X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=block%2Fgenhd.c;h=f4c64c2b303a33e2f46bd10b01d36c2cd931b4d6;hb=8e498751f2f36074ffa6fc7f0a9ec6e055b350e6;hp=fa32d09fda24c1f840454f3671dd8ace2cd491de;hpb=f331c0296f2a9fee0d396a70598b954062603015;p=safe%2Fjmp%2Flinux-2.6 diff --git a/block/genhd.c b/block/genhd.c index fa32d09..f4c64c2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -10,12 +10,14 @@ #include #include #include +#include #include #include #include #include #include #include +#include #include "blk.h" @@ -24,8 +26,210 @@ static DEFINE_MUTEX(block_class_lock); struct kobject *block_depr; #endif +/* for extended dynamic devt allocation, currently only one major is used */ +#define MAX_EXT_DEVT (1 << MINORBITS) + +/* For extended devt allocation. ext_devt_mutex prevents look up + * results from going away underneath its user. + */ +static DEFINE_MUTEX(ext_devt_mutex); +static DEFINE_IDR(ext_devt_idr); + static struct device_type disk_type; +/** + * disk_get_part - get partition + * @disk: disk to look partition from + * @partno: partition number + * + * Look for partition @partno from @disk. If found, increment + * reference count and return it. + * + * CONTEXT: + * Don't care. + * + * RETURNS: + * Pointer to the found partition on success, NULL if not found. + */ +struct hd_struct *disk_get_part(struct gendisk *disk, int partno) +{ + struct hd_struct *part = NULL; + struct disk_part_tbl *ptbl; + + if (unlikely(partno < 0)) + return NULL; + + rcu_read_lock(); + + ptbl = rcu_dereference(disk->part_tbl); + if (likely(partno < ptbl->len)) { + part = rcu_dereference(ptbl->part[partno]); + if (part) + get_device(part_to_dev(part)); + } + + rcu_read_unlock(); + + return part; +} +EXPORT_SYMBOL_GPL(disk_get_part); + +/** + * disk_part_iter_init - initialize partition iterator + * @piter: iterator to initialize + * @disk: disk to iterate over + * @flags: DISK_PITER_* flags + * + * Initialize @piter so that it iterates over partitions of @disk. + * + * CONTEXT: + * Don't care. + */ +void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk, + unsigned int flags) +{ + struct disk_part_tbl *ptbl; + + rcu_read_lock(); + ptbl = rcu_dereference(disk->part_tbl); + + piter->disk = disk; + piter->part = NULL; + + if (flags & DISK_PITER_REVERSE) + piter->idx = ptbl->len - 1; + else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0)) + piter->idx = 0; + else + piter->idx = 1; + + piter->flags = flags; + + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(disk_part_iter_init); + +/** + * disk_part_iter_next - proceed iterator to the next partition and return it + * @piter: iterator of interest + * + * Proceed @piter to the next partition and return it. + * + * CONTEXT: + * Don't care. + */ +struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) +{ + struct disk_part_tbl *ptbl; + int inc, end; + + /* put the last partition */ + disk_put_part(piter->part); + piter->part = NULL; + + /* get part_tbl */ + rcu_read_lock(); + ptbl = rcu_dereference(piter->disk->part_tbl); + + /* determine iteration parameters */ + if (piter->flags & DISK_PITER_REVERSE) { + inc = -1; + if (piter->flags & (DISK_PITER_INCL_PART0 | + DISK_PITER_INCL_EMPTY_PART0)) + end = -1; + else + end = 0; + } else { + inc = 1; + end = ptbl->len; + } + + /* iterate to the next partition */ + for (; piter->idx != end; piter->idx += inc) { + struct hd_struct *part; + + part = rcu_dereference(ptbl->part[piter->idx]); + if (!part) + continue; + if (!part->nr_sects && + !(piter->flags & DISK_PITER_INCL_EMPTY) && + !