From 426d31071ac476ea62c62656b242930c17b58c00 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Sat, 7 Aug 2010 12:30:03 +0200 Subject: fix printk typo 'faild' Signed-off-by: Paul Bolle Signed-off-by: Jiri Kosina --- kernel/trace/trace_kprobe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index f52b5f50299d..58716e73e2a2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -490,7 +490,7 @@ static int register_trace_probe(struct trace_probe *tp) } ret = register_probe_event(tp); if (ret) { - pr_warning("Faild to register probe event(%d)\n", ret); + pr_warning("Failed to register probe event(%d)\n", ret); goto end; } -- cgit v1.2.3 From 401a8d048eadfbe1b1c1bf53d3b614fcc894c61a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:36:00 +0200 Subject: workqueue: cleanup flush/cancel functions Make the following cleanup changes. * Relocate flush/cancel function prototypes and definitions. * Relocate wait_on_cpu_work() and wait_on_work() before try_to_grab_pending(). These will be used to implement flush_work_sync(). * Make all flush/cancel functions return bool instead of int. * Update wait_on_cpu_work() and wait_on_work() to return %true if they actually waited. * Add / update comments. This patch doesn't cause any functional changes. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 18 ++--- kernel/workqueue.c | 175 +++++++++++++++++++++++++--------------------- 2 files changed, 103 insertions(+), 90 deletions(-) (limited to 'kernel') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 07c48925a8fc..bb9b683ea6fa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -343,7 +343,6 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void flush_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); -extern void flush_delayed_work(struct delayed_work *work); extern int schedule_work(struct work_struct *work); extern int schedule_work_on(int cpu, struct work_struct *work); @@ -355,8 +354,11 @@ extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); -extern int flush_work(struct work_struct *work); -extern int cancel_work_sync(struct work_struct *work); +extern bool flush_work(struct work_struct *work); +extern bool cancel_work_sync(struct work_struct *work); + +extern bool flush_delayed_work(struct delayed_work *dwork); +extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); @@ -370,9 +372,9 @@ extern unsigned int work_busy(struct work_struct *work); * it returns 1 and the work doesn't re-arm itself. Run flush_workqueue() or * cancel_work_sync() to wait on it. */ -static inline int cancel_delayed_work(struct delayed_work *work) +static inline bool cancel_delayed_work(struct delayed_work *work) { - int ret; + bool ret; ret = del_timer_sync(&work->timer); if (ret) @@ -385,9 +387,9 @@ static inline int cancel_delayed_work(struct delayed_work *work) * if it returns 0 the timer function may be running and the queueing is in * progress. */ -static inline int __cancel_delayed_work(struct delayed_work *work) +static inline bool __cancel_delayed_work(struct delayed_work *work) { - int ret; + bool ret; ret = del_timer(&work->timer); if (ret) @@ -395,8 +397,6 @@ static inline int __cancel_delayed_work(struct delayed_work *work) return ret; } -extern int cancel_delayed_work_sync(struct delayed_work *work); - /* Obsolete. use cancel_delayed_work_sync() */ static inline void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f77afd939229..1240b9d94b03 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2327,16 +2327,24 @@ out_unlock: EXPORT_SYMBOL_GPL(flush_workqueue); /** - * flush_work - block until a work_struct's callback has terminated - * @work: the work which is to be flushed + * flush_work - wait for a work to finish executing the last queueing instance + * @work: the work to flush * - * Returns false if @work has already terminated. + * Wait until @work has finished execution. This function considers + * only the last queueing instance of @work. If @work has been + * enqueued across different CPUs on a non-reentrant workqueue or on + * multiple workqueues, @work might still be executing on return on + * some of the CPUs from earlier queueing. * - * It is expected that, prior to calling flush_work(), the caller has - * arranged for the work to not be requeued, otherwise it doesn't make - * sense to use this function. + * If @work was queued only on a non-reentrant, ordered or unbound + * workqueue, @work is guaranteed to be idle on return if it hasn't + * been requeued since flush started. + * + * RETURNS: + * %true if flush_work() waited for the work to finish execution, + * %false if it was already idle. */ -int flush_work(struct work_struct *work) +bool flush_work(struct work_struct *work) { struct worker *worker = NULL; struct global_cwq *gcwq; @@ -2374,13 +2382,49 @@ int flush_work(struct work_struct *work) wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); - return 1; + return true; already_gone: spin_unlock_irq(&gcwq->lock); - return 0; + return false; } EXPORT_SYMBOL_GPL(flush_work); +static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) +{ + struct wq_barrier barr; + struct worker *worker; + + spin_lock_irq(&gcwq->lock); + + worker = find_worker_executing_work(gcwq, work); + if (unlikely(worker)) + insert_wq_barrier(worker->current_cwq, &barr, work, worker); + + spin_unlock_irq(&gcwq->lock); + + if (unlikely(worker)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else + return false; +} + +static bool wait_on_work(struct work_struct *work) +{ + bool ret = false; + int cpu; + + might_sleep(); + + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); + + for_each_gcwq_cpu(cpu) + ret |= wait_on_cpu_work(get_gcwq(cpu), work); + return ret; +} + /* * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, * so this work can't be re-armed in any way. @@ -2423,39 +2467,7 @@ static int try_to_grab_pending(struct work_struct *work) return ret; } -static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) -{ - struct wq_barrier barr; - struct worker *worker; - - spin_lock_irq(&gcwq->lock); - - worker = find_worker_executing_work(gcwq, work); - if (unlikely(worker)) - insert_wq_barrier(worker->current_cwq, &barr, work, worker); - - spin_unlock_irq(&gcwq->lock); - - if (unlikely(worker)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - } -} - -static void wait_on_work(struct work_struct *work) -{ - int cpu; - - might_sleep(); - - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - - for_each_gcwq_cpu(cpu) - wait_on_cpu_work(get_gcwq(cpu), work); -} - -static int __cancel_work_timer(struct work_struct *work, +static bool __cancel_work_timer(struct work_struct *work, struct timer_list* timer) { int ret; @@ -2472,42 +2484,60 @@ static int __cancel_work_timer(struct work_struct *work, } /** - * cancel_work_sync - block until a work_struct's callback has terminated - * @work: the work which is to be flushed - * - * Returns true if @work was pending. + * cancel_work_sync - cancel a work and wait for it to finish + * @work: the work to cancel * - * cancel_work_sync() will cancel the work if it is queued. If the work's - * callback appears to be running, cancel_work_sync() will block until it - * has completed. + * Cancel @work and wait for its execution to finish. This function + * can be used even if the work re-queues itself or migrates to + * another workqueue. On return from this function, @work is + * guaranteed to be not pending or executing on any CPU. * - * It is possible to use this function if the work re-queues itself. It can - * cancel the work even if it migrates to another workqueue, however in that - * case it only guarantees that work->func() has completed on the last queued - * workqueue. - * - * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not - * pending, otherwise it goes into a busy-wait loop until the timer expires. + * cancel_work_sync(&delayed_work->work) must not be used for + * delayed_work's. Use cancel_delayed_work_sync() instead. * - * The caller must ensure that workqueue_struct on which this work was last + * The caller must ensure that the workqueue on which @work was last * queued can't be destroyed before this function returns. + * + * RETURNS: + * %true if @work was pending, %false otherwise. */ -int cancel_work_sync(struct work_struct *work) +bool cancel_work_sync(struct work_struct *work) { return __cancel_work_timer(work, NULL); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** - * cancel_delayed_work_sync - reliably kill off a delayed work. - * @dwork: the delayed work struct + * flush_delayed_work - wait for a dwork to finish executing the last queueing + * @dwork: the delayed work to flush + * + * Delayed timer is cancelled and the pending work is queued for + * immediate execution. Like flush_work(), this function only + * considers the last queueing instance of @dwork. + * + * RETURNS: + * %true if flush_work() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_delayed_work(struct delayed_work *dwork) +{ + if (del_timer_sync(&dwork->timer)) + __queue_work(raw_smp_processor_id(), + get_work_cwq(&dwork->work)->wq, &dwork->work); + return flush_work(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work); + +/** + * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish + * @dwork: the delayed work cancel * - * Returns true if @dwork was pending. + * This is cancel_work_sync() for delayed works. * - * It is possible to use this function if @dwork rearms itself via queue_work() - * or queue_delayed_work(). See also the comment for cancel_work_sync(). + * RETURNS: + * %true if @dwork was pending, %false otherwise. */ -int cancel_delayed_work_sync(struct delayed_work *dwork) +bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_timer(&dwork->work, &dwork->timer); } @@ -2558,23 +2588,6 @@ int schedule_delayed_work(struct delayed_work *dwork, } EXPORT_SYMBOL(schedule_delayed_work); -/** - * flush_delayed_work - block until a dwork_struct's callback has terminated - * @dwork: the delayed work which is to be flushed - * - * Any timeout is cancelled, and any pending work is run immediately. - */ -void flush_delayed_work(struct delayed_work *dwork) -{ - if (del_timer_sync(&dwork->timer)) { - __queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq, - &dwork->work); - put_cpu(); - } - flush_work(&dwork->work); -} -EXPORT_SYMBOL(flush_delayed_work); - /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use -- cgit v1.2.3 From baf59022c37d43f202e62d5130e4bac5e825b426 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:42:16 +0200 Subject: workqueue: factor out start_flush_work() Factor out start_flush_work() from flush_work(). start_flush_work() has @wait_executing argument which controls whether the barrier is queued only if the work is pending or also if executing. As flush_work() needs to wait for execution too, it uses %true. This commit doesn't cause any behavior difference. start_flush_work() will be used to implement flush_work_sync(). Signed-off-by: Tejun Heo --- kernel/workqueue.c | 64 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 37 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1240b9d94b03..33d31d768706 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2326,35 +2326,17 @@ out_unlock: } EXPORT_SYMBOL_GPL(flush_workqueue); -/** - * flush_work - wait for a work to finish executing the last queueing instance - * @work: the work to flush - * - * Wait until @work has finished execution. This function considers - * only the last queueing instance of @work. If @work has been - * enqueued across different CPUs on a non-reentrant workqueue or on - * multiple workqueues, @work might still be executing on return on - * some of the CPUs from earlier queueing. - * - * If @work was queued only on a non-reentrant, ordered or unbound - * workqueue, @work is guaranteed to be idle on return if it hasn't - * been requeued since flush started. - * - * RETURNS: - * %true if flush_work() waited for the work to finish execution, - * %false if it was already idle. - */ -bool flush_work(struct work_struct *work) +static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, + bool wait_executing) { struct worker *worker = NULL; struct global_cwq *gcwq; struct cpu_workqueue_struct *cwq; - struct wq_barrier barr; might_sleep(); gcwq = get_work_gcwq(work); if (!gcwq) - return 0; + return false; spin_lock_irq(&gcwq->lock); if (!list_empty(&work->entry)) { @@ -2367,26 +2349,54 @@ bool flush_work(struct work_struct *work) cwq = get_work_cwq(work); if (unlikely(!cwq || gcwq != cwq->gcwq)) goto already_gone; - } else { + } else if (wait_executing) { worker = find_worker_executing_work(gcwq, work); if (!worker) goto already_gone; cwq = worker->current_cwq; - } + } else + goto already_gone; - insert_wq_barrier(cwq, &barr, work, worker); + insert_wq_barrier(cwq, barr, work, worker); spin_unlock_irq(&gcwq->lock); lock_map_acquire(&cwq->wq->lockdep_map); lock_map_release(&cwq->wq->lockdep_map); - - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); return true; already_gone: spin_unlock_irq(&gcwq->lock); return false; } + +/** + * flush_work - wait for a work to finish executing the last queueing instance + * @work: the work to flush + * + * Wait until @work has finished execution. This function considers + * only the last queueing instance of @work. If @work has been + * enqueued across different CPUs on a non-reentrant workqueue or on + * multiple workqueues, @work might still be executing on return on + * some of the CPUs from earlier queueing. + * + * If @work was queued only on a non-reentrant, ordered or unbound + * workqueue, @work is guaranteed to be idle on return if it hasn't + * been requeued since flush started. + * + * RETURNS: + * %true if flush_work() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_work(struct work_struct *work) +{ + struct wq_barrier barr; + + if (start_flush_work(work, &barr, true)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else + return false; +} EXPORT_SYMBOL_GPL(flush_work); static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) -- cgit v1.2.3 From 09383498c5d35262e643bfdbae84826177a3c624 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:48:29 +0200 Subject: workqueue: implement flush[_delayed]_work_sync() Implement flush[_delayed]_work_sync(). These are flush functions which also make sure no CPU is still executing the target work from earlier queueing instances. These are similar to cancel[_delayed]_work_sync() except that the target work item is flushed instead of cancelled. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'kernel') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bb9b683ea6fa..e33ff4a91703 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -355,9 +355,11 @@ extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); +extern bool flush_work_sync(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); +extern bool flush_delayed_work_sync(struct delayed_work *work); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33d31d768706..19e4bc15ee99 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2435,6 +2435,41 @@ static bool wait_on_work(struct work_struct *work) return ret; } +/** + * flush_work_sync - wait until a work has finished execution + * @work: the work to flush + * + * Wait until @work has finished execution. On return, it's + * guaranteed that all queueing instances of @work which happened + * before this function is called are finished. In other words, if + * @work hasn't been requeued since this function was called, @work is + * guaranteed to be idle on return. + * + * RETURNS: + * %true if flush_work_sync() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_work_sync(struct work_struct *work) +{ + struct wq_barrier barr; + bool pending, waited; + + /* we'll wait for executions separately, queue barr only if pending */ + pending = start_flush_work(work, &barr, false); + + /* wait for executions to finish */ + waited = wait_on_work(work); + + /* wait for the pending one */ + if (pending) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + } + + return pending || waited; +} +EXPORT_SYMBOL_GPL(flush_work_sync); + /* * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, * so this work can't be re-armed in any way. @@ -2538,6 +2573,27 @@ bool flush_delayed_work(struct delayed_work *dwork) } EXPORT_SYMBOL(flush_delayed_work); +/** + * flush_delayed_work_sync - wait for a dwork to finish + * @dwork: the delayed work to flush + * + * Delayed timer is cancelled and the pending work is queued for + * execution immediately. Other than timer handling, its behavior + * is identical to flush_work_sync(). + * + * RETURNS: + * %true if flush_work_sync() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_delayed_work_sync(struct delayed_work *dwork) +{ + if (del_timer_sync(&dwork->timer)) + __queue_work(raw_smp_processor_id(), + get_work_cwq(&dwork->work)->wq, &dwork->work); + return flush_work_sync(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work_sync); + /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel -- cgit v1.2.3 From 676cb02dc32adef13d9efb5ea52079e4ede1e3ec Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 20 Jul 2009 23:33:49 +0200 Subject: softirqs: Make wakeup_softirqd static No users outside of kernel/softirq.c Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 1 - kernel/softirq.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a0384a4d1e6f..0a9141e69241 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -410,7 +410,6 @@ extern void softirq_init(void); #define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0) extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); -extern void wakeup_softirqd(void); /* This is the worklist that queues up per-cpu softirq work. * diff --git a/kernel/softirq.c b/kernel/softirq.c index 07b4f1b1a73a..80f6e3bd1d2a 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -67,7 +67,7 @@ char *softirq_to_name[NR_SOFTIRQS] = { * to the pending events, so lets the scheduler to balance * the softirq load for us. */ -void wakeup_softirqd(void) +static void wakeup_softirqd(void) { /* Interrupts are disabled: no need to stop preemption */ struct task_struct *tsk = __get_cpu_var(ksoftirqd); -- cgit v1.2.3 From 99a51792dbb7e6e39b2a4ebcfe202f1dcc7354c4 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sat, 4 Sep 2010 18:52:50 -0700 Subject: kernel/pm_qos_params.c: Remove unnecessary casts of private_data Signed-off-by: Joe Perches Signed-off-by: Jiri Kosina --- kernel/pm_qos_params.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index 996a4dec5f96..49829c5b4b47 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -394,7 +394,7 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, } else return -EINVAL; - pm_qos_req = (struct pm_qos_request_list *)filp->private_data; + pm_qos_req = filp->private_data; pm_qos_update_request(pm_qos_req, value); return count; -- cgit v1.2.3 From db71922217a214e5c9268448e537b54fc1f301ea Mon Sep 17 00:00:00 2001 From: Jan Blunck Date: Sun, 15 Aug 2010 22:51:10 +0200 Subject: BKL: Explicitly add BKL around get_sb/fill_super This patch is a preparation necessary to remove the BKL from do_new_mount(). It explicitly adds calls to lock_kernel()/unlock_kernel() around get_sb/fill_super operations for filesystems that still uses the BKL. I've read through all the code formerly covered by the BKL inside do_kern_mount() and have satisfied myself that it doesn't need the BKL any more. do_kern_mount() is already called without the BKL when mounting the rootfs and in nfsctl. do_kern_mount() calls vfs_kern_mount(), which is called from various places without BKL: simple_pin_fs(), nfs_do_clone_mount() through nfs_follow_mountpoint(), afs_mntpt_do_automount() through afs_mntpt_follow_link(). Both later functions are actually the filesystems follow_link inode operation. vfs_kern_mount() is calling the specified get_sb function and lets the filesystem do its job by calling the given fill_super function. Therefore I think it is safe to push down the BKL from the VFS to the low-level filesystems get_sb/fill_super operation. [arnd: do not add the BKL to those file systems that already don't use it elsewhere] Signed-off-by: Jan Blunck Signed-off-by: Arnd Bergmann Cc: Matthew Wilcox Cc: Christoph Hellwig --- fs/adfs/super.c | 8 +++++++- fs/affs/super.c | 9 ++++++++- fs/afs/super.c | 5 +++++ fs/bfs/inode.c | 8 +++++++- fs/cifs/cifsfs.c | 12 ++++++++++-- fs/coda/inode.c | 8 +++++++- fs/ecryptfs/main.c | 4 ++++ fs/ext2/super.c | 10 ++++++++-- fs/ext3/super.c | 9 ++++++++- fs/ext4/super.c | 8 ++++++-- fs/fat/namei_msdos.c | 7 ++++++- fs/fat/namei_vfat.c | 7 ++++++- fs/freevxfs/vxfs_super.c | 7 ++++++- fs/hfs/super.c | 8 +++++++- fs/hpfs/super.c | 8 +++++++- fs/isofs/inode.c | 8 +++++++- fs/jffs2/super.c | 11 +++++++++-- fs/jfs/super.c | 12 ++++++++++-- fs/nilfs2/super.c | 8 +++++++- fs/ntfs/super.c | 5 +++++ fs/ocfs2/dlmfs/dlmfs.c | 9 ++++++++- fs/ocfs2/super.c | 5 +++++ fs/qnx4/inode.c | 8 +++++++- fs/smbfs/inode.c | 5 +++++ fs/squashfs/super.c | 6 ++++++ fs/udf/super.c | 8 +++++++- fs/ufs/super.c | 5 +++++ kernel/cgroup.c | 4 ++++ 28 files changed, 187 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 4a3af7075c1d..d9803f73236f 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -352,11 +352,15 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) struct adfs_sb_info *asb; struct inode *root; + lock_kernel(); + sb->s_flags |= MS_NODIRATIME; asb = kzalloc(sizeof(*asb), GFP_KERNEL); - if (!asb) + if (!asb) { + unlock_kernel(); return -ENOMEM; + } sb->s_fs_info = asb; /* set default options */ @@ -474,6 +478,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) goto error; } else sb->s_root->d_op = &adfs_dentry_operations; + unlock_kernel(); return 0; error_free_bh: @@ -481,6 +486,7 @@ error_free_bh: error: sb->s_fs_info = NULL; kfree(asb); + unlock_kernel(); return -EINVAL; } diff --git a/fs/affs/super.c b/fs/affs/super.c index 33c4e7eef470..3a6d1dee4a51 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -291,6 +291,8 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) u8 sig[4]; int ret = -EINVAL; + lock_kernel(); + save_mount_options(sb, data); pr_debug("AFFS: read_super(%s)\n",data ? (const char *)data : "no options"); @@ -300,8 +302,10 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= MS_NODIRATIME; sbi = kzalloc(sizeof(struct affs_sb_info), GFP_KERNEL); - if (!sbi) + if (!sbi) { + unlock_kernel(); return -ENOMEM; + } sb->s_fs_info = sbi; mutex_init(&sbi->s_bmlock); spin_lock_init(&sbi->symlink_lock); @@ -312,6 +316,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) printk(KERN_ERR "AFFS: Error parsing options\n"); kfree(sbi->s_prefix); kfree(sbi); + unlock_kernel(); return -EINVAL; } /* N.B. after this point s_prefix must be released */ @@ -482,6 +487,7 @@ got_root: sb->s_root->d_op = &affs_dentry_operations; pr_debug("AFFS: s_flags=%lX\n",sb->s_flags); + unlock_kernel(); return 0; /* @@ -496,6 +502,7 @@ out_error_noinode: kfree(sbi->s_prefix); kfree(sbi); sb->s_fs_info = NULL; + unlock_kernel(); return ret; } diff --git a/fs/afs/super.c b/fs/afs/super.c index 77e1e5a61154..6c2fef44d385 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -302,12 +302,15 @@ static int afs_fill_super(struct super_block *sb, void *data) struct inode *inode = NULL; int ret; + lock_kernel(); + _enter(""); /* allocate a superblock info record */ as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); if (!as) { _leave(" = -ENOMEM"); + unlock_kernel(); return -ENOMEM; } @@ -341,6 +344,7 @@ static int afs_fill_super(struct super_block *sb, void *data) sb->s_root = root; _leave(" = 0"); + unlock_kernel(); return 0; error_inode: @@ -354,6 +358,7 @@ error: sb->s_fs_info = NULL; _leave(" = %d", ret); + unlock_kernel(); return ret; } diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index c4daf0f5fc02..d2e09363dd93 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -322,9 +322,13 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) int ret = -EINVAL; unsigned long i_sblock, i_eblock, i_eoff, s_size; + lock_kernel(); + info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) + if (!info) { + unlock_kernel(); return -ENOMEM; + } mutex_init(&info->bfs_lock); s->s_fs_info = info; @@ -439,6 +443,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) brelse(bh); brelse(sbh); dump_imap("read_super", s); + unlock_kernel(); return 0; out3: @@ -452,6 +457,7 @@ out: mutex_destroy(&info->bfs_lock); kfree(info); s->s_fs_info = NULL; + unlock_kernel(); return ret; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index b7431afdd76d..070bf1aecd2d 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -514,22 +514,30 @@ cifs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { int rc; - struct super_block *sb = sget(fs_type, NULL, set_anon_super, NULL); + struct super_block *sb; + + lock_kernel(); + + sb = sget(fs_type, NULL, set_anon_super, NULL); cFYI(1, "Devname: %s flags: %d ", dev_name, flags); - if (IS_ERR(sb)) + if (IS_ERR(sb)) { + unlock_kernel(); return PTR_ERR(sb); + } sb->s_flags = flags; rc = cifs_read_super(sb, data, dev_name, flags & MS_SILENT ? 1 : 0); if (rc) { deactivate_locked_super(sb); + unlock_kernel(); return rc; } sb->s_flags |= MS_ACTIVE; simple_set_mnt(mnt, sb); + unlock_kernel(); return 0; } diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 6526e6f21ecf..bfe8179b1295 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -148,6 +148,8 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) int error; int idx; + lock_kernel(); + idx = get_device_index((struct coda_mount_data *) data); /* Ignore errors in data, for backward compatibility */ @@ -159,11 +161,13 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) vc = &coda_comms[idx]; if (!vc->vc_inuse) { printk("coda_read_super: No pseudo device\n"); + unlock_kernel(); return -EINVAL; } if ( vc->vc_sb ) { printk("coda_read_super: Device already mounted\n"); + unlock_kernel(); return -EBUSY; } @@ -202,7 +206,8 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) sb->s_root = d_alloc_root(root); if (!sb->s_root) goto error; - return 0; + unlock_kernel(); + return 0; error: bdi_destroy(&vc->bdi); @@ -212,6 +217,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) if (vc) vc->vc_sb = NULL; + unlock_kernel(); return -EINVAL; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index cbd4e18adb20..c4af92fa12c3 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -36,6 +36,7 @@ #include #include #include +#include /* For lock_kernel() */ #include "ecryptfs_kernel.h" /** @@ -550,6 +551,7 @@ static int ecryptfs_get_sb(struct file_system_type *fs_type, int flags, const char *err = "Getting sb failed"; int rc; + lock_kernel(); sbi = kmem_cache_zalloc(ecryptfs_sb_info_cache, GFP_KERNEL); if (!sbi) { rc = -ENOMEM; @@ -608,6 +610,7 @@ static int ecryptfs_get_sb(struct file_system_type *fs_type, int flags, goto out; } simple_set_mnt(mnt, s); + unlock_kernel(); return 0; out: @@ -616,6 +619,7 @@ out: kmem_cache_free(ecryptfs_sb_info_cache, sbi); } printk(KERN_ERR "%s; rc = [%d]\n", err, rc); + unlock_kernel(); return rc; } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 1ec602673ea8..f98c390caf1d 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -747,15 +747,18 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) __le32 features; int err; + lock_kernel(); + + err = -ENOMEM; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) - return -ENOMEM; + goto failed_unlock; sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) { kfree(sbi); - return -ENOMEM; + goto failed_unlock; } sb->s_fs_info = sbi; sbi->s_sb_block = sb_block; @@ -1083,6 +1086,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY)) sb->s_flags |= MS_RDONLY; ext2_write_super(sb); + unlock_kernel(); return 0; cantfind_ext2: @@ -1107,6 +1111,8 @@ failed_sbi: sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); kfree(sbi); +failed_unlock: + unlock_kernel(); return ret; } diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 5dbf4dba03c4..41f9dcd73e97 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1611,14 +1611,19 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) __le32 features; int err; + lock_kernel(); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - if (!sbi) + if (!sbi) { + unlock_kernel(); return -ENOMEM; + } sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) { kfree(sbi); + unlock_kernel(); return -ENOMEM; } sb->s_fs_info = sbi; @@ -2026,6 +2031,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) "writeback"); lock_kernel(); + unlock_kernel(); return 0; cantfind_ext3: @@ -2056,6 +2062,7 @@ out_fail: kfree(sbi->s_blockgroup_lock); kfree(sbi); lock_kernel(); + unlock_kernel(); return ret; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 26147746c272..0f0021f4990c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2568,6 +2568,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) int err; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + lock_kernel(); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) goto out_free_orig; @@ -3166,7 +3168,6 @@ no_journal: if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ - lock_kernel(); kfree(orig_data); return 0; @@ -3213,8 +3214,11 @@ out_fail: sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); kfree(sbi); - lock_kernel(); + kfree(orig_data); + return ret; + out_free_orig: + unlock_kernel(); kfree(orig_data); return ret; } diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index bbc94ae4fd77..e2b0b978340d 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -9,6 +9,7 @@ #include #include #include +#include /* For lock_kernel() */ #include "fat.h" /* Characters that are undesirable in an MS-DOS file name */ @@ -662,12 +663,16 @@ static int msdos_fill_super(struct super_block *sb, void *data, int silent) { int res; + lock_kernel(); res = fat_fill_super(sb, data, silent, &msdos_dir_inode_operations, 0); - if (res) + if (res) { + unlock_kernel(); return res; + } sb->s_flags |= MS_NOATIME; sb->s_root->d_op = &msdos_dentry_operations; + unlock_kernel(); return 0; } diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 6fcc7e71fbaa..9006ad9c7b11 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -21,6 +21,7 @@ #include #include #include +#include /* For lock_kernel() */ #include "fat.h" /* @@ -1055,15 +1056,19 @@ static int vfat_fill_super(struct super_block *sb, void *data, int silent) { int res; + lock_kernel(); res = fat_fill_super(sb, data, silent, &vfat_dir_inode_operations, 1); - if (res) + if (res) { + unlock_kernel(); return res; + } if (MSDOS_SB(sb)->options.name_check != 's') sb->s_root->d_op = &vfat_ci_dentry_ops; else sb->s_root->d_op = &vfat_dentry_ops; + unlock_kernel(); return 0; } diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c index dc0c041e85cb..eb2b9e09c996 100644 --- a/fs/freevxfs/vxfs_super.c +++ b/fs/freevxfs/vxfs_super.c @@ -148,7 +148,7 @@ static int vxfs_remount(struct super_block *sb, int *flags, char *data) * The superblock on success, else %NULL. * * Locking: - * We are under the bkl and @sbp->s_lock. + * We are under @sbp->s_lock. */ static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent) { @@ -159,11 +159,14 @@ static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent) struct inode *root; int ret = -EINVAL; + lock_kernel(); + sbp->s_flags |= MS_RDONLY; infp = kzalloc(sizeof(*infp), GFP_KERNEL); if (!infp) { printk(KERN_WARNING "vxfs: unable to allocate incore superblock\n"); + unlock_kernel(); return -ENOMEM; } @@ -236,6 +239,7 @@ static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent) goto out_free_ilist; } + unlock_kernel(); return 0; out_free_ilist: @@ -245,6 +249,7 @@ out_free_ilist: out: brelse(bp); kfree(infp); + unlock_kernel(); return ret; } diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 34235d4bf08b..3069416fa8ef 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -382,9 +382,13 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *root_inode; int res; + lock_kernel(); + sbi = kzalloc(sizeof(struct hfs_sb_info), GFP_KERNEL); - if (!sbi) + if (!sbi) { + unlock_kernel(); return -ENOMEM; + } sb->s_fs_info = sbi; INIT_HLIST_HEAD(&sbi->rsrc_inodes); @@ -435,6 +439,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_root->d_op = &hfs_dentry_operations; /* everything's okay */ + unlock_kernel(); return 0; bail_iput: @@ -443,6 +448,7 @@ bail_no_root: printk(KERN_ERR "hfs: get root inode failed.\n"); bail: hfs_mdb_put(sb); + unlock_kernel(); return res; } diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 2607010be2fe..c969a1aa163a 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -477,11 +477,15 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) int o; + lock_kernel(); + save_mount_options(s, options); sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - if (!sbi) + if (!sbi) { + unlock_kernel(); return -ENOMEM; + } s->s_fs_info = sbi; sbi->sb_bmp_dir = NULL; @@ -666,6 +670,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) root->i_blocks = 5; hpfs_brelse4(&qbh); } + unlock_kernel(); return 0; bail4: brelse(bh2); @@ -677,6 +682,7 @@ bail0: kfree(sbi->sb_cp_table); s->s_fs_info = NULL; kfree(sbi); + unlock_kernel(); return -EINVAL; } diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 5a44811b5027..05baf7721e8c 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -571,11 +571,15 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) int table, error = -EINVAL; unsigned int vol_desc_start; + lock_kernel(); + save_mount_options(s, data); sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - if (!sbi) + if (!sbi) { + unlock_kernel(); return -ENOMEM; + } s->s_fs_info = sbi; if (!parse_options((char *)data, &opt)) @@ -900,6 +904,7 @@ root_found: kfree(opt.iocharset); + unlock_kernel(); return 0; /* @@ -939,6 +944,7 @@ out_freesbi: kfree(opt.iocharset); kfree(sbi); s->s_fs_info = NULL; + unlock_kernel(); return error; } diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 662bba099501..58dd9cf06206 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -146,14 +146,19 @@ static const struct super_operations jffs2_super_operations = static int jffs2_fill_super(struct super_block *sb, void *data, int silent) { struct jffs2_sb_info *c; + int ret; + + lock_kernel(); D1(printk(KERN_DEBUG "jffs2_get_sb_mtd():" " New superblock for device %d (\"%s\")\n", sb->s_mtd->index, sb->s_mtd->name)); c = kzalloc(sizeof(*c), GFP_KERNEL); - if (!c) + if (!c) { + unlock_kernel(); return -ENOMEM; + } c->mtd = sb->s_mtd; c->os_priv = sb; @@ -175,7 +180,9 @@ static int jffs2_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_JFFS2_FS_POSIX_ACL sb->s_flags |= MS_POSIXACL; #endif - return jffs2_do_fill_super(sb, data, silent); + ret = jffs2_do_fill_super(sb, data, silent); + unlock_kernel(); + return ret; } static int jffs2_get_sb(struct file_system_type *fs_type, diff --git a/fs/jfs/super.c b/fs/jfs/super.c index ec8c3e4baca3..eb31f677347d 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -438,14 +438,20 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) s64 newLVSize = 0; int flag, ret = -EINVAL; + lock_kernel(); + jfs_info("In jfs_read_super: s_flags=0x%lx", sb->s_flags); - if (!new_valid_dev(sb->s_bdev->bd_dev)) + if (!new_valid_dev(sb->s_bdev->bd_dev)) { + unlock_kernel(); return -EOVERFLOW; + } sbi = kzalloc(sizeof (struct jfs_sb_info), GFP_KERNEL); - if (!sbi) + if (!sbi) { + unlock_kernel(); return -ENOMEM; + } sb->s_fs_info = sbi; sbi->sb = sb; sbi->uid = sbi->gid = sbi->umask = -1; @@ -542,6 +548,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_maxbytes = min(((u64) PAGE_CACHE_SIZE << 32) - 1, (u64)sb->s_maxbytes); #endif sb->s_time_gran = 1; + unlock_kernel(); return 0; out_no_root: @@ -564,6 +571,7 @@ out_unload: unload_nls(sbi->nls_tab); out_kfree: kfree(sbi); + unlock_kernel(); return ret; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 922263393c76..0d573c2a6860 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1113,9 +1113,12 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags, if (!(flags & MS_RDONLY)) mode |= FMODE_WRITE; + lock_kernel(); sd.bdev = open_bdev_exclusive(dev_name, mode, fs_type); - if (IS_ERR(sd.bdev)) + if (IS_ERR(sd.bdev)) { + unlock_kernel(); return PTR_ERR(sd.bdev); + } /* * To get mount instance using sget() vfs-routine, NILFS needs @@ -1198,6 +1201,7 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags, if (need_to_close) close_bdev_exclusive(sd.bdev, mode); simple_set_mnt(mnt, s); + unlock_kernel(); return 0; failed_unlock: @@ -1206,6 +1210,7 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags, failed: close_bdev_exclusive(sd.bdev, mode); + unlock_kernel(); return err; cancel_new: @@ -1218,6 +1223,7 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags, * We must finish all post-cleaning before this call; * put_nilfs() needs the block device. */ + unlock_kernel(); return err; } diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 512806171bfa..1f31e77fc41f 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2732,6 +2732,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) struct inode *tmp_ino; int blocksize, result; + lock_kernel(); + /* * We do a pretty difficult piece of bootstrap by reading the * MFT (and other metadata) from disk into memory. We'll only @@ -2755,6 +2757,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) ntfs_error(sb, "Allocation of NTFS volume structure " "failed. Aborting mount..."); lockdep_on(); + unlock_kernel(); return -ENOMEM; } /* Initialize ntfs_volume structure. */ @@ -2942,6 +2945,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) sb->s_export_op = &ntfs_export_ops; lock_kernel(); lockdep_on(); + unlock_kernel(); return 0; } ntfs_error(sb, "Failed to allocate root directory."); @@ -3062,6 +3066,7 @@ err_out_now: kfree(vol); ntfs_debug("Failed, returning -EINVAL."); lockdep_on(); + unlock_kernel(); return -EINVAL; } diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index c2903b84bb7a..667d7ceba8c9 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -44,6 +44,7 @@ #include #include #include +#include #include @@ -588,21 +589,27 @@ static int dlmfs_fill_super(struct super_block * sb, struct inode * inode; struct dentry * root; + lock_kernel(); + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = DLMFS_MAGIC; sb->s_op = &dlmfs_ops; inode = dlmfs_get_root_inode(sb); - if (!inode) + if (!inode) { + unlock_kernel(); return -ENOMEM; + } root = d_alloc_root(inode); if (!root) { iput(inode); + unlock_kernel(); return -ENOMEM; } sb->s_root = root; + unlock_kernel(); return 0; } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index fa1be1b304d1..b7e4f2d19d40 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1002,6 +1002,8 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) char nodestr[8]; struct ocfs2_blockcheck_stats stats; + lock_kernel(); + mlog_entry("%p, %p, %i", sb, data, silent); if (!ocfs2_parse_options(sb, data, &parsed_options, 0)) { @@ -1179,6 +1181,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) atomic_set(&osb->vol_state, VOLUME_DISABLED); wake_up(&osb->osb_mount_event); mlog_exit(status); + unlock_kernel(); return status; } } @@ -1193,6 +1196,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) ocfs2_orphan_scan_start(osb); mlog_exit(status); + unlock_kernel(); return status; read_super_error: @@ -1208,6 +1212,7 @@ read_super_error: } mlog_exit(status); + unlock_kernel(); return status; } diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 16829722be93..86a7be1399a8 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -234,9 +234,13 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent) struct qnx4_sb_info *qs; int ret = -EINVAL; + lock_kernel(); + qs = kzalloc(sizeof(struct qnx4_sb_info), GFP_KERNEL); - if (!qs) + if (!qs) { + unlock_kernel(); return -ENOMEM; + } s->s_fs_info = qs; sb_set_blocksize(s, QNX4_BLOCK_SIZE); @@ -284,6 +288,7 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent) brelse(bh); + unlock_kernel(); return 0; outi: @@ -293,6 +298,7 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent) outnobh: kfree(qs); s->s_fs_info = NULL; + unlock_kernel(); return ret; } diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 450c91941988..8fc5e50e142f 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -501,6 +501,8 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent) void *mem; static int warn_count; + lock_kernel(); + if (warn_count < 5) { warn_count++; printk(KERN_EMERG "smbfs is deprecated and will be removed" @@ -621,6 +623,7 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent) smb_new_dentry(sb->s_root); + unlock_kernel(); return 0; out_no_root: @@ -643,9 +646,11 @@ out_wrong_data: out_no_data: printk(KERN_ERR "smb_fill_super: missing data argument\n"); out_fail: + unlock_kernel(); return -EINVAL; out_no_server: printk(KERN_ERR "smb_fill_super: cannot allocate struct smb_sb_info\n"); + unlock_kernel(); return -ENOMEM; } diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 88b4f8606652..ab1a401a0e19 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -87,11 +87,14 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) u64 lookup_table_start, xattr_id_table_start; int err; + lock_kernel(); + TRACE("Entered squashfs_fill_superblock\n"); sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL); if (sb->s_fs_info == NULL) { ERROR("Failed to allocate squashfs_sb_info\n"); + unlock_kernel(); return -ENOMEM; } msblk = sb->s_fs_info; @@ -301,6 +304,7 @@ allocate_root: TRACE("Leaving squashfs_fill_super\n"); kfree(sblk); + unlock_kernel(); return 0; failed_mount: @@ -315,11 +319,13 @@ failed_mount: kfree(sb->s_fs_info); sb->s_fs_info = NULL; kfree(sblk); + unlock_kernel(); return err; failure: kfree(sb->s_fs_info); sb->s_fs_info = NULL; + unlock_kernel(); return -ENOMEM; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 65412d84a45d..76f3d6d97b40 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1880,6 +1880,8 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) struct kernel_lb_addr rootdir, fileset; struct udf_sb_info *sbi; + lock_kernel(); + uopt.flags = (1 << UDF_FLAG_USE_AD_IN_ICB) | (1 << UDF_FLAG_STRICT); uopt.uid = -1; uopt.gid = -1; @@ -1888,8 +1890,10 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) uopt.dmode = UDF_INVALID_MODE; sbi = kzalloc(sizeof(struct udf_sb_info), GFP_KERNEL); - if (!sbi) + if (!sbi) { + unlock_kernel(); return -ENOMEM; + } sb->s_fs_info = sbi; @@ -2035,6 +2039,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) goto error_out; } sb->s_maxbytes = MAX_LFS_FILESIZE; + unlock_kernel(); return 0; error_out: @@ -2055,6 +2060,7 @@ error_out: kfree(sbi); sb->s_fs_info = NULL; + unlock_kernel(); return -EINVAL; } diff --git a/fs/ufs/super.c b/fs/ufs/super.c index d510c1b91817..6b9be90dae7d 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -696,6 +696,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) unsigned maxsymlen; int ret = -EINVAL; + lock_kernel(); + uspi = NULL; ubh = NULL; flags = 0; @@ -1163,6 +1165,7 @@ magic_found: goto failed; UFSD("EXIT\n"); + unlock_kernel(); return 0; dalloc_failed: @@ -1174,10 +1177,12 @@ failed: kfree(sbi); sb->s_fs_info = NULL; UFSD("EXIT (FAILED)\n"); + unlock_kernel(); return ret; failed_nomem: UFSD("EXIT (NOMEM)\n"); + unlock_kernel(); return -ENOMEM; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c9483d8f6140..a7ba3bccadc5 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1430,6 +1430,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type, struct super_block *sb; struct cgroupfs_root *new_root; + lock_kernel(); + /* First find the desired set of subsystems */ mutex_lock(&cgroup_mutex); ret = parse_cgroupfs_options(data, &opts); @@ -1559,6 +1561,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, simple_set_mnt(mnt, sb); kfree(opts.release_agent); kfree(opts.name); + unlock_kernel(); return 0; drop_new_super: @@ -1568,6 +1571,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, out_err: kfree(opts.release_agent); kfree(opts.name); + unlock_kernel(); return ret; } -- cgit v1.2.3 From 38d018dba3f725b969f196550d92a6ec1c092428 Mon Sep 17 00:00:00 2001 From: Jan Blunck Date: Wed, 24 Feb 2010 13:25:34 +0100 Subject: BKL: Remove BKL from cgroup The BKL is only used in remount_fs and get_sb that are both protected by the superblocks s_umount rw_semaphore. Therefore it is safe to remove the BKL entirely. Signed-off-by: Jan Blunck Signed-off-by: Arnd Bergmann --- kernel/cgroup.c | 8 -------- 1 file changed, 8 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a7ba3bccadc5..304d27759949 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -52,7 +52,6 @@ #include #include #include -#include #include #include #include /* TODO: replace with more sophisticated array */ @@ -1222,7 +1221,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) struct cgroup *cgrp = &root->top_cgroup; struct cgroup_sb_opts opts; - lock_kernel(); mutex_lock(&cgrp->dentry->d_inode->i_mutex); mutex_lock(&cgroup_mutex); @@ -1255,7 +1253,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) kfree(opts.name); mutex_unlock(&cgroup_mutex); mutex_unlock(&cgrp->dentry->d_inode->i_mutex); - unlock_kernel(); return ret; } @@ -1430,8 +1427,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type, struct super_block *sb; struct cgroupfs_root *new_root; - lock_kernel(); - /* First find the desired set of subsystems */ mutex_lock(&cgroup_mutex); ret = parse_cgroupfs_options(data, &opts); @@ -1561,7 +1556,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type, simple_set_mnt(mnt, sb); kfree(opts.release_agent); kfree(opts.name); - unlock_kernel(); return 0; drop_new_super: @@ -1571,8 +1565,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type, out_err: kfree(opts.release_agent); kfree(opts.name); - unlock_kernel(); - return ret; } -- cgit v1.2.3 From 97bd234701b2b39a0e749c1fe0e44f1d14c94292 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 5 Oct 2010 10:41:14 +0200 Subject: workqueue: prepare for more tracepoints Define workqueue_work event class and use it for workqueue_execute_end trace point. Also, move trace/events/workqueue.h include downwards such that all struct definitions are visible to it. This is to prepare for more tracepoints and doesn't cause any functional change. Signed-off-by: Tejun Heo Cc: Frederic Weisbecker --- include/trace/events/workqueue.h | 32 +++++++++++++++++++------------- kernel/workqueue.c | 6 +++--- 2 files changed, 22 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 49682d7e9d60..ec9d7244eb9f 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -7,13 +7,7 @@ #include #include -/** - * workqueue_execute_start - called immediately before the workqueue callback - * @work: pointer to struct work_struct - * - * Allows to track workqueue execution. - */ -TRACE_EVENT(workqueue_execute_start, +DECLARE_EVENT_CLASS(workqueue_work, TP_PROTO(struct work_struct *work), @@ -21,24 +15,22 @@ TRACE_EVENT(workqueue_execute_start, TP_STRUCT__entry( __field( void *, work ) - __field( void *, function) ), TP_fast_assign( __entry->work = work; - __entry->function = work->func; ), - TP_printk("work struct %p: function %pf", __entry->work, __entry->function) + TP_printk("work struct %p", __entry->work) ); /** - * workqueue_execute_end - called immediately before the workqueue callback + * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. */ -TRACE_EVENT(workqueue_execute_end, +TRACE_EVENT(workqueue_execute_start, TP_PROTO(struct work_struct *work), @@ -46,15 +38,29 @@ TRACE_EVENT(workqueue_execute_end, TP_STRUCT__entry( __field( void *, work ) + __field( void *, function) ), TP_fast_assign( __entry->work = work; + __entry->function = work->func; ), - TP_printk("work struct %p", __entry->work) + TP_printk("work struct %p: function %pf", __entry->work, __entry->function) ); +/** + * workqueue_execute_end - called immediately before the workqueue callback + * @work: pointer to struct work_struct + * + * Allows to track workqueue execution. + */ +DEFINE_EVENT(workqueue_work, workqueue_execute_end, + + TP_PROTO(struct work_struct *work), + + TP_ARGS(work) +); #endif /* _TRACE_WORKQUEUE_H */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 19e4bc15ee99..026f778e879b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -42,9 +42,6 @@ #include #include -#define CREATE_TRACE_POINTS -#include - #include "workqueue_sched.h" enum { @@ -257,6 +254,9 @@ EXPORT_SYMBOL_GPL(system_long_wq); EXPORT_SYMBOL_GPL(system_nrt_wq); EXPORT_SYMBOL_GPL(system_unbound_wq); +#define CREATE_TRACE_POINTS +#include + #define for_each_busy_worker(worker, i, pos, gcwq) \ for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \ hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry) -- cgit v1.2.3 From cdadf0097cdca06c497ffaeb5982e028c6e4ed38 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 5 Oct 2010 10:49:55 +0200 Subject: workqueue: add queue_work and activate_work trace points These two tracepoints allow tracking when and how a work is queued and activated. This patch is based on Frederic's patch to add queue_work trace point. Signed-off-by: Tejun Heo Cc: Frederic Weisbecker --- include/trace/events/workqueue.h | 53 ++++++++++++++++++++++++++++++++++++++++ kernel/workqueue.c | 3 +++ 2 files changed, 56 insertions(+) (limited to 'kernel') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index ec9d7244eb9f..7d497291c85d 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -24,6 +24,59 @@ DECLARE_EVENT_CLASS(workqueue_work, TP_printk("work struct %p", __entry->work) ); +/** + * workqueue_queue_work - called when a work gets queued + * @req_cpu: the requested cpu + * @cwq: pointer to struct cpu_workqueue_struct + * @work: pointer to struct work_struct + * + * This event occurs when a work is queued immediately or once a + * delayed work is actually queued on a workqueue (ie: once the delay + * has been reached). + */ +TRACE_EVENT(workqueue_queue_work, + + TP_PROTO(unsigned int req_cpu, struct cpu_workqueue_struct *cwq, + struct work_struct *work), + + TP_ARGS(req_cpu, cwq, work), + + TP_STRUCT__entry( + __field( void *, work ) + __field( void *, function) + __field( void *, workqueue) + __field( unsigned int, req_cpu ) + __field( unsigned int, cpu ) + ), + + TP_fast_assign( + __entry->work = work; + __entry->function = work->func; + __entry->workqueue = cwq->wq; + __entry->req_cpu = req_cpu; + __entry->cpu = cwq->gcwq->cpu; + ), + + TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u", + __entry->work, __entry->function, __entry->workqueue, + __entry->req_cpu, __entry->cpu) +); + +/** + * workqueue_activate_work - called when a work gets activated + * @work: pointer to struct work_struct + * + * This event occurs when a queued work is put on the active queue, + * which happens immediately after queueing unless @max_active limit + * is reached. + */ +DEFINE_EVENT(workqueue_work, workqueue_activate_work, + + TP_PROTO(struct work_struct *work), + + TP_ARGS(work) +); + /** * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 026f778e879b..cb2ccfbed0c6 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -997,6 +997,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, /* gcwq determined, get cwq and queue */ cwq = get_cwq(gcwq->cpu, wq); + trace_workqueue_queue_work(cpu, cwq, work); BUG_ON(!list_empty(&work->entry)); @@ -1004,6 +1005,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, work_flags = work_color_to_flags(cwq->work_color); if (likely(cwq->nr_active < cwq->max_active)) { + trace_workqueue_activate_work(work); cwq->nr_active++; worklist = gcwq_determine_ins_pos(gcwq, cwq); } else { @@ -1679,6 +1681,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) struct work_struct, entry); struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq); + trace_workqueue_activate_work(work); move_linked_works(work, pos, NULL); __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); cwq->nr_active++; -- cgit v1.2.3 From 30310045dd20a286cf3800f063f79b468e132fb1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 11 Oct 2010 11:51:57 +0200 Subject: workqueue: fix HIGHPRI handling in keep_working() The policy function keep_working() didn't check GCWQ_HIGHPRI_PENDING and could return %false with highpri work pending. This could lead to late execution of a highpri work which was delayed due to @max_active throttling if other works are actively consuming CPU cycles. For example, the following could happen. 1. Work W0 which burns CPU cycles. 2. Two works W1 and W2 are queued to a highpri wq w/ @max_active of 1. 3. W1 starts executing and W2 is put to delayed queue. W0 and W1 are both runnable. 4. W1 finishes which puts W2 to pending queue but keep_working() incorrectly returns %false and the worker goes to sleep. 5. W0 finishes and W2 starts execution. With this patch applied, W2 starts execution as soon as W1 finishes. Signed-off-by: Tejun Heo --- kernel/workqueue.