From c6ea70604249bc357ce09e9f8e16c29df0fb2fa2 Mon Sep 17 00:00:00 2001 From: "dougmill@linux.vnet.ibm.com" Date: Tue, 16 Aug 2022 15:07:13 +0100 Subject: block: sed-opal: Add ioctl to return device status Provide a mechanism to retrieve basic status information about the device, including the "supported" flag indicating whether SED-OPAL is supported. The information returned is from the various feature descriptors received during the discovery0 step, and so this ioctl does nothing more than perform the discovery0 step and then save the information received. See "struct opal_status" and OPAL_FL_* bits for the status information currently returned. This is necessary to be able to check whether a device is OPAL enabled, set up, locked or unlocked from userspace programs like systemd-cryptsetup and libcryptsetup. Right now we just have to assume the user 'knows' or blindly attempt setup/lock/unlock operations. Signed-off-by: Douglas Miller Tested-by: Luca Boccassi Reviewed-by: Scott Bauer Acked-by: Christian Brauner (Microsoft) Link: https://lore.kernel.org/r/20220816140713.84893-1-luca.boccassi@gmail.com Signed-off-by: Jens Axboe --- include/linux/sed-opal.h | 1 + include/uapi/linux/sed-opal.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 1ac0d712a9c3..6f837bb6c715 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -43,6 +43,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_MBR_DONE: case IOC_OPAL_WRITE_SHADOW_MBR: case IOC_OPAL_GENERIC_TABLE_RW: + case IOC_OPAL_GET_STATUS: return true; } return false; diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index 6f5af1a84213..2573772e2fb3 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -132,6 +132,18 @@ struct opal_read_write_table { __u64 priv; }; +#define OPAL_FL_SUPPORTED 0x00000001 +#define OPAL_FL_LOCKING_SUPPORTED 0x00000002 +#define OPAL_FL_LOCKING_ENABLED 0x00000004 +#define OPAL_FL_LOCKED 0x00000008 +#define OPAL_FL_MBR_ENABLED 0x00000010 +#define OPAL_FL_MBR_DONE 0x00000020 + +struct opal_status { + __u32 flags; + __u32 reserved; +}; + #define IOC_OPAL_SAVE _IOW('p', 220, struct opal_lock_unlock) #define IOC_OPAL_LOCK_UNLOCK _IOW('p', 221, struct opal_lock_unlock) #define IOC_OPAL_TAKE_OWNERSHIP _IOW('p', 222, struct opal_key) @@ -148,5 +160,6 @@ struct opal_read_write_table { #define IOC_OPAL_MBR_DONE _IOW('p', 233, struct opal_mbr_done) #define IOC_OPAL_WRITE_SHADOW_MBR _IOW('p', 234, struct opal_shadow_mbr) #define IOC_OPAL_GENERIC_TABLE_RW _IOW('p', 235, struct opal_read_write_table) +#define IOC_OPAL_GET_STATUS _IOR('p', 236, struct opal_status) #endif /* _UAPI_SED_OPAL_H */ -- cgit v1.2.3 From a4e1d0b76e7b32c0839e72679c530445172a2564 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 15 Aug 2022 10:00:43 -0700 Subject: block: Change the return type of blk_mq_map_queues() into void Since blk_mq_map_queues() and the .map_queues() callbacks always return 0, change their return type into void. Most callers ignore the returned value anyway. Cc: Christoph Hellwig Cc: Jason Wang Cc: Keith Busch Cc: Martin K. Petersen Cc: Doug Gilbert Cc: Michael S. Tsirkin Signed-off-by: Bart Van Assche Reviewed-by: John Garry Acked-by: Md Haris Iqbal Reviewed-by: Sagi Grimberg Link: https://lore.kernel.org/r/20220815170043.19489-3-bvanassche@acm.org [axboe: fold in fix from Bart] Signed-off-by: Jens Axboe --- block/blk-mq-cpumap.c | 4 +--- block/blk-mq-pci.c | 7 +++---- block/blk-mq-rdma.c | 6 +++--- block/blk-mq-virtio.c | 7 ++++--- block/blk-mq.c | 10 ++++------ drivers/block/null_blk/main.c | 4 +--- drivers/block/rnbd/rnbd-clt.c | 4 +--- drivers/block/virtio_blk.c | 4 +--- drivers/nvme/host/fc.c | 3 +-- drivers/nvme/host/pci.c | 4 +--- drivers/nvme/host/rdma.c | 4 +--- drivers/nvme/host/tcp.c | 4 +--- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 5 +---- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 5 ++--- drivers/scsi/megaraid/megaraid_sas_base.c | 6 ++---- drivers/scsi/mpi3mr/mpi3mr_os.c | 5 +---- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 5 ++--- drivers/scsi/pm8001/pm8001_init.c | 2 +- drivers/scsi/qla2xxx/qla_nvme.c | 6 +----- drivers/scsi/qla2xxx/qla_os.c | 10 ++++------ drivers/scsi/scsi_debug.c | 7 ++----- drivers/scsi/scsi_lib.c | 4 ++-- drivers/scsi/smartpqi/smartpqi_init.c | 6 +++--- drivers/scsi/virtio_scsi.c | 4 ++-- drivers/ufs/core/ufshcd.c | 9 +++------ include/linux/blk-mq-pci.h | 4 ++-- include/linux/blk-mq-rdma.h | 2 +- include/linux/blk-mq-virtio.h | 2 +- include/linux/blk-mq.h | 4 ++-- include/scsi/scsi_host.h | 2 +- 30 files changed, 55 insertions(+), 94 deletions(-) (limited to 'include') diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 3db84d3197f1..9c2fce1a7b50 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -32,7 +32,7 @@ static int get_first_sibling(unsigned int cpu) return cpu; } -int blk_mq_map_queues(struct blk_mq_queue_map *qmap) +void blk_mq_map_queues(struct blk_mq_queue_map *qmap) { unsigned int *map = qmap->mq_map; unsigned int nr_queues = qmap->nr_queues; @@ -70,8 +70,6 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap) map[cpu] = map[first_sibling]; } } - - return 0; } EXPORT_SYMBOL_GPL(blk_mq_map_queues); diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c index b595a94c4d16..a90b88fd1332 100644 --- a/block/blk-mq-pci.c +++ b/block/blk-mq-pci.c @@ -23,8 +23,8 @@ * that maps a queue to the CPUs that have irq affinity for the corresponding * vector. */ -int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset) +void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, + int offset) { const struct cpumask *mask; unsigned int queue, cpu; @@ -38,11 +38,10 @@ int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, qmap->mq_map[cpu] = qmap->queue_offset + queue; } - return 0; + return; fallback: WARN_ON_ONCE(qmap->nr_queues > 1); blk_mq_clear_mq_map(qmap); - return 0; } EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues); diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c index 14f968e58b8f..29c1f4d6eb04 100644 --- a/block/blk-mq-rdma.c +++ b/block/blk-mq-rdma.c @@ -21,7 +21,7 @@ * @set->nr_hw_queues, or @dev does not provide an affinity mask for a * vector, we fallback to the naive mapping. */ -int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, +void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, struct ib_device *dev, int first_vec) { const struct cpumask *mask; @@ -36,9 +36,9 @@ int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, map->mq_map[cpu] = map->queue_offset + queue; } - return 0; + return; fallback: - return blk_mq_map_queues(map); + blk_mq_map_queues(map); } EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues); diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c index 7b8a42c35102..6589f076a096 100644 --- a/block/blk-mq-virtio.c +++ b/block/blk-mq-virtio.c @@ -21,7 +21,7 @@ * that maps a queue to the CPUs that have irq affinity for the corresponding * vector. */ -int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, +void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, struct virtio_device *vdev, int first_vec) { const struct cpumask *mask; @@ -39,8 +39,9 @@ int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, qmap->mq_map[cpu] = qmap->queue_offset + queue; } - return 0; + return; + fallback: - return blk_mq_map_queues(qmap); + blk_mq_map_queues(qmap); } EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues); diff --git a/block/blk-mq.c b/block/blk-mq.c index 3c1e6b6d991d..4b90d2d8cfb0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4190,7 +4190,7 @@ static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set) return 0; } -static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) +static void blk_mq_update_queue_map(struct blk_mq_tag_set *set) { /* * blk_mq_map_queues() and multiple .map_queues() implementations @@ -4220,10 +4220,10 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) for (i = 0; i < set->nr_maps; i++) blk_mq_clear_mq_map(&set->map[i]); - return set->ops->map_queues(set); + set->ops->map_queues(set); } else { BUG_ON(set->nr_maps > 1); - return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } } @@ -4322,9 +4322,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues; } - ret = blk_mq_update_queue_map(set); - if (ret) - goto out_free_mq_map; + blk_mq_update_queue_map(set); ret = blk_mq_alloc_set_map_and_rqs(set); if (ret) diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 535059209693..1f154f92f4c2 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1528,7 +1528,7 @@ static bool should_requeue_request(struct request *rq) return false; } -static int null_map_queues(struct blk_mq_tag_set *set) +static void null_map_queues(struct blk_mq_tag_set *set) { struct nullb *nullb = set->driver_data; int i, qoff; @@ -1579,8 +1579,6 @@ static int null_map_queues(struct blk_mq_tag_set *set) qoff += map->nr_queues; blk_mq_map_queues(map); } - - return 0; } static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 