From 7ba1ba12eeef0aa7113beb16410ef8b7c748e18b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 30 Jun 2008 20:04:41 +0200 Subject: block: Block layer data integrity support Some block devices support verifying the integrity of requests by way of checksums or other protection information that is submitted along with the I/O. This patch implements support for generating and verifying integrity metadata, as well as correctly merging, splitting and cloning bios and requests that have this extra information attached. See Documentation/block/data-integrity.txt for more information. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/genhd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index ae7aec3cabee..524ec96f5a23 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -141,6 +141,9 @@ struct gendisk { struct disk_stats dkstats; #endif struct work_struct async_notify; +#ifdef CONFIG_BLK_DEV_INTEGRITY + struct blk_integrity *integrity; +#endif }; /* -- cgit v1.2.3 From 0b07de85a76e1346e675f0e98437378932473df7 Mon Sep 17 00:00:00 2001 From: Adel Gadllah Date: Thu, 26 Jun 2008 13:48:27 +0200 Subject: allow userspace to modify scsi command filter on per device basis This patch exports the per-gendisk command filter to user space through sysfs, so it can be changed by the system administrator. All users of the old cmd filter have been converted to use the new one. Original patch from Peter Jones. Signed-off-by: Adel Gadllah Signed-off-by: Peter Jones Signed-off-by: Jens Axboe --- include/linux/genhd.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 524ec96f5a23..e8787417f65a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -110,6 +110,14 @@ struct hd_struct { #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 #define GENHD_FL_FAIL 64 +#define BLK_SCSI_MAX_CMDS (256) +#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) + +struct blk_scsi_cmd_filter { + unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; + unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; + struct kobject kobj; +}; struct gendisk { int major; /* major number of driver */ @@ -120,6 +128,7 @@ struct gendisk { struct hd_struct **part; /* [indexed by minor] */ struct block_device_operations *fops; struct request_queue *queue; + struct blk_scsi_cmd_filter cmd_filter; void *private_data; sector_t capacity; -- cgit v1.2.3 From d805dda412346225a50af2d399d958a4bc676c38 Mon Sep 17 00:00:00 2001 From: Abdel Benamrouche Date: Fri, 25 Jul 2008 01:48:25 -0700 Subject: fs/partition/check.c: fix return value warning fs/partitions/check.c:381: warning: ignoring return value of ___device_add___, declared with attribute warn_unused_result [akpm@linux-foundation.org: multiple-return-statements-per-function are evil] Signed-off-by: Abdel Benamrouche Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e8787417f65a..118216f1bd3c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -541,7 +541,7 @@ extern dev_t blk_lookup_devt(const char *name, int part); extern char *disk_name (struct gendisk *hd, int part, char *buf); extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); -extern void add_partition(struct gendisk *, int, sector_t, sector_t, int); +extern int __must_check add_partition(struct gendisk *, int, sector_t, sector_t, int); extern void delete_partition(struct gendisk *, int); extern void printk_all_partitions(void); -- cgit v1.2.3 From abf5439370491dd6fbb4fe1a7939680d2a9bc9d4 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sat, 16 Aug 2008 14:10:05 +0900 Subject: block: move cmdfilter from gendisk to request_queue cmd_filter works only for the block layer SG_IO with SCSI block devices. It breaks scsi/sg.c, bsg, and the block layer SG_IO with SCSI character devices (such as st). We hit a kernel crash with them. The problem is that cmd_filter code accesses to gendisk (having struct blk_scsi_cmd_filter) via inode->i_bdev->bd_disk. It works for only SCSI block device files. With character device files, inode->i_bdev leads you to struct cdev. inode->i_bdev->bd_disk->blk_scsi_cmd_filter isn't safe. SCSI ULDs don't expose gendisk; they keep it private. bsg needs to be independent on any protocols. We shouldn't change ULDs to expose their gendisk. This patch moves struct blk_scsi_cmd_filter from gendisk to request_queue, a common object, which eveyone can access to. The user interface doesn't change; users can change the filters via /sys/block/. gendisk has a pointer to request_queue so the cmd_filter code accesses to struct blk_scsi_cmd_filter. Signed-off-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- include/linux/genhd.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 118216f1bd3c..be4f5e5bfe06 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -110,15 +110,6 @@ struct hd_struct { #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 #define GENHD_FL_FAIL 64 -#define BLK_SCSI_MAX_CMDS (256) -#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) - -struct blk_scsi_cmd_filter { - unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; - unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; - struct kobject kobj; -}; - struct gendisk { int major; /* major number of driver */ int first_minor; @@ -128,7 +119,6 @@ struct gendisk { struct hd_struct **part; /* [indexed by minor] */ struct block_device_operations *fops; struct request_queue *queue; - struct blk_scsi_cmd_filter cmd_filter; void *private_data; sector_t capacity; -- cgit v1.2.3 From 310a2c1012934f590192377f65940cad4aa72b15 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:47:17 +0900 Subject: block: misc updates This patch makes the following misc updates in preparation for disk->part dereference fix and extended block devt support. * implment part_to_disk() * fix comment about gendisk->part indexing * rename get_part() to disk_map_sector() * don't use n which is always zero while printing disk information in diskstats_show() Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index be4f5e5bfe06..c64e659c9843 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -116,7 +116,7 @@ struct gendisk { int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ char disk_name[32]; /* name of major driver */ - struct hd_struct **part; /* [indexed by minor] */ + struct hd_struct **part; /* [indexed by minor - 1] */ struct block_device_operations *fops; struct request_queue *queue; void *private_data; @@ -145,14 +145,21 @@ struct gendisk { #endif }; +static inline struct gendisk *part_to_disk(struct hd_struct *part) +{ + if (likely(part)) + return dev_to_disk((part)->dev.parent); + return NULL; +} + /* * Macros to operate on percpu disk statistics: * * The __ variants should only be called in critical sections. The full * variants disable/enable preemption. */ -static inline struct hd_struct *get_part(struct gendisk *gendiskp, - sector_t sector) +static inline struct hd_struct *disk_map_sector(struct gendisk *gendiskp, + sector_t sector) { struct hd_struct *part; int i; -- cgit v1.2.3 From cf771cb5a7b716f3f9e532fd42a1e3a0a75adec5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 3 Sep 2008 09:01:09 +0200 Subject: block: make variable and argument names more consistent In hd_struct, @partno is used to denote partition number and a number of other places use @part to denote hd_struct. Functions use @part and @index instead. This causes confusion and makes it difficult to use consistent variable names for hd_struct. Always use @partno if a variable represents partition number. Also, print out functions use @f or @part for seq_file argument. Use @seqf uniformly instead. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index c64e659c9843..d1723c0a8600 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -365,7 +365,7 @@ extern int get_blkdev_list(char *, int); extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); extern void unlink_gendisk(struct gendisk *gp); -extern struct gendisk *get_gendisk(dev_t dev, int *part); +extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); @@ -534,8 +534,8 @@ struct unixware_disklabel { #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 -extern dev_t blk_lookup_devt(const char *name, int part); -extern char *disk_name (struct gendisk *hd, int part, char *buf); +extern dev_t blk_lookup_devt(const char *name, int partno); +extern char *disk_name (struct gendisk *hd, int partno, char *buf); extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); extern int __must_check add_partition(struct gendisk *, int, sector_t, sector_t, int); @@ -553,16 +553,16 @@ extern void blk_register_region(dev_t devt, unsigned long range, void *data); extern void blk_unregister_region(dev_t devt, unsigned long range); -static inline struct block_device *bdget_disk(struct gendisk *disk, int index) +static inline struct block_device *bdget_disk(struct gendisk *disk, int partno) { - return bdget(MKDEV(disk->major, disk->first_minor) + index); + return bdget(MKDEV(disk->major, disk->first_minor) + partno); } #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } -static inline dev_t blk_lookup_devt(const char *name, int part) +static inline dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); return devt; -- cgit v1.2.3 From f331c0296f2a9fee0d396a70598b954062603015 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 3 Sep 2008 09:01:48 +0200 Subject: block: don't depend on consecutive minor space * Implement disk_devt() and part_devt() and use them to directly access devt instead of computing it from ->major and ->first_minor. Note that all references to ->major and ->first_minor outside of block layer is used to determine devt of the disk (the part0) and as ->major and ->first_minor will continue to represent devt for the disk, converting these users aren't strictly necessary. However, convert them for consistency. * Implement disk_max_parts() to avoid directly deferencing genhd->minors. * Update bdget_disk() such that it doesn't assume consecutive minor space. * Move devt computation from register_disk() to add_disk() and make it the only one (all other usages use the initially determined value). These changes clean up the code and will help disk->part dereference fix and extended block device numbers. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index d1723c0a8600..0ff75329199c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -111,10 +111,14 @@ struct hd_struct { #define GENHD_FL_FAIL 64 struct gendisk { + /* major, first_minor and minors are input parameters only, + * don't use directly. Use disk_devt() and disk_max_parts(). + */ int major; /* major number of driver */ int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ + char disk_name[32]; /* name of major driver */ struct hd_struct **part; /* [indexed by minor - 1] */ struct block_device_operations *fops; @@ -152,6 +156,21 @@ static inline struct gendisk *part_to_disk(struct hd_struct *part) return NULL; } +static inline int disk_max_parts(struct gendisk *disk) +{ + return disk->minors - 1; +} + +static inline dev_t disk_devt(struct gendisk *disk) +{ + return disk->dev.devt; +} + +static inline dev_t part_devt(struct hd_struct *part) +{ + return part->dev.devt; +} + /* * Macros to operate on percpu disk statistics: * @@ -163,7 +182,7 @@ static inline struct hd_struct *disk_map_sector(struct gendisk *gendiskp, { struct hd_struct *part; int i; - for (i = 0; i < gendiskp->minors - 1; i++) { + for (i = 0; i < disk_max_parts(gendiskp); i++) { part = gendiskp->part[i]; if (part && part->start_sect <= sector && sector < part->start_sect + part->nr_sects) @@ -366,6 +385,7 @@ extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); extern void unlink_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); +extern struct block_device *bdget_disk(struct gendisk *disk, int partno); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); @@ -553,11 +573,6 @@ extern void blk_register_region(dev_t devt, unsigned long range, void *data); extern void blk_unregister_region(dev_t devt, unsigned long range); -static inline struct block_device *bdget_disk(struct gendisk *disk, int partno) -{ - return bdget(MKDEV(disk->major, disk->first_minor) + partno); -} - #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } -- cgit v1.2.3 From e71bf0d0ee89e51b92776391c5634938236977d5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 3 Sep 2008 09:03:02 +0200 Subject: block: fix disk->part[] dereferencing race disk->part[] is protected by its matching bdev's lock. However, non-critical accesses like collecting stats and printing out sysfs and proc information used to be performed without any locking. As partitions can come and go dynamically, partitions can go away underneath those non-critical accesses. As some of those accesses are writes, this theoretically can lead to silent corruption. This patch fixes the race by using RCU for the partition array and dev reference counter to hold partitions. * Rename disk->part[] to disk->__part[] to make sure no one outside genhd layer proper accesses it directly. * Use RCU for disk->__part[] dereferencing. * Implement disk_{get|put}_part() which can be used to get and put partitions from gendisk respectively. * Iterators are implemented to help iterate through all partitions safely. * Functions which require RCU readlock are marked with _rcu suffix. * Use disk_put_part() in __blkdev_put() instead of directly putting the contained kobject. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 53 +++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 39 insertions(+), 14 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0ff75329199c..7fbba19e076b 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -11,6 +11,7 @@ #include #include +#include #ifdef CONFIG_BLOCK @@ -100,6 +101,7 @@ struct hd_struct { #else struct disk_stats dkstats; #endif + struct rcu_head rcu_head; }; #define GENHD_FL_REMOVABLE 1 @@ -120,7 +122,14 @@ struct gendisk { * disks that can't be partitioned. */ char disk_name[32]; /* name of major driver */ - struct hd_struct **part; /* [indexed by minor - 1] */ + + /* Array of pointers to partitions indexed by partno - 1. + * Protected with matching bdev lock but stat and other + * non-critical accesses use RCU. Always access through + * helpers. + */ + struct hd_struct **__part; + struct block_device_operations *fops; struct request_queue *queue; void *private_data; @@ -171,25 +180,41 @@ static inline dev_t part_devt(struct hd_struct *part) return part->dev.devt; } +extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno); + +static inline void disk_put_part(struct hd_struct *part) +{ + if (likely(part)) + put_device(&part->dev); +} + +/* + * Smarter partition iterator without context limits. + */ +#define DISK_PITER_REVERSE (1 << 0) /* iterate in the reverse direction */ +#define DISK_PITER_INCL_EMPTY (1 << 1) /* include 0-sized parts */ + +struct disk_part_iter { + struct gendisk *disk; + struct hd_struct *part; + int idx; + unsigned int flags; +}; + +extern void disk_part_iter_init(struct disk_part_iter *piter, + struct gendisk *disk, unsigned int flags); +extern struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter); +extern void disk_part_iter_exit(struct disk_part_iter *piter); + +extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, + sector_t sector); + /* * Macros to operate on percpu disk statistics: * * The __ variants should only be called in critical sections. The full * variants disable/enable preemption. */ -static inline struct hd_struct *disk_map_sector(struct gendisk *gendiskp, - sector_t sector) -{ - struct hd_struct *part; - int i; - for (i = 0; i < disk_max_parts(gendiskp); i++) { - part = gendiskp->part[i]; - if (part && part->start_sect <= sector - && sector < part->start_sect + part->nr_sects) - return part; - } - return NULL; -} #ifdef CONFIG_SMP #define __disk_stat_add(gendiskp, field, addnd) \ -- cgit v1.2.3 From c9959059161ddd7bf4670cf47367033d6b2f79c4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:47:21 +0900 Subject: block: fix diskstats access There are two variants of stat functions - ones prefixed with double underbars which don't care about preemption and ones without which disable preemption before manipulating per-cpu counters. It's unclear whether the underbarred ones assume that preemtion is disabled on entry as some callers don't do that. This patch unifies diskstats access by implementing disk_stat_lock() and disk_stat_unlock() which take care of both RCU (for partition access) and preemption (for per-cpu counter access). diskstats access should always be enclosed between the two functions. As such, there's no need for the versions which disables preemption. They're removed and double underbars ones are renamed to drop the underbars. As an extra argument is added, there's no danger of using the old version unconverted. disk_stat_lock() uses get_cpu() and returns the cpu index and all diskstat functions which access per-cpu counters now has @cpu argument to help RT. This change adds RCU or preemption operations at some places but also collapses several preemption ops into one at others. Overall, the performance difference should be negligible as all involved ops are very lightweight per-cpu ones. Signed-off-by: Tejun Heo Cc: Peter Zijlstra Signed-off-by: Jens Axboe --- include/linux/genhd.h | 139 +++++++++++++++++++++----------------------------- 1 file changed, 57 insertions(+), 82 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7fbba19e076b..ac8a901f2002 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -209,16 +209,24 @@ extern void disk_part_iter_exit(struct disk_part_iter *piter); extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); -/* +/* * Macros to operate on percpu disk statistics: * - * The __ variants should only be called in critical sections. The full - * variants disable/enable preemption. + * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters + * and should be called between disk_stat_lock() and + * disk_stat_unlock(). + * + * part_stat_read() can be called at any time. + * + * part_stat_{add|set_all}() and {init|free}_part_stats are for + * internal use only. */ - #ifdef CONFIG_SMP -#define __disk_stat_add(gendiskp, field, addnd) \ - (per_cpu_ptr(gendiskp->dkstats, smp_processor_id())->field += addnd) +#define disk_stat_lock() ({ rcu_read_lock(); get_cpu(); }) +#define disk_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) + +#define disk_stat_add(cpu, gendiskp, field, addnd) \ + (per_cpu_ptr(gendiskp->dkstats, cpu)->field += addnd) #define disk_stat_read(gendiskp, field) \ ({ \ @@ -229,7 +237,8 @@ extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, res; \ }) -static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) { +static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) +{ int i; for_each_possible_cpu(i) @@ -237,14 +246,14 @@ static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) { sizeof(struct disk_stats)); } -#define __part_stat_add(part, field, addnd) \ - (per_cpu_ptr(part->dkstats, smp_processor_id())->field += addnd) +#define part_stat_add(cpu, part, field, addnd) \ + (per_cpu_ptr(part->dkstats, cpu)->field += addnd) -#define __all_stat_add(gendiskp, part, field, addnd, sector) \ -({ \ - if (part) \ - __part_stat_add(part, field, addnd); \ - __disk_stat_add(gendiskp, field, addnd); \ +#define all_stat_add(cpu, gendiskp, part, field, addnd, sector) \ +({ \ + if (part) \ + part_stat_add(cpu, part, field, addnd); \ + disk_stat_add(cpu, gendiskp, field, addnd); \ }) #define part_stat_read(part, field) \ @@ -264,10 +273,13 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) memset(per_cpu_ptr(part->dkstats, i), value, sizeof(struct disk_stats)); } - + #else /* !CONFIG_SMP */ -#define __disk_stat_add(gendiskp, field, addnd) \ - (gendiskp->dkstats.field += addnd) +#define disk_stat_lock() ({ rcu_read_lock(); 0; }) +#define disk_stat_unlock() rcu_read_unlock() + +#define