diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-04 16:23:30 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-04 16:23:30 -0700 |
| commit | 98959948a7ba33cf8c708626e0d2a1456397e1c6 (patch) | |
| tree | 8ba9b6c2679a06e89f23bdd7018e9bb0249e3bda | |
| parent | ef35ad26f8ff44d2c93e29952cdb336bda729d9d (diff) | |
| parent | cd3bd4e628a6d57d66afe77835fe8d93ae3e41f8 (diff) | |
| download | linux-98959948a7ba33cf8c708626e0d2a1456397e1c6.tar.bz2 | |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Move the nohz kick code out of the scheduler tick to a dedicated IPI,
from Frederic Weisbecker.
This necessiated quite some background infrastructure rework,
including:
* Clean up some irq-work internals
* Implement remote irq-work
* Implement nohz kick on top of remote irq-work
* Move full dynticks timer enqueue notification to new kick
* Move multi-task notification to new kick
* Remove unecessary barriers on multi-task notification
- Remove proliferation of wait_on_bit() action functions and allow
wait_on_bit_action() functions to support a timeout. (Neil Brown)
- Another round of sched/numa improvements, cleanups and fixes. (Rik
van Riel)
- Implement fast idling of CPUs when the system is partially loaded,
for better scalability. (Tim Chen)
- Restructure and fix the CPU hotplug handling code that may leave
cfs_rq and rt_rq's throttled when tasks are migrated away from a dead
cpu. (Kirill Tkhai)
- Robustify the sched topology setup code. (Peterz Zijlstra)
- Improve sched_feat() handling wrt. static_keys (Jason Baron)
- Misc fixes.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
sched/fair: Fix 'make xmldocs' warning caused by missing description
sched: Use macro for magic number of -1 for setparam
sched: Robustify topology setup
sched: Fix sched_setparam() policy == -1 logic
sched: Allow wait_on_bit_action() functions to support a timeout
sched: Remove proliferation of wait_on_bit() action functions
sched/numa: Revert "Use effective_load() to balance NUMA loads"
sched: Fix static_key race with sched_feat()
sched: Remove extra static_key*() function indirection
sched/rt: Fix replenish_dl_entity() comments to match the current upstream code
sched: Transform resched_task() into resched_curr()
sched/deadline: Kill task_struct->pi_top_task
sched: Rework check_for_tasks()
sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()
sched/fair: Disable runtime_enabled on dying rq
sched/numa: Change scan period code to match intent
sched/numa: Rework best node setting in task_numa_migrate()
sched/numa: Examine a task move when examining a task swap
sched/numa: Simplify task_numa_compare()
sched/numa: Use effective_load() to balance NUMA loads
...
57 files changed, 588 insertions, 560 deletions
diff --git a/Documentation/filesystems/caching/operations.txt b/Documentation/filesystems/caching/operations.txt index bee2a5f93d60..a1c052cbba35 100644 --- a/Documentation/filesystems/caching/operations.txt +++ b/Documentation/filesystems/caching/operations.txt @@ -90,7 +90,7 @@ operations: to be cleared before proceeding: wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); (2) The operation may be fast asynchronous (FSCACHE_OP_FAST), in which case it diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 2479b2a0c77c..4da42616939f 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -1515,7 +1515,7 @@ Doing the same with chrt -r 5 and function-trace set. <idle>-0 3d.h4 1us+: 0:120:R + [003] 2448: 94:R sleep <idle>-0 3d.h4 2us : ttwu_do_activate.constprop.87 <-try_to_wake_up <idle>-0 3d.h3 3us : check_preempt_curr <-ttwu_do_wakeup - <idle>-0 3d.h3 3us : resched_task <-check_preempt_curr + <idle>-0 3d.h3 3us : resched_curr <-check_preempt_curr <idle>-0 3dNh3 4us : task_woken_rt <-ttwu_do_wakeup <idle>-0 3dNh3 4us : _raw_spin_unlock <-try_to_wake_up <idle>-0 3dNh3 4us : sub_preempt_count <-_raw_spin_unlock diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index d724459860d9..ab472c557d18 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -615,16 +615,6 @@ static void write_endio(struct bio *bio, int error) } /* - * This function is called when wait_on_bit is actually waiting. - */ -static int do_io_schedule(void *word) -{ - io_schedule(); - - return 0; -} - -/* * Initiate a write on a dirty buffer, but don't wait for it. * * - If the buffer is not dirty, exit. @@ -640,8 +630,7 @@ static void __write_dirty_buffer(struct dm_buffer *b, return; clear_bit(B_DIRTY, &b->state); - wait_on_bit_lock(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); if (!write_list) submit_io(b, WRITE, b->block, write_endio); @@ -675,9 +664,9 @@ static void __make_buffer_clean(struct dm_buffer *b) if (!b->state) /* fast case */ return; - wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); __write_dirty_buffer(b, NULL); - wait_on_bit(&b->state, B_WRITING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE); } /* @@ -1030,7 +1019,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block, if (need_submit) submit_io(b, READ, b->block, read_endio); - wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); if (b->read_error) { int error = b->read_error; @@ -1209,15 +1198,13 @@ again: dropped_lock = 1; b->hold_count++; dm_bufio_unlock(c); - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); dm_bufio_lock(c); b->hold_count--; } else - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); } if (!test_bit(B_DIRTY, &b->state) && @@ -1321,15 +1308,15 @@ retry: __write_dirty_buffer(b, NULL); if (b->hold_count == 1) { - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); set_bit(B_DIRTY, &b->state); __unlink_buffer(b); __link_buffer(b, new_block, LIST_DIRTY); } else { sector_t old_block; - wait_on_bit_lock(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); /* * Relink buffer to "new_block" so that write_callback * sees "new_block" as a block number. @@ -1341,8 +1328,8 @@ retry: __unlink_buffer(b); __link_buffer(b, new_block, b->list_mode); submit_io(b, WRITE, new_block, write_endio); - wait_on_bit(&b->state, B_WRITING, - do_io_schedule, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&b->state, B_WRITING, + TASK_UNINTERRUPTIBLE); __unlink_buffer(b); __link_buffer(b, old_block, b->list_mode); } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 5bd2290cfb1e..864b03f47727 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1032,21 +1032,13 @@ static void start_merge(struct dm_snapshot *s) snapshot_merge_next_chunks(s); } -static int wait_schedule(void *ptr) -{ - schedule(); - - return 0; -} - /* * Stop the merging process and wait until it finishes. */ static void stop_merge(struct dm_snapshot *s) { set_bit(SHUTDOWN_MERGE, &s->state_bits); - wait_on_bit(&s->state_bits, RUNNING_MERGE, wait_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit(&s->state_bits, RUNNING_MERGE, TASK_UNINTERRUPTIBLE); clear_bit(SHUTDOWN_MERGE, &s->state_bits); } diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c index e35580618936..f296394bb7c5 100644 --- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c +++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c @@ -253,13 +253,6 @@ static int dvb_usbv2_adapter_stream_exit(struct dvb_usb_adapter *adap) return usb_urb_exitv2(&adap->stream); } -static int wait_schedule(void *ptr) -{ - schedule(); - - return 0; -} - static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed) { struct dvb_usb_adapter *adap = dvbdmxfeed->demux->priv; @@ -273,8 +266,7 @@ static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed) dvbdmxfeed->pid, dvbdmxfeed->index); /* wait init is done */ - wait_on_bit(&adap->state_bits, ADAP_INIT, wait_schedule, - TASK_UNINTERRUPTIBLE); + wait_on_bit(&adap->state_bits, ADAP_INIT, TASK_UNINTERRUPTIBLE); if (adap->active_fe == -1) return -EINVAL; @@ -568,7 +560,7 @@ static int dvb_usb_fe_sleep(struct dvb_frontend *fe) if (!adap->suspend_resume_active) { set_bit(ADAP_SLEEP, &adap->state_bits); - wait_on_bit(&adap->state_bits, ADAP_STREAMING, wait_schedule, + wait_on_bit(&adap->state_bits, ADAP_STREAMING, TASK_UNINTERRUPTIBLE); } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a389820d158b..3e11aab9f391 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3437,16 +3437,10 @@ done_unlocked: return 0; } -static int eb_wait(void *word) -{ - io_schedule(); - return 0; -} - void wait_on_extent_buffer_writeback(struct extent_buffer *eb) { - wait_on_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK, eb_wait, - TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK, + TASK_UNINTERRUPTIBLE); } static noinline_for_stack int diff --git a/fs/buffer.c b/fs/buffer.c index eba6e4f621ce..8f05111bbb8b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -61,16 +61,9 @@ inline void touch_buffer(struct buffer_head *bh) } EXPORT_SYMBOL(touch_buffer); -static int sleep_on_buffer(void *word) -{ - io_schedule(); - return 0; -} - void __lock_buffer(struct buffer_head *bh) { - wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer, - TASK_UNINTERRUPTIBLE); + wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); @@ -123,7 +116,7 @@ EXPORT_SYMBOL(buffer_check_dirty_writeback); */ void __wait_on_buffer(struct buffer_head * bh) { - wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 20d75b8ddb26..b98366f21f9e 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3934,13 +3934,6 @@ cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) return tlink_tcon(cifs_sb_master_tlink(cifs_sb)); } -static int -cifs_sb_tcon_pending_wait(void *unused) -{ - schedule(); - return signal_pending(current) ? -ERESTARTSYS : 0; -} - /* find and return a tlink with given uid */ static struct tcon_link * tlink_rb_search(struct rb_root *root, kuid_t uid) @@ -4039,11 +4032,10 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb) } else { wait_for_construction: ret = wait_on_bit(&tlink->tl_flags, TCON_LINK_PENDING, - cifs_sb_tcon_pending_wait, TASK_INTERRUPTIBLE); if (ret) { cifs_put_tlink(tlink); - return ERR_PTR(ret); + return ERR_PTR(-ERESTARTSYS); } /* if it's good, return it */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e90a1e9aa627..b88b1ade4d3d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3618,13 +3618,6 @@ static int cifs_launder_page(struct page *page) return rc; } -static int -cifs_pending_writers_wait(void *unused) -{ - schedule(); - return 0; -} - void cifs_oplock_break(struct work_struct *work) { struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, @@ -3636,7 +3629,7 @@ void cifs_oplock_break(struct work_struct *work) int rc = 0; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, - cifs_pending_writers_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); server->ops->downgrade_oplock(server, cinode, test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags)); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a174605f6afa..41de3935caa0 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1780,7 +1780,7 @@ cifs_invalidate_mapping(struct inode *inode) * @word: long word containing the bit lock */ static int -cifs_wait_bit_killable(void *word) +cifs_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; @@ -1794,8 +1794,8 @@ cifs_revalidate_mapping(struct inode *inode) int rc; unsigned long *flags = &CIFS_I(inode)->flags; - rc = wait_on_bit_lock(flags, CIFS_INO_LOCK, cifs_wait_bit_killable, - TASK_KILLABLE); + rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable, + TASK_KILLABLE); if (rc) return rc; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 3b0c62e622da..6bf55d0ed494 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -582,7 +582,7 @@ int cifs_get_writer(struct cifsInodeInfo *cinode) start: rc = wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK, - cifs_oplock_break_wait, TASK_KILLABLE); + TASK_KILLABLE); if (rc) return rc; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index be568b7311d6..ef9bef118342 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -342,7 +342,8 @@ static void __inode_wait_for_writeback(struct inode *inode) wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); - __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); + __wait_on_bit(wqh, &wq, bit_wait, + TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index aec01be91b0a..89acec742e0b 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -160,7 +160,7 @@ void __fscache_enable_cookie(struct fscache_cookie *cookie, _enter("%p", cookie); wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) goto out_unlock; @@ -255,7 +255,7 @@ static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie) if (!fscache_defer_lookup) { _debug("non-deferred lookup %p", &cookie->flags); wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); _debug("complete"); if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags)) goto unavailable; @@ -463,7 +463,6 @@ void __fscache_wait_on_invalidate(struct fscache_cookie *cookie) _enter("%p", cookie); wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING, - fscache_wait_bit_interruptible, TASK_UNINTERRUPTIBLE); _leave(""); @@ -525,7 +524,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate) } wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) goto out_unlock_enable; diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index bc6c08fcfddd..7872a62ef30c 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -97,8 +97,6 @@ static inline bool fscache_object_congested(void) return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq); } -extern int fscache_wait_bit(void *); -extern int fscache_wait_bit_interruptible(void *); extern int fscache_wait_atomic_t(atomic_t *); /* diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 63f868e869b9..a31b83c5cbd9 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -197,24 +197,6 @@ static void __exit fscache_exit(void) module_exit(fscache_exit); /* - * wait_on_bit() sleep function for uninterruptible waiting - */ -int fscache_wait_bit(void *flags) -{ - schedule(); - return 0; -} - -/* - * wait_on_bit() sleep function for interruptible waiting - */ -int fscache_wait_bit_interruptible(void *flags) -{ - schedule(); - return signal_pending(current); -} - -/* * wait_on_atomic_t() sleep function for uninterruptible waiting */ int fscache_wait_atomic_t(atomic_t *p) diff --git a/fs/fscache/page.c b/fs/fscache/page.c index ed70714503fa..85332b9d19d1 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -298,7 +298,6 @@ int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) jif = jiffies; if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - fscache_wait_bit_interruptible, TASK_INTERRUPTIBLE) != 0) { fscache_stat(&fscache_n_retrievals_intr); _leave(" = -ERESTARTSYS"); @@ -342,7 +341,6 @@ int fscache_wait_for_operation_activation(struct fscache_object *object, if (stat_op_waits) fscache_stat(stat_op_waits); if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - fscache_wait_bit_interruptible, TASK_INTERRUPTIBLE) != 0) { ret = fscache_cancel_op(op, do_cancel); if (ret == 0) @@ -351,7 +349,7 @@ int fscache_wait_for_operation_activation(struct fscache_object *object, /* it's been removed from the pending queue by another party, * so we should get to run shortly */ wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); } _debug("<<< GO"); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index ee4e04fe60fc..7f513b1ceb2c 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -856,27 +856,6 @@ void gfs2_holder_uninit(struct gfs2_holder *gh) } /** - * gfs2_glock_holder_wait - * @word: unused - * - * This function and gfs2_glock_demote_wait both show up in the WCHAN - * field. Thus I've separated these otherwise identical functions in - * order to be more informative to the user. - */ - -static int gfs2_glock_holder_wait(void *word) -{ - schedule(); - return 0; -} - -static int gfs2_glock_demote_wait(void *word) -{ - schedule(); - return 0; -} - -/** * gfs2_glock_wait - wait on a glock acquisition * @gh: the glock holder * @@ -888,7 +867,7 @@ int gfs2_glock_wait(struct gfs2_holder *gh) unsigned long time1 = jiffies; might_sleep(); - wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gh->gh_iflags, HIF_WAIT, TASK_UNINTERRUPTIBLE); if (time_after(jiffies, time1 + HZ)) /* have we waited > a second? */ /* Lengthen the minimum hold time. */ gh->gh_gl->gl_hold_time = min(gh->gh_gl->gl_hold_time + @@ -1128,7 +1107,7 @@ void gfs2_glock_dq_wait(struct gfs2_holder *gh) struct gfs2_glock *gl = gh->gh_gl; gfs2_glock_dq(gh); might_sleep(); - wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gl->gl_flags, GLF_DEMOTE, TASK_UNINTERRUPTIBLE); } /** diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 4fafea1c9ecf..641383a9c1bb 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -936,12 +936,6 @@ fail: return error; } -static int dlm_recovery_wait(void *word) -{ - schedule(); - return 0; -} - static int control_first_done(struct gfs2_sbd *sdp) { struct lm_lockstruct *ls = &sdp->sd_lockstruct; @@ -976,7 +970,7 @@ restart: fs_info(sdp, "control_first_done wait gen %u\n", start_gen); wait_on_bit(&ls->ls_recover_flags, DFL_DLM_RECOVERY, - dlm_recovery_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); goto restart; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index bc564c0d6d16..d3eae244076e 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1024,20 +1024,13 @@ void gfs2_lm_unmount(struct gfs2_sbd *sdp) lm->lm_unmount(sdp); } -static int gfs2_journalid_wait(void *word) -{ - if (signal_pending(current)) - return -EINTR; - schedule(); - return 0; -} - static int wait_on_journal(struct gfs2_sbd *sdp) { if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) return 0; - return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, gfs2_journalid_wait, TASK_INTERRUPTIBLE); + return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, TASK_INTERRUPTIBLE) + ? -EINTR : 0; } void gfs2_online_uevent(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 94555d4c5698..573bd3b758fa 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -591,12 +591,6 @@ done: wake_up_bit(&jd->jd_flags, JDF_RECOVERY); } -static int gfs2_recovery_wait(void *word) -{ - schedule(); - return 0; -} - int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait) { int rv; @@ -609,7 +603,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait) BUG_ON(!rv); if (wait) - wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, + wait_on_bit(&jd->jd_flags, JDF_RECOVERY, TASK_UNINTERRUPTIBLE); return wait ? jd->jd_recover_error : 0; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 1319b5c4ec68..2607ff13d486 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -864,12 +864,6 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) return error; } -static int gfs2_umount_recovery_wait(void *word) -{ - schedule(); - return 0; -} - /** * gfs2_put_super - Unmount the filesystem * @sb: The VFS superblock @@ -894,7 +888,7 @@ restart: continue; spin_unlock(&sdp->sd_jindex_spin); wait_on_bit(&jd->jd_flags, JDF_RECOVERY, - gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); goto restart; } spin_unlock(&sdp->sd_jindex_spin); diff --git a/fs/inode.c b/fs/inode.c index 6eecb7ff0b9a..5938f3928944 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1695,13 +1695,6 @@ int inode_needs_sync(struct inode *inode) } EXPORT_SYMBOL(inode_needs_sync); -int inode_wait(void *word) -{ - schedule(); - return 0; -} -EXPORT_SYMBOL(inode_wait); - /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6f0f590cc5a3..5f09370c90a8 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -763,12 +763,6 @@ static void warn_dirty_buffer(struct buffer_head *bh) bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); } -static int sleep_on_shadow_bh(void *word) -{ - io_schedule(); - return 0; -} - /* * If the buffer is already part of the current transaction, then there * is nothing we need to do. If it is already part of a prior @@ -906,8 +900,8 @@ repeat: if (buffer_shadow(bh)) { JBUFFER_TRACE(jh, "on shadow: sleep"); jbd_unlock_bh_state(bh); - wait_on_bit(&bh->b_state, BH_Shadow, - sleep_on_shadow_bh, TASK_UNINTERRUPTIBLE); + wait_on_bit_io(&bh->b_state, BH_Shadow, + TASK_UNINTERRUPTIBLE); goto repeat; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 4042ff58fe3f..524dd80d1898 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -361,8 +361,8 @@ start: * Prevent starvation