The patch titled lockdep: annotate blkdev nesting has been added to the -mm tree. Its filename is lockdep-annotate-blkdev-nesting.patch See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find out what to do about this ------------------------------------------------------ Subject: lockdep: annotate blkdev nesting From: Ingo Molnar <mingo@xxxxxxx> Teach special (recursive) locking code to the lock validator. Effects on non-lockdep kernels: - the introduction of the following function variants: extern struct block_device *open_partition_by_devnum(dev_t, unsigned); extern int blkdev_put_partition(struct block_device *); static int blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags); which on non-lockdep are the same as open_by_devnum(), blkdev_put() and blkdev_get(). - a subclass parameter to do_open(). [unused on non-lockdep] - a subclass parameter to __blkdev_put(), which is a new internal function for the main blkdev_put*() functions. [parameter unused on non-lockdep kernels, except for two sanity check WARN_ON()s] these functions carry no semantical difference - they only express object dependencies towards the lockdep subsystem. Signed-off-by: Ingo Molnar <mingo@xxxxxxx> Signed-off-by: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxx> --- drivers/md/md.c | 6 +- fs/block_dev.c | 101 +++++++++++++++++++++++++++++++++++++------ include/linux/fs.h | 17 +++++++ 3 files changed, 108 insertions(+), 16 deletions(-) diff -puN drivers/md/md.c~lockdep-annotate-blkdev-nesting drivers/md/md.c --- a/drivers/md/md.c~lockdep-annotate-blkdev-nesting +++ a/drivers/md/md.c @@ -1406,7 +1406,7 @@ static int lock_rdev(mdk_rdev_t *rdev, d struct block_device *bdev; char b[BDEVNAME_SIZE]; - bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE); + bdev = open_partition_by_devnum(dev, FMODE_READ|FMODE_WRITE); if (IS_ERR(bdev)) { printk(KERN_ERR "md: could not open %s.\n", __bdevname(dev, b)); @@ -1416,7 +1416,7 @@ static int lock_rdev(mdk_rdev_t *rdev, d if (err) { printk(KERN_ERR "md: could not bd_claim %s.\n", bdevname(bdev, b)); - blkdev_put(bdev); + blkdev_put_partition(bdev); return err; } rdev->bdev = bdev; @@ -1430,7 +1430,7 @@ static void unlock_rdev(mdk_rdev_t *rdev if (!bdev) MD_BUG(); bd_release(bdev); - blkdev_put(bdev); + blkdev_put_partition(bdev); } void md_autodetect_dev(dev_t dev); diff -puN fs/block_dev.c~lockdep-annotate-blkdev-nesting fs/block_dev.c --- a/fs/block_dev.c~lockdep-annotate-blkdev-nesting +++ a/fs/block_dev.c @@ -741,7 +741,7 @@ static int bd_claim_by_kobject(struct bl if (!bo) return -ENOMEM; - mutex_lock(&bdev->bd_mutex); + mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION); res = bd_claim(bdev, holder); if (res || !add_bd_holder(bdev, bo)) free_bd_holder(bo); @@ -766,7 +766,7 @@ static void bd_release_from_kobject(stru if (!kobj) return; - mutex_lock(&bdev->bd_mutex); + mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_PARTITION); bd_release(bdev); if ((bo = del_bd_holder(bdev, kobj))) free_bd_holder(bo); @@ -824,6 +824,22 @@ struct block_device *open_by_devnum(dev_ EXPORT_SYMBOL(open_by_devnum); +static int +blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags); + +struct block_device *open_partition_by_devnum(dev_t dev, unsigned mode) +{ + struct block_device *bdev = bdget(dev); + int err = -ENOMEM; + int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY; + if (bdev) + err = blkdev_get_partition(bdev, mode, flags); + return err ? ERR_PTR(err) : bdev; +} + +EXPORT_SYMBOL(open_partition_by_devnum); + + /* * This routine checks whether a removable media has been changed, * and invalidates all buffer-cache-entries in that case. This @@ -874,7 +890,11 @@ void bd_set_size(struct block_device *bd } EXPORT_SYMBOL(bd_set_size); -static int