From 4739824e2d7878dcea88397a6758e31e3c5c124e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 15 Oct 2022 11:25:56 +0300 Subject: nvme: fix error pointer dereference in error handling There is typo here so it releases the wrong variable. "ctrl->admin_q" was intended instead of "ctrl->fabrics_q". Fixes: fe60e8c53411 ("nvme: add common helpers to allocate and free tagsets") Signed-off-by: Dan Carpenter Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 059737c1a2c1..9cbe7854d488 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4846,7 +4846,7 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, return 0; out_cleanup_admin_q: - blk_mq_destroy_queue(ctrl->fabrics_q); + blk_mq_destroy_queue(ctrl->admin_q); out_free_tagset: blk_mq_free_tag_set(ctrl->admin_tagset); return ret; -- cgit v1.2.3-58-ga151 From ac9b57d4e1e3ecf0122e915bbba1bd4c90ec3031 Mon Sep 17 00:00:00 2001 From: Xander Li Date: Tue, 11 Oct 2022 04:06:42 -0700 Subject: nvme-pci: disable write zeroes on various Kingston SSD Kingston SSDs do support NVMe Write_Zeroes cmd but take long time to process. The firmware version is locked by these SSDs, we can not expect firmware improvement, so disable Write_Zeroes cmd. Signed-off-by: Xander Li Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index bcbef6bc5672..31e577b01257 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3511,6 +3511,16 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x2646, 0x5018), /* KINGSTON OM8SFP4xxxxP OS21012 NVMe SSD */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x2646, 0x5016), /* KINGSTON OM3PGP4xxxxP OS21011 NVMe SSD */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x2646, 0x501A), /* KINGSTON OM8PGP4xxxxP OS21005 NVMe SSD */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x2646, 0x501B), /* KINGSTON OM8PGP4xxxxQ OS21005 NVMe SSD */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x2646, 0x501E), /* KINGSTON OM3PGP4xxxxQ OS21011 NVMe SSD */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1e4B, 0x1001), /* MAXIO MAP1001 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1e4B, 0x1002), /* MAXIO MAP1002 */ -- cgit v1.2.3-58-ga151 From d622f8477a8018974f8df961440dca58224f9c6b Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 12 Oct 2022 12:46:06 +0100 Subject: nvme-apple: don't limit DMA segement size NVMe uses PRPs for data transfers and has no specific limit for a single DMA segement. Limiting the size will cause problems because the block layer assumes PRP-ish devices using a virt boundary mask don't have a segment limit. And while this is true, we also really need to tell the DMA mapping layer about it, otherwise dma-debug will trip over it. Fixes: 5bd2927aceba ("nvme-apple: Add initial Apple SoC NVMe driver") Suggested-by: Sven Peter Signed-off-by: Russell King (Oracle) [hch: rewrote the commit message based on the PCIe commit] Signed-off-by: Christoph Hellwig Reviewed-by: Eric Curtin Reviewed-by: Sven Peter --- drivers/nvme/host/apple.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers') diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 5fc5ea196b40..ff8b083dc5c6 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1039,6 +1039,8 @@ static void apple_nvme_reset_work(struct work_struct *work) dma_max_mapping_size(anv->dev) >> 9); anv->ctrl.max_segments = NVME_MAX_SEGS; + dma_set_max_seg_size(anv->dev, 0xffffffff); + /* * Enable NVMMU and linear submission queues. * While we could keep those disabled and pretend this is slightly -- cgit v1.2.3-58-ga151 From 6b8cf94005187952f794c0c4ed3920a1e8accfa3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 18 Oct 2022 16:55:55 +0200 Subject: nvme-hwmon: consistently ignore errors from nvme_hwmon_init An NVMe controller works perfectly fine even when the hwmon initialization fails. Stop returning errors that do not come from a controller reset from nvme_hwmon_init to handle this case consistently. Signed-off-by: Christoph Hellwig Reviewed-by: Guenter Roeck Reviewed-by: Serge Semin --- drivers/nvme/host/core.c | 6 +++++- drivers/nvme/host/hwmon.c | 13 ++++++++----- 