diff options
Diffstat (limited to 'drivers/nvme/host')
-rw-r--r-- | drivers/nvme/host/Kconfig | 22 | ||||
-rw-r--r-- | drivers/nvme/host/apple.c | 62 | ||||
-rw-r--r-- | drivers/nvme/host/auth.c | 145 | ||||
-rw-r--r-- | drivers/nvme/host/constants.c | 2 | ||||
-rw-r--r-- | drivers/nvme/host/core.c | 310 | ||||
-rw-r--r-- | drivers/nvme/host/fabrics.c | 36 | ||||
-rw-r--r-- | drivers/nvme/host/fabrics.h | 9 | ||||
-rw-r--r-- | drivers/nvme/host/fc.c | 90 | ||||
-rw-r--r-- | drivers/nvme/host/ioctl.c | 86 | ||||
-rw-r--r-- | drivers/nvme/host/multipath.c | 357 | ||||
-rw-r--r-- | drivers/nvme/host/nvme.h | 57 | ||||
-rw-r--r-- | drivers/nvme/host/pci.c | 367 | ||||
-rw-r--r-- | drivers/nvme/host/pr.c | 2 | ||||
-rw-r--r-- | drivers/nvme/host/rdma.c | 7 | ||||
-rw-r--r-- | drivers/nvme/host/sysfs.c | 59 | ||||
-rw-r--r-- | drivers/nvme/host/tcp.c | 343 | ||||
-rw-r--r-- | drivers/nvme/host/zns.c | 10 |
17 files changed, 1450 insertions, 514 deletions
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 486afe598184..31974c7dd20c 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -18,10 +18,15 @@ config NVME_MULTIPATH bool "NVMe multipath support" depends on NVME_CORE help - This option enables support for multipath access to NVMe - subsystems. If this option is enabled only a single - /dev/nvmeXnY device will show up for each NVMe namespace, - even if it is accessible through multiple controllers. + This option controls support for multipath access to NVMe + subsystems. If this option is enabled support for NVMe multipath + access is included in the kernel. If this option is disabled support + for NVMe multipath access is excluded from the kernel. When this + option is disabled each controller/namespace receives its + own /dev/nvmeXnY device entry and NVMe multipath access is + not supported. + + If unsure, say Y. config NVME_VERBOSE_ERRORS bool "NVMe verbose error reporting" @@ -79,9 +84,9 @@ config NVME_TCP tristate "NVM Express over Fabrics TCP host driver" depends on INET depends on BLOCK + select CRC32 + select NET_CRC32C select NVME_FABRICS - select CRYPTO - select CRYPTO_CRC32C help This provides support for the NVMe over Fabrics protocol using the TCP transport. This allows you to use remote block devices @@ -97,10 +102,11 @@ config NVME_TCP_TLS depends on NVME_TCP select NET_HANDSHAKE select KEYS + select TLS help Enables TLS encryption for NVMe TCP using the netlink handshake API. - The TLS handshake daemon is availble at + The TLS handshake daemon is available at https://github.com/oracle/ktls-utils. If unsure, say N. @@ -109,7 +115,7 @@ config NVME_HOST_AUTH bool "NVMe over Fabrics In-Band Authentication in host side" depends on NVME_CORE select NVME_AUTH - select NVME_KEYRING if NVME_TCP_TLS + select NVME_KEYRING help This provides support for NVMe over Fabrics In-Band Authentication in host side. diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 1de11b722f04..b1fddfa33ab9 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -221,7 +221,7 @@ static unsigned int apple_nvme_queue_depth(struct apple_nvme_queue *q) return APPLE_ANS_MAX_QUEUE_DEPTH; } -static void apple_nvme_rtkit_crashed(void *cookie) +static void apple_nvme_rtkit_crashed(void *cookie, const void *crashlog, size_t crashlog_size) { struct apple_nvme *anv = cookie; @@ -525,7 +525,7 @@ static blk_status_t apple_nvme_map_data(struct apple_nvme *anv, if (!iod->sg) return BLK_STS_RESOURCE; sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); - iod->nents = blk_rq_map_sg(req->q, req, iod->sg); + iod->nents = blk_rq_map_sg(req, iod->sg); if (!iod->nents) goto out_free_sg; @@ -599,7 +599,8 @@ static inline void apple_nvme_handle_cqe(struct apple_nvme_queue *q, } if (!nvme_try_complete_req(req, cqe->status, cqe->result) && - !blk_mq_add_to_batch(req, iob, nvme_req(req)->status, + !blk_mq_add_to_batch(req, iob, + nvme_req(req)->status != NVME_SC_SUCCESS, apple_nvme_complete_batch)) apple_nvme_complete_rq(req); } @@ -1011,25 +1012,37 @@ static void apple_nvme_reset_work(struct work_struct *work) ret = apple_rtkit_shutdown(anv->rtk); if (ret) goto out; + + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); } - writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + /* + * Only do the soft-reset if the CPU is not running, which means either we + * or the previous stage shut it down cleanly. + */ + if (!(readl(anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL) & + APPLE_ANS_COPROC_CPU_CONTROL_RUN)) { - ret = reset_control_assert(anv->reset); - if (ret) - goto out; + ret = reset_control_assert(anv->reset); + if (ret) + goto out; - ret = apple_rtkit_reinit(anv->rtk); - if (ret) - goto out; + ret = apple_rtkit_reinit(anv->rtk); + if (ret) + goto out; - ret = reset_control_deassert(anv->reset); - if (ret) - goto out; + ret = reset_control_deassert(anv->reset); + if (ret) + goto out; + + writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN, + anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + + ret = apple_rtkit_boot(anv->rtk); + } else { + ret = apple_rtkit_wake(anv->rtk); + } - writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN, - anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); - ret = apple_rtkit_boot(anv->rtk); if (ret) { dev_err(anv->dev, "ANS did not boot"); goto out; @@ -1516,6 +1529,7 @@ static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev) return anv; put_dev: + apple_nvme_detach_genpd(anv); put_device(anv->dev); return ERR_PTR(ret); } @@ -1549,6 +1563,7 @@ out_uninit_ctrl: nvme_uninit_ctrl(&anv->ctrl); out_put_ctrl: nvme_put_ctrl(&anv->ctrl); + apple_nvme_detach_genpd(anv); return ret; } @@ -1563,9 +1578,12 @@ static void apple_nvme_remove(struct platform_device *pdev) apple_nvme_disable(anv, true); nvme_uninit_ctrl(&anv->ctrl); - if (apple_rtkit_is_running(anv->rtk)) + if (apple_rtkit_is_running(anv->rtk)) { apple_rtkit_shutdown(anv->rtk); + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + } + apple_nvme_detach_genpd(anv); } @@ -1574,8 +1592,11 @@ static void apple_nvme_shutdown(struct platform_device *pdev) struct apple_nvme *anv = platform_get_drvdata(pdev); apple_nvme_disable(anv, true); - if (apple_rtkit_is_running(anv->rtk)) + if (apple_rtkit_is_running(anv->rtk)) { apple_rtkit_shutdown(anv->rtk); + + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + } } static int apple_nvme_resume(struct device *dev) @@ -1592,10 +1613,11 @@ static int apple_nvme_suspend(struct device *dev) apple_nvme_disable(anv, true); - if (apple_rtkit_is_running(anv->rtk)) + if (apple_rtkit_is_running(anv->rtk)) { ret = apple_rtkit_shutdown(anv->rtk); - writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + } return ret; } diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index 5ea0e21709da..f6ddbe553289 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -12,6 +12,7 @@ #include "nvme.h" #include "fabrics.h" #include <linux/nvme-auth.h> +#include <linux/nvme-keyring.h> #define CHAP_BUF_SIZE 4096 static struct kmem_cache *nvme_chap_buf_cache; @@ -30,6 +31,7 @@ struct nvme_dhchap_queue_context { u32 s1; u32 s2; bool bi_directional; + bool authenticated; u16 transaction; u8 status; u8 dhgroup_id; @@ -131,7 +133,13 @@ static int nvme_auth_set_dhchap_negotiate_data(struct nvme_ctrl *ctrl, data->auth_type = NVME_AUTH_COMMON_MESSAGES; data->auth_id = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; data->t_id = cpu_to_le16(chap->transaction); - data->sc_c = 0; /* No secure channel concatenation */ + if (ctrl->opts->concat && chap->qid == 0) { + if (ctrl->opts->tls_key) + data->sc_c = NVME_AUTH_SECP_REPLACETLSPSK; + else + data->sc_c = NVME_AUTH_SECP_NEWTLSPSK; + } else + data->sc_c = NVME_AUTH_SECP_NOSC; data->napd = 1; data->auth_protocol[0].dhchap.authid = NVME_AUTH_DHCHAP_AUTH_ID; data->auth_protocol[0].dhchap.halen = 3; @@ -311,8 +319,9 @@ static int nvme_auth_set_dhchap_reply_data(struct nvme_ctrl *ctrl, data->hl = chap->hash_len; data->dhvlen = cpu_to_le16(chap->host_key_len); memcpy(data->rval, chap->response, chap->hash_len); - if (ctrl->ctrl_key) { + if (ctrl->ctrl_key) chap->bi_directional = true; + if (ctrl->ctrl_key || ctrl->opts->concat) { get_random_bytes(chap->c2, chap->hash_len); data->cvalid = 1; memcpy(data->rval + chap->hash_len, chap->c2, @@ -322,7 +331,10 @@ static int nvme_auth_set_dhchap_reply_data(struct nvme_ctrl *ctrl, } else { memset(chap->c2, 0, chap->hash_len); } - chap->s2 = nvme_auth_get_seqnum(); + if (ctrl->opts->concat) + chap->s2 = 0; + else + 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", @@ -671,12 +683,99 @@ static void nvme_auth_reset_dhchap(struct nvme_dhchap_queue_context *chap) static void nvme_auth_free_dhchap(struct nvme_dhchap_queue_context *chap) { nvme_auth_reset_dhchap(chap); + chap->authenticated = false; if (chap->shash_tfm) crypto_free_shash(chap->shash_tfm); if (chap->dh_tfm) crypto_free_kpp(chap->dh_tfm); } +void nvme_auth_revoke_tls_key(struct nvme_ctrl *ctrl) +{ + dev_dbg(ctrl->device, "Wipe generated TLS PSK %08x\n", + key_serial(ctrl->opts->tls_key)); + key_revoke(ctrl->opts->tls_key); + key_put(ctrl->opts->tls_key); + ctrl->opts->tls_key = NULL; +} +EXPORT_SYMBOL_GPL(nvme_auth_revoke_tls_key); + +static int nvme_auth_secure_concat(struct nvme_ctrl *ctrl, + struct nvme_dhchap_queue_context *chap) +{ + u8 *psk, *digest, *tls_psk; + struct key *tls_key; + size_t psk_len; + int ret = 0; + + if (!chap->sess_key) { + dev_warn(ctrl->device, + "%s: qid %d no session key negotiated\n", + __func__, chap->qid); + return -ENOKEY; + } + + if (chap->qid) { + dev_warn(ctrl->device, + "qid %d: secure concatenation not supported on I/O queues\n", + chap->qid); + return -EINVAL; + } + ret = nvme_auth_generate_psk(chap->hash_id, chap->sess_key, + chap->sess_key_len, + chap->c1, chap->c2, + chap->hash_len, &psk, &psk_len); + if (ret) { + dev_warn(ctrl->device, + "%s: qid %d failed to generate PSK, error %d\n", + __func__, chap->qid, ret); + return ret; + } + dev_dbg(ctrl->device, + "%s: generated psk %*ph\n", __func__, (int)psk_len, psk); + + ret = nvme_auth_generate_digest(chap->hash_id, psk, psk_len, + ctrl->opts->subsysnqn, + ctrl->opts->host->nqn, &digest); + if (ret) { + dev_warn(ctrl->device, + "%s: qid %d failed to generate digest, error %d\n", + __func__, chap->qid, ret); + goto out_free_psk; + }; + dev_dbg(ctrl->device, "%s: generated digest %s\n", + __func__, digest); + ret = nvme_auth_derive_tls_psk(chap->hash_id, psk, psk_len, + digest, &tls_psk); + if (ret) { + dev_warn(ctrl->device, + "%s: qid %d failed to derive TLS psk, error %d\n", + __func__, chap->qid, ret); + goto out_free_digest; + }; + + tls_key = nvme_tls_psk_refresh(ctrl->opts->keyring, + ctrl->opts->host->nqn, + ctrl->opts->subsysnqn, chap->hash_id, + tls_psk, psk_len, digest); + if (IS_ERR(tls_key)) { + ret = PTR_ERR(tls_key); + dev_warn(ctrl->device, + "%s: qid %d failed to insert generated key, error %d\n", + __func__, chap->qid, ret); + tls_key = NULL; + } + kfree_sensitive(tls_psk); + if (ctrl->opts->tls_key) + nvme_auth_revoke_tls_key(ctrl); + ctrl->opts->tls_key = tls_key; +out_free_digest: + kfree_sensitive(digest); +out_free_psk: + kfree_sensitive(psk); + return ret; +} + static void nvme_queue_auth_work(struct work_struct *work) { struct nvme_dhchap_queue_context *chap = @@ -833,6 +932,15 @@ static void nvme_queue_auth_work(struct work_struct *work) } if (!ret) { chap->error = 0; + chap->authenticated = true; + if (ctrl->opts->concat && + (ret = nvme_auth_secure_concat(ctrl, chap))) { + dev_warn(ctrl->device, + "%s: qid %d failed to enable secure concatenation\n", + __func__, chap->qid); + chap->error = ret; + chap->authenticated = false; + } return; } @@ -912,15 +1020,23 @@ static void nvme_ctrl_auth_work(struct work_struct *work) "qid 0: authentication failed\n"); return; } + /* + * Only run authentication on the admin queue for secure concatenation. + */ + if (ctrl->opts->concat) + return; for (q = 1; q < ctrl->queue_count; q++) { - ret = nvme_auth_negotiate(ctrl, q); - if (ret) { - dev_warn(ctrl->device, - "qid %d: error %d setting up authentication\n", - q, ret); - break; - } + struct nvme_dhchap_queue_context *chap = + &ctrl->dhchap_ctxs[q]; + /* + * Skip re-authentication if the queue had + * not been authenticated initially. + */ + if (!chap->authenticated) + continue; + cancel_work_sync(&chap->auth_work); + queue_work(nvme_auth_wq, &chap->auth_work); } /* @@ -928,7 +1044,13 @@ static void nvme_ctrl_auth_work(struct work_struct *work) * the controller terminates the connection. */ for (q = 1; q < ctrl->queue_count; q++) { - ret = nvme_auth_wait(ctrl, q); + struct nvme_dhchap_queue_context *chap = + &ctrl->dhchap_ctxs[q]; + if (!chap->authenticated) + continue; + flush_work(&chap->auth_work); + ret = chap->error; + nvme_auth_reset_dhchap(chap); if (ret) dev_warn(ctrl->device, "qid %d: authentication failed\n", q); @@ -967,6 +1089,7 @@ int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl) chap = &ctrl->dhchap_ctxs[i]; chap->qid = i; chap->ctrl = ctrl; + chap->authenticated = false; INIT_WORK(&chap->auth_work, nvme_queue_auth_work); } diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index 2b9e6cfaf2a8..1a0058be5821 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -145,7 +145,7 @@ static const char * const nvme_statuses[] = { [NVME_SC_BAD_ATTRIBUTES] = "Conflicting Attributes", [NVME_SC_INVALID_PI] = "Invalid Protection Information", [NVME_SC_READ_ONLY] = "Attempted Write to Read Only Range", - [NVME_SC_ONCS_NOT_SUPPORTED] = "ONCS Not Supported", + [NVME_SC_CMD_SIZE_LIM_EXCEEDED ] = "Command Size Limits Exceeded", [NVME_SC_ZONE_BOUNDARY_ERROR] = "Zoned Boundary Error", [NVME_SC_ZONE_FULL] = "Zone Is Full", [NVME_SC_ZONE_READ_ONLY] = "Zone Is Read Only", diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 818d4e49aab5..e533d791955d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -38,6 +38,8 @@ struct nvme_ns_info { u32 nsid; __le32 anagrpid; u8 pi_offset; + u16 endgid; + u64 runs; bool is_shared; bool is_readonly; bool is_ready; @@ -150,6 +152,8 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, unsigned nsid); static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, struct nvme_command *cmd); +static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, + u8 lsp, u8 csi, void *log, size_t size, u64 offset, u16 lsi); void nvme_queue_scan(struct nvme_ctrl *ctrl) { @@ -286,7 +290,6 @@ static blk_status_t nvme_error_status(u16 status) case NVME_SC_NS_NOT_READY: return BLK_STS_TARGET; case NVME_SC_BAD_ATTRIBUTES: - case NVME_SC_ONCS_NOT_SUPPORTED: case NVME_SC_INVALID_OPCODE: case NVME_SC_INVALID_FIELD: case NVME_SC_INVALID_NS: @@ -431,6 +434,12 @@ static inline void nvme_end_req_zoned(struct request *req) static inline void __nvme_end_req(struct request *req) { + 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_zoned(req); nvme_trace_bio_complete(req); if (req->cmd_flags & REQ_NVME_MPATH) @@ -441,12 +450,6 @@ 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); } @@ -564,8 +567,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { - case NVME_CTRL_NEW: - case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: changed = true; fallthrough; @@ -666,10 +667,11 @@ static void nvme_free_ns_head(struct kref *ref) struct nvme_ns_head *head = container_of(ref, struct nvme_ns_head, ref); - nvme_mpath_remove_disk(head); + nvme_mpath_put_disk(head); ida_free(&head->subsys->ns_ida, head->instance); cleanup_srcu_struct(&head->srcu); nvme_put_subsystem(head->subsys); + kfree(head->plids); kfree(head); } @@ -993,6 +995,18 @@ 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 (op == nvme_cmd_write && ns->head->nr_plids) { + u16 write_stream = req->bio->bi_write_stream; + + if (WARN_ON_ONCE(write_stream > ns->head->nr_plids)) + return BLK_STS_INVAL; + + if (write_stream) { + dsmgmt |= ns->head->plids[write_stream - 1] << 16; + control |= NVME_RW_DTYPE_DPLCMT; + } + } + if (req->cmd_flags & REQ_ATOMIC && !nvme_valid_atomic_write(req)) return BLK_STS_INVAL; @@ -1012,7 +1026,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, if (ns->head->ms) { /* - * If formated with metadata, the block layer always provides a + * If formatted with metadata, the block layer always provides a * metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled. Else * we enable the PRACT bit for protection information or set the * namespace capacity to zero to prevent any I/O. @@ -1159,7 +1173,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, req->cmd_flags &= ~REQ_FAILFAST_DRIVER; if (buffer && bufflen) { - ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); + ret = blk_rq_map_kern(req, buffer, bufflen, GFP_KERNEL); if (ret) goto out; } @@ -1611,6 +1625,7 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl, info->is_shared = id->nmic & NVME_NS_NMIC_SHARED; info->is_readonly = id->nsattr & NVME_NS_ATTR_RO; info->is_ready = true; + info->endgid = le16_to_cpu(id->endgid); if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { dev_info(ctrl->device, "Ignoring bogus Namespace Identifiers\n"); @@ -1651,6 +1666,7 @@ static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl, info->is_ready = id->nstat & NVME_NSTAT_NRDY; info->is_rotational = id->nsfeat & NVME_NS_ROTATIONAL; info->no_vwc = id->nsfeat & NVME_NS_VWC_NOT_PRESENT; + info->endgid = le16_to_cpu(id->endgid); } kfree(id); return ret; @@ -1676,7 +1692,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, - u32 *result) + void *result) { return nvme_features(dev, nvme_admin_set_features, fid, dword11, buffer, buflen, result); @@ -1685,7 +1701,7 @@ EXPORT_SYMBOL_GPL(nvme_set_features); int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, - u32 *result) + void *result) { return nvme_features(dev, nvme_admin_get_features, fid, dword11, buffer, buflen, result); @@ -1999,21 +2015,41 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, } -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) +static u32 nvme_configure_atomic_write(struct nvme_ns *ns, + struct nvme_id_ns *id, struct queue_limits *lim, u32 bs) { - unsigned int boundary = 0; + u32 atomic_bs, boundary = 0; + + /* + * We do not support an offset for the atomic boundaries. + */ + if (id->nabo) + return bs; - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) { - if (le16_to_cpu(id->nabspf)) + if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) { + /* + * Use the per-namespace atomic write unit when available. + */ + atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; + if (id->nabspf) boundary = (le16_to_cpu(id->nabspf) + 1) * bs; + } else { + /* + * Use the controller wide atomic write unit. This sucks + * because the limit is defined in terms of logical blocks while + * namespaces can have different formats, and because there is + * no clear language in the specification prohibiting different + * values for different controllers in the subsystem. + */ + atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; } + lim->atomic_write_hw_max = atomic_bs; lim->atomic_write_hw_boundary = boundary; lim->atomic_write_hw_unit_min = bs; lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs); lim->features |= BLK_FEAT_ATOMIC_WRITES; + return atomic_bs; } static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl) @@ -2051,20 +2087,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, valid = false; } - atomic_bs = phys_bs = bs; - if (id->nabo == 0) { - /* - * Bit 1 indicates whether NAWUPF is defined for this namespace - * and whether it should be used instead of AWUPF. If NAWUPF == - * 0 then AWUPF must be used instead. - */ - if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) - 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); - } + phys_bs = bs; + atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs); if (id->nsfeat & NVME_NS_FEAT_IO_OPT) { /* NPWG = Namespace Preferred Write Granularity */ @@ -2155,6 +2179,148 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns, return ret; } +static int nvme_query_fdp_granularity(struct nvme_ctrl *ctrl, + struct nvme_ns_info *info, u8 fdp_idx) +{ + struct nvme_fdp_config_log hdr, *h; + struct nvme_fdp_config_desc *desc; + size_t size = sizeof(hdr); + void *log, *end; + int i, n, ret; + + ret = nvme_get_log_lsi(ctrl, 0, NVME_LOG_FDP_CONFIGS, 0, + NVME_CSI_NVM, &hdr, size, 0, info->endgid); + if (ret) { + dev_warn(ctrl->device, + "FDP configs log header status:0x%x endgid:%d\n", ret, + info->endgid); + return ret; + } + + size = le32_to_cpu(hdr.sze); + if (size > PAGE_SIZE * MAX_ORDER_NR_PAGES) { + dev_warn(ctrl->device, "FDP config size too large:%zu\n", + size); + return 0; + } + + h = kvmalloc(size, GFP_KERNEL); + if (!h) + return -ENOMEM; + + ret = nvme_get_log_lsi(ctrl, 0, NVME_LOG_FDP_CONFIGS, 0, + NVME_CSI_NVM, h, size, 0, info->endgid); + if (ret) { + dev_warn(ctrl->device, + "FDP configs log status:0x%x endgid:%d\n", ret, + info->endgid); + goto out; + } + + n = le16_to_cpu(h->numfdpc) + 1; + if (fdp_idx > n) { + dev_warn(ctrl->device, "FDP index:%d out of range:%d\n", + fdp_idx, n); + /* Proceed without registering FDP streams */ + ret = 0; + goto out; + } + + log = h + 1; + desc = log; + end = log + size - sizeof(*h); + for (i = 0; i < fdp_idx; i++) { + log += le16_to_cpu(desc->dsze); + desc = log; + if (log >= end) { + dev_warn(ctrl->device, + "FDP invalid config descriptor list\n"); + ret = 0; + goto out; + } + } + + if (le32_to_cpu(desc->nrg) > 1) { + dev_warn(ctrl->device, "FDP NRG > 1 not supported\n"); + ret = 0; + goto out; + } + + info->runs = le64_to_cpu(desc->runs); +out: + kvfree(h); + return ret; +} + +static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info) +{ + struct nvme_ns_head *head = ns->head; + struct nvme_ctrl *ctrl = ns->ctrl; + struct nvme_fdp_ruh_status *ruhs; + struct nvme_fdp_config fdp; + struct nvme_command c = {}; + size_t size; + int i, ret; + + /* + * The FDP configuration is static for the lifetime of the namespace, + * so return immediately if we've already registered this namespace's + * streams. + */ + if (head->nr_plids) + return 0; + + ret = nvme_get_features(ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0, + &fdp); + if (ret) { + dev_warn(ctrl->device, "FDP get feature status:0x%x\n", ret); + return ret; + } + + if (!(fdp.flags & FDPCFG_FDPE)) + return 0; + + ret = nvme_query_fdp_granularity(ctrl, info, fdp.fdpcidx); + if (!info->runs) + return ret; + + size = struct_size(ruhs, ruhsd, S8_MAX - 1); + ruhs = kzalloc(size, GFP_KERNEL); + if (!ruhs) + return -ENOMEM; + + c.imr.opcode = nvme_cmd_io_mgmt_recv; + c.imr.nsid = cpu_to_le32(head->ns_id); + c.imr.mo = NVME_IO_MGMT_RECV_MO_RUHS; + c.imr.numd = cpu_to_le32(nvme_bytes_to_numd(size)); + ret = nvme_submit_sync_cmd(ns->queue, &c, ruhs, size); + if (ret) { + dev_warn(ctrl->device, "FDP io-mgmt status:0x%x\n", ret); + goto free; + } + + head->nr_plids = le16_to_cpu(ruhs->nruhsd); + if (!head->nr_plids) + goto free; + + head->plids = kcalloc(head->nr_plids, sizeof(*head->plids), + GFP_KERNEL); + if (!head->plids) { + dev_warn(ctrl->device, + "failed to allocate %u FDP placement IDs\n", + head->nr_plids); + head->nr_plids = 0; + ret = -ENOMEM; + goto free; + } + + for (i = 0; i < head->nr_plids; i++) + head->plids[i] = le16_to_cpu(ruhs->ruhsd[i].pid); +free: + kfree(ruhs); + return ret; +} + static int nvme_update_ns_info_block(struct nvme_ns *ns, struct nvme_ns_info *info) { @@ -2192,6 +2358,12 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, goto out; } + if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) { + ret = nvme_query_fdp_info(ns, info); + if (ret < 0) + goto out; + } + lim = queue_limits_start_update(ns->disk->queue); memflags = blk_mq_freeze_queue(ns->disk->queue); @@ -2203,6 +2375,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, 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) @@ -2225,6 +2398,12 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (!nvme_init_integrity(ns->head, &lim, info)) capacity = 0; + lim.max_write_streams = ns->head->nr_plids; + if (lim.max_write_streams) + lim.write_stream_granularity = min(info->runs, U32_MAX); + else + lim.write_stream_granularity = 0; + ret = queue_limits_commit_update(ns->disk->queue, &lim); if (ret) { blk_mq_unfreeze_queue(ns->disk->queue, memflags); @@ -2328,6 +2507,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) ns->head->disk->flags |= GENHD_FL_HIDDEN; else nvme_init_integrity(ns->head, &lim, info); + lim.max_write_streams = ns_lim->max_write_streams; + lim.write_stream_granularity = ns_lim->write_stream_granularity; ret = queue_limits_commit_update(ns->head->disk->queue, &lim); set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk)); @@ -3018,6 +3199,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) memcpy(subsys->model, id->mn, sizeof(subsys->model)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; + subsys->awupf = le16_to_cpu(id->awupf); /* Versions prior to 1.4 don't necessarily report a valid type */ if (id->cntrltype == NVME_CTRL_DISC || @@ -3033,7 +3215,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) kfree(subsys); return -EINVAL; } - subsys->awupf = le16_to_cpu(id->awupf); nvme_mpath_default_iopolicy(subsys); subsys->dev.class = &nvme_subsys_class; @@ -3086,8 +3267,8 @@ out_unlock: return ret; } -int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, - void *log, size_t size, u64 offset) +static int nvme_get_log_lsi(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, + u8 lsp, u8 csi, void *log, size_t size, u64 offset, u16 lsi) { struct nvme_command c = { }; u32 dwlen = nvme_bytes_to_numd(size); @@ -3101,10 +3282,18 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset)); c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset)); c.get_log_page.csi = csi; + c.get_log_page.lsi = cpu_to_le16(lsi); return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size); } +int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, + void *log, size_t size, u64 offset) +{ + return nvme_get_log_lsi(ctrl, nsid, log_page, lsp, csi, log, size, + offset, 0); +} + static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, struct nvme_effects_log **log) { @@ -3348,6 +3537,15 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret) goto out_free; } + + if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) { + dev_err_ratelimited(ctrl->device, + "inconsistent AWUPF, controller not added (%u/%u).\n", + le16_to_cpu(id->awupf), ctrl->subsys->awupf); + ret = -EINVAL; + goto out_free; + } + memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); @@ -3443,7 +3641,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) dev_pm_qos_expose_latency_tolerance(ctrl->device); else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - out_free: kfree(id); return ret; @@ -3562,7 +3759,7 @@ static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl, */ if (h->ns_id != nsid || !nvme_is_unique_nsid(ctrl, h)) continue; - if (!list_empty(&h->list) && nvme_tryget_ns_head(h)) + if (nvme_tryget_ns_head(h)) return h; } @@ -3806,7 +4003,8 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) } } else { ret = -EINVAL; - if (!info->is_shared || !head->shared) { + if ((!info->is_shared || !head->shared) && + !list_empty(&head->list)) { dev_err(ctrl->device, "Duplicate unshared namespace %d\n", info->nsid); @@ -3824,13 +4022,17 @@ 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"); + "Shared namespace support requires core_nvme.multipath=Y.\n"); } } list_add_tail_rcu(&ns->siblings, &head->list); ns->head = head; mutex_unlock(&ctrl->subsys->lock); + +#ifdef CONFIG_NVME_MULTIPATH + cancel_delayed_work(&head->remove_work); +#endif return 0; out_put_ns_head: @@ -4010,7 +4212,8 @@ static void nvme_ns_remove(struct nvme_ns *ns) mutex_lock(&ns->ctrl->subsys->lock); list_del_rcu(&ns->siblings); if (list_empty(&ns->head->list)) { - list_del_init(&ns->head->entry); + if (!nvme_mpath_queue_if_no_path(ns->head)) + list_del_init(&ns->head->entry); last_path = true; } mutex_unlock(&ns->ctrl->subsys->lock); @@ -4020,6 +4223,9 @@ static void nvme_ns_remove(struct nvme_ns *ns) if (!nvme_ns_head_multipath(ns->head)) nvme_cdev_del(&ns->cdev, &ns->cdev_device); + + nvme_mpath_remove_sysfs_link(ns); + del_gendisk(ns->disk); mutex_lock(&ns->ctrl->namespaces_lock); @@ -4028,7 +4234,7 @@ static void nvme_ns_remove(struct nvme_ns *ns) synchronize_srcu(&ns->ctrl->srcu); if (last_path) - nvme_mpath_shutdown_disk(ns->head); + nvme_mpath_remove_disk(ns->head); nvme_put_ns(ns); } @@ -4294,6 +4500,15 @@ static void nvme_scan_work(struct work_struct *work) nvme_scan_ns_sequential(ctrl); } mutex_unlock(&ctrl->scan_lock); + + /* Requeue if we have missed AENs */ + if (test_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) + nvme_queue_scan(ctrl); +#ifdef CONFIG_NVME_MULTIPATH + else if (ctrl->ana_log_buf) + /* Re-read the ANA log page to not miss updates */ + queue_work(nvme_wq, &ctrl->ana_work); +#endif } /* @@ -4468,11 +4683,9 @@ static void nvme_fw_act_work(struct work_struct *work) nvme_auth_stop(ctrl); if (ctrl->mtfa) - fw_act_timeout = jiffies + - msecs_to_jiffies(ctrl->mtfa * 100); + fw_act_timeout = jiffies + msecs_to_jiffies(ctrl->mtfa * 100); else - fw_act_timeout = jiffies + - msecs_to_jiffies(admin_timeout * 1000); + fw_act_timeout = jiffies + secs_to_jiffies(admin_timeout); nvme_quiesce_io_queues(ctrl); while (nvme_ctrl_pp_status(ctrl)) { @@ -4485,7 +4698,8 @@ static void nvme_fw_act_work(struct work_struct *work) msleep(100); } - if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) || + !