disk_stat_add(cpu, gendiskp, field, addnd) \ + (gendiskp->dkstats.field += addnd) #define disk_stat_read(gendiskp, field) (gendiskp->dkstats.field) static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) @@ -275,14 +287,14 @@ static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) memset(&gendiskp->dkstats, value, sizeof (struct disk_stats)); } -#define __part_stat_add(part, field, addnd) \ +#define part_stat_add(cpu, part, field, addnd) \ (part->dkstats.field += addnd) -#define __all_stat_add(gendiskp, part, field, addnd, sector) \ -({ \ - if (part) \ - part->dkstats.field += addnd; \ - __disk_stat_add(gendiskp, field, addnd); \ +#define all_stat_add(cpu, gendiskp, part, field, addnd, sector) \ +({ \ + if (part) \ + part_stat_add(cpu, part, field, addnd); \ + disk_stat_add(cpu, gendiskp, field, addnd); \ }) #define part_stat_read(part, field) (part->dkstats.field) @@ -294,63 +306,26 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) #endif /* CONFIG_SMP */ -#define disk_stat_add(gendiskp, field, addnd) \ - do { \ - preempt_disable(); \ - __disk_stat_add(gendiskp, field, addnd); \ - preempt_enable(); \ - } while (0) - -#define __disk_stat_dec(gendiskp, field) __disk_stat_add(gendiskp, field, -1) -#define disk_stat_dec(gendiskp, field) disk_stat_add(gendiskp, field, -1) - -#define __disk_stat_inc(gendiskp, field) __disk_stat_add(gendiskp, field, 1) -#define disk_stat_inc(gendiskp, field) disk_stat_add(gendiskp, field, 1) - -#define __disk_stat_sub(gendiskp, field, subnd) \ - __disk_stat_add(gendiskp, field, -subnd) -#define disk_stat_sub(gendiskp, field, subnd) \ - disk_stat_add(gendiskp, field, -subnd) - -#define part_stat_add(gendiskp, field, addnd) \ - do { \ - preempt_disable(); \ - __part_stat_add(gendiskp, field, addnd);\ - preempt_enable(); \ - } while (0) - -#define __part_stat_dec(gendiskp, field) __part_stat_add(gendiskp, field, -1) -#define part_stat_dec(gendiskp, field) part_stat_add(gendiskp, field, -1) - -#define __part_stat_inc(gendiskp, field) __part_stat_add(gendiskp, field, 1) -#define part_stat_inc(gendiskp, field) part_stat_add(gendiskp, field, 1) - -#define __part_stat_sub(gendiskp, field, subnd) \ - __part_stat_add(gendiskp, field, -subnd) -#define part_stat_sub(gendiskp, field, subnd) \ - part_stat_add(gendiskp, field, -subnd) - -#define all_stat_add(gendiskp, part, field, addnd, sector) \ - do { \ - preempt_disable(); \ - __all_stat_add(gendiskp, part, field, addnd, sector); \ - preempt_enable(); \ - } while (0) - -#define __all_stat_dec(gendiskp, field, sector) \ - __all_stat_add(gendiskp, field, -1, sector) -#define all_stat_dec(gendiskp, field, sector) \ - all_stat_add(gendiskp, field, -1, sector) - -#define __all_stat_inc(gendiskp, part, field, sector) \ - __all_stat_add(gendiskp, part, field, 1, sector) -#define all_stat_inc(gendiskp, part, field, sector) \ - all_stat_add(gendiskp, part, field, 1, sector) - -#define __all_stat_sub(gendiskp, part, field, subnd, sector) \ - __all_stat_add(gendiskp, part, field, -subnd, sector) -#define all_stat_sub(gendiskp, part, field, subnd, sector) \ - all_stat_add(gendiskp, part, field, -subnd, sector) +#define disk_stat_dec(cpu, gendiskp, field) \ + disk_stat_add(cpu, gendiskp, field, -1) +#define disk_stat_inc(cpu, gendiskp, field) \ + disk_stat_add(cpu, gendiskp, field, 1) +#define disk_stat_sub(cpu, gendiskp, field, subnd) \ + disk_stat_add(cpu, gendiskp, field, -subnd) + +#define part_stat_dec(cpu, gendiskp, field) \ + part_stat_add(cpu, gendiskp, field, -1) +#define part_stat_inc(cpu, gendiskp, field) \ + part_stat_add(cpu, gendiskp, field, 1) +#define part_stat_sub(cpu, gendiskp, field, subnd) \ + part_stat_add(cpu, gendiskp, field, -subnd) + +#define all_stat_dec(cpu, gendiskp, field, sector) \ + all_stat_add(cpu, gendiskp, field, -1, sector) +#define all_stat_inc(cpu, gendiskp, part, field, sector) \ + all_stat_add(cpu, gendiskp, part, field, 1, sector) +#define all_stat_sub(cpu, gendiskp, part, field, subnd, sector) \ + all_stat_add(cpu, gendiskp, part, field, -subnd, sector) /* Inlines to alloc and free disk stats in struct gendisk */ #ifdef CONFIG_SMP @@ -401,8 +376,8 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ /* drivers/block/ll_rw_blk.c */ -extern void disk_round_stats(struct gendisk *disk); -extern void part_round_stats(struct hd_struct *part); +extern void disk_round_stats(int cpu, struct gendisk *disk); +extern void part_round_stats(int cpu, struct hd_struct *part); /* drivers/block/genhd.c */ extern int get_blkdev_list(char *, int); -- cgit v1.2.3 From bcce3de1be61e424deef35d1e86e86a35c4b6e65 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:47:22 +0900 Subject: block: implement extended dev numbers Implement extended device numbers. A block driver can tell block layer that it wants to use extended device numbers. After the usual minor space is used up, block layer automatically allocates devt's from EXT_BLOCK_MAJOR. Currently only one major number is allocated for this but as the allocation is strictly on-demand, ~1mil minor space under it should suffice unless the system actually has more than ~1mil partitions and if that ever happens adding more majors to the extended devt area is easy. Due to internal implementation issues, the first partition can't be allocated on the extended area. In other words, genhd->minors should at least be 1. This limitation will be lifted by later changes. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index ac8a901f2002..6fc532424062 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -113,13 +113,15 @@ struct hd_struct { #define GENHD_FL_FAIL 64 struct gendisk { - /* major, first_minor and minors are input parameters only, - * don't use directly. Use disk_devt() and disk_max_parts(). + /* major, first_minor, minors and ext_minors are input + * parameters only, don't use directly. Use disk_devt() and + * disk_max_parts(). */ int major; /* major number of driver */ int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ + int ext_minors; /* number of extended dynamic minors */ char disk_name[32]; /* name of major driver */ @@ -167,7 +169,7 @@ static inline struct gendisk *part_to_disk(struct hd_struct *part) static inline int disk_max_parts(struct gendisk *disk) { - return disk->minors - 1; + return disk->minors + disk->ext_minors - 1; } static inline dev_t disk_devt(struct gendisk *disk) @@ -554,6 +556,8 @@ struct unixware_disklabel { #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 +extern int blk_alloc_devt(struct hd_struct *part, dev_t *devt); +extern void blk_free_devt(dev_t devt); extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); @@ -564,6 +568,9 @@ extern void printk_all_partitions(void); extern struct gendisk *alloc_disk_node(int minors, int node_id); extern struct gendisk *alloc_disk(int minors); +extern struct gendisk *alloc_disk_ext_node(int minors, int ext_minrs, + int node_id); +extern struct gendisk *alloc_disk_ext(int minors, int ext_minors); extern struct kobject *get_disk(struct gendisk *disk); extern void put_disk(struct gendisk *disk); extern void blk_register_region(dev_t devt, unsigned long range, -- cgit v1.2.3 From ed9e1982347b36573cd622ee5f4e2a7ccd79b3fd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:05 +0900 Subject: block: implement and use {disk|part}_to_dev() Implement {disk|part}_to_dev() and use them to access generic device instead of directly dereferencing {disk|part}->dev. To make sure no user is left behind, rename generic devices fields to __dev. This is in preparation of unifying partition 0 handling with other partitions. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fc532424062..e4e18c509ac5 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -15,9 +15,11 @@ #ifdef CONFIG_BLOCK -#define kobj_to_dev(k) container_of(k, struct device, kobj) -#define dev_to_disk(device) container_of(device, struct gendisk, dev) -#define dev_to_part(device) container_of(device, struct hd_struct, dev) +#define kobj_to_dev(k) container_of((k), struct device, kobj) +#define dev_to_disk(device) container_of((device), struct gendisk, __dev) +#define dev_to_part(device) container_of((device), struct hd_struct, __dev) +#define disk_to_dev(disk) (&((disk)->__dev)) +#define part_to_dev(part) (&((part)->__dev)) extern struct device_type part_type; extern struct kobject *block_depr; @@ -88,7 +90,7 @@ struct disk_stats { struct hd_struct { sector_t start_sect; sector_t nr_sects; - struct device dev; + struct device __dev; struct kobject *holder_dir; int policy, partno; #ifdef CONFIG_FAIL_MAKE_REQUEST @@ -139,7 +141,7 @@ struct gendisk { int flags; struct device *driverfs_dev; // FIXME: remove - struct device dev; + struct device __dev; struct kobject *holder_dir; struct kobject *slave_dir; @@ -163,7 +165,7 @@ struct gendisk { static inline struct gendisk *part_to_disk(struct hd_struct *part) { if (likely(part)) - return dev_to_disk((part)->dev.parent); + return dev_to_disk(part_to_dev(part)->parent); return NULL; } @@ -174,12 +176,12 @@ static inline int disk_max_parts(struct gendisk *disk) static inline dev_t disk_devt(struct gendisk *disk) { - return disk->dev.devt; + return disk_to_dev(disk)->devt; } static inline dev_t part_devt(struct hd_struct *part) { - return part->dev.devt; + return part_to_dev(part)->devt; } extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno); @@ -187,7 +189,7 @@ extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno); static inline void disk_put_part(struct hd_struct *part) { if (likely(part)) - put_device(&part->dev); + put_device(part_to_dev(part)); } /* -- cgit v1.2.3 From b5d0b9df0ba5d9a044f3a21e7544f53d90bd1465 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 3 Sep 2008 09:06:42 +0200 Subject: block: introduce partition 0 genhd and partition code handled disk and partitions separately. All information about the whole disk was in struct genhd and partitions in struct hd_struct. However, the whole disk (part0) and other partitions have a lot in common and the data structures end up having good number of common fields and thus separate code paths doing the same thing. Also, the partition array was indexed by partno - 1 which gets pretty confusing at times. This patch introduces partition 0 and makes the partition array indexed by partno. Following patches will unify the handling of disk and parts piece-by-piece. This patch also implements disk_partitionable() which tests whether a disk is partitionable. With coming dynamic partition array change, the most common usage of disk_max_parts() will be testing whether a disk is partitionable and the number of max partitions will become much less important. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e4e18c509ac5..9e866a2aee50 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -127,12 +127,13 @@ struct gendisk { char disk_name[32]; /* name of major driver */ - /* Array of pointers to partitions indexed by partno - 1. + /* Array of pointers to partitions indexed by partno. * Protected with matching bdev lock but stat and other * non-critical accesses use RCU. Always access through * helpers. */ struct hd_struct **__part; + struct hd_struct part0; struct block_device_operations *fops; struct request_queue *queue; @@ -171,7 +172,12 @@ static inline struct gendisk *part_to_disk(struct hd_struct *part) static inline int disk_max_parts(struct gendisk *disk) { - return disk->minors + disk->ext_minors - 1; + return disk->minors + disk->ext_minors; +} + +static inline bool disk_partitionable(struct gendisk *disk) +{ + return disk_max_parts(disk) > 1; } static inline dev_t disk_devt(struct gendisk *disk) @@ -197,6 +203,7 @@ static inline void disk_put_part(struct hd_struct *part) */ #define DISK_PITER_REVERSE (1 << 0) /* iterate in the reverse direction */ #define DISK_PITER_INCL_EMPTY (1 << 1) /* include 0-sized parts */ +#define DISK_PITER_INCL_PART0 (1 << 2) /* include partition 0 */ struct disk_part_iter { struct gendisk *disk; -- cgit v1.2.3 From 80795aefb76d10c5d698e60c7e7750b5330787da Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:07 +0900 Subject: block: move capacity from disk to part0 Move disk->capacity to part0->nr_sects and convert all users who directly accessed the field to use {get|set}_capacity(). This is done early to allow the __dev field to be moved. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9e866a2aee50..1cf828148ec6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -138,7 +138,6 @@ struct gendisk { struct block_device_operations *fops; struct request_queue *queue; void *private_data; - sector_t capacity; int flags; struct device *driverfs_dev; // FIXME: remove @@ -411,11 +410,11 @@ static inline sector_t get_start_sect(struct block_device *bdev) } static inline sector_t get_capacity(struct gendisk *disk) { - return disk->capacity; + return disk->part0.nr_sects; } static inline void set_capacity(struct gendisk *disk, sector_t size) { - disk->capacity = size; + disk->part0.nr_sects = size; } #ifdef CONFIG_SOLARIS_X86_PARTITION -- cgit v1.2.3 From 548b10eb2959c96cef6fc29fc96e0931eeb53bc5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 29 Aug 2008 09:01:47 +0200 Subject: block: move __dev from disk to part0 Move disk->__dev to part0->__dev. This simplifies bdget_disk() and lookup_devt() and allows common sysfs attributes to be unified. part_to_disk() is updated to handle part0 -> disk. Updated to include a fix from Bartlomiej Zolnierkiewicz , he writes: "part0 is a "special" partition and doesn't need to have capacity set - this fixes regression caused by "block: move __dev from disk to part0" commit." Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 1cf828148ec6..ff293ec8b3f7 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -16,9 +16,9 @@ #ifdef CONFIG_BLOCK #define kobj_to_dev(k) container_of((k), struct device, kobj) -#define dev_to_disk(device) container_of((device), struct gendisk, __dev) +#define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev) #define dev_to_part(device) container_of((device), struct hd_struct, __dev) -#define disk_to_dev(disk) (&((disk)->__dev)) +#define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) extern struct device_type part_type; @@ -141,7 +141,6 @@ struct gendisk { int flags; struct device *driverfs_dev; // FIXME: remove - struct device __dev; struct kobject *holder_dir; struct kobject *slave_dir; @@ -164,8 +163,12 @@ struct gendisk { static inline struct gendisk *part_to_disk(struct hd_struct *part) { - if (likely(part)) - return dev_to_disk(part_to_dev(part)->parent); + if (likely(part)) { + if (part->partno) + return dev_to_disk(part_to_dev(part)->parent); + else + return dev_to_disk(part_to_dev(part)); + } return NULL; } -- cgit v1.2.3 From e56105214943ce5f0901d20e972a7cfd0d1d0656 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:09 +0900 Subject: block: unify sysfs size node handling Now that capacity and __dev are moved to part0, part0 and others can share the same method. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index ff293ec8b3f7..9cb8380cf0eb 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -591,6 +591,9 @@ extern void blk_register_region(dev_t devt, unsigned long range, void *data); extern void blk_unregister_region(dev_t devt, unsigned long range); +extern ssize_t part_size_show(struct device *dev, + struct device_attribute *attr, char *buf); + #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } -- cgit v1.2.3 From b7db9956e57c8151b930d5e5fe5c766e6aad3ff7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:10 +0900 Subject: block: move policy from disk to part0 Move disk->policy to part0->policy. Implement and use get_disk_ro(). Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 9cb8380cf0eb..4411bdd671dd 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -145,7 +145,6 @@ struct gendisk { struct kobject *slave_dir; struct timer_rand_state *random; - int policy; atomic_t sync_io; /* RAID */ unsigned long stamp; @@ -403,6 +402,11 @@ extern struct block_device *bdget_disk(struct gendisk *disk, int partno); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); +static inline int get_disk_ro(struct gendisk *disk) +{ + return disk->part0.policy; +} + /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk); extern void rand_initialize_disk(struct gendisk *disk); -- cgit v1.2.3 From 4c46501d1659475dc6c89554af6ce7fe6ecf615c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:11 +0900 Subject: block: move holder_dir from disk to part0 Move disk->holder_dir to part0->holder_dir. Kill now mostly superflous bdev_get_holder(). While at it, kill superflous kobject_get/put() around holder_dir, slave_dir and cmd_filter creation and collapse disk_sysfs_add_subdirs() into register_disk(). These serve no purpose but obfuscating the code. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 4411bdd671dd..2c0e1b597ab4 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -141,7 +141,6 @@ struct gendisk { int flags; struct device *driverfs_dev; // FIXME: remove - struct kobject *holder_dir; struct kobject *slave_dir; struct timer_rand_state *random; -- cgit v1.2.3 From 0762b8bde9729f10f8e6249809660ff2ec3ad735 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:12 +0900 Subject: block: always set bdev->bd_part Till now, bdev->bd_part is set only if the bdev was for parts other than part0. This patch makes bdev->bd_part always set so that code paths don't have to differenciate common handling. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 2c0e1b597ab4..45a3682b5d87 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -412,7 +412,7 @@ extern void rand_initialize_disk(struct gendisk *disk); static inline sector_t get_start_sect(struct block_device *bdev) { - return bdev->bd_contains == bdev ? 0 : bdev->bd_part->start_sect; + return bdev->bd_part->start_sect; } static inline sector_t get_capacity(struct gendisk *disk) { -- cgit v1.2.3 From eddb2e26b5ee3c5da68ba4bf1921ba20e2097bff Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:13 +0900 Subject: block: kill GENHD_FL_FAIL and use part0->make_it_fail GENHD_FL_FAIL for disk is what make_it_fail is for parts. Kill it and use part0->make_it_fail. Sysfs node handling is unified too. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 45a3682b5d87..3d15b42dc352 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -112,7 +112,6 @@ struct hd_struct { #define GENHD_FL_CD 8 #define GENHD_FL_UP 16 #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 -#define GENHD_FL_FAIL 64 struct gendisk { /* major, first_minor, minors and ext_minors are input @@ -596,6 +595,13 @@ extern void blk_unregister_region(dev_t devt, unsigned long range); extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); +#ifdef CONFIG_FAIL_MAKE_REQUEST +extern ssize_t part_fail_show(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t part_fail_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count); +#endif /* CONFIG_FAIL_MAKE_REQUEST */ #else /* CONFIG_BLOCK */ -- cgit v1.2.3 From 074a7aca7afa6f230104e8e65eba3420263714a5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:14 +0900 Subject: block: move stats from disk to part0 Move stats related fields - stamp, in_flight, dkstats - from disk to part0 and unify stat handling such that... * part_stat_*() now updates part0 together if the specified partition is not part0. ie. part_stat_*() are now essentially all_stat_*(). * {disk|all}_stat_*() are gone. * part_round_stats() is updated similary. It handles part0 stats automatically and disk_round_stats() is killed. * part_{inc|dec}_in_fligh() is implemented which automatically updates part0 stats for parts other than part0. * disk_map_sector_rcu() is updated to return part0 if no part matches. Combined with the above changes, this makes NULL special case handling in callers unnecessary. * Separate stats show code paths for disk are collapsed into part stats show code paths. * Rename disk_stat_lock/unlock() to part_stat_lock/unlock() While at it, reposition stat handling macros a bit and add missing parentheses around macro parameters. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 159 ++++++++++++++------------------------------------ 1 file changed, 45 insertions(+), 114 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 3d15b42dc352..c90e1b4fbe5a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -145,13 +145,6 @@ struct gendisk { struct timer_rand_state *random; atomic_t sync_io; /* RAID */ - unsigned long stamp; - int in_flight; -#ifdef CONFIG_SMP - struct disk_stats *dkstats; -#else - struct disk_stats dkstats; -#endif struct work_struct async_notify; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity *integrity; @@ -232,46 +225,18 @@ extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, * internal use only. */ #ifdef CONFIG_SMP -#define disk_stat_lock() ({ rcu_read_lock(); get_cpu(); }) -#define disk_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) - -#define disk_stat_add(cpu, gendiskp, field, addnd) \ - (per_cpu_ptr(gendiskp->dkstats, cpu)->field += addnd) - -#define disk_stat_read(gendiskp, field) \ -({ \ - typeof(gendiskp->dkstats->field) res = 0; \ - int i; \ - for_each_possible_cpu(i) \ - res += per_cpu_ptr(gendiskp->dkstats, i)->field; \ - res; \ -}) - -static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) -{ - int i; - - for_each_possible_cpu(i) - memset(per_cpu_ptr(gendiskp->dkstats, i), value, - sizeof(struct disk_stats)); -} +#define part_stat_lock() ({ rcu_read_lock(); get_cpu(); }) +#define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) -#define part_stat_add(cpu, part, field, addnd) \ - (per_cpu_ptr(part->dkstats, cpu)->field += addnd) - -#define all_stat_add(cpu, gendiskp, part, field, addnd, sector) \ -({ \ - if (part) \ - part_stat_add(cpu, part, field, addnd); \ - disk_stat_add(cpu, gendiskp, field, addnd); \ -}) +#define __part_stat_add(cpu, part, field, addnd) \ + (per_cpu_ptr((part)->dkstats, (cpu))->field += (addnd)) #define part_stat_read(part, field) \ ({ \ - typeof(part->dkstats->field) res = 0; \ + typeof((part)->dkstats->field) res = 0; \ int i; \ for_each_possible_cpu(i) \ - res += per_cpu_ptr(part->dkstats, i)->field; \ + res += per_cpu_ptr((part)->dkstats, i)->field; \ res; \ }) @@ -284,109 +249,73 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) sizeof(struct disk_stats)); } -#else /* !CONFIG_SMP */ -#define disk_stat_lock() ({ rcu_read_lock(); 0; }) -#define disk_stat_unlock() rcu_read_unlock() - -#define disk_stat_add(cpu, gendiskp, field, addnd) \ - (gendiskp->dkstats.field += addnd) -#define disk_stat_read(gendiskp, field) (gendiskp->dkstats.field) - -static inline void disk_stat_set_all(struct gendisk *gendiskp, int value) +static inline int init_part_stats(struct hd_struct *part) { - memset(&gendiskp->dkstats, value, sizeof (struct disk_stats)); + part->dkstats = alloc_percpu(struct disk_stats); + if (!part->dkstats) + return 0; + return 1; } -#define part_stat_add(cpu, part, field, addnd) \ - (part->dkstats.field += addnd) - -#define all_stat_add(cpu, gendiskp, part, field, addnd, sector) \ -({ \ - if (part) \ - part_stat_add(cpu, part, field, addnd); \ - disk_stat_add(cpu, gendiskp, field, addnd); \ -}) - -#define part_stat_read(part, field) (part->dkstats.field) - -static inline void part_stat_set_all(struct hd_struct *part, int value) +static inline void free_part_stats(struct hd_struct *part) { - memset(&part->dkstats, value, sizeof(struct disk_stats)); + free_percpu(part->dkstats); } -#endif /* CONFIG_SMP */ - -#define disk_stat_dec(cpu, gendiskp, field) \ - disk_stat_add(cpu, gendiskp, field, -1) -#define disk_stat_inc(cpu, gendiskp, field) \ - disk_stat_add(cpu, gendiskp, field, 1) -#define disk_stat_sub(cpu, gendiskp, field, subnd) \ - disk_stat_add(cpu, gendiskp, field, -subnd) - -#define part_stat_dec(cpu, gendiskp, field) \ - part_stat_add(cpu, gendiskp, field, -1) -#define part_stat_inc(cpu, gendiskp, field) \ - part_stat_add(cpu, gendiskp, field, 1) -#define part_stat_sub(cpu, gendiskp, field, subnd) \ - part_stat_add(cpu, gendiskp, field, -subnd) +#else /* !CONFIG_SMP */ +#define part_stat_lock() ({ rcu_read_lock(); 0; }) +#define part_stat_unlock() rcu_read_unlock() -#define all_stat_dec(cpu, gendiskp, field, sector) \ - all_stat_add(cpu, gendiskp, field, -1, sector) -#define all_stat_inc(cpu, gendiskp, part, field, sector) \ - all_stat_add(cpu, gendiskp, part, field, 1, sector) -#define all_stat_sub(cpu, gendiskp, part, field, subnd, sector) \ - all_stat_add(cpu, gendiskp, part, field, -subnd, sector) +#define __part_stat_add(cpu, part, field, addnd) \ + ((part)->dkstats.field += addnd) -/* Inlines to alloc and free disk stats in struct gendisk */ -#ifdef CONFIG_SMP -static inline int init_disk_stats(struct gendisk *disk) -{ - disk->dkstats = alloc_percpu(struct disk_stats); - if (!disk->dkstats) - return 0; - return 1; -} +#define part_stat_read(part, field) ((part)->dkstats.field) -static inline void free_disk_stats(struct gendisk *disk) +static inline void part_stat_set_all(struct hd_struct *part, int value) { - free_percpu(disk->dkstats); + memset(&part->dkstats, value, sizeof(struct disk_stats)); } static inline int init_part_stats(struct hd_struct *part) { - part->dkstats = alloc_percpu(struct disk_stats); - if (!part->dkstats) - return 0; return 1; } static inline void free_part_stats(struct hd_struct *part) { - free_percpu(part->dkstats); } -#else /* CONFIG_SMP */ -static inline int init_disk_stats(struct gendisk *disk) -{ - return 1; -} +#endif /* CONFIG_SMP */ -static inline void free_disk_stats(struct gendisk *disk) -{ -} +#define part_stat_add(cpu, part, field, addnd) do { \ + __part_stat_add((cpu), (part), field, addnd); \ + if ((part)->partno) \ + __part_stat_add((cpu), &part_to_disk((part))->part0, \ + field, addnd); \ +} while (0) -static inline int init_part_stats(struct hd_struct *part) +#define part_stat_dec(cpu, gendiskp, field) \ + part_stat_add(cpu, gendiskp, field, -1) +#define part_stat_inc(cpu, gendiskp, field) \ + part_stat_add(cpu, gendiskp, field, 1) +#define part_stat_sub(cpu, gendiskp, field, subnd) \ + part_stat_add(cpu, gendiskp, field, -subnd) + +static inline void part_inc_in_flight(struct hd_struct *part) { - return 1; + part->in_flight++; + if (part->partno) + part_to_disk(part)->part0.in_flight++; } -static inline void free_part_stats(struct hd_struct *part) +static inline void part_dec_in_flight(struct hd_struct *part) { + part->in_flight--; + if (part->partno) + part_to_disk(part)->part0.in_flight--; } -#endif /* CONFIG_SMP */ /* drivers/block/ll_rw_blk.c */ -extern void disk_round_stats(int cpu, struct gendisk *disk); extern void part_round_stats(int cpu, struct hd_struct *part); /* drivers/block/genhd.c */ @@ -595,6 +524,8 @@ extern void blk_unregister_region(dev_t devt, unsigned long range); extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t part_stat_show(struct device *dev, + struct device_attribute *attr, char *buf); #ifdef CONFIG_FAIL_MAKE_REQUEST extern ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); -- cgit v1.2.3 From 540eed5637b766bb1e881ef744c42617760b4815 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:15 +0900 Subject: block: make partition array dynamic disk->__part used to be statically allocated to the maximum possible number of partitions. This patch makes partition array allocation dynamic. The added overhead is minimal as only real change is one memory dereference changed to RCU one. This saves both a bit of memory and cpu cycles iterating through unoccupied slots and makes increasing partition limit easier. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index c90e1b4fbe5a..ecf649c3deed 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -113,6 +113,21 @@ struct hd_struct { #define GENHD_FL_UP 16 #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 +#define BLK_SCSI_MAX_CMDS (256) +#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) + +struct blk_scsi_cmd_filter { + unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; + unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; + struct kobject kobj; +}; + +struct disk_part_tbl { + struct rcu_head rcu_head; + int len; + struct hd_struct *part[]; +}; + struct gendisk { /* major, first_minor, minors and ext_minors are input * parameters only, don't use directly. Use disk_devt() and @@ -131,7 +146,7 @@ struct gendisk { * non-critical accesses use RCU. Always access through * helpers. */ - struct hd_struct **__part; + struct disk_part_tbl *part_tbl; struct hd_struct part0; struct block_device_operations *fops; @@ -149,6 +164,7 @@ struct gendisk { #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity *integrity; #endif + int node_id; }; static inline struct gendisk *part_to_disk(struct hd_struct *part) @@ -503,6 +519,7 @@ extern void blk_free_devt(dev_t devt); extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); +extern int disk_expand_part_tbl(struct gendisk *disk, int target); extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); extern int __must_check add_partition(struct gendisk *, int, sector_t, sector_t, int); extern void delete_partition(struct gendisk *, int); -- cgit v1.2.3 From 689d6fac40b41c7bf154f362deaf442548e4dc81 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:16 +0900 Subject: block: replace @ext_minors with GENHD_FL_EXT_DEVT With previous changes, it's meaningless to limit the number of partitions. Replace @ext_minors with GENHD_FL_EXT_DEVT such that setting the flag allows the disk to have maximum number of allowed partitions (only limited by the number of entries in parsed_partitions as determined by MAX_PART constant). This kills not-too-pretty alloc_disk_ext[_node]() functions and makes @minors parameter to alloc_disk[_node]() unnecessary. The parameter is left alone to avoid disturbing the users. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index ecf649c3deed..04524c213de1 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -58,6 +58,8 @@ enum { UNIXWARE_PARTITION = 0x63, /* Same as GNU_HURD and SCO Unix */ }; +#define DISK_MAX_PARTS 256 + #include #include #include @@ -112,6 +114,7 @@ struct hd_struct { #define GENHD_FL_CD 8 #define GENHD_FL_UP 16 #define GENHD_FL_SUPPRESS_PARTITION_INFO 32 +#define GENHD_FL_EXT_DEVT 64 /* allow extended devt */ #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) @@ -129,15 +132,13 @@ struct disk_part_tbl { }; struct gendisk { - /* major, first_minor, minors and ext_minors are input - * parameters only, don't use directly. Use disk_devt() and - * disk_max_parts(). + /* major, first_minor and minors are input parameters only, + * don't use directly. Use disk_devt() and disk_max_parts(). */ int major; /* major number of driver */ int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ - int ext_minors; /* number of extended dynamic minors */ char disk_name[32]; /* name of major driver */ @@ -180,7 +181,9 @@ static inline struct gendisk *part_to_disk(struct hd_struct *part) static inline int disk_max_parts(struct gendisk *disk) { - return disk->minors + disk->ext_minors; + if (disk->flags & GENHD_FL_EXT_DEVT) + return DISK_MAX_PARTS; + return disk->minors; } static inline bool disk_partitionable(struct gendisk *disk) @@ -527,9 +530,6 @@ extern void printk_all_partitions(void); extern struct gendisk *alloc_disk_node(int minors, int node_id); extern struct gendisk *alloc_disk(int minors); -extern struct gendisk *alloc_disk_ext_node(int minors, int ext_minrs, - int node_id); -extern struct gendisk *alloc_disk_ext(int minors, int ext_minors); extern struct kobject *get_disk(struct gendisk *disk); extern void put_disk(struct gendisk *disk); extern void blk_register_region(dev_t devt, unsigned long range, -- cgit v1.2.3 From 3e1a7ff8a0a7b948f2684930166954f9e8e776fe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Aug 2008 19:56:17 +0900 Subject: block: allow disk to have extended device number Now that disk and partition handlings are mostly unified, it's easy to allow disk to have extended device number. This patch makes add_disk() use extended device number if disk->minors is zero. Both sd and ide-disk are updated to use this. * sd_format_disk_name() is implemented which can generically determine the drive name. This removes disk number restriction stemming from limited device names. * If sd index goes over SD_MAX_DISKS (which can be increased now BTW), sd simply doesn't initialize minors letting block layer choose extended device number. * If CONFIG_DEBUG_EXT_DEVT is set, both sd and ide-disk always set minors to 0 and use extended device numbers. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/genhd.h') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 04524c213de1..206cdf96c3a7 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -59,6 +59,7 @@ enum { }; #define DISK_MAX_PARTS 256 +#define DISK_NAME_LEN 32 #include #include @@ -140,7 +141,7 @@ struct gendisk { int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ - char disk_name[32]; /* name of major driver */ + char disk_name[DISK_NAME_LEN]; /* name of major driver */ /* Array of pointers to partitions indexed by partno. * Protected with matching bdev lock but stat and other -- cgit v1.2.3