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cb2ccfbed0c6..b57a8babdec3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -604,7 +604,9 @@ static bool keep_working(struct global_cwq *gcwq) { atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu); - return !list_empty(&gcwq->worklist) && atomic_read(nr_running) <= 1; + return !list_empty(&gcwq->worklist) && + (atomic_read(nr_running) <= 1 || + gcwq->flags & GCWQ_HIGHPRI_PENDING); } /* Do we need a new worker? Called from manager. */ -- cgit v1.2.3 From 6370a6ad3b53df90b4700977f7718118a2cd524a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 11 Oct 2010 15:12:27 +0200 Subject: workqueue: add and use WQ_MEM_RECLAIM flag Add WQ_MEM_RECLAIM flag which currently maps to WQ_RESCUER, mark WQ_RESCUER as internal and replace all external WQ_RESCUER usages to WQ_MEM_RECLAIM. This makes the API users express the intent of the workqueue instead of indicating the internal mechanism used to guarantee forward progress. This is also to make it cleaner to add more semantics to WQ_MEM_RECLAIM. For example, if deemed necessary, memory reclaim workqueues can be made highpri. This patch doesn't introduce any functional change. Signed-off-by: Tejun Heo Cc: Jeff Garzik Cc: Dave Chinner Cc: Steven Whitehouse --- Documentation/workqueue.txt | 29 +++++++++++++++-------------- drivers/ata/libata-sff.c | 2 +- fs/gfs2/main.c | 2 +- fs/xfs/linux-2.6/xfs_buf.c | 2 +- include/linux/workqueue.h | 11 ++++++----- kernel/workqueue.c | 7 +++++++ 6 files changed, 31 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt index e4498a2872c3..996a27d9b8db 100644 --- a/Documentation/workqueue.txt +++ b/Documentation/workqueue.txt @@ -196,11 +196,11 @@ resources, scheduled and executed. suspend operations. Work items on the wq are drained and no new work item starts execution until thawed. - WQ_RESCUER + WQ_MEM_RECLAIM All wq which might be used in the memory reclaim paths _MUST_ - have this flag set. This reserves one worker exclusively for - the execution of this wq under memory pressure. + have this flag set. The wq is guaranteed to have at least one + execution context regardless of memory pressure. WQ_HIGHPRI @@ -356,11 +356,11 @@ If q1 has WQ_CPU_INTENSIVE set, 6. Guidelines -* Do not forget to use WQ_RESCUER if a wq may process work items which - are used during memory reclaim. Each wq with WQ_RESCUER set has one - rescuer thread reserved for it. If there is dependency among - multiple work items used during memory reclaim, they should be - queued to separate wq each with WQ_RESCUER. +* Do not forget to use WQ_MEM_RECLAIM if a wq may process work items + which are used during memory reclaim. Each wq with WQ_MEM_RECLAIM + set has an execution context reserved for it. If there is + dependency among multiple work items used during memory reclaim, + they should be queued to separate wq each with WQ_MEM_RECLAIM. * Unless strict ordering is required, there is no need to use ST wq. @@ -368,12 +368,13 @@ If q1 has WQ_CPU_INTENSIVE set, recommended. In most use cases, concurrency level usually stays well under the default limit. -* A wq serves as a domain for forward progress guarantee (WQ_RESCUER), - flush and work item attributes. Work items which are not involved - in memory reclaim and don't need to be flushed as a part of a group - of work items, and don't require any special attribute, can use one - of the system wq. There is no difference in execution - characteristics between using a dedicated wq and a system wq. +* A wq serves as a domain for forward progress guarantee + (WQ_MEM_RECLAIM, flush and work item attributes. Work items which + are not involved in memory reclaim and don't need to be flushed as a + part of a group of work items, and don't require any special + attribute, can use one of the system wq. There is no difference in + execution characteristics between using a dedicated wq and a system + wq. * Unless work items are expected to consume a huge amount of CPU cycles, using a bound wq is usually beneficial due to the increased diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index e30c537cce32..f5296bb19ec0 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -3335,7 +3335,7 @@ void ata_sff_port_init(struct ata_port *ap) int __init ata_sff_init(void) { - ata_sff_wq = alloc_workqueue("ata_sff", WQ_RESCUER, WQ_MAX_ACTIVE); + ata_sff_wq = alloc_workqueue("ata_sff", WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); if (!ata_sff_wq) return -ENOMEM; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index b1e9630eb46a..1c5f46075d52 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -140,7 +140,7 @@ static int __init init_gfs2_fs(void) error = -ENOMEM; gfs_recovery_wq = alloc_workqueue("gfs_recovery", - WQ_NON_REENTRANT | WQ_RESCUER, 0); + WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); if (!gfs_recovery_wq) goto fail_wq; diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 286e36e21dae..6838aefca71f 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1933,7 +1933,7 @@ xfs_buf_init(void) goto out; xfslogd_workqueue = alloc_workqueue("xfslogd", - WQ_RESCUER | WQ_HIGHPRI, 1); + WQ_MEM_RECLAIM | WQ_HIGHPRI, 1); if (!xfslogd_workqueue) goto out_free_buf_zone; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e33ff4a91703..03bbe903e5ce 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -243,11 +243,12 @@ enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */ - WQ_RESCUER = 1 << 3, /* has an rescue worker */ + WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_RESCUER = 1 << 7, /* internal: workqueue has rescuer */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -309,7 +310,7 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, /** * alloc_ordered_workqueue - allocate an ordered workqueue * @name: name of the workqueue - * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_RESCUER are meaningful) + * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_MEM_RECLAIM are meaningful) * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are @@ -325,11 +326,11 @@ alloc_ordered_workqueue(const char *name, unsigned int flags) } #define create_workqueue(name) \ - alloc_workqueue((name), WQ_RESCUER, 1) + alloc_workqueue((name), WQ_MEM_RECLAIM, 1) #define create_freezeable_workqueue(name) \ - alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1) #define create_singlethread_workqueue(name) \ - alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b57a8babdec3..2c6871cbcbee 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2847,6 +2847,13 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, struct workqueue_struct *wq; unsigned int cpu; + /* + * Workqueues which may be used during memory reclaim should + * have a rescuer to guarantee forward progress. + */ + if (flags & WQ_MEM_RECLAIM) + flags |= WQ_RESCUER; + /* * Unbound workqueues aren't concurrency managed and should be * dispatched to workers immediately. -- cgit v1.2.3 From 6038f373a3dc1f1c26496e60b6c40b164716f07e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 15 Aug 2010 18:52:59 +0200 Subject: llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann Cc: Julia Lawall Cc: Christoph Hellwig --- arch/arm/kernel/etm.c | 1 + arch/arm/mach-msm/last_radio_log.c | 3 ++- arch/arm/mach-msm/smd_debug.c | 1 + arch/arm/plat-mxc/audmux-v2.c | 1 + arch/avr32/boards/mimc200/fram.c | 1 + arch/blackfin/kernel/kgdb_test.c | 1 + arch/blackfin/mach-bf561/coreb.c | 1 + arch/cris/arch-v10/drivers/ds1302.c | 1 + arch/cris/arch-v10/drivers/gpio.c | 1 + arch/cris/arch-v10/drivers/i2c.c | 1 + arch/cris/arch-v10/drivers/pcf8563.c | 1 + arch/cris/arch-v10/drivers/sync_serial.c | 3 ++- arch/cris/arch-v32/drivers/cryptocop.c | 3 ++- arch/cris/arch-v32/drivers/i2c.c | 1 + arch/cris/arch-v32/drivers/mach-a3/gpio.c | 1 + arch/cris/arch-v32/drivers/mach-fs/gpio.c | 1 + arch/cris/arch-v32/drivers/pcf8563.c | 1 + arch/cris/arch-v32/drivers/sync_serial.c | 3 ++- arch/cris/kernel/profile.c | 1 + arch/ia64/kernel/salinfo.c | 2 ++ arch/ia64/sn/kernel/sn2/sn_hwperf.c | 1 + arch/m68k/bvme6000/rtc.c | 1 + arch/m68k/mvme16x/rtc.c | 1 + arch/mips/kernel/rtlx.c | 3 ++- arch/mips/kernel/vpe.c | 3 ++- arch/mips/sibyte/common/sb_tbprof.c | 1 + arch/powerpc/kernel/lparcfg.c | 1 + arch/powerpc/kernel/rtas_flash.c | 3 +++ arch/powerpc/kernel/rtasd.c | 1 + arch/powerpc/platforms/iseries/mf.c | 1 + arch/powerpc/platforms/pseries/reconfig.c | 3 ++- arch/powerpc/platforms/pseries/scanlog.c | 1 + arch/s390/crypto/prng.c | 1 + arch/s390/hypfs/hypfs_diag.c | 1 + arch/s390/hypfs/hypfs_vm.c | 1 + arch/s390/hypfs/inode.c | 1 + arch/s390/kernel/debug.c | 1 + arch/sh/boards/mach-landisk/gio.c | 1 + arch/sparc/kernel/apc.c | 1 + arch/sparc/kernel/mdesc.c | 1 + arch/tile/kernel/hardwall.c | 1 + arch/um/drivers/harddog_kern.c | 1 + arch/um/drivers/mconsole_kern.c | 1 + arch/um/drivers/mmapper_kern.c | 1 + arch/um/drivers/random.c | 1 + arch/x86/kernel/apm_32.c | 1 + arch/x86/kernel/cpu/mcheck/mce-severity.c | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 1 + arch/x86/kernel/kdebugfs.c | 1 + arch/x86/kernel/microcode_core.c | 1 + arch/x86/kernel/tlb_uv.c | 1 + arch/x86/xen/debugfs.c | 1 + block/bsg.c | 1 + drivers/acpi/apei/erst-dbg.c | 1 + drivers/acpi/debugfs.c | 1 + drivers/acpi/ec_sys.c | 1 + drivers/acpi/event.c | 1 + drivers/block/DAC960.c | 3 ++- drivers/block/aoe/aoechr.c | 1 + drivers/block/paride/pg.c | 1 + drivers/block/paride/pt.c | 1 + drivers/block/pktcdvd.c | 1 + drivers/bluetooth/btmrvl_debugfs.c | 10 +++++++ drivers/bluetooth/hci_vhci.c | 1 + drivers/char/apm-emulation.c | 1 + drivers/char/bfin-otp.c | 1 + drivers/char/briq_panel.c | 1 + drivers/char/bsr.c | 1 + drivers/char/cs5535_gpio.c | 3 ++- drivers/char/ds1302.c | 1 + drivers/char/ds1620.c | 1 + drivers/char/dsp56k.c | 1 + drivers/char/dtlk.c | 1 + drivers/char/genrtc.c | 1 + drivers/char/hw_random/core.c | 1 + drivers/char/ip2/ip2main.c | 1 + drivers/char/ipmi/ipmi_devintf.c | 1 + drivers/char/ipmi/ipmi_watchdog.c | 1 + drivers/char/istallion.c | 1 + drivers/char/lp.c | 1 + drivers/char/mem.c | 3 +++ drivers/char/misc.c | 1 + drivers/char/mmtimer.c | 1 + drivers/char/mspec.c | 9 ++++--- drivers/char/mwave/mwavedd.c | 3 ++- drivers/char/nwbutton.c | 1 + drivers/char/pc8736x_gpio.c | 1 + drivers/char/pcmcia/cm4000_cs.c | 1 + drivers/char/pcmcia/cm4040_cs.c | 1 + drivers/char/random.c | 2 ++ drivers/char/rio/rio_linux.c | 1 + drivers/char/scx200_gpio.c | 1 + drivers/char/snsc.c | 1 + drivers/char/stallion.c | 1 + drivers/char/sx.c | 1 + drivers/char/sysrq.c | 1 + drivers/char/tb0219.c | 1 + drivers/char/tlclk.c | 1 + drivers/char/toshiba.c | 1 + drivers/char/uv_mmtimer.c | 1 + drivers/char/xilinx_hwicap/xilinx_hwicap.c | 1 + drivers/dma/coh901318.c | 1 + drivers/firewire/nosy.c | 1 + drivers/gpu/drm/drm_drv.c | 3 ++- drivers/gpu/drm/i810/i810_dma.c | 1 + drivers/gpu/drm/i830/i830_dma.c | 1 + drivers/gpu/drm/i915/i915_debugfs.c | 1 + drivers/gpu/vga/vgaarb.c | 1 + drivers/hid/hid-debug.c | 1 + drivers/hid/hid-roccat.c | 1 + drivers/hid/hidraw.c | 1 + drivers/hid/usbhid/hiddev.c | 1 + drivers/hwmon/asus_atk0110.c | 1 + drivers/ide/ide-tape.c | 1 + drivers/idle/i7300_idle.c | 1 + drivers/infiniband/hw/ipath/ipath_diag.c | 4 ++- drivers/infiniband/hw/ipath/ipath_file_ops.c | 3 ++- drivers/infiniband/hw/ipath/ipath_fs.c | 3 +++ drivers/infiniband/hw/qib/qib_diag.c | 4 ++- drivers/infiniband/hw/qib/qib_file_ops.c | 3 ++- drivers/infiniband/hw/qib/qib_fs.c | 1 + drivers/input/evdev.c | 3 ++- drivers/input/input.c | 1 + drivers/input/joydev.c | 1 + drivers/input/misc/uinput.c | 1 + drivers/input/mousedev.c | 1 + drivers/input/serio/serio_raw.c | 1 + drivers/isdn/mISDN/timerdev.c | 1 + drivers/lguest/lguest_user.c | 1 + drivers/macintosh/ans-lcd.c | 1 + drivers/macintosh/via-pmu.c | 1 + drivers/md/dm-ioctl.c | 1 + drivers/media/IR/imon.c | 6 +++-- drivers/media/IR/lirc_dev.c | 1 + drivers/media/dvb/bt8xx/dst_ca.c | 3 ++- drivers/media/dvb/dvb-core/dmxdev.c | 2 ++ drivers/media/dvb/dvb-core/dvb_ca_en50221.c | 1 + drivers/media/dvb/dvb-core/dvb_frontend.c | 3 ++- drivers/media/dvb/dvb-core/dvb_net.c | 1 + drivers/media/dvb/dvb-core/dvbdev.c | 1 + drivers/media/dvb/firewire/firedtv-ci.c | 1 + drivers/media/dvb/ttpci/av7110.c | 1 + drivers/media/dvb/ttpci/av7110_av.c | 2 ++ drivers/media/dvb/ttpci/av7110_ca.c | 1 + drivers/media/dvb/ttpci/av7110_ir.c | 1 + drivers/mfd/ab3100-core.c | 1 + drivers/misc/hpilo.c | 1 + drivers/misc/phantom.c | 1 + drivers/misc/sgi-gru/grufile.c | 1 + drivers/mmc/core/debugfs.c | 1 + drivers/mtd/ubi/cdev.c | 1 + drivers/net/caif/caif_spi.c | 6 +++-- drivers/net/cxgb4/cxgb4_main.c | 1 + drivers/net/ppp_generic.c | 3 ++- drivers/net/wimax/i2400m/debugfs.c | 2 ++ drivers/net/wireless/airo.c | 24 +++++++++++------ drivers/net/wireless/ath/ath5k/debug.c | 7 +++++ drivers/net/wireless/ath/ath9k/debug.c | 33 ++++++++++++++++-------- drivers/net/wireless/ath/ath9k/htc_drv_main.c | 9 ++++--- drivers/net/wireless/iwlwifi/iwl-3945-rs.c | 1 + drivers/net/wireless/iwlwifi/iwl-agn-rs.c | 3 +++ drivers/net/wireless/iwmc3200wifi/debugfs.c | 4 +++ drivers/net/wireless/iwmc3200wifi/sdio.c | 1 + drivers/net/wireless/libertas/debugfs.c | 1 + drivers/net/wireless/ray_cs.c | 2 ++ drivers/net/wireless/rt2x00/rt2x00debug.c | 4 +++ drivers/net/wireless/wl12xx/wl1251_debugfs.c | 2 ++ drivers/net/wireless/wl12xx/wl1271_debugfs.c | 4 ++- drivers/oprofile/oprofile_files.c | 8 +++++- drivers/oprofile/oprofilefs.c | 3 +++ drivers/pci/pcie/aer/aer_inject.c | 1 + drivers/platform/x86/sony-laptop.c | 1 + drivers/rtc/rtc-m41t80.c | 1 + drivers/s390/block/dasd_eer.c | 1 + drivers/s390/char/fs3270.c | 1 + drivers/s390/char/monreader.c | 1 + drivers/s390/char/monwriter.c | 1 + drivers/s390/char/tape_char.c | 1 + drivers/s390/char/vmcp.c | 1 + drivers/s390/char/vmlogrdr.c | 1 + drivers/s390/char/vmwatchdog.c | 1 + drivers/s390/char/zcore.c | 2 ++ drivers/s390/cio/chsc_sch.c | 1 + drivers/s390/cio/css.c | 1 + drivers/s390/crypto/zcrypt_api.c | 3 ++- drivers/s390/scsi/zfcp_cfdc.c | 3 ++- drivers/sbus/char/display7seg.c | 1 + drivers/sbus/char/envctrl.c | 1 + drivers/scsi/3w-9xxx.c | 3 ++- drivers/scsi/3w-sas.c | 3 ++- drivers/scsi/3w-xxxx.c | 3 ++- drivers/scsi/aacraid/linit.c | 1 + drivers/scsi/ch.c | 1 + drivers/scsi/dpt_i2o.c | 1 + drivers/scsi/gdth.c | 1 + drivers/scsi/megaraid.c | 1 + drivers/scsi/megaraid/megaraid_mm.c | 1 + drivers/scsi/megaraid/megaraid_sas.c | 1 + drivers/scsi/mpt2sas/mpt2sas_ctl.c | 1 + drivers/scsi/osd/osd_uld.c | 1 + drivers/scsi/pmcraid.c | 1 + drivers/scsi/qla2xxx/qla_os.c | 1 + drivers/scsi/scsi_tgt_if.c | 1 + drivers/scsi/sg.c | 1 + drivers/serial/mfd.c | 2 ++ drivers/spi/dw_spi.c | 1 + drivers/spi/spidev.c | 1 + drivers/staging/comedi/comedi_fops.c | 1 + drivers/staging/crystalhd/crystalhd_lnx.c | 1 + drivers/staging/dream/camera/msm_camera.c | 3 +++ drivers/staging/dream/pmem.c | 2 ++ drivers/staging/dream/qdsp5/adsp_driver.c | 1 + drivers/staging/dream/qdsp5/audio_aac.c | 1 + drivers/staging/dream/qdsp5/audio_amrnb.c | 1 + drivers/staging/dream/qdsp5/audio_evrc.c | 1 + drivers/staging/dream/qdsp5/audio_in.c | 2 ++ drivers/staging/dream/qdsp5/audio_mp3.c | 1 + drivers/staging/dream/qdsp5/audio_out.c | 2 ++ drivers/staging/dream/qdsp5/audio_qcelp.c | 1 + drivers/staging/dream/qdsp5/evlog.h | 1 + drivers/staging/dream/qdsp5/snd.c | 1 + drivers/staging/frontier/alphatrack.c | 1 + drivers/staging/frontier/tranzport.c | 1 + drivers/staging/iio/industrialio-core.c | 1 + drivers/staging/iio/industrialio-ring.c | 1 + drivers/staging/lirc/lirc_imon.c | 3 ++- drivers/staging/lirc/lirc_it87.c | 1 + drivers/staging/lirc/lirc_sasem.c | 1 + drivers/staging/memrar/memrar_handler.c | 1 + drivers/staging/panel/panel.c | 1 + drivers/staging/tidspbridge/rmgr/drv_interface.c | 1 + drivers/telephony/ixj.c | 3 ++- drivers/telephony/phonedev.c | 1 + drivers/uio/uio.c | 1 + drivers/usb/class/cdc-wdm.c | 3 ++- drivers/usb/class/usblp.c | 1 + drivers/usb/class/usbtmc.c | 1 + drivers/usb/core/file.c | 1 + drivers/usb/gadget/f_hid.c | 1 + drivers/usb/gadget/printer.c | 3 ++- drivers/usb/host/ehci-dbg.c | 4 +++ drivers/usb/host/ohci-dbg.c | 3 +++ drivers/usb/image/mdc800.c | 1 + drivers/usb/misc/adutux.c | 1 + drivers/usb/misc/idmouse.c | 1 + drivers/usb/misc/iowarrior.c | 1 + drivers/usb/misc/ldusb.c | 1 + drivers/usb/misc/rio500.c | 1 + drivers/usb/misc/usblcd.c | 1 + drivers/usb/usb-skeleton.c | 1 + drivers/vhost/net.c | 1 + drivers/video/fbmem.c | 1 + drivers/video/mbx/mbxdebugfs.c | 6 +++++ drivers/watchdog/ar7_wdt.c | 1 + drivers/watchdog/cpwd.c | 1 + drivers/watchdog/ep93xx_wdt.c | 1 + drivers/watchdog/omap_wdt.c | 1 + drivers/xen/evtchn.c | 1 + drivers/xen/xenfs/super.c | 1 + drivers/xen/xenfs/xenbus.c | 1 + fs/afs/mntpt.c | 1 + fs/autofs4/dev-ioctl.c | 1 + fs/binfmt_misc.c | 3 +++ fs/btrfs/super.c | 1 + fs/cachefiles/daemon.c | 1 + fs/char_dev.c | 1 + fs/coda/pioctl.c | 1 + fs/coda/psdev.c | 1 + fs/debugfs/file.c | 3 +++ fs/dlm/debug_fs.c | 3 ++- fs/dlm/plock.c | 3 ++- fs/dlm/user.c | 3 +++ fs/ecryptfs/file.c | 1 + fs/ecryptfs/miscdev.c | 1 + fs/eventfd.c | 1 + fs/eventpoll.c | 3 ++- fs/fifo.c | 1 + fs/fuse/control.c | 4 +++ fs/fuse/cuse.c | 1 + fs/gfs2/file.c | 2 ++ fs/hppfs/hppfs.c | 1 + fs/hugetlbfs/inode.c | 1 + fs/logfs/dir.c | 1 + fs/nfsd/nfsctl.c | 1 + fs/no-block.c | 1 + fs/notify/fanotify/fanotify_user.c | 1 + fs/notify/inotify/inotify_user.c | 1 + fs/ocfs2/dlmfs/dlmfs.c | 1 + fs/ocfs2/stack_user.c | 1 + fs/proc/base.c | 8 ++++++ fs/proc/proc_sysctl.c | 1 + fs/proc/root.c | 1 + fs/proc/task_mmu.c | 1 + fs/romfs/super.c | 1 + fs/signalfd.c | 1 + fs/squashfs/dir.c | 3 ++- fs/timerfd.c | 1 + fs/ubifs/debug.c | 1 + ipc/mqueue.c | 1 + ipc/shm.c | 2 ++ kernel/configs.c | 1 + kernel/gcov/fs.c | 1 + kernel/kprobes.c | 1 + kernel/pm_qos_params.c | 1 + kernel/profile.c | 1 + kernel/trace/blktrace.c | 2 ++ kernel/trace/ftrace.c | 2 ++ kernel/trace/ring_buffer.c | 1 + kernel/trace/trace_events.c | 6 +++++ kernel/trace/trace_stack.c | 1 + lib/dma-debug.c | 1 + net/atm/proc.c | 1 + net/dccp/probe.c | 1 + net/ipv4/tcp_probe.c | 1 + net/mac80211/debugfs.c | 19 +++++++++----- net/mac80211/rate.c | 1 + net/mac80211/rc80211_minstrel_debugfs.c | 1 + net/mac80211/rc80211_pid_debugfs.c | 1 + net/netfilter/xt_recent.c | 1 + net/nonet.c | 1 + net/rfkill/core.c | 1 + net/sctp/probe.c | 1 + net/socket.c | 1 + net/sunrpc/cache.c | 2 ++ net/wireless/debugfs.c | 1 + samples/kfifo/bytestream-example.c | 1 + samples/kfifo/inttype-example.c | 1 + samples/kfifo/record-example.c | 1 + samples/tracepoints/tracepoint-sample.c | 1 + security/apparmor/apparmorfs.c | 9 ++++--- security/inode.c | 1 + security/smack/smackfs.c | 5 ++++ sound/core/seq/oss/seq_oss.c | 1 + sound/core/sound.c | 3 ++- sound/oss/msnd_pinnacle.c | 1 + sound/soc/soc-core.c | 1 + sound/soc/soc-dapm.c | 1 + sound/sound_core.c | 1 + virt/kvm/kvm_main.c | 3 +++ 339 files changed, 538 insertions(+), 73 deletions(-) (limited to 'kernel') diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c index 33c7077174db..30b8878f1202 100644 --- a/arch/arm/kernel/etm.c +++ b/arch/arm/kernel/etm.c @@ -314,6 +314,7 @@ static const struct file_operations etb_fops = { .read = etb_read, .open = etb_open, .release = etb_release, + .llseek = no_llseek, }; static struct miscdevice etb_miscdev = { diff --git a/arch/arm/mach-msm/last_radio_log.c b/arch/arm/mach-msm/last_radio_log.c index b64ba5a98686..1e243f46a969 100644 --- a/arch/arm/mach-msm/last_radio_log.c +++ b/arch/arm/mach-msm/last_radio_log.c @@ -48,7 +48,8 @@ static ssize_t last_radio_log_read(struct file *file, char __user *buf, } static struct file_operations last_radio_log_fops = { - .read = last_radio_log_read + .read = last_radio_log_read, + .llseek = default_llseek, }; void msm_init_last_radio_log(struct module *owner) diff --git a/arch/arm/mach-msm/smd_debug.c b/arch/arm/mach-msm/smd_debug.c index 3b2dd717b788..f91c3b7bc655 100644 --- a/arch/arm/mach-msm/smd_debug.c +++ b/arch/arm/mach-msm/smd_debug.c @@ -212,6 +212,7 @@ static int debug_open(struct inode *inode, struct file *file) static const struct file_operations debug_ops = { .read = debug_read, .open = debug_open, + .llseek = default_llseek, }; static void debug_create(const char *name, mode_t mode, diff --git a/arch/arm/plat-mxc/audmux-v2.c b/arch/arm/plat-mxc/audmux-v2.c index f9e7cdbd0005..25ad95ba92a4 100644 --- a/arch/arm/plat-mxc/audmux-v2.c +++ b/arch/arm/plat-mxc/audmux-v2.c @@ -137,6 +137,7 @@ static ssize_t audmux_read_file(struct file *file, char __user *user_buf, static const struct file_operations audmux_debugfs_fops = { .open = audmux_open_file, .read = audmux_read_file, + .llseek = default_llseek, }; static void audmux_debugfs_init(void) diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c index 54fbd95cee9b..9764a1a1073e 100644 --- a/arch/avr32/boards/mimc200/fram.c +++ b/arch/avr32/boards/mimc200/fram.c @@ -41,6 +41,7 @@ static int fram_mmap(struct file *filp, struct vm_area_struct *vma) static const struct file_operations fram_fops = { .owner = THIS_MODULE, .mmap = fram_mmap, + .llseek = noop_llseek, }; #define FRAM_MINOR 0 diff --git a/arch/blackfin/kernel/kgdb_test.c b/arch/blackfin/kernel/kgdb_test.c index 9a4b07594389..08c0236acf3c 100644 --- a/arch/blackfin/kernel/kgdb_test.c +++ b/arch/blackfin/kernel/kgdb_test.c @@ -88,6 +88,7 @@ static const struct file_operations kgdb_test_proc_fops = { .owner = THIS_MODULE, .read = kgdb_test_proc_read, .write = kgdb_test_proc_write, + .llseek = noop_llseek, }; static int __init kgdbtest_init(void) diff --git a/arch/blackfin/mach-bf561/coreb.c b/arch/blackfin/mach-bf561/coreb.c index deb2271d09a3..c6a4c8f2d37b 100644 --- a/arch/blackfin/mach-bf561/coreb.c +++ b/arch/blackfin/mach-bf561/coreb.c @@ -51,6 +51,7 @@ coreb_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations coreb_fops = { .owner = THIS_MODULE, .unlocked_ioctl = coreb_ioctl, + .llseek = noop_llseek, }; static struct miscdevice coreb_dev = { diff --git a/arch/cris/arch-v10/drivers/ds1302.c b/arch/cris/arch-v10/drivers/ds1302.c index 884275629ef7..95aadb4a8cf1 100644 --- a/arch/cris/arch-v10/drivers/ds1302.c +++ b/arch/cris/arch-v10/drivers/ds1302.c @@ -387,6 +387,7 @@ print_rtc_status(void) static const struct file_operations rtc_fops = { .owner = THIS_MODULE, .unlocked_ioctl = rtc_unlocked_ioctl, + .llseek = noop_llseek, }; /* Probe for the chip by writing something to its RAM and try reading it back. */ diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c index a07b6d25b0c7..a276f0811731 100644 --- a/arch/cris/arch-v10/drivers/gpio.c +++ b/arch/cris/arch-v10/drivers/gpio.c @@ -745,6 +745,7 @@ static const struct file_operations gpio_fops = { .write = gpio_write, .open = gpio_open, .release = gpio_release, + .llseek = noop_llseek, }; static void ioif_watcher(const unsigned int gpio_in_available, diff --git a/arch/cris/arch-v10/drivers/i2c.c b/arch/cris/arch-v10/drivers/i2c.c index 77a941813819..c413539d4205 100644 --- a/arch/cris/arch-v10/drivers/i2c.c +++ b/arch/cris/arch-v10/drivers/i2c.c @@ -617,6 +617,7 @@ static const struct file_operations i2c_fops = { .unlocked_ioctl = i2c_ioctl, .open = i2c_open, .release = i2c_release, + .llseek = noop_llseek, }; int __init diff --git a/arch/cris/arch-v10/drivers/pcf8563.c b/arch/cris/arch-v10/drivers/pcf8563.c index 7dcb1f85f42b..7aa6ff00a117 100644 --- a/arch/cris/arch-v10/drivers/pcf8563.c +++ b/arch/cris/arch-v10/drivers/pcf8563.c @@ -64,6 +64,7 @@ static int voltage_low; static const struct file_operations pcf8563_fops = { .owner = THIS_MODULE, .unlocked_ioctl = pcf8563_unlocked_ioctl, + .llseek = noop_llseek, }; unsigned char diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c index ee2dd4323daf..e501632fa8c2 100644 --- a/arch/cris/arch-v10/drivers/sync_serial.c +++ b/arch/cris/arch-v10/drivers/sync_serial.c @@ -250,7 +250,8 @@ static const struct file_operations sync_serial_fops = { .poll = sync_serial_poll, .unlocked_ioctl = sync_serial_ioctl, .open = sync_serial_open, - .release = sync_serial_release + .release = sync_serial_release, + .llseek = noop_llseek, }; static int __init etrax_sync_serial_init(void) diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c index b07646a30509..dcb43fddfb99 100644 --- a/arch/cris/arch-v32/drivers/cryptocop.c +++ b/arch/cris/arch-v32/drivers/cryptocop.c @@ -281,7 +281,8 @@ const struct file_operations cryptocop_fops = { .owner = THIS_MODULE, .open = cryptocop_open, .release = cryptocop_release, - .unlocked_ioctl = cryptocop_ioctl + .unlocked_ioctl = cryptocop_ioctl, + .llseek = noop_llseek, }; diff --git a/arch/cris/arch-v32/drivers/i2c.c b/arch/cris/arch-v32/drivers/i2c.c index 5a3e900c9a78..ddb23996f11a 100644 --- a/arch/cris/arch-v32/drivers/i2c.c +++ b/arch/cris/arch-v32/drivers/i2c.c @@ -698,6 +698,7 @@ static const struct file_operations i2c_fops = { .unlocked_ioctl = i2c_ioctl, .open = i2c_open, .release = i2c_release, + .llseek = noop_llseek, }; static int __init i2c_init(void) diff --git a/arch/cris/arch-v32/drivers/mach-a3/gpio.c b/arch/cris/arch-v32/drivers/mach-a3/gpio.c index 2dcd27adbad4..06b24ebda410 100644 --- a/arch/cris/arch-v32/drivers/mach-a3/gpio.c +++ b/arch/cris/arch-v32/drivers/mach-a3/gpio.c @@ -893,6 +893,7 @@ static const struct file_operations gpio_fops = { .write = gpio_write, .open = gpio_open, .release = gpio_release, + .llseek = noop_llseek, }; #ifdef CONFIG_ETRAX_VIRTUAL_GPIO diff --git a/arch/cris/arch-v32/drivers/mach-fs/gpio.c b/arch/cris/arch-v32/drivers/mach-fs/gpio.c index 5ec8a7d4e7d7..0649c8bea676 100644 --- a/arch/cris/arch-v32/drivers/mach-fs/gpio.c +++ b/arch/cris/arch-v32/drivers/mach-fs/gpio.c @@ -870,6 +870,7 @@ static const struct file_operations gpio_fops = { .write = gpio_write, .open = gpio_open, .release = gpio_release, + .llseek = noop_llseek, }; #ifdef CONFIG_ETRAX_VIRTUAL_GPIO diff --git a/arch/cris/arch-v32/drivers/pcf8563.c b/arch/cris/arch-v32/drivers/pcf8563.c index bef6eb53b153..0f7b101ee5ee 100644 --- a/arch/cris/arch-v32/drivers/pcf8563.c +++ b/arch/cris/arch-v32/drivers/pcf8563.c @@ -60,6 +60,7 @@ static int voltage_low; static const struct file_operations pcf8563_fops = { .owner = THIS_MODULE, .unlocked_ioctl = pcf8563_unlocked_ioctl, + .llseek = noop_llseek, }; unsigned char diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c index ca248f3adb80..a2e8a8c39856 100644 --- a/arch/cris/arch-v32/drivers/sync_serial.c +++ b/arch/cris/arch-v32/drivers/sync_serial.c @@ -247,7 +247,8 @@ static const struct file_operations sync_serial_fops = { .poll = sync_serial_poll, .unlocked_ioctl = sync_serial_ioctl, .open = sync_serial_open, - .release = sync_serial_release + .release = sync_serial_release, + .llseek = noop_llseek, }; static int __init etrax_sync_serial_init(void) diff --git a/arch/cris/kernel/profile.c b/arch/cris/kernel/profile.c index 195ec5fa0dd2..b82e08615d1b 100644 --- a/arch/cris/kernel/profile.c +++ b/arch/cris/kernel/profile.c @@ -59,6 +59,7 @@ write_cris_profile(struct file *file, const char __user *buf, static const struct file_operations cris_proc_profile_operations = { .read = read_cris_profile, .write = write_cris_profile, + .llseek = default_llseek, }; static int __init init_cris_profile(void) diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index aa8b5fa1a8de..6f22c4041630 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -354,6 +354,7 @@ retry: static const struct file_operations salinfo_event_fops = { .open = salinfo_event_open, .read = salinfo_event_read, + .llseek = noop_llseek, }; static int @@ -571,6 +572,7 @@ static const struct file_operations salinfo_data_fops = { .release = salinfo_log_release, .read = salinfo_log_read, .write = salinfo_log_write, + .llseek = default_llseek, }; static int __cpuinit diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c index fa1eceed0d23..30862c0358cd 100644 --- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c +++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c @@ -860,6 +860,7 @@ error: static const struct file_operations sn_hwperf_fops = { .unlocked_ioctl = sn_hwperf_ioctl, + .llseek = noop_llseek, }; static struct miscdevice sn_hwperf_dev = { diff --git a/arch/m68k/bvme6000/rtc.c b/arch/m68k/bvme6000/rtc.c index cb8617bb194b..1c4d4c7bf4d4 100644 --- a/arch/m68k/bvme6000/rtc.c +++ b/arch/m68k/bvme6000/rtc.c @@ -155,6 +155,7 @@ static const struct file_operations rtc_fops = { .unlocked_ioctl = rtc_ioctl, .open = rtc_open, .release = rtc_release, + .llseek = noop_llseek, }; static struct miscdevice rtc_dev = { diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c index 11ac6f63967a..39c79ebcd18a 100644 --- a/arch/m68k/mvme16x/rtc.c +++ b/arch/m68k/mvme16x/rtc.c @@ -144,6 +144,7 @@ static const struct file_operations rtc_fops = { .unlocked_ioctl = rtc_ioctl, .open = rtc_open, .release = rtc_release, + .llseek = noop_llseek, }; static struct miscdevice rtc_dev= diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c index 26f9b9ab19cc..557ef72472e0 100644 --- a/arch/mips/kernel/rtlx.c +++ b/arch/mips/kernel/rtlx.c @@ -468,7 +468,8 @@ static const struct file_operations rtlx_fops = { .release = file_release, .write = file_write, .read = file_read, - .poll = file_poll + .poll = file_poll, + .llseek = noop_llseek, }; static struct irqaction rtlx_irq = { diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 2bd2151c586a..3eb3cde2f661 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -1192,7 +1192,8 @@ static const struct file_operations vpe_fops = { .owner = THIS_MODULE, .open = vpe_open, .release = vpe_release, - .write = vpe_write + .write = vpe_write, + .llseek = noop_llseek, }; /* module wrapper entry points */ diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c index d4ed7a9156f5..ca35b730d189 100644 --- a/arch/mips/sibyte/common/sb_tbprof.c +++ b/arch/mips/sibyte/common/sb_tbprof.c @@ -545,6 +545,7 @@ static const struct file_operations sbprof_tb_fops = { .unlocked_ioctl = sbprof_tb_ioctl, .compat_ioctl = sbprof_tb_ioctl, .mmap = NULL, + .llseek = default_llseek, }; static struct class *tb_class; diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 50362b6ef6e9..b1dd962e247e 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -780,6 +780,7 @@ static const struct file_operations lparcfg_fops = { .write = lparcfg_write, .open = lparcfg_open, .release = single_release, + .llseek = seq_lseek, }; static int __init lparcfg_init(void) diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 67a84d8f118d..2b442e6c21e6 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -716,6 +716,7 @@ static const struct file_operations rtas_flash_operations = { .write = rtas_flash_write, .open = rtas_excl_open, .release = rtas_flash_release, + .llseek = default_llseek, }; static const struct file_operations manage_flash_operations = { @@ -724,6 +725,7 @@ static const struct file_operations manage_flash_operations = { .write = manage_flash_write, .open = rtas_excl_open, .release = rtas_excl_release, + .llseek = default_llseek, }; static const struct file_operations validate_flash_operations = { @@ -732,6 +734,7 @@ static const struct file_operations validate_flash_operations = { .write = validate_flash_write, .open = rtas_excl_open, .release = validate_flash_release, + .llseek = default_llseek, }; static int __init rtas_flash_init(void) diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 638883e23e3a..0438f819fe6b 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -354,6 +354,7 @@ static const struct file_operations proc_rtas_log_operations = { .poll = rtas_log_poll, .open = rtas_log_open, .release = rtas_log_release, + .llseek = noop_llseek, }; static int enable_surveillance(int timeout) diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c index 33e5fc7334fc..42d0a886de05 100644 --- a/arch/powerpc/platforms/iseries/mf.c +++ b/arch/powerpc/platforms/iseries/mf.c @@ -1249,6 +1249,7 @@ out: static const struct file_operations proc_vmlinux_operations = { .write = proc_mf_change_vmlinux, + .llseek = default_llseek, }; static int __init mf_proc_init(void) diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 57ddbb43b33a..1de2cbb92303 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -539,7 +539,8 @@ out: } static const struct file_operations ofdt_fops = { - .write = ofdt_write + .write = ofdt_write, + .llseek = noop_llseek, }; /* create /proc/powerpc/ofdt write-only by root */ diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c index 80e9e7652a4d..554457294a2b 100644 --- a/arch/powerpc/platforms/pseries/scanlog.c +++ b/arch/powerpc/platforms/pseries/scanlog.c @@ -170,6 +170,7 @@ const struct file_operations scanlog_fops = { .write = scanlog_write, .open = scanlog_open, .release = scanlog_release, + .llseek = noop_llseek, }; static int __init scanlog_init(void) diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index aa819dac2360..975e3ab13cb5 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -152,6 +152,7 @@ static const struct file_operations prng_fops = { .open = &prng_open, .release = NULL, .read = &prng_read, + .llseek = noop_llseek, }; static struct miscdevice prng_dev = { diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 1211bb1d2f24..020e51c063d2 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -618,6 +618,7 @@ static const struct file_operations dbfs_d204_ops = { .open = dbfs_d204_open, .read = dbfs_d204_read, .release = dbfs_d204_release, + .llseek = no_llseek, }; static int hypfs_dbfs_init(void) diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index ee5ab1a578e7..26cf177f6a3a 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -275,6 +275,7 @@ static const struct file_operations dbfs_d2fc_ops = { .open = dbfs_d2fc_open, .read = dbfs_d2fc_read, .release = dbfs_d2fc_release, + .llseek = no_llseek, }; int hypfs_vm_init(void) diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 98a4a4c267a7..74d98670be27 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -449,6 +449,7 @@ static const struct file_operations hypfs_file_ops = { .write = do_sync_write, .aio_read = hypfs_aio_read, .aio_write = hypfs_aio_write, + .llseek = no_llseek, }; static struct file_system_type hypfs_type = { diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 98192261491d..5ad6bc078bfd 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -174,6 +174,7 @@ static const struct file_operations debug_file_ops = { .write = debug_input, .open = debug_open, .release = debug_close, + .llseek = no_llseek, }; static struct dentry *debug_debugfs_root_entry; diff --git a/arch/sh/boards/mach-landisk/gio.c b/arch/sh/boards/mach-landisk/gio.c index 01e6abb769b9..8132dff078fb 100644 --- a/arch/sh/boards/mach-landisk/gio.c +++ b/arch/sh/boards/mach-landisk/gio.c @@ -128,6 +128,7 @@ static const struct file_operations gio_fops = { .open = gio_open, /* open */ .release = gio_close, /* release */ .unlocked_ioctl = gio_ioctl, + .llseek = noop_llseek, }; static int __init gio_init(void) diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index 2c0046ecc715..52de4a9424e8 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -132,6 +132,7 @@ static const struct file_operations apc_fops = { .unlocked_ioctl = apc_ioctl, .open = apc_open, .release = apc_release, + .llseek = noop_llseek, }; static struct miscdevice apc_miscdev = { APC_MINOR, APC_DEVNAME, &apc_fops }; diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 83e85c2e802a..6addb914fcc8 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -890,6 +890,7 @@ static ssize_t mdesc_read(struct file *file, char __user *buf, static const struct file_operations mdesc_fops = { .read = mdesc_read, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice mdesc_misc = { diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c index 584b965dc824..1e54a7843410 100644 --- a/arch/tile/kernel/hardwall.c +++ b/arch/tile/kernel/hardwall.c @@ -774,6 +774,7 @@ static const struct file_operations dev_hardwall_fops = { #endif .flush = hardwall_flush, .release = hardwall_release, + .llseek = noop_llseek, }; static struct cdev hardwall_dev; diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index cfcac1ff4cf2..dd1e6f871fe4 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -166,6 +166,7 @@ static const struct file_operations harddog_fops = { .unlocked_ioctl = harddog_ioctl, .open = harddog_open, .release = harddog_release, + .llseek = no_llseek, }; static struct miscdevice harddog_miscdev = { diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index ebc680717e59..975613b23dcf 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -843,6 +843,7 @@ static ssize_t mconsole_proc_write(struct file *file, static const struct file_operations mconsole_proc_fops = { .owner = THIS_MODULE, .write = mconsole_proc_write, + .llseek = noop_llseek, }; static int create_proc_mconsole(void) diff --git a/arch/um/drivers/mmapper_kern.c b/arch/um/drivers/mmapper_kern.c index 7158393b6793..8501e7d0015c 100644 --- a/arch/um/drivers/mmapper_kern.c +++ b/arch/um/drivers/mmapper_kern.c @@ -93,6 +93,7 @@ static const struct file_operations mmapper_fops = { .mmap = mmapper_mmap, .open = mmapper_open, .release = mmapper_release, + .llseek = default_llseek, }; /* diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index 4949044773ba..981085a93f30 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -100,6 +100,7 @@ static const struct file_operations rng_chrdev_ops = { .owner = THIS_MODULE, .open = rng_dev_open, .read = rng_dev_read, + .llseek = noop_llseek, }; /* rng_init shouldn't be called more than once at boot time */ diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 4c9c67bf09b7..fbbc4dadecc4 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1926,6 +1926,7 @@ static const struct file_operations apm_bios_fops = { .unlocked_ioctl = do_ioctl, .open = do_open, .release = do_release, + .llseek = noop_llseek, }; static struct miscdevice apm_device = { diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 8a85dd1b1aa1..1e8d66c1336a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -192,6 +192,7 @@ static const struct file_operations severities_coverage_fops = { .release = seq_release, .read = seq_read, .write = severities_coverage_write, + .llseek = seq_lseek, }; static int __init severities_debugfs_init(void) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index ed41562909fe..7a35b72d7c03 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1665,6 +1665,7 @@ struct file_operations mce_chrdev_ops = { .read = mce_read, .poll = mce_poll, .unlocked_ioctl = mce_ioctl, + .llseek = no_llseek, }; EXPORT_SYMBOL_GPL(mce_chrdev_ops); diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 8afd9f321f10..90fcf62854bb 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -78,6 +78,7 @@ static int setup_data_open(struct inode *inode, struct file *file) static const struct file_operations fops_setup_data = { .read = setup_data_read, .open = setup_data_open, + .llseek = default_llseek, }; static int __init diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index fa6551d36c10..0b3d37e83606 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -232,6 +232,7 @@ static const struct file_operations microcode_fops = { .owner = THIS_MODULE, .write = microcode_write, .open = microcode_open, + .llseek = no_llseek, }; static struct miscdevice microcode_dev = { diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 312ef0292815..50ac949c7f1c 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -1285,6 +1285,7 @@ static const struct file_operations tunables_fops = { .open = tunables_open, .read = tunables_read, .write = tunables_write, + .llseek = default_llseek, }; static int __init uv_ptc_init(void) diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c index 1304bcec8ee5..7c0fedd98ea0 100644 --- a/arch/x86/xen/debugfs.c +++ b/arch/x86/xen/debugfs.c @@ -106,6 +106,7 @@ static const struct file_operations u32_array_fops = { .open = u32_array_open, .release= xen_array_release, .read = u32_array_read, + .llseek = no_llseek, }; struct dentry *xen_debugfs_create_u32_array(const char *name, mode_t mode, diff --git a/block/bsg.c b/block/bsg.c index 82d58829ba59..83e381a26b58 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -968,6 +968,7 @@ static const struct file_operations bsg_fops = { .release = bsg_release, .unlocked_ioctl = bsg_ioctl, .owner = THIS_MODULE, + .llseek = default_llseek, }; void bsg_unregister_queue(struct request_queue *q) diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c index 5281ddda2777..cbab9b07bf28 100644 --- a/drivers/acpi/apei/erst-dbg.c +++ b/drivers/acpi/apei/erst-dbg.c @@ -180,6 +180,7 @@ static const struct file_operations erst_dbg_ops = { .read = erst_dbg_read, .write = erst_dbg_write, .unlocked_ioctl = erst_dbg_ioctl, + .llseek = no_llseek, }; static struct miscdevice erst_dbg_dev = { diff --git a/drivers/acpi/debugfs.c b/drivers/acpi/debugfs.c index 7de27d49c4b9..6355b575ee5a 100644 --- a/drivers/acpi/debugfs.c +++ b/drivers/acpi/debugfs.c @@ -69,6 +69,7 @@ static ssize_t cm_write(struct file *file, const char __user * user_buf, static const struct file_operations cm_fops = { .write = cm_write, + .llseek = default_llseek, }; int __init acpi_debugfs_init(void) diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c index 0e869b3f81ca..411620ef84c2 100644 --- a/drivers/acpi/ec_sys.c +++ b/drivers/acpi/ec_sys.c @@ -101,6 +101,7 @@ static struct file_operations acpi_ec_io_ops = { .open = acpi_ec_open_io, .read = acpi_ec_read_io, .write = acpi_ec_write_io, + .llseek = default_llseek, }; int acpi_ec_add_debugfs(struct acpi_ec *ec, unsigned int ec_device_count) diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index d439314a75d8..85d908993809 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -110,6 +110,7 @@ static const struct file_operations acpi_system_event_ops = { .read = acpi_system_read_event, .release = acpi_system_close_event, .poll = acpi_system_poll_event, + .llseek = default_llseek, }; #endif /* CONFIG_ACPI_PROC_EVENT */ diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 4e2c367fec11..dfcb33e8d405 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -7062,7 +7062,8 @@ static long DAC960_gam_ioctl(struct file *file, unsigned int Request, static const struct file_operations DAC960_gam_fops = { .owner = THIS_MODULE, - .unlocked_ioctl = DAC960_gam_ioctl + .unlocked_ioctl = DAC960_gam_ioctl, + .llseek = noop_llseek, }; static struct miscdevice DAC960_gam_dev = { diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c index 4a1b9e7464aa..32b484ba21bd 100644 --- a/drivers/block/aoe/aoechr.c +++ b/drivers/block/aoe/aoechr.c @@ -265,6 +265,7 @@ static const struct file_operations aoe_fops = { .open = aoechr_open, .release = aoechr_rel, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static char *aoe_devnode(struct device *dev, mode_t *mode) diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c index c397b3ddba9b..aa27cd84f633 100644 --- a/drivers/block/paride/pg.c +++ b/drivers/block/paride/pg.c @@ -234,6 +234,7 @@ static const struct file_operations pg_fops = { .write = pg_write, .open = pg_open, .release = pg_release, + .llseek = noop_llseek, }; static void pg_init_units(void) diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c index bc5825fdeaab..c372c32e0db3 100644 --- a/drivers/block/paride/pt.c +++ b/drivers/block/paride/pt.c @@ -239,6 +239,7 @@ static const struct file_operations pt_fops = { .unlocked_ioctl = pt_ioctl, .open = pt_open, .release = pt_release, + .llseek = noop_llseek, }; /* sysfs class support */ diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index b1cbeb59bb76..6a4642dd8283 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -3046,6 +3046,7 @@ static const struct file_operations pkt_ctl_fops = { .compat_ioctl = pkt_ctl_compat_ioctl, #endif .owner = THIS_MODULE, + .llseek = no_llseek, }; static struct miscdevice pkt_misc = { diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c index 54739b08c308..fd6305bf953e 100644 --- a/drivers/bluetooth/btmrvl_debugfs.c +++ b/drivers/bluetooth/btmrvl_debugfs.c @@ -92,6 +92,7 @@ static const struct file_operations btmrvl_hscfgcmd_fops = { .read = btmrvl_hscfgcmd_read, .write = btmrvl_hscfgcmd_write, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_psmode_write(struct file *file, const char __user *ubuf, @@ -130,6 +131,7 @@ static const struct file_operations btmrvl_psmode_fops = { .read = btmrvl_psmode_read, .write = btmrvl_psmode_write, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_pscmd_write(struct file *file, const char __user *ubuf, @@ -173,6 +175,7 @@ static const struct file_operations btmrvl_pscmd_fops = { .read = btmrvl_pscmd_read, .write = btmrvl_pscmd_write, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_gpiogap_write(struct file *file, const char __user *ubuf, @@ -211,6 +214,7 @@ static const struct file_operations btmrvl_gpiogap_fops = { .read = btmrvl_gpiogap_read, .write = btmrvl_gpiogap_write, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_hscmd_write(struct file *file, const char __user *ubuf, @@ -252,6 +256,7 @@ static const struct file_operations btmrvl_hscmd_fops = { .read = btmrvl_hscmd_read, .write = btmrvl_hscmd_write, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_hsmode_write(struct file *file, const char __user *ubuf, @@ -289,6 +294,7 @@ static const struct file_operations btmrvl_hsmode_fops = { .read = btmrvl_hsmode_read, .write = btmrvl_hsmode_write, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_curpsmode_read(struct file *file, char __user *userbuf, @@ -306,6 +312,7 @@ static ssize_t btmrvl_curpsmode_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_curpsmode_fops = { .read = btmrvl_curpsmode_read, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_psstate_read(struct file *file, char __user * userbuf, @@ -323,6 +330,7 @@ static ssize_t btmrvl_psstate_read(struct file *file, char __user * userbuf, static const struct file_operations btmrvl_psstate_fops = { .read = btmrvl_psstate_read, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_hsstate_read(struct file *file, char __user *userbuf, @@ -340,6 +348,7 @@ static ssize_t btmrvl_hsstate_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_hsstate_fops = { .read = btmrvl_hsstate_read, .open = btmrvl_open_generic, + .llseek = default_llseek, }; static ssize_t btmrvl_txdnldready_read(struct file *file, char __user *userbuf, @@ -358,6 +367,7 @@ static ssize_t btmrvl_txdnldready_read(struct file *file, char __user *userbuf, static const struct file_operations btmrvl_txdnldready_fops = { .read = btmrvl_txdnldready_read, .open = btmrvl_open_generic, + .llseek = default_llseek, }; void btmrvl_debugfs_init(struct hci_dev *hdev) diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 3aa7b2a54b6f..67c180c2c1e0 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -282,6 +282,7 @@ static const struct file_operations vhci_fops = { .poll = vhci_poll, .open = vhci_open, .release = vhci_release, + .llseek = no_llseek, }; static struct miscdevice vhci_miscdev= { diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c index 033e1505fca9..5ffa6904ea6b 100644 --- a/drivers/char/apm-emulation.c +++ b/drivers/char/apm-emulation.c @@ -402,6 +402,7 @@ static const struct file_operations apm_bios_fops = { .unlocked_ioctl = apm_ioctl, .open = apm_open, .release = apm_release, + .llseek = noop_llseek, }; static struct miscdevice apm_device = { diff --git a/drivers/char/bfin-otp.c b/drivers/char/bfin-otp.c index 836d4f0a876f..44660f1c4849 100644 --- a/drivers/char/bfin-otp.c +++ b/drivers/char/bfin-otp.c @@ -222,6 +222,7 @@ static const struct file_operations bfin_otp_fops = { .unlocked_ioctl = bfin_otp_ioctl, .read = bfin_otp_read, .write = bfin_otp_write, + .llseek = default_llseek, }; static struct miscdevice bfin_otp_misc_device = { diff --git a/drivers/char/briq_panel.c b/drivers/char/briq_panel.c index d5fa113afe37..f6718f05dad4 100644 --- a/drivers/char/briq_panel.c +++ b/drivers/char/briq_panel.c @@ -186,6 +186,7 @@ static const struct file_operations briq_panel_fops = { .write = briq_panel_write, .open = briq_panel_open, .release = briq_panel_release, + .llseek = noop_llseek, }; static struct miscdevice briq_panel_miscdev = { diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c index 91917133ae0a..a4a6c2f044b5 100644 --- a/drivers/char/bsr.c +++ b/drivers/char/bsr.c @@ -155,6 +155,7 @@ static const struct file_operations bsr_fops = { .owner = THIS_MODULE, .mmap = bsr_mmap, .open = bsr_open, + .llseek = noop_llseek, }; static void bsr_cleanup_devs(void) diff --git a/drivers/char/cs5535_gpio.c b/drivers/char/cs5535_gpio.c index 4d830dc482ef..0cf1e5fad9ab 100644 --- a/drivers/char/cs5535_gpio.c +++ b/drivers/char/cs5535_gpio.c @@ -169,7 +169,8 @@ static const struct file_operations cs5535_gpio_fops = { .owner = THIS_MODULE, .write = cs5535_gpio_write, .read = cs5535_gpio_read, - .open = cs5535_gpio_open + .open = cs5535_gpio_open, + .llseek = no_llseek, }; static int __init cs5535_gpio_init(void) diff --git a/drivers/char/ds1302.c b/drivers/char/ds1302.c index 170693c93c73..4f7aa364167c 100644 --- a/drivers/char/ds1302.c +++ b/drivers/char/ds1302.c @@ -288,6 +288,7 @@ get_rtc_status(char *buf) static const struct file_operations rtc_fops = { .owner = THIS_MODULE, .unlocked_ioctl = rtc_ioctl, + .llseek = noop_llseek, }; /* Probe for the chip by writing something to its RAM and try reading it back. */ diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c index dbee8688f75c..50462b63e51b 100644 --- a/drivers/char/ds1620.c +++ b/drivers/char/ds1620.c @@ -357,6 +357,7 @@ static const struct file_operations ds1620_fops = { .open = ds1620_open, .read = ds1620_read, .unlocked_ioctl = ds1620_unlocked_ioctl, + .llseek = no_llseek, }; static struct miscdevice ds1620_miscdev = { diff --git a/drivers/char/dsp56k.c b/drivers/char/dsp56k.c index 8a1b28a10ef0..353be4707d92 100644 --- a/drivers/char/dsp56k.c +++ b/drivers/char/dsp56k.c @@ -482,6 +482,7 @@ static const struct file_operations dsp56k_fops = { .unlocked_ioctl = dsp56k_ioctl, .open = dsp56k_open, .release = dsp56k_release, + .llseek = noop_llseek, }; diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c index e3859d4eaead..007eca3ed77c 100644 --- a/drivers/char/dtlk.c +++ b/drivers/char/dtlk.c @@ -105,6 +105,7 @@ static const struct file_operations dtlk_fops = .unlocked_ioctl = dtlk_ioctl, .open = dtlk_open, .release = dtlk_release, + .llseek = no_llseek, }; /* local prototypes */ diff --git a/drivers/char/genrtc.c b/drivers/char/genrtc.c index b6c2cc167c11..eaa0e4264e16 100644 --- a/drivers/char/genrtc.c +++ b/drivers/char/genrtc.c @@ -497,6 +497,7 @@ static const struct file_operations gen_rtc_fops = { .unlocked_ioctl = gen_rtc_unlocked_ioctl, .open = gen_rtc_open, .release = gen_rtc_release, + .llseek = noop_llseek, }; static struct miscdevice rtc_gen_dev = diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 3d9c61e5acbf..788da05190cc 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -170,6 +170,7 @@ static const struct file_operations rng_chrdev_ops = { .owner = THIS_MODULE, .open = rng_dev_open, .read = rng_dev_read, + .llseek = noop_llseek, }; static struct miscdevice rng_miscdev = { diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c index d4b71e8d0d23..2e49e515d8e7 100644 --- a/drivers/char/ip2/ip2main.c +++ b/drivers/char/ip2/ip2main.c @@ -236,6 +236,7 @@ static const struct file_operations ip2_ipl = { .write = ip2_ipl_write, .unlocked_ioctl = ip2_ipl_ioctl, .open = ip2_ipl_open, + .llseek = noop_llseek, }; static unsigned long irq_counter; diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index d8ec92a38980..c6709d6b0fd0 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -850,6 +850,7 @@ static const struct file_operations ipmi_fops = { .release = ipmi_release, .fasync = ipmi_fasync, .poll = ipmi_poll, + .llseek = noop_llseek, }; #define DEVICE_NAME "ipmidev" diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 654d566ca57c..da041f88f64a 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -909,6 +909,7 @@ static const struct file_operations ipmi_wdog_fops = { .open = ipmi_open, .release = ipmi_close, .fasync = ipmi_fasync, + .llseek = no_llseek, }; static struct miscdevice ipmi_wdog_miscdev = { diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c index be28391adb79..667abd23ad6a 100644 --- a/drivers/char/istallion.c +++ b/drivers/char/istallion.c @@ -704,6 +704,7 @@ static const struct file_operations stli_fsiomem = { .read = stli_memread, .write = stli_memwrite, .unlocked_ioctl = stli_memioctl, + .llseek = default_llseek, }; /*****************************************************************************/ diff --git a/drivers/char/lp.c b/drivers/char/lp.c index 938a3a273886..d2344117eaf5 100644 --- a/drivers/char/lp.c +++ b/drivers/char/lp.c @@ -748,6 +748,7 @@ static const struct file_operations lp_fops = { #ifdef CONFIG_PARPORT_1284 .read = lp_read, #endif + .llseek = noop_llseek, }; /* --- support for console on the line printer ----------------- */ diff --git a/drivers/char/mem.c b/drivers/char/mem.c index a398ecdbd758..8ebd232132fd 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -804,6 +804,7 @@ static const struct file_operations full_fops = { static const struct file_operations oldmem_fops = { .read = read_oldmem, .open = open_oldmem, + .llseek = default_llseek, }; #endif @@ -830,6 +831,7 @@ static ssize_t kmsg_write(struct file *file, const char __user *buf, static const struct file_operations kmsg_fops = { .write = kmsg_write, + .llseek = noop_llseek, }; static const struct memdev { @@ -881,6 +883,7 @@ static int memory_open(struct inode *inode, struct file *filp) static const struct file_operations memory_fops = { .open = memory_open, + .llseek = noop_llseek, }; static char *mem_devnode(struct device *dev, mode_t *mode) diff --git a/drivers/char/misc.c b/drivers/char/misc.c index abdafd488980..778273c93242 100644 --- a/drivers/char/misc.c +++ b/drivers/char/misc.c @@ -162,6 +162,7 @@ static struct class *misc_class; static const struct file_operations misc_fops = { .owner = THIS_MODULE, .open = misc_open, + .llseek = noop_llseek, }; /** diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c index ea7c99fa978f..1c4070ced066 100644 --- a/drivers/char/mmtimer.c +++ b/drivers/char/mmtimer.c @@ -72,6 +72,7 @@ static const struct file_operations mmtimer_fops = { .owner = THIS_MODULE, .mmap = mmtimer_mmap, .unlocked_ioctl = mmtimer_ioctl, + .llseek = noop_llseek, }; /* diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c index ecb89d798e35..966a95bc974b 100644 --- a/drivers/char/mspec.c +++ b/drivers/char/mspec.c @@ -316,7 +316,8 @@ uncached_mmap(struct file *file, struct vm_area_struct *vma) static const struct file_operations fetchop_fops = { .owner = THIS_MODULE, - .mmap = fetchop_mmap + .mmap = fetchop_mmap, + .llseek = noop_llseek, }; static struct miscdevice fetchop_miscdev = { @@ -327,7 +328,8 @@ static struct miscdevice fetchop_miscdev = { static const struct file_operations cached_fops = { .owner = THIS_MODULE, - .mmap = cached_mmap + .mmap = cached_mmap, + .llseek = noop_llseek, }; static struct miscdevice cached_miscdev = { @@ -338,7 +340,8 @@ static struct miscdevice cached_miscdev = { static const struct file_operations uncached_fops = { .owner = THIS_MODULE, - .mmap = uncached_mmap + .mmap = uncached_mmap, + .llseek = noop_llseek, }; static struct miscdevice uncached_miscdev = { diff --git a/drivers/char/mwave/mwavedd.c b/drivers/char/mwave/mwavedd.c index a4ec50c95072..0464822eac53 100644 --- a/drivers/char/mwave/mwavedd.c +++ b/drivers/char/mwave/mwavedd.c @@ -479,7 +479,8 @@ static const struct file_operations mwave_fops = { .write = mwave_write, .unlocked_ioctl = mwave_ioctl, .open = mwave_open, - .release = mwave_close + .release = mwave_close, + .llseek = default_llseek, }; diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c index 2604246501e4..8994ce32e6c7 100644 --- a/drivers/char/nwbutton.c +++ b/drivers/char/nwbutton.c @@ -182,6 +182,7 @@ static int button_read (struct file *filp, char __user *buffer, static const struct file_operations button_fops = { .owner = THIS_MODULE, .read = button_read, + .llseek = noop_llseek, }; /* diff --git a/drivers/char/pc8736x_gpio.c b/drivers/char/pc8736x_gpio.c index 8ecbcc174c15..b304ec052501 100644 --- a/drivers/char/pc8736x_gpio.c +++ b/drivers/char/pc8736x_gpio.c @@ -234,6 +234,7 @@ static const struct file_operations pc8736x_gpio_fileops = { .open = pc8736x_gpio_open, .write = nsc_gpio_write, .read = nsc_gpio_read, + .llseek = no_llseek, }; static void __init pc8736x_init_shadow(void) diff --git a/drivers/char/pcmcia/cm4000_cs.c b/drivers/char/pcmcia/cm4000_cs.c index ec73d9f6d9ed..c99f6997e5e7 100644 --- a/drivers/char/pcmcia/cm4000_cs.c +++ b/drivers/char/pcmcia/cm4000_cs.c @@ -1880,6 +1880,7 @@ static const struct file_operations cm4000_fops = { .unlocked_ioctl = cmm_ioctl, .open = cmm_open, .release= cmm_close, + .llseek = no_llseek, }; static struct pcmcia_device_id cm4000_ids[] = { diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c index 815cde1d0570..9ecc58baa8f3 100644 --- a/drivers/char/pcmcia/cm4040_cs.c +++ b/drivers/char/pcmcia/cm4040_cs.c @@ -650,6 +650,7 @@ static const struct file_operations reader_fops = { .open = cm4040_open, .release = cm4040_close, .poll = cm4040_poll, + .llseek = no_llseek, }; static struct pcmcia_device_id cm4040_ids[] = { diff --git a/drivers/char/random.c b/drivers/char/random.c index caef35a46890..5a1aa64f4e76 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1165,6 +1165,7 @@ const struct file_operations random_fops = { .poll = random_poll, .unlocked_ioctl = random_ioctl, .fasync = random_fasync, + .llseek = noop_llseek, }; const struct file_operations urandom_fops = { @@ -1172,6 +1173,7 @@ const struct file_operations urandom_fops = { .write = random_write, .unlocked_ioctl = random_ioctl, .fasync = random_fasync, + .llseek = noop_llseek, }; /*************************************************************** diff --git a/drivers/char/rio/rio_linux.c b/drivers/char/rio/rio_linux.c index d58c2eb07f07..1e87a93164bf 100644 --- a/drivers/char/rio/rio_linux.c +++ b/drivers/char/rio/rio_linux.c @@ -241,6 +241,7 @@ static struct real_driver rio_real_driver = { static const struct file_operations rio_fw_fops = { .owner = THIS_MODULE, .unlocked_ioctl = rio_fw_ioctl, + .llseek = noop_llseek, }; static struct miscdevice rio_fw_device = { diff --git a/drivers/char/scx200_gpio.c b/drivers/char/scx200_gpio.c index 99e5272e3c53..0bc135b9b16f 100644 --- a/drivers/char/scx200_gpio.c +++ b/drivers/char/scx200_gpio.c @@ -67,6 +67,7 @@ static const struct file_operations scx200_gpio_fileops = { .read = nsc_gpio_read, .open = scx200_gpio_open, .release = scx200_gpio_release, + .llseek = no_llseek, }; static struct cdev scx200_gpio_cdev; /* use 1 cdev for all pins */ diff --git a/drivers/char/snsc.c b/drivers/char/snsc.c index 32b74de18f5f..444ce17ac722 100644 --- a/drivers/char/snsc.c +++ b/drivers/char/snsc.c @@ -357,6 +357,7 @@ static const struct file_operations scdrv_fops = { .poll = scdrv_poll, .open = scdrv_open, .release = scdrv_release, + .llseek = noop_llseek, }; static struct class *snsc_class; diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c index f2167f8e5aab..8ef16490810c 100644 --- a/drivers/char/stallion.c +++ b/drivers/char/stallion.c @@ -608,6 +608,7 @@ static unsigned int sc26198_baudtable[] = { static const struct file_operations stl_fsiomem = { .owner = THIS_MODULE, .unlocked_ioctl = stl_memioctl, + .llseek = noop_llseek, }; static struct class *stallion_class; diff --git a/drivers/char/sx.c b/drivers/char/sx.c index 5b24db4ff7f1..e53f16865397 100644 --- a/drivers/char/sx.c +++ b/drivers/char/sx.c @@ -397,6 +397,7 @@ static struct real_driver sx_real_driver = { static const struct file_operations sx_fw_fops = { .owner = THIS_MODULE, .unlocked_ioctl = sx_fw_ioctl, + .llseek = noop_llseek, }; static struct miscdevice sx_fw_device = { diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index ef31bb81e843..f3019f53e875 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -772,6 +772,7 @@ static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf, static const struct file_operations proc_sysrq_trigger_operations = { .write = write_sysrq_trigger, + .llseek = noop_llseek, }; static void sysrq_init_procfs(void) diff --git a/drivers/char/tb0219.c b/drivers/char/tb0219.c index cad4eb65f13d..ad264185eb10 100644 --- a/drivers/char/tb0219.c +++ b/drivers/char/tb0219.c @@ -261,6 +261,7 @@ static const struct file_operations tb0219_fops = { .write = tanbac_tb0219_write, .open = tanbac_tb0219_open, .release = tanbac_tb0219_release, + .llseek = no_llseek, }; static void tb0219_restart(char *command) diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c index 80ea6bcfffdc..d087532b29d7 100644 --- a/drivers/char/tlclk.c +++ b/drivers/char/tlclk.c @@ -267,6 +267,7 @@ static const struct file_operations tlclk_fops = { .read = tlclk_read, .open = tlclk_open, .release = tlclk_release, + .llseek = noop_llseek, }; diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c index f8bc79f6de34..3d6e96172453 100644 --- a/drivers/char/toshiba.c +++ b/drivers/char/toshiba.c @@ -95,6 +95,7 @@ static long tosh_ioctl(struct file *, unsigned int, static const struct file_operations tosh_fops = { .owner = THIS_MODULE, .unlocked_ioctl = tosh_ioctl, + .llseek = noop_llseek, }; static struct miscdevice tosh_device = { diff --git a/drivers/char/uv_mmtimer.c b/drivers/char/uv_mmtimer.c index c7072ba14f48..493b47a0d511 100644 --- a/drivers/char/uv_mmtimer.c +++ b/drivers/char/uv_mmtimer.c @@ -52,6 +52,7 @@ static const struct file_operations uv_mmtimer_fops = { .owner = THIS_MODULE, .mmap = uv_mmtimer_mmap, .unlocked_ioctl = uv_mmtimer_ioctl, + .llseek = noop_llseek, }; /** diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c index b663d573aad9..be6d6fb47cc5 100644 --- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c +++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c @@ -567,6 +567,7 @@ static const struct file_operations hwicap_fops = { .read = hwicap_read, .open = hwicap_open, .release = hwicap_release, + .llseek = noop_llseek, }; static int __devinit hwicap_setup(struct device *dev, int id, diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c index 557e2272e5b3..ae2b8714d190 100644 --- a/drivers/dma/coh901318.c +++ b/drivers/dma/coh901318.c @@ -157,6 +157,7 @@ static const struct file_operations coh901318_debugfs_status_operations = { .owner = THIS_MODULE, .open = coh901318_debugfs_open, .read = coh901318_debugfs_read, + .llseek = default_llseek, }; diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index 8528b10763ed..bf184fb59a5e 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -405,6 +405,7 @@ static const struct file_operations nosy_ops = { .poll = nosy_poll, .open = nosy_open, .release = nosy_release, + .llseek = noop_llseek, }; #define PHY_PACKET_SIZE 12 /* 1 payload, 1 inverse, 1 ack = 3 quadlets */ diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 84da748555bc..ff6690f4fc87 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -284,7 +284,8 @@ EXPORT_SYMBOL(drm_exit); /** File operations structure */ static const struct file_operations drm_stub_fops = { .owner = THIS_MODULE, - .open = drm_stub_open + .open = drm_stub_open, + .llseek = noop_llseek, }; static int __init drm_core_init(void) diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c index 61b4caf220fa..00f1bdaa65cd 100644 --- a/drivers/gpu/drm/i810/i810_dma.c +++ b/drivers/gpu/drm/i810/i810_dma.c @@ -119,6 +119,7 @@ static const struct file_operations i810_buffer_fops = { .unlocked_ioctl = drm_ioctl, .mmap = i810_mmap_buffers, .fasync = drm_fasync, + .llseek = noop_llseek, }; static int i810_map_buffer(struct drm_buf *buf, struct drm_file *file_priv) diff --git a/drivers/gpu/drm/i830/i830_dma.c b/drivers/gpu/drm/i830/i830_dma.c index 671aa18415ac..5c6eb65f4e51 100644 --- a/drivers/gpu/drm/i830/i830_dma.c +++ b/drivers/gpu/drm/i830/i830_dma.c @@ -121,6 +121,7 @@ static const struct file_operations i830_buffer_fops = { .unlocked_ioctl = drm_ioctl, .mmap = i830_mmap_buffers, .fasync = drm_fasync, + .llseek = noop_llseek, }; static int i830_map_buffer(struct drm_buf *buf, struct drm_file *file_priv) diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 5e43d7076789..048149748fdc 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -782,6 +782,7 @@ static const struct file_operations i915_wedged_fops = { .open = i915_wedged_open, .read = i915_wedged_read, .write = i915_wedged_write, + .llseek = default_llseek, }; /* As the drm_debugfs_init() routines are called before dev->dev_private is diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c index b87569e96b16..3b7e0acf8164 100644 --- a/drivers/gpu/vga/vgaarb.c +++ b/drivers/gpu/vga/vgaarb.c @@ -1211,6 +1211,7 @@ static const struct file_operations vga_arb_device_fops = { .poll = vga_arb_fpoll, .open = vga_arb_open, .release = vga_arb_release, + .llseek = noop_llseek, }; static struct miscdevice vga_arb_device = { diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 850d02a7a925..61a3e572224a 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -1051,6 +1051,7 @@ static const struct file_operations hid_debug_events_fops = { .read = hid_debug_events_read, .poll = hid_debug_events_poll, .release = hid_debug_events_release, + .llseek = noop_llseek, }; diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c index f6e80c7ca61e..5a6879e235ac 100644 --- a/drivers/hid/hid-roccat.c +++ b/drivers/hid/hid-roccat.c @@ -384,6 +384,7 @@ static const struct file_operations roccat_ops = { .poll = roccat_poll, .open = roccat_open, .release = roccat_release, + .llseek = noop_llseek, }; static int __init roccat_init(void) diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index 47d70c523d93..bb98fa87aa86 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -329,6 +329,7 @@ static const struct file_operations hidraw_ops = { .open = hidraw_open, .release = hidraw_release, .unlocked_ioctl = hidraw_ioctl, + .llseek = noop_llseek, }; void hidraw_report_event(struct hid_device *hid, u8 *data, int len) diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 0a29c51114aa..e8f45d7ef3b2 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -847,6 +847,7 @@ static const struct file_operations hiddev_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = hiddev_compat_ioctl, #endif + .llseek = noop_llseek, }; static char *hiddev_devnode(struct device *dev, mode_t *mode) diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c index 653db1bda934..23b8555215d2 100644 --- a/drivers/hwmon/asus_atk0110.c +++ b/drivers/hwmon/asus_atk0110.c @@ -762,6 +762,7 @@ static const struct file_operations atk_debugfs_ggrp_fops = { .read = atk_debugfs_ggrp_read, .open = atk_debugfs_ggrp_open, .release = atk_debugfs_ggrp_release, + .llseek = no_llseek, }; static void atk_debugfs_init(struct atk_data *data) diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index 6d622cb5ac81..23d1d1c5587c 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -1903,6 +1903,7 @@ static const struct file_operations idetape_fops = { .unlocked_ioctl = idetape_chrdev_ioctl, .open = idetape_chrdev_open, .release = idetape_chrdev_release, + .llseek = noop_llseek, }; static int idetape_open(struct block_device *bdev, fmode_t mode) diff --git a/drivers/idle/i7300_idle.c b/drivers/idle/i7300_idle.c index 15341fc1c68b..c976285d313e 100644 --- a/drivers/idle/i7300_idle.c +++ b/drivers/idle/i7300_idle.c @@ -536,6 +536,7 @@ static ssize_t stats_read_ul(struct file *fp, char __user *ubuf, size_t count, static const struct file_operations idle_fops = { .open = stats_open_generic, .read = stats_read_ul, + .llseek = default_llseek, }; struct debugfs_file_info { diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c index d4ce8b63e19e..daef61d5e5bb 100644 --- a/drivers/infiniband/hw/ipath/ipath_diag.c +++ b/drivers/infiniband/hw/ipath/ipath_diag.c @@ -65,7 +65,8 @@ static const struct file_operations diag_file_ops = { .write = ipath_diag_write, .read = ipath_diag_read, .open = ipath_diag_open, - .release = ipath_diag_release + .release = ipath_diag_release, + .llseek = default_llseek, }; static ssize_t ipath_diagpkt_write(struct file *fp, @@ -75,6 +76,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp, static const struct file_operations diagpkt_file_ops = { .owner = THIS_MODULE, .write = ipath_diagpkt_write, + .llseek = noop_llseek, }; static atomic_t diagpkt_count = ATOMIC_INIT(0); diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c index 65eb8929db22..6078992da3f0 100644 --- a/drivers/infiniband/hw/ipath/ipath_file_ops.c +++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c @@ -63,7 +63,8 @@ static const struct file_operations ipath_file_ops = { .open = ipath_open, .release = ipath_close, .poll = ipath_poll, - .mmap = ipath_mmap + .mmap = ipath_mmap, + .llseek = noop_llseek, }; /* diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index 2fca70836dae..d13e72685dcf 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -103,6 +103,7 @@ static ssize_t atomic_stats_read(struct file *file, char __user *buf, static const struct file_operations atomic_stats_ops = { .read = atomic_stats_read, + .llseek = default_llseek, }; static ssize_t atomic_counters_read(struct file *file, char __user *buf, @@ -120,6 +121,7 @@ static ssize_t atomic_counters_read(struct file *file, char __user *buf, static const struct file_operations atomic_counters_ops = { .read = atomic_counters_read, + .llseek = default_llseek, }; static ssize_t flash_read(struct file *file, char __user *buf, @@ -224,6 +226,7 @@ bail: static const struct file_operations flash_ops = { .read = flash_read, .write = flash_write, + .llseek = default_llseek, }; static int create_device_files(struct super_block *sb, diff --git a/drivers/infiniband/hw/qib/qib_diag.c b/drivers/infiniband/hw/qib/qib_diag.c index 05dcf0d9a7d3..204c4dd9dce0 100644 --- a/drivers/infiniband/hw/qib/qib_diag.c +++ b/drivers/infiniband/hw/qib/qib_diag.c @@ -136,7 +136,8 @@ static const struct file_operations diag_file_ops = { .write = qib_diag_write, .read = qib_diag_read, .open = qib_diag_open, - .release = qib_diag_release + .release = qib_diag_release, + .llseek = default_llseek, }; static atomic_t diagpkt_count = ATOMIC_INIT(0); @@ -149,6 +150,7 @@ static ssize_t qib_diagpkt_write(struct file *fp, const char __user *data, static const struct file_operations diagpkt_file_ops = { .owner = THIS_MODULE, .write = qib_diagpkt_write, + .llseek = noop_llseek, }; int qib_diag_add(struct qib_devdata *dd) diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 6b11645edf35..aa2be214270f 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -63,7 +63,8 @@ static const struct file_operations qib_file_ops = { .open = qib_open, .release = qib_close, .poll = qib_poll, - .mmap = qib_mmapf + .mmap = qib_mmapf, + .llseek = noop_llseek, }; /* diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index 9f989c0ba9d3..a0e6613e8be6 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -367,6 +367,7 @@ bail: static const struct file_operations flash_ops = { .read = flash_read, .write = flash_write, + .llseek = default_llseek, }; static int add_cntr_files(struct super_block *sb, struct qib_devdata *dd) diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index c908c5f83645..51330363c0eb 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -761,7 +761,8 @@ static const struct file_operations evdev_fops = { .compat_ioctl = evdev_ioctl_compat, #endif .fasync = evdev_fasync, - .flush = evdev_flush + .flush = evdev_flush, + .llseek = no_llseek, }; static int evdev_install_chrdev(struct evdev *evdev) diff --git a/drivers/input/input.c b/drivers/input/input.c index ab6982056518..7919c2537225 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -2047,6 +2047,7 @@ out: static const struct file_operations input_fops = { .owner = THIS_MODULE, .open = input_open_file, + .llseek = noop_llseek, }; static int __init input_init(void) diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index d85bd8a7967d..502b2f73b434 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -736,6 +736,7 @@ static const struct file_operations joydev_fops = { .compat_ioctl = joydev_compat_ioctl, #endif .fasync = joydev_fasync, + .llseek = no_llseek, }; static int joydev_install_chrdev(struct joydev *joydev) diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 0d4266a533a5..2771ea778d34 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -804,6 +804,7 @@ static const struct file_operations uinput_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = uinput_compat_ioctl, #endif + .llseek = no_llseek, }; static struct miscdevice uinput_misc = { diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index d528a2dba064..31ec7265aac6 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -792,6 +792,7 @@ static const struct file_operations mousedev_fops = { .open = mousedev_open, .release = mousedev_release, .fasync = mousedev_fasync, + .llseek = noop_llseek, }; static int mousedev_install_chrdev(struct mousedev *mousedev) diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c index 998664854440..cd82bb125915 100644 --- a/drivers/input/serio/serio_raw.c +++ b/drivers/input/serio/serio_raw.c @@ -243,6 +243,7 @@ static const struct file_operations serio_raw_fops = { .write = serio_raw_write, .poll = serio_raw_poll, .fasync = serio_raw_fasync, + .llseek = noop_llseek, }; diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index de43c8c70ad0..859c81e9483b 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -267,6 +267,7 @@ static const struct file_operations mISDN_fops = { .unlocked_ioctl = mISDN_ioctl, .open = mISDN_open, .release = mISDN_close, + .llseek = no_llseek, }; static struct miscdevice mISDNtimer = { diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index 85b714df8eae..3c781cdddda9 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -514,6 +514,7 @@ static const struct file_operations lguest_fops = { .release = close, .write = write, .read = read, + .llseek = default_llseek, }; /* diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c index a3d25da2f275..1a57e88a38f7 100644 --- a/drivers/macintosh/ans-lcd.c +++ b/drivers/macintosh/ans-lcd.c @@ -137,6 +137,7 @@ const struct file_operations anslcd_fops = { .write = anslcd_write, .unlocked_ioctl = anslcd_ioctl, .open = anslcd_open, + .llseek = default_llseek, }; static struct miscdevice anslcd_dev = { diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index 2d17e76066bd..44d171cc2252 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -2398,6 +2398,7 @@ static const struct file_operations pmu_device_fops = { #endif .open = pmu_open, .release = pmu_release, + .llseek = noop_llseek, }; static struct miscdevice pmu_device = { diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 3e39193e5036..4b54618b4159 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1596,6 +1596,7 @@ static const struct file_operations _ctl_fops = { .unlocked_ioctl = dm_ctl_ioctl, .compat_ioctl = dm_compat_ctl_ioctl, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice _dm_misc = { diff --git a/drivers/media/IR/imon.c b/drivers/media/IR/imon.c index c185422ef28c..faed5a332c71 100644 --- a/drivers/media/IR/imon.c +++ b/drivers/media/IR/imon.c @@ -151,7 +151,8 @@ static const struct file_operations vfd_fops = { .owner = THIS_MODULE, .open = &display_open, .write = &vfd_write, - .release = &display_close + .release = &display_close, + .llseek = noop_llseek, }; /* lcd character device file operations */ @@ -159,7 +160,8 @@ static const struct file_operations lcd_fops = { .owner = THIS_MODULE, .open = &display_open, .write = &lcd_write, - .release = &display_close + .release = &display_close, + .llseek = noop_llseek, }; enum { diff --git a/drivers/media/IR/lirc_dev.c b/drivers/media/IR/lirc_dev.c index 5b145e8672fe..0acf6396e068 100644 --- a/drivers/media/IR/lirc_dev.c +++ b/drivers/media/IR/lirc_dev.c @@ -163,6 +163,7 @@ static struct file_operations fops = { .unlocked_ioctl = lirc_dev_fop_ioctl, .open = lirc_dev_fop_open, .release = lirc_dev_fop_close, + .llseek = noop_llseek, }; static int lirc_cdev_add(struct irctl *ir) diff --git a/drivers/media/dvb/bt8xx/dst_ca.c b/drivers/media/dvb/bt8xx/dst_ca.c index cf8705162845..7ed74dfc6b92 100644 --- a/drivers/media/dvb/bt8xx/dst_ca.c +++ b/drivers/media/dvb/bt8xx/dst_ca.c @@ -694,7 +694,8 @@ static const struct file_operations dst_ca_fops = { .open = dst_ca_open, .release = dst_ca_release, .read = dst_ca_read, - .write = dst_ca_write + .write = dst_ca_write, + .llseek = noop_llseek, }; static struct dvb_device dvbdev_ca = { diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c index 0042306ea11b..75c20ac82c0f 100644 --- a/drivers/media/dvb/dvb-core/dmxdev.c +++ b/drivers/media/dvb/dvb-core/dmxdev.c @@ -1150,6 +1150,7 @@ static const struct file_operations dvb_demux_fops = { .open = dvb_demux_open, .release = dvb_demux_release, .poll = dvb_demux_poll, + .llseek = default_llseek, }; static struct dvb_device dvbdev_demux = { @@ -1225,6 +1226,7 @@ static const struct file_operations dvb_dvr_fops = { .open = dvb_dvr_open, .release = dvb_dvr_release, .poll = dvb_dvr_poll, + .llseek = default_llseek, }; static struct dvb_device dvbdev_dvr = { diff --git a/drivers/media/dvb/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb/dvb-core/dvb_ca_en50221.c index cb97e6b85432..ff8921dd737f 100644 --- a/drivers/media/dvb/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb/dvb-core/dvb_ca_en50221.c @@ -1628,6 +1628,7 @@ static const struct file_operations dvb_ca_fops = { .open = dvb_ca_en50221_io_open, .release = dvb_ca_en50221_io_release, .poll = dvb_ca_en50221_io_poll, + .llseek = noop_llseek, }; static struct dvb_device dvbdev_ca = { diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c index 4d45b7d6b3fb..970c9b8882d4 100644 --- a/drivers/media/dvb/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb/dvb-core/dvb_frontend.c @@ -2034,7 +2034,8 @@ static const struct file_operations dvb_frontend_fops = { .unlocked_ioctl = dvb_generic_ioctl, .poll = dvb_frontend_poll, .open = dvb_frontend_open, - .release = dvb_frontend_release + .release = dvb_frontend_release, + .llseek = noop_llseek, }; int dvb_register_frontend(struct dvb_adapter* dvb, diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c index 6c3a8a06ccab..82636f517b9e 100644 --- a/drivers/media/dvb/dvb-core/dvb_net.c +++ b/drivers/media/dvb/dvb-core/dvb_net.c @@ -1475,6 +1475,7 @@ static const struct file_operations dvb_net_fops = { .unlocked_ioctl = dvb_net_ioctl, .open = dvb_generic_open, .release = dvb_net_close, + .llseek = noop_llseek, }; static struct dvb_device dvbdev_net = { diff --git a/drivers/media/dvb/dvb-core/dvbdev.c b/drivers/media/dvb/dvb-core/dvbdev.c index b915c39d782f..774b40e4f589 100644 --- a/drivers/media/dvb/dvb-core/dvbdev.c +++ b/drivers/media/dvb/dvb-core/dvbdev.c @@ -105,6 +105,7 @@ static const struct file_operations dvb_device_fops = { .owner = THIS_MODULE, .open = dvb_device_open, + .llseek = noop_llseek, }; static struct cdev dvb_device_cdev; diff --git a/drivers/media/dvb/firewire/firedtv-ci.c b/drivers/media/dvb/firewire/firedtv-ci.c index d3c2cf60de76..8ffb565f0704 100644 --- a/drivers/media/dvb/firewire/firedtv-ci.c +++ b/drivers/media/dvb/firewire/firedtv-ci.c @@ -220,6 +220,7 @@ static const struct file_operations fdtv_ca_fops = { .open = dvb_generic_open, .release = dvb_generic_release, .poll = fdtv_ca_io_poll, + .llseek = noop_llseek, }; static struct dvb_device fdtv_ca = { diff --git a/drivers/media/dvb/ttpci/av7110.c b/drivers/media/dvb/ttpci/av7110.c index a6be529eec5c..893fbc57c72f 100644 --- a/drivers/media/dvb/ttpci/av7110.c +++ b/drivers/media/dvb/ttpci/av7110.c @@ -730,6 +730,7 @@ static const struct file_operations dvb_osd_fops = { .unlocked_ioctl = dvb_generic_ioctl, .open = dvb_generic_open, .release = dvb_generic_release, + .llseek = noop_llseek, }; static struct dvb_device dvbdev_osd = { diff --git a/drivers/media/dvb/ttpci/av7110_av.c b/drivers/media/dvb/ttpci/av7110_av.c index 13efba942dac..6ef3996565ad 100644 --- a/drivers/media/dvb/ttpci/av7110_av.c +++ b/drivers/media/dvb/ttpci/av7110_av.c @@ -1521,6 +1521,7 @@ static const struct file_operations dvb_video_fops = { .open = dvb_video_open, .release = dvb_video_release, .poll = dvb_video_poll, + .llseek = noop_llseek, }; static struct dvb_device dvbdev_video = { @@ -1539,6 +1540,7 @@ static const struct file_operations dvb_audio_fops = { .open = dvb_audio_open, .release = dvb_audio_release, .poll = dvb_audio_poll, + .llseek = noop_llseek, }; static struct dvb_device dvbdev_audio = { diff --git a/drivers/media/dvb/ttpci/av7110_ca.c b/drivers/media/dvb/ttpci/av7110_ca.c index 4eba35a018e3..43f61f2eca98 100644 --- a/drivers/media/dvb/ttpci/av7110_ca.c +++ b/drivers/media/dvb/ttpci/av7110_ca.c @@ -353,6 +353,7 @@ static const struct file_operations dvb_ca_fops = { .open = dvb_ca_open, .release = dvb_generic_release, .poll = dvb_ca_poll, + .llseek = default_llseek, }; static struct dvb_device dvbdev_ca = { diff --git a/drivers/media/dvb/ttpci/av7110_ir.c b/drivers/media/dvb/ttpci/av7110_ir.c index b070e88d8c6b..908f272fe26c 100644 --- a/drivers/media/dvb/ttpci/av7110_ir.c +++ b/drivers/media/dvb/ttpci/av7110_ir.c @@ -312,6 +312,7 @@ static ssize_t av7110_ir_proc_write(struct file *file, const char __user *buffer static const struct file_operations av7110_ir_proc_fops = { .owner = THIS_MODULE, .write = av7110_ir_proc_write, + .llseek = noop_llseek, }; /* interrupt handler */ diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c index 66379b413906..b048ecc56db9 100644 --- a/drivers/mfd/ab3100-core.c +++ b/drivers/mfd/ab3100-core.c @@ -583,6 +583,7 @@ static ssize_t ab3100_get_set_reg(struct file *file, static const struct file_operations ab3100_get_set_reg_fops = { .open = ab3100_get_set_reg_open_file, .write = ab3100_get_set_reg, + .llseek = noop_llseek, }; static struct dentry *ab3100_dir; diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c index 557a8c2a7336..69c1f2fca141 100644 --- a/drivers/misc/hpilo.c +++ b/drivers/misc/hpilo.c @@ -640,6 +640,7 @@ static const struct file_operations ilo_fops = { .poll = ilo_poll, .open = ilo_open, .release = ilo_close, + .llseek = noop_llseek, }; static irqreturn_t ilo_isr(int irq, void *data) diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index 75ee0d3f6f45..6b38b5964294 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -279,6 +279,7 @@ static const struct file_operations phantom_file_ops = { .unlocked_ioctl = phantom_ioctl, .compat_ioctl = phantom_compat_ioctl, .poll = phantom_poll, + .llseek = no_llseek, }; static irqreturn_t phantom_isr(int irq, void *data) diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index cb3b4d228475..28852dfa310d 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -587,6 +587,7 @@ static const struct file_operations gru_fops = { .owner = THIS_MODULE, .unlocked_ioctl = gru_file_unlocked_ioctl, .mmap = gru_file_mmap, + .llseek = noop_llseek, }; static struct miscdevice gru_miscdev = { diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c index 53cb380c0987..46bc6d7551a3 100644 --- a/drivers/mmc/core/debugfs.c +++ b/drivers/mmc/core/debugfs.c @@ -245,6 +245,7 @@ static const struct file_operations mmc_dbg_ext_csd_fops = { .open = mmc_ext_csd_open, .read = mmc_ext_csd_read, .release = mmc_ext_csd_release, + .llseek = default_llseek, }; void mmc_add_card_debugfs(struct mmc_card *card) diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 3d2d1a69e9a0..af9fb0ff8210 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -1100,4 +1100,5 @@ const struct file_operations ubi_ctrl_cdev_operations = { .owner = THIS_MODULE, .unlocked_ioctl = ctrl_cdev_ioctl, .compat_ioctl = ctrl_cdev_compat_ioctl, + .llseek = noop_llseek, }; diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c index f5058ff2b210..8427533fe313 100644 --- a/drivers/net/caif/caif_spi.c +++ b/drivers/net/caif/caif_spi.c @@ -240,13 +240,15 @@ static ssize_t dbgfs_frame(struct file *file, char __user *user_buf, static const struct file_operations dbgfs_state_fops = { .open = dbgfs_open, .read = dbgfs_state, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static const struct file_operations dbgfs_frame_fops = { .open = dbgfs_open, .read = dbgfs_frame, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static inline void dev_debugfs_add(struct cfspi *cfspi) diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c index c327527fbbc8..e2bf10d90add 100644 --- a/drivers/net/cxgb4/cxgb4_main.c +++ b/drivers/net/cxgb4/cxgb4_main.c @@ -2026,6 +2026,7 @@ static const struct file_operations mem_debugfs_fops = { .owner = THIS_MODULE, .open = mem_open, .read = mem_read, + .llseek = default_llseek, }; static void __devinit add_debugfs_mem(struct adapter *adap, const char *name, diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index 6695a51e09e9..323e81e9e808 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -856,7 +856,8 @@ static const struct file_operations ppp_device_fops = { .poll = ppp_poll, .unlocked_ioctl = ppp_ioctl, .open = ppp_open, - .release = ppp_release + .release = ppp_release, + .llseek = noop_llseek, }; static __net_init int ppp_init_net(struct net *net) diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c index b1aec3e1892f..9c70b5fa3f51 100644 --- a/drivers/net/wimax/i2400m/debugfs.c +++ b/drivers/net/wimax/i2400m/debugfs.c @@ -119,6 +119,7 @@ const struct file_operations i2400m_rx_stats_fops = { .open = i2400m_stats_open, .read = i2400m_rx_stats_read, .write = i2400m_rx_stats_write, + .llseek = default_llseek, }; @@ -171,6 +172,7 @@ const struct file_operations i2400m_tx_stats_fops = { .open = i2400m_stats_open, .read = i2400m_tx_stats_read, .write = i2400m_tx_stats_write, + .llseek = default_llseek, }; diff --git a/drivers/net/wireless/airo.c b/drivers/net/wireless/airo.c index 1d05445d4ba3..ce77575e88b3 100644 --- a/drivers/net/wireless/airo.c +++ b/drivers/net/wireless/airo.c @@ -4430,21 +4430,24 @@ static const struct file_operations proc_statsdelta_ops = { .owner = THIS_MODULE, .read = proc_read, .open = proc_statsdelta_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static const struct file_operations proc_stats_ops = { .owner = THIS_MODULE, .read = proc_read, .open = proc_stats_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static const struct file_operations proc_status_ops = { .owner = THIS_MODULE, .read = proc_read, .open = proc_status_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static const struct file_operations proc_SSID_ops = { @@ -4452,7 +4455,8 @@ static const struct file_operations proc_SSID_ops = { .read = proc_read, .write = proc_write, .open = proc_SSID_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static const struct file_operations proc_BSSList_ops = { @@ -4460,7 +4464,8 @@ static const struct file_operations proc_BSSList_ops = { .read = proc_read, .write = proc_write, .open = proc_BSSList_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static const struct file_operations proc_APList_ops = { @@ -4468,7 +4473,8 @@ static const struct file_operations proc_APList_ops = { .read = proc_read, .write = proc_write, .open = proc_APList_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static const struct file_operations proc_config_ops = { @@ -4476,7 +4482,8 @@ static const struct file_operations proc_config_ops = { .read = proc_read, .write = proc_write, .open = proc_config_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static const struct file_operations proc_wepkey_ops = { @@ -4484,7 +4491,8 @@ static const struct file_operations proc_wepkey_ops = { .read = proc_read, .write = proc_write, .open = proc_wepkey_open, - .release = proc_close + .release = proc_close, + .llseek = default_llseek, }; static struct proc_dir_entry *airo_entry; diff --git a/drivers/net/wireless/ath/ath5k/debug.c b/drivers/net/wireless/ath/ath5k/debug.c index 4cccc29964f6..fb339c3852ee 100644 --- a/drivers/net/wireless/ath/ath5k/debug.c +++ b/drivers/net/wireless/ath/ath5k/debug.c @@ -271,6 +271,7 @@ static const struct file_operations fops_beacon = { .write = write_file_beacon, .open = ath5k_debugfs_open, .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -290,6 +291,7 @@ static const struct file_operations fops_reset = { .write = write_file_reset, .open = ath5k_debugfs_open, .owner = THIS_MODULE, + .llseek = noop_llseek, }; @@ -369,6 +371,7 @@ static const struct file_operations fops_debug = { .write = write_file_debug, .open = ath5k_debugfs_open, .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -480,6 +483,7 @@ static const struct file_operations fops_antenna = { .write = write_file_antenna, .open = ath5k_debugfs_open, .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -591,6 +595,7 @@ static const struct file_operations fops_frameerrors = { .write = write_file_frameerrors, .open = ath5k_debugfs_open, .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -748,6 +753,7 @@ static const struct file_operations fops_ani = { .write = write_file_ani, .open = ath5k_debugfs_open, .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -811,6 +817,7 @@ static const struct file_operations fops_queue = { .write = write_file_queue, .open = ath5k_debugfs_open, .owner = THIS_MODULE, + .llseek = default_llseek, }; diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 54aae931424e..cf500bf25ad5 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -71,7 +71,8 @@ static const struct file_operations fops_debug = { .read = read_file_debug, .write = write_file_debug, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; #endif @@ -116,7 +117,8 @@ static const struct file_operations fops_tx_chainmask = { .read = read_file_tx_chainmask, .write = write_file_tx_chainmask, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -158,7 +160,8 @@ static const struct file_operations fops_rx_chainmask = { .read = read_file_rx_chainmask, .write = write_file_rx_chainmask, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -259,7 +262,8 @@ static ssize_t read_file_dma(struct file *file, char __user *user_buf, static const struct file_operations fops_dma = { .read = read_file_dma, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; @@ -375,7 +379,8 @@ static ssize_t read_file_interrupt(struct file *file, char __user *user_buf, static const struct file_operations fops_interrupt = { .read = read_file_interrupt, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; void ath_debug_stat_rc(struct ath_softc *sc, int final_rate) @@ -464,7 +469,8 @@ static ssize_t read_file_rcstat(struct file *file, char __user *user_buf, static const struct file_operations fops_rcstat = { .read = read_file_rcstat, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static const char * ath_wiphy_state_str(enum ath_wiphy_state state) @@ -623,7 +629,8 @@ static const struct file_operations fops_wiphy = { .read = read_file_wiphy, .write = write_file_wiphy, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; #define PR(str, elem) \ @@ -702,7 +709,8 @@ void ath_debug_stat_tx(struct ath_softc *sc, struct ath_txq *txq, static const struct file_operations fops_xmit = { .read = read_file_xmit, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static ssize_t read_file_recv(struct file *file, char __user *user_buf, @@ -814,7 +822,8 @@ void ath_debug_stat_rx(struct ath_softc *sc, struct ath_rx_status *rs) static const struct file_operations fops_recv = { .read = read_file_recv, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static ssize_t read_file_regidx(struct file *file, char __user *user_buf, @@ -852,7 +861,8 @@ static const struct file_operations fops_regidx = { .read = read_file_regidx, .write = write_file_regidx, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static ssize_t read_file_regval(struct file *file, char __user *user_buf, @@ -894,7 +904,8 @@ static const struct file_operations fops_regval = { .read = read_file_regval, .write = write_file_regval, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; int ath9k_init_debug(struct ath_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index 7d09b4b17bbd..bc2ca7d898e9 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -536,7 +536,8 @@ static ssize_t read_file_tgt_stats(struct file *file, char __user *user_buf, static const struct file_operations fops_tgt_stats = { .read = read_file_tgt_stats, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static ssize_t read_file_xmit(struct file *file, char __user *user_buf, @@ -584,7 +585,8 @@ static ssize_t read_file_xmit(struct file *file, char __user *user_buf, static const struct file_operations fops_xmit = { .read = read_file_xmit, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; static ssize_t read_file_recv(struct file *file, char __user *user_buf, @@ -613,7 +615,8 @@ static ssize_t read_file_recv(struct file *file, char __user *user_buf, static const struct file_operations fops_recv = { .read = read_file_recv, .open = ath9k_debugfs_open, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = default_llseek, }; int ath9k_htc_init_debug(struct ath_hw *ah) diff --git a/drivers/net/wireless/iwlwifi/iwl-3945-rs.c b/drivers/net/wireless/iwlwifi/iwl-3945-rs.c index 8e84a08ff951..293e1dbc166c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945-rs.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945-rs.c @@ -873,6 +873,7 @@ static ssize_t iwl3945_sta_dbgfs_stats_table_read(struct file *file, static const struct file_operations rs_sta_dbgfs_stats_table_ops = { .read = iwl3945_sta_dbgfs_stats_table_read, .open = iwl3945_open_file_generic, + .llseek = default_llseek, }; static void iwl3945_add_debugfs(void *priv, void *priv_sta, diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c index 23e5c42e7d7e..a4378ba31ef6 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c @@ -2873,6 +2873,7 @@ static const struct file_operations rs_sta_dbgfs_scale_table_ops = { .write = rs_sta_dbgfs_scale_table_write, .read = rs_sta_dbgfs_scale_table_read, .open = open_file_generic, + .llseek = default_llseek, }; static ssize_t rs_sta_dbgfs_stats_table_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -2915,6 +2916,7 @@ static ssize_t rs_sta_dbgfs_stats_table_read(struct file *file, static const struct file_operations rs_sta_dbgfs_stats_table_ops = { .read = rs_sta_dbgfs_stats_table_read, .open = open_file_generic, + .llseek = default_llseek, }; static ssize_t rs_sta_dbgfs_rate_scale_data_read(struct file *file, @@ -2946,6 +2948,7 @@ static ssize_t rs_sta_dbgfs_rate_scale_data_read(struct file *file, static const struct file_operations rs_sta_dbgfs_rate_scale_data_ops = { .read = rs_sta_dbgfs_rate_scale_data_read, .open = open_file_generic, + .llseek = default_llseek, }; static void rs_add_debugfs(void *priv, void *priv_sta, diff --git a/drivers/net/wireless/iwmc3200wifi/debugfs.c b/drivers/net/wireless/iwmc3200wifi/debugfs.c index 53b0b7711f02..0a0cc9667cd6 100644 --- a/drivers/net/wireless/iwmc3200wifi/debugfs.c +++ b/drivers/net/wireless/iwmc3200wifi/debugfs.c @@ -402,24 +402,28 @@ static const struct file_operations iwm_debugfs_txq_fops = { .owner = THIS_MODULE, .open = iwm_generic_open, .read = iwm_debugfs_txq_read, + .llseek = default_llseek, }; static const struct file_operations iwm_debugfs_tx_credit_fops = { .owner = THIS_MODULE, .open = iwm_generic_open, .read = iwm_debugfs_tx_credit_read, + .llseek = default_llseek, }; static const struct file_operations iwm_debugfs_rx_ticket_fops = { .owner = THIS_MODULE, .open = iwm_generic_open, .read = iwm_debugfs_rx_ticket_read, + .llseek = default_llseek, }; static const struct file_operations iwm_debugfs_fw_err_fops = { .owner = THIS_MODULE, .open = iwm_generic_open, .read = iwm_debugfs_fw_err_read, + .llseek = default_llseek, }; void iwm_debugfs_init(struct iwm_priv *iwm) diff --git a/drivers/net/wireless/iwmc3200wifi/sdio.c b/drivers/net/wireless/iwmc3200wifi/sdio.c index edcb52330cf5..56383e7be835 100644 --- a/drivers/net/wireless/iwmc3200wifi/sdio.c +++ b/drivers/net/wireless/iwmc3200wifi/sdio.c @@ -364,6 +364,7 @@ static const struct file_operations iwm_debugfs_sdio_fops = { .owner = THIS_MODULE, .open = iwm_debugfs_sdio_open, .read = iwm_debugfs_sdio_read, + .llseek = default_llseek, }; static void if_sdio_debugfs_init(struct iwm_priv *iwm, struct dentry *parent_dir) diff --git a/drivers/net/wireless/libertas/debugfs.c b/drivers/net/wireless/libertas/debugfs.c index 74e94cc10e01..fbf3b0332bb7 100644 --- a/drivers/net/wireless/libertas/debugfs.c +++ b/drivers/net/wireless/libertas/debugfs.c @@ -962,6 +962,7 @@ static const struct file_operations lbs_debug_fops = { .open = open_file_generic, .write = lbs_debugfs_write, .read = lbs_debugfs_read, + .llseek = default_llseek, }; /** diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 88560d0ae50a..dab30a8c7470 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -2802,6 +2802,7 @@ static ssize_t ray_cs_essid_proc_write(struct file *file, static const struct file_operations ray_cs_essid_proc_fops = { .owner = THIS_MODULE, .write = ray_cs_essid_proc_write, + .llseek = noop_llseek, }; static ssize_t int_proc_write(struct file *file, const char __user *buffer, @@ -2835,6 +2836,7 @@ static ssize_t int_proc_write(struct file *file, const char __user *buffer, static const struct file_operations int_proc_fops = { .owner = THIS_MODULE, .write = int_proc_write, + .llseek = noop_llseek, }; #endif diff --git a/drivers/net/wireless/rt2x00/rt2x00debug.c b/drivers/net/wireless/rt2x00/rt2x00debug.c index 7d6f19a2805e..cea81e4c5c82 100644 --- a/drivers/net/wireless/rt2x00/rt2x00debug.c +++ b/drivers/net/wireless/rt2x00/rt2x00debug.c @@ -315,6 +315,7 @@ static const struct file_operations rt2x00debug_fop_queue_dump = { .poll = rt2x00debug_poll_queue_dump, .open = rt2x00debug_open_queue_dump, .release = rt2x00debug_release_queue_dump, + .llseek = default_llseek, }; static ssize_t rt2x00debug_read_queue_stats(struct file *file, @@ -371,6 +372,7 @@ static const struct file_operations rt2x00debug_fop_queue_stats = { .read = rt2x00debug_read_queue_stats, .open = rt2x00debug_file_open, .release = rt2x00debug_file_release, + .llseek = default_llseek, }; #ifdef CONFIG_RT2X00_LIB_CRYPTO @@ -423,6 +425,7 @@ static const struct file_operations rt2x00debug_fop_crypto_stats = { .read = rt2x00debug_read_crypto_stats, .open = rt2x00debug_file_open, .release = rt2x00debug_file_release, + .llseek = default_llseek, }; #endif @@ -543,6 +546,7 @@ static const struct file_operations rt2x00debug_fop_dev_flags = { .read = rt2x00debug_read_dev_flags, .open = rt2x00debug_file_open, .release = rt2x00debug_file_release, + .llseek = default_llseek, }; static struct dentry *rt2x00debug_create_file_driver(const char *name, diff --git a/drivers/net/wireless/wl12xx/wl1251_debugfs.c b/drivers/net/wireless/wl12xx/wl1251_debugfs.c index a4ae7c4d94b5..fa620a5e5303 100644 --- a/drivers/net/wireless/wl12xx/wl1251_debugfs.c +++ b/drivers/net/wireless/wl12xx/wl1251_debugfs.c @@ -238,6 +238,7 @@ static ssize_t tx_queue_len_read(struct file *file, char __user *userbuf, static const struct file_operations tx_queue_len_ops = { .read = tx_queue_len_read, .open = wl1251_open_file_generic, + .llseek = generic_file_llseek, }; static ssize_t tx_queue_status_read(struct file *file, char __user *userbuf, @@ -259,6 +260,7 @@ static ssize_t tx_queue_status_read(struct file *file, char __user *userbuf, static const struct file_operations tx_queue_status_ops = { .read = tx_queue_status_read, .open = wl1251_open_file_generic, + .llseek = generic_file_llseek, }; static void wl1251_debugfs_delete_files(struct wl1251 *wl) diff --git a/drivers/net/wireless/wl12xx/wl1271_debugfs.c b/drivers/net/wireless/wl12xx/wl1271_debugfs.c index 6e25303a8e7f..66c2b90ddfd4 100644 --- a/drivers/net/wireless/wl12xx/wl1271_debugfs.c +++ b/drivers/net/wireless/wl12xx/wl1271_debugfs.c @@ -239,6 +239,7 @@ static ssize_t tx_queue_len_read(struct file *file, char __user *userbuf, static const struct file_operations tx_queue_len_ops = { .read = tx_queue_len_read, .open = wl1271_open_file_generic, + .llseek = default_llseek, }; static ssize_t gpio_power_read(struct file *file, char __user *user_buf, @@ -293,7 +294,8 @@ out: static const struct file_operations gpio_power_ops = { .read = gpio_power_read, .write = gpio_power_write, - .open = wl1271_open_file_generic + .open = wl1271_open_file_generic, + .llseek = default_llseek, }; static void wl1271_debugfs_delete_files(struct wl1271 *wl) diff --git a/drivers/oprofile/oprofile_files.c b/drivers/oprofile/oprofile_files.c index bbd7516e0869..9bb4d4bdc237 100644 --- a/drivers/oprofile/oprofile_files.c +++ b/drivers/oprofile/oprofile_files.c @@ -59,6 +59,7 @@ static ssize_t timeout_write(struct file *file, char const __user *buf, static const struct file_operations timeout_fops = { .read = timeout_read, .write = timeout_write, + .llseek = default_llseek, }; #endif @@ -93,7 +94,8 @@ static ssize_t depth_write(struct file *file, char const __user *buf, size_t cou static const struct file_operations depth_fops = { .read = depth_read, - .write = depth_write + .write = depth_write, + .llseek = default_llseek, }; @@ -105,6 +107,7 @@ static ssize_t pointer_size_read(struct file *file, char __user *buf, size_t cou static const struct file_operations pointer_size_fops = { .read = pointer_size_read, + .llseek = default_llseek, }; @@ -116,6 +119,7 @@ static ssize_t cpu_type_read(struct file *file, char __user *buf, size_t count, static const struct file_operations cpu_type_fops = { .read = cpu_type_read, + .llseek = default_llseek, }; @@ -151,6 +155,7 @@ static ssize_t enable_write(struct file *file, char const __user *buf, size_t co static const struct file_operations enable_fops = { .read = enable_read, .write = enable_write, + .llseek = default_llseek, }; @@ -163,6 +168,7 @@ static ssize_t dump_write(struct file *file, char const __user *buf, size_t coun static const struct file_operations dump_fops = { .write = dump_write, + .llseek = noop_llseek, }; void oprofile_create_files(struct super_block *sb, struct dentry *root) diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index 2766a6d3c2e9..6b6a1f71957d 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -117,12 +117,14 @@ static const struct file_operations ulong_fops = { .read = ulong_read_file, .write = ulong_write_file, .open = default_open, + .llseek = default_llseek, }; static const struct file_operations ulong_ro_fops = { .read = ulong_read_file, .open = default_open, + .llseek = default_llseek, }; @@ -183,6 +185,7 @@ static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t coun static const struct file_operations atomic_ro_fops = { .read = atomic_read_file, .open = default_open, + .llseek = default_llseek, }; diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index 909924692b8a..b3cf6223f63a 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -472,6 +472,7 @@ static ssize_t aer_inject_write(struct file *filp, const char __user *ubuf, static const struct file_operations aer_inject_fops = { .write = aer_inject_write, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice aer_inject_device = { diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index e3154ff7a39f..f200677851b8 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -2360,6 +2360,7 @@ static const struct file_operations sonypi_misc_fops = { .release = sonypi_misc_release, .fasync = sonypi_misc_fasync, .unlocked_ioctl = sonypi_misc_ioctl, + .llseek = noop_llseek, }; static struct miscdevice sonypi_misc_device = { diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index d60557cae8ef..ef151ce04430 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -748,6 +748,7 @@ static const struct file_operations wdt_fops = { .write = wdt_write, .open = wdt_open, .release = wdt_release, + .llseek = no_llseek, }; static struct miscdevice wdt_dev = { diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index 7158f9528ecc..c71d89dba302 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -670,6 +670,7 @@ static const struct file_operations dasd_eer_fops = { .read = &dasd_eer_read, .poll = &dasd_eer_poll, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice *dasd_eer_dev = NULL; diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 857dfcb7b359..eb28fb01a38a 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -520,6 +520,7 @@ static const struct file_operations fs3270_fops = { .compat_ioctl = fs3270_ioctl, /* ioctl */ .open = fs3270_open, /* open */ .release = fs3270_close, /* release */ + .llseek = no_llseek, }; /* diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c index e021ec663ef9..5b8b8592d311 100644 --- a/drivers/s390/char/monreader.c +++ b/drivers/s390/char/monreader.c @@ -447,6 +447,7 @@ static const struct file_operations mon_fops = { .release = &mon_close, .read = &mon_read, .poll = &mon_poll, + .llseek = noop_llseek, }; static struct miscdevice mon_dev = { diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c index 572a1e7fd099..e0702d3ea33b 100644 --- a/drivers/s390/char/monwriter.c +++ b/drivers/s390/char/monwriter.c @@ -274,6 +274,7 @@ static const struct file_operations monwrite_fops = { .open = &monwrite_open, .release = &monwrite_close, .write = &monwrite_write, + .llseek = noop_llseek, }; static struct miscdevice mon_dev = { diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c index 539045acaad4..883e2db02bd3 100644 --- a/drivers/s390/char/tape_char.c +++ b/drivers/s390/char/tape_char.c @@ -53,6 +53,7 @@ static const struct file_operations tape_fops = #endif .open = tapechar_open, .release = tapechar_release, + .llseek = no_llseek, }; static int tapechar_major = TAPECHAR_MAJOR; diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c index 04e532eec032..0e7cb1a84151 100644 --- a/drivers/s390/char/vmcp.c +++ b/drivers/s390/char/vmcp.c @@ -177,6 +177,7 @@ static const struct file_operations vmcp_fops = { .write = vmcp_write, .unlocked_ioctl = vmcp_ioctl, .compat_ioctl = vmcp_ioctl, + .llseek = no_llseek, }; static struct miscdevice vmcp_dev = { diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index e40a1b892866..0d6dc4b92cc2 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -97,6 +97,7 @@ static const struct file_operations vmlogrdr_fops = { .open = vmlogrdr_open, .release = vmlogrdr_release, .read = vmlogrdr_read, + .llseek = no_llseek, }; diff --git a/drivers/s390/char/vmwatchdog.c b/drivers/s390/char/vmwatchdog.c index e13508c98b1a..12ef9121d4f0 100644 --- a/drivers/s390/char/vmwatchdog.c +++ b/drivers/s390/char/vmwatchdog.c @@ -297,6 +297,7 @@ static const struct file_operations vmwdt_fops = { .unlocked_ioctl = &vmwdt_ioctl, .write = &vmwdt_write, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice vmwdt_dev = { diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index f5ea3384a4b9..3b94044027c2 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -459,6 +459,7 @@ static const struct file_operations zcore_memmap_fops = { .read = zcore_memmap_read, .open = zcore_memmap_open, .release = zcore_memmap_release, + .llseek = no_llseek, }; static ssize_t zcore_reipl_write(struct file *filp, const char __user *buf, @@ -486,6 +487,7 @@ static const struct file_operations zcore_reipl_fops = { .write = zcore_reipl_write, .open = zcore_reipl_open, .release = zcore_reipl_release, + .llseek = no_llseek, }; #ifdef CONFIG_32BIT diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index a83877c664a6..f2b77e7bfc6f 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -806,6 +806,7 @@ static const struct file_operations chsc_fops = { .open = nonseekable_open, .unlocked_ioctl = chsc_ioctl, .compat_ioctl = chsc_ioctl, + .llseek = no_llseek, }; static struct miscdevice chsc_misc_device = { diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index ac94ac751459..ca8e1c240c3c 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1067,6 +1067,7 @@ static ssize_t cio_settle_write(struct file *file, const char __user *buf, static const struct file_operations cio_settle_proc_fops = { .open = nonseekable_open, .write = cio_settle_write, + .llseek = no_llseek, }; static int __init cio_settle_init(void) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 41e0aaefafd5..f5221749d180 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -897,7 +897,8 @@ static const struct file_operations zcrypt_fops = { .compat_ioctl = zcrypt_compat_ioctl, #endif .open = zcrypt_open, - .release = zcrypt_release + .release = zcrypt_release, + .llseek = no_llseek, }; /* diff --git a/drivers/s390/scsi/zfcp_cfdc.c b/drivers/s390/scsi/zfcp_cfdc.c index fcbd2b756da4..1838cda68ba8 100644 --- a/drivers/s390/scsi/zfcp_cfdc.c +++ b/drivers/s390/scsi/zfcp_cfdc.c @@ -251,8 +251,9 @@ static const struct file_operations zfcp_cfdc_fops = { .open = nonseekable_open, .unlocked_ioctl = zfcp_cfdc_dev_ioctl, #ifdef CONFIG_COMPAT - .compat_ioctl = zfcp_cfdc_dev_ioctl + .compat_ioctl = zfcp_cfdc_dev_ioctl, #endif + .llseek = no_llseek, }; struct miscdevice zfcp_cfdc_misc = { diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c index 1690e53fb84a..55f71ea9c418 100644 --- a/drivers/sbus/char/display7seg.c +++ b/drivers/sbus/char/display7seg.c @@ -162,6 +162,7 @@ static const struct file_operations d7s_fops = { .compat_ioctl = d7s_ioctl, .open = d7s_open, .release = d7s_release, + .llseek = noop_llseek, }; static struct miscdevice d7s_miscdev = { diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c index 078e5f4520ef..8ce414e39489 100644 --- a/drivers/sbus/char/envctrl.c +++ b/drivers/sbus/char/envctrl.c @@ -720,6 +720,7 @@ static const struct file_operations envctrl_fops = { #endif .open = envctrl_open, .release = envctrl_release, + .llseek = noop_llseek, }; static struct miscdevice envctrl_dev = { diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index e20b7bdd4c78..67aad69cfbc2 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -222,7 +222,8 @@ static const struct file_operations twa_fops = { .owner = THIS_MODULE, .unlocked_ioctl = twa_chrdev_ioctl, .open = twa_chrdev_open, - .release = NULL + .release = NULL, + .llseek = noop_llseek, }; /* This function will complete an aen request from the isr */ diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index f481e734aad4..7afac93d889f 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -890,7 +890,8 @@ static const struct file_operations twl_fops = { .owner = THIS_MODULE, .unlocked_ioctl = twl_chrdev_ioctl, .open = twl_chrdev_open, - .release = NULL + .release = NULL, + .llseek = noop_llseek, }; /* This function passes sense data from firmware to scsi layer */ diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index 30d735ad35b5..5a2337306037 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -1059,7 +1059,8 @@ static const struct file_operations tw_fops = { .owner = THIS_MODULE, .unlocked_ioctl = tw_chrdev_ioctl, .open = tw_chrdev_open, - .release = NULL + .release = NULL, + .llseek = noop_llseek, }; /* This function will free up device extension resources */ diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index cad6f9abaeb9..13af86eec96e 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1039,6 +1039,7 @@ static const struct file_operations aac_cfg_fops = { .compat_ioctl = aac_compat_cfg_ioctl, #endif .open = aac_cfg_open, + .llseek = noop_llseek, }; static struct scsi_host_template aac_driver_template = { diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c index d6532187f616..e40c9f7a002a 100644 --- a/drivers/scsi/ch.c +++ b/drivers/scsi/ch.c @@ -981,6 +981,7 @@ static const struct file_operations changer_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = ch_ioctl_compat, #endif + .llseek = noop_llseek, }; static int __init init_ch_module(void) diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c index ffc1edf5e80d..7a61206ed1c0 100644 --- a/drivers/scsi/dpt_i2o.c +++ b/drivers/scsi/dpt_i2o.c @@ -126,6 +126,7 @@ static const struct file_operations adpt_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = compat_adpt_ioctl, #endif + .llseek = noop_llseek, }; /* Structures and definitions for synchronous message posting. diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c index b860d650a563..9886586df01f 100644 --- a/drivers/scsi/gdth.c +++ b/drivers/scsi/gdth.c @@ -372,6 +372,7 @@ static const struct file_operations gdth_fops = { .unlocked_ioctl = gdth_unlocked_ioctl, .open = gdth_open, .release = gdth_close, + .llseek = noop_llseek, }; #include "gdth_proc.h" diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 0b6e3228610a..aac80f7bb999 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -101,6 +101,7 @@ static const struct file_operations megadev_fops = { .owner = THIS_MODULE, .unlocked_ioctl = megadev_unlocked_ioctl, .open = megadev_open, + .llseek = noop_llseek, }; /* diff --git a/drivers/scsi/megaraid/megaraid_mm.c b/drivers/scsi/megaraid/megaraid_mm.c index 41f82f76d884..ab801232d777 100644 --- a/drivers/scsi/megaraid/megaraid_mm.c +++ b/drivers/scsi/megaraid/megaraid_mm.c @@ -75,6 +75,7 @@ static const struct file_operations lsi_fops = { .compat_ioctl = mraid_mm_compat_ioctl, #endif .