diff options
111 files changed, 3776 insertions, 3069 deletions
diff --git a/Documentation/admin-guide/cgroup-v1/blkio-controller.rst b/Documentation/admin-guide/cgroup-v1/blkio-controller.rst index 36d43ae7dc13..16253eda192e 100644 --- a/Documentation/admin-guide/cgroup-v1/blkio-controller.rst +++ b/Documentation/admin-guide/cgroup-v1/blkio-controller.rst @@ -17,36 +17,37 @@ level logical devices like device mapper. HOWTO ===== + Throttling/Upper Limit policy ----------------------------- -- Enable Block IO controller:: +Enable Block IO controller:: CONFIG_BLK_CGROUP=y -- Enable throttling in block layer:: +Enable throttling in block layer:: CONFIG_BLK_DEV_THROTTLING=y -- Mount blkio controller (see cgroups.txt, Why are cgroups needed?):: +Mount blkio controller (see cgroups.txt, Why are cgroups needed?):: mount -t cgroup -o blkio none /sys/fs/cgroup/blkio -- Specify a bandwidth rate on particular device for root group. The format - for policy is "<major>:<minor> <bytes_per_second>":: +Specify a bandwidth rate on particular device for root group. The format +for policy is "<major>:<minor> <bytes_per_second>":: echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device - Above will put a limit of 1MB/second on reads happening for root group - on device having major/minor number 8:16. +This will put a limit of 1MB/second on reads happening for root group +on device having major/minor number 8:16. -- Run dd to read a file and see if rate is throttled to 1MB/s or not:: +Run dd to read a file and see if rate is throttled to 1MB/s or not:: # dd iflag=direct if=/mnt/common/zerofile of=/dev/null bs=4K count=1024 1024+0 records in 1024+0 records out 4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s - Limits for writes can be put using blkio.throttle.write_bps_device file. +Limits for writes can be put using blkio.throttle.write_bps_device file. Hierarchical Cgroups ==================== @@ -79,85 +80,89 @@ following:: Various user visible config options =================================== -CONFIG_BLK_CGROUP - - Block IO controller. -CONFIG_BFQ_CGROUP_DEBUG - - Debug help. Right now some additional stats file show up in cgroup + CONFIG_BLK_CGROUP + Block IO controller. + + CONFIG_BFQ_CGROUP_DEBUG + Debug help. Right now some additional stats file show up in cgroup if this option is enabled. -CONFIG_BLK_DEV_THROTTLING - - Enable block device throttling support in block layer. + CONFIG_BLK_DEV_THROTTLING + Enable block device throttling support in block layer. Details of cgroup files ======================= + Proportional weight policy files -------------------------------- -- blkio.weight - - Specifies per cgroup weight. This is default weight of the group - on all the devices until and unless overridden by per device rule. - (See blkio.weight_device). - Currently allowed range of weights is from 10 to 1000. -- blkio.weight_device - - One can specify per cgroup per device rules using this interface. - These rules override the default value of group weight as specified - by blkio.weight. + blkio.bfq.weight + Specifies per cgroup weight. This is default weight of the group + on all the devices until and unless overridden by per device rule + (see `blkio.bfq.weight_device` below). + + Currently allowed range of weights is from 1 to 1000. For more details, + see Documentation/block/bfq-iosched.rst. + + blkio.bfq.weight_device + Specifes per cgroup per device weights, overriding the default group + weight. For more details, see Documentation/block/bfq-iosched.rst. Following is the format:: - # echo dev_maj:dev_minor weight > blkio.weight_device + # echo dev_maj:dev_minor weight > blkio.bfq.weight_device Configure weight=300 on /dev/sdb (8:16) in this cgroup:: - # echo 8:16 300 > blkio.weight_device - # cat blkio.weight_device + # echo 8:16 300 > blkio.bfq.weight_device + # cat blkio.bfq.weight_device dev weight 8:16 300 Configure weight=500 on /dev/sda (8:0) in this cgroup:: - # echo 8:0 500 > blkio.weight_device - # cat blkio.weight_device + # echo 8:0 500 > blkio.bfq.weight_device + # cat blkio.bfq.weight_device dev weight 8:0 500 8:16 300 Remove specific weight for /dev/sda in this cgroup:: - # echo 8:0 0 > blkio.weight_device - # cat blkio.weight_device + # echo 8:0 0 > blkio.bfq.weight_device + # cat blkio.bfq.weight_device dev weight 8:16 300 -- blkio.time - - disk time allocated to cgroup per device in milliseconds. First + blkio.time + Disk time allocated to cgroup per device in milliseconds. First two fields specify the major and minor number of the device and third field specifies the disk time allocated to group in milliseconds. -- blkio.sectors - - number of sectors transferred to/from disk by the group. First + blkio.sectors + Number of sectors transferred to/from disk by the group. First two fields specify the major and minor number of the device and third field specifies the number of sectors transferred by the group to/from the device. -- blkio.io_service_bytes - - Number of bytes transferred to/from the disk by the group. These + blkio.io_service_bytes + Number of bytes transferred to/from the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of bytes. -- blkio.io_serviced - - Number of IOs (bio) issued to the disk by the group. These + blkio.io_serviced + Number of IOs (bio) issued to the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of IOs. -- blkio.io_service_time - - Total amount of time between request dispatch and request completion + blkio.io_service_time + Total amount of time between request dispatch and request completion for the IOs done by this cgroup. This is in nanoseconds to make it meaningful for flash devices too. For devices with queue depth of 1, this time represents the actual service time. When queue_depth > 1, @@ -170,8 +175,8 @@ Proportional weight policy files specifies the operation type and the fourth field specifies the io_service_time in ns. -- blkio.io_wait_time - - Total amount of time the IOs for this cgroup spent waiting in the + blkio.io_wait_time + Total amount of time the IOs for this cgroup spent waiting in the scheduler queues for service. This can be greater than the total time elapsed since it is cumulative io_wait_time for all IOs. It is not a measure of total time the cgroup spent waiting but rather a measure of @@ -185,24 +190,24 @@ Proportional weight policy files minor number of the device, third field specifies the operation type and the fourth field specifies the io_wait_time in ns. -- blkio.io_merged - - Total number of bios/requests merged into requests belonging to this + blkio.io_merged + Total number of bios/requests merged into requests belonging to this cgroup. This is further divided by the type of operation - read or write, sync or async. -- blkio.io_queued - - Total number of requests queued up at any given instant for this + blkio.io_queued + Total number of requests queued up at any given instant for this cgroup. This is further divided by the type of operation - read or write, sync or async. -- blkio.avg_queue_size - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.avg_queue_size + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. The average queue size for this cgroup over the entire time of this cgroup's existence. Queue size samples are taken each time one of the queues of this cgroup gets a timeslice. -- blkio.group_wait_time - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.group_wait_time + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This is the amount of time the cgroup had to wait since it became busy (i.e., went from 0 to 1 request queued) to get a timeslice for one of its queues. This is different from the io_wait_time which is the @@ -212,8 +217,8 @@ Proportional weight policy files will only report the group_wait_time accumulated till the last time it got a timeslice and will not include the current delta. -- blkio.empty_time - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.empty_time + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This is the amount of time a cgroup spends without any pending requests when not being served, i.e., it does not include any time spent idling for one of the queues of the cgroup. This is in @@ -221,8 +226,8 @@ Proportional weight policy files the stat will only report the empty_time accumulated till the last time it had a pending request and will not include the current delta. -- blkio.idle_time - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.idle_time + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the existing ones from other queues/cgroups. This is in nanoseconds. If this is read @@ -230,60 +235,60 @@ Proportional weight policy files idle_time accumulated till the last idle period and will not include the current delta. -- blkio.dequeue - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This + blkio.dequeue + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This gives the statistics about how many a times a group was dequeued from service tree of the device. First two fields specify the major and minor number of the device and third field specifies the number of times a group was dequeued from a particular device. -- blkio.*_recursive - - Recursive version of various stats. These files show the + blkio.*_recursive + Recursive version of various stats. These files show the same information as their non-recursive counterparts but include stats from all the descendant cgroups. Throttling/Upper limit policy files ----------------------------------- -- blkio.throttle.read_bps_device - - Specifies upper limit on READ rate from the device. IO rate is + blkio.throttle.read_bps_device + Specifies upper limit on READ rate from the device. IO rate is specified in bytes per second. Rules are per device. Following is the format:: echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.read_bps_device -- blkio.throttle.write_bps_device - - Specifies upper limit on WRITE rate to the device. IO rate is + blkio.throttle.write_bps_device + Specifies upper limit on WRITE rate to the device. IO rate is specified in bytes per second. Rules are per device. Following is the format:: echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.write_bps_device -- blkio.throttle.read_iops_device - - Specifies upper limit on READ rate from the device. IO rate is + blkio.throttle.read_iops_device + Specifies upper limit on READ rate from the device. IO rate is specified in IO per second. Rules are per device. Following is the format:: echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.read_iops_device -- blkio.throttle.write_iops_device - - Specifies upper limit on WRITE rate to the device. IO rate is + blkio.throttle.write_iops_device + Specifies upper limit on WRITE rate to the device. IO rate is specified in io per second. Rules are per device. Following is the format:: echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.write_iops_device -Note: If both BW and IOPS rules are specified for a device, then IO is - subjected to both the constraints. + Note: If both BW and IOPS rules are specified for a device, then IO is + subjected to both the constraints. -- blkio.throttle.io_serviced - - Number of IOs (bio) issued to the disk by the group. These + blkio.throttle.io_serviced + Number of IOs (bio) issued to the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of IOs. -- blkio.throttle.io_service_bytes - - Number of bytes transferred to/from the disk by the group. These + blkio.throttle.io_service_bytes + Number of bytes transferred to/from the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field @@ -291,6 +296,6 @@ Note: If both BW and IOPS rules are specified for a device, then IO is Common files among various policies ----------------------------------- -- blkio.reset_stats - - Writing an int to this file will result in resetting all the stats + blkio.reset_stats + Writing an int to this file will result in resetting all the stats for that cgroup. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index b1e81aa8598a..4e59925e6583 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -56,6 +56,7 @@ v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgrou 5-3-3. IO Latency 5-3-3-1. How IO Latency Throttling Works 5-3-3-2. IO Latency Interface Files + 5-3-4. IO Priority 5-4. PID 5-4-1. PID Interface Files 5-5. Cpuset @@ -1866,6 +1867,60 @@ IO Latency Interface Files duration of time between evaluation events. Windows only elapse with IO activity. Idle periods extend the most recent window. +IO Priority +~~~~~~~~~~~ + +A single attribute controls the behavior of the I/O priority cgroup policy, +namely the blkio.prio.class attribute. The following values are accepted for +that attribute: + + no-change + Do not modify the I/O priority class. + + none-to-rt + For requests that do not have an I/O priority class (NONE), + change the I/O priority class into RT. Do not modify + the I/O priority class of other requests. + + restrict-to-be + For requests that do not have an I/O priority class or that have I/O + priority class RT, change it into BE. Do not modify the I/O priority + class of requests that have priority class IDLE. + + idle + Change the I/O priority class of all requests into IDLE, the lowest + I/O priority class. + +The following numerical values are associated with the I/O priority policies: + ++-------------+---+ +| no-change | 0 | ++-------------+---+ +| none-to-rt | 1 | ++-------------+---+ +| rt-to-be | 2 | ++-------------+---+ +| all-to-idle | 3 | ++-------------+---+ + +The numerical value that corresponds to each I/O priority class is as follows: + ++-------------------------------+---+ +| IOPRIO_CLASS_NONE | 0 | ++-------------------------------+---+ +| IOPRIO_CLASS_RT (real-time) | 1 | ++-------------------------------+---+ +| IOPRIO_CLASS_BE (best effort) | 2 | ++-------------------------------+---+ +| IOPRIO_CLASS_IDLE | 3 | ++-------------------------------+---+ + +The algorithm to set the I/O priority class for a request is as follows: + +- Translate the I/O priority class policy into a number. +- Change the request I/O priority class into the maximum of the I/O priority + class policy number and the numerical I/O priority class. + PID --- diff --git a/Documentation/admin-guide/laptops/laptop-mode.rst b/Documentation/admin-guide/laptops/laptop-mode.rst index c984c4262f2e..b61cc601d298 100644 --- a/Documentation/admin-guide/laptops/laptop-mode.rst +++ b/Documentation/admin-guide/laptops/laptop-mode.rst @@ -101,17 +101,6 @@ this results in concentration of disk activity in a small time interval which occurs only once every 10 minutes, or whenever the disk is forced to spin up by a cache miss. The disk can then be spun down in the periods of inactivity. -If you want to find out which process caused the disk to spin up, you can -gather information by setting the flag /proc/sys/vm/block_dump. When this flag -is set, Linux reports all disk read and write operations that take place, and -all block dirtyings done to files. This makes it possible to debug why a disk -needs to spin up, and to increase battery life even more. The output of -block_dump is written to the kernel output, and it can be retrieved using -"dmesg". When you use block_dump and your kernel logging level also includes -kernel debugging messages, you probably want to turn off klogd, otherwise -the output of block_dump will be logged, causing disk activity that is not -normally there. - Configuration ------------- diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 8387ad0b0b83..003d5cc3751b 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -25,7 +25,6 @@ files can be found in mm/swap.c. Currently, these files are in /proc/sys/vm: - admin_reserve_kbytes -- block_dump - compact_memory - compaction_proactiveness - compact_unevictable_allowed @@ -106,13 +105,6 @@ On x86_64 this is about 128MB. Changing this takes effect whenever an application requests memory. -block_dump -========== - -block_dump enables block I/O debugging when set to a nonzero value. More -information on block I/O debugging is in Documentation/admin-guide/laptops/laptop-mode.rst. - - compact_memory ============== diff --git a/Documentation/block/bfq-iosched.rst b/Documentation/block/bfq-iosched.rst index 66c5a4e54130..df3a8a47f58c 100644 --- a/Documentation/block/bfq-iosched.rst +++ b/Documentation/block/bfq-iosched.rst @@ -553,20 +553,36 @@ throughput sustainable with bfq, because updating the blkio.bfq.* stats is rather costly, especially for some of the stats enabled by CONFIG_BFQ_CGROUP_DEBUG. -Parameters to set ------------------ +Parameters +---------- -For each group, there is only the following parameter to set. +For each group, the following parameters can be set: -weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the -group inside its parent. Available values: 1..1000 (default 100). The -linear mapping between ioprio and weights, described at the beginning -of the tunable section, is still valid, but all weights higher than -IOPRIO_BE_NR*10 are mapped to ioprio 0. + weight + This specifies the default weight for the cgroup inside its parent. + Available values: 1..1000 (default: 100). -Recall that, if low-latency is set, then BFQ automatically raises the -weight of the queues associated with interactive and soft real-time -applications. Unset this tunable if you need/want to control weights. + For cgroup v1, it is set by writing the value to `blkio.bfq.weight`. + + For cgroup v2, it is set by writing the value to `io.bfq.weight`. + (with an optional prefix of `default` and a space). + + The linear mapping between ioprio and weights, described at the beginning + of the tunable section, is still valid, but all weights higher than + IOPRIO_BE_NR*10 are mapped to ioprio 0. + + Recall that, if low-latency is set, then BFQ automatically raises the + weight of the queues associated with interactive and soft real-time + applications. Unset this tunable if you need/want to control weights. + + weight_device + This specifies a per-device weight for the cgroup. The syntax is + `minor:major weight`. A weight of `0` may be used to reset to the default + weight. + + For cgroup v1, it is set by writing the value to `blkio.bfq.weight_device`. + + For cgroup v2, the file name is `io.bfq.weight`. [1] diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 1e894480115b..2183fd8cc350 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -480,7 +480,7 @@ prototypes:: locking rules: ======================= =================== -ops bd_mutex +ops open_mutex ======================= =================== open: yes release: yes diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index ba808543161a..9a8394e96388 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -55,7 +55,6 @@ struct nfhd_device { int id; u32 blocks, bsize; int bshift; - struct request_queue *queue; struct gendisk *disk; }; @@ -119,32 +118,24 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) dev->bsize = bsize; dev->bshift = ffs(bsize) - 10; - dev->queue = blk_alloc_queue(NUMA_NO_NODE); - if (dev->queue == NULL) - goto free_dev; - - blk_queue_logical_block_size(dev->queue, bsize); - - dev->disk = alloc_disk(16); + dev->disk = blk_alloc_disk(NUMA_NO_NODE); if (!dev->disk) - goto free_queue; + goto free_dev; dev->disk->major = major_num; dev->disk->first_minor = dev_id * 16; + dev->disk->minors = 16; dev->disk->fops = &nfhd_ops; dev->disk->private_data = dev; sprintf(dev->disk->disk_name, "nfhd%u", dev_id); set_capacity(dev->disk, (sector_t)blocks * (bsize / 512)); - dev->disk->queue = dev->queue; - + blk_queue_logical_block_size(dev->disk->queue, bsize); add_disk(dev->disk); list_add_tail(&dev->list, &nfhd_list); return 0; -free_queue: - blk_cleanup_queue(dev->queue); free_dev: kfree(dev); out: @@ -186,8 +177,7 @@ static void __exit nfhd_exit(void) list_for_each_entry_safe(dev, next, &nfhd_list, list) { list_del(&dev->list); del_gendisk(dev->disk); - put_disk(dev->disk); - blk_cleanup_queue(dev->queue); + blk_cleanup_disk(dev->disk); kfree(dev); } unregister_blkdev(major_num, "nfhd"); diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index fc09be7b1347..3cdfa00738e0 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -27,7 +27,6 @@ struct simdisk { const char *filename; spinlock_t lock; - struct request_queue *queue; struct gendisk *gd; struct proc_dir_entry *procfile; int users; @@ -266,21 +265,13 @@ static int __init simdisk_setup(struct simdisk *dev, int which, spin_lock_init(&dev->lock); dev->users = 0; - dev->queue = blk_alloc_queue(NUMA_NO_NODE); - if (dev->queue == NULL) { - pr_err("blk_alloc_queue failed\n"); - goto out_alloc_queue; - } - - dev->gd = alloc_disk(SIMDISK_MINORS); - if (dev->gd == NULL) { - pr_err("alloc_disk failed\n"); - goto out_alloc_disk; - } + dev->gd = blk_alloc_disk(NUMA_NO_NODE); + if (!dev->gd) + return -ENOMEM; dev->gd->major = simdisk_major; dev->gd->first_minor = which; + dev->gd->minors = SIMDISK_MINORS; dev->gd->fops = &simdisk_ops; - dev->gd->queue = dev->queue; dev->gd->private_data = dev; snprintf(dev->gd->disk_name, 32, "simdisk%d", which); set_capacity(dev->gd, 0); @@ -288,12 +279,6 @@ static int __init simdisk_setup(struct simdisk *dev, int which, dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev); return 0; - -out_alloc_disk: - blk_cleanup_queue(dev->queue); - dev->queue = NULL; -out_alloc_queue: - return -ENOMEM; } static int __init simdisk_init(void) @@ -343,10 +328,10 @@ static void simdisk_teardown(struct simdisk *dev, int which, char tmp[2] = { '0' + which, 0 }; simdisk_detach(dev); - if (dev->gd) + if (dev->gd) { del_gendisk(dev->gd); - if (dev->queue) - blk_cleanup_queue(dev->queue); + blk_cleanup_disk(dev->gd); + } remove_proc_entry(tmp, procdir); } diff --git a/block/Kconfig b/block/Kconfig index a2297edfdde8..e71c63eaaf52 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -133,6 +133,13 @@ config BLK_WBT dynamically on an algorithm loosely based on CoDel, factoring in the realtime performance of the disk. +config BLK_WBT_MQ + bool "Enable writeback throttling by default" + default y + depends on BLK_WBT + help + Enable writeback throttling by default for request-based block devices. + config BLK_CGROUP_IOLATENCY bool "Enable support for latency based cgroup IO protection" depends on BLK_CGROUP=y @@ -155,12 +162,14 @@ config BLK_CGROUP_IOCOST distributes IO capacity between different groups based on their share of the overall weight distribution. -config BLK_WBT_MQ - bool "Multiqueue writeback throttling" - default y - depends on BLK_WBT +config BLK_CGROUP_IOPRIO + bool "Cgroup I/O controller for assigning an I/O priority class" + depends on BLK_CGROUP help - Enable writeback throttling by default on multiqueue devices. + Enable the .prio interface for assigning an I/O priority class to + requests. The I/O priority class affects the order in which an I/O + scheduler and block devices process requests. Only some I/O schedulers + and some block devices support I/O priorities. config BLK_DEBUG_FS bool "Block layer debugging information in debugfs" diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 2f2158e05a91..64053d67a97b 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -9,6 +9,12 @@ config MQ_IOSCHED_DEADLINE help MQ version of the deadline IO scheduler. +config MQ_IOSCHED_DEADLINE_CGROUP + tristate + default y + depends on MQ_IOSCHED_DEADLINE + depends on BLK_CGROUP + config MQ_IOSCHED_KYBER tristate "Kyber I/O scheduler" default y diff --git a/block/Makefile b/block/Makefile index 8d841f5f986f..bfbe4e13ca1e 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,7 +8,8 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \ blk-exec.o blk-merge.o blk-timeout.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ - genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o + genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \ + disk-events.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o @@ -17,9 +18,12 @@ obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o +obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o +mq-deadline-y += mq-deadline-main.o +mq-deadline-$(CONFIG_MQ_IOSCHED_DEADLINE_CGROUP)+= mq-deadline-cgroup.o obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index acd1f881273e..727955918563 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -364,6 +364,16 @@ static int ref_wr_duration[2]; */ static const unsigned long max_service_from_wr = 120000; +/* + * Maximum time between the creation of two queues, for stable merge + * to be activated (in ms) + */ +static const unsigned long bfq_activation_stable_merging = 600; +/* + * Minimum time to be waited before evaluating delayed stable merge (in ms) + */ +static const unsigned long bfq_late_stable_merging = 600; + #define RQ_BIC(rq) icq_to_bic((rq)->elv.priv[0]) #define RQ_BFQQ(rq) ((rq)->elv.priv[1]) @@ -1729,10 +1739,23 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, bfqq->entity.new_weight == 40; *interactive = !in_burst && idle_for_long_time && bfqq->entity.new_weight == 40; + /* + * Merged bfq_queues are kept out of weight-raising + * (low-latency) mechanisms. The reason is that these queues + * are usually created for non-interactive and + * non-soft-real-time tasks. Yet this is not the case for + * stably-merged queues. These queues are merged just because + * they are created shortly after each other. So they may + * easily serve the I/O of an interactive or soft-real time + * application, if the application happens to spawn multiple + * processes. So let also stably-merged queued enjoy weight + * raising. + */ wr_or_deserves_wr = bfqd->low_latency && (bfqq->wr_coeff > 1 || (bfq_bfqq_sync(bfqq) && - bfqq->bic && (*interactive || soft_rt))); + (bfqq->bic || RQ_BIC(rq)->stably_merged) && + (*interactive || soft_rt))); /* * Using the last flag, update budget and check whether bfqq @@ -1962,14 +1985,18 @@ static void bfq_update_io_intensity(struct bfq_queue *bfqq, u64 now_ns) * Turning back to the detection of a waker queue, a queue Q is deemed * as a waker queue for bfqq if, for three consecutive times, bfqq * happens to become non empty right after a request of Q has been - * completed. In particular, on the first time, Q is tentatively set - * as a candidate waker queue, while on the third consecutive time - * that Q is detected, the field waker_bfqq is set to Q, to confirm - * that Q is a waker queue for bfqq. These detection steps are - * performed only if bfqq has a long think time, so as to make it more - * likely that bfqq's I/O is actually being blocked by a - * synchronization. This last filter, plus the above three-times - * requirement, make false positives less likely. + * completed. In this respect, even if bfqq is empty, we do not check + * for a waker if it still has some in-flight I/O. In fact, in this + * case bfqq is actually still being served by the drive, and may + * receive new I/O on the completion of some of the in-flight + * requests. In particular, on the first time, Q is tentatively set as + * a candidate waker queue, while on the third consecutive time that Q + * is detected, the field waker_bfqq is set to Q, to confirm that Q is + * a waker queue for bfqq. These detection steps are performed only if + * bfqq has a long think time, so as to make it more likely that + * bfqq's I/O is actually being blocked by a synchronization. This + * last filter, plus the above three-times requirement, make false + * positives less likely. * * NOTE * @@ -1995,6 +2022,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (!bfqd->last_completed_rq_bfqq || bfqd->last_completed_rq_bfqq == bfqq || bfq_bfqq_has_short_ttime(bfqq) || + bfqq->dispatched > 0 || now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC || bfqd->last_completed_rq_bfqq == bfqq->waker_bfqq) return; @@ -2317,9 +2345,9 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); + spin_unlock_irq(&bfqd->lock); if (free) blk_mq_free_request(free); - spin_unlock_irq(&bfqd->lock); return ret; } @@ -2405,7 +2433,7 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq, *next_bfqq = bfq_init_rq(next); if (!bfqq) - return; + goto remove; /* * If next and rq belong to the same bfq_queue and next is older @@ -2428,6 +2456,14 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq, bfqq->next_rq = rq; bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags); +remove: + /* Merged request may be in the IO scheduler. Remove it. */ + if (!RB_EMPTY_NODE(&next->rb_node)) { + bfq_remove_request(next->q, next); + if (next_bfqq) + bfqg_stats_update_io_remove(bfqq_group(next_bfqq), + next->cmd_flags); + } } /* Must be called with bfqq != NULL */ @@ -2695,10 +2731,18 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, * costly and complicated. */ if (unlikely(!bfqd->nonrot_with_queueing)) { - if (bic->stable_merge_bfqq && + /* + * Make sure also that bfqq is sync, because + * bic->stable_merge_bfqq may point to some queue (for + * stable merging) also if bic is associated with a + * sync queue, but this bfqq is async + */ + if (bfq_bfqq_sync(bfqq) && bic->stable_merge_bfqq && !bfq_bfqq_just_created(bfqq) && - time_is_after_jiffies(bfqq->split_time + - msecs_to_jiffies(200))) { + time_is_before_jiffies(bfqq->split_time + + msecs_to_jiffies(bfq_late_stable_merging)) && + time_is_before_jiffies(bfqq->creation_time + + msecs_to_jiffies(bfq_late_stable_merging))) { struct bfq_queue *stable_merge_bfqq = bic->stable_merge_bfqq; int proc_ref = min(bfqq_process_refs(bfqq), @@ -5479,7 +5523,7 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, */ if (!last_bfqq_created || time_before(last_bfqq_created->creation_time + - bfqd->bfq_burst_interval, + msecs_to_jiffies(bfq_activation_stable_merging), bfqq->creation_time) || bfqq->entity.parent != last_bfqq_created->entity.parent || bfqq->ioprio != last_bfqq_created->ioprio || @@ -5925,14 +5969,16 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, struct bfq_queue *bfqq; bool idle_timer_disabled = false; unsigned int cmd_flags; + LIST_HEAD(free); #ifdef CONFIG_BFQ_GROUP_IOSCHED if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio) bfqg_stats_update_legacy_io(q, rq); #endif spin_lock_irq(&bfqd->lock); - if (blk_mq_sched_try_insert_merge(q, rq)) { + if (blk_mq_sched_try_insert_merge(q, rq, &free)) { spin_unlock_irq(&bfqd->lock); + blk_mq_free_requests(&free); return; } @@ -6129,11 +6175,13 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) * of other queues. But a false waker will unjustly steal * bandwidth to its supposedly woken queue. So considering * also shared queues in the waking mechanism may cause more - * control troubles than throughput benefits. Then do not set - * last_completed_rq_bfqq to bfqq if bfqq is a shared queue. + * control troubles than throughput benefits. Then reset + * last_completed_rq_bfqq if bfqq is a shared queue. */ if (!bfq_bfqq_coop(bfqq)) bfqd->last_completed_rq_bfqq = bfqq; + else + bfqd->last_completed_rq_bfqq = NULL; /* * If we are waiting to discover whether the request pattern @@ -6376,6 +6424,7 @@ static void bfq_finish_requeue_request(struct request *rq) { struct bfq_queue *bfqq = RQ_BFQQ(rq); struct bfq_data *bfqd; + unsigned long flags; /* * rq either is not associated with any icq, or is an already @@ -6393,39 +6442,15 @@ static void bfq_finish_requeue_request(struct request *rq) rq->io_start_time_ns, rq->cmd_flags); + spin_lock_irqsave(&bfqd->lock, flags); if (likely(rq->rq_flags & RQF_STARTED)) { - unsigned long flags; - - spin_lock_irqsave(&bfqd->lock, flags); - if (rq == bfqd->waited_rq) bfq_update_inject_limit(bfqd, bfqq); bfq_completed_request(bfqq, bfqd); - bfq_finish_requeue_request_body(bfqq); - - spin_unlock_irqrestore(&bfqd->lock, flags); - } else { - /* - * Request rq may be still/already in the scheduler, - * in which case we need to remove it (this should - * never happen in case of requeue). And we cannot - * defer such a check and removal, to avoid - * inconsistencies in the time interval from the end - * of this function to the start of the deferred work. - * This situation seems to occur only in process - * context, as a consequence of a merge. In the - * current version of the code, this implies that the - * lock is held. - */ - - if (!RB_EMPTY_NODE(&rq->rb_node)) { - bfq_remove_request(rq->q, rq); - bfqg_stats_update_io_remove(bfqq_group(bfqq), - rq->cmd_flags); - } - bfq_finish_requeue_request_body(bfqq); } + bfq_finish_requeue_request_body(bfqq); + spin_unlock_irqrestore(&bfqd->lock, flags); /* * Reset private fields. In case of a requeue, this allows diff --git a/block/bio.c b/block/bio.c index 44205dfb6b60..1fab762e079b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1375,8 +1375,7 @@ static inline bool bio_remaining_done(struct bio *bio) * * bio_endio() can be called several times on a bio that has been chained * using bio_chain(). The ->bi_end_io() function will only be called the - * last time. At this point the BLK_TA_COMPLETE tracing event will be - * generated if BIO_TRACE_COMPLETION is set. + * last time. **/ void bio_endio(struct bio *bio) { @@ -1389,6 +1388,11 @@ again: if (bio->bi_bdev) rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio); + if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { + trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio); + bio_clear_flag(bio, BIO_TRACE_COMPLETION); + } + /* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that @@ -1402,11 +1406,6 @@ again: goto again; } - if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { - trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio); - bio_clear_flag(bio, BIO_TRACE_COMPLETION); - } - blk_throtl_bio_endio(bio); /* release cgroup info */ bio_uninit(bio); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 582d2f18717e..7b06a5fa3cac 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -31,6 +31,7 @@ #include <linux/tracehook.h> #include <linux/psi.h> #include "blk.h" +#include "blk-ioprio.h" /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. @@ -1183,15 +1184,18 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); - ret = blk_throtl_init(q); + ret = blk_iolatency_init(q); if (ret) goto err_destroy_all; - ret = blk_iolatency_init(q); - if (ret) { - blk_throtl_exit(q); + ret = blk_ioprio_init(q); + if (ret) goto err_destroy_all; - } + + ret = blk_throtl_init(q); + if (ret) + goto err_destroy_all; + return 0; err_destroy_all: @@ -1217,32 +1221,6 @@ void blkcg_exit_queue(struct request_queue *q) blk_throtl_exit(q); } -/* - * We cannot support shared io contexts, as we have no mean to support - * two tasks with the same ioc in two different groups without major rework - * of the main cic data structures. For now we allow a task to change - * its cgroup only if it's the only owner of its ioc. - */ -static int blkcg_can_attach(struct cgroup_taskset *tset) -{ - struct task_struct *task; - struct cgroup_subsys_state *dst_css; - struct io_context *ioc; - int ret = 0; - - /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, dst_css, tset) { - task_lock(task); - ioc = task->io_context; - if (ioc && atomic_read(&ioc->nr_tasks) > 1) - ret = -EINVAL; - task_unlock(task); - if (ret) - break; - } - return ret; -} - static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; @@ -1275,7 +1253,6 @@ struct cgroup_subsys io_cgrp_subsys = { .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, - .can_attach = blkcg_can_attach, .css_rstat_flush = blkcg_rstat_flush, .bind = blkcg_bind, .dfl_cftypes = blkcg_files, diff --git a/block/blk-core.c b/block/blk-core.c index 9bcdae93f6d4..514838ccab2d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -599,7 +599,6 @@ fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } -EXPORT_SYMBOL(blk_alloc_queue); /** * blk_get_queue - increment the request_queue refcount @@ -1086,15 +1085,6 @@ blk_qc_t submit_bio(struct bio *bio) task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } - - if (unlikely(block_dump)) { - char b[BDEVNAME_SIZE]; - printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", - current->comm, task_pid_nr(current), - op_is_write(bio_op(bio)) ? "WRITE" : "READ", - (unsigned long long)bio->bi_iter.bi_sector, - bio_devname(bio, b), count); - } } /* @@ -1394,26 +1384,22 @@ void blk_steal_bios(struct bio_list *list, struct request *rq) EXPORT_SYMBOL_GPL(blk_steal_bios); /** - * blk_update_request - Special helper function for request stacking drivers + * blk_update_request - Complete multiple bytes without completing the request * @req: the request being processed * @error: block status code - * @nr_bytes: number of bytes to complete @req + * @nr_bytes: number of bytes to complete for @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * - * This special helper function is only for request stacking drivers - * (e.g. request-based dm) so that they can handle partial completion. - * Actual device drivers should use blk_mq_end_request instead. - * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: - * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both - * blk_rq_bytes() and in blk_update_request(). + * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function + * except in the consistency check at the end of this function. * * Return: * %false - this request doesn't have any more data diff --git a/block/blk-flush.c b/block/blk-flush.c index 7942ca6ed321..1002f6c58181 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -219,8 +219,6 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) unsigned long flags = 0; struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); - blk_account_io_flush(flush_rq); - /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); @@ -230,6 +228,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) return; } + blk_account_io_flush(flush_rq); /* * Flush request has to be marked as IDLE when it is really ended * because its .end_io() is called from timeout code path too for diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c new file mode 100644 index 000000000000..332a07761bf8 --- /dev/null +++ b/block/blk-ioprio.