diff --git a/Documentation/power/freezing-of-tasks.txt b/Documentation/power/freezing-of-tasks.txt index 316c2ba187f4..3ab9fbd2800a 100644 --- a/Documentation/power/freezing-of-tasks.txt +++ b/Documentation/power/freezing-of-tasks.txt @@ -21,7 +21,7 @@ freeze_processes() (defined in kernel/power/process.c) is called. It executes try_to_freeze_tasks() that sets TIF_FREEZE for all of the freezable tasks and either wakes them up, if they are kernel threads, or sends fake signals to them, if they are user space processes. A task that has TIF_FREEZE set, should react -to it by calling the function called refrigerator() (defined in +to it by calling the function called __refrigerator() (defined in kernel/freezer.c), which sets the task's PF_FROZEN flag, changes its state to TASK_UNINTERRUPTIBLE and makes it loop until PF_FROZEN is cleared for it. Then, we say that the task is 'frozen' and therefore the set of functions @@ -29,10 +29,10 @@ handling this mechanism is referred to as 'the freezer' (these functions are defined in kernel/power/process.c, kernel/freezer.c & include/linux/freezer.h). User space processes are generally frozen before kernel threads. -It is not recommended to call refrigerator() directly. Instead, it is -recommended to use the try_to_freeze() function (defined in -include/linux/freezer.h), that checks the task's TIF_FREEZE flag and makes the -task enter refrigerator() if the flag is set. +__refrigerator() must not be called directly. Instead, use the +try_to_freeze() function (defined in include/linux/freezer.h), that checks +the task's TIF_FREEZE flag and makes the task enter __refrigerator() if the +flag is set. For user space processes try_to_freeze() is called automatically from the signal-handling code, but the freezable kernel threads need to call it @@ -61,13 +61,13 @@ wait_event_freezable() and wait_event_freezable_timeout() macros. After the system memory state has been restored from a hibernation image and devices have been reinitialized, the function thaw_processes() is called in order to clear the PF_FROZEN flag for each frozen task. Then, the tasks that -have been frozen leave refrigerator() and continue running. +have been frozen leave __refrigerator() and continue running. III. Which kernel threads are freezable? Kernel threads are not freezable by default. However, a kernel thread may clear PF_NOFREEZE for itself by calling set_freezable() (the resetting of PF_NOFREEZE -directly is strongly discouraged). From this point it is regarded as freezable +directly is not allowed). From this point it is regarded as freezable and must call try_to_freeze() in a suitable place. IV. Why do we do that? diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index ff73db022342..28335bd40e40 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -79,7 +79,6 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TIF_UAC_SIGBUS 12 /* ! userspace part of 'osf_sysinfo' */ #define TIF_MEMDIE 13 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 14 /* restore signal mask in do_signal */ -#define TIF_FREEZE 16 /* is freezing for suspend */ #define _TIF_SYSCALL_TRACE (1<flags |= PF_NOFREEZE; - for (;;) { add_wait_queue(&thread->wait_q, &wait); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index eb1d8641cf5c..2b8661b54eaf 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -214,9 +214,18 @@ static unsigned int dmatest_verify(u8 **bufs, unsigned int start, return error_count; } -static void dmatest_callback(void *completion) +/* poor man's completion - we want to use wait_event_freezable() on it */ +struct dmatest_done { + bool done; + wait_queue_head_t *wait; +}; + +static void dmatest_callback(void *arg) { - complete(completion); + struct dmatest_done *done = arg; + + done->done = true; + wake_up_all(done->wait); } /* @@ -235,7 +244,9 @@ static void dmatest_callback(void *completion) */ static int dmatest_func(void *data) { + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(done_wait); struct dmatest_thread *thread = data; + struct dmatest_done done = { .wait = &done_wait }; struct dma_chan *chan; const char *thread_name; unsigned int src_off, dst_off, len; @@ -252,7 +263,7 @@ static int dmatest_func(void *data) int i; thread_name = current->comm; - set_freezable_with_signal(); + set_freezable(); ret = -ENOMEM; @@ -306,9 +317,6 @@ static int dmatest_func(void *data) struct dma_async_tx_descriptor *tx = NULL; dma_addr_t dma_srcs[src_cnt]; dma_addr_t dma_dsts[dst_cnt]; - struct completion cmp; - unsigned long start, tmo, end = 0 /* compiler... */; - bool reload = true; u8 align = 0; total_tests++; @@ -391,9 +399,9 @@ static int dmatest_func(void *data) continue; } - init_completion(&cmp); + done.done = false; tx->callback = dmatest_callback; - tx->callback_param = &cmp; + tx->callback_param = &done; cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { @@ -407,20 +415,20 @@ static int dmatest_func(void *data) } dma_async_issue_pending(chan); - do { - start = jiffies; - if (reload) - end = start + msecs_to_jiffies(timeout); - else if (end <= start) - end = start + 1; - tmo = wait_for_completion_interruptible_timeout(&cmp, - end - start); - reload = try_to_freeze(); - } while (tmo == -ERESTARTSYS); + wait_event_freezable_timeout(done_wait, done.done, + msecs_to_jiffies(timeout)); status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); - if (tmo == 0) { + if (!done.done) { + /* + * We're leaving the timed out dma operation with + * dangling pointer to done_wait. To make this + * correct, we'll need to allocate wait_done for + * each test iteration and perform "who's gonna + * free it this time?" dancing. For now, just + * leave it dangling. + */ pr_warning("%s: #%u: test timed out\n", thread_name, total_tests - 1); failed_tests++; diff --git a/drivers/mfd/twl6030-irq.c b/drivers/mfd/twl6030-irq.c index 3eee45ffb096..c6b456ad7342 100644 --- a/drivers/mfd/twl6030-irq.c +++ b/drivers/mfd/twl6030-irq.c @@ -138,8 +138,6 @@ static int twl6030_irq_thread(void *data) static const unsigned max_i2c_errors = 100; int ret; - current->flags |= PF_NOFREEZE; - while (!kthread_should_stop()) { int i; union { diff --git a/drivers/net/irda/stir4200.c b/drivers/net/irda/stir4200.c index 41c96b3d8152..e880c79d7bd8 100644 --- a/drivers/net/irda/stir4200.c +++ b/drivers/net/irda/stir4200.c @@ -750,7 +750,7 @@ static int stir_transmit_thread(void *arg) write_reg(stir, REG_CTRL1, CTRL1_TXPWD|CTRL1_RXPWD); - refrigerator(); + try_to_freeze(); if (change_speed(stir, stir->speed)) break; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 7b828680b21d..4b11fc91fa7d 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -2456,8 +2456,9 @@ static int hotkey_kthread(void *data) u32 poll_mask, event_mask; unsigned int si, so; unsigned long t; - unsigned int change_detector, must_reset; + unsigned int change_detector; unsigned int poll_freq; + bool was_frozen; mutex_lock(&hotkey_thread_mutex); @@ -2488,14 +2489,14 @@ static int hotkey_kthread(void *data) t = 100; /* should never happen... */ } t = msleep_interruptible(t); - if (unlikely(kthread_should_stop())) + if (unlikely(kthread_freezable_should_stop(&was_frozen))) break; - must_reset = try_to_freeze(); - if (t > 0 && !must_reset) + + if (t > 0 && !was_frozen) continue; mutex_lock(&hotkey_thread_data_mutex); - if (must_reset || hotkey_config_change != change_detector) { + if (was_frozen || hotkey_config_change != change_detector) { /* forget old state on thaw or config change */ si = so; t = 0; @@ -2528,10 +2529,6 @@ exit: static void hotkey_poll_stop_sync(void) { if (tpacpi_hotkey_task) { - if (frozen(tpacpi_hotkey_task) || - freezing(tpacpi_hotkey_task)) - thaw_process(tpacpi_hotkey_task); - kthread_stop(tpacpi_hotkey_task); tpacpi_hotkey_task = NULL; mutex_lock(&hotkey_thread_mutex); diff --git a/drivers/staging/rts_pstor/rtsx.c b/drivers/staging/rts_pstor/rtsx.c index 480b0ed2e4de..8a7803cf88d2 100644 --- a/drivers/staging/rts_pstor/rtsx.c +++ b/drivers/staging/rts_pstor/rtsx.c @@ -466,8 +466,6 @@ static int rtsx_control_thread(void *__dev) struct rtsx_chip *chip = dev->chip; struct Scsi_Host *host = rtsx_to_host(dev); - current->flags |= PF_NOFREEZE; - for (;;) { if (wait_for_completion_interruptible(&dev->cmnd_ready)) break; diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index c325e69415a1..aa84b3d77274 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -831,7 +831,8 @@ static int usb_stor_scan_thread(void * __us) dev_dbg(dev, "device found\n"); - set_freezable_with_signal(); + set_freezable(); + /* * Wait for the timeout to expire or for a disconnect * @@ -839,16 +840,16 @@ static int usb_stor_scan_thread(void * __us) * fail to freeze, but we can't be non-freezable either. Nor can * khubd freeze while waiting for scanning to complete as it may * hold the device lock, causing a hang when suspending devices. - * So we request a fake signal when freezing and use - * interruptible sleep to kick us out of our wait early when - * freezing happens. + * So instead of using wait_event_freezable(), explicitly test + * for (DONT_SCAN || freezing) in interruptible wait and proceed + * if any of DONT_SCAN, freezing or timeout has happened. */ if (delay_use > 0) { dev_dbg(dev, "waiting for device to settle " "before scanning\n"); wait_event_interruptible_timeout(us->delay_wait, - test_bit(US_FLIDX_DONT_SCAN, &us->dflags), - delay_use * HZ); + test_bit(US_FLIDX_DONT_SCAN, &us->dflags) || + freezing(current), delay_use * HZ); } /* If the device is still connected, perform the scanning */ diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 7ec14097fef1..98ab240072e5 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -340,7 +340,7 @@ again: if (freezing(current)) { worker->working = 0; spin_unlock_irq(&worker->lock); - refrigerator(); + try_to_freeze(); } else { spin_unlock_irq(&worker->lock); if (!kthread_should_stop()) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 632f8f3cc9db..b09175901521 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1579,9 +1579,7 @@ static int cleaner_kthread(void *arg) btrfs_run_defrag_inodes(root->fs_info); } - if (freezing(current)) { - refrigerator(); - } else { + if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop()) schedule(); @@ -1635,9 +1633,7 @@ sleep: wake_up_process(root->fs_info->cleaner_kthread); mutex_unlock(&root->fs_info->transaction_kthread_mutex); - if (freezing(current)) { - refrigerator(); - } else { + if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop() && !btrfs_transaction_blocked(root->fs_info)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 3858767ec672..1c7bbd00e7e5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2884,8 +2884,7 @@ cont_thread: } mutex_unlock(&eli->li_list_mtx); - if (freezing(current)) - refrigerator(); + try_to_freeze(); cur = jiffies; if ((time_after_eq(cur, next_wakeup)) || diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 73c3992b2bb4..271fde50f0ee 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -947,7 +947,7 @@ int bdi_writeback_thread(void *data) trace_writeback_thread_start(bdi); - while (!kthread_should_stop()) { + while (!kthread_freezable_should_stop(NULL)) { /* * Remove own delayed wake-up timer, since we are already awake * and we'll take care of the preriodic write-back. @@ -977,8 +977,6 @@ int bdi_writeback_thread(void *data) */ schedule(); } - - try_to_freeze(); } /* Flush any work that raced with us exiting */ diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 598646434362..8154d42e4647 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -951,8 +951,8 @@ int gfs2_logd(void *data) wake_up(&sdp->sd_log_waitq); t = gfs2_tune_get(sdp, gt_logd_secs) * HZ; - if (freezing(current)) - refrigerator(); + + try_to_freeze(); do { prepare_to_wait(&sdp->sd_logd_waitq, &wait, diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 7e528dc14f85..d49669e92652 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1427,8 +1427,8 @@ int gfs2_quotad(void *data) /* Check for & recover partially truncated inodes */ quotad_check_trunc_list(sdp); - if (freezing(current)) - refrigerator(); + try_to_freeze(); + t = min(quotad_timeo, statfs_timeo); prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_INTERRUPTIBLE); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index fea8dd661d2b..a96cff0c5f1d 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -166,7 +166,7 @@ loop: */ jbd_debug(1, "Now suspending kjournald\n"); spin_unlock(&journal->j_state_lock); - refrigerator(); + try_to_freeze(); spin_lock(&journal->j_state_lock); } else { /* diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0fa0123151d3..c0a5f9f1b127 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -173,7 +173,7 @@ loop: */ jbd_debug(1, "Now suspending kjournald2\n"); write_unlock(&journal->j_state_lock); - refrigerator(); + try_to_freeze(); write_lock(&journal->j_state_lock); } else { /* diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index cc5f811ed383..2eb952c41a69 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -2349,7 +2349,7 @@ int jfsIOWait(void *arg) if (freezing(current)) { spin_unlock_irq(&log_redrive_lock); - refrigerator(); + try_to_freeze(); } else { set_current_state(TASK_INTERRUPTIBLE); spin_unlock_irq(&log_redrive_lock); diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index af9606057dde..bb8b661bcc50 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -2800,7 +2800,7 @@ int jfs_lazycommit(void *arg) if (freezing(current)) { LAZY_UNLOCK(flags); - refrigerator(); + try_to_freeze(); } else { DECLARE_WAITQUEUE(wq, current); @@ -2994,7 +2994,7 @@ int jfs_sync(void *arg) if (freezing(current)) { TXN_UNLOCK(); - refrigerator(); + try_to_freeze(); } else { set_current_state(TASK_INTERRUPTIBLE); TXN_UNLOCK(); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index bb24ab6c282f..0e72ad6f22aa 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2470,7 +2470,7 @@ static int nilfs_segctor_thread(void *arg) if (freezing(current)) { spin_unlock(&sci->sc_state_lock); - refrigerator(); + try_to_freeze(); spin_lock(&sci->sc_state_lock); } else { DEFINE_WAIT(wait); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index cf0ac056815f..018829936d6d 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1703,7 +1703,7 @@ xfsbufd( if (unlikely(freezing(current))) { set_bit(XBT_FORCE_SLEEP, &target->bt_flags); - refrigerator(); + try_to_freeze(); } else { clear_bit(XBT_FORCE_SLEEP, &target->bt_flags); } diff --git a/include/linux/freezer.h b/include/linux/freezer.h index a5386e3ee756..09570ac22be6 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -5,71 +5,58 @@ #include #include +#include #ifdef CONFIG_FREEZER +extern atomic_t system_freezing_cnt; /* nr of freezing conds in effect */ +extern bool pm_freezing; /* PM freezing in effect */ +extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ + /* * Check if a process has been frozen */ -static inline int frozen(struct task_struct *p) +static inline bool frozen(struct task_struct *p) { return p->flags & PF_FROZEN; } +extern bool freezing_slow_path(struct task_struct *p); + /* * Check if there is a request to freeze a process */ -static inline int freezing(struct task_struct *p) +static inline bool freezing(struct task_struct *p) { - return test_tsk_thread_flag(p, TIF_FREEZE); -} - -/* - * Request that a process be frozen - */ -static inline void set_freeze_flag(struct task_struct *p) -{ - set_tsk_thread_flag(p, TIF_FREEZE); -} - -/* - * Sometimes we may need to cancel the previous 'freeze' request - */ -static inline void clear_freeze_flag(struct task_struct *p) -{ - clear_tsk_thread_flag(p, TIF_FREEZE); -} - -static inline bool should_send_signal(struct task_struct *p) -{ - return !