From nobody Thu Apr 2 15:41:46 2026 Received: from mail-pl1-f169.google.com (mail-pl1-f169.google.com [209.85.214.169]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3E1501C6B4 for ; Sat, 28 Mar 2026 00:45:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.214.169 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774658756; cv=none; b=QiDNmmZrA5orvU/e7ibkpmCZF0SwRZ+ujLrzlzMBzVcn39H33cZClDz9y+jn2Cg6Xxz877aLcp5yw/jyc0VpE42PSSVynFWMsoWf39I9lohTz7jdEp9Qal4GWcZ3OwEFrYUIv+RKXjB6qaj54lS7imHQgEqj/BZ4U0//GM+27ZE= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774658756; c=relaxed/simple; bh=DeedujTPrEtZADIb+NjxFrdGWc1mDzs4lo5jfHxZiRA=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=kxrroPYOwskRBGlmbkT33wPQLpBy1KMUGBwj2iivqtdxYuPVFAZPnsP7D77oQ1wdCjoinPrIzkF16DFn03fCiilrSHHvdilYqfwKstuiQYW107al8YNUqtA6kX2w6yzWVsbaxqUWGDFv4kgOcFMa+yEt+rpvImhH6nkkF6Wjq5s= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=purestorage.com; spf=fail smtp.mailfrom=purestorage.com; dkim=pass (2048-bit key) header.d=purestorage.com header.i=@purestorage.com header.b=M876EIwJ; arc=none smtp.client-ip=209.85.214.169 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=purestorage.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=purestorage.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=purestorage.com header.i=@purestorage.com header.b="M876EIwJ" Received: by mail-pl1-f169.google.com with SMTP id d9443c01a7336-2aaf43014d0so18073585ad.2 for ; Fri, 27 Mar 2026 17:45:55 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=purestorage.com; s=google2022; t=1774658754; x=1775263554; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=u0vIN98NbTlxUWbhWQbufIdEJ8esjoER7iKpbr4c9ZI=; b=M876EIwJHm/y0N+j+ySoqYDHIPFXyFJS3BVx5lViHz3jg4JcnLLcvNrjqjnAU2B1fK e9txhL4vPGDulVrls3HsrHJ68ZhJv9HI49VABusTBkE0LtED8kMJ5E82n98SceAAnebz /Xoh7cuFzoqpJ4AblKB+AIGQRtidhjwZMuDUgZQT9mv9pQvmWRjV0Zz0zkT5WzUfeigd Yok83mNWFwbbPGzsTUHDowP7ynf6HCenm/maXDOp8t6HurFDP4fTunq0aR3GajQNOo1h VhvMG2+akxLZOW88VsEdMF5kYwEEySJdefnzzX6k/bZRdY3EVAmoomfKTHiDPCOlErHW gmVQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1774658754; x=1775263554; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=u0vIN98NbTlxUWbhWQbufIdEJ8esjoER7iKpbr4c9ZI=; b=QRBbAQ0gy97vR5xGa7y0BwDLg8cuEe7I7dnKxeadSuLl2VtXvsa4txE3/KIWNTXBbT O7GPUapI62FwqfAHtAN9YaU5AlesPI03/65S7zPesvMaF9JThVgfbCyF1dCNDURyDWzk vciEJRedZKu6aKWlbm9zYxjdoaxh/jkJi2+De7AO2oUvcFN3m32I7U9CCRSTKJF6Z31t hQRoJcjNGFh0Iswx6U5hTT6JcMofLrSckGjilI8eCJk3qoArDn6PnCCNzNRJyNsm2RO2 QEqVWpcV3n/iz95PbME7xMe8Hos3AN2N9drWGi00ivO3hM0qWWKPS5fZveB5W58HVNBE R1Zw== X-Forwarded-Encrypted: i=1; AJvYcCW7hdVzqr5wrbtWyUU5Bf9UpljzwQvOpnCii9nixxrYmYNUpCdcwzpxw5St+QH5nX1ZZ8UFszhNSL9LBbI=@vger.kernel.org X-Gm-Message-State: AOJu0Yyo9380lV/uuU4cQq+qJ5icYvxOmz5e/Y1YlMvHxioodLGKOwNL qRi0D9ZI+kAbBj85m8J762t3+kc7V0iGnJFi1p9vKYs0UEj/5xY1DlKtx5arIImi6fU= X-Gm-Gg: ATEYQzwcoZmxRcAJ4KAWpyl4pWBw4EOqOWEOIyq7jnTDkPpeJLDPPwsjVqRw9AwQdZ7 SdT4A1lh9i4Vs9h/wiVVlJEPMt69hVWQunpwZyvKxngZIwKUyrQmH6n+UB1wO9sfkVbWmJSqRT3 KI+Qk91RNiQVnzhATsVJYfJ9l2YgQLFEZbPGGtQ9iPqBi46HCD7vvtUXDfi77ZNFKjikxVX9yeP N0XWly6y6j3uhuW9Ux1s70BAW9z3RpejIWfTrQ3DQhL7rwYsoYCLVxm9pCN/+DT8ZMzE/uVYBYL D+eZJV9y1hINse9AlQtbnV6IZ5xESdUIsvfqtHklg11/8nE+ZSd1iWd1kGD37WaVElGTeqyS8h8 QmA+2SRYyWPwTPj6DMnkwloA95YLi2yFLtYG3sXKubjZvPwHCDZsB2dNRwmIU0RQEHml/iCR5yl wtjy1cfWE= X-Received: by 2002:a17:903:22d2:b0:2b0:52b7:e82 with SMTP id d9443c01a7336-2b0cdc281ccmr52223235ad.16.1774658754195; Fri, 27 Mar 2026 17:45:54 -0700 (PDT) Received: from ceto ([2601:640:8202:6fb0::9c63]) by smtp.googlemail.com with ESMTPSA id d9443c01a7336-2b242683064sm5342705ad.33.2026.03.27.17.45.53 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 27 Mar 2026 17:45:53 -0700 (PDT) From: Mohamed Khalfella To: Justin Tee , Naresh Gottumukkala , Paul Ely , Chaitanya Kulkarni , Jens Axboe , Keith Busch , Sagi Grimberg , James Smart , Hannes Reinecke Cc: Aaron Dailey , Randy Jennings , Dhaval Giani , linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org, Mohamed Khalfella Subject: [PATCH v4 03/15] nvmet: Implement CCR nvme command Date: Fri, 27 Mar 2026 17:43:34 -0700 Message-ID: <20260328004518.1729186-4-mkhalfella@purestorage.com> X-Mailer: git-send-email 2.52.0 In-Reply-To: <20260328004518.1729186-1-mkhalfella@purestorage.com> References: <20260328004518.1729186-1-mkhalfella@purestorage.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Defined by TP8028 Rapid Path Failure Recovery, CCR (Cross-Controller Reset) command is an nvme command issued to source controller by initiator to reset impacted controller. Implement CCR command for linux nvme target. Signed-off-by: Mohamed Khalfella --- drivers/nvme/target/admin-cmd.c | 74 ++++++++++++++++++++++++++++++++ drivers/nvme/target/core.c | 76 +++++++++++++++++++++++++++++++++ drivers/nvme/target/nvmet.h | 13 ++++++ include/linux/nvme.h | 23 ++++++++++ 4 files changed, 186 insertions(+) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cm= d.c index ec09e30eca18..0a37c0eeebb5 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -376,7 +376,9 @@ static void nvmet_get_cmd_effects_admin(struct nvmet_ct= rl *ctrl, log->acs[nvme_admin_get_features] =3D log->acs[nvme_admin_async_event] =3D log->acs[nvme_admin_keep_alive] =3D + log->acs[nvme_admin_cross_ctrl_reset] =3D cpu_to_le32(NVME_CMD_EFFECTS_CSUPP); + } =20 static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log) @@ -1613,6 +1615,75 @@ void nvmet_execute_keep_alive(struct nvmet_req *req) nvmet_req_complete(req, status); } =20 +void nvmet_execute_cross_ctrl_reset(struct nvmet_req *req) +{ + struct nvmet_ctrl *ictrl, *sctrl =3D req->sq->ctrl; + struct nvme_command *cmd =3D req->cmd; + struct nvmet_ccr *ccr, *new_ccr; + int ccr_active, ccr_total; + u16 cntlid, status =3D NVME_SC_SUCCESS; + + cntlid =3D le16_to_cpu(cmd->ccr.icid); + if (sctrl->cntlid =3D=3D cntlid) { + req->error_loc =3D + offsetof(struct nvme_cross_ctrl_reset_cmd, icid); + status =3D NVME_SC_INVALID_FIELD | NVME_STATUS_DNR; + goto out; + } + + /* Find and get impacted controller */ + ictrl =3D nvmet_ctrl_find_get_ccr(sctrl->subsys, sctrl->hostnqn, + cmd->ccr.ciu, cntlid, + le64_to_cpu(cmd->ccr.cirn)); + if (!ictrl) { + /* Immediate Reset Successful */ + nvmet_set_result(req, 1); + status =3D NVME_SC_SUCCESS; + goto out; + } + + ccr_total =3D ccr_active =3D 0; + mutex_lock(&sctrl->lock); + list_for_each_entry(ccr, &sctrl->ccr_list, entry) { + if (ccr->ctrl =3D=3D ictrl) { + status =3D NVME_SC_CCR_IN_PROGRESS | NVME_STATUS_DNR; + goto out_unlock; + } + + ccr_total++; + if (ccr->ctrl) + ccr_active++; + } + + if (ccr_active >=3D NVMF_CCR_LIMIT) { + status =3D NVME_SC_CCR_LIMIT_EXCEEDED; + goto out_unlock; + } + if (ccr_total >=3D NVMF_CCR_PER_PAGE) { + status =3D NVME_SC_CCR_LOGPAGE_FULL; + goto out_unlock; + } + + new_ccr =3D kmalloc_obj(*new_ccr, GFP_KERNEL); + if (!new_ccr) { + status =3D NVME_SC_INTERNAL; + goto out_unlock; + } + + new_ccr->ciu =3D cmd->ccr.ciu; + new_ccr->icid =3D cntlid; + new_ccr->ctrl =3D ictrl; + list_add_tail(&new_ccr->entry, &sctrl->ccr_list); + +out_unlock: + mutex_unlock(&sctrl->lock); + if (status =3D=3D NVME_SC_SUCCESS) + nvmet_ctrl_fatal_error(ictrl); + nvmet_ctrl_put(ictrl); +out: + nvmet_req_complete(req, status); +} + u32 nvmet_admin_cmd_data_len(struct nvmet_req *req) { struct nvme_command *cmd =3D req->cmd; @@ -1690,6 +1761,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) case nvme_admin_keep_alive: req->execute =3D nvmet_execute_keep_alive; return 0; + case nvme_admin_cross_ctrl_reset: + req->execute =3D nvmet_execute_cross_ctrl_reset; + return 0; default: return nvmet_report_invalid_opcode(req); } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index e8b945a01f35..2e0c31d82bad 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -117,6 +117,20 @@ u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, s= ize_t len) return 0; } =20 +void nvmet_ctrl_cleanup_ccrs(struct nvmet_ctrl *ctrl, bool all) +{ + struct nvmet_ccr *ccr, *tmp; + + lockdep_assert_held(&ctrl->lock); + + list_for_each_entry_safe(ccr, tmp, &ctrl->ccr_list, entry) { + if (all || ccr->ctrl =3D=3D NULL) { + list_del(&ccr->entry); + kfree(ccr); + } + } +} + static u32 nvmet_max_nsid(struct nvmet_subsys *subsys) { struct nvmet_ns *cur; @@ -1399,6 +1413,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) if (!nvmet_is_disc_subsys(ctrl->subsys)) { ctrl->ciu =3D ((u8)(ctrl->ciu + 1)) ? : 1; ctrl->cirn =3D get_random_u64(); + nvmet_ctrl_cleanup_ccrs(ctrl, false); } ctrl->csts =3D NVME_CSTS_RDY; =20 @@ -1504,6 +1519,35 @@ struct nvmet_ctrl *nvmet_ctrl_find_get(const char *s= ubsysnqn, return ctrl; } =20 +struct nvmet_ctrl *nvmet_ctrl_find_get_ccr(struct nvmet_subsys *subsys, + const char *hostnqn, u8 ciu, + u16 cntlid, u64 cirn) +{ + struct nvmet_ctrl *ctrl, *ictrl =3D NULL; + bool found =3D false; + + mutex_lock(&subsys->lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) { + if (ctrl->cntlid !=3D cntlid) + continue; + + /* Avoid racing with a controller that is becoming ready */ + mutex_lock(&ctrl->lock); + if (ctrl->ciu =3D=3D ciu && ctrl->cirn =3D=3D cirn) + found =3D true; + mutex_unlock(&ctrl->lock); + + if (found) { + if (kref_get_unless_zero(&ctrl->ref)) + ictrl =3D ctrl; + break; + } + }; + mutex_unlock(&subsys->lock); + + return ictrl; +} + u16 nvmet_check_ctrl_status(struct nvmet_req *req) { if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) { @@ -1629,6 +1673,7 @@ struct nvmet_ctrl *nvmet_alloc_ctrl(struct nvmet_allo= c_ctrl_args *args) subsys->clear_ids =3D 1; #endif =20 + INIT_LIST_HEAD(&ctrl->ccr_list); INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work); INIT_LIST_HEAD(&ctrl->async_events); INIT_RADIX_TREE(&ctrl->p2p_ns_map, GFP_KERNEL); @@ -1739,12 +1784,43 @@ struct nvmet_ctrl *nvmet_alloc_ctrl(struct nvmet_al= loc_ctrl_args *args) } EXPORT_SYMBOL_GPL(nvmet_alloc_ctrl); =20 +static void nvmet_ctrl_complete_pending_ccr(struct nvmet_ctrl *ctrl) +{ + struct nvmet_subsys *subsys =3D ctrl->subsys; + struct nvmet_ctrl *sctrl; + struct nvmet_ccr *ccr; + + lockdep_assert_held(&subsys->lock); + + /* Cleanup all CCRs issued by ctrl as source controller */ + mutex_lock(&ctrl->lock); + nvmet_ctrl_cleanup_ccrs(ctrl, true); + mutex_unlock(&ctrl->lock); + + /* + * Find all CCRs targeting ctrl as impacted controller and + * set ccr->ctrl to NULL. This tells the source controller + * that CCR completed successfully. + */ + list_for_each_entry(sctrl, &subsys->ctrls, subsys_entry) { + mutex_lock(&sctrl->lock); + list_for_each_entry(ccr, &sctrl->ccr_list, entry) { + if (ccr->ctrl =3D=3D ctrl) { + ccr->ctrl =3D NULL; + break; + } + } + mutex_unlock(&sctrl->lock); + } +} + static void nvmet_ctrl_free(struct kref *ref) { struct nvmet_ctrl *ctrl =3D container_of(ref, struct nvmet_ctrl, ref); struct nvmet_subsys *subsys =3D ctrl->subsys; =20 mutex_lock(&subsys->lock); + nvmet_ctrl_complete_pending_ccr(ctrl); nvmet_ctrl_destroy_pr(ctrl); nvmet_release_p2p_ns_map(ctrl); list_del(&ctrl->subsys_entry); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 2181ac45ae7f..b9eb044ded19 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -268,6 +268,7 @@ struct nvmet_ctrl { u32 kato; u64 cirn; =20 + struct list_head ccr_list; struct nvmet_port *port; =20 u32 aen_enabled; @@ -314,6 +315,13 @@ struct nvmet_ctrl { struct nvmet_pr_log_mgr pr_log_mgr; }; =20 +struct nvmet_ccr { + struct nvmet_ctrl *ctrl; + struct list_head entry; + u16 icid; + u8 ciu; +}; + struct nvmet_subsys { enum nvme_subsys_type type; =20 @@ -577,6 +585,7 @@ void nvmet_req_free_sgls(struct nvmet_req *req); void nvmet_execute_set_features(struct nvmet_req *req); void nvmet_execute_get_features(struct nvmet_req *req); void nvmet_execute_keep_alive(struct nvmet_req *req); +void nvmet_execute_cross_ctrl_reset(struct nvmet_req *req); =20 u16 nvmet_check_cqid(struct nvmet_ctrl *ctrl, u16 cqid, bool create); u16 nvmet_check_io_cqid(struct nvmet_ctrl *ctrl, u16 cqid, bool create); @@ -619,6 +628,10 @@ struct nvmet_ctrl *nvmet_alloc_ctrl(struct nvmet_alloc= _ctrl_args *args); struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid, struct nvmet_req *req); +struct nvmet_ctrl *nvmet_ctrl_find_get_ccr(struct nvmet_subsys *subsys, + const char *hostnqn, u8 ciu, + u16 cntlid, u64 cirn); +void nvmet_ctrl_cleanup_ccrs(struct nvmet_ctrl *ctrl, bool all); void nvmet_ctrl_put(struct nvmet_ctrl *ctrl); u16 nvmet_check_ctrl_status(struct nvmet_req *req); ssize_t nvmet_ctrl_host_traddr(struct nvmet_ctrl *ctrl, diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7746b6d30349..bd3b3f2a5377 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -22,6 +22,7 @@ #define NVMF_TSAS_SIZE 256 =20 #define NVMF_CCR_LIMIT 4 +#define NVMF_CCR_PER_PAGE 511 =20 #define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" =20 @@ -1222,6 +1223,22 @@ struct nvme_zone_mgmt_recv_cmd { __le32 cdw14[2]; }; =20 +struct nvme_cross_ctrl_reset_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __le64 rsvd2[2]; + union nvme_data_ptr dptr; + __le16 icid; + __u8 ciu; + __u8 rsvd10; + __le32 cdw11; + __le64 cirn; + __le32 cdw14; + __le32 cdw15; +}; + struct nvme_io_mgmt_recv_cmd { __u8 opcode; __u8 flags; @@ -1320,6 +1337,7 @@ enum nvme_admin_opcode { nvme_admin_virtual_mgmt =3D 0x1c, nvme_admin_nvme_mi_send =3D 0x1d, nvme_admin_nvme_mi_recv =3D 0x1e, + nvme_admin_cross_ctrl_reset =3D 0x38, nvme_admin_dbbuf =3D 0x7C, nvme_admin_format_nvm =3D 0x80, nvme_admin_security_send =3D 0x81, @@ -1353,6 +1371,7 @@ enum nvme_admin_opcode { nvme_admin_opcode_name(nvme_admin_virtual_mgmt), \ nvme_admin_opcode_name(nvme_admin_nvme_mi_send), \ nvme_admin_opcode_name(nvme_admin_nvme_mi_recv), \ + nvme_admin_opcode_name(nvme_admin_cross_ctrl_reset), \ nvme_admin_opcode_name(nvme_admin_dbbuf), \ nvme_admin_opcode_name(nvme_admin_format_nvm), \ nvme_admin_opcode_name(nvme_admin_security_send), \ @@ -2006,6 +2025,7 @@ struct nvme_command { struct nvme_dbbuf dbbuf; struct nvme_directive_cmd directive; struct nvme_io_mgmt_recv_cmd imr; + struct nvme_cross_ctrl_reset_cmd ccr; }; }; =20 @@ -2170,6 +2190,9 @@ enum { NVME_SC_PMR_SAN_PROHIBITED =3D 0x123, NVME_SC_ANA_GROUP_ID_INVALID =3D 0x124, NVME_SC_ANA_ATTACH_FAILED =3D 0x125, + NVME_SC_CCR_IN_PROGRESS =3D 0x13f, + NVME_SC_CCR_LOGPAGE_FULL =3D 0x140, + NVME_SC_CCR_LIMIT_EXCEEDED =3D 0x141, =20 /* * I/O Command Set Specific - NVM commands: --=20 2.52.0