From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Ming Lei To: Keith Busch Cc: Jens Axboe , linux-block@vger.kernel.org, Ming Lei , James Smart , Jianchao Wang , Christoph Hellwig , Sagi Grimberg , linux-nvme@lists.infradead.org, Laurence Oberman Subject: [PATCH V5 5/9] nvme: pci: prepare for supporting error recovery from resetting context Date: Fri, 11 May 2018 20:29:29 +0800 Message-Id: <20180511122933.27155-6-ming.lei@redhat.com> In-Reply-To: <20180511122933.27155-1-ming.lei@redhat.com> References: <20180511122933.27155-1-ming.lei@redhat.com> List-ID: Either the admin or normal IO in reset context may be timed out because controller error happens. When this timeout happens, we may have to start controller recovery again. This patch introduces 'reset_lock' and holds this lock when running reset, so that we may support nested reset in the following patches. Cc: James Smart Cc: Jianchao Wang Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: linux-nvme@lists.infradead.org Cc: Laurence Oberman Signed-off-by: Ming Lei --- drivers/nvme/host/core.c | 2 ++ drivers/nvme/host/nvme.h | 3 +++ drivers/nvme/host/pci.c | 20 +++++++++++++++++--- 3 files changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a3771c5729f5..adb1743e87f7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3424,6 +3424,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work); + mutex_init(&ctrl->reset_lock); + ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL); if (ret < 0) goto out; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 7ded7a51c430..021f7147f779 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -146,6 +146,9 @@ struct nvme_ctrl { struct device ctrl_device; struct device *device; /* char device */ struct cdev cdev; + + /* sync reset activities */ + struct mutex reset_lock; struct work_struct reset_work; struct work_struct delete_work; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1fafe5d01355..a924246ffdb6 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2365,14 +2365,14 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) nvme_put_ctrl(&dev->ctrl); } -static void nvme_reset_work(struct work_struct *work) +static void nvme_reset_dev(struct nvme_dev *dev) { - struct nvme_dev *dev = - container_of(work, struct nvme_dev, ctrl.reset_work); bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result = -ENODEV; enum nvme_ctrl_state new_state = NVME_CTRL_LIVE; + lockdep_assert_held(&dev->ctrl.reset_lock); + if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) goto out; @@ -2448,7 +2448,11 @@ static void nvme_reset_work(struct work_struct *work) new_state = NVME_CTRL_ADMIN_ONLY; } else { nvme_start_queues(&dev->ctrl); + mutex_unlock(&dev->ctrl.reset_lock); + nvme_wait_freeze(&dev->ctrl); + + mutex_lock(&dev->ctrl.reset_lock); /* hit this only when allocate tagset fails */ if (nvme_dev_add(dev)) new_state = NVME_CTRL_ADMIN_ONLY; @@ -2472,6 +2476,16 @@ static void nvme_reset_work(struct work_struct *work) nvme_remove_dead_ctrl(dev, result); } +static void nvme_reset_work(struct work_struct *work) +{ + struct nvme_dev *dev = + container_of(work, struct nvme_dev, ctrl.reset_work); + + mutex_lock(&dev->ctrl.reset_lock); + nvme_reset_dev(dev); + mutex_unlock(&dev->ctrl.reset_lock); +} + static void nvme_remove_dead_ctrl_work(struct work_struct *work) { struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work); -- 2.9.5 From mboxrd@z Thu Jan 1 00:00:00 1970 From: ming.lei@redhat.com (Ming Lei) Date: Fri, 11 May 2018 20:29:29 +0800 Subject: [PATCH V5 5/9] nvme: pci: prepare for supporting error recovery from resetting context In-Reply-To: <20180511122933.27155-1-ming.lei@redhat.com> References: <20180511122933.27155-1-ming.lei@redhat.com> Message-ID: <20180511122933.27155-6-ming.lei@redhat.com> Either the admin or normal IO in reset context may be timed out because controller error happens. When this timeout happens, we may have to start controller recovery again. This patch introduces 'reset_lock' and holds this lock when running reset, so that we may support nested reset in the following patches. Cc: James Smart Cc: Jianchao Wang Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: linux-nvme at lists.infradead.org Cc: Laurence Oberman Signed-off-by: Ming Lei --- drivers/nvme/host/core.c | 2 ++ drivers/nvme/host/nvme.h | 3 +++ drivers/nvme/host/pci.c | 20 +++++++++++++++++--- 3 files changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a3771c5729f5..adb1743e87f7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3424,6 +3424,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work); + mutex_init(&ctrl->reset_lock); + ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL); if (ret < 0) goto out; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 7ded7a51c430..021f7147f779 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -146,6 +146,9 @@ struct nvme_ctrl { struct device ctrl_device; struct device *device; /* char device */ struct cdev cdev; + + /* sync reset activities */ + struct mutex reset_lock; struct work_struct reset_work; struct work_struct delete_work; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1fafe5d01355..a924246ffdb6 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2365,14 +2365,14 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) nvme_put_ctrl(&dev->ctrl); } -static void nvme_reset_work(struct work_struct *work) +static void nvme_reset_dev(struct nvme_dev *dev) { - struct nvme_dev *dev = - container_of(work, struct nvme_dev, ctrl.reset_work); bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL); int result = -ENODEV; enum nvme_ctrl_state new_state = NVME_CTRL_LIVE; + lockdep_assert_held(&dev->ctrl.reset_lock); + if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) goto out; @@ -2448,7 +2448,11 @@ static void nvme_reset_work(struct work_struct *work) new_state = NVME_CTRL_ADMIN_ONLY; } else { nvme_start_queues(&dev->ctrl); + mutex_unlock(&dev->ctrl.reset_lock); + nvme_wait_freeze(&dev->ctrl); + + mutex_lock(&dev->ctrl.reset_lock); /* hit this only when allocate tagset fails */ if (nvme_dev_add(dev)) new_state = NVME_CTRL_ADMIN_ONLY; @@ -2472,6 +2476,16 @@ static void nvme_reset_work(struct work_struct *work) nvme_remove_dead_ctrl(dev, result); } +static void nvme_reset_work(struct work_struct *work) +{ + struct nvme_dev *dev = + container_of(work, struct nvme_dev, ctrl.reset_work); + + mutex_lock(&dev->ctrl.reset_lock); + nvme_reset_dev(dev); + mutex_unlock(&dev->ctrl.reset_lock); +} + static void nvme_remove_dead_ctrl_work(struct work_struct *work) { struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work); -- 2.9.5