From dc1a0afbacaeaced8f5679a99047c0467f1099e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 14 Jul 2017 11:12:09 +0200 Subject: nvme: fix byte swapping in the streams code Signed-off-by: Christoph Hellwig Reviewed-by: Jens Axboe Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index cb96f4a7ae3a..3b77cfe5aa1e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -336,7 +336,7 @@ static int nvme_get_stream_params(struct nvme_ctrl *ctrl, c.directive.opcode = nvme_admin_directive_recv; c.directive.nsid = cpu_to_le32(nsid); - c.directive.numd = sizeof(*s); + c.directive.numd = cpu_to_le32(sizeof(*s)); c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM; c.directive.dtype = NVME_DIR_STREAMS; -- cgit v1.2.1 From 6484f5d16f9d5368afac61091972242f3bd695a9 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 12 Jul 2017 15:38:56 +0200 Subject: nvme: also provide a UUID in the WWID sysfs attribute The WWID sysfs attribute can provide multiple means of a World Wide ID for a NVMe device. It can either be a NGUID, a EUI-64 or a concatenation of VID, Serial Number, Model and the Namespace ID in this order of preference. If the target also sends us a UUID use the UUID for identification and give it the highest priority. This eases generation of /dev/disk/by-* symlinks. Signed-off-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3b77cfe5aa1e..4cacab331f2a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1995,6 +1995,9 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, int serial_len = sizeof(ctrl->serial); int model_len = sizeof(ctrl->model); + if (!uuid_is_null(&ns->uuid)) + return sprintf(buf, "uuid.%pU\n", &ns->uuid); + if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) return sprintf(buf, "eui.%16phN\n", ns->nguid); -- cgit v1.2.1 From 7dd1ab163c17e11473a65b11f7e748db30618ebb Mon Sep 17 00:00:00 2001 From: Scott Bauer Date: Tue, 25 Jul 2017 10:27:06 -0600 Subject: nvme: validate admin queue before unquiesce With a misbehaving controller it's possible we'll never enter the live state and create an admin queue. When we fail out of reset work it's possible we failed out early enough without setting up the admin queue. We tear down queues after a failed reset, but needed to do some more sanitization. Fixes 443bd90f2cca: "nvme: host: unquiesce queue in nvme_kill_queues()" [ 189.650995] nvme nvme1: pci function 0000:0b:00.0 [ 317.680055] nvme nvme0: Device not ready; aborting reset [ 317.680183] nvme nvme0: Removing after probe failure status: -19 [ 317.681258] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 317.681397] general protection fault: 0000 [#1] SMP KASAN [ 317.682984] CPU: 3 PID: 477 Comm: kworker/3:2 Not tainted 4.13.0-rc1+ #5 [ 317.683112] Hardware name: Gigabyte Technology Co., Ltd. Z170X-UD5/Z170X-UD5-CF, BIOS F5 03/07/2016 [ 317.683284] Workqueue: events nvme_remove_dead_ctrl_work [nvme] [ 317.683398] task: ffff8803b0990000 task.stack: ffff8803c2ef0000 [ 317.683516] RIP: 0010:blk_mq_unquiesce_queue+0x2b/0xa0 [ 317.683614] RSP: 0018:ffff8803c2ef7d40 EFLAGS: 00010282 [ 317.683716] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 1ffff1006fbdcde3 [ 317.683847] RDX: 0000000000000038 RSI: 1ffff1006f5a9245 RDI: 0000000000000000 [ 317.683978] RBP: ffff8803c2ef7d58 R08: 1ffff1007bcdc974 R09: 0000000000000000 [ 317.684108] R10: 1ffff1007bcdc975 R11: 0000000000000000 R12: 00000000000001c0 [ 317.684239] R13: ffff88037ad49228 R14: ffff88037ad492d0 R15: ffff88037ad492e0 [ 317.684371] FS: 0000000000000000(0000) GS:ffff8803de6c0000(0000) knlGS:0000000000000000 [ 317.684519] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 317.684627] CR2: 0000002d1860c000 CR3: 000000045b40d000 CR4: 00000000003406e0 [ 317.684758] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 317.684888] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 317.685018] Call Trace: [ 317.685084] nvme_kill_queues+0x4d/0x170 [nvme_core] [ 317.685185] nvme_remove_dead_ctrl_work+0x3a/0x90 [nvme] [ 317.685289] process_one_work+0x771/0x1170 [ 317.685372] worker_thread+0xde/0x11e0 [ 317.685452] ? pci_mmcfg_check_reserved+0x110/0x110 [ 317.685550] kthread+0x2d3/0x3d0 [ 317.685617] ? process_one_work+0x1170/0x1170 [ 317.685704] ? kthread_create_on_node+0xc0/0xc0 [ 317.685785] ret_from_fork+0x25/0x30 [ 317.685798] Code: 0f 1f 44 00 00 55 48 b8 00 00 00 00 00 fc ff df 48 89 e5 41 54 4c 8d a7 c0 01 00 00 53 48 89 fb 4c 89 e2 48 c1 ea 03 48 83 ec 08 <80> 3c 02 00 75 50 48 8b bb c0 01 00 00 e8 33 8a f9 00 0f ba b3 [ 317.685872] RIP: blk_mq_unquiesce_queue+0x2b/0xa0 RSP: ffff8803c2ef7d40 [ 317.685908] ---[ end trace a3f8704150b1e8b4 ]--- Signed-off-by: Scott Bauer Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 4cacab331f2a..c49f1f8b2e57 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2712,7 +2712,8 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) mutex_lock(&ctrl->namespaces_mutex); /* Forcibly