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Block rq-qos policy for assigning an I/O priority class to requests. + * + * Using an rq-qos policy for assigning I/O priority class has two advantages + * over using the ioprio_set() system call: + * + * - This policy is cgroup based so it has all the advantages of cgroups. + * - While ioprio_set() does not affect page cache writeback I/O, this rq-qos + * controller affects page cache writeback I/O for filesystems that support + * assiociating a cgroup with writeback I/O. See also + * Documentation/admin-guide/cgroup-v2.rst. + */ + +#include <linux/blk-cgroup.h> +#include <linux/blk-mq.h> +#include <linux/blk_types.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include "blk-ioprio.h" +#include "blk-rq-qos.h" + +/** + * enum prio_policy - I/O priority class policy. + * @POLICY_NO_CHANGE: (default) do not modify the I/O priority class. + * @POLICY_NONE_TO_RT: modify IOPRIO_CLASS_NONE into IOPRIO_CLASS_RT. + * @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into + * IOPRIO_CLASS_BE. + * @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE. + * + * See also <linux/ioprio.h>. + */ +enum prio_policy { + POLICY_NO_CHANGE = 0, + POLICY_NONE_TO_RT = 1, + POLICY_RESTRICT_TO_BE = 2, + POLICY_ALL_TO_IDLE = 3, +}; + +static const char *policy_name[] = { + [POLICY_NO_CHANGE] = "no-change", + [POLICY_NONE_TO_RT] = "none-to-rt", + [POLICY_RESTRICT_TO_BE] = "restrict-to-be", + [POLICY_ALL_TO_IDLE] = "idle", +}; + +static struct blkcg_policy ioprio_policy; + +/** + * struct ioprio_blkg - Per (cgroup, request queue) data. + * @pd: blkg_policy_data structure. + */ +struct ioprio_blkg { + struct blkg_policy_data pd; +}; + +/** + * struct ioprio_blkcg - Per cgroup data. + * @cpd: blkcg_policy_data structure. + * @prio_policy: One of the IOPRIO_CLASS_* values. See also <linux/ioprio.h>. + */ +struct ioprio_blkcg { + struct blkcg_policy_data cpd; + enum prio_policy prio_policy; +}; + +static inline struct ioprio_blkg *pd_to_ioprio(struct blkg_policy_data *pd) +{ + return pd ? container_of(pd, struct ioprio_blkg, pd) : NULL; +} + +static struct ioprio_blkcg *blkcg_to_ioprio_blkcg(struct blkcg *blkcg) +{ + return container_of(blkcg_to_cpd(blkcg, &ioprio_policy), + struct ioprio_blkcg, cpd); +} + +static struct ioprio_blkcg * +ioprio_blkcg_from_css(struct cgroup_subsys_state *css) +{ + return blkcg_to_ioprio_blkcg(css_to_blkcg(css)); +} + +static struct ioprio_blkcg *ioprio_blkcg_from_bio(struct bio *bio) +{ + struct blkg_policy_data *pd = blkg_to_pd(bio->bi_blkg, &ioprio_policy); + + if (!pd) + return NULL; + + return blkcg_to_ioprio_blkcg(pd->blkg->blkcg); +} + +static int ioprio_show_prio_policy(struct seq_file *sf, void *v) +{ + struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(seq_css(sf)); + + seq_printf(sf, "%s\n", policy_name[blkcg->prio_policy]); + return 0; +} + +static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(of_css(of)); + int ret; + + if (off != 0) + return -EIO; + /* kernfs_fop_write_iter() terminates 'buf' with '\0'. */ + ret = sysfs_match_string(policy_name, buf); + if (ret < 0) + return ret; + blkcg->prio_policy = ret; + + return nbytes; +} + +static struct blkg_policy_data * +ioprio_alloc_pd(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) +{ + struct ioprio_blkg *ioprio_blkg; + + ioprio_blkg = kzalloc(sizeof(*ioprio_blkg), gfp); + if (!ioprio_blkg) + return NULL; + + return &ioprio_blkg->pd; +} + +static void ioprio_free_pd(struct blkg_policy_data *pd) +{ + struct ioprio_blkg *ioprio_blkg = pd_to_ioprio(pd); + + kfree(ioprio_blkg); +} + +static struct blkcg_policy_data *ioprio_alloc_cpd(gfp_t gfp) +{ + struct ioprio_blkcg *blkcg; + + blkcg = kzalloc(sizeof(*blkcg), gfp); + if (!blkcg) + return NULL; + blkcg->prio_policy = POLICY_NO_CHANGE; + return &blkcg->cpd; +} + +static void ioprio_free_cpd(struct blkcg_policy_data *cpd) +{ + struct ioprio_blkcg *blkcg = container_of(cpd, typeof(*blkcg), cpd); + + kfree(blkcg); +} + +#define IOPRIO_ATTRS \ + { \ + .name = "prio.class", \ + .seq_show = ioprio_show_prio_policy, \ + .write = ioprio_set_prio_policy, \ + }, \ + { } /* sentinel */ + +/* cgroup v2 attributes */ +static struct cftype ioprio_files[] = { + IOPRIO_ATTRS +}; + +/* cgroup v1 attributes */ +static struct cftype ioprio_legacy_files[] = { + IOPRIO_ATTRS +}; + +static struct blkcg_policy ioprio_policy = { + .dfl_cftypes = ioprio_files, + .legacy_cftypes = ioprio_legacy_files, + + .cpd_alloc_fn = ioprio_alloc_cpd, + .cpd_free_fn = ioprio_free_cpd, + + .pd_alloc_fn = ioprio_alloc_pd, + .pd_free_fn = ioprio_free_pd, +}; + +struct blk_ioprio { + struct rq_qos rqos; +}; + +static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq, + struct bio *bio) +{ + struct ioprio_blkcg *blkcg = ioprio_blkcg_from_bio(bio); + + /* + * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers + * correspond to a lower priority. Hence, the max_t() below selects + * the lower priority of bi_ioprio and the cgroup I/O priority class. + * If the cgroup policy has been set to POLICY_NO_CHANGE == 0, the + * bio I/O priority is not modified. If the bio I/O priority equals + * IOPRIO_CLASS_NONE, the cgroup I/O priority is assigned to the bio. + */ + bio->bi_ioprio = max_t(u16, bio->bi_ioprio, + IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0)); +} + +static void blkcg_ioprio_exit(struct rq_qos *rqos) +{ + struct blk_ioprio *blkioprio_blkg = + container_of(rqos, typeof(*blkioprio_blkg), rqos); + + blkcg_deactivate_policy(rqos->q, &ioprio_policy); + kfree(blkioprio_blkg); +} + +static struct rq_qos_ops blkcg_ioprio_ops = { + .track = blkcg_ioprio_track, + .exit = blkcg_ioprio_exit, +}; + +int blk_ioprio_init(struct request_queue *q) +{ + struct blk_ioprio *blkioprio_blkg; + struct rq_qos *rqos; + int ret; + + blkioprio_blkg = kzalloc(sizeof(*blkioprio_blkg), GFP_KERNEL); + if (!blkioprio_blkg) + return -ENOMEM; + + ret = blkcg_activate_policy(q, &ioprio_policy); + if (ret) { + kfree(blkioprio_blkg); + return ret; + } + + rqos = &blkioprio_blkg->rqos; + rqos->id = RQ_QOS_IOPRIO; + rqos->ops = &blkcg_ioprio_ops; + rqos->q = q; + + /* + * Registering the rq-qos policy after activating the blk-cgroup + * policy guarantees that ioprio_blkcg_from_bio(bio) != NULL in the + * rq-qos callbacks. + */ + rq_qos_add(q, rqos); + + return 0; +} + +static int __init ioprio_init(void) +{ + return blkcg_policy_register(&ioprio_policy); +} + +static void __exit ioprio_exit(void) +{ + blkcg_policy_unregister(&ioprio_policy); +} + +module_init(ioprio_init); +module_exit(ioprio_exit); diff --git a/block/blk-ioprio.h b/block/blk-ioprio.h new file mode 100644 index 000000000000..a7785c2f1aea --- /dev/null +++ b/block/blk-ioprio.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BLK_IOPRIO_H_ +#define _BLK_IOPRIO_H_ + +#include <linux/kconfig.h> + +struct request_queue; + +#ifdef CONFIG_BLK_CGROUP_IOPRIO +int blk_ioprio_init(struct request_queue *q); +#else +static inline int blk_ioprio_init(struct request_queue *q) +{ + return 0; +} +#endif + +#endif /* _BLK_IOPRIO_H_ */ diff --git a/block/blk-merge.c b/block/blk-merge.c index 4d97fb6dd226..a11b3b53717e 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -559,10 +559,14 @@ static inline unsigned int blk_rq_get_max_segments(struct request *rq) static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { - if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) + if (blk_integrity_merge_bio(req->q, req, bio) == false) goto no_merge; - if (blk_integrity_merge_bio(req->q, req, bio) == false) + /* discard request merge won't add new segment */ + if (req_op(req) == REQ_OP_DISCARD) + return 1; + + if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; /* @@ -846,18 +850,15 @@ static struct request *attempt_front_merge(struct request_queue *q, return NULL; } -int blk_attempt_req_merge(struct request_queue *q, struct request *rq, - struct request *next) +/* + * Try to merge 'next' into 'rq'. Return true if the merge happened, false + * otherwise. The caller is responsible for freeing 'next' if the merge + * happened. + */ +bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, + struct request *next) { - struct request *free; - - free = attempt_merge(q, rq, next); - if (free) { - blk_put_request(free); - return 1; - } - - return 0; + return attempt_merge(q, rq, next); } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 2a75bc7401df..4b66d2776eda 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -937,6 +937,21 @@ void blk_mq_debugfs_unregister_sched(struct request_queue *q) q->sched_debugfs_dir = NULL; } +static const char *rq_qos_id_to_name(enum rq_qos_id id) +{ + switch (id) { + case RQ_QOS_WBT: + return "wbt"; + case RQ_QOS_LATENCY: + return "latency"; + case RQ_QOS_COST: + return "cost"; + case RQ_QOS_IOPRIO: + return "ioprio"; + } + return "unknown"; +} + void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) { debugfs_remove_recursive(rqos->debugfs_dir); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 996a4b2f73aa..c838d81ac058 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -168,9 +168,19 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) * in blk_mq_dispatch_rq_list(). */ list_add_tail(&rq->queuelist, &rq_list); + count++; if (rq->mq_hctx != hctx) multi_hctxs = true; - } while (++count < max_dispatch); + + /* + * If we cannot get tag for the request, stop dequeueing + * requests from the IO scheduler. We are unlikely to be able + * to submit them anyway and it creates false impression for + * scheduling heuristics that the device can take more IO. + */ + if (!blk_mq_get_driver_tag(rq)) + break; + } while (count < max_dispatch); if (!count) { if (run_queue) @@ -284,8 +294,7 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; - struct elevator_queue *e = q->elevator; - const bool has_sched_dispatch = e && e->type->ops.dispatch_request; + const bool has_sched = q->elevator; int ret = 0; LIST_HEAD(rq_list); @@ -316,12 +325,12 @@ static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); if (blk_mq_dispatch_rq_list(hctx, &rq_list, 0)) { - if (has_sched_dispatch) + if (has_sched) ret = blk_mq_do_dispatch_sched(hctx); else ret = blk_mq_do_dispatch_ctx(hctx); } - } else if (has_sched_dispatch) { + } else if (has_sched) { ret = blk_mq_do_dispatch_sched(hctx); } else if (hctx->dispatch_busy) { /* dequeue request one by one from sw queue if queue is busy */ @@ -390,9 +399,10 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, return ret; } -bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq) +bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq, + struct list_head *free) { - return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq); + return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq, free); } EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge); @@ -453,7 +463,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, goto run; } - if (e && e->type->ops.insert_requests) { + if (e) { LIST_HEAD(list); list_add(&rq->queuelist, &list); @@ -484,9 +494,9 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, percpu_ref_get(&q->q_usage_counter); e = hctx->queue->elevator; - if (e && e->type->ops.insert_requests) + if (e) { e->type->ops.insert_requests(hctx, list, false); - else { + } else { /* * try to issue requests directly if the hw queue isn't * busy in case of 'none' scheduler, and this way may save @@ -509,11 +519,9 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { - unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; - if (hctx->sched_tags) { blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); - blk_mq_free_rq_map(hctx->sched_tags, flags); + blk_mq_free_rq_map(hctx->sched_tags, set->flags); hctx->sched_tags = NULL; } } @@ -523,12 +531,10 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, unsigned int hctx_idx) { struct blk_mq_tag_set *set = q->tag_set; - /* Clear HCTX_SHARED so tags are init'ed */ - unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; int ret; hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests, - set->reserved_tags, flags); + set->reserved_tags, set->flags); if (!hctx->sched_tags) return -ENOMEM; @@ -546,16 +552,50 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q) int i; queue_for_each_hw_ctx(q, hctx, i) { - /* Clear HCTX_SHARED so tags are freed */ - unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; - if (hctx->sched_tags) { - blk_mq_free_rq_map(hctx->sched_tags, flags); + blk_mq_free_rq_map(hctx->sched_tags, hctx->flags); hctx->sched_tags = NULL; } } } +static int blk_mq_init_sched_shared_sbitmap(struct request_queue *queue) +{ + struct blk_mq_tag_set *set = queue->tag_set; + int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); + struct blk_mq_hw_ctx *hctx; + int ret, i; + + /* + * Set initial depth at max so that we don't need to reallocate for + * updating nr_requests. + */ + ret = blk_mq_init_bitmaps(&queue->sched_bitmap_tags, + &queue->sched_breserved_tags, + MAX_SCHED_RQ, set->reserved_tags, + set->numa_node, alloc_policy); + if (ret) + return ret; + + queue_for_each_hw_ctx(queue, hctx, i) { + hctx->sched_tags->bitmap_tags = + &queue->sched_bitmap_tags; + hctx->sched_tags->breserved_tags = + &queue->sched_breserved_tags; + } + + sbitmap_queue_resize(&queue->sched_bitmap_tags, + queue->nr_requests - set->reserved_tags); + + return 0; +} + +static void blk_mq_exit_sched_shared_sbitmap(struct request_queue *queue) +{ + sbitmap_queue_free(&queue->sched_bitmap_tags); + sbitmap_queue_free(&queue->sched_breserved_tags); +} + int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) { struct blk_mq_hw_ctx *hctx; @@ -580,12 +620,18 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_sched_alloc_tags(q, hctx, i); if (ret) - goto err; + goto err_free_tags; + } + + if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) { + ret = blk_mq_init_sched_shared_sbitmap(q); + if (ret) + goto err_free_tags; } ret = e->ops.init_sched(q, e); if (ret) - goto err; + goto err_free_sbitmap; blk_mq_debugfs_register_sched(q); @@ -605,7 +651,10 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) return 0; -err: +err_free_sbitmap: + if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) + blk_mq_exit_sched_shared_sbitmap(q); +err_free_tags: blk_mq_sched_free_requests(q); blk_mq_sched_tags_teardown(q); q->elevator = NULL; @@ -631,6 +680,7 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) { struct blk_mq_hw_ctx *hctx; unsigned int i; + unsigned int flags = 0; queue_for_each_hw_ctx(q, hctx, i) { blk_mq_debugfs_unregister_sched_hctx(hctx); @@ -638,10 +688,13 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) e->type->ops.exit_hctx(hctx, i); hctx->sched_data = NULL; } + flags = hctx->flags; } blk_mq_debugfs_unregister_sched(q); if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); blk_mq_sched_tags_teardown(q); + if (blk_mq_is_sbitmap_shared(flags)) + blk_mq_exit_sched_shared_sbitmap(q); q->elevator = NULL; } diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 5b18ab915c65..5246ae040704 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -5,13 +5,16 @@ #include "blk-mq.h" #include "blk-mq-tag.h" +#define MAX_SCHED_RQ (16 * BLKDEV_MAX_RQ) + void blk_mq_sched_assign_ioc(struct request *rq); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request); bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs); -bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq); +bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq, + struct list_head *free); void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 2a37731e8244..86f87346232a 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -13,6 +13,7 @@ #include <linux/delay.h> #include "blk.h" #include "blk-mq.h" +#include "blk-mq-sched.h" #include "blk-mq-tag.h" /* @@ -199,6 +200,20 @@ struct bt_iter_data { bool reserved; }; +static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, + unsigned int bitnr) +{ + struct request *rq; + unsigned long flags; + + spin_lock_irqsave(&tags->lock, flags); + rq = tags->rqs[bitnr]; + if (!rq || !refcount_inc_not_zero(&rq->ref)) + rq = NULL; + spin_unlock_irqrestore(&tags->lock, flags); + return rq; +} + static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_iter_data *iter_data = data; @@ -206,18 +221,22 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) struct blk_mq_tags *tags = hctx->tags; bool reserved = iter_data->reserved; struct request *rq; + bool ret = true; if (!reserved) bitnr += tags->nr_reserved_tags; - rq = tags->rqs[bitnr]; - /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx) - return iter_data->fn(hctx, rq, iter_data->data, reserved); - return true; + rq = blk_mq_find_and_get_req(tags, bitnr); + if (!rq) + return true; + + if (rq->q == hctx->queue && rq->mq_hctx == hctx) + ret = iter_data->fn(hctx, rq, iter_data->data, reserved); + blk_mq_put_rq_ref(rq); + return ret; } /** @@ -264,6 +283,8 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) struct blk_mq_tags *tags = iter_data->tags; bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED; struct request *rq; + bool ret = true; + bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); if (!reserved) bitnr += tags->nr_reserved_tags; @@ -272,16 +293,19 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (iter_data->flags & BT_TAG_ITER_STATIC_RQS) + if (iter_static_rqs) rq = tags->static_rqs[bitnr]; else - rq = tags->rqs[bitnr]; + rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; - if ((iter_data->flags & BT_TAG_ITER_STARTED) && - !blk_mq_request_started(rq)) - return true; - return iter_data->fn(rq, iter_data->data, reserved); + + if (!(iter_data->flags & BT_TAG_ITER_STARTED) || + blk_mq_request_started(rq)) + ret = iter_data->fn(rq, iter_data->data, reserved); + if (!iter_static_rqs) + blk_mq_put_rq_ref(rq); + return ret; } /** @@ -348,6 +372,9 @@ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. + * + * We grab one request reference before calling @fn and release it after + * @fn returns. */ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv) @@ -445,39 +472,54 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, node); } -static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, - int node, int alloc_policy) +int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, + struct sbitmap_queue *breserved_tags, + unsigned int queue_depth, unsigned int reserved, + int node, int alloc_policy) { - unsigned int depth = tags->nr_tags - tags->nr_reserved_tags; + unsigned int depth = queue_depth - reserved; bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; - if (bt_alloc(&tags->__bitmap_tags, depth, round_robin, node)) + if (bt_alloc(bitmap_tags, depth, round_robin, node)) return -ENOMEM; - if (bt_alloc(&tags->__breserved_tags, tags->nr_reserved_tags, - round_robin, node)) + if (bt_alloc(breserved_tags, reserved, round_robin, node)) goto free_bitmap_tags; + return 0; + +free_bitmap_tags: + sbitmap_queue_free(bitmap_tags); + return -ENOMEM; +} + +static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, + int node, int alloc_policy) +{ + int ret; + + ret = blk_mq_init_bitmaps(&tags->__bitmap_tags, + &tags->__breserved_tags, + tags->nr_tags, tags->nr_reserved_tags, + node, alloc_policy); + if (ret) + return ret; + tags->bitmap_tags = &tags->__bitmap_tags; tags->breserved_tags = &tags->__breserved_tags; return 0; -free_bitmap_tags: - sbitmap_queue_free(&tags->__bitmap_tags); - return -ENOMEM; } -int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) +int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set) { - unsigned int depth = set->queue_depth - set->reserved_tags; int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); - bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; - int i, node = set->numa_node; + int i, ret; - if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node)) - return -ENOMEM; - if (bt_alloc(&set->__breserved_tags, set->reserved_tags, - round_robin, node)) - goto free_bitmap_tags; + ret = blk_mq_init_bitmaps(&set->__bitmap_tags, &set->__breserved_tags, + set->queue_depth, set->reserved_tags, + set->numa_node, alloc_policy); + if (ret) + return ret; for (i = 0; i < set->nr_hw_queues; i++) { struct blk_mq_tags *tags = set->tags[i]; @@ -487,9 +529,6 @@ int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) } return 0; -free_bitmap_tags: - sbitmap_queue_free(&set->__bitmap_tags); - return -ENOMEM; } void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) @@ -516,6 +555,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; + spin_lock_init(&tags->lock); if (blk_mq_is_sbitmap_shared(flags)) return tags; @@ -551,8 +591,6 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; - /* Only sched tags can grow, so clear HCTX_SHARED flag */ - unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; struct blk_mq_tags *new; bool ret; @@ -563,21 +601,21 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, * We need some sort of upper limit, set it high enough that * no valid use cases should require more. */ - if (tdepth > 16 * BLKDEV_MAX_RQ) + if (tdepth > MAX_SCHED_RQ) return -EINVAL; new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, - tags->nr_reserved_tags, flags); + tags->nr_reserved_tags, set->flags); if (!new) return -ENOMEM; ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth); if (ret) { - blk_mq_free_rq_map(new, flags); + blk_mq_free_rq_map(new, set->flags); return -ENOMEM; } blk_mq_free_rqs(set, *tagsptr, hctx->queue_num); - blk_mq_free_rq_map(*tagsptr, flags); + blk_mq_free_rq_map(*tagsptr, set->flags); *tagsptr = new; } else { /* diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 7d3e6b333a4a..8ed55af08427 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -20,17 +20,26 @@ struct blk_mq_tags { struct request **rqs; struct request **static_rqs; struct list_head page_list; + + /* + * used to clear request reference in rqs[] before freeing one + * request pool + */ + spinlock_t lock; }; extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, unsigned int flags); extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags); +extern int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, + struct sbitmap_queue *breserved_tags, + unsigned int queue_depth, + unsigned int reserved, + int node, int alloc_policy); -extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, - unsigned int flags); +extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set); extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set); - extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); diff --git a/block/blk-mq.c b/block/blk-mq.c index e41edae97487..2e9fd0ec63d7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -909,6 +909,14 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next) return false; } +void blk_mq_put_rq_ref(struct request *rq) +{ + if (is_flush_rq(rq, rq->mq_hctx)) + rq->end_io(rq, 0); + else if (refcount_dec_and_test(&rq->ref)) + __blk_mq_free_request(rq); +} + static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { @@ -942,11 +950,7 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, if (blk_mq_req_expired(rq, next)) blk_mq_rq_timed_out(rq, reserved); - if (is_flush_rq(rq, hctx)) - rq->end_io(rq, 0); - else if (refcount_dec_and_test(&rq->ref)) - __blk_mq_free_request(rq); - + blk_mq_put_rq_ref(rq); return true; } @@ -1100,7 +1104,7 @@ static bool __blk_mq_get_driver_tag(struct request *rq) return true; } -static bool blk_mq_get_driver_tag(struct request *rq) +bool blk_mq_get_driver_tag(struct request *rq) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; @@ -1220,9 +1224,6 @@ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) { unsigned int ewma; - if (hctx->queue->elevator) - return; - ewma = hctx->dispatch_busy; if (!ewma && !busy) @@ -2303,6 +2304,45 @@ queue_exit: return BLK_QC_T_NONE; } +static size_t order_to_size(unsigned int order) +{ + return (size_t)PAGE_SIZE << order; +} + +/* called before freeing request pool in @tags */ +static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set, + struct blk_mq_tags *tags, unsigned int hctx_idx) +{ + struct blk_mq_tags *drv_tags = set->tags[hctx_idx]; + struct page *page; + unsigned long flags; + + list_for_each_entry(page, &tags->page_list, lru) { + unsigned long start = (unsigned long)page_address(page); + unsigned long end = start + order_to_size(page->private); + int i; + + for (i = 0; i < set->queue_depth; i++) { + struct request *rq = drv_tags->rqs[i]; + unsigned long rq_addr = (unsigned long)rq; + + if (rq_addr >= start && rq_addr < end) { + WARN_ON_ONCE(refcount_read(&rq->ref) != 0); + cmpxchg(&drv_tags->rqs[i], rq, NULL); + } + } + } + + /* + * Wait until all pending iteration is done. + * + * Request reference is cleared and it is guaranteed to be observed + * after the ->lock is released. + */ + spin_lock_irqsave(&drv_tags->lock, flags); + spin_unlock_irqrestore(&drv_tags->lock, flags); +} + void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { @@ -2321,6 +2361,8 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, } } + blk_mq_clear_rq_mapping(set, tags, hctx_idx); + while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); @@ -2380,11 +2422,6 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, return tags; } -static size_t order_to_size(unsigned int order) -{ - return (size_t)PAGE_SIZE << order; -} - static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { @@ -2603,16 +2640,49 @@ static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) &hctx->cpuhp_dead); } +/* + * Before freeing hw queue, clearing the flush request reference in + * tags->rqs[] for avoiding potential UAF. + */ +static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, + unsigned int queue_depth, struct request *flush_rq) +{ + int i; + unsigned long flags; + + /* The hw queue may not be mapped yet */ + if (!tags) + return; + + WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0); + + for (i = 0; i < queue_depth; i++) + cmpxchg(&tags->rqs[i], flush_rq, NULL); + + /* + * Wait until all pending iteration is done. + * + * Request reference is cleared and it is guaranteed to be observed + * after the ->lock is released. + */ + spin_lock_irqsave(&tags->lock, flags); + spin_unlock_irqrestore(&tags->lock, flags); +} + /* hctx->ctxs will be freed in queue's release handler */ static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { + struct request *flush_rq = hctx->fq->flush_rq; + if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); + blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], + set->queue_depth, flush_rq); if (set->ops->exit_request) - set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx); + set->ops->exit_request(set, flush_rq, hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); @@ -3042,21 +3112,18 @@ void blk_mq_release(struct request_queue *q) struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata) { - struct request_queue *uninit_q, *q; + struct request_queue *q; + int ret; - uninit_q = blk_alloc_queue(set->numa_node); - if (!uninit_q) + q = blk_alloc_queue(set->numa_node); + if (!q) return ERR_PTR(-ENOMEM); - uninit_q->queuedata = queuedata; - - /* - * Initialize the queue without an elevator. device_add_disk() will do - * the initialization. - */ - q = blk_mq_init_allocated_queue(set, uninit_q, false); - if (IS_ERR(q)) - blk_cleanup_queue(uninit_q); - + q->queuedata = queuedata; + ret = blk_mq_init_allocated_queue(set, q); + if (ret) { + blk_cleanup_queue(q); + return ERR_PTR(ret); + } return q; } EXPORT_SYMBOL_GPL(blk_mq_init_queue_data); @@ -3067,39 +3134,24 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) } EXPORT_SYMBOL(blk_mq_init_queue); -/* - * Helper for setting up a queue with mq ops, given queue depth, and - * the passed in mq ops flags. - */ -struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, - const struct blk_mq_ops *ops, - unsigned int queue_depth, - unsigned int set_flags) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata) { struct request_queue *q; - int ret; + struct gendisk *disk; - memset(set, 0, sizeof(*set)); - set->ops = ops; - set->nr_hw_queues = 1; - set->nr_maps = 1; - set->queue_depth = queue_depth; - set->numa_node = NUMA_NO_NODE; - set->flags = set_flags; - - ret = blk_mq_alloc_tag_set(set); - if (ret) - return ERR_PTR(ret); + q = blk_mq_init_queue_data(set, queuedata); + if (IS_ERR(q)) + return ERR_CAST(q); - q = blk_mq_init_queue(set); - if (IS_ERR(q)) { - blk_mq_free_tag_set(set); - return q; + disk = __alloc_disk_node(0, set->numa_node); + if (!disk) { + blk_cleanup_queue(q); + return ERR_PTR(-ENOMEM); } - - return q; + disk->queue = q; + return disk; } -EXPORT_SYMBOL(blk_mq_init_sq_queue); +EXPORT_SYMBOL(__blk_mq_alloc_disk); static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, @@ -3212,9 +3264,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, mutex_unlock(&q->sysfs_lock); } -struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, - struct request_queue *q, - bool elevator_init) +int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, + struct request_queue *q) { /* mark the queue as mq asap */ q->mq_ops = set->ops; @@ -3264,11 +3315,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); - - if (elevator_init) - elevator_init_mq(q); - - return q; + return 0; err_hctxs: kfree(q->queue_hw_ctx); @@ -3279,7 +3326,7 @@ err_poll: q->poll_cb = NULL; err_exit: q->mq_ops = NULL; - return ERR_PTR(-ENOMEM); + return -ENOMEM; } EXPORT_SYMBOL(blk_mq_init_allocated_queue); @@ -3491,7 +3538,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (blk_mq_is_sbitmap_shared(set->flags)) { atomic_set(&set->active_queues_shared_sbitmap, 0); - if (blk_mq_init_shared_sbitmap(set, set->flags)) { + if (blk_mq_init_shared_sbitmap(set)) { ret = -ENOMEM; goto out_free_mq_rq_maps; } @@ -3516,6 +3563,22 @@ out_free_mq_map: } EXPORT_SYMBOL(blk_mq_alloc_tag_set); +/* allocate and initialize a tagset for a simple single-queue device */ +int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int queue_depth, + unsigned int set_flags) +{ + memset(set, 0, sizeof(*set)); + set->ops = ops; + set->nr_hw_queues = 1; + set->nr_maps = 1; + set->queue_depth = queue_depth; + set->numa_node = NUMA_NO_NODE; + set->flags = set_flags; + return blk_mq_alloc_tag_set(set); +} +EXPORT_SYMBOL_GPL(blk_mq_alloc_sq_tag_set); + void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; @@ -3567,15 +3630,24 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } else { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); + if (blk_mq_is_sbitmap_shared(set->flags)) { + hctx->sched_tags->bitmap_tags = + &q->sched_bitmap_tags; + hctx->sched_tags->breserved_tags = + &q->sched_breserved_tags; + } } if (ret) break; if (q->elevator && q->elevator->type->ops.depth_updated) q->elevator->type->ops.depth_updated(hctx); } - - if (!ret) + if (!ret) { q->nr_requests = nr; + if (q->elevator && blk_mq_is_sbitmap_shared(set->flags)) + sbitmap_queue_resize(&q->sched_bitmap_tags, + nr - set->reserved_tags); + } blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); diff --git a/block/blk-mq.h b/block/blk-mq.h index 9ce64bc4a6c8..d08779f77a26 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -47,6 +47,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); +void blk_mq_put_rq_ref(struct request *rq); /* * Internal helpers for allocating/freeing the request map @@ -259,6 +260,8 @@ static inline void blk_mq_put_driver_tag(struct request *rq) __blk_mq_put_driver_tag(rq->mq_hctx, rq); } +bool blk_mq_get_driver_tag(struct request *rq); + static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) { int cpu; @@ -299,6 +302,17 @@ static inline struct blk_plug *blk_mq_plug(struct request_queue *q, return NULL; } +/* Free all requests on the list */ +static inline void blk_mq_free_requests(struct list_head *list) +{ + while (!list_empty(list)) { + struct request *rq = list_entry_rq(list->next); + + list_del_init(&rq->queuelist); + blk_mq_free_request(rq); + } +} + /* * For shared tag users, we track the number of currently active users * and attempt to provide a fair share of the tag depth for each of them. diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 656460636ad3..e83af7bc7591 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -266,8 +266,8 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) return; - prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); - has_sleeper = !wq_has_single_sleeper(&rqw->wait); + has_sleeper = !prepare_to_wait_exclusive(&rqw->wait, &data.wq, + TASK_UNINTERRUPTIBLE); do { /* The memory barrier in set_task_state saves us here. */ if (data.got_token) diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 2bc43e94f4c4..f000f83e0621 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -7,6 +7,7 @@ #include <linux/blk_types.h> #include <linux/atomic.h> #include <linux/wait.h> +#include <linux/blk-mq.h> #include "blk-mq-debugfs.h" @@ -16,6 +17,7 @@ enum rq_qos_id { RQ_QOS_WBT, RQ_QOS_LATENCY, RQ_QOS_COST, + RQ_QOS_IOPRIO, }; struct rq_wait { @@ -78,19 +80,6 @@ static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q) return rq_qos_id(q, RQ_QOS_LATENCY); } -static inline const char *rq_qos_id_to_name(enum rq_qos_id id) -{ - switch (id) { - case RQ_QOS_WBT: - return "wbt"; - case RQ_QOS_LATENCY: - return "latency"; - case RQ_QOS_COST: - return "cost"; - } - return "unknown"; -} - static inline void rq_wait_init(struct rq_wait *rq_wait) { atomic_set(&rq_wait->inflight, 0); @@ -99,8 +88,21 @@ static inline void rq_wait_init(struct rq_wait *rq_wait) static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { + /* + * No IO can be in-flight when adding rqos, so freeze queue, which + * is fine since we only support rq_qos for blk-mq queue. + * + * Reuse ->queue_lock for protecting against other concurrent + * rq_qos adding/deleting + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(&q->queue_lock); rqos->next = q->rq_qos; q->rq_qos = rqos; + spin_unlock_irq(&q->queue_lock); + + blk_mq_unfreeze_queue(q); if (rqos->ops->debugfs_attrs) blk_mq_debugfs_register_rqos(rqos); @@ -110,12 +112,22 @@ static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) { struct rq_qos **cur; + /* + * See comment in rq_qos_add() about freezing queue & using + * ->queue_lock. + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(&q->queue_lock); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } + spin_unlock_irq(&q->queue_lock); + + blk_mq_unfreeze_queue(q); blk_mq_debugfs_unregister_rqos(rqos); } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e03bedf180ab..370d83c18057 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -91,7 +91,7 @@ static ssize_t queue_ra_show(struct request_queue *q, char *page) unsigned long ra_kb = q->backing_dev_info->ra_pages << (PAGE_SHIFT - 10); - return queue_var_show(ra_kb, (page)); + return queue_var_show(ra_kb, page); } static ssize_t @@ -112,28 +112,28 @@ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page) { int max_sectors_kb = queue_max_sectors(q) >> 1; - return queue_var_show(max_sectors_kb, (page)); + return queue_var_show(max_sectors_kb, page); } static ssize_t queue_max_segments_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_segments(q), (page)); + return queue_var_show(queue_max_segments(q), page); } static ssize_t queue_max_discard_segments_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_discard_segments(q), (page)); + return queue_var_show(queue_max_discard_segments(q), page); } static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) { - return queue_var_show(q->limits.max_integrity_segments, (page)); + return queue_var_show(q->limits.max_integrity_segments, page); } static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_segment_size(q), (page)); + return queue_var_show(queue_max_segment_size(q), page); } static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page) @@ -261,12 +261,12 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page) { int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1; - return queue_var_show(max_hw_sectors_kb, (page)); + return