From 85989106feb734437e2d598b639991b9185a43a6 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 8 May 2023 09:58:53 +0200 Subject: sched/deadline: Create DL BW alloc, free & check overflow interface While moving a set of tasks between exclusive cpusets, cpuset_can_attach() -> task_can_attach() calls dl_cpu_busy(..., p) for DL BW overflow checking and per-task DL BW allocation on the destination root_domain for the DL tasks in this set. This approach has the issue of not freeing already allocated DL BW in the following error cases: (1) The set of tasks includes multiple DL tasks and DL BW overflow checking fails for one of the subsequent DL tasks. (2) Another controller next to the cpuset controller which is attached to the same cgroup fails in its can_attach(). To address this problem rework dl_cpu_busy(): (1) Split it into dl_bw_check_overflow() & dl_bw_alloc() and add a dedicated dl_bw_free(). (2) dl_bw_alloc() & dl_bw_free() take a `u64 dl_bw` parameter instead of a `struct task_struct *p` used in dl_cpu_busy(). This allows to allocate DL BW for a set of tasks too rather than only for a single task. Signed-off-by: Dietmar Eggemann Signed-off-by: Juri Lelli Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index eed5d65b8d1f..0bee06542450 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1853,6 +1853,8 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int dl_bw_alloc(int cpu, u64 dl_bw); +extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); -- cgit v1.2.3 From 2ef269ef1ac006acf974793d975539244d77b28f Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 8 May 2023 09:58:54 +0200 Subject: cgroup/cpuset: Free DL BW in case can_attach() fails cpuset_can_attach() can fail. Postpone DL BW allocation until all tasks have been checked. DL BW is not allocated per-task but as a sum over all DL tasks migrating. If multiple controllers are attached to the cgroup next to the cpuset controller a non-cpuset can_attach() can fail. In this case free DL BW in cpuset_cancel_attach(). Finally, update cpuset DL task count (nr_deadline_tasks) only in cpuset_attach(). Suggested-by: Waiman Long Signed-off-by: Dietmar Eggemann Signed-off-by: Juri Lelli Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 +- kernel/cgroup/cpuset.c | 53 +++++++++++++++++++++++++++++++++++++++++++++----- kernel/sched/core.c | 17 ++-------------- 3 files changed, 51 insertions(+), 21 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0bee06542450..2553918f0b61 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1852,7 +1852,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); +extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b7168970fff2..2c76fcd9f0bc 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -198,6 +198,8 @@ struct cpuset { * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; + int nr_migrate_dl_tasks; + u64 sum_migrate_dl_bw; /* Invalid partition error code, not lock protected */ enum prs_errcode prs_err; @@ -2496,16 +2498,23 @@ static int cpuset_can_attach_check(struct cpuset *cs) return 0; } +static void reset_migrate_dl_data(struct cpuset *cs) +{ + cs->nr_migrate_dl_tasks = 0; + cs->sum_migrate_dl_bw = 0; +} + /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; - struct cpuset *cs; + struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -2516,7 +2525,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); @@ -2524,11 +2533,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) goto out_unlock; if (dl_task(task)) { - cs->nr_deadline_tasks++; - cpuset_attach_old_cs->nr_deadline_tasks--; + cs->nr_migrate_dl_tasks++; + cs->sum_migrate_dl_bw += task->dl.dl_bw; } } + if (!cs->nr_migrate_dl_tasks) + goto out_success; + + if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { + int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + + if (unlikely(cpu >= nr_cpu_ids)) { + reset_migrate_dl_data(cs); + ret = -EINVAL; + goto out_unlock; + } + + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) { + reset_migrate_dl_data(cs); + goto out_unlock; + } + } + +out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. @@ -2551,6 +2580,14 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); + + if (cs->nr_migrate_dl_tasks) { + int cpu = cpumask_any(cs->effective_cpus); + + dl_bw_free(cpu, cs->sum_migrate_dl_bw); + reset_migrate_dl_data(cs); + } + mutex_unlock(&cpuset_mutex); } @@ -2651,6 +2688,12 @@ static void cpuset_attach(struct cgroup_taskset *tset) out: cs->old_mems_allowed = cpuset_attach_nodemask_to; + if (cs->nr_migrate_dl_tasks) { + cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; + oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; + reset_migrate_dl_data(cs); + } + cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); @@ -3330,7 +3373,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) if (ret) goto out_unlock; - ret = task_can_attach(task, cs->effective_cpus); + ret = task_can_attach(task); if (ret) goto out_unlock; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index df659892d7d5..ed0d7381b2ec 