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && + piter->idx == 0)) + continue; + + get_device(part_to_dev(part)); + piter->part = part; + piter->idx += inc; + break; + } + + rcu_read_unlock(); + + return piter->part; +} +EXPORT_SYMBOL_GPL(disk_part_iter_next); + +/** + * disk_part_iter_exit - finish up partition iteration + * @piter: iter of interest + * + * Called when iteration is over. Cleans up @piter. + * + * CONTEXT: + * Don't care. + */ +void disk_part_iter_exit(struct disk_part_iter *piter) +{ + disk_put_part(piter->part); + piter->part = NULL; +} +EXPORT_SYMBOL_GPL(disk_part_iter_exit); + +static inline int sector_in_part(struct hd_struct *part, sector_t sector) +{ + return part->start_sect <= sector && + sector < part->start_sect + part->nr_sects; +} + +/** + * disk_map_sector_rcu - map sector to partition + * @disk: gendisk of interest + * @sector: sector to map + * + * Find out which partition @sector maps to on @disk. This is + * primarily used for stats accounting. + * + * CONTEXT: + * RCU read locked. The returned partition pointer is valid only + * while preemption is disabled. + * + * RETURNS: + * Found partition on success, part0 is returned if no partition matches + */ +struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) +{ + struct disk_part_tbl *ptbl; + struct hd_struct *part; + int i; + + ptbl = rcu_dereference(disk->part_tbl); + + part = rcu_dereference(ptbl->last_lookup); + if (part && sector_in_part(part, sector)) + return part; + + for (i = 1; i < ptbl->len; i++) { + part = rcu_dereference(ptbl->part[i]); + + if (part && sector_in_part(part, sector)) { + rcu_assign_pointer(ptbl->last_lookup, part); + return part; + } + } + return &disk->part0; +} +EXPORT_SYMBOL_GPL(disk_map_sector_rcu); + /* * Can be deleted altogether. Later. * @@ -56,6 +260,22 @@ void blkdev_show(struct seq_file *seqf, off_t offset) } #endif /* CONFIG_PROC_FS */ +/** + * register_blkdev - register a new block device + * + * @major: the requested major device number [1..255]. If @major=0, try to + * allocate any unused major number. + * @name: the name of the new block device as a zero terminated string + * + * The @name must be unique within the system. + * + * The return value depends on the @major input parameter. + * - if a major device number was requested in range [1..255] then the + * function returns zero on success, or a negative error code + * - if any unused major number was requested with @major=0 parameter + * then the return value is the allocated major number in range + * [1..255] or a negative error code otherwise + */ int register_blkdev(unsigned int major, const char *name) { struct blk_major_name **n, *p; @@ -136,6 +356,117 @@ EXPORT_SYMBOL(unregister_blkdev); static struct kobj_map *bdev_map; +/** + * blk_mangle_minor - scatter minor numbers apart + * @minor: minor number to mangle + * + * Scatter consecutively allocated @minor number apart if MANGLE_DEVT + * is enabled. Mangling twice gives the original value. + * + * RETURNS: + * Mangled value. + * + * CONTEXT: + * Don't care. + */ +static int blk_mangle_minor(int minor) +{ +#ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT + int i; + + for (i = 0; i < MINORBITS / 2; i++) { + int low = minor & (1 << i); + int high = minor & (1 << (MINORBITS - 1 - i)); + int distance = MINORBITS - 1 - 2 * i; + + minor ^= low | high; /* clear both bits */ + low <<= distance; /* swap the positions */ + high >>= distance; + minor |= low | high; /* and set */ + } +#endif + return minor; +} + +/** + * blk_alloc_devt - allocate a dev_t for a partition + * @part: partition 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 hd_struct *part, dev_t *devt) +{ + struct gendisk *disk = part_to_disk(part); + int idx, rc; + + /* in consecutive minor range? */ + if (part->partno < disk->minors) { + *devt = MKDEV(disk->major, disk->first_minor + part->partno); + return 0; + } + + /* allocate ext devt */ + do { + if (!idr_pre_get(&ext_devt_idr, GFP_KERNEL)) + return -ENOMEM; + rc = idr_get_new(&ext_devt_idr, part, &idx); + } while (rc == -EAGAIN); + + if (rc) + return rc; + + if (idx > MAX_EXT_DEVT) { + idr_remove(&ext_devt_idr, idx); + return -EBUSY; + } + + *devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx)); + return 0; +} + +/** + * 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) +{ + might_sleep(); + + if (devt == MKDEV(0, 0)) + return; + + if (MAJOR(devt) == BLOCK_EXT_MAJOR) { + mutex_lock(&ext_devt_mutex); + idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); + mutex_unlock(&ext_devt_mutex); + } +} + +static char *bdevt_str(dev_t devt, char *buf) +{ + if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { + char tbuf[BDEVT_SIZE]; + snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); + snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); + } else + snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); + + return buf; +} + /* * Register device numbers dev..(dev+range-1) * range must be nonzero @@ -161,7 +492,7 @@ static struct kobject *exact_match(dev_t devt, int *partno, void *data) { struct gendisk *p = data; - return &p->dev.kobj; + return &disk_to_dev(p)->kobj; } static int exact_lock(dev_t devt, void *data) @@ -179,14 +510,37 @@ static int exact_lock(dev_t devt, void *data) * * This function registers the partitioning information in @disk * with the kernel. + * + * FIXME: error handling */ void add_disk(struct gendisk *disk) { struct backing_dev_info *bdi; + dev_t devt; int retval; + /* minors == 0 indicates to use ext devt from part0 and should + * be accompanied with EXT_DEVT flag. Make sure all + * parameters make sense. + */ + WARN_ON(disk->minors && !(disk->major || disk->first_minor)); + WARN_ON(!disk->minors && !(disk->flags & GENHD_FL_EXT_DEVT)); + disk->flags |= GENHD_FL_UP; - disk->dev.devt = MKDEV(disk->major, disk->first_minor); + + retval = blk_alloc_devt(&disk->part0, &devt); + if (retval) { + WARN_ON(1); + return; + } + disk_to_dev(disk)->devt = devt; + + /* ->major and ->first_minor aren't supposed to be + * dereferenced from here on, but set them just in case. + */ + disk->major = MAJOR(devt); + disk->first_minor = MINOR(devt); + blk_register_region(disk_devt(disk), disk->minors, NULL, exact_match, exact_lock, disk); register_disk(disk); @@ -194,7 +548,8 @@ void add_disk(struct gendisk *disk) bdi = &disk->queue->backing_dev_info; bdi_register_dev(bdi, disk_devt(disk)); - retval = sysfs_create_link(&disk->dev.kobj, &bdi->dev->kobj, "bdi"); + retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj, + "bdi"); WARN_ON(retval); } @@ -203,7 +558,7 @@ EXPORT_SYMBOL(del_gendisk); /* in partitions/check.c */ void unlink_gendisk(struct gendisk *disk) { - sysfs_remove_link(&disk->dev.kobj, "bdi"); + sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); bdi_unregister(&disk->queue->backing_dev_info); blk_unregister_queue(disk); blk_unregister_region(disk_devt(disk), disk->minors); @@ -212,17 +567,34 @@ void unlink_gendisk(struct gendisk *disk) /** * get_gendisk - get partitioning information for a given device * @devt: device to get partitioning information for - * @part: returned partition index + * @partno: returned partition index * * This function gets the structure containing partitioning * information for the given device @devt. */ struct gendisk *get_gendisk(dev_t devt, int *partno) { - struct kobject *kobj = kobj_lookup(bdev_map, devt, partno); - struct device *dev = kobj_to_dev(kobj); + struct gendisk *disk = NULL; - return kobj ? dev_to_disk(dev) : NULL; + if (MAJOR(devt) != BLOCK_EXT_MAJOR) { + struct kobject *kobj; + + kobj = kobj_lookup(bdev_map, devt, partno); + if (kobj) + disk = dev_to_disk(kobj_to_dev(kobj)); + } else { + struct hd_struct *part; + + mutex_lock(&ext_devt_mutex); + part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); + if (part && get_disk(part_to_disk(part))) { + *partno = part->partno; + disk = part_to_disk(part); + } + mutex_unlock(&ext_devt_mutex); + } + + return disk; } /** @@ -238,22 +610,17 @@ struct gendisk *get_gendisk(dev_t devt, int *partno) * RETURNS: * Resulting block_device on success, NULL on failure. */ -extern struct block_device *bdget_disk(struct gendisk *disk, int partno) +struct block_device *bdget_disk(struct gendisk *disk, int partno) { - dev_t devt = MKDEV(0, 0); + struct hd_struct *part; + struct block_device *bdev = NULL; - if (partno == 0) - devt = disk_devt(disk); - else { - struct hd_struct *part = disk->part[partno - 1]; + part = disk_get_part(disk, partno); + if (part) + bdev = bdget(part_devt(part)); + disk_put_part(part); - if (part && part->nr_sects) - devt = part_devt(part); - } - - if (likely(devt != MKDEV(0, 0))) - return bdget(devt); - return NULL; + return bdev; } EXPORT_SYMBOL(bdget_disk); @@ -270,8 +637,10 @@ void __init printk_all_partitions(void) class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); - char buf[BDEVNAME_SIZE]; - int n; + struct disk_part_iter piter; + struct hd_struct *part; + char name_buf[BDEVNAME_SIZE]; + char devt_buf[BDEVT_SIZE]; /* * Don't show empty devices or things that have been @@ -286,28 +655,25 @@ void __init printk_all_partitions(void) * numbers in hex - the same format as the root= * option takes. */ - printk("%02x%02x %10llu %s", - MAJOR(disk_devt(disk)), MINOR(disk_devt(disk)), - (unsigned long long)get_capacity(disk) >> 1, - disk_name(disk, 0, buf)); - if (disk->driverfs_dev != NULL && - disk->driverfs_dev->driver != NULL) - printk(" driver: %s\n", - disk->driverfs_dev->driver->name); - else - printk(" (driver?)\n"); + disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0); + while ((part = disk_part_iter_next(&piter))) { + bool is_part0 = part == &disk->part0; - /* now show the partitions */ - for (n = 0; n < disk_max_parts(disk); ++n) { - struct hd_struct *part = disk->part[n]; - - if (!part || !part->nr_sects) - continue; - printk(" %02x%02x %10llu %s\n", - MAJOR(part_devt(part)), MINOR(part_devt(part)), + printk("%s%s %10llu %s", is_part0 ? "" : " ", + bdevt_str(part_devt(part), devt_buf), (unsigned long long)part->nr_sects >> 1, - disk_name(disk, part->partno, buf)); + disk_name(disk, part->partno, name_buf)); + if (is_part0) { + if (disk->driverfs_dev != NULL && + disk->driverfs_dev->driver != NULL) + printk(" driver: %s\n", + disk->driverfs_dev->driver->name); + else + printk(" (driver?)\n"); + } else + printk("\n"); } + disk_part_iter_exit(&piter); } class_dev_iter_exit(&iter); } @@ -320,7 +686,7 @@ static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos) struct class_dev_iter *iter; struct device *dev; - iter = kmalloc(GFP_KERNEL, sizeof(*iter)); + iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return ERR_PTR(-ENOMEM); @@ -363,7 +729,7 @@ static void *show_partition_start(struct seq_file *seqf, loff_t *pos) static void *p; p = disk_seqf_start(seqf, pos); - if (!IS_ERR(p) && p) + if (!IS_ERR(p) && p && !