_req->status = -ECONNREFUSED; spin_lock(&tport->lock); - list_add_tail(&tport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &tport->ls_list); spin_unlock(&tport->lock); queue_work(nvmet_wq, &tport->ls_work); return ret; @@ -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. @@ -995,11 +1005,6 @@ fcloop_nport_free(struct kref *ref) { struct fcloop_nport *nport = container_of(ref, struct fcloop_nport, ref); - unsigned long flags; - - spin_lock_irqsave(&fcloop_lock, flags); - list_del(&nport->nport_list); - spin_unlock_irqrestore(&fcloop_lock, flags); kfree(nport); } @@ -1079,6 +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, @@ -1357,6 +1363,8 @@ __unlink_remote_port(struct fcloop_nport *nport) nport->tport->remoteport = NULL; nport->rport = NULL; + list_del(&nport->nport_list); + return rport; } @@ -1559,7 +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; @@ -1567,15 +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"); @@ -1588,7 +1597,7 @@ static int __init fcloop_init(void) return 0; out_destroy_class: - class_destroy(fcloop_class); + class_unregister(&fcloop_class); return ret; } @@ -1646,11 +1655,12 @@ 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); module_exit(fcloop_exit); +MODULE_DESCRIPTION("NVMe target FC loop transport driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 2733e0158585..0bda83d0fc3e 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -50,9 +50,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) void nvmet_bdev_ns_disable(struct nvmet_ns *ns) { - if (ns->bdev) { - blkdev_put(ns->bdev, NULL); + if (ns->bdev_file) { + fput(ns->bdev_file); ns->bdev = NULL; + ns->bdev_file = NULL; } } @@ -60,15 +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; } } @@ -84,23 +87,24 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) if (ns->buffered_io) return -ENOTBLK; - ns->bdev = blkdev_get_by_path(ns->device_path, - BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL); - if (IS_ERR(ns->bdev)) { - ret = PTR_ERR(ns->bdev); + ns->bdev_file = bdev_file_open_by_path(ns->device_path, + BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL); + if (IS_ERR(ns->bdev_file)) { + ret = PTR_ERR(ns->bdev_file); if (ret != -ENOTBLK) { - pr_err("failed to open block device %s: (%ld)\n", - ns->device_path, PTR_ERR(ns->bdev)); + pr_err("failed to open block device %s: (%d)\n", + ns->device_path, ret); } - ns->bdev = NULL; + ns->bdev_file = NULL; return ret; } + 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)) { @@ -133,11 +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: @@ -145,10 +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: @@ -157,7 +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); } @@ -206,12 +210,11 @@ static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio, return PTR_ERR(bip); } - bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio)); /* virtual start sector must be in integrity interval units */ bip_set_seed(bip, bio->bi_iter.bi_sector >> (bi->interval_exp - SECTOR_SHIFT)); - resid = bip->bip_iter.bi_size; + resid = bio_integrity_bytes(bi, bio_sectors(bio)); while (resid > 0 && sg_miter_next(miter)) { len = min_t(size_t, miter->length, resid); rc = bio_integrity_add_page(bio, miter->page, len, @@ -355,7 +358,7 @@ 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 48d5df054cd0..e32790d8fc26 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -400,7 +400,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl) } nvme_quiesce_admin_queue(&ctrl->ctrl); - if (ctrl->ctrl.state == NVME_CTRL_LIVE) + if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE) nvme_disable_ctrl(&ctrl->ctrl, true); nvme_cancel_admin_tagset(&ctrl->ctrl); @@ -434,8 +434,10 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work) nvme_loop_shutdown_ctrl(ctrl); if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { - if (ctrl->ctrl.state != NVME_CTRL_DELETING && - ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO) + enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); + + if (state != NVME_CTRL_DELETING && + state != NVME_CTRL_DELETING_NOIO) /* state change failure for non-deleted ctrl? */ WARN_ON_ONCE(1); return; @@ -466,6 +468,8 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work) out_destroy_io: nvme_loop_destroy_io_queues(ctrl); out_destroy_admin: + nvme_quiesce_admin_queue(&ctrl->ctrl); + nvme_cancel_admin_tagset(&ctrl->ctrl); nvme_loop_destroy_admin_queue(ctrl); out_disable: dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); @@ -551,6 +555,10 @@ 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); @@ -600,11 +608,14 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, return &ctrl->ctrl; out_remove_admin_queue: + nvme_quiesce_admin_queue(&ctrl->ctrl); + nvme_cancel_admin_tagset(&ctrl->ctrl); nvme_loop_destroy_admin_queue(ctrl); out_free_queues: kfree(ctrl->queues); out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); +out_put_ctrl: nvme_put_ctrl(&ctrl->ctrl); out: if (ret > 0) @@ -684,5 +695,6 @@ static void __exit nvme_loop_cleanup_module(void) module_init(nvme_loop_init_module); module_exit(nvme_loop_cleanup_module); +MODULE_DESCRIPTION("NVMe target loop transport driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */ diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 8cfd60f3b564..190f55e6d753 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -58,6 +58,7 @@ struct nvmet_ns { struct percpu_ref ref; + struct file *bdev_file; struct block_device *bdev; struct file *file; bool readonly; @@ -112,8 +113,8 @@ 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; @@ -158,9 +159,11 @@ struct nvmet_port { struct config_group ana_groups_group; struct nvmet_ana_group ana_default_group; enum nvme_ana_state *ana_state; + struct key *keyring; void *priv; bool enabled; int inline_data_size; + int max_queue_size; const struct nvmet_fabrics_ops *tr_ops; bool pi_enable; }; @@ -178,6 +181,16 @@ static inline struct nvmet_port *ana_groups_to_port( ana_groups_group); } +static inline u8 nvmet_port_disc_addr_treq_secure_channel(struct nvmet_port *port) +{ + return (port->disc_addr.treq & NVME_TREQ_SECURE_CHANNEL_MASK); +} + +static inline bool nvmet_port_secure_channel_required(struct nvmet_port *port) +{ + return nvmet_port_disc_addr_treq_secure_channel(port) == NVMF_TREQ_REQUIRED; +} + struct nvmet_ctrl { struct nvmet_subsys *subsys; struct nvmet_sq **sqs; @@ -217,7 +230,9 @@ 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]; @@ -249,7 +264,9 @@ 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; @@ -337,6 +354,8 @@ 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); @@ -485,6 +504,8 @@ struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn, 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); @@ -530,10 +551,12 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys, struct nvmet_host *host); void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, u8 event_info, u8 log_page); +bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid); -#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. @@ -699,7 +722,7 @@ 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); @@ -718,7 +741,7 @@ 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; } diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 9fe07d7efa96..24d0e2418d2e 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -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) @@ -306,7 +306,7 @@ 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 +426,7 @@ 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 +478,7 @@ 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; } } @@ -546,7 +546,7 @@ 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; case NVME_ID_CNS_NS: req->execute = nvmet_passthru_execute_cmd; req->p.use_workqueue = true; @@ -558,7 +558,7 @@ 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); } @@ -602,7 +602,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys) goto out_put_file; } - old = xa_cmpxchg(&passthru_subsystems, ctrl->cntlid, NULL, + old = xa_cmpxchg(&passthru_subsystems, ctrl->instance, NULL, subsys, GFP_KERNEL); if (xa_is_err(old)) { ret = xa_err(old); @@ -635,7 +635,7 @@ out_unlock: static void __nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys) { if (subsys->passthru_ctrl) { - xa_erase(&passthru_subsystems, subsys->passthru_ctrl->cntlid); + xa_erase(&passthru_subsystems, subsys->passthru_ctrl->instance); module_put(subsys->passthru_ctrl->ops->module); nvme_put_ctrl(subsys->passthru_ctrl); } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 4597bca43a6d..1b6264fa5803 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -37,6 +37,8 @@ #define NVMET_RDMA_MAX_MDTS 8 #define NVMET_RDMA_MAX_METADATA_MDTS 5 +#define NVMET_RDMA_BACKLOG 128 + struct nvmet_rdma_srq; struct nvmet_rdma_cmd { @@ -51,7 +53,6 @@ struct nvmet_rdma_cmd { enum { NVMET_RDMA_REQ_INLINE_DATA = (1 << 0), - NVMET_RDMA_REQ_INVALIDATE_RKEY = (1 << 1), }; struct nvmet_rdma_rsp { @@ -473,12 +474,8 @@ nvmet_rdma_alloc_rsps(struct nvmet_rdma_queue *queue) 