(p->flags & PF_FREEZER_NOSIG); + if (likely(!atomic_read(&system_freezing_cnt))) + return false; + return freezing_slow_path(p); } /* Takes and releases task alloc lock using task_lock() */ -extern int thaw_process(struct task_struct *p); +extern void __thaw_task(struct task_struct *t); -extern void refrigerator(void); +extern bool __refrigerator(bool check_kthr_stop); extern int freeze_processes(void); extern int freeze_kernel_threads(void); extern void thaw_processes(void); -static inline int try_to_freeze(void) +static inline bool try_to_freeze(void) { - if (freezing(current)) { - refrigerator(); - return 1; - } else - return 0; + might_sleep(); + if (likely(!freezing(current))) + return false; + return __refrigerator(false); } -extern bool freeze_task(struct task_struct *p, bool sig_only); -extern void cancel_freezing(struct task_struct *p); +extern bool freeze_task(struct task_struct *p); +extern bool set_freezable(void); #ifdef CONFIG_CGROUP_FREEZER -extern int cgroup_freezing_or_frozen(struct task_struct *task); +extern bool cgroup_freezing(struct task_struct *task); #else /* !CONFIG_CGROUP_FREEZER */ -static inline int cgroup_freezing_or_frozen(struct task_struct *task) +static inline bool cgroup_freezing(struct task_struct *task) { - return 0; + return false; } #endif /* !CONFIG_CGROUP_FREEZER */ @@ -117,23 +104,6 @@ static inline int freezer_should_skip(struct task_struct *p) return !!(p->flags & PF_FREEZER_SKIP); } -/* - * Tell the freezer that the current task should be frozen by it - */ -static inline void set_freezable(void) -{ - current->flags &= ~PF_NOFREEZE; -} - -/* - * Tell the freezer that the current task should be frozen by it and that it - * should send a fake signal to the task to freeze it. - */ -static inline void set_freezable_with_signal(void) -{ - current->flags &= ~(PF_NOFREEZE | PF_FREEZER_NOSIG); -} - /* * Freezer-friendly wrappers around wait_event_interruptible(), * wait_event_killable() and wait_event_interruptible_timeout(), originally @@ -152,47 +122,45 @@ static inline void set_freezable_with_signal(void) #define wait_event_freezable(wq, condition) \ ({ \ int __retval; \ - do { \ + for (;;) { \ __retval = wait_event_interruptible(wq, \ (condition) || freezing(current)); \ - if (__retval && !freezing(current)) \ + if (__retval || (condition)) \ break; \ - else if (!(condition)) \ - __retval = -ERESTARTSYS; \ - } while (try_to_freeze()); \ + try_to_freeze(); \ + } \ __retval; \ }) - #define wait_event_freezable_timeout(wq, condition, timeout) \ ({ \ long __retval = timeout; \ - do { \ + for (;;) { \ __retval = wait_event_interruptible_timeout(wq, \ (condition) || freezing(current), \ __retval); \ - } while (try_to_freeze()); \ + if (__retval <= 0 || (condition)) \ + break; \ + try_to_freeze(); \ + } \ __retval; \ }) -#else /* !CONFIG_FREEZER */ -static inline int frozen(struct task_struct *p) { return 0; } -static inline int freezing(struct task_struct *p) { return 0; } -static inline void set_freeze_flag(struct task_struct *p) {} -static inline void clear_freeze_flag(struct task_struct *p) {} -static inline int thaw_process(struct task_struct *p) { return 1; } -static inline void refrigerator(void) {} +#else /* !CONFIG_FREEZER */ +static inline bool frozen(struct task_struct *p) { return false; } +static inline bool freezing(struct task_struct *p) { return false; } + +static inline bool __refrigerator(bool check_kthr_stop) { return false; } static inline int freeze_processes(void) { return -ENOSYS; } static inline int freeze_kernel_threads(void) { return -ENOSYS; } static inline void thaw_processes(void) {} -static inline int try_to_freeze(void) { return 0; } +static inline bool try_to_freeze(void) { return false; } static inline void freezer_do_not_count(void) {} static inline void freezer_count(void) {} static inline int freezer_should_skip(struct task_struct *p) { return 0; } static inline void set_freezable(void) {} -static inline void set_freezable_with_signal(void) {} #define wait_event_freezable(wq, condition) \ wait_event_interruptible(wq, condition) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 5cac19b3a266..0714b24c0e45 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -35,6 +35,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void kthread_bind(struct task_struct *k, unsigned int cpu); int kthread_stop(struct task_struct *k); int kthread_should_stop(void); +bool kthread_freezable_should_stop(bool *was_frozen); void *kthread_data(struct task_struct *k); int kthreadd(void *unused); diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c4f3e9b9bc5..d81cce933869 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -220,7 +220,7 @@ extern char ___assert_task_state[1 - 2*!!( ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) #define task_contributes_to_load(task) \ ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FREEZING) == 0) + (task->flags & PF_FROZEN) == 0) #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) @@ -1772,7 +1772,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */ -#define PF_FREEZING 0x00004000 /* freeze in progress. do not account to load */ #define PF_NOFREEZE 0x00008000 /* this thread should not be frozen */ #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ @@ -1788,7 +1787,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ -#define PF_FREEZER_NOSIG 0x80000000 /* Freezer won't send signals to it */ /* * Only the _current_ task can read/write to tsk->flags, but other diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 5e828a2ca8e6..e411a60cc2c8 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -48,19 +48,17 @@ static inline struct freezer *task_freezer(struct task_struct *task) struct freezer, css); } -static inline int __cgroup_freezing_or_frozen(struct task_struct *task) +bool cgroup_freezing(struct task_struct *task) { - enum freezer_state state = task_freezer(task)->state; - return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN); -} + enum freezer_state state; + bool ret; -int cgroup_freezing_or_frozen(struct task_struct *task) -{ - int result; - task_lock(task); - result = __cgroup_freezing_or_frozen(task); - task_unlock(task); - return result; + rcu_read_lock(); + state = task_freezer(task)->state; + ret = state == CGROUP_FREEZING || state == CGROUP_FROZEN; + rcu_read_unlock(); + + return ret; } /* @@ -102,9 +100,6 @@ struct cgroup_subsys freezer_subsys; * freezer_can_attach(): * cgroup_mutex (held by caller of can_attach) * - * cgroup_freezing_or_frozen(): - * task->alloc_lock (to get task's cgroup) - * * freezer_fork() (preserving fork() performance means can't take cgroup_mutex): * freezer->lock * sighand->siglock (if the cgroup is freezing) @@ -130,7 +125,7 @@ struct cgroup_subsys freezer_subsys; * write_lock css_set_lock (cgroup iterator start) * task->alloc_lock * read_lock css_set_lock (cgroup iterator start) - * task->alloc_lock (inside thaw_process(), prevents race with refrigerator()) + * task->alloc_lock (inside __thaw_task(), prevents race with refrigerator()) * sighand->siglock */ static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss, @@ -150,7 +145,11 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss, static void freezer_destroy(struct cgroup_subsys *ss, struct cgroup *cgroup) { - kfree(cgroup_freezer(cgroup)); + struct freezer *freezer = cgroup_freezer(cgroup); + + if (freezer->state != CGROUP_THAWED) + atomic_dec(&system_freezing_cnt); + kfree(freezer); } /* @@ -177,13 +176,7 @@ static int freezer_can_attach(struct cgroup_subsys *ss, static int freezer_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { - rcu_read_lock(); - if (__cgroup_freezing_or_frozen(tsk)) { - rcu_read_unlock(); - return -EBUSY; - } - rcu_read_unlock(); - return 0; + return cgroup_freezing(tsk) ? -EBUSY : 0; } static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) @@ -213,7 +206,7 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task) /* Locking avoids race with FREEZING -> THAWED transitions. */ if (freezer->state == CGROUP_FREEZING) - freeze_task(task, true); + freeze_task(task); spin_unlock_irq(&freezer->lock); } @@ -231,7 +224,7 @@ static void update_if_frozen(struct cgroup *cgroup, cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { ntotal++; - if (frozen(task)) + if (freezing(task) && frozen(task)) nfrozen++; } @@ -279,10 +272,9 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) struct task_struct *task; unsigned int num_cant_freeze_now = 0; - freezer->state = CGROUP_FREEZING; cgroup_iter_start(cgroup, &it); while ((task = cgroup_iter_next(cgroup, &it))) { - if (!freeze_task(task, true)) + if (!freeze_task(task)) continue; if (frozen(task)) continue; @@ -300,12 +292,9 @@ static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer) struct task_struct *task; cgroup_iter_start(cgroup, &it); - while ((task = cgroup_iter_next(cgroup, &it))) { - thaw_process(task); - } + while ((task = cgroup_iter_next(cgroup, &it))) + __thaw_task(task); cgroup_iter_end(cgroup, &it); - - freezer->state = CGROUP_THAWED; } static int freezer_change_state(struct cgroup *cgroup, @@ -319,20 +308,24 @@ static int freezer_change_state(struct cgroup *cgroup, spin_lock_irq(&freezer->lock); update_if_frozen(cgroup, freezer); - if (goal_state == freezer->state) - goto out; switch (goal_state) { case CGROUP_THAWED: + if (freezer->state != CGROUP_THAWED) + atomic_dec(&system_freezing_cnt); + freezer->state = CGROUP_THAWED; unfreeze_cgroup(cgroup, freezer); break; case CGROUP_FROZEN: + if (freezer->state == CGROUP_THAWED) + atomic_inc(&system_freezing_cnt); + freezer->state = CGROUP_FREEZING; retval = try_to_freeze_cgroup(cgroup, freezer); break; default: BUG(); } -out: + spin_unlock_irq(&freezer->lock); return retval; diff --git a/kernel/exit.c b/kernel/exit.c index d0b7d988f873..95a4141d07e7 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -679,8 +679,6 @@ static void exit_mm(struct task_struct * tsk) tsk->mm = NULL; up_read(&mm->mmap_sem); enter_lazy_tlb(mm, current); - /* We don't want this task to be frozen prematurely */ - clear_freeze_flag(tsk); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); @@ -1040,6 +1038,7 @@ NORET_TYPE void do_exit(long code) exit_rcu(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; + tsk->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ schedule(); BUG(); /* Avoid "noreturn function does