*pos) seq_puts(seqf, "major minor #blocks name\n\n"); return p; } @@ -371,42 +737,47 @@ static void *show_partition_start(struct seq_file *seqf, loff_t *pos) static int show_partition(struct seq_file *seqf, void *v) { struct gendisk *sgp = v; - int n; + struct disk_part_iter piter; + struct hd_struct *part; char buf[BDEVNAME_SIZE]; /* Don't show non-partitionable removeable devices or empty devices */ - if (!get_capacity(sgp) || (!disk_max_parts(sgp) && + if (!get_capacity(sgp) || (!disk_partitionable(sgp) && (sgp->flags & GENHD_FL_REMOVABLE))) return 0; if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO) return 0; /* show the full disk and all non-0 size partitions of it */ - seq_printf(seqf, "%4d %4d %10llu %s\n", - MAJOR(disk_devt(sgp)), MINOR(disk_devt(sgp)), - (unsigned long long)get_capacity(sgp) >> 1, - disk_name(sgp, 0, buf)); - for (n = 0; n < disk_max_parts(sgp); n++) { - struct hd_struct *part = sgp->part[n]; - if (!part) - continue; - if (part->nr_sects == 0) - continue; - seq_printf(seqf, "%4d %4d %10llu %s\n", + disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0); + while ((part = disk_part_iter_next(&piter))) + seq_printf(seqf, "%4d %7d %10llu %s\n", MAJOR(part_devt(part)), MINOR(part_devt(part)), (unsigned long long)part->nr_sects >> 1, disk_name(sgp, part->partno, buf)); - } + disk_part_iter_exit(&piter); return 0; } -const struct seq_operations partitions_op = { +static const struct seq_operations partitions_op = { .start = show_partition_start, .next = disk_seqf_next, .stop = disk_seqf_stop, .show = show_partition }; + +static int partitions_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &partitions_op); +} + +static const struct file_operations proc_partitions_operations = { + .open = partitions_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; #endif @@ -429,6 +800,8 @@ static int __init genhd_device_init(void) bdev_map = kobj_map_init(base_probe, &block_class_lock); blk_dev_init(); + register_blkdev(BLOCK_EXT_MAJOR, "blkext"); + #ifndef CONFIG_SYSFS_DEPRECATED /* create top-level block dir */ block_depr = kobject_create_and_add("block", NULL); @@ -446,29 +819,29 @@ static ssize_t disk_range_show(struct device *dev, return sprintf(buf, "%d\n", disk->minors); } -static ssize_t disk_removable_show(struct device *dev, +static ssize_t disk_ext_range_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", - (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0)); + return sprintf(buf, "%d\n", disk_max_parts(disk)); } -static ssize_t disk_ro_show(struct device *dev, +static ssize_t disk_removable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", disk->policy ? 1 : 0); + return sprintf(buf, "%d\n", + (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0)); } -static ssize_t disk_size_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t disk_ro_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%llu\n", (unsigned long long)get_capacity(disk)); + return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0); } static ssize_t disk_capability_show(struct device *dev, @@ -479,81 +852,48 @@ static ssize_t disk_capability_show(struct device *dev, return sprintf(buf, "%x\n", disk->flags); } -static ssize_t disk_stat_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct gendisk *disk = dev_to_disk(dev); - - preempt_disable(); - disk_round_stats(disk); - preempt_enable(); - return sprintf(buf, - "%8lu %8lu %8llu %8u " - "%8lu %8lu %8llu %8u " - "%8u %8u %8u" - "\n", - disk_stat_read(disk, ios[READ]), - disk_stat_read(disk, merges[READ]), - (unsigned long long)disk_stat_read(disk, sectors[READ]), - jiffies_to_msecs(disk_stat_read(disk, ticks[READ])), - disk_stat_read(disk, ios[WRITE]), - disk_stat_read(disk, merges[WRITE]), - (unsigned long long)disk_stat_read(disk, sectors[WRITE]), - jiffies_to_msecs(disk_stat_read(disk, ticks[WRITE])), - disk->in_flight, - jiffies_to_msecs(disk_stat_read(disk, io_ticks)), - jiffies_to_msecs(disk_stat_read(disk, time_in_queue))); -} - -#ifdef CONFIG_FAIL_MAKE_REQUEST -static ssize_t disk_fail_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t disk_alignment_offset_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", disk->flags & GENHD_FL_FAIL ? 