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice megaraid_mm_dev = { diff --git a/drivers/scsi/megaraid/megaraid_sas.c b/drivers/scsi/megaraid/megaraid_sas.c index 99e4478c3f3e..209cc87b9a32 100644 --- a/drivers/scsi/megaraid/megaraid_sas.c +++ b/drivers/scsi/megaraid/megaraid_sas.c @@ -3957,6 +3957,7 @@ static const struct file_operations megasas_mgmt_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = megasas_mgmt_compat_ioctl, #endif + .llseek = noop_llseek, }; /* diff --git a/drivers/scsi/mpt2sas/mpt2sas_ctl.c b/drivers/scsi/mpt2sas/mpt2sas_ctl.c index b774973f0765..9a4e584ae3cc 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_ctl.c +++ b/drivers/scsi/mpt2sas/mpt2sas_ctl.c @@ -2952,6 +2952,7 @@ static const struct file_operations ctl_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = _ctl_ioctl_compat, #endif + .llseek = noop_llseek, }; static struct miscdevice ctl_dev = { diff --git a/drivers/scsi/osd/osd_uld.c b/drivers/scsi/osd/osd_uld.c index ffdd9fdb9995..b31a8e3841d7 100644 --- a/drivers/scsi/osd/osd_uld.c +++ b/drivers/scsi/osd/osd_uld.c @@ -182,6 +182,7 @@ static const struct file_operations osd_fops = { .open = osd_uld_open, .release = osd_uld_release, .unlocked_ioctl = osd_uld_ioctl, + .llseek = noop_llseek, }; struct osd_dev *osduld_path_lookup(const char *name) diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index ecc45c8b4e6b..4b8765785aeb 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -4165,6 +4165,7 @@ static const struct file_operations pmcraid_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = pmcraid_chr_ioctl, #endif + .llseek = noop_llseek, }; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 1e4bff695254..9946fac54255 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3948,6 +3948,7 @@ static struct pci_driver qla2xxx_pci_driver = { static struct file_operations apidev_fops = { .owner = THIS_MODULE, + .llseek = noop_llseek, }; /** diff --git a/drivers/scsi/scsi_tgt_if.c b/drivers/scsi/scsi_tgt_if.c index a87e21c35ef2..bbb02f6e917c 100644 --- a/drivers/scsi/scsi_tgt_if.c +++ b/drivers/scsi/scsi_tgt_if.c @@ -333,6 +333,7 @@ static const struct file_operations tgt_fops = { .poll = tgt_poll, .write = tgt_write, .mmap = tgt_mmap, + .llseek = noop_llseek, }; static struct miscdevice tgt_miscdev = { diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 78d616315d8e..00baea1e2dbf 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1351,6 +1351,7 @@ static const struct file_operations sg_fops = { .mmap = sg_mmap, .release = sg_release, .fasync = sg_fasync, + .llseek = no_llseek, }; static struct class *sg_sysfs_class; diff --git a/drivers/serial/mfd.c b/drivers/serial/mfd.c index bc9af503907f..6703f3e802a2 100644 --- a/drivers/serial/mfd.c +++ b/drivers/serial/mfd.c @@ -227,12 +227,14 @@ static const struct file_operations port_regs_ops = { .owner = THIS_MODULE, .open = hsu_show_regs_open, .read = port_show_regs, + .llseek = default_llseek, }; static const struct file_operations dma_regs_ops = { .owner = THIS_MODULE, .open = hsu_show_regs_open, .read = dma_show_regs, + .llseek = default_llseek, }; static int hsu_debugfs_init(struct hsu_port *hsu) diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c index d256cb00604c..a32aa66d66bf 100644 --- a/drivers/spi/dw_spi.c +++ b/drivers/spi/dw_spi.c @@ -131,6 +131,7 @@ static const struct file_operations mrst_spi_regs_ops = { .owner = THIS_MODULE, .open = spi_show_regs_open, .read = spi_show_regs, + .llseek = default_llseek, }; static int mrst_spi_debugfs_init(struct dw_spi *dws) diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index ea1bec3c9a13..4e6245e67995 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -545,6 +545,7 @@ static const struct file_operations spidev_fops = { .unlocked_ioctl = spidev_ioctl, .open = spidev_open, .release = spidev_release, + .llseek = no_llseek, }; /*-------------------------------------------------------------------------*/ diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c index 14091313cebb..fecb89e8c663 100644 --- a/drivers/staging/comedi/comedi_fops.c +++ b/drivers/staging/comedi/comedi_fops.c @@ -1922,6 +1922,7 @@ const struct file_operations comedi_fops = { .mmap = comedi_mmap, .poll = comedi_poll, .fasync = comedi_fasync, + .llseek = noop_llseek, }; struct class *comedi_class; diff --git a/drivers/staging/crystalhd/crystalhd_lnx.c b/drivers/staging/crystalhd/crystalhd_lnx.c index fbb80f09a3d9..af258991fe7f 100644 --- a/drivers/staging/crystalhd/crystalhd_lnx.c +++ b/drivers/staging/crystalhd/crystalhd_lnx.c @@ -351,6 +351,7 @@ static const struct file_operations chd_dec_fops = { .unlocked_ioctl = chd_dec_ioctl, .open = chd_dec_open, .release = chd_dec_close, + .llseek = noop_llseek, }; static int __devinit chd_dec_init_chdev(struct crystalhd_adp *adp) diff --git a/drivers/staging/dream/camera/msm_camera.c b/drivers/staging/dream/camera/msm_camera.c index 81bd71fd816e..de4ab61efd4b 100644 --- a/drivers/staging/dream/camera/msm_camera.c +++ b/drivers/staging/dream/camera/msm_camera.c @@ -1941,6 +1941,7 @@ static const struct file_operations msm_fops_config = { .open = msm_open, .unlocked_ioctl = msm_ioctl_config, .release = msm_release_config, + .llseek = no_llseek, }; static const struct file_operations msm_fops_control = { @@ -1948,6 +1949,7 @@ static const struct file_operations msm_fops_control = { .open = msm_open_control, .unlocked_ioctl = msm_ioctl_control, .release = msm_release_control, + .llseek = no_llseek, }; static const struct file_operations msm_fops_frame = { @@ -1956,6 +1958,7 @@ static const struct file_operations msm_fops_frame = { .unlocked_ioctl = msm_ioctl_frame, .release = msm_release_frame, .poll = msm_poll_frame, + .llseek = no_llseek, }; static int msm_setup_cdev(struct msm_device *msm, diff --git a/drivers/staging/dream/pmem.c b/drivers/staging/dream/pmem.c index 7d6bbadd7fc7..3640d1f2376d 100644 --- a/drivers/staging/dream/pmem.c +++ b/drivers/staging/dream/pmem.c @@ -180,6 +180,7 @@ const struct file_operations pmem_fops = { .mmap = pmem_mmap, .open = pmem_open, .unlocked_ioctl = pmem_ioctl, + .llseek = noop_llseek, }; static int get_id(struct file *file) @@ -1204,6 +1205,7 @@ static ssize_t debug_read(struct file *file, char __user *buf, size_t count, static struct file_operations debug_fops = { .read = debug_read, .open = debug_open, + .llseek = default_llseek, }; #endif diff --git a/drivers/staging/dream/qdsp5/adsp_driver.c b/drivers/staging/dream/qdsp5/adsp_driver.c index 8197765aae1e..28a6f8da9477 100644 --- a/drivers/staging/dream/qdsp5/adsp_driver.c +++ b/drivers/staging/dream/qdsp5/adsp_driver.c @@ -582,6 +582,7 @@ static struct file_operations adsp_fops = { .open = adsp_open, .unlocked_ioctl = adsp_ioctl, .release = adsp_release, + .llseek = no_llseek, }; static void adsp_create(struct adsp_device *adev, const char *name, diff --git a/drivers/staging/dream/qdsp5/audio_aac.c b/drivers/staging/dream/qdsp5/audio_aac.c index a373f3522384..45f4c78ab6e7 100644 --- a/drivers/staging/dream/qdsp5/audio_aac.c +++ b/drivers/staging/dream/qdsp5/audio_aac.c @@ -1030,6 +1030,7 @@ static struct file_operations audio_aac_fops = { .read = audio_read, .write = audio_write, .unlocked_ioctl = audio_ioctl, + .llseek = noop_llseek, }; struct miscdevice audio_aac_misc = { diff --git a/drivers/staging/dream/qdsp5/audio_amrnb.c b/drivers/staging/dream/qdsp5/audio_amrnb.c index 07b79d5836e5..402bbc13281a 100644 --- a/drivers/staging/dream/qdsp5/audio_amrnb.c +++ b/drivers/staging/dream/qdsp5/audio_amrnb.c @@ -841,6 +841,7 @@ static struct file_operations audio_amrnb_fops = { .read = audamrnb_read, .write = audamrnb_write, .unlocked_ioctl = audamrnb_ioctl, + .llseek = noop_llseek, }; struct miscdevice audio_amrnb_misc = { diff --git a/drivers/staging/dream/qdsp5/audio_evrc.c b/drivers/staging/dream/qdsp5/audio_evrc.c index ad989ee87690..24a892647370 100644 --- a/drivers/staging/dream/qdsp5/audio_evrc.c +++ b/drivers/staging/dream/qdsp5/audio_evrc.c @@ -813,6 +813,7 @@ static struct file_operations audio_evrc_fops = { .read = audevrc_read, .write = audevrc_write, .unlocked_ioctl = audevrc_ioctl, + .llseek = noop_llseek, }; struct miscdevice audio_evrc_misc = { diff --git a/drivers/staging/dream/qdsp5/audio_in.c b/drivers/staging/dream/qdsp5/audio_in.c index 6ae48e72d145..b51fa096074e 100644 --- a/drivers/staging/dream/qdsp5/audio_in.c +++ b/drivers/staging/dream/qdsp5/audio_in.c @@ -921,12 +921,14 @@ static struct file_operations audio_fops = { .read = audio_in_read, .write = audio_in_write, .unlocked_ioctl = audio_in_ioctl, + .llseek = noop_llseek, }; static struct file_operations audpre_fops = { .owner = THIS_MODULE, .open = audpre_open, .unlocked_ioctl = audpre_ioctl, + .llseek = noop_llseek, }; struct miscdevice audio_in_misc = { diff --git a/drivers/staging/dream/qdsp5/audio_mp3.c b/drivers/staging/dream/qdsp5/audio_mp3.c index 530e1f35eed3..409a19ce6039 100644 --- a/drivers/staging/dream/qdsp5/audio_mp3.c +++ b/drivers/staging/dream/qdsp5/audio_mp3.c @@ -948,6 +948,7 @@ static struct file_operations audio_mp3_fops = { .read = audio_read, .write = audio_write, .unlocked_ioctl = audio_ioctl, + .llseek = noop_llseek, }; struct miscdevice audio_mp3_misc = { diff --git a/drivers/staging/dream/qdsp5/audio_out.c b/drivers/staging/dream/qdsp5/audio_out.c index 76d7fa5667d5..d20e89541567 100644 --- a/drivers/staging/dream/qdsp5/audio_out.c +++ b/drivers/staging/dream/qdsp5/audio_out.c @@ -807,12 +807,14 @@ static struct file_operations audio_fops = { .read = audio_read, .write = audio_write, .unlocked_ioctl = audio_ioctl, + .llseek = noop_llseek, }; static struct file_operations audpp_fops = { .owner = THIS_MODULE, .open = audpp_open, .unlocked_ioctl = audpp_ioctl, + .llseek = noop_llseek, }; struct miscdevice audio_misc = { diff --git a/drivers/staging/dream/qdsp5/audio_qcelp.c b/drivers/staging/dream/qdsp5/audio_qcelp.c index effa96f34fdc..911bab416b85 100644 --- a/drivers/staging/dream/qdsp5/audio_qcelp.c +++ b/drivers/staging/dream/qdsp5/audio_qcelp.c @@ -824,6 +824,7 @@ static struct file_operations audio_qcelp_fops = { .read = audqcelp_read, .write = audqcelp_write, .unlocked_ioctl = audqcelp_ioctl, + .llseek = noop_llseek, }; struct miscdevice audio_qcelp_misc = { diff --git a/drivers/staging/dream/qdsp5/evlog.h b/drivers/staging/dream/qdsp5/evlog.h index 922ce670a32a..e5ab86b9dd7c 100644 --- a/drivers/staging/dream/qdsp5/evlog.h +++ b/drivers/staging/dream/qdsp5/evlog.h @@ -123,6 +123,7 @@ static int ev_log_open(struct inode *inode, struct file *file) static const struct file_operations ev_log_ops = { .read = ev_log_read, .open = ev_log_open, + .llseek = default_llseek, }; static int ev_log_init(struct ev_log *log) diff --git a/drivers/staging/dream/qdsp5/snd.c b/drivers/staging/dream/qdsp5/snd.c index 037d7ffb7e67..e0f2f7bca29e 100644 --- a/drivers/staging/dream/qdsp5/snd.c +++ b/drivers/staging/dream/qdsp5/snd.c @@ -247,6 +247,7 @@ static struct file_operations snd_fops = { .open = snd_open, .release = snd_release, .unlocked_ioctl = snd_ioctl, + .llseek = noop_llseek, }; struct miscdevice snd_misc = { diff --git a/drivers/staging/frontier/alphatrack.c b/drivers/staging/frontier/alphatrack.c index 4e52105e6070..689099b57fd2 100644 --- a/drivers/staging/frontier/alphatrack.c +++ b/drivers/staging/frontier/alphatrack.c @@ -641,6 +641,7 @@ static const struct file_operations usb_alphatrack_fops = { .open = usb_alphatrack_open, .release = usb_alphatrack_release, .poll = usb_alphatrack_poll, + .llseek = no_llseek, }; /* diff --git a/drivers/staging/frontier/tranzport.c b/drivers/staging/frontier/tranzport.c index eed74f0fe0b6..3d12c1737edc 100644 --- a/drivers/staging/frontier/tranzport.c +++ b/drivers/staging/frontier/tranzport.c @@ -767,6 +767,7 @@ static const struct file_operations usb_tranzport_fops = { .open = usb_tranzport_open, .release = usb_tranzport_release, .poll = usb_tranzport_poll, + .llseek = no_llseek, }; /* diff --git a/drivers/staging/iio/industrialio-core.c b/drivers/staging/iio/industrialio-core.c index dd4d87a8bcaf..92a212f064bd 100644 --- a/drivers/staging/iio/industrialio-core.c +++ b/drivers/staging/iio/industrialio-core.c @@ -349,6 +349,7 @@ static const struct file_operations iio_event_chrdev_fileops = { .release = iio_event_chrdev_release, .open = iio_event_chrdev_open, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static void iio_event_dev_release(struct device *dev) diff --git a/drivers/staging/iio/industrialio-ring.c b/drivers/staging/iio/industrialio-ring.c index 6ab578e4f5f3..1c5f67253b82 100644 --- a/drivers/staging/iio/industrialio-ring.c +++ b/drivers/staging/iio/industrialio-ring.c @@ -133,6 +133,7 @@ static const struct file_operations iio_ring_fileops = { .release = iio_ring_release, .open = iio_ring_open, .owner = THIS_MODULE, + .llseek = noop_llseek, }; /** diff --git a/drivers/staging/lirc/lirc_imon.c b/drivers/staging/lirc/lirc_imon.c index 66493253042e..ed5c5fe022c9 100644 --- a/drivers/staging/lirc/lirc_imon.c +++ b/drivers/staging/lirc/lirc_imon.c @@ -115,7 +115,8 @@ static const struct file_operations display_fops = { .owner = THIS_MODULE, .open = &display_open, .write = &vfd_write, - .release = &display_close + .release = &display_close, + .llseek = noop_llseek, }; /* diff --git a/drivers/staging/lirc/lirc_it87.c b/drivers/staging/lirc/lirc_it87.c index ec11c0e949a0..543c5c3bf907 100644 --- a/drivers/staging/lirc/lirc_it87.c +++ b/drivers/staging/lirc/lirc_it87.c @@ -342,6 +342,7 @@ static const struct file_operations lirc_fops = { .unlocked_ioctl = lirc_ioctl, .open = lirc_open, .release = lirc_close, + .llseek = noop_llseek, }; static int set_use_inc(void *data) diff --git a/drivers/staging/lirc/lirc_sasem.c b/drivers/staging/lirc/lirc_sasem.c index 73166c3f581f..8f72a84f34ec 100644 --- a/drivers/staging/lirc/lirc_sasem.c +++ b/drivers/staging/lirc/lirc_sasem.c @@ -125,6 +125,7 @@ static const struct file_operations vfd_fops = { .write = &vfd_write, .unlocked_ioctl = &vfd_ioctl, .release = &vfd_close, + .llseek = noop_llseek, }; /* USB Device ID for Sasem USB Control Board */ diff --git a/drivers/staging/memrar/memrar_handler.c b/drivers/staging/memrar/memrar_handler.c index a98b3f1f11e0..cfcaa8e5b8e6 100644 --- a/drivers/staging/memrar/memrar_handler.c +++ b/drivers/staging/memrar/memrar_handler.c @@ -890,6 +890,7 @@ static const struct file_operations memrar_fops = { .mmap = memrar_mmap, .open = memrar_open, .release = memrar_release, + .llseek = no_llseek, }; static struct miscdevice memrar_miscdev = { diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c index 3221814a856e..6885f9a46609 100644 --- a/drivers/staging/panel/panel.c +++ b/drivers/staging/panel/panel.c @@ -1631,6 +1631,7 @@ static const struct file_operations keypad_fops = { .read = keypad_read, /* read */ .open = keypad_open, /* open */ .release = keypad_release, /* close */ + .llseek = default_llseek, }; static struct miscdevice keypad_dev = { diff --git a/drivers/staging/tidspbridge/rmgr/drv_interface.c b/drivers/staging/tidspbridge/rmgr/drv_interface.c index 7ee89492a755..7b3a7d04a109 100644 --- a/drivers/staging/tidspbridge/rmgr/drv_interface.c +++ b/drivers/staging/tidspbridge/rmgr/drv_interface.c @@ -144,6 +144,7 @@ static const struct file_operations bridge_fops = { .release = bridge_release, .unlocked_ioctl = bridge_ioctl, .mmap = bridge_mmap, + .llseek = noop_llseek, }; #ifdef CONFIG_PM diff --git a/drivers/telephony/ixj.c b/drivers/telephony/ixj.c index b53deee25d74..5c6239e5aa21 100644 --- a/drivers/telephony/ixj.c +++ b/drivers/telephony/ixj.c @@ -6676,7 +6676,8 @@ static const struct file_operations ixj_fops = .poll = ixj_poll, .unlocked_ioctl = ixj_ioctl, .release = ixj_release, - .fasync = ixj_fasync + .fasync = ixj_fasync, + .llseek = default_llseek, }; static int ixj_linetest(IXJ *j) diff --git a/drivers/telephony/phonedev.c b/drivers/telephony/phonedev.c index f3873f650bb4..1915af201175 100644 --- a/drivers/telephony/phonedev.c +++ b/drivers/telephony/phonedev.c @@ -130,6 +130,7 @@ static const struct file_operations phone_fops = { .owner = THIS_MODULE, .open = phone_open, + .llseek = noop_llseek, }; /* diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index bff1afbde5a4..4d3a6fd1a152 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -740,6 +740,7 @@ static const struct file_operations uio_fops = { .mmap = uio_mmap, .poll = uio_poll, .fasync = uio_fasync, + .llseek = noop_llseek, }; static int uio_major_init(void) diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 094c76b5de17..6ee4451bfe2d 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -584,7 +584,8 @@ static const struct file_operations wdm_fops = { .open = wdm_open, .flush = wdm_flush, .release = wdm_release, - .poll = wdm_poll + .poll = wdm_poll, + .llseek = noop_llseek, }; static struct usb_class_driver wdm_class = { diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index e325162859b0..9eca4053312e 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -1043,6 +1043,7 @@ static const struct file_operations usblp_fops = { .compat_ioctl = usblp_ioctl, .open = usblp_open, .release = usblp_release, + .llseek = noop_llseek, }; static char *usblp_devnode(struct device *dev, mode_t *mode) diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 3e7c1b800ebb..6a54634ab823 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -987,6 +987,7 @@ static const struct file_operations fops = { .open = usbtmc_open, .release = usbtmc_release, .unlocked_ioctl = usbtmc_ioctl, + .llseek = default_llseek, }; static struct usb_class_driver usbtmc_class = { diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c index f06f5dbc8cdc..580bcd396839 100644 --- a/drivers/usb/core/file.c +++ b/drivers/usb/core/file.c @@ -59,6 +59,7 @@ static int usb_open(struct inode * inode, struct file * file) static const struct file_operations usb_fops = { .owner = THIS_MODULE, .open = usb_open, + .llseek = noop_llseek, }; static struct usb_class { diff --git a/drivers/usb/gadget/f_hid.c b/drivers/usb/gadget/f_hid.c index 53e120208e99..2b98bd26364b 100644 --- a/drivers/usb/gadget/f_hid.c +++ b/drivers/usb/gadget/f_hid.c @@ -451,6 +451,7 @@ const struct file_operations f_hidg_fops = { .write = f_hidg_write, .read = f_hidg_read, .poll = f_hidg_poll, + .llseek = noop_llseek, }; static int __init hidg_bind(struct usb_configuration *c, struct usb_function *f) diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c index cf241c371a71..327a92a137b4 100644 --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -884,7 +884,8 @@ static const struct file_operations printer_io_operations = { .fsync = printer_fsync, .poll = printer_poll, .unlocked_ioctl = printer_ioctl, - .release = printer_close + .release = printer_close, + .llseek = noop_llseek, }; /*-------------------------------------------------------------------------*/ diff --git a/drivers/usb/host/ehci-dbg.c b/drivers/usb/host/ehci-dbg.c index 76b7fd2d838a..86afdc73322f 100644 --- a/drivers/usb/host/ehci-dbg.c +++ b/drivers/usb/host/ehci-dbg.c @@ -369,18 +369,21 @@ static const struct file_operations debug_async_fops = { .open = debug_async_open, .read = debug_output, .release = debug_close, + .llseek = default_llseek, }; static const struct file_operations debug_periodic_fops = { .owner = THIS_MODULE, .open = debug_periodic_open, .read = debug_output, .release = debug_close, + .llseek = default_llseek, }; static const struct file_operations debug_registers_fops = { .owner = THIS_MODULE, .open = debug_registers_open, .read = debug_output, .release = debug_close, + .llseek = default_llseek, }; static const struct file_operations debug_lpm_fops = { .owner = THIS_MODULE, @@ -388,6 +391,7 @@ static const struct file_operations debug_lpm_fops = { .read = debug_lpm_read, .write = debug_lpm_write, .release = debug_lpm_close, + .llseek = noop_llseek, }; static struct dentry *ehci_debug_root; diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c index 36abd2baa3ea..d7d34492934a 100644 --- a/drivers/usb/host/ohci-dbg.c +++ b/drivers/usb/host/ohci-dbg.c @@ -413,18 +413,21 @@ static const struct file_operations debug_async_fops = { .open = debug_async_open, .read = debug_output, .release = debug_close, + .llseek = default_llseek, }; static const struct file_operations debug_periodic_fops = { .owner = THIS_MODULE, .open = debug_periodic_open, .read = debug_output, .release = debug_close, + .llseek = default_llseek, }; static const struct file_operations debug_registers_fops = { .owner = THIS_MODULE, .open = debug_registers_open, .read = debug_output, .release = debug_close, + .llseek = default_llseek, }; static struct dentry *ohci_debug_root; diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c index e192e8f7c560..575b56c79e97 100644 --- a/drivers/usb/image/mdc800.c +++ b/drivers/usb/image/mdc800.c @@ -963,6 +963,7 @@ static const struct file_operations mdc800_device_ops = .write = mdc800_device_write, .open = mdc800_device_open, .release = mdc800_device_release, + .llseek = noop_llseek, }; diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c index 801324af9470..44f8b9225054 100644 --- a/drivers/usb/misc/adutux.c +++ b/drivers/usb/misc/adutux.c @@ -679,6 +679,7 @@ static const struct file_operations adu_fops = { .write = adu_write, .open = adu_open, .release = adu_release, + .llseek = noop_llseek, }; /* diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c index a54c3cb804ce..c6184b4d1695 100644 --- a/drivers/usb/misc/idmouse.c +++ b/drivers/usb/misc/idmouse.c @@ -105,6 +105,7 @@ static const struct file_operations idmouse_fops = { .read = idmouse_read, .open = idmouse_open, .release = idmouse_release, + .llseek = default_llseek, }; /* class driver information */ diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index bc88c79875a1..9b50db257019 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -730,6 +730,7 @@ static const struct file_operations iowarrior_fops = { .open = iowarrior_open, .release = iowarrior_release, .poll = iowarrior_poll, + .llseek = noop_llseek, }; static char *iowarrior_devnode(struct device *dev, mode_t *mode) diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index dd41d8710043..edffef642337 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -613,6 +613,7 @@ static const struct file_operations ld_usb_fops = { .open = ld_usb_open, .release = ld_usb_release, .poll = ld_usb_poll, + .llseek = no_llseek, }; /* diff --git a/drivers/usb/misc/rio500.c b/drivers/usb/misc/rio500.c index cc13ae61712a..4e23d3841b43 100644 --- a/drivers/usb/misc/rio500.c +++ b/drivers/usb/misc/rio500.c @@ -439,6 +439,7 @@ static const struct file_operations usb_rio_fops = { .unlocked_ioctl = ioctl_rio, .open = open_rio, .release = close_rio, + .llseek = noop_llseek, }; static struct usb_class_driver usb_rio_class = { diff --git a/drivers/usb/misc/usblcd.c b/drivers/usb/misc/usblcd.c index d00dde19194c..51648154bb44 100644 --- a/drivers/usb/misc/usblcd.c +++ b/drivers/usb/misc/usblcd.c @@ -282,6 +282,7 @@ static const struct file_operations lcd_fops = { .open = lcd_open, .unlocked_ioctl = lcd_ioctl, .release = lcd_release, + .llseek = noop_llseek, }; /* diff --git a/drivers/usb/usb-skeleton.c b/drivers/usb/usb-skeleton.c index 552679b8dbd1..e24ce3123071 100644 --- a/drivers/usb/usb-skeleton.c +++ b/drivers/usb/usb-skeleton.c @@ -507,6 +507,7 @@ static const struct file_operations skel_fops = { .open = skel_open, .release = skel_release, .flush = skel_flush, + .llseek = noop_llseek, }; /* diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 29e850a7a2f9..c8523ce2e4c6 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -869,6 +869,7 @@ static const struct file_operations vhost_net_fops = { .compat_ioctl = vhost_net_compat_ioctl, #endif .open = vhost_net_open, + .llseek = noop_llseek, }; static struct miscdevice vhost_net_misc = { diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c index b06647517c0e..42e303ff862a 100644 --- a/drivers/video/fbmem.c +++ b/drivers/video/fbmem.c @@ -1439,6 +1439,7 @@ static const struct file_operations fb_fops = { #ifdef CONFIG_FB_DEFERRED_IO .fsync = fb_deferred_io_fsync, #endif + .llseek = default_llseek, }; struct class *fb_class; diff --git a/drivers/video/mbx/mbxdebugfs.c b/drivers/video/mbx/mbxdebugfs.c index ecad96524570..12dec7634c55 100644 --- a/drivers/video/mbx/mbxdebugfs.c +++ b/drivers/video/mbx/mbxdebugfs.c @@ -175,36 +175,42 @@ static const struct file_operations sysconf_fops = { .read = sysconf_read_file, .write = write_file_dummy, .open = open_file_generic, + .llseek = default_llseek, }; static const struct file_operations clock_fops = { .read = clock_read_file, .write = write_file_dummy, .open = open_file_generic, + .llseek = default_llseek, }; static const struct file_operations display_fops = { .read = display_read_file, .write = write_file_dummy, .open = open_file_generic, + .llseek = default_llseek, }; static const struct file_operations gsctl_fops = { .read = gsctl_read_file, .write = write_file_dummy, .open = open_file_generic, + .llseek = default_llseek, }; static const struct file_operations sdram_fops = { .read = sdram_read_file, .write = write_file_dummy, .open = open_file_generic, + .llseek = default_llseek, }; static const struct file_operations misc_fops = { .read = misc_read_file, .write = write_file_dummy, .open = open_file_generic, + .llseek = default_llseek, }; static void __devinit mbxfb_debugfs_init(struct fb_info *fbi) diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c index c764c52412e4..b29221783598 100644 --- a/drivers/watchdog/ar7_wdt.c +++ b/drivers/watchdog/ar7_wdt.c @@ -267,6 +267,7 @@ static const struct file_operations ar7_wdt_fops = { .unlocked_ioctl = ar7_wdt_ioctl, .open = ar7_wdt_open, .release = ar7_wdt_release, + .llseek = no_llseek, }; static struct miscdevice ar7_wdt_miscdev = { diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index 566343b3c131..51ae4e84f4f9 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -524,6 +524,7 @@ static const struct file_operations cpwd_fops = { .write = cpwd_write, .read = cpwd_read, .release = cpwd_release, + .llseek = no_llseek, }; static int __devinit cpwd_probe(struct platform_device *op, diff --git a/drivers/watchdog/ep93xx_wdt.c b/drivers/watchdog/ep93xx_wdt.c index 59359c9a5e01..726b7df61fd0 100644 --- a/drivers/watchdog/ep93xx_wdt.c +++ b/drivers/watchdog/ep93xx_wdt.c @@ -188,6 +188,7 @@ static const struct file_operations ep93xx_wdt_fops = { .unlocked_ioctl = ep93xx_wdt_ioctl, .open = ep93xx_wdt_open, .release = ep93xx_wdt_release, + .llseek = no_llseek, }; static struct miscdevice ep93xx_wdt_miscdev = { diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c index 76b58abf4451..81e3d6100894 100644 --- a/drivers/watchdog/omap_wdt.c +++ b/drivers/watchdog/omap_wdt.c @@ -258,6 +258,7 @@ static const struct file_operations omap_wdt_fops = { .unlocked_ioctl = omap_wdt_ioctl, .open = omap_wdt_open, .release = omap_wdt_release, + .llseek = no_llseek, }; static int __devinit omap_wdt_probe(struct platform_device *pdev) diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 66e185cfe92f..fec6ba3c08a8 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -467,6 +467,7 @@ static const struct file_operations evtchn_fops = { .fasync = evtchn_fasync, .open = evtchn_open, .release = evtchn_release, + .llseek = noop_llseek, }; static struct miscdevice evtchn_miscdev = { diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c index 78bfab0700ba..bd96340063c1 100644 --- a/drivers/xen/xenfs/super.c +++ b/drivers/xen/xenfs/super.c @@ -35,6 +35,7 @@ static ssize_t capabilities_read(struct file *file, char __user *buf, static const struct file_operations capabilities_file_ops = { .read = capabilities_read, + .llseek = default_llseek, }; static int xenfs_fill_super(struct super_block *sb, void *data, int silent) diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c index 3b39c3752e21..1c1236087f78 100644 --- a/drivers/xen/xenfs/xenbus.c +++ b/drivers/xen/xenfs/xenbus.c @@ -594,4 +594,5 @@ const struct file_operations xenbus_file_ops = { .open = xenbus_file_open, .release = xenbus_file_release, .poll = xenbus_file_poll, + .llseek = no_llseek, }; diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 6d552686c498..6153417caf57 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -29,6 +29,7 @@ static void afs_mntpt_expiry_timed_out(struct work_struct *work); const struct file_operations afs_mntpt_file_operations = { .open = afs_mntpt_open, + .llseek = noop_llseek, }; const struct inode_operations afs_mntpt_inode_operations = { diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index ba4a38b9c22f..eff9a419469a 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -724,6 +724,7 @@ static const struct file_operations _dev_ioctl_fops = { .unlocked_ioctl = autofs_dev_ioctl, .compat_ioctl = autofs_dev_ioctl_compat, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice _autofs_dev_ioctl_misc = { diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index fd0cc0bf9a40..139fc8083f53 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -576,6 +576,7 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, static const struct file_operations bm_entry_operations = { .read = bm_entry_read, .write = bm_entry_write, + .llseek = default_llseek, }; /* /register */ @@ -643,6 +644,7 @@ out: static const struct file_operations bm_register_operations = { .write = bm_register_write, + .llseek = noop_llseek, }; /* /status */ @@ -680,6 +682,7 @@ static ssize_t bm_status_write(struct file * file, const char __user * buffer, static const struct file_operations bm_status_operations = { .read = bm_status_read, .write = bm_status_write, + .llseek = default_llseek, }; /* Superblock handling */ diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 1776dbd8dc98..144f8a5730f5 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -815,6 +815,7 @@ static const struct file_operations btrfs_ctl_fops = { .unlocked_ioctl = btrfs_control_ioctl, .compat_ioctl = btrfs_control_ioctl, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice btrfs_misc = { diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 727caedcdd92..0a1467b15516 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -55,6 +55,7 @@ const struct file_operations cachefiles_daemon_fops = { .read = cachefiles_daemon_read, .write = cachefiles_daemon_write, .poll = cachefiles_daemon_poll, + .llseek = noop_llseek, }; struct cachefiles_daemon_cmd { diff --git a/fs/char_dev.c b/fs/char_dev.c index f80a4f25123c..e4a3318b812a 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -454,6 +454,7 @@ static void cdev_purge(struct cdev *cdev) */ const struct file_operations def_chr_fops = { .open = chrdev_open, + .llseek = noop_llseek, }; static struct kobject *exact_match(dev_t dev, int *part, void *data) diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index ca25d96d45c9..028a9a0f588b 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -39,6 +39,7 @@ const struct inode_operations coda_ioctl_inode_operations = { const struct file_operations coda_ioctl_operations = { .owner = THIS_MODULE, .unlocked_ioctl = coda_pioctl, + .llseek = noop_llseek, }; /* the coda pioctl inode ops */ diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index de89645777c7..9fa280bfcffe 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -346,6 +346,7 @@ static const struct file_operations coda_psdev_fops = { .unlocked_ioctl = coda_psdev_ioctl, .open = coda_psdev_open, .release = coda_psdev_release, + .llseek = noop_llseek, }; static int init_coda_psdev(void) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 0210898458b2..89d394d8fe24 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -43,6 +43,7 @@ const struct file_operations debugfs_file_operations = { .read = default_read_file, .write = default_write_file, .open = default_open, + .llseek = noop_llseek, }; static void *debugfs_follow_link(struct dentry *dentry, struct nameidata *nd) @@ -454,6 +455,7 @@ static const struct file_operations fops_bool = { .read = read_file_bool, .write = write_file_bool, .open = default_open, + .llseek = default_llseek, }; /** @@ -498,6 +500,7 @@ static ssize_t read_file_blob(struct file *file, char __user *user_buf, static const struct file_operations fops_blob = { .read = read_file_blob, .open = default_open, + .llseek = default_llseek, }; /** diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index c6cf25158746..6b42ba807dfd 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -643,7 +643,8 @@ static ssize_t waiters_read(struct file *file, char __user *userbuf, static const struct file_operations waiters_fops = { .owner = THIS_MODULE, .open = waiters_open, - .read = waiters_read + .read = waiters_read, + .llseek = default_llseek, }; void dlm_delete_debug_file(struct dlm_ls *ls) diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index d45c02db6943..30d8b85febbf 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -412,7 +412,8 @@ static const struct file_operations dev_fops = { .read = dev_read, .write = dev_write, .poll = dev_poll, - .owner = THIS_MODULE + .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice plock_dev_misc = { diff --git a/fs/dlm/user.c b/fs/dlm/user.c index b6272853130c..66d6c16bf440 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -1009,6 +1009,7 @@ static const struct file_operations device_fops = { .write = device_write, .poll = device_poll, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static const struct file_operations ctl_device_fops = { @@ -1017,6 +1018,7 @@ static const struct file_operations ctl_device_fops = { .read = device_read, .write = device_write, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice ctl_device = { @@ -1029,6 +1031,7 @@ static const struct file_operations monitor_device_fops = { .open = monitor_device_open, .release = monitor_device_close, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice monitor_device = { diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 622c95140802..86e9da1c787e 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -332,6 +332,7 @@ const struct file_operations ecryptfs_dir_fops = { .fsync = ecryptfs_fsync, .fasync = ecryptfs_fasync, .splice_read = generic_file_splice_read, + .llseek = default_llseek, }; const struct file_operations ecryptfs_main_fops = { diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 00208c3d7e92..940a82e63dc3 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -482,6 +482,7 @@ static const struct file_operations ecryptfs_miscdev_fops = { .read = ecryptfs_miscdev_read, .write = ecryptfs_miscdev_write, .release = ecryptfs_miscdev_release, + .llseek = noop_llseek, }; static struct miscdevice ecryptfs_miscdev = { diff --git a/fs/eventfd.c b/fs/eventfd.c index 6bd3f76fdf88..e0194b3e14d6 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -293,6 +293,7 @@ static const struct file_operations eventfd_fops = { .poll = eventfd_poll, .read = eventfd_read, .write = eventfd_write, + .llseek = noop_llseek, }; /** diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3817149919cb..256bb7bb102a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -674,7 +674,8 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait) /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { .release = ep_eventpoll_release, - .poll = ep_eventpoll_poll + .poll = ep_eventpoll_poll, + .llseek = noop_llseek, }; /* Fast test to see if the file is an evenpoll file */ diff --git a/fs/fifo.c b/fs/fifo.c index 5d6606ffc2d2..4e303c22d5ee 100644 --- a/fs/fifo.c +++ b/fs/fifo.c @@ -151,4 +151,5 @@ err_nocleanup: */ const struct file_operations def_fifo_fops = { .open = fifo_open, /* will set read_ or write_pipefifo_fops */ + .llseek = noop_llseek, }; diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 3773fd63d2f9..7367e177186f 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -179,23 +179,27 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file, static const struct file_operations fuse_ctl_abort_ops = { .open = nonseekable_open, .write = fuse_conn_abort_write, + .llseek = no_llseek, }; static const struct file_operations fuse_ctl_waiting_ops = { .open = nonseekable_open, .read = fuse_conn_waiting_read, + .llseek = no_llseek, }; static const struct file_operations fuse_conn_max_background_ops = { .open = nonseekable_open, .read = fuse_conn_max_background_read, .write = fuse_conn_max_background_write, + .llseek = no_llseek, }; static const struct file_operations fuse_conn_congestion_threshold_ops = { .open = nonseekable_open, .read = fuse_conn_congestion_threshold_read, .write = fuse_conn_congestion_threshold_write, + .llseek = no_llseek, }; static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index e1f8171278bd..3e87cce5837d 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -182,6 +182,7 @@ static const struct file_operations cuse_frontend_fops = { .unlocked_ioctl = cuse_file_ioctl, .compat_ioctl = cuse_file_compat_ioctl, .poll = fuse_file_poll, + .llseek = noop_llseek, }; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 4edd662c8232..55d25a68b496 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -771,6 +771,7 @@ const struct file_operations gfs2_dir_fops = { .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, + .llseek = default_llseek, }; #endif /* CONFIG_GFS2_FS_LOCKING_DLM */ @@ -797,5 +798,6 @@ const struct file_operations gfs2_dir_fops_nolock = { .open = gfs2_open, .release = gfs2_close, .fsync = gfs2_fsync, + .llseek = default_llseek, }; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 7b027720d820..4e2a45ea6140 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -598,6 +598,7 @@ static const struct file_operations hppfs_dir_fops = { .readdir = hppfs_readdir, .open = hppfs_dir_open, .fsync = hppfs_fsync, + .llseek = default_llseek, }; static int hppfs_statfs(struct dentry *dentry, struct kstatfs *sf) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 6e5bd42f3860..113eba3d3c38 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -674,6 +674,7 @@ const struct file_operations hugetlbfs_file_operations = { .mmap = hugetlbfs_file_mmap, .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, + .llseek = default_llseek, }; static const struct inode_operations hugetlbfs_dir_inode_operations = { diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index 9777eb5b5522..1eb4e89e045b 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -827,4 +827,5 @@ const struct file_operations logfs_dir_fops = { .unlocked_ioctl = logfs_ioctl, .readdir = logfs_readdir, .read = generic_read_dir, + .llseek = default_llseek, }; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b53b1d042f1f..06fa87e52e82 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -137,6 +137,7 @@ static const struct file_operations transaction_ops = { .write = nfsctl_transaction_write, .read = nfsctl_transaction_read, .release = simple_transaction_release, + .llseek = default_llseek, }; static int exports_open(struct inode *inode, struct file *file) diff --git a/fs/no-block.c b/fs/no-block.c index d269a93d3467..6e40e42a43de 100644 --- a/fs/no-block.c +++ b/fs/no-block.c @@ -19,4 +19,5 @@ static int no_blkdev_open(struct inode * inode, struct file * filp) const struct file_operations def_blk_fops = { .open = no_blkdev_open, + .llseek = noop_llseek, }; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 5ed8e58d7bfc..bbcb98e7fcc6 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -433,6 +433,7 @@ static const struct file_operations fanotify_fops = { .release = fanotify_release, .unlocked_ioctl = fanotify_ioctl, .compat_ioctl = fanotify_ioctl, + .llseek = noop_llseek, }; static void fanotify_free_mark(struct fsnotify_mark *fsn_mark) diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index bf7f6d776c31..24edc1185d53 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -344,6 +344,7 @@ static const struct file_operations inotify_fops = { .release = inotify_release, .unlocked_ioctl = inotify_ioctl, .compat_ioctl = inotify_ioctl, + .llseek = noop_llseek, }; diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index c2903b84bb7a..a7ebd9d42dc8 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -612,6 +612,7 @@ static const struct file_operations dlmfs_file_operations = { .poll = dlmfs_file_poll, .read = dlmfs_file_read, .write = dlmfs_file_write, + .llseek = default_llseek, }; static const struct inode_operations dlmfs_dir_inode_operations = { diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 2dc57bca0688..0dbc6dae1de8 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -628,6 +628,7 @@ static const struct file_operations ocfs2_control_fops = { .read = ocfs2_control_read, .write = ocfs2_control_write, .owner = THIS_MODULE, + .llseek = default_llseek, }; static struct miscdevice ocfs2_control_device = { diff --git a/fs/proc/base.c b/fs/proc/base.c index a1c43e7c8a7b..bc307d7a5b76 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1151,6 +1151,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, static const struct file_operations proc_oom_score_adj_operations = { .read = oom_score_adj_read, .write = oom_score_adj_write, + .llseek = default_llseek, }; #ifdef CONFIG_AUDITSYSCALL @@ -2039,11 +2040,13 @@ static ssize_t proc_fdinfo_read(struct file *file, char __user *buf, static const struct file_operations proc_fdinfo_file_operations = { .open = nonseekable_open, .read = proc_fdinfo_read, + .llseek = no_llseek, }; static const struct file_operations proc_fd_operations = { .read = generic_read_dir, .readdir = proc_readfd, + .llseek = default_llseek, }; /* @@ -2112,6 +2115,7 @@ static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir) static const struct file_operations proc_fdinfo_operations = { .read = generic_read_dir, .readdir = proc_readfdinfo, + .llseek = default_llseek, }; /* @@ -2343,6 +2347,7 @@ static int proc_attr_dir_readdir(struct file * filp, static const struct file_operations proc_attr_dir_operations = { .read = generic_read_dir, .readdir = proc_attr_dir_readdir, + .llseek = default_llseek, }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, @@ -2751,6 +2756,7 @@ static int proc_tgid_base_readdir(struct file * filp, static const struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, .readdir = proc_tgid_base_readdir, + .llseek = default_llseek, }; static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ @@ -3088,6 +3094,7 @@ static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *den static const struct file_operations proc_tid_base_operations = { .read = generic_read_dir, .readdir = proc_tid_base_readdir, + .llseek = default_llseek, }; static const struct inode_operations proc_tid_base_inode_operations = { @@ -3324,4 +3331,5 @@ static const struct inode_operations proc_task_inode_operations = { static const struct file_operations proc_task_operations = { .read = generic_read_dir, .readdir = proc_task_readdir, + .llseek = default_llseek, }; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 5be436ea088e..2fc52552271d 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -364,6 +364,7 @@ static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct static const struct file_operations proc_sys_file_operations = { .read = proc_sys_read, .write = proc_sys_write, + .llseek = default_llseek, }; static const struct file_operations proc_sys_dir_file_operations = { diff --git a/fs/proc/root.c b/fs/proc/root.c index 4258384ed22d..93d99b316325 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -179,6 +179,7 @@ static int proc_root_readdir(struct file * filp, static const struct file_operations proc_root_operations = { .read = generic_read_dir, .readdir = proc_root_readdir, + .llseek = default_llseek, }; /* diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 271afc48b9a5..aa56920df335 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -539,6 +539,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, const struct file_operations proc_clear_refs_operations = { .write = clear_refs_write, + .llseek = noop_llseek, }; struct pagemapread { diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 42d213546894..268580535c92 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -282,6 +282,7 @@ error: static const struct file_operations romfs_dir_operations = { .read = generic_read_dir, .readdir = romfs_readdir, + .llseek = default_llseek, }; static const struct inode_operations romfs_dir_inode_operations = { diff --git a/fs/signalfd.c b/fs/signalfd.c index 1c5a6add779d..74047304b01a 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -206,6 +206,7 @@ static const struct file_operations signalfd_fops = { .release = signalfd_release, .poll = signalfd_poll, .read = signalfd_read, + .llseek = noop_llseek, }; SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c index 12b933ac6585..0dc340aa2be9 100644 --- a/fs/squashfs/dir.c +++ b/fs/squashfs/dir.c @@ -230,5 +230,6 @@ failed_read: const struct file_operations squashfs_dir_ops = { .read = generic_read_dir, - .readdir = squashfs_readdir + .readdir = squashfs_readdir, + .llseek = default_llseek, }; diff --git a/fs/timerfd.c b/fs/timerfd.c index b86ab8eff79a..8c4fc1425b3e 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -144,6 +144,7 @@ static const struct file_operations timerfd_fops = { .release = timerfd_release, .poll = timerfd_poll, .read = timerfd_read, + .llseek = noop_llseek, }; static struct file *timerfd_fget(int fd) diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index c2a68baa782f..c6c553fd0b3d 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2625,6 +2625,7 @@ static const struct file_operations dfs_fops = { .open = open_debugfs_file, .write = write_debugfs_file, .owner = THIS_MODULE, + .llseek = default_llseek, }; /** diff --git a/ipc/mqueue.c b/ipc/mqueue.c index c60e519e2917..e1e7b9635f5d 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1219,6 +1219,7 @@ static const struct file_operations mqueue_file_operations = { .flush = mqueue_flush_file, .poll = mqueue_poll_file, .read = mqueue_read_file, + .llseek = default_llseek, }; static const struct super_operations mqueue_super_ops = { diff --git a/ipc/shm.c b/ipc/shm.c index 52ed77eb9713..7bc46a9fe1f8 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -298,6 +298,7 @@ static const struct file_operations shm_file_operations = { #ifndef CONFIG_MMU .get_unmapped_area = shm_get_unmapped_area, #endif + .llseek = noop_llseek, }; static const struct file_operations shm_file_operations_huge = { @@ -305,6 +306,7 @@ static const struct file_operations shm_file_operations_huge = { .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, + .llseek = noop_llseek, }; int is_file_shm_hugepages(struct file *file) diff --git a/kernel/configs.c b/kernel/configs.c index abaee684ecbf..b4066b44a99d 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -66,6 +66,7 @@ ikconfig_read_current(struct file *file, char __user *buf, static const struct file_operations ikconfig_file_ops = { .owner = THIS_MODULE, .read = ikconfig_read_current, + .llseek = default_llseek, }; static int __init ikconfig_init(void) diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index f83972b16564..9bd0934f6c33 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -561,6 +561,7 @@ static ssize_t reset_read(struct file *file, char __user *addr, size_t len, static const struct file_operations gcov_reset_fops = { .write = reset_write, .read = reset_read, + .llseek = noop_llseek, }; /* diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 282035f3ae96..8b5ff2655ae0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1992,6 +1992,7 @@ static ssize_t write_enabled_file_bool(struct file *file, static const struct file_operations fops_kp = { .read = read_enabled_file_bool, .write = write_enabled_file_bool, + .llseek = default_llseek, }; static int __kprobes debugfs_kprobe_init(void) diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index 645e541a45f6..a96b850ba08a 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -110,6 +110,7 @@ static const struct file_operations pm_qos_power_fops = { .write = pm_qos_power_write, .open = pm_qos_power_open, .release = pm_qos_power_release, + .llseek = noop_llseek, }; /* unlocked internal variant */ diff --git a/kernel/profile.c b/kernel/profile.c index b22a899934cc..66f841b7fbd3 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -555,6 +555,7 @@ static ssize_t write_profile(struct file *file, const char __user *buf, static const struct file_operations proc_profile_operations = { .read = read_profile, .write = write_profile, + .llseek = default_llseek, }; #ifdef CONFIG_SMP diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 959f8d6c8cc1..2d5f3a757316 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -326,6 +326,7 @@ static const struct file_operations blk_dropped_fops = { .owner = THIS_MODULE, .open = blk_dropped_open, .read = blk_dropped_read, + .llseek = default_llseek, }; static int blk_msg_open(struct inode *inode, struct file *filp) @@ -365,6 +366,7 @@ static const struct file_operations blk_msg_fops = { .owner = THIS_MODULE, .open = blk_msg_open, .write = blk_msg_write, + .llseek = noop_llseek, }; /* diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fa7ece649fe1..5e1ad4763090 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -800,6 +800,7 @@ static const struct file_operations ftrace_profile_fops = { .open = tracing_open_generic, .read = ftrace_profile_read, .write = ftrace_profile_write, + .llseek = default_llseek, }; /* used to initialize the real stat files */ @@ -2632,6 +2633,7 @@ static const struct file_operations ftrace_graph_fops = { .read = seq_read, .write = ftrace_graph_write, .release = ftrace_graph_release, + .llseek = seq_lseek, }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 492197e2f86c..3aea966d16de 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3965,6 +3965,7 @@ static const struct file_operations rb_simple_fops = { .open = tracing_open_generic, .read = rb_simple_read, .write = rb_simple_write, + .llseek = default_llseek, }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4c758f146328..0369c5e09984 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -951,6 +951,7 @@ static const struct file_operations ftrace_enable_fops = { .open = tracing_open_generic, .read = event_enable_read, .write = event_enable_write, + .llseek = default_llseek, }; static const struct file_operations ftrace_event_format_fops = { @@ -963,29 +964,34 @@ static const struct file_operations ftrace_event_format_fops = { static const struct file_operations ftrace_event_id_fops = { .open = tracing_open_generic, .read = event_id_read, + .llseek = default_llseek, }; static const struct file_operations ftrace_event_filter_fops = { .open = tracing_open_generic, .read = event_filter_read, .write = event_filter_write, + .llseek = default_llseek, }; static const struct file_operations ftrace_subsystem_filter_fops = { .open = tracing_open_generic, .read = subsystem_filter_read, .write = subsystem_filter_write, + .llseek = default_llseek, }; static const struct file_operations ftrace_system_enable_fops = { .open = tracing_open_generic, .read = system_enable_read, .write = system_enable_write, + .llseek = default_llseek, }; static const struct file_operations ftrace_show_header_fops = { .open = tracing_open_generic, .read = show_header, + .llseek = default_llseek, }; static struct dentry *event_trace_events_dir(void) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index a6b7e0e0f3eb..4c5dead0c239 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -195,6 +195,7 @@ static const struct file_operations stack_max_size_fops = { .open = tracing_open_generic, .read = stack_max_size_read, .write = stack_max_size_write, + .llseek = default_llseek, }; static void * diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 01e64270e246..4bfb0471f106 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -590,6 +590,7 @@ out_unlock: static const struct file_operations filter_fops = { .read = filter_read, .write = filter_write, + .llseek = default_llseek, }; static int dma_debug_fs_init(void) diff --git a/net/atm/proc.c b/net/atm/proc.c index 6262aeae398e..f85da0779e5e 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -38,6 +38,7 @@ static ssize_t proc_dev_atm_read(struct file *file, char __user *buf, static const struct file_operations proc_atm_dev_ops = { .owner = THIS_MODULE, .read = proc_dev_atm_read, + .llseek = noop_llseek, }; static void add_stats(struct seq_file *seq, const char *aal, diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 078e48d442fd..33d0e6297c21 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -149,6 +149,7 @@ static const struct file_operations dccpprobe_fops = { .owner = THIS_MODULE, .open = dccpprobe_open, .read = dccpprobe_read, + .llseek = noop_llseek, }; static __init int dccpprobe_init(void) diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index f8efada580e8..6211e2114173 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -214,6 +214,7 @@ static const struct file_operations tcpprobe_fops = { .owner = THIS_MODULE, .open = tcpprobe_open, .read = tcpprobe_read, + .llseek = noop_llseek, }; static __init int tcpprobe_init(void) diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 4a4d35c750c6..b8b0ae79a743 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -102,7 +102,8 @@ static ssize_t tsf_write(struct file *file, static const struct file_operations tsf_ops = { .read = tsf_read, .write = tsf_write, - .open = mac80211_open_file_generic + .open = mac80211_open_file_generic, + .llseek = default_llseek, }; static ssize_t reset_write(struct file *file, const char __user *user_buf, @@ -121,6 +122,7 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, static const struct file_operations reset_ops = { .write = reset_write, .open = mac80211_open_file_generic, + .llseek = noop_llseek, }; static ssize_t noack_read(struct file *file, char __user *user_buf, @@ -156,7 +158,8 @@ static ssize_t noack_write(struct file *file, static const struct file_operations noack_ops = { .read = noack_read, .write = noack_write, - .open = mac80211_open_file_generic + .open = mac80211_open_file_generic, + .llseek = default_llseek, }; static ssize_t uapsd_queues_read(struct file *file, char __user *user_buf, @@ -202,7 +205,8 @@ static ssize_t uapsd_queues_write(struct file *file, static const struct file_operations uapsd_queues_ops = { .read = uapsd_queues_read, .write = uapsd_queues_write, - .open = mac80211_open_file_generic + .open = mac80211_open_file_generic, + .llseek = default_llseek, }; static ssize_t uapsd_max_sp_len_read(struct file *file, char __user *user_buf, @@ -248,7 +252,8 @@ static ssize_t uapsd_max_sp_len_write(struct file *file, static const struct file_operations uapsd_max_sp_len_ops = { .read = uapsd_max_sp_len_read, .write = uapsd_max_sp_len_write, - .open = mac80211_open_file_generic + .open = mac80211_open_file_generic, + .llseek = default_llseek, }; static ssize_t channel_type_read(struct file *file, char __user *user_buf, @@ -280,7 +285,8 @@ static ssize_t channel_type_read(struct file *file, char __user *user_buf, static const struct file_operations channel_type_ops = { .read = channel_type_read, - .open = mac80211_open_file_generic + .open = mac80211_open_file_generic, + .llseek = default_llseek, }; static ssize_t queues_read(struct file *file, char __user *user_buf, @@ -303,7 +309,8 @@ static ssize_t queues_read(struct file *file, char __user *user_buf, static const struct file_operations queues_ops = { .read = queues_read, - .open = mac80211_open_file_generic + .open = mac80211_open_file_generic, + .llseek = default_llseek, }; /* statistics stuff */ diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index be04d46110fe..334cbd3d2aae 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -145,6 +145,7 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf, static const struct file_operations rcname_ops = { .read = rcname_read, .open = mac80211_open_file_generic, + .llseek = default_llseek, }; #endif diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c index 241e76f3fdf2..a290ad231d77 100644 --- a/net/mac80211/rc80211_minstrel_debugfs.c +++ b/net/mac80211/rc80211_minstrel_debugfs.c @@ -122,6 +122,7 @@ static const struct file_operations minstrel_stat_fops = { .open = minstrel_stats_open, .read = minstrel_stats_read, .release = minstrel_stats_release, + .llseek = default_llseek, }; void diff --git a/net/mac80211/rc80211_pid_debugfs.c b/net/mac80211/rc80211_pid_debugfs.c index 47438b4a9af5..7905f79cc2e4 100644 --- a/net/mac80211/rc80211_pid_debugfs.c +++ b/net/mac80211/rc80211_pid_debugfs.c @@ -206,6 +206,7 @@ static const struct file_operations rc_pid_fop_events = { .poll = rate_control_pid_events_poll, .open = rate_control_pid_events_open, .release = rate_control_pid_events_release, + .llseek = noop_llseek, }; void rate_control_pid_add_sta_debugfs(void *priv, void *priv_sta, diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 76aec6a44762..d2ff15a2412b 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -567,6 +567,7 @@ static const struct file_operations recent_mt_fops = { .write = recent_mt_proc_write, .release = seq_release_private, .owner = THIS_MODULE, + .llseek = seq_lseek, }; static int __net_init recent_proc_net_init(struct net *net) diff --git a/net/nonet.c b/net/nonet.c index 92e76640c7cd..b1a73fda9c12 100644 --- a/net/nonet.c +++ b/net/nonet.c @@ -22,4 +22,5 @@ static int sock_no_open(struct inode *irrelevant, struct file *dontcare) const struct file_operations bad_sock_fops = { .owner = THIS_MODULE, .open = sock_no_open, + .llseek = noop_llseek, }; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 51875a0c5d48..04f599089e6d 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1241,6 +1241,7 @@ static const struct file_operations rfkill_fops = { .unlocked_ioctl = rfkill_fop_ioctl, .compat_ioctl = rfkill_fop_ioctl, #endif + .llseek = no_llseek, }; static struct miscdevice rfkill_miscdev = { diff --git a/net/sctp/probe.c b/net/sctp/probe.c index db3a42b8b349..289b1ba62cac 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -117,6 +117,7 @@ static const struct file_operations sctpprobe_fops = { .owner = THIS_MODULE, .open = sctpprobe_open, .read = sctpprobe_read, + .llseek = noop_llseek, }; sctp_disposition_t jsctp_sf_eat_sack(const struct sctp_endpoint *ep, diff --git a/net/socket.c b/net/socket.c index 2270b941bcc7..9eac5c394134 100644 --- a/net/socket.c +++ b/net/socket.c @@ -502,6 +502,7 @@ static int sock_no_open(struct inode *irrelevant, struct file *dontcare) const struct file_operations bad_sock_fops = { .owner = THIS_MODULE, .open = sock_no_open, + .llseek = noop_llseek, }; /** diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2b06410e584e..6bc692582de5 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1441,6 +1441,7 @@ static const struct file_operations cache_flush_operations_procfs = { .read = read_flush_procfs, .write = write_flush_procfs, .release = release_flush_procfs, + .llseek = no_llseek, }; static void remove_cache_proc_entries(struct cache_detail *cd) @@ -1646,6 +1647,7 @@ const struct file_operations cache_flush_operations_pipefs = { .read = read_flush_pipefs, .write = write_flush_pipefs, .release = release_flush_pipefs, + .llseek = no_llseek, }; int sunrpc_cache_register_pipefs(struct dentry *parent, diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c index 3f9a57e96508..39765bcfb472 100644 --- a/net/wireless/debugfs.c +++ b/net/wireless/debugfs.c @@ -103,6 +103,7 @@ static ssize_t ht40allow_map_read(struct file *file, static const struct file_operations ht40allow_map_ops = { .read = ht40allow_map_read, .open = cfg80211_open_file_generic, + .llseek = default_llseek, }; #define DEBUGFS_ADD(name) \ diff --git a/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c index 178061e87ffe..cfe40addda76 100644 --- a/samples/kfifo/bytestream-example.c +++ b/samples/kfifo/bytestream-example.c @@ -148,6 +148,7 @@ static const struct file_operations fifo_fops = { .owner = THIS_MODULE, .read = fifo_read, .write = fifo_write, + .llseek = noop_llseek, }; static int __init example_init(void) diff --git a/samples/kfifo/inttype-example.c b/samples/kfifo/inttype-example.c index 71b2aabca96a..6f8e79e76c9e 100644 --- a/samples/kfifo/inttype-example.c +++ b/samples/kfifo/inttype-example.c @@ -141,6 +141,7 @@ static const struct file_operations fifo_fops = { .owner = THIS_MODULE, .read = fifo_read, .write = fifo_write, + .llseek = noop_llseek, }; static int __init example_init(void) diff --git a/samples/kfifo/record-example.c b/samples/kfifo/record-example.c index e68bd16a5da4..2d7529eeb294 100644 --- a/samples/kfifo/record-example.c +++ b/samples/kfifo/record-example.c @@ -155,6 +155,7 @@ static const struct file_operations fifo_fops = { .owner = THIS_MODULE, .read = fifo_read, .write = fifo_write, + .llseek = noop_llseek, }; static int __init example_init(void) diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c index 26fab33ffa8c..f4d89e008c32 100644 --- a/samples/tracepoints/tracepoint-sample.c +++ b/samples/tracepoints/tracepoint-sample.c @@ -30,6 +30,7 @@ static int my_open(struct inode *inode, struct file *file) static const struct file_operations mark_ops = { .open = my_open, + .llseek = noop_llseek, }; static int __init sample_init(void) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 7320331b44ab..a27086d16f05 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -86,7 +86,8 @@ static ssize_t profile_load(struct file *f, const char __user *buf, size_t size, } static const struct file_operations aa_fs_profile_load = { - .write = profile_load + .write = profile_load, + .llseek = default_llseek, }; /* .replace file hook fn to load and/or replace policy */ @@ -107,7 +108,8 @@ static ssize_t profile_replace(struct file *f, const char __user *buf, } static const struct file_operations aa_fs_profile_replace = { - .write = profile_replace + .write = profile_replace, + .llseek = default_llseek, }; /* .remove file hook fn to remove loaded policy */ @@ -134,7 +136,8 @@ static ssize_t profile_remove(struct file *f, const char __user *buf, } static const struct file_operations aa_fs_profile_remove = { - .write = profile_remove + .write = profile_remove, + .llseek = default_llseek, }; /** Base file system setup **/ diff --git a/security/inode.c b/security/inode.c index 8c777f022ad1..88839866cbcd 100644 --- a/security/inode.c +++ b/security/inode.c @@ -53,6 +53,7 @@ static const struct file_operations default_file_ops = { .read = default_read_file, .write = default_write_file, .open = default_open, + .llseek = noop_llseek, }; static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev) diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index a2b72d77f926..7512502d0162 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -968,6 +968,7 @@ static ssize_t smk_write_doi(struct file *file, const char __user *buf, static const struct file_operations smk_doi_ops = { .read = smk_read_doi, .write = smk_write_doi, + .llseek = default_llseek, }; /** @@ -1031,6 +1032,7 @@ static ssize_t smk_write_direct(struct file *file, const char __user *buf, static const struct file_operations smk_direct_ops = { .read = smk_read_direct, .write = smk_write_direct, + .llseek = default_llseek, }; /** @@ -1112,6 +1114,7 @@ static ssize_t smk_write_ambient(struct file *file, const char __user *buf, static const struct file_operations smk_ambient_ops = { .read = smk_read_ambient, .write = smk_write_ambient, + .llseek = default_llseek, }; /** @@ -1191,6 +1194,7 @@ static ssize_t smk_write_onlycap(struct file *file, const char __user *buf, static const struct file_operations smk_onlycap_ops = { .read = smk_read_onlycap, .write = smk_write_onlycap, + .llseek = default_llseek, }; /** @@ -1255,6 +1259,7 @@ static ssize_t smk_write_logging(struct file *file, const char __user *buf, static const struct file_operations smk_logging_ops = { .read = smk_read_logging, .write = smk_write_logging, + .llseek = default_llseek, }; /** * smk_fill_super - fill the /smackfs superblock diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c index f25e3cc7ddfa..a1f1a2f00ccb 100644 --- a/sound/core/seq/oss/seq_oss.c +++ b/sound/core/seq/oss/seq_oss.c @@ -220,6 +220,7 @@ static const struct file_operations seq_oss_f_ops = .poll = odev_poll, .unlocked_ioctl = odev_ioctl, .compat_ioctl = odev_ioctl_compat, + .llseek = noop_llseek, }; static int __init diff --git a/sound/core/sound.c b/sound/core/sound.c index ac42af42b787..62a093efb453 100644 --- a/sound/core/sound.c +++ b/sound/core/sound.c @@ -184,7 +184,8 @@ static int snd_open(struct inode *inode, struct file *file) static const struct file_operations snd_fops = { .owner = THIS_MODULE, - .open = snd_open + .open = snd_open, + .llseek = noop_llseek, }; #ifdef CONFIG_SND_DYNAMIC_MINORS diff --git a/sound/oss/msnd_pinnacle.c b/sound/oss/msnd_pinnacle.c index 2e48b17667d0..ca942f7cd231 100644 --- a/sound/oss/msnd_pinnacle.c +++ b/sound/oss/msnd_pinnacle.c @@ -1117,6 +1117,7 @@ static const struct file_operations dev_fileops = { .unlocked_ioctl = dev_ioctl, .open = dev_open, .release = dev_release, + .llseek = noop_llseek, }; static int reset_dsp(void) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index acc91daa1c55..4057d35343bb 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -223,6 +223,7 @@ static const struct file_operations codec_reg_fops = { .open = codec_reg_open_file, .read = codec_reg_read_file, .write = codec_reg_write_file, + .llseek = default_llseek, }; static void soc_init_codec_debugfs(struct snd_soc_codec *codec) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 03cb7c05ebec..72a53d0a41e9 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1089,6 +1089,7 @@ static ssize_t dapm_widget_power_read_file(struct file *file, static const struct file_operations dapm_widget_power_fops = { .open = dapm_widget_power_open_file, .read = dapm_widget_power_read_file, + .llseek = default_llseek, }; void snd_soc_dapm_debugfs_init(struct snd_soc_codec *codec) diff --git a/sound/sound_core.c b/sound/sound_core.c index cb61317df509..c03bbaefdbc3 100644 --- a/sound/sound_core.c +++ b/sound/sound_core.c @@ -165,6 +165,7 @@ static const struct file_operations soundcore_fops = /* We must have an owner or the module locking fails */ .owner = THIS_MODULE, .open = soundcore_open, + .llseek = noop_llseek, }; /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d4853a54771a..e039f641d66b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1305,6 +1305,7 @@ static struct file_operations kvm_vcpu_fops = { .unlocked_ioctl = kvm_vcpu_ioctl, .compat_ioctl = kvm_vcpu_ioctl, .mmap = kvm_vcpu_mmap, + .llseek = noop_llseek, }; /* @@ -1774,6 +1775,7 @@ static struct file_operations kvm_vm_fops = { .compat_ioctl = kvm_vm_compat_ioctl, #endif .mmap = kvm_vm_mmap, + .llseek = noop_llseek, }; static int kvm_dev_ioctl_create_vm(void) @@ -1867,6 +1869,7 @@ out: static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, .compat_ioctl = kvm_dev_ioctl, + .llseek = noop_llseek, }; static struct miscdevice kvm_dev = { -- cgit v1.2.3 From 31ddd871fc3db73e2024cb3eb3ee5051edf5a80f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Oct 2010 11:14:49 +0200 Subject: workqueue: Clarify that schedule_on_each_cpu is synchronous The documentation for schedule_on_each_cpu() states that it calls a function on each online CPU from keventd. This can easily be interpreted as an asyncronous call because the description does not mention that flush_work is called. Clarify that it is synchronous. tj: rephrased a bit Signed-off-by: Mel Gorman Reviewed-by: KOSAKI Motohiro Signed-off-by: Tejun Heo --- kernel/workqueue.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2c6871cbcbee..eb5c1972443a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2676,13 +2676,15 @@ int schedule_delayed_work_on(int cpu, EXPORT_SYMBOL(schedule_delayed_work_on); /** - * schedule_on_each_cpu - call a function on each online CPU from keventd + * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * - * Returns zero on success. - * Returns -ve errno on failure. - * + * schedule_on_each_cpu() executes @func on each online CPU using the + * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. + * + * RETURNS: + * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { -- cgit v1.2.3 From daaae6b010ac0f60c9c35e481589966f9f1fcc22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Oct 2010 11:28:15 +0200 Subject: workqueue: remove in_workqueue_context() Commit a25909a4 (lockdep: Add an in_workqueue_context() lockdep-based test function) added in_workqueue_context() but there hasn't been any in-kernel user and the lockdep annotation in workqueue is scheduled to change. Remove the unused function. Signed-off-by: Tejun Heo Cc: Paul E. McKenney --- include/linux/workqueue.h | 4 ---- kernel/workqueue.c | 15 --------------- 2 files changed, 19 deletions(-) (limited to 'kernel') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 03bbe903e5ce..070bb7a88936 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -430,8 +430,4 @@ extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ -#ifdef CONFIG_LOCKDEP -int in_workqueue_context(struct workqueue_struct *wq); -#endif - #endif diff --git a/kernel/workqueue.c b/kernel/workqueue.c index eb5c1972443a..30acdb74cc23 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -310,21 +310,6 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, (cpu) < WORK_CPU_NONE; \ (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq))) -#ifdef CONFIG_LOCKDEP -/** - * in_workqueue_context() - in context of specified workqueue? - * @wq: the workqueue of interest - * - * Checks lockdep state to see if the current task is executing from - * within a workqueue item. This function exists only if lockdep is - * enabled. - */ -int in_workqueue_context(struct workqueue_struct *wq) -{ - return lock_is_held(&wq->lockdep_map); -} -#endif - #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; -- cgit v1.2.3 From 0fc86c7bd924debd0bddee790ecc884604fdcc63 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 11 Sep 2010 20:11:08 +0200 Subject: rtmutex-tester: make it build without BKL The big kernel lock is going away, so make sure that if it is disabled by Kconfig, we do not try to validate it, which would result in compile errors. Signed-off-by: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Arjan van de Ven Cc: Andrew Morton --- kernel/rtmutex-tester.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c index a56f629b057a..66cb89bc5ef1 100644 --- a/kernel/rtmutex-tester.c +++ b/kernel/rtmutex-tester.c @@ -76,7 +76,9 @@ static int handle_op(struct test_thread_data *td, int lockwakeup) } if (!lockwakeup && td->bkl == 4) { +#ifdef CONFIG_LOCK_KERNEL unlock_kernel(); +#endif td->bkl = 0; } return 0; @@ -133,14 +135,18 @@ static int handle_op(struct test_thread_data *td, int lockwakeup) if (td->bkl) return 0; td->bkl = 1; +#ifdef CONFIG_LOCK_KERNEL lock_kernel(); +#endif td->bkl = 4; return 0; case RTTEST_UNLOCKBKL: if (td->bkl != 4) break; +#ifdef CONFIG_LOCK_KERNEL unlock_kernel(); +#endif td->bkl = 0; return 0; -- cgit v1.2.3 From 01b284f9b6d51cc3f3bcf3b49f16d2601d3ca22d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 17 Sep 2010 20:39:22 +0200 Subject: blktrace: remove the big kernel lock According to Jens, this code does not need the BKL at all, it is sufficiently serialized by bd_mutex. Signed-off-by: Arnd Bergmann Cc: Jens Axboe Cc: Steven Rostedt --- kernel/trace/blktrace.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 959f8d6c8cc1..5328e8779d4d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include @@ -639,7 +638,6 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - lock_kernel(); mutex_lock(&bdev->bd_mutex); switch (cmd) { @@ -667,7 +665,6 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) } mutex_unlock(&bdev->bd_mutex); - unlock_kernel(); return ret; } @@ -1652,10 +1649,9 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct block_device *bdev; ssize_t ret = -ENXIO; - lock_kernel(); bdev = bdget(part_devt(p)); if (bdev == NULL) - goto out_unlock_kernel; + goto out; q = blk_trace_get_queue(bdev); if (q == NULL) @@ -1683,8 +1679,7 @@ out_unlock_bdev: mutex_unlock(&bdev->bd_mutex); out_bdput: bdput(bdev); -out_unlock_kernel: - unlock_kernel(); +out: return ret; } @@ -1714,11 +1709,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, ret = -ENXIO; - lock_kernel(); p = dev_to_part(dev); bdev = bdget(part_devt(p)); if (bdev == NULL) - goto out_unlock_kernel; + goto out; q = blk_trace_get_queue(bdev); if (q == NULL) @@ -1753,8 +1747,6 @@ out_unlock_bdev: mutex_unlock(&bdev->bd_mutex); out_bdput: bdput(bdev); -out_unlock_kernel: - unlock_kernel(); out: return ret ? ret : count; } -- cgit v1.2.3 From 747e94ae3d1b4c9bf5380e569f614eb9040b79e7 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 8 Oct 2010 13:51:48 -0400 Subject: ring-buffer: Make write slow path out of line Gcc inlines the slow path of the ring buffer write which can hurt performance. This patch simply forces the slow path function rb_move_tail() to always be a function. The ring_buffer_benchmark module with reader_disabled=1 shows that this patch changes the time to record an event from 135 ns to 132 ns. (3 ns or 2.22% improvement) Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bca96377fd4e..0b88df849a59 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1823,7 +1823,10 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, local_sub(length, &tail_page->write); } -static struct ring_buffer_event * +/* + * This is the slow path, force gcc not to inline it. + */ +static noinline struct ring_buffer_event * rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long length, unsigned long tail, struct buffer_page *tail_page, u64 *ts) @@ -1943,7 +1946,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, tail = write - length; /* See if we shot pass the end of this buffer page */ - if (write > BUF_PAGE_SIZE) + if (unlikely(write > BUF_PAGE_SIZE)) return rb_move_tail(cpu_buffer, length, tail, tail_page, ts); -- cgit v1.2.3 From e8bc43e84fada397af1b677b07dbf26e6ac78fcc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 20 Oct 2010 10:58:02 -0400 Subject: ring-buffer: Pass timestamp by value and not by reference The original code for the ring buffer had locations that modified the timestamp and that change was used by the callers. Now, the timestamp is not reused by the callers and there is no reason to pass it by reference. By changing the call to pass by value, lets gcc optimize the code a bit more where it can store the timestamp in a register and not worry about updating the reference. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0b88df849a59..c8ce6bde7fa4 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1829,7 +1829,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, static noinline struct ring_buffer_event * rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long length, unsigned long tail, - struct buffer_page *tail_page, u64 *ts) + struct buffer_page *tail_page, u64 ts) { struct buffer_page *commit_page = cpu_buffer->commit_page; struct ring_buffer *buffer = cpu_buffer->buffer; @@ -1912,8 +1912,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, * Nested commits always have zero deltas, so * just reread the time stamp */ - *ts = rb_time_stamp(buffer); - next_page->page->time_stamp = *ts; + ts = rb_time_stamp(buffer); + next_page->page->time_stamp = ts; } out_again: @@ -1932,7 +1932,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, static struct ring_buffer_event * __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, - unsigned type, unsigned long length, u64 *ts) + unsigned type, unsigned long length, u64 ts) { struct buffer_page *tail_page; struct ring_buffer_event *event; @@ -1965,7 +1965,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, * its timestamp. */ if (!tail) - tail_page->page->time_stamp = *ts; + tail_page->page->time_stamp = ts; return event; } @@ -2008,7 +2008,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, static int rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, - u64 *ts, u64 *delta) + u64 ts, u64 *delta) { struct ring_buffer_event *event; int ret; @@ -2016,7 +2016,7 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, WARN_ONCE(*delta > (1ULL << 59), KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n", (unsigned long long)*delta, - (unsigned long long)*ts, + (unsigned long long)ts, (unsigned long long)cpu_buffer->write_stamp); /* @@ -2051,7 +2051,7 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, event->array[0] = 0; } } - cpu_buffer->write_stamp = *ts; + cpu_buffer->write_stamp = ts; /* let the caller know this was the commit */ ret = 1; } else { @@ -2175,7 +2175,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, delta = diff; if (unlikely(test_time_stamp(delta))) { - commit = rb_add_time_stamp(cpu_buffer, &ts, &delta); + commit = rb_add_time_stamp(cpu_buffer, ts, &delta); if (commit == -EBUSY) goto out_fail; @@ -2187,7 +2187,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, } get_event: - event = __rb_reserve_next(cpu_buffer, 0, length, &ts); + event = __rb_reserve_next(cpu_buffer, 0, length, ts); if (unlikely(PTR_ERR(event) == -EAGAIN)) goto again; -- cgit v1.2.3 From f25106aeab7408394b9dd707e5ecf557e269c723 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 20 Oct 2010 12:40:12 -0400 Subject: ring-buffer: Pass delta by value and not by reference The delta between events is passed to the timestamp code by reference and the timestamp code will reset the value. But it can be reset from the caller. No need to pass it in by reference. By changing the call to pass by value, lets gcc optimize the code a bit more where it can store the delta in a register and not worry about updating the reference. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c8ce6bde7fa4..3af77cd47f21 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2008,14 +2008,14 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, static int rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, - u64 ts, u64 *delta) + u64 ts, u64 delta) { struct ring_buffer_event *event; int ret; - WARN_ONCE(*delta > (1ULL << 59), + WARN_ONCE(delta > (1ULL << 59), KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n", - (unsigned long long)*delta, + (unsigned long long)delta, (unsigned long long)ts, (unsigned long long)cpu_buffer->write_stamp); @@ -2041,8 +2041,8 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, * and if we can't just make it zero. */ if (rb_event_index(event)) { - event->time_delta = *delta & TS_MASK; - event->array[0] = *delta >> TS_SHIFT; + event->time_delta = delta & TS_MASK; + event->array[0] = delta >> TS_SHIFT; } else { /* try to discard, since we do not need this */ if (!rb_try_to_discard(cpu_buffer, event)) { @@ -2064,8 +2064,6 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, ret = 0; } - *delta = 0; - return ret; } @@ -2175,7 +2173,9 @@ rb_reserve_next_event(struct ring_buffer *buffer, delta = diff; if (unlikely(test_time_stamp(delta))) { - commit = rb_add_time_stamp(cpu_buffer, ts, &delta); + commit = rb_add_time_stamp(cpu_buffer, ts, delta); + delta = 0; + if (commit == -EBUSY) goto out_fail; -- cgit v1.2.3 From 69d1b839f7eee347e357b3f6cce7f630cc6ff93d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 7 Oct 2010 18:18:05 -0400 Subject: ring-buffer: Bind time extend and data events together When the time between two timestamps is greater than 2^27 nanosecs (~134 ms) a time extend event is added that extends the time difference to 59 bits (~18 years). This is due to events only having a 27 bit field to store time. Currently this time extend is a separate event. We add it just before the event data that is being written to the buffer. But before the event data is committed, the event data can also be discarded (as with the case of filters). But because the time extend has already been committed, it will stay in the buffer. If lots of events are being filtered and no event is being written, then every 134ms a time extend can be added to the buffer without any data attached. To keep from filling the entire buffer with time extends, a time extend will never be the first event in a page because the page timestamp can be used. Time extends can only fill the rest of a page with some data at the beginning. This patch binds the time extend with the data. The difference here is that the time extend is not committed before the data is added. Instead, when a time extend is needed, the space reserved on the ring buffer is the time extend + the data event size. The time extend is added to the first part of the reserved block and the data is added to the second. The time extend event is passed back to the reserver, but since the reserver also uses a function to find the data portion of the reserved block, no changes to the ring buffer interface need to be made. When a commit is discarded, we now remove both the time extend and the event. With this approach no more than one time extend can be in the buffer in a row. Data must always follow a time extend. Thanks to Mathieu Desnoyers for suggesting this idea. Suggested-by: Mathieu Desnoyers Cc: Thomas Gleixner Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 266 ++++++++++++++++++++++++--------------------- 1 file changed, 142 insertions(+), 124 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3af77cd47f21..f50f43107e93 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -224,6 +224,9 @@ enum { RB_LEN_TIME_STAMP = 16, }; +#define skip_time_extend(event) \ + ((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND)) + static inline int rb_null_event(struct ring_buffer_event *event) { return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta; @@ -248,8 +251,12 @@ rb_event_data_length(struct ring_buffer_event *event) return length + RB_EVNT_HDR_SIZE; } -/* inline for ring buffer fast paths */ -static unsigned +/* + * Return the length of the given event. Will return + * the length of the time extend if the event is a + * time extend. + */ +static inline unsigned rb_event_length(struct ring_buffer_event *event) { switch (event->type_len) { @@ -274,13 +281,41 @@ rb_event_length(struct ring_buffer_event *event) return 0; } +/* + * Return total length of time extend and data, + * or just the event length for all other events. + */ +static inline unsigned +rb_event_ts_length(struct ring_buffer_event *event) +{ + unsigned len = 0; + + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) { + /* time extends include the data event after it */ + len = RB_LEN_TIME_EXTEND; + event = skip_time_extend(event); + } + return len + rb_event_length(event); +} + /** * ring_buffer_event_length - return the length of the event * @event: the event to get the length of + * + * Returns the size of the data load of a data event. + * If the event is something other than a data event, it + * returns the size of the event itself. With the exception + * of a TIME EXTEND, where it still returns the size of the + * data load of the data event after it. */ unsigned ring_buffer_event_length(struct ring_buffer_event *event) { - unsigned length = rb_event_length(event); + unsigned length; + + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) + event = skip_time_extend(event); + + length = rb_event_length(event); if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX) return length; length -= RB_EVNT_HDR_SIZE; @@ -294,6 +329,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_length); static void * rb_event_data(struct ring_buffer_event *event) { + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) + event = skip_time_extend(event); BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); /* If length is in len field, then array[0] has the data */ if (event->type_len) @@ -1546,6 +1583,25 @@ static void rb_inc_iter(struct ring_buffer_iter *iter) iter->head = 0; } +/* Slow path, do not inline */ +static noinline struct ring_buffer_event * +rb_add_time_stamp(struct ring_buffer_event *event, u64 delta) +{ + event->type_len = RINGBUF_TYPE_TIME_EXTEND; + + /* Not the first event on the page? */ + if (rb_event_index(event)) { + event->time_delta = delta & TS_MASK; + event->array[0] = delta >> TS_SHIFT; + } else { + /* nope, just zero it */ + event->time_delta = 0; + event->array[0] = 0; + } + + return skip_time_extend(event); +} + /** * ring_buffer_update_event - update event type and data * @event: the even to update @@ -1558,28 +1614,31 @@ static void rb_inc_iter(struct ring_buffer_iter *iter) * data field. */ static void -rb_update_event(struct ring_buffer_event *event, - unsigned type, unsigned length) +rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, + struct ring_buffer_event *event, unsigned length, + int add_timestamp, u64 delta) { - event->type_len = type; - - switch (type) { - - case RINGBUF_TYPE_PADDING: - case RINGBUF_TYPE_TIME_EXTEND: - case RINGBUF_TYPE_TIME_STAMP: - break; + /* Only a commit updates the timestamp */ + if (unlikely(!rb_event_is_commit(cpu_buffer, event))) + delta = 0; - case 0: - length -= RB_EVNT_HDR_SIZE; - if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) - event->array[0] = length; - else - event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT); - break; - default: - BUG(); + /* + * If we need to add a timestamp, then we + * add it to the start of the resevered space. + */ + if (unlikely(add_timestamp)) { + event = rb_add_time_stamp(event, delta); + length -= RB_LEN_TIME_EXTEND; + delta = 0; } + + event->time_delta = delta; + length -= RB_EVNT_HDR_SIZE; + if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) { + event->type_len = 0; + event->array[0] = length; + } else + event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT); } /* @@ -1932,12 +1991,21 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, static struct ring_buffer_event * __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, - unsigned type, unsigned long length, u64 ts) + unsigned long length, u64 ts, + u64 delta, int add_timestamp) { struct buffer_page *tail_page; struct ring_buffer_event *event; unsigned long tail, write; + /* + * If the time delta since the last event is too big to + * hold in the time field of the event, then we append a + * TIME EXTEND event ahead of the data event. + */ + if (unlikely(add_timestamp)) + length += RB_LEN_TIME_EXTEND; + tail_page = cpu_buffer->tail_page; write = local_add_return(length, &tail_page->write); @@ -1954,11 +2022,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); kmemcheck_annotate_bitfield(event, bitfield); - rb_update_event(event, type, length); + rb_update_event(cpu_buffer, event, length, add_timestamp, delta); - /* The passed in type is zero for DATA */ - if (likely(!type)) - local_inc(&tail_page->entries); + local_inc(&tail_page->entries); /* * If this is the first commit on the page, then update @@ -1980,7 +2046,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, unsigned long addr; new_index = rb_event_index(event); - old_index = new_index + rb_event_length(event); + old_index = new_index + rb_event_ts_length(event); addr = (unsigned long)event; addr &= PAGE_MASK; @@ -2006,67 +2072,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, return 0; } -static int -rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, - u64 ts, u64 delta) -{ - struct ring_buffer_event *event; - int ret; - - WARN_ONCE(delta > (1ULL << 59), - KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n", - (unsigned long long)delta, - (unsigned long long)ts, - (unsigned long long)cpu_buffer->write_stamp); - - /* - * The delta is too big, we to add a - * new timestamp. - */ - event = __rb_reserve_next(cpu_buffer, - RINGBUF_TYPE_TIME_EXTEND, - RB_LEN_TIME_EXTEND, - ts); - if (!event) - return -EBUSY; - - if (PTR_ERR(event) == -EAGAIN) - return -EAGAIN; - - /* Only a commited time event can update the write stamp */ - if (rb_event_is_commit(cpu_buffer, event)) { - /* - * If this is the first on the page, then it was - * updated with the page itself. Try to discard it - * and if we can't just make it zero. - */ - if (rb_event_index(event)) { - event->time_delta = delta & TS_MASK; - event->array[0] = delta >> TS_SHIFT; - } else { - /* try to discard, since we do not need this */ - if (!rb_try_to_discard(cpu_buffer, event)) { - /* nope, just zero it */ - event->time_delta = 0; - event->array[0] = 0; - } - } - cpu_buffer->write_stamp = ts; - /* let the caller know this was the commit */ - ret = 1; - } else { - /* Try to discard the event */ - if (!rb_try_to_discard(cpu_buffer, event)) { - /* Darn, this is just wasted space */ - event->time_delta = 0; - event->array[0] = 0; - } - ret = 0; - } - - return ret; -} - static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer) { local_inc(&cpu_buffer->committing); @@ -2111,9 +2116,9 @@ rb_reserve_next_event(struct ring_buffer *buffer, unsigned long length) { struct ring_buffer_event *event; - u64 ts, delta = 0; - int commit = 0; + u64 ts, delta; int nr_loops = 0; + int add_timestamp; rb_start_commit(cpu_buffer); @@ -2134,6 +2139,9 @@ rb_reserve_next_event(struct ring_buffer *buffer, length = rb_calculate_event_length(length); again: + add_timestamp = 0; + delta = 0; + /* * We allow for interrupts to reenter here and do a trace. * If one does, it will cause this original code to loop @@ -2172,33 +2180,24 @@ rb_reserve_next_event(struct ring_buffer *buffer, delta = diff; if (unlikely(test_time_stamp(delta))) { - - commit = rb_add_time_stamp(cpu_buffer, ts, delta); - delta = 0; - - if (commit == -EBUSY) - goto out_fail; - - if (commit == -EAGAIN) - goto again; - - RB_WARN_ON(cpu_buffer, commit < 0); + WARN_ONCE(delta > (1ULL << 59), + KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n", + (unsigned long long)delta, + (unsigned long long)ts, + (unsigned long long)cpu_buffer->write_stamp); + add_timestamp = 1; } } get_event: - event = __rb_reserve_next(cpu_buffer, 0, length, ts); + event = __rb_reserve_next(cpu_buffer, length, ts, + delta, add_timestamp); if (unlikely(PTR_ERR(event) == -EAGAIN)) goto again; if (!event) goto out_fail; - if (!rb_event_is_commit(cpu_buffer, event)) - delta = 0; - - event->time_delta = delta; - return event; out_fail: @@ -2311,12 +2310,28 @@ static void rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { + u64 delta; + /* * The event first in the commit queue updates the * time stamp. */ - if (rb_event_is_commit(cpu_buffer, event)) - cpu_buffer->write_stamp += event->time_delta; + if (rb_event_is_commit(cpu_buffer, event)) { + /* + * A commit event that is first on a page + * updates the write timestamp with the page stamp + */ + if (!rb_event_index(event)) + cpu_buffer->write_stamp = + cpu_buffer->commit_page->page->time_stamp; + else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) { + delta = event->array[0]; + delta <<= TS_SHIFT; + delta += event->time_delta; + cpu_buffer->write_stamp += delta; + } else + cpu_buffer->write_stamp += event->time_delta; + } } static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, @@ -2356,6 +2371,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit); static inline void rb_event_discard(struct ring_buffer_event *event) { + if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) + event = skip_time_extend(event); + /* array[0] holds the actual length for the discarded event */ event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE; event->type_len = RINGBUF_TYPE_PADDING; @@ -3043,12 +3061,12 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, again: /* - * We repeat when a timestamp is encountered. It is possible - * to get multiple timestamps from an interrupt entering just - * as one timestamp is about to be written, or from discarded - * commits. The most that we can have is the number on a single page. + * We repeat when a time extend is encountered. + * Since the time extend is always attached to a data event, + * we should never loop more than once. + * (We never hit the following condition more than twice). */ - if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE)) + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2)) return NULL; reader = rb_get_reader_page(cpu_buffer); @@ -3124,14 +3142,12 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return NULL; /* - * We repeat when a timestamp is encountered. - * We can get multiple timestamps by nested interrupts or also - * if filtering is on (discarding commits). Since discarding - * commits can be frequent we can get a lot of timestamps. - * But we limit them by not adding timestamps if they begin - * at the start of a page. + * We repeat when a time extend is encountered. + * Since the time extend is always attached to a data event, + * we should never loop more than once. + * (We never hit the following condition more than twice). */ - if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE)) + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2)) return NULL; if (rb_per_cpu_empty(cpu_buffer)) @@ -3829,7 +3845,8 @@ int ring_buffer_read_page(struct ring_buffer *buffer, if (len > (commit - read)) len = (commit - read); - size = rb_event_length(event); + /* Always keep the time extend and data together */ + size = rb_event_ts_length(event); if (len < size) goto out_unlock; @@ -3851,7 +3868,8 @@ int ring_buffer_read_page(struct ring_buffer *buffer, break; event = rb_reader_event(cpu_buffer); - size = rb_event_length(event); + /* Always keep the time extend and data together */ + size = rb_event_ts_length(event); } while (len > size); /* update bpage */ -- cgit v1.2.3 From 140ff89127c74b1b1c1b0152a36ea3720ccf6bc3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 8 Oct 2010 10:50:30 -0400 Subject: ring-buffer: Remove condition to add timestamp in fast path There's a condition to check if we should add a time extend or not in the fast path. But this condition is racey (in the sense that we can add a unnecessary time extend, but nothing that can break anything). We later check if the time or event time delta should be zero or have real data in it (not racey), making this first check redundant. This check may help save space once in a while, but really is not worth the hassle to try to save some space that happens at most 134 ms at a time. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 28 ++++++---------------------- 1 file changed, 6 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f50f43107e93..d9f3e7a82137 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2119,6 +2119,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, u64 ts, delta; int nr_loops = 0; int add_timestamp; + u64 diff; rb_start_commit(cpu_buffer); @@ -2155,29 +2156,13 @@ rb_reserve_next_event(struct ring_buffer *buffer, goto out_fail; ts = rb_time_stamp(cpu_buffer->buffer); + diff = ts - cpu_buffer->write_stamp; - /* - * Only the first commit can update the timestamp. - * Yes there is a race here. If an interrupt comes in - * just after the conditional and it traces too, then it - * will also check the deltas. More than one timestamp may - * also be made. But only the entry that did the actual - * commit will be something other than zero. - */ - if (likely(cpu_buffer->tail_page == cpu_buffer->commit_page && - rb_page_write(cpu_buffer->tail_page) == - rb_commit_index(cpu_buffer))) { - u64 diff; - - diff = ts - cpu_buffer->write_stamp; - - /* make sure this diff is calculated here */ - barrier(); - - /* Did the write stamp get updated already? */ - if (unlikely(ts < cpu_buffer->write_stamp)) - goto get_event; + /* make sure this diff is calculated here */ + barrier(); + /* Did the write stamp get updated already? */ + if (likely(ts >= cpu_buffer->write_stamp)) { delta = diff; if (unlikely(test_time_stamp(delta))) { WARN_ONCE(delta > (1ULL << 59), @@ -2189,7 +2174,6 @@ rb_reserve_next_event(struct ring_buffer *buffer, } } - get_event: event = __rb_reserve_next(cpu_buffer, length, ts, delta, add_timestamp); if (unlikely(PTR_ERR(event) == -EAGAIN)) -- cgit v1.2.3 From d9abde2138e0a00a0d7e44676928efa0ef629d48 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 19 Oct 2010 13:17:08 -0400 Subject: ring-buffer: Micro-optimize with some strategic inlining By using inline and noinline, we are able to make the fast path of recording an event 4% faster. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d9f3e7a82137..f5007d0d932d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2078,7 +2078,7 @@ static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer) local_inc(&cpu_buffer->commits); } -static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer) +static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer) { unsigned long commits; @@ -2193,13 +2193,9 @@ rb_reserve_next_event(struct ring_buffer *buffer, #define TRACE_RECURSIVE_DEPTH 16 -static int trace_recursive_lock(void) +/* Keep this code out of the fast path cache */ +static noinline void trace_recursive_fail(void) { - current->trace_recursion++; - - if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH)) - return 0; - /* Disable all tracing before we do anything else */ tracing_off_permanent(); @@ -2211,10 +2207,21 @@ static int trace_recursive_lock(void) in_nmi()); WARN_ON_ONCE(1); +} + +static inline int trace_recursive_lock(void) +{ + current->trace_recursion++; + + if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH)) + return 0; + + trace_recursive_fail(); + return -1; } -static void trace_recursive_unlock(void) +static inline void trace_recursive_unlock(void) { WARN_ON_ONCE(!current->trace_recursion); -- cgit v1.2.3 From b8b2663bd7c9da04ac804659b9f617c199d0252c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 19 Oct 2010 13:23:25 -0400 Subject: ring-buffer: Remove unused macro RB_TIMESTAMPS_PER_PAGE With the binding of time extends to events we no longer need to use the macro RB_TIMESTAMPS_PER_PAGE. Remove it. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f5007d0d932d..ad25490f8b40 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -441,9 +441,6 @@ static inline int test_time_stamp(u64 delta) /* Max payload is BUF_PAGE_SIZE - header (8bytes) */ #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2)) -/* Max number of timestamps that can fit on a page */ -#define RB_TIMESTAMPS_PER_PAGE (BUF_PAGE_SIZE / RB_LEN_TIME_EXTEND) - int ring_buffer_print_page_header(struct trace_seq *s) { struct buffer_data_page field; -- cgit v1.2.3 From 16cdc628c3aed47d02205135b7e2f01e0064f566 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Fri, 6 Aug 2010 11:47:14 -0500 Subject: debug_core: move all watch dog syncs to a single function Move the various clock and watch dog syncs to a single function in advance of adding another sync for the rcu stall detector. Signed-off-by: Jason Wessel --- kernel/debug/debug_core.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index de407c78178d..c812857d0b80 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -470,6 +470,12 @@ static void dbg_cpu_switch(int cpu, int next_cpu) kgdb_info[next_cpu].exception_state |= DCPU_NEXT_MASTER; } +static void dbg_touch_watchdogs(void) +{ + touch_softlockup_watchdog_sync(); + clocksource_touch_watchdog(); +} + static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs) { unsigned long flags; @@ -523,8 +529,7 @@ return_normal: if (trace_on) tracing_on(); atomic_dec(&cpu_in_kgdb[cpu]); - touch_softlockup_watchdog_sync(); - clocksource_touch_watchdog(); + dbg_touch_watchdogs(); local_irq_restore(flags); return 0; } @@ -541,8 +546,7 @@ return_normal: (kgdb_info[cpu].task && kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) { atomic_set(&kgdb_active, -1); - touch_softlockup_watchdog_sync(); - clocksource_touch_watchdog(); + dbg_touch_watchdogs(); local_irq_restore(flags); goto acquirelock; @@ -659,8 +663,7 @@ kgdb_restore: tracing_on(); /* Free kgdb_active */ atomic_set(&kgdb_active, -1); - touch_softlockup_watchdog_sync(); - clocksource_touch_watchdog(); + dbg_touch_watchdogs(); local_irq_restore(flags); return kgdb_info[cpu].ret_state; -- cgit v1.2.3 From fb70b5888b70b0b50f738fbfc019445493112eb1 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Fri, 13 Aug 2010 12:44:04 -0500 Subject: debug_core: stop rcu warnings on kernel resume When returning from the kernel debugger reset the rcu jiffies_stall value to prevent the rcu stall detector from sending NMI events which invoke a stack dump for each cpu in the system. Signed-off-by: Jason Wessel --- kernel/debug/debug_core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index c812857d0b80..5a3b04d20497 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -474,6 +475,7 @@ static void dbg_touch_watchdogs(void) { touch_softlockup_watchdog_sync(); clocksource_touch_watchdog(); + rcu_cpu_stall_reset(); } static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs) -- cgit v1.2.3 From f7030bbc446430ecd12c9ad02cf0ea94934e5f91 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Mon, 11 Oct 2010 10:20:14 -0500 Subject: kdb: Allow kernel loadable modules to add kdb shell functions In order to allow kernel modules to dynamically add a command to the kdb shell the kdb_register, kdb_register_repeat, kdb_unregister, and kdb_printf need to be exported as GPL symbols. Any kernel module that adds a dynamic kdb shell function should only need to include linux/kdb.h. Signed-off-by: Jason Wessel --- include/linux/kdb.h | 43 ++++++++++++++++++++++++++++++++++++++++++ kernel/debug/kdb/kdb_io.c | 2 +- kernel/debug/kdb/kdb_main.c | 4 ++++ kernel/debug/kdb/kdb_private.h | 39 -------------------------------------- 4 files changed, 48 insertions(+), 40 deletions(-) (limited to 'kernel') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index ea6e5244ed3f..deda197ced62 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -28,6 +28,41 @@ extern int kdb_poll_idx; extern int kdb_initial_cpu; extern atomic_t kdb_event; +/* Types and messages used for dynamically added kdb shell commands */ + +#define KDB_MAXARGS 16 /* Maximum number of arguments to a function */ + +typedef enum { + KDB_REPEAT_NONE = 0, /* Do not repeat this command */ + KDB_REPEAT_NO_ARGS, /* Repeat the command without arguments */ + KDB_REPEAT_WITH_ARGS, /* Repeat the command including its arguments */ +} kdb_repeat_t; + +typedef int (*kdb_func_t)(int, const char **); + +/* KDB return codes from a command or internal kdb function */ +#define KDB_NOTFOUND (-1) +#define KDB_ARGCOUNT (-2) +#define KDB_BADWIDTH (-3) +#define KDB_BADRADIX (-4) +#define KDB_NOTENV (-5) +#define KDB_NOENVVALUE (-6) +#define KDB_NOTIMP (-7) +#define KDB_ENVFULL (-8) +#define KDB_ENVBUFFULL (-9) +#define KDB_TOOMANYBPT (-10) +#define KDB_TOOMANYDBREGS (-11) +#define KDB_DUPBPT (-12) +#define KDB_BPTNOTFOUND (-13) +#define KDB_BADMODE (-14) +#define KDB_BADINT (-15) +#define KDB_INVADDRFMT (-16) +#define KDB_BADREG (-17) +#define KDB_BADCPUNUM (-18) +#define KDB_BADLENGTH (-19) +#define KDB_NOBP (-20) +#define KDB_BADADDR (-21) + /* * kdb_diemsg * @@ -105,9 +140,17 @@ int kdb_process_cpu(const struct task_struct *p) /* kdb access to register set for stack dumping */ extern struct pt_regs *kdb_current_regs; +/* Dynamic kdb shell command registration */ +extern int kdb_register(char *, kdb_func_t, char *, char *, short); +extern int kdb_register_repeat(char *, kdb_func_t, char *, char *, + short, kdb_repeat_t); +extern int kdb_unregister(char *); #else /* ! CONFIG_KGDB_KDB */ #define kdb_printf(...) #define kdb_init(x) +#define kdb_register(...) +#define kdb_register_repeat(...) +#define kdb_uregister(x) #endif /* CONFIG_KGDB_KDB */ enum { KDB_NOT_INITIALIZED, diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index c9b7f4f90bba..96fdaac46a80 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -823,4 +823,4 @@ int kdb_printf(const char *fmt, ...) return r; } - +EXPORT_SYMBOL_GPL(kdb_printf); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index caf057a3de0e..5448990a299e 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2783,6 +2783,8 @@ int kdb_register_repeat(char *cmd, return 0; } +EXPORT_SYMBOL_GPL(kdb_register_repeat); + /* * kdb_register - Compatibility register function for commands that do @@ -2805,6 +2807,7 @@ int kdb_register(char *cmd, return kdb_register_repeat(cmd, func, usage, help, minlen, KDB_REPEAT_NONE); } +EXPORT_SYMBOL_GPL(kdb_register); /* * kdb_unregister - This function is used to unregister a kernel @@ -2833,6 +2836,7 @@ int kdb_unregister(char *cmd) /* Couldn't find it. */ return 1; } +EXPORT_SYMBOL_GPL(kdb_unregister); /* Initialize the kdb command table. */ static void __init kdb_inittab(void) diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index be775f7e81e0..1921e6e4c0bc 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -15,29 +15,6 @@ #include #include "../debug_core.h" -/* Kernel Debugger Error codes. Must not overlap with command codes. */ -#define KDB_NOTFOUND (-1) -#define KDB_ARGCOUNT (-2) -#define KDB_BADWIDTH (-3) -#define KDB_BADRADIX (-4) -#define KDB_NOTENV (-5) -#define KDB_NOENVVALUE (-6) -#define KDB_NOTIMP (-7) -#define KDB_ENVFULL (-8) -#define KDB_ENVBUFFULL (-9) -#define KDB_TOOMANYBPT (-10) -#define KDB_TOOMANYDBREGS (-11) -#define KDB_DUPBPT (-12) -#define KDB_BPTNOTFOUND (-13) -#define KDB_BADMODE (-14) -#define KDB_BADINT (-15) -#define KDB_INVADDRFMT (-16) -#define KDB_BADREG (-17) -#define KDB_BADCPUNUM (-18) -#define KDB_BADLENGTH (-19) -#define KDB_NOBP (-20) -#define KDB_BADADDR (-21) - /* Kernel Debugger Command codes. Must not overlap with error codes. */ #define KDB_CMD_GO (-1001) #define KDB_CMD_CPU (-1002) @@ -93,17 +70,6 @@ */ #define KDB_MAXBPT 16 -/* Maximum number of arguments to a function */ -#define KDB_MAXARGS 16 - -typedef enum { - KDB_REPEAT_NONE = 0, /* Do not repeat this command */ - KDB_REPEAT_NO_ARGS, /* Repeat the command without arguments */ - KDB_REPEAT_WITH_ARGS, /* Repeat the command including its arguments */ -} kdb_repeat_t; - -typedef int (*kdb_func_t)(int, const char **); - /* Symbol table format returned by kallsyms. */ typedef struct __ksymtab { unsigned long value; /* Address of symbol */ @@ -123,11 +89,6 @@ extern int kallsyms_symbol_next(char *prefix_name, int flag); extern int kallsyms_symbol_complete(char *prefix_name, int max_len); /* Exported Symbols for kernel loadable modules to use. */ -extern int kdb_register(char *, kdb_func_t, char *, char *, short); -extern int kdb_register_repeat(char *, kdb_func_t, char *, char *, - short, kdb_repeat_t); -extern int kdb_unregister(char *); - extern int kdb_getarea_size(void *, unsigned long, size_t); extern int kdb_putarea_size(unsigned long, void *, size_t); -- cgit v1.2.3 From e3bda3ac33d3bf3e5a4049e2cabe82d3caaffc26 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Mon, 11 Oct 2010 10:20:14 -0500 Subject: kdb,ftdump: Remove reference to internal kdb include Now that include/linux/kdb.h properly exports all the functions required to dynamically add a kdb shell command, the reference to the private kdb header can be removed. Signed-off-by: Jason Wessel --- kernel/trace/trace_kdb.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 7b8ecd751d93..3c5c5dfea0b3 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -13,7 +13,6 @@ #include #include -#include "../debug/kdb/kdb_private.h" #include "trace.h" #include "trace_output.h" -- cgit v1.2.3 From 75d14edee5689716b55afe467acfc13206a31f95 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Mon, 11 Oct 2010 10:20:14 -0500 Subject: kdb: Fix oops in kdb_unregister Nothing should try to use kdb_commands directly as sometimes it is null. Instead, use the for_each_kdbcmd() iterator. This particular problem dates back to the initial kdb merge (2.6.35), but at that point nothing was dynamically unregistering commands from the kdb shell. Signed-off-by: Jason Wessel --- kernel/debug/kdb/kdb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 5448990a299e..4226f32517d1 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2826,7 +2826,7 @@ int kdb_unregister(char *cmd) /* * find the command. */ - for (i = 0, kp = kdb_commands; i < kdb_max_commands; i++, kp++) { + for_each_kdbcmd(kp, i) { if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) { kp->cmd_name = NULL; return 0; -- cgit v1.2.3 From 91b152aa85bbcf076e269565394c31964f940371 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Mon, 23 Aug 2010 09:20:14 -0500 Subject: kdb,kgdb: fix sparse fixups Fix the following sparse warnings: kdb_main.c:328:5: warning: symbol 'kdbgetu64arg' was not declared. Should it be static? kgdboc.c:246:12: warning: symbol 'kgdboc_early_init' was not declared. Should it be static? kgdb.c:652:26: warning: incorrect type in argument 1 (different address spaces) kgdb.c:652:26: expected void const *ptr kgdb.c:652:26: got struct perf_event *[noderef] *pev The one in kgdb.c required the (void * __force) because of the return code from register_wide_hw_breakpoint looking like: return (void __percpu __force *)ERR_PTR(err); Signed-off-by: Jason Wessel --- arch/x86/kernel/kgdb.c | 2 +- drivers/serial/kgdboc.c | 2 +- include/linux/kdb.h | 8 ++++++++ kernel/debug/kdb/kdb_private.h | 9 +-------- 4 files changed, 11 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 497f97386412..101bf22cf164 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -649,7 +649,7 @@ void kgdb_arch_late(void) if (breakinfo[i].pev) continue; breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL); - if (IS_ERR(breakinfo[i].pev)) { + if (IS_ERR((void * __force)breakinfo[i].pev)) { printk(KERN_ERR "kgdb: Could not allocate hw" "breakpoints\nDisabling the kernel debugger\n"); breakinfo[i].pev = NULL; diff --git a/drivers/serial/kgdboc.c b/drivers/serial/kgdboc.c index 39f9a1adaa75..d4b711c9a416 100644 --- a/drivers/serial/kgdboc.c +++ b/drivers/serial/kgdboc.c @@ -243,7 +243,7 @@ static struct kgdb_io kgdboc_io_ops = { #ifdef CONFIG_KGDB_SERIAL_CONSOLE /* This is only available if kgdboc is a built in for early debugging */ -int __init kgdboc_early_init(char *opt) +static int __init kgdboc_early_init(char *opt) { /* save the first character of the config string because the * init routine can destroy it. diff --git a/include/linux/kdb.h b/include/linux/kdb.h index deda197ced62..aadff7cc2b84 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -139,6 +139,14 @@ int kdb_process_cpu(const struct task_struct *p) /* kdb access to register set for stack dumping */ extern struct pt_regs *kdb_current_regs; +#ifdef CONFIG_KALLSYMS +extern const char *kdb_walk_kallsyms(loff_t *pos); +#else /* ! CONFIG_KALLSYMS */ +static inline const char *kdb_walk_kallsyms(loff_t *pos) +{ + return NULL; +} +#endif /* ! CONFIG_KALLSYMS */ /* Dynamic kdb shell command registration */ extern int kdb_register(char *, kdb_func_t, char *, char *, short); diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 1921e6e4c0bc..35d69ed1dfb5 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -105,6 +105,7 @@ extern int kdb_getword(unsigned long *, unsigned long, size_t); extern int kdb_putword(unsigned long, unsigned long, size_t); extern int kdbgetularg(const char *, unsigned long *); +extern int kdbgetu64arg(const char *, u64 *); extern char *kdbgetenv(const char *); extern int kdbgetaddrarg(int, const char **, int*, unsigned long *, long *, char **); @@ -216,14 +217,6 @@ extern void kdb_ps1(const struct task_struct *p); extern void kdb_print_nameval(const char *name, unsigned long val); extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info); extern void kdb_meminfo_proc_show(void); -#ifdef CONFIG_KALLSYMS -extern const char *kdb_walk_kallsyms(loff_t *pos); -#else /* ! CONFIG_KALLSYMS */ -static inline const char *kdb_walk_kallsyms(loff_t *pos) -{ - return NULL; -} -#endif /* ! CONFIG_KALLSYMS */ extern char *kdb_getstr(char *, size_t, char *); /* Defines for kdb_symbol_print */ -- cgit v1.2.3 From c1bb9a9c1911036549c5cdfb23f32d7d20ffdc5a Mon Sep 17 00:00:00 2001 From: Dongdong Deng Date: Mon, 13 Sep 2010 06:58:00 -0500 Subject: debug_core: disable hw_breakpoints on all cores in kgdb_cpu_enter() The slave cpus do not have the hw breakpoints disabled upon entry to the debug_core and as a result could cause unrecoverable recursive faults on badly placed breakpoints, or get out of sync with the arch specific hw breakpoint operations. This patch addresses the problem by invoking kgdb_disable_hw_debug() earlier in kgdb_enter_cpu for each cpu that enters the debug core. The hw breakpoint dis/enable flow should be: master_debug_cpu slave_debug_cpu \ / kgdb_cpu_enter | kgdb_disable_hw_debug --> uninstall pre-enabled hw_breakpoint | do add/rm dis/enable operates to hw_breakpoints on master_debug_cpu.. | correct_hw_break --> correct/install the enabled hw_breakpoint | leave_kgdb Signed-off-by: Dongdong Deng Signed-off-by: Jason Wessel --- kernel/debug/debug_core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 5a3b04d20497..bb9497724808 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -485,6 +485,9 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs) int error; int i, cpu; int trace_on = 0; + + kgdb_disable_hw_debug(ks->linux_regs); + acquirelock: /* * Interrupts will be restored by the 'trap return' code, except when @@ -569,8 +572,6 @@ return_normal: if (dbg_io_ops->pre_exception) dbg_io_ops->pre_exception(); - kgdb_disable_hw_debug(ks->linux_regs); - /* * Get the passive CPU lock which will hold all the non-primary * CPU in a spin state while the debugger is active @@ -661,6 +662,8 @@ kgdb_restore: else kgdb_sstep_pid = 0; } + if (arch_kgdb_ops.correct_hw_break) + arch_kgdb_ops.correct_hw_break(); if (trace_on) tracing_on(); /* Free kgdb_active */ -- cgit v1.2.3 From dfee3a7b92208b30f77876068aece9ea571270c2 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Fri, 21 May 2010 08:46:00 -0500 Subject: debug_core: refactor locking for master/slave cpus For quite some time there have been problems with memory barriers and various races with NMI on multi processor systems using the kernel debugger. The algorithm for entering the kernel debug core and resuming kernel execution was racy and had several known edge case problems with attempting to debug something on a heavily loaded system using breakpoints that are hit repeatedly and quickly. The prior "locking" design entry worked as follows: * The atomic counter kgdb_active was used with atomic exchange in order to elect a master cpu out of all the cpus that may have taken a debug exception. * The master cpu increments all elements of passive_cpu_wait[]. * The master cpu issues the round up cpus message. * Each "slave cpu" that enters the debug core increments its own element in cpu_in_kgdb[]. * Each "slave cpu" spins on passive_cpu_wait[] until it becomes 0. * The master cpu debugs the system. The new scheme removes the two arrays of atomic counters and replaces them with 2 single counters. One counter is used to count the number of cpus waiting to become a master cpu (because one or more hit an exception). The second counter is use to indicate how many cpus have entered as slave cpus. The new entry logic works as follows: * One or more cpus enters via kgdb_handle_exception() and increments the masters_in_kgdb. Each cpu attempts to get the spin lock called dbg_master_lock. * The master cpu sets kgdb_active to the current cpu. * The master cpu takes the spinlock dbg_slave_lock. * The master cpu asks to round up all the other cpus. * Each slave cpu that is not already in kgdb_handle_exception() will enter and increment slaves_in_kgdb. Each slave will now spin try_locking on dbg_slave_lock. * The master cpu waits for the sum of masters_in_kgdb and slaves_in_kgdb to be equal to the sum of the online cpus. * The master cpu debugs the system. In the new design the kgdb_active can only be changed while holding dbg_master_lock. Stress testing has not turned up any further entry/exit races that existed in the prior locking design. The prior locking design suffered from atomic variables not being truly atomic (in the capacity as used by kgdb) along with memory barrier races. Signed-off-by: Jason Wessel Acked-by: Dongdong Deng --- kernel/debug/debug_core.c | 105 ++++++++++++++++++++++++---------------------- kernel/debug/debug_core.h | 1 + 2 files changed, 56 insertions(+), 50 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index bb9497724808..26dbdc37d219 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -110,13 +110,15 @@ static struct kgdb_bkpt kgdb_break[KGDB_MAX_BREAKPOINTS] = { */ atomic_t kgdb_active = ATOMIC_INIT(-1); EXPORT_SYMBOL_GPL(kgdb_active); +static DEFINE_RAW_SPINLOCK(dbg_master_lock); +static DEFINE_RAW_SPINLOCK(dbg_slave_lock); /* * We use NR_CPUs not PERCPU, in case kgdb is used to debug early * bootup code (which might not have percpu set up yet): */ -static atomic_t passive_cpu_wait[NR_CPUS]; -static atomic_t cpu_in_kgdb[NR_CPUS]; +static atomic_t masters_in_kgdb; +static atomic_t slaves_in_kgdb; static atomic_t kgdb_break_tasklet_var; atomic_t kgdb_setting_breakpoint; @@ -478,14 +480,23 @@ static void dbg_touch_watchdogs(void) rcu_cpu_stall_reset(); } -static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs) +static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, + int exception_state) { unsigned long flags; int sstep_tries = 100; int error; - int i, cpu; + int cpu; int trace_on = 0; + int online_cpus = num_online_cpus(); + kgdb_info[ks->cpu].enter_kgdb++; + kgdb_info[ks->cpu].exception_state |= exception_state; + + if (exception_state == DCPU_WANT_MASTER) + atomic_inc(&masters_in_kgdb); + else + atomic_inc(&slaves_in_kgdb); kgdb_disable_hw_debug(ks->linux_regs); acquirelock: @@ -500,14 +511,15 @@ acquirelock: kgdb_info[cpu].task = current; kgdb_info[cpu].ret_state = 0; kgdb_info[cpu].irq_depth = hardirq_count() >> HARDIRQ_SHIFT; - /* - * Make sure the above info reaches the primary CPU before - * our cpu_in_kgdb[] flag setting does: - */ - atomic_inc(&cpu_in_kgdb[cpu]); - if (exception_level == 1) + /* Make sure the above info reaches the primary CPU */ + smp_mb(); + + if (exception_level == 1) { + if (raw_spin_trylock(&dbg_master_lock)) + atomic_xchg(&kgdb_active, cpu); goto cpu_master_loop; + } /* * CPU will loop if it is a slave or request to become a kgdb @@ -519,10 +531,12 @@ cpu_loop: kgdb_info[cpu].exception_state &= ~DCPU_NEXT_MASTER; goto cpu_master_loop; } else if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) { - if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu) + if (raw_spin_trylock(&dbg_master_lock)) { + atomic_xchg(&kgdb_active, cpu); break; + } } else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) { - if (!atomic_read(&passive_cpu_wait[cpu])) + if (!raw_spin_is_locked(&dbg_slave_lock)) goto return_normal; } else { return_normal: @@ -533,7 +547,11 @@ return_normal: arch_kgdb_ops.correct_hw_break(); if (trace_on) tracing_on(); - atomic_dec(&cpu_in_kgdb[cpu]); + kgdb_info[cpu].exception_state &= + ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE); + kgdb_info[cpu].enter_kgdb--; + smp_mb__before_atomic_dec(); + atomic_dec(&slaves_in_kgdb); dbg_touch_watchdogs(); local_irq_restore(flags); return 0; @@ -551,6 +569,7 @@ return_normal: (kgdb_info[cpu].task && kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) { atomic_set(&kgdb_active, -1); + raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); @@ -576,10 +595,8 @@ return_normal: * Get the passive CPU lock which will hold all the non-primary * CPU in a spin state while the debugger is active */ - if (!kgdb_single_step) { - for (i = 0; i < NR_CPUS; i++) - atomic_inc(&passive_cpu_wait[i]); - } + if (!kgdb_single_step) + raw_spin_lock(&dbg_slave_lock); #ifdef CONFIG_SMP /* Signal the other CPUs to enter kgdb_wait() */ @@ -590,10 +607,9 @@ return_normal: /* * Wait for the other CPUs to be notified and be waiting for us: */ - for_each_online_cpu(i) { - while (kgdb_do_roundup && !atomic_read(&cpu_in_kgdb[i])) - cpu_relax(); - } + while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) + + atomic_read(&slaves_in_kgdb)) != online_cpus) + cpu_relax(); /* * At this point the primary processor is completely @@ -634,24 +650,11 @@ cpu_master_loop: if (dbg_io_ops->post_exception) dbg_io_ops->post_exception(); - atomic_dec(&cpu_in_kgdb[ks->cpu]); - if (!kgdb_single_step) { - for (i = NR_CPUS-1; i >= 0; i--) - atomic_dec(&passive_cpu_wait[i]); - /* - * Wait till all the CPUs have quit from the debugger, - * but allow a CPU that hit an exception and is - * waiting to become the master to remain in the debug - * core. - */ - for_each_online_cpu(i) { - while (kgdb_do_roundup && - atomic_read(&cpu_in_kgdb[i]) && - !