return". */ diff --git a/kernel/fork.c b/kernel/fork.c index da4a6a10d088..827808613847 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -992,7 +992,6 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) new_flags |= PF_FORKNOEXEC; new_flags |= PF_STARTING; p->flags = new_flags; - clear_freeze_flag(p); } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) diff --git a/kernel/freezer.c b/kernel/freezer.c index 7be56c534397..9815b8d1eed5 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -9,101 +9,114 @@ #include #include #include +#include -/* - * freezing is complete, mark current process as frozen +/* total number of freezing conditions in effect */ +atomic_t system_freezing_cnt = ATOMIC_INIT(0); +EXPORT_SYMBOL(system_freezing_cnt); + +/* indicate whether PM freezing is in effect, protected by pm_mutex */ +bool pm_freezing; +bool pm_nosig_freezing; + +/* protects freezing and frozen transitions */ +static DEFINE_SPINLOCK(freezer_lock); + +/** + * freezing_slow_path - slow path for testing whether a task needs to be frozen + * @p: task to be tested + * + * This function is called by freezing() if system_freezing_cnt isn't zero + * and tests whether @p needs to enter and stay in frozen state. Can be + * called under any context. The freezers are responsible for ensuring the + * target tasks see the updated state. */ -static inline void frozen_process(void) +bool freezing_slow_path(struct task_struct *p) { - if (!unlikely(current->flags & PF_NOFREEZE)) { - current->flags |= PF_FROZEN; - smp_wmb(); - } - clear_freeze_flag(current); + if (p->flags & PF_NOFREEZE) + return false; + + if (pm_nosig_freezing || cgroup_freezing(p)) + return true; + + if (pm_freezing && !(p->flags & PF_KTHREAD)) + return true; + + return false; } +EXPORT_SYMBOL(freezing_slow_path); /* Refrigerator is place where frozen processes are stored :-). */ -void refrigerator(void) +bool __refrigerator(bool check_kthr_stop) { /* Hmm, should we be allowed to suspend when there are realtime processes around? */ - long save; + bool was_frozen = false; + long save = current->state; - task_lock(current); - if (freezing(current)) { - frozen_process(); - task_unlock(current); - } else { - task_unlock(current); - return; - } - save = current->state; pr_debug("%s entered refrigerator\n", current->comm); - spin_lock_irq(¤t->sighand->siglock); - recalc_sigpending(); /* We sent fake signal, clean it up */ - spin_unlock_irq(¤t->sighand->siglock); - - /* prevent accounting of that task to load */ - current->flags |= PF_FREEZING; - for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!frozen(current)) + + spin_lock_irq(&freezer_lock); + current->flags |= PF_FROZEN; + if (!freezing(current) || + (check_kthr_stop && kthread_should_stop())) + current->flags &= ~PF_FROZEN; + spin_unlock_irq(&freezer_lock); + + if (!(current->flags & PF_FROZEN)) break; + was_frozen = true; schedule(); } - /* Remove the accounting blocker */ - current->flags &= ~PF_FREEZING; - pr_debug("%s left refrigerator\n", current->comm); - __set_current_state(save); + + /* + * Restore saved task state before returning. The mb'd version + * needs to be used; otherwise, it might silently break + * synchronization which depends on ordered task state change. + */ + set_current_state(save); + + return was_frozen; } -EXPORT_SYMBOL(refrigerator); +EXPORT_SYMBOL(__refrigerator); static void fake_signal_wake_up(struct task_struct *p) { unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - signal_wake_up(p, 0); - spin_unlock_irqrestore(&p->sighand->siglock, flags); + if (lock_task_sighand(p, &flags)) { + signal_wake_up(p, 0); + unlock_task_sighand(p, &flags); + } } /** - * freeze_task - send a freeze request to given task - * @p: task to send the request to - * @sig_only: if set, the request will only be sent if the task has the - * PF_FREEZER_NOSIG flag unset - * Return value: 'false', if @sig_only is set and the task has - * PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise + * freeze_task - send a freeze request to given task + * @p: task to send the request to * - * The freeze request is sent by setting the tasks's TIF_FREEZE flag and - * either sending a fake signal to it or waking it up, depending on whether - * or not it has PF_FREEZER_NOSIG set. If @sig_only is set and the task - * has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its - * TIF_FREEZE flag will not be set. + * If @p is freezing, the freeze request is sent by setting %TIF_FREEZE + * flag and either sending a fake signal to it or waking it up, depending + * on whether it has %PF_FREEZER_NOSIG set. + * + * RETURNS: + * %false, if @p is not freezing or already frozen; %true, otherwise */ -bool freeze_task(struct task_struct *p, bool sig_only) +bool freeze_task(struct task_struct *p) { - /* - * We first check if the task is freezing and next if it has already - * been frozen to avoid the race with frozen_process() which first marks - * the task as frozen and next clears its TIF_FREEZE. - */ - if (!freezing(p)) { - smp_rmb(); - if (frozen(p)) - return false; + unsigned long flags; - if (!sig_only || should_send_signal(p)) - set_freeze_flag(p); - else - return false; + spin_lock_irqsave(&freezer_lock, flags); + if (!freezing(p) || frozen(p)) { + spin_unlock_irqrestore(&freezer_lock, flags); + return false; } - if (should_send_signal(p)) { + if (!