04da33a22ef4..9d01e7ab33e4 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1165,7 +1165,7 @@ static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) return cnt; } -static int rnbd_rdma_map_queues(struct blk_mq_tag_set *set) +static void rnbd_rdma_map_queues(struct blk_mq_tag_set *set) { struct rnbd_clt_session *sess = set->driver_data; @@ -1194,8 +1194,6 @@ static int rnbd_rdma_map_queues(struct blk_mq_tag_set *set) set->map[HCTX_TYPE_DEFAULT].nr_queues, set->map[HCTX_TYPE_READ].nr_queues); } - - return 0; } static struct blk_mq_ops rnbd_mq_ops = { diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 30255fcaf181..23c5a1239520 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -802,7 +802,7 @@ static const struct attribute_group *virtblk_attr_groups[] = { NULL, }; -static int virtblk_map_queues(struct blk_mq_tag_set *set) +static void virtblk_map_queues(struct blk_mq_tag_set *set) { struct virtio_blk *vblk = set->driver_data; int i, qoff; @@ -827,8 +827,6 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set) else blk_mq_virtio_map_queues(&set->map[i], vblk->vdev, 0); } - - return 0; } static void virtblk_complete_batch(struct io_comp_batch *iob) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 127abaf9ba5d..42767fb75455 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2860,7 +2860,7 @@ nvme_fc_complete_rq(struct request *rq) nvme_fc_ctrl_put(ctrl); } -static int nvme_fc_map_queues(struct blk_mq_tag_set *set) +static void nvme_fc_map_queues(struct blk_mq_tag_set *set) { struct nvme_fc_ctrl *ctrl = set->driver_data; int i; @@ -2880,7 +2880,6 @@ static int nvme_fc_map_queues(struct blk_mq_tag_set *set) else blk_mq_map_queues(map); } - return 0; } static const struct blk_mq_ops nvme_fc_mq_ops = { diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 3a1c37f32f30..4a8cfb360d31 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -450,7 +450,7 @@ static int queue_irq_offset(struct nvme_dev *dev) return 0; } -static int nvme_pci_map_queues(struct blk_mq_tag_set *set) +static void nvme_pci_map_queues(struct blk_mq_tag_set *set) { struct nvme_dev *dev = set->driver_data; int i, qoff, offset; @@ -477,8 +477,6 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set) qoff += map->nr_queues; offset += map->nr_queues; } - - return 0; } /* diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 3100643be299..ba08851e42c3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2188,7 +2188,7 @@ static void nvme_rdma_complete_rq(struct request *rq) nvme_complete_rq(rq); } -static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) +static void nvme_rdma_map_queues(struct blk_mq_tag_set *set) { struct nvme_rdma_ctrl *ctrl = set->driver_data; struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; @@ -2231,8 +2231,6 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) ctrl->io_queues[HCTX_TYPE_DEFAULT], ctrl->io_queues[HCTX_TYPE_READ], ctrl->io_queues[HCTX_TYPE_POLL]); - - return 0; } static const struct blk_mq_ops nvme_rdma_mq_ops = { diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 044da18c06f5..ef151c23d495 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2471,7 +2471,7 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) +static void nvme_tcp_map_queues(struct blk_mq_tag_set *set) { struct nvme_tcp_ctrl *ctrl = set->driver_data; struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; @@ -2512,8 +2512,6 @@ static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) ctrl->io_queues[HCTX_TYPE_DEFAULT], ctrl->io_queues[HCTX_TYPE_READ], ctrl->io_queues[HCTX_TYPE_POLL]); - - return 0; } static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 70e401fd432a..c37027276162 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -3537,7 +3537,7 @@ static struct attribute *host_v2_hw_attrs[] = { ATTRIBUTE_GROUPS(host_v2_hw); -static int map_queues_v2_hw(struct Scsi_Host *shost) +static void map_queues_v2_hw(struct Scsi_Host *shost) { struct hisi_hba *hisi_hba = shost_priv(shost); struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; @@ -3552,9 +3552,6 @@ static int map_queues_v2_hw(struct Scsi_Host *shost) for_each_cpu(cpu, mask) qmap->mq_map[cpu] = qmap->queue_offset + queue; } - - return 0; - } static struct scsi_host_template sht_v2_hw = { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index efe8c5be5870..d716e5632d0f 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -3171,13 +3171,12 @@ static int debugfs_set_bist_v3_hw(struct hisi_hba *hisi_hba, bool enable) return 0; } -static int hisi_sas_map_queues(struct Scsi_Host *shost) +static void hisi_sas_map_queues(struct Scsi_Host *shost) { struct hisi_hba *hisi_hba = shost_priv(shost); struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - return blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev, - BASE_VECTORS_V3_HW); + blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev, BASE_VECTORS_V3_HW); } static struct scsi_host_template sht_v3_hw = { diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index a3e117a4b8e7..f17813b1ffae 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3174,7 +3174,7 @@ megasas_bios_param(struct scsi_device *sdev, struct block_device *bdev, return 0; } -static int megasas_map_queues(struct Scsi_Host *shost) +static void megasas_map_queues(struct Scsi_Host *shost) { struct megasas_instance *instance; int qoff = 0, offset; @@ -3183,7 +3183,7 @@ static int megasas_map_queues(struct Scsi_Host *shost) instance = (struct megasas_instance *)shost->hostdata; if (shost->nr_hw_queues == 1) - return 0; + return; offset = instance->low_latency_index_start; @@ -3209,8 +3209,6 @@ static int megasas_map_queues(struct Scsi_Host *shost) map->queue_offset = qoff; blk_mq_map_queues(map); } - - return 0; } static void megasas_aen_polling(struct work_struct *work); diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index bfa1165e23b6..9681c8bf24ed 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -3464,7 +3464,7 @@ static int mpi3mr_bios_param(struct scsi_device *sdev, * * Return: return zero. */ -static int mpi3mr_map_queues(struct Scsi_Host *shost) +static void mpi3mr_map_queues(struct Scsi_Host *shost) { struct mpi3mr_ioc *mrioc = shost_priv(shost); int i, qoff, offset; @@ -3500,9 +3500,6 @@ static int mpi3mr_map_queues(struct Scsi_Host *shost) qoff += map->nr_queues; offset += map->nr_queues; } - - return 0; - } /** diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index def37a7e5980..44618bf66d9b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11872,7 +11872,7 @@ out: * scsih_map_queues - map reply queues with request queues * @shost: SCSI host pointer */ -static int scsih_map_queues(struct Scsi_Host *shost) +static void scsih_map_queues(struct Scsi_Host *shost) { struct MPT3SAS_ADAPTER *ioc = (struct MPT3SAS_ADAPTER *)shost->hostdata; @@ -11882,7 +11882,7 @@ static int scsih_map_queues(struct Scsi_Host *shost) int iopoll_q_count = ioc->reply_queue_count - nr_msix_vectors; if (shost->nr_hw_queues == 1) - return 0; + return; for (i = 0, qoff = 0; i < shost->nr_maps; i++) { map = &shost->tag_set.map[i]; @@ -11910,7 +11910,6 @@ static int scsih_map_queues(struct Scsi_Host *shost) qoff += map->nr_queues; } - return 0; } /* shost template for SAS 2.0 HBA devices */ diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index a0028e130a7e..2ff2fac1e403 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -81,7 +81,7 @@ LIST_HEAD(hba_list); struct workqueue_struct *pm8001_wq; -static int pm8001_map_queues(struct Scsi_Host *shost) +static void pm8001_map_queues(struct Scsi_Host *shost) { struct sas_ha_struct *sha = SHOST_TO_SAS_HA(shost); struct pm8001_hba_info *pm8001_ha = sha->lldd_ha; diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 7450c3458be7..02fdeb0d31ec 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -684,12 +684,8 @@ static void qla_nvme_map_queues(struct nvme_fc_local_port *lport, struct blk_mq_queue_map *map) { struct scsi_qla_host *vha = lport->private; - int rc; - rc = blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset); - if (rc) - ql_log(ql_log_warn, vha, 0x21de, - "pci map queue failed 0x%x", rc); + blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset); } static void qla_nvme_localport_delete(struct nvme_fc_local_port *lport) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 0bd0fd1042df..87a93892deac 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -350,7 +350,7 @@ MODULE_PARM_DESC(ql2xrspq_follow_inptr_legacy, static void qla2x00_clear_drv_active(struct qla_hw_data *); static void qla2x00_free_device(scsi_qla_host_t *); -static int qla2xxx_map_queues(struct Scsi_Host *shost); +static void qla2xxx_map_queues(struct Scsi_Host *shost); static void qla2x00_destroy_deferred_work(struct qla_hw_data *); u32 ql2xnvme_queues = DEF_NVME_HW_QUEUES; @@ -7994,17 +7994,15 @@ qla_pci_reset_done(struct pci_dev *pdev) clear_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags); } -static