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) return; nvme_unquiesce_io_queues(ctrl); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 432efcbf9e2f..2e58a7ce1090 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -472,8 +472,9 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) result = le32_to_cpu(res.u32); ctrl->cntlid = result & 0xFFFF; if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) { - /* Secure concatenation is not implemented */ - if (result & NVME_CONNECT_AUTHREQ_ASCR) { + /* Check for secure concatenation */ + if ((result & NVME_CONNECT_AUTHREQ_ASCR) && + !ctrl->opts->concat) { dev_warn(ctrl->device, "qid 0: secure concatenation is not supported\n"); ret = -EOPNOTSUPP; @@ -550,7 +551,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) /* Secure concatenation is not implemented */ if (result & NVME_CONNECT_AUTHREQ_ASCR) { dev_warn(ctrl->device, - "qid 0: secure concatenation is not supported\n"); + "qid %d: secure concatenation is not supported\n", qid); ret = -EOPNOTSUPP; goto out_free_data; } @@ -581,7 +582,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue); * 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. + * attempts with the same set of parameters should be attempted. * * - when the authentication attempt fails, because the key was invalid. * This error code is set on the host side. @@ -706,6 +707,7 @@ static const match_table_t opt_tokens = { #endif #ifdef CONFIG_NVME_TCP_TLS { NVMF_OPT_TLS, "tls" }, + { NVMF_OPT_CONCAT, "concat" }, #endif { NVMF_OPT_ERR, NULL } }; @@ -735,6 +737,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->tls = false; opts->tls_key = NULL; opts->keyring = NULL; + opts->concat = false; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -1053,6 +1056,14 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } opts->tls = true; break; + case NVMF_OPT_CONCAT: + if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) { + pr_err("TLS is not supported\n"); + ret = -EINVAL; + goto out; + } + opts->concat = true; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); @@ -1079,6 +1090,23 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, pr_warn("failfast tmo (%d) larger than controller loss tmo (%d)\n", opts->fast_io_fail_tmo, ctrl_loss_tmo); } + if (opts->concat) { + if (opts->tls) { + pr_err("Secure concatenation over TLS is not supported\n"); + ret = -EINVAL; + goto out; + } + if (opts->tls_key) { + pr_err("Cannot specify a TLS key for secure concatenation\n"); + ret = -EINVAL; + goto out; + } + if (!opts->dhchap_secret) { + pr_err("Need to enable DH-CHAP for secure concatenation\n"); + ret = -EINVAL; + goto out; + } + } opts->host = nvmf_host_add(hostnqn, &hostid); if (IS_ERR(opts->host)) { diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 21d75dc4a3a0..1b58ee7d0dce 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -66,6 +66,7 @@ enum { NVMF_OPT_TLS = 1 << 25, NVMF_OPT_KEYRING = 1 << 26, NVMF_OPT_TLS_KEY = 1 << 27, + NVMF_OPT_CONCAT = 1 << 28, }; /** @@ -79,7 +80,7 @@ enum { * @transport: Holds the fabric transport "technology name" (for a lack of * better description) that will be used by an NVMe controller * being added. - * @subsysnqn: Hold the fully qualified NQN subystem name (format defined + * @subsysnqn: Hold the fully qualified NQN subsystem name (format defined * in the NVMe specification, "NVMe Qualified Names"). * @traddr: The transport-specific TRADDR field for a port on the * subsystem which is adding a controller. @@ -101,6 +102,7 @@ enum { * @keyring: Keyring to use for key lookups * @tls_key: TLS key for encrypted connections (TCP) * @tls: Start TLS encrypted connections (TCP) + * @concat: Enabled Secure channel concatenation (TCP) * @disable_sqflow: disable controller sq flow control * @hdr_digest: generate/verify header digest (TCP) * @data_digest: generate/verify data digest (TCP) @@ -130,6 +132,7 @@ struct nvmf_ctrl_options { struct key *keyring; struct key *tls_key; bool tls; + bool concat; bool disable_sqflow; bool hdr_digest; bool data_digest; @@ -153,7 +156,7 @@ struct nvmf_ctrl_options { * @create_ctrl(): function pointer that points to a non-NVMe * implementation-specific fabric technology * that would go into starting up that fabric - * for the purpose of conneciton to an NVMe controller + * for the purpose of connection to an NVMe controller * using that fabric technology. * * Notes: @@ -162,7 +165,7 @@ struct nvmf_ctrl_options { * 2. create_ctrl() must be defined (even if it does nothing) * 3. struct nvmf_transport_ops must be statically allocated in the * modules .bss section so that a pure module_get on @module - * prevents the memory from beeing freed. + * prevents the memory from being freed. */ struct nvmf_transport_ops { struct list_head entry; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index f4f1866fbd5b..014b387f1e8b 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -781,61 +781,12 @@ restart: static void nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) { - enum nvme_ctrl_state state; - unsigned long flags; - dev_info(ctrl->ctrl.device, "NVME-FC{%d}: controller connectivity lost. Awaiting " "Reconnect", ctrl->cnum); - spin_lock_irqsave(&ctrl->lock, flags); set_bit(ASSOC_FAILED, &ctrl->flags); - state = nvme_ctrl_state(&ctrl->ctrl); - spin_unlock_irqrestore(&ctrl->lock, flags); - - switch (state) { - case NVME_CTRL_NEW: - case NVME_CTRL_LIVE: - /* - * Schedule a controller reset. The reset will terminate the - * association and schedule the reconnect timer. Reconnects - * will be attempted until either the ctlr_loss_tmo - * (max_retries * connect_delay) expires or the remoteport's - * dev_loss_tmo expires. - */ - if (nvme_reset_ctrl(&ctrl->ctrl)) { - dev_warn(ctrl->ctrl.device, - "NVME-FC{%d}: Couldn't schedule reset.\n", - ctrl->cnum); - nvme_delete_ctrl(&ctrl->ctrl); - } - break; - - case NVME_CTRL_CONNECTING: - /* - * The association has already been terminated and the - * controller is attempting reconnects. No need to do anything - * futher. Reconnects will be attempted until either the - * ctlr_loss_tmo (max_retries * connect_delay) expires or the - * remoteport's dev_loss_tmo expires. - */ - break; - - case NVME_CTRL_RESETTING: - /* - * Controller is already in the process of terminating the - * association. No need to do anything further. The reconnect - * step will kick in naturally after the association is - * terminated. - */ - break; - - case NVME_CTRL_DELETING: - case NVME_CTRL_DELETING_NOIO: - default: - /* no action to take - let it delete */ - break; - } + nvme_reset_ctrl(&ctrl->ctrl); } /** @@ -1459,9 +1410,8 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl) } static void -nvme_fc_xmt_ls_rsp_done(struct nvmefc_ls_rsp *lsrsp) +nvme_fc_xmt_ls_rsp_free(struct nvmefc_ls_rcv_op *lsop) { - struct nvmefc_ls_rcv_op *lsop = lsrsp->nvme_fc_private; struct nvme_fc_rport *rport = lsop->rport; struct nvme_fc_lport *lport = rport->lport; unsigned long flags; @@ -1483,6 +1433,14 @@ nvme_fc_xmt_ls_rsp_done(struct nvmefc_ls_rsp *lsrsp) } static void +nvme_fc_xmt_ls_rsp_done(struct nvmefc_ls_rsp *lsrsp) +{ + struct nvmefc_ls_rcv_op *lsop = lsrsp->nvme_fc_private; + + nvme_fc_xmt_ls_rsp_free(lsop); +} + +static void nvme_fc_xmt_ls_rsp(struct nvmefc_ls_rcv_op *lsop) { struct nvme_fc_rport *rport = lsop->rport; @@ -1499,7 +1457,7 @@ nvme_fc_xmt_ls_rsp(struct nvmefc_ls_rcv_op *lsop) dev_warn(lport->dev, "LLDD rejected LS RSP xmt: LS %d status %d\n", w0->ls_cmd, ret); - nvme_fc_xmt_ls_rsp_done(lsop->lsrsp); + nvme_fc_xmt_ls_rsp_free(lsop); return; } } @@ -1997,7 +1955,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) } /* - * For the linux implementation, if we have an unsuccesful + * For the linux implementation, if we have an unsucceesful * status, they blk-mq layer can typically be called with the * non-zero status and the content of the cqe isn't important. */ @@ -2521,7 +2479,7 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues) * writing the registers for shutdown and polling (call * nvme_disable_ctrl()). Given a bunch of i/o was potentially * just aborted and we will wait on those contexts, and given - * there was no indication of how live the controlelr is on the + * there was no indication of how live the controller is on the * link, don't send more io to create more contexts for the * shutdown. Let the controller fail via keepalive failure if * its still present. @@ -2620,7 +2578,7 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq, if (ret) return -ENOMEM; - op->nents = blk_rq_map_sg(rq->q, rq, freq->sg_table.sgl); + op->nents = blk_rq_map_sg(rq, freq->sg_table.sgl); WARN_ON(op->nents > blk_rq_nr_phys_segments(rq)); freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl, op->nents, rq_dma_dir(rq)); @@ -2907,7 +2865,7 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) unsigned int nr_io_queues; int ret; - nr_io_queues = min(min(opts->nr_io_queues, num_online_cpus()), + nr_io_queues = min3(opts->nr_io_queues, num_online_cpus(), ctrl->lport->ops->max_hw_queues); ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) { @@ -2961,7 +2919,7 @@ nvme_fc_recreate_io_queues(struct nvme_fc_ctrl *ctrl) unsigned int nr_io_queues; int ret; - nr_io_queues = min(min(opts->nr_io_queues, num_online_cpus()), + nr_io_queues = min3(opts->nr_io_queues, num_online_cpus(), ctrl->lport->ops->max_hw_queues); ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) { @@ -3071,7 +3029,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) struct nvmefc_ls_rcv_op *disls = NULL; unsigned long flags; int ret; - bool changed; ++ctrl->ctrl.nr_reconnects; @@ -3177,23 +3134,18 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) else ret = nvme_fc_recreate_io_queues(ctrl); } + if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) + ret = -EIO; if (ret) goto out_term_aen_ops; - spin_lock_irqsave(&ctrl->lock, flags); - if (!test_bit(ASSOC_FAILED, &ctrl->flags)) - changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - else + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) { ret = -EIO; - spin_unlock_irqrestore(&ctrl->lock, flags); - - if (ret) goto out_term_aen_ops; + } ctrl->ctrl.nr_reconnects = 0; - - if (changed) - nvme_start_ctrl(&ctrl->ctrl); + nvme_start_ctrl(&ctrl->ctrl); return 0; /* Success */ diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index e8930146847a..6b3ac8ae3f34 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -114,7 +114,7 @@ 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, - struct io_uring_cmd *ioucmd, unsigned int flags) + struct iov_iter *iter, unsigned int flags) { struct request_queue *q = req->q; struct nvme_ns *ns = q->queuedata; @@ -130,30 +130,21 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, if (has_metadata) { if (!supports_metadata) return -EINVAL; + if (!nvme_ctrl_meta_sgl_supported(ctrl)) dev_warn_once(ctrl->device, "using unchecked metadata buffer\n"); } - if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) { - struct iov_iter iter; - - /* fixedbufs is only for non-vectored io */ - if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC)) - return -EINVAL; - ret = io_uring_cmd_import_fixed(ubuffer, bufflen, - rq_data_dir(req), &iter, ioucmd); - if (ret < 0) - goto out; - ret = blk_rq_map_user_iov(q, req, NULL, &iter, GFP_KERNEL); - } else { + if (iter) + ret = blk_rq_map_user_iov(q, req, NULL, iter, GFP_KERNEL); + else ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer), bufflen, GFP_KERNEL, flags & NVME_IOCTL_VEC, 0, 0, rq_data_dir(req)); - } if (ret) - goto out; + return ret; bio = req->bio; if (bdev) @@ -170,8 +161,6 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, out_unmap: if (bio) blk_rq_unmap_user(bio); -out: - blk_mq_free_request(req); return ret; } @@ -196,7 +185,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer, meta_len, NULL, flags); if (ret) - return ret; + goto out_free_req; } bio = req->bio; @@ -212,7 +201,10 @@ static int nvme_submit_user_cmd(struct request_queue *q, if (effects) nvme_passthru_end(ctrl, ns, effects, cmd, ret); + return ret; +out_free_req: + blk_mq_free_request(req); return ret; } @@ -283,8 +275,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, { if (ns && nsid != ns->head->ns_id) { dev_err(ctrl->device, - "%s: nsid (%u) in cmd does not match nsid (%u)" - "of namespace\n", + "%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n", current->comm, nsid, ns->head->ns_id); return false; } @@ -438,21 +429,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, pdu->result = le64_to_cpu(nvme_req(req)->result.u64); /* - * 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. + * IOPOLL could potentially complete this request directly, but + * if multiple rings are polling on the same queue, then it's possible + * for one ring to find completions for another ring. Punting the + * completion via task_work will always direct it to the right + * location, rather than potentially complete requests for ringA + * under iopoll invocations from ringB. */ - if (blk_rq_is_poll(req)) { - if (pdu->bio) - blk_rq_unmap_user(pdu->bio); - io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status); - } else { - io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); - } - + io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); return RQ_END_IO_FREE; } @@ -464,6 +448,8 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct request_queue *q = ns ? ns->queue : ctrl->admin_q; struct nvme_uring_data d; struct nvme_command c; + struct iov_iter iter; + struct iov_iter *map_iter = NULL; struct request *req; blk_opf_t rq_flags = REQ_ALLOC_CACHE; blk_mq_req_flags_t blk_flags = 0; @@ -499,6 +485,22 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, d.metadata_len = READ_ONCE(cmd->metadata_len); d.timeout_ms = READ_ONCE(cmd->timeout_ms); + if (d.data_len && (ioucmd->flags & IORING_URING_CMD_FIXED)) { + int ddir = nvme_is_write(&c) ? WRITE : READ; + + if (vec) + ret = io_uring_cmd_import_fixed_vec(ioucmd, + u64_to_user_ptr(d.addr), d.data_len, + ddir, &iter, issue_flags); + else + ret = io_uring_cmd_import_fixed(d.addr, d.data_len, + ddir, &iter, ioucmd, issue_flags); + if (ret < 0) + return ret; + + map_iter = &iter; + } + if (issue_flags & IO_URING_F_NONBLOCK) { rq_flags |= REQ_NOWAIT; blk_flags = BLK_MQ_REQ_NOWAIT; @@ -511,12 +513,12 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return PTR_ERR(req); req->timeout = d.timeout_ms ? msecs_to_jiffies(d.timeout_ms) : 0; - 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, ioucmd, vec); + if (d.data_len) { + ret = nvme_map_user_request(req, d.addr, d.data_len, + nvme_to_user_ptr(d.metadata), d.metadata_len, + map_iter, vec ? NVME_IOCTL_VEC : 0); if (ret) - return ret; + goto out_free_req; } /* to free bio on completion, as req->bio will be null at that time */ @@ -526,6 +528,10 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, req->end_io = nvme_uring_cmd_end_io; blk_execute_rq_nowait(req, false); return -EIOCBQUEUED; + +out_free_req: + blk_mq_free_request(req); + return ret; } static bool is_ctrl_ioctl(unsigned int cmd) @@ -716,7 +722,7 @@ int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode, /* * Handle ioctls that apply to the controller instead of the namespace - * seperately and drop the ns SRCU reference early. This avoids a + * separately and drop the ns SRCU reference early. This avoids a * deadlock when deleting namespaces using the passthrough interface. */ if (is_ctrl_ioctl(cmd)) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 2a7635565083..316a269842fa 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -10,10 +10,61 @@ #include "nvme.h" bool multipath = true; -module_param(multipath, bool, 0444); +static bool multipath_always_on; + +static int multipath_param_set(const char *val, const struct kernel_param *kp) +{ + int ret; + bool *arg = kp->arg; + + ret = param_set_bool(val, kp); + if (ret) + return ret; + + if (multipath_always_on && !*arg) { + pr_err("Can't disable multipath when multipath_always_on is configured.\n"); + *arg = true; + return -EINVAL; + } + + return 0; +} + +static const struct kernel_param_ops multipath_param_ops = { + .set = multipath_param_set, + .get = param_get_bool, +}; + +module_param_cb(multipath, &multipath_param_ops, &multipath, 0444); MODULE_PARM_DESC(multipath, "turn on native support for multiple controllers per subsystem"); +static int multipath_always_on_set(const char *val, + const struct kernel_param *kp) +{ + int ret; + bool *arg = kp->arg; + + ret = param_set_bool(val, kp); + if (ret < 0) + return ret; + + if (*arg) + multipath = true; + + return 0; +} + +static const struct kernel_param_ops multipath_always_on_ops = { + .set = multipath_always_on_set, + .get = param_get_bool, +}; + +module_param_cb(multipath_always_on, &multipath_always_on_ops, + &multipath_always_on, 0444); +MODULE_PARM_DESC(multipath_always_on, + "create multipath node always except for private namespace with non-unique nsid; note that this also implicitly enables native multipath support"); + static const char *nvme_iopolicy_names[] = { [NVME_IOPOLICY_NUMA] = "numa", [NVME_IOPOLICY_RR] = "round-robin", @@ -427,7 +478,7 @@ 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; + return false; list_for_each_entry_srcu(ns, &head->list, siblings, srcu_read_lock_held(&head->srcu)) { @@ -442,7 +493,17 @@ static bool nvme_available_path(struct nvme_ns_head *head) break; } } - return false; + + /* + * If "head->delayed_removal_secs" is configured (i.e., non-zero), do + * not immediately fail I/O. Instead, requeue the I/O for the configured + * duration, anticipating that if there's a transient link failure then + * it may recover within this time window. This parameter is exported to + * userspace via sysfs, and its default value is zero. It is internally + * mapped to NVME_NSHEAD_QUEUE_IF_NO_PATH. When delayed_removal_secs is + * non-zero, this flag is set to true. When zero, the flag is cleared. + */ + return nvme_mpath_queue_if_no_path(head); } static void nvme_ns_head_submit_bio(struct bio *bio) @@ -617,6 +678,40 @@ static void nvme_requeue_work(struct work_struct *work) } } +static void nvme_remove_head(struct nvme_ns_head *head) +{ + if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { + /* + * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared + * to allow multipath to fail all I/O. + */ + kblockd_schedule_work(&head->requeue_work); + + nvme_cdev_del(&head->cdev, &head->cdev_device); + synchronize_srcu(&head->srcu); + del_gendisk(head->disk); + nvme_put_ns_head(head); + } +} + +static void nvme_remove_head_work(struct work_struct *work) +{ + struct nvme_ns_head *head = container_of(to_delayed_work(work), + struct nvme_ns_head, remove_work); + bool remove = false; + + mutex_lock(&head->subsys->lock); + if (list_empty(&head->list)) { + list_del_init(&head->entry); + remove = true; + } + mutex_unlock(&head->subsys->lock); + if (remove) + nvme_remove_head(head); + + module_put(THIS_MODULE); +} + int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) { struct queue_limits lim; @@ -626,19 +721,31 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) spin_lock_init(&head->requeue_lock); INIT_WORK(&head->requeue_work, nvme_requeue_work); INIT_WORK(&head->partition_scan_work, nvme_partition_scan_work); + INIT_DELAYED_WORK(&head->remove_work, nvme_remove_head_work); + head->delayed_removal_secs = 0; /* - * Add a multipath node if the subsystems supports multiple controllers. - * We also do this for private namespaces as the namespace sharing flag - * could change after a rescan. + * If "multipath_always_on" is enabled, a multipath node is added + * regardless of whether the disk is single/multi ported, and whether + * the namespace is shared or private. If "multipath_always_on" is not + * enabled, a multipath node is added only if the subsystem supports + * multiple controllers and the "multipath" option is configured. In + * either case, for private namespaces, we ensure that the NSID is + * unique. */ - if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || - !nvme_is_unique_nsid(ctrl, head) || !multipath) + if (!multipath_always_on) { + if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || + !multipath) + return 0; + } + + if (!nvme_is_unique_nsid(ctrl, head)) return 0; blk_set_stacking_limits(&lim); lim.dma_alignment = 3; - lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL; + lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | + BLK_FEAT_POLL | BLK_FEAT_ATOMIC_WRITES; if (head->ids.csi == NVME_CSI_ZNS) lim.features |= BLK_FEAT_ZONED; @@ -653,12 +760,13 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) * controller's scan_work context. If a path error occurs here, the IO * will wait until a path becomes available or all paths are torn down, * but that action also occurs within scan_work, so it would deadlock. - * Defer the partion scan to a different context that does not block + * Defer the partition scan to a different context that does not block * scan_work. */ set_bit(GD_SUPPRESS_PART_SCAN, &head->disk->state); sprintf(head->disk->disk_name, "nvme%dn%d", ctrl->subsys->instance, head->instance); + nvme_tryget_ns_head(head); return 0; } @@ -686,6 +794,8 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) kblockd_schedule_work(&head->partition_scan_work); } + nvme_mpath_add_sysfs_link(ns->head); + mutex_lock(&head->lock); if (nvme_path_is_optimized(ns)) { int node, srcu_idx; @@ -768,6 +878,25 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, if (nvme_state_is_live(ns->ana_state) && nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE) nvme_mpath_set_live(ns); + else { + /* + * Add sysfs link from multipath head gendisk node to path + * device gendisk node. + * If path's ana state is live (i.e. state is either optimized + * or non-optimized) while we alloc the ns then sysfs link would + * be created from nvme_mpath_set_live(). In that case we would + * not fallthrough this code path. However for the path's ana + * state other than live, we call nvme_mpath_set_live() only + * after ana state transitioned to the live state. But we still + * want to create the sysfs link from head node to a path device + * irrespctive of the path's ana state. + * If we reach through here then it means that path's ana state + * is not live but still create the sysfs link to this path from + * head node if head node of the path has already come alive. + */ + if (test_bit(NVME_NSHEAD_DISK_LIVE, &ns->head->flags)) + nvme_mpath_add_sysfs_link(ns->head); + } } static int nvme_update_ana_state(struct nvme_ctrl *ctrl, @@ -839,7 +968,7 @@ static int nvme_read_ana_log(struct nvme_ctrl *ctrl) if (nr_change_groups) mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies); else - del_timer_sync(&ctrl->anatt_timer); + timer_delete_sync(&ctrl->anatt_timer); out_unlock: mutex_unlock(&ctrl->ana_lock); return error; @@ -869,7 +998,7 @@ void nvme_mpath_update(struct nvme_ctrl *ctrl) static void nvme_anatt_timeout(struct timer_list *t) { - struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer); + struct nvme_ctrl *ctrl = timer_container_of(ctrl, t, anatt_timer); dev_info(ctrl->device, "ANATT timeout, resetting controller.\n"); nvme_reset_ctrl(ctrl); @@ -879,7 +1008,7 @@ void nvme_mpath_stop(struct nvme_ctrl *ctrl) { if (!nvme_ctrl_use_ana(ctrl)) return; - del_timer_sync(&ctrl->anatt_timer); + timer_delete_sync(&ctrl->anatt_timer); cancel_work_sync(&ctrl->ana_work); } @@ -955,6 +1084,88 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr, } DEVICE_ATTR_RO(ana_state); +static ssize_t queue_depth_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); + + if (ns->head->subsys->iopolicy != NVME_IOPOLICY_QD) + return 0; + + return sysfs_emit(buf, "%d\n", atomic_read(&ns->ctrl->nr_active)); +} +DEVICE_ATTR_RO(queue_depth); + +static ssize_t numa_nodes_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int node, srcu_idx; + nodemask_t numa_nodes; + struct nvme_ns *current_ns; + struct nvme_ns *ns = nvme_get_ns_from_dev(dev); + struct nvme_ns_head *head = ns->head; + + if (head->subsys->iopolicy != NVME_IOPOLICY_NUMA) + return 0; + + nodes_clear(numa_nodes); + + srcu_idx = srcu_read_lock(&head->srcu); + for_each_node(node) { + current_ns = srcu_dereference(head->current_path[node], + &head->srcu); + if (ns == current_ns) + node_set(node, numa_nodes); + } + srcu_read_unlock(&head->srcu, srcu_idx); + + return sysfs_emit(buf, "%*pbl\n", nodemask_pr_args(&numa_nodes)); +} +DEVICE_ATTR_RO(numa_nodes); + +static ssize_t delayed_removal_secs_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + struct nvme_ns_head *head = disk->private_data; + int ret; + + mutex_lock(&head->subsys->lock); + ret = sysfs_emit(buf, "%u\n", head->delayed_removal_secs); + mutex_unlock(&head->subsys->lock); + return ret; +} + +static ssize_t delayed_removal_secs_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct gendisk *disk = dev_to_disk(dev); + struct nvme_ns_head *head = disk->private_data; + unsigned int sec; + int ret; + + ret = kstrtouint(buf, 0, &sec); + if (ret < 0) + return ret; + + mutex_lock(&head->subsys->lock); + head->delayed_removal_secs = sec; + if (sec) + set_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags); + else + clear_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags); + mutex_unlock(&head->subsys->lock); + /* + * Ensure that update to NVME_NSHEAD_QUEUE_IF_NO_PATH is seen + * by its reader. + */ + synchronize_srcu(&head->srcu); + + return count; +} + +DEVICE_ATTR_RW(delayed_removal_secs); + static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *desc, void *data) { @@ -967,6 +1178,84 @@ static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl, return -ENXIO; /* just break out of the loop */ } +void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head) +{ + struct device *target; + int rc, srcu_idx; + struct nvme_ns *ns; + struct kobject *kobj; + + /* + * Ensure head disk node is already added otherwise we may get invalid + * kobj for head disk node + */ + if (!test_bit(GD_ADDED, &head->disk->state)) + return; + + kobj = &disk_to_dev(head->disk)->kobj; + + /* + * loop through each ns chained through the head->list and create the + * sysfs link from head node to the ns path node + */ + srcu_idx = srcu_read_lock(&head->srcu); + + list_for_each_entry_rcu(ns, &head->list, siblings) { + /* + * Ensure that ns path disk node is already added otherwise we + * may get invalid kobj name for target + */ + if (!test_bit(GD_ADDED, &ns->disk->state)) + continue; + + /* + * Avoid creating link if it already exists for the given path. + * When path ana state transitions from optimized to non- + * optimized or vice-versa, the nvme_mpath_set_live() is + * invoked which in truns call this function. Now if the sysfs + * link already exists for the given path and we attempt to re- + * create the link then sysfs code would warn about it loudly. + * So we evaluate NVME_NS_SYSFS_ATTR_LINK flag here to ensure + * that we're not creating duplicate link. + * The test_and_set_bit() is used because it is protecting + * against multiple nvme paths being simultaneously added. + */ + if (test_and_set_bit(NVME_NS_SYSFS_ATTR_LINK, &ns->flags)) + continue; + + target = disk_to_dev(ns->disk); + /* + * Create sysfs link from head gendisk kobject @kobj to the + * ns path gendisk kobject @target->kobj. + */ + rc = sysfs_add_link_to_group(kobj, nvme_ns_mpath_attr_group.name, + &target->kobj, dev_name(target)); + if (unlikely(rc)) { + dev_err(disk_to_dev(ns->head->disk), + "failed to create link to %s\n", + dev_name(target)); + clear_bit(NVME_NS_SYSFS_ATTR_LINK, &ns->flags); + } + } + + srcu_read_unlock(&head->srcu, srcu_idx); +} + +void nvme_mpath_remove_sysfs_link(struct nvme_ns *ns) +{ + struct device *target; + struct kobject *kobj; + + if (!test_bit(NVME_NS_SYSFS_ATTR_LINK, &ns->flags)) + return; + + target = disk_to_dev(ns->disk); + kobj = &disk_to_dev(ns->head->disk)->kobj; + sysfs_remove_link_from_group(kobj, nvme_ns_mpath_attr_group.name, + dev_name(target)); + clear_bit(NVME_NS_SYSFS_ATTR_LINK, &ns->flags); +} + void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid) { if (nvme_ctrl_use_ana(ns->ctrl)) { @@ -998,23 +1287,43 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid) #endif } -void nvme_mpath_shutdown_disk(struct nvme_ns_head *head) +void nvme_mpath_remove_disk(struct nvme_ns_head *head) { - if (!head->disk) - return; - if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { - nvme_cdev_del(&head->cdev, &head->cdev_device); + bool remove = false; + + mutex_lock(&head->subsys->lock); + /* + * We are called when all paths have been removed, and at that point + * head->list is expected to be empty. However, nvme_remove_ns() and + * nvme_init_ns_head() can run concurrently and so if head->delayed_ + * removal_secs is configured, it is possible that by the time we reach + * this point, head->list may no longer be empty. Therefore, we recheck + * head->list here. If it is no longer empty then we skip enqueuing the + * delayed head removal work. + */ + if (!list_empty(&head->list)) + goto out; + + if (head->delayed_removal_secs) { /* - * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared - * to allow multipath to fail all I/O. + * Ensure that no one could remove this module while the head + * remove work is pending. */ - synchronize_srcu(&head->srcu); - kblockd_schedule_work(&head->requeue_work); - del_gendisk(head->disk); + if (!try_module_get(THIS_MODULE)) + goto out; + mod_delayed_work(nvme_wq, &head->remove_work, + head->delayed_removal_secs * HZ); + } else { + list_del_init(&head->entry); + remove = true; } +out: + mutex_unlock(&head->subsys->lock); + if (remove) + nvme_remove_head(head); } -void nvme_mpath_remove_disk(struct nvme_ns_head *head) +void nvme_mpath_put_disk(struct nvme_ns_head *head) { if (!head->disk) return; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 7be92d07430e..7df2ea21851f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -442,7 +442,7 @@ struct nvme_subsystem { u8 cmic; enum nvme_subsys_type subtype; u16 vendor_id; - u16 awupf; /* 0's based awupf value. */ + u16 awupf; /* 0's based value. */ struct ida ns_ida; #ifdef CONFIG_NVME_MULTIPATH enum nvme_iopolicy iopolicy; @@ -496,6 +496,9 @@ struct nvme_ns_head { struct device cdev_device; struct gendisk *disk; + + u16 nr_plids; + u16 *plids; #ifdef CONFIG_NVME_MULTIPATH struct bio_list requeue_list; spinlock_t requeue_lock; @@ -503,7 +506,10 @@ struct nvme_ns_head { struct work_struct partition_scan_work; struct mutex lock; unsigned long flags; -#define NVME_NSHEAD_DISK_LIVE 0 + struct delayed_work remove_work; + unsigned int delayed_removal_secs; +#define NVME_NSHEAD_DISK_LIVE 0 +#define NVME_NSHEAD_QUEUE_IF_NO_PATH 1 struct nvme_ns __rcu *current_path[]; #endif }; @@ -516,7 +522,7 @@ 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 = 1 << 2, /* DEAC bit in Write Zeores supported */ + NVME_NS_DEAC = 1 << 2, /* DEAC bit in Write Zeroes supported */ }; struct nvme_ns { @@ -534,10 +540,11 @@ struct nvme_ns { struct nvme_ns_head *head; unsigned long flags; -#define NVME_NS_REMOVING 0 -#define NVME_NS_ANA_PENDING 2 -#define NVME_NS_FORCE_RO 3 -#define NVME_NS_READY 4 +#define NVME_NS_REMOVING 0 +#define NVME_NS_ANA_PENDING 2 +#define NVME_NS_FORCE_RO 3 +#define NVME_NS_READY 4 +#define NVME_NS_SYSFS_ATTR_LINK 5 struct cdev cdev; struct device cdev_device; @@ -895,10 +902,10 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, 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); + void *result); int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, - u32 *result); + void *result); int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); @@ -933,6 +940,7 @@ 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_attr_groups[]; +extern const struct attribute_group nvme_ns_mpath_attr_group; 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; @@ -955,8 +963,10 @@ void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys); void nvme_failover_req(struct request *req); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); +void nvme_mpath_add_sysfs_link(struct nvme_ns_head *ns); +void nvme_mpath_remove_sysfs_link(struct nvme_ns *ns); void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid); -void nvme_mpath_remove_disk(struct nvme_ns_head *head); +void nvme_mpath_put_disk(struct nvme_ns_head *head); int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl); void nvme_mpath_update(struct nvme_ctrl *ctrl); @@ -965,7 +975,7 @@ void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); void nvme_mpath_revalidate_paths(struct nvme_ns *ns); void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl); -void nvme_mpath_shutdown_disk(struct nvme_ns_head *head); +void nvme_mpath_remove_disk(struct nvme_ns_head *head); void nvme_mpath_start_request(struct request *rq); void nvme_mpath_end_request(struct request *rq); @@ -980,12 +990,21 @@ static inline void nvme_trace_bio_complete(struct request *req) extern bool multipath; extern struct device_attribute dev_attr_ana_grpid; extern struct device_attribute dev_attr_ana_state; +extern struct device_attribute dev_attr_queue_depth; +extern struct device_attribute dev_attr_numa_nodes; +extern struct device_attribute dev_attr_delayed_removal_secs; 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; } +static inline bool nvme_mpath_queue_if_no_path(struct nvme_ns_head *head) +{ + if (test_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags)) + return true; + return false; +} #else #define multipath false static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) @@ -1006,7 +1025,13 @@ static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, static inline void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid) { } -static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) +static inline void nvme_mpath_put_disk(struct nvme_ns_head *head) +{ +} +static inline void nvme_mpath_add_sysfs_link(struct nvme_ns *ns) +{ +} +static inline void nvme_mpath_remove_sysfs_link(struct nvme_ns *ns) { } static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns) @@ -1019,7 +1044,7 @@ static inline void nvme_mpath_revalidate_paths(struct nvme_ns *ns) static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) { } -static inline void nvme_mpath_shutdown_disk(struct nvme_ns_head *head) +static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) { } static inline void nvme_trace_bio_complete(struct request *req) @@ -1067,6 +1092,10 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk) { return false; } +static inline bool nvme_mpath_queue_if_no_path(struct nvme_ns_head *head) +{ + return false; +} #endif /* CONFIG_NVME_MULTIPATH */ int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16], @@ -1147,6 +1176,7 @@ void nvme_auth_stop(struct nvme_ctrl *ctrl); int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid); int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid); void nvme_auth_free(struct nvme_ctrl *ctrl); +void nvme_auth_revoke_tls_key(struct nvme_ctrl *ctrl); #else static inline int nvme_auth_init_ctrl(struct nvme_ctrl *ctrl) { @@ -1169,6 +1199,7 @@ static inline int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid) return -EPROTONOSUPPORT; } static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {}; +static inline void nvme_auth_revoke_tls_key(struct nvme_ctrl *ctrl) {}; #endif u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9197a5b173fd..8ff12e415cb5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -18,6 +18,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/nodemask.h> #include <linux/once.h> #include <linux/pci.h> #include <linux/suspend.h> @@ -34,16 +35,31 @@ #define SQ_SIZE(q) ((q)->q_depth << (q)->sqes) #define CQ_SIZE(q) ((q)->q_depth * sizeof(struct nvme_completion)) -#define SGES_PER_PAGE (NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc)) +/* Optimisation for I/Os between 4k and 128k */ +#define NVME_SMALL_POOL_SIZE 256 /* * These can be higher, but we need to ensure that any command doesn't * require an sg allocation that needs more than a page of data. */ #define NVME_MAX_KB_SZ 8192 -#define NVME_MAX_SEGS 128 -#define NVME_MAX_META_SEGS 15 -#define NVME_MAX_NR_ALLOCATIONS 5 +#define NVME_MAX_NR_DESCRIPTORS 5 + +/* + * For data SGLs we support a single descriptors worth of SGL entries, but for + * now we also limit it to avoid an allocation larger than PAGE_SIZE for the + * scatterlist. + */ +#define NVME_MAX_SEGS \ + min(NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc), \ + (PAGE_SIZE / sizeof(struct scatterlist))) + +/* + * For metadata SGLs, only the small descriptor is supported, and the first + * entry is the segment descriptor, which for the data pointer sits in the SQE. + */ +#define NVME_MAX_META_SEGS \ + ((NVME_SMALL_POOL_SIZE / sizeof(struct nvme_sgl_desc)) - 1) static int use_threaded_interrupts; module_param(use_threaded_interrupts, int, 0444); @@ -112,6 +128,11 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); static void nvme_delete_io_queues(struct nvme_dev *dev); static void nvme_update_attrs(struct nvme_dev *dev); +struct nvme_descriptor_pools { + struct dma_pool *large; + struct dma_pool *small; +}; + /* * Represents an NVM Express device. Each nvme_dev is a PCI function. */ @@ -121,8 +142,6 @@ struct nvme_dev { struct blk_mq_tag_set admin_tagset; u32 __iomem *dbs; struct device *dev; - struct dma_pool *prp_page_pool; - struct dma_pool *prp_small_pool; unsigned online_queues; unsigned max_qid; unsigned io_queues[HCTX_MAX_TYPES]; @@ -162,6 +181,7 @@ struct nvme_dev { unsigned int nr_allocated_queues; unsigned int nr_write_queues; unsigned int nr_poll_queues; + struct nvme_descriptor_pools descriptor_pools[]; }; static int io_queue_depth_set(const char *val, const struct kernel_param *kp) @@ -191,6 +211,7 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl) */ struct nvme_queue { struct nvme_dev *dev; + struct nvme_descriptor_pools descriptor_pools; spinlock_t sq_lock; void *sq_cmds; /* only used for poll queues: */ @@ -219,30 +240,30 @@ struct nvme_queue { struct completion delete_done; }; -union nvme_descriptor { - struct nvme_sgl_desc *sg_list; - __le64 *prp_list; +/* bits for iod->flags */ +enum nvme_iod_flags { + /* this command has been aborted by the timeout handler */ + IOD_ABORTED = 1U << 0, + + /* uses the small descriptor pool */ + IOD_SMALL_DESCRIPTOR = 1U << 1, }; /* * The nvme_iod describes the data in an I/O. - * - * The sg pointer contains the list of PRP/SGL chunk allocations in addition - * to the actual struct scatterlist. */ struct nvme_iod { struct nvme_request req; struct nvme_command cmd; - bool aborted; - s8 nr_allocations; /* PRP list pool allocations. 0 means small - pool in use */ + u8 flags; + u8 nr_descriptors; unsigned int dma_len; /* length of single DMA segment mapping */ dma_addr_t first_dma; dma_addr_t meta_dma; struct sg_table sgt; struct sg_table meta_sgt; - union nvme_descriptor meta_list; - union nvme_descriptor list[NVME_MAX_NR_ALLOCATIONS]; + struct nvme_sgl_desc *meta_descriptor; + void *descriptors[NVME_MAX_NR_DESCRIPTORS]; }; static inline unsigned int nvme_dbbuf_size(struct nvme_dev *dev) @@ -390,37 +411,85 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, * as it only leads to a small amount of wasted memory for the lifetime of * the I/O. */ -static int nvme_pci_npages_prp(void) +static __always_inline int nvme_pci_npages_prp(void) { unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8); } -static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, - unsigned int hctx_idx) +static struct nvme_descriptor_pools * +nvme_setup_descriptor_pools(struct nvme_dev *dev, unsigned numa_node) { - struct nvme_dev *dev = to_nvme_dev(data); - struct nvme_queue *nvmeq = &dev->queues[0]; + struct nvme_descriptor_pools *pools = &dev->descriptor_pools[numa_node]; + size_t small_align = NVME_SMALL_POOL_SIZE; - WARN_ON(hctx_idx != 0); - WARN_ON(dev->admin_tagset.tags[0] != hctx->tags); + if (pools->small) + return pools; /* already initialized */ - hctx->driver_data = nvmeq; - return 0; + pools->large = dma_pool_create_node("nvme descriptor page", dev->dev, + NVME_CTRL_PAGE_SIZE, NVME_CTRL_PAGE_SIZE, 0, numa_node); + if (!pools->large) + return ERR_PTR(-ENOMEM); + + if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512) + small_align = 512; + + pools->small = dma_pool_create_node("nvme descriptor small", dev->dev, + NVME_SMALL_POOL_SIZE, small_align, 0, numa_node); + if (!pools->small) { + dma_pool_destroy(pools->large); + pools->large = NULL; + return ERR_PTR(-ENOMEM); + } + + return pools; } -static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, - unsigned int hctx_idx) +static void nvme_release_descriptor_pools(struct nvme_dev *dev) +{ + unsigned i; + + for (i = 0; i < nr_node_ids; i++) { + struct nvme_descriptor_pools *pools = &dev->descriptor_pools[i]; + + dma_pool_destroy(pools->large); + dma_pool_destroy(pools->small); + } +} + +static int nvme_init_hctx_common(struct blk_mq_hw_ctx *hctx, void *data, + unsigned qid) { struct nvme_dev *dev = to_nvme_dev(data); - struct nvme_queue *nvmeq = &dev->queues[hctx_idx + 1]; + struct nvme_queue *nvmeq = &dev->queues[qid]; + struct nvme_descriptor_pools *pools; + struct blk_mq_tags *tags; - WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags); + tags = qid ? dev->tagset.tags[qid - 1] : dev->admin_tagset.tags[0]; + WARN_ON(tags != hctx->tags); + pools = nvme_setup_descriptor_pools(dev, hctx->numa_node); + if (IS_ERR(pools)) + return PTR_ERR(pools); + + nvmeq->descriptor_pools = *pools; hctx->driver_data = nvmeq; return 0; } +static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + WARN_ON(hctx_idx != 0); + return nvme_init_hctx_common(hctx, data, 0); +} + +static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, + unsigned int hctx_idx) +{ + return nvme_init_hctx_common(hctx, data, hctx_idx + 1); +} + static int nvme_pci_init_request(struct blk_mq_tag_set *set, struct request *req, unsigned int hctx_idx, unsigned int numa_node) @@ -537,23 +606,39 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req, return true; } -static void nvme_free_prps(struct nvme_dev *dev, struct request *req) +static inline struct dma_pool *nvme_dma_pool(struct nvme_queue *nvmeq, + struct nvme_iod *iod) +{ + if (iod->flags & IOD_SMALL_DESCRIPTOR) + return nvmeq->descriptor_pools.small; + return nvmeq->descriptor_pools.large; +} + +static void nvme_free_descriptors(struct nvme_queue *nvmeq, struct request *req) { const int last_prp = NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 1; struct nvme_iod *iod = blk_mq_rq_to_pdu(req); dma_addr_t dma_addr = iod->first_dma; int i; - for (i = 0; i < iod->nr_allocations; i++) { - __le64 *prp_list = iod->list[i].prp_list; + if (iod->nr_descriptors == 1) { + dma_pool_free(nvme_dma_pool(nvmeq, iod), iod->descriptors[0], + dma_addr); + return; + } + + for (i = 0; i < iod->nr_descriptors; i++) { + __le64 *prp_list = iod->descriptors[i]; dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]); - dma_pool_free(dev->prp_page_pool, prp_list, dma_addr); + dma_pool_free(nvmeq->descriptor_pools.large, prp_list, + dma_addr); dma_addr = next_dma_addr; } } -static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) +static void nvme_unmap_data(struct nvme_dev *dev, struct nvme_queue *nvmeq, + struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -566,15 +651,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) WARN_ON_ONCE(!iod->sgt.nents); dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0); - - if (iod->nr_allocations == 0) - dma_pool_free(dev->prp_small_pool, iod->list[0].sg_list, - iod->first_dma); - else if (iod->nr_allocations == 1) - dma_pool_free(dev->prp_page_pool, iod->list[0].sg_list, - iod->first_dma); - else - nvme_free_prps(dev, req); + nvme_free_descriptors(nvmeq, req); mempool_free(iod->sgt.sgl, dev->iod_mempool); } @@ -592,11 +669,10 @@ static void nvme_print_sgl(struct scatterlist *sgl, int nents) } } -static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, +static blk_status_t nvme_pci_setup_prps(struct nvme_queue *nvmeq, struct request *req, struct nvme_rw_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct dma_pool *pool; int length = blk_rq_payload_bytes(req); struct scatterlist *sg = iod->sgt.sgl; int dma_len = sg_dma_len(sg); @@ -604,7 +680,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, int offset = dma_addr & (NVME_CTRL_PAGE_SIZE - 1); __le64 *prp_list; dma_addr_t prp_dma; - int nprps, i; + int i; length -= (NVME_CTRL_PAGE_SIZE - offset); if (length <= 0) { @@ -626,30 +702,26 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, goto done; } - nprps = DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE); - if (nprps <= (256 / 8)) { - pool = dev->prp_small_pool; - iod->nr_allocations = 0; - } else { - pool = dev->prp_page_pool; - iod->nr_allocations = 1; - } + if (DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE) <= + NVME_SMALL_POOL_SIZE / sizeof(__le64)) + iod->flags |= IOD_SMALL_DESCRIPTOR; - prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); - if (!prp_list) { - iod->nr_allocations = -1; + prp_list = dma_pool_alloc(nvme_dma_pool(nvmeq, iod), GFP_ATOMIC, + &prp_dma); + if (!prp_list) return BLK_STS_RESOURCE; - } - iod->list[0].prp_list = prp_list; + iod->descriptors[iod->nr_descriptors++] = prp_list; iod->first_dma = prp_dma; i = 0; for (;;) { if (i == NVME_CTRL_PAGE_SIZE >> 3) { __le64 *old_prp_list = prp_list; - prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + + prp_list = dma_pool_alloc(nvmeq->descriptor_pools.large, + GFP_ATOMIC, &prp_dma); if (!prp_list) goto free_prps; - iod->list[iod->nr_allocations++].prp_list = prp_list; + iod->descriptors[iod->nr_descriptors++] = prp_list; prp_list[0] = old_prp_list[i - 1]; old_prp_list[i - 1] = cpu_to_le64(prp_dma); i = 1; @@ -673,7 +745,7 @@ done: cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma); return BLK_STS_OK; free_prps: - nvme_free_prps(dev, req); + nvme_free_descriptors(nvmeq, req); return BLK_STS_RESOURCE; bad_sgl: WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents), @@ -698,11 +770,10 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge, sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4; } -static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, +static blk_status_t nvme_pci_setup_sgls(struct nvme_queue *nvmeq, struct request *req, struct nvme_rw_command *cmd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct dma_pool *pool; struct nvme_sgl_desc *sg_list; struct scatterlist *sg = iod->sgt.sgl; unsigned int entries = iod->sgt.nents; @@ -717,21 +788,14 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, return BLK_STS_OK; } - if (entries <= (256 / sizeof(struct nvme_sgl_desc))) { - pool = dev->prp_small_pool; - iod->nr_allocations = 0; - } else { - pool = dev->prp_page_pool; - iod->nr_allocations = 1; - } + if (entries <= NVME_SMALL_POOL_SIZE / sizeof(*sg_list)) + iod->flags |= IOD_SMALL_DESCRIPTOR; - sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); - if (!sg_list) { - iod->nr_allocations = -1; + sg_list = dma_pool_alloc(nvme_dma_pool(nvmeq, iod), GFP_ATOMIC, + &sgl_dma); + if (!sg_list) return BLK_STS_RESOURCE; - } - - iod->list[0].sg_list = sg_list; + iod->descriptors[iod->nr_descriptors++] = sg_list; iod->first_dma = sgl_dma; nvme_pci_sgl_set_seg(&cmd->dptr.sgl, sgl_dma, entries); @@ -785,12 +849,12 @@ static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev, static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, struct nvme_command *cmnd) { + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; struct nvme_iod *iod = blk_mq_rq_to_pdu(req); blk_status_t ret = BLK_STS_RESOURCE; int rc; if (blk_rq_nr_phys_segments(req) == 1) { - struct nvme_queue *nvmeq = req->mq_hctx->driver_data; struct bio_vec bv = req_bvec(req); if (!is_pci_p2pdma_page(bv.bv_page)) { @@ -812,7 +876,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, if (!iod->sgt.sgl) return BLK_STS_RESOURCE; sg_init_table(iod->sgt.sgl, blk_rq_nr_phys_segments(req)); - iod->sgt.orig_nents = blk_rq_map_sg(req->q, req, iod->sgt.sgl); + iod->sgt.orig_nents = blk_rq_map_sg(req, iod->sgt.sgl); if (!iod->sgt.orig_nents) goto out_free_sg; @@ -825,9 +889,9 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, } if (nvme_pci_use_sgls(dev, req, iod->sgt.nents)) - ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw); + ret = nvme_pci_setup_sgls(nvmeq, req, &cmnd->rw); else - ret = nvme_pci_setup_prps(dev, req, &cmnd->rw); + ret = nvme_pci_setup_prps(nvmeq, req, &cmnd->rw); if (ret != BLK_STS_OK) goto out_unmap_sg; return BLK_STS_OK; @@ -842,6 +906,7 @@ out_free_sg: static blk_status_t nvme_pci_setup_meta_sgls(struct nvme_dev *dev, struct request *req) { + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_rw_command *cmnd = &iod->cmd.rw; struct nvme_sgl_desc *sg_list; @@ -865,12 +930,13 @@ static blk_status_t nvme_pci_setup_meta_sgls(struct nvme_dev *dev, if (rc) goto out_free_sg; - sg_list = dma_pool_alloc(dev->prp_small_pool, GFP_ATOMIC, &sgl_dma); + sg_list = dma_pool_alloc(nvmeq->descriptor_pools.small, GFP_ATOMIC, + &sgl_dma); if (!sg_list) goto out_unmap_sg; entries = iod->meta_sgt.nents; - iod->meta_list.sg_list = sg_list; + iod->meta_descriptor = sg_list; iod->meta_dma = sgl_dma; cmnd->flags = NVME_CMD_SGL_METASEG; @@ -912,7 +978,10 @@ static blk_status_t nvme_pci_setup_meta_mptr(struct nvme_dev *dev, static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req) { - if (nvme_pci_metadata_use_sgls(dev, req)) + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + + if ((iod->cmd.common.flags & NVME_CMD_SGL_METABUF) && + nvme_pci_metadata_use_sgls(dev, req)) return nvme_pci_setup_meta_sgls(dev, req); return nvme_pci_setup_meta_mptr(dev, req); } @@ -922,8 +991,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req) struct nvme_iod *iod = blk_mq_rq_to_pdu(req); blk_status_t ret; - iod->aborted = false; - iod->nr_allocations = -1; + iod->flags = 0; + iod->nr_descriptors = 0; iod->sgt.nents = 0; iod->meta_sgt.nents = 0; @@ -947,15 +1016,12 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req) return BLK_STS_OK; out_unmap_data: if (blk_rq_nr_phys_segments(req)) - nvme_unmap_data(dev, req); + nvme_unmap_data(dev, req->mq_hctx->driver_data, req); out_free_cmd: nvme_cleanup_cmd(req); return ret; } -/* - * NOTE: ns is NULL when called on the admin queue. - */ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -989,6 +1055,9 @@ static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct rq_list *rqlist) { struct request *req; + if (rq_list_empty(rqlist)) + return; + spin_lock(&nvmeq->sq_lock); while ((req = rq_list_pop(rqlist))) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -1037,6 +1106,7 @@ static void nvme_queue_rqs(struct rq_list *rqlist) } static __always_inline void nvme_unmap_metadata(struct nvme_dev *dev, + struct nvme_queue *nvmeq, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -1048,8 +1118,8 @@ static __always_inline void nvme_unmap_metadata(struct nvme_dev *dev, return; } - dma_pool_free(dev->prp_small_pool, iod->meta_list.sg_list, - iod->meta_dma); + dma_pool_free(nvmeq->descriptor_pools.small, iod->meta_descriptor, + iod->meta_dma); dma_unmap_sgtable(dev->dev, &iod->meta_sgt, rq_dma_dir(req), 0); mempool_free(iod->meta_sgt.sgl, dev->iod_meta_mempool); } @@ -1060,10 +1130,10 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req) struct nvme_dev *dev = nvmeq->dev; if (blk_integrity_rq(req)) - nvme_unmap_metadata(dev, req); + nvme_unmap_metadata(dev, nvmeq, req); if (blk_rq_nr_phys_segments(req)) - nvme_unmap_data(dev, req); + nvme_unmap_data(dev, nvmeq, req); } static void nvme_pci_complete_rq(struct request *req) @@ -1130,8 +1200,9 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail); if (!nvme_try_complete_req(req, cqe->status, cqe->result) && - !blk_mq_add_to_batch(req, iob, nvme_req(req)->status, - nvme_pci_complete_batch)) + !blk_mq_add_to_batch(req, iob, + nvme_req(req)->status != NVME_SC_SUCCESS, + nvme_pci_complete_batch)) nvme_pci_complete_rq(req); } @@ -1201,7 +1272,9 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq) WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags)); disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); + spin_lock(&nvmeq->cq_poll_lock); nvme_poll_cq(nvmeq, NULL); + spin_unlock(&nvmeq->cq_poll_lock); enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); } @@ -1411,9 +1484,20 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) struct nvme_dev *dev = nvmeq->dev; struct request *abort_req; struct nvme_command cmd = { }; + struct pci_dev *pdev = to_pci_dev(dev->dev); u32 csts = readl(dev->bar + NVME_REG_CSTS); u8 opcode; + /* + * Shutdown the device immediately if we see it is disconnected. This + * unblocks PCIe error handling if the nvme driver is waiting in + * error_resume for a device that has been removed. We can't unbind the + * driver while the driver's error callback is waiting to complete, so + * we're relying on a timeout to break that deadlock if a removal + * occurs while reset work is running. + */ + if (pci_dev_is_disconnected(pdev)) + nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING); if (nvme_state_terminal(&dev->ctrl)) goto disable; @@ -1421,7 +1505,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) * the recovery mechanism will surely fail. */ mb(); - if (pci_channel_offline(to_pci_dev(dev->dev))) + if (pci_channel_offline(pdev)) return BLK_EH_RESET_TIMER; /* @@ -1476,7 +1560,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) * returned to the driver, or if this is the admin queue. */ opcode = nvme_req(req)->cmd->common.opcode; - if (!nvmeq->qid || iod->aborted) { + if (!nvmeq->qid || (iod->flags & IOD_ABORTED)) { dev_warn(dev->ctrl.device, "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n", req->tag, nvme_cid(req), opcode, @@ -1489,7 +1573,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) atomic_inc(&dev->ctrl.abort_limit); return BLK_EH_RESET_TIMER; } - iod->aborted = true; + iod->flags |= IOD_ABORTED; cmd.abort.opcode = nvme_admin_abort_cmd; cmd.abort.cid = nvme_cid(req); @@ -1983,6 +2067,18 @@ static void nvme_map_cmb(struct nvme_dev *dev) return; /* + * Controllers may support a CMB size larger than their BAR, for + * example, due to being behind a bridge. Reduce the CMB to the + * reported size of the BAR + */ + size = min(size, bar_size - offset); + + if (!IS_ALIGNED(size, memremap_compat_align()) || + !IS_ALIGNED(pci_resource_start(pdev, bar), + memremap_compat_align())) + return; + + /* * Tell the controller about the host side address mapping the CMB, * and enable CMB decoding for the NVMe 1.4+ scheme: */ @@ -1992,17 +2088,10 @@ static void nvme_map_cmb(struct nvme_dev *dev) dev->bar + NVME_REG_CMBMSC); } - /* - * Controllers may support a CMB size larger than their BAR, - * for example, due to being behind a bridge. Reduce the CMB to - * the reported size of the BAR - */ - if (size > bar_size - offset) - size = bar_size - offset; - if (pci_p2pdma_add_resource(pdev, bar, size, offset)) { dev_warn(dev->ctrl.device, "failed to register the CMB\n"); + hi_lo_writeq(0, dev->bar + NVME_REG_CMBMSC); return; } @@ -2823,35 +2912,6 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown) return 0; } -static int nvme_setup_prp_pools(struct nvme_dev *dev) -{ - size_t small_align = 256; - - dev->prp_page_pool = dma_pool_create("prp list page", dev->dev, - NVME_CTRL_PAGE_SIZE, - NVME_CTRL_PAGE_SIZE, 0); - if (!dev->prp_page_pool) - return -ENOMEM; - - if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512) - small_align = 512; - - /* Optimisation for I/Os between 4k and 128k */ - dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev, - 256, small_align, 0); - if (!dev->prp_small_pool) { - dma_pool_destroy(dev->prp_page_pool); - return -ENOMEM; - } - return 0; -} - -static void nvme_release_prp_pools(struct nvme_dev *dev) -{ - dma_pool_destroy(dev->prp_page_pool); - dma_pool_destroy(dev->prp_small_pool); -} - static int nvme_pci_alloc_iod_mempool(struct nvme_dev *dev) { size_t meta_size = sizeof(struct scatterlist) * (NVME_MAX_META_SEGS + 1); @@ -2955,7 +3015,7 @@ static void nvme_reset_work(struct work_struct *work) goto out; /* - * Freeze and update the number of I/O queues as thos might have + * Freeze and update the number of I/O queues as those might have * changed. If there are no I/O queues left after this reset, keep the * controller around but remove all namespaces. */ @@ -3126,7 +3186,7 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) /* * 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. + * lot of energy with s2idle sleep on some TUXEDO platforms. */ if (dmi_match(DMI_BOARD_NAME, "NS5X_NS7XAU") || dmi_match(DMI_BOARD_NAME, "NS5x_7xAU") || @@ -3166,7 +3226,8 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, struct nvme_dev *dev; int ret = -ENOMEM; - dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node); + dev = kzalloc_node(struct_size(dev, descriptor_pools, nr_node_ids), + GFP_KERNEL, node); if (!dev) return ERR_PTR(-ENOMEM); INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work); @@ -3241,13 +3302,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (result) goto out_uninit_ctrl; - result = nvme_setup_prp_pools(dev); - if (result) - goto out_dev_unmap; - result = nvme_pci_alloc_iod_mempool(dev); if (result) - goto out_release_prp_pools; + goto out_dev_unmap; dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); @@ -3323,8 +3380,6 @@ out_disable: out_release_iod_mempool: mempool_destroy(dev->iod_mempool); mempool_destroy(dev->iod_meta_mempool); -out_release_prp_pools: - nvme_release_prp_pools(dev); out_dev_unmap: nvme_dev_unmap(dev); out_uninit_ctrl: @@ -3389,7 +3444,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_free_queues(dev, 0); mempool_destroy(dev->iod_mempool); mempool_destroy(dev->iod_meta_mempool); - nvme_release_prp_pools(dev); + nvme_release_descriptor_pools(dev); nvme_dev_unmap(dev); nvme_uninit_ctrl(&dev->ctrl); } @@ -3558,7 +3613,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev) dev_info(dev->ctrl.device, "restart after slot reset\n"); pci_restore_state(pdev); - if (!nvme_try_sched_reset(&dev->ctrl)) + if (nvme_try_sched_reset(&dev->ctrl)) nvme_unquiesce_io_queues(&dev->ctrl); return PCI_ERS_RESULT_RECOVERED; } @@ -3606,6 +3661,9 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */ .driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, }, + { PCI_DEVICE(0x126f, 0x1001), /* Silicon Motion generic */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_BOGUS_NID, }, @@ -3629,6 +3687,9 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x15b7, 0x5008), /* Sandisk SN530 */ .driver_data = NVME_QUIRK_BROKEN_MSI }, + { PCI_DEVICE(0x15b7, 0x5009), /* Sandisk SN550 */ + .driver_data = NVME_QUIRK_BROKEN_MSI | + NVME_QUIRK_NO_DEEPEST_PS }, { PCI_DEVICE(0x1987, 0x5012), /* Phison E12 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */ @@ -3706,12 +3767,16 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1cc1, 0x5350), /* ADATA XPG GAMMIX S50 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1dbe, 0x5216), /* Acer/INNOGRIT FA100/5216 NVMe SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1dbe, 0x5236), /* ADATA XPG GAMMIX S70 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1e49, 0x0021), /* ZHITAI TiPro5000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x025e, 0xf1ac), /* SOLIDIGM P44 pro SSDPFKKW020X7 */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */ @@ -3780,9 +3845,7 @@ static int __init nvme_init(void) BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64); BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64); BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2); - BUILD_BUG_ON(NVME_MAX_SEGS > SGES_PER_PAGE); - BUILD_BUG_ON(sizeof(struct scatterlist) * NVME_MAX_SEGS > PAGE_SIZE); - BUILD_BUG_ON(nvme_pci_npages_prp() > NVME_MAX_NR_ALLOCATIONS); + BUILD_BUG_ON(nvme_pci_npages_prp() > NVME_MAX_NR_DESCRIPTORS); return pci_register_driver(&nvme_driver); } diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index cf2d2c5039dd..ca6a74607b13 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -82,8 +82,6 @@ static int nvme_status_to_pr_err(int status) return PR_STS_SUCCESS; case NVME_SC_RESERVATION_CONFLICT: return PR_STS_RESERVATION_CONFLICT; - case NVME_SC_ONCS_NOT_SUPPORTED: - return -EOPNOTSUPP; case NVME_SC_BAD_ATTRIBUTES: case NVME_SC_INVALID_OPCODE: case NVME_SC_INVALID_FIELD: diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 86a2891d9bcc..9bd3646568d0 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -221,7 +221,7 @@ static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev, /* * Bind the CQEs (post recv buffers) DMA mapping to the RDMA queue - * lifetime. It's safe, since any chage in the underlying RDMA device + * lifetime. It's safe, since any change in the underlying RDMA device * will issue error recovery and queue re-creation. */ for (i = 0; i < ib_queue_size; i++) { @@ -800,7 +800,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, /* * Bind the async event SQE DMA mapping to the admin queue lifetime. - * It's safe, since any chage in the underlying RDMA device will issue + * It's safe, since any change in the underlying RDMA device will issue * error recovery and queue re-creation. */ error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe, @@ -1476,8 +1476,7 @@ static int nvme_rdma_dma_map_req(struct ib_device *ibdev, struct request *rq, if (ret) return -ENOMEM; - req->data_sgl.nents = blk_rq_map_sg(rq->q, rq, - req->data_sgl.sg_table.sgl); + req->data_sgl.nents = blk_rq_map_sg(rq, req->data_sgl.sg_table.sgl); *count = ib_dma_map_sg(ibdev, req->data_sgl.sg_table.sgl, req->data_sgl.nents, rq_dma_dir(rq)); diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 3a41b9ab0f13..29430949ce2f 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -258,6 +258,9 @@ static struct attribute *nvme_ns_attrs[] = { #ifdef CONFIG_NVME_MULTIPATH &dev_attr_ana_grpid.attr, &dev_attr_ana_state.attr, + &dev_attr_queue_depth.attr, + &dev_attr_numa_nodes.attr, + &dev_attr_delayed_removal_secs.attr, #endif &dev_attr_io_passthru_err_log_enabled.attr, NULL, @@ -290,6 +293,16 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl)) return 0; } + if (a == &dev_attr_queue_depth.attr || a == &dev_attr_numa_nodes.attr) { + if (nvme_disk_is_ns_head(dev_to_disk(dev))) + return 0; + } + if (a == &dev_attr_delayed_removal_secs.attr) { + struct gendisk *disk = dev_to_disk(dev); + + if (!nvme_disk_is_ns_head(disk)) + return 0; + } #endif return a->mode; } @@ -299,8 +312,50 @@ static const struct attribute_group nvme_ns_attr_group = { .is_visible = nvme_ns_attrs_are_visible, }; +#ifdef CONFIG_NVME_MULTIPATH +/* + * NOTE: The dummy attribute does not appear in sysfs. It exists solely to allow + * control over the visibility of the multipath sysfs node. Without at least one + * attribute defined in nvme_ns_mpath_attrs[], the sysfs implementation does not + * invoke the multipath_sysfs_group_visible() method. As a result, we would not + * be able to control the visibility of the multipath sysfs node. + */ +static struct attribute dummy_attr = { + .name = "dummy", +}; + +static struct attribute *nvme_ns_mpath_attrs[] = { + &dummy_attr, + NULL, +}; + +static bool multipath_sysfs_group_visible(struct kobject *kobj) +{ + struct device *dev = container_of(kobj, struct device, kobj); + + return nvme_disk_is_ns_head(dev_to_disk(dev)); +} + +static bool multipath_sysfs_attr_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + return false; +} + +DEFINE_SYSFS_GROUP_VISIBLE(multipath_sysfs) + +const struct attribute_group nvme_ns_mpath_attr_group = { + .name = "multipath", + .attrs = nvme_ns_mpath_attrs, + .is_visible = SYSFS_GROUP_VISIBLE(multipath_sysfs), +}; +#endif + const struct attribute_group *nvme_ns_attr_groups[] = { &nvme_ns_attr_group, +#ifdef CONFIG_NVME_MULTIPATH + &nvme_ns_mpath_attr_group, +#endif NULL, }; @@ -780,10 +835,10 @@ static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj, return 0; if (a == &dev_attr_tls_key.attr && - !ctrl->opts->tls) + !ctrl->opts->tls && !ctrl->opts->concat) return 0; if (a == &dev_attr_tls_configured_key.attr && - !ctrl->opts->tls_key) + (!ctrl->opts->tls_key || ctrl->opts->concat)) return 0; if (a == &dev_attr_tls_keyring.attr && !ctrl->opts->keyring) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 841238f38fdd..d924008c3949 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -8,7 +8,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/err.h> -#include <linux/key.h> +#include <linux/crc32.h> #include <linux/nvme-tcp.h> #include <linux/nvme-keyring.h> #include <net/sock.h> @@ -17,7 +17,6 @@ #include <net/tls_prot.h> #include <net/handshake.h> #include <linux/blk-mq.h> -#include <crypto/hash.h> #include <net/busy_poll.h> #include <trace/events/sock.h> @@ -169,8 +168,8 @@ struct nvme_tcp_queue { bool hdr_digest; bool data_digest; bool tls_enabled; - struct ahash_request *rcv_hash; - struct ahash_request *snd_hash; + u32 rcv_crc; + u32 snd_crc; __le32 exp_ddgst; __le32 recv_ddgst; struct completion tls_complete; @@ -217,6 +216,19 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue) return queue - queue->ctrl->queues; } +static inline bool nvme_tcp_recv_pdu_supported(enum nvme_tcp_pdu_type type) +{ + switch (type) { + case nvme_tcp_c2h_term: + case nvme_tcp_c2h_data: + case nvme_tcp_r2t: + case nvme_tcp_rsp: + return true; + default: + return false; + } +} + /* * Check if the queue is TLS encrypted */ @@ -236,7 +248,7 @@ static inline bool nvme_tcp_tls_configured(struct nvme_ctrl *ctrl) if (!IS_ENABLED(CONFIG_NVME_TCP_TLS)) return 0; - return ctrl->opts->tls; + return ctrl->opts->tls || ctrl->opts->concat; } static inline struct blk_mq_tags *nvme_tcp_tagset(struct nvme_tcp_queue *queue) @@ -391,7 +403,7 @@ static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) } static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, - bool sync, bool last) + bool last) { struct nvme_tcp_queue *queue = req->queue; bool empty; @@ -405,7 +417,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, * are on the same cpu, so we don't introduce contention. */ if (queue->io_cpu == raw_smp_processor_id() && - sync && empty && mutex_trylock(&queue->send_mutex)) { + empty && mutex_trylock(&queue->send_mutex)) { nvme_tcp_send_all(queue); mutex_unlock(&queue->send_mutex); } @@ -440,36 +452,43 @@ nvme_tcp_fetch_request(struct nvme_tcp_queue *queue) return NULL; } - list_del(&req->entry); + list_del_init(&req->entry); + init_llist_node(&req->lentry); return req; } -static inline void nvme_tcp_ddgst_final(struct ahash_request *hash, - __le32 *dgst) +#define NVME_TCP_CRC_SEED (~0) + +static inline void nvme_tcp_ddgst_update(u32 *crcp, + struct page *page, size_t off, size_t len) { - ahash_request_set_crypt(hash, NULL, (u8 *)dgst, 0); - crypto_ahash_final(hash); + page += off / PAGE_SIZE; + off %= PAGE_SIZE; + while (len) { + const void *vaddr = kmap_local_page(page); + size_t n = min(len, (size_t)PAGE_SIZE - off); + + *crcp = crc32c(*crcp, vaddr + off, n); + kunmap_local(vaddr); + page++; + off = 0; + len -= n; + } } -static inline void nvme_tcp_ddgst_update(struct ahash_request *hash, - struct page *page, off_t off, size_t len) +static inline __le32 nvme_tcp_ddgst_final(u32 crc) { - struct scatterlist sg; - - sg_init_table(&sg, 1); - sg_set_page(&sg, page, len, off); - ahash_request_set_crypt(hash, &sg, NULL, len); - crypto_ahash_update(hash); + return cpu_to_le32(~crc); } -static inline void nvme_tcp_hdgst(struct ahash_request *hash, - void *pdu, size_t len) +static inline __le32 nvme_tcp_hdgst(const void *pdu, size_t len) { - struct scatterlist sg; + return cpu_to_le32(~crc32c(NVME_TCP_CRC_SEED, pdu, len)); +} - sg_init_one(&sg, pdu, len); - ahash_request_set_crypt(hash, &sg, pdu + len, len); - crypto_ahash_digest(hash); +static inline void nvme_tcp_set_hdgst(void *pdu, size_t len) +{ + *(__le32 *)(pdu + len) = nvme_tcp_hdgst(pdu, len); } static int nvme_tcp_verify_hdgst(struct nvme_tcp_queue *queue, @@ -487,8 +506,7 @@ static int nvme_tcp_verify_hdgst(struct nvme_tcp_queue *queue, } recv_digest = *(__le32 *)(pdu + hdr->hlen); - nvme_tcp_hdgst(queue->rcv_hash, pdu, pdu_len); - exp_digest = *(__le32 *)(pdu + hdr->hlen); + exp_digest = nvme_tcp_hdgst(pdu, pdu_len); if (recv_digest != exp_digest) { dev_err(queue->ctrl->ctrl.device, "header digest error: recv %#x expected %#x\n", @@ -514,7 +532,7 @@ static int nvme_tcp_check_ddgst(struct nvme_tcp_queue *queue, void *pdu) nvme_tcp_queue_id(queue)); return -EPROTO; } - crypto_ahash_init(queue->rcv_hash); + queue->rcv_crc = NVME_TCP_CRC_SEED; return 0; } @@ -548,6 +566,8 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set, req->queue = queue; nvme_req(rq)->ctrl = &ctrl->ctrl; nvme_req(rq)->cmd = &pdu->cmd; + init_llist_node(&req->lentry); + INIT_LIST_HEAD(&req->entry); return 0; } @@ -752,17 +772,61 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, return -EPROTO; } + if (llist_on_list(&req->lentry) || + !list_empty(&req->entry)) { + dev_err(queue->ctrl->ctrl.device, + "req %d unexpected r2t while processing request\n", + rq->tag); + return -EPROTO; + } + req->pdu_len = 0; req->h2cdata_left = r2t_length; req->h2cdata_offset = r2t_offset; req->ttag = pdu->ttag; nvme_tcp_setup_h2c_data_pdu(req); - nvme_tcp_queue_request(req, false, true); + + llist_add(&req->lentry, &queue->req_list); + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); return 0; } +static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue, + struct nvme_tcp_term_pdu *pdu) +{ + u16 fes; + const char *msg; + u32 plen = le32_to_cpu(pdu->hdr.plen); + + static const char * const msg_table[] = { + [NVME_TCP_FES_INVALID_PDU_HDR] = "Invalid PDU Header Field", + [NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error", + [NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error", + [NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range", + [NVME_TCP_FES_DATA_LIMIT_EXCEEDED] = "Data Transfer Limit Exceeded", + [NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter", + }; + + if (plen < NVME_TCP_MIN_C2HTERM_PLEN || + plen > NVME_TCP_MAX_C2HTERM_PLEN) { + dev_err(queue->ctrl->ctrl.device, + "Received a malformed C2HTermReq PDU (plen = %u)\n", + plen); + return; + } + + fes = le16_to_cpu(pdu->fes); + if (fes && fes < ARRAY_SIZE(msg_table)) + msg = msg_table[fes]; + else + msg = "Unknown"; + + dev_err(queue->ctrl->ctrl.device, + "Received C2HTermReq (FES = %s)\n", msg); +} + static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, unsigned int *offset, size_t *len) { @@ -784,6 +848,25 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, return 0; hdr = queue->pdu; + if (unlikely(hdr->hlen != sizeof(struct nvme_tcp_rsp_pdu))) { + if (!nvme_tcp_recv_pdu_supported(hdr->type)) + goto unsupported_pdu; + + dev_err(queue->ctrl->ctrl.device, + "pdu type %d has unexpected header length (%d)\n", + hdr->type, hdr->hlen); + return -EPROTO; + } + + if (unlikely(hdr->type == nvme_tcp_c2h_term)) { + /* + * C2HTermReq never includes Header or Data digests. + * Skip the checks. + */ + nvme_tcp_handle_c2h_term(queue, (void *)queue->pdu); + return -EINVAL; + } + if (queue->hdr_digest) { ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen); if (unlikely(ret)) @@ -807,10 +890,13 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, nvme_tcp_init_recv_ctx(queue); return nvme_tcp_handle_r2t(queue, (void *)queue->pdu); default: - dev_err(queue->ctrl->ctrl.device, - "unsupported pdu type (%d)\n", hdr->type); - return -EINVAL; + goto unsupported_pdu; } + +unsupported_pdu: + dev_err(queue->ctrl->ctrl.device, + "unsupported pdu type (%d)\n", hdr->type); + return -EINVAL; } static inline void nvme_tcp_end_request(struct request *rq, u16 status) @@ -858,8 +944,8 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, iov_iter_count(&req->iter)); if (queue->data_digest) - ret = skb_copy_and_hash_datagram_iter(skb, *offset, - &req->iter, recv_len, queue->rcv_hash); + ret = skb_copy_and_crc32c_datagram_iter(skb, *offset, + &req->iter, recv_len, &queue->rcv_crc); else ret = skb_copy_datagram_iter(skb, *offset, &req->iter, recv_len); @@ -877,7 +963,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, if (!queue->data_remaining) { if (queue->data_digest) { - nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst); + queue->exp_ddgst = nvme_tcp_ddgst_final(queue->rcv_crc); queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH; } else { if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) { @@ -1079,7 +1165,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) return ret; if (queue->data_digest) - nvme_tcp_ddgst_update(queue->snd_hash, page, + nvme_tcp_ddgst_update(&queue->snd_crc, page, offset, ret); /* @@ -1093,8 +1179,8 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) /* fully successful last send in current PDU */ if (last && ret == len) { if (queue->data_digest) { - nvme_tcp_ddgst_final(queue->snd_hash, - &req->ddgst); + req->ddgst = + nvme_tcp_ddgst_final(queue->snd_crc); req->state = NVME_TCP_SEND_DDGST; req->offset = 0; } else { @@ -1126,7 +1212,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req) msg.msg_flags |= MSG_EOR; if (queue->hdr_digest && !req->offset) - nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + nvme_tcp_set_hdgst(pdu, sizeof(*pdu)); bvec_set_virt(&bvec, (void *)pdu + req->offset, len); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len); @@ -1139,7 +1225,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req) if (inline_data) { req->state = NVME_TCP_SEND_DATA; if (queue->data_digest) - crypto_ahash_init(queue->snd_hash); + queue->snd_crc = NVME_TCP_CRC_SEED; } else { nvme_tcp_done_send_req(queue); } @@ -1161,7 +1247,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req) int ret; if (queue->hdr_digest && !req->offset) - nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); + nvme_tcp_set_hdgst(pdu, sizeof(*pdu)); if (!req->h2cdata_left) msg.msg_flags |= MSG_SPLICE_PAGES; @@ -1176,7 +1262,7 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req) if (!len) { req->state = NVME_TCP_SEND_DATA; if (queue->data_digest) - crypto_ahash_init(queue->snd_hash); + queue->snd_crc = NVME_TCP_CRC_SEED; return 1; } req->offset += ret; @@ -1280,7 +1366,7 @@ static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue) queue->nr_cqe = 0; consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb); release_sock(sk); - return consumed; + return consumed == -EAGAIN ? 0 : consumed; } static void nvme_tcp_io_work(struct work_struct *w) @@ -1308,6 +1394,11 @@ static void nvme_tcp_io_work(struct work_struct *w) else if (unlikely(result < 0)) return; + /* did we get some space after spending time in recv? */ + if (nvme_tcp_queue_has_pending(queue) && + sk_stream_is_writeable(queue->sock->sk)) + pending = true; + if (!pending || !queue->rd_enabled) return; @@ -1316,41 +1407,6 @@ static void nvme_tcp_io_work(struct work_struct *w) queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); } -static void nvme_tcp_free_crypto(struct nvme_tcp_queue *queue) -{ - struct crypto_ahash *tfm = crypto_ahash_reqtfm(queue->rcv_hash); - - ahash_request_free(queue->rcv_hash); - ahash_request_free(queue->snd_hash); - crypto_free_ahash(tfm); -} - -static int nvme_tcp_alloc_crypto(struct nvme_tcp_queue *queue) -{ - struct crypto_ahash *tfm; - - tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - queue->snd_hash = ahash_request_alloc(tfm, GFP_KERNEL); - if (!queue->snd_hash) - goto free_tfm; - ahash_request_set_callback(queue->snd_hash, 0, NULL, NULL); - - queue->rcv_hash = ahash_request_alloc(tfm, GFP_KERNEL); - if (!queue->rcv_hash) - goto free_snd_hash; - ahash_request_set_callback(queue->rcv_hash, 0, NULL, NULL); - - return 0; -free_snd_hash: - ahash_request_free(queue->snd_hash); -free_tfm: - crypto_free_ahash(tfm); - return -ENOMEM; -} - static void nvme_tcp_free_async_req(struct nvme_tcp_ctrl *ctrl) { struct nvme_tcp_request *async = &ctrl->async_req; @@ -1383,9 +1439,6 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) return; - if (queue->hdr_digest || queue->data_digest) - nvme_tcp_free_crypto(queue); - page_frag_cache_drain(&queue->pf_cache); noreclaim_flag = memalloc_noreclaim_save(); @@ -1449,8 +1502,11 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) msg.msg_control = cbuf; msg.msg_controllen = sizeof(cbuf); } + msg.msg_flags = MSG_WAITALL; ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, iov.iov_len, msg.msg_flags); + if (ret >= 0 && ret < sizeof(*icresp)) + ret = -ECONNRESET; if (ret < 0) { pr_warn("queue %d: failed to receive icresp, error %d\n", nvme_tcp_queue_id(queue), ret); @@ -1565,7 +1621,7 @@ static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue) ctrl->io_queues[HCTX_TYPE_POLL]; } -/** +/* * Track the number of queues assigned to each cpu using a global per-cpu * counter and select the least used cpu from the mq_map. Our goal is to spread * different controllers I/O threads across different cpu cores. @@ -1718,7 +1774,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, queue->cmnd_capsule_len = sizeof(struct nvme_command) + NVME_TCP_ADMIN_CCSZ; - ret = sock_create(ctrl->addr.ss_family, SOCK_STREAM, + ret = sock_create_kern(current->nsproxy->net_ns, + ctrl->addr.ss_family, SOCK_STREAM, IPPROTO_TCP, &queue->sock); if (ret) { dev_err(nctrl->device, @@ -1731,6 +1788,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, ret = PTR_ERR(sock_file); goto err_destroy_mutex; } + + sk_net_refcnt_upgrade(queue->sock->sk); nvme_tcp_reclassify_socket(queue->sock); /* Single syn retry */ @@ -1793,21 +1852,13 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, queue->hdr_digest = nctrl->opts->hdr_digest; queue->data_digest = nctrl->opts->data_digest; - if (queue->hdr_digest || queue->data_digest) { - ret = nvme_tcp_alloc_crypto(queue); - if (ret) { - dev_err(nctrl->device, - "failed to allocate queue %d crypto\n", qid); - goto err_sock; - } - } rcv_pdu_size = sizeof(struct nvme_tcp_rsp_pdu) + nvme_tcp_hdgst_len(queue); queue->pdu = kmalloc(rcv_pdu_size, GFP_KERNEL); if (!queue->pdu) { ret = -ENOMEM; - goto err_crypto; + goto err_sock; } dev_dbg(nctrl->device, "connecting queue %d\n", @@ -1840,9 +1891,6 @@ err_init_connect: kernel_sock_shutdown(queue->sock, SHUT_RDWR); err_rcv_pdu: kfree(queue->pdu); -err_crypto: - if (queue->hdr_digest || queue->data_digest) - nvme_tcp_free_crypto(queue); err_sock: /* ->sock will be released by fput() */ fput(queue->sock->file); @@ -1872,7 +1920,7 @@ static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue) cancel_work_sync(&queue->io_work); } -static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) +static void nvme_tcp_stop_queue_nowait(struct nvme_ctrl *nctrl, int qid) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; @@ -1891,6 +1939,31 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) mutex_unlock(&queue->queue_lock); } +static void nvme_tcp_wait_queue(struct nvme_ctrl *nctrl, int qid) +{ + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[qid]; + int timeout = 100; + + while (timeout > 0) { + if (!test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags) || + !sk_wmem_alloc_get(queue->sock->sk)) + return; + msleep(2); + timeout -= 2; + } + dev_warn(nctrl->device, + "qid %d: timeout draining sock wmem allocation expired\n", + qid); +} + +static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) +{ + nvme_tcp_stop_queue_nowait(nctrl, qid); + nvme_tcp_wait_queue(nctrl, qid); +} + + static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue) { write_lock_bh(&queue->sock->sk->sk_callback_lock); @@ -1958,7 +2031,9 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl) int i; for (i = 1; i < ctrl->queue_count; i++) - nvme_tcp_stop_queue(ctrl, i); + nvme_tcp_stop_queue_nowait(ctrl, i); + for (i = 1; i < ctrl->queue_count; i++) + nvme_tcp_wait_queue(ctrl, i); } static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl, @@ -1988,7 +2063,7 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) if (nvme_tcp_tls_configured(ctrl)) { if (ctrl->opts->tls_key) pskid = key_serial(ctrl->opts->tls_key); - else { + else if (ctrl->opts->tls) { pskid = nvme_tls_psk_default(ctrl->opts->keyring, ctrl->opts->host->nqn, ctrl->opts->subsysnqn); @@ -2018,9 +2093,25 @@ 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; + if (nvme_tcp_tls_configured(ctrl)) { + if (ctrl->opts->concat) { + /* + * The generated PSK is stored in the + * fabric options + */ + if (!ctrl->opts->tls_key) { + dev_err(ctrl->device, "no PSK generated\n"); + return -ENOKEY; + } + if (ctrl->tls_pskid && + ctrl->tls_pskid != key_serial(ctrl->opts->tls_key)) { + dev_err(ctrl->device, "Stale PSK id %08x\n", ctrl->tls_pskid); + ctrl->tls_pskid = 0; + } + } else if (!ctrl->tls_pskid) { + dev_err(ctrl->device, "no PSK negotiated\n"); + return -ENOKEY; + } } for (i = 1; i < ctrl->queue_count; i++) { @@ -2238,6 +2329,27 @@ static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl, } } +/* + * The TLS key is set by secure concatenation after negotiation has been + * completed on the admin queue. We need to revoke the key when: + * - concatenation is enabled (otherwise it's a static key set by the user) + * and + * - the generated key is present in ctrl->tls_key (otherwise there's nothing + * to revoke) + * and + * - a valid PSK key ID has been set in ctrl->tls_pskid (otherwise TLS + * negotiation has not run). + * + * We cannot always revoke the key as nvme_tcp_alloc_admin_queue() is called + * twice during secure concatenation, once on a 'normal' connection to run the + * DH-HMAC-CHAP negotiation (which generates the key, so it _must not_ be set), + * and once after the negotiation (which uses the key, so it _must_ be set). + */ +static bool nvme_tcp_key_revoke_needed(struct nvme_ctrl *ctrl) +{ + return ctrl->opts->concat && ctrl->opts->tls_key && ctrl->tls_pskid; +} + static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new) { struct nvmf_ctrl_options *opts = ctrl->opts; @@ -2247,6 +2359,16 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new) if (ret) return ret; + if (ctrl->opts->concat && !ctrl->tls_pskid) { + /* See comments for nvme_tcp_key_revoke_needed() */ + dev_dbg(ctrl->device, "restart admin queue for secure concatenation\n"); + nvme_stop_keep_alive(ctrl); + nvme_tcp_teardown_admin_queue(ctrl, false); + ret = nvme_tcp_configure_admin_queue(ctrl, false); + if (ret) + goto destroy_admin; + } + if (ctrl->icdoff) { ret = -EOPNOTSUPP; dev_err(ctrl->device, "icdoff is not supported!\n"); @@ -2343,6 +2465,8 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) struct nvme_tcp_ctrl, err_work); struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl; + if (nvme_tcp_key_revoke_needed(ctrl)) + nvme_auth_revoke_tls_key(ctrl); nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); nvme_tcp_teardown_io_queues(ctrl, false); @@ -2383,6 +2507,8 @@ static void nvme_reset_ctrl_work(struct work_struct *work) container_of(work, struct nvme_ctrl, reset_work); int ret; + if (nvme_tcp_key_revoke_needed(ctrl)) + nvme_auth_revoke_tls_key(ctrl); nvme_stop_ctrl(ctrl); nvme_tcp_teardown_ctrl(ctrl, false); @@ -2484,8 +2610,10 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg) ctrl->async_req.offset = 0; ctrl->async_req.curr_bio = NULL; ctrl->async_req.data_len = 0; + init_llist_node(&ctrl->async_req.lentry); + INIT_LIST_HEAD(&ctrl->async_req.entry); - nvme_tcp_queue_request(&ctrl->async_req, true, true); + nvme_tcp_queue_request(&ctrl->async_req, true); } static void nvme_tcp_complete_timed_out(struct request *rq) @@ -2637,7 +2765,7 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, nvme_start_request(rq); - nvme_tcp_queue_request(req, true, bd->last); + nvme_tcp_queue_request(req, bd->last); return BLK_STS_OK; } @@ -2653,6 +2781,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct nvme_tcp_queue *queue = hctx->driver_data; struct sock *sk = queue->sock->sk; + int ret; if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags)) return 0; @@ -2660,9 +2789,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) set_bit(NVME_TCP_Q_POLLING, &queue->flags); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue)) sk_busy_loop(sk, true); - nvme_tcp_try_recv(queue); + ret = nvme_tcp_try_recv(queue); clear_bit(NVME_TCP_Q_POLLING, &queue->flags); - return queue->nr_cqe; + return ret < 0 ? ret : queue->nr_cqe; } static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size) @@ -2878,7 +3007,7 @@ static struct nvmf_transport_ops nvme_tcp_transport = { 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_TLS | - NVMF_OPT_KEYRING | NVMF_OPT_TLS_KEY, + NVMF_OPT_KEYRING | NVMF_OPT_TLS_KEY | NVMF_OPT_CONCAT, .create_ctrl = nvme_tcp_create_ctrl, }; diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 382949e18c6a..cce4c5b55aa9 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -146,17 +146,16 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns, return NULL; } -static int nvme_zone_parse_entry(struct nvme_ctrl *ctrl, - struct nvme_ns_head *head, +static int nvme_zone_parse_entry(struct nvme_ns *ns, struct nvme_zone_descriptor *entry, unsigned int idx, report_zones_cb cb, void *data) { + struct nvme_ns_head *head = ns->head; struct blk_zone zone = { }; if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) { - dev_err(ctrl->device, "invalid zone type %#x\n", - entry->zt); + dev_err(ns->ctrl->device, "invalid zone type %#x\n", entry->zt); return -EINVAL; } @@ -213,8 +212,7 @@ 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->ctrl, ns->head, - &report->entries[i], + ret = nvme_zone_parse_entry(ns, &report->entries[i], zone_idx, cb, data); if (ret) goto out_free; |