(p->flags & PF_KTHREAD)) { fake_signal_wake_up(p); /* * fake_signal_wake_up() goes through p's scheduler @@ -111,56 +124,48 @@ bool freeze_task(struct task_struct *p, bool sig_only) * TASK_RUNNING transition can't race with task state * testing in try_to_freeze_tasks(). */ - } else if (sig_only) { - return false; } else { wake_up_state(p, TASK_INTERRUPTIBLE); } + spin_unlock_irqrestore(&freezer_lock, flags); return true; } -void cancel_freezing(struct task_struct *p) +void __thaw_task(struct task_struct *p) { unsigned long flags; - if (freezing(p)) { - pr_debug(" clean up: %s\n", p->comm); - clear_freeze_flag(p); - spin_lock_irqsave(&p->sighand->siglock, flags); - recalc_sigpending_and_wake(p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - } -} - -static int __thaw_process(struct task_struct *p) -{ - if (frozen(p)) { - p->flags &= ~PF_FROZEN; - return 1; - } - clear_freeze_flag(p); - return 0; -} - -/* - * Wake up a frozen process - * - * task_lock() is needed to prevent the race with refrigerator() which may - * occur if the freezing of tasks fails. Namely, without the lock, if the - * freezing of tasks failed, thaw_tasks() might have run before a task in - * refrigerator() could call frozen_process(), in which case the task would be - * frozen and no one would thaw it. - */ -int thaw_process(struct task_struct *p) -{ - task_lock(p); - if (__thaw_process(p) == 1) { - task_unlock(p); + /* + * Clear freezing and kick @p if FROZEN. Clearing is guaranteed to + * be visible to @p as waking up implies wmb. Waking up inside + * freezer_lock also prevents wakeups from leaking outside + * refrigerator. + */ + spin_lock_irqsave(&freezer_lock, flags); + if (frozen(p)) wake_up_process(p); - return 1; - } - task_unlock(p); - return 0; + spin_unlock_irqrestore(&freezer_lock, flags); } -EXPORT_SYMBOL(thaw_process); + +/** + * set_freezable - make %current freezable + * + * Mark %current freezable and enter refrigerator if necessary. + */ +bool set_freezable(void) +{ + might_sleep(); + + /* + * Modify flags while holding freezer_lock. This ensures the + * freezer notices that we aren't frozen yet or the freezing + * condition is visible to try_to_freeze() below. + */ + spin_lock_irq(&freezer_lock); + current->flags &= ~PF_NOFREEZE; + spin_unlock_irq(&freezer_lock); + + return try_to_freeze(); +} +EXPORT_SYMBOL(set_freezable); diff --git a/kernel/kthread.c b/kernel/kthread.c index b6d216a92639..3d3de633702e 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -58,6 +58,31 @@ int kthread_should_stop(void) } EXPORT_SYMBOL(kthread_should_stop); +/** + * kthread_freezable_should_stop - should this freezable kthread return now? + * @was_frozen: optional out parameter, indicates whether %current was frozen + * + * kthread_should_stop() for freezable kthreads, which will enter + * refrigerator if necessary. This function is safe from kthread_stop() / + * freezer deadlock and freezable kthreads should use this function instead + * of calling try_to_freeze() directly. + */ +bool kthread_freezable_should_stop(bool *was_frozen) +{ + bool frozen = false; + + might_sleep(); + + if (unlikely(freezing(current))) + frozen = __refrigerator(true); + + if (was_frozen) + *was_frozen = frozen; + + return kthread_should_stop(); +} +EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); + /** * kthread_data - return data value specified on kthread creation * @task: kthread task in question @@ -257,7 +282,7 @@ int kthreadd(void *unused) set_cpus_allowed_ptr(tsk, cpu_all_mask); set_mems_allowed(node_states[N_HIGH_MEMORY]); - current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; + current->flags |= PF_NOFREEZE; for (;;) { set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a6b0503574ee..e7ffa8952083 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -611,17 +611,6 @@ static void power_down(void) while(1); } -static int prepare_processes(void) -{ - int error = 0; - - if (freeze_processes()) { - error = -EBUSY; - thaw_processes(); - } - return error; -} - /** * hibernate - Carry out system hibernation, including saving the image. */ @@ -654,7 +643,7 @@ int hibernate(void) sys_sync(); printk("done.\n"); - error = prepare_processes(); + error = freeze_processes(); if (error) goto Finish; @@ -815,7 +804,7 @@ static int software_resume(void) goto close_finish; pr_debug("PM: Preparing processes for restore.