do_open(struct block_device *bdev, struct file *file) +static int +blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags); + +static int +do_open(struct block_device *bdev, struct file *file, unsigned int subclass) { struct module *owner = NULL; struct gendisk *disk; @@ -891,7 +911,8 @@ static int do_open(struct block_device * } owner = disk->fops->owner; - mutex_lock(&bdev->bd_mutex); + mutex_lock_nested(&bdev->bd_mutex, subclass); + if (!bdev->bd_openers) { bdev->bd_disk = disk; bdev->bd_contains = bdev; @@ -918,11 +939,11 @@ static int do_open(struct block_device * ret = -ENOMEM; if (!whole) goto out_first; - ret = blkdev_get(whole, file->f_mode, file->f_flags); + ret = blkdev_get_whole(whole, file->f_mode, file->f_flags); if (ret) goto out_first; bdev->bd_contains = whole; - mutex_lock(&whole->bd_mutex); + mutex_lock_nested(&whole->bd_mutex, BD_MUTEX_WHOLE); whole->bd_part_count++; p = disk->part[part - 1]; bdev->bd_inode->i_data.backing_dev_info = @@ -950,7 +971,8 @@ static int do_open(struct block_device * if (bdev->bd_invalidated) rescan_partitions(bdev->bd_disk, bdev); } else { - mutex_lock(&bdev->bd_contains->bd_mutex); + mutex_lock_nested(&bdev->bd_contains->bd_mutex, + BD_MUTEX_PARTITION); bdev->bd_contains->bd_part_count++; mutex_unlock(&bdev->bd_contains->bd_mutex); } @@ -991,11 +1013,49 @@ int blkdev_get(struct block_device *bdev fake_file.f_dentry = &fake_dentry; fake_dentry.d_inode = bdev->bd_inode; - return do_open(bdev, &fake_file); + return do_open(bdev, &fake_file, BD_MUTEX_NORMAL); } EXPORT_SYMBOL(blkdev_get); +static int +blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags) +{ + /* + * This crockload is due to bad choice of ->open() type. + * It will go away. + * For now, block device ->open() routine must _not_ + * examine anything in 'inode' argument except ->i_rdev. + */ + struct file fake_file = {}; + struct dentry fake_dentry = {}; + fake_file.f_mode = mode; + fake_file.f_flags = flags; + fake_file.f_dentry = &fake_dentry; + fake_dentry.d_inode = bdev->bd_inode; + + return do_open(bdev, &fake_file, BD_MUTEX_WHOLE); +} + +static int +blkdev_get_partition(struct block_device *bdev, mode_t mode, unsigned flags) +{ + /* + * This crockload is due to bad choice of ->open() type. + * It will go away. + * For now, block device ->open() routine must _not_ + * examine anything in 'inode' argument except ->i_rdev. + */ + struct file fake_file = {}; + struct dentry fake_dentry = {}; + fake_file.f_mode = mode; + fake_file.f_flags = flags; + fake_file.f_dentry = &fake_dentry; + fake_dentry.d_inode = bdev->bd_inode; + + return do_open(bdev, &fake_file, BD_MUTEX_PARTITION); +} + static int blkdev_open(struct inode * inode, struct file * filp) { struct block_device *bdev; @@ -1011,7 +1071,7 @@ static int blkdev_open(struct inode * in bdev = bd_acquire(inode); - res = do_open(bdev, filp); + res = do_open(bdev, filp, BD_MUTEX_NORMAL); if (res) return res; @@ -1025,13 +1085,13 @@ static int blkdev_open(struct inode * in return res; } -int blkdev_put(struct block_device *bdev) +static int __blkdev_put(struct block_device *bdev, unsigned int subclass) { int ret = 0; struct inode *bd_inode = bdev->bd_inode; struct gendisk *disk = bdev->bd_disk; - mutex_lock(&bdev->bd_mutex); + mutex_lock_nested(&bdev->bd_mutex, subclass); lock_kernel(); if (!