queue_var_show(max_hw_sectors_kb, page); } static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page) { - return queue_var_show(q->limits.virt_boundary_mask, (page)); + return queue_var_show(q->limits.virt_boundary_mask, page); } #define QUEUE_SYSFS_BIT_FNS(name, flag, neg) \ @@ -866,20 +866,6 @@ int blk_register_queue(struct gendisk *disk) "%s is registering an already registered queue\n", kobject_name(&dev->kobj)); - /* - * SCSI probing may synchronously create and destroy a lot of - * request_queues for non-existent devices. Shutting down a fully - * functional queue takes measureable wallclock time as RCU grace - * periods are involved. To avoid excessive latency in these - * cases, a request_queue starts out in a degraded mode which is - * faster to shut down and is made fully functional here as - * request_queues for non-existent devices never get registered. - */ - if (!blk_queue_init_done(q)) { - blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); - percpu_ref_switch_to_percpu(&q->q_usage_counter); - } - blk_queue_update_readahead(q); ret = blk_trace_init_sysfs(dev); @@ -938,6 +924,21 @@ int blk_register_queue(struct gendisk *disk) ret = 0; unlock: mutex_unlock(&q->sysfs_dir_lock); + + /* + * SCSI probing may synchronously create and destroy a lot of + * request_queues for non-existent devices. Shutting down a fully + * functional queue takes measureable wallclock time as RCU grace + * periods are involved. To avoid excessive latency in these + * cases, a request_queue starts out in a degraded mode which is + * faster to shut down and is made fully functional here as + * request_queues for non-existent devices never get registered. + */ + if (!blk_queue_init_done(q)) { + blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); + percpu_ref_switch_to_percpu(&q->q_usage_counter); + } + return ret; } EXPORT_SYMBOL_GPL(blk_register_queue); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 42aed0160f86..3ed71b8da887 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -77,7 +77,8 @@ enum { static inline bool rwb_enabled(struct rq_wb *rwb) { - return rwb && rwb->wb_normal != 0; + return rwb && rwb->enable_state != WBT_STATE_OFF_DEFAULT && + rwb->wb_normal != 0; } static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) @@ -563,7 +564,6 @@ static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio) } /* - * Returns true if the IO request should be accounted, false if not. * May sleep, if we have exceeded the writeback limits. Caller can pass * in an irq held spinlock, if it holds one when calling this function. * If we do sleep, we'll release and re-grab it. @@ -636,9 +636,13 @@ void wbt_set_write_cache(struct request_queue *q, bool write_cache_on) void wbt_enable_default(struct request_queue *q) { struct rq_qos *rqos = wbt_rq_qos(q); + /* Throttling already enabled? */ - if (rqos) + if (rqos) { + if (RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) + RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; return; + } /* Queue not registered? Maybe shutting down... */ if (!blk_queue_registered(q)) @@ -702,7 +706,7 @@ void wbt_disable_default(struct request_queue *q) rwb = RQWB(rqos); if (rwb->enable_state == WBT_STATE_ON_DEFAULT) { blk_stat_deactivate(rwb->cb); - rwb->wb_normal = 0; + rwb->enable_state = WBT_STATE_OFF_DEFAULT; } } EXPORT_SYMBOL_GPL(wbt_disable_default); diff --git a/block/blk-wbt.h b/block/blk-wbt.h index 16bdc85b8df9..2eb01becde8c 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -34,6 +34,7 @@ enum { enum { WBT_STATE_ON_DEFAULT = 1, WBT_STATE_ON_MANUAL = 2, + WBT_STATE_OFF_DEFAULT }; struct rq_wb { diff --git a/block/blk.h b/block/blk.h index 8b3591aee0a5..4b885c0f6708 100644 --- a/block/blk.h +++ b/block/blk.h @@ -192,7 +192,6 @@ void blk_account_io_done(struct request *req, u64 now); void blk_insert_flush(struct request *rq); -void elevator_init_mq(struct request_queue *q); int elevator_switch_mq(struct request_queue *q, struct elevator_type *new_e); void __elevator_exit(struct request_queue *, struct elevator_queue *); @@ -225,7 +224,7 @@ ssize_t part_timeout_store(struct device *, struct device_attribute *, void __blk_queue_split(struct bio **bio, unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); -int blk_attempt_req_merge(struct request_queue *q, struct request *rq, +bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next); unsigned int blk_recalc_rq_segments(struct request *rq); void blk_rq_set_mixed_merge(struct request *rq); @@ -343,8 +342,8 @@ static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} static inline void blk_queue_clear_zone_settings(struct request_queue *q) {} #endif -int blk_alloc_devt(struct block_device *part, dev_t *devt); -void blk_free_devt(dev_t devt); +int blk_alloc_ext_minor(void); +void blk_free_ext_minor(unsigned int minor); char *disk_name(struct gendisk *hd, int partno, char *buf); #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 @@ -359,4 +358,14 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); +struct request_queue *blk_alloc_queue(int node_id); + +void disk_alloc_events(struct gendisk *disk); +void disk_add_events(struct gendisk *disk); +void disk_del_events(struct gendisk *disk); +void disk_release_events(struct gendisk *disk); +extern struct device_attribute dev_attr_events; +extern struct device_attribute dev_attr_events_async; +extern struct device_attribute dev_attr_events_poll_msecs; + #endif /* BLK_INTERNAL_H */ diff --git a/block/disk-events.c b/block/disk-events.c new file mode 100644 index 000000000000..a75931ff5da4 --- /dev/null +++ b/block/disk-events.c @@ -0,0 +1,469 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Disk events - monitor disk events like media change and eject request. + */ +#include <linux/export.h> +#include <linux/moduleparam.h> +#include <linux/genhd.h> +#include "blk.h" + +struct disk_events { + struct list_head node; /* all disk_event's */ + struct gendisk *disk; /* the associated disk */ + spinlock_t lock; + + struct mutex block_mutex; /* protects blocking */ + int block; /* event blocking depth */ + unsigned int pending; /* events already sent out */ + unsigned int clearing; /* events being cleared */ + + long poll_msecs; /* interval, -1 for default */ + struct delayed_work dwork; +}; + +static const char *disk_events_strs[] = { + [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", + [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", +}; + +static char *disk_uevents[] = { + [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", + [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", +}; + +/* list of all disk_events */ +static DEFINE_MUTEX(disk_events_mutex); +static LIST_HEAD(disk_events); + +/* disable in-kernel polling by default */ +static unsigned long disk_events_dfl_poll_msecs; + +static unsigned long disk_events_poll_jiffies(struct gendisk *disk) +{ + struct disk_events *ev = disk->ev; + long intv_msecs = 0; + + /* + * If device-specific poll interval is set, always use it. If + * the default is being used, poll if the POLL flag is set. + */ + if (ev->poll_msecs >= 0) + intv_msecs = ev->poll_msecs; + else if (disk->event_flags & DISK_EVENT_FLAG_POLL) + intv_msecs = disk_events_dfl_poll_msecs; + + return msecs_to_jiffies(intv_msecs); +} + +/** + * disk_block_events - block and flush disk event checking + * @disk: disk to block events for + * + * On return from this function, it is guaranteed that event checking + * isn't in progress and won't happen until unblocked by + * disk_unblock_events(). Events blocking is counted and the actual + * unblocking happens after the matching number of unblocks are done. + * + * Note that this intentionally does not block event checking from + * disk_clear_events(). + * + * CONTEXT: + * Might sleep. + */ +void disk_block_events(struct gendisk *disk) +{ + struct disk_events *ev = disk->ev; + unsigned long flags; + bool cancel; + + if (!ev) + return; + + /* + * Outer mutex ensures that the first blocker completes canceling + * the event work before further blockers are allowed to finish. + */ + mutex_lock(&ev->block_mutex); + + spin_lock_irqsave(&ev->lock, flags); + cancel = !ev->block++; + spin_unlock_irqrestore(&ev->lock, flags); + + if (cancel) + cancel_delayed_work_sync(&disk->ev->dwork); + + mutex_unlock(&ev->block_mutex); +} + +static void __disk_unblock_events(struct gendisk *disk, bool check_now) +{ + struct disk_events *ev = disk->ev; + unsigned long intv; + unsigned long flags; + + spin_lock_irqsave(&ev->lock, flags); + + if (WARN_ON_ONCE(ev->block <= 0)) + goto out_unlock; + + if (--ev->block) + goto out_unlock; + + intv = disk_events_poll_jiffies(disk); + if (check_now) + queue_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, 0); + else if (intv) + queue_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, intv); +out_unlock: + spin_unlock_irqrestore(&ev->lock, flags); +} + +/** + * disk_unblock_events - unblock disk event checking + * @disk: disk to unblock events for + * + * Undo disk_block_events(). When the block count reaches zero, it + * starts events polling if configured. + * + * CONTEXT: + * Don't care. Safe to call from irq context. + */ +void disk_unblock_events(struct gendisk *disk) +{ + if (disk->ev) + __disk_unblock_events(disk, false); +} + +/** + * disk_flush_events - schedule immediate event checking and flushing + * @disk: disk to check and flush events for + * @mask: events to flush + * + * Schedule immediate event checking on @disk if not blocked. Events in + * @mask are scheduled to be cleared from the driver. Note that this + * doesn't clear the events from @disk->ev. + * + * CONTEXT: + * If @mask is non-zero must be called with disk->open_mutex held. + */ +void disk_flush_events(struct gendisk *disk, unsigned int mask) +{ + struct disk_events *ev = disk->ev; + + if (!ev) + return; + + spin_lock_irq(&ev->lock); + ev->clearing |= mask; + if (!ev->block) + mod_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, 0); + spin_unlock_irq(&ev->lock); +} + +static void disk_check_events(struct disk_events *ev, + unsigned int *clearing_ptr) +{ + struct gendisk *disk = ev->disk; + char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; + unsigned int clearing = *clearing_ptr; + unsigned int events; + unsigned long intv; + int nr_events = 0, i; + + /* check events */ + events = disk->fops->check_events(disk, clearing); + + /* accumulate pending events and schedule next poll if necessary */ + spin_lock_irq(&ev->lock); + + events &= ~ev->pending; + ev->pending |= events; + *clearing_ptr &= ~clearing; + + intv = disk_events_poll_jiffies(disk); + if (!ev->block && intv) + queue_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, intv); + + spin_unlock_irq(&ev->lock); + + /* + * Tell userland about new events. Only the events listed in + * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT + * is set. Otherwise, events are processed internally but never + * get reported to userland. + */ + for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) + if ((events & disk->events & (1 << i)) && + (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) + envp[nr_events++] = disk_uevents[i]; + + if (nr_events) + kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); +} + +/** + * disk_clear_events - synchronously check, clear and return pending events + * @disk: disk to fetch and clear events from + * @mask: mask of events to be fetched and cleared + * + * Disk events are synchronously checked and pending events in @mask + * are cleared and returned. This ignores the block count. + * + * CONTEXT: + * Might sleep. + */ +static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) +{ + struct disk_events *ev = disk->ev; + unsigned int pending; + unsigned int clearing = mask; + + if (!ev) + return 0; + + disk_block_events(disk); + + /* + * store the union of mask and ev->clearing on the stack so that the + * race with disk_flush_events does not cause ambiguity (ev->clearing + * can still be modified even if events are blocked). + */ + spin_lock_irq(&ev->lock); + clearing |= ev->clearing; + ev->clearing = 0; + spin_unlock_irq(&ev->lock); + + disk_check_events(ev, &clearing); + /* + * if ev->clearing is not 0, the disk_flush_events got called in the + * middle of this function, so we want to run the workfn without delay. + */ + __disk_unblock_events(disk, ev->clearing ? true : false); + + /* then, fetch and clear pending events */ + spin_lock_irq(&ev->lock); + pending = ev->pending & mask; + ev->pending &= ~mask; + spin_unlock_irq(&ev->lock); + WARN_ON_ONCE(clearing & mask); + + return pending; +} + +/** + * bdev_check_media_change - check if a removable media has been changed + * @bdev: block device to check + * + * Check whether a removable media has been changed, and attempt to free all + * dentries and inodes and invalidates all block device page cache entries in + * that case. + * + * Returns %true if the block device changed, or %false if not. + */ +bool bdev_check_media_change(struct block_device *bdev) +{ + unsigned int events; + + events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | + DISK_EVENT_EJECT_REQUEST); + if (!(events & DISK_EVENT_MEDIA_CHANGE)) + return false; + + if (__invalidate_device(bdev, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + bdev->bd_disk->disk_name); + set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + return true; +} +EXPORT_SYMBOL(bdev_check_media_change); + +/* + * Separate this part out so that a different pointer for clearing_ptr can be + * passed in for disk_clear_events. + */ +static void disk_events_workfn(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct disk_events *ev = container_of(dwork, struct disk_events, dwork); + + disk_check_events(ev, &ev->clearing); +} + +/* + * A disk events enabled device has the following sysfs nodes under + * its /sys/block/X/ directory. + * + * events : list of all supported events + * events_async : list of events which can be detected w/o polling + * (always empty, only for backwards compatibility) + * events_poll_msecs : polling interval, 0: disable, -1: system default + */ +static ssize_t __disk_events_show(unsigned int events, char *buf) +{ + const char *delim = ""; + ssize_t pos = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) + if (events & (1 << i)) { + pos += sprintf(buf + pos, "%s%s", + delim, disk_events_strs[i]); + delim = " "; + } + if (pos) + pos += sprintf(buf + pos, "\n"); + return pos; +} + +static ssize_t disk_events_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) + return 0; + return __disk_events_show(disk->events, buf); +} + +static ssize_t disk_events_async_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return 0; +} + +static ssize_t disk_events_poll_msecs_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->ev) + return sprintf(buf, "-1\n"); + return sprintf(buf, "%ld\n", disk->ev->poll_msecs); +} + +static ssize_t disk_events_poll_msecs_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct gendisk *disk = dev_to_disk(dev); + long intv; + + if (!count || !sscanf(buf, "%ld", &intv)) + return -EINVAL; + + if (intv < 0 && intv != -1) + return -EINVAL; + + if (!disk->ev) + return -ENODEV; + + disk_block_events(disk); + disk->ev->poll_msecs = intv; + __disk_unblock_events(disk, true); + return count; +} + +DEVICE_ATTR(events, 0444, disk_events_show, NULL); +DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); +DEVICE_ATTR(events_poll_msecs, 0644, disk_events_poll_msecs_show, + disk_events_poll_msecs_store); + +/* + * The default polling interval can be specified by the kernel + * parameter block.events_dfl_poll_msecs which defaults to 0 + * (disable). This can also be modified runtime by writing to + * /sys/module/block/parameters/events_dfl_poll_msecs. + */ +static int disk_events_set_dfl_poll_msecs(const char *val, + const struct kernel_param *kp) +{ + struct disk_events *ev; + int ret; + + ret = param_set_ulong(val, kp); + if (ret < 0) + return ret; + + mutex_lock(&disk_events_mutex); + list_for_each_entry(ev, &disk_events, node) + disk_flush_events(ev->disk, 0); + mutex_unlock(&disk_events_mutex); + return 0; +} + +static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { + .set = disk_events_set_dfl_poll_msecs, + .get = param_get_ulong, +}; + +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "block." + +module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, + &disk_events_dfl_poll_msecs, 0644); + +/* + * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. + */ +void disk_alloc_events(struct gendisk *disk) +{ + struct disk_events *ev; + + if (!disk->fops->check_events || !disk->events) + return; + + ev = kzalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) { + pr_warn("%s: failed to initialize events\n", disk->disk_name); + return; + } + + INIT_LIST_HEAD(&ev->node); + ev->disk = disk; + spin_lock_init(&ev->lock); + mutex_init(&ev->block_mutex); + ev->block = 1; + ev->poll_msecs = -1; + INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); + + disk->ev = ev; +} + +void disk_add_events(struct gendisk *disk) +{ + if (!disk->ev) + return; + + mutex_lock(&disk_events_mutex); + list_add_tail(&disk->ev->node, &disk_events); + mutex_unlock(&disk_events_mutex); + + /* + * Block count is initialized to 1 and the following initial + * unblock kicks it into action. + */ + __disk_unblock_events(disk, true); +} + +void disk_del_events(struct gendisk *disk) +{ + if (disk->ev) { + disk_block_events(disk); + + mutex_lock(&disk_events_mutex); + list_del_init(&disk->ev->node); + mutex_unlock(&disk_events_mutex); + } +} + +void disk_release_events(struct gendisk *disk) +{ + /* the block count should be 1 from disk_del_events() */ + WARN_ON_ONCE(disk->ev && disk->ev->block != 1); + kfree(disk->ev); +} diff --git a/block/elevator.c b/block/elevator.c index 440699c28119..52ada14cfe45 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -350,9 +350,11 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req, * we can append 'rq' to an existing request, so we can throw 'rq' away * afterwards. * - * Returns true if we merged, false otherwise + * Returns true if we merged, false otherwise. 'free' will contain all + * requests that need to be freed. */ -bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq) +bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq, + struct list_head *free) { struct request *__rq; bool ret; @@ -363,8 +365,10 @@ bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq) /* * First try one-hit cache. */ - if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq)) + if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq)) { + list_add(&rq->queuelist, free); return true; + } if (blk_queue_noxmerges(q)) return false; @@ -378,6 +382,7 @@ bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq) if (!__rq || !blk_attempt_req_merge(q, __rq, rq)) break; + list_add(&rq->queuelist, free); /* The merged request could be merged with others, try again */ ret = true; rq = __rq; @@ -522,6 +527,10 @@ void elv_unregister_queue(struct request_queue *q) int elv_register(struct elevator_type *e) { + /* insert_requests and dispatch_request are mandatory */ + if (WARN_ON_ONCE(!e->ops.insert_requests || !e->ops.dispatch_request)) + return -EINVAL; + /* create icq_cache if requested */ if (e->icq_size) { if (WARN_ON(e->icq_size < sizeof(struct io_cq)) || @@ -693,7 +702,7 @@ void elevator_init_mq(struct request_queue *q) elevator_put(e); } } - +EXPORT_SYMBOL_GPL(elevator_init_mq); /* only for dm-rq */ /* * switch to new_e io scheduler. be careful not to introduce deadlocks - diff --git a/block/genhd.c b/block/genhd.c index 9f8cb7beaad1..79aa40b4c39c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -33,13 +33,6 @@ static struct kobject *block_depr; #define NR_EXT_DEVT (1 << MINORBITS) static DEFINE_IDA(ext_devt_ida); -static void disk_check_events(struct disk_events *ev, - unsigned int *clearing_ptr); -static void disk_alloc_events(struct gendisk *disk); -static void disk_add_events(struct gendisk *disk); -static void disk_del_events(struct gendisk *disk); -static void disk_release_events(struct gendisk *disk); - void set_capacity(struct gendisk *disk, sector_t sectors) { struct block_device *bdev = disk->part0; @@ -333,52 +326,22 @@ static int blk_mangle_minor(int minor) return minor; } -/** - * blk_alloc_devt - allocate a dev_t for a block device - * @bdev: block device to allocate dev_t for - * @devt: out parameter for resulting dev_t - * - * Allocate a dev_t for block device. - * - * RETURNS: - * 0 on success, allocated dev_t is returned in *@devt. -errno on - * failure. - * - * CONTEXT: - * Might sleep. - */ -int blk_alloc_devt(struct block_device *bdev, dev_t *devt) +int blk_alloc_ext_minor(void) { - struct gendisk *disk = bdev->bd_disk; int idx; - /* in consecutive minor range? */ - if (bdev->bd_partno < disk->minors) { - *devt = MKDEV(disk->major, disk->first_minor + bdev->bd_partno); - return 0; - } - idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT, GFP_KERNEL); - if (idx < 0) - return idx == -ENOSPC ? -EBUSY : idx; - - *devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx)); - return 0; + if (idx < 0) { + if (idx == -ENOSPC) + return -EBUSY; + return idx; + } + return blk_mangle_minor(idx); } -/** - * blk_free_devt - free a dev_t - * @devt: dev_t to free - * - * Free @devt which was allocated using blk_alloc_devt(). - * - * CONTEXT: - * Might sleep. - */ -void blk_free_devt(dev_t devt) +void blk_free_ext_minor(unsigned int minor) { - if (MAJOR(devt) == BLOCK_EXT_MAJOR) - ida_free(&ext_devt_ida, blk_mangle_minor(MINOR(devt))); + ida_free(&ext_devt_ida, blk_mangle_minor(minor)); } static char *bdevt_str(dev_t devt, char *buf) @@ -499,8 +462,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, bool register_queue) { - dev_t devt; - int retval; + int ret; /* * The disk queue should now be all set with enough information about @@ -511,23 +473,35 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, if (register_queue) elevator_init_mq(disk->queue); - /* minors == 0 indicates to use ext devt from part0 and should - * be accompanied with EXT_DEVT flag. Make sure all - * parameters make sense. + /* + * If the driver provides an explicit major number it also must provide + * the number of minors numbers supported, and those will be used to + * setup the gendisk. + * Otherwise just allocate the device numbers for both the whole device + * and all partitions from the extended dev_t space. */ - WARN_ON(disk->minors && !(disk->major || disk->first_minor)); - WARN_ON(!disk->minors && - !(disk->flags & (GENHD_FL_EXT_DEVT | GENHD_FL_HIDDEN))); + if (disk->major) { + WARN_ON(!disk->minors); - disk->flags |= GENHD_FL_UP; + if (disk->minors > DISK_MAX_PARTS) { + pr_err("block: can't allocate more than %d partitions\n", + DISK_MAX_PARTS); + disk->minors = DISK_MAX_PARTS; + } + } else { + WARN_ON(disk->minors); - retval = blk_alloc_devt(disk->part0, &devt); - if (retval) { - WARN_ON(1); - return; + ret = blk_alloc_ext_minor(); + if (ret < 0) { + WARN_ON(1); + return; + } + disk->major = BLOCK_EXT_MAJOR; + disk->first_minor = MINOR(ret); + disk->flags |= GENHD_FL_EXT_DEVT; } - disk->major = MAJOR(devt); - disk->first_minor = MINOR(devt); + + disk->flags |= GENHD_FL_UP; disk_alloc_events(disk); @@ -541,14 +515,14 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, } else { struct backing_dev_info *bdi = disk->queue->backing_dev_info; struct device *dev = disk_to_dev(disk); - int ret; /* Register BDI before referencing it from bdev */ - dev->devt = devt; - ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt)); + dev->devt = MKDEV(disk->major, disk->first_minor); + ret = bdi_register(bdi, "%u:%u", + disk->major, disk->first_minor); WARN_ON(ret); bdi_set_owner(bdi, dev); - bdev_add(disk->part0, devt); + bdev_add(disk->part0, dev->devt); } register_disk(parent, disk, groups); if (register_queue) @@ -558,7 +532,10 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, * Take an extra ref on queue which will be put on disk_release() * so that it sticks around as long as @disk is there. */ - WARN_ON_ONCE(!blk_get_queue(disk->queue)); + if (blk_get_queue(disk->queue)) + set_bit(GD_QUEUE_REF, &disk->state); + else + WARN_ON_ONCE(1); disk_add_events(disk); blk_integrity_add(disk); @@ -607,10 +584,10 @@ void del_gendisk(struct gendisk *disk) blk_integrity_del(disk); disk_del_events(disk); - mutex_lock(&disk->part0->bd_mutex); + mutex_lock(&disk->open_mutex); disk->flags &= ~GENHD_FL_UP; blk_drop_partitions(disk); - mutex_unlock(&disk->part0->bd_mutex); + mutex_unlock(&disk->open_mutex); fsync_bdev(disk->part0); __invalidate_device(disk->part0, true); @@ -692,32 +669,6 @@ void blk_request_module(dev_t devt) request_module("block-major-%d", MAJOR(devt)); } -/** - * bdget_disk - do bdget() by gendisk and partition number - * @disk: gendisk of interest - * @partno: partition number - * - * Find partition @partno from @disk, do bdget() on it. - * - * CONTEXT: - * Don't care. - * - * RETURNS: - * Resulting block_device on success, NULL on failure. - */ -struct block_device *bdget_disk(struct gendisk *disk, int partno) -{ - struct block_device *bdev = NULL; - - rcu_read_lock(); - bdev = xa_load(&disk->part_tbl, partno); - if (bdev && !bdgrab(bdev)) - bdev = NULL; - rcu_read_unlock(); - - return bdev; -} - /* * print a full list of all partitions - intended for places where the root * filesystem can't be mounted and thus to give the victim some idea of what @@ -1071,6 +1022,9 @@ static struct attribute *disk_attrs[] = { &dev_attr_stat.attr, &dev_attr_inflight.attr, &dev_attr_badblocks.attr, + &dev_attr_events.attr, + &dev_attr_events_async.attr, + &dev_attr_events_poll_msecs.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1120,12 +1074,13 @@ static void disk_release(struct device *dev) might_sleep(); - blk_free_devt(dev->devt); + if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) + blk_free_ext_minor(MINOR(dev->devt)); disk_release_events(disk); kfree(disk->random); xa_destroy(&disk->part_tbl); bdput(disk->part0); - if (disk->queue) + if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue) blk_put_queue(disk->queue); kfree(disk); } @@ -1242,6 +1197,20 @@ static int __init proc_genhd_init(void) module_init(proc_genhd_init); #endif /* CONFIG_PROC_FS */ +dev_t part_devt(struct gendisk *disk, u8 partno) +{ + struct block_device *part; + dev_t devt = 0; + + rcu_read_lock(); + part = xa_load(&disk->part_tbl, partno); + if (part) + devt = part->bd_dev; + rcu_read_unlock(); + + return devt; +} + dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); @@ -1251,7 +1220,6 @@ dev_t blk_lookup_devt(const char *name, int partno) class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); - struct block_device *part; if (strcmp(dev_name(dev), name)) continue; @@ -1262,13 +1230,10 @@ dev_t blk_lookup_devt(const char *name, int partno) */ devt = MKDEV(MAJOR(dev->devt), MINOR(dev->devt) + partno); - break; - } - part = bdget_disk(disk, partno); - if (part) { - devt = part->bd_dev; - bdput(part); - break; + } else { + devt = part_devt(disk, partno); + if (devt) + break; } } class_dev_iter_exit(&iter); @@ -1279,13 +1244,6 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) { struct gendisk *disk; - if (minors > DISK_MAX_PARTS) { - printk(KERN_ERR - "block: can't allocate more than %d partitions\n", - DISK_MAX_PARTS); - minors = DISK_MAX_PARTS; - } - disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (!disk) return NULL; @@ -1295,6 +1253,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) goto out_free_disk; disk->node_id = node_id; + mutex_init(&disk->open_mutex); xa_init(&disk->part_tbl); if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL)) goto out_destroy_part_tbl; @@ -1315,6 +1274,25 @@ out_free_disk: } EXPORT_SYMBOL(__alloc_disk_node); +struct gendisk *__blk_alloc_disk(int node) +{ + struct request_queue *q; + struct gendisk *disk; + + q = blk_alloc_queue(node); + if (!q) + return NULL; + + disk = __alloc_disk_node(0, node); + if (!disk) { + blk_cleanup_queue(q); + return NULL; + } + disk->queue = q; + return disk; +} +EXPORT_SYMBOL(__blk_alloc_disk); + /** * put_disk - decrements the gendisk refcount * @disk: the struct gendisk to decrement the refcount for @@ -1332,6 +1310,22 @@ void put_disk(struct gendisk *disk) } EXPORT_SYMBOL(put_disk); +/** + * blk_cleanup_disk - shutdown a gendisk allocated by blk_alloc_disk + * @disk: gendisk to shutdown + * + * Mark the queue hanging off @disk DYING, drain all pending requests, then mark + * the queue DEAD, destroy and put it and the gendisk structure. + * + * Context: can sleep + */ +void blk_cleanup_disk(struct gendisk *disk) +{ + blk_cleanup_queue(disk->queue); + put_disk(disk); +} +EXPORT_SYMBOL(blk_cleanup_disk); + static void set_disk_ro_uevent(struct gendisk *gd, int ro) { char event[] = "DISK_RO=1"; @@ -1369,488 +1363,3 @@ int bdev_read_only(struct block_device *bdev) return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); } EXPORT_SYMBOL(bdev_read_only); - -/* - * Disk events - monitor disk events like media change and eject request. - */ -struct disk_events { - struct list_head node; /* all disk_event's */ - struct gendisk *disk; /* the associated disk */ - spinlock_t lock; - - struct mutex block_mutex; /* protects blocking */ - int block; /* event blocking depth */ - unsigned int pending; /* events already sent out */ - unsigned int clearing; /* events being cleared */ - - long poll_msecs; /* interval, -1 for default */ - struct delayed_work dwork; -}; - -static const char *disk_events_strs[] = { - [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", - [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", -}; - -static char *disk_uevents[] = { - [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", - [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", -}; - -/* list of all disk_events */ -static DEFINE_MUTEX(disk_events_mutex); -static LIST_HEAD(disk_events); - -/* disable in-kernel polling by default */ -static unsigned long disk_events_dfl_poll_msecs; - -static unsigned long disk_events_poll_jiffies(struct gendisk *disk) -{ - struct disk_events *ev = disk->ev; - long intv_msecs = 0; - - /* - * If device-specific poll interval is set, always use it. If - * the default is being used, poll if the POLL flag is set. - */ - if (ev->poll_msecs >= 0) - intv_msecs = ev->poll_msecs; - else if (disk->event_flags & DISK_EVENT_FLAG_POLL) - intv_msecs = disk_events_dfl_poll_msecs; - - return msecs_to_jiffies(intv_msecs); -} - -/** - * disk_block_events - block and flush disk event checking - * @disk: disk to block events for - * - * On return from this function, it is guaranteed that event checking - * isn't in progress and won't happen until unblocked by - * disk_unblock_events(). Events blocking is counted and the actual - * unblocking happens after the matching number of unblocks are done. - * - * Note that this intentionally does not block event checking from - * disk_clear_events(). - * - * CONTEXT: - * Might sleep. - */ -void disk_block_events(struct gendisk *disk) -{ - struct disk_events *ev = disk->ev; - unsigned long flags; - bool cancel; - - if (!ev) - return; - - /* - * Outer mutex ensures that the first blocker completes canceling - * the event work before further blockers are allowed to finish. - */ - mutex_lock(&ev->block_mutex); - - spin_lock_irqsave(&ev->lock, flags); - cancel = !ev->block++; - spin_unlock_irqrestore(&ev->lock, flags); - - if (cancel) - cancel_delayed_work_sync(&disk->ev->dwork); - - mutex_unlock(&ev->block_mutex); -} - -static void __disk_unblock_events(struct gendisk *disk, bool check_now) -{ - struct disk_events *ev = disk->ev; - unsigned long intv; - unsigned long flags; - - spin_lock_irqsave(&ev->lock, flags); - - if (WARN_ON_ONCE(ev->block <= 0)) - goto out_unlock; - - if (--ev->block) - goto out_unlock; - - intv = disk_events_poll_jiffies(disk); - if (check_now) - queue_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, 0); - else if (intv) - queue_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, intv); -out_unlock: - spin_unlock_irqrestore(&ev->lock, flags); -} - -/** - * disk_unblock_events - unblock disk event checking - * @disk: disk to unblock events for - * - * Undo disk_block_events(). When the block count reaches zero, it - * starts events polling if configured. - * - * CONTEXT: - * Don't care. Safe to call from irq context. - */ -void disk_unblock_events(struct gendisk *disk) -{ - if (disk->ev) - __disk_unblock_events(disk, false); -} - -/** - * disk_flush_events - schedule immediate event checking and flushing - * @disk: disk to check and flush events for - * @mask: events to flush - * - * Schedule immediate event checking on @disk if not blocked. Events in - * @mask are scheduled to be cleared from the driver. Note that this - * doesn't clear the events from @disk->ev. - * - * CONTEXT: - * If @mask is non-zero must be called with bdev->bd_mutex held. - */ -void disk_flush_events(struct gendisk *disk, unsigned int mask) -{ - struct disk_events *ev = disk->ev; - - if (!ev) - return; - - spin_lock_irq(&ev->lock); - ev->clearing |= mask; - if (!ev->block) - mod_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, 0); - spin_unlock_irq(&ev->lock); -} - -/** - * disk_clear_events - synchronously check, clear and return pending events - * @disk: disk to fetch and clear events from - * @mask: mask of events to be fetched and cleared - * - * Disk events are synchronously checked and pending events in @mask - * are cleared and returned. This ignores the block count. - * - * CONTEXT: - * Might sleep. - */ -static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) -{ - struct disk_events *ev = disk->ev; - unsigned int pending; - unsigned int clearing = mask; - - if (!ev) - return 0; - - disk_block_events(disk); - - /* - * store the union of mask and ev->clearing on the stack so that the - * race with disk_flush_events does not cause ambiguity (ev->clearing - * can still be modified even if events are blocked). - */ - spin_lock_irq(&ev->lock); - clearing |= ev->clearing; - ev->clearing = 0; - spin_unlock_irq(&ev->lock); - - disk_check_events(ev, &clearing); - /* - * if ev->clearing is not 0, the disk_flush_events got called in the - * middle of this function, so we want to run the workfn without delay. - */ - __disk_unblock_events(disk, ev->clearing ? true : false); - - /* then, fetch and clear pending events */ - spin_lock_irq(&ev->lock); - pending = ev->pending & mask; - ev->pending &= ~mask; - spin_unlock_irq(&ev->lock); - WARN_ON_ONCE(clearing & mask); - - return pending; -} - -/** - * bdev_check_media_change - check if a removable media has been changed - * @bdev: block device to check - * - * Check whether a removable media has been changed, and attempt to free all - * dentries and inodes and invalidates all block device page cache entries in - * that case. - * - * Returns %true if the block device changed, or %false if not. - */ -bool bdev_check_media_change(struct block_device *bdev) -{ - unsigned int events; - - events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | - DISK_EVENT_EJECT_REQUEST); - if (!