\n"); - error = prepare_processes(); + error = freeze_processes(); if (error) { swsusp_close(FMODE_READ); goto Done; diff --git a/kernel/power/process.c b/kernel/power/process.c index addbbe5531bc..77274c9ba2f1 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -22,16 +22,7 @@ */ #define TIMEOUT (20 * HZ) -static inline int freezable(struct task_struct * p) -{ - if ((p == current) || - (p->flags & PF_NOFREEZE) || - (p->exit_state != 0)) - return 0; - return 1; -} - -static int try_to_freeze_tasks(bool sig_only) +static int try_to_freeze_tasks(bool user_only) { struct task_struct *g, *p; unsigned long end_time; @@ -46,17 +37,14 @@ static int try_to_freeze_tasks(bool sig_only) end_time = jiffies + TIMEOUT; - if (!sig_only) + if (!user_only) freeze_workqueues_begin(); while (true) { todo = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { - if (frozen(p) || !freezable(p)) - continue; - - if (!freeze_task(p, sig_only)) + if (p == current || !freeze_task(p)) continue; /* @@ -77,7 +65,7 @@ static int try_to_freeze_tasks(bool sig_only) } while_each_thread(g, p); read_unlock(&tasklist_lock); - if (!sig_only) { + if (!user_only) { wq_busy = freeze_workqueues_busy(); todo += wq_busy; } @@ -103,11 +91,6 @@ static int try_to_freeze_tasks(bool sig_only) elapsed_csecs = elapsed_csecs64; if (todo) { - /* This does not unfreeze processes that are already frozen - * (we have slightly ugly calling convention in that respect, - * and caller must call thaw_processes() if something fails), - * but it cleans up leftover PF_FREEZE requests. - */ printk("\n"); printk(KERN_ERR "Freezing of tasks %s after %d.%02d seconds " "(%d tasks refusing to freeze, wq_busy=%d):\n", @@ -115,15 +98,11 @@ static int try_to_freeze_tasks(bool sig_only) elapsed_csecs / 100, elapsed_csecs % 100, todo - wq_busy, wq_busy); - thaw_workqueues(); - read_lock(&tasklist_lock); do_each_thread(g, p) { - task_lock(p); - if (!wakeup && freezing(p) && !freezer_should_skip(p)) + if (!wakeup && !freezer_should_skip(p) && + p != current && freezing(p) && !frozen(p)) sched_show_task(p); - cancel_freezing(p); - task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); } else { @@ -136,12 +115,18 @@ static int try_to_freeze_tasks(bool sig_only) /** * freeze_processes - Signal user space processes to enter the refrigerator. + * + * On success, returns 0. On failure, -errno and system is fully thawed. */ int freeze_processes(void) { int error; + if (!pm_freezing) + atomic_inc(&system_freezing_cnt); + printk("Freezing user space processes ... "); + pm_freezing = true; error = try_to_freeze_tasks(true); if (!error) { printk("done."); @@ -150,17 +135,22 @@ int freeze_processes(void) printk("\n"); BUG_ON(in_atomic()); + if (error) + thaw_processes(); return error; } /** * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator. + * + * On success, returns 0. On failure, -errno and system is fully thawed. */ int freeze_kernel_threads(void) { int error; printk("Freezing remaining freezable tasks ... "); + pm_nosig_freezing = true; error = try_to_freeze_tasks(false); if (!error) printk("done."); @@ -168,37 +158,32 @@ int freeze_kernel_threads(void) printk("\n"); BUG_ON(in_atomic()); + if (error) + thaw_processes(); return error; } -static void thaw_tasks(bool nosig_only) -{ - struct task_struct *g, *p; - - read_lock(&tasklist_lock); - do_each_thread(g, p) { - if (!freezable(p)) - continue; - - if (nosig_only && should_send_signal(p)) - continue; - - if (cgroup_freezing_or_frozen(p)) - continue; - - thaw_process(p); - } while_each_thread(g, p); - read_unlock(&tasklist_lock); -} - void thaw_processes(void) { + struct task_struct *g, *p; + + if (pm_freezing) + atomic_dec(&system_freezing_cnt); + pm_freezing = false; + pm_nosig_freezing = false; + oom_killer_enable(); printk("Restarting tasks ... "); + thaw_workqueues(); - thaw_tasks(true); - thaw_tasks(false); + + read_lock(&tasklist_lock); + do_each_thread(g, p) { + __thaw_task(p); + } while_each_thread(g, p); + read_unlock(&tasklist_lock); + schedule(); printk("done.\n"); } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 4953dc054c53..d336b27d1104 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -106,13 +106,11 @@ static int suspend_prepare(void) goto Finish; error = suspend_freeze_processes(); - if (error) { - suspend_stats.failed_freeze++; - dpm_save_failed_step(SUSPEND_FREEZE); - } else + if (!error) return 0; - suspend_thaw_processes(); + suspend_stats.failed_freeze++; + dpm_save_failed_step(SUSPEND_FREEZE); usermodehelper_enable(); Finish: pm_notifier_call_chain(PM_POST_SUSPEND); diff --git a/kernel/power/user.c b/kernel/power/user.c index 6d8f535c2b88..7cc3f5bc5c24 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -257,10 +257,8 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, break; error = freeze_processes(); - if (error) { - thaw_processes(); + if (error) usermodehelper_enable(); - } if (!error) data->frozen = 1; break; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 71034f41a2ba..7ba8feae11b8 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -600,14 +600,10 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) /* * Finally, kill the kernel thread. We don't need to be RCU - * safe anymore, since the bdi is gone from visibility. Force - * unfreeze of the thread before calling kthread_stop(), otherwise - * it would never exet if it is currently stuck in the refrigerator. + * safe anymore, since the bdi is gone from visibility. */ - if (bdi->wb.task) { - thaw_process(bdi->wb.task); + if (bdi->wb.task) kthread_stop(bdi->wb.task); - } } /* diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 76f2c5ae908e..3134ee2fb2e8 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -328,7 +328,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, */ if (test_tsk_thread_flag(p, TIF_MEMDIE)) { if (unlikely(frozen(p))) - thaw_process(p); + __thaw_task(p); return ERR_PTR(-1UL); } if (!p->mm)