--bdev->bd_openers) { sync_blockdev(bdev); @@ -1041,7 +1101,9 @@ int blkdev_put(struct block_device *bdev if (disk->fops->release) ret = disk->fops->release(bd_inode, NULL); } else { - mutex_lock(&bdev->bd_contains->bd_mutex); + WARN_ON(subclass != 0); + mutex_lock_nested(&bdev->bd_contains->bd_mutex, + BD_MUTEX_PARTITION); bdev->bd_contains->bd_part_count--; mutex_unlock(&bdev->bd_contains->bd_mutex); } @@ -1058,7 +1120,8 @@ int blkdev_put(struct block_device *bdev bdev->bd_disk = NULL; bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info; if (bdev != bdev->bd_contains) { - blkdev_put(bdev->bd_contains); + WARN_ON(subclass != 0); + __blkdev_put(bdev->bd_contains, 1); } bdev->bd_contains = NULL; } @@ -1068,8 +1131,20 @@ int blkdev_put(struct block_device *bdev return ret; } +int blkdev_put(struct block_device *bdev) +{ + return __blkdev_put(bdev, BD_MUTEX_NORMAL); +} + EXPORT_SYMBOL(blkdev_put); +int blkdev_put_partition(struct block_device *bdev) +{ + return __blkdev_put(bdev, BD_MUTEX_PARTITION); +} + +EXPORT_SYMBOL(blkdev_put_partition); + static int blkdev_close(struct inode * inode, struct file * filp) { struct block_device *bdev = I_BDEV(filp->f_mapping->host); diff -puN include/linux/fs.h~lockdep-annotate-blkdev-nesting include/linux/fs.h --- a/include/linux/fs.h~lockdep-annotate-blkdev-nesting +++ a/include/linux/fs.h @@ -436,6 +436,21 @@ struct block_device { }; /* + * bdev->bd_mutex nesting subclasses for the lock validator: + * + * 0: normal + * 1: 'whole' + * 2: 'partition' + */ +enum bdev_bd_mutex_lock_class +{ + BD_MUTEX_NORMAL, + BD_MUTEX_WHOLE, + BD_MUTEX_PARTITION +}; + + +/* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache * radix trees */ @@ -1484,6 +1499,7 @@ extern void bd_set_size(struct block_dev extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern struct block_device *open_by_devnum(dev_t, unsigned); +extern struct block_device *open_partition_by_devnum(dev_t, unsigned); extern const struct file_operations def_blk_fops; extern const struct address_space_operations def_blk_aops; extern const struct file_operations def_chr_fops; @@ -1497,6 +1513,7 @@ extern int blkdev_driver_ioctl(struct in extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); extern int blkdev_get(struct block_device *, mode_t, unsigned); extern int blkdev_put(struct block_device *); +extern int blkdev_put_partition(struct block_device *); extern int bd_claim(struct block_device *, void *); extern void bd_release(struct block_device *); #ifdef CONFIG_SYSFS _ Patches currently in -mm which might be from mingo@xxxxxxx are origin.patch define-__raw_get_cpu_var-and-use-it.patch ide-cd-end-of-media-error-fix.patch lock-validator-introduce-warn_on_oncecond.patch emu10k1-mark-midi_spinlock-as-used.patch epoll-use-unlocked-wqueue-operations.patch pacct-none-delayed-process-accounting-accumulation.patch disable-debugging-version-of-write_lock.patch fix-drivers-mfd-ucb1x00-corec-irq-probing-bug.patch cifs-remove-f_ownerlock-use.patch lock-validator-fix-ns83820c-irq-flags-bug.patch revert-gregkh-pci-pci-test-that-drivers-properly-call-pci_set_master.patch x86-re-enable-generic-numa.patch i386-fix-softirq-accounting-with-4k-stacks.patch vdso-randomize-the-i386-vdso-by-moving-it-into-a-vma.patch vdso-randomize-the-i386-vdso-by-moving-it-into-a-vma-tidy.patch vdso-randomize-the-i386-vdso-by-moving-it-into-a-vma-arch_vma_name-fix.patch vdso-randomize-the-i386-vdso-by-moving-it-into-a-vma-vs-x86_64-mm-reliable-stack-trace-support-i386.patch vdso-randomize-the-i386-vdso-by-moving-it-into-a-vma-vs-x86_64-mm-reliable-stack-trace-support-i386-2.patch vdso-randomize-the-i386-vdso-by-moving-it-into-a-vma-vs-x86_64-mm-reliable-stack-trace-support-i386-2-revert-maxmem-change.patch work-around-ppc64-bootup-bug-by-making-mutex-debugging-save-restore-irqs.patch kernel-kernel-cpuc-to-mutexes.patch spin-rwlock-init-cleanups.patch time-clocksource-infrastructure.patch sched-fix-smt-nice-lock-contention-and-optimization.patch sched-fix-smt-nice-lock-contention-and-optimization-tidy.patch sched-comment-bitmap-size-accounting.patch sched-fix-interactive-ceiling-code.patch sched-cpu-hotplug-race-vs-set_cpus_allowed.patch sched-implement-smpnice.patch