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: return ret; @@ -489,12 +486,8 @@ 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); } @@ -585,8 +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; @@ -720,7 +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 { @@ -859,12 +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? */ @@ -903,10 +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; @@ -928,7 +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) { @@ -940,12 +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; } } @@ -1045,6 +1036,7 @@ 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; @@ -1583,8 +1575,19 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, } if (queue->host_qid == 0) { - /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_wq); + struct nvmet_rdma_queue *q; + int pending = 0; + + /* Check for pending controller teardown */ + mutex_lock(&nvmet_rdma_queue_mutex); + list_for_each_entry(q, &nvmet_rdma_queue_list, queue_list) { + if (q->nvme_sq.ctrl == queue->nvme_sq.ctrl && + q->state == NVMET_RDMA_Q_DISCONNECTING) + pending++; + } + mutex_unlock(&nvmet_rdma_queue_mutex); + if (pending > NVMET_RDMA_BACKLOG) + return NVME_SC_CONNECT_CTRL_BUSY; } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); @@ -1803,18 +1806,14 @@ 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); } @@ -1880,7 +1879,7 @@ static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port) goto out_destroy_id; } - ret = rdma_listen(cm_id, 128); + ret = rdma_listen(cm_id, NVMET_RDMA_BACKLOG); if (ret) { pr_err("listening to %pISpcs failed (%d)\n", addr, ret); goto out_destroy_id; @@ -1943,6 +1942,14 @@ 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) { @@ -1993,6 +2000,17 @@ 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) @@ -2002,6 +2020,8 @@ 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; } @@ -2015,6 +2035,7 @@ 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, }; @@ -2091,5 +2112,6 @@ static void __exit nvmet_rdma_exit(void) module_init(nvmet_rdma_init); module_exit(nvmet_rdma_exit); +MODULE_DESCRIPTION("NVMe target RDMA transport driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("nvmet-transport-1"); /* 1 == NVMF_TRTYPE_RDMA */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 868aa4de2e4c..7c51c2a8c109 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -8,9 +8,14 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/err.h> +#include <linux/key.h> #include <linux/nvme-tcp.h> +#include <linux/nvme-keyring.h> #include <net/sock.h> #include <net/tcp.h> +#include <net/tls.h> +#include <net/tls_prot.h> +#include <net/handshake.h> #include <linux/inet.h> #include <linux/llist.h> #include <crypto/hash.h> @@ -19,6 +24,8 @@ #include "nvmet.h" #define NVMET_TCP_DEF_INLINE_DATA_SIZE (4 * PAGE_SIZE) +#define NVMET_TCP_MAXH2CDATA 0x400000 /* 16M arbitrary limit */ +#define NVMET_TCP_BACKLOG 128 static int param_store_val(const char *str, int *val, int min, int max) { @@ -66,6 +73,16 @@ device_param_cb(idle_poll_period_usecs, &set_param_ops, MODULE_PARM_DESC(idle_poll_period_usecs, "nvmet tcp io_work poll till idle time period in usecs: Default 0"); +#ifdef CONFIG_NVME_TARGET_TCP_TLS +/* + * TLS handshake timeout + */ +static int tls_handshake_timeout = 10; +module_param(tls_handshake_timeout, int, 0644); +MODULE_PARM_DESC(tls_handshake_timeout, + "nvme TLS handshake timeout in seconds (default 10)"); +#endif + #define NVMET_TCP_RECV_BUDGET 8 #define NVMET_TCP_SEND_BUDGET 8 #define NVMET_TCP_IO_WORK_BUDGET 64 @@ -104,6 +121,7 @@ struct nvmet_tcp_cmd { u32 pdu_len; u32 pdu_recv; int sg_idx; + char recv_cbuf[CMSG_LEN(sizeof(char))]; struct msghdr recv_msg; struct bio_vec *iov; u32 flags; @@ -122,8 +140,10 @@ struct nvmet_tcp_cmd { enum nvmet_tcp_queue_state { NVMET_TCP_Q_CONNECTING, + NVMET_TCP_Q_TLS_HANDSHAKE, NVMET_TCP_Q_LIVE, NVMET_TCP_Q_DISCONNECTING, + NVMET_TCP_Q_FAILED, }; struct nvmet_tcp_queue { @@ -132,6 +152,7 @@ struct nvmet_tcp_queue { struct work_struct io_work; struct nvmet_cq nvme_cq; struct nvmet_sq nvme_sq; + struct kref kref; /* send state */ struct nvmet_tcp_cmd *cmds; @@ -155,6 +176,10 @@ struct nvmet_tcp_queue { struct ahash_request *snd_hash; struct ahash_request *rcv_hash; + /* TLS state */ + key_serial_t tls_pskid; + struct delayed_work tls_handshake_tmo_work; + unsigned long poll_end; spinlock_t state_lock; @@ -323,6 +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); @@ -348,7 +374,7 @@ static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) while (length) { u32 