(kgdb_info[i].exception_state & - DCPU_WANT_MASTER)) - cpu_relax(); - } + raw_spin_unlock(&dbg_slave_lock); + /* Wait till all the CPUs have quit from the debugger. */ + while (kgdb_do_roundup && atomic_read(&slaves_in_kgdb)) + cpu_relax(); } kgdb_restore: @@ -666,8 +669,15 @@ kgdb_restore: arch_kgdb_ops.correct_hw_break(); if (trace_on) tracing_on(); + + kgdb_info[cpu].exception_state &= + ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE); + kgdb_info[cpu].enter_kgdb--; + smp_mb__before_atomic_dec(); + atomic_dec(&masters_in_kgdb); /* Free kgdb_active */ atomic_set(&kgdb_active, -1); + raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); @@ -686,7 +696,6 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) { struct kgdb_state kgdb_var; struct kgdb_state *ks = &kgdb_var; - int ret; ks->cpu = raw_smp_processor_id(); ks->ex_vector = evector; @@ -697,11 +706,10 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) if (kgdb_reenter_check(ks)) return 0; /* Ouch, double exception ! */ - kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER; - ret = kgdb_cpu_enter(ks, regs); - kgdb_info[ks->cpu].exception_state &= ~(DCPU_WANT_MASTER | - DCPU_IS_SLAVE); - return ret; + if (kgdb_info[ks->cpu].enter_kgdb != 0) + return 0; + + return kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER); } int kgdb_nmicallback(int cpu, void *regs) @@ -714,12 +722,9 @@ int kgdb_nmicallback(int cpu, void *regs) ks->cpu = cpu; ks->linux_regs = regs; - if (!atomic_read(&cpu_in_kgdb[cpu]) && - atomic_read(&kgdb_active) != -1 && - atomic_read(&kgdb_active) != cpu) { - kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE; - kgdb_cpu_enter(ks, regs); - kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE; + if (kgdb_info[ks->cpu].enter_kgdb == 0 && + raw_spin_is_locked(&dbg_master_lock)) { + kgdb_cpu_enter(ks, regs, DCPU_IS_SLAVE); return 0; } #endif diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h index c5d753d80f67..3494c28a7e7a 100644 --- a/kernel/debug/debug_core.h +++ b/kernel/debug/debug_core.h @@ -40,6 +40,7 @@ struct debuggerinfo_struct { int exception_state; int ret_state; int irq_depth; + int enter_kgdb; }; extern struct debuggerinfo_struct kgdb_info[]; -- cgit v1.2.3 From 495363d380b4f4745bd8677912688654afc44020 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Fri, 21 May 2010 08:46:00 -0500 Subject: kdb,debug_core: adjust master cpu switch logic against new debug_core locking The kdb shell needs to enforce switching back to the original CPU that took the exception before restoring normal kernel execution. Resuming from a different CPU than what took the original exception will cause problems with spin locks that are freed from the a different processor than had taken the lock. The special logic in dbg_cpu_switch() can go away entirely with because the state of what cpus want to be masters or slaves will remain unchanged between entry and exit of the debug_core exception context. Signed-off-by: Jason Wessel --- kernel/debug/debug_core.c | 16 ++-------------- kernel/debug/kdb/kdb_debugger.c | 3 +-- kernel/debug/kdb/kdb_main.c | 12 ++++++------ 3 files changed, 9 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 26dbdc37d219..fec596da9bd0 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -460,19 +460,6 @@ static int kgdb_reenter_check(struct kgdb_state *ks) return 1; } -static void dbg_cpu_switch(int cpu, int next_cpu) -{ - /* Mark the cpu we are switching away from as a slave when it - * holds the kgdb_active token. This must be done so that the - * that all the cpus wait in for the debug core will not enter - * again as the master. */ - if (cpu == atomic_read(&kgdb_active)) { - kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE; - kgdb_info[cpu].exception_state &= ~DCPU_WANT_MASTER; - } - kgdb_info[next_cpu].exception_state |= DCPU_NEXT_MASTER; -} - static void dbg_touch_watchdogs(void) { touch_softlockup_watchdog_sync(); @@ -638,7 +625,8 @@ cpu_master_loop: if (error == DBG_PASS_EVENT) { dbg_kdb_mode = !dbg_kdb_mode; } else if (error == DBG_SWITCH_CPU_EVENT) { - dbg_cpu_switch(cpu, dbg_switch_cpu); + kgdb_info[dbg_switch_cpu].exception_state |= + DCPU_NEXT_MASTER; goto cpu_loop; } else { kgdb_info[cpu].ret_state = error; diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c index bf6e8270e957..dd0b1b7dd02c 100644 --- a/kernel/debug/kdb/kdb_debugger.c +++ b/kernel/debug/kdb/kdb_debugger.c @@ -86,7 +86,7 @@ int kdb_stub(struct kgdb_state *ks) } /* Set initial kdb state variables */ KDB_STATE_CLEAR(KGDB_TRANS); - kdb_initial_cpu = ks->cpu; + kdb_initial_cpu = atomic_read(&kgdb_active); kdb_current_task = kgdb_info[ks->cpu].task; kdb_current_regs = kgdb_info[ks->cpu].debuggerinfo; /* Remove any breakpoints as needed by kdb and clear single step */ @@ -105,7 +105,6 @@ int kdb_stub(struct kgdb_state *ks) ks->pass_exception = 1; KDB_FLAG_SET(CATASTROPHIC); } - kdb_initial_cpu = ks->cpu; if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) { KDB_STATE_CLEAR(SSBPT); KDB_STATE_CLEAR(DOING_SS); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 4226f32517d1..d7bda21a106b 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1749,13 +1749,13 @@ static int kdb_go(int argc, const char **argv) int nextarg; long offset; + if (raw_smp_processor_id() != kdb_initial_cpu) { + kdb_printf("go must execute on the entry cpu, " + "please use \"cpu %d\" and then execute go\n", + kdb_initial_cpu); + return KDB_BADCPUNUM; + } if (argc == 1) { - if (raw_smp_processor_id() != kdb_initial_cpu) { - kdb_printf("go
must be issued from the " - "initial cpu, do cpu %d first\n", - kdb_initial_cpu); - return KDB_ARGCOUNT; - } nextarg = 1; diag = kdbgetaddrarg(argc, argv, &nextarg, &addr, &offset, NULL); -- cgit v1.2.3 From 5260562754c0aa4b95eebb1f851eaccce7286365 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Oct 2010 23:41:11 +0100 Subject: MN10300: Fix the PERCPU() alignment to allow for workqueues In the MN10300 arch, we occasionally see an assertion being tripped in alloc_cwqs() at the following line: /* just in case, make sure it's actually aligned */ ---> BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); return wq->cpu_wq.v ? 0 : -ENOMEM; The values are: wa->cpu_wq.v => 0x902776e0 align => 0x100 and align is calculated by the following: const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS, __alignof__(unsigned long long)); This is because the pointer in question (wq->cpu_wq.v) loses some of its lower bits to control flags, and so the object it points to must be sufficiently aligned to avoid the need to use those bits for pointing to things. Currently, 4 control bits and 4 colour bits are used in normal circumstances, plus a debugging bit if debugging is set. This requires the cpu_workqueue_struct struct to be at least 256 bytes aligned (or 512 bytes aligned with debugging). PERCPU() alignment on MN13000, however, is only 32 bytes as set in vmlinux.lds.S. So we set this to PAGE_SIZE (4096) to match most other arches and stick a comment in alloc_cwqs() for anyone else who triggers the assertion. Reported-by: Akira Takeuchi Signed-off-by: David Howells Acked-by: Mark Salter Cc: Tejun Heo Signed-off-by: Linus Torvalds --- arch/mn10300/kernel/vmlinux.lds.S | 2 +- kernel/workqueue.c | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S index 10549dcfb610..febbeee7f2f5 100644 --- a/arch/mn10300/kernel/vmlinux.lds.S +++ b/arch/mn10300/kernel/vmlinux.lds.S @@ -70,7 +70,7 @@ SECTIONS .exit.text : { EXIT_TEXT; } .exit.data : { EXIT_DATA; } - PERCPU(32) + PERCPU(PAGE_SIZE) . = ALIGN(PAGE_SIZE); __init_end = .; /* freed after init ends here */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 30acdb74cc23..e5ff2cbaadc2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2791,7 +2791,9 @@ static int alloc_cwqs(struct workqueue_struct *wq) } } - /* just in case, make sure it's actually aligned */ + /* just in case, make sure it's actually aligned + * - this is affected by PERCPU() alignment in vmlinux.lds.S + */ BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); return wq->cpu_wq.v ? 0 : -ENOMEM; } -- cgit v1.2.3 From 7e360c38abe2c70eae3ba5a8a17f17671d8b77c5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Oct 2010 09:32:55 +0200 Subject: fs: allow for more than 2^31 files Andrew, Could you please review this patch, you probably are the right guy to take it, because it crosses fs and net trees. Note : /proc/sys/fs/file-nr is a read-only file, so this patch doesnt depend on previous patch (sysctl: fix min/max handling in __do_proc_doulongvec_minmax()) Thanks ! [PATCH V4] fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt Signed-off-by: Eric Dumazet Acked-by: David Miller Reviewed-by: Robin Holt Tested-by: Robin Holt Signed-off-by: Al Viro --- fs/file_table.c | 17 +++++++---------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 6 +++--- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-) (limited to 'kernel') diff --git a/fs/file_table.c b/fs/file_table.c index a04bdd81c11c..c3dee381f1b4 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -60,7 +60,7 @@ static inline void file_free(struct file *f) /* * Return the total number of open files in the system */ -static int get_nr_files(void) +static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } @@ -68,7 +68,7 @@ static int get_nr_files(void) /* * Return the maximum number of open files in the system */ -int get_max_files(void) +unsigned long get_max_files(void) { return files_stat.max_files; } @@ -82,7 +82,7 @@ int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(ctl_table *table, int write, @@ -105,7 +105,7 @@ int proc_nr_files(ctl_table *table, int write, struct file *get_empty_filp(void) { const struct cred *cred = current_cred(); - static int old_max; + static long old_max; struct file * f; /* @@ -140,8 +140,7 @@ struct file *get_empty_filp(void) over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { - printk(KERN_INFO "VFS: file-max limit %d reached\n", - get_max_files()); + pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } goto fail; @@ -487,7 +486,7 @@ retry: void __init files_init(unsigned long mempages) { - int n; + unsigned long n; filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); @@ -498,9 +497,7 @@ void __init files_init(unsigned long mempages) */ n = (mempages * (PAGE_SIZE / 1024)) / 10; - files_stat.max_files = n; - if (files_stat.max_files < NR_FILE) - files_stat.max_files = NR_FILE; + files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); lg_lock_init(files_lglock); percpu_counter_init(&nr_files, 0); diff --git a/include/linux/fs.h b/include/linux/fs.h index 0a5d83633884..0cd6821013a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -34,9 +34,9 @@ /* And dynamically-tunable limits and defaults: */ struct files_stat_struct { - int nr_files; /* read only */ - int nr_free_files; /* read only */ - int max_files; /* tunable */ + unsigned long nr_files; /* read only */ + unsigned long nr_free_files; /* read only */ + unsigned long max_files; /* tunable */ }; struct inodes_stat_t { @@ -400,7 +400,7 @@ extern void __init inode_init_early(void); extern void __init files_init(unsigned long); extern struct files_stat_struct files_stat; -extern int get_max_files(void); +extern unsigned long get_max_files(void); extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3a45c224770f..694b140852c2 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1352,16 +1352,16 @@ static struct ctl_table fs_table[] = { { .procname = "file-nr", .data = &files_stat, - .maxlen = 3*sizeof(int), + .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, - .maxlen = sizeof(int), + .maxlen = sizeof(files_stat.max_files), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "nr_open", diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0ebc777a6660..3c95304a0817 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,7 +117,7 @@ static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; static DEFINE_SPINLOCK(unix_table_lock); -static atomic_t unix_nr_socks = ATOMIC_INIT(0); +static atomic_long_t unix_nr_socks; #define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE]) @@ -360,13 +360,13 @@ static void unix_sock_destructor(struct sock *sk) if (u->addr) unix_release_addr(u->addr); - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); #ifdef UNIX_REFCNT_DEBUG - printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk, - atomic_read(&unix_nr_socks)); + printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk, + atomic_long_read(&unix_nr_socks)); #endif } @@ -606,8 +606,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) struct sock *sk = NULL; struct unix_sock *u; - atomic_inc(&unix_nr_socks); - if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) + atomic_long_inc(&unix_nr_socks); + if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) goto out; sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto); @@ -632,7 +632,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) unix_insert_socket(unix_sockets_unbound, sk); out: if (sk == NULL) - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); else { local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); -- cgit v1.2.3 From cffbc8aa334f55c9ed42d25202eb3ebf3a97c195 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 23 Oct 2010 05:03:02 -0400 Subject: fs: Convert nr_inodes and nr_unused to per-cpu counters The number of inodes allocated does not need to be tied to the addition or removal of an inode to/from a list. If we are not tied to a list lock, we could update the counters when inodes are initialised or destroyed, but to do that we need to convert the counters to be per-cpu (i.e. independent of a lock). This means that we have the freedom to change the list/locking implementation without needing to care about the counters. Based on a patch originally from Eric Dumazet. [AV: cleaned up a bit, fixed build breakage on weird configs Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/fs-writeback.c | 5 ++--- fs/inode.c | 64 ++++++++++++++++++++++++++++++++++++++---------------- fs/internal.h | 1 + include/linux/fs.h | 3 ++- kernel/sysctl.c | 4 ++-- 5 files changed, 52 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 39f44f2e709a..f04d04af84f2 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -723,7 +723,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) wb->last_old_flush = jiffies; nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS) + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); + get_nr_dirty_inodes(); if (nr_pages) { struct wb_writeback_work work = { @@ -1090,8 +1090,7 @@ void writeback_inodes_sb(struct super_block *sb) WARN_ON(!rwsem_is_locked(&sb->s_umount)); - work.nr_pages = nr_dirty + nr_unstable + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); + work.nr_pages = nr_dirty + nr_unstable + get_nr_dirty_inodes(); bdi_queue_work(sb->s_bdi, &work); wait_for_completion(&done); diff --git a/fs/inode.c b/fs/inode.c index 4440cf1034ec..0d5aeccbdd90 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -103,8 +103,41 @@ static DECLARE_RWSEM(iprune_sem); */ struct inodes_stat_t inodes_stat; +static struct percpu_counter nr_inodes __cacheline_aligned_in_smp; +static struct percpu_counter nr_inodes_unused __cacheline_aligned_in_smp; + static struct kmem_cache *inode_cachep __read_mostly; +static inline int get_nr_inodes(void) +{ + return percpu_counter_sum_positive(&nr_inodes); +} + +static inline int get_nr_inodes_unused(void) +{ + return percpu_counter_sum_positive(&nr_inodes_unused); +} + +int get_nr_dirty_inodes(void) +{ + int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); + return nr_dirty > 0 ? nr_dirty : 0; + +} + +/* + * Handle nr_inode sysctl + */ +#ifdef CONFIG_SYSCTL +int proc_nr_inodes(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + inodes_stat.nr_inodes = get_nr_inodes(); + inodes_stat.nr_unused = get_nr_inodes_unused(); + return proc_dointvec(table, write, buffer, lenp, ppos); +} +#endif + static void wake_up_inode(struct inode *inode) { /* @@ -192,6 +225,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif + percpu_counter_inc(&nr_inodes); + return 0; out: return -ENOMEM; @@ -232,6 +267,7 @@ void __destroy_inode(struct inode *inode) if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED) posix_acl_release(inode->i_default_acl); #endif + percpu_counter_dec(&nr_inodes); } EXPORT_SYMBOL(__destroy_inode); @@ -286,7 +322,7 @@ void __iget(struct inode *inode) if (!(inode->i_state & (I_DIRTY|I_SYNC))) list_move(&inode->i_list, &inode_in_use); - inodes_stat.nr_unused--; + percpu_counter_dec(&nr_inodes_unused); } void end_writeback(struct inode *inode) @@ -327,8 +363,6 @@ static void evict(struct inode *inode) */ static void dispose_list(struct list_head *head) { - int nr_disposed = 0; - while (!list_empty(head)) { struct inode *inode; @@ -344,11 +378,7 @@ static void dispose_list(struct list_head *head) wake_up_inode(inode); destroy_inode(inode); - nr_disposed++; } - spin_lock(&inode_lock); - inodes_stat.nr_inodes -= nr_disposed; - spin_unlock(&inode_lock); } /* @@ -357,7 +387,7 @@ static void dispose_list(struct list_head *head) static int invalidate_list(struct list_head *head, struct list_head *dispose) { struct list_head *next; - int busy = 0, count = 0; + int busy = 0; next = head->next; for (;;) { @@ -383,13 +413,11 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose) list_move(&inode->i_list, dispose); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - count++; + percpu_counter_dec(&nr_inodes_unused); continue; } busy = 1; } - /* only unused inodes may be cached with i_count zero */ - inodes_stat.nr_unused -= count; return busy; } @@ -447,7 +475,6 @@ static int can_unuse(struct inode *inode) static void prune_icache(int nr_to_scan) { LIST_HEAD(freeable); - int nr_pruned = 0; int nr_scanned; unsigned long reap = 0; @@ -483,9 +510,8 @@ static void prune_icache(int nr_to_scan) list_move(&inode->i_list, &freeable); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - nr_pruned++; + percpu_counter_dec(&nr_inodes_unused); } - inodes_stat.nr_unused -= nr_pruned; if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else @@ -517,7 +543,7 @@ static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) return -1; prune_icache(nr); } - return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; + return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure; } static struct shrinker icache_shrinker = { @@ -594,7 +620,6 @@ static inline void __inode_add_to_lists(struct super_block *sb, struct hlist_head *head, struct inode *inode) { - inodes_stat.nr_inodes++; list_add(&inode->i_list, &inode_in_use); list_add(&inode->i_sb_list, &sb->s_inodes); if (head) @@ -1214,7 +1239,7 @@ static void iput_final(struct inode *inode) if (!drop) { if (!(inode->i_state & (I_DIRTY|I_SYNC))) list_move(&inode->i_list, &inode_unused); - inodes_stat.nr_unused++; + percpu_counter_inc(&nr_inodes_unused); if (sb->s_flags & MS_ACTIVE) { spin_unlock(&inode_lock); return; @@ -1226,14 +1251,13 @@ static void iput_final(struct inode *inode) spin_lock(&inode_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; - inodes_stat.nr_unused--; + percpu_counter_dec(&nr_inodes_unused); hlist_del_init(&inode->i_hash); } list_del_init(&inode->i_list); list_del_init(&inode->i_sb_list); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - inodes_stat.nr_inodes--; spin_unlock(&inode_lock); evict(inode); spin_lock(&inode_lock); @@ -1502,6 +1526,8 @@ void __init inode_init(void) SLAB_MEM_SPREAD), init_once); register_shrinker(&icache_shrinker); + percpu_counter_init(&nr_inodes, 0); + percpu_counter_init(&nr_inodes_unused, 0); /* Hash may have been set up in inode_init_early */ if (!hashdist) diff --git a/fs/internal.h b/fs/internal.h index f6dce46d80dc..4cc67eb6ed56 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -105,4 +105,5 @@ extern void release_open_intent(struct nameidata *); /* * inode.c */ +extern int get_nr_dirty_inodes(void); extern int invalidate_inodes(struct super_block *); diff --git a/include/linux/fs.h b/include/linux/fs.h index 78043da85e1f..a3937a8ee95e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2486,7 +2486,8 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); - +int proc_nr_inodes(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 694b140852c2..99a510cbfbb3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1340,14 +1340,14 @@ static struct ctl_table fs_table[] = { .data = &inodes_stat, .maxlen = 2*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_inodes, }, { .procname = "file-nr", -- cgit v1.2.3 From 7de9c6ee3ecffd99e1628e81a5ea5468f7581a1f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Oct 2010 11:11:40 -0400 Subject: new helper: ihold() Clones an existing reference to inode; caller must already hold one. Signed-off-by: Al Viro --- fs/9p/vfs_inode.c | 5 +++-- fs/affs/inode.c | 2 +- fs/afs/dir.c | 2 +- fs/aio.c | 5 ++--- fs/anon_inodes.c | 5 ++--- fs/bfs/dir.c | 2 +- fs/block_dev.c | 8 ++++---- fs/btrfs/inode.c | 2 +- fs/coda/dir.c | 2 +- fs/exofs/namei.c | 2 +- fs/ext2/namei.c | 2 +- fs/ext3/namei.c | 2 +- fs/ext4/namei.c | 2 +- fs/gfs2/ops_inode.c | 2 +- fs/hfsplus/dir.c | 2 +- fs/inode.c | 9 +++++++++ fs/jffs2/dir.c | 4 ++-- fs/jfs/jfs_txnmgr.c | 2 +- fs/jfs/namei.c | 2 +- fs/libfs.c | 2 +- fs/logfs/dir.c | 2 +- fs/minix/namei.c | 2 +- fs/namei.c | 2 +- fs/nfs/dir.c | 2 +- fs/nfs/getroot.c | 3 +-- fs/nilfs2/namei.c | 2 +- fs/ntfs/super.c | 4 ++-- fs/ocfs2/namei.c | 2 +- fs/reiserfs/namei.c | 2 +- fs/sysv/namei.c | 2 +- fs/ubifs/dir.c | 2 +- fs/udf/namei.c | 2 +- fs/ufs/namei.c | 2 +- fs/xfs/linux-2.6/xfs_iops.c | 2 +- fs/xfs/xfs_inode.h | 2 +- include/linux/fs.h | 1 + ipc/mqueue.c | 2 +- kernel/futex.c | 2 +- mm/shmem.c | 2 +- net/socket.c | 2 +- 40 files changed, 57 insertions(+), 49 deletions(-) (limited to 'kernel') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 9e670d527646..ef5905f7c8a3 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1789,9 +1789,10 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, kfree(st); } else { /* Caching disabled. No need to get upto date stat info. - * This dentry will be released immediately. So, just i_count++ + * This dentry will be released immediately. So, just hold the + * inode */ - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); } dentry->d_op = old_dentry->d_op; diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 3a0fdec175ba..5d828903ac69 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -388,7 +388,7 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3 affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain)); mark_buffer_dirty_inode(inode_bh, inode); inode->i_nlink = 2; - atomic_inc(&inode->i_count); + ihold(inode); } affs_fix_checksum(sb, bh); mark_buffer_dirty_inode(bh, inode); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 0d38c09bd55e..5439e1bc9a86 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1045,7 +1045,7 @@ static int afs_link(struct dentry *from, struct inode *dir, if (ret < 0) goto link_error; - atomic_inc(&vnode->vfs_inode.i_count); + ihold(&vnode->vfs_inode); d_instantiate(dentry, &vnode->vfs_inode); key_put(key); _leave(" = 0"); diff --git a/fs/aio.c b/fs/aio.c index 9e319a04780e..8c8f6c5b6d79 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1553,10 +1553,9 @@ static void aio_batch_add(struct address_space *mapping, * * When we're called, we always have a reference * on the file, so we must always have a reference - * on the inode, so igrab must always just - * bump the count and move on. + * on the inode, so ihold() is safe here. */ - atomic_inc(&mapping->host->i_count); + ihold(mapping->host); abe->mapping = mapping; hlist_add_head(&abe->list, &batch_hash[bucket]); return; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index e4b75d6eda83..9c8e87b0361f 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -111,10 +111,9 @@ struct file *anon_inode_getfile(const char *name, path.mnt = mntget(anon_inode_mnt); /* * We know the anon_inode inode count is always greater than zero, - * so we can avoid doing an igrab() and we can use an open-coded - * atomic_inc(). + * so ihold() is safe. */ - atomic_inc(&anon_inode_inode->i_count); + ihold(anon_inode_inode); path.dentry->d_op = &anon_inodefs_dentry_operations; d_instantiate(path.dentry, anon_inode_inode); diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index d967e052b779..685ecff3ab31 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -176,7 +176,7 @@ static int bfs_link(struct dentry *old, struct inode *dir, inc_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(new, inode); mutex_unlock(&info->bfs_lock); return 0; diff --git a/fs/block_dev.c b/fs/block_dev.c index b737451e2e9d..81972eb34b39 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -550,7 +550,7 @@ EXPORT_SYMBOL(bdget); */ struct block_device *bdgrab(struct block_device *bdev) { - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); return bdev; } @@ -580,7 +580,7 @@ static struct block_device *bd_acquire(struct inode *inode) spin_lock(&bdev_lock); bdev = inode->i_bdev; if (bdev) { - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); spin_unlock(&bdev_lock); return bdev; } @@ -591,12 +591,12 @@ static struct block_device *bd_acquire(struct inode *inode) spin_lock(&bdev_lock); if (!inode->i_bdev) { /* - * We take an additional bd_inode->i_count for inode, + * We take an additional reference to bd_inode, * and it's released in clear_inode() of inode. * So, we can access it via ->i_mapping always * without igrab(). */ - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); inode->i_bdev = bdev; inode->i_mapping = bdev->bd_inode->i_mapping; list_add(&inode->i_devices, &bdev->bd_inodes); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f6f2a0da2695..64f99cf69ce0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4758,7 +4758,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, } btrfs_set_trans_block_group(trans, dir); - atomic_inc(&inode->i_count); + ihold(inode); err = btrfs_add_nondir(trans, dentry, inode, 1, index); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 96fbeab77f2f..5d8b35539601 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -276,7 +276,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, } coda_dir_update_mtime(dir_inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(de, inode); inc_nlink(inode); return 0; diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index b7dd0c236863..264e95d02830 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -153,7 +153,7 @@ static int exofs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return exofs_add_nondir(dentry, inode); } diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 71efb0e9a3f2..f8aecd2e3297 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -206,7 +206,7 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext2_add_link(dentry, inode); if (!err) { diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 2b35ddb70d65..bce9dce639b8 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -2260,7 +2260,7 @@ retry: inode->i_ctime = CURRENT_TIME_SEC; inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext3_add_entry(handle, dentry, inode); if (!err) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 314c0d3b3fa9..bd39885b5998 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2312,7 +2312,7 @@ retry: inode->i_ctime = ext4_current_time(inode); ext4_inc_count(handle, inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext4_add_entry(handle, dentry, inode); if (!err) { diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 48a274f1674c..12cbea7502c2 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -255,7 +255,7 @@ out_parent: gfs2_holder_uninit(ghs); gfs2_holder_uninit(ghs + 1); if (!error) { - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); mark_inode_dirty(inode); } diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index d236d85ec9d7..e318bbc0daf6 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -286,7 +286,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir, inc_nlink(inode); hfsplus_instantiate(dst_dentry, inode, cnid); - atomic_inc(&inode->i_count); + ihold(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); sbi->file_count++; diff --git a/fs/inode.c b/fs/inode.c index 430d70f2abe7..05ea293d5f32 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -320,6 +320,15 @@ void __iget(struct inode *inode) atomic_inc(&inode->i_count); } +/* + * get additional reference to inode; caller must already hold one. + */ +void ihold(struct inode *inode) +{ + WARN_ON(atomic_inc_return(&inode->i_count) < 2); +} +EXPORT_SYMBOL(ihold); + static void inode_lru_list_add(struct inode *inode) { if (list_empty(&inode->i_list)) { diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index ed78a3cf3cb0..79121aa5858b 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -289,7 +289,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de mutex_unlock(&f->sem); d_instantiate(dentry, old_dentry->d_inode); dir_i->i_mtime = dir_i->i_ctime = ITIME(now); - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); } return ret; } @@ -864,7 +864,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, printk(KERN_NOTICE "jffs2_rename(): Link succeeded, unlink failed (err %d). You now have a hard link\n", ret); /* Might as well let the VFS know */ d_instantiate(new_dentry, old_dentry->d_inode); - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); return ret; } diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index d945ea76b445..9466957ec841 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1279,7 +1279,7 @@ int txCommit(tid_t tid, /* transaction identifier */ * lazy commit thread finishes processing */ if (tblk->xflag & COMMIT_DELETE) { - atomic_inc(&tblk->u.ip->i_count); + ihold(tblk->u.ip); /* * Avoid a rare deadlock * diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index a9cf8e8675be..231ca4af9bce 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -839,7 +839,7 @@ static int jfs_link(struct dentry *old_dentry, ip->i_ctime = CURRENT_TIME; dir->i_ctime = dir->i_mtime = CURRENT_TIME; mark_inode_dirty(dir); - atomic_inc(&ip->i_count); + ihold(ip); iplist[0] = ip; iplist[1] = dir; diff --git a/fs/libfs.c b/fs/libfs.c index 2dbf4877d7ef..304a5132ca27 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -255,7 +255,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index 1eb4e89e045b..409dfd65e9a1 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -569,7 +569,7 @@ static int logfs_link(struct dentry *old_dentry, struct inode *dir, return -EMLINK; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - atomic_inc(&inode->i_count); + ihold(inode); inode->i_nlink++; mark_inode_dirty_sync(inode); diff --git a/fs/minix/namei.c b/fs/minix/namei.c index f3f3578393a4..c0d35a3accef 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -101,7 +101,7 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return add_nondir(dentry, inode); } diff --git a/fs/namei.c b/fs/namei.c index f1ef97dbc6c4..f7dbc06857ab 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2285,7 +2285,7 @@ static long do_unlinkat(int dfd, const char __user *pathname) goto slashes; inode = dentry->d_inode; if (inode) - atomic_inc(&inode->i_count); + ihold(inode); error = mnt_want_write(nd.path.mnt); if (error) goto exit2; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e257172d438c..0fac7fea18ef 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1580,7 +1580,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) d_drop(dentry); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { - atomic_inc(&inode->i_count); + ihold(inode); d_add(dentry, inode); } return error; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index a70e446e1605..ac7b814ce162 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -54,8 +54,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i iput(inode); return -ENOMEM; } - /* Circumvent igrab(): we know the inode is not being freed */ - atomic_inc(&inode->i_count); + ihold(inode); /* * Ensure that this dentry is invisible to d_find_alias(). * Otherwise, it may be spliced into the tree by diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 185d1607cb00..6e9557ecf161 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -207,7 +207,7 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = nilfs_add_nondir(dentry, inode); if (!err) diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index d4dec2d32117..d3fbe5730bfc 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2911,8 +2911,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) goto unl_upcase_iput_tmp_ino_err_out_now; } if ((sb->s_root = d_alloc_root(vol->root_ino))) { - /* We increment i_count simulating an ntfs_iget(). */ - atomic_inc(&vol->root_ino->i_count); + /* We grab a reference, simulating an ntfs_iget(). */ + ihold(vol->root_ino); ntfs_debug("Exiting, status successful."); /* Release the default upcase if it has no users. */ mutex_lock(&ntfs_lock); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index e7bde21149ae..ff5744e1e36f 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -742,7 +742,7 @@ static int ocfs2_link(struct dentry *old_dentry, goto out_commit; } - atomic_inc(&inode->i_count); + ihold(inode); dentry->d_op = &ocfs2_dentry_ops; d_instantiate(dentry, inode); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index ee78d4a0086a..ba5f51ec3458 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1156,7 +1156,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME_SEC; reiserfs_update_sd(&th, inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); reiserfs_write_unlock(dir->i_sb); diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index 33e047b59b8d..11e7f7d11cd0 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -126,7 +126,7 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return add_nondir(dentry, inode); } diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 87ebcce72213..14f64b689d7f 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -550,7 +550,7 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, lock_2_inodes(dir, inode); inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); inode->i_ctime = ubifs_current_time(inode); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index bf5fc674193c..6d8dc02baebb 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1101,7 +1101,7 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, inc_nlink(inode); inode->i_ctime = current_fs_time(inode->i_sb); mark_inode_dirty(inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); unlock_kernel(); diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index b056f02b1fb3..12f39b9e4437 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -180,7 +180,7 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); error = ufs_add_nondir(dentry, inode); unlock_kernel(); diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index 71d83c93621c..96107efc0c61 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -317,7 +317,7 @@ xfs_vn_link( if (unlikely(error)) return -error; - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); return 0; } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index fac52290de90..fb2ca2e4cdc9 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -500,7 +500,7 @@ void xfs_mark_inode_dirty_sync(xfs_inode_t *); #define IHOLD(ip) \ do { \ ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \ - atomic_inc(&(VFS_I(ip)->i_count)); \ + ihold(VFS_I(ip)); \ trace_xfs_ihold(ip, _THIS_IP_); \ } while (0) diff --git a/include/linux/fs.h b/include/linux/fs.h index d43e8b6685a2..bd6ae6c71fc8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2171,6 +2171,7 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); +extern void ihold(struct inode * inode); extern void iput(struct inode *); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index e1e7b9635f5d..80b35ffca25d 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -769,7 +769,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) inode = dentry->d_inode; if (inode) - atomic_inc(&inode->i_count); + ihold(inode); err = mnt_want_write(ipc_ns->mq_mnt); if (err) goto out_err; diff --git a/kernel/futex.c b/kernel/futex.c index a118bf160e0b..6c683b37f2ce 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -169,7 +169,7 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - atomic_inc(&key->shared.inode->i_count); + ihold(key->shared.inode); break; case FUT_OFF_MMSHARED: atomic_inc(&key->private.mm->mm_count); diff --git a/mm/shmem.c b/mm/shmem.c index 27a58120dbd5..d4e2852526e6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1903,7 +1903,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; inc_nlink(inode); - atomic_inc(&inode->i_count); /* New dentry reference */ + ihold(inode); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); out: diff --git a/net/socket.c b/net/socket.c index abf3e2561521..d223725f99e5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -377,7 +377,7 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags) &socket_file_ops); if (unlikely(!file)) { /* drop dentry, keep inode */ - atomic_inc(&path.dentry->d_inode->i_count); + ihold(path.dentry->d_inode); path_put(&path); put_unused_fd(fd); return -ENFILE; -- cgit v1.2.3 From 85fe4025c616a7c0ed07bc2fc8c5371b07f3888c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 Oct 2010 11:19:54 -0400 Subject: fs: do not assign default i_ino in new_inode Instead of always assigning an increasing inode number in new_inode move the call to assign it into those callers that actually need it. For now callers that need it is estimated conservatively, that is the call is added to all filesystems that do not assign an i_ino by themselves. For a few more filesystems we can avoid assigning any inode number given that they aren't user visible, and for others it could be done lazily when an inode number is actually needed, but that's left for later patches. Signed-off-by: Christoph Hellwig Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- drivers/infiniband/hw/ipath/ipath_fs.c | 1 + drivers/infiniband/hw/qib/qib_fs.c | 1 + drivers/misc/ibmasm/ibmasmfs.c | 1 + drivers/oprofile/oprofilefs.c | 1 + drivers/usb/core/inode.c | 1 + drivers/usb/gadget/f_fs.c | 1 + drivers/usb/gadget/inode.c | 1 + fs/anon_inodes.c | 1 + fs/autofs4/inode.c | 1 + fs/binfmt_misc.c | 1 + fs/configfs/inode.c | 1 + fs/debugfs/inode.c | 1 + fs/ext4/mballoc.c | 1 + fs/freevxfs/vxfs_inode.c | 1 + fs/fuse/control.c | 1 + fs/hugetlbfs/inode.c | 1 + fs/inode.c | 4 ++-- fs/ocfs2/dlmfs/dlmfs.c | 2 ++ fs/pipe.c | 2 ++ fs/proc/base.c | 2 ++ fs/proc/proc_sysctl.c | 2 ++ fs/ramfs/inode.c | 1 + fs/xfs/linux-2.6/xfs_buf.c | 1 + include/linux/fs.h | 1 + ipc/mqueue.c | 1 + kernel/cgroup.c | 1 + mm/shmem.c | 1 + net/socket.c | 1 + net/sunrpc/rpc_pipe.c | 1 + security/inode.c | 1 + security/selinux/selinuxfs.c | 1 + 31 files changed, 36 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index d13e72685dcf..12d5bf76302c 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -57,6 +57,7 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry, goto bail; } + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_private = data; diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index a0e6613e8be6..7e433d75c775 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -58,6 +58,7 @@ static int qibfs_mknod(struct inode *dir, struct dentry *dentry, goto bail; } + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = 0; inode->i_gid = 0; diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index af2497ae5fe3..0a53500636c9 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -146,6 +146,7 @@ static struct inode *ibmasmfs_make_inode(struct super_block *sb, int mode) struct inode *ret = new_inode(sb); if (ret) { + ret->i_ino = get_next_ino(); ret->i_mode = mode; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index 95f711b251ad..449de59bf35b 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -28,6 +28,7 @@ static struct inode *oprofilefs_get_inode(struct super_block *sb, int mode) struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; } diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 095fa5366690..e2f63c0ea09d 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -276,6 +276,7 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index e4f595055208..e093fd8d04d3 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -980,6 +980,7 @@ ffs_sb_make_inode(struct super_block *sb, void *data, if (likely(inode)) { struct timespec current_time = CURRENT_TIME; + inode->i_ino = usbfs_get_inode(); inode->i_mode = perms->mode; inode->i_uid = perms->uid; inode->i_gid = perms->gid; diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index d1d72d946b04..ba145e7fbe03 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -1991,6 +1991,7 @@ gadgetfs_make_inode (struct super_block *sb, struct inode *inode = new_inode (sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = default_uid; inode->i_gid = default_gid; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 9c8e87b0361f..5365527ca43f 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -193,6 +193,7 @@ static struct inode *anon_inode_mkinode(void) if (!inode) return ERR_PTR(-ENOMEM); + inode->i_ino = get_next_ino(); inode->i_fop = &anon_inode_fops; inode->i_mapping->a_ops = &anon_aops; diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 821b2b955dac..ac87e49fa706 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -398,6 +398,7 @@ struct inode *autofs4_get_inode(struct super_block *sb, inode->i_gid = sb->s_root->d_inode->i_gid; } inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_ino = get_next_ino(); if (S_ISDIR(inf->mode)) { inode->i_nlink = 2; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 139fc8083f53..29990f0eee0c 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -495,6 +495,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) struct inode * inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb); diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index cf78d44a8d6a..253476d78ed8 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -135,6 +135,7 @@ struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; inode->i_op = &configfs_inode_operations; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 30a87b3dbcac..a4ed8380e98a 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -40,6 +40,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 19aa0d44d822..42f77b1dc72d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2373,6 +2373,7 @@ static int ext4_mb_init_backend(struct super_block *sb) printk(KERN_ERR "EXT4-fs: can't get new inode\n"); goto err_freesgi; } + sbi->s_buddy_cache->i_ino = get_next_ino(); EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 79d1b4ea13e7..8c04eac5079d 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -260,6 +260,7 @@ vxfs_get_fake_inode(struct super_block *sbp, struct vxfs_inode_info *vip) struct inode *ip = NULL; if ((ip = new_inode(sbp))) { + ip->i_ino = get_next_ino(); vxfs_iinit(ip, vip); ip->i_mapping->a_ops = &vxfs_aops; } diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 7367e177186f..4eba07661e5c 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -222,6 +222,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = fc->user_id; inode->i_gid = fc->group_id; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 113eba3d3c38..8d0607b37266 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -455,6 +455,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode = new_inode(sb); if (inode) { struct hugetlbfs_inode_info *info; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = uid; inode->i_gid = gid; diff --git a/fs/inode.c b/fs/inode.c index 46a3e120b196..2cd2e48f7a20 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -735,7 +735,7 @@ repeat: #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); -static unsigned int get_next_ino(void) +unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; @@ -753,6 +753,7 @@ static unsigned int get_next_ino(void) put_cpu_var(last_ino); return res; } +EXPORT_SYMBOL(get_next_ino); /** * new_inode - obtain an inode @@ -776,7 +777,6 @@ struct inode *new_inode(struct super_block *sb) if (inode) { spin_lock(&inode_lock); __inode_sb_list_add(inode); - inode->i_ino = get_next_ino(); inode->i_state = 0; spin_unlock(&inode_lock); } diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index a7ebd9d42dc8..75e115f1bd73 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -400,6 +400,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { ip = DLMFS_I(inode); + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); @@ -425,6 +426,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/fs/pipe.c b/fs/pipe.c index 37eb1ebeaa90..d2d7566ce68e 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -954,6 +954,8 @@ static struct inode * get_pipe_inode(void) if (!inode) goto fail_inode; + inode->i_ino = get_next_ino(); + pipe = alloc_pipe_info(inode); if (!pipe) goto fail_iput; diff --git a/fs/proc/base.c b/fs/proc/base.c index fb2a5abd4e4f..9883f1e18332 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1603,6 +1603,7 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st /* Common stuff */ ei = PROC_I(inode); + inode->i_ino = get_next_ino(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_op = &proc_def_inode_operations; @@ -2549,6 +2550,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir, /* Initialize the inode */ ei = PROC_I(inode); + inode->i_ino = get_next_ino(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 2fc52552271d..b652cb00906b 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -23,6 +23,8 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, if (!inode) goto out; + inode->i_ino = get_next_ino(); + sysctl_head_get(head); ei = PROC_I(inode); ei->sysctl = head; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index a5ebae70dc6d..67fadb1ad2c1 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -58,6 +58,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, struct inode * inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index ba5312802aa9..63fd2c07cb57 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1580,6 +1580,7 @@ xfs_mapping_buftarg( XFS_BUFTARG_NAME(btp)); return ENOMEM; } + inode->i_ino = get_next_ino(); inode->i_mode = S_IFBLK; inode->i_bdev = bdev; inode->i_rdev = bdev->bd_dev; diff --git a/include/linux/fs.h b/include/linux/fs.h index bd6ae6c71fc8..4a573cf13f51 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2191,6 +2191,7 @@ extern struct inode * iget_locked(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); extern void unlock_new_inode(struct inode *); +extern unsigned int get_next_ino(void); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 80b35ffca25d..3a61ffefe884 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -116,6 +116,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7b69b8d0313d..9270d532ec3c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -777,6 +777,7 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/mm/shmem.c b/mm/shmem.c index d4e2852526e6..f6d350e8adc5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1586,6 +1586,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; diff --git a/net/socket.c b/net/socket.c index d223725f99e5..5cac1c707755 100644 --- a/net/socket.c +++ b/net/socket.c @@ -480,6 +480,7 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); kmemcheck_annotate_bitfield(sock, type); + inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 52f252432144..7df92d237cb8 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -445,6 +445,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode) struct inode *inode = new_inode(sb); if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch(mode & S_IFMT) { diff --git a/security/inode.c b/security/inode.c index 88839866cbcd..cb8f47c66a58 100644 --- a/security/inode.c +++ b/security/inode.c @@ -61,6 +61,7 @@ static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev) struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 87e0556bae70..55a755c1a1bd 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -978,6 +978,7 @@ static struct inode *sel_make_inode(struct super_block *sb, int mode) struct inode *ret = new_inode(sb); if (ret) { + ret->i_ino = get_next_ino(); ret->i_mode = mode; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; } -- cgit v1.2.3 From 312d3ca856d369bb04d0443846b85b4cdde6fa8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 10 Oct 2010 05:36:23 -0400 Subject: fs: use percpu counter for nr_dentry and nr_dentry_unused The nr_dentry stat is a globally touched cacheline and atomic operation twice over the lifetime of a dentry. It is used for the benfit of userspace only. Turn it into a per-cpu counter and always decrement it in d_free instead of doing various batching operations to reduce lock hold times in the callers. Based on an earlier patch from Nick Piggin . Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/dcache.c | 51 ++++++++++++++++++++++++++++++++------------------- include/linux/fs.h | 2 ++ kernel/sysctl.c | 2 +- 3 files changed, 35 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/fs/dcache.c b/fs/dcache.c index 028753951e95..c37a656802b0 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -67,6 +67,19 @@ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; +static struct percpu_counter nr_dentry __cacheline_aligned_in_smp; +static struct percpu_counter nr_dentry_unused __cacheline_aligned_in_smp; + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) +int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + dentry_stat.nr_dentry = percpu_counter_sum_positive(&nr_dentry); + dentry_stat.nr_unused = percpu_counter_sum_positive(&nr_dentry_unused); + return proc_dointvec(table, write, buffer, lenp, ppos); +} +#endif + static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); @@ -78,13 +91,14 @@ static void __d_free(struct rcu_head *head) } /* - * no dcache_lock, please. The caller must decrement dentry_stat.nr_dentry - * inside dcache_lock. + * no dcache_lock, please. */ static void d_free(struct dentry *dentry) { + percpu_counter_dec(&nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); + /* if dentry was never inserted into hash, immediate free is OK */ if (hlist_unhashed(&dentry->d_hash)) __d_free(&dentry->d_u.d_rcu); @@ -125,14 +139,14 @@ static void dentry_lru_add(struct dentry *dentry) { list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; + percpu_counter_inc(&nr_dentry_unused); } static void dentry_lru_add_tail(struct dentry *dentry) { list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; + percpu_counter_inc(&nr_dentry_unused); } static void dentry_lru_del(struct dentry *dentry) @@ -140,7 +154,7 @@ static void dentry_lru_del(struct dentry *dentry) if (!list_empty(&dentry->d_lru)) { list_del(&dentry->d_lru); dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; + percpu_counter_dec(&nr_dentry_unused); } } @@ -149,7 +163,7 @@ static void dentry_lru_del_init(struct dentry *dentry) if (likely(!list_empty(&dentry->d_lru))) { list_del_init(&dentry->d_lru); dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; + percpu_counter_dec(&nr_dentry_unused); } } @@ -168,7 +182,6 @@ static struct dentry *d_kill(struct dentry *dentry) struct dentry *parent; list_del(&dentry->d_u.d_child); - dentry_stat.nr_dentry--; /* For d_free, below */ /*drops the locks, at that point nobody can reach this dentry */ dentry_iput(dentry); if (IS_ROOT(dentry)) @@ -314,7 +327,6 @@ int d_invalidate(struct dentry * dentry) EXPORT_SYMBOL(d_invalidate); /* This should be called _only_ with dcache_lock held */ - static inline struct dentry * __dget_locked(struct dentry *dentry) { atomic_inc(&dentry->d_count); @@ -534,7 +546,7 @@ static void prune_dcache(int count) { struct super_block *sb, *p = NULL; int w_count; - int unused = dentry_stat.nr_unused; + int unused = percpu_counter_sum_positive(&nr_dentry_unused); int prune_ratio; int pruned; @@ -699,20 +711,13 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) * otherwise we ascend to the parent and move to the * next sibling if there is one */ if (!parent) - goto out; - + return; dentry = parent; - } while (list_empty(&dentry->d_subdirs)); dentry = list_entry(dentry->d_subdirs.next, struct dentry, d_u.d_child); } -out: - /* several dentries were freed, need to correct nr_dentry */ - spin_lock(&dcache_lock); - dentry_stat.nr_dentry -= detached; - spin_unlock(&dcache_lock); } /* @@ -896,12 +901,16 @@ EXPORT_SYMBOL(shrink_dcache_parent); */ static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { + int nr_unused; + if (nr) { if (!