1 : 0); + return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue)); } -static ssize_t disk_fail_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gendisk *disk = dev_to_disk(dev); - int i; - - if (count > 0 && sscanf(buf, "%d", &i) > 0) { - if (i == 0) - disk->flags &= ~GENHD_FL_FAIL; - else - disk->flags |= GENHD_FL_FAIL; - } - - return count; -} - -#endif - static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL); +static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL); static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL); -static DEVICE_ATTR(size, S_IRUGO, disk_size_show, NULL); +static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); +static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); -static DEVICE_ATTR(stat, S_IRUGO, disk_stat_show, NULL); +static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = - __ATTR(make-it-fail, S_IRUGO|S_IWUSR, disk_fail_show, disk_fail_store); + __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); +#endif +#ifdef CONFIG_FAIL_IO_TIMEOUT +static struct device_attribute dev_attr_fail_timeout = + __ATTR(io-timeout-fail, S_IRUGO|S_IWUSR, part_timeout_show, + part_timeout_store); #endif static struct attribute *disk_attrs[] = { &dev_attr_range.attr, + &dev_attr_ext_range.attr, &dev_attr_removable.attr, &dev_attr_ro.attr, &dev_attr_size.attr, + &dev_attr_alignment_offset.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif +#ifdef CONFIG_FAIL_IO_TIMEOUT + &dev_attr_fail_timeout.attr, +#endif NULL }; @@ -566,23 +906,110 @@ static struct attribute_group *disk_attr_groups[] = { NULL }; +static void disk_free_ptbl_rcu_cb(struct rcu_head *head) +{ + struct disk_part_tbl *ptbl = + container_of(head, struct disk_part_tbl, rcu_head); + + kfree(ptbl); +} + +/** + * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way + * @disk: disk to replace part_tbl for + * @new_ptbl: new part_tbl to install + * + * Replace disk->part_tbl with @new_ptbl in RCU-safe way. The + * original ptbl is freed using RCU callback. + * + * LOCKING: + * Matching bd_mutx locked. + */ +static void disk_replace_part_tbl(struct gendisk *disk, + struct disk_part_tbl *new_ptbl) +{ + struct disk_part_tbl *old_ptbl = disk->part_tbl; + + rcu_assign_pointer(disk->part_tbl, new_ptbl); + + if (old_ptbl) { + rcu_assign_pointer(old_ptbl->last_lookup, NULL); + call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb); + } +} + +/** + * disk_expand_part_tbl - expand disk->part_tbl + * @disk: disk to expand part_tbl for + * @partno: expand such that this partno can fit in + * + * Expand disk->part_tbl such that @partno can fit in. disk->part_tbl + * uses RCU to allow unlocked dereferencing for stats and other stuff. + * + * LOCKING: + * Matching bd_mutex locked, might sleep. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int disk_expand_part_tbl(struct gendisk *disk, int partno) +{ + struct disk_part_tbl *old_ptbl = disk->part_tbl; + struct disk_part_tbl *new_ptbl; + int len = old_ptbl ? old_ptbl->len : 0; + int target = partno + 1; + size_t size; + int i; + + /* disk_max_parts() is zero during initialization, ignore if so */ + if (disk_max_parts(disk) && target > disk_max_parts(disk)) + return -EINVAL; + + if (target <= len) + return 0; + + size = sizeof(*new_ptbl) + target * sizeof(new_ptbl->part[0]); + new_ptbl = kzalloc_node(size, GFP_KERNEL, disk->node_id); + if (!new_ptbl) + return -ENOMEM; + + INIT_RCU_HEAD(&new_ptbl->rcu_head); + new_ptbl->len = target; + + for (i = 0; i < len; i++) + rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]); + + disk_replace_part_tbl(disk, new_ptbl); + return 0; +} + static void disk_release(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); kfree(disk->random); - kfree(disk->part); - free_disk_stats(disk); + disk_replace_part_tbl(disk, NULL); + free_part_stats(&disk->part0); kfree(disk); } struct class block_class = { .name = "block", }; +static char *block_nodename(struct device *dev) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (disk->nodename) + return disk->nodename(disk); + return NULL; +} + static struct device_type disk_type = { .name = "disk", .groups = disk_attr_groups, .release = disk_release, + .nodename = block_nodename, }; #ifdef CONFIG_PROC_FS @@ -596,44 +1023,25 @@ static struct device_type disk_type = { static int diskstats_show(struct seq_file *seqf, void *v) { struct gendisk *gp = v; + struct disk_part_iter piter; + struct hd_struct *hd; char buf[BDEVNAME_SIZE]; - int n; + int cpu; /* - if (&gp->dev.kobj.entry == block_class.devices.next) + if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next) seq_puts(seqf, "major minor name" " rio rmerge rsect ruse wio wmerge " "wsect wuse running use aveq" "\n\n"); */ - preempt_disable(); - disk_round_stats(gp); - preempt_enable(); - seq_printf(seqf, "%4d %4d %s %lu %lu %llu %u %lu %lu %llu %u %u %u %u\n", - MAJOR(disk_devt(gp)), MINOR(disk_devt(gp)), - disk_name(gp, 0, buf), - disk_stat_read(gp, ios[0]), disk_stat_read(gp, merges[0]), - (unsigned long long)disk_stat_read(gp, sectors[0]), - jiffies_to_msecs(disk_stat_read(gp, ticks[0])), - disk_stat_read(gp, ios[1]), disk_stat_read(gp, merges[1]), - (unsigned long long)disk_stat_read(gp, sectors[1]), - jiffies_to_msecs(disk_stat_read(gp, ticks[1])), - gp->in_flight, - jiffies_to_msecs(disk_stat_read(gp, io_ticks)), - jiffies_to_msecs(disk_stat_read(gp, time_in_queue))); - - /* now show all non-0 size partitions of it */ - for (n = 0; n < disk_max_parts(gp); n++) { - struct hd_struct *hd = gp->part[n]; - - if (!hd || !hd->nr_sects) - continue; - - preempt_disable(); - part_round_stats(hd); - preempt_enable(); - seq_printf(seqf, "%4d %4d %s %lu %lu %llu " + disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0); + while ((hd = disk_part_iter_next(&piter))) { + cpu = part_stat_lock(); + part_round_stats(cpu, hd); + part_stat_unlock(); + seq_printf(seqf, "%4d %7d %s %lu %lu %llu " "%u %lu %lu %llu %u %u %u %u\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), @@ -650,16 +1058,37 @@ static int diskstats_show(struct seq_file *seqf, void *v) jiffies_to_msecs(part_stat_read(hd, time_in_queue)) ); } + disk_part_iter_exit(&piter); return 0; } -const struct seq_operations diskstats_op = { +static const struct seq_operations diskstats_op = { .start = disk_seqf_start, .next = disk_seqf_next, .stop = disk_seqf_stop, .show = diskstats_show }; + +static int diskstats_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &diskstats_op); +} + +static const struct file_operations proc_diskstats_operations = { + .open = diskstats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_genhd_init(void) +{ + proc_create("diskstats", 0, NULL, &proc_diskstats_operations); + proc_create("partitions", 0, NULL, &proc_partitions_operations); + return 0; +} +module_init(proc_genhd_init); #endif /* CONFIG_PROC_FS */ static void media_change_notify_thread(struct work_struct *work) @@ -672,7 +1101,7 @@ static void media_change_notify_thread(struct work_struct *work) * set enviroment vars to indicate which event this is for * so that user space will know to go check the media