int qla2xxx_map_queues(struct Scsi_Host *shost) +static void qla2xxx_map_queues(struct Scsi_Host *shost) { - int rc; scsi_qla_host_t *vha = (scsi_qla_host_t *)shost->hostdata; struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; if (USER_CTRL_IRQ(vha->hw) || !vha->hw->mqiobase) - rc = blk_mq_map_queues(qmap); + blk_mq_map_queues(qmap); else - rc = blk_mq_pci_map_queues(qmap, vha->hw->pdev, vha->irq_offset); - return rc; + blk_mq_pci_map_queues(qmap, vha->hw->pdev, vha->irq_offset); } struct scsi_host_template qla2xxx_driver_template = { diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index b8a76b89f85a..697fc57bc711 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7474,12 +7474,12 @@ static int resp_not_ready(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) return check_condition_result; } -static int sdebug_map_queues(struct Scsi_Host *shost) +static void sdebug_map_queues(struct Scsi_Host *shost) { int i, qoff; if (shost->nr_hw_queues == 1) - return 0; + return; for (i = 0, qoff = 0; i < HCTX_MAX_TYPES; i++) { struct blk_mq_queue_map *map = &shost->tag_set.map[i]; @@ -7501,9 +7501,6 @@ static int sdebug_map_queues(struct Scsi_Host *shost) qoff += map->nr_queues; } - - return 0; - } static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 4dbd29ab1dcc..677f632d6fd3 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1849,13 +1849,13 @@ static int scsi_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, return 0; } -static int scsi_map_queues(struct blk_mq_tag_set *set) +static void scsi_map_queues(struct blk_mq_tag_set *set) { struct Scsi_Host *shost = container_of(set, struct Scsi_Host, tag_set); if (shost->hostt->map_queues) return shost->hostt->map_queues(shost); - return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q) diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 7a8c2c75acba..b971fbe3b3a1 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -6436,12 +6436,12 @@ static int pqi_slave_alloc(struct scsi_device *sdev) return 0; } -static int pqi_map_queues(struct Scsi_Host *shost) +static void pqi_map_queues(struct Scsi_Host *shost) { struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost); - return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - ctrl_info->pci_dev, 0); + blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], + ctrl_info->pci_dev, 0); } static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 578c4b6d0f7d..077a8e24bd28 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -711,12 +711,12 @@ static int virtscsi_abort(struct scsi_cmnd *sc) return virtscsi_tmf(vscsi, cmd); } -static int virtscsi_map_queues(struct Scsi_Host *shost) +static void virtscsi_map_queues(struct Scsi_Host *shost) { struct virtio_scsi *vscsi = shost_priv(shost); struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - return blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2); + blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2); } static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 6bc679d22927..f27a812a4416 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2701,9 +2701,9 @@ static inline bool is_device_wlun(struct scsi_device *sdev) * Associate the UFS controller queue with the default and poll HCTX types. * Initialize the mq_map[] arrays. */ -static int ufshcd_map_queues(struct Scsi_Host *shost) +static void ufshcd_map_queues(struct Scsi_Host *shost) { - int i, ret; + int i; for (i = 0; i < shost->nr_maps; i++) { struct blk_mq_queue_map *map = &shost->tag_set.map[i]; @@ -2720,11 +2720,8 @@ static int ufshcd_map_queues(struct Scsi_Host *shost) WARN_ON_ONCE(true); } map->queue_offset = 0; - ret = blk_mq_map_queues(map); - WARN_ON_ONCE(ret); + blk_mq_map_queues(map); } - - return 0; } static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h index 0b1f45c62623..ca544e1d3508 100644 --- a/include/linux/blk-mq-pci.h +++ b/include/linux/blk-mq-pci.h @@ -5,7 +5,7 @@ struct blk_mq_queue_map; struct pci_dev; -int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset); +void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, + int offset); #endif /* _LINUX_BLK_MQ_PCI_H */ diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h index 5cc5f0f36218..53b58c610e76 100644 --- a/include/linux/blk-mq-rdma.h +++ b/include/linux/blk-mq-rdma.h @@ -5,7 +5,7 @@ struct blk_mq_tag_set; struct ib_device; -int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, +void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, struct ib_device *dev, int first_vec); #endif /* _LINUX_BLK_MQ_RDMA_H */ diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h index 687ae287e1dc..13226e9b22dd 100644 --- a/include/linux/blk-mq-virtio.h +++ b/include/linux/blk-mq-virtio.h @@ -5,7 +5,7 @@ struct blk_mq_queue_map; struct virtio_device; -int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, +void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, struct virtio_device *vdev, int first_vec); #endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 92294a5fb083..c38575209d51 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -630,7 +630,7 @@ struct blk_mq_ops { * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ - int (*map_queues)(struct blk_mq_tag_set *set); + void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** @@ -880,7 +880,7 @@ void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_map_queues(struct blk_mq_queue_map *qmap); +void blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index aa7b7496c93a..7d51af3e7c40 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -276,7 +276,7 @@ struct scsi_host_template { * * Status: OPTIONAL */ - int (* map_queues)(struct Scsi_Host *shost); + void (* map_queues)(struct Scsi_Host *shost); /* * SCSI interface of blk_poll - poll for IO completions. -- cgit v1.2.3 From f5d632d15e9e0a037339601680d82bb840f85d10 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Aug 2022 16:39:04 -0600 Subject: block: shrink rq_map_data a bit We don't need full ints for several of these members. Change the page_order and nr_entries to unsigned shorts, and the true/false from_user and null_mapped to booleans. This shrinks the struct from 32 to 24 bytes on 64-bit archs. Reviewed-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe --- block/blk-map.c | 2 +- include/linux/blk-mq.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/block/blk-map.c b/block/blk-map.c index 7196a6b64c80..379c52d2f2d1 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -158,7 +158,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, req_op(rq)); if (map_data) { - nr_pages = 1 << map_data->page_order; + nr_pages = 1U << map_data->page_order; i = map_data->offset / PAGE_SIZE; } while (len) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index c38575209d51..74b99d716b0b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -963,11 +963,11 @@ blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; - int page_order; - int nr_entries; unsigned long offset; - int null_mapped; - int from_user; + unsigned short page_order; + unsigned short nr_entries; + bool null_mapped; + bool from_user; }; int blk_rq_map_user(struct request_queue *, struct request *, -- cgit v1.2.3 From 16ede66973c84f890c03584f79158dd5b2d725f5 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 25 Aug 2022 07:53:12 -0700 Subject: sbitmap: fix batched wait_cnt accounting Batched completions can clear multiple bits, but we're only decrementing the wait_cnt by one each time. This can cause waiters to never be woken, stalling IO. Use the batched count instead. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215679 Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220825145312.1217900-1-kbusch@fb.com Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 2 +- include/linux/sbitmap.h | 3 ++- lib/sbitmap.c | 31 +++++++++++++++++-------------- 3 files changed, 20 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 8e3b36d1cb57..9eb968e14d31 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -196,7 +196,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) * other allocations on previous queue won't be starved. */ if (bt != bt_prev) - sbitmap_queue_wake_up(bt_prev); + sbitmap_queue_wake_up(bt_prev, 1); ws = bt_wait_ptr(bt, data->hctx); } while (1); diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 8f5a86e210b9..4d2d5205ab58 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -575,8 +575,9 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. + * @nr: Number of bits cleared. */ -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct diff --git a/lib/sbitmap.c b/lib/sbitmap.c index a39b1a877366..2fedf07a9db5 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -599,34 +599,38 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) return NULL; } -static bool __sbq_wake_up(struct sbitmap_queue *sbq) +static bool __sbq_wake_up(struct sbitmap_queue *sbq, int nr) { struct