(gfp_mask & __GFP_FS)) return -1; prune_dcache(nr); } - return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; + + nr_unused = percpu_counter_sum_positive(&nr_dentry_unused); + return (nr_unused / 100) * sysctl_vfs_cache_pressure; } static struct shrinker dcache_shrinker = { @@ -968,9 +977,10 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) spin_lock(&dcache_lock); if (parent) list_add(&dentry->d_u.d_child, &parent->d_subdirs); - dentry_stat.nr_dentry++; spin_unlock(&dcache_lock); + percpu_counter_inc(&nr_dentry); + return dentry; } EXPORT_SYMBOL(d_alloc); @@ -2417,6 +2427,9 @@ static void __init dcache_init(void) { int loop; + percpu_counter_init(&nr_dentry, 0); + percpu_counter_init(&nr_dentry_unused, 0); + /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature diff --git a/include/linux/fs.h b/include/linux/fs.h index 4a573cf13f51..d58059944801 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2490,6 +2490,8 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +int proc_nr_dentry(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); int proc_nr_inodes(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 99a510cbfbb3..8b77ff5c502c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1377,7 +1377,7 @@ static struct ctl_table fs_table[] = { .data = &dentry_stat, .maxlen = 6*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_dentry, }, { .procname = "overflowuid", -- cgit v1.2.3 From 3d5992d2ac7dc09aed8ab537cba074589f0f0a52 Mon Sep 17 00:00:00 2001 From: Ying Han Date: Tue, 26 Oct 2010 14:21:23 -0700 Subject: oom: add per-mm oom disable count It's pointless to kill a task if another thread sharing its mm cannot be killed to allow future memory freeing. A subsequent patch will prevent kills in such cases, but first it's necessary to have a way to flag a task that shares memory with an OOM_DISABLE task that doesn't incur an additional tasklist scan, which would make select_bad_process() an O(n^2) function. This patch adds an atomic counter to struct mm_struct that follows how many threads attached to it have an oom_score_adj of OOM_SCORE_ADJ_MIN. They cannot be killed by the kernel, so their memory cannot be freed in oom conditions. This only requires task_lock() on the task that we're operating on, it does not require mm->mmap_sem since task_lock() pins the mm and the operation is atomic. [rientjes@google.com: changelog and sys_unshare() code] [rientjes@google.com: protect oom_disable_count with task_lock in fork] [rientjes@google.com: use old_mm for oom_disable_count in exec] Signed-off-by: Ying Han Signed-off-by: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 5 +++++ fs/proc/base.c | 30 ++++++++++++++++++++++++++++++ include/linux/mm_types.h | 2 ++ kernel/exit.c | 3 +++ kernel/fork.c | 15 ++++++++++++++- 5 files changed, 54 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/fs/exec.c b/fs/exec.c index 6d2b6f936858..3aa75b8888a1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include @@ -759,6 +760,10 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + if (old_mm && tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + atomic_dec(&old_mm->oom_disable_count); + atomic_inc(&tsk->mm->oom_disable_count); + } task_unlock(tsk); arch_pick_mmap_layout(mm); if (old_mm) { diff --git a/fs/proc/base.c b/fs/proc/base.c index dc5d5f51f3fe..6e50c8e65513 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1047,6 +1047,21 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, return -EACCES; } + task_lock(task); + if (!task->mm) { + task_unlock(task); + unlock_task_sighand(task, &flags); + put_task_struct(task); + return -EINVAL; + } + + if (oom_adjust != task->signal->oom_adj) { + if (oom_adjust == OOM_DISABLE) + atomic_inc(&task->mm->oom_disable_count); + if (task->signal->oom_adj == OOM_DISABLE) + atomic_dec(&task->mm->oom_disable_count); + } + /* * Warn that /proc/pid/oom_adj is deprecated, see * Documentation/feature-removal-schedule.txt. @@ -1065,6 +1080,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, else task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + task_unlock(task); unlock_task_sighand(task, &flags); put_task_struct(task); @@ -1133,6 +1149,19 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, return -EACCES; } + task_lock(task); + if (!task->mm) { + task_unlock(task); + unlock_task_sighand(task, &flags); + put_task_struct(task); + return -EINVAL; + } + if (oom_score_adj != task->signal->oom_score_adj) { + if (oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_inc(&task->mm->oom_disable_count); + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&task->mm->oom_disable_count); + } task->signal->oom_score_adj = oom_score_adj; /* * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is @@ -1143,6 +1172,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, else task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) / OOM_SCORE_ADJ_MAX; + task_unlock(task); unlock_task_sighand(task, &flags); put_task_struct(task); return count; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cb57d657ce4d..bb7288a782fd 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -310,6 +310,8 @@ struct mm_struct { #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_mm *mmu_notifier_mm; #endif + /* How many tasks sharing this mm are OOM_DISABLE */ + atomic_t oom_disable_count; }; /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ diff --git a/kernel/exit.c b/kernel/exit.c index e2bdf37f9fde..894179a32ec1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -50,6 +50,7 @@ #include #include #include +#include #include #include @@ -687,6 +688,8 @@ static void exit_mm(struct task_struct * tsk) enter_lazy_tlb(mm, current); /* We don't want this task to be frozen prematurely */ clear_freeze_flag(tsk); + if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&mm->oom_disable_count); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); diff --git a/kernel/fork.c b/kernel/fork.c index c445f8cc408d..e87aaaaf5131 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include @@ -488,6 +489,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); + atomic_set(&mm->oom_disable_count, 0); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; @@ -741,6 +743,8 @@ good_mm: /* Initializing for Swap token stuff */ mm->token_priority = 0; mm->last_interval = 0; + if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_inc(&mm->oom_disable_count); tsk->mm = mm; tsk->active_mm = mm; @@ -1299,8 +1303,13 @@ bad_fork_cleanup_io: bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: - if (p->mm) + if (p->mm) { + task_lock(p); + if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&p->mm->oom_disable_count); + task_unlock(p); mmput(p->mm); + } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); @@ -1693,6 +1702,10 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) active_mm = current->active_mm; current->mm = new_mm; current->active_mm = new_mm; + if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + atomic_dec(&mm->oom_disable_count); + atomic_inc(&new_mm->oom_disable_count); + } activate_mm(active_mm, new_mm); new_mm = mm; } -- cgit v1.2.3 From 61ecdb801ef2cd28e32442383106d7837d76deac Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 26 Oct 2010 14:21:47 -0700 Subject: mm: strictly nested kmap_atomic() Ensure kmap_atomic() usage is strictly nested Signed-off-by: Peter Zijlstra Reviewed-by: Rik van Riel Acked-by: Chris Metcalf Cc: David Howells Cc: Hugh Dickins Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Steven Rostedt Cc: Russell King Cc: Ralf Baechle Cc: David Miller Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- crypto/async_tx/async_memcpy.c | 2 +- crypto/blkcipher.c | 2 +- drivers/block/loop.c | 4 ++-- include/linux/highmem.h | 4 ++-- kernel/power/snapshot.c | 4 ++-- 5 files changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index 0ec1fb69d4ea..518c22bd9562 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -83,8 +83,8 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, memcpy(dest_buf, src_buf, len); - kunmap_atomic(dest_buf, KM_USER0); kunmap_atomic(src_buf, KM_USER1); + kunmap_atomic(dest_buf, KM_USER0); async_tx_sync_epilog(submit); } diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c index 90d26c91f4e9..7a7219266e3c 100644 --- a/crypto/blkcipher.c +++ b/crypto/blkcipher.c @@ -89,9 +89,9 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk, memcpy(walk->dst.virt.addr, walk->page, n); blkcipher_unmap_dst(walk); } else if (!(walk->flags & BLKCIPHER_WALK_PHYS)) { - blkcipher_unmap_src(walk); if (walk->flags & BLKCIPHER_WALK_DIFF) blkcipher_unmap_dst(walk); + blkcipher_unmap_src(walk); } scatterwalk_advance(&walk->in, n); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 6c48b3545f84..450c958b514f 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -101,8 +101,8 @@ static int transfer_none(struct loop_device *lo, int cmd, else memcpy(raw_buf, loop_buf, size); - kunmap_atomic(raw_buf, KM_USER0); kunmap_atomic(loop_buf, KM_USER1); + kunmap_atomic(raw_buf, KM_USER0); cond_resched(); return 0; } @@ -130,8 +130,8 @@ static int transfer_xor(struct loop_device *lo, int cmd, for (i = 0; i < size; i++) *out++ = *in++ ^ key[(i & 511) % keysize]; - kunmap_atomic(raw_buf, KM_USER0); kunmap_atomic(loop_buf, KM_USER1); + kunmap_atomic(raw_buf, KM_USER0); cond_resched(); return 0; } diff --git a/include/linux/highmem.h b/include/linux/highmem.h index e3060ef85b6d..283cd47bb34c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -201,8 +201,8 @@ static inline void copy_user_highpage(struct page *to, struct page *from, vfrom = kmap_atomic(from, KM_USER0); vto = kmap_atomic(to, KM_USER1); copy_user_page(vto, vfrom, vaddr, to); - kunmap_atomic(vfrom, KM_USER0); kunmap_atomic(vto, KM_USER1); + kunmap_atomic(vfrom, KM_USER0); } #endif @@ -214,8 +214,8 @@ static inline void copy_highpage(struct page *to, struct page *from) vfrom = kmap_atomic(from, KM_USER0); vto = kmap_atomic(to, KM_USER1); copy_page(vto, vfrom); - kunmap_atomic(vfrom, KM_USER0); kunmap_atomic(vto, KM_USER1); + kunmap_atomic(vfrom, KM_USER0); } #endif /* _LINUX_HIGHMEM_H */ diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index ac7eb109f196..9e3581f4619a 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -984,8 +984,8 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) src = kmap_atomic(s_page, KM_USER0); dst = kmap_atomic(d_page, KM_USER1); do_copy_page(dst, src); - kunmap_atomic(src, KM_USER0); kunmap_atomic(dst, KM_USER1); + kunmap_atomic(src, KM_USER0); } else { if (PageHighMem(d_page)) { /* Page pointed to by src may contain some kernel @@ -2273,8 +2273,8 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf) memcpy(buf, kaddr1, PAGE_SIZE); memcpy(kaddr1, kaddr2, PAGE_SIZE); memcpy(kaddr2, buf, PAGE_SIZE); - kunmap_atomic(kaddr1, KM_USER0); kunmap_atomic(kaddr2, KM_USER1); + kunmap_atomic(kaddr1, KM_USER0); } /** -- cgit v1.2.3 From 3ecb01df3261d3b1f02ccfcf8384e2a255d2a1d0 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 26 Oct 2010 14:22:27 -0700 Subject: use clear_page()/copy_page() in favor of memset()/memcpy() on whole pages After all that's what they are intended for. Signed-off-by: Jan Beulich Cc: Miklos Szeredi Cc: "Eric W. Biederman" Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 2 +- kernel/kexec.c | 2 +- kernel/power/snapshot.c | 14 +++++++------- kernel/power/swap.c | 6 +++--- mm/memory.c | 2 +- 5 files changed, 13 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index cde755cca564..69037118b2c9 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -811,7 +811,7 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep, if (page && zeroing && count < PAGE_SIZE) { void *mapaddr = kmap_atomic(page, KM_USER1); - memset(mapaddr, 0, PAGE_SIZE); + clear_page(mapaddr); kunmap_atomic(mapaddr, KM_USER1); } while (count) { diff --git a/kernel/kexec.c b/kernel/kexec.c index c0613f7d6730..b55045bc7563 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -816,7 +816,7 @@ static int kimage_load_normal_segment(struct kimage *image, ptr = kmap(page); /* Start with a clear page */ - memset(ptr, 0, PAGE_SIZE); + clear_page(ptr); ptr += maddr & ~PAGE_MASK; mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK); if (mchunk > mbytes) diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 9e3581f4619a..0dac75ea4456 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -993,7 +993,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) */ safe_copy_page(buffer, s_page); dst = kmap_atomic(d_page, KM_USER0); - memcpy(dst, buffer, PAGE_SIZE); + copy_page(dst, buffer); kunmap_atomic(dst, KM_USER0); } else { safe_copy_page(page_address(d_page), s_page); @@ -1687,7 +1687,7 @@ int snapshot_read_next(struct snapshot_handle *handle) memory_bm_position_reset(&orig_bm); memory_bm_position_reset(©_bm); } else if (handle->cur <= nr_meta_pages) { - memset(buffer, 0, PAGE_SIZE); + clear_page(buffer); pack_pfns(buffer, &orig_bm); } else { struct page *page; @@ -1701,7 +1701,7 @@ int snapshot_read_next(struct snapshot_handle *handle) void *kaddr; kaddr = kmap_atomic(page, KM_USER0); - memcpy(buffer, kaddr, PAGE_SIZE); + copy_page(buffer, kaddr); kunmap_atomic(kaddr, KM_USER0); handle->buffer = buffer; } else { @@ -1984,7 +1984,7 @@ static void copy_last_highmem_page(void) void *dst; dst = kmap_atomic(last_highmem_page, KM_USER0); - memcpy(dst, buffer, PAGE_SIZE); + copy_page(dst, buffer); kunmap_atomic(dst, KM_USER0); last_highmem_page = NULL; } @@ -2270,9 +2270,9 @@ swap_two_pages_data(struct page *p1, struct page *p2, void *buf) kaddr1 = kmap_atomic(p1, KM_USER0); kaddr2 = kmap_atomic(p2, KM_USER1); - memcpy(buf, kaddr1, PAGE_SIZE); - memcpy(kaddr1, kaddr2, PAGE_SIZE); - memcpy(kaddr2, buf, PAGE_SIZE); + copy_page(buf, kaddr1); + copy_page(kaddr1, kaddr2); + copy_page(kaddr2, buf); kunmap_atomic(kaddr2, KM_USER1); kunmap_atomic(kaddr1, KM_USER0); } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 916eaa790399..a0e4a86ccf94 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -251,7 +251,7 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain) if (bio_chain) { src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); if (src) { - memcpy(src, buf, PAGE_SIZE); + copy_page(src, buf); } else { WARN_ON_ONCE(1); bio_chain = NULL; /* Go synchronous */ @@ -325,7 +325,7 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf, error = write_page(handle->cur, handle->cur_swap, NULL); if (error) goto out; - memset(handle->cur, 0, PAGE_SIZE); + clear_page(handle->cur); handle->cur_swap = offset; handle->k = 0; } @@ -910,7 +910,7 @@ int swsusp_check(void) hib_resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); - memset(swsusp_header, 0, PAGE_SIZE); + clear_page(swsusp_header); error = hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL); if (error) diff --git a/mm/memory.c b/mm/memory.c index 861f7982dd54..02e48aa0ed13 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2080,7 +2080,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) - memset(kaddr, 0, PAGE_SIZE); + clear_page(kaddr); kunmap_atomic(kaddr, KM_USER0); flush_dcache_page(dst); } else -- cgit v1.2.3 From ca1cab37d91cbe8a8333732540d43cabb54cfa85 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 26 Oct 2010 14:22:34 -0700 Subject: workqueues: s/ON_STACK/ONSTACK/ Silly though it is, completions and wait_queue_heads use foo_ONSTACK (COMPLETION_INITIALIZER_ONSTACK, DECLARE_COMPLETION_ONSTACK, __WAIT_QUEUE_HEAD_INIT_ONSTACK and DECLARE_WAIT_QUEUE_HEAD_ONSTACK) so I guess workqueues should do the same thing. s/INIT_WORK_ON_STACK/INIT_WORK_ONSTACK/ s/INIT_DELAYED_WORK_ON_STACK/INIT_DELAYED_WORK_ONSTACK/ Cc: Peter Zijlstra Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/hpet.c | 2 +- arch/x86/kernel/smpboot.c | 2 +- drivers/md/dm-snap-persistent.c | 2 +- include/linux/workqueue.h | 6 +++--- kernel/workqueue.c | 2 +- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index aff0b3c27509..ae03cab4352e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -713,7 +713,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, switch (action & 0xf) { case CPU_ONLINE: - INIT_DELAYED_WORK_ON_STACK(&work.work, hpet_work); + INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work); init_completion(&work.complete); /* FIXME: add schedule_work_on() */ schedule_delayed_work_on(cpu, &work.work, 0); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6af118511b4a..6c7faecd9e4a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -747,7 +747,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; - INIT_WORK_ON_STACK(&c_idle.work, do_fork_idle); + INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); alternatives_smp_switch(1); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 0b61792a2780..2129cdb115dc 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -254,7 +254,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, * Issue the synchronous I/O from a different thread * to avoid generic_make_request recursion. */ - INIT_WORK_ON_STACK(&req.work, do_metadata); + INIT_WORK_ONSTACK(&req.work, do_metadata); queue_work(ps->metadata_wq, &req.work); flush_workqueue(ps->metadata_wq); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 070bb7a88936..0c0771f06bfa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -190,7 +190,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } __INIT_WORK((_work), (_func), 0); \ } while (0) -#define INIT_WORK_ON_STACK(_work, _func) \ +#define INIT_WORK_ONSTACK(_work, _func) \ do { \ __INIT_WORK((_work), (_func), 1); \ } while (0) @@ -201,9 +201,9 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } init_timer(&(_work)->timer); \ } while (0) -#define INIT_DELAYED_WORK_ON_STACK(_work, _func) \ +#define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ do { \ - INIT_WORK_ON_STACK(&(_work)->work, (_func)); \ + INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ init_timer_on_stack(&(_work)->timer); \ } while (0) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e5ff2cbaadc2..90db1bd1a978 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2064,7 +2064,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * checks and call back into the fixup functions where we * might deadlock. */ - INIT_WORK_ON_STACK(&barr->work, wq_barrier_func); + INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); -- cgit v1.2.3 From 571428be550fbe37160596995e96ad398873fcbd Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Oct 2010 14:22:43 -0700 Subject: kernel/user.c: add lock release annotation on free_user() free_user() releases uidhash_lock but was missing annotation. Add it. This removes following sparse warnings: include/linux/spinlock.h:339:9: warning: context imbalance in 'free_user' - unexpected unlock kernel/user.c:120:6: warning: context imbalance in 'free_uid' - wrong count at exit Signed-off-by: Namhyung Kim Cc: Ingo Molnar Cc: Dhaval Giani Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/user.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/user.c b/kernel/user.c index 7e72614b736d..2c7d8d5914b1 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -91,6 +91,7 @@ static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) + __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); -- cgit v1.2.3 From 518de9b39e854542de59bfb8b9f61c8f7ecf808b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Oct 2010 14:22:44 -0700 Subject: fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt Signed-off-by: Eric Dumazet Acked-by: David Miller Reviewed-by: Robin Holt Tested-by: Robin Holt Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/file_table.c | 17 +++++++---------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 6 +++--- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-) (limited to 'kernel') diff --git a/fs/file_table.c b/fs/file_table.c index a04bdd81c11c..c3dee381f1b4 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -60,7 +60,7 @@ static inline void file_free(struct file *f) /* * Return the total number of open files in the system */ -static int get_nr_files(void) +static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } @@ -68,7 +68,7 @@ static int get_nr_files(void) /* * Return the maximum number of open files in the system */ -int get_max_files(void) +unsigned long get_max_files(void) { return files_stat.max_files; } @@ -82,7 +82,7 @@ int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(ctl_table *table, int write, @@ -105,7 +105,7 @@ int proc_nr_files(ctl_table *table, int write, struct file *get_empty_filp(void) { const struct cred *cred = current_cred(); - static int old_max; + static long old_max; struct file * f; /* @@ -140,8 +140,7 @@ struct file *get_empty_filp(void) over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { - printk(KERN_INFO "VFS: file-max limit %d reached\n", - get_max_files()); + pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } goto fail; @@ -487,7 +486,7 @@ retry: void __init files_init(unsigned long mempages) { - int n; + unsigned long n; filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); @@ -498,9 +497,7 @@ void __init files_init(unsigned long mempages) */ n = (mempages * (PAGE_SIZE / 1024)) / 10; - files_stat.max_files = n; - if (files_stat.max_files < NR_FILE) - files_stat.max_files = NR_FILE; + files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); lg_lock_init(files_lglock); percpu_counter_init(&nr_files, 0); diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f34ff6e5558..b2cdb6bc8287 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -34,9 +34,9 @@ /* And dynamically-tunable limits and defaults: */ struct files_stat_struct { - int nr_files; /* read only */ - int nr_free_files; /* read only */ - int max_files; /* tunable */ + unsigned long nr_files; /* read only */ + unsigned long nr_free_files; /* read only */ + unsigned long max_files; /* tunable */ }; struct inodes_stat_t { @@ -400,7 +400,7 @@ extern void __init inode_init_early(void); extern void __init files_init(unsigned long); extern struct files_stat_struct files_stat; -extern int get_max_files(void); +extern unsigned long get_max_files(void); extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3a45c224770f..694b140852c2 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1352,16 +1352,16 @@ static struct ctl_table fs_table[] = { { .procname = "file-nr", .data = &files_stat, - .maxlen = 3*sizeof(int), + .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, - .maxlen = sizeof(int), + .maxlen = sizeof(files_stat.max_files), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "nr_open", diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0ebc777a6660..3c95304a0817 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,7 +117,7 @@ static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; static DEFINE_SPINLOCK(unix_table_lock); -static atomic_t unix_nr_socks = ATOMIC_INIT(0); +static atomic_long_t unix_nr_socks; #define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE]) @@ -360,13 +360,13 @@ static void unix_sock_destructor(struct sock *sk) if (u->addr) unix_release_addr(u->addr); - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); #ifdef UNIX_REFCNT_DEBUG - printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk, - atomic_read(&unix_nr_socks)); + printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk, + atomic_long_read(&unix_nr_socks)); #endif } @@ -606,8 +606,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) struct sock *sk = NULL; struct unix_sock *u; - atomic_inc(&unix_nr_socks); - if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) + atomic_long_inc(&unix_nr_socks); + if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) goto out; sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto); @@ -632,7 +632,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) unix_insert_socket(unix_sockets_unbound, sk); out: if (sk == NULL) - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); else { local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); -- cgit v1.2.3 From ca51c5a76345b28c6f1b742f9f5f0a6fc9afd9ca Mon Sep 17 00:00:00 2001 From: Rakib Mullick Date: Tue, 26 Oct 2010 14:22:44 -0700 Subject: kernel/stop_machine.c: fix unused variable warning kernel/stop_machine.c: In function `cpu_stopper_thread': kernel/stop_machine.c:265: warning: unused variable `ksym_buf' ksym_buf[] is unused if WARN_ON() is a no-op. Signed-off-by: Rakib Mullick Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/stop_machine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 090c28812ce1..3cb4a9a8ae1c 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -262,7 +262,7 @@ repeat: cpu_stop_fn_t fn = work->fn; void *arg = work->arg; struct cpu_stop_done *done = work->done; - char ksym_buf[KSYM_NAME_LEN]; + char ksym_buf[KSYM_NAME_LEN] __maybe_unused; __set_current_state(TASK_RUNNING); -- cgit v1.2.3 From 4ce6494dbd8909718840bb88d5a699ef6ce5c212 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 26 Oct 2010 14:22:45 -0700 Subject: stop_machine: convert cpu notifier to return encapsulate errno value In commit e6bde73b07edeb703d4c89c1daabc09c303de11f ("cpu-hotplug: return better errno on cpu hotplug failure"), the cpu notifier can return an encapsulated errno value. This converts the cpu notifier to return an encapsulated errno value for stop_machine(). Signed-off-by: Akinobu Mita Cc: Rusty Russell Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/stop_machine.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 3cb4a9a8ae1c..2df820b03beb 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -304,7 +304,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, p = kthread_create(cpu_stopper_thread, stopper, "migration/%d", cpu); if (IS_ERR(p)) - return NOTIFY_BAD; + return notifier_from_errno(PTR_ERR(p)); get_task_struct(p); kthread_bind(p, cpu); sched_set_stop_task(cpu, p); @@ -372,7 +372,7 @@ static int __init cpu_stop_init(void) /* start one for the boot cpu */ err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE, bcpu); - BUG_ON(err == NOTIFY_BAD); + BUG_ON(err != NOTIFY_OK); cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu); register_cpu_notifier(&cpu_stop_cpu_notifier); -- cgit v1.2.3 From 6c095efd82e8f6a98515426a733110f91cf0a709 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Oct 2010 14:22:47 -0700 Subject: printk: fixup declaration of kmsg_reasons Move redundant 'const' after '*' to make pointer itself const Signed-off-by: Namhyung Kim Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/printk.c b/kernel/printk.c index 2531017795f6..d18933a92819 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1511,7 +1511,7 @@ int kmsg_dump_unregister(struct kmsg_dumper *dumper) } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); -static const char const *kmsg_reasons[] = { +static const char * const kmsg_reasons[] = { [KMSG_DUMP_OOPS] = "oops", [KMSG_DUMP_PANIC] = "panic", [KMSG_DUMP_KEXEC] = "kexec", -- cgit v1.2.3 From 8155c02a44a95562e1ae0999360eb31288d7195a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Oct 2010 14:22:47 -0700 Subject: printk: add lock context annotation acquire_console_semaphore_for_printk() releases logbuf_lock but was missing proper annotation. Add it. Signed-off-by: Namhyung Kim Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/printk.c b/kernel/printk.c index d18933a92819..6ff26151f4ff 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -647,6 +647,7 @@ static inline int can_use_console(unsigned int cpu) * released but interrupts still disabled. */ static int acquire_console_semaphore_for_printk(unsigned int cpu) + __releases(&logbuf_lock) { int retval = 0; -- cgit v1.2.3 From 674dff6507d3f9b110219ea125cf5e1213c9acef Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Oct 2010 14:22:48 -0700 Subject: printk: change type of 'boot_delay' to int * get_option() takes its 2nd arg as int * so passing boot_delay to it caused following warnings from sparse: kernel/printk.c:223:27: warning: incorrect type in argument 2 (different signedness) kernel/printk.c:223:27: expected int *pint kernel/printk.c:223:27: got unsigned int static [toplevel] * Since boot_delay can't grow more than 10,000 changing it to 'int *' will not produce any problem. Signed-off-by: Namhyung Kim Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/printk.c b/kernel/printk.c index 6ff26151f4ff..b2ebaee8c377 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -210,7 +210,7 @@ __setup("log_buf_len=", log_buf_len_setup); #ifdef CONFIG_BOOT_PRINTK_DELAY -static unsigned int boot_delay; /* msecs delay after each printk during bootup */ +static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) -- cgit v1.2.3 From f5d87d851d76a390d0fab2f77bd1d563d69ee586 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Oct 2010 14:22:49 -0700 Subject: printk: declare printk_ratelimit_state in ratelimit.h Adding declaration of printk_ratelimit_state in ratelimit.h removes potential build breakage and following sparse warning: kernel/printk.c:1426:1: warning: symbol 'printk_ratelimit_state' was not declared. Should it be static? [akpm@linux-foundation.org: remove unneeded ifdef] Signed-off-by: Namhyung Kim Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ratelimit.h | 2 ++ kernel/sysctl.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 8f69d09a41a5..03ff67b0cdf5 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -36,6 +36,8 @@ static inline void ratelimit_state_init(struct ratelimit_state *rs, rs->begin = 0; } +extern struct ratelimit_state printk_ratelimit_state; + extern int ___ratelimit(struct ratelimit_state *rs, const char *func); #define __ratelimit(state) ___ratelimit(state, __func__) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 694b140852c2..48d9d689498f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -161,8 +161,6 @@ extern int no_unaligned_warning; extern int unaligned_dump_stack; #endif -extern struct ratelimit_state printk_ratelimit_state; - #ifdef CONFIG_PROC_SYSCTL static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From ee2f154a598e96df2ebb01648a7699373bc085c7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 26 Oct 2010 14:17:25 -0700 Subject: docbook: add more wait/wake/completion to device-drivers docbook Add more wait, wake, and completion interfaces to the device-drivers docbook. Fix kernel-doc notation in the added files. Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- Documentation/DocBook/device-drivers.tmpl | 5 +++++ include/linux/completion.h | 10 +++++----- kernel/wait.c | 6 +++--- 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index feca0758391e..22edcbb9ddaf 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -51,7 +51,12 @@ Delaying, scheduling, and timer routines !Iinclude/linux/sched.h !Ekernel/sched.c +!Iinclude/linux/completion.h !Ekernel/timer.c + + Wait queues and Wake events +!Iinclude/linux/wait.h +!Ekernel/wait.c High-resolution timers !Iinclude/linux/ktime.h diff --git a/include/linux/completion.h b/include/linux/completion.h index 51e3145196f6..36d57f74cd01 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -10,7 +10,7 @@ #include -/** +/* * struct completion - structure used to maintain state for a "completion" * * This is the opaque structure used to maintain the state for a "completion". @@ -34,7 +34,7 @@ struct completion { ({ init_completion(&work); work; }) /** - * DECLARE_COMPLETION: - declare and initialize a completion structure + * DECLARE_COMPLETION - declare and initialize a completion structure * @work: identifier for the completion structure * * This macro declares and initializes a completion structure. Generally used @@ -50,7 +50,7 @@ struct completion { * are on the kernel stack: */ /** - * DECLARE_COMPLETION_ONSTACK: - declare and initialize a completion structure + * DECLARE_COMPLETION_ONSTACK - declare and initialize a completion structure * @work: identifier for the completion structure * * This macro declares and initializes a completion structure on the kernel @@ -64,7 +64,7 @@ struct completion { #endif /** - * init_completion: - Initialize a dynamically allocated completion + * init_completion - Initialize a dynamically allocated completion * @x: completion structure that is to be initialized * * This inline function will initialize a dynamically created completion @@ -92,7 +92,7 @@ extern void complete(struct completion *); extern void complete_all(struct completion *); /** - * INIT_COMPLETION: - reinitialize a completion structure + * INIT_COMPLETION - reinitialize a completion structure * @x: completion structure to be reinitialized * * This macro should be used to reinitialize a completion structure so it can diff --git a/kernel/wait.c b/kernel/wait.c index c4bd3d825f35..b0310eb6cc1e 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -92,7 +92,7 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) } EXPORT_SYMBOL(prepare_to_wait_exclusive); -/* +/** * finish_wait - clean up after waiting in a queue * @q: waitqueue waited on * @wait: wait descriptor @@ -127,11 +127,11 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) } EXPORT_SYMBOL(finish_wait); -/* +/** * abort_exclusive_wait - abort exclusive waiting in a queue * @q: waitqueue waited on * @wait: wait descriptor - * @state: runstate of the waiter to be woken + * @mode: runstate of the waiter to be woken * @key: key to identify a wait bit queue or %NULL * * Sets current thread back to running state and removes -- cgit v1.2.3 From abbce906d05ec37289cd0c3b4e35b2db26eab19b Mon Sep 17 00:00:00 2001 From: MichaÅ‚ MirosÅ‚aw Date: Mon, 20 Sep 2010 01:58:08 +0200 Subject: (trivial) Fix compiler warning in kernel/modules.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building with CONFIG_KALLSYMS=n gives following warning: /mnt/src/linux-git/kernel/module.c: In function ‘post_relocation’: /mnt/src/linux-git/kernel/module.c:2534:2: warning: passing argument 2 of ‘add_kallsyms’ discards qualifiers from pointer target type /mnt/src/linux-git/kernel/module.c:2038:13: note: expected ‘struct load_info *’ but argument is of type ‘const struct load_info *’ Signed-off-by: MichaÅ‚ MirosÅ‚aw Signed-off-by: Rusty Russell --- kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 2df46301a7a4..437a74a7524a 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2037,7 +2037,7 @@ static inline void layout_symtab(struct module *mod, struct load_info *info) { } -static void add_kallsyms(struct module *mod, struct load_info *info) +static void add_kallsyms(struct module *mod, const struct load_info *info) { } #endif /* CONFIG_KALLSYMS */ -- cgit v1.2.3 From 3a5f65df5a0fcbaa35e5417c0420d691fee4ac56 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Oct 2010 17:28:36 +0100 Subject: Typedef SMP call function pointer Typedef the pointer to the function to be called by smp_call_function() and friends: typedef void (*smp_call_func_t)(void *info); as it is used in a fair number of places. Signed-off-by: David Howells cc: linux-arch@vger.kernel.org --- include/linux/smp.h | 19 ++++++++++--------- kernel/smp.c | 8 ++++---- 2 files changed, 14 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/include/linux/smp.h b/include/linux/smp.h index cfa2d20e35f1..6dc95cac6b3d 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -13,9 +13,10 @@ extern void cpu_idle(void); +typedef void (*smp_call_func_t)(void *info); struct call_single_data { struct list_head list; - void (*func) (void *info); + smp_call_func_t func; void *info; u16 flags; u16 priv; @@ -24,8 +25,8 @@ struct call_single_data { /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; -int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, - int wait); +int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, + int wait); #ifdef CONFIG_SMP @@ -69,15 +70,15 @@ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ -int smp_call_function(void(*func)(void *info), void *info, int wait); +int smp_call_function(smp_call_func_t func, void *info, int wait); void smp_call_function_many(const struct cpumask *mask, - void (*func)(void *info), void *info, bool wait); + smp_call_func_t func, void *info, bool wait); void __smp_call_function_single(int cpuid, struct call_single_data *data, int wait); int smp_call_function_any(const struct cpumask *mask, - void (*func)(void *info), void *info, int wait); + smp_call_func_t func, void *info, int wait); /* * Generic and arch helpers @@ -94,7 +95,7 @@ void ipi_call_unlock_irq(void); /* * Call a function on all processors */ -int on_each_cpu(void (*func) (void *info), void *info, int wait); +int on_each_cpu(smp_call_func_t func, void *info, int wait); #define MSG_ALL_BUT_SELF 0x8000 /* Assume <32768 CPU's */ #define MSG_ALL 0x8001 @@ -122,7 +123,7 @@ static inline void smp_send_stop(void) { } * These macros fold the SMP functionality into a single CPU system */ #define raw_smp_processor_id() 0 -static inline int up_smp_call_function(void (*func)(void *), void *info) +static inline int up_smp_call_function(smp_call_func_t func, void *info) { return 0; } @@ -143,7 +144,7 @@ static inline void smp_send_reschedule(int cpu) { } static inline void init_call_single_data(void) { } static inline int -smp_call_function_any(const struct cpumask *mask, void (*func)(void *info), +smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { return smp_call_function_single(0, func, info, wait); diff --git a/kernel/smp.c b/kernel/smp.c index ed6aacfcb7ef..12ed8b013e2d 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -267,7 +267,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data); * * Returns 0 on success, else a negative status code. */ -int smp_call_function_single(int cpu, void (*func) (void *info), void *info, +int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { struct call_single_data d = { @@ -336,7 +336,7 @@ EXPORT_SYMBOL(smp_call_function_single); * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, - void (*func)(void *info), void *info, int wait) + smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; @@ -416,7 +416,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *data, * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, - void (*func)(void *), void *info, bool wait) + smp_call_func_t func, void *info, bool wait) { struct call_function_data *data; unsigned long flags; @@ -500,7 +500,7 @@ EXPORT_SYMBOL(smp_call_function_many); * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ -int smp_call_function(void (*func)(void *), void *info, int wait) +int smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); -- cgit v1.2.3 From d5de4ddb1bc430289bede76c0d87cabee93f749a Mon Sep 17 00:00:00 2001 From: Tomasz Buchert Date: Wed, 27 Oct 2010 15:33:32 -0700 Subject: cgroup_freezer: unnecessary test in cgroup_freezing_or_frozen() The root freezer_state is always CGROUP_THAWED so we can remove the special case from the code. The test itself can be handy and is extracted to static function. Signed-off-by: Tomasz Buchert Cc: Matt Helsley Cc: Paul Menage Cc: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup_freezer.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index ce71ed53e88f..321e2a007d25 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -48,20 +48,19 @@ static inline struct freezer *task_freezer(struct task_struct *task) struct freezer, css); } -int cgroup_freezing_or_frozen(struct task_struct *task) +static inline int __cgroup_freezing_or_frozen(struct task_struct *task) { - struct freezer *freezer; - enum freezer_state state; + enum freezer_state state = task_freezer(task)->state; + return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN); +} +int cgroup_freezing_or_frozen(struct task_struct *task) +{ + int result; task_lock(task); - freezer = task_freezer(task); - if (!freezer->css.cgroup->parent) - state = CGROUP_THAWED; /* root cgroup can't be frozen */ - else - state = freezer->state; + result = __cgroup_freezing_or_frozen(task); task_unlock(task); - - return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN); + return result; } /* -- cgit v1.2.3 From 0bdba580ab052a21e3eda2764ed22d9ee962392b Mon Sep 17 00:00:00 2001 From: Tomasz Buchert Date: Wed, 27 Oct 2010 15:33:33 -0700 Subject: cgroup_freezer: fix can_attach() to prohibit moving from/to freezing/frozen cgroups It is possible to move a task from its cgroup even if this group is 'FREEZING'. This results in a nasty bug - the moved task will become frozen OUTSIDE its original cgroup and will remain in a permanent 'D' state. This patch allows to migrate the task only between THAWED cgroups. This behavior was observed and easily reproduced on a single core laptop. Notice that reproducibility depends highly on the machine used. Program and instructions how to reproduce the bug can be fetched from: http://pentium.hopto.org/~thinred/repos/linux-misc/freezer_bug.c Signed-off-by: Tomasz Buchert Cc: Matt Helsley Cc: Paul Menage Cc: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup_freezer.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 321e2a007d25..c287627bed3d 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -173,24 +173,25 @@ static int freezer_can_attach(struct cgroup_subsys *ss, /* * Anything frozen can't move or be moved to/from. - * - * Since orig_freezer->state == FROZEN means that @task has been - * frozen, so it's sufficient to check the latter condition. */ - if (is_task_frozen_enough(task)) + freezer = cgroup_freezer(new_cgroup); + if (freezer->state != CGROUP_THAWED) return -EBUSY; - freezer = cgroup_freezer(new_cgroup); - if (freezer->state == CGROUP_FROZEN) + rcu_read_lock(); + if (__cgroup_freezing_or_frozen(task)) { + rcu_read_unlock(); return -EBUSY; + } + rcu_read_unlock(); if (threadgroup) { struct task_struct *c; rcu_read_lock(); list_for_each_entry_rcu(c, &task->thread_group, thread_group) { - if (is_task_frozen_enough(c)) { + if (__cgroup_freezing_or_frozen(c)) { rcu_read_unlock(); return -EBUSY; } -- cgit v1.2.3 From 2d3cbf8bc852ac1bc3d098186143c5973f87b753 Mon Sep 17 00:00:00 2001 From: Tomasz Buchert Date: Wed, 27 Oct 2010 15:33:34 -0700 Subject: cgroup_freezer: update_freezer_state() does incorrect state transitions There are 4 state transitions possible for a freezer. Only FREEZING -> FROZEN transaction is done lazily. This patch allows update_freezer_state only to perform this transaction and renames the function to update_if_frozen. Moreover is_task_frozen_enough function is removed and its every occurence is replaced with frozen(). Therefore for a group to become FROZEN every task must be frozen. The previous version could trigger a following bug: When cgroup is in the process of freezing (but none of its tasks are frozen yet), update_freezer_state() (called from freezer_read or freezer_write) would incorrectly report that a group is 'THAWED' (because nfrozen = 0), allowing the transaction FREEZING -> THAWED without writing anything to 'freezer.state'. This is incorrect according to the documentation. This could result in a 'THAWED' cgroup with frozen tasks inside. A code to reproduce this bug is available here: http://pentium.hopto.org/~thinred/repos/linux-misc/freezer_bug2.c [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Tomasz Buchert Cc: Matt Helsley Cc: Paul Menage Cc: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup_freezer.c | 38 +++++++++++++++----------------------- 1 file changed, 15 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index c287627bed3d..e7bebb7c6c38 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -153,13 +153,6 @@ static void freezer_destroy(struct cgroup_subsys *ss, kfree(cgroup_freezer(cgroup)); } -/* Task is frozen or will freeze immediately when next it gets woken */ -static bool is_task_frozen_enough(struct task_struct *task) -{ - return frozen(task) || - (task_is_stopped_or_traced(task) && freezing(task)); -} - /* * The call to cgroup_lock() in the freezer.state write method prevents * a write to that file racing against an attach, and hence the @@ -236,31 +229,30 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) /* * caller must hold freezer->lock */ -static void update_freezer_state(struct cgroup *cgroup, +static void update_if_frozen(struct cgroup *cgroup, struct freezer *freezer) { struct cgroup_iter it; struct task_struct *task; unsigned int nfrozen = 0, ntotal = 0; + enum freezer_state old_state = freezer->state; cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { ntotal++; - if (is_task_frozen_enough(task)) + if (frozen(task)) nfrozen++; } - /* - * Transition to FROZEN when no new tasks can be added ensures - * that we never exist in the FROZEN state while there are unfrozen - * tasks. - */ - if (nfrozen == ntotal) - freezer->state = CGROUP_FROZEN; - else if (nfrozen > 0) - freezer->state = CGROUP_FREEZING; - else - freezer->state = CGROUP_THAWED; + if (old_state == CGROUP_THAWED) { + BUG_ON(nfrozen > 0); + } else if (old_state == CGROUP_FREEZING) { + if (nfrozen == ntotal) + freezer->state = CGROUP_FROZEN; + } else { /* old_state == CGROUP_FROZEN */ + BUG_ON(nfrozen != ntotal); + } + cgroup_iter_end(cgroup, &it); } @@ -279,7 +271,7 @@ static int freezer_read(struct cgroup *cgroup, struct cftype *cft, if (state == CGROUP_FREEZING) { /* We change from FREEZING to FROZEN lazily if the cgroup was * only partially frozen when we exitted write. */ - update_freezer_state(cgroup, freezer); + update_if_frozen(cgroup, freezer); state = freezer->state; } spin_unlock_irq(&freezer->lock); @@ -301,7 +293,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) while ((task = cgroup_iter_next(cgroup, &it))) { if (!freeze_task(task, true)) continue; - if (is_task_frozen_enough(task)) + if (frozen(task)) continue; if (!freezing(task) && !freezer_should_skip(task)) num_cant_freeze_now++; @@ -335,7 +327,7 @@ static int freezer_change_state(struct cgroup *cgroup, spin_lock_irq(&freezer->lock); - update_freezer_state(cgroup, freezer); + update_if_frozen(cgroup, freezer); if (goal_state == freezer->state) goto out; -- cgit v1.2.3 From 97978e6d1f2da0073416870410459694fbdbfd9b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 27 Oct 2010 15:33:35 -0700 Subject: cgroup: add clone_children control file The ns_cgroup is a control group interacting with the namespaces. When a new namespace is created, a corresponding cgroup is automatically created too. The cgroup name is the pid of the process who did 'unshare' or the child of 'clone'. This cgroup is tied with the namespace because it prevents a process to escape the control group and use the post_clone callback, so the child cgroup inherits the values of the parent cgroup. Unfortunately, the more we use this cgroup and the more we are facing problems with it: (1) when a process unshares, the cgroup name may conflict with a previous cgroup with the same pid, so unshare or clone return -EEXIST (2) the cgroup creation is out of control because there may have an application creating several namespaces where the system will automatically create several cgroups in his back and let them on the cgroupfs (eg. a vrf based on the network namespace). (3) the mix of (1) and (2) force an administrator to regularly check and clean these cgroups. This patchset removes the ns_cgroup by adding a new flag to the cgroup and the cgroupfs mount option. It enables the copy of the parent cgroup when a child cgroup is created. We can then safely remove the ns_cgroup as this flag brings a compatibility. We have now to manually create and add the task to a cgroup, which is consistent with the cgroup framework. This patch: Sent as an answer to a previous thread around the ns_cgroup. https://lists.linux-foundation.org/pipermail/containers/2009-June/018627.html It adds a control file 'clone_children' for a cgroup. This control file is a boolean specifying if the child cgroup should be a clone of the parent cgroup or not. The default value is 'false'. This flag makes the child cgroup to call the post_clone callback of all the subsystem, if it is available. At present, the cpuset is the only one which had implemented the post_clone callback. The option can be set at mount time by specifying the 'clone_children' mount option. Signed-off-by: Daniel Lezcano Signed-off-by: Serge E. Hallyn Cc: Eric W. Biederman Acked-by: Paul Menage Reviewed-by: Li Zefan Cc: Jamal Hadi Salim Cc: Matt Helsley Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/cgroups.txt | 14 ++++++++++++-- include/linux/cgroup.h | 4 ++++ kernel/cgroup.c | 39 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index b34823ff1646..190018b0c649 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -18,7 +18,8 @@ CONTENTS: 1.2 Why are cgroups needed ? 1.3 How are cgroups implemented ? 1.4 What does notify_on_release do ? - 1.5 How do I use cgroups ? + 1.5 What does clone_children do ? + 1.6 How do I use cgroups ? 2. Usage Examples and Syntax 2.1 Basic Usage 2.2 Attaching processes @@ -293,7 +294,16 @@ notify_on_release in the root cgroup at system boot is disabled value of their parents notify_on_release setting. The default value of a cgroup hierarchy's release_agent path is empty. -1.5 How do I use cgroups ? +1.5 What does clone_children do ? +--------------------------------- + +If the clone_children flag is enabled (1) in a cgroup, then all +cgroups created beneath will call the post_clone callbacks for each +subsystem of the newly created cgroup. Usually when this callback is +implemented for a subsystem, it copies the values of the parent +subsystem, this is the case for the cpuset. + +1.6 How do I use cgroups ? -------------------------- To start a new job that is to be contained within a cgroup, using diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 709dfb901d11..ed4ba111bc8d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -154,6 +154,10 @@ enum { * A thread in rmdir() is wating for this cgroup. */ CGRP_WAIT_ON_RMDIR, + /* + * Clone cgroup values when creating a new child cgroup + */ + CGRP_CLONE_CHILDREN, }; /* which pidlist file are we talking about? */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 9270d532ec3c..4b218a46ddd3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -243,6 +243,11 @@ static int notify_on_release(const struct cgroup *cgrp) return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } +static int clone_children(const struct cgroup *cgrp) +{ + return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); +} + /* * for_each_subsys() allows you to iterate on each subsystem attached to * an active hierarchy @@ -1040,6 +1045,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",noprefix"); if (strlen(root->release_agent_path)) seq_printf(seq, ",release_agent=%s", root->release_agent_path); + if (clone_children(&root->top_cgroup)) + seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_printf(seq, ",name=%s", root->name); mutex_unlock(&cgroup_mutex); @@ -1050,6 +1057,7 @@ struct cgroup_sb_opts { unsigned long subsys_bits; unsigned long flags; char *release_agent; + bool clone_children; char *name; /* User explicitly requested empty subsystem */ bool none; @@ -1097,6 +1105,8 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) opts->none = true; } else if (!strcmp(token, "noprefix")) { set_bit(ROOT_NOPREFIX, &opts->flags); + } else if (!strcmp(token, "clone_children")) { + opts->clone_children = true; } else if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) @@ -1355,6 +1365,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts) strcpy(root->release_agent_path, opts->release_agent); if (opts->name) strcpy(root->name, opts->name); + if (opts->clone_children) + set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags); return root; } @@ -3173,6 +3185,23 @@ fail: return ret; } +static u64 cgroup_clone_children_read(struct cgroup *cgrp, + struct cftype *cft) +{ + return clone_children(cgrp); +} + +static int cgroup_clone_children_write(struct cgroup *cgrp, + struct cftype *cft, + u64 val) +{ + if (val) + set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); + else + clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); + return 0; +} + /* * for the common functions, 'private' gives the type of file */ @@ -3203,6 +3232,11 @@ static struct cftype files[] = { .write_string = cgroup_write_event_control, .mode = S_IWUGO, }, + { + .name = "cgroup.clone_children", + .read_u64 = cgroup_clone_children_read, + .write_u64 = cgroup_clone_children_write, + }, }; static struct cftype cft_release_agent = { @@ -3332,6 +3366,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); + if (clone_children(parent)) + set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); + for_each_subsys(root, ss) { struct cgroup_subsys_state *css = ss->create(ss, cgrp); @@ -3346,6 +3383,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, goto err_destroy; } /* At error, ->destroy() callback has to free assigned ID. */ + if (clone_children(parent) && ss->post_clone) + ss->post_clone(ss, cgrp); } cgroup_lock_hierarchy(root); -- cgit v1.2.3 From 32a8cf235e2f192eb002755076994525cdbaa35a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 27 Oct 2010 15:33:37 -0700 Subject: cgroup: make the mount options parsing more accurate Current behavior: ================= (1) When we mount a cgroup, we can specify the 'all' option which means to enable all the cgroup subsystems. This is the default option when no option is specified. (2) If we want to mount a cgroup with a subset of the supported cgroup subsystems, we have to specify a subsystems name list for the mount option. (3) If we specify another option like 'noprefix' or 'release_agent', the actual code wants the 'all' or a subsystem name option specified also. Not critical but a bit not friendly as we should assume (1) in this case. (4) Logically, the 'all' option is mutually exclusive with a subsystem name, but this is not detected. In other words: succeed : mount -t cgroup -o all,freezer cgroup /cgroup => is it 'all' or 'freezer' ? fails : mount -t cgroup -o noprefix cgroup /cgroup => succeed if we do '-o noprefix,all' The following patches consolidate a bit the mount options check. New behavior: ============= (1) untouched (2) untouched (3) the 'all' option will be by default when specifying other than a subsystem name option (4) raises an error In other words: fails : mount -t cgroup -o all,freezer cgroup /cgroup succeed : mount -t cgroup -o noprefix cgroup /cgroup For the sake of lisibility, the if ... then ... else ... if ... indentation when parsing the options has been changed to: if ... then ... continue fi Signed-off-by: Daniel Lezcano Signed-off-by: Serge E. Hallyn Reviewed-by: Li Zefan Reviewed-by: Paul Menage Cc: Eric W. Biederman Cc: Jamal Hadi Salim Cc: Matt Helsley Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 90 ++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 60 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4b218a46ddd3..3e6517e51fd3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1074,7 +1074,8 @@ struct cgroup_sb_opts { */ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { - char *token, *o = data ?: "all"; + char *token, *o = data; + bool all_ss = false, one_ss = false; unsigned long mask = (unsigned long)-1; int i; bool module_pin_failed = false; @@ -1090,24 +1091,27 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) while ((token = strsep(&o, ",")) != NULL) { if (!