status. */ - kobject_uevent_env(&gd->dev.kobj, KOBJ_CHANGE, envp); + kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp); put_device(gd->driverfs_dev); } @@ -694,23 +1123,26 @@ 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 hd_struct *part; - if (strcmp(dev->bus_id, name)) - continue; - if (partno < 0 || partno > disk_max_parts(disk)) + if (strcmp(dev_name(dev), name)) continue; - if (partno == 0) - devt = disk_devt(disk); - else { - struct hd_struct *part = disk->part[partno - 1]; - - if (!part || !part->nr_sects) - continue; - + if (partno < disk->minors) { + /* We need to return the right devno, even + * if the partition doesn't exist yet. + */ + devt = MKDEV(MAJOR(dev->devt), + MINOR(dev->devt) + partno); + break; + } + part = disk_get_part(disk, partno); + if (part) { devt = part_devt(part); + disk_put_part(part); + break; } - break; + disk_put_part(part); } class_dev_iter_exit(&iter); return devt; @@ -721,6 +1153,7 @@ struct gendisk *alloc_disk(int minors) { return alloc_disk_node(minors, -1); } +EXPORT_SYMBOL(alloc_disk); struct gendisk *alloc_disk_node(int minors, int node_id) { @@ -729,32 +1162,28 @@ struct gendisk *alloc_disk_node(int minors, int node_id) disk = kmalloc_node(sizeof(struct gendisk), GFP_KERNEL | __GFP_ZERO, node_id); if (disk) { - if (!init_disk_stats(disk)) { + if (!init_part_stats(&disk->part0)) { kfree(disk); return NULL; } - if (minors > 1) { - int size = (minors - 1) * sizeof(struct hd_struct *); - disk->part = kmalloc_node(size, - GFP_KERNEL | __GFP_ZERO, node_id); - if (!disk->part) { - free_disk_stats(disk); - kfree(disk); - return NULL; - } + disk->node_id = node_id; + if (disk_expand_part_tbl(disk, 0)) { + free_part_stats(&disk->part0); + kfree(disk); + return NULL; } + disk->part_tbl->part[0] = &disk->part0; + disk->minors = minors; rand_initialize_disk(disk); - disk->dev.class = &block_class; - disk->dev.type = &disk_type; - device_initialize(&disk->dev); + disk_to_dev(disk)->class = &block_class; + disk_to_dev(disk)->type = &disk_type; + device_initialize(disk_to_dev(disk)); INIT_WORK(&disk->async_notify, media_change_notify_thread); } return disk; } - -EXPORT_SYMBOL(alloc_disk); EXPORT_SYMBOL(alloc_disk_node); struct kobject *get_disk(struct gendisk *disk) @@ -767,7 +1196,7 @@ struct kobject *get_disk(struct gendisk *disk) owner = disk->fops->owner; if (owner && !try_module_get(owner)) return NULL; - kobj = kobject_get(&disk->dev.kobj); + kobj = kobject_get(&disk_to_dev(disk)->kobj); if (kobj == NULL) { module_put(owner); return NULL; @@ -781,27 +1210,28 @@ EXPORT_SYMBOL(get_disk); void put_disk(struct gendisk *disk) { if (disk) - kobject_put(&disk->dev.kobj); + kobject_put(&disk_to_dev(disk)->kobj); } EXPORT_SYMBOL(put_disk); void set_device_ro(struct block_device *bdev, int flag) { - if (bdev->bd_contains != bdev) - bdev->bd_part->policy = flag; - else - bdev->bd_disk->policy = flag; + bdev->bd_part->policy = flag; } EXPORT_SYMBOL(set_device_ro); void set_disk_ro(struct gendisk *disk, int flag) { - int i; - disk->policy = flag; - for (i = 0; i < disk_max_parts(disk); i++) - if (disk->part[i]) disk->part[i]->policy = flag; + struct disk_part_iter piter; + struct hd_struct *part; + + disk_part_iter_init(&piter, disk, + DISK_PITER_INCL_EMPTY | DISK_PITER_INCL_PART0); + while ((part = disk_part_iter_next(&piter))) + part->policy = flag; + disk_part_iter_exit(&piter); } EXPORT_SYMBOL(set_disk_ro); @@ -810,10 +1240,7 @@ int bdev_read_only(struct block_device *bdev) { if (!bdev) return 0; - else if (bdev->bd_contains != bdev) - return bdev->bd_part->policy; - else - return bdev->bd_disk->policy; + return bdev->bd_part->policy; } EXPORT_SYMBOL(bdev_read_only);