(events & DISK_EVENT_MEDIA_CHANGE)) - return false; - - if (__invalidate_device(bdev, true)) - pr_warn("VFS: busy inodes on changed media %s\n", - bdev->bd_disk->disk_name); - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); - return true; -} -EXPORT_SYMBOL(bdev_check_media_change); - -/* - * Separate this part out so that a different pointer for clearing_ptr can be - * passed in for disk_clear_events. - */ -static void disk_events_workfn(struct work_struct *work) -{ - struct delayed_work *dwork = to_delayed_work(work); - struct disk_events *ev = container_of(dwork, struct disk_events, dwork); - - disk_check_events(ev, &ev->clearing); -} - -static void disk_check_events(struct disk_events *ev, - unsigned int *clearing_ptr) -{ - struct gendisk *disk = ev->disk; - char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; - unsigned int clearing = *clearing_ptr; - unsigned int events; - unsigned long intv; - int nr_events = 0, i; - - /* check events */ - events = disk->fops->check_events(disk, clearing); - - /* accumulate pending events and schedule next poll if necessary */ - spin_lock_irq(&ev->lock); - - events &= ~ev->pending; - ev->pending |= events; - *clearing_ptr &= ~clearing; - - intv = disk_events_poll_jiffies(disk); - if (!ev->block && intv) - queue_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, intv); - - spin_unlock_irq(&ev->lock); - - /* - * Tell userland about new events. Only the events listed in - * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT - * is set. Otherwise, events are processed internally but never - * get reported to userland. - */ - for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) - if ((events & disk->events & (1 << i)) && - (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) - envp[nr_events++] = disk_uevents[i]; - - if (nr_events) - kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); -} - -/* - * A disk events enabled device has the following sysfs nodes under - * its /sys/block/X/ directory. - * - * events : list of all supported events - * events_async : list of events which can be detected w/o polling - * (always empty, only for backwards compatibility) - * events_poll_msecs : polling interval, 0: disable, -1: system default - */ -static ssize_t __disk_events_show(unsigned int events, char *buf) -{ - const char *delim = ""; - ssize_t pos = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) - if (events & (1 << i)) { - pos += sprintf(buf + pos, "%s%s", - delim, disk_events_strs[i]); - delim = " "; - } - if (pos) - pos += sprintf(buf + pos, "\n"); - return pos; -} - -static ssize_t disk_events_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct gendisk *disk = dev_to_disk(dev); - - if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) - return 0; - - return __disk_events_show(disk->events, buf); -} - -static ssize_t disk_events_async_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return 0; -} - -static ssize_t disk_events_poll_msecs_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct gendisk *disk = dev_to_disk(dev); - - if (!disk->ev) - return sprintf(buf, "-1\n"); - - return sprintf(buf, "%ld\n", disk->ev->poll_msecs); -} - -static ssize_t disk_events_poll_msecs_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gendisk *disk = dev_to_disk(dev); - long intv; - - if (!count || !sscanf(buf, "%ld", &intv)) - return -EINVAL; - - if (intv < 0 && intv != -1) - return -EINVAL; - - if (!disk->ev) - return -ENODEV; - - disk_block_events(disk); - disk->ev->poll_msecs = intv; - __disk_unblock_events(disk, true); - - return count; -} - -static const DEVICE_ATTR(events, 0444, disk_events_show, NULL); -static const DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); -static const DEVICE_ATTR(events_poll_msecs, 0644, - disk_events_poll_msecs_show, - disk_events_poll_msecs_store); - -static const struct attribute *disk_events_attrs[] = { - &dev_attr_events.attr, - &dev_attr_events_async.attr, - &dev_attr_events_poll_msecs.attr, - NULL, -}; - -/* - * The default polling interval can be specified by the kernel - * parameter block.events_dfl_poll_msecs which defaults to 0 - * (disable). This can also be modified runtime by writing to - * /sys/module/block/parameters/events_dfl_poll_msecs. - */ -static int disk_events_set_dfl_poll_msecs(const char *val, - const struct kernel_param *kp) -{ - struct disk_events *ev; - int ret; - - ret = param_set_ulong(val, kp); - if (ret < 0) - return ret; - - mutex_lock(&disk_events_mutex); - - list_for_each_entry(ev, &disk_events, node) - disk_flush_events(ev->disk, 0); - - mutex_unlock(&disk_events_mutex); - - return 0; -} - -static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { - .set = disk_events_set_dfl_poll_msecs, - .get = param_get_ulong, -}; - -#undef MODULE_PARAM_PREFIX -#define MODULE_PARAM_PREFIX "block." - -module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, - &disk_events_dfl_poll_msecs, 0644); - -/* - * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. - */ -static void disk_alloc_events(struct gendisk *disk) -{ - struct disk_events *ev; - - if (!disk->fops->check_events || !disk->events) - return; - - ev = kzalloc(sizeof(*ev), GFP_KERNEL); - if (!ev) { - pr_warn("%s: failed to initialize events\n", disk->disk_name); - return; - } - - INIT_LIST_HEAD(&ev->node); - ev->disk = disk; - spin_lock_init(&ev->lock); - mutex_init(&ev->block_mutex); - ev->block = 1; - ev->poll_msecs = -1; - INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); - - disk->ev = ev; -} - -static void disk_add_events(struct gendisk *disk) -{ - /* FIXME: error handling */ - if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0) - pr_warn("%s: failed to create sysfs files for events\n", - disk->disk_name); - - if (!disk->ev) - return; - - mutex_lock(&disk_events_mutex); - list_add_tail(&disk->ev->node, &disk_events); - mutex_unlock(&disk_events_mutex); - - /* - * Block count is initialized to 1 and the following initial - * unblock kicks it into action. - */ - __disk_unblock_events(disk, true); -} - -static void disk_del_events(struct gendisk *disk) -{ - if (disk->ev) { - disk_block_events(disk); - - mutex_lock(&disk_events_mutex); - list_del_init(&disk->ev->node); - mutex_unlock(&disk_events_mutex); - } - - sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs); -} - -static void disk_release_events(struct gendisk *disk) -{ - /* the block count should be 1 from disk_del_events() */ - WARN_ON_ONCE(disk->ev && disk->ev->block != 1); - kfree(disk->ev); -} diff --git a/block/ioctl.c b/block/ioctl.c index 8ba1ed8defd0..24beec9ca9c9 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -89,7 +89,7 @@ static int blkdev_reread_part(struct block_device *bdev, fmode_t mode) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - if (bdev->bd_part_count) + if (bdev->bd_disk->open_partitions) return -EBUSY; /* diff --git a/block/mq-deadline-cgroup.c b/block/mq-deadline-cgroup.c new file mode 100644 index 000000000000..3b4bfddec39f --- /dev/null +++ b/block/mq-deadline-cgroup.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/blk-cgroup.h> +#include <linux/ioprio.h> + +#include "mq-deadline-cgroup.h" + +static struct blkcg_policy dd_blkcg_policy; + +static struct blkcg_policy_data *dd_cpd_alloc(gfp_t gfp) +{ + struct dd_blkcg *pd; + + pd = kzalloc(sizeof(*pd), gfp); + if (!pd) + return NULL; + pd->stats = alloc_percpu_gfp(typeof(*pd->stats), + GFP_KERNEL | __GFP_ZERO); + if (!pd->stats) { + kfree(pd); + return NULL; + } + return &pd->cpd; +} + +static void dd_cpd_free(struct blkcg_policy_data *cpd) +{ + struct dd_blkcg *dd_blkcg = container_of(cpd, typeof(*dd_blkcg), cpd); + + free_percpu(dd_blkcg->stats); + kfree(dd_blkcg); +} + +static struct dd_blkcg *dd_blkcg_from_pd(struct blkg_policy_data *pd) +{ + return container_of(blkcg_to_cpd(pd->blkg->blkcg, &dd_blkcg_policy), + struct dd_blkcg, cpd); +} + +/* + * Convert an association between a block cgroup and a request queue into a + * pointer to the mq-deadline information associated with a (blkcg, queue) pair. + */ +struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) +{ + struct blkg_policy_data *pd; + + pd = blkg_to_pd(bio->bi_blkg, &dd_blkcg_policy); + if (!pd) + return NULL; + + return dd_blkcg_from_pd(pd); +} + +static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) +{ + static const char *const prio_class_name[] = { + [IOPRIO_CLASS_NONE] = "NONE", + [IOPRIO_CLASS_RT] = "RT", + [IOPRIO_CLASS_BE] = "BE", + [IOPRIO_CLASS_IDLE] = "IDLE", + }; + struct dd_blkcg *blkcg = dd_blkcg_from_pd(pd); + int res = 0; + u8 prio; + + for (prio = 0; prio < ARRAY_SIZE(blkcg->stats->stats); prio++) + res += scnprintf(buf + res, size - res, + " [%s] dispatched=%u inserted=%u merged=%u", + prio_class_name[prio], + ddcg_sum(blkcg, dispatched, prio) + + ddcg_sum(blkcg, merged, prio) - + ddcg_sum(blkcg, completed, prio), + ddcg_sum(blkcg, inserted, prio) - + ddcg_sum(blkcg, completed, prio), + ddcg_sum(blkcg, merged, prio)); + + return res; +} + +static struct blkg_policy_data *dd_pd_alloc(gfp_t gfp, struct request_queue *q, + struct blkcg *blkcg) +{ + struct dd_blkg *pd; + + pd = kzalloc(sizeof(*pd), gfp); + if (!pd) + return NULL; + return &pd->pd; +} + +static void dd_pd_free(struct blkg_policy_data *pd) +{ + struct dd_blkg *dd_blkg = container_of(pd, typeof(*dd_blkg), pd); + + kfree(dd_blkg); +} + +static struct blkcg_policy dd_blkcg_policy = { + .cpd_alloc_fn = dd_cpd_alloc, + .cpd_free_fn = dd_cpd_free, + + .pd_alloc_fn = dd_pd_alloc, + .pd_free_fn = dd_pd_free, + .pd_stat_fn = dd_pd_stat, +}; + +int dd_activate_policy(struct request_queue *q) +{ + return blkcg_activate_policy(q, &dd_blkcg_policy); +} + +void dd_deactivate_policy(struct request_queue *q) +{ + blkcg_deactivate_policy(q, &dd_blkcg_policy); +} + +int __init dd_blkcg_init(void) +{ + return blkcg_policy_register(&dd_blkcg_policy); +} + +void __exit dd_blkcg_exit(void) +{ + blkcg_policy_unregister(&dd_blkcg_policy); +} diff --git a/block/mq-deadline-cgroup.h b/block/mq-deadline-cgroup.h new file mode 100644 index 000000000000..0143fd74f3ce --- /dev/null +++ b/block/mq-deadline-cgroup.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#if !defined(_MQ_DEADLINE_CGROUP_H_) +#define _MQ_DEADLINE_CGROUP_H_ + +#include <linux/blk-cgroup.h> + +struct request_queue; + +/** + * struct io_stats_per_prio - I/O statistics per I/O priority class. + * @inserted: Number of inserted requests. + * @merged: Number of merged requests. + * @dispatched: Number of dispatched requests. + * @completed: Number of I/O completions. + */ +struct io_stats_per_prio { + local_t inserted; + local_t merged; + local_t dispatched; + local_t completed; +}; + +/* I/O statistics per I/O cgroup per I/O priority class (IOPRIO_CLASS_*). */ +struct blkcg_io_stats { + struct io_stats_per_prio stats[4]; +}; + +/** + * struct dd_blkcg - Per cgroup data. + * @cpd: blkcg_policy_data structure. + * @stats: I/O statistics. + */ +struct dd_blkcg { + struct blkcg_policy_data cpd; /* must be the first member */ + struct blkcg_io_stats __percpu *stats; +}; + +/* + * Count one event of type 'event_type' and with I/O priority class + * 'prio_class'. + */ +#define ddcg_count(ddcg, event_type, prio_class) do { \ +if (ddcg) { \ + struct blkcg_io_stats *io_stats = get_cpu_ptr((ddcg)->stats); \ + \ + BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ + BUILD_BUG_ON(!__same_type((prio_class), u8)); \ + local_inc(&io_stats->stats[(prio_class)].event_type); \ + put_cpu_ptr(io_stats); \ +} \ +} while (0) + +/* + * Returns the total number of ddcg_count(ddcg, event_type, prio_class) calls + * across all CPUs. No locking or barriers since it is fine if the returned + * sum is slightly outdated. + */ +#define ddcg_sum(ddcg, event_type, prio) ({ \ + unsigned int cpu; \ + u32 sum = 0; \ + \ + BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ + BUILD_BUG_ON(!__same_type((prio), u8)); \ + for_each_present_cpu(cpu) \ + sum += local_read(&per_cpu_ptr((ddcg)->stats, cpu)-> \ + stats[(prio)].event_type); \ + sum; \ +}) + +#ifdef CONFIG_BLK_CGROUP + +/** + * struct dd_blkg - Per (cgroup, request queue) data. + * @pd: blkg_policy_data structure. + */ +struct dd_blkg { + struct blkg_policy_data pd; /* must be the first member */ +}; + +struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio); +int dd_activate_policy(struct request_queue *q); +void dd_deactivate_policy(struct request_queue *q); +int __init dd_blkcg_init(void); +void __exit dd_blkcg_exit(void); + +#else /* CONFIG_BLK_CGROUP */ + +static inline struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) +{ + return NULL; +} + +static inline int dd_activate_policy(struct request_queue *q) +{ + return 0; +} + +static inline void dd_deactivate_policy(struct request_queue *q) +{ +} + +static inline int dd_blkcg_init(void) +{ + return 0; +} + +static inline void dd_blkcg_exit(void) +{ +} + +#endif /* CONFIG_BLK_CGROUP */ + +#endif /* _MQ_DEADLINE_CGROUP_H_ */ diff --git a/block/mq-deadline-main.c b/block/mq-deadline-main.c new file mode 100644 index 000000000000..6f612e6dc82b --- /dev/null +++ b/block/mq-deadline-main.c @@ -0,0 +1,1175 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler, + * for the blk-mq scheduling framework + * + * Copyright (C) 2016 Jens Axboe <axboe@kernel.dk> + */ +#include <linux/kernel.h> +#include <linux/fs.h> +#include <linux/blkdev.h> +#include <linux/blk-mq.h> +#include <linux/elevator.h> +#include <linux/bio.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/compiler.h> +#include <linux/rbtree.h> +#include <linux/sbitmap.h> + +#include <trace/events/block.h> + +#include "blk.h" +#include "blk-mq.h" +#include "blk-mq-debugfs.h" +#include "blk-mq-tag.h" +#include "blk-mq-sched.h" +#include "mq-deadline-cgroup.h" + +/* + * See Documentation/block/deadline-iosched.rst + */ +static const int read_expire = HZ / 2; /* max time before a read is submitted. */ +static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */ +/* + * Time after which to dispatch lower priority requests even if higher + * priority requests are pending. + */ +static const int aging_expire = 10 * HZ; +static const int writes_starved = 2; /* max times reads can starve a write */ +static const int fifo_batch = 16; /* # of sequential requests treated as one + by the above parameters. For throughput. */ + +enum dd_data_dir { + DD_READ = READ, + DD_WRITE = WRITE, +}; + +enum { DD_DIR_COUNT = 2 }; + +enum dd_prio { + DD_RT_PRIO = 0, + DD_BE_PRIO = 1, + DD_IDLE_PRIO = 2, + DD_PRIO_MAX = 2, +}; + +enum { DD_PRIO_COUNT = 3 }; + +/* I/O statistics for all I/O priorities (enum dd_prio). */ +struct io_stats { + struct io_stats_per_prio stats[DD_PRIO_COUNT]; +}; + +/* + * Deadline scheduler data per I/O priority (enum dd_prio). Requests are + * present on both sort_list[] and fifo_list[]. + */ +struct dd_per_prio { + struct list_head dispatch; + struct rb_root sort_list[DD_DIR_COUNT]; + struct list_head fifo_list[DD_DIR_COUNT]; + /* Next request in FIFO order. Read, write or both are NULL. */ + struct request *next_rq[DD_DIR_COUNT]; +}; + +struct deadline_data { + /* + * run time data + */ + + /* Request queue that owns this data structure. */ + struct request_queue *queue; + + struct dd_per_prio per_prio[DD_PRIO_COUNT]; + + /* Data direction of latest dispatched request. */ + enum dd_data_dir last_dir; + unsigned int batching; /* number of sequential requests made */ + unsigned int starved; /* times reads have starved writes */ + + struct io_stats __percpu *stats; + + /* + * settings that change how the i/o scheduler behaves + */ + int fifo_expire[DD_DIR_COUNT]; + int fifo_batch; + int writes_starved; + int front_merges; + u32 async_depth; + int aging_expire; + + spinlock_t lock; + spinlock_t zone_lock; +}; + +/* Count one event of type 'event_type' and with I/O priority 'prio' */ +#define dd_count(dd, event_type, prio) do { \ + struct io_stats *io_stats = get_cpu_ptr((dd)->stats); \ + \ + BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \ + BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \ + local_inc(&io_stats->stats[(prio)].event_type); \ + put_cpu_ptr(io_stats); \ +} while (0) + +/* + * Returns the total number of dd_count(dd, event_type, prio) calls across all + * CPUs. No locking or barriers since it is fine if the returned sum is slightly + * outdated. + */ +#define dd_sum(dd, event_type, prio) ({ \ + unsigned int cpu; \ + u32 sum = 0; \ + \ + BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \ + BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \ + for_each_present_cpu(cpu) \ + sum += local_read(&per_cpu_ptr((dd)->stats, cpu)-> \ + stats[(prio)].event_type); \ + sum; \ +}) + +/* Maps an I/O priority class to a deadline scheduler priority. */ +static const enum dd_prio ioprio_class_to_prio[] = { + [IOPRIO_CLASS_NONE] = DD_BE_PRIO, + [IOPRIO_CLASS_RT] = DD_RT_PRIO, + [IOPRIO_CLASS_BE] = DD_BE_PRIO, + [IOPRIO_CLASS_IDLE] = DD_IDLE_PRIO, +}; + +static inline struct rb_root * +deadline_rb_root(struct dd_per_prio *per_prio, struct request *rq) +{ + return &per_prio->sort_list[rq_data_dir(rq)]; +} + +/* + * Returns the I/O priority class (IOPRIO_CLASS_*) that has been assigned to a + * request. + */ +static u8 dd_rq_ioclass(struct request *rq) +{ + return IOPRIO_PRIO_CLASS(req_get_ioprio(rq)); +} + +/* + * get the request after `rq' in sector-sorted order + */ +static inline struct request * +deadline_latter_request(struct request *rq) +{ + struct rb_node *node = rb_next(&rq->rb_node); + + if (node) + return rb_entry_rq(node); + + return NULL; +} + +static void +deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) +{ + struct rb_root *root = deadline_rb_root(per_prio, rq); + + elv_rb_add(root, rq); +} + +static inline void +deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq) +{ + const enum dd_data_dir data_dir = rq_data_dir(rq); + + if (per_prio->next_rq[data_dir] == rq) + per_prio->next_rq[data_dir] = deadline_latter_request(rq); + + elv_rb_del(deadline_rb_root(per_prio, rq), rq); +} + +/* + * remove rq from rbtree and fifo. + */ +static void deadline_remove_request(struct request_queue *q, + struct dd_per_prio *per_prio, + struct request *rq) +{ + list_del_init(&rq->queuelist); + + /* + * We might not be on the rbtree, if we are doing an insert merge + */ + if (!RB_EMPTY_NODE(&rq->rb_node)) + deadline_del_rq_rb(per_prio, rq); + + elv_rqhash_del(q, rq); + if (q->last_merge == rq) + q->last_merge = NULL; +} + +static void dd_request_merged(struct request_queue *q, struct request *req, + enum elv_merge type) +{ + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = dd_rq_ioclass(req); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + /* + * if the merge was a front merge, we need to reposition request + */ + if (type == ELEVATOR_FRONT_MERGE) { + elv_rb_del(deadline_rb_root(per_prio, req), req); + deadline_add_rq_rb(per_prio, req); + } +} + +/* + * Callback function that is invoked after @next has been merged into @req. + */ +static void dd_merged_requests(struct request_queue *q, struct request *req, + struct request *next) +{ + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = dd_rq_ioclass(next); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_blkcg *blkcg = next->elv.priv[0]; + + dd_count(dd, merged, prio); + ddcg_count(blkcg, merged, ioprio_class); + + /* + * if next expires before rq, assign its expire time to rq + * and move into next position (next will be deleted) in fifo + */ + if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) { + if (time_before((unsigned long)next->fifo_time, + (unsigned long)req->fifo_time)) { + list_move(&req->queuelist, &next->queuelist); + req->fifo_time = next->fifo_time; + } + } + + /* + * kill knowledge of next, this one is a goner + */ + deadline_remove_request(q, &dd->per_prio[prio], next); +} + +/* + * move an entry to dispatch queue + */ +static void +deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + struct request *rq) +{ + const enum dd_data_dir data_dir = rq_data_dir(rq); + + per_prio->next_rq[data_dir] = deadline_latter_request(rq); + + /* + * take it off the sort and fifo list + */ + deadline_remove_request(rq->q, per_prio, rq); +} + +/* Number of requests queued for a given priority level. */ +static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio) +{ + return dd_sum(dd, inserted, prio) - dd_sum(dd, completed, prio); +} + +/* + * deadline_check_fifo returns 0 if there are no expired requests on the fifo, + * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir]) + */ +static inline int deadline_check_fifo(struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) +{ + struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); + + /* + * rq is expired! + */ + if (time_after_eq(jiffies, (unsigned long)rq->fifo_time)) + return 1; + + return 0; +} + +/* + * For the specified data direction, return the next request to + * dispatch using arrival ordered lists. + */ +static struct request * +deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) +{ + struct request *rq; + unsigned long flags; + + if (list_empty(&per_prio->fifo_list[data_dir])) + return NULL; + + rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); + if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q)) + return rq; + + /* + * Look for a write request that can be dispatched, that is one with + * an unlocked target zone. + */ + spin_lock_irqsave(&dd->zone_lock, flags); + list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) { + if (blk_req_can_dispatch_to_zone(rq)) + goto out; + } + rq = NULL; +out: + spin_unlock_irqrestore(&dd->zone_lock, flags); + + return rq; +} + +/* + * For the specified data direction, return the next request to + * dispatch using sector position sorted lists. + */ +static struct request * +deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) +{ + struct request *rq; + unsigned long flags; + + rq = per_prio->next_rq[data_dir]; + if (!rq) + return NULL; + + if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q)) + return rq; + + /* + * Look for a write request that can be dispatched, that is one with + * an unlocked target zone. + */ + spin_lock_irqsave(&dd->zone_lock, flags); + while (rq) { + if (blk_req_can_dispatch_to_zone(rq)) + break; + rq = deadline_latter_request(rq); + } + spin_unlock_irqrestore(&dd->zone_lock, flags); + + return rq; +} + +/* + * deadline_dispatch_requests selects the best request according to + * read/write expire, fifo_batch, etc and with a start time <= @latest. + */ +static struct request *__dd_dispatch_request(struct deadline_data *dd, + struct dd_per_prio *per_prio, + u64 latest_start_ns) +{ + struct request *rq, *next_rq; + enum dd_data_dir data_dir; + struct dd_blkcg *blkcg; + enum dd_prio prio; + u8 ioprio_class; + + lockdep_assert_held(&dd->lock); + + if (!list_empty(&per_prio->dispatch)) { + rq = list_first_entry(&per_prio->dispatch, struct request, + queuelist); + if (rq->start_time_ns > latest_start_ns) + return NULL; + list_del_init(&rq->queuelist); + goto done; + } + + /* + * batches are currently reads XOR writes + */ + rq = deadline_next_request(dd, per_prio, dd->last_dir); + if (rq && dd->batching < dd->fifo_batch) + /* we have a next request are still entitled to batch */ + goto dispatch_request; + + /* + * at this point we are not running a batch. select the appropriate + * data direction (read / write) + */ + + if (!list_empty(&per_prio->fifo_list[DD_READ])) { + BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_READ])); + + if (deadline_fifo_request(dd, per_prio, DD_WRITE) && + (dd->starved++ >= dd->writes_starved)) + goto dispatch_writes; + + data_dir = DD_READ; + + goto dispatch_find_request; + } + + /* + * there are either no reads or writes have been starved + */ + + if (!list_empty(&per_prio->fifo_list[DD_WRITE])) { +dispatch_writes: + BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_WRITE])); + + dd->starved = 0; + + data_dir = DD_WRITE; + + goto dispatch_find_request; + } + + return NULL; + +dispatch_find_request: + /* + * we are not running a batch, find best request for selected data_dir + */ + next_rq = deadline_next_request(dd, per_prio, data_dir); + if (deadline_check_fifo(per_prio, data_dir) || !next_rq) { + /* + * A deadline has expired, the last request was in the other + * direction, or we have run out of higher-sectored requests. + * Start again from the request with the earliest expiry time. + */ + rq = deadline_fifo_request(dd, per_prio, data_dir); + } else { + /* + * The last req was the same dir and we have a next request in + * sort order. No expired requests so continue on from here. + */ + rq = next_rq; + } + + /* + * For a zoned block device, if we only have writes queued and none of + * them can be dispatched, rq will be NULL. + */ + if (!rq) + return NULL; + + dd->last_dir = data_dir; + dd->batching = 0; + +dispatch_request: + if (rq->start_time_ns > latest_start_ns) + return NULL; + /* + * rq is the selected appropriate request. + */ + dd->batching++; + deadline_move_request(dd, per_prio, rq); +done: + ioprio_class = dd_rq_ioclass(rq); + prio = ioprio_class_to_prio[ioprio_class]; + dd_count(dd, dispatched, prio); + blkcg = rq->elv.priv[0]; + ddcg_count(blkcg, dispatched, ioprio_class); + /* + * If the request needs its target zone locked, do it. + */ + blk_req_zone_write_lock(rq); + rq->rq_flags |= RQF_STARTED; + return rq; +} + +/* + * Called from blk_mq_run_hw_queue() -> __blk_mq_sched_dispatch_requests(). + * + * One confusing aspect here is that we get called for a specific + * hardware queue, but we may return a request that is for a + * different hardware queue. This is because mq-deadline has shared + * state for all hardware queues, in terms of sorting, FIFOs, etc. + */ +static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) +{ + struct deadline_data *dd = hctx->queue->elevator->elevator_data; + const u64 now_ns = ktime_get_ns(); + struct request *rq = NULL; + enum dd_prio prio; + + spin_lock(&dd->lock); + /* + * Start with dispatching requests whose deadline expired more than + * aging_expire jiffies ago. + */ + for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) { + rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns - + jiffies_to_nsecs(dd->aging_expire)); + if (rq) + goto unlock; + } + /* + * Next, dispatch requests in priority order. Ignore lower priority + * requests if any higher priority requests are pending. + */ + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns); + if (rq || dd_queued(dd, prio)) + break; + } + +unlock: + spin_unlock(&dd->lock); + + return rq; +} + +/* + * Called by __blk_mq_alloc_request(). The shallow_depth value set by this + * function is used by __blk_mq_get_tag(). + */ +static void dd_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) +{ + struct deadline_data *dd = data->q->elevator->elevator_data; + + /* Do not throttle synchronous reads. */ + if (op_is_sync(op) && !op_is_write(op)) + return; + + /* + * Throttle asynchronous requests and writes such that these requests + * do not block the allocation of synchronous requests. + */ + data->shallow_depth = dd->async_depth; +} + +/* Called by blk_mq_update_nr_requests(). */ +static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + struct deadline_data *dd = q->elevator->elevator_data; + struct blk_mq_tags *tags = hctx->sched_tags; + + dd->async_depth = max(1UL, 3 * q->nr_requests / 4); + + sbitmap_queue_min_shallow_depth(tags->bitmap_tags, dd->async_depth); +} + +/* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */ +static int dd_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) +{ + dd_depth_updated(hctx); + return 0; +} + +static void dd_exit_sched(struct elevator_queue *e) +{ + struct deadline_data *dd = e->elevator_data; + enum dd_prio prio; + + dd_deactivate_policy(dd->queue); + + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_READ])); + WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_WRITE])); + } + + free_percpu(dd->stats); + + kfree(dd); +} + +/* + * Initialize elevator private data (deadline_data) and associate with blkcg. + */ +static int dd_init_sched(struct request_queue *q, struct elevator_type *e) +{ + struct deadline_data *dd; + struct elevator_queue *eq; + enum dd_prio prio; + int ret = -ENOMEM; + + /* + * Initialization would be very tricky if the queue is not frozen, + * hence the warning statement below. + */ + WARN_ON_ONCE(!percpu_ref_is_zero(&q->q_usage_counter)); + + eq = elevator_alloc(q, e); + if (!eq) + return ret; + + dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); + if (!dd) + goto put_eq; + + eq->elevator_data = dd; + + dd->stats = alloc_percpu_gfp(typeof(*dd->stats), + GFP_KERNEL | __GFP_ZERO); + if (!dd->stats) + goto free_dd; + + dd->queue = q; + + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + INIT_LIST_HEAD(&per_prio->dispatch); + INIT_LIST_HEAD(&per_prio->fifo_list[DD_READ]); + INIT_LIST_HEAD(&per_prio->fifo_list[DD_WRITE]); + per_prio->sort_list[DD_READ] = RB_ROOT; + per_prio->sort_list[DD_WRITE] = RB_ROOT; + } + dd->fifo_expire[DD_READ] = read_expire; + dd->fifo_expire[DD_WRITE] = write_expire; + dd->writes_starved = writes_starved; + dd->front_merges = 1; + dd->last_dir = DD_WRITE; + dd->fifo_batch = fifo_batch; + dd->aging_expire = aging_expire; + spin_lock_init(&dd->lock); + spin_lock_init(&dd->zone_lock); + + ret = dd_activate_policy(q); + if (ret) + goto free_stats; + + ret = 0; + q->elevator = eq; + return 0; + +free_stats: + free_percpu(dd->stats); + +free_dd: + kfree(dd); + +put_eq: + kobject_put(&eq->kobj); + return ret; +} + +/* + * Try to merge @bio into an existing request. If @bio has been merged into + * an existing request, store the pointer to that request into *@rq. + */ +static int dd_request_merge(struct request_queue *q, struct request **rq, + struct bio *bio) +{ + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = IOPRIO_PRIO_CLASS(bio->bi_ioprio); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + sector_t sector = bio_end_sector(bio); + struct request *__rq; + + if (!dd->front_merges) + return ELEVATOR_NO_MERGE; + + __rq = elv_rb_find(&per_prio->sort_list[bio_data_dir(bio)], sector); + if (__rq) { + BUG_ON(sector != blk_rq_pos(__rq)); + + if (elv_bio_merge_ok(__rq, bio)) { + *rq = __rq; + return ELEVATOR_FRONT_MERGE; + } + } + + return ELEVATOR_NO_MERGE; +} + +/* + * Attempt to merge a bio into an existing request. This function is called + * before @bio is associated with a request. + */ +static bool dd_bio_merge(struct request_queue *q, struct bio *bio, + unsigned int nr_segs) +{ + struct deadline_data *dd = q->elevator->elevator_data; + struct request *free = NULL; + bool ret; + + spin_lock(&dd->lock); + ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); + spin_unlock(&dd->lock); + + if (free) + blk_mq_free_request(free); + + return ret; +} + +/* + * add rq to rbtree and fifo + */ +static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, + bool at_head) +{ + struct request_queue *q = hctx->queue; + struct deadline_data *dd = q->elevator->elevator_data; + const enum dd_data_dir data_dir = rq_data_dir(rq); + u16 ioprio = req_get_ioprio(rq); + u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); + struct dd_per_prio *per_prio; + enum dd_prio prio; + struct dd_blkcg *blkcg; + LIST_HEAD(free); + + lockdep_assert_held(&dd->lock); + + /* + * This may be a requeue of a write request that has locked its + * target zone. If it is the case, this releases the zone lock. + */ + blk_req_zone_write_unlock(rq); + + /* + * If a block cgroup has been associated with the submitter and if an + * I/O priority has been set in the associated block cgroup, use the + * lowest of the cgroup priority and the request priority for the + * request. If no priority has been set in the request, use the cgroup + * priority. + */ + prio = ioprio_class_to_prio[ioprio_class]; + dd_count(dd, inserted, prio); + blkcg = dd_blkcg_from_bio(rq->bio); + ddcg_count(blkcg, inserted, ioprio_class); + rq->elv.priv[0] = blkcg; + + if (blk_mq_sched_try_insert_merge(q, rq, &free)) { + blk_mq_free_requests(&free); + return; + } + + trace_block_rq_insert(rq); + + per_prio = &dd->per_prio[prio]; + if (at_head) { + list_add(&rq->queuelist, &per_prio->dispatch); + } else { + deadline_add_rq_rb(per_prio, rq); + + if (rq_mergeable(rq)) { + elv_rqhash_add(q, rq); + if (!q->last_merge) + q->last_merge = rq; + } + + /* + * set expire time and add to fifo list + */ + rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; + list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]); + } +} + +/* + * Called from blk_mq_sched_insert_request() or blk_mq_sched_insert_requests(). + */ +static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, + struct list_head *list, bool at_head) +{ + struct request_queue *q = hctx->queue; + struct deadline_data *dd = q->elevator->elevator_data; + + spin_lock(&dd->lock); + while (!list_empty(list)) { + struct request *rq; + + rq = list_first_entry(list, struct request, queuelist); + list_del_init(&rq->queuelist); + dd_insert_request(hctx, rq, at_head); + } + spin_unlock(&dd->lock); +} + +/* Callback from inside blk_mq_rq_ctx_init(). */ +static void dd_prepare_request(struct request *rq) +{ + rq->elv.priv[0] = NULL; +} + +/* + * Callback from inside blk_mq_free_request(). + * + * For zoned block devices, write unlock the target zone of + * completed write requests. Do this while holding the zone lock + * spinlock so that the zone is never unlocked while deadline_fifo_request() + * or deadline_next_request() are executing. This function is called for + * all requests, whether or not these requests complete successfully. + * + * For a zoned block device, __dd_dispatch_request() may have stopped + * dispatching requests if all the queued requests are write requests directed + * at zones that are already locked due to on-going write requests. To ensure + * write request dispatch progress in this case, mark the queue as needing a + * restart to ensure that the queue is run again after completion of the + * request and zones being unlocked. + */ +static void dd_finish_request(struct request *rq) +{ + struct request_queue *q = rq->q; + struct deadline_data *dd = q->elevator->elevator_data; + struct dd_blkcg *blkcg = rq->elv.priv[0]; + const u8 ioprio_class = dd_rq_ioclass(rq); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + dd_count(dd, completed, prio); + ddcg_count(blkcg, completed, ioprio_class); + + if (blk_queue_is_zoned(q)) { + unsigned long flags; + + spin_lock_irqsave(&dd->zone_lock, flags); + blk_req_zone_write_unlock(rq); + if (!list_empty(&per_prio->fifo_list[DD_WRITE])) + blk_mq_sched_mark_restart_hctx(rq->mq_hctx); + spin_unlock_irqrestore(&dd->zone_lock, flags); + } +} + +static bool dd_has_work_for_prio(struct dd_per_prio *per_prio) +{ + return !list_empty_careful(&per_prio->dispatch) || + !list_empty_careful(&per_prio->fifo_list[DD_READ]) || + !list_empty_careful(&per_prio->fifo_list[DD_WRITE]); +} + +static bool dd_has_work(struct blk_mq_hw_ctx *hctx) +{ + struct deadline_data *dd = hctx->queue->elevator->elevator_data; + enum dd_prio prio; + + for (prio = 0; prio <= DD_PRIO_MAX; prio++) + if (dd_has_work_for_prio(&dd->per_prio[prio])) + return true; + + return false; +} + +/* + * sysfs parts below + */ +#define SHOW_INT(__FUNC, __VAR) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ +{ \ + struct deadline_data *dd = e->elevator_data; \ + \ + return sysfs_emit(page, "%d\n", __VAR); \ +} +#define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR)) +SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]); +SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]); +SHOW_JIFFIES(deadline_aging_expire_show, dd->aging_expire); +SHOW_INT(deadline_writes_starved_show, dd->writes_starved); +SHOW_INT(deadline_front_merges_show, dd->front_merges); +SHOW_INT(deadline_async_depth_show, dd->front_merges); +SHOW_INT(deadline_fifo_batch_show, dd->fifo_batch); +#undef SHOW_INT +#undef SHOW_JIFFIES + +#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ +static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ +{ \ + struct deadline_data *dd = e->elevator_data; \ + int __data, __ret; \ + \ + __ret = kstrtoint(page, 0, &__data); \ + if (__ret < 0) \ + return __ret; \ + if (__data < (MIN)) \ + __data = (MIN); \ + else if (__data > (MAX)) \ + __data = (MAX); \ + *(__PTR) = __CONV(__data); \ + return count; \ +} +#define STORE_INT(__FUNC, __PTR, MIN, MAX) \ + STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, ) +#define STORE_JIFFIES(__FUNC, __PTR, MIN, MAX) \ + STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies) +STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX); +STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX); +STORE_JIFFIES(deadline_aging_expire_store, &dd->aging_expire, 0, INT_MAX); +STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX); +STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1); +STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX); +STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX); +#undef STORE_FUNCTION +#undef STORE_INT +#undef STORE_JIFFIES + +#define DD_ATTR(name) \ + __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) + +static struct elv_fs_entry deadline_attrs[] = { + DD_ATTR(read_expire), + DD_ATTR(write_expire), + DD_ATTR(writes_starved), + DD_ATTR(front_merges), + DD_ATTR(async_depth), + DD_ATTR(fifo_batch), + DD_ATTR(aging_expire), + __ATTR_NULL +}; + +#ifdef CONFIG_BLK_DEBUG_FS +#define DEADLINE_DEBUGFS_DDIR_ATTRS(prio, data_dir, name) \ +static void *deadline_##name##_fifo_start(struct seq_file *m, \ + loff_t *pos) \ + __acquires(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + spin_lock(&dd->lock); \ + return seq_list_start(&per_prio->fifo_list[data_dir], *pos); \ +} \ + \ +static void *deadline_##name##_fifo_next(struct seq_file *m, void *v, \ + loff_t *pos) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + return seq_list_next(v, &per_prio->fifo_list[data_dir], pos); \ +} \ + \ +static void deadline_##name##_fifo_stop(struct seq_file *m, void *v) \ + __releases(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + \ + spin_unlock(&dd->lock); \ +} \ + \ +static const struct seq_operations deadline_##name##_fifo_seq_ops = { \ + .start = deadline_##name##_fifo_start, \ + .next = deadline_##name##_fifo_next, \ + .stop = deadline_##name##_fifo_stop, \ + .show = blk_mq_debugfs_rq_show, \ +}; \ + \ +static int deadline_##name##_next_rq_show(void *data, \ + struct seq_file *m) \ +{ \ + struct request_queue *q = data; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + struct request *rq = per_prio->next_rq[data_dir]; \ + \ + if (rq) \ + __blk_mq_debugfs_rq_show(m, rq); \ + return 0; \ +} + +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_READ, read0); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_WRITE, write0); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_READ, read1); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_WRITE, write1); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_READ, read2); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_WRITE, write2); +#undef DEADLINE_DEBUGFS_DDIR_ATTRS + +static int deadline_batching_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u\n", dd->batching); + return 0; +} + +static int deadline_starved_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u\n", dd->starved); + return 0; +} + +static int dd_async_depth_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u\n", dd->async_depth); + return 0; +} + +static int dd_queued_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u %u %u\n", dd_queued(dd, DD_RT_PRIO), + dd_queued(dd, DD_BE_PRIO), + dd_queued(dd, DD_IDLE_PRIO)); + return 0; +} + +/* Number of requests owned by the block driver for a given priority. */ +static u32 dd_owned_by_driver(struct deadline_data *dd, enum dd_prio prio) +{ + return dd_sum(dd, dispatched, prio) + dd_sum(dd, merged, prio) + - dd_sum(dd, completed, prio); +} + +static int dd_owned_by_driver_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u %u %u\n", dd_owned_by_driver(dd, DD_RT_PRIO), + dd_owned_by_driver(dd, DD_BE_PRIO), + dd_owned_by_driver(dd, DD_IDLE_PRIO)); + return 0; +} + +#define DEADLINE_DISPATCH_ATTR(prio) \ +static void *deadline_dispatch##prio##_start(struct seq_file *m, \ + loff_t *pos) \ + __acquires(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + spin_lock(&dd->lock); \ + return seq_list_start(&per_prio->dispatch, *pos); \ +} \ + \ +static void *deadline_dispatch##prio##_next(struct seq_file *m, \ + void *v, loff_t *pos) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + return seq_list_next(v, &per_prio->dispatch, pos); \ +} \ + \ +static void deadline_dispatch##prio##_stop(struct seq_file *m, void *v) \ + __releases(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + \ + spin_unlock(&dd->lock); \ +} \ + \ +static const struct seq_operations deadline_dispatch##prio##_seq_ops = { \ + .start = deadline_dispatch##prio##_start, \ + .next = deadline_dispatch##prio##_next, \ + .stop = deadline_dispatch##prio##_stop, \ + .show = blk_mq_debugfs_rq_show, \ +} + +DEADLINE_DISPATCH_ATTR(0); +DEADLINE_DISPATCH_ATTR(1); +DEADLINE_DISPATCH_ATTR(2); +#undef DEADLINE_DISPATCH_ATTR + +#define DEADLINE_QUEUE_DDIR_ATTRS(name) \ + {#name "_fifo_list", 0400, \ + .seq_ops = &deadline_##name##_fifo_seq_ops} +#define DEADLINE_NEXT_RQ_ATTR(name) \ + {#name "_next_rq", 0400, deadline_##name##_next_rq_show} +static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { + DEADLINE_QUEUE_DDIR_ATTRS(read0), + DEADLINE_QUEUE_DDIR_ATTRS(write0), + DEADLINE_QUEUE_DDIR_ATTRS(read1), + DEADLINE_QUEUE_DDIR_ATTRS(write1), + DEADLINE_QUEUE_DDIR_ATTRS(read2), + DEADLINE_QUEUE_DDIR_ATTRS(write2), + DEADLINE_NEXT_RQ_ATTR(read0), + DEADLINE_NEXT_RQ_ATTR(write0), + DEADLINE_NEXT_RQ_ATTR(read1), + DEADLINE_NEXT_RQ_ATTR(write1), + DEADLINE_NEXT_RQ_ATTR(read2), + DEADLINE_NEXT_RQ_ATTR(write2), + {"batching", 0400, deadline_batching_show}, + {"starved", 0400, deadline_starved_show}, + {"async_depth", 0400, dd_async_depth_show}, + {"dispatch0", 0400, .seq_ops = &deadline_dispatch0_seq_ops}, + {"dispatch1", 0400, .seq_ops = &deadline_dispatch1_seq_ops}, + {"dispatch2", 0400, .seq_ops = &deadline_dispatch2_seq_ops}, + {"owned_by_driver", 0400, dd_owned_by_driver_show}, + {"queued", 0400, dd_queued_show}, + {}, +}; +#undef DEADLINE_QUEUE_DDIR_ATTRS +#endif + +static struct elevator_type mq_deadline = { + .ops = { + .depth_updated = dd_depth_updated, + .limit_depth = dd_limit_depth, + .insert_requests = dd_insert_requests, + .dispatch_request = dd_dispatch_request, + .prepare_request = dd_prepare_request, + .finish_request = dd_finish_request, + .next_request = elv_rb_latter_request, + .former_request = elv_rb_former_request, + .bio_merge = dd_bio_merge, + .request_merge = dd_request_merge, + .requests_merged = dd_merged_requests, + .request_merged = dd_request_merged, + .has_work = dd_has_work, + .init_sched = dd_init_sched, + .exit_sched = dd_exit_sched, + .init_hctx = dd_init_hctx, + }, + +#ifdef CONFIG_BLK_DEBUG_FS + .queue_debugfs_attrs = deadline_queue_debugfs_attrs, +#endif + .elevator_attrs = deadline_attrs, + .elevator_name = "mq-deadline", + .elevator_alias = "deadline", + .elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE, + .elevator_owner = THIS_MODULE, +}; +MODULE_ALIAS("mq-deadline-iosched"); + +static int __init deadline_init(void) +{ + int ret; + + ret = elv_register(&mq_deadline); + if (ret) + goto out; + ret = dd_blkcg_init(); + if (ret) + goto unreg; + +out: + return ret; + +unreg: + elv_unregister(&mq_deadline); + goto out; +} + +static void __exit deadline_exit(void) +{ + dd_blkcg_exit(); + elv_unregister(&mq_deadline); +} + +module_init(deadline_init); +module_exit(deadline_exit); + +MODULE_AUTHOR("Jens Axboe, Damien Le Moal and Bart Van Assche"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MQ deadline IO scheduler"); diff --git a/block/mq-deadline.c b/block/mq-deadline.c deleted file mode 100644 index 8eea2cbf2bf4..000000000000 --- a/block/mq-deadline.c +++ /dev/null @@ -1,815 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler, - * for the blk-mq scheduling framework - * - * Copyright (C) 2016 Jens Axboe <axboe@kernel.dk> - */ -#include <linux/kernel.h> -#include <linux/fs.h> -#include <linux/blkdev.h> -#include <linux/blk-mq.h> -#include <linux/elevator.h> -#include <linux/bio.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/compiler.h> -#include <linux/rbtree.h> -#include <linux/sbitmap.h> - -#include <trace/events/block.h> - -#include "blk.h" -#include "blk-mq.h" -#include "blk-mq-debugfs.h" -#include "blk-mq-tag.h" -#include "blk-mq-sched.h" - -/* - * See Documentation/block/deadline-iosched.rst - */ -static const int read_expire = HZ / 2; /* max time before a read is submitted. */ -static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */ -static const int writes_starved = 2; /* max times reads can starve a write */ -static const int fifo_batch = 16; /* # of sequential requests treated as one - by the above parameters. For throughput. */ - -struct deadline_data { - /* - * run time data - */ - - /* - * requests (deadline_rq s) are present on both sort_list and fifo_list - */ - struct rb_root sort_list[2]; - struct list_head fifo_list[2]; - - /* - * next in sort order. read, write or both are NULL - */ - struct request *next_rq[2]; - unsigned int batching; /* number of sequential requests made */ - unsigned int starved; /* times reads have starved writes */ - - /* - * settings that change how the i/o scheduler behaves - */ - int fifo_expire[2]; - int fifo_batch; - int writes_starved; - int front_merges; - - spinlock_t lock; - spinlock_t zone_lock; - struct list_head dispatch; -}; - -static inline struct rb_root * -deadline_rb_root(struct deadline_data *dd, struct request *rq) -{ - return &dd->sort_list[rq_data_dir(rq)]; -} - -/* - * get the request after `rq' in sector-sorted order - */ -static inline struct request * -deadline_latter_request(struct request *rq) -{ - struct rb_node *node = rb_next(&rq->rb_node); - - if (node) - return rb_entry_rq(node); - - return NULL; -} - -static void -deadline_add_rq_rb(struct deadline_data *dd, struct request *rq) -{ - struct rb_root *root = deadline_rb_root(dd, rq); - - elv_rb_add(root, rq); -} - -static inline void -deadline_del_rq_rb(struct deadline_data *dd, struct request *rq) -{ - const int data_dir = rq_data_dir(rq); - - if (dd->next_rq[data_dir] == rq) - dd->next_rq[data_dir] = deadline_latter_request(rq); - - elv_rb_del(deadline_rb_root(dd, rq), rq); -} - -/* - * remove rq from rbtree and fifo. - */ -static void deadline_remove_request(struct request_queue *q, struct request *rq) -{ - struct deadline_data *dd = q->elevator->elevator_data; - - list_del_init(&rq->queuelist); - - /* - * We might not be on the rbtree, if we are doing an insert merge - */ - if (!RB_EMPTY_NODE(&rq->rb_node)) - deadline_del_rq_rb(dd, rq); - - elv_rqhash_del(q, rq); - if (q->last_merge == rq) - q->last_merge = NULL; -} - -static void dd_request_merged(struct request_queue *q, struct request *req, - enum elv_merge type) -{ - struct deadline_data *dd = q->elevator->elevator_data; - - /* - * if the merge was a front merge, we need to reposition request - */ - if (type == ELEVATOR_FRONT_MERGE) { - elv_rb_del(deadline_rb_root(dd, req), req); - deadline_add_rq_rb(dd, req); - } -} - -static void dd_merged_requests(struct request_queue *q, struct request *req, - struct request *next) -{ - /* - * if next expires before rq, assign its expire time to rq - * and move into next position (next will be deleted) in fifo - */ - if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) { - if (time_before((unsigned long)next->fifo_time, - (unsigned long)req->fifo_time)) { - list_move(&req->queuelist, &next->queuelist); - req->fifo_time = next->fifo_time; - } - } - - /* - * kill knowledge of next, this one is a goner - */ - deadline_remove_request(q, next); -} - -/* - * move an entry to dispatch queue - */ -static void -deadline_move_request(struct deadline_data *dd, struct request *rq) -{ - const int data_dir = rq_data_dir(rq); - - dd->next_rq[READ] = NULL; - dd->next_rq[WRITE] = NULL; - dd->next_rq[data_dir] = deadline_latter_request(rq); - - /* - * take it off the sort and fifo list - */ - deadline_remove_request(rq->q, rq); -} - -/* - * deadline_check_fifo returns 0 if there are no expired requests on the fifo, - * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir]) - */ -static inline int deadline_check_fifo(struct deadline_data *dd, int ddir) -{ - struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next); - - /* - * rq is expired! - */ - if (time_after_eq(jiffies, (unsigned long)rq->fifo_time)) - return 1; - - return 0; -} - -/* - * For the specified data direction, return the next request to - * dispatch using arrival ordered lists. - */ -static struct request * -deadline_fifo_request(struct deadline_data *dd, int data_dir) -{ - struct request *rq; - unsigned long flags; - - if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE)) - return NULL; - - if (list_empty(&dd->fifo_list[data_dir])) - return NULL; - - rq = rq_entry_fifo(dd->fifo_list[data_dir].next); - if (data_dir == READ || !blk_queue_is_zoned(rq->q)) - return rq; - - /* - * Look for a write request that can be dispatched, that is one with - * an unlocked target zone. - */ - spin_lock_irqsave(&dd->zone_lock, flags); - list_for_each_entry(rq, &dd->fifo_list[WRITE], queuelist) { - if (blk_req_can_dispatch_to_zone(rq)) - goto out; - } - rq = NULL; -out: - spin_unlock_irqrestore(&dd->zone_lock, flags); - - return rq; -} - -/* - * For the specified data direction, return the next request to - * dispatch using sector position sorted lists. - */ -static struct request * -deadline_next_request(struct deadline_data *dd, int data_dir) -{ - struct request *rq; - unsigned long flags; - - if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE)) - return NULL; - - rq = dd->next_rq[data_dir]; - if (!rq) - return NULL; - - if (data_dir == READ || !blk_queue_is_zoned(rq->q)) - return rq; - - /* - * Look for a write request that can be dispatched, that is one with - * an unlocked target zone. - */ - spin_lock_irqsave(&dd->zone_lock, flags); - while (rq) { - if (blk_req_can_dispatch_to_zone(rq)) - break; - rq = deadline_latter_request(rq); - } - spin_unlock_irqrestore(&dd->zone_lock, flags); - - return rq; -} - -/* - * deadline_dispatch_requests selects the best request according to - * read/write expire, fifo_batch, etc - */ -static struct request *__dd_dispatch_request(struct deadline_data *dd) -{ - struct request *rq, *next_rq; - bool reads, writes; - int data_dir; - - if (!list_empty(&dd->dispatch)) { - rq = list_first_entry(&dd->dispatch, struct request, queuelist); - list_del_init(&rq->queuelist); - goto done; - } - - reads = !list_empty(&dd->fifo_list[READ]); - writes = !list_empty(&dd->fifo_list[WRITE]); - - /* - * batches are currently reads XOR writes - */ - rq = deadline_next_request(dd, WRITE); - if (!rq) - rq = deadline_next_request(dd, READ); - - if (rq && dd->batching < dd->fifo_batch) - /* we have a next request are still entitled to batch */ - goto dispatch_request; - - /* - * at this point we are not running a batch. select the appropriate - * data direction (read / write) - */ - - if (reads) { - BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ])); - - if (deadline_fifo_request(dd, WRITE) && - (dd->starved++ >= dd->writes_starved)) - goto dispatch_writes; - - data_dir = READ; - - goto dispatch_find_request; - } - - /* - * there are either no reads or writes have been starved - */ - - if (writes) { -dispatch_writes: - BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE])); - - dd->starved = 0; - - data_dir = WRITE; - - goto dispatch_find_request; - } - - return NULL; - -dispatch_find_request: - /* - * we are not running a batch, find best request for selected data_dir - */ - next_rq = deadline_next_request(dd, data_dir); - if (deadline_check_fifo(dd, data_dir) || !next_rq) { - /* - * A deadline has expired, the last request was in the other - * direction, or we have run out of higher-sectored requests. - * Start again from the request with the earliest expiry time. - */ - rq = deadline_fifo_request(dd, data_dir); - } else { - /* - * The last req was the same dir and we have a next request in - * sort order. No expired requests so continue on from here. - */ - rq = next_rq; - } - - /* - * For a zoned block device, if we only have writes queued and none of - * them can be dispatched, rq will be NULL. - */ - if (!rq) - return NULL; - - dd->batching = 0; - -dispatch_request: - /* - * rq is the selected appropriate request. - */ - dd->batching++; - deadline_move_request(dd, rq); -done: - /* - * If the request needs its target zone locked, do it. - */ - blk_req_zone_write_lock(rq); - rq->rq_flags |= RQF_STARTED; - return rq; -} - -/* - * One confusing aspect here is that we get called for a specific - * hardware queue, but we may return a request that is for a - * different hardware queue. This is because mq-deadline has shared - * state for all hardware queues, in terms of sorting, FIFOs, etc. - */ -static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) -{ - struct deadline_data *dd = hctx->queue->elevator->elevator_data; - struct request *rq; - - spin_lock(&dd->lock); - rq = __dd_dispatch_request(dd); - spin_unlock(&dd->lock); - - return rq; -} - -static void dd_exit_queue(struct elevator_queue *e) -{ - struct deadline_data *dd = e->elevator_data; - - BUG_ON(!list_empty(&dd->fifo_list[READ])); - BUG_ON(!list_empty(&dd->fifo_list[WRITE])); - - kfree(dd); -} - -/* - * initialize elevator private data (deadline_data). - */ -static int dd_init_queue(struct request_queue *q, struct elevator_type *e) -{ - struct deadline_data *dd; - struct elevator_queue *eq; - - eq = elevator_alloc(q, e); - if (!eq) - return -ENOMEM; - - dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); - if (!dd) { - kobject_put(&eq->kobj); - return -ENOMEM; - } - eq->elevator_data = dd; - - INIT_LIST_HEAD(&dd->fifo_list[READ]); - INIT_LIST_HEAD(&dd->fifo_list[WRITE]); - dd->sort_list[READ] = RB_ROOT; - dd->sort_list[WRITE] = RB_ROOT; - dd->fifo_expire[READ] = read_expire; - dd->fifo_expire[WRITE] = write_expire; - dd->writes_starved = writes_starved; - dd->front_merges = 1; - dd->fifo_batch = fifo_batch; - spin_lock_init(&dd->lock); - spin_lock_init(&dd->zone_lock); - INIT_LIST_HEAD(&dd->dispatch); - - q->elevator = eq; - return 0; -} - -static int dd_request_merge(struct request_queue *q, struct request **rq, - struct bio *bio) -{ - struct deadline_data *dd = q->elevator->elevator_data; - sector_t sector = bio_end_sector(bio); - struct request *__rq; - - if (!dd->front_merges) - return ELEVATOR_NO_MERGE; - - __rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector); - if (__rq) { - BUG_ON(sector != blk_rq_pos(__rq)); - - if (elv_bio_merge_ok(__rq, bio)) { - *rq = __rq; - return ELEVATOR_FRONT_MERGE; - } - } - - return ELEVATOR_NO_MERGE; -} - -static bool dd_bio_merge(struct request_queue *q, struct bio *bio, - unsigned int nr_segs) -{ - struct deadline_data *dd = q->elevator->elevator_data; - struct request *free = NULL; - bool ret; - - spin_lock(&dd->lock); - ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); - spin_unlock(&dd->lock); - - if (free) - blk_mq_free_request(free); - - return ret; -} - -/* - * add rq to rbtree and fifo - */ -static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, - bool at_head) -{ - struct request_queue *q = hctx->queue; - struct deadline_data *dd = q->elevator->elevator_data; - const int data_dir = rq_data_dir(rq); - - /* - * This may be a requeue of a write request that has locked its - * target zone. If it is the case, this releases the zone lock. - */ - blk_req_zone_write_unlock(rq); - - if (blk_mq_sched_try_insert_merge(q, rq)) - return; - - trace_block_rq_insert(rq); - - if (at_head) { - list_add(&rq->queuelist, &dd->dispatch); - } else { - deadline_add_rq_rb(dd, rq); - - if (rq_mergeable(rq)) { - elv_rqhash_add(q, rq); - if (!q->last_merge) - q->last_merge = rq; - } - - /* - * set expire time and add to fifo list - */ - rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; - list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]); - } -} - -static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, - struct list_head *list, bool at_head) -{ - struct request_queue *q = hctx->queue; - struct deadline_data *dd = q->elevator->elevator_data; - - spin_lock(&dd->lock); - while (!list_empty(list)) { - struct request *rq; - - rq = list_first_entry(list, struct request, queuelist); - list_del_init(&rq->queuelist); - dd_insert_request(hctx, rq, at_head); - } - spin_unlock(&dd->lock); -} - -/* - * Nothing to do here. This is defined only to ensure that .finish_request - * method is called upon request completion. - */ -static void dd_prepare_request(struct request *rq) -{ -} - -/* - * For zoned block devices, write unlock the target zone of - * completed write requests. Do this while holding the zone lock - * spinlock so that the zone is never unlocked while deadline_fifo_request() - * or deadline_next_request() are executing. This function is called for - * all requests, whether or not these requests complete successfully. - * - * For a zoned block device, __dd_dispatch_request() may have stopped - * dispatching requests if all the queued requests are write requests directed - * at zones that are already locked due to on-going write requests. To ensure - * write request dispatch progress in this case, mark the queue as needing a - * restart to ensure that the queue is run again after completion of the - * request and zones being unlocked. - */ -static void dd_finish_request(struct request *rq) -{ - struct request_queue *q = rq->q; - - if (blk_queue_is_zoned(q)) { - struct deadline_data *dd = q->elevator->elevator_data; - unsigned long flags; - - spin_lock_irqsave(&dd->zone_lock, flags); - blk_req_zone_write_unlock(rq); - if (!list_empty(&dd->fifo_list[WRITE])) - blk_mq_sched_mark_restart_hctx(rq->mq_hctx); - spin_unlock_irqrestore(&dd->zone_lock, flags); - } -} - -static bool dd_has_work(struct blk_mq_hw_ctx *hctx) -{ - struct deadline_data *dd = hctx->queue->elevator->elevator_data; - - return !list_empty_careful(&dd->dispatch) || - !list_empty_careful(&dd->fifo_list[0]) || - !list_empty_careful(&dd->fifo_list[1]); -} - -/* - * sysfs parts below - */ -static ssize_t -deadline_var_show(int var, char *page) -{ - return sprintf(page, "%d\n", var); -} - -static void -deadline_var_store(int *var, const char *page) -{ - char *p = (char *) page; - - *var = simple_strtol(p, &p, 10); -} - -#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ -static ssize_t __FUNC(struct elevator_queue *e, char *page) \ -{ \ - struct deadline_data *dd = e->elevator_data; \ - int __data = __VAR; \ - if (__CONV) \ - __data = jiffies_to_msecs(__data); \ - return deadline_var_show(__data, (page)); \ -} -SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1); -SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1); -SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0); -SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0); -SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0); -#undef SHOW_FUNCTION - -#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ -static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ -{ \ - struct deadline_data *dd = e->elevator_data; \ - int __data; \ - deadline_var_store(&__data, (page)); \ - if (__data < (MIN)) \ - __data = (MIN); \ - else if (__data > (MAX)) \ - __data = (MAX); \ - if (__CONV) \ - *(__PTR) = msecs_to_jiffies(__data); \ - else \ - *(__PTR) = __data; \ - return count; \ -} -STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1); -STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1); -STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0); -STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0); -STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0); -#undef STORE_FUNCTION - -#define DD_ATTR(name) \ - __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) - -static struct elv_fs_entry deadline_attrs[] = { - DD_ATTR(read_expire), - DD_ATTR(write_expire), - DD_ATTR(writes_starved), - DD_ATTR(front_merges), - DD_ATTR(fifo_batch), - __ATTR_NULL -}; - -#ifdef CONFIG_BLK_DEBUG_FS -#define DEADLINE_DEBUGFS_DDIR_ATTRS(ddir, name) \ -static void *deadline_##name##_fifo_start(struct seq_file *m, \ - loff_t *pos) \ - __acquires(&dd->lock) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - \ - spin_lock(&dd->lock); \ - return seq_list_start(&dd->fifo_list[ddir], *pos); \ -} \ - \ -static void *deadline_##name##_fifo_next(struct seq_file *m, void *v, \ - loff_t *pos) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - \ - return seq_list_next(v, &dd->fifo_list[ddir], pos); \ -} \ - \ -static void deadline_##name##_fifo_stop(struct seq_file *m, void *v) \ - __releases(&dd->lock) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - \ - spin_unlock(&dd->lock); \ -} \ - \ -static const struct seq_operations deadline_##name##_fifo_seq_ops = { \ - .start = deadline_##name##_fifo_start, \ - .next = deadline_##name##_fifo_next, \ - .stop = deadline_##name##_fifo_stop, \ - .show = blk_mq_debugfs_rq_show, \ -}; \ - \ -static int deadline_##name##_next_rq_show(void *data, \ - struct seq_file *m) \ -{ \ - struct request_queue *q = data; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - struct request *rq = dd->next_rq[ddir]; \ - \ - if (rq) \ - __blk_mq_debugfs_rq_show(m, rq); \ - return 0; \ -} -DEADLINE_DEBUGFS_DDIR_ATTRS(READ, read) -DEADLINE_DEBUGFS_DDIR_ATTRS(WRITE, write) -#undef DEADLINE_DEBUGFS_DDIR_ATTRS - -static int deadline_batching_show(void *data, struct seq_file *m) -{ - struct request_queue *q = data; - struct deadline_data *dd = q->elevator->elevator_data; - - seq_printf(m, "%u\n", dd->batching); - return 0; -} - -static int deadline_starved_show(void *data, struct seq_file *m) -{ - struct request_queue *q = data; - struct deadline_data *dd = q->elevator->elevator_data; - - seq_printf(m, "%u\n", dd->starved); - return 0; -} - -static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos) - __acquires(&dd->lock) -{ - struct request_queue *q = m->private; - struct deadline_data *dd = q->elevator->elevator_data; - - spin_lock(&dd->lock); - return seq_list_start(&dd->dispatch, *pos); -} - -static void *deadline_dispatch_next(struct seq_file *m, void *v, loff_t *pos) -{ - struct request_queue *q = m->private; - struct deadline_data *dd = q->elevator->elevator_data; - - return seq_list_next(v, &dd->dispatch, pos); -} - -static void deadline_dispatch_stop(struct seq_file *m, void *v) - __releases(&dd->lock) -{ - struct request_queue *q = m->private; - struct deadline_data *dd = q->elevator->elevator_data; - - spin_unlock(&dd->lock); -} - -static const struct seq_operations deadline_dispatch_seq_ops = { - .start = deadline_dispatch_start, - .next = deadline_dispatch_next, - .stop = deadline_dispatch_stop, - .show = blk_mq_debugfs_rq_show, -}; - -#define DEADLINE_QUEUE_DDIR_ATTRS(name) \ - {#name "_fifo_list", 0400, .seq_ops = &deadline_##name##_fifo_seq_ops}, \ - {#name "_next_rq", 0400, deadline_##name##_next_rq_show} -static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { - DEADLINE_QUEUE_DDIR_ATTRS(read), - DEADLINE_QUEUE_DDIR_ATTRS(write), - {"batching", 0400, deadline_batching_show}, - {"starved", 0400, deadline_starved_show}, - {"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops}, - {}, -}; -#undef DEADLINE_QUEUE_DDIR_ATTRS -#endif - -static struct elevator_type mq_deadline = { - .ops = { - .insert_requests = dd_insert_requests, - .dispatch_request = dd_dispatch_request, - .prepare_request = dd_prepare_request, - .finish_request = dd_finish_request, - .next_request = elv_rb_latter_request, - .former_request = elv_rb_former_request, - .bio_merge = dd_bio_merge, - .request_merge = dd_request_merge, - .requests_merged = dd_merged_requests, - .request_merged = dd_request_merged, - .has_work = dd_has_work, - .init_sched = dd_init_queue, - .exit_sched = dd_exit_queue, - }, - -#ifdef CONFIG_BLK_DEBUG_FS - .queue_debugfs_attrs = deadline_queue_debugfs_attrs, -#endif - .elevator_attrs = deadline_attrs, - .elevator_name = "mq-deadline", - .elevator_alias = "deadline", - .elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE, - .elevator_owner = THIS_MODULE, -}; -MODULE_ALIAS("mq-deadline-iosched"); - -static int __init deadline_init(void) -{ - return elv_register(&mq_deadline); -} - -static void __exit deadline_exit(void) -{ - elv_unregister(&mq_deadline); -} - -module_init(deadline_init); -module_exit(deadline_exit); - -MODULE_AUTHOR("Jens Axboe"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("MQ deadline IO scheduler"); diff --git a/block/partitions/core.c b/block/partitions/core.c index dc60ecf46fe6..347c56a51d87 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -120,8 +120,7 @@ static void free_partitions(struct parsed_partitions *state) kfree(state); } -static struct parsed_partitions *check_partition(struct gendisk *hd, - struct block_device *bdev) +static struct parsed_partitions *check_partition(struct gendisk *hd) { struct parsed_partitions *state; int i, res, err; @@ -136,7 +135,7 @@ static struct parsed_partitions *check_partition(struct gendisk *hd, } state->pp_buf[0] = '\0'; - state->bdev = bdev; + state->bdev = hd->part0; disk_name(hd, 0, state->name); snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name); if (isdigit(state->name[strlen(state->name)-1])) @@ -260,7 +259,8 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { - blk_free_devt(dev->devt); + if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) + blk_free_ext_minor(MINOR(dev->devt)); bdput(dev_to_bdev(dev)); } @@ -282,7 +282,7 @@ struct device_type part_type = { }; /* - * Must be called either with bd_mutex held, before a disk can be opened or + * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static void delete_partition(struct block_device *part) @@ -311,7 +311,7 @@ static ssize_t whole_disk_show(struct device *dev, static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* - * Must be called either with bd_mutex held, before a disk can be opened or + * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static struct block_device *add_partition(struct gendisk *disk, int partno, @@ -325,10 +325,8 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, const char *dname; int err; - /* - * disk_max_parts() won't be zero, either GENHD_FL_EXT_DEVT is set - * or 'minors' is passed to alloc_disk(). - */ + lockdep_assert_held(&disk->open_mutex); + if (partno >= disk_max_parts(disk)) return ERR_PTR(-EINVAL); @@ -379,9 +377,15 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, pdev->type = &part_type; pdev->parent = ddev; - err = blk_alloc_devt(bdev, &devt); - if (err) - goto out_put; + /* in consecutive minor range? */ + if (bdev->bd_partno < disk->minors) { + devt = MKDEV(disk->major, disk->first_minor + bdev->bd_partno); + } else { + err = blk_alloc_ext_minor(); + if (err < 0) + goto out_put; + devt = MKDEV(BLOCK_EXT_MAJOR, err); + } pdev->devt = devt; /* delay uevent until 'holders' subdir is created */ @@ -450,29 +454,27 @@ int bdev_add_partition(struct block_device *bdev, int partno, { struct block_device *part; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (partition_overlaps(bdev->bd_disk, start, length, -1)) { - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return -EBUSY; } part = add_partition(bdev->bd_disk, partno, start, length, ADDPART_FLAG_NONE, NULL); - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return PTR_ERR_OR_ZERO(part); } int bdev_del_partition(struct block_device *bdev, int partno) { - struct block_device *part; - int ret; + struct block_device *part = NULL; + int ret = -ENXIO; - part = bdget_disk(bdev->bd_disk, partno); + mutex_lock(&bdev->bd_disk->open_mutex); + part = xa_load(&bdev->bd_disk->part_tbl, partno); if (!part) - return -ENXIO; - - mutex_lock(&part->bd_mutex); - mutex_lock_nested(&bdev->bd_mutex, 1); + goto out_unlock; ret = -EBUSY; if (part->bd_openers) @@ -481,24 +483,21 @@ int bdev_del_partition(struct block_device *bdev, int partno) delete_partition(part); ret = 0; out_unlock: - mutex_unlock(&bdev->bd_mutex); - mutex_unlock(&part->bd_mutex); - bdput(part); + mutex_unlock(&bdev->bd_disk->open_mutex); return ret; } int bdev_resize_partition(struct block_device *bdev, int partno, sector_t start, sector_t length) { - struct block_device *part; - int ret = 0; + struct block_device *part = NULL; + int ret = -ENXIO; - part = bdget_disk(bdev->bd_disk, partno); + mutex_lock(&bdev->bd_disk->open_mutex); + part = xa_load(&bdev->bd_disk->part_tbl, partno); if (!part) - return -ENXIO; + goto out_unlock; - mutex_lock(&part->bd_mutex); - mutex_lock_nested(&bdev->bd_mutex, 1); ret = -EINVAL; if (start != part->bd_start_sect) goto out_unlock; @@ -511,9 +510,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno, ret = 0; out_unlock: - mutex_unlock(&part->bd_mutex); - mutex_unlock(&bdev->bd_mutex); - bdput(part); + mutex_unlock(&bdev->bd_disk->open_mutex); return ret; } @@ -538,7 +535,7 @@ void blk_drop_partitions(struct gendisk *disk) struct block_device *part; unsigned long idx; - lockdep_assert_held(&disk->part0->bd_mutex); + lockdep_assert_held(&disk->open_mutex); xa_for_each_start(&disk->part_tbl, idx, part, 1) { if (!bdgrab(part)) @@ -548,7 +545,7 @@ void blk_drop_partitions(struct gendisk *disk) } } -static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, +static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { sector_t size = state->parts[p].size; @@ -598,7 +595,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, return true; } -int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) +static int blk_add_partitions(struct gendisk *disk) { struct parsed_partitions *state; int ret = -EAGAIN, p; @@ -606,7 +603,7 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) if (!disk_part_scan_enabled(disk)) return 0; - state = check_partition(disk, bdev); + state = check_partition(disk); if (!state) return 0; if (IS_ERR(state)) { @@ -650,7 +647,7 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); for (p = 1; p < state->limit; p++) - if (!blk_add_partition(disk, bdev, state, p)) + if (!blk_add_partition(disk, state, p)) goto out_free_state; ret = 0; @@ -659,6 +656,58 @@ out_free_state: return ret; } +int bdev_disk_changed(struct gendisk *disk, bool invalidate) +{ + int ret = 0; + + lockdep_assert_held(&disk->open_mutex); + + if (!(disk->flags & GENHD_FL_UP)) + return -ENXIO; + +rescan: + if (disk->open_partitions) + return -EBUSY; + sync_blockdev(disk->part0); + invalidate_bdev(disk->part0); + blk_drop_partitions(disk); + + clear_bit(GD_NEED_PART_SCAN, &disk->state); + + /* + * Historically we only set the capacity to zero for devices that + * support partitions (independ of actually having partitions created). + * Doing that is rather inconsistent, but changing it broke legacy + * udisks polling for legacy ide-cdrom devices. Use the crude check + * below to get the sane behavior for most device while not breaking + * userspace for this particular setup. + */ + if (invalidate) { + if (disk_part_scan_enabled(disk) || + !(disk->flags & GENHD_FL_REMOVABLE)) + set_capacity(disk, 0); + } + + if (get_capacity(disk)) { + ret = blk_add_partitions(disk); + if (ret == -EAGAIN) + goto rescan; + } else if (invalidate) { + /* + * Tell userspace that the media / partition table may have + * changed. + */ + kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); + } + + return ret; +} +/* + * Only exported for loop and dasd for historic reasons. Don't use in new + * code! + */ +EXPORT_SYMBOL_GPL(bdev_disk_changed); + void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { struct address_space *mapping = state->bdev->bd_inode->i_mapping; diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c index 8f2fcc080264..63e4f6f8b6e9 100644 --- a/block/partitions/msdos.c +++ b/block/partitions/msdos.c @@ -622,7 +622,7 @@ int msdos_partition(struct parsed_partitions *state) for (slot = 1; slot <= 4; slot++, p++) { if (p->boot_ind != 0 && p->boot_ind != 0x80) { /* - * Even without a valid boot inidicator value + * Even without a valid boot indicator value * its still possible this is valid FAT filesystem * without a partition table. */ diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 9e2d0c6a3877..8b1714021498 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1781,15 +1781,13 @@ static int fd_alloc_disk(int drive, int system) { struct gendisk *disk; - disk = alloc_disk(1); - if (!disk) - goto out; - disk->queue = blk_mq_init_queue(&unit[drive].tag_set); - if (IS_ERR(disk->queue)) - goto out_put_disk; + disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); disk->major = FLOPPY_MAJOR; disk->first_minor = drive + system; + disk->minors = 1; disk->fops = &floppy_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; if (system) @@ -1802,12 +1800,6 @@ static int fd_alloc_disk(int drive, int system) unit[drive].gendisk[system] = disk; add_disk(disk); return 0; - -out_put_disk: - disk->queue = NULL; - put_disk(disk); -out: - return -ENOMEM; } static int fd_alloc_drive(int drive) diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index c34e71b0c4a9..06b360f7123a 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -338,14 +338,13 @@ static const struct blk_mq_ops aoeblk_mq_ops = { .queue_rq = aoeblk_queue_rq, }; -/* alloc_disk and add_disk can sleep */ +/* blk_mq_alloc_disk and add_disk can sleep */ void aoeblk_gdalloc(void *vp) { struct aoedev *d = vp; struct gendisk *gd; mempool_t *mp; - struct request_queue *q; struct blk_mq_tag_set *set; ulong flags; int late = 0; @@ -362,19 +361,12 @@ aoeblk_gdalloc(void *vp) if (late) return; - gd = alloc_disk(AOE_PARTITIONS); - if (gd == NULL) { - pr_err("aoe: cannot allocate disk structure for %ld.%d\n", - d->aoemajor, d->aoeminor); - goto err; - } - mp = mempool_create(MIN_BUFS, mempool_alloc_slab, mempool_free_slab, buf_pool_cache); if (mp == NULL) { printk(KERN_ERR "aoe: cannot allocate bufpool for %ld.%d\n", d->aoemajor, d->aoeminor); - goto err_disk; + goto err; } set = &d->tag_set; @@ -391,12 +383,11 @@ aoeblk_gdalloc(void *vp) goto err_mempool; } - q = blk_mq_init_queue(set); - if (IS_ERR(q)) { + gd = blk_mq_alloc_disk(set, d); + if (IS_ERR(gd)) { pr_err("aoe: cannot allocate block queue for %ld.