sched-protect-calculation-of-max_pull-from-integer-wrap.patch sched-store-weighted-load-on-up.patch sched-add-discrete-weighted-cpu-load-function.patch sched-prevent-high-load-weight-tasks-suppressing-balancing.patch sched-improve-stability-of-smpnice-load-balancing.patch sched-improve-smpnice-load-balancing-when-load-per-task.patch smpnice-dont-consider-sched-groups-which-are-lightly-loaded-for-balancing.patch smpnice-dont-consider-sched-groups-which-are-lightly-loaded-for-balancing-fix.patch sched-modify-move_tasks-to-improve-load-balancing-outcomes.patch sched-avoid-unnecessarily-moving-highest-priority-task-move_tasks.patch sched-avoid-unnecessarily-moving-highest-priority-task-move_tasks-fix-2.patch sched_domain-handle-kmalloc-failure.patch sched_domain-handle-kmalloc-failure-fix.patch sched_domain-dont-use-gfp_atomic.patch sched_domain-use-kmalloc_node.patch sched_domain-allocate-sched_group-structures-dynamically.patch sched-mc-smt-power-savings-sched-policy.patch sched-uninline-task_rq_lock.patch bug-if-setscheduler-is-called-from-interrupt-context.patch sched-add-above-background-load-function.patch mm-implement-swap-prefetching.patch pi-futex-futex-code-cleanups.patch pi-futex-robust-futex-docs-fix.patch pi-futex-introduce-debug_check_no_locks_freed.patch pi-futex-introduce-warn_on_smp.patch pi-futex-add-plist-implementation.patch pi-futex-scheduler-support-for-pi.patch pi-futex-rt-mutex-core.patch pi-futex-rt-mutex-docs.patch pi-futex-rt-mutex-docs-update.patch pi-futex-rt-mutex-debug.patch pi-futex-rt-mutex-tester.patch pi-futex-rt-mutex-tester-fix.patch pi-futex-rt-mutex-futex-api.patch pi-futex-futex_lock_pi-futex_unlock_pi-support.patch pi-futex-futex_lock_pi-futex_unlock_pi-support-fix.patch fix-rt-mutex-defaults-and-dependencies.patch drop-tasklist-lock-in-do_sched_setscheduler.patch rtmutex-modify-rtmutex-tester-to-test-the-setscheduler.patch rtmutex-propagate-priority-settings-into-pi-lock-chains.patch rtmutex-propagate-priority-settings-into-pi-lock-chains-fix.patch futex_requeue-optimization.patch fix-ide-deadlock-in-error-reporting-code.patch genirq-rename-desc-handler-to-desc-chip.patch genirq-rename-desc-handler-to-desc-chip-power-fix.patch genirq-rename-desc-handler-to-desc-chip-ia64-fix.patch genirq-rename-desc-handler-to-desc-chip-ia64-fix-2.patch genirq-rename-desc-handler-to-desc-chip-terminate_irqs-fix.patch genirq-sem2mutex-probe_sem-probing_active.patch genirq-cleanup-merge-irq_affinity-into-irq_desc.patch genirq-cleanup-remove-irq_descp.patch genirq-cleanup-remove-irq_descp-fix.patch genirq-cleanup-remove-fastcall.patch genirq-cleanup-misc-code-cleanups.patch genirq-cleanup-reduce-irq_desc_t-use-mark-it-obsolete.patch genirq-cleanup-include-linux-irqh.patch genirq-cleanup-merge-irq_dir-smp_affinity_entry-into-irq_desc.patch genirq-cleanup-merge-pending_irq_cpumask-into-irq_desc.patch genirq-cleanup-turn-arch_has_irq_per_cpu-into-config_irq_per_cpu.patch genirq-debug-better-debug-printout-in-enable_irq.patch genirq-add-retrigger-irq-op-to-consolidate-hw_irq_resend.patch genirq-doc-comment-include-linux-irqh-structures.patch genirq-doc-handle_irq_event-and-__do_irq-comments.patch genirq-cleanup-no_irq_type-cleanups.patch genirq-doc-add-design-documentation.patch genirq-add-genirq-sw-irq-retrigger.patch genirq-add-irq_noprobe-support.patch genirq-add-irq_norequest-support.patch genirq-add-irq_noautoen-support.patch genirq-update-copyrights.patch genirq-core.patch genirq-msi-fixes-2.patch genirq-add-irq-chip-support.patch genirq-add-irq-chip-support-fix.patch genirq-add-irq-chip-support-misroute-irq-dont-call-desc-chip-end.patch genirq-add-handle_bad_irq.patch genirq-add-irq-wake-power-management-support.patch genirq-add-sa_trigger-support.patch