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9294,8 +9294,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int task_can_attach(struct task_struct *p, - const struct cpumask *cs_effective_cpus) +int task_can_attach(struct task_struct *p) { int ret = 0; @@ -9308,21 +9307,9 @@ int task_can_attach(struct task_struct *p, * success of set_cpus_allowed_ptr() on all attached tasks * before cpus_mask may be changed. */ - if (p->flags & PF_NO_SETAFFINITY) { + if (p->flags & PF_NO_SETAFFINITY) ret = -EINVAL; - goto out; - } - - if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus); - if (unlikely(cpu >= nr_cpu_ids)) - return -EINVAL; - ret = dl_bw_alloc(cpu, p->dl.dl_bw); - } - -out: return ret; } -- cgit v1.2.3 From d5e1586617be7093ea3419e3fa9387ed833cdbb1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 2 Jun 2023 10:42:53 +0200 Subject: sched: Unconditionally use full-fat wait_task_inactive() While modifying wait_task_inactive() for PREEMPT_RT; the build robot noted that UP got broken. This led to audit and consideration of the UP implementation of wait_task_inactive(). It looks like the UP implementation is also broken for PREEMPT; consider task_current_syscall() getting preempted between the two calls to wait_task_inactive(). Therefore move the wait_task_inactive() implementation out of CONFIG_SMP and unconditionally use it. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230602103731.GA630648%40hirez.programming.kicks-ass.net --- include/linux/sched.h | 7 +- kernel/sched/core.c | 216 +++++++++++++++++++++++++------------------------- 2 files changed, 110 insertions(+), 113 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index eed5d65b8d1f..1292d38d66cc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2006,15 +2006,12 @@ static __always_inline void scheduler_ipi(void) */ preempt_fold_need_resched(); } -extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); #else static inline void scheduler_ipi(void) { } -static inline unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) -{ - return 1; -} #endif +extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); + /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 944c3ae39861..810cf7dc98cf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2213,6 +2213,114 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq); } +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * Wait for the thread to block in any of the states set in @match_state. + * If it changes, i.e. @p might have woken up, then return zero. When we + * succeed in waiting for @p to be off its CPU, we return a positive number + * (its total switch count). If a second call a short while later returns the + * same number, the caller can be sure that @p has remained unscheduled the + * whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) +{ + int running, queued; + struct rq_flags rf; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + /* + * We do the initial early heuristics without holding + * any task-queue locks at all. We'll only try to get + * the runqueue lock when things look like they will + * work out! + */ + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since "task_on_cpu()" will + * return false if the runqueue has changed and p + * is actually now running somewhere else! + */ + while (task_on_cpu(rq, p)) { + if (!(READ_ONCE(p->__state) & match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_rq_lock(p, &rf); + trace_sched_wait_task(p); + running = task_on_cpu(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; + if (READ_ONCE(p->__state) & match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &rf); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it was still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(queued)) { + ktime_t to = NSEC_PER_SEC / HZ; + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + #ifdef CONFIG_SMP static void @@ -3341,114 +3449,6 @@ out: } #endif /* CONFIG_NUMA_BALANCING */ -/* - * wait_task_inactive - wait for a thread to unschedule. - * - * Wait for the thread to block in any of the states set in @match_state. - * If it changes, i.e. @p might have woken up, then return zero. When we - * succeed in waiting for @p to be off its CPU, we return a positive number - * (its total switch count). If a second call a short while later returns the - * same number, the caller can be sure that @p has remained unscheduled the - * whole time. - * - * The caller must ensure that the task *will* unschedule sometime soon, - * else this function might spin for a *long* time. This function can't - * be called with interrupts off, or it may introduce deadlock with - * smp_call_function() if an IPI is sent by the same process we are - * waiting to become inactive. - */ -unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) -{ - int running, queued; - struct rq_flags rf; - unsigned long ncsw; - struct rq *rq; - - for (;;) { - /* - * We do the initial early heuristics without holding - * any task-queue locks at all. We'll only try to get - * the runqueue lock when things look like they will - * work out! - */ - rq = task_rq(p); - - /* - * If the task is actively running on another CPU - * still, just relax and busy-wait without holding - * any locks. - * - * NOTE! Since we don't hold any locks, it's not - * even sure that "rq" stays as the right runqueue! - * But we don't care, since "task_on_cpu()" will - * return false if the runqueue has changed and p - * is actually now running somewhere else! - */ - while (task_on_cpu(rq, p)) { - if (!(READ_ONCE(p->__state) & match_state)) - return 0; - cpu_relax(); - } - - /* - * Ok, time to look more closely! We need the rq - * lock now, to be *sure*. If we're wrong, we'll - * just go back and repeat. - */ - rq = task_rq_lock(p, &rf); - trace_sched_wait_task(p); - running = task_on_cpu(rq, p); - queued = task_on_rq_queued(p); - ncsw = 0; - if (READ_ONCE(p->__state) & match_state) - ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, p, &rf); - - /* - * If it changed from the expected state, bail out now. - */ - if (unlikely(!ncsw)) - break; - - /* - * Was it really running after all now that we - * checked with the proper locks actually held? - * - * Oops. Go back and try again.. - */ - if (unlikely(running)) { - cpu_relax(); - continue; - } - - /* - * It's not enough that it's not actively running, - * it must be off the runqueue _entirely_, and not - * preempted! - * - * So if it was still runnable (but just not actively - * running right now), it's preempted, and we should - * yield - it could be a while. - */ - if (unlikely(queued)) { - ktime_t to = NSEC_PER_SEC / HZ; - - set_current_state(TASK_UNINTERRUPTIBLE); - schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD); - continue; - } - - /* - * Ahh, all good. It wasn't running, and it wasn't - * runnable, which means that it will never become - * running in the future either. We're all done! - */ - break; - } - - return ncsw; -} - /*** * kick_process - kick a running thread to enter/exit the kernel * @p: the to-be-kicked thread -- cgit v1.2.3 From 0d625446d0a451a683a357799912b9e688629707 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 1 Jun 2023 16:58:53 +0200 Subject: backing_dev: remove current->backing_dev_info Patch series "cleanup the filemap / direct I/O interaction", v4. This series cleans up some of the generic write helper calling conventions and the page cache writeback / invalidation for direct I/O. This is a spinoff from the no-bufferhead kernel project, for which we'll want to an use iomap based buffered write path in the block layer. This patch (of 12): The last user of current->backing_dev_info disappeared in commit b9b1335e6403 ("remove bdi_congested() and wb_congested() and related functions"). Remove the field and all assignments to it. Link: https://lkml.kernel.org/r/20230601145904.1385409-1-hch@lst.de Link: https://lkml.kernel.org/r/20230601145904.1385409-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Christian Brauner Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Darrick J. Wong Acked-by: Theodore Ts'o Cc: Al Viro Cc: Andreas Gruenbacher Cc: Anna Schumaker Cc: Chao Yu Cc: Ilya Dryomov Cc: Jaegeuk Kim Cc: Jens Axboe Cc: Matthew Wilcox Cc: Miklos Szeredi Cc: Miklos Szeredi Cc: Trond Myklebust Cc: Xiubo Li Signed-off-by: Andrew Morton --- fs/btrfs/file.c | 6 +----- fs/ceph/file.c | 4 ---- fs/ext4/file.c | 2 -- fs/f2fs/file.c | 2 -- fs/fuse/file.c | 4 ---- fs/gfs2/file.c | 2 -- fs/nfs/file.c | 5 +---- fs/ntfs/file.c | 2 -- fs/ntfs3/file.c | 3 --- fs/xfs/xfs_file.c | 4 ---- include/linux/sched.h | 3 --- mm/filemap.c | 3 --- 12 files changed, 2 insertions(+), 38 deletions(-) (limited to 'include/linux/sched.h') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f649647392e0..ecd43ab66fa6 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1145,7 +1145,6 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, !(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) return -EAGAIN; - current->backing_dev_info = inode_to_bdi(inode); ret = file_remove_privs(file); if (ret) return ret; @@ -1165,10 +1164,8 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, loff_t end_pos = round_up(pos + count, fs_info->sectorsize); ret = btrfs_cont_expand(BTRFS_I(inode), oldsize, end_pos); - if (ret) { - current->backing_dev_info = NULL; + if (ret) return ret; - } } return 0; @@ -1689,7 +1686,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from, if (sync) atomic_dec(&inode->sync_writers); - current->backing_dev_info = NULL; return num_written; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index f4d8bf7dec88..c8ef72f723ba 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1791,9 +1791,6 @@ retry_snap: else ceph_start_io_write(inode); - /* We can write back this queue in page reclaim */ - current->backing_dev_info = inode_to_bdi(inode); - if (iocb->ki_flags & IOCB_APPEND) { err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false); if (err < 0) @@ -1940,7 +1937,6 @@ out: ceph_end_io_write(inode); out_unlocked: ceph_free_cap_flush(prealloc_cf); - current->backing_dev_info = NULL; return written ? written : err; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index d101b3b0c7da..bc430270c23c 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -285,9 +285,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, if (ret <= 0) goto out; - current->backing_dev_info = inode_to_bdi(inode); ret = generic_perform_write(iocb, from); - current->backing_dev_info = NULL; out: inode_unlock(inode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5ac53d2627d2..4f423d367a44 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -4517,9 +4517,7 @@ static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb, if (iocb->ki_flags & IOCB_NOWAIT) return -EOPNOTSUPP; - current->backing_dev_info = inode_to_bdi(inode); ret = generic_perform_write(iocb, from); - current->backing_dev_info = NULL; if (ret > 0) { iocb->ki_pos += ret; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 89d97f6188e0..97d435874b14 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1362,9 +1362,6 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) writethrough: inode_lock(inode); - /* We can write back this queue in page reclaim */ - current->backing_dev_info = inode_to_bdi(inode); - err = generic_write_checks(iocb, from); if (err <= 0) goto out; @@ -1409,7 +1406,6 @@ writethrough: iocb->ki_pos += written; } out: - current->backing_dev_info = NULL; inode_unlock(inode); if (written > 0) written = generic_write_sync(iocb, written); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 300844f50dcd..904a0d6ac1a1 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1041,11 +1041,9 @@ retry: goto out_unlock; } - current->backing_dev_info = inode_to_bdi(inode); pagefault_disable(); ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops); pagefault_enable(); - current->backing_dev_info = NULL; if (ret > 0) { iocb->ki_pos += ret; written += ret; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index f0edf5a36237..665ce3fc62ea 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -648,11 +648,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); result = generic_write_checks(iocb, from); - if (result > 0) { - current->backing_dev_info = inode_to_bdi(inode); + if (result > 0) result = generic_perform_write(iocb, from); - current->backing_dev_info = NULL; - } nfs_end_io_write(inode); if (result <= 0) goto out; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index c481b14e4fd9..e296f804a9c4 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1911,11 +1911,9 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) inode_lock(vi); /* We can write back this queue in page reclaim. */ - current->backing_dev_info = inode_to_bdi(vi); err = ntfs_prepare_file_for_write(iocb, from); if (iov_iter_count(from) && !err) written = ntfs_perform_write(file, from, iocb->ki_pos); - current->backing_dev_info = NULL; inode_unlock(vi); iocb->ki_pos += written; if (likely(written > 0)) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 9a3d55c367d9..86d16a2c8339 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -820,7 +820,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) if (!pages) return -ENOMEM; - current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) goto out; @@ -993,8 +992,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) out: kfree(pages); - current->backing_dev_info = NULL; - if (err < 0) return err; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index aede746541f8..431c3fd0e2b5 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -717,9 +717,6 @@ write_retry: if (ret) goto out; - /* We can write back this queue in page reclaim */ - current->backing_dev_info = inode_to_bdi(inode); - trace_xfs_file_buffered_write(iocb, from); ret = iomap_file_buffered_write(iocb, from, &xfs_buffered_write_iomap_ops); @@ -753,7 +750,6 @@ write_retry: goto write_retry; } - current->backing_dev_info = NULL; out: if (iolock) xfs_iunlock(ip, iolock); diff --git a/include/linux/sched.h b/include/linux/sched.h index eed5d65b8d1f..54780571fe9a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -41,7 +41,6 @@ /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; -struct backing_dev_info; struct bio_list; struct blk_plug; struct bpf_local_storage; @@ -1186,8 +1185,6 @@ struct task_struct { /* VM state: */ struct reclaim_state *reclaim_state; - struct backing_dev_info *backing_dev_info; - struct io_context *io_context; #ifdef CONFIG_COMPACTION diff --git a/mm/filemap.c b/mm/filemap.c index 570bc8c3db87..0d371ed91a68 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3964,8 +3964,6 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t err; ssize_t status; - /* We can write back this queue in page reclaim */ - current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) goto out; @@ -4026,7 +4024,6 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) iocb->ki_pos += written; } out: - current->backing_dev_info = NULL; return written ? written : err; } EXPORT_SYMBOL(__generic_file_write_iter); -- cgit v1.2.3