%d\n", d->aoemajor, d->aoeminor); - blk_mq_free_tag_set(set); - goto err_mempool; + goto err_tagset; } spin_lock_irqsave(&d->lock, flags); @@ -405,16 +396,16 @@ aoeblk_gdalloc(void *vp) WARN_ON(d->flags & DEVFL_TKILL); WARN_ON(d->gd); WARN_ON(d->flags & DEVFL_UP); - blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS); - blk_queue_io_opt(q, SZ_2M); + blk_queue_max_hw_sectors(gd->queue, BLK_DEF_MAX_SECTORS); + blk_queue_io_opt(gd->queue, SZ_2M); d->bufpool = mp; - d->blkq = gd->queue = q; - q->queuedata = d; + d->blkq = gd->queue; d->gd = gd; if (aoe_maxsectors) - blk_queue_max_hw_sectors(q, aoe_maxsectors); + blk_queue_max_hw_sectors(gd->queue, aoe_maxsectors); gd->major = AOE_MAJOR; gd->first_minor = d->sysminor; + gd->minors = AOE_PARTITIONS; gd->fops = &aoe_bdops; gd->private_data = d; set_capacity(gd, d->ssize); @@ -435,10 +426,10 @@ aoeblk_gdalloc(void *vp) spin_unlock_irqrestore(&d->lock, flags); return; +err_tagset: + blk_mq_free_tag_set(set); err_mempool: mempool_destroy(mp); -err_disk: - put_disk(gd); err: spin_lock_irqsave(&d->lock, flags); d->flags &= ~DEVFL_GD_NOW; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index ecd77897a761..588889bea7c3 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -1701,8 +1701,6 @@ aoecmd_init(void) goto ktiowq_fail; } - mutex_init(&ktio_spawn_lock); - for (i = 0; i < ncpus; i++) { INIT_LIST_HEAD(&iocq[i].head); spin_lock_init(&iocq[i].lock); diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index e2ea2356da06..c5753c6bfe80 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -277,9 +277,8 @@ freedev(struct aoedev *d) if (d->gd) { aoedisk_rm_debugfs(d); del_gendisk(d->gd); - put_disk(d->gd); + blk_cleanup_disk(d->gd); blk_mq_free_tag_set(&d->tag_set); - blk_cleanup_queue(d->blkq); } t = d->targets; e = t + d->ntargets; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index d601e49f80e0..a093644ac39f 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1968,22 +1968,14 @@ static const struct blk_mq_ops ataflop_mq_ops = { static int ataflop_alloc_disk(unsigned int drive, unsigned int type) { struct gendisk *disk; - int ret; - - disk = alloc_disk(1); - if (!disk) - return -ENOMEM; - disk->queue = blk_mq_init_queue(&unit[drive].tag_set); - if (IS_ERR(disk->queue)) { - ret = PTR_ERR(disk->queue); - disk->queue = NULL; - put_disk(disk); - return ret; - } + disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); disk->major = FLOPPY_MAJOR; disk->first_minor = drive + (type << 2); + disk->minors = 1; sprintf(disk->disk_name, "fd%d", drive); disk->fops = &floppy_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 7562cf30b14e..95694113e38e 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -38,9 +38,7 @@ * device). */ struct brd_device { - int brd_number; - - struct request_queue *brd_queue; + int brd_number; struct gendisk *brd_disk; struct list_head brd_list; @@ -372,7 +370,7 @@ static LIST_HEAD(brd_devices); static DEFINE_MUTEX(brd_devices_mutex); static struct dentry *brd_debugfs_dir; -static struct brd_device *brd_alloc(int i) +static int brd_alloc(int i) { struct brd_device *brd; struct gendisk *disk; @@ -380,64 +378,55 @@ static struct brd_device *brd_alloc(int i) brd = kzalloc(sizeof(*brd), GFP_KERNEL); if (!brd) - goto out; + return -ENOMEM; brd->brd_number = i; spin_lock_init(&brd->brd_lock); INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC); - brd->brd_queue = blk_alloc_queue(NUMA_NO_NODE); - if (!brd->brd_queue) - goto out_free_dev; - snprintf(buf, DISK_NAME_LEN, "ram%d", i); if (!IS_ERR_OR_NULL(brd_debugfs_dir)) debugfs_create_u64(buf, 0444, brd_debugfs_dir, &brd->brd_nr_pages); - /* This is so fdisk will align partitions on 4k, because of - * direct_access API needing 4k alignment, returning a PFN - * (This is only a problem on very small devices <= 4M, - * otherwise fdisk will align on 1M. Regardless this call - * is harmless) - */ - blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE); - disk = brd->brd_disk = alloc_disk(max_part); + disk = brd->brd_disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) - goto out_free_queue; + goto out_free_dev; + disk->major = RAMDISK_MAJOR; disk->first_minor = i * max_part; + disk->minors = max_part; disk->fops = &brd_fops; disk->private_data = brd; disk->flags = GENHD_FL_EXT_DEVT; strlcpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); + + /* + * This is so fdisk will align partitions on 4k, because of + * direct_access API needing 4k alignment, returning a PFN + * (This is only a problem on very small devices <= 4M, + * otherwise fdisk will align on 1M. Regardless this call + * is harmless) + */ + blk_queue_physical_block_size(disk->queue, PAGE_SIZE); /* Tell the block layer that this is not a rotational device */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, brd->brd_queue); + blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); + add_disk(disk); + list_add_tail(&brd->brd_list, &brd_devices); - return brd; + return 0; -out_free_queue: - blk_cleanup_queue(brd->brd_queue); out_free_dev: kfree(brd); -out: - return NULL; -} - -static void brd_free(struct brd_device *brd) -{ - put_disk(brd->brd_disk); - blk_cleanup_queue(brd->brd_queue); - brd_free_pages(brd); - kfree(brd); + return -ENOMEM; } static void brd_probe(dev_t dev) { - struct brd_device *brd; int i = MINOR(dev) / max_part; + struct brd_device *brd; mutex_lock(&brd_devices_mutex); list_for_each_entry(brd, &brd_devices, brd_list) { @@ -445,13 +434,7 @@ static void brd_probe(dev_t dev) goto out_unlock; } - brd = brd_alloc(i); - if (brd) { - brd->brd_disk->queue = brd->brd_queue; - add_disk(brd->brd_disk); - list_add_tail(&brd->brd_list, &brd_devices); - } - + brd_alloc(i); out_unlock: mutex_unlock(&brd_devices_mutex); } @@ -460,7 +443,9 @@ static void brd_del_one(struct brd_device *brd) { list_del(&brd->brd_list); del_gendisk(brd->brd_disk); - brd_free(brd); + blk_cleanup_disk(brd->brd_disk); + brd_free_pages(brd); + kfree(brd); } static inline void brd_check_and_reset_par(void) @@ -485,7 +470,7 @@ static inline void brd_check_and_reset_par(void) static int __init brd_init(void) { struct brd_device *brd, *next; - int i; + int err, i; /* * brd module now has a feature to instantiate underlying device @@ -511,22 +496,11 @@ static int __init brd_init(void) mutex_lock(&brd_devices_mutex); for (i = 0; i < rd_nr; i++) { - brd = brd_alloc(i); - if (!brd) + err = brd_alloc(i); + if (err) goto out_free; - list_add_tail(&brd->brd_list, &brd_devices); } - /* point of no return */ - - list_for_each_entry(brd, &brd_devices, brd_list) { - /* - * associate with queue just before adding disk for - * avoiding to mess up failure path - */ - brd->brd_disk->queue = brd->brd_queue; - add_disk(brd->brd_disk); - } mutex_unlock(&brd_devices_mutex); pr_info("brd: module loaded\n"); @@ -535,15 +509,13 @@ static int __init brd_init(void) out_free: debugfs_remove_recursive(brd_debugfs_dir); - list_for_each_entry_safe(brd, next, &brd_devices, brd_list) { - list_del(&brd->brd_list); - brd_free(brd); - } + list_for_each_entry_safe(brd, next, &brd_devices, brd_list) + brd_del_one(brd); mutex_unlock(&brd_devices_mutex); unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); pr_info("brd: module NOT loaded !!!\n"); - return -ENOMEM; + return err; } static void __exit brd_exit(void) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index de463773b530..55234a558e98 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2231,8 +2231,7 @@ void drbd_destroy_device(struct kref *kref) if (device->bitmap) /* should no longer be there. */ drbd_bm_cleanup(device); __free_page(device->md_io.page); - put_disk(device->vdisk); - blk_cleanup_queue(device->rq_queue); + blk_cleanup_disk(device->vdisk); kfree(device->rs_plan_s); /* not for_each_connection(connection, resource): @@ -2701,7 +2700,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig struct drbd_device *device; struct drbd_peer_device *peer_device, *tmp_peer_device; struct gendisk *disk; - struct request_queue *q; int id; int vnr = adm_ctx->volume; enum drbd_ret_code err = ERR_NOMEM; @@ -2723,29 +2721,26 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_init_set_defaults(device); - q = blk_alloc_queue(NUMA_NO_NODE); - if (!q) - goto out_no_q; - device->rq_queue = q; - - disk = alloc_disk(1); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) goto out_no_disk; + device->vdisk = disk; + device->rq_queue = disk->queue; set_disk_ro(disk, true); - disk->queue = q; disk->major = DRBD_MAJOR; disk->first_minor = minor; + disk->minors = 1; disk->fops = &drbd_ops; sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; - blk_queue_write_cache(q, true, true); + blk_queue_write_cache(disk->queue, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ - blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8); + blk_queue_max_hw_sectors(disk->queue, DRBD_MAX_BIO_SIZE_SAFE >> 8); device->md_io.page = alloc_page(GFP_KERNEL); if (!device->md_io.page) @@ -2834,10 +2829,8 @@ out_no_minor_idr: out_no_bitmap: __free_page(device->md_io.page); out_no_io_page: - put_disk(disk); + blk_cleanup_disk(disk); out_no_disk: - blk_cleanup_queue(q); -out_no_q: kref_put(&resource->kref, drbd_destroy_resource); kfree(device); return err; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 8a9d22207c59..cbed9776f285 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4491,23 +4491,15 @@ static bool floppy_available(int drive) static int floppy_alloc_disk(unsigned int drive, unsigned int type) { struct gendisk *disk; - int err; - - disk = alloc_disk(1); - if (!disk) - return -ENOMEM; - disk->queue = blk_mq_init_queue(&tag_sets[drive]); - if (IS_ERR(disk->queue)) { - err = PTR_ERR(disk->queue); - disk->queue = NULL; - put_disk(disk); - return err; - } + disk = blk_mq_alloc_disk(&tag_sets[drive], NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); blk_queue_max_hw_sectors(disk->queue, 64); disk->major = FLOPPY_MAJOR; disk->first_minor = TOMINOR(drive) | (type << 2); + disk->minors = 1; disk->fops = &floppy_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; if (type) @@ -4727,10 +4719,8 @@ out_put_disk: if (!disks[drive][0]) break; del_timer_sync(&motor_off_timer[drive]); - blk_cleanup_queue(disks[drive][0]->queue); - disks[drive][0]->queue = NULL; + blk_cleanup_disk(disks[drive][0]); blk_mq_free_tag_set(&tag_sets[drive]); - put_disk(disks[drive][0]); } return err; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 452c7437e1f0..36e4312f6381 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -644,14 +644,13 @@ static inline void loop_update_dio(struct loop_device *lo) lo->use_dio); } -static void loop_reread_partitions(struct loop_device *lo, - struct block_device *bdev) +static void loop_reread_partitions(struct loop_device *lo) { int rc; - mutex_lock(&bdev->bd_mutex); - rc = bdev_disk_changed(bdev, false); - mutex_unlock(&bdev->bd_mutex); + mutex_lock(&lo->lo_disk->open_mutex); + rc = bdev_disk_changed(lo->lo_disk, false); + mutex_unlock(&lo->lo_disk->open_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); @@ -744,12 +743,12 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, mutex_unlock(&lo->lo_mutex); /* * We must drop file reference outside of lo_mutex as dropping - * the file ref can take bd_mutex which creates circular locking + * the file ref can take open_mutex which creates circular locking * dependency. */ fput(old_file); if (partscan) - loop_reread_partitions(lo, bdev); + loop_reread_partitions(lo); return 0; out_err: @@ -1255,7 +1254,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, bdgrab(bdev); mutex_unlock(&lo->lo_mutex); if (partscan) - loop_reread_partitions(lo, bdev); + loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); return 0; @@ -1353,7 +1352,7 @@ out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) { /* - * bd_mutex has been held already in release path, so don't + * open_mutex has been held already in release path, so don't * acquire it if this function is called in such case. * * If the reread partition isn't from release path, lo_refcnt @@ -1361,10 +1360,10 @@ out_unlock: * current holder is released. */ if (!release) - mutex_lock(&bdev->bd_mutex); - err = bdev_disk_changed(bdev, false); + mutex_lock(&lo->lo_disk->open_mutex); + err = bdev_disk_changed(lo->lo_disk, false); if (!release) - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&lo->lo_disk->open_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo_number, err); @@ -1391,7 +1390,7 @@ out_unlock: /* * Need not hold lo_mutex to fput backing file. Calling fput holding * lo_mutex triggers a circular lock dependency possibility warning as - * fput can take bd_mutex which is usually taken before lo_mutex. + * fput can take open_mutex which is usually taken before lo_mutex. */ if (filp) fput(filp); @@ -1509,7 +1508,7 @@ out_unfreeze: out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) - loop_reread_partitions(lo, bdev); + loop_reread_partitions(lo); return err; } @@ -2275,12 +2274,12 @@ static int loop_add(struct loop_device **l, int i) if (err) goto out_free_idr; - lo->lo_queue = blk_mq_init_queue(&lo->tag_set); - if (IS_ERR(lo->lo_queue)) { - err = PTR_ERR(lo->lo_queue); + disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, lo); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_cleanup_tags; } - lo->lo_queue->queuedata = lo; + lo->lo_queue = lo->lo_disk->queue; blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS); @@ -2292,11 +2291,6 @@ static int loop_add(struct loop_device **l, int i) */ blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); - err = -ENOMEM; - disk = lo->lo_disk = alloc_disk(1 << part_shift); - if (!disk) - goto out_free_queue; - /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its @@ -2325,6 +2319,7 @@ static int loop_add(struct loop_device **l, int i) spin_lock_init(&lo->lo_work_lock); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; + disk->minors = 1 << part_shift; disk->fops = &lo_fops; disk->private_data = lo; disk->queue = lo->lo_queue; @@ -2333,8 +2328,6 @@ static int loop_add(struct loop_device **l, int i) *l = lo; return lo->lo_number; -out_free_queue: - blk_cleanup_queue(lo->lo_queue); out_cleanup_tags: blk_mq_free_tag_set(&lo->tag_set); out_free_idr: @@ -2348,9 +2341,8 @@ out: static void loop_remove(struct loop_device *lo) { del_gendisk(lo->lo_disk); - blk_cleanup_queue(lo->lo_queue); + blk_cleanup_disk(lo->lo_disk); blk_mq_free_tag_set(&lo->tag_set); - put_disk(lo->lo_disk); mutex_destroy(&lo->lo_mutex); kfree(lo); } diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index 47bdf324e962..7b4dd10af9ec 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -132,16 +132,12 @@ static int __init n64cart_probe(struct platform_device *pdev) if (!reg_base) return -EINVAL; - disk = alloc_disk(0); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) return -ENOMEM; - disk->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!disk->queue) - return -ENOMEM; - disk->first_minor = 0; - disk->flags = GENHD_FL_NO_PART_SCAN | GENHD_FL_EXT_DEVT; + disk->flags = GENHD_FL_NO_PART_SCAN; disk->fops = &n64cart_fops; disk->private_data = &pdev->dev; strcpy(disk->disk_name, "n64cart"); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 45d2c28c8fc8..614d82e7fae4 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -219,15 +219,11 @@ static const struct device_attribute pid_attr = { static void nbd_dev_remove(struct nbd_device *nbd) { struct gendisk *disk = nbd->disk; - struct request_queue *q; if (disk) { - q = disk->queue; del_gendisk(disk); - blk_cleanup_queue(q); blk_mq_free_tag_set(&nbd->tag_set); - disk->private_data = NULL; - put_disk(disk); + blk_cleanup_disk(disk); } /* @@ -1646,15 +1642,24 @@ static int nbd_dev_add(int index) { struct nbd_device *nbd; struct gendisk *disk; - struct request_queue *q; int err = -ENOMEM; nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL); if (!nbd) goto out; - disk = alloc_disk(1 << part_shift); - if (!disk) + nbd->tag_set.ops = &nbd_mq_ops; + nbd->tag_set.nr_hw_queues = 1; + nbd->tag_set.queue_depth = 128; + nbd->tag_set.numa_node = NUMA_NO_NODE; + nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); + nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | + BLK_MQ_F_BLOCKING; + nbd->tag_set.driver_data = nbd; + nbd->destroy_complete = NULL; + + err = blk_mq_alloc_tag_set(&nbd->tag_set); + if (err) goto out_free_nbd; if (index >= 0) { @@ -1668,30 +1673,15 @@ static int nbd_dev_add(int index) index = err; } if (err < 0) - goto out_free_disk; - + goto out_free_tags; nbd->index = index; - nbd->disk = disk; - nbd->tag_set.ops = &nbd_mq_ops; - nbd->tag_set.nr_hw_queues = 1; - nbd->tag_set.queue_depth = 128; - nbd->tag_set.numa_node = NUMA_NO_NODE; - nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); - nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | - BLK_MQ_F_BLOCKING; - nbd->tag_set.driver_data = nbd; - nbd->destroy_complete = NULL; - err = blk_mq_alloc_tag_set(&nbd->tag_set); - if (err) + disk = blk_mq_alloc_disk(&nbd->tag_set, NULL); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_free_idr; - - q = blk_mq_init_queue(&nbd->tag_set); - if (IS_ERR(q)) { - err = PTR_ERR(q); - goto out_free_tags; } - disk->queue = q; + nbd->disk = disk; /* * Tell the block layer that we are not a rotational device @@ -1712,6 +1702,7 @@ static int nbd_dev_add(int index) INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; disk->first_minor = index << part_shift; + disk->minors = 1 << part_shift; disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); @@ -1719,12 +1710,10 @@ static int nbd_dev_add(int index) nbd_total_devices++; return index; -out_free_tags: - blk_mq_free_tag_set(&nbd->tag_set); out_free_idr: idr_remove(&nbd_index_idr, index); -out_free_disk: - put_disk(disk); +out_free_tags: + blk_mq_free_tag_set(&nbd->tag_set); out_free_nbd: kfree(nbd); out: diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 5f006d9e1472..3b320b005aa8 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1597,11 +1597,10 @@ static void null_del_dev(struct nullb *nullb) null_restart_queue_async(nullb); } - blk_cleanup_queue(nullb->q); + blk_cleanup_disk(nullb->disk); if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); - put_disk(nullb->disk); cleanup_queues(nullb); if (null_cache_active(nullb)) null_free_device_storage(nullb->dev, true); @@ -1700,22 +1699,19 @@ static int init_driver_queues(struct nullb *nullb) static int null_gendisk_register(struct nullb *nullb) { sector_t size = ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT; - struct gendisk *disk; + struct gendisk *disk = nullb->disk; - disk = nullb->disk = alloc_disk_node(1, nullb->dev->home_node); - if (!disk) - return -ENOMEM; set_capacity(disk, size); disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO; disk->major = null_major; disk->first_minor = nullb->index; + disk->minors = 1; if (queue_is_mq(nullb->q)) disk->fops = &null_rq_ops; else disk->fops = &null_bio_ops; disk->private_data = nullb; - disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); if (nullb->dev->zoned) { @@ -1851,23 +1847,26 @@ static int null_add_dev(struct nullb_device *dev) goto out_cleanup_queues; if (!null_setup_fault()) - goto out_cleanup_queues; + goto out_cleanup_tags; + rv = -ENOMEM; nullb->tag_set->timeout = 5 * HZ; - nullb->q = blk_mq_init_queue_data(nullb->tag_set, nullb); - if (IS_ERR(nullb->q)) { - rv = -ENOMEM; + nullb->disk = blk_mq_alloc_disk(nullb->tag_set, nullb); + if (IS_ERR(nullb->disk)) { + rv = PTR_ERR(nullb->disk); goto out_cleanup_tags; } + nullb->q = nullb->disk->queue; } else if (dev->queue_mode == NULL_Q_BIO) { - nullb->q = blk_alloc_queue(dev->home_node); - if (!nullb->q) { - rv = -ENOMEM; + rv = -ENOMEM; + nullb->disk = blk_alloc_disk(nullb->dev->home_node); + if (!nullb->disk) goto out_cleanup_queues; - } + + nullb->q = nullb->disk->queue; rv = init_driver_queues(nullb); if (rv) - goto out_cleanup_blk_queue; + goto out_cleanup_disk; } if (dev->mbps) { @@ -1883,7 +1882,7 @@ static int null_add_dev(struct nullb_device *dev) if (dev->zoned) { rv = null_init_zoned_dev(dev, nullb->q); if (rv) - goto out_cleanup_blk_queue; + goto out_cleanup_disk; } nullb->q->queuedata = nullb; @@ -1921,8 +1920,8 @@ static int null_add_dev(struct nullb_device *dev) return 0; out_cleanup_zone: null_free_zoned_dev(dev); -out_cleanup_blk_queue: - blk_cleanup_queue(nullb->q); +out_cleanup_disk: + blk_cleanup_disk(nullb->disk); out_cleanup_tags: if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 70da8b86ce58..f9cdd11f02f5 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -309,21 +309,19 @@ static void pcd_init_units(void) pcd_drive_count = 0; for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - struct gendisk *disk = alloc_disk(1); + struct gendisk *disk; - if (!disk) + if (blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE)) continue; - disk->queue = blk_mq_init_sq_queue(&cd->tag_set, &pcd_mq_ops, - 1, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disk->queue)) { - disk->queue = NULL; - put_disk(disk); + disk = blk_mq_alloc_disk(&cd->tag_set, cd); + if (IS_ERR(disk)) { + blk_mq_free_tag_set(&cd->tag_set); continue; } INIT_LIST_HEAD(&cd->rq_list); - disk->queue->queuedata = cd; blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); cd->disk = disk; cd->pi = &cd->pia; @@ -343,6 +341,7 @@ static void pcd_init_units(void) cd->info.mask = 0; disk->major = major; disk->first_minor = unit; + disk->minors = 1; strcpy(disk->disk_name, cd->name); /* umm... */ disk->fops = &pcd_bdops; disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; @@ -759,10 +758,8 @@ static int pcd_detect(void) for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { if (!cd->disk) continue; - blk_cleanup_queue(cd->disk->queue); - cd->disk->queue = NULL; + blk_cleanup_disk(cd->disk); blk_mq_free_tag_set(&cd->tag_set); - put_disk(cd->disk); } pi_unregister_driver(par_drv); return -1; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 828a45ffe0e7..3b2b8e872beb 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -879,18 +879,6 @@ static void pd_probe_drive(struct pd_unit *disk) { struct gendisk *p; - p = alloc_disk(1 << PD_BITS); - if (!p) - return; - - strcpy(p->disk_name, disk->name); - p->fops = &pd_fops; - p->major = major; - p->first_minor = (disk - pd) << PD_BITS; - p->events = DISK_EVENT_MEDIA_CHANGE; - disk->gd = p; - p->private_data = disk; - memset(&disk->tag_set, 0, sizeof(disk->tag_set)); disk->tag_set.ops = &pd_mq_ops; disk->tag_set.cmd_size = sizeof(struct pd_req); @@ -903,14 +891,21 @@ static void pd_probe_drive(struct pd_unit *disk) if (blk_mq_alloc_tag_set(&disk->tag_set)) return; - p->queue = blk_mq_init_queue(&disk->tag_set); - if (IS_ERR(p->queue)) { + p = blk_mq_alloc_disk(&disk->tag_set, disk); + if (!p) { blk_mq_free_tag_set(&disk->tag_set); - p->queue = NULL; return; } + disk->gd = p; + + strcpy(p->disk_name, disk->name); + p->fops = &pd_fops; + p->major = major; + p->first_minor = (disk - pd) << PD_BITS; + p->minors = 1 << PD_BITS; + p->events = DISK_EVENT_MEDIA_CHANGE; + p->private_data = disk; - p->queue->queuedata = disk; blk_queue_max_hw_sectors(p->queue, cluster); blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH); @@ -1019,9 +1014,8 @@ static void __exit pd_exit(void) if (p) { disk->gd = NULL; del_gendisk(p); - blk_cleanup_queue(p->queue); blk_mq_free_tag_set(&disk->tag_set); - put_disk(p); + blk_cleanup_disk(p); pi_release(disk->pi); } } diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index bb09f21ce21a..d5b9c88ba76f 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -294,20 +294,17 @@ static void __init pf_init_units(void) for (unit = 0, pf = units; unit < PF_UNITS; unit++, pf++) { struct gendisk *disk; - disk = alloc_disk(1); - if (!disk) + if (blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE)) continue; - disk->queue = blk_mq_init_sq_queue(&pf->tag_set, &pf_mq_ops, - 1, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disk->queue)) { - disk->queue = NULL; - put_disk(disk); + disk = blk_mq_alloc_disk(&pf->tag_set, pf); + if (IS_ERR(disk)) { + blk_mq_free_tag_set(&pf->tag_set); continue; } INIT_LIST_HEAD(&pf->rq_list); - disk->queue->queuedata = pf; blk_queue_max_segments(disk->queue, cluster); blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); pf->disk = disk; @@ -318,6 +315,7 @@ static void __init pf_init_units(void) snprintf(pf->name, PF_NAMELEN, "%s%d", name, unit); disk->major = major; disk->first_minor = unit; + disk->minors = 1; strcpy(disk->disk_name, pf->name); disk->fops = &pf_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; @@ -766,10 +764,8 @@ static int pf_detect(void) for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { if (!pf->disk) continue; - blk_cleanup_queue(pf->disk->queue); - pf->disk->queue = NULL; + blk_cleanup_disk(pf->disk); blk_mq_free_tag_set(&pf->tag_set); - put_disk(pf->disk); } pi_unregister_driver(par_drv); return -1; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index bd3556585122..f69b5c69c2a6 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2711,19 +2711,17 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) pd->write_congestion_off = write_congestion_off; ret = -ENOMEM; - disk = alloc_disk(1); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) goto out_mem; pd->disk = disk; disk->major = pktdev_major; disk->first_minor = idx; + disk->minors = 1; disk->fops = &pktcdvd_ops; disk->flags = GENHD_FL_REMOVABLE; strcpy(disk->disk_name, pd->name); disk->private_data = pd; - disk->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!disk->queue) - goto out_mem2; pd->pkt_dev = MKDEV(pktdev_major, idx); ret = pkt_new_dev(pd, dev); @@ -2746,7 +2744,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) return 0; out_mem2: - put_disk(disk); + blk_cleanup_disk(disk); out_mem: mempool_exit(&pd->rb_pool); kfree(pd); @@ -2796,8 +2794,7 @@ static int pkt_remove_dev(dev_t pkt_dev) pkt_dbg(1, pd, "writer unmapped\n"); del_gendisk(pd->disk); - blk_cleanup_queue(pd->disk->queue); - put_disk(pd->disk); + blk_cleanup_disk(pd->disk); mempool_exit(&pd->rb_pool); kfree(pd); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index ba3ece56cbb3..f374ea2c67ce 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -29,7 +29,6 @@ struct ps3disk_private { spinlock_t lock; /* Request queue spinlock */ - struct request_queue *queue; struct blk_mq_tag_set tag_set; struct gendisk *gendisk; unsigned int blocking_factor; @@ -267,7 +266,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data) blk_mq_end_request(req, error); spin_unlock(&priv->lock); - blk_mq_run_hw_queues(priv->queue, true); + blk_mq_run_hw_queues(priv->gendisk->queue, true); return IRQ_HANDLED; } @@ -441,17 +440,20 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) ps3disk_identify(dev); - queue = blk_mq_init_sq_queue(&priv->tag_set, &ps3disk_mq_ops, 1, + error = blk_mq_alloc_sq_tag_set(&priv->tag_set, &ps3disk_mq_ops, 1, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(queue)) { - dev_err(&dev->sbd.core, "%s:%u: blk_mq_init_queue failed\n", - __func__, __LINE__); - error = PTR_ERR(queue); + if (error) goto fail_teardown; + + gendisk = blk_mq_alloc_disk(&priv->tag_set, dev); + if (IS_ERR(gendisk)) { + dev_err(&dev->sbd.core, "%s:%u: blk_mq_alloc_disk failed\n", + __func__, __LINE__); + error = PTR_ERR(gendisk); + goto fail_free_tag_set; } - priv->queue = queue; - queue->queuedata = dev; + queue = gendisk->queue; blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9); blk_queue_dma_alignment(queue, dev->blk_size-1); @@ -462,19 +464,11 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) blk_queue_max_segments(queue, -1); blk_queue_max_segment_size(queue, dev->bounce_size); - gendisk = alloc_disk(PS3DISK_MINORS); - if (!gendisk) { - dev_err(&dev->sbd.core, "%s:%u: alloc_disk failed\n", __func__, - __LINE__); - error = -ENOMEM; - goto fail_cleanup_queue; - } - priv->gendisk = gendisk; gendisk->major = ps3disk_major; gendisk->first_minor = devidx * PS3DISK_MINORS; + gendisk->minors = PS3DISK_MINORS; gendisk->fops = &ps3disk_fops; - gendisk->queue = queue; gendisk->private_data = dev; snprintf(gendisk->disk_name, sizeof(gendisk->disk_name), PS3DISK_NAME, devidx+'a'); @@ -490,8 +484,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) device_add_disk(&dev->sbd.core, gendisk, NULL); return 0; -fail_cleanup_queue: - blk_cleanup_queue(queue); +fail_free_tag_set: blk_mq_free_tag_set(&priv->tag_set); fail_teardown: ps3stor_teardown(dev); @@ -517,9 +510,8 @@ static void ps3disk_remove(struct ps3_system_bus_device *_dev) &ps3disk_mask); mutex_unlock(&ps3disk_mask_mutex); del_gendisk(priv->gendisk); - blk_cleanup_queue(priv->queue); + blk_cleanup_disk(priv->gendisk); blk_mq_free_tag_set(&priv->tag_set); - put_disk(priv->gendisk); dev_notice(&dev->sbd.core, "Synchronizing disk cache\n"); ps3disk_sync_cache(dev); ps3stor_teardown(dev); diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 1d738999fb69..7fbf469651c4 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -67,7 +67,6 @@ struct ps3vram_cache { }; struct ps3vram_priv { - struct request_queue *queue; struct gendisk *gendisk; u64 size; @@ -613,7 +612,6 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) { struct ps3vram_priv *priv; int error, status; - struct request_queue *queue; struct gendisk *gendisk; u64 ddr_size, ddr_lpar, ctrl_lpar, info_lpar, reports_lpar, reports_size, xdr_lpar; @@ -736,33 +734,23 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) ps3vram_proc_init(dev); - queue = blk_alloc_queue(NUMA_NO_NODE); - if (!queue) { - dev_err(&dev->core, "blk_alloc_queue failed\n"); - error = -ENOMEM; - goto out_cache_cleanup; - } - - priv->queue = queue; - blk_queue_max_segments(queue, BLK_MAX_SEGMENTS); - blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE); - blk_queue_max_hw_sectors(queue, BLK_SAFE_MAX_SECTORS); - - gendisk = alloc_disk(1); + gendisk = blk_alloc_disk(NUMA_NO_NODE); if (!gendisk) { - dev_err(&dev->core, "alloc_disk failed\n"); + dev_err(&dev->core, "blk_alloc_disk failed\n"); error = -ENOMEM; - goto fail_cleanup_queue; + goto out_cache_cleanup; } priv->gendisk = gendisk; gendisk->major = ps3vram_major; - gendisk->first_minor = 0; + gendisk->minors = 1; gendisk->fops = &ps3vram_fops; - gendisk->queue = queue; gendisk->private_data = dev; strlcpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name)); set_capacity(gendisk, priv->size >> 9); + blk_queue_max_segments(gendisk->queue, BLK_MAX_SEGMENTS); + blk_queue_max_segment_size(gendisk->queue, BLK_MAX_SEGMENT_SIZE); + blk_queue_max_hw_sectors(gendisk->queue, BLK_SAFE_MAX_SECTORS); dev_info(&dev->core, "%s: Using %llu MiB of GPU memory\n", gendisk->disk_name, get_capacity(gendisk) >> 11); @@ -770,8 +758,6 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) device_add_disk(&dev->core, gendisk, NULL); return 0; -fail_cleanup_queue: - blk_cleanup_queue(queue); out_cache_cleanup: remove_proc_entry(DEVICE_NAME, NULL); ps3vram_cache_cleanup(dev); @@ -802,8 +788,7 @@ static void ps3vram_remove(struct ps3_system_bus_device *dev) struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); del_gendisk(priv->gendisk); - put_disk(priv->gendisk); - blk_cleanup_queue(priv->queue); + blk_cleanup_disk(priv->gendisk); remove_proc_entry(DEVICE_NAME, NULL); ps3vram_cache_cleanup(dev); iounmap(priv->reports); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index bbb88eb009e0..531d390902dd 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4750,9 +4750,8 @@ static blk_status_t rbd_queue_rq(struct blk_mq_hw_ctx *hctx, static void rbd_free_disk(struct rbd_device *rbd_dev) { - blk_cleanup_queue(rbd_dev->disk->queue); + blk_cleanup_disk(rbd_dev->disk); blk_mq_free_tag_set(&rbd_dev->tag_set); - put_disk(rbd_dev->disk); rbd_dev->disk = NULL; } @@ -4922,22 +4921,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) rbd_dev->layout.object_size * rbd_dev->layout.stripe_count; int err; - /* create gendisk info */ - disk = alloc_disk(single_major ? - (1 << RBD_SINGLE_MAJOR_PART_SHIFT) : - RBD_MINORS_PER_MAJOR); - if (!disk) - return -ENOMEM; - - snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d", - rbd_dev->dev_id); - disk->major = rbd_dev->major; - disk->first_minor = rbd_dev->minor; - if (single_major) - disk->flags |= GENHD_FL_EXT_DEVT; - disk->fops = &rbd_bd_ops; - disk->private_data = rbd_dev; - memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set)); rbd_dev->tag_set.ops = &rbd_mq_ops; rbd_dev->tag_set.queue_depth = rbd_dev->opts->queue_depth; @@ -4948,13 +4931,26 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) err = blk_mq_alloc_tag_set(&rbd_dev->tag_set); if (err) - goto out_disk; + return err; - q = blk_mq_init_queue(&rbd_dev->tag_set); - if (IS_ERR(q)) { - err = PTR_ERR(q); + disk = blk_mq_alloc_disk(&rbd_dev->tag_set, rbd_dev); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_tag_set; } + q = disk->queue; + + snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d", + rbd_dev->dev_id); + disk->major = rbd_dev->major; + disk->first_minor = rbd_dev->minor; + if (single_major) { + disk->minors = (1 << RBD_SINGLE_MAJOR_PART_SHIFT); + disk->flags |= GENHD_FL_EXT_DEVT; + } else { + disk->minors = RBD_MINORS_PER_MAJOR; + } + disk->fops = &rbd_bd_ops; blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */ @@ -4976,21 +4972,11 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); - /* - * disk_release() expects a queue ref from add_disk() and will - * put it. Hold an extra ref until add_disk() is called. - */ - WARN_ON(!blk_get_queue(q)); - disk->queue = q; - q->queuedata = rbd_dev; - rbd_dev->disk = disk; return 0; out_tag_set: blk_mq_free_tag_set(&rbd_dev->tag_set); -out_disk: - put_disk(disk); return err; } @@ -7088,8 +7074,6 @@ static ssize_t do_rbd_add(struct bus_type *bus, goto err_out_image_lock; device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL); - /* see rbd_init_disk() */ - blk_put_queue(rbd_dev->disk->queue); spin_lock(&rbd_dev_list_lock); list_add_tail(&rbd_dev->node, &rbd_dev_list); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index c604a402cd5c..f4fa45d24c0b 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1353,18 +1353,6 @@ static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev) } } -static int setup_mq_dev(struct rnbd_clt_dev *dev) -{ - dev->queue = blk_mq_init_queue(&dev->sess->tag_set); - if (IS_ERR(dev->queue)) { - rnbd_clt_err(dev, "Initializing multiqueue queue failed, err: %ld\n", - PTR_ERR(dev->queue)); - return PTR_ERR(dev->queue); - } - rnbd_init_mq_hw_queues(dev); - return 0; -} - static void setup_request_queue(struct rnbd_clt_dev *dev) { blk_queue_logical_block_size(dev->queue, dev->logical_block_size); @@ -1393,13 +1381,13 @@ static void setup_request_queue(struct rnbd_clt_dev *dev) blk_queue_io_opt(dev->queue, dev->sess->max_io_size); blk_queue_virt_boundary(dev->queue, SZ_4K - 1); blk_queue_write_cache(dev->queue, dev->wc, dev->fua); - dev->queue->queuedata = dev; } static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) { dev->gd->major = rnbd_client_major; dev->gd->first_minor = idx << RNBD_PART_BITS; + dev->gd->minors = 1 << RNBD_PART_BITS; dev->gd->fops = &rnbd_client_ops; dev->gd->queue = dev->queue; dev->gd->private_data = dev; @@ -1426,24 +1414,18 @@ static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) static int rnbd_client_setup_device(struct rnbd_clt_dev *dev) { - int err, idx = dev->clt_device_id; + int idx = dev->clt_device_id; dev->size = dev->nsectors * dev->logical_block_size; - err = setup_mq_dev(dev); - if (err) - return err; + dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, dev); + if (IS_ERR(dev->gd)) + return PTR_ERR(dev->gd); + dev->queue = dev->gd->queue; + rnbd_init_mq_hw_queues(dev); setup_request_queue(dev); - - dev->gd = alloc_disk_node(1 << RNBD_PART_BITS, NUMA_NO_NODE); - if (!dev->gd) { - blk_cleanup_queue(dev->queue); - return -ENOMEM; - } - rnbd_clt_setup_gen_disk(dev, idx); - return 0; } @@ -1650,8 +1632,7 @@ put_sess: static void destroy_gen_disk(struct rnbd_clt_dev *dev) { del_gendisk(dev->gd); - blk_cleanup_queue(dev->queue); - put_disk(dev->gd); + blk_cleanup_disk(dev->gd); } static void destroy_sysfs(struct rnbd_clt_dev *dev, diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index 9a28322a8cd8..1cc40b0ea761 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -236,47 +236,40 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card) return -ENOMEM; } - card->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!card->queue) { - dev_err(CARD_TO_DEV(card), "Failed queue alloc\n"); - unregister_blkdev(card->major, DRIVER_NAME); - return -ENOMEM; - } - - card->gendisk = alloc_disk(blkdev_minors); + card->gendisk = blk_alloc_disk(blkdev_minors); if (!card->gendisk) { dev_err(CARD_TO_DEV(card), "Failed disk alloc\n"); - blk_cleanup_queue(card->queue); unregister_blkdev(card->major, DRIVER_NAME); return -ENOMEM; } if (card->config_valid) { blk_size = card->config.data.block_size; - blk_queue_dma_alignment(card->queue, blk_size - 1); - blk_queue_logical_block_size(card->queue, blk_size); + blk_queue_dma_alignment(card->gendisk->queue, blk_size - 1); + blk_queue_logical_block_size(card->gendisk->queue, blk_size); } - blk_queue_max_hw_sectors(card->queue, blkdev_max_hw_sectors); - blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE); + blk_queue_max_hw_sectors(card->gendisk->queue, blkdev_max_hw_sectors); + blk_queue_physical_block_size(card->gendisk->queue, RSXX_HW_BLK_SIZE); - blk_queue_flag_set(QUEUE_FLAG_NONROT, card->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, card->queue); + blk_queue_flag_set(QUEUE_FLAG_NONROT, card->gendisk->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, card->gendisk->queue); if (rsxx_discard_supported(card)) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, card->queue); - blk_queue_max_discard_sectors(card->queue, + blk_queue_flag_set(QUEUE_FLAG_DISCARD, card->gendisk->queue); + blk_queue_max_discard_sectors(card->gendisk->queue, RSXX_HW_BLK_SIZE >> 9); - card->queue->limits.discard_granularity = RSXX_HW_BLK_SIZE; - card->queue->limits.discard_alignment = RSXX_HW_BLK_SIZE; + card->gendisk->queue->limits.discard_granularity = + RSXX_HW_BLK_SIZE; + card->gendisk->queue->limits.discard_alignment = + RSXX_HW_BLK_SIZE; } snprintf(card->gendisk->disk_name, sizeof(card->gendisk->disk_name), "rsxx%d", card->disk_id); card->gendisk->major = card->major; - card->gendisk->first_minor = 0; + card->gendisk->minors = blkdev_minors; card->gendisk->fops = &rsxx_fops; card->gendisk->private_data = card; - card->gendisk->queue = card->queue; return 0; } @@ -286,10 +279,8 @@ void rsxx_destroy_dev(struct rsxx_cardinfo *card) if (!enable_blkdev) return; - put_disk(card->gendisk); + blk_cleanup_disk(card->gendisk); card->gendisk = NULL; - - blk_cleanup_queue(card->queue); unregister_blkdev(card->major, DRIVER_NAME); } diff --git a/drivers/block/rsxx/rsxx_priv.h b/drivers/block/rsxx/rsxx_priv.h index 6147977994ff..26c320c0d924 100644 --- a/drivers/block/rsxx/rsxx_priv.h +++ b/drivers/block/rsxx/rsxx_priv.h @@ -154,7 +154,6 @@ struct rsxx_cardinfo { bool bdev_attached; int disk_id; int major; - struct request_queue *queue; struct gendisk *gendisk; struct { /* Used to convert a byte address to a device address. */ diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 39aeebc6837d..c53b38578bb7 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -780,27 +780,6 @@ static const struct blk_mq_ops vdc_mq_ops = { .queue_rq = vdc_queue_rq, }; -static void cleanup_queue(struct request_queue *q) -{ - struct vdc_port *port = q->queuedata; - - blk_cleanup_queue(q); - blk_mq_free_tag_set(&port->tag_set); -} - -static struct request_queue *init_queue(struct vdc_port *port) -{ - struct request_queue *q; - - q = blk_mq_init_sq_queue(&port->tag_set, &vdc_mq_ops, VDC_TX_RING_SIZE, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(q)) - return q; - - q->queuedata = port; - return q; -} - static int probe_disk(struct vdc_port *port) { struct request_queue *q; @@ -838,21 +817,21 @@ static int probe_disk(struct vdc_port *port) (u64)geom.num_sec); } - q = init_queue(port); - if (IS_ERR(q)) { - printk(KERN_ERR PFX "%s: Could not allocate queue.