sbq_wait_state *ws; - unsigned int wake_batch; - int wait_cnt; + int wake_batch, wait_cnt, cur; ws = sbq_wake_ptr(sbq); - if (!ws) + if (!ws || !nr) return false; - wait_cnt = atomic_dec_return(&ws->wait_cnt); + wake_batch = READ_ONCE(sbq->wake_batch); + cur = atomic_read(&ws->wait_cnt); + do { + if (cur <= 0) + return true; + wait_cnt = cur - nr; + } while (!atomic_try_cmpxchg(&ws->wait_cnt, &cur, wait_cnt)); + /* * For concurrent callers of this, callers should call this function * again to wakeup a new batch on a different 'ws'. */ - if (wait_cnt < 0 || !waitqueue_active(&ws->wait)) + if (!waitqueue_active(&ws->wait)) return true; if (wait_cnt > 0) return false; - wake_batch = READ_ONCE(sbq->wake_batch); - /* * Wake up first in case that concurrent callers decrease wait_cnt * while waitqueue is empty. */ - wake_up_nr(&ws->wait, wake_batch); + wake_up_nr(&ws->wait, max(wake_batch, nr)); /* * Pairs with the memory barrier in sbitmap_queue_resize() to @@ -651,12 +655,11 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq) return false; } -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr) { - while (__sbq_wake_up(sbq)) + while (__sbq_wake_up(sbq, nr)) ; } -EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag) { @@ -693,7 +696,7 @@ void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, atomic_long_andnot(mask, (atomic_long_t *) addr); smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, nr_tags); sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(), tags[nr_tags - 1] - offset); } @@ -721,7 +724,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, * waiter. See the comment on waitqueue_active(). */ smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, 1); sbitmap_update_cpu_hint(&sbq->sb, cpu, nr); } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); -- cgit v1.2.3 From bce1b56c73826fec8caf6187f0c922ede397a5a8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 4 Sep 2022 06:39:25 -0600 Subject: Revert "sbitmap: fix batched wait_cnt accounting" This reverts commit 16ede66973c84f890c03584f79158dd5b2d725f5. This is causing issues with CPU stalls on my test box, revert it for now until we understand what is going on. It looks like infinite looping off sbitmap_queue_wake_up(), but hard to tell with a lot of CPUs hitting this issue and the console scrolling infinitely. Link: https://lore.kernel.org/linux-block/e742813b-ce5c-0d58-205b-1626f639b1bd@kernel.dk/ Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 2 +- include/linux/sbitmap.h | 3 +-- lib/sbitmap.c | 31 ++++++++++++++----------------- 3 files changed, 16 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 9eb968e14d31..8e3b36d1cb57 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -196,7 +196,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) * other allocations on previous queue won't be starved. */ if (bt != bt_prev) - sbitmap_queue_wake_up(bt_prev, 1); + sbitmap_queue_wake_up(bt_prev); ws = bt_wait_ptr(bt, data->hctx); } while (1); diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 4d2d5205ab58..8f5a86e210b9 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -575,9 +575,8 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. - * @nr: Number of bits cleared. */ -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr); +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 2fedf07a9db5..a39b1a877366 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -599,38 +599,34 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) return NULL; } -static bool __sbq_wake_up(struct sbitmap_queue *sbq, int nr) +static bool __sbq_wake_up(struct sbitmap_queue *sbq) { struct sbq_wait_state *ws; - int wake_batch, wait_cnt, cur; + unsigned int wake_batch; + int wait_cnt; ws = sbq_wake_ptr(sbq); - if (!ws || !nr) + if (!ws) return false; - wake_batch = READ_ONCE(sbq->wake_batch); - cur = atomic_read(&ws->wait_cnt); - do { - if (cur <= 0) - return true; - wait_cnt = cur - nr; - } while (!atomic_try_cmpxchg(&ws->wait_cnt, &cur, wait_cnt)); - + wait_cnt = atomic_dec_return(&ws->wait_cnt); /* * For concurrent callers of this, callers should call this function * again to wakeup a new batch on a different 'ws'. */ - if (!waitqueue_active(&ws->wait)) + if (wait_cnt < 0 || !waitqueue_active(&ws->wait)) return true; if (wait_cnt > 0) return false; + wake_batch = READ_ONCE(sbq->wake_batch); + /* * Wake up first in case that concurrent callers decrease wait_cnt * while waitqueue is empty. */ - wake_up_nr(&ws->wait, max(wake_batch, nr)); + wake_up_nr(&ws->wait, wake_batch); /* * Pairs with the memory barrier in sbitmap_queue_resize() to @@ -655,11 +651,12 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq, int nr) return false; } -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr) +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) { - while (__sbq_wake_up(sbq, nr)) + while (__sbq_wake_up(sbq)) ; } +EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag) { @@ -696,7 +693,7 @@ void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, atomic_long_andnot(mask, (atomic_long_t *) addr); smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq, nr_tags); + sbitmap_queue_wake_up(sbq); sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(), tags[nr_tags - 1] - offset); } @@ -724,7 +721,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, * waiter. See the comment on waitqueue_active(). */ smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq, 1); + sbitmap_queue_wake_up(sbq); sbitmap_update_cpu_hint(&sbq->sb, cpu, nr); } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); -- cgit v1.2.3 From 4acb83417cadfdcbe64215f9d0ddcf3132af808e Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 9 Sep 2022 11:40:22 -0700 Subject: sbitmap: fix batched wait_cnt accounting Batched completions can clear multiple bits, but we're only decrementing the wait_cnt by one each time. This can cause waiters to never be woken, stalling IO. Use the batched count instead. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215679 Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220909184022.1709476-1-kbusch@fb.com Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 2 +- include/linux/sbitmap.h | 3 ++- lib/sbitmap.c | 37 +++++++++++++++++++++++-------------- 3 files changed, 26 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 8e3b36d1cb57..9eb968e14d31 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -196,7 +196,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) * other allocations on previous queue won't be starved. */ if (bt != bt_prev) - sbitmap_queue_wake_up(bt_prev); + sbitmap_queue_wake_up(bt_prev, 1); ws = bt_wait_ptr(bt, data->hctx); } while (1); diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 8f5a86e210b9..4d2d5205ab58 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -575,8 +575,9 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. + * @nr: Number of bits cleared. */ -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct diff --git a/lib/sbitmap.c b/lib/sbitmap.c index cbfd2e677d87..624fa7f118d1 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -599,24 +599,31 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) return NULL; } -static bool __sbq_wake_up(struct sbitmap_queue *sbq) +static bool __sbq_wake_up(struct sbitmap_queue *sbq, int *nr) { struct sbq_wait_state *ws; unsigned int wake_batch; - int wait_cnt; + int wait_cnt, cur, sub; bool ret; + if (*nr <= 0) + return false; + ws = sbq_wake_ptr(sbq); if (!ws) return false; - wait_cnt = atomic_dec_return(&ws->wait_cnt); - /* - * For concurrent callers of this, callers should call this function - * again to wakeup a new batch on a different 'ws'. - */ - if (wait_cnt < 0) - return true; + cur = atomic_read(&ws->wait_cnt); + do { + /* + * For concurrent callers of this, callers should call this + * function again to wakeup a new batch on a different 'ws'. + */ + if (cur == 0) + return true; + sub = min(*nr, cur); + wait_cnt = cur - sub; + } while (!atomic_try_cmpxchg(&ws->wait_cnt, &cur, wait_cnt)); /* * If we decremented queue without waiters, retry to avoid lost @@ -625,6 +632,8 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq) if (wait_cnt > 0) return !waitqueue_active(&ws->wait); + *nr -= sub; + /* * When wait_cnt == 0, we have to be particularly careful as we are * responsible to reset wait_cnt regardless whether we've actually @@ -660,12 +669,12 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq) sbq_index_atomic_inc(&sbq->wake_index); atomic_set(&ws->wait_cnt, wake_batch); - return ret; + return ret || *nr; } -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr) { - while (__sbq_wake_up(sbq)) + while (__sbq_wake_up(sbq, &nr)) ; } EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); @@ -705,7 +714,7 @@ void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, atomic_long_andnot(mask, (atomic_long_t *) addr); smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, nr_tags); sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(), tags[nr_tags - 1] - offset); } @@ -733,7 +742,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, * waiter. See the comment on waitqueue_active(). */ smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, 1); sbitmap_update_cpu_hint(&sbq->sb, cpu, nr); } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); -- cgit v1.2.3 From 320fb0f91e55ba248d4bad106b408e59099cfa89 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 29 Aug 2022 10:22:37 +0800 Subject: blk-throttle: fix that io throttle can only work for single bio Test scripts: cd /sys/fs/cgroup/blkio/ echo "8:0 1024" > blkio.throttle.write_bps_device echo $$ > cgroup.procs dd if=/dev/zero of=/dev/sda bs=10k count=1 oflag=direct & dd if=/dev/zero of=/dev/sda bs=10k count=1 oflag=direct & Test result: 10240 bytes (10 kB, 10 KiB) copied, 10.0134 s, 1.0 kB/s 10240 bytes (10 kB, 10 KiB) copied, 10.0135 s, 1.0 kB/s The problem is that the second bio is finished after 10s instead of 20s. Root cause: 1) second bio will be flagged: __blk_throtl_bio while (true) { ... if (sq->nr_queued[rw]) -> some bio is throttled already break }; bio_set_flag(bio, BIO_THROTTLED); -> flag the bio 2) flagged bio will be dispatched without waiting: throtl_dispatch_tg tg_may_dispatch tg_with_in_bps_limit if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) *wait = 0; -> wait time is zero return true; commit 9f5ede3c01f9 ("block: throttle split bio in case of iops limit") support to count split bios for iops limit, thus it adds flagged bio checking in tg_with_in_bps_limit() so that split bios will only count once for bps limit, however, it introduce a new problem that io throttle won't work if multiple bios are throttled. In order to fix the problem, handle iops/bps limit in different ways: 1) for iops limit, there is no flag to record if the bio is throttled, and iops is always applied. 2) for bps limit, original bio will be flagged with BIO_BPS_THROTTLED, and io throttle will ignore bio with the flag. Noted this patch also remove the code to set flag in __bio_clone(), it's introduced in commit 111be8839817 ("block-throttle: avoid double charge"), and author thinks split bio can be resubmited and throttled again, which is wrong because split bio will continue to dispatch from caller. Fixes: 9f5ede3c01f9 ("block: throttle split bio in case of iops limit") Cc: Signed-off-by: Yu Kuai Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220829022240.3348319-2-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- block/bio.c | 2 -- block/blk-throttle.c | 20 ++++++-------------- block/blk-throttle.h | 2 +- include/linux/bio.h | 2 +- include/linux/blk_types.h | 2 +- 5 files changed, 9 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index d3154d8beed7..c88459a9507d 100644 --- a/block/bio.c +++ b/block/bio.c @@ -760,8 +760,6 @@ EXPORT_SYMBOL(bio_put); static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) { bio_set_flag(bio, BIO_CLONED); - if (bio_flagged(bio_src, BIO_THROTTLED)) - bio_set_flag(bio, BIO_THROTTLED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_iter = bio_src->bi_iter; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 667b2958471a..a5e495b67827 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -811,7 +811,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, unsigned int bio_size = throtl_bio_data_size(bio); /* no need to throttle if this bio's bytes have been accounted */ - if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) { + if (bps_limit == U64_MAX || bio_flagged(bio, BIO_BPS_THROTTLED)) { if (wait) *wait = 0; return true; @@ -921,22 +921,13 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) unsigned int bio_size = throtl_bio_data_size(bio); /* Charge the bio to the group */ - if (!bio_flagged(bio, BIO_THROTTLED)) { + if (!bio_flagged(bio, BIO_BPS_THROTTLED)) { tg->bytes_disp[rw] += bio_size; tg->last_bytes_disp[rw] += bio_size; } tg->io_disp[rw]++; tg->last_io_disp[rw]++; - - /* - * BIO_THROTTLED is used to prevent the same bio to be throttled - * more than once as a throttled bio will go through blk-throtl the - * second time when it eventually gets issued. Set it when a bio - * is being charged to a tg. - */ - if (!bio_flagged(bio, BIO_THROTTLED)) - bio_set_flag(bio, BIO_THROTTLED); } /** @@ -1026,6 +1017,7 @@ static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) sq->nr_queued[rw]--; throtl_charge_bio(tg, bio); + bio_set_flag(bio, BIO_BPS_THROTTLED); /* * If our parent is another tg, we just need to transfer @bio to @@ -2181,8 +2173,10 @@ again: qn = &tg->qnode_on_parent[rw]; sq = sq->parent_sq; tg = sq_to_tg(sq); - if (!tg) + if (!tg) { + bio_set_flag(bio, BIO_BPS_THROTTLED); goto out_unlock; + } } /* out-of-limit, queue to @tg */ @@ -2211,8 +2205,6 @@ again: } out_unlock: - bio_set_flag(bio, BIO_THROTTLED); - #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; diff --git a/block/blk-throttle.h b/block/blk-throttle.h index c1b602996127..ee7299e6dea9 100644 --- a/block/blk-throttle.h +++ b/block/blk-throttle.h @@ -175,7 +175,7 @@ static inline bool blk_throtl_bio(struct bio *bio) struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg); /* no need to throttle bps any more if the bio has been throttled */ - if (bio_flagged(bio, BIO_THROTTLED) && + if (bio_flagged(bio, BIO_BPS_THROTTLED) && !(tg->flags & THROTL_TG_HAS_IOPS_LIMIT)) return false; diff --git a/include/linux/bio.h b/include/linux/bio.h index ca22b06700a9..2c5806997bbf 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -509,7 +509,7 @@ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) { bio_clear_flag(bio, BIO_REMAPPED); if (bio->bi_bdev != bdev) - bio_clear_flag(bio, BIO_THROTTLED); + bio_clear_flag(bio, BIO_BPS_THROTTLED); bio->bi_bdev = bdev; bio_associate_blkg(bio); } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1ef99790f6ed..41afb4cfb9b0 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -325,7 +325,7 @@ enum { BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ - BIO_THROTTLED, /* This bio has already been subjected to + BIO_BPS_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ -- cgit v1.2.3 From 176042404ee6a96ba7e9054e1bda6220360a26ad Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Sep 2022 10:41:56 +0100 Subject: mm: add PSI accounting around ->read_folio and ->readahead calls PSI tries to account for the cost of bringing back in pages discarded by the MM LRU management. Currently the prime place for that is hooked into the bio submission path, which is a rather bad place: - it does not actually account I/O for non-block file systems, of which we have many - it adds overhead and a layering violation to the block layer Add the accounting into the two places in the core MM code that read pages into an address space by calling into ->read_folio and ->readahead so that the entire file system operations are covered, to broaden the coverage and allow removing the accounting in the block layer going forward. As psi_memstall_enter can deal with nested calls this will not lead to double accounting even while the bio annotations are still present. Signed-off-by: Christoph Hellwig Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220915094200.139713-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/pagemap.h | 2 ++ mm/filemap.c | 7 +++++++ mm/readahead.c | 22 ++++++++++++++++++---- 3 files changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0178b2040ea3..201dc7281640 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1173,6 +1173,8 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool _workingset; + unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ diff --git a/mm/filemap.c b/mm/filemap.c index 15800334147b..c943d1b90cc2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2382,6 +2382,8 @@ retry: static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { + bool workingset = folio_test_workingset(folio); + unsigned long pflags; int error; /* @@ -2390,8 +2392,13 @@ static int filemap_read_folio(struct file *file, filler_t filler, * fails. */ folio_clear_error(folio); + /* Start the actual read. The read will unlock the page. */ + if (unlikely(workingset)) + psi_memstall_enter(&pflags); error = filler(file, folio); + if (unlikely(workingset)) + psi_memstall_leave(&pflags); if (error) return error; diff --git a/mm/readahead.c b/mm/readahead.c index fdcd28cbd92d..b10f0cf81d80 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -122,6 +122,7 @@ #include #include #include +#include #include #include #include @@ -152,6 +153,8 @@ static void read_pages(struct readahead_control *rac) if (!readahead_count(rac)) return; + if (unlikely(rac->_workingset)) + psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { @@ -179,6 +182,9 @@ static void read_pages(struct readahead_control *rac) } blk_finish_plug(&plug); + if (unlikely(rac->_workingset)) + psi_memstall_leave(&rac->_pflags); + rac->_workingset = false; BUG_ON(readahead_count(rac)); } @@ -252,6 +258,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, } if (i == nr_to_read - lookahead_size) folio_set_readahead(folio); + ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages++; } @@ -480,11 +487,14 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); - if (err) + if (err) { folio_put(folio); - else - ractl->_nr_pages += 1UL << order; - return err; + return err; + } + + ractl->_nr_pages += 1UL << order; + ractl->_workingset |= folio_test_workingset(folio); + return 0; } void page_cache_ra_order(struct readahead_control *ractl, @@ -826,6 +836,10 @@ void readahead_expand(struct readahead_control *ractl, put_page(page); return; } + if (unlikely(PageWorkingset(page)) && !ractl->_workingset) { + ractl->_workingset = true; + psi_memstall_enter(&ractl->_pflags); + } ractl->_nr_pages++; if (ra) { ra->size++; -- cgit v1.2.3 From 118f3663fbc658e9ad6165e129076981c7b685c5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Sep 2022 10:42:00 +0100 Subject: block: remove PSI accounting from the bio layer PSI accounting is now done by the VM code, where it should have been since the beginning. Signed-off-by: Christoph Hellwig Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220915094200.139713-6-hch@lst.de Signed-off-by: Jens Axboe --- block/bio.c | 8 -------- block/blk-core.c | 17 ----------------- fs/direct-io.c | 2 -- include/linux/blk_types.h | 1 - 4 files changed, 28 deletions(-) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index c88459a9507d..7cb7d2ff139b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1063,9 +1063,6 @@ void __bio_add_page(struct bio *bio, struct page *page, bio->bi_iter.bi_size += len; bio->bi_vcnt++; - - if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page))) - bio_set_flag(bio, BIO_WORKINGSET); } EXPORT_SYMBOL_GPL(__bio_add_page); @@ -1274,9 +1271,6 @@ out: * fit into the bio, or are requested in @iter, whatever is smaller. If * MM encounters an error pinning the requested pages, it stops. Error * is returned only if 0 pages could be pinned. - * - * It's intended for direct IO, so doesn't do PSI tracking, the caller is - * responsible for setting BIO_WORKINGSET if necessary. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { @@ -1292,8 +1286,6 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) ret = __bio_iov_iter_get_pages(bio, iter); } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); - /* don't account direct I/O as memory stall */ - bio_clear_flag(bio, BIO_WORKINGSET); return bio->bi_vcnt ? 0 : ret; } EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); diff --git a/block/blk-core.c b/block/blk-core.c index fa609569c3d2..052444c9b594 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -825,22 +824,6 @@ void submit_bio(struct bio *bio) count_vm_events(PGPGOUT, bio_sectors(bio)); } - /* - * If we're reading data that is part of the userspace workingset, count - * submission time as memory stall. When the device is congested, or - * the submitting cgroup IO-throttled, submission can be a significant - * part of overall IO time. - */ - if (unlikely(bio_op(bio) == REQ_OP_READ && - bio_flagged(bio, BIO_WORKINGSET))) { - unsigned long pflags; - - psi_memstall_enter(&pflags); - submit_bio_noacct(bio); - psi_memstall_leave(&pflags); - return; - } - submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); diff --git a/fs/direct-io.c b/fs/direct-io.c index f669163d5860..03d381377ae1 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -421,8 +421,6 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) unsigned long flags; bio->bi_private = dio; - /* don't account direct I/O as memory stall */ - bio_clear_flag(bio, BIO_WORKINGSET); spin_lock_irqsave(&dio->bio_lock, flags); dio->refcount++; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 41afb4cfb9b0..e0b098089ef2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -321,7 +321,6 @@ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ - BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ -- cgit v1.2.3 From b2bed51a5261f4266ecb857bba680a7f668d3ddf Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 20 Sep 2022 13:06:26 -0700 Subject: block: Fix the enum blk_eh_timer_return documentation The documentation of the blk_eh_timer_return enumeration values does not reflect correctly how e.g. the SCSI core uses these values. Fix the documentation. Cc: Christoph Hellwig Cc: Ming Lei Cc: Hannes Reinecke Cc: Damien Le Moal Cc: Johannes Thumshirn Fixes: 88b0cfad2888 ("block: document the blk_eh_timer_return values") Signed-off-by: Bart Van Assche Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Link: https://lore.kernel.org/r/20220920200626.3422296-1-bvanassche@acm.org Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 74b99d716b0b..e21ff85751cf 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -268,9 +268,16 @@ static inline void rq_list_move(struct request **src, struct request **dst, rq_list_add(dst, rq); } +/** + * enum blk_eh_timer_return - How the timeout handler should proceed + * @BLK_EH_DONE: The block driver completed the command or will complete it at + * a later time. + * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the + * request to complete. + */ enum blk_eh_timer_return { - BLK_EH_DONE, /* drivers has completed the command */ - BLK_EH_RESET_TIMER, /* reset timer and try again */ + BLK_EH_DONE, + BLK_EH_RESET_TIMER, }; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ -- cgit v1.2.3 From 77a440e2cbb4b8688b567104f80ce1cda1afbbc4 Mon Sep 17 00:00:00 2001 From: ZiyangZhang Date: Fri, 23 Sep 2022 23:39:14 +0800 Subject: ublk_drv: define macros for recovery feature and check them Define some macros for recovery feature. UBLK_S_DEV_QUIESCED implies that ublk_device is quiesced and is ready for recovery. This state can be observed by userspace. UBLK_F_USER_RECOVERY implies that: (1) ublk_drv enables recovery feature. It won't let monitor_work to automatically abort rqs and release the device. (2) With a dying ubq_daemon, ublk_drv ends(aborts) rqs issued to userspace(ublksrv) before crash. (3) With a dying ubq_daemon, in task work and ublk_queue_rq(), ublk_drv requeues rqs. Signed-off-by: ZiyangZhang Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20220923153919.44078-3-ZiyangZhang@linux.alibaba.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 18 +++++++++++++++++- include/uapi/linux/ublk_cmd.h | 3 +++ 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c39b67d7133d..05bfbaa49696 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -49,7 +49,8 @@ /* All UBLK_F_* have to be included into UBLK_F_ALL */ #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \ | UBLK_F_URING_CMD_COMP_IN_TASK \ - | UBLK_F_NEED_GET_DATA) + | UBLK_F_NEED_GET_DATA \ + | UBLK_F_USER_RECOVERY) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) @@ -323,6 +324,21 @@ static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id) PAGE_SIZE); } +static inline bool ublk_queue_can_use_recovery( + struct ublk_queue *ubq) +{ + if (ubq->flags & UBLK_F_USER_RECOVERY) + return true; + return false; +} + +static inline bool ublk_can_use_recovery(struct ublk_device *ub) +{ + if (ub->dev_info.flags & UBLK_F_USER_RECOVERY) + return true; + return false; +} + static void ublk_free_disk(struct gendisk *disk) { struct ublk_device *ub = disk->private_data; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 677edaab2b66..340ff14bde49 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -74,9 +74,12 @@ */ #define UBLK_F_NEED_GET_DATA (1UL << 2) +#define UBLK_F_USER_RECOVERY (1UL << 3) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 +#define UBLK_S_DEV_QUIESCED 2 /* shipped via sqe->cmd of io_uring command */ struct ublksrv_ctrl_cmd { -- cgit v1.2.3 From a0d41dc1137470fd4c5c2ef8fdc244d7565e69e6 Mon Sep 17 00:00:00 2001 From: ZiyangZhang Date: Fri, 23 Sep 2022 23:39:17 +0800 Subject: ublk_drv: support UBLK_F_USER_RECOVERY_REISSUE UBLK_F_USER_RECOVERY_REISSUE implies that: With a dying ubq_daemon, ublk_drv let monitor_work requeues rq issued to userspace(ublksrv) before the ubq_daemon is dying. UBLK_F_USER_RECOVERY_REISSUE is designed for backends which: (1) tolerate double-write since ublk_drv may issue the same rq twice. (2) does not let frontend users get I/O error, such as read-only FS and VM backend. Signed-off-by: ZiyangZhang Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20220923153919.44078-6-ZiyangZhang@linux.alibaba.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 22 ++++++++++++++++++---- include/uapi/linux/ublk_cmd.h | 2 ++ 2 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 3cdcc9bd635f..76ee41e82973 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -50,7 +50,8 @@ #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \ | UBLK_F_URING_CMD_COMP_IN_TASK \ | UBLK_F_NEED_GET_DATA \ - | UBLK_F_USER_RECOVERY) + | UBLK_F_USER_RECOVERY \ + | UBLK_F_USER_RECOVERY_REISSUE) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) @@ -325,6 +326,15 @@ static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id) PAGE_SIZE); } +static inline bool ublk_queue_can_use_recovery_reissue( + struct ublk_queue *ubq) +{ + if ((ubq->flags & UBLK_F_USER_RECOVERY) && + (ubq->flags & UBLK_F_USER_RECOVERY_REISSUE)) + return true; + return false; +} + static inline bool ublk_queue_can_use_recovery( struct ublk_queue *ubq) { @@ -629,13 +639,17 @@ static void ublk_complete_rq(struct request *req) * Also aborting may not be started yet, keep in mind that one failed * request may be issued by block layer again. */ -static void __ublk_fail_req(struct ublk_io *io, struct request *req) +static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, + struct request *req) { WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); if (!(io->flags & UBLK_IO_FLAG_ABORTED)) { io->flags |= UBLK_IO_FLAG_ABORTED; - blk_mq_end_request(req, BLK_STS_IOERR); + if (ublk_queue_can_use_recovery_reissue(ubq)) + blk_mq_requeue_request(req, false); + else + blk_mq_end_request(req, BLK_STS_IOERR); } } @@ -962,7 +976,7 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq) */ rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i); if (rq) - __ublk_fail_req(io, rq); + __ublk_fail_req(ubq, io, rq); } } ublk_put_device(ub); diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 340ff14bde49..332370628757 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -76,6 +76,8 @@ #define UBLK_F_USER_RECOVERY (1UL << 3) +#define UBLK_F_USER_RECOVERY_REISSUE (1UL << 4) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 -- cgit v1.2.3 From c732a852b419fa057b53657e2daaf9433940391c Mon Sep 17 00:00:00 2001 From: ZiyangZhang Date: Fri, 23 Sep 2022 23:39:18 +0800 Subject: ublk_drv: add START_USER_RECOVERY and END_USER_RECOVERY support START_USER_RECOVERY and END_USER_RECOVERY are two new control commands to support user recovery feature. After a crash, user should send START_USER_RECOVERY, it will: (1) check if (a)current ublk_device is UBLK_S_DEV_QUIESCED which was set by quiesce_work and (b)chardev is released (2) reinit all ubqs, including: (a) put the task_struct and reset ->ubq_daemon to NULL. (b) reset all ublk_io. (3) reset ub->mm to NULL. Then, user should start a new process and send FETCH_REQ on each ubq_daemon. Finally, user should send END_USER_RECOVERY, it will: (1) wait for all new ubq_daemons getting ready. (2) update ublksrv_pid (3) unquiesce the request queue and expect incoming ublk_queue_rq() (4) convert ub's state to UBLK_S_DEV_LIVE Note: we can handle STOP_DEV between START_USER_RECOVERY and END_USER_RECOVERY. This is helpful to users who cannot start new process after sending START_USER_RECOVERY ctrl-cmd. Signed-off-by: ZiyangZhang Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20220923153919.44078-7-ZiyangZhang@linux.alibaba.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 116 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/ublk_cmd.h | 3 +- 2 files changed, 118 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 76ee41e82973..2651bf41dde3 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1861,6 +1861,116 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd) return ret; } +static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) +{ + int i; + + WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq))); + /* All old ioucmds have to be completed */ + WARN_ON_ONCE(ubq->nr_io_ready); + /* old daemon is PF_EXITING, put it now */ + put_task_struct(ubq->ubq_daemon); + /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ + ubq->ubq_daemon = NULL; + + for (i = 0; i < ubq->q_depth; i++) { + struct ublk_io *io = &ubq->ios[i]; + + /* forget everything now and be ready for new FETCH_REQ */ + io->flags = 0; + io->cmd = NULL; + io->addr = 0; + } +} + +static int ublk_ctrl_start_recovery(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + struct ublk_device *ub; + int ret = -EINVAL; + int i; + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return ret; + + mutex_lock(&ub->mutex); + if (!ublk_can_use_recovery(ub)) + goto out_unlock; + /* + * START_RECOVERY is only allowd after: + * + * (1) UB_STATE_OPEN is not set, which means the dying process is exited + * and related io_uring ctx is freed so file struct of /dev/ublkcX is + * released. + * + * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work: + * (a)has quiesced request queue + * (b)has requeued every inflight rqs whose io_flags is ACTIVE + * (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE + * (d)has completed/camceled all ioucmds owned by ther dying process + */ + if (test_bit(UB_STATE_OPEN, &ub->state) || + ub->dev_info.state != UBLK_S_DEV_QUIESCED) { + ret = -EBUSY; + goto out_unlock; + } + pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id); + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_queue_reinit(ub, ublk_get_queue(ub, i)); + /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ + ub->mm = NULL; + ub->nr_queues_ready = 0; + init_completion(&ub->completion); + ret = 0; + out_unlock: + mutex_unlock(&ub->mutex); + ublk_put_device(ub); + return ret; +} + +static int ublk_ctrl_end_recovery(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + int ublksrv_pid = (int)header->data[0]; + struct ublk_device *ub; + int ret = -EINVAL; + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return ret; + + pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n", + __func__, ub->dev_info.nr_hw_queues, header->dev_id); + /* wait until new ubq_daemon sending all FETCH_REQ */ + wait_for_completion_interruptible(&ub->completion); + pr_devel("%s: All new ubq_daemons(nr: %d) are ready, dev id %d\n", + __func__, ub->dev_info.nr_hw_queues, header->dev_id); + + mutex_lock(&ub->mutex); + if (!ublk_can_use_recovery(ub)) + goto out_unlock; + + if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) { + ret = -EBUSY; + goto out_unlock; + } + ub->dev_info.ublksrv_pid = ublksrv_pid; + pr_devel("%s: new ublksrv_pid %d, dev id %d\n", + __func__, ublksrv_pid, header->dev_id); + blk_mq_unquiesce_queue(ub->ub_disk->queue); + pr_devel("%s: queue unquiesced, dev id %d.\n", + __func__, header->dev_id); + blk_mq_kick_requeue_list(ub->ub_disk->queue); + ub->dev_info.state = UBLK_S_DEV_LIVE; + schedule_delayed_work(&ub->monitor_work, UBLK_DAEMON_MONITOR_PERIOD); + ret = 0; + out_unlock: + mutex_unlock(&ub->mutex); + ublk_put_device(ub); + return ret; +} + static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -1902,6 +2012,12 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, case UBLK_CMD_SET_PARAMS: ret = ublk_ctrl_set_params(cmd); break; + case UBLK_CMD_START_USER_RECOVERY: + ret = ublk_ctrl_start_recovery(cmd); + break; + case UBLK_CMD_END_USER_RECOVERY: + ret = ublk_ctrl_end_recovery(cmd); + break; default: break; } diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 332370628757..8f88e3a29998 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -17,7 +17,8 @@ #define UBLK_CMD_STOP_DEV 0x07 #define UBLK_CMD_SET_PARAMS 0x08 #define UBLK_CMD_GET_PARAMS 0x09 - +#define UBLK_CMD_START_USER_RECOVERY 0x10 +#define UBLK_CMD_END_USER_RECOVERY 0x11 /* * IO commands, issued by ublk server, and handled by ublk driver. * -- cgit v1.2.3 From de185b56e8a62822d4e1cdb3e068b38ca709aa47 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Sep 2022 20:05:00 +0200 Subject: blk-cgroup: pass a gendisk to blkcg_schedule_throttle Pass the gendisk to blkcg_schedule_throttle as part of moving the blk-cgroup infrastructure to be gendisk based. Remove the unused !BLK_CGROUP stub while we're at it. Signed-off-by: Christoph Hellwig Reviewed-by: Andreas Herrmann Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220921180501.1539876-17-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 8 +++++--- block/blk-iocost.c | 4 ++-- block/blk-iolatency.c | 2 +- include/linux/blk-cgroup.h | 5 ++--- mm/swapfile.c | 2 +- 5 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c2d5ca2eb92e..fc82057db962 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1792,13 +1792,13 @@ out: /** * blkcg_schedule_throttle - this task needs to check for throttling - * @q: the request queue IO was submitted on + * @gendisk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for - * instance will only have a request_queue at that point. This set's the + * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * @@ -1807,8 +1807,10 @@ out: * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ -void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) +void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { + struct request_queue *q = disk->queue; + if (unlikely(current->flags & PF_KTHREAD)) return; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index c0f69bc99db9..495396425bad 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2636,7 +2636,7 @@ retry_lock: if (use_debt) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) - blkcg_schedule_throttle(rqos->q, + blkcg_schedule_throttle(rqos->q->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); iocg_unlock(iocg, ioc_locked, &flags); return; @@ -2737,7 +2737,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, if (likely(!list_empty(&iocg->active_list))) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) - blkcg_schedule_throttle(rqos->q, + blkcg_schedule_throttle(rqos->q->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); } else { iocg_commit_bio(iocg, bio, abs_cost, cost); diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index c6f61fe88b87..571fa95aafe9 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -292,7 +292,7 @@ static void __blkcg_iolatency_throttle(struct rq_qos *rqos, unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay); if (use_delay) - blkcg_schedule_throttle(rqos->q, use_memdelay); + blkcg_schedule_throttle(rqos->q->disk, use_memdelay); /* * To avoid priority inversions we want to just take a slot if we are diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 9f40dbc65f82..dd5841a42c33 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -18,14 +18,14 @@ struct bio; struct cgroup_subsys_state; -struct request_queue; +struct gendisk; #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); +void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay); void blkcg_maybe_throttle_current(void); bool blk_cgroup_congested(void); void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); @@ -39,7 +39,6 @@ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } -static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { return NULL; diff --git a/mm/swapfile.c b/mm/swapfile.c index 1fdccd2f1422..82e62007881d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3655,7 +3655,7 @@ void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { - blkcg_schedule_throttle(bdev_get_queue(si->bdev), true); + blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } -- cgit v1.2.3 From 1c32a8012b7fabe469b6af826edfd4ae2a6201d3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 20 Sep 2022 15:38:58 +0200 Subject: nvme: improve the NVME_CONNECT_AUTHREQ* definitions Mark them as unsigned so that we don't need extra casts, and define them relative to cdword0 instead of requiring extra shifts. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Hannes Reinecke --- drivers/nvme/target/fabrics-cmd.c | 6 ++---- include/linux/nvme.h | 4 ++-- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index c7e903589d37..618f7adca70f 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -272,8 +272,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); if (nvmet_has_auth(ctrl)) - req->cqe->result.u32 |= - cpu_to_le32((u32)NVME_CONNECT_AUTHREQ_ATR << 16); + req->cqe->result.u32 |= cpu_to_le32(NVME_CONNECT_AUTHREQ_ATR); out: kfree(d); complete: @@ -334,8 +333,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) pr_debug("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid); if (nvmet_has_auth(ctrl)) - req->cqe->result.u32 |= - cpu_to_le32((u32)NVME_CONNECT_AUTHREQ_ATR << 16); + req->cqe->result.u32 |= cpu_to_le32(NVME_CONNECT_AUTHREQ_ATR); out: kfree(d); diff --git a/include/linux/nvme.h b/include/linux/nvme.h index ae53d74f3696..050d7d0cd81b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1482,8 +1482,8 @@ struct nvmf_connect_command { }; enum { - NVME_CONNECT_AUTHREQ_ASCR = (1 << 2), - NVME_CONNECT_AUTHREQ_ATR = (1 << 1), + NVME_CONNECT_AUTHREQ_ASCR = (1U << 18), + NVME_CONNECT_AUTHREQ_ATR = (1U << 17), }; struct nvmf_connect_data { -- cgit v1.2.3 From 568ec936bf1384fc15873908c96a9aeb62536edb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Sep 2022 09:58:15 +0200 Subject: block: replace blk_queue_nowait with bdev_nowait Replace blk_queue_nowait with a bdev_nowait helpers that takes the block_device given that the I/O submission path should not have to look into the request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Pankaj Raghav Link: https://lore.kernel.org/r/20220927075815.269694-1-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- drivers/md/dm-table.c | 4 +--- drivers/md/md.c | 4 ++-- include/linux/blkdev.h | 6 +++++- io_uring/io_uring.c | 2 +- 5 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 052444c9b594..dc1fa454ae30 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -713,7 +713,7 @@ void submit_bio_noacct(struct bio *bio) * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ - if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q)) + if ((bio->bi_opf & REQ_NOWAIT) && !bdev_nowait(bdev)) goto not_supported; if (should_fail_bio(bio)) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 332f96b58252..d8034ff0cb24 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1856,9 +1856,7 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t) static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_nowait(q); + return !bdev_nowait(dev->bdev); } static bool dm_table_supports_nowait(struct dm_table *t) diff --git a/drivers/md/md.c b/drivers/md/md.c index 9dc0175280b4..3e9a1a00776b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5844,7 +5844,7 @@ int md_run(struct mddev *mddev) } } sysfs_notify_dirent_safe(rdev->sysfs_state); - nowait = nowait && blk_queue_nowait(bdev_get_queue(rdev->bdev)); + nowait = nowait && bdev_nowait(rdev->bdev); } if (!bioset_initialized(&mddev->bio_set)) { @@ -6980,7 +6980,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) * If the new disk does not support REQ_NOWAIT, * disable on the whole MD. */ - if (!blk_queue_nowait(bdev_get_queue(rdev->bdev))) { + if (!bdev_nowait(rdev->bdev)) { pr_info("%s: Disabling nowait because %pg does not support nowait\n", mdname(mddev), rdev->bdev); blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 84b13fdd34a7..4750772ef228 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -618,7 +618,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) -#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); @@ -1280,6 +1279,11 @@ static inline bool bdev_fua(struct block_device *bdev) return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); } +static inline bool bdev_nowait(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ebfdb2212ec2..b2c80c2aa431 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1377,7 +1377,7 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) static bool io_bdev_nowait(struct block_device *bdev) { - return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); + return !bdev || bdev_nowait(bdev); } /* -- cgit v1.2.3 From 8cafdb5ab94cda3ebb0975be16e2d564a05132ea Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 29 Sep 2022 09:47:44 +0200 Subject: block: adapt blk_mq_plug() to not plug for writes that require a zone lock The current implementation of blk_mq_plug() disables plugging for all operations that involves a transfer to the device as we just check if the last bit in op_is_write() function. Modify blk_mq_plug() to disable plugging only for REQ_OP_WRITE and REQ_OP_WRITE_ZEROS as they might require a zone lock. Suggested-by: Christoph Hellwig Suggested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Pankaj Raghav Reviewed-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20220929074745.103073-2-p.raghav@samsung.com Signed-off-by: Jens Axboe --- block/blk-mq.h | 3 ++- block/blk-zoned.c | 9 +++------ include/linux/blkdev.h | 9 +++++++++ 3 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/block/blk-mq.h b/block/blk-mq.h index 8ca453ac243d..0b2870839cdd 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -312,7 +312,8 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) static inline struct blk_plug *blk_mq_plug( struct bio *bio) { /* Zoned block device write operation case: do not plug the BIO */ - if (bdev_is_zoned(bio->bi_bdev) && op_is_write(bio_op(bio))) + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + bdev_op_is_zoned_write(bio->bi_bdev, bio_op(bio))) return NULL; /* diff --git a/block/blk-zoned.c b/block/blk-zoned.c index a264621d4905..db829401d8d0 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -63,13 +63,10 @@ bool blk_req_needs_zone_write_lock(struct request *rq) if (!rq->q->disk->seq_zones_wlock) return false; - switch (req_op(rq)) { - case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE: + if (bdev_op_is_zoned_write(rq->q->disk->part0, req_op(rq))) return blk_rq_zone_is_seq(rq); - default: - return false; - } + + return false; } EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4750772ef228..49373d002631 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1304,6 +1304,15 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } +static inline bool bdev_op_is_zoned_write(struct block_device *bdev, + blk_opf_t op) +{ + if (!bdev_is_zoned(bdev)) + return false; + + return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; +} + static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3