issues if someone is doing a consistency * sync-to-disk */ - ret = wait_on_bit(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING, - nfs_wait_bit_killable, TASK_KILLABLE); + ret = wait_on_bit_action(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING, + nfs_wait_bit_killable, TASK_KILLABLE); if (ret) return ret; diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 44bf0140a4c7..e2a0361e24c6 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -783,8 +783,8 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j) static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds) { might_sleep(); - wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING, - nfs_wait_bit_killable, TASK_KILLABLE); + wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING, + nfs_wait_bit_killable, TASK_KILLABLE); } static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 9927913c97c2..abd37a380535 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -75,7 +75,7 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks * @word: long word containing the bit lock */ -int nfs_wait_bit_killable(void *word) +int nfs_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; @@ -1074,8 +1074,8 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) * the bit lock here if it looks like we're going to be doing that. */ for (;;) { - ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING, - nfs_wait_bit_killable, TASK_KILLABLE); + ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, + nfs_wait_bit_killable, TASK_KILLABLE); if (ret) goto out; spin_lock(&inode->i_lock); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index f415cbf9f6c3..617f36611d4a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -348,7 +348,7 @@ extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); -extern int nfs_wait_bit_killable(void *word); +extern int nfs_wait_bit_killable(struct wait_bit_key *key); /* super.c */ extern const struct super_operations nfs_sops; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 848f6853c59e..42f121182167 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1251,8 +1251,8 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp) might_sleep(); atomic_inc(&clp->cl_count); - res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, - nfs_wait_bit_killable, TASK_KILLABLE); + res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, + nfs_wait_bit_killable, TASK_KILLABLE); if (res) goto out; if (clp->cl_cons_state < 0) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 17fab89f6358..0be5050638f7 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -115,7 +115,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) set_bit(NFS_IO_INPROGRESS, &c->flags); if (atomic_read(&c->io_count) == 0) break; - ret = nfs_wait_bit_killable(&c->flags); + ret = nfs_wait_bit_killable(&q.key); } while (atomic_read(&c->io_count) != 0); finish_wait(wq, &q.wait); return ret; @@ -136,12 +136,6 @@ nfs_iocounter_wait(struct nfs_io_counter *c) return __nfs_iocounter_wait(c); } -static int nfs_wait_bit_uninterruptible(void *word) -{ - io_schedule(); - return 0; -} - /* * nfs_page_group_lock - lock the head of the page group * @req - request in group that is to be locked @@ -156,7 +150,6 @@ nfs_page_group_lock(struct nfs_page *req) WARN_ON_ONCE(head != head->wb_head); wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, - nfs_wait_bit_uninterruptible, TASK_UNINTERRUPTIBLE); } @@ -435,9 +428,8 @@ void nfs_release_request(struct nfs_page *req) int nfs_wait_on_request(struct nfs_page *req) { - return wait_on_bit(&req->wb_flags, PG_BUSY, - nfs_wait_bit_uninterruptible, - TASK_UNINTERRUPTIBLE); + return wait_on_bit_io(&req->wb_flags, PG_BUSY, + TASK_UNINTERRUPTIBLE); } /* diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 6fdcd233d6f7..a8914b335617 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1885,7 +1885,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) { if (!sync) goto out; - status = wait_on_bit_lock(&nfsi->flags, + status = wait_on_bit_lock_action(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING, nfs_wait_bit_killable, TASK_KILLABLE); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5e2f10304548..962c9ee758be 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -623,7 +623,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) int err; /* Stop dirtying of new pages while we sync */ - err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING, + err = wait_on_bit_lock_action(bitlock, NFS_INO_FLUSHING, nfs_wait_bit_killable, TASK_KILLABLE); if (err) goto out_err; @@ -1703,7 +1703,7 @@ int nfs_commit_inode(struct inode *inode, int how) return error; if (!may_wait) goto out_mark_dirty; - error = wait_on_bit(&NFS_I(inode)->flags, + error = wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_COMMIT, nfs_wait_bit_killable, TASK_KILLABLE); diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 19ae05d4b8ec..bf9422c3aefe 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -33,6 +33,11 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } bool irq_work_queue(struct irq_work *work); + +#ifdef CONFIG_SMP +bool irq_work_queue_on(struct irq_work *work, int cpu); +#endif + void irq_work_run(void); void irq_work_sync(struct irq_work *work); diff --git a/include/linux/sched.h b/include/linux/sched.h index b39a671cfd59..42cac4dc2157 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1437,8 +1437,6 @@ struct task_struct { struct rb_node *pi_waiters_leftmost; /* Deadlock detection and priority inheritance handling */ struct rt_mutex_waiter *pi_blocked_on; - /* Top pi_waiters task */ - struct task_struct *pi_top_task; #endif #ifdef CONFIG_DEBUG_MUTEXES @@ -2782,7 +2780,7 @@ static inline bool __must_check current_set_polling_and_test(void) /* * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() + * paired by resched_curr() */ smp_mb__after_atomic(); @@ -2800,7 +2798,7 @@ static inline bool __must_check current_clr_polling_and_test(void) /* * Polling state must be visible before we test NEED_RESCHED, - * paired by resched_task() + * paired by resched_curr() */ smp_mb__after_atomic(); @@ -2832,7 +2830,7 @@ static inline void current_clr_polling(void) * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also * fold. */ - smp_mb(); /* paired with resched_task() */ + smp_mb(); /* paired with resched_curr() */ preempt_fold_need_resched(); } diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ad7dbe2cfecd..1a8959944c5f 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -236,7 +236,7 @@ void * rpc_malloc(struct rpc_task *, size_t); void rpc_free(void *); int rpciod_up(void); void rpciod_down(void); -int __rpc_wait_for_completion_task(struct rpc_task *task, int (*)(void *)); +int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *); #ifdef RPC_DEBUG struct net; void rpc_show_tasks(struct net *); diff --git a/include/linux/tick.h b/include/linux/tick.h index 06cc093ab7ad..059052306831 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -183,7 +183,13 @@ static inline bool tick_nohz_full_cpu(int cpu) extern void tick_nohz_init(void); extern void __tick_nohz_full_check(void); -extern void tick_nohz_full_kick(void); +extern void tick_nohz_full_kick_cpu(int cpu); + +static inline void tick_nohz_full_kick(void) +{ + tick_nohz_full_kick_cpu(smp_processor_id()); +} + extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(struct task_struct *tsk); #else @@ -191,6 +197,7 @@ static inline void tick_nohz_init(void) { } static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void __tick_nohz_full_check(void) { } +static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } static inline void __tick_nohz_task_switch(struct task_struct *tsk) { } diff --git a/include/linux/wait.h b/include/linux/wait.h index bd68819f0815..6fb1ba5f9b2f 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -25,6 +25,7 @@ struct wait_bit_key { void *flags; int bit_nr; #define WAIT_ATOMIC_T_BIT_NR -1 + unsigned long private; }; struct wait_bit_queue { @@ -141,18 +142,19 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) list_del(&old->task_list); } +typedef int wait_bit_action_f(struct wait_bit_key *); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); -int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); -int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); +int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); +int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned); void wake_up_bit(void *, int); void wake_up_atomic_t(atomic_t *); -int out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned); -int out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned); +int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned); +int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned); int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned); wait_queue_head_t *bit_waitqueue(void *, int); @@ -854,11 +856,14 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); (wait)->flags = 0; \ } while (0) + +extern int bit_wait(struct wait_bit_key *); +extern int bit_wait_io(struct wait_bit_key *); + /** * wait_on_bit - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This @@ -867,9 +872,62 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit(void *word, int bit, unsigned mode) +{ + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait, + mode); +} + +/** + * wait_on_bit_io - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), but calls + * io_schedule() instead of schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. + */ +static inline int +wait_on_bit_io(void *word, int bit, unsigned mode) +{ + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit(word, bit, + bit_wait_io, + mode); +} + +/** + * wait_on_bit_action - wait for a bit to be cleared + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared, and allow the waiting action to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returned value will be zero if the bit was cleared, or non-zero + * if the process received a signal and the mode permitted wakeup + * on that signal. */ static inline int -wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) { if (!test_bit(bit, word)) return 0; @@ -880,7 +938,6 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on - * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This @@ -891,9 +948,61 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode) * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock(void *word, int bit, unsigned mode) +{ + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); +} + +/** + * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to atomically set it. This is similar + * to wait_on_bit(), but calls io_schedule() instead of schedule() + * for the actual waiting. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. + */ +static inline int +wait_on_bit_lock_io(void *word, int bit, unsigned mode) +{ + if (!test_and_set_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); +} + +/** + * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @action: the function used to sleep, which may take special actions + * @mode: the task state to sleep in + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared and then to set it, and allow the waiting action + * to be specified. + * This is like wait_on_bit() but allows fine control of how the waiting + * is done. + * + * Returns zero if the bit was (eventually) found to be clear and was + * set. Returns non-zero if a signal was delivered to the process and + * the @mode allows that signal to wake the process. */ static inline int -wait_on_bit_lock(void *word, int bit, int (*action)(void *), unsigned mode) +wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode) { if (!test_and_set_bit(bit, word)) return 0; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 5777c13849ba..a219be961c0a 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -90,7 +90,6 @@ struct writeback_control { * fs/fs-writeback.c */ struct bdi_writeback; -int inode_wait(void *); void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); @@ -105,7 +104,7 @@ void inode_wait_for_writeback(struct inode *inode); static inline void wait_on_inode(struct inode *inode) { might_sleep(); - wait_on_bit(&inode->i_state, __I_NEW, inode_wait, TASK_UNINTERRUPTIBLE); + wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } /* diff --git a/kernel/cpu.c b/kernel/cpu.c index a343bde710b1..81e2a388a0f6 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -274,21 +274,28 @@ void clear_tasks_mm_cpumask(int cpu) rcu_read_unlock(); } -static inline void check_for_tasks(int cpu) +static inline void check_for_tasks(int dead_cpu) { - struct task_struct *p; - cputime_t utime, stime; + struct task_struct *g, *p; - write_lock_irq(&tasklist_lock); - for_each_process(p) { - task_cputime(p, &utime, &stime); - if (task_cpu(p) == cpu && p->state == TASK_RUNNING && - (utime || stime)) - pr_warn("Task %s (pid = %d) is on cpu %d (state = %ld, flags = %x)\n", - p->comm, task_pid_nr(p), cpu, - p->state, p->flags); - } - write_unlock_irq(&tasklist_lock); + read_lock_irq(&tasklist_lock); + do_each_thread(g, p) { + if (!p->on_rq) + continue; + /* + * We do the check with unlocked task_rq(p)->lock. + * Order the reading to do not warn about a task, + * which was running on this cpu in the past, and + * it's just been woken on another cpu. + */ + rmb(); + if (task_cpu(p) != dead_cpu) + continue; + + pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n", + p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags); + } while_each_thread(g, p); + read_unlock_irq(&tasklist_lock); } struct take_cpu_down_param { diff --git a/kernel/fork.c b/kernel/fork.c index 6a13c46cd87d..962885edbe53 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1095,7 +1095,6 @@ static void rt_mutex_init_task(struct task_struct *p) p->pi_waiters = RB_ROOT; p->pi_waiters_leftmost = NULL; p->pi_blocked_on = NULL; - p->pi_top_task = NULL; #endif } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index a82170e2fa78..e6bcbe756663 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -16,11 +16,12 @@ #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> +#include <linux/smp.h> #include <asm/processor.h> -static DEFINE_PER_CPU(struct llist_head, irq_work_list); -static DEFINE_PER_CPU(int, irq_work_raised); +static DEFINE_PER_CPU(struct llist_head, raised_list); +static DEFINE_PER_CPU(struct llist_head, lazy_list); /* * Claim the entry so that no one else will poke at it. @@ -55,12 +56,34 @@ void __weak arch_irq_work_raise(void) */ } +#ifdef CONFIG_SMP /* - * Enqueue the irq_work @entry unless it's already pending + * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ +bool irq_work_queue_on(struct irq_work *work, int cpu) +{ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + + /* Arch remote IPI send/receive backend aren't NMI safe */ + WARN_ON_ONCE(in_nmi()); + + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; + + if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) + arch_send_call_function_single_ipi(cpu); + + return true; +} +EXPORT_SYMBOL_GPL(irq_work_queue_on); +#endif + +/* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ @@ -70,15 +93,13 @@ bool irq_work_queue(struct irq_work *work) /* Queue the entry and raise the IPI if needed. */ preempt_disable(); - llist_add(&work->llnode, &__get_cpu_var(irq_work_list)); - - /* - * If the work is not "lazy" or the tick is stopped, raise the irq - * work interrupt (if supported by the arch), otherwise, just wait - * for the next tick. - */ - if (!(work->flags & IRQ_WORK_LAZY) || tick_nohz_tick_stopped()) { - if (!this_cpu_cmpxchg(irq_work_raised, 0, 1)) + /* If the work is "lazy", handle it from next tick if any */ + if (work->flags & IRQ_WORK_LAZY) { + if (llist_add(&work->llnode, &__get_cpu_var(lazy_list)) && + tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } else { + if (llist_add(&work->llnode, &__get_cpu_var(raised_list))) arch_irq_work_raise(); } @@ -90,10 +111,11 @@ EXPORT_SYMBOL_GPL(irq_work_queue); bool irq_work_needs_cpu(void) { - struct llist_head *this_list; + struct llist_head *raised, *lazy; - this_list = &__get_cpu_var(irq_work_list); - if (llist_empty(this_list)) + raised = &__get_cpu_var(raised_list); + lazy = &__get_cpu_var(lazy_list); + if (llist_empty(raised) && llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ @@ -102,28 +124,18 @@ bool irq_work_needs_cpu(void) return true; } -static void __irq_work_run(void) +static void irq_work_run_list(struct llist_head *list) { unsigned long flags; struct irq_work *work; - struct llist_head *this_list; struct llist_node *llnode; + BUG_ON(!irqs_disabled()); - /* - * Reset the "raised" state right before we check the list because - * an NMI may enqueue after we find the list empty from the runner. - */ - __this_cpu_write(irq_work_raised, 0); - barrier(); - - this_list = &__get_cpu_var(irq_work_list); - if (llist_empty(this_list)) + if (llist_empty(list)) return; - BUG_ON(!irqs_disabled()); - - llnode = llist_del_all(this_list); + llnode = llist_del_all(list); while (llnode != NULL) { work = llist_entry(llnode, struct irq_work, llnode); @@ -149,13 +161,13 @@ static void __irq_work_run(void) } /* - * Run the irq_work entries on this cpu. Requires to be ran from hardirq - * context with local IRQs disabled. + * hotplug calls this through: + * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { - BUG_ON(!in_irq()); - __irq_work_run(); + irq_work_run_list(&__get_cpu_var(raised_list)); + irq_work_run_list(&__get_cpu_var(lazy_list)); } EXPORT_SYMBOL_GPL(irq_work_run); @@ -171,35 +183,3 @@ void irq_work_sync(struct irq_work *work) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); - -#ifdef CONFIG_HOTPLUG_CPU -static int irq_work_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - long cpu = (long)hcpu; - - switch (action) { - case CPU_DYING: - /* Called from stop_machine */ - if (WARN_ON_ONCE(cpu != smp_processor_id())) - break; - __irq_work_run(); - break; - default: - break; - } - return NOTIFY_OK; -} - -static struct notifier_block cpu_notify; - -static __init int irq_work_init_cpu_notifier(void) -{ - cpu_notify.notifier_call = irq_work_cpu_notify; - cpu_notify.priority = 0; - register_cpu_notifier(&cpu_notify); - return 0; -} -device_initcall(irq_work_init_cpu_notifier); - -#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/ptrace.c b/kernel/ptrace.c index adf98622cb32..54e75226c2c4 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -28,12 +28,6 @@ #include <linux/compat.h> -static int ptrace_trapping_sleep_fn(void *flags) -{ - schedule(); - return 0; -} - /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. @@ -371,7 +365,7 @@ unlock_creds: out: if (!retval) { wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, - ptrace_trapping_sleep_fn, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); proc_ptrace_connector(task, PTRACE_ATTACH); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 126f7e3f04e7..1211575a2208 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -139,6 +139,8 @@ void update_rq_clock(struct rq *rq) return; delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + if (delta < 0) + return; rq->clock += delta; update_rq_clock_task(rq, delta); } @@ -243,6 +245,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, char buf[64]; char *cmp; int i; + struct inode *inode; if (cnt > 63) cnt = 63; @@ -253,7 +256,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf, buf[cnt] = 0; cmp = strstrip(buf); + /* Ensure the static_key remains in a consistent state */ + inode = file_inode(filp); + mutex_lock(&inode->i_mutex); i = sched_feat_set(cmp); + mutex_unlock(&inode->i_mutex); if (i == __SCHED_FEAT_NR) return -EINVAL; @@ -587,30 +594,31 @@ static bool set_nr_if_polling(struct task_struct *p) #endif /* - * resched_task - mark a task 'to be rescheduled now'. + * resched_curr - mark rq's current task 'to be rescheduled now'. * * On UP this means the setting of the need_resched flag, on SMP it * might also involve a cross-CPU call to trigger the scheduler on * the target CPU. */ -void resched_task(struct task_struct *p) +void resched_curr(struct rq *rq) { + struct task_struct *curr = rq->curr; int cpu; - lockdep_assert_held(&task_rq(p)->lock); + lockdep_assert_held(&rq->lock); - if (test_tsk_need_resched(p)) + if (test_tsk_need_resched(curr)) return; - cpu = task_cpu(p); + cpu = cpu_of(rq); if (cpu == smp_processor_id()) { - set_tsk_need_resched(p); + set_tsk_need_resched(curr); set_preempt_need_resched(); return; } - if (set_nr_and_not_polling(p)) + if (set_nr_and_not_polling(curr)) smp_send_reschedule(cpu); else trace_sched_wake_idle_without_ipi(cpu); @@ -623,7 +631,7 @@ void resched_cpu(int cpu) if (!raw_spin_trylock_irqsave(&rq->lock, flags)) return; - resched_task(cpu_curr(cpu)); + resched_curr(rq); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -684,10 +692,16 @@ static void wake_up_idle_cpu(int cpu) static bool wake_up_full_nohz_cpu(int cpu) { + /* + * We just need the target to call irq_exit() and re-evaluate + * the next tick. The nohz full kick at least implies that. + * If needed we can still optimize that later with an + * empty IRQ. + */ if (tick_nohz_full_cpu(cpu)) { if (cpu != smp_processor_id() || tick_nohz_tick_stopped()) - smp_send_reschedule(cpu); + tick_nohz_full_kick_cpu(cpu); return true; } @@ -730,18 +744,15 @@ static inline bool got_nohz_idle_kick(void) #ifdef CONFIG_NO_HZ_FULL bool sched_can_stop_tick(void) { - struct rq *rq; - - rq = this_rq(); - - /* Make sure rq->nr_running update is visible after the IPI */ - smp_rmb(); - - /* More than one running task need preemption */ - if (rq->nr_running > 1) - return false; + /* + * More than one running task need preemption. + * nr_running update is assumed to be visible + * after IPI is sent from wakers. + */ + if (this_rq()->nr_running > 1) + return false; - return true; + return true; } #endif /* CONFIG_NO_HZ_FULL */ @@ -1022,7 +1033,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) if (class == rq->curr->sched_class) break; if (class == p->sched_class) { - resched_task(rq->curr); + resched_curr(rq); break; } } @@ -1568,9 +1579,7 @@ void scheduler_ipi(void) */ preempt_fold_need_resched(); - if (llist_empty(&this_rq()->wake_list) - && !tick_nohz_full_cpu(smp_processor_id()) - && !got_nohz_idle_kick()) + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) return; /* @@ -1587,7 +1596,6 @@ void scheduler_ipi(void) * somewhat pessimize the simple resched case. */ irq_enter(); - tick_nohz_full_check(); sched_ttwu_pending(); /* @@ -2431,7 +2439,12 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) { u64 ns = 0; - if (task_current(rq, p)) { + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (task_current(rq, p) && p->on_rq) { update_rq_clock(rq); ns = rq_clock_task(rq) - p->se.exec_start; if ((s64)ns < 0) @@ -2474,8 +2487,10 @@ unsigned long long task_sched_runtime(struct task_struct *p) * If we race with it leaving cpu, we'll take a lock. So we're correct. * If we race with it entering cpu, unaccounted time is 0. This is * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. */ - if (!p->on_cpu) + if (!p->on_cpu || !p->on_rq) return p->se.sum_exec_runtime; #endif @@ -2971,7 +2986,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } trace_sched_pi_setprio(p, prio); - p->pi_top_task = rt_mutex_get_top_task(p); oldprio = p->prio; prev_class = p->sched_class; on_rq = p->on_rq; @@ -2991,8 +3005,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio) * running task */ if (dl_prio(prio)) { - if (!dl_prio(p->normal_prio) || (p->pi_top_task && - dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) { + struct task_struct *pi_task = rt_mutex_get_top_task(p); + if (!dl_prio(p->normal_prio) || + (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; p->dl.dl_throttled = 0; enqueue_flag = ENQUEUE_REPLENISH; @@ -3064,7 +3079,7 @@ void set_user_nice(struct task_struct *p, long nice) * lowered its priority, then reschedule its CPU: */ if (delta < 0 || (delta > 0 && task_running(rq, p))) - resched_task(rq->curr); + resched_curr(rq); } out_unlock: task_rq_unlock(rq, p, &flags); @@ -3203,12 +3218,18 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) dl_se->dl_yielded = 0; } +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + static void __setscheduler_params(struct task_struct *p, const struct sched_attr *attr) { int policy = attr->sched_policy; - if (policy == -1) /* setparam */ + if (policy == SETPARAM_POLICY) policy = p->policy; p->policy = policy; @@ -3557,10 +3578,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy, .sched_nice = PRIO_TO_NICE(p->static_prio), }; - /* - * Fixup the legacy SCHED_RESET_ON_FORK hack - */ - if (policy & SCHED_RESET_ON_FORK) { + /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ + if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; policy &= ~SCHED_RESET_ON_FORK; attr.sched_policy = policy; @@ -3730,7 +3749,7 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, */ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) { - return do_sched_setscheduler(pid, -1, param); + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); } /** @@ -4285,7 +4304,7 @@ again: * fairness. */ if (preempt && rq != p_rq) - resched_task(p_rq->curr); + resched_curr(p_rq); } out_unlock: @@ -6465,6 +6484,20 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, sched_domain_level_max = max(sched_domain_level_max, sd->level); child->parent = sd; sd->child = child; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + } set_domain_attribute(sd, attr); @@ -7092,7 +7125,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) __setscheduler(rq, p, &attr); if (on_rq) { enqueue_task(rq, p, 0); - resched_task(rq->curr); + resched_curr(rq); } check_class_changed(rq, p, prev_class, old_prio); @@ -7803,6 +7836,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) if (period > max_cfs_quota_period) return -EINVAL; + /* + * Prevent race between setting of cfs_rq->runtime_enabled and + * unthrottle_offline_cfs_rqs(). + */ + get_online_cpus(); mutex_lock(&cfs_constraints_mutex); ret = __cfs_schedulable(tg, period, quota); if (ret) @@ -7828,7 +7866,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) } raw_spin_unlock_irq(&cfs_b->lock); - for_each_possible_cpu(i) { + for_each_online_cpu(i) { struct cfs_rq *cfs_rq = tg->cfs_rq[i]; struct rq *rq = cfs_rq->rq; @@ -7844,6 +7882,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) cfs_bandwidth_usage_dec(); out_unlock: mutex_unlock(&cfs_constraints_mutex); + put_online_cpus(); return ret; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fc4f98b1258f..255ce138b652 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -306,7 +306,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, * the overrunning entity can't interfere with other entity in the system and * can't make them miss their deadlines. Reasons why this kind of overruns * could happen are, typically, a entity voluntarily trying to overcome its - * runtime, or it just underestimated it during sched_setscheduler_ex(). + * runtime, or it just underestimated it during sched_setattr(). */ static void replenish_dl_entity(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se) @@ -535,7 +535,7 @@ again: if (task_has_dl_policy(rq->curr)) check_preempt_curr_dl(rq, p, 0); else - resched_task(rq->curr); + resched_curr(rq); #ifdef CONFIG_SMP /* * Queueing this task back might have overloaded rq, @@ -634,7 +634,7 @@ static void update_curr_dl(struct rq *rq) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) - resched_task(curr); + resched_curr(rq); } /* @@ -964,7 +964,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) cpudl_find(&rq->rd->cpudl, p, NULL) != -1) return; - resched_task(rq->curr); + resched_curr(rq); } static int pull_dl_task(struct rq *this_rq); @@ -979,7 +979,7 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags) { if (dl_entity_preempt(&p->dl, &rq->curr->dl)) { - resched_task(rq->curr); + resched_curr(rq); return; } @@ -1333,7 +1333,7 @@ retry: if (dl_task(rq->curr) && dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && rq->curr->nr_cpus_allowed > 1) { - resched_task(rq->curr); + resched_curr(rq); return 0; } @@ -1373,7 +1373,7 @@ retry: set_task_cpu(next_task, later_rq->cpu); activate_task(later_rq, next_task, 0); - resched_task(later_rq->curr); + resched_curr(later_rq); double_unlock_balance(rq, later_rq); @@ -1632,14 +1632,14 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, */ if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) && rq->curr == p) - resched_task(p); + resched_curr(rq); #else /* * Again, we don't know if p has a earlier * or later deadline, so let's blindly set a * (maybe not needed) rescheduling point. */ - resched_task(p); + resched_curr(rq); #endif /* CONFIG_SMP */ } else switched_to_dl(rq, p); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fea7d3335e1f..bfa3c86d0d68 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1062,7 +1062,6 @@ static void update_numa_stats(struct numa_stats *ns, int nid) if (!cpus) return; - ns->load = (ns->load * SCHED_CAPACITY_SCALE) / ns->compute_capacity; ns->task_capacity = DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE); ns->has_free_capacity = (ns->nr_running < ns->task_capacity); @@ -1096,18 +1095,30 @@ static void task_numa_assign(struct task_numa_env *env, env->best_cpu = env->dst_cpu; } -static bool load_too_imbalanced(long orig_src_load, long orig_dst_load, - long src_load, long dst_load, +static bool load_too_imbalanced(long src_load, long dst_load, struct task_numa_env *env) { long imb, old_imb; + long orig_src_load, orig_dst_load; + long src_capacity, dst_capacity; + + /* + * The load is corrected for the CPU capacity available on each node. + * + * src_load dst_load + * ------------ vs --------- + * src_capacity dst_capacity + */ + src_capacity = env->src_stats.compute_capacity; + dst_capacity = env->dst_stats.compute_capacity; /* We care about the slope of the imbalance, not the direction. */ if (dst_load < src_load) swap(dst_load, src_load); /* Is the difference below the threshold? */ - imb = dst_load * 100 - src_load * env->imbalance_pct; + imb = dst_load * src_capacity * 100 - + src_load * dst_capacity * env->imbalance_pct; if (imb <= 0) return false; @@ -1115,10 +1126,14 @@ static bool load_too_imbalanced(long orig_src_load, long orig_dst_load, * The imbalance is above the allowed threshold. * Compare