\n", - port->vio.name); - return PTR_ERR(q); - } - g = alloc_disk(1 << PARTITION_SHIFT); - if (!g) { + err = blk_mq_alloc_sq_tag_set(&port->tag_set, &vdc_mq_ops, + VDC_TX_RING_SIZE, BLK_MQ_F_SHOULD_MERGE); + if (err) + return err; + + g = blk_mq_alloc_disk(&port->tag_set, port); + if (IS_ERR(g)) { printk(KERN_ERR PFX "%s: Could not allocate gendisk.\n", port->vio.name); - cleanup_queue(q); - return -ENOMEM; + blk_mq_free_tag_set(&port->tag_set); + return PTR_ERR(g); } port->disk = g; + q = g->queue; /* Each segment in a request is up to an aligned page in size. */ blk_queue_segment_boundary(q, PAGE_SIZE - 1); @@ -862,6 +841,7 @@ static int probe_disk(struct vdc_port *port) blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT; + g->minors = 1 << PARTITION_SHIFT; strcpy(g->disk_name, port->disk_name); g->fops = &vdc_fops; @@ -1083,9 +1063,8 @@ static int vdc_port_remove(struct vio_dev *vdev) del_timer_sync(&port->vio.timer); del_gendisk(port->disk); - cleanup_queue(port->disk->queue); - put_disk(port->disk); - port->disk = NULL; + blk_cleanup_disk(port->disk); + blk_mq_free_tag_set(&port->tag_set); vdc_free_tx_ring(port); vio_ldc_free(&port->vio); diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 2917b21f48ff..7ccc8d2a41bc 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -800,23 +800,20 @@ static int swim_floppy_init(struct swim_priv *swd) spin_lock_init(&swd->lock); for (drive = 0; drive < swd->floppy_count; drive++) { - struct request_queue *q; - - swd->unit[drive].disk = alloc_disk(1); - if (swd->unit[drive].disk == NULL) { - err = -ENOMEM; + err = blk_mq_alloc_sq_tag_set(&swd->unit[drive].tag_set, + &swim_mq_ops, 2, BLK_MQ_F_SHOULD_MERGE); + if (err) goto exit_put_disks; - } - q = blk_mq_init_sq_queue(&swd->unit[drive].tag_set, &swim_mq_ops, - 2, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(q)) { - err = PTR_ERR(q); + swd->unit[drive].disk = + blk_mq_alloc_disk(&swd->unit[drive].tag_set, + &swd->unit[drive]); + if (IS_ERR(swd->unit[drive].disk)) { + blk_mq_free_tag_set(&swd->unit[drive].tag_set); + err = PTR_ERR(swd->unit[drive].disk); goto exit_put_disks; } - swd->unit[drive].disk->queue = q; - swd->unit[drive].disk->queue->queuedata = &swd->unit[drive]; swd->unit[drive].swd = swd; } @@ -824,6 +821,7 @@ static int swim_floppy_init(struct swim_priv *swd) swd->unit[drive].disk->flags = GENHD_FL_REMOVABLE; swd->unit[drive].disk->major = FLOPPY_MAJOR; swd->unit[drive].disk->first_minor = drive; + swd->unit[drive].disk->minors = 1; sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive); swd->unit[drive].disk->fops = &floppy_fops; swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE; @@ -839,14 +837,10 @@ exit_put_disks: do { struct gendisk *disk = swd->unit[drive].disk; - if (disk) { - if (disk->queue) { - blk_cleanup_queue(disk->queue); - disk->queue = NULL; - } - blk_mq_free_tag_set(&swd->unit[drive].tag_set); - put_disk(disk); - } + if (!disk) + continue; + blk_cleanup_disk(disk); + blk_mq_free_tag_set(&swd->unit[drive].tag_set); } while (drive--); return err; } diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index a515d0c1d2cb..965af0a3e95b 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1202,30 +1202,27 @@ static int swim3_attach(struct macio_dev *mdev, return rc; } - disk = alloc_disk(1); - if (disk == NULL) { - rc = -ENOMEM; - goto out_unregister; - } - fs = &floppy_states[floppy_count]; memset(fs, 0, sizeof(*fs)); - disk->queue = blk_mq_init_sq_queue(&fs->tag_set, &swim3_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disk->queue)) { - rc = PTR_ERR(disk->queue); - disk->queue = NULL; - goto out_put_disk; + rc = blk_mq_alloc_sq_tag_set(&fs->tag_set, &swim3_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE); + if (rc) + goto out_unregister; + + disk = blk_mq_alloc_disk(&fs->tag_set, fs); + if (IS_ERR(disk)) { + rc = PTR_ERR(disk); + goto out_free_tag_set; } - disk->queue->queuedata = fs; rc = swim3_add_device(mdev, floppy_count); if (rc) - goto out_cleanup_queue; + goto out_cleanup_disk; disk->major = FLOPPY_MAJOR; disk->first_minor = floppy_count; + disk->minors = 1; disk->fops = &floppy_fops; disk->private_data = fs; disk->events = DISK_EVENT_MEDIA_CHANGE; @@ -1237,12 +1234,10 @@ static int swim3_attach(struct macio_dev *mdev, disks[floppy_count++] = disk; return 0; -out_cleanup_queue: - blk_cleanup_queue(disk->queue); - disk->queue = NULL; +out_cleanup_disk: + blk_cleanup_disk(disk); +out_free_tag_set: blk_mq_free_tag_set(&fs->tag_set); -out_put_disk: - put_disk(disk); out_unregister: if (floppy_count == 0) unregister_blkdev(FLOPPY_MAJOR, "fd"); diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 2cdf2771f8e8..f01f860b0e62 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -1343,32 +1343,25 @@ static int carm_init_disk(struct carm_host *host, unsigned int port_no) { struct carm_port *port = &host->port[port_no]; struct gendisk *disk; - struct request_queue *q; port->host = host; port->port_no = port_no; - disk = alloc_disk(CARM_MINORS_PER_MAJOR); - if (!disk) - return -ENOMEM; + disk = blk_mq_alloc_disk(&host->tag_set, port); + if (IS_ERR(disk)) + return PTR_ERR(disk); port->disk = disk; sprintf(disk->disk_name, DRV_NAME "/%u", (unsigned int)host->id * CARM_MAX_PORTS + port_no); disk->major = host->major; disk->first_minor = port_no * CARM_MINORS_PER_MAJOR; + disk->minors = CARM_MINORS_PER_MAJOR; disk->fops = &carm_bd_ops; disk->private_data = port; - q = blk_mq_init_queue(&host->tag_set); - if (IS_ERR(q)) - return PTR_ERR(q); - - blk_queue_max_segments(q, CARM_MAX_REQ_SG); - blk_queue_segment_boundary(q, CARM_SG_BOUNDARY); - - q->queuedata = port; - disk->queue = q; + blk_queue_max_segments(disk->queue, CARM_MAX_REQ_SG); + blk_queue_segment_boundary(disk->queue, CARM_SG_BOUNDARY); return 0; } @@ -1382,9 +1375,7 @@ static void carm_free_disk(struct carm_host *host, unsigned int port_no) if (disk->flags & GENHD_FL_UP) del_gendisk(disk); - if (disk->queue) - blk_cleanup_queue(disk->queue); - put_disk(disk); + blk_cleanup_disk(disk); } static int carm_init_shm(struct carm_host *host) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index b9fa3ef5b57c..e4bd3b1fc3c2 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -749,13 +749,6 @@ static int virtblk_probe(struct virtio_device *vdev) if (err) goto out_free_vblk; - /* FIXME: How many partitions? How long is a piece of string? */ - vblk->disk = alloc_disk(1 << PART_BITS); - if (!vblk->disk) { - err = -ENOMEM; - goto out_free_vq; - } - /* Default queue sizing is to fill the ring. */ if (likely(!virtblk_queue_depth)) { queue_depth = vblk->vqs[0].vq->num_free; @@ -779,21 +772,20 @@ static int virtblk_probe(struct virtio_device *vdev) err = blk_mq_alloc_tag_set(&vblk->tag_set); if (err) - goto out_put_disk; + goto out_free_vq; - q = blk_mq_init_queue(&vblk->tag_set); - if (IS_ERR(q)) { - err = -ENOMEM; + vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, vblk); + if (IS_ERR(vblk->disk)) { + err = PTR_ERR(vblk->disk); goto out_free_tags; } - vblk->disk->queue = q; - - q->queuedata = vblk; + q = vblk->disk->queue; virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN); vblk->disk->major = major; vblk->disk->first_minor = index_to_minor(index); + vblk->disk->minors = 1 << PART_BITS; vblk->disk->private_data = vblk; vblk->disk->fops = &virtblk_fops; vblk->disk->flags |= GENHD_FL_EXT_DEVT; @@ -892,8 +884,6 @@ static int virtblk_probe(struct virtio_device *vdev) out_free_tags: blk_mq_free_tag_set(&vblk->tag_set); -out_put_disk: - put_disk(vblk->disk); out_free_vq: vdev->config->del_vqs(vdev); kfree(vblk->vqs); @@ -913,8 +903,7 @@ static void virtblk_remove(struct virtio_device *vdev) flush_work(&vblk->config_work); del_gendisk(vblk->disk); - blk_cleanup_queue(vblk->disk->queue); - + blk_cleanup_disk(vblk->disk); blk_mq_free_tag_set(&vblk->tag_set); mutex_lock(&vblk->vdev_mutex); @@ -925,7 +914,6 @@ static void virtblk_remove(struct virtio_device *vdev) /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ vblk->vdev = NULL; - put_disk(vblk->disk); vdev->config->del_vqs(vdev); kfree(vblk->vqs); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 10df39a8b18d..8d49f8fa98bb 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -968,48 +968,6 @@ static void blkif_set_queue_limits(struct blkfront_info *info) blk_queue_dma_alignment(rq, 511); } -static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, - unsigned int physical_sector_size) -{ - struct request_queue *rq; - struct blkfront_info *info = gd->private_data; - - memset(&info->tag_set, 0, sizeof(info->tag_set)); - info->tag_set.ops = &blkfront_mq_ops; - info->tag_set.nr_hw_queues = info->nr_rings; - if (HAS_EXTRA_REQ && info->max_indirect_segments == 0) { - /* - * When indirect descriptior is not supported, the I/O request - * will be split between multiple request in the ring. - * To avoid problems when sending the request, divide by - * 2 the depth of the queue. - */ - info->tag_set.queue_depth = BLK_RING_SIZE(info) / 2; - } else - info->tag_set.queue_depth = BLK_RING_SIZE(info); - info->tag_set.numa_node = NUMA_NO_NODE; - info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - info->tag_set.cmd_size = sizeof(struct blkif_req); - info->tag_set.driver_data = info; - - if (blk_mq_alloc_tag_set(&info->tag_set)) - return -EINVAL; - rq = blk_mq_init_queue(&info->tag_set); - if (IS_ERR(rq)) { - blk_mq_free_tag_set(&info->tag_set); - return PTR_ERR(rq); - } - - rq->queuedata = info; - info->rq = gd->queue = rq; - info->gd = gd; - info->sector_size = sector_size; - info->physical_sector_size = physical_sector_size; - blkif_set_queue_limits(info); - - return 0; -} - static const char *flush_info(struct blkfront_info *info) { if (info->feature_flush && info->feature_fua) @@ -1146,12 +1104,36 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, err = xlbd_reserve_minors(minor, nr_minors); if (err) - goto out; + return err; err = -ENODEV; - gd = alloc_disk(nr_minors); - if (gd == NULL) - goto release; + memset(&info->tag_set, 0, sizeof(info->tag_set)); + info->tag_set.ops = &blkfront_mq_ops; + info->tag_set.nr_hw_queues = info->nr_rings; + if (HAS_EXTRA_REQ && info->max_indirect_segments == 0) { + /* + * When indirect descriptior is not supported, the I/O request + * will be split between multiple request in the ring. + * To avoid problems when sending the request, divide by + * 2 the depth of the queue. + */ + info->tag_set.queue_depth = BLK_RING_SIZE(info) / 2; + } else + info->tag_set.queue_depth = BLK_RING_SIZE(info); + info->tag_set.numa_node = NUMA_NO_NODE; + info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + info->tag_set.cmd_size = sizeof(struct blkif_req); + info->tag_set.driver_data = info; + + err = blk_mq_alloc_tag_set(&info->tag_set); + if (err) + goto out_release_minors; + + gd = blk_mq_alloc_disk(&info->tag_set, info); + if (IS_ERR(gd)) { + err = PTR_ERR(gd); + goto out_free_tag_set; + } strcpy(gd->disk_name, DEV_NAME); ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset); @@ -1164,14 +1146,16 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, gd->major = XENVBD_MAJOR; gd->first_minor = minor; + gd->minors = nr_minors; gd->fops = &xlvbd_block_fops; gd->private_data = info; set_capacity(gd, capacity); - if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) { - del_gendisk(gd); - goto release; - } + info->rq = gd->queue; + info->gd = gd; + info->sector_size = sector_size; + info->physical_sector_size = physical_sector_size; + blkif_set_queue_limits(info); xlvbd_flush(info); @@ -1186,9 +1170,10 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, return 0; - release: +out_free_tag_set: + blk_mq_free_tag_set(&info->tag_set); +out_release_minors: xlbd_release_minors(minor, nr_minors); - out: return err; } @@ -1217,12 +1202,9 @@ static void xlvbd_release_gendisk(struct blkfront_info *info) nr_minors = info->gd->minors; xlbd_release_minors(minor, nr_minors); - blk_cleanup_queue(info->rq); - blk_mq_free_tag_set(&info->tag_set); - info->rq = NULL; - - put_disk(info->gd); + blk_cleanup_disk(info->gd); info->gd = NULL; + blk_mq_free_tag_set(&info->tag_set); } /* Already hold rinfo->ring_lock. */ @@ -2163,7 +2145,7 @@ static void blkfront_closing(struct blkfront_info *info) return; } - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (bdev->bd_openers) { xenbus_dev_error(xbdev, -EBUSY, @@ -2174,7 +2156,7 @@ static void blkfront_closing(struct blkfront_info *info) xenbus_frontend_closed(xbdev); } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); bdput(bdev); } @@ -2531,7 +2513,7 @@ static int blkfront_remove(struct xenbus_device *xbdev) * isn't closed yet, we let release take care of it. */ - mutex_lock(&bdev->bd_mutex); + mutex_lock(&disk->open_mutex); info = disk->private_data; dev_warn(disk_to_dev(disk), @@ -2546,7 +2528,7 @@ static int blkfront_remove(struct xenbus_device *xbdev) mutex_unlock(&blkfront_mutex); } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&disk->open_mutex); bdput(bdev); return 0; diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index c1d20818e649..a8968d9e759b 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -323,27 +323,20 @@ static const struct blk_mq_ops z2_mq_ops = { static int z2ram_register_disk(int minor) { - struct request_queue *q; struct gendisk *disk; - disk = alloc_disk(1); - if (!disk) - return -ENOMEM; - - q = blk_mq_init_queue(&tag_set); - if (IS_ERR(q)) { - put_disk(disk); - return PTR_ERR(q); - } + disk = blk_mq_alloc_disk(&tag_set, NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); disk->major = Z2RAM_MAJOR; disk->first_minor = minor; + disk->minors = 1; disk->fops = &z2_fops; if (minor) sprintf(disk->disk_name, "z2ram%d", minor); else sprintf(disk->disk_name, "z2ram"); - disk->queue = q; z2ram_gendisk[minor] = disk; add_disk(disk); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index cf8deecc39ef..fcaf2750f68f 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1781,24 +1781,24 @@ static ssize_t reset_store(struct device *dev, zram = dev_to_zram(dev); bdev = zram->disk->part0; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); /* Do not reset an active device or claimed device */ if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return -EBUSY; } /* From now on, anyone can't open /dev/zram[0-9] */ zram->claim = true; - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); zram->claim = false; - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return len; } @@ -1808,7 +1808,7 @@ static int zram_open(struct block_device *bdev, fmode_t mode) int ret = 0; struct zram *zram; - WARN_ON(!mutex_is_locked(&bdev->bd_mutex)); + WARN_ON(!mutex_is_locked(&bdev->bd_disk->open_mutex)); zram = bdev->bd_disk->private_data; /* zram was claimed to reset so open request fails */ @@ -1890,7 +1890,6 @@ static const struct attribute_group *zram_disk_attr_groups[] = { static int zram_add(void) { struct zram *zram; - struct request_queue *queue; int ret, device_id; zram = kzalloc(sizeof(struct zram), GFP_KERNEL); @@ -1906,27 +1905,20 @@ static int zram_add(void) #ifdef CONFIG_ZRAM_WRITEBACK spin_lock_init(&zram->wb_limit_lock); #endif - queue = blk_alloc_queue(NUMA_NO_NODE); - if (!queue) { - pr_err("Error allocating disk queue for device %d\n", - device_id); - ret = -ENOMEM; - goto out_free_idr; - } /* gendisk structure */ - zram->disk = alloc_disk(1); + zram->disk = blk_alloc_disk(NUMA_NO_NODE); if (!zram->disk) { pr_err("Error allocating disk structure for device %d\n", device_id); ret = -ENOMEM; - goto out_free_queue; + goto out_free_idr; } zram->disk->major = zram_major; zram->disk->first_minor = device_id; + zram->disk->minors = 1; zram->disk->fops = &zram_devops; - zram->disk->queue = queue; zram->disk->private_data = zram; snprintf(zram->disk->disk_name, 16, "zram%d", device_id); @@ -1969,8 +1961,6 @@ static int zram_add(void) pr_info("Added device: %s\n", zram->disk->disk_name); return device_id; -out_free_queue: - blk_cleanup_queue(queue); out_free_idr: idr_remove(&zram_index_idr, device_id); out_free_dev: @@ -1982,14 +1972,14 @@ static int zram_remove(struct zram *zram) { struct block_device *bdev = zram->disk->part0; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return -EBUSY; } zram->claim = true; - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); zram_debugfs_unregister(zram); @@ -2000,8 +1990,7 @@ static int zram_remove(struct zram *zram) pr_info("Removed device: %s\n", zram->disk->disk_name); del_gendisk(zram->disk); - blk_cleanup_queue(zram->disk->queue); - put_disk(zram->disk); + blk_cleanup_disk(zram->disk); kfree(zram); return 0; } diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 419a7e8281ee..74c411911b6e 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -112,7 +112,7 @@ struct zram { /* * zram is claimed so open request will be failed */ - bool claim; /* Protected by bdev->bd_mutex */ + bool claim; /* Protected by disk->open_mutex */ struct file *backing_dev; #ifdef CONFIG_ZRAM_WRITEBACK spinlock_t wb_limit_lock; diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index c6d8c0f59722..8e1fe75af93f 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -772,53 +772,50 @@ static int probe_gdrom(struct platform_device *devptr) goto probe_fail_no_mem; } probe_gdrom_setupcd(); - gd.disk = alloc_disk(1); - if (!gd.disk) { - err = -ENODEV; - goto probe_fail_no_disk; + + err = blk_mq_alloc_sq_tag_set(&gd.tag_set, &gdrom_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); + if (err) + goto probe_fail_free_cd_info; + + gd.disk = blk_mq_alloc_disk(&gd.tag_set, NULL); + if (IS_ERR(gd.disk)) { + err = PTR_ERR(gd.disk); + goto probe_fail_free_tag_set; } + gd.gdrom_rq = gd.disk->queue; probe_gdrom_setupdisk(); if (register_cdrom(gd.disk, gd.cd_info)) { err = -ENODEV; - goto probe_fail_cdrom_register; + goto probe_fail_cleanup_disk; } gd.disk->fops = &gdrom_bdops; gd.disk->events = DISK_EVENT_MEDIA_CHANGE; /* latch on to the interrupt */ err = gdrom_set_interrupt_handlers(); if (err) - goto probe_fail_cmdirq_register; - - gd.gdrom_rq = blk_mq_init_sq_queue(&gd.tag_set, &gdrom_mq_ops, 1, - BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); - if (IS_ERR(gd.gdrom_rq)) { - err = PTR_ERR(gd.gdrom_rq); - gd.gdrom_rq = NULL; - goto probe_fail_requestq; - } + goto probe_fail_cleanup_disk; err = probe_gdrom_setupqueue(); if (err) - goto probe_fail_toc; + goto probe_fail_free_irqs; gd.toc = kzalloc(sizeof(struct gdromtoc), GFP_KERNEL); if (!gd.toc) { err = -ENOMEM; - goto probe_fail_toc; + goto probe_fail_free_irqs; } add_disk(gd.disk); return 0; -probe_fail_toc: - blk_cleanup_queue(gd.gdrom_rq); - blk_mq_free_tag_set(&gd.tag_set); -probe_fail_requestq: +probe_fail_free_irqs: free_irq(HW_EVENT_GDROM_DMA, &gd); free_irq(HW_EVENT_GDROM_CMD, &gd); -probe_fail_cmdirq_register: -probe_fail_cdrom_register: - del_gendisk(gd.disk); -probe_fail_no_disk: +probe_fail_cleanup_disk: + blk_cleanup_disk(gd.disk); +probe_fail_free_tag_set: + blk_mq_free_tag_set(&gd.tag_set); +probe_fail_free_cd_info: kfree(gd.cd_info); probe_fail_no_mem: unregister_blkdev(gdrom_major, GDROM_DEV_NAME); diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index 40a948c08a0b..cf8a75494833 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -305,7 +305,6 @@ static int __nvm_config_extended(struct nvm_dev *dev, static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) { struct nvm_ioctl_create_extended e; - struct request_queue *tqueue; struct gendisk *tdisk; struct nvm_tgt_type *tt; struct nvm_target *t; @@ -370,24 +369,16 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) goto err_t; } - tdisk = alloc_disk(0); + tdisk = blk_alloc_disk(dev->q->node); if (!tdisk) { ret = -ENOMEM; goto err_dev; } - tqueue = blk_alloc_queue(dev->q->node); - if (!tqueue) { - ret = -ENOMEM; - goto err_disk; - } - strlcpy(tdisk->disk_name, create->tgtname, sizeof(tdisk->disk_name)); - tdisk->flags = GENHD_FL_EXT_DEVT; tdisk->major = 0; tdisk->first_minor = 0; tdisk->fops = tt->bops; - tdisk->queue = tqueue; targetdata = tt->init(tgt_dev, tdisk, create->flags); if (IS_ERR(targetdata)) { @@ -396,14 +387,14 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) } tdisk->private_data = targetdata; - tqueue->queuedata = targetdata; + tdisk->queue->queuedata = targetdata; mdts = (dev->geo.csecs >> 9) * NVM_MAX_VLBA; if (dev->geo.mdts) { mdts = min_t(u32, dev->geo.mdts, (dev->geo.csecs >> 9) * NVM_MAX_VLBA); } - blk_queue_max_hw_sectors(tqueue, mdts); + blk_queue_max_hw_sectors(tdisk->queue, mdts); set_capacity(tdisk, tt->capacity(targetdata)); add_disk(tdisk); @@ -428,10 +419,7 @@ err_sysfs: if (tt->exit) tt->exit(targetdata, true); err_init: - blk_cleanup_queue(tqueue); - tdisk->queue = NULL; -err_disk: - put_disk(tdisk); + blk_cleanup_disk(tdisk); err_dev: nvm_remove_tgt_dev(tgt_dev, 0); err_t: @@ -445,10 +433,8 @@ static void __nvm_remove_target(struct nvm_target *t, bool graceful) { struct nvm_tgt_type *tt = t->type; struct gendisk *tdisk = t->disk; - struct request_queue *q = tdisk->queue; del_gendisk(tdisk); - blk_cleanup_queue(q); if (tt->sysfs_exit) tt->sysfs_exit(tdisk); @@ -457,7 +443,7 @@ static void __nvm_remove_target(struct nvm_target *t, bool graceful) tt->exit(tdisk->private_data, graceful); nvm_remove_tgt_dev(t->dev, 1); - put_disk(tdisk); + blk_cleanup_disk(tdisk); module_put(t->type->owner); list_del(&t->list); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index bea8c4429ae8..185246a0d855 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -890,13 +890,9 @@ static void bcache_device_free(struct bcache_device *d) if (disk_added) del_gendisk(disk); - if (disk->queue) - blk_cleanup_queue(disk->queue); - + blk_cleanup_disk(disk); ida_simple_remove(&bcache_device_idx, first_minor_to_idx(disk->first_minor)); - if (disk_added) - put_disk(disk); } bioset_exit(&d->bio_split); @@ -946,7 +942,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) goto err; - d->disk = alloc_disk(BCACHE_MINORS); + d->disk = blk_alloc_disk(NUMA_NO_NODE); if (!d->disk) goto err; @@ -955,14 +951,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk->major = bcache_major; d->disk->first_minor = idx_to_first_minor(idx); + d->disk->minors = BCACHE_MINORS; d->disk->fops = ops; d->disk->private_data = d; - q = blk_alloc_queue(NUMA_NO_NODE); - if (!q) - return -ENOMEM; - - d->disk->queue = q; + q = d->disk->queue; q->limits.max_hw_sectors = UINT_MAX; q->limits.max_sectors = UINT_MAX; q->limits.max_segment_size = UINT_MAX; diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 9c3bc3711b33..0dbd48cbdff9 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -530,7 +530,6 @@ static const struct blk_mq_ops dm_mq_ops = { int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) { - struct request_queue *q; struct dm_target *immutable_tgt; int err; @@ -557,12 +556,10 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) if (err) goto out_kfree_tag_set; - q = blk_mq_init_allocated_queue(md->tag_set, md->queue, true); - if (IS_ERR(q)) { - err = PTR_ERR(q); + err = blk_mq_init_allocated_queue(md->tag_set, md->queue); + if (err) goto out_tag_set; - } - + elevator_init_mq(md->queue); return 0; out_tag_set: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 190e714cb565..a57aba553ebb 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1801,13 +1801,13 @@ static void cleanup_mapped_device(struct mapped_device *md) md->disk->private_data = NULL; spin_unlock(&_minor_lock); del_gendisk(md->disk); - put_disk(md->disk); } - if (md->queue) { + if (md->queue) dm_queue_destroy_keyslot_manager(md->queue); - blk_cleanup_queue(md->queue); - } + + if (md->disk) + blk_cleanup_disk(md->disk); cleanup_srcu_struct(&md->io_barrier); @@ -1869,13 +1869,10 @@ static struct mapped_device *alloc_dev(int minor) * established. If request-based table is loaded: blk-mq will * override accordingly. */ - md->queue = blk_alloc_queue(numa_node_id); - if (!md->queue) - goto bad; - - md->disk = alloc_disk_node(1, md->numa_node_id); + md->disk = blk_alloc_disk(md->numa_node_id); if (!md->disk) goto bad; + md->queue = md->disk->queue; init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); @@ -1888,6 +1885,7 @@ static struct mapped_device *alloc_dev(int minor) md->disk->major = _major; md->disk->first_minor = minor; + md->disk->minors = 1; md->disk->fops = &dm_blk_dops; md->disk->queue = md->queue; md->disk->private_data = md; diff --git a/drivers/md/md.c b/drivers/md/md.c index 49f897fbb89b..d806be8cc210 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5598,12 +5598,10 @@ static void md_free(struct kobject *ko) if (mddev->sysfs_level) sysfs_put(mddev->sysfs_level); - if (mddev->gendisk) + if (mddev->gendisk) { del_gendisk(mddev->gendisk); - if (mddev->queue) - blk_cleanup_queue(mddev->queue); - if (mddev->gendisk) - put_disk(mddev->gendisk); + blk_cleanup_disk(mddev->gendisk); + } percpu_ref_exit(&mddev->writes_pending); bioset_exit(&mddev->bio_set); @@ -5711,20 +5709,13 @@ static int md_alloc(dev_t dev, char *name) goto abort; error = -ENOMEM; - mddev->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!mddev->queue) + disk = blk_alloc_disk(NUMA_NO_NODE); + if (!disk) goto abort; - blk_set_stacking_limits(&mddev->queue->limits); - - disk = alloc_disk(1 << shift); - if (!disk) { - blk_cleanup_queue(mddev->queue); - mddev->queue = NULL; - goto abort; - } disk->major = MAJOR(mddev->unit); disk->first_minor = unit << shift; + disk->minors = 1 << shift; if (name) strcpy(disk->disk_name, name); else if (partitioned) @@ -5733,7 +5724,9 @@ static int md_alloc(dev_t dev, char *name) sprintf(disk->disk_name, "md%d", unit); disk->fops = &md_fops; disk->private_data = mddev; - disk->queue = mddev->queue; + + mddev->queue = disk->queue; + blk_set_stacking_limits(&mddev->queue->limits); blk_queue_write_cache(mddev->queue, true, true); /* Allow extended partitions. This makes the * 'mdp' device redundant, but we can't really diff --git a/drivers/md/md.h b/drivers/md/md.h index fb7eab58cfd5..a88086d4110c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -395,10 +395,10 @@ struct mddev { * that we are never stopping an array while it is open. * 'reconfig_mutex' protects all other reconfiguration. * These locks are separate due to conflicting interactions - * with bdev->bd_mutex. + * with disk->open_mutex. * Lock ordering is: - * reconfig_mutex -> bd_mutex - * bd_mutex -> open_mutex: e.g. __blkdev_get -> md_open + * reconfig_mutex -> disk->open_mutex + * disk->open_mutex -> open_mutex: e.g. __blkdev_get -> md_open */ struct mutex open_mutex; struct mutex reconfig_mutex; diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index d971acd98236..4a4573fa7b0f 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -2120,21 +2120,17 @@ static int msb_init_disk(struct memstick_dev *card) if (msb->disk_id < 0) return msb->disk_id; - msb->disk = alloc_disk(0); - if (!msb->disk) { - rc = -ENOMEM; + rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &msb_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE); + if (rc) goto out_release_id; - } - msb->queue = blk_mq_init_sq_queue(&msb->tag_set, &msb_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(msb->queue)) { - rc = PTR_ERR(msb->queue); - msb->queue = NULL; - goto out_put_disk; + msb->disk = blk_mq_alloc_disk(&msb->tag_set, card); + if (IS_ERR(msb->disk)) { + rc = PTR_ERR(msb->disk); + goto out_free_tag_set; } - - msb->queue->queuedata = card; + msb->queue = msb->disk->queue; blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES); blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS); @@ -2145,8 +2141,6 @@ static int msb_init_disk(struct memstick_dev *card) sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id); msb->disk->fops = &msb_bdops; msb->disk->private_data = msb; - msb->disk->queue = msb->queue; - msb->disk->flags |= GENHD_FL_EXT_DEVT; capacity = msb->pages_in_block * msb->logical_block_count; capacity *= (msb->page_size / 512); @@ -2166,8 +2160,8 @@ static int msb_init_disk(struct memstick_dev *card) dbg("Disk added"); return 0; -out_put_disk: - put_disk(msb->disk); +out_free_tag_set: + blk_mq_free_tag_set(&msb->tag_set); out_release_id: mutex_lock(&msb_disk_lock); idr_remove(&msb_disk_idr, msb->disk_id); diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index cf7fe0d58ee7..22778d0e24f5 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1205,21 +1205,17 @@ static int mspro_block_init_disk(struct memstick_dev *card) if (disk_id < 0) return disk_id; - msb->disk = alloc_disk(1 << MSPRO_BLOCK_PART_SHIFT); - if (!msb->disk) { - rc = -ENOMEM; + rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &mspro_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE); + if (rc) goto out_release_id; - } - msb->queue = blk_mq_init_sq_queue(&msb->tag_set, &mspro_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(msb->queue)) { - rc = PTR_ERR(msb->queue); - msb->queue = NULL; - goto out_put_disk; + msb->disk = blk_mq_alloc_disk(&msb->tag_set, card); + if (IS_ERR(msb->disk)) { + rc = PTR_ERR(msb->disk); + goto out_free_tag_set; } - - msb->queue->queuedata = card; + msb->queue = msb->disk->queue; blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES); blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); @@ -1228,10 +1224,10 @@ static int mspro_block_init_disk(struct memstick_dev *card) msb->disk->major = major; msb->disk->first_minor = disk_id << MSPRO_BLOCK_PART_SHIFT; + msb->disk->minors = 1 << MSPRO_BLOCK_PART_SHIFT; msb->disk->fops = &ms_block_bdops; msb->usage_count = 1; msb->disk->private_data = msb; - msb->disk->queue = msb->queue; sprintf(msb->disk->disk_name, "mspblk%d", disk_id); @@ -1247,8 +1243,8 @@ static int mspro_block_init_disk(struct memstick_dev *card) msb->active = 1; return 0; -out_put_disk: - put_disk(msb->disk); +out_free_tag_set: + blk_mq_free_tag_set(&msb->tag_set); out_release_id: mutex_lock(&mspro_block_disk_lock); idr_remove(&mspro_block_disk_idr, disk_id); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index fb8e12d590a1..6ce4bc57f919 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -30,11 +30,9 @@ static void blktrans_dev_release(struct kref *kref) struct mtd_blktrans_dev *dev = container_of(kref, struct mtd_blktrans_dev, ref); - dev->disk->private_data = NULL; - blk_cleanup_queue(dev->rq); + blk_cleanup_disk(dev->disk); blk_mq_free_tag_set(dev->tag_set); kfree(dev->tag_set); - put_disk(dev->disk); list_del(&dev->list); kfree(dev); } @@ -354,7 +352,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) if (new->devnum > (MINORMASK >> tr->part_bits) || (tr->part_bits && new->devnum >= 27 * 26)) { mutex_unlock(&blktrans_ref_mutex); - goto error1; + return ret; } list_add_tail(&new->list, &tr->devs); @@ -366,17 +364,29 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) if (!tr->writesect) new->readonly = 1; - /* Create gendisk */ ret = -ENOMEM; - gd = alloc_disk(1 << tr->part_bits); + new->tag_set = kzalloc(sizeof(*new->tag_set), GFP_KERNEL); + if (!new->tag_set) + goto out_list_del; - if (!gd) - goto error2; + ret = blk_mq_alloc_sq_tag_set(new->tag_set, &mtd_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); + if (ret) + goto out_kfree_tag_set; + + /* Create gendisk */ + gd = blk_mq_alloc_disk(new->tag_set, new); + if (IS_ERR(gd)) { + ret = PTR_ERR(gd); + goto out_free_tag_set; + } new->disk = gd; + new->rq = new->disk->queue; gd->private_data = new; gd->major = tr->major; gd->first_minor = (new->devnum) << tr->part_bits; + gd->minors = 1 << tr->part_bits; gd->fops = &mtd_block_ops; if (tr->part_bits) @@ -398,22 +408,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) spin_lock_init(&new->queue_lock); INIT_LIST_HEAD(&new->rq_list); - new->tag_set = kzalloc(sizeof(*new->tag_set), GFP_KERNEL); - if (!new->tag_set) - goto error3; - - new->rq = blk_mq_init_sq_queue(new->tag_set, &mtd_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); - if (IS_ERR(new->rq)) { - ret = PTR_ERR(new->rq); - new->rq = NULL; - goto error4; - } - if (tr->flush) blk_queue_write_cache(new->rq, true, false); - new->rq->queuedata = new; blk_queue_logical_block_size(new->rq, tr->blksize); blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq); @@ -437,13 +434,13 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) WARN_ON(ret); } return 0; -error4: + +out_free_tag_set: + blk_mq_free_tag_set(new->tag_set); +out_kfree_tag_set: kfree(new->tag_set); -error3: - put_disk(new->disk); -error2: +out_list_del: list_del(&new->list); -error1: return ret; } diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index e1a2ae21dfd3..e003b4b44ffa 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -394,53 +394,46 @@ int ubiblock_create(struct ubi_volume_info *vi) dev->vol_id = vi->vol_id; dev->leb_size = vi->usable_leb_size; + dev->tag_set.ops = &ubiblock_mq_ops; + dev->tag_set.queue_depth = 64; + dev->tag_set.numa_node = NUMA_NO_NODE; + dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + dev->tag_set.cmd_size = sizeof(struct ubiblock_pdu); + dev->tag_set.driver_data = dev; + dev->tag_set.nr_hw_queues = 1; + + ret = blk_mq_alloc_tag_set(&dev->tag_set); + if (ret) { + dev_err(disk_to_dev(dev->gd), "blk_mq_alloc_tag_set failed"); + goto out_free_dev;; + } + + /* Initialize the gendisk of this ubiblock device */ - gd = alloc_disk(1); - if (!gd) { - pr_err("UBI: block: alloc_disk failed\n"); - ret = -ENODEV; - goto out_free_dev; + gd = blk_mq_alloc_disk(&dev->tag_set, dev); + if (IS_ERR(gd)) { + ret = PTR_ERR(gd); + goto out_free_tags; } gd->fops = &ubiblock_ops; gd->major = ubiblock_major; + gd->minors = 1; gd->first_minor = idr_alloc(&ubiblock_minor_idr, dev, 0, 0, GFP_KERNEL); if (gd->first_minor < 0) { dev_err(disk_to_dev(gd), "block: dynamic minor allocation failed"); ret = -ENODEV; - goto out_put_disk; + goto out_cleanup_disk; } gd->private_data = dev; sprintf(gd->disk_name, "ubiblock%d_%d", dev->ubi_num, dev->vol_id); set_capacity(gd, disk_capacity); dev->gd = gd; - dev->tag_set.ops = &ubiblock_mq_ops; - dev->tag_set.queue_depth = 64; - dev->tag_set.numa_node = NUMA_NO_NODE; - dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - dev->tag_set.cmd_size = sizeof(struct ubiblock_pdu); - dev->tag_set.driver_data = dev; - dev->tag_set.nr_hw_queues = 1; - - ret = blk_mq_alloc_tag_set(&dev->tag_set); - if (ret) { - dev_err(disk_to_dev(dev->gd), "blk_mq_alloc_tag_set failed"); - goto out_remove_minor; - } - - dev->rq = blk_mq_init_queue(&dev->tag_set); - if (IS_ERR(dev->rq)) { - dev_err(disk_to_dev(gd), "blk_mq_init_queue failed"); - ret = PTR_ERR(dev->rq); - goto out_free_tags; - } + dev->rq = gd->queue; blk_queue_max_segments(dev->rq, UBI_MAX_SG_COUNT); - dev->rq->queuedata = dev; - dev->gd->queue = dev->rq; - /* * Create one workqueue per volume (per registered block device). * Rembember workqueues are cheap, they're not threads. @@ -448,7 +441,7 @@ int ubiblock_create(struct ubi_volume_info *vi) dev->wq = alloc_workqueue("%s", 0, 0, gd->disk_name); if (!dev->wq) { ret = -ENOMEM; - goto out_free_queue; + goto out_remove_minor; } list_add_tail(&dev->list, &ubiblock_devices); @@ -460,14 +453,12 @@ int ubiblock_create(struct ubi_volume_info *vi) mutex_unlock(&devices_mutex); return 0; -out_free_queue: - blk_cleanup_queue(dev->rq); -out_free_tags: - blk_mq_free_tag_set(&dev->tag_set); out_remove_minor: idr_remove(&ubiblock_minor_idr, gd->first_minor); -out_put_disk: - put_disk(dev->gd); +out_cleanup_disk: + blk_cleanup_disk(dev->gd); +out_free_tags: + blk_mq_free_tag_set(&dev->tag_set); out_free_dev: kfree(dev); out_unlock: @@ -483,11 +474,10 @@ static void ubiblock_cleanup(struct ubiblock *dev) /* Flush pending work */ destroy_workqueue(dev->wq); /* Finally destroy the blk queue */ - blk_cleanup_queue(dev->rq); - blk_mq_free_tag_set(&dev->tag_set); dev_info(disk_to_dev(dev->gd), "released"); + blk_cleanup_disk(dev->gd); + blk_mq_free_tag_set(&dev->tag_set); idr_remove(&ubiblock_minor_idr, dev->gd->first_minor); - put_disk(dev->gd); } int ubiblock_remove(struct ubi_volume_info *vi) diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index 7b9556291eb1..088d3dd6f6fa 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -228,49 +228,34 @@ static const struct block_device_operations nd_blk_fops = { .submit_bio = nd_blk_submit_bio, }; -static void nd_blk_release_queue(void *q) -{ - blk_cleanup_queue(q); -} - static void nd_blk_release_disk(void *disk) { del_gendisk(disk); - put_disk(disk); + blk_cleanup_disk(disk); } static int nsblk_attach_disk(struct nd_namespace_blk *nsblk) { struct device *dev = &nsblk->common.dev; resource_size_t available_disk_size; - struct request_queue *q; struct gendisk *disk; u64 internal_nlba; internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk)); available_disk_size = internal_nlba * nsblk_sector_size(nsblk); - q = blk_alloc_queue(NUMA_NO_NODE); - if (!q) - return -ENOMEM; - if (devm_add_action_or_reset(dev, nd_blk_release_queue, q)) - return -ENOMEM; - - blk_queue_max_hw_sectors(q, UINT_MAX); - blk_queue_logical_block_size(q, nsblk_sector_size(nsblk)); - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - - disk = alloc_disk(0); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) return -ENOMEM; - disk->first_minor = 0; disk->fops = &nd_blk_fops; - disk->queue = q; - disk->flags = GENHD_FL_EXT_DEVT; disk->private_data = nsblk; nvdimm_namespace_disk_name(&nsblk->common, disk->disk_name); + blk_queue_max_hw_sectors(disk->queue, UINT_MAX); + blk_queue_logical_block_size(disk->queue, nsblk_sector_size(nsblk)); + blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + if (devm_add_action_or_reset(dev, nd_blk_release_disk, disk)) return -ENOMEM; diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 18a267d5073f..92dec4952297 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1521,35 +1521,25 @@ static int btt_blk_init(struct btt *btt) struct nd_btt *nd_btt = btt->nd_btt; struct nd_namespace_common *ndns = nd_btt->ndns; - /* create a new disk and request queue for btt */ - btt->btt_queue = blk_alloc_queue(NUMA_NO_NODE); - if (!btt->btt_queue) + btt->btt_disk = blk_alloc_disk(NUMA_NO_NODE); + if (!btt->btt_disk) return -ENOMEM; - btt->btt_disk = alloc_disk(0); - if (!btt->btt_disk) { - blk_cleanup_queue(btt->btt_queue); - return -ENOMEM; - } - nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name); btt->btt_disk->first_minor = 0; btt->btt_disk->fops = &btt_fops; btt->btt_disk->private_data = btt; - btt->btt_disk->queue = btt->btt_queue; - btt->btt_disk->flags = GENHD_FL_EXT_DEVT; - blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); - blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX); - blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_queue); + blk_queue_logical_block_size(btt->btt_disk->queue, btt->sector_size); + blk_queue_max_hw_sectors(btt->btt_disk->queue, UINT_MAX); + blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue); if (btt_meta_size(btt)) { int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt)); if (rc) { del_gendisk(btt->btt_disk); - put_disk(btt->btt_disk); - blk_cleanup_queue(btt->btt_queue); + blk_cleanup_disk(btt->btt_disk); return rc; } } @@ -1564,8 +1554,7 @@ static int btt_blk_init(struct btt *btt) static void btt_blk_cleanup(struct btt *btt) { del_gendisk(btt->btt_disk); - put_disk(btt->btt_disk); - blk_cleanup_queue(btt->btt_queue); + blk_cleanup_disk(btt->btt_disk); } /** diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h index aa53e0b769bd..0c76c0333f6e 100644 --- a/drivers/nvdimm/btt.h +++ b/drivers/nvdimm/btt.h @@ -201,7 +201,6 @@ struct badblocks; /** * struct btt - handle for a BTT instance * @btt_disk: Pointer to the gendisk for BTT device - * @btt_queue: Pointer to the request queue for the BTT device * @arena_list: Head of the list of arenas * @debugfs_dir: Debugfs dentry * @nd_btt: Parent nd_btt struct @@ -219,7 +218,6 @@ struct badblocks; */ struct btt { struct gendisk *btt_disk; - struct request_queue *btt_queue; struct list_head arena_list; struct dentry *debugfs_dir; struct nd_btt *nd_btt; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index ed10a8b66068..1e0615b8565e 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -335,10 +335,9 @@ static const struct attribute_group *pmem_attribute_groups[] = { static void pmem_pagemap_cleanup(struct dev_pagemap *pgmap) { - struct request_queue *q = - container_of(pgmap->ref, struct request_queue, q_usage_counter); + struct pmem_device *pmem = pgmap->owner; - blk_cleanup_queue(q); + blk_cleanup_disk(pmem->disk); } static void pmem_release_queue(void *pgmap) @@ -361,7 +360,6 @@ static void pmem_release_disk(void *__pmem) kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); del_gendisk(pmem->disk); - put_disk(pmem->disk); } static const struct dev_pagemap_ops fsdax_pagemap_ops = { @@ -422,10 +420,13 @@ static int pmem_attach_disk(struct device *dev, return -EBUSY; } - q = blk_alloc_queue(dev_to_node(dev)); - if (!q) + disk = blk_alloc_disk(nid); + if (!disk) return -ENOMEM; + q = disk->queue; + pmem->disk = disk; + pmem->pgmap.owner = pmem; pmem->pfn_flags = PFN_DEV; pmem->pgmap.ref = &q->q_usage_counter; if (is_nd_pfn(dev)) { @@ -470,14 +471,7 @@ static int pmem_attach_disk(struct device *dev, if (pmem->pfn_flags & PFN_MAP) blk_queue_flag_set(QUEUE_FLAG_DAX, q); - disk = alloc_disk_node(0, nid); - if (!disk) - return -ENOMEM; - pmem->disk = disk; - disk->fops = &pmem_fops; - disk->queue = q; - disk->flags = GENHD_FL_EXT_DEVT; disk->private_data = pmem; nvdimm_namespace_disk_name(ndns, disk->disk_name); set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) @@ -491,7 +485,6 @@ static int pmem_attach_disk(struct device *dev, flags = DAXDEV_F_SYNC; dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags); if (IS_ERR(dax_dev)) { - put_disk(disk); return PTR_ERR(dax_dev); } dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 66973bb56305..01889a8abb6b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3701,7 +3701,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, disk->fops = &nvme_bdev_ops; disk->private_data = ns; disk->queue = ns->queue; - disk->flags = GENHD_FL_EXT_DEVT; /* * Without the multipath code enabled, multiple controller per * subsystems are visible as devices and thus we cannot use the diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index f81871c7128a..b5fbdb416022 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -427,7 +427,6 @@ static void nvme_requeue_work(struct work_struct *work) int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) { - struct request_queue *q; bool vwc = false; mutex_init(&head->lock); @@ -443,34 +442,24 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath) return 0; - q = blk_alloc_queue(ctrl->numa_node); - if (!q) - goto out; - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - /* set to a default value for 512 until disk is validated */ - blk_queue_logical_block_size(q, 512); - blk_set_stacking_limits(&q->limits); - - /* we need to propagate up the VMC settings */ - if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) - vwc = true; - blk_queue_write_cache(q, vwc, vwc); - - head->disk = alloc_disk(0); + head->disk = blk_alloc_disk(ctrl->numa_node); if (!head->disk) - goto out_cleanup_queue; + return -ENOMEM; head->disk->fops = &nvme_ns_head_ops; head->disk->private_data = head; - head->disk->queue = q; - head->disk->flags = GENHD_FL_EXT_DEVT; sprintf(head->disk->disk_name, "nvme%dn%d", ctrl->subsys->instance, head->instance); - return 0; -out_cleanup_queue: - blk_cleanup_queue(q); -out: - return -ENOMEM; + blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue); + /* set to a default value of 512 until the disk is validated */ + blk_queue_logical_block_size(head->disk->queue, 512); + blk_set_stacking_limits(&head->disk->queue->limits); + + /* we need to propagate up the VMC settings */ + if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) + vwc = true; + blk_queue_write_cache(head->disk->queue, vwc, vwc); + return 0; } static void nvme_mpath_set_live(struct nvme_ns *ns) @@ -769,16 +758,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); - blk_cleanup_queue(head->disk->queue); - if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { - /* - * if device_add_disk wasn't called, prevent - * disk release to put a bogus reference on the - * request queue - */ - head->disk->queue = NULL; - } - put_disk(head->disk); + blk_cleanup_disk(head->disk); } void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl) diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 8d6587ec73e2..493e8469893c 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -109,9 +109,9 @@ int dasd_scan_partitions(struct dasd_block *block) return -ENODEV; } - mutex_lock(&bdev->bd_mutex); - rc = bdev_disk_changed(bdev, false); - mutex_unlock(&bdev->bd_mutex); + mutex_lock(&block->gdp->open_mutex); + rc = bdev_disk_changed(block->gdp, false); + mutex_unlock(&block->gdp->open_mutex); if (rc) DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, rc %d", rc); @@ -145,9 +145,9 @@ void dasd_destroy_partitions(struct dasd_block *block) bdev = block->bdev; block->bdev = NULL; - mutex_lock(&bdev->bd_mutex); - bdev_disk_changed(bdev, true); - mutex_unlock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); + bdev_disk_changed(bdev->bd_disk, true); + mutex_unlock(&bdev->bd_disk->open_mutex); /* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */ blkdev_put(bdev, FMODE_READ); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index da33cb4cba28..7faa56399999 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -90,7 +90,6 @@ struct dcssblk_dev_info { int segment_type; unsigned char save_pending; unsigned char is_shared; - struct request_queue *dcssblk_queue; int num_of_segments; struct list_head seg_list; struct dax_device *dax_dev; @@ -429,9 +428,7 @@ removeseg: kill_dax(dev_info->dax_dev); put_dax(dev_info->dax_dev); del_gendisk(dev_info->gd); - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); up_write(&dcssblk_devices_sem); if (device_remove_file_self(dev, attr)) { @@ -644,18 +641,17 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char dev_info->dev.release = dcssblk_release_segment; dev_info->dev.groups = dcssblk_dev_attr_groups; INIT_LIST_HEAD(&dev_info->lh); - dev_info->gd = alloc_disk(DCSSBLK_MINORS_PER_DISK); + dev_info->gd = blk_alloc_disk(NUMA_NO_NODE); if (dev_info->gd == NULL) { rc = -ENOMEM; goto seg_list_del; } dev_info->gd->major = dcssblk_major; + dev_info->gd->minors = DCSSBLK_MINORS_PER_DISK; dev_info->gd->fops = &dcssblk_devops; - dev_info->dcssblk_queue = blk_alloc_queue(NUMA_NO_NODE); - dev_info->gd->queue = dev_info->dcssblk_queue; dev_info->gd->private_data = dev_info; - blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096); - blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->dcssblk_queue); + blk_queue_logical_block_size(dev_info->gd->queue, 4096); + blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->gd->queue); seg_byte_size = (dev_info->end - dev_info->start + 1); set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors @@ -719,9 +715,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char put_dev: list_del(&dev_info->lh); - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); list_for_each_entry(seg_info, &dev_info->seg_list, lh) { segment_unload(seg_info->segment_name); } @@ -731,9 +725,7 @@ put_dev: dev_list_del: list_del(&dev_info->lh); release_gd: - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); up_write(&dcssblk_devices_sem); seg_list_del: if (dev_info == NULL) @@ -801,9 +793,7 @@ dcssblk_remove_store(struct device *dev, struct device_attribute *attr, const ch kill_dax(dev_info->dax_dev); put_dax(dev_info->dax_dev); del_gendisk(dev_info->gd); - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); /* unload all related segments */ list_for_each_entry(entry, &dev_info->seg_list, lh) diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index a4f6f2e62b1d..88cba6212ee2 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -462,12 +462,12 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) if (ret) goto out; - rq = blk_mq_init_queue(&bdev->tag_set); - if (IS_ERR(rq)) { - ret = PTR_ERR(rq); + bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, scmdev); + if (IS_ERR(bdev->gendisk)) { + ret = PTR_ERR(bdev->gendisk); goto out_tag; } - bdev->rq = rq; + rq = bdev->rq = bdev->gendisk->queue; nr_max_blk = min(scmdev->nr_max_block, (unsigned int) (PAGE_SIZE / sizeof(struct aidaw))); @@ -477,17 +477,11 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) blk_queue_flag_set(QUEUE_FLAG_NONROT, rq); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, rq); - bdev->gendisk = alloc_disk(SCM_NR_PARTS); - if (!bdev->gendisk) { - ret = -ENOMEM; - goto out_queue; - } - rq->queuedata = scmdev; bdev->gendisk->private_data = scmdev; bdev->gendisk->fops = &scm_blk_devops; - bdev->gendisk->queue = rq; bdev->gendisk->major = scm_major; bdev->gendisk->first_minor = devindex * SCM_NR_PARTS; + bdev->gendisk->minors = SCM_NR_PARTS; len = snprintf(bdev->gendisk->disk_name, DISK_NAME_LEN, "scm"); if (devindex > 25) { @@ -504,8 +498,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) device_add_disk(&scmdev->dev, bdev->gendisk, NULL); return 0; -out_queue: - blk_cleanup_queue(rq); out_tag: blk_mq_free_tag_set(&bdev->tag_set); out: @@ -516,9 +508,8 @@ out: void scm_blk_dev_cleanup(struct scm_blk_dev *bdev) { del_gendisk(bdev->gendisk); - blk_cleanup_queue(bdev->gendisk->queue); + blk_cleanup_disk(bdev->gendisk); blk_mq_free_tag_set(&bdev->tag_set); - put_disk(bdev->gendisk); } void scm_blk_set_available(struct scm_blk_dev *bdev) diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c index d1ed39162943..91ef710edfd2 100644 --- a/drivers/s390/block/xpram.c +++ b/drivers/s390/block/xpram.c @@ -56,7 +56,6 @@ typedef struct { static xpram_device_t xpram_devices[XPRAM_MAX_DEVS]; static unsigned int xpram_sizes[XPRAM_MAX_DEVS]; static struct gendisk *xpram_disks[XPRAM_MAX_DEVS]; -static struct request_queue *xpram_queues[XPRAM_MAX_DEVS]; static unsigned int xpram_pages; static int xpram_devs; @@ -341,17 +340,13 @@ static int __init xpram_setup_blkdev(void) int i, rc = -ENOMEM; for (i = 0; i < xpram_devs; i++) { - xpram_disks[i] = alloc_disk(1); + xpram_disks[i] = blk_alloc_disk(NUMA_NO_NODE); if (!xpram_disks[i]) goto out; - xpram_queues[i] = blk_alloc_queue(NUMA_NO_NODE); - if (!xpram_queues[i]) { - put_disk(xpram_disks[i]); - goto out; - } - blk_queue_flag_set(QUEUE_FLAG_NONROT, xpram_queues[i]); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, xpram_queues[i]); - blk_queue_logical_block_size(xpram_queues[i], 4096); + blk_queue_flag_set(QUEUE_FLAG_NONROT, xpram_disks[i]->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, + xpram_disks[i]->queue); + blk_queue_logical_block_size(xpram_disks[i]->queue, 4096); } /* @@ -373,9 +368,9 @@ static int __init xpram_setup_blkdev(void) offset += xpram_devices[i].size; disk->major = XPRAM_MAJOR; disk->first_minor = i; + disk->minors = 1; disk->fops = &xpram_devops; disk->private_data = &xpram_devices[i]; - disk->queue = xpram_queues[i]; sprintf(disk->disk_name, "slram%d", i); set_capacity(disk, xpram_sizes[i] << 1); add_disk(disk); @@ -383,10 +378,8 @@ static int __init xpram_setup_blkdev(void) return 0; out: - while (i--) { - blk_cleanup_queue(xpram_queues[i]); - put_disk(xpram_disks[i]); - } + while (i--) + blk_cleanup_disk(xpram_disks[i]); return rc; } @@ -434,8 +427,7 @@ static void __exit xpram_exit(void) int i; for (i = 0; i < xpram_devs; i++) { del_gendisk(xpram_disks[i]); - blk_cleanup_queue(xpram_queues[i]); - put_disk(xpram_disks[i]); + blk_cleanup_disk(xpram_disks[i]); } unregister_blkdev(XPRAM_MAJOR, XPRAM_NAME); platform_device_unregister(xpram_pdev); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a2c3d9ad9ee4..746a7def2825 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1416,7 +1416,7 @@ static bool sd_need_revalidate(struct block_device *bdev, * In the latter case @inode and @filp carry an abridged amount * of information as noted above. * - * Locking: called with bdev->bd_mutex held. + * Locking: called with bdev->bd_disk->open_mutex held. **/ static int sd_open(struct block_device *bdev, fmode_t mode) { @@ -1490,7 +1490,7 @@ error_out: * Note: may block (uninterruptible) if error recovery is underway * on this disk. * - * Locking: called with bdev->bd_mutex held. + * Locking: called with bdev->bd_disk->open_mutex held. **/ static void sd_release(struct gendisk *disk, fmode_t mode) { diff --git a/fs/block_dev.c b/fs/block_dev.c index eb34f5c357cf..ca8bf1869ca8 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -895,7 +895,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) mapping_set_gfp_mask(&inode->i_data, GFP_USER); bdev = I_BDEV(inode); - mutex_init(&bdev->bd_mutex); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); bdev->bd_disk = disk; @@ -1154,7 +1153,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) struct bd_holder_disk *holder; int ret = 0; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); WARN_ON_ONCE(!bdev->bd_holder); @@ -1199,7 +1198,7 @@ out_del: out_free: kfree(holder); out_unlock: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return ret; } EXPORT_SYMBOL_GPL(bd_link_disk_holder); @@ -1218,7 +1217,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { struct bd_holder_disk *holder; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); holder = bd_find_holder_disk(bdev, disk); @@ -1230,138 +1229,97 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) kfree(holder); } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); } EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); #endif -static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); +static void blkdev_flush_mapping(struct block_device *bdev) +{ + WARN_ON_ONCE(bdev->bd_holders); + sync_blockdev(bdev); + kill_bdev(bdev); + bdev_write_inode(bdev); +} -int bdev_disk_changed(struct block_device *bdev, bool invalidate) +static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) { struct gendisk *disk = bdev->bd_disk; int ret = 0; - lockdep_assert_held(&bdev->bd_mutex); - - if (!(disk->flags & GENHD_FL_UP)) - return -ENXIO; - -rescan: - if (bdev->bd_part_count) - return -EBUSY; - sync_blockdev(bdev); - invalidate_bdev(bdev); - blk_drop_partitions(disk); - - clear_bit(GD_NEED_PART_SCAN, &disk->state); - - /* - * Historically we only set the capacity to zero for devices that - * support partitions (independ of actually having partitions created). - * Doing that is rather inconsistent, but changing it broke legacy - * udisks polling for legacy ide-cdrom devices. Use the crude check - * below to get the sane behavior for most device while not breaking - * userspace for this particular setup. - */ - if (invalidate) { - if (disk_part_scan_enabled(disk) || - !(disk->flags & GENHD_FL_REMOVABLE)) - set_capacity(disk, 0); + if (disk->fops->open) { + ret = disk->fops->open(bdev, mode); + if (ret) { + /* avoid ghost partitions on a removed medium */ + if (ret == -ENOMEDIUM && + test_bit(GD_NEED_PART_SCAN, &disk->state)) + bdev_disk_changed(disk, true); + return ret; + } } - if (get_capacity(disk)) { - ret = blk_add_partitions(disk, bdev); - if (ret == -EAGAIN) - goto rescan; - } else if (invalidate) { - /* - * Tell userspace that the media / partition table may have - * changed. - */ - kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); + if (!bdev->bd_openers) { + set_init_blocksize(bdev); + if (bdev->bd_bdi == &noop_backing_dev_info) + bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); } + if (test_bit(GD_NEED_PART_SCAN, &disk->state)) + bdev_disk_changed(disk, false); + bdev->bd_openers++; + return 0;; +} - return ret; +static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) +{ + if (!--bdev->bd_openers) + blkdev_flush_mapping(bdev); + if (bdev->bd_disk->fops->release) + bdev->bd_disk->fops->release(bdev->bd_disk, mode); } -/* - * Only exported for loop and dasd for historic reasons. Don't use in new - * code! - */ -EXPORT_SYMBOL_GPL(bdev_disk_changed); -/* - * bd_mutex locking: - * - * mutex_lock(part->bd_mutex) - * mutex_lock_nested(whole->bd_mutex, 1) - */ -static int __blkdev_get(struct block_device *bdev, fmode_t mode) +static int blkdev_get_part(struct block_device *part, fmode_t mode) { - struct gendisk *disk = bdev->bd_disk; - int ret = 0; + struct gendisk *disk = part->bd_disk; + struct block_device *whole; + int ret; - if (!(disk->flags & GENHD_FL_UP)) - return -ENXIO; + if (part->bd_openers) + goto done; - if (!bdev->bd_openers) { - if (!bdev_is_partition(bdev)) { - ret = 0; - if (disk->fops->open) - ret = disk->fops->open(bdev, mode); + whole = bdgrab(disk->part0); + ret = blkdev_get_whole(whole, mode); + if (ret) + goto out_put_whole; - if (!ret) - set_init_blocksize(bdev); + ret = -ENXIO; + if (!bdev_nr_sectors(part)) + goto out_blkdev_put; - /* - * If the device is invalidated, rescan partition - * if open succeeded or failed with -ENOMEDIUM. - * The latter is necessary to prevent ghost - * partitions on a removed medium. - */ - if (test_bit(GD_NEED_PART_SCAN, &disk->state) && - (!ret || ret == -ENOMEDIUM)) - bdev_disk_changed(bdev, ret == -ENOMEDIUM); + disk->open_partitions++; + set_init_blocksize(part); + if (part->bd_bdi == &noop_backing_dev_info) + part->bd_bdi = bdi_get(disk->queue->backing_dev_info); +done: + part->bd_openers++; + return 0; - if (ret) - return ret; - } else { - struct block_device *whole = bdgrab(disk->part0); - - mutex_lock_nested(&whole->bd_mutex, 1); - ret = __blkdev_get(whole, mode); - if (ret) { - mutex_unlock(&whole->bd_mutex); - bdput(whole); - return ret; - } - whole->bd_part_count++; - mutex_unlock(&whole->bd_mutex); +out_blkdev_put: + blkdev_put_whole(whole, mode); +out_put_whole: + bdput(whole); + return ret; +} - if (!bdev_nr_sectors(bdev)) { - __blkdev_put(whole, mode, 1); - bdput(whole); - return -ENXIO; - } - set_init_blocksize(bdev); - } +static void blkdev_put_part(struct block_device *part, fmode_t mode) +{ + struct block_device *whole = bdev_whole(part); - if (bdev->bd_bdi == &noop_backing_dev_info) - bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); - } else { - if (!bdev_is_partition(bdev)) { - if (bdev->bd_disk->fops->open) - ret = bdev->bd_disk->fops->open(bdev, mode); - /* the same as first opener case, read comment there */ - if (test_bit(GD_NEED_PART_SCAN, &disk->state) && - (!ret || ret == -ENOMEDIUM)) - bdev_disk_changed(bdev, ret == -ENOMEDIUM); - if (ret) - return ret; - } - } - bdev->bd_openers++; - return 0; + if (--part->bd_openers) + return; + blkdev_flush_mapping(part); + whole->bd_disk->open_partitions--; + blkdev_put_whole(whole, mode); + bdput(whole); } struct block_device *blkdev_get_no_open(dev_t dev) @@ -1447,8 +1405,14 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) disk_block_events(disk); - mutex_lock(&bdev->bd_mutex); - ret =__blkdev_get(bdev, mode); + mutex_lock(&disk->open_mutex); + ret = -ENXIO; + if (!(disk->flags & GENHD_FL_UP)) + goto abort_claiming; + if (bdev_is_partition(bdev)) + ret = blkdev_get_part(bdev, mode); + else + ret = blkdev_get_whole(bdev, mode); if (ret) goto abort_claiming; if (mode & FMODE_EXCL) { @@ -1467,7 +1431,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) unblock_events = false; } } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&disk->open_mutex); if (unblock_events) disk_unblock_events(disk); @@ -1476,7 +1440,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) abort_claiming: if (mode & FMODE_EXCL) bd_abort_claiming(bdev, holder); - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&disk->open_mutex); disk_unblock_events(disk); put_blkdev: blkdev_put_no_open(bdev); @@ -1551,10 +1515,9 @@ static int blkdev_open(struct inode * inode, struct file * filp) return 0; } -static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) +void blkdev_put(struct block_device *bdev, fmode_t mode) { struct gendisk *disk = bdev->bd_disk; - struct block_device *victim = NULL; /* * Sync early if it looks like we're the last one. If someone else @@ -1566,41 +1529,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) if (bdev->bd_openers == 1) sync_blockdev(bdev); - mutex_lock_nested(&bdev->bd_mutex, for_part); - if (for_part) - bdev->bd_part_count--; - - if (!--bdev->bd_openers) { - WARN_ON_ONCE(bdev->bd_holders); - sync_blockdev(bdev); - kill_bdev(bdev); - bdev_write_inode(bdev); - if (bdev_is_partition(bdev)) - victim = bdev_whole(bdev); - } - - if (!bdev_is_partition(bdev) && disk->fops->release) - disk->fops->release(disk, mode); - mutex_unlock(&bdev->bd_mutex); - if (victim) { - __blkdev_put(victim, mode, 1); - bdput(victim); - } -} - -void blkdev_put(struct block_device *bdev, fmode_t mode) -{ - struct gendisk *disk = bdev->bd_disk; - - mutex_lock(&bdev->bd_mutex); - + mutex_lock(&disk->open_mutex); if (mode & FMODE_EXCL) { struct block_device *whole = bdev_whole(bdev); bool bdev_free; /* * Release a claim on the device. The holder fields - * are protected with bdev_lock. bd_mutex is to + * are protected with bdev_lock. open_mutex is to * synchronize disk_holder unlinking. */ spin_lock(&bdev_lock); @@ -1631,9 +1567,13 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) * from userland - e.g. eject(1). */ disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE); - mutex_unlock(&bdev->bd_mutex); - __blkdev_put(bdev, mode, 0); + if (bdev_is_partition(bdev)) + blkdev_put_part(bdev, mode); + else + blkdev_put_whole(bdev, mode); + mutex_unlock(&disk->open_mutex); + blkdev_put_no_open(bdev); } EXPORT_SYMBOL(blkdev_put); @@ -1941,10 +1881,10 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) old_inode = inode; bdev = I_BDEV(inode); - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (bdev->bd_openers) func(bdev, arg); - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); spin_lock(&blockdev_superblock->s_inode_list_lock); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 782e16795bc4..807502cd6510 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1247,7 +1247,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, lockdep_assert_held(&uuid_mutex); /* * The device_list_mutex cannot be taken here in case opening the - * underlying device takes further locks like bd_mutex. + * underlying device takes further locks like open_mutex. * * We also don't need the lock here as this is called during mount and * exclusion is provided by uuid_mutex diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 62193106683d..8c7e9e51a398 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2343,28 +2343,6 @@ int dirtytime_interval_handler(struct ctl_table *table, int write, return ret; } -static noinline void block_dump___mark_inode_dirty(struct inode *inode) -{ - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { - struct dentry *dentry; - const char *name = "?"; - - dentry = d_find_alias(inode); - if (dentry) { - spin_lock(&dentry->d_lock); - name = (const char *) dentry->d_name.name; - } - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - if (dentry) { - spin_unlock(&dentry->d_lock); - dput(dentry); - } - } -} - /** * __mark_inode_dirty - internal function to mark an inode dirty * @@ -2434,9 +2412,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; - if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); - spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; diff --git a/fs/super.c b/fs/super.c index 11b7e7213fd1..91b7f156735b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1277,9 +1277,9 @@ int get_tree_bdev(struct fs_context *fc, } /* - * s_umount nests inside bd_mutex during + * s_umount nests inside open_mutex during * __invalidate_device(). blkdev_put() acquires - * bd_mutex and can't be called under s_umount. Drop + * open_mutex and can't be called under s_umount. Drop * s_umount temporarily. This is safe as we're * holding an active reference. */ @@ -1352,9 +1352,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, } /* - * s_umount nests inside bd_mutex during + * s_umount nests inside open_mutex during * __invalidate_device(). blkdev_put() acquires - * bd_mutex and can't be called under s_umount. Drop + * open_mutex and can't be called under s_umount. Drop * s_umount temporarily. This is safe as we're * holding an active reference. */ diff --git a/include/linux/bio.h b/include/linux/bio.h index a0b4cfdf62a4..d2b98efb5cc5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -44,9 +44,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) -#define bio_multiple_segments(bio) \ - ((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len) - #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) @@ -271,7 +268,7 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { - *bv = bio_iovec(bio); + *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) @@ -279,10 +276,9 @@ static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) struct bvec_iter iter = bio->bi_iter; int idx; - if (unlikely(!bio_multiple_segments(bio))) { - *bv = bio_iovec(bio); - return; - } + bio_get_first_bvec(bio, bv); + if (bv->bv_len == bio->bi_iter.bi_size) + return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 359486940fa0..fd2de2b422ed 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -426,19 +426,29 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define blk_mq_alloc_disk(set, queuedata) \ +({ \ + static struct lock_class_key __key; \ + struct gendisk *__disk = __blk_mq_alloc_disk(set, queuedata); \ + \ + if (!IS_ERR(__disk)) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, + void *queuedata); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata); -struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, - struct request_queue *q, - bool elevator_init); -struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, - const struct blk_mq_ops *ops, - unsigned int queue_depth, - unsigned int set_flags); +int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, + struct request_queue *q); void blk_mq_unregister_dev(struct device *, struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); +int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int queue_depth, + unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index db026b6ec15a..fd3860d18d7e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -29,7 +29,6 @@ struct block_device { int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ void * bd_claiming; struct device bd_device; void * bd_holder; @@ -40,9 +39,6 @@ struct block_device { #endif struct kobject *bd_holder_dir; u8 bd_partno; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f69c75bd6d27..d66d0da72529 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include <linux/scatterlist.h> #include <linux/blkzoned.h> #include <linux/pm.h> +#include <linux/sbitmap.h> struct module; struct scsi_ioctl_command; @@ -493,6 +494,9 @@ struct request_queue { atomic_t nr_active_requests_shared_sbitmap; + struct sbitmap_queue sched_bitmap_tags; + struct sbitmap_queue sched_breserved_tags; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); @@ -1209,7 +1213,6 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); -struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index dcb2f9022c1d..ef9ceead3db1 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -117,9 +117,11 @@ extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, enum elv_merge); -extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); +extern bool elv_attempt_insert_merge(struct request_queue *, struct request *, + struct list_head *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); +void elevator_init_mq(struct request_queue *q); /* * io scheduler registration diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fc26f7bdf71..13b34177cc85 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -153,6 +153,11 @@ struct gendisk { unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 +#define GD_QUEUE_REF 2 + + struct mutex open_mutex; /* open/close mutex */ + unsigned open_partitions; /* number of open partitions */ + struct kobject *slave_dir; struct timer_rand_state *random; @@ -218,7 +223,6 @@ static inline void add_disk_no_queue_reg(struct gendisk *disk) } extern void del_gendisk(struct gendisk *gp); -extern struct block_device *bdget_disk(struct gendisk *disk, int partno); void set_disk_ro(struct gendisk *disk, bool read_only); @@ -252,8 +256,7 @@ static inline sector_t get_capacity(struct gendisk *disk) return bdev_nr_sectors(disk->part0); } -int bdev_disk_changed(struct block_device *bdev, bool invalidate); -int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); +int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); extern struct gendisk *__alloc_disk_node(int minors, int node_id); @@ -277,6 +280,28 @@ extern void put_disk(struct gendisk *disk); #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +/** + * blk_alloc_disk - allocate a gendisk structure + * @node_id: numa node to allocate on + * + * Allocate and pre-initialize a gendisk structure for use with BIO based + * drivers. + * + * Context: can sleep + */ +#define blk_alloc_disk(node_id) \ +({ \ + struct gendisk *__disk = __blk_alloc_disk(node_id); \ + static struct lock_class_key __key; \ + \ + if (__disk) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_alloc_disk(int node); +void blk_cleanup_disk(struct gendisk *disk); + int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)); #define register_blkdev(major, name) \ @@ -306,6 +331,7 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ +dev_t part_devt(struct gendisk *disk, u8 partno); dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK diff --git a/include/linux/wait.h b/include/linux/wait.h index fe10e8570a52..6598ae35e1b5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1136,7 +1136,7 @@ do { \ * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); -void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 95de51c10248..667e86cfbdcf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -361,7 +361,6 @@ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; -extern int block_dump; extern int laptop_mode; int dirty_background_ratio_handler(struct ctl_table *table, int write, diff --git a/init/do_mounts.c b/init/do_mounts.c index a78e44ee6adb..74aede860de7 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -133,14 +133,8 @@ static dev_t devt_from_partuuid(const char *uuid_str) * Attempt to find the requested partition by adding an offset * to the partition number found by UUID. */ - struct block_device *part; - - part = bdget_disk(dev_to_disk(dev), - dev_to_bdev(dev)->bd_partno + offset); - if (part) { - devt = part->bd_dev; - bdput(part); - } + devt = part_devt(dev_to_disk(dev), + dev_to_bdev(dev)->bd_partno + offset); } else { devt = dev->devt; } diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 183cc6ae68a6..76577d1642a5 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -264,17 +264,22 @@ prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_ent } EXPORT_SYMBOL(prepare_to_wait); -void +/* Returns true if we are the first waiter in the queue, false otherwise. */ +bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; + bool was_empty = false; wq_entry->flags |= WQ_FLAG_EXCLUSIVE; spin_lock_irqsave(&wq_head->lock, flags); - if (list_empty(&wq_entry->entry)) + if (list_empty(&wq_entry->entry)) { + was_empty = list_empty(&wq_head->head); __add_wait_queue_entry_tail(wq_head, wq_entry); + } set_current_state(state); spin_unlock_irqrestore(&wq_head->lock, flags); + return was_empty; } EXPORT_SYMBOL(prepare_to_wait_exclusive); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index bade84290e24..e1aa24e1545c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2963,14 +2963,6 @@ static struct ctl_table vm_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .procname = "block_dump", - .data = &block_dump, - .maxlen = sizeof(block_dump), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e5b38ffe9fca..9f63548f247c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -108,11 +108,6 @@ EXPORT_SYMBOL_GPL(dirty_writeback_interval); unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* - * Flag that makes the machine dump writes/reads and block dirtyings. - */ -int block_dump; - -/* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ |