From 196cfe2ae8fcdc03b3c7d627e7dfe8c0ce7229f9 Mon Sep 17 00:00:00 2001 From: Stefan Bader Date: Thu, 14 Jul 2011 15:30:22 +0200 Subject: xen-blkfront: Drop name and minor adjustments for emulated scsi devices These were intended to avoid the namespace clash when representing emulated IDE and SCSI devices. However that seems to confuse users more than expected (a disk defined as sda becomes xvde). So for now go back to the scheme which does no adjustments. This will break when mixing IDE and SCSI names in the configuration of guests but should be by now expected. Acked-by: Stefano Stabellini Signed-off-by: Stefan Bader Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkfront.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index b536a9cef917..238b9419c6d3 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -123,8 +123,8 @@ static DEFINE_SPINLOCK(minor_lock); #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED)) #define EMULATED_HD_DISK_MINOR_OFFSET (0) #define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256) -#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16)) -#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4) +#define EMULATED_SD_DISK_MINOR_OFFSET (0) +#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_SD_DISK_MINOR_OFFSET / 256) #define DEV_NAME "xvd" /* name in /dev */ -- cgit v1.2.3 From 89153b5cae9f40c224a5d321665a97bf14220c2c Mon Sep 17 00:00:00 2001 From: Stefan Bader Date: Thu, 14 Jul 2011 15:30:37 +0200 Subject: xen-blkfront: Fix one off warning about name clash Avoid telling users to use xvde and onwards when using xvde. Acked-by: Stefano Stabellini Signed-off-by: Stefan Bader Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkfront.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/block') diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 238b9419c6d3..9ea8c2576c70 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -529,7 +529,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, minor = BLKIF_MINOR_EXT(info->vdevice); nr_parts = PARTS_PER_EXT_DISK; offset = minor / nr_parts; - if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4) + if (xen_hvm_domain() && offset < EMULATED_HD_DISK_NAME_OFFSET + 4) printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with " "emulated IDE disks,\n\t choose an xvd device name" "from xvde on\n", info->vdevice); -- cgit v1.2.3 From 34dd82afd27da2537199d7f71f1542501c6f96e7 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 31 Jul 2011 22:08:04 +0200 Subject: loop: replace linked list of allocated devices with an idr index Replace the linked list, that keeps track of allocated devices, with an idr index to allow a more efficient lookup of devices. Cc: Tejun Heo Signed-off-by: Kay Sievers Signed-off-by: Jens Axboe --- drivers/block/loop.c | 152 +++++++++++++++++++++++++++------------------------ include/linux/loop.h | 1 - 2 files changed, 80 insertions(+), 73 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 76c8da78212b..f58532e77777 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -78,8 +78,8 @@ #include -static LIST_HEAD(loop_devices); -static DEFINE_MUTEX(loop_devices_mutex); +static DEFINE_IDR(loop_index_idr); +static DEFINE_MUTEX(loop_index_mutex); static int max_part; static int part_shift; @@ -722,17 +722,10 @@ static inline int is_loop_device(struct file *file) static ssize_t loop_attr_show(struct device *dev, char *page, ssize_t (*callback)(struct loop_device *, char *)) { - struct loop_device *l, *lo = NULL; - - mutex_lock(&loop_devices_mutex); - list_for_each_entry(l, &loop_devices, lo_list) - if (disk_to_dev(l->lo_disk) == dev) { - lo = l; - break; - } - mutex_unlock(&loop_devices_mutex); + struct gendisk *disk = dev_to_disk(dev); + struct loop_device *lo = disk->private_data; - return lo ? callback(lo, page) : -EIO; + return callback(lo, page); } #define LOOP_ATTR_RO(_name) \ @@ -1557,40 +1550,64 @@ int loop_register_transfer(struct loop_func_table *funcs) return 0; } +static int unregister_transfer_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; + struct loop_func_table *xfer = data; + + mutex_lock(&lo->lo_ctl_mutex); + if (lo->lo_encryption == xfer) + loop_release_xfer(lo); + mutex_unlock(&lo->lo_ctl_mutex); + return 0; +} + int loop_unregister_transfer(int number) { unsigned int n = number; - struct loop_device *lo; struct loop_func_table *xfer; if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL) return -EINVAL; xfer_funcs[n] = NULL; - - list_for_each_entry(lo, &loop_devices, lo_list) { - mutex_lock(&lo->lo_ctl_mutex); - - if (lo->lo_encryption == xfer) - loop_release_xfer(lo); - - mutex_unlock(&lo->lo_ctl_mutex); - } - + idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer); return 0; } EXPORT_SYMBOL(loop_register_transfer); EXPORT_SYMBOL(loop_unregister_transfer); -static struct loop_device *loop_alloc(int i) +static int loop_add(struct loop_device **l, int i) { struct loop_device *lo; struct gendisk *disk; + int err; lo = kzalloc(sizeof(*lo), GFP_KERNEL); - if (!lo) + if (!lo) { + err = -ENOMEM; goto out; + } + + err = idr_pre_get(&loop_index_idr, GFP_KERNEL); + if (err < 0) + goto out_free_dev; + + if (i >= 0) { + int m; + + /* create specific i in the index */ + err = idr_get_new_above(&loop_index_idr, lo, i, &m); + if (err >= 0 && i != m) { + idr_remove(&loop_index_idr, m); + err = -EEXIST; + } + } else { + err = -EINVAL; + } + if (err < 0) + goto out_free_dev; lo->lo_queue = blk_alloc_queue(GFP_KERNEL); if (!lo->lo_queue) @@ -1611,56 +1628,54 @@ static struct loop_device *loop_alloc(int i) disk->private_data = lo; disk->queue = lo->lo_queue; sprintf(disk->disk_name, "loop%d", i); - return lo; + add_disk(disk); + *l = lo; + return lo->lo_number; out_free_queue: blk_cleanup_queue(lo->lo_queue); out_free_dev: kfree(lo); out: - return NULL; + return err; } -static void loop_free(struct loop_device *lo) +static void loop_remove(struct loop_device *lo) { + del_gendisk(lo->lo_disk); blk_cleanup_queue(lo->lo_queue); put_disk(lo->lo_disk); - list_del(&lo->lo_list); kfree(lo); } -static struct loop_device *loop_init_one(int i) +static int loop_lookup(struct loop_device **l, int i) { struct loop_device *lo; + int ret = -ENODEV; - list_for_each_entry(lo, &loop_devices, lo_list) { - if (lo->lo_number == i) - return lo; - } - - lo = loop_alloc(i); + lo = idr_find(&loop_index_idr, i); if (lo) { - add_disk(lo->lo_disk); - list_add_tail(&lo->lo_list, &loop_devices); + *l = lo; + ret = lo->lo_number; } - return lo; -} - -static void loop_del_one(struct loop_device *lo) -{ - del_gendisk(lo->lo_disk); - loop_free(lo); + return ret; } static struct kobject *loop_probe(dev_t dev, int *part, void *data) { struct loop_device *lo; struct kobject *kobj; + int err; - mutex_lock(&loop_devices_mutex); - lo = loop_init_one(MINOR(dev) >> part_shift); - kobj = lo ? get_disk(lo->lo_disk) : ERR_PTR(-ENOMEM); - mutex_unlock(&loop_devices_mutex); + mutex_lock(&loop_index_mutex); + err = loop_lookup(&lo, MINOR(dev) >> part_shift); + if (err < 0) + err = loop_add(&lo, MINOR(dev) >> part_shift); + if (err < 0) + kobj = ERR_PTR(err); + else + kobj = get_disk(lo->lo_disk); + mutex_unlock(&loop_index_mutex); *part = 0; return kobj; @@ -1670,7 +1685,7 @@ static int __init loop_init(void) { int i, nr; unsigned long range; - struct loop_device *lo, *next; + struct loop_device *lo; /* * loop module now has a feature to instantiate underlying device @@ -1719,43 +1734,36 @@ static int __init loop_init(void) if (register_blkdev(LOOP_MAJOR, "loop")) return -EIO; - for (i = 0; i < nr; i++) { - lo = loop_alloc(i); - if (!lo) - goto Enomem; - list_add_tail(&lo->lo_list, &loop_devices); - } - - /* point of no return */ - - list_for_each_entry(lo, &loop_devices, lo_list) - add_disk(lo->lo_disk); - blk_register_region(MKDEV(LOOP_MAJOR, 0), range, THIS_MODULE, loop_probe, NULL, NULL); + /* pre-create number devices of devices given by config or max_loop */ + mutex_lock(&loop_index_mutex); + for (i = 0; i < nr; i++) + loop_add(&lo, i); + mutex_unlock(&loop_index_mutex); + printk(KERN_INFO "loop: module loaded\n"); return 0; +} -Enomem: - printk(KERN_INFO "loop: out of memory\n"); - - list_for_each_entry_safe(lo, next, &loop_devices, lo_list) - loop_free(lo); +static int loop_exit_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; - unregister_blkdev(LOOP_MAJOR, "loop"); - return -ENOMEM; + loop_remove(lo); + return 0; } static void __exit loop_exit(void) { unsigned long range; - struct loop_device *lo, *next; range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; - list_for_each_entry_safe(lo, next, &loop_devices, lo_list) - loop_del_one(lo); + idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); + idr_remove_all(&loop_index_idr); + idr_destroy(&loop_index_idr); blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); unregister_blkdev(LOOP_MAJOR, "loop"); diff --git a/include/linux/loop.h b/include/linux/loop.h index 66c194e2d9b9..5f08d18fa148 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -64,7 +64,6 @@ struct loop_device { struct request_queue *lo_queue; struct gendisk *lo_disk; - struct list_head lo_list; }; #endif /* __KERNEL__ */ -- cgit v1.2.3 From 770fe30a46a12b6fb6b63fbe1737654d28e84844 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 31 Jul 2011 22:08:04 +0200 Subject: loop: add management interface for on-demand device allocation Loop devices today have a fixed pre-allocated number of usually 8. The number can only be changed at module init time. To find a free device to use, /dev/loop%i needs to be scanned, and all devices need to be opened until a free one is possibly found. This adds a new /dev/loop-control device node, that allows to dynamically find or allocate a free device, and to add and remove loop devices from the running system: LOOP_CTL_ADD adds a specific device. Arg is the number of the device. It returns the device i or a negative error code. LOOP_CTL_REMOVE removes a specific device, Arg is the number the device. It returns the device i or a negative error code. LOOP_CTL_GET_FREE finds the next unbound device or allocates a new one. No arg is given. It returns the device i or a negative error code. The loop kernel module gets automatically loaded when /dev/loop-control is accessed the first time. The alias specified in the module, instructs udev to create this 'dead' device node, even when the module is not loaded. Example: cfd = open("/dev/loop-control", O_RDWR); # add a new specific loop device err = ioctl(cfd, LOOP_CTL_ADD, devnr); # remove a specific loop device err = ioctl(cfd, LOOP_CTL_REMOVE, devnr); # find or allocate a free loop device to use devnr = ioctl(cfd, LOOP_CTL_GET_FREE); sprintf(loopname, "/dev/loop%i", devnr); ffd = open("backing-file", O_RDWR); lfd = open(loopname, O_RDWR); err = ioctl(lfd, LOOP_SET_FD, ffd); Cc: Tejun Heo Cc: Karel Zak Signed-off-by: Kay Sievers Signed-off-by: Jens Axboe --- drivers/block/loop.c | 120 +++++++++++++++++++++++++++++++++++++++++++-- include/linux/loop.h | 4 ++ include/linux/miscdevice.h | 1 + 3 files changed, 121 insertions(+), 4 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index f58532e77777..5c9edf944879 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -75,7 +75,7 @@ #include #include #include - +#include #include static DEFINE_IDR(loop_index_idr); @@ -1478,13 +1478,22 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, static int lo_open(struct block_device *bdev, fmode_t mode) { - struct loop_device *lo = bdev->bd_disk->private_data; + struct loop_device *lo; + int err = 0; + + mutex_lock(&loop_index_mutex); + lo = bdev->bd_disk->private_data; + if (!lo) { + err = -ENXIO; + goto out; + } mutex_lock(&lo->lo_ctl_mutex); lo->lo_refcnt++; mutex_unlock(&lo->lo_ctl_mutex); - - return 0; +out: + mutex_unlock(&loop_index_mutex); + return err; } static int lo_release(struct gendisk *disk, fmode_t mode) @@ -1603,6 +1612,13 @@ static int loop_add(struct loop_device **l, int i) idr_remove(&loop_index_idr, m); err = -EEXIST; } + } else if (i == -1) { + int m; + + /* get next free nr */ + err = idr_get_new(&loop_index_idr, lo, &m); + if (err >= 0) + i = m; } else { err = -EINVAL; } @@ -1648,16 +1664,41 @@ static void loop_remove(struct loop_device *lo) kfree(lo); } +static int find_free_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; + struct loop_device **l = data; + + if (lo->lo_state == Lo_unbound) { + *l = lo; + return 1; + } + return 0; +} + static int loop_lookup(struct loop_device **l, int i) { struct loop_device *lo; int ret = -ENODEV; + if (i < 0) { + int err; + + err = idr_for_each(&loop_index_idr, &find_free_cb, &lo); + if (err == 1) { + *l = lo; + ret = lo->lo_number; + } + goto out; + } + + /* lookup and return a specific i */ lo = idr_find(&loop_index_idr, i); if (lo) { *l = lo; ret = lo->lo_number; } +out: return ret; } @@ -1681,11 +1722,76 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data) return kobj; } +static long loop_control_ioctl(struct file *file, unsigned int cmd, + unsigned long parm) +{ + struct loop_device *lo; + int ret = -ENOSYS; + + mutex_lock(&loop_index_mutex); + switch (cmd) { + case LOOP_CTL_ADD: + ret = loop_lookup(&lo, parm); + if (ret >= 0) { + ret = -EEXIST; + break; + } + ret = loop_add(&lo, parm); + break; + case LOOP_CTL_REMOVE: + ret = loop_lookup(&lo, parm); + if (ret < 0) + break; + mutex_lock(&lo->lo_ctl_mutex); + if (lo->lo_state != Lo_unbound) { + ret = -EBUSY; + mutex_unlock(&lo->lo_ctl_mutex); + break; + } + if (lo->lo_refcnt > 0) { + ret = -EBUSY; + mutex_unlock(&lo->lo_ctl_mutex); + break; + } + lo->lo_disk->private_data = NULL; + mutex_unlock(&lo->lo_ctl_mutex); + idr_remove(&loop_index_idr, lo->lo_number); + loop_remove(lo); + break; + case LOOP_CTL_GET_FREE: + ret = loop_lookup(&lo, -1); + if (ret >= 0) + break; + ret = loop_add(&lo, -1); + } + mutex_unlock(&loop_index_mutex); + + return ret; +} + +static const struct file_operations loop_ctl_fops = { + .open = nonseekable_open, + .unlocked_ioctl = loop_control_ioctl, + .compat_ioctl = loop_control_ioctl, + .owner = THIS_MODULE, + .llseek = noop_llseek, +}; + +static struct miscdevice loop_misc = { + .minor = LOOP_CTRL_MINOR, + .name = "loop-control", + .fops = &loop_ctl_fops, +}; + +MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR); +MODULE_ALIAS("devname:loop-control"); + static int __init loop_init(void) { int i, nr; unsigned long range; struct loop_device *lo; + int err; /* * loop module now has a feature to instantiate underlying device @@ -1702,6 +1808,10 @@ static int __init loop_init(void) * device on-demand. */ + err = misc_register(&loop_misc); + if (err < 0) + return err; + part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); @@ -1767,6 +1877,8 @@ static void __exit loop_exit(void) blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); unregister_blkdev(LOOP_MAJOR, "loop"); + + misc_deregister(&loop_misc); } module_init(loop_init); diff --git a/include/linux/loop.h b/include/linux/loop.h index 5f08d18fa148..683d69890119 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -160,4 +160,8 @@ int loop_unregister_transfer(int number); #define LOOP_CHANGE_FD 0x4C06 #define LOOP_SET_CAPACITY 0x4C07 +/* /dev/loop-control interface */ +#define LOOP_CTL_ADD 0x4C80 +#define LOOP_CTL_REMOVE 0x4C81 +#define LOOP_CTL_GET_FREE 0x4C82 #endif diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 18fd13028ba1..c309b1ecdc1c 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -40,6 +40,7 @@ #define BTRFS_MINOR 234 #define AUTOFS_MINOR 235 #define MAPPER_CTRL_MINOR 236 +#define LOOP_CTRL_MINOR 237 #define MISC_DYNAMIC_MINOR 255 struct device; -- cgit v1.2.3 From d134b00b9acca3fb054d7c88a5f5d562ecbb42d1 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 31 Jul 2011 22:08:04 +0200 Subject: loop: add BLK_DEV_LOOP_MIN_COUNT=%i to allow distros 0 pre-allocated loop devices Instead of unconditionally creating a fixed number of dead loop devices which need to be investigated by storage handling services, even when they are never used, we allow distros start with 0 loop devices and have losetup(8) and similar switch to the dynamic /dev/loop-control interface instead of searching /dev/loop%i for free devices. Signed-off-by: Kay Sievers Signed-off-by: Jens Axboe --- Documentation/kernel-parameters.txt | 9 ++++++--- drivers/block/Kconfig | 15 +++++++++++++++ drivers/block/loop.c | 27 ++++++++++----------------- 3 files changed, 31 insertions(+), 20 deletions(-) (limited to 'drivers/block') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4ca93898fbd3..c32851131646 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1340,9 +1340,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. it is equivalent to "nosmp", which also disables the IO APIC. - max_loop= [LOOP] Maximum number of loopback devices that can - be mounted - Format: <1-256> + max_loop= [LOOP] The number of loop block devices that get + (loop.max_loop) unconditionally pre-created at init time. The default + number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead + of statically allocating a predefined number, loop + devices can be requested on-demand with the + /dev/loop-control interface. mcatest= [IA-64] diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 717d6e4e18d3..57212c5235e2 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -256,6 +256,21 @@ config BLK_DEV_LOOP Most users will answer N here. +config BLK_DEV_LOOP_MIN_COUNT + int "Number of loop devices to pre-create at init time" + depends on BLK_DEV_LOOP + default 8 + help + Static number of loop devices to be unconditionally pre-created + at init time. + + This default value can be overwritten on the kernel command + line or with module-parameter loop.max_loop. + + The historic default is 8. If a late 2011 version of losetup(8) + is used, it can be set to 0, since needed loop devices can be + dynamically allocated with the /dev/loop-control interface. + config BLK_DEV_CRYPTOLOOP tristate "Cryptoloop Support" select CRYPTO diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 5c9edf944879..3defc52f060c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1793,21 +1793,6 @@ static int __init loop_init(void) struct loop_device *lo; int err; - /* - * loop module now has a feature to instantiate underlying device - * structure on-demand, provided that there is an access dev node. - * However, this will not work well with user space tool that doesn't - * know about such "feature". In order to not break any existing - * tool, we do the following: - * - * (1) if max_loop is specified, create that many upfront, and this - * also becomes a hard limit. - * (2) if max_loop is not specified, create 8 loop device on module - * load, user can further extend loop device by create dev node - * themselves and have kernel automatically instantiate actual - * device on-demand. - */ - err = misc_register(&loop_misc); if (err < 0) return err; @@ -1833,11 +1818,19 @@ static int __init loop_init(void) if (max_loop > 1UL << (MINORBITS - part_shift)) return -EINVAL; + /* + * If max_loop is specified, create that many devices upfront. + * This also becomes a hard limit. If max_loop is not specified, + * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module + * init time. Loop devices can be requested on-demand with the + * /dev/loop-control interface, or be instantiated by accessing + * a 'dead' device node. + */ if (max_loop) { nr = max_loop; range = max_loop << part_shift; } else { - nr = 8; + nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT; range = 1UL << MINORBITS; } @@ -1847,7 +1840,7 @@ static int __init loop_init(void) blk_register_region(MKDEV(LOOP_MAJOR, 0), range, THIS_MODULE, loop_probe, NULL, NULL); - /* pre-create number devices of devices given by config or max_loop */ + /* pre-create number of devices given by config or max_loop */ mutex_lock(&loop_index_mutex); for (i = 0; i < nr; i++) loop_add(&lo, i); -- cgit v1.2.3 From 05eb0f252b04aa94ace0794f73d56c6a02351d80 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 31 Jul 2011 22:21:35 +0200 Subject: loop: fix deadlock when sysfs and LOOP_CLR_FD race against each other LOOP_CLR_FD takes lo->lo_ctl_mutex and tries to remove the loop sysfs files. Sysfs calls show() and waits for lo->lo_ctl_mutex. LOOP_CLR_FD waits for show() to finish to remove the sysfs file. cat /sys/class/block/loop0/loop/backing_file mutex_lock_nested+0x176/0x350 ? loop_attr_do_show_backing_file+0x2f/0xd0 [loop] ? loop_attr_do_show_backing_file+0x2f/0xd0 [loop] loop_attr_do_show_backing_file+0x2f/0xd0 [loop] dev_attr_show+0x1b/0x60 ? sysfs_read_file+0x86/0x1a0 ? __get_free_pages+0x12/0x50 sysfs_read_file+0xaf/0x1a0 ioctl(LOOP_CLR_FD): wait_for_common+0x12c/0x180 ? try_to_wake_up+0x2a0/0x2a0 wait_for_completion+0x18/0x20 sysfs_deactivate+0x178/0x180 ? sysfs_addrm_finish+0x43/0x70 ? sysfs_addrm_start+0x1d/0x20 sysfs_addrm_finish+0x43/0x70 sysfs_hash_and_remove+0x85/0xa0 sysfs_remove_group+0x59/0x100 loop_clr_fd+0x1dc/0x3f0 [loop] lo_ioctl+0x223/0x7a0 [loop] Instead of taking the lo_ctl_mutex from sysfs code, take the inner lo->lo_lock, to protect the access to the backing_file data. Thanks to Tejun for help debugging and finding a solution. Cc: Milan Broz Cc: Tejun Heo Signed-off-by: Kay Sievers Cc: stable@kernel.org Signed-off-by: Jens Axboe --- drivers/block/loop.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 3defc52f060c..4720c7ade0ae 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -743,10 +743,10 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) ssize_t ret; char *p = NULL; - mutex_lock(&lo->lo_ctl_mutex); + spin_lock_irq(&lo->lo_lock); if (lo->lo_backing_file) p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1); - mutex_unlock(&lo->lo_ctl_mutex); + spin_unlock_irq(&lo->lo_lock); if (IS_ERR_OR_NULL(p)) ret = PTR_ERR(p); @@ -1000,7 +1000,9 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) kthread_stop(lo->lo_thread); + spin_lock_irq(&lo->lo_lock); lo->lo_backing_file = NULL; + spin_unlock_irq(&lo->lo_lock); loop_release_xfer(lo); lo->transfer = NULL; -- cgit v1.2.3 From ddad9ef5826efdfbbdb67b13b46f30e43e46ec3e Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Tue, 2 Aug 2011 12:43:49 +0200 Subject: drivers/block/drbd/drbd_nl.c: use bitmap_parse instead of __bitmap_parse The buffer 'sc.cpu_mask' is a kernel buffer. If bitmap_parse is used instead of __bitmap_parse the extra parameter that indicates a kernel buffer is not needed. Signed-off-by: H Hartley Sweeten Cc: Lars Ellenberg Cc: Philipp Reisner Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_nl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 515bcd948a43..0feab261e295 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1829,10 +1829,10 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n /* silently ignore cpu mask on UP kernel */ if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) { - err = __bitmap_parse(sc.cpu_mask, 32, 0, + err = bitmap_parse(sc.cpu_mask, 32, cpumask_bits(new_cpu_mask), nr_cpu_ids); if (err) { - dev_warn(DEV, "__bitmap_parse() failed with %d\n", err); + dev_warn(DEV, "bitmap_parse() failed with %d\n", err); retcode = ERR_CPU_MASK_PARSE; goto fail; } -- cgit v1.2.3 From f41c53a569c4cf0556893ec9cfcf697d069799e1 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 3 Aug 2011 15:02:55 +0200 Subject: block: swim3: fix unterminated of_device_id table of_device_id structures need a NULL terminating entry, add it. Signed-off-by: Axel Lin Signed-off-by: Jens Axboe --- drivers/block/swim3.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/block') diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 773bfa792777..ae3e167e17ad 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1184,6 +1184,7 @@ static struct of_device_id swim3_match[] = { .compatible = "swim3" }, + { /* end of list */ } }; static struct macio_driver swim3_driver = -- cgit v1.2.3 From ea5e116162b7e0cf83a2b8a273440514404604de Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 3 Aug 2011 11:12:17 -0400 Subject: xen/blkback: Make description more obvious. With the frontend having Xen but the backend not, it just looks odd: <*> Xen virtual block device support <*> Block-device backend driver Fix it to have the 'Xen' in front of it. Reported-by: Sander Eikelenboom Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/block') diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 717d6e4e18d3..a89ebf1b28aa 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -471,7 +471,7 @@ config XEN_BLKDEV_FRONTEND in another domain which drives the actual block device. config XEN_BLKDEV_BACKEND - tristate "Block-device backend driver" + tristate "Xen block-device backend driver" depends on XEN_BACKEND help The block-device backend driver allows the kernel to export its -- cgit v1.2.3 From 6f5986bce558e64fe867bff600a2127a3cb0c006 Mon Sep 17 00:00:00 2001 From: Joe Jin Date: Mon, 15 Aug 2011 12:51:31 +0800 Subject: xen-blkback: Don't disconnect backend until state switched to XenbusStateClosed. When do block-attach/block-detach test with below steps, umount hangs in the guest. Furthermore shutdown ends up being stuck when umounting file-systems. 1. start guest. 2. attach new block device by xm block-attach in Dom0. 3. mount new disk in guest. 4. execute xm block-detach to detach the block device in dom0 until timeout 5. Any request to the disk will hung. Root cause: This issue is caused when setting backend device's state to 'XenbusStateClosing', which sends to the frontend the XenbusStateClosing notification. When frontend receives the notification it tries to release the disk in blkfront_closing(), but at that moment the disk is still in use by guest, so frontend refuses to close. Specifically it sets the disk state to XenbusStateClosing and sends the notification to backend - when backend receives the event, it disconnects the vbd from real device, and sets the vbd device state to XenbusStateClosing. The backend disconnects the real device/file, and any IO requests to the disk in guest will end up in ether, leaving disk DEAD and set to XenbusStateClosing. When the guest wants to disconnect the disk, umount will hang on blkif_release()->xlvbd_release_gendisk() as it is unable to send any IO to the disk, which prevents clean system shutdown. Solution: Don't disconnect backend until frontend state switched to XenbusStateClosed. Signed-off-by: Joe Jin Cc: Daniel Stodden Cc: Jens Axboe Cc: Annie Li Cc: Ian Campbell [v1: Modified description a bit] Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkback/xenbus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/block') diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 6cc0db1bf522..7be3d0fe8ad3 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -601,11 +601,11 @@ static void frontend_changed(struct xenbus_device *dev, break; case XenbusStateClosing: - xen_blkif_disconnect(be->blkif); xenbus_switch_state(dev, XenbusStateClosing); break; case XenbusStateClosed: + xen_blkif_disconnect(be->blkif); xenbus_switch_state(dev, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; -- cgit v1.2.3 From 1bc05b0ae6448b20d46076899e0cc12ad999e50e Mon Sep 17 00:00:00 2001 From: Joe Jin Date: Mon, 15 Aug 2011 12:57:07 +0800 Subject: xen-blkback: fixed indentation and comments This patch fixes belows: 1. Fix code style issue. 2. Fix incorrect functions name in comments. Signed-off-by: Joe Jin Cc: Jens Axboe Cc: Ian Campbell Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkback/common.h | 2 +- drivers/block/xen-blkback/xenbus.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 9e40b283a468..00c57c90e2d6 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -46,7 +46,7 @@ #define DRV_PFX "xen-blkback:" #define DPRINTK(fmt, args...) \ - pr_debug(DRV_PFX "(%s:%d) " fmt ".\n", \ + pr_debug(DRV_PFX "(%s:%d) " fmt ".\n", \ __func__, __LINE__, ##args) diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 7be3d0fe8ad3..a96cb5f893a8 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -590,7 +590,7 @@ static void frontend_changed(struct xenbus_device *dev, /* * Enforce precondition before potential leak point. - * blkif_disconnect() is idempotent. + * xen_blkif_disconnect() is idempotent. */ xen_blkif_disconnect(be->blkif); @@ -611,7 +611,7 @@ static void frontend_changed(struct xenbus_device *dev, break; /* fall through if not online */ case XenbusStateUnknown: - /* implies blkif_disconnect() via blkback_remove() */ + /* implies xen_blkif_disconnect() via xen_blkbk_remove() */ device_unregister(&dev->dev); break; -- cgit v1.2.3 From 6c4867f6469964e34c5f4ee229a2a7f71a34c7ff Mon Sep 17 00:00:00 2001 From: Carsten Emde Date: Wed, 21 Sep 2011 10:22:11 +0200 Subject: floppy: use del_timer_sync() in init cleanup When no floppy is found the module code can be released while a timer function is pending or about to be executed. CPU0 CPU1 floppy_init() timer_softirq() spin_lock_irq(&base->lock); detach_timer(); spin_unlock_irq(&base->lock); -> Interrupt del_timer(); return -ENODEV; module_cleanup(); <- EOI call_timer_fn(); OOPS Use del_timer_sync() to prevent this. Signed-off-by: Carsten Emde Signed-off-by: Thomas Gleixner Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- drivers/block/floppy.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 98de8f418676..9955a53733b2 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4250,7 +4250,7 @@ static int __init floppy_init(void) use_virtual_dma = can_use_virtual_dma & 1; fdc_state[0].address = FDC1; if (fdc_state[0].address == -1) { - del_timer(&fd_timeout); + del_timer_sync(&fd_timeout); err = -ENODEV; goto out_unreg_region; } @@ -4261,7 +4261,7 @@ static int __init floppy_init(void) fdc = 0; /* reset fdc in case of unexpected interrupt */ err = floppy_grab_irq_and_dma(); if (err) { - del_timer(&fd_timeout); + del_timer_sync(&fd_timeout); err = -EBUSY; goto out_unreg_region; } @@ -4318,7 +4318,7 @@ static int __init floppy_init(void) user_reset_fdc(-1, FD_RESET_ALWAYS, false); } fdc = 0; - del_timer(&fd_timeout); + del_timer_sync(&fd_timeout); current_drive = 0; initialized = true; if (have_no_fdc) { @@ -4368,7 +4368,7 @@ out_unreg_blkdev: unregister_blkdev(FLOPPY_MAJOR, "fd"); out_put_disk: while (dr--) { - del_timer(&motor_off_timer[dr]); + del_timer_sync(&motor_off_timer[dr]); if (disks[dr]->queue) blk_cleanup_queue(disks[dr]->queue); put_disk(disks[dr]); -- cgit v1.2.3