unquiesce queues to avoid blocking dispatch */ - blk_mq_unquiesce_queue(ctrl->admin_q); + if (ctrl->admin_q) + blk_mq_unquiesce_queue(ctrl->admin_q); list_for_each_entry(ns, &ctrl->namespaces, list) { /* -- cgit v1.2.1 From 758f3735580c21b8a36d644128af6608120a1dde Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Thu, 20 Jul 2017 18:34:02 +0200 Subject: nvme: strip trailing 0-bytes in wwid_show Some broken controllers (such as earlier Linux targets) pad model or serial fields with 0-bytes rather than spaces. The NVMe spec disallows 0 bytes in "ASCII" fields. Thus strip trailing 0-bytes, too. Also make sure that we get no underflow for pathological input. Signed-off-by: Martin Wilck Reviewed-by: Hannes Reinecke Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c49f1f8b2e57..1e9290983694 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2004,9 +2004,11 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, if (memchr_inv(ns->eui, 0, sizeof(ns->eui))) return sprintf(buf, "eui.%8phN\n", ns->eui); - while (ctrl->serial[serial_len - 1] == ' ') + while (serial_len > 0 && (ctrl->serial[serial_len - 1] == ' ' || + ctrl->serial[serial_len - 1] == '\0')) serial_len--; - while (ctrl->model[model_len - 1] == ' ') + while (model_len > 0 && (ctrl->model[model_len - 1] == ' ' || + ctrl->model[model_len - 1] == '\0')) model_len--; return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid, -- cgit v1.2.1 From 634b8325905031eeafa61951623681ebc1329385 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 10 Aug 2017 11:23:31 +0200 Subject: nvme: fix nvme reset command timeout handling We need to return an error if a timeout occurs on any NVMe command during initialization. Without this, the nvme reset work will be stuck. A timeout will have a negative error code, meaning we need to stop initializing the controller. All postitive returns mean the controller is still usable. bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196325 Signed-off-by: Keith Busch Cc: Martin Peres [jth consolidated cleanup path ] Signed-off-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 1e9290983694..6212cf4e9829 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1509,7 +1509,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, blk_queue_write_cache(q, vwc, vwc); } -static void nvme_configure_apst(struct nvme_ctrl *ctrl) +static int nvme_configure_apst(struct nvme_ctrl *ctrl) { /* * APST (Autonomous Power State Transition) lets us program a @@ -1538,16 +1538,16 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) * then don't do anything. */ if (!ctrl->apsta) - return; + return 0; if (ctrl->npss > 31) { dev_warn(ctrl->device, "NPSS is invalid; not using APST\n"); - return; + return 0; } table = kzalloc(sizeof(*table), GFP_KERNEL); if (!table) - return; + return 0; if (!ctrl->apst_enabled || ctrl->ps_max_latency_us == 0) { /* Turn off APST. */ @@ -1629,6 +1629,7 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl) dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret); kfree(table); + return ret; } static void nvme_set_latency_tolerance(struct device *dev, s32 val) @@ -1835,13 +1836,16 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) * In fabrics we need to verify the cntlid matches the * admin connect */ - if (ctrl->cntlid != le16_to_cpu(id->cntlid)) + if (ctrl->cntlid != le16_to_cpu(id->cntlid)) { ret = -EINVAL; + goto out_free; + } if (!ctrl->opts->discovery_nqn && !ctrl->kas) { dev_err(ctrl->device, "keep-alive support is mandatory for fabrics\n"); ret = -EINVAL; + goto out_free; } } else { ctrl->cntlid = le16_to_cpu(id->cntlid); @@ -1856,11 +1860,20 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - nvme_configure_apst(ctrl); - nvme_configure_directives(ctrl); + ret = nvme_configure_apst(ctrl); + if (ret < 0) + return ret; + + ret = nvme_configure_directives(ctrl); + if (ret < 0) + return ret; ctrl->identified = true; + return 0; + +out_free: + kfree(id); return ret; } EXPORT_SYMBOL_GPL(nvme_init_identify); -- cgit v1.2.1 From a082b426286d1ead97fb87646ea361d528be023d Mon Sep 17 00:00:00 2001 From: "Kwan (Hingkwan) Huen-SSI" Date: Wed, 9 Aug 2017 11:26:29 -0700 Subject: nvme: fix directive command numd calculation The numd field of directive receive command takes number of dwords to transfer. This fix has the correct calculation for numd. Signed-off-by: Kwan (Hingkwan) Huen-SSI Reviewed-by: Jens Axboe Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6212cf4e9829..37046ac2c441 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -336,7 +336,7 @@ static int nvme_get_stream_params(struct nvme_ctrl *ctrl, c.directive.opcode = nvme_admin_directive_recv; c.directive.nsid = cpu_to_le32(nsid); - c.directive.numd = cpu_to_le32(sizeof(*s)); + c.directive.numd = cpu_to_le32((sizeof(*s) >> 2) - 1); c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM; c.directive.dtype = NVME_DIR_STREAMS; -- cgit v1.2.1