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9cbe7854d488..dc4220600585 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3262,8 +3262,12 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl) return ret; if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) { + /* + * Do not return errors unless we are in a controller reset, + * the controller works perfectly fine without hwmon. + */ ret = nvme_hwmon_init(ctrl); - if (ret < 0) + if (ret == -EINTR) return ret; } diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 0a586d712920..23918bb7bdca 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -230,7 +230,7 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) - return 0; + return -ENOMEM; data->ctrl = ctrl; mutex_init(&data->read_lock); @@ -238,8 +238,7 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) err = nvme_hwmon_get_smart_log(data); if (err) { dev_warn(dev, "Failed to read smart log (error %d)\n", err); - kfree(data); - return err; + goto err_free_data; } hwmon = hwmon_device_register_with_info(dev, "nvme", @@ -247,11 +246,15 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) NULL); if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); - kfree(data); - return PTR_ERR(hwmon); + err = PTR_ERR(hwmon); + goto err_free_data; } ctrl->hwmon_device = hwmon; return 0; + +err_free_data: + kfree(data); + return err; } void nvme_hwmon_exit(struct nvme_ctrl *ctrl) -- cgit v1.2.3-58-ga151 From c94b7f9bab22ac504f9153767676e659988575ad Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Tue, 18 Oct 2022 17:33:52 +0200 Subject: nvme-hwmon: kmalloc the NVME SMART log buffer Recent commit 52fde2c07da6 ("nvme: set dma alignment to dword") has caused a regression on our platform. It turned out that the nvme_get_log() method invocation caused the nvme_hwmon_data structure instance corruption. In particular the nvme_hwmon_data.ctrl pointer was overwritten either with zeros or with garbage. After some research we discovered that the problem happened even before the actual NVME DMA execution, but during the buffer mapping. Since our platform is DMA-noncoherent, the mapping implied the cache-line invalidations or write-backs depending on the DMA-direction parameter. In case of the NVME SMART log getting the DMA was performed from-device-to-memory, thus the cache-invalidation was activated during the buffer mapping. Since the log-buffer isn't cache-line aligned, the cache-invalidation caused the neighbour data to be discarded. The neighbouring data turned to be the data surrounding the buffer in the framework of the nvme_hwmon_data structure. In order to fix that we need to make sure that the whole log-buffer is defined within the cache-line-aligned memory region so the cache-invalidation procedure wouldn't involve the adjacent data. One of the option to guarantee that is to kmalloc the DMA-buffer [1]. Seeing the rest of the NVME core driver prefer that method it has been chosen to fix this problem too. Note after a deeper researches we found out that the denoted commit wasn't a root cause of the problem. It just revealed the invalidity by activating the DMA-based NVME SMART log getting performed in the framework of the NVME hwmon driver. The problem was here since the initial commit of the driver. [1] Documentation/core-api/dma-api-howto.rst Fixes: 400b6a7b13a3 ("nvme: Add hardware monitoring support") Signed-off-by: Serge Semin Signed-off-by: Christoph Hellwig --- drivers/nvme/host/hwmon.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) (limited to 'drivers') diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 23918bb7bdca..9e6e56c20ec9 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -12,7 +12,7 @@ struct nvme_hwmon_data { struct nvme_ctrl *ctrl; - struct nvme_smart_log log; + struct nvme_smart_log *log; struct mutex read_lock; }; @@ -60,14 +60,14 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) { return nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, - NVME_CSI_NVM, &data->log, sizeof(data->log), 0); + NVME_CSI_NVM, data->log, sizeof(*data->log), 0); } static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { struct nvme_hwmon_data *data = dev_get_drvdata(dev); - struct nvme_smart_log *log = &data->log; + struct nvme_smart_log *log = data->log; int temp; int err; @@ -163,7 +163,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log.temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1])) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; @@ -176,7 +176,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data, break; case hwmon_temp_input: case hwmon_temp_label: - if (!channel || data->log.temp_sensor[channel - 1]) + if (!channel || data->log->temp_sensor[channel - 1]) return 0444; break; default: @@ -232,13 +232,19 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) if (!data) return -ENOMEM; + data->log = kzalloc(sizeof(*data->log), GFP_KERNEL); + if (!data->log) { + err = -ENOMEM; + goto err_free_data; + } + data->ctrl = ctrl; mutex_init(&data->read_lock); err = nvme_hwmon_get_smart_log(data); if (err) { dev_warn(dev, "Failed to read smart log (error %d)\n", err); - goto err_free_data; + goto err_free_log; } hwmon = hwmon_device_register_with_info(dev, "nvme", @@ -247,11 +253,13 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); err = PTR_ERR(hwmon); - goto err_free_data; + goto err_free_log; } ctrl->hwmon_device = hwmon; return 0; +err_free_log: + kfree(data->log); err_free_data: kfree(data); return err; @@ -265,6 +273,7 @@ void nvme_hwmon_exit(struct nvme_ctrl *ctrl) hwmon_device_unregister(ctrl->hwmon_device); ctrl->hwmon_device = NULL; + kfree(data->log); kfree(data); } } -- cgit v1.2.3-58-ga151 From ddd2b8de9f85b388925e7dc46b3890fc1a0d8d24 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 28 Sep 2022 09:39:10 +0300 Subject: nvmet: fix workqueue MEM_RECLAIM flushing dependency The keep alive timer needs to stay on nvmet_wq, and not modified to reschedule on the system_wq. This fixes a warning: ------------[ cut here ]------------ workqueue: WQ_MEM_RECLAIM nvmet-wq:nvmet_rdma_release_queue_work [nvmet_rdma] is flushing !WQ_MEM_RECLAIM events:nvmet_keep_alive_timer [nvmet] WARNING: CPU: 3 PID: 1086 at kernel/workqueue.c:2628 check_flush_dependency+0x16c/0x1e0 Reported-by: Yi Zhang Fixes: 8832cf922151 ("nvmet: use a private workqueue instead of the system workqueue") Signed-off-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/target/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 14677145bbba..aecb5853f8da 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1176,7 +1176,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) * reset the keep alive timer when the controller is enabled. */ if (ctrl->kato) - mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ); + mod_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ); } static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl) -- cgit v1.2.3-58-ga151 From 94f5a06884074dcd99606d7b329e133ee65ea6ad Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Fri, 7 Oct 2022 09:29:34 +0200 Subject: nvmet: fix invalid memory reference in nvmet_subsys_attr_qid_max_show The item passed into nvmet_subsys_attr_qid_max_show is not a member of struct nvmet_port, it is part of nvmet_subsys. Hence, don't try to dereference it as struct nvme_ctrl pointer. Fixes: 3e980f5995e0 ("nvmet: Expose max queues to configfs") Reported-by: Shinichiro Kawasaki Link: https://lore.kernel.org/r/20220913064203.133536-1-dwagner@suse.de Signed-off-by: Daniel Wagner Reviewed-by: Hannes Reinecke Acked-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/target/configfs.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'drivers') diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index e34a2896fedb..9443ee1d4ae3 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1290,12 +1290,8 @@ static ssize_t nvmet_subsys_attr_qid_max_show(struct config_item *item, static ssize_t nvmet_subsys_attr_qid_max_store(struct config_item *item, const char *page, size_t cnt) { - struct nvmet_port *port = to_nvmet_port(item); u16 qid_max; - if (nvmet_is_port_enabled(port, __func__)) - return -EACCES; - if (sscanf(page, "%hu\n", &qid_max) != 1) return -EINVAL; -- cgit v1.2.3-58-ga151