iov_len = min_t(u32, length, sg->length - sg_offset); - bvec_set_page(iov, sg_page(sg), sg->length, + bvec_set_page(iov, sg_page(sg), iov_len, sg->offset + sg_offset); length -= iov_len; @@ -372,6 +398,7 @@ static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) { + queue->rcv_state = NVMET_TCP_RECV_ERR; if (status == -EPIPE || status == -ECONNRESET) kernel_sock_shutdown(queue->sock, SHUT_RDWR); else @@ -389,10 +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; @@ -872,6 +899,7 @@ 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) { @@ -899,7 +927,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) icresp->hdr.pdo = 0; icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen); icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0); - icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */ + icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA); icresp->cpda = 0; if (queue->hdr_digest) icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE; @@ -909,16 +937,14 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) iov.iov_base = icresp; iov.iov_len = sizeof(*icresp); ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); - if (ret < 0) - goto free_crypto; + if (ret < 0) { + queue->state = NVMET_TCP_Q_FAILED; + return ret; /* queue removal will cleanup */ + } queue->state = NVMET_TCP_Q_LIVE; nvmet_prepare_receive_pdu(queue); return 0; -free_crypto: - if (queue->hdr_digest || queue->data_digest) - nvmet_tcp_free_crypto(queue); - return ret; } static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, @@ -956,13 +982,13 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) { struct nvme_tcp_data_pdu *data = &queue->pdu.data; struct nvmet_tcp_cmd *cmd; + unsigned int exp_data_len; if (likely(queue->nr_cmds)) { if (unlikely(data->ttag >= queue->nr_cmds)) { pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n", queue->idx, data->ttag, queue->nr_cmds); - nvmet_tcp_fatal_error(queue); - return -EPROTO; + goto err_proto; } cmd = &queue->cmds[data->ttag]; } else { @@ -973,19 +999,32 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) pr_err("ttag %u unexpected data offset %u (expected %u)\n", data->ttag, le32_to_cpu(data->data_offset), cmd->rbytes_done); - /* FIXME: use path and transport errors */ - nvmet_req_complete(&cmd->req, - NVME_SC_INVALID_FIELD | NVME_SC_DNR); - return -EPROTO; + goto err_proto; } + exp_data_len = le32_to_cpu(data->hdr.plen) - + nvmet_tcp_hdgst_len(queue) - + nvmet_tcp_ddgst_len(queue) - + sizeof(*data); + cmd->pdu_len = le32_to_cpu(data->data_length); + if (unlikely(cmd->pdu_len != exp_data_len || + cmd->pdu_len == 0 || + cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) { + pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len); + goto err_proto; + } cmd->pdu_recv = 0; nvmet_tcp_build_pdu_iovec(cmd); queue->cmd = cmd; queue->rcv_state = NVMET_TCP_RECV_DATA; return 0; + +err_proto: + /* FIXME: use proper transport errors */ + nvmet_tcp_fatal_error(queue); + return -EPROTO; } static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) @@ -1099,20 +1138,65 @@ static inline bool nvmet_tcp_pdu_valid(u8 type) return false; } +static int nvmet_tcp_tls_record_ok(struct nvmet_tcp_queue *queue, + struct msghdr *msg, char *cbuf) +{ + struct cmsghdr *cmsg = (struct cmsghdr *)cbuf; + u8 ctype, level, description; + int ret = 0; + + ctype = tls_get_record_type(queue->sock->sk, cmsg); + switch (ctype) { + case 0: + break; + case TLS_RECORD_TYPE_DATA: + break; + case TLS_RECORD_TYPE_ALERT: + tls_alert_recv(queue->sock->sk, msg, &level, &description); + if (level == TLS_ALERT_LEVEL_FATAL) { + pr_err("queue %d: TLS Alert desc %u\n", + queue->idx, description); + ret = -ENOTCONN; + } else { + pr_warn("queue %d: TLS Alert desc %u\n", + queue->idx, description); + ret = -EAGAIN; + } + break; + default: + /* discard this record type */ + pr_err("queue %d: TLS record %d unhandled\n", + queue->idx, ctype); + ret = -EAGAIN; + break; + } + return ret; +} + static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue) { struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr; - int len; + int len, ret; struct kvec iov; + char cbuf[CMSG_LEN(sizeof(char))] = {}; struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; recv: iov.iov_base = (void *)&queue->pdu + queue->offset; iov.iov_len = queue->left; + if (queue->tls_pskid) { + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + } len = kernel_recvmsg(queue->sock, &msg, &iov, 1, iov.iov_len, msg.msg_flags); if (unlikely(len < 0)) return len; + if (queue->tls_pskid) { + ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf); + if (ret < 0) + return ret; + } queue->offset += len; queue->left -= len; @@ -1165,16 +1249,22 @@ static void nvmet_tcp_prep_recv_ddgst(struct nvmet_tcp_cmd *cmd) static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) { struct nvmet_tcp_cmd *cmd = queue->cmd; - int ret; + int len, ret; while (msg_data_left(&cmd->recv_msg)) { - ret = sock_recvmsg(cmd->queue->sock, &cmd->recv_msg, + len = sock_recvmsg(cmd->queue->sock, &cmd->recv_msg, cmd->recv_msg.msg_flags); - if (ret <= 0) - return ret; + if (len <= 0) + return len; + if (queue->tls_pskid) { + ret = nvmet_tcp_tls_record_ok(cmd->queue, + &cmd->recv_msg, cmd->recv_cbuf); + if (ret < 0) + return ret; + } - cmd->pdu_recv += ret; - cmd->rbytes_done += ret; + cmd->pdu_recv += len; + cmd->rbytes_done += len; } if (queue->data_digest) { @@ -1192,20 +1282,30 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) { struct nvmet_tcp_cmd *cmd = queue->cmd; - int ret; + int ret, len; + char cbuf[CMSG_LEN(sizeof(char))] = {}; struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; struct kvec iov = { .iov_base = (void *)&cmd->recv_ddgst + queue->offset, .iov_len = queue->left }; - ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, + if (queue->tls_pskid) { + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + } + len = kernel_recvmsg(queue->sock, &msg, &iov, 1, iov.iov_len, msg.msg_flags); - if (unlikely(ret < 0)) - return ret; + if (unlikely(len < 0)) + return len; + if (queue->tls_pskid) { + ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf); + if (ret < 0) + return ret; + } - queue->offset += ret; - queue->left -= ret; + queue->offset += len; + queue->left -= len; if (queue->left) return -EAGAIN; @@ -1283,14 +1383,27 @@ done: return ret; } +static void nvmet_tcp_release_queue(struct kref *kref) +{ + struct nvmet_tcp_queue *queue = + container_of(kref, struct nvmet_tcp_queue, kref); + + WARN_ON(queue->state != NVMET_TCP_Q_DISCONNECTING); + queue_work(nvmet_wq, &queue->release_work); +} + static void nvmet_tcp_schedule_release_queue(struct nvmet_tcp_queue *queue) { - spin_lock(&queue->state_lock); + spin_lock_bh(&queue->state_lock); + if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) { + /* Socket closed during handshake */ + tls_handshake_cancel(queue->sock->sk); + } if (queue->state != NVMET_TCP_Q_DISCONNECTING) { queue->state = NVMET_TCP_Q_DISCONNECTING; - queue_work(nvmet_wq, &queue->release_work); + kref_put(&queue->kref, nvmet_tcp_release_queue); } - spin_unlock(&queue->state_lock); + spin_unlock_bh(&queue->state_lock); } static inline void nvmet_tcp_arm_queue_deadline(struct nvmet_tcp_queue *queue) @@ -1372,6 +1485,10 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue, if (!c->r2t_pdu) goto out_free_data; + if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) { + c->recv_msg.msg_control = c->recv_cbuf; + c->recv_msg.msg_controllen = sizeof(c->recv_cbuf); + } c->recv_msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL; list_add_tail(&c->entry, &queue->free_list); @@ -1465,18 +1582,13 @@ 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); @@ -1485,6 +1597,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) mutex_unlock(&nvmet_tcp_queue_mutex); nvmet_tcp_restore_socket_callbacks(queue); + cancel_delayed_work_sync(&queue->tls_handshake_tmo_work); cancel_work_sync(&queue->io_work); /* stop accepting incoming data */ queue->rcv_state = NVMET_TCP_RECV_ERR; @@ -1493,14 +1606,13 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) nvmet_sq_destroy(&queue->nvme_sq); cancel_work_sync(&queue->io_work); nvmet_tcp_free_cmd_data_in_buffers(queue); - sock_release(queue->sock); + /* ->sock will be released by fput() */ + fput(queue->sock->file); nvmet_tcp_free_cmds(queue); if (queue->hdr_digest || queue->data_digest) nvmet_tcp_free_crypto(queue); ida_free(&nvmet_tcp_queue_ida, queue->idx); - - page = virt_to_head_page(queue->pf_cache.va); - __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); + page_frag_cache_drain(&queue->pf_cache); kfree(queue); } @@ -1512,8 +1624,13 @@ static void nvmet_tcp_data_ready(struct sock *sk) read_lock_bh(&sk->sk_callback_lock); queue = sk->sk_user_data; - if (likely(queue)) - queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work); + if (likely(queue)) { + if (queue->data_ready) + queue->data_ready(sk); + if (queue->state != NVMET_TCP_Q_TLS_HANDSHAKE) + queue_work_on(queue_cpu(queue), nvmet_tcp_wq, + &queue->io_work); + } read_unlock_bh(&sk->sk_callback_lock); } @@ -1621,31 +1738,176 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue) return ret; } -static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, +#ifdef CONFIG_NVME_TARGET_TCP_TLS +static int nvmet_tcp_try_peek_pdu(struct nvmet_tcp_queue *queue) +{ + struct nvme_tcp_hdr *hdr = &queue->pdu.cmd.hdr; + int len, ret; + struct kvec iov = { + .iov_base = (u8 *)&queue->pdu + queue->offset, + .iov_len = sizeof(struct nvme_tcp_hdr), + }; + char cbuf[CMSG_LEN(sizeof(char))] = {}; + struct msghdr msg = { + .msg_control = cbuf, + .msg_controllen = sizeof(cbuf), + .msg_flags = MSG_PEEK, + }; + + if (nvmet_port_secure_channel_required(queue->port->nport)) + return 0; + + len = kernel_recvmsg(queue->sock, &msg, &iov, 1, + iov.iov_len, msg.msg_flags); + if (unlikely(len < 0)) { + pr_debug("queue %d: peek error %d\n", + queue->idx, len); + return len; + } + + ret = nvmet_tcp_tls_record_ok(queue, &msg, cbuf); + if (ret < 0) + return ret; + + if (len < sizeof(struct nvme_tcp_hdr)) { + pr_debug("queue %d: short read, %d bytes missing\n", + queue->idx, (int)iov.iov_len - len); + return -EAGAIN; + } + pr_debug("queue %d: hdr type %d hlen %d plen %d size %d\n", + queue->idx, hdr->type, hdr->hlen, hdr->plen, + (int)sizeof(struct nvme_tcp_icreq_pdu)); + if (hdr->type == nvme_tcp_icreq && + hdr->hlen == sizeof(struct nvme_tcp_icreq_pdu) && + hdr->plen == cpu_to_le32(sizeof(struct nvme_tcp_icreq_pdu))) { + pr_debug("queue %d: icreq detected\n", + queue->idx); + return len; + } + return 0; +} + +static void nvmet_tcp_tls_handshake_done(void *data, int status, + key_serial_t peerid) +{ + struct nvmet_tcp_queue *queue = data; + + pr_debug("queue %d: TLS handshake done, key %x, status %d\n", + queue->idx, peerid, status); + spin_lock_bh(&queue->state_lock); + if (WARN_ON(queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)) { + spin_unlock_bh(&queue->state_lock); + return; + } + if (!status) { + queue->tls_pskid = peerid; + queue->state = NVMET_TCP_Q_CONNECTING; + } else + queue->state = NVMET_TCP_Q_FAILED; + spin_unlock_bh(&queue->state_lock); + + cancel_delayed_work_sync(&queue->tls_handshake_tmo_work); + if (status) + nvmet_tcp_schedule_release_queue(queue); + else + nvmet_tcp_set_queue_sock(queue); + kref_put(&queue->kref, nvmet_tcp_release_queue); +} + +static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w) +{ + struct nvmet_tcp_queue *queue = container_of(to_delayed_work(w), + struct nvmet_tcp_queue, tls_handshake_tmo_work); + + pr_warn("queue %d: TLS handshake timeout\n", queue->idx); + /* + * If tls_handshake_cancel() fails we've lost the race with + * nvmet_tcp_tls_handshake_done() */ + if (!tls_handshake_cancel(queue->sock->sk)) + return; + spin_lock_bh(&queue->state_lock); + if (WARN_ON(queue->state != NVMET_TCP_Q_TLS_HANDSHAKE)) { + spin_unlock_bh(&queue->state_lock); + return; + } + queue->state = NVMET_TCP_Q_FAILED; + spin_unlock_bh(&queue->state_lock); + nvmet_tcp_schedule_release_queue(queue); + kref_put(&queue->kref, nvmet_tcp_release_queue); +} + +static int nvmet_tcp_tls_handshake(struct nvmet_tcp_queue *queue) +{ + int ret = -EOPNOTSUPP; + struct tls_handshake_args args; + + if (queue->state != NVMET_TCP_Q_TLS_HANDSHAKE) { + pr_warn("cannot start TLS in state %d\n", queue->state); + return -EINVAL; + } + + kref_get(&queue->kref); + pr_debug("queue %d: TLS ServerHello\n", queue->idx); + memset(&args, 0, sizeof(args)); + args.ta_sock = queue->sock; + args.ta_done = nvmet_tcp_tls_handshake_done; + args.ta_data = queue; + args.ta_keyring = key_serial(queue->port->nport->keyring); + args.ta_timeout_ms = tls_handshake_timeout * 1000; + + ret = tls_server_hello_psk(&args, GFP_KERNEL); + if (ret) { + kref_put(&queue->kref, nvmet_tcp_release_queue); + pr_err("failed to start TLS, err=%d\n", ret); + } else { + queue_delayed_work(nvmet_wq, &queue->tls_handshake_tmo_work, + tls_handshake_timeout * HZ); + } + return ret; +} +#else +static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w) {} +#endif + +static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, struct socket *newsock) { struct nvmet_tcp_queue *queue; + struct file *sock_file = NULL; int ret; queue = kzalloc(sizeof(*queue), GFP_KERNEL); - if (!queue) - return -ENOMEM; + if (!queue) { + ret = -ENOMEM; + goto out_release; + } INIT_WORK(&queue->release_work, nvmet_tcp_release_queue_work); INIT_WORK(&queue->io_work, nvmet_tcp_io_work); + kref_init(&queue->kref); queue->sock = newsock; queue->port = port; queue->nr_cmds = 