genirq-cleanup-no_irq_type-no_irq_chip-rename.patch genirq-more-verbose-debugging-on-unexpected-irq-vectors.patch genirq-ia64-build-fix.patch genirq-add-irq_type_sense_mask.patch genirq-add-irq-chip-support-fasteoi-handler-handle-interrupt-disabling.patch genirq-irq-document-what-an-irq-is.patch genirq-add-chip-eoi-fastack-fasteoi-core.patch genirq-add-chip-eoi-fastack-fasteoi-fix.patch lockdep-floppyc-irq-release-fix.patch lockdep-acpi-locking-fix.patch lockdep-console_init-after-local_irq_enable.patch lockdep-add-is_module_address.patch lockdep-add-print_ip_sym.patch lockdep-add-per_cpu_offset.patch lockdep-add-disable-enable_irq_lockdep-api.patch lockdep-add-local_irq_enable_in_hardirq-api.patch lockdep-add-declare_completion_onstack-api.patch lockdep-clean-up-rwsems.patch lockdep-rename-debug_warn_on.patch lockdep-remove-debug_bug_on.patch lockdep-remove-mutex-deadlock-checking-code.patch lockdep-better-lock-debugging.patch lockdep-mutex-section-binutils-workaround.patch lockdep-locking-init-debugging-improvement.patch lockdep-beautify-x86_64-stacktraces.patch lockdep-x86_64-document-stack-frame-internals.patch lockdep-i386-remove-multi-entry-backtraces.patch lockdep-stacktrace-subsystem-core.patch lockdep-s390-config_frame_pointer-support.patch lockdep-stacktrace-subsystem-i386-support.patch lockdep-stacktrace-subsystem-x86_64-support.patch lockdep-stacktrace-subsystem-s390-support.patch lockdep-irqtrace-subsystem-core.patch lockdep-irqtrace-subsystem-docs.patch lockdep-irqtrace-subsystem-i386-support.patch lockdep-irqtrace-subsystem-x86_64-support.patch lockdep-irqtrace-subsystem-s390-support.patch lockdep-locking-api-self-tests.patch lockdep-irqtrace-cleanup-of-include-asm-i386-irqflagsh.patch lockdep-irqtrace-cleanup-of-include-asm-x86_64-irqflagsh.patch lockdep-core.patch lockdep-design-docs.patch lockdep-procfs.patch lockdep-prove-rwsem-locking-correctness.patch lockdep-prove-spinlock-rwlock-locking-correctness.patch lockdep-prove-mutex-locking-correctness.patch lockdep-kconfig.patch lockdep-print-all-lock-classes-on-sysrq-d.patch lockdep-x86_64-early-init.patch lockdep-x86-smp-alternatives-workaround.patch lockdep-do-not-recurse-in-printk.patch lockdep-fix-rt_hash_lock_sz.patch lockdep-s390-turn-validator-off-in-machine-check-handler.patch lockdep-enable-on-i386.patch lockdep-enable-on-x86_64.patch lockdep-enable-on-s390.patch lockdep-annotate-direct-io.patch lockdep-annotate-serial.patch lockdep-annotate-dcache.patch lockdep-annotate-i_mutex.patch lockdep-annotate-futex.patch lockdep-annotate-genirq.patch lockdep-annotate-waitqueues.patch lockdep-annotate-mm.patch lockdep-annotate-serio.patch lockdep-annotate-skb_queue_head_init.patch lockdep-annotate-timer-base-locks.patch lockdep-annotate-scheduler-runqueue-locks.patch lockdep-annotate-hrtimer-base-locks.patch lockdep-annotate-sock_lock_init.patch lockdep-annotate-af_unix-locking.patch lockdep-annotate-bh_lock_sock.patch lockdep-annotate-ieee1394-skb-queue-head-locking.patch lockdep-annotate-mmap_sem.patch lockdep-annotate-sunrpc-code.patch lockdep-annotate-ntfs-locking-rules.patch lockdep-annotate-the-quota-code.patch lockdep-annotate-usbfs.patch lockdep-annotate-sound-core-seq-seq_portsc.patch lockdep-annotate-sound-core-seq-seq_devicec.patch lockdep-annotate-8390c-disable_irq.patch lockdep-annotate-3c59xc-disable_irq.patch lockdep-annotate-forcedethc-disable_irq.patch lockdep-annotate-enable_in_hardirq.patch lockdep-annotate-on-stack-completions.patch lockdep-annotate-qeth-driver.patch lockdep-annotate-s_lock.patch lockdep-annotate-sb-s_umount.patch lockdep-annotate-slab-code.patch lockdep-annotate-blkdev-nesting.patch acpi-reduce-code-size-clean-up-fix-validator-message.patch - To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html