*token) return -EINVAL; - if (!strcmp(token, "all")) { - /* Add all non-disabled subsystems */ - opts->subsys_bits = 0; - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - struct cgroup_subsys *ss = subsys[i]; - if (ss == NULL) - continue; - if (!ss->disabled) - opts->subsys_bits |= 1ul << i; - } - } else if (!strcmp(token, "none")) { + if (!strcmp(token, "none")) { /* Explicitly have no subsystems */ opts->none = true; - } else if (!strcmp(token, "noprefix")) { + continue; + } + if (!strcmp(token, "all")) { + /* Mutually exclusive option 'all' + subsystem name */ + if (one_ss) + return -EINVAL; + all_ss = true; + continue; + } + if (!strcmp(token, "noprefix")) { set_bit(ROOT_NOPREFIX, &opts->flags); - } else if (!strcmp(token, "clone_children")) { + continue; + } + if (!strcmp(token, "clone_children")) { opts->clone_children = true; - } else if (!strncmp(token, "release_agent=", 14)) { + continue; + } + if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) return -EINVAL; @@ -1115,7 +1119,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); if (!opts->release_agent) return -ENOMEM; - } else if (!strncmp(token, "name=", 5)) { + continue; + } + if (!strncmp(token, "name=", 5)) { const char *name = token + 5; /* Can't specify an empty name */ if (!strlen(name)) @@ -1137,20 +1143,44 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) GFP_KERNEL); if (!opts->name) return -ENOMEM; - } else { - struct cgroup_subsys *ss; - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - ss = subsys[i]; - if (ss == NULL) - continue; - if (!strcmp(token, ss->name)) { - if (!ss->disabled) - set_bit(i, &opts->subsys_bits); - break; - } - } - if (i == CGROUP_SUBSYS_COUNT) - return -ENOENT; + + continue; + } + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; + if (strcmp(token, ss->name)) + continue; + if (ss->disabled) + continue; + + /* Mutually exclusive option 'all' + subsystem name */ + if (all_ss) + return -EINVAL; + set_bit(i, &opts->subsys_bits); + one_ss = true; + + break; + } + if (i == CGROUP_SUBSYS_COUNT) + return -ENOENT; + } + + /* + * If the 'all' option was specified select all the subsystems, + * otherwise 'all, 'none' and a subsystem name options were not + * specified, let's default to 'all' + */ + if (all_ss || (!all_ss && !one_ss && !opts->none)) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; + if (ss->disabled) + continue; + set_bit(i, &opts->subsys_bits); } } -- cgit v1.2.3 From f4a2589feaef0a9b737a3e582b37ee96695bb25f Mon Sep 17 00:00:00 2001 From: Evgeny Kuznetsov Date: Wed, 27 Oct 2010 15:33:37 -0700 Subject: cgroups: add check for strcpy destination string overflow Function "strcpy" is used without check for maximum allowed source string length and could cause destination string overflow. Check for string length is added before using "strcpy". Function now is return error if source string length is more than a maximum. akpm: presently considered NotABug, but add the check for general future-safeness and robustness. Signed-off-by: Evgeny Kuznetsov Acked-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3e6517e51fd3..5cf366965d0c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1922,6 +1922,8 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft, const char *buffer) { BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + if (strlen(buffer) >= PATH_MAX) + return -EINVAL; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; strcpy(cgrp->root->release_agent_path, buffer); -- cgit v1.2.3 From 45531757b45cae0ce64c5aff08c2534d5a0fa3e7 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 27 Oct 2010 15:33:38 -0700 Subject: cgroup: notify ns_cgroup deprecated The ns_cgroup will be removed very soon. Let's warn, for this version, ns_cgroup is deprecated. Make ns_cgroup and clone_children exclusive. If the clone_children is set and the ns_cgroup is mounted, let's fail with EINVAL when the ns_cgroup subsys is created (a printk will help the user to understand why the creation fails). Update the feature remove schedule file with the deprecated ns_cgroup. Signed-off-by: Daniel Lezcano Acked-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/feature-removal-schedule.txt | 17 +++++++++++++++++ kernel/ns_cgroup.c | 8 ++++++++ 2 files changed, 25 insertions(+) (limited to 'kernel') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index d2af87ba96e1..f3da8c0a3af2 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -526,6 +526,23 @@ Who: FUJITA Tomonori ---------------------------- +What: namespace cgroup (ns_cgroup) +When: 2.6.38 +Why: The ns_cgroup leads to some problems: + * cgroup creation is out-of-control + * cgroup name can conflict when pids are looping + * it is not possible to have a single process handling + a lot of namespaces without falling in a exponential creation time + * we may want to create a namespace without creating a cgroup + + The ns_cgroup is replaced by a compatibility flag 'clone_children', + where a newly created cgroup will copy the parent cgroup values. + The userspace has to manually create a cgroup and add a task to + the 'tasks' file. +Who: Daniel Lezcano + +---------------------------- + What: iwlwifi disable_hw_scan module parameters When: 2.6.40 Why: Hareware scan is the prefer method for iwlwifi devices for diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c index 2a5dfec8efe0..2c98ad94ba0e 100644 --- a/kernel/ns_cgroup.c +++ b/kernel/ns_cgroup.c @@ -85,6 +85,14 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss, return ERR_PTR(-EPERM); if (!cgroup_is_descendant(cgroup, current)) return ERR_PTR(-EPERM); + if (test_bit(CGRP_CLONE_CHILDREN, &cgroup->flags)) { + printk("ns_cgroup can't be created with parent " + "'clone_children' set.\n"); + return ERR_PTR(-EINVAL); + } + + printk_once("ns_cgroup deprecated: consider using the " + "'clone_children' flag without the ns_cgroup.\n"); ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL); if (!ns_cgroup) -- cgit v1.2.3 From c4b5ed250eebf854d40f27b43362c80f115cb57a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 27 Oct 2010 15:33:44 -0700 Subject: ptrace: annotate lock context change on exit_ptrace() exit_ptrace() releases and regrabs tasklist_lock but was missing proper annotation. Add it. Signed-off-by: Namhyung Kim Acked-by: Roland McGrath Cc: Ingo Molnar Cc: Oleg Nesterov Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index f34d798ef4a2..4afd9b86cc0b 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -329,6 +329,8 @@ int ptrace_detach(struct task_struct *child, unsigned int data) * and reacquire the lock. */ void exit_ptrace(struct task_struct *tracer) + __releases(&tasklist_lock) + __acquires(&tasklist_lock) { struct task_struct *p, *n; LIST_HEAD(ptrace_dead); -- cgit v1.2.3 From 4abf986960ecda6a87fc2f795aacf888a2f0127e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 27 Oct 2010 15:33:45 -0700 Subject: ptrace: change signature of sys_ptrace() and friends Since userspace API of ptrace syscall defines @addr and @data as void pointers, it would be more appropriate to define them as unsigned long in kernel. Therefore related functions are changed also. 'unsigned long' is typically used in other places in kernel as an opaque data type and that using this helps cleaning up a lot of warnings from sparse. Suggested-by: Arnd Bergmann Signed-off-by: Namhyung Kim Acked-by: Arnd Bergmann Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 9 ++++++--- include/linux/syscalls.h | 3 ++- kernel/ptrace.c | 16 ++++++++++------ 3 files changed, 18 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4272521e29e9..67a4cd77c352 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -108,7 +108,8 @@ extern int ptrace_attach(struct task_struct *tsk); extern int ptrace_detach(struct task_struct *, unsigned int); extern void ptrace_disable(struct task_struct *); extern int ptrace_check_attach(struct task_struct *task, int kill); -extern int ptrace_request(struct task_struct *child, long request, long addr, long data); +extern int ptrace_request(struct task_struct *child, long request, + unsigned long addr, unsigned long data); extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); @@ -132,8 +133,10 @@ static inline void ptrace_unlink(struct task_struct *child) __ptrace_unlink(child); } -int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data); -int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data); +int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, + unsigned long data); +int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, + unsigned long data); /** * task_ptrace - return %PT_* flags that apply to a task diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e6319d18a55d..cacc27a0e285 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -701,7 +701,8 @@ asmlinkage long sys_nfsservctl(int cmd, asmlinkage long sys_syslog(int type, char __user *buf, int len); asmlinkage long sys_uselib(const char __user *library); asmlinkage long sys_ni_syscall(void); -asmlinkage long sys_ptrace(long request, long pid, long addr, long data); +asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, + unsigned long data); asmlinkage long sys_add_key(const char __user *_type, const char __user *_description, diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 4afd9b86cc0b..06981a8b271b 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -404,7 +404,7 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds return copied; } -static int ptrace_setoptions(struct task_struct *child, long data) +static int ptrace_setoptions(struct task_struct *child, unsigned long data) { child->ptrace &= ~PT_TRACE_MASK; @@ -483,7 +483,8 @@ static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info) #define is_sysemu_singlestep(request) 0 #endif -static int ptrace_resume(struct task_struct *child, long request, long data) +static int ptrace_resume(struct task_struct *child, long request, + unsigned long data) { if (!valid_signal(data)) return -EIO; @@ -560,7 +561,7 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type, #endif int ptrace_request(struct task_struct *child, long request, - long addr, long data) + unsigned long addr, unsigned long data) { int ret = -EIO; siginfo_t siginfo; @@ -693,7 +694,8 @@ static struct task_struct *ptrace_get_task_struct(pid_t pid) #define arch_ptrace_attach(child) do { } while (0) #endif -SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data) +SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, + unsigned long, data) { struct task_struct *child; long ret; @@ -734,7 +736,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data) return ret; } -int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data) +int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, + unsigned long data) { unsigned long tmp; int copied; @@ -745,7 +748,8 @@ int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data) return put_user(tmp, (unsigned long __user *)data); } -int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data) +int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, + unsigned long data) { int copied; -- cgit v1.2.3 From 9fed81dc40f5a1ac2783bcc78d4029873be72894 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 27 Oct 2010 15:33:46 -0700 Subject: ptrace: cleanup ptrace_request() Use new 'datavp' and 'datalp' variables to remove unnecesary castings. Signed-off-by: Namhyung Kim Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 06981a8b271b..ea7ce0215cd1 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -565,6 +565,8 @@ int ptrace_request(struct task_struct *child, long request, { int ret = -EIO; siginfo_t siginfo; + void __user *datavp = (void __user *) data; + unsigned long __user *datalp = datavp; switch (request) { case PTRACE_PEEKTEXT: @@ -581,19 +583,17 @@ int ptrace_request(struct task_struct *child, long request, ret = ptrace_setoptions(child, data); break; case PTRACE_GETEVENTMSG: - ret = put_user(child->ptrace_message, (unsigned long __user *) data); + ret = put_user(child->ptrace_message, datalp); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) - ret = copy_siginfo_to_user((siginfo_t __user *) data, - &siginfo); + ret = copy_siginfo_to_user(datavp, &siginfo); break; case PTRACE_SETSIGINFO: - if (copy_from_user(&siginfo, (siginfo_t __user *) data, - sizeof siginfo)) + if (copy_from_user(&siginfo, datavp, sizeof siginfo)) ret = -EFAULT; else ret = ptrace_setsiginfo(child, &siginfo); @@ -624,7 +624,7 @@ int ptrace_request(struct task_struct *child, long request, } mmput(mm); - ret = put_user(tmp, (unsigned long __user *) data); + ret = put_user(tmp, datalp); break; } #endif @@ -653,7 +653,7 @@ int ptrace_request(struct task_struct *child, long request, case PTRACE_SETREGSET: { struct iovec kiov; - struct iovec __user *uiov = (struct iovec __user *) data; + struct iovec __user *uiov = datavp; if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov))) return -EFAULT; -- cgit v1.2.3 From b8ed374e202e23caaf9bd77dcadc9de6447faaa8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 27 Oct 2010 15:34:06 -0700 Subject: signals: annotate lock_task_sighand() lock_task_sighand() grabs sighand->siglock in case of returning non-NULL but unlock_task_sighand() releases it unconditionally. This leads sparse to complain about the lock context imbalance. Rename and wrap lock_task_sighand() using __cond_lock() macro to make sparse happy. Suggested-by: Eric Dumazet Signed-off-by: Namhyung Kim Cc: Ingo Molnar Cc: Oleg Nesterov Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 ++++++++- kernel/signal.c | 3 ++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index 393ce94e54b7..3ff5c8519abd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2236,9 +2236,16 @@ static inline void task_unlock(struct task_struct *p) spin_unlock(&p->alloc_lock); } -extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk, +extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, unsigned long *flags); +#define lock_task_sighand(tsk, flags) \ +({ struct sighand_struct *__ss; \ + __cond_lock(&(tsk)->sighand->siglock, \ + (__ss = __lock_task_sighand(tsk, flags))); \ + __ss; \ +}) \ + static inline void unlock_task_sighand(struct task_struct *tsk, unsigned long *flags) { diff --git a/kernel/signal.c b/kernel/signal.c index 919562c3d6b7..e921409b85a9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1105,7 +1105,8 @@ int zap_other_threads(struct task_struct *p) return count; } -struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags) +struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) { struct sighand_struct *sighand; -- cgit v1.2.3 From b84011508360d6885a9d95a235ec77d56f133377 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 27 Oct 2010 15:34:07 -0700 Subject: signals: annotate lock context change on ptrace_stop() ptrace_stop() releases and regrabs current->sighand->siglock but was missing proper annotation. Add it. Signed-off-by: Namhyung Kim Acked-by: Roland McGrath Cc: Ingo Molnar Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index e921409b85a9..4e3cff10fdce 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1618,6 +1618,8 @@ static int sigkill_pending(struct task_struct *tsk) * is gone, we keep current->exit_code unless clear_code. */ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info) + __releases(¤t->sighand->siglock) + __acquires(¤t->sighand->siglock) { if (arch_ptrace_stop_needed(exit_code, info)) { /* -- cgit v1.2.3 From 9b1bf12d5d51bca178dea21b04a0805e29d60cf1 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 27 Oct 2010 15:34:08 -0700 Subject: signals: move cred_guard_mutex from task_struct to signal_struct Oleg Nesterov pointed out we have to prevent multiple-threads-inside-exec itself and we can reuse ->cred_guard_mutex for it. Yes, concurrent execve() has no worth. Let's move ->cred_guard_mutex from task_struct to signal_struct. It naturally prevent multiple-threads-inside-exec. Signed-off-by: KOSAKI Motohiro Reviewed-by: Oleg Nesterov Acked-by: Roland McGrath Acked-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 10 +++++----- fs/proc/base.c | 8 ++++---- include/linux/init_task.h | 4 ++-- include/linux/sched.h | 7 ++++--- include/linux/tracehook.h | 2 +- kernel/cred.c | 4 +--- kernel/fork.c | 2 ++ kernel/ptrace.c | 4 ++-- 8 files changed, 21 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/fs/exec.c b/fs/exec.c index 3aa75b8888a1..9722909c4d88 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1083,14 +1083,14 @@ EXPORT_SYMBOL(setup_new_exec); */ int prepare_bprm_creds(struct linux_binprm *bprm) { - if (mutex_lock_interruptible(¤t->cred_guard_mutex)) + if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR; bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; - mutex_unlock(¤t->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); return -ENOMEM; } @@ -1098,7 +1098,7 @@ void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { - mutex_unlock(¤t->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } kfree(bprm); @@ -1119,13 +1119,13 @@ void install_exec_creds(struct linux_binprm *bprm) * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); - mutex_unlock(¤t->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); } EXPORT_SYMBOL(install_exec_creds); /* * determine how safe it is to execute the proposed program - * - the caller must hold current->cred_guard_mutex to protect against + * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH */ int check_unsafe_exec(struct linux_binprm *bprm) diff --git a/fs/proc/base.c b/fs/proc/base.c index 9b094c1c8465..f3d02ca461ec 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -226,7 +226,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task) { struct mm_struct *mm; - if (mutex_lock_killable(&task->cred_guard_mutex)) + if (mutex_lock_killable(&task->signal->cred_guard_mutex)) return NULL; mm = get_task_mm(task); @@ -235,7 +235,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task) mmput(mm); mm = NULL; } - mutex_unlock(&task->cred_guard_mutex); + mutex_unlock(&task->signal->cred_guard_mutex); return mm; } @@ -2354,14 +2354,14 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, goto out_free; /* Guard against adverse ptrace interaction */ - length = mutex_lock_interruptible(&task->cred_guard_mutex); + length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); if (length < 0) goto out_free; length = security_setprocattr(task, (char*)file->f_path.dentry->d_name.name, (void*)page, count); - mutex_unlock(&task->cred_guard_mutex); + mutex_unlock(&task->signal->cred_guard_mutex); out_free: free_page((unsigned long) page); out: diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 2fea6c8ef6ba..1f8c06ce0fa6 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -29,6 +29,8 @@ extern struct fs_struct init_fs; .running = 0, \ .lock = __SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \ }, \ + .cred_guard_mutex = \ + __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ } extern struct nsproxy init_nsproxy; @@ -145,8 +147,6 @@ extern struct cred init_cred; .group_leader = &tsk, \ RCU_INIT_POINTER(.real_cred, &init_cred), \ RCU_INIT_POINTER(.cred, &init_cred), \ - .cred_guard_mutex = \ - __MUTEX_INITIALIZER(tsk.cred_guard_mutex), \ .comm = "swapper", \ .thread = INIT_THREAD, \ .fs = &init_fs, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3ff5c8519abd..be7adb7588e5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -626,6 +626,10 @@ struct signal_struct { int oom_adj; /* OOM kill score adjustment (bit shift) */ int oom_score_adj; /* OOM kill score adjustment */ + + struct mutex cred_guard_mutex; /* guard against foreign influences on + * credential calculations + * (notably. ptrace) */ }; /* Context switch must be unlocked if interrupts are to be enabled */ @@ -1305,9 +1309,6 @@ struct task_struct { * credentials (COW) */ const struct cred __rcu *cred; /* effective (overridable) subjective task * credentials (COW) */ - struct mutex cred_guard_mutex; /* guard against foreign influences on - * credential calculations - * (notably. ptrace) */ struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */ char comm[TASK_COMM_LEN]; /* executable name excluding path diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 10db0102a890..3a2e66d88a32 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -150,7 +150,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) * * Return %LSM_UNSAFE_* bits applied to an exec because of tracing. * - * @task->cred_guard_mutex is held by the caller through the do_execve(). + * @task->signal->cred_guard_mutex is held by the caller through the do_execve(). */ static inline int tracehook_unsafe_exec(struct task_struct *task) { diff --git a/kernel/cred.c b/kernel/cred.c index 9a3e22641fe7..6a1aa004e376 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -325,7 +325,7 @@ EXPORT_SYMBOL(prepare_creds); /* * Prepare credentials for current to perform an execve() - * - The caller must hold current->cred_guard_mutex + * - The caller must hold ->cred_guard_mutex */ struct cred *prepare_exec_creds(void) { @@ -384,8 +384,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) struct cred *new; int ret; - mutex_init(&p->cred_guard_mutex); - if ( #ifdef CONFIG_KEYS !p->cred->thread_keyring && diff --git a/kernel/fork.c b/kernel/fork.c index e87aaaaf5131..3b159c5991b7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -908,6 +908,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; + mutex_init(&sig->cred_guard_mutex); + return 0; } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index ea7ce0215cd1..99bbaa3e5b0d 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -181,7 +181,7 @@ int ptrace_attach(struct task_struct *task) * under ptrace. */ retval = -ERESTARTNOINTR; - if (mutex_lock_interruptible(&task->cred_guard_mutex)) + if (mutex_lock_interruptible(&task->signal->cred_guard_mutex)) goto out; task_lock(task); @@ -208,7 +208,7 @@ int ptrace_attach(struct task_struct *task) unlock_tasklist: write_unlock_irq(&tasklist_lock); unlock_creds: - mutex_unlock(&task->cred_guard_mutex); + mutex_unlock(&task->signal->cred_guard_mutex); out: return retval; } -- cgit v1.2.3 From d16e15f5b029fc7d03540ba0e5fb23b0abb0ebe0 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 27 Oct 2010 15:34:10 -0700 Subject: exit: add lock context annotation on find_new_reaper() find_new_reaper() releases and regrabs tasklist_lock but was missing proper annotations. Add it. This remove following sparse warning: warning: context imbalance in 'find_new_reaper' - unexpected unlock Signed-off-by: Namhyung Kim Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index 894179a32ec1..b194febf5799 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -703,6 +703,8 @@ static void exit_mm(struct task_struct * tsk) * space. */ static struct task_struct *find_new_reaper(struct task_struct *father) + __releases(&tasklist_lock) + __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *thread; -- cgit v1.2.3 From 478735e38887077ac77a9756121b6ce0cb956e2f Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 27 Oct 2010 15:34:15 -0700 Subject: /proc/stat: fix scalability of irq sum of all cpu In /proc/stat, the number of per-IRQ event is shown by making a sum each irq's events on all cpus. But we can make use of kstat_irqs(). kstat_irqs() do the same calculation, If !CONFIG_GENERIC_HARDIRQ, it's not a big cost. (Both of the number of cpus and irqs are small.) If a system is very big and CONFIG_GENERIC_HARDIRQ, it does for_each_irq() for_each_cpu() - look up a radix tree - read desc->irq_stat[cpu] This seems not efficient. This patch adds kstat_irqs() for CONFIG_GENRIC_HARDIRQ and change the calculation as for_each_irq() look up radix tree for_each_cpu() - read desc->irq_stat[cpu] This reduces cost. A test on (4096cpusp, 256 nodes, 4592 irqs) host (by Jack Steiner) %time cat /proc/stat > /dev/null Before Patch: 2.459 sec After Patch : .561 sec [akpm@linux-foundation.org: unexport kstat_irqs, coding-style tweaks] [akpm@linux-foundation.org: fix unused variable 'per_irq_sum'] Signed-off-by: KAMEZAWA Hiroyuki Tested-by: Jack Steiner Acked-by: Jack Steiner Cc: Yinghai Lu Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/stat.c | 10 ++-------- include/linux/kernel_stat.h | 4 ++++ kernel/irq/irqdesc.c | 15 +++++++++++++++ 3 files changed, 21 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/fs/proc/stat.c b/fs/proc/stat.c index b80c620565bf..e15a19c93bae 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -31,7 +31,6 @@ static int show_stat(struct seq_file *p, void *v) u64 sum_softirq = 0; unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; struct timespec boottime; - unsigned int per_irq_sum; user = nice = system = idle = iowait = irq = softirq = steal = cputime64_zero; @@ -108,13 +107,8 @@ static int show_stat(struct seq_file *p, void *v) seq_printf(p, "intr %llu", (unsigned long long)sum); /* sum again ? it could be updated? */ - for_each_irq_nr(j) { - per_irq_sum = 0; - for_each_possible_cpu(i) - per_irq_sum += kstat_irqs_cpu(j, i); - - seq_printf(p, " %u", per_irq_sum); - } + for_each_irq_nr(j) + seq_printf(p, " %u", kstat_irqs(j)); seq_printf(p, "\nctxt %llu\n" diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 8b9b89085530..ad54c846911b 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -86,6 +86,7 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu) /* * Number of interrupts per specific IRQ source, since bootup */ +#ifndef CONFIG_GENERIC_HARDIRQS static inline unsigned int kstat_irqs(unsigned int irq) { unsigned int sum = 0; @@ -96,6 +97,9 @@ static inline unsigned int kstat_irqs(unsigned int irq) return sum; } +#else +extern unsigned int kstat_irqs(unsigned int irq); +#endif /* * Number of interrupts per cpu, since bootup diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 9d917ff72675..9988d03797f5 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -393,3 +393,18 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) struct irq_desc *desc = irq_to_desc(irq); return desc ? desc->kstat_irqs[cpu] : 0; } + +#ifdef CONFIG_GENERIC_HARDIRQS +unsigned int kstat_irqs(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + int cpu; + int sum = 0; + + if (!desc) + return 0; + for_each_possible_cpu(cpu) + sum += desc->kstat_irqs[cpu]; + return sum; +} +#endif /* CONFIG_GENERIC_HARDIRQS */ -- cgit v1.2.3 From 85893120699f8bae8caa12a8ee18ab5fceac978e Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Wed, 27 Oct 2010 15:34:43 -0700 Subject: delayacct: align to 8 byte boundary on 64-bit systems prepare_reply() sets up an skb for the response. The payload contains: +--------------------------------+ | genlmsghdr - 4 bytes | +--------------------------------+ | NLA header - 4 bytes | /* Aggregate header */ +-+------------------------------+ | | NLA header - 4 bytes | /* PID header */ | +------------------------------+ | | pid/tgid - 4 bytes | | +------------------------------+ | | NLA header - 4 bytes | /* stats header */ | + -----------------------------+ <- oops. aligned on 4 byte boundary | | struct taskstats - 328 bytes | +-+------------------------------+ The start of the taskstats struct must be 8 byte aligned on IA64 (and other systems with 8 byte alignment rules for 64-bit types) or runtime alignment warnings will be issued. This patch pads the pid/tgid field out to sizeof(long), which forces the alignment of taskstats. The getdelays userspace code is ok with this since it assumes 32-bit pid/tgid and then honors that header's length field. An array is used to avoid exposing kernel memory contents to userspace in the response. Signed-off-by: Jeff Mahoney Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/taskstats.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 11281d5792bd..5a651aa63d61 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -360,6 +360,12 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) struct nlattr *na, *ret; int aggr; + /* If we don't pad, we end up with alignment on a 4 byte boundary. + * This causes lots of runtime warnings on systems requiring 8 byte + * alignment */ + u32 pids[2] = { pid, 0 }; + int pid_size = ALIGN(sizeof(pid), sizeof(long)); + aggr = (type == TASKSTATS_TYPE_PID) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; @@ -367,7 +373,7 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) na = nla_nest_start(skb, aggr); if (!na) goto err; - if (nla_put(skb, type, sizeof(pid), &pid) < 0) + if (nla_put(skb, type, pid_size, pids) < 0) goto err; ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats)); if (!ret) -- cgit v1.2.3 From 9323312592cca636d7c2580dc85fa4846efa86a2 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Wed, 27 Oct 2010 15:34:44 -0700 Subject: taskstats: separate taskstats commands Move each taskstats command into a single function. This makes the code more readable and makes it easier to add new commands. Signed-off-by: Michael Holzheu Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/taskstats.c | 118 +++++++++++++++++++++++++++++++++++------------------ 1 file changed, 78 insertions(+), 40 deletions(-) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 5a651aa63d61..9970cae04f15 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -430,39 +430,46 @@ err: return rc; } -static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +static int cmd_attr_register_cpumask(struct genl_info *info) { - int rc; - struct sk_buff *rep_skb; - struct taskstats *stats; - size_t size; cpumask_var_t mask; + int rc; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; - rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) - goto free_return_rc; - if (rc == 0) { - rc = add_del_listener(info->snd_pid, mask, REGISTER); - goto free_return_rc; - } + goto out; + rc = add_del_listener(info->snd_pid, mask, REGISTER); +out: + free_cpumask_var(mask); + return rc; +} +static int cmd_attr_deregister_cpumask(struct genl_info *info) +{ + cpumask_var_t mask; + int rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); if (rc < 0) - goto free_return_rc; - if (rc == 0) { - rc = add_del_listener(info->snd_pid, mask, DEREGISTER); -free_return_rc: - free_cpumask_var(mask); - return rc; - } + goto out; + rc = add_del_listener(info->snd_pid, mask, DEREGISTER); +out: free_cpumask_var(mask); + return rc; +} + +static int cmd_attr_pid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 pid; + int rc; - /* - * Size includes space for nested attributes - */ size = nla_total_size(sizeof(u32)) + nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); @@ -471,33 +478,64 @@ free_return_rc: return rc; rc = -EINVAL; - if (info->attrs[TASKSTATS_CMD_ATTR_PID]) { - u32 pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); - stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); - if (!stats) - goto err; - - rc = fill_pid(pid, NULL, stats); - if (rc < 0) - goto err; - } else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) { - u32 tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]); - stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid); - if (!stats) - goto err; - - rc = fill_tgid(tgid, NULL, stats); - if (rc < 0) - goto err; - } else + pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); + if (!stats) + goto err; + + rc = fill_pid(pid, NULL, stats); + if (rc < 0) + goto err; + return send_reply(rep_skb, info); +err: + nlmsg_free(rep_skb); + return rc; +} + +static int cmd_attr_tgid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 tgid; + int rc; + + size = nla_total_size(sizeof(u32)) + + nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + + rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return rc; + + rc = -EINVAL; + tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid); + if (!stats) goto err; + rc = fill_tgid(tgid, NULL, stats); + if (rc < 0) + goto err; return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } +static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +{ + if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK]) + return cmd_attr_register_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK]) + return cmd_attr_deregister_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_PID]) + return cmd_attr_pid(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) + return cmd_attr_tgid(info); + else + return -EINVAL; +} + static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; -- cgit v1.2.3 From 3d9e0cf1fe007b88db55d43dfdb6839e1a029ca5 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Wed, 27 Oct 2010 15:34:44 -0700 Subject: taskstats: split fill_pid function Separate the finding of a task_struct by pid or tgid from filling the taskstats data. This makes the code more readable. Signed-off-by: Michael Holzheu Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/taskstats.c | 50 +++++++++++++++++++++----------------------------- 1 file changed, 21 insertions(+), 29 deletions(-) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 9970cae04f15..c8231fb15708 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -175,22 +175,8 @@ static void send_cpu_listeners(struct sk_buff *skb, up_write(&listeners->sem); } -static int fill_pid(pid_t pid, struct task_struct *tsk, - struct taskstats *stats) +static void fill_stats(struct task_struct *tsk, struct taskstats *stats) { - int rc = 0; - - if (!tsk) { - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (tsk) - get_task_struct(tsk); - rcu_read_unlock(); - if (!tsk) - return -ESRCH; - } else - get_task_struct(tsk); - memset(stats, 0, sizeof(*stats)); /* * Each accounting subsystem adds calls to its functions to @@ -209,17 +195,27 @@ static int fill_pid(pid_t pid, struct task_struct *tsk, /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); +} - /* Define err: label here if needed */ - put_task_struct(tsk); - return rc; +static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) +{ + struct task_struct *tsk; + rcu_read_lock(); + tsk = find_task_by_vpid(pid); + if (tsk) + get_task_struct(tsk); + rcu_read_unlock(); + if (!tsk) + return -ESRCH; + fill_stats(tsk, stats); + put_task_struct(tsk); + return 0; } -static int fill_tgid(pid_t tgid, struct task_struct *first, - struct taskstats *stats) +static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) { - struct task_struct *tsk; + struct task_struct *tsk, *first; unsigned long flags; int rc = -ESRCH; @@ -228,8 +224,7 @@ static int fill_tgid(pid_t tgid, struct task_struct *first, * leaders who are already counted with the dead tasks */ rcu_read_lock(); - if (!first) - first = find_task_by_vpid(tgid); + first = find_task_by_vpid(tgid); if (!first || !lock_task_sighand(first, &flags)) goto out; @@ -268,7 +263,6 @@ out: return rc; } - static void fill_tgid_exit(struct task_struct *tsk) { unsigned long flags; @@ -483,7 +477,7 @@ static int cmd_attr_pid(struct genl_info *info) if (!stats) goto err; - rc = fill_pid(pid, NULL, stats); + rc = fill_stats_for_pid(pid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); @@ -513,7 +507,7 @@ static int cmd_attr_tgid(struct genl_info *info) if (!stats) goto err; - rc = fill_tgid(tgid, NULL, stats); + rc = fill_stats_for_tgid(tgid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); @@ -599,9 +593,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) if (!stats) goto err; - rc = fill_pid(-1, tsk, stats); - if (rc < 0) - goto err; + fill_stats(tsk, stats); /* * Doesn't matter if tsk is the leader or the last group member leaving -- cgit v1.2.3 From d57af9b2142f31a39dcfdeb30776baadfc802827 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Wed, 27 Oct 2010 15:34:45 -0700 Subject: taskstats: use real microsecond granularity for CPU times The taskstats interface uses microsecond granularity for the user and system time values. The conversion from cputime to the taskstats values uses the cputime_to_msecs primitive which effectively limits the granularity to milliseconds. Add the cputime_to_usecs primitive for architectures that have better, more precise CPU time values. Remove cputime_to_msecs primitive because there are no more users left. Signed-off-by: Michael Holzheu Acked-by: Balbir Singh Cc: Luck Tony Cc: Shailabh Nagar Cc: Martin Schwidefsky Cc: Oleg Nesterov Cc: Benjamin Herrenschmidt Cc: Heiko Carstens Cc: Thomas Gleixner Cc: Shailabh Nagar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/cputime.h | 6 +++--- arch/powerpc/include/asm/cputime.h | 12 ++++++------ arch/s390/include/asm/cputime.h | 10 +++++----- include/asm-generic/cputime.h | 6 +++--- kernel/tsacct.c | 10 ++++------ 5 files changed, 21 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h index 7fa8a8594660..6073b187528a 100644 --- a/arch/ia64/include/asm/cputime.h +++ b/arch/ia64/include/asm/cputime.h @@ -56,10 +56,10 @@ typedef u64 cputime64_t; #define jiffies64_to_cputime64(__jif) ((__jif) * (NSEC_PER_SEC / HZ)) /* - * Convert cputime <-> milliseconds + * Convert cputime <-> microseconds */ -#define cputime_to_msecs(__ct) ((__ct) / NSEC_PER_MSEC) -#define msecs_to_cputime(__msecs) ((__msecs) * NSEC_PER_MSEC) +#define cputime_to_usecs(__ct) ((__ct) / NSEC_PER_USEC) +#define usecs_to_cputime(__usecs) ((__usecs) * NSEC_PER_USEC) /* * Convert cputime <-> seconds diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 8bdc6a9e5773..1cf20bdfbeca 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -124,23 +124,23 @@ static inline u64 cputime64_to_jiffies64(const cputime_t ct) } /* - * Convert cputime <-> milliseconds + * Convert cputime <-> microseconds */ extern u64 __cputime_msec_factor; -static inline unsigned long cputime_to_msecs(const cputime_t ct) +static inline unsigned long cputime_to_usecs(const cputime_t ct) { - return mulhdu(ct, __cputime_msec_factor); + return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC; } -static inline cputime_t msecs_to_cputime(const unsigned long ms) +static inline cputime_t usecs_to_cputime(const unsigned long us) { cputime_t ct; unsigned long sec; /* have to be a little careful about overflow */ - ct = ms % 1000; - sec = ms / 1000; + ct = us % 1000000; + sec = us / 1000000; if (ct) { ct *= tb_ticks_per_sec; do_div(ct, 1000); diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 8b1a52a137c5..40e2ab0fa3f0 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -73,18 +73,18 @@ cputime64_to_jiffies64(cputime64_t cputime) } /* - * Convert cputime to milliseconds and back. + * Convert cputime to microseconds and back. */ static inline unsigned int -cputime_to_msecs(const cputime_t cputime) +cputime_to_usecs(const cputime_t cputime) { - return cputime_div(cputime, 4096000); + return cputime_div(cputime, 4096); } static inline cputime_t -msecs_to_cputime(const unsigned int m) +usecs_to_cputime(const unsigned int m) { - return (cputime_t) m * 4096000; + return (cputime_t) m * 4096; } /* diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h index ca0f239f0e13..2bcc5c7c22a6 100644 --- a/include/asm-generic/cputime.h +++ b/include/asm-generic/cputime.h @@ -33,10 +33,10 @@ typedef u64 cputime64_t; /* - * Convert cputime to milliseconds and back. + * Convert cputime to microseconds and back. */ -#define cputime_to_msecs(__ct) jiffies_to_msecs(__ct) -#define msecs_to_cputime(__msecs) msecs_to_jiffies(__msecs) +#define cputime_to_usecs(__ct) jiffies_to_usecs(__ct); +#define usecs_to_cputime(__msecs) usecs_to_jiffies(__msecs); /* * Convert cputime to seconds and back. diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 0a67e041edf8..24dc60d9fa1f 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -63,12 +63,10 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) stats->ac_ppid = pid_alive(tsk) ? rcu_dereference(tsk->real_parent)->tgid : 0; rcu_read_unlock(); - stats->ac_utime = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC; - stats->ac_stime = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC; - stats->ac_utimescaled = - cputime_to_msecs(tsk->utimescaled) * USEC_PER_MSEC; - stats->ac_stimescaled = - cputime_to_msecs(tsk->stimescaled) * USEC_PER_MSEC; + stats->ac_utime = cputime_to_usecs(tsk->utime); + stats->ac_stime = cputime_to_usecs(tsk->stime); + stats->ac_utimescaled = cputime_to_usecs(tsk->utimescaled); + stats->ac_stimescaled = cputime_to_usecs(tsk->stimescaled); stats->ac_minflt = tsk->min_flt; stats->ac_majflt = tsk->maj_flt; -- cgit v1.2.3 From 5de1cb2d0f1c1e5475d2bedf65b76828f8cdde22 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Wed, 27 Oct 2010 15:34:52 -0700 Subject: kernel/resource.c: handle reinsertion of an already-inserted resource If the same resource is inserted to the resource tree (maybe not on purpose), a dead loop will be created. In this situation, The kernel does not report any warning or error :( The command below will show a endless print. #cat /proc/iomem [akpm@linux-foundation.org: add WARN_ON()] Signed-off-by: Huang Shijie Cc: Jesse Barnes Cc: Bjorn Helgaas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 7b36976e5dea..9c9841cb6902 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -453,6 +453,8 @@ static struct resource * __insert_resource(struct resource *parent, struct resou if (first == parent) return first; + if (WARN_ON(first == new)) /* duplicated insertion */ + return first; if ((first->start > new->start) || (first->end < new->end)) break; -- cgit v1.2.3 From 61d8e11e519ee7912ab59610fba1aaf08e3c1d84 Mon Sep 17 00:00:00 2001 From: Zimny Lech Date: Wed, 27 Oct 2010 15:34:53 -0700 Subject: Remove duplicate includes from many files Signed-off-by: Zimny Lech Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mach-tegra/timer.c | 1 - arch/arm/plat-nomadik/include/plat/ste_dma40.h | 1 - arch/tile/kernel/setup.c | 2 -- arch/x86/mm/init_64.c | 1 - arch/x86/xen/enlighten.c | 1 - drivers/media/IR/lirc_dev.c | 1 - drivers/platform/x86/intel_pmic_gpio.c | 1 - include/linux/virtio_9p.h | 1 - kernel/trace/trace_kprobe.c | 1 - 9 files changed, 10 deletions(-) (limited to 'kernel') diff --git a/arch/arm/mach-tegra/timer.c b/arch/arm/mach-tegra/timer.c index 2f420210d406..9057d6fd1d31 100644 --- a/arch/arm/mach-tegra/timer.c +++ b/arch/arm/mach-tegra/timer.c @@ -27,7 +27,6 @@ #include #include -#include #include #include diff --git a/arch/arm/plat-nomadik/include/plat/ste_dma40.h b/arch/arm/plat-nomadik/include/plat/ste_dma40.h index 5fbde4b8dc12..93a812672d9a 100644 --- a/arch/arm/plat-nomadik/include/plat/ste_dma40.h +++ b/arch/arm/plat-nomadik/include/plat/ste_dma40.h @@ -14,7 +14,6 @@ #include #include #include -#include /* dev types for memcpy */ #define STEDMA40_DEV_DST_MEMORY (-1) diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index f3a50e74f9a4..ae51cad12da0 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -30,8 +30,6 @@ #include #include #include -#include -#include #include #include #include diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 84346200e783..71a59296af80 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -51,7 +51,6 @@ #include #include #include -#include static int __init parse_direct_gbpages_off(char *arg) { diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 44ab12dc2a12..0cd12db0b142 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -59,7 +59,6 @@ #include #include #include -#include #include #include diff --git a/drivers/media/IR/lirc_dev.c b/drivers/media/IR/lirc_dev.c index 0acf6396e068..202581808bdc 100644 --- a/drivers/media/IR/lirc_dev.c +++ b/drivers/media/IR/lirc_dev.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c index f540ff96c53f..e61db9dfebef 100644 --- a/drivers/platform/x86/intel_pmic_gpio.c +++ b/drivers/platform/x86/intel_pmic_gpio.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/virtio_9p.h b/include/linux/virtio_9p.h index 1faa80d92f05..e68b439b2860 100644 --- a/include/linux/virtio_9p.h +++ b/include/linux/virtio_9p.h @@ -5,7 +5,6 @@ #include #include #include -#include /* The feature bitmap for virtio 9P */ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b8d2852baa4a..2dec9bcde8b4 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include "trace.h" -- cgit v1.2.3 From b842f8faf6c7dc2005c6a70631c1a91bac02f180 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 1 Oct 2010 17:23:41 -0400 Subject: jump label: Fix module __init section race Jump label uses is_module_text_address() to ensure that the module __init sections are valid before updating them. However, between the check for a valid module __init section and the subsequent jump label update, the module's __init section could be freed out from under us. We fix this potential race by adding a notifier callback to the MODULE_STATE_LIVE state. This notifier is called *after* the __init section has been run but before it is going to be freed. In the callback, the jump label code zeros the key value for any __init jump code within the module, and we add a check for a non-zero key value when we update jump labels. In this way we require no additional data structures. Thanks to Mathieu Desnoyers for pointing out this race condition. Reported-by: Mathieu Desnoyers Cc: Masami Hiramatsu Signed-off-by: Jason Baron LKML-Reference: [ Renamed remove_module_init() to remove_jump_label_module_init() as suggested by Masami Hiramatsu. ] Signed-off-by: Steven Rostedt --- kernel/jump_label.c | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 7be868bf25c6..be9e105345eb 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -168,7 +168,8 @@ void jump_label_update(unsigned long key, enum jump_label_type type) count = e_module->nr_entries; iter = e_module->table; while (count--) { - if (kernel_text_address(iter->code)) + if (iter->key && + kernel_text_address(iter->code)) arch_jump_label_transform(iter, type); iter++; } @@ -366,6 +367,39 @@ static void remove_jump_label_module(struct module *mod) } } +static void remove_jump_label_module_init(struct module *mod) +{ + struct hlist_head *head; + struct hlist_node *node, *node_next, *module_node, *module_node_next; + struct jump_label_entry *e; + struct jump_label_module_entry *e_module; + struct jump_entry *iter; + int i, count; + + /* if the module doesn't have jump label entries, just return */ + if (!mod->num_jump_entries) + return; + + for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { + head = &jump_label_table[i]; + hlist_for_each_entry_safe(e, node, node_next, head, hlist) { + hlist_for_each_entry_safe(e_module, module_node, + module_node_next, + &(e->modules), hlist) { + if (e_module->mod != mod) + continue; + count = e_module->nr_entries; + iter = e_module->table; + while (count--) { + if (within_module_init(iter->code, mod)) + iter->key = 0; + iter++; + } + } + } + } +} + static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) @@ -386,6 +420,11 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, remove_jump_label_module(mod); mutex_unlock(&jump_label_mutex); break; + case MODULE_STATE_LIVE: + mutex_lock(&jump_label_mutex); + remove_jump_label_module_init(mod); + mutex_unlock(&jump_label_mutex); + break; } return ret; } -- cgit v1.2.3 From 91bad2f8d3057482b9afb599f14421b007136960 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 1 Oct 2010 17:23:48 -0400 Subject: jump label: Fix deadlock b/w jump_label_mutex vs. text_mutex register_kprobe() downs the 'text_mutex' and then calls jump_label_text_reserved(), which downs the 'jump_label_mutex'. However, the jump label code takes those mutexes in the reverse order. Fix by requiring the caller of jump_label_text_reserved() to do the jump label locking via the newly added: jump_label_lock(), jump_label_unlock(). Currently, kprobes is the only user of jump_label_text_reserved(). Reported-by: Ingo Molnar Acked-by: Masami Hiramatsu Signed-off-by: Jason Baron LKML-Reference: <759032c48d5e30c27f0bba003d09bffa8e9f28bb.1285965957.git.jbaron@redhat.com> Signed-off-by: Steven Rostedt --- include/linux/jump_label.h | 5 +++++ kernel/jump_label.c | 33 +++++++++++++++++++++------------ kernel/kprobes.c | 6 ++++++ 3 files changed, 32 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index b67cb180e6e9..1947a1212678 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -18,6 +18,8 @@ struct module; extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; +extern void jump_label_lock(void); +extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_text_poke_early(jump_label_t addr); @@ -59,6 +61,9 @@ static inline int jump_label_text_reserved(void *start, void *end) return 0; } +static inline void jump_label_lock(void) {} +static inline void jump_label_unlock(void) {} + #endif #define COND_STMT(key, stmt) \ diff --git a/kernel/jump_label.c b/kernel/jump_label.c index be9e105345eb..12cce78e9568 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -39,6 +39,16 @@ struct jump_label_module_entry { struct module *mod; }; +void jump_label_lock(void) +{ + mutex_lock(&jump_label_mutex); +} + +void jump_label_unlock(void) +{ + mutex_unlock(&jump_label_mutex); +} + static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; @@ -152,7 +162,7 @@ void jump_label_update(unsigned long key, enum jump_label_type type) struct jump_label_module_entry *e_module; int count; - mutex_lock(&jump_label_mutex); + jump_label_lock(); entry = get_jump_label_entry((jump_label_t)key); if (entry) { count = entry->nr_entries; @@ -175,7 +185,7 @@ void jump_label_update(unsigned long key, enum jump_label_type type) } } } - mutex_unlock(&jump_label_mutex); + jump_label_unlock(); } static int addr_conflict(struct jump_entry *entry, void *start, void *end) @@ -232,6 +242,7 @@ out: * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. + * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ @@ -242,7 +253,6 @@ int jump_label_text_reserved(void *start, void *end) struct jump_entry *iter_stop = __start___jump_table; int conflict = 0; - mutex_lock(&jump_label_mutex); iter = iter_start; while (iter < iter_stop) { if (addr_conflict(iter, start, end)) { @@ -257,7 +267,6 @@ int jump_label_text_reserved(void *start, void *end) conflict = module_conflict(start, end); #endif out: - mutex_unlock(&jump_label_mutex); return conflict; } @@ -268,7 +277,7 @@ static __init int init_jump_label(void) struct jump_entry *iter_stop = __stop___jump_table; struct jump_entry *iter; - mutex_lock(&jump_label_mutex); + jump_label_lock(); ret = build_jump_label_hashtable(__start___jump_table, __stop___jump_table); iter = iter_start; @@ -276,7 +285,7 @@ static __init int init_jump_label(void) arch_jump_label_text_poke_early(iter->code); iter++; } - mutex_unlock(&jump_label_mutex); + jump_label_unlock(); return ret; } early_initcall(init_jump_label); @@ -409,21 +418,21 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, switch (val) { case MODULE_STATE_COMING: - mutex_lock(&jump_label_mutex); + jump_label_lock(); ret = add_jump_label_module(mod); if (ret) remove_jump_label_module(mod); - mutex_unlock(&jump_label_mutex); + jump_label_unlock(); break; case MODULE_STATE_GOING: - mutex_lock(&jump_label_mutex); + jump_label_lock(); remove_jump_label_module(mod); - mutex_unlock(&jump_label_mutex); + jump_label_unlock(); break; case MODULE_STATE_LIVE: - mutex_lock(&jump_label_mutex); + jump_label_lock(); remove_jump_label_module_init(mod); - mutex_unlock(&jump_label_mutex); + jump_label_unlock(); break; } return ret; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 99865c33a60d..9437e14f36bd 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1146,13 +1146,16 @@ int __kprobes register_kprobe(struct kprobe *p) return ret; preempt_disable(); + jump_label_lock(); if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr) || ftrace_text_reserved(p->addr, p->addr) || jump_label_text_reserved(p->addr, p->addr)) { preempt_enable(); + jump_label_unlock(); return -EINVAL; } + jump_label_unlock(); /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ p->flags &= KPROBE_FLAG_DISABLED; @@ -1187,6 +1190,8 @@ int __kprobes register_kprobe(struct kprobe *p) INIT_LIST_HEAD(&p->list); mutex_lock(&kprobe_mutex); + jump_label_lock(); /* needed to call jump_label_text_reserved() */ + get_online_cpus(); /* For avoiding text_mutex deadlock. */ mutex_lock(&text_mutex); @@ -1214,6 +1219,7 @@ int __kprobes register_kprobe(struct kprobe *p) out: mutex_unlock(&text_mutex); put_online_cpus(); + jump_label_unlock(); mutex_unlock(&kprobe_mutex); if (probed_mod) -- cgit v1.2.3 From de31c3ca8179d7c21def7ecb56e4fec0c8659d36 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 18 Oct 2010 10:38:58 -0400 Subject: jump label: Fix error with preempt disable holding mutex Kprobes and jump label were having a race between mutexes that was fixed by reordering the jump label. But this reordering moved the jump label mutex into a preempt disable location. This patch does a little fiddling to move the grabbing of the jump label mutex from inside the preempt disable section and still keep the order correct between the mutex and the kprobes lock. Reported-by: Ingo Molnar Acked-by: Masami Hiramatsu Cc: Jason Baron Signed-off-by: Steven Rostedt --- kernel/kprobes.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9437e14f36bd..9737a76e106f 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1145,17 +1145,13 @@ int __kprobes register_kprobe(struct kprobe *p) if (ret) return ret; - preempt_disable(); jump_label_lock(); + preempt_disable(); if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr) || ftrace_text_reserved(p->addr, p->addr) || - jump_label_text_reserved(p->addr, p->addr)) { - preempt_enable(); - jump_label_unlock(); - return -EINVAL; - } - jump_label_unlock(); + jump_label_text_reserved(p->addr, p->addr)) + goto fail_with_jump_label; /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ p->flags &= KPROBE_FLAG_DISABLED; @@ -1169,10 +1165,9 @@ int __kprobes register_kprobe(struct kprobe *p) * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. */ - if (unlikely(!try_module_get(probed_mod))) { - preempt_enable(); - return -EINVAL; - } + if (unlikely(!try_module_get(probed_mod))) + goto fail_with_jump_label; + /* * If the module freed .init.text, we couldn't insert * kprobes in there. @@ -1180,11 +1175,11 @@ int __kprobes register_kprobe(struct kprobe *p) if (within_module_init((unsigned long)p->addr, probed_mod) && probed_mod->state != MODULE_STATE_COMING) { module_put(probed_mod); - preempt_enable(); - return -EINVAL; + goto fail_with_jump_label; } } preempt_enable(); + jump_label_unlock(); p->nmissed = 0; INIT_LIST_HEAD(&p->list); @@ -1226,6 +1221,11 @@ out: module_put(probed_mod); return ret; + +fail_with_jump_label: + preempt_enable(); + jump_label_unlock(); + return -EINVAL; } EXPORT_SYMBOL_GPL(register_kprobe); -- cgit v1.2.3 From 95bcd683fb694a3e2d0538bf486430a0dfbb4111 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Oct 2010 11:02:43 -0400 Subject: jump label: Make arch_jump_label_text_poke_early() optional Some archs do not need to do anything special for jump labels on startup (like MIPS). This patch adds a weak function stub for arch_jump_label_text_poke_early(); Cc: Jason Baron Cc: David Miller Cc: David Daney Suggested-by: Thomas Gleixner LKML-Reference: <1286218615-24011-2-git-send-email-ddaney@caviumnetworks.com> LKML-Reference: <20101015201037.703989993@goodmis.org> Signed-off-by: Steven Rostedt --- kernel/jump_label.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 12cce78e9568..3b79bd938330 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -270,6 +270,13 @@ out: return conflict; } +/* + * Not all archs need this. + */ +void __weak arch_jump_label_text_poke_early(jump_label_t addr) +{ +} + static __init int init_jump_label(void) { int ret; -- cgit v1.2.3