0; spin_lock_init(&queue->state_lock); - queue->state = NVMET_TCP_Q_CONNECTING; + if (queue->port->nport->disc_addr.tsas.tcp.sectype == + NVMF_TCP_SECTYPE_TLS13) + queue->state = NVMET_TCP_Q_TLS_HANDSHAKE; + else + queue->state = NVMET_TCP_Q_CONNECTING; INIT_LIST_HEAD(&queue->free_list); init_llist_head(&queue->resp_list); INIT_LIST_HEAD(&queue->resp_send_list); + sock_file = sock_alloc_file(queue->sock, O_CLOEXEC, NULL); + if (IS_ERR(sock_file)) { + ret = PTR_ERR(sock_file); + goto out_free_queue; + } + queue->idx = ida_alloc(&nvmet_tcp_queue_ida, GFP_KERNEL); if (queue->idx < 0) { ret = queue->idx; - goto out_free_queue; + goto out_sock; } ret = nvmet_tcp_alloc_cmd(queue, &queue->connect); @@ -1662,11 +1924,33 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, list_add_tail(&queue->queue_list, &nvmet_tcp_queue_list); mutex_unlock(&nvmet_tcp_queue_mutex); + INIT_DELAYED_WORK(&queue->tls_handshake_tmo_work, + nvmet_tcp_tls_handshake_timeout); +#ifdef CONFIG_NVME_TARGET_TCP_TLS + if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) { + struct sock *sk = queue->sock->sk; + + /* Restore the default callbacks before starting upcall */ + read_lock_bh(&sk->sk_callback_lock); + sk->sk_user_data = NULL; + sk->sk_data_ready = port->data_ready; + read_unlock_bh(&sk->sk_callback_lock); + if (!nvmet_tcp_try_peek_pdu(queue)) { + if (!nvmet_tcp_tls_handshake(queue)) + return; + /* TLS handshake failed, terminate the connection */ + goto out_destroy_sq; + } + /* Not a TLS connection, continue with normal processing */ + queue->state = NVMET_TCP_Q_CONNECTING; + } +#endif + ret = nvmet_tcp_set_queue_sock(queue); if (ret) goto out_destroy_sq; - return 0; + return; out_destroy_sq: mutex_lock(&nvmet_tcp_queue_mutex); list_del_init(&queue->queue_list); @@ -1676,9 +1960,14 @@ out_free_connect: nvmet_tcp_free_cmd(&queue->connect); out_ida_remove: ida_free(&nvmet_tcp_queue_ida, queue->idx); +out_sock: + fput(queue->sock->file); out_free_queue: kfree(queue); - return ret; +out_release: + pr_err("failed to allocate queue, error %d\n", ret); + if (!sock_file) + sock_release(newsock); } static void nvmet_tcp_accept_work(struct work_struct *w) @@ -1695,11 +1984,7 @@ static void nvmet_tcp_accept_work(struct work_struct *w) pr_warn("failed to accept err=%d\n", ret); return; } - ret = nvmet_tcp_alloc_queue(port, newsock); - if (ret) { - pr_err("failed to allocate queue\n"); - sock_release(newsock); - } + nvmet_tcp_alloc_queue(port, newsock); } } @@ -1779,7 +2064,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) goto err_sock; } - ret = kernel_listen(port->sock, 128); + ret = kernel_listen(port->sock, NVMET_TCP_BACKLOG); if (ret) { pr_err("failed to listen %d on port sock\n", ret); goto err_sock; @@ -1845,13 +2130,26 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq) container_of(sq, struct nvmet_tcp_queue, nvme_sq); if (sq->qid == 0) { - /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_wq); + struct nvmet_tcp_queue *q; + int pending = 0; + + /* Check for pending controller teardown */ + mutex_lock(&nvmet_tcp_queue_mutex); + list_for_each_entry(q, &nvmet_tcp_queue_list, queue_list) { + if (q->nvme_sq.ctrl == sq->ctrl && + q->state == NVMET_TCP_Q_DISCONNECTING) + pending++; + } + mutex_unlock(&nvmet_tcp_queue_mutex); + if (pending > NVMET_TCP_BACKLOG) + return NVME_SC_CONNECT_CTRL_BUSY; } 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; } @@ -1871,6 +2169,19 @@ 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, @@ -1881,6 +2192,7 @@ 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) @@ -1916,10 +2228,12 @@ static void __exit nvmet_tcp_exit(void) flush_workqueue(nvmet_wq); destroy_workqueue(nvmet_tcp_wq); + ida_destroy(&nvmet_tcp_queue_ida); } module_init(nvmet_tcp_init); module_exit(nvmet_tcp_exit); +MODULE_DESCRIPTION("NVMe target TCP transport driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("nvmet-transport-3"); /* 3 == NVMF_TRTYPE_TCP */ diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c index bff454d46255..8d1806a82887 100644 --- a/drivers/nvme/target/trace.c +++ b/drivers/nvme/target/trace.c @@ -119,6 +119,67 @@ 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; +} + const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode, u8 *cdw10) { @@ -126,9 +187,14 @@ 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); default: return nvmet_trace_common(p, cdw10); } @@ -176,6 +242,34 @@ 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 +289,10 @@ 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); } @@ -211,7 +309,7 @@ const char *nvmet_trace_disk_name(struct trace_seq *p, char *name) return ret; } -const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl) +const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id) { const char *ret = trace_seq_buffer_ptr(p); @@ -224,8 +322,8 @@ const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl) * If we can know the extra data of the connect command in this stage, * we can update this print statement later. */ - if (ctrl) - trace_seq_printf(p, "%d", ctrl->cntlid); + if (ctrl_id) + trace_seq_printf(p, "%d", ctrl_id); else trace_seq_printf(p, "_"); trace_seq_putc(p, 0); diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h index 6109b3806b12..7f7ebf9558e5 100644 --- a/drivers/nvme/target/trace.h +++ b/drivers/nvme/target/trace.h @@ -32,18 +32,24 @@ const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p, u8 fctype, nvmet_trace_parse_nvm_cmd(p, opcode, cdw10) : \ nvmet_trace_parse_admin_cmd(p, opcode, cdw10))) -const char *nvmet_trace_ctrl_name(struct trace_seq *p, struct nvmet_ctrl *ctrl); -#define __print_ctrl_name(ctrl) \ - nvmet_trace_ctrl_name(p, ctrl) +const char *nvmet_trace_ctrl_id(struct trace_seq *p, u16 ctrl_id); +#define __print_ctrl_id(ctrl_id) \ + nvmet_trace_ctrl_id(p, ctrl_id) const char *nvmet_trace_disk_name(struct trace_seq *p, char *name); #define __print_disk_name(name) \ nvmet_trace_disk_name(p, name) #ifndef TRACE_HEADER_MULTI_READ -static inline struct nvmet_ctrl *nvmet_req_to_ctrl(struct nvmet_req *req) +static inline u16 nvmet_req_to_ctrl_id(struct nvmet_req *req) { - return req->sq->ctrl; + /* + * The queue and controller pointers are not valid until an association + * has been established. + */ + if (!req->sq || !req->sq->ctrl) + return 0; + return req->sq->ctrl->cntlid; } static inline void __assign_req_name(char *name, struct nvmet_req *req) @@ -53,8 +59,7 @@ static inline void __assign_req_name(char *name, struct nvmet_req *req) return; } - strncpy(name, req->ns->device_path, - min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path))); + strscpy_pad(name, req->ns->device_path, DISK_NAME_LEN); } #endif @@ -63,7 +68,7 @@ TRACE_EVENT(nvmet_req_init, TP_ARGS(req, cmd), TP_STRUCT__entry( __field(struct nvme_command *, cmd) - __field(struct nvmet_ctrl *, ctrl) + __field(u16, ctrl_id) __array(char, disk, DISK_NAME_LEN) __field(int, qid) __field(u16, cid) @@ -76,7 +81,7 @@ TRACE_EVENT(nvmet_req_init, ), TP_fast_assign( __entry->cmd = cmd; - __entry->ctrl = nvmet_req_to_ctrl(req); + __entry->ctrl_id = nvmet_req_to_ctrl_id(req); __assign_req_name(__entry->disk, req); __entry->qid = req->sq->qid; __entry->cid = cmd->common.command_id; @@ -85,12 +90,12 @@ TRACE_EVENT(nvmet_req_init, __entry->flags = cmd->common.flags; __entry->nsid = le32_to_cpu(cmd->common.nsid); __entry->metadata = le64_to_cpu(cmd->common.metadata); - memcpy(__entry->cdw10, &cmd->common.cdw10, + memcpy(__entry->cdw10, &cmd->common.cdws, sizeof(__entry->cdw10)); ), TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, " "meta=%#llx, cmd=(%s, %s)", - __print_ctrl_name(__entry->ctrl), + __print_ctrl_id(__entry->ctrl_id), __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->nsid, __entry->flags, __entry->metadata, @@ -104,7 +109,7 @@ TRACE_EVENT(nvmet_req_complete, TP_PROTO(struct nvmet_req *req), TP_ARGS(req), TP_STRUCT__entry( - __field(struct nvmet_ctrl *, ctrl) + __field(u16, ctrl_id) __array(char, disk, DISK_NAME_LEN) __field(int, qid) __field(int, cid) @@ -112,7 +117,7 @@ TRACE_EVENT(nvmet_req_complete, __field(u16, status) ), TP_fast_assign( - __entry->ctrl = nvmet_req_to_ctrl(req); + __entry->ctrl_id = nvmet_req_to_ctrl_id(req); __entry->qid = req->cq->qid; __entry->cid = req->cqe->command_id; __entry->result = le64_to_cpu(req->cqe->result.u64); @@ -120,7 +125,7 @@ TRACE_EVENT(nvmet_req_complete, __assign_req_name(__entry->disk, req); ), TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x", - __print_ctrl_name(__entry->ctrl), + __print_ctrl_id(__entry->ctrl_id), __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->result, __entry->status) diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 5b5c1e481722..af9e13be7678 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); @@ -556,13 +551,13 @@ 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; } @@ -595,7 +590,7 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req) } if (total_len != nvmet_rw_data_len(req)) { - status = NVME_SC_INTERNAL | NVME_SC_DNR; + status = NVME_SC_INTERNAL | NVME_STATUS_DNR; goto out_put_bio; } |