it with the old imbalance. */ + orig_src_load = env->src_stats.load; + orig_dst_load = env->dst_stats.load; + if (orig_dst_load < orig_src_load) swap(orig_dst_load, orig_src_load); - old_imb = orig_dst_load * 100 - orig_src_load * env->imbalance_pct; + old_imb = orig_dst_load * src_capacity * 100 - + orig_src_load * dst_capacity * env->imbalance_pct; /* Would this change make things worse? */ return (imb > old_imb); @@ -1136,10 +1151,10 @@ static void task_numa_compare(struct task_numa_env *env, struct rq *src_rq = cpu_rq(env->src_cpu); struct rq *dst_rq = cpu_rq(env->dst_cpu); struct task_struct *cur; - long orig_src_load, src_load; - long orig_dst_load, dst_load; + long src_load, dst_load; long load; - long imp = (groupimp > 0) ? groupimp : taskimp; + long imp = env->p->numa_group ? groupimp : taskimp; + long moveimp = imp; rcu_read_lock(); cur = ACCESS_ONCE(dst_rq->curr); @@ -1177,11 +1192,6 @@ static void task_numa_compare(struct task_numa_env *env, * itself (not part of a group), use the task weight * instead. */ - if (env->p->numa_group) - imp = groupimp; - else - imp = taskimp; - if (cur->numa_group) imp += group_weight(cur, env->src_nid) - group_weight(cur, env->dst_nid); @@ -1191,7 +1201,7 @@ static void task_numa_compare(struct task_numa_env *env, } } - if (imp < env->best_imp) + if (imp <= env->best_imp && moveimp <= env->best_imp) goto unlock; if (!cur) { @@ -1204,20 +1214,34 @@ static void task_numa_compare(struct task_numa_env *env, } /* Balance doesn't matter much if we're running a task per cpu */ - if (src_rq->nr_running == 1 && dst_rq->nr_running == 1) + if (imp > env->best_imp && src_rq->nr_running == 1 && + dst_rq->nr_running == 1) goto assign; /* * In the overloaded case, try and keep the load balanced. */ balance: - orig_dst_load = env->dst_stats.load; - orig_src_load = env->src_stats.load; - - /* XXX missing capacity terms */ load = task_h_load(env->p); - dst_load = orig_dst_load + load; - src_load = orig_src_load - load; + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + if (moveimp > imp && moveimp > env->best_imp) { + /* + * If the improvement from just moving env->p direction is + * better than swapping tasks around, check if a move is + * possible. Store a slightly smaller score than moveimp, + * so an actually idle CPU will win. + */ + if (!load_too_imbalanced(src_load, dst_load, env)) { + imp = moveimp - 1; + cur = NULL; + goto assign; + } + } + + if (imp <= env->best_imp) + goto unlock; if (cur) { load = task_h_load(cur); @@ -1225,8 +1249,7 @@ balance: src_load += load; } - if (load_too_imbalanced(orig_src_load, orig_dst_load, - src_load, dst_load, env)) + if (load_too_imbalanced(src_load, dst_load, env)) goto unlock; assign: @@ -1302,9 +1325,8 @@ static int task_numa_migrate(struct task_struct *p) groupimp = group_weight(p, env.dst_nid) - groupweight; update_numa_stats(&env.dst_stats, env.dst_nid); - /* If the preferred nid has free capacity, try to use it. */ - if (env.dst_stats.has_free_capacity) - task_numa_find_cpu(&env, taskimp, groupimp); + /* Try to find a spot on the preferred nid. */ + task_numa_find_cpu(&env, taskimp, groupimp); /* No space available on the preferred nid. Look elsewhere. */ if (env.best_cpu == -1) { @@ -1324,10 +1346,6 @@ static int task_numa_migrate(struct task_struct *p) } } - /* No better CPU than the current one was found. */ - if (env.best_cpu == -1) - return -EAGAIN; - /* * If the task is part of a workload that spans multiple NUMA nodes, * and is migrating into one of the workload's active nodes, remember @@ -1336,8 +1354,19 @@ static int task_numa_migrate(struct task_struct *p) * A task that migrated to a second choice node will be better off * trying for a better one later. Do not set the preferred node here. */ - if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes)) - sched_setnuma(p, env.dst_nid); + if (p->numa_group) { + if (env.best_cpu == -1) + nid = env.src_nid; + else + nid = env.dst_nid; + + if (node_isset(nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); + } + + /* No better CPU than the current one was found. */ + if (env.best_cpu == -1) + return -EAGAIN; /* * Reset the scan period if the task is being rescheduled on an @@ -1415,12 +1444,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group) /* * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS * increments. The more local the fault statistics are, the higher the scan - * period will be for the next scan window. If local/remote ratio is below - * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the - * scan period will decrease + * period will be for the next scan window. If local/(local+remote) ratio is + * below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) + * the scan period will decrease. Aim for 70% local accesses. */ #define NUMA_PERIOD_SLOTS 10 -#define NUMA_PERIOD_THRESHOLD 3 +#define NUMA_PERIOD_THRESHOLD 7 /* * Increase the scan period (slow down scanning) if the majority of @@ -1595,30 +1624,17 @@ static void task_numa_placement(struct task_struct *p) if (p->numa_group) { update_numa_active_node_mask(p->numa_group); - /* - * If the preferred task and group nids are different, - * iterate over the nodes again to find the best place. - */ - if (max_nid != max_group_nid) { - unsigned long weight, max_weight = 0; - - for_each_online_node(nid) { - weight = task_weight(p, nid) + group_weight(p, nid); - if (weight > max_weight) { - max_weight = weight; - max_nid = nid; - } - } - } - spin_unlock_irq(group_lock); + max_nid = max_group_nid; } - /* Preferred node as the node with the most faults */ - if (max_faults && max_nid != p->numa_preferred_nid) { - /* Update the preferred nid and migrate task if possible */ - sched_setnuma(p, max_nid); - numa_migrate_preferred(p); + if (max_faults) { + /* Set the new preferred node */ + if (max_nid != p->numa_preferred_nid) + sched_setnuma(p, max_nid); + + if (task_node(p) != p->numa_preferred_nid) + numa_migrate_preferred(p); } } @@ -2899,7 +2915,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; if (delta_exec > ideal_runtime) { - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); /* * The current task ran long enough, ensure it doesn't get * re-elected due to buddy favours. @@ -2923,7 +2939,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) return; if (delta > ideal_runtime) - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); } static void @@ -3063,7 +3079,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * validating it and just reschedule. */ if (queued) { - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); return; } /* @@ -3254,7 +3270,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) * hierarchy can be throttled */ if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) - resched_task(rq_of(cfs_rq)->curr); + resched_curr(rq_of(cfs_rq)); } static __always_inline @@ -3360,7 +3376,11 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) cfs_rq->throttled = 1; cfs_rq->throttled_clock = rq_clock(rq); raw_spin_lock(&cfs_b->lock); - list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + /* + * Add to the _head_ of the list, so that an already-started + * distribute_cfs_runtime will not see us + */ + list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); if (!cfs_b->timer_active) __start_cfs_bandwidth(cfs_b, false); raw_spin_unlock(&cfs_b->lock); @@ -3410,14 +3430,15 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* determine whether we need to wake up potentially idle cpu */ if (rq->curr == rq->idle && rq->cfs.nr_running) - resched_task(rq->curr); + resched_curr(rq); } static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining, u64 expires) { struct cfs_rq *cfs_rq; - u64 runtime = remaining; + u64 runtime; + u64 starting_runtime = remaining; rcu_read_lock(); list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, @@ -3448,7 +3469,7 @@ next: } rcu_read_unlock(); - return remaining; + return starting_runtime - remaining; } /* @@ -3494,22 +3515,17 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) /* account preceding periods in which throttling occurred */ cfs_b->nr_throttled += overrun; - /* - * There are throttled entities so we must first use the new bandwidth - * to unthrottle them before making it generally available. This - * ensures that all existing debts will be paid before a new cfs_rq is - * allowed to run. - */ - runtime = cfs_b->runtime; runtime_expires = cfs_b->runtime_expires; - cfs_b->runtime = 0; /* - * This check is repeated as we are holding onto the new bandwidth - * while we unthrottle. This can potentially race with an unthrottled - * group trying to acquire new bandwidth from the global pool. + * This check is repeated as we are holding onto the new bandwidth while + * we unthrottle. This can potentially race with an unthrottled group + * trying to acquire new bandwidth from the global pool. This can result + * in us over-using our runtime if it is all used during this loop, but + * only by limited amounts in that extreme case. */ - while (throttled && runtime > 0) { + while (throttled && cfs_b->runtime > 0) { + runtime = cfs_b->runtime; raw_spin_unlock(&cfs_b->lock); /* we can't nest cfs_b->lock while distributing bandwidth */ runtime = distribute_cfs_runtime(cfs_b, runtime, @@ -3517,10 +3533,10 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) raw_spin_lock(&cfs_b->lock); throttled = !list_empty(&cfs_b->throttled_cfs_rq); + + cfs_b->runtime -= min(runtime, cfs_b->runtime); } - /* return (any) remaining runtime */ - cfs_b->runtime = runtime; /* * While we are ensured activity in the period following an * unthrottle, this also covers the case in which the new bandwidth is @@ -3631,10 +3647,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) return; } - if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) { + if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) runtime = cfs_b->runtime; - cfs_b->runtime = 0; - } + expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); @@ -3645,7 +3660,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) raw_spin_lock(&cfs_b->lock); if (expires == cfs_b->runtime_expires) - cfs_b->runtime = runtime; + cfs_b->runtime -= min(runtime, cfs_b->runtime); raw_spin_unlock(&cfs_b->lock); } @@ -3775,6 +3790,19 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_cancel(&cfs_b->slack_timer); } +static void __maybe_unused update_runtime_enabled(struct rq *rq) +{ + struct cfs_rq *cfs_rq; + + for_each_leaf_cfs_rq(rq, cfs_rq) { + struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth; + + raw_spin_lock(&cfs_b->lock); + cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; + raw_spin_unlock(&cfs_b->lock); + } +} + static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) { struct cfs_rq *cfs_rq; @@ -3788,6 +3816,12 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) * there's some valid quota amount */ cfs_rq->runtime_remaining = 1; + /* + * Offline rq is schedulable till cpu is completely disabled + * in take_cpu_down(), so we prevent new cfs throttling here. + */ + cfs_rq->runtime_enabled = 0; + if (cfs_rq_throttled(cfs_rq)) unthrottle_cfs_rq(cfs_rq); } @@ -3831,6 +3865,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) return NULL; } static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} +static inline void update_runtime_enabled(struct rq *rq) {} static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {} #endif /* CONFIG_CFS_BANDWIDTH */ @@ -3854,7 +3889,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) if (delta < 0) { if (rq->curr == p) - resched_task(p); + resched_curr(rq); return; } @@ -4723,7 +4758,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; preempt: - resched_task(curr); + resched_curr(rq); /* * Only set the backward buddy when the current task is still * on the rq. This can happen when a wakeup gets interleaved @@ -5094,8 +5129,7 @@ static void move_task(struct task_struct *p, struct lb_env *env) /* * Is this task likely cache-hot: */ -static int -task_hot(struct task_struct *p, u64 now) +static int task_hot(struct task_struct *p, struct lb_env *env) { s64 delta; @@ -5108,7 +5142,7 @@ task_hot(struct task_struct *p, u64 now) /* * Buddy candidates are cache hot: */ - if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running && + if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running && (&p->se == cfs_rq_of(&p->se)->next || &p->se == cfs_rq_of(&p->se)->last)) return 1; @@ -5118,7 +5152,7 @@ task_hot(struct task_struct *p, u64 now) if (sysctl_sched_migration_cost == 0) return 0; - delta = now - p->se.exec_start; + delta = rq_clock_task(env->src_rq) - p->se.exec_start; return delta < (s64)sysctl_sched_migration_cost; } @@ -5272,7 +5306,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * 2) task is cache cold, or * 3) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq)); + tsk_cache_hot = task_hot(p, env); if (!tsk_cache_hot) tsk_cache_hot = migrate_degrades_locality(p, env); @@ -5864,10 +5898,12 @@ static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *gro * @load_idx: Load index of sched_domain of this_cpu for load calc. * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. + * @overload: Indicate more than one runnable task for any CPU. */ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, - int local_group, struct sg_lb_stats *sgs) + int local_group, struct sg_lb_stats *sgs, + bool *overload) { unsigned long load; int i; @@ -5885,6 +5921,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_load += load; sgs->sum_nr_running += rq->nr_running; + + if (rq->nr_running > 1) + *overload = true; + #ifdef CONFIG_NUMA_BALANCING sgs->nr_numa_running += rq->nr_numa_running; sgs->nr_preferred_running += rq->nr_preferred_running; @@ -5995,6 +6035,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats tmp_sgs; int load_idx, prefer_sibling = 0; + bool overload = false; if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1; @@ -6015,7 +6056,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_group_capacity(env->sd, env->dst_cpu); } - update_sg_lb_stats(env, sg, load_idx, local_group, sgs); + update_sg_lb_stats(env, sg, load_idx, local_group, sgs, + &overload); if (local_group) goto next_group; @@ -6049,6 +6091,13 @@ next_group: if (env->sd->flags & SD_NUMA) env->fbq_type = fbq_classify_group(&sds->busiest_stat); + + if (!env->sd->parent) { + /* update overload indicator if we are at root domain */ + if (env->dst_rq->rd->overload != overload) + env->dst_rq->rd->overload = overload; + } + } /** @@ -6767,7 +6816,8 @@ static int idle_balance(struct rq *this_rq) */ this_rq->idle_stamp = rq_clock(this_rq); - if (this_rq->avg_idle < sysctl_sched_migration_cost) { + if (this_rq->avg_idle < sysctl_sched_migration_cost || + !this_rq->rd->overload) { rcu_read_lock(); sd = rcu_dereference_check_sched_domain(this_rq->sd); if (sd) @@ -7325,6 +7375,8 @@ void trigger_load_balance(struct rq *rq) static void rq_online_fair(struct rq *rq) { update_sysctl(); + + update_runtime_enabled(rq); } static void rq_offline_fair(struct rq *rq) @@ -7398,7 +7450,7 @@ static void task_fork_fair(struct task_struct *p) * 'current' within the tree based on its new key value. */ swap(curr->vruntime, se->vruntime); - resched_task(rq->curr); + resched_curr(rq); } se->vruntime -= cfs_rq->min_vruntime; @@ -7423,7 +7475,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) */ if (rq->curr == p) { if (p->prio > oldprio) - resched_task(rq->curr); + resched_curr(rq); } else check_preempt_curr(rq, p, 0); } @@ -7486,7 +7538,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) * if we can still preempt the current task. */ if (rq->curr == p) - resched_task(rq->curr); + resched_curr(rq); else check_preempt_curr(rq, p, 0); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index cf009fb0bc25..9f1608f99819 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -79,7 +79,7 @@ static void cpuidle_idle_call(void) struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; - bool broadcast; + unsigned int broadcast; /* * Check if the idle task must be rescheduled. If it is the @@ -135,7 +135,7 @@ use_default: goto exit_idle; } - broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP); + broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP; /* * Tell the time framework to switch to a broadcast timer diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 879f2b75266a..67ad4e7f506a 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -20,7 +20,7 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) */ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags) { - resched_task(rq->idle); + resched_curr(rq); } static struct task_struct * diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a49083192c64..5f6edca4fafd 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -463,9 +463,10 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; + struct rq *rq = rq_of_rt_rq(rt_rq); struct sched_rt_entity *rt_se; - int cpu = cpu_of(rq_of_rt_rq(rt_rq)); + int cpu = cpu_of(rq); rt_se = rt_rq->tg->rt_se[cpu]; @@ -476,7 +477,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) enqueue_rt_entity(rt_se, false); if (rt_rq->highest_prio.curr < curr->prio) - resched_task(curr); + resched_curr(rq); } } @@ -566,7 +567,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) return; enqueue_top_rt_rq(rt_rq); - resched_task(rq->curr); + resched_curr(rq); } static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) @@ -740,6 +741,9 @@ balanced: rt_rq->rt_throttled = 0; raw_spin_unlock(&rt_rq->rt_runtime_lock); raw_spin_unlock(&rt_b->rt_runtime_lock); + + /* Make rt_rq available for pick_next_task() */ + sched_rt_rq_enqueue(rt_rq); } } @@ -948,7 +952,7 @@ static void update_curr_rt(struct rq *rq) raw_spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_time += delta_exec; if (sched_rt_runtime_exceeded(rt_rq)) - resched_task(curr); + resched_curr(rq); raw_spin_unlock(&rt_rq->rt_runtime_lock); } } @@ -1363,7 +1367,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) * to try and push current away: */ requeue_task_rt(rq, p, 1); - resched_task(rq->curr); + resched_curr(rq); } #endif /* CONFIG_SMP */ @@ -1374,7 +1378,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags) { if (p->prio < rq->curr->prio) { - resched_task(rq->curr); + resched_curr(rq); return; } @@ -1690,7 +1694,7 @@ retry: * just reschedule current. */ if (unlikely(next_task->prio < rq->curr->prio)) { - resched_task(rq->curr); + resched_curr(rq); return 0; } @@ -1737,7 +1741,7 @@ retry: activate_task(lowest_rq, next_task, 0); ret = 1; - resched_task(lowest_rq->curr); + resched_curr(lowest_rq); double_unlock_balance(rq, lowest_rq); @@ -1936,7 +1940,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) return; if (pull_rt_task(rq)) - resched_task(rq->curr); + resched_curr(rq); } void __init init_sched_rt_class(void) @@ -1974,7 +1978,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) check_resched = 0; #endif /* CONFIG_SMP */ if (check_resched && p->prio < rq->curr->prio) - resched_task(rq->curr); + resched_curr(rq); } } @@ -2003,11 +2007,11 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) * Only reschedule if p is still on the same runqueue. */ if (p->prio > rq->rt.highest_prio.curr && rq->curr == p) - resched_task(p); + resched_curr(rq); #else /* For UP simply resched on drop of prio */ if (oldprio < p->prio) - resched_task(p); + resched_curr(rq); #endif /* CONFIG_SMP */ } else { /* @@ -2016,7 +2020,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) * then reschedule. */ if (p->prio < rq->curr->prio) - resched_task(rq->curr); + resched_curr(rq); } } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 31cc02ebc54e..579712f4e9d5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -477,6 +477,9 @@ struct root_domain { cpumask_var_t span; cpumask_var_t online; + /* Indicate more than one runnable task for any CPU */ + bool overload; + /* * The bit corresponding to a CPU gets set here if such CPU has more * than one runnable -deadline task (as it is below for RT tasks). @@ -884,20 +887,10 @@ enum { #undef SCHED_FEAT #if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) -static __always_inline bool static_branch__true(struct static_key *key) -{ - return static_key_true(key); /* Not out of line branch. */ -} - -static __always_inline bool static_branch__false(struct static_key *key) -{ - return static_key_false(key); /* Out of line branch. */ -} - #define SCHED_FEAT(name, enabled) \ static __always_inline bool static_branch_##name(struct static_key *key) \ { \ - return static_branch__##enabled(key); \ + return static_key_##enabled(key); \ } #include "features.h" @@ -1196,7 +1189,7 @@ extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); extern void init_sched_dl_class(void); -extern void resched_task(struct task_struct *p); +extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; @@ -1218,15 +1211,26 @@ static inline void add_nr_running(struct rq *rq, unsigned count) rq->nr_running = prev_nr + count; -#ifdef CONFIG_NO_HZ_FULL if (prev_nr < 2 && rq->nr_running >= 2) { +#ifdef CONFIG_SMP + if (!rq->rd->overload) + rq->rd->overload = true; +#endif + +#ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_cpu(rq->cpu)) { - /* Order rq->nr_running write against the IPI */ - smp_wmb(); - smp_send_reschedule(rq->cpu); + /* + * Tick is needed if more than one task runs on a CPU. + * Send the target an IPI to kick it out of nohz mode. + * + * We assume that IPI implies full memory barrier and the + * new value of rq->nr_running is visible on reception + * from the target. + */ + tick_nohz_full_kick_cpu(rq->cpu); } - } #endif + } } static inline void sub_nr_running(struct rq *rq, unsigned count) diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 0ffa20ae657b..15cab1a4f84e 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -319,14 +319,14 @@ EXPORT_SYMBOL(wake_bit_function); */ int __sched __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { int ret = 0; do { prepare_to_wait(wq, &q->wait, mode); if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(q->key.flags); + ret = (*action)(&q->key); } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); finish_wait(wq, &q->wait); return ret; @@ -334,7 +334,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, EXPORT_SYMBOL(__wait_on_bit); int __sched out_of_line_wait_on_bit(void *word, int bit, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { wait_queue_head_t *wq = bit_waitqueue(word, bit); DEFINE_WAIT_BIT(wait, word, bit); @@ -345,7 +345,7 @@ EXPORT_SYMBOL(out_of_line_wait_on_bit); int __sched __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { do { int ret; @@ -353,7 +353,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait_exclusive(wq, &q->wait, mode); if (!test_bit(q->key.bit_nr, q->key.flags)) continue; - ret = action(q->key.flags); + ret = action(&q->key); if (!ret) continue; abort_exclusive_wait(wq, &q->wait, mode, &q->key); @@ -365,7 +365,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, EXPORT_SYMBOL(__wait_on_bit_lock); int __sched out_of_line_wait_on_bit_lock(void *word, int bit, - int (*action)(void *), unsigned mode) + wait_bit_action_f *action, unsigned mode) { wait_queue_head_t *wq = bit_waitqueue(word, bit); DEFINE_WAIT_BIT(wait, word, bit); @@ -502,3 +502,21 @@ void wake_up_atomic_t(atomic_t *p) __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); } EXPORT_SYMBOL(wake_up_atomic_t); + +__sched int bit_wait(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait); + +__sched int bit_wait_io(struct wait_bit_key *word) +{ + if (signal_pending_state(current->state, current)) + return 1; + io_schedule(); + return 0; +} +EXPORT_SYMBOL(bit_wait_io); diff --git a/kernel/smp.c b/kernel/smp.c index 80c33f8de14f..487653b5844f 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -3,6 +3,7 @@ * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ +#include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> @@ -251,6 +252,14 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) csd->func(csd->info); csd_unlock(csd); } + + /* + * Handle irq works queued remotely by irq_work_queue_on(). + * Smp functions above are typically synchronous so they + * better run first since some other CPUs may be busy waiting + * for them. + */ + irq_work_run(); } /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f784d83e29f1..99aa6ee3908f 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -225,13 +225,15 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { }; /* - * Kick the current CPU if it's full dynticks in order to force it to + * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. */ -void tick_nohz_full_kick(void) +void tick_nohz_full_kick_cpu(int cpu) { - if (tick_nohz_full_cpu(smp_processor_id())) - irq_work_queue(&__get_cpu_var(nohz_full_kick_work)); + if (!tick_nohz_full_cpu(cpu)) + return; + + irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } static void nohz_full_kick_ipi(void *info) diff --git a/mm/filemap.c b/mm/filemap.c index 900edfaf6df5..65d44fd88c78 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -241,18 +241,6 @@ void delete_from_page_cache(struct page *page) } EXPORT_SYMBOL(delete_from_page_cache); -static int sleep_on_page(void *word) -{ - io_schedule(); - return 0; -} - -static int sleep_on_page_killable(void *word) -{ - sleep_on_page(word); - return fatal_signal_pending(current) ? -EINTR : 0; -} - static int filemap_check_errors(struct address_space *mapping) { int ret = 0; @@ -692,7 +680,7 @@ void wait_on_page_bit(struct page *page, int bit_nr) DEFINE_WAIT_BIT(wait, &page->flags, bit_nr); if (test_bit(bit_nr, &page->flags)) - __wait_on_bit(page_waitqueue(page), &wait, sleep_on_page, + __wait_on_bit(page_waitqueue(page), &wait, bit_wait_io, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(wait_on_page_bit); @@ -705,7 +693,7 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr) return 0; return __wait_on_bit(page_waitqueue(page), &wait, - sleep_on_page_killable, TASK_KILLABLE); + bit_wait_io, TASK_KILLABLE); } /** @@ -806,7 +794,7 @@ void __lock_page(struct page *page) { DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); - __wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page, + __wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_page); @@ -816,7 +804,7 @@ int __lock_page_killable(struct page *page) DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); return __wait_on_bit_lock(page_waitqueue(page), &wait, - sleep_on_page_killable, TASK_KILLABLE); + bit_wait_io, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__lock_page_killable); @@ -1978,18 +1978,12 @@ void ksm_migrate_page(struct page *newpage, struct page *oldpage) #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE -static int just_wait(void *word) -{ - schedule(); - return 0; -} - static void wait_while_offlining(void) { while (ksm_run & KSM_RUN_OFFLINE) { mutex_unlock(&ksm_thread_mutex); wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), - just_wait, TASK_UNINTERRUPTIBLE); + TASK_UNINTERRUPTIBLE); mutex_lock(&ksm_thread_mutex); } } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 0a43cce9a914..e090bffe1bf8 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2186,12 +2186,6 @@ static void hci_inq_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_INQUIRY, sizeof(cp), &cp); } -static int wait_inquiry(void *word) -{ - schedule(); - return signal_pending(current); -} - int hci_inquiry(void __user *arg) { __u8 __user *ptr = arg; @@ -2242,7 +2236,7 @@ int hci_inquiry(void __user *arg) /* Wait until Inquiry procedure finishes (HCI_INQUIRY flag is * cleared). If it is interrupted by a signal, return -EINTR. */ - if (wait_on_bit(&hdev->flags, HCI_INQUIRY, wait_inquiry, + if (wait_on_bit(&hdev->flags, HCI_INQUIRY, TASK_INTERRUPTIBLE)) return -EINTR; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c0365c14b858..9358c79fd589 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -250,7 +250,7 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue) } EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); -static int rpc_wait_bit_killable(void *word) +static int rpc_wait_bit_killable(struct wait_bit_key *key) { if (fatal_signal_pending(current)) return -ERESTARTSYS; @@ -309,7 +309,7 @@ static int rpc_complete_task(struct rpc_task *task) * to enforce taking of the wq->lock and hence avoid races with * rpc_complete_task(). */ -int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *)) +int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *action) { if (action == NULL) action = rpc_wait_bit_killable; diff --git a/security/keys/gc.c b/security/keys/gc.c index d3222b6d7d59..9609a7f0faea 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -92,15 +92,6 @@ static void key_gc_timer_func(unsigned long data) } /* - * wait_on_bit() sleep function for uninterruptible waiting - */ -static int key_gc_wait_bit(void *flags) -{ - schedule(); - return 0; -} - -/* * Reap keys of dead type. * * We use three flags to make sure we see three complete cycles of the garbage @@ -123,7 +114,7 @@ void key_gc_keytype(struct key_type *ktype) schedule_work(&key_gc_work); kdebug("sleep"); - wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE, key_gc_wait_bit, + wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE, TASK_UNINTERRUPTIBLE); key_gc_dead_keytype = NULL; diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 381411941cc1..26a94f18af94 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -21,24 +21,6 @@ #define key_negative_timeout 60 /* default timeout on a negative key's existence */ -/* - * wait_on_bit() sleep function for uninterruptible waiting - */ -static int key_wait_bit(void *flags) -{ - schedule(); - return 0; -} - -/* - * wait_on_bit() sleep function for interruptible waiting - */ -static int key_wait_bit_intr(void *flags) -{ - schedule(); - return signal_pending(current) ? -ERESTARTSYS : 0; -} - /** * complete_request_key - Complete the construction of a key. * @cons: The key construction record. @@ -592,10 +574,9 @@ int wait_for_key_construction(struct key *key, bool intr) int ret; ret = wait_on_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT, - intr ? key_wait_bit_intr : key_wait_bit, intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); - if (ret < 0) - return ret; + if (ret) + return -ERESTARTSYS; if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { smp_rmb(); return key->type_data.reject_error; |