Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "24 fixes"

* emailed patches from Andrew Morton <[email protected]>: (24 commits)
  autofs: fix error return in autofs_fill_super()
  autofs: drop dentry reference only when it is never used
  fs/drop_caches.c: avoid softlockups in drop_pagecache_sb()
  mm: migrate: don't rely on __PageMovable() of newpage after unlocking it
  psi: clarify the Kconfig text for the default-disable option
  mm, memory_hotplug: __offline_pages fix wrong locking
  mm: hwpoison: use do_send_sig_info() instead of force_sig()
  kasan: mark file common so ftrace doesn't trace it
  init/Kconfig: fix grammar by moving a closing parenthesis
  lib/test_kmod.c: potential double free in error handling
  mm, oom: fix use-after-free in oom_kill_process
  mm/hotplug: invalid PFNs from pfn_to_online_page()
  mm,memory_hotplug: fix scan_movable_pages() for gigantic hugepages
  psi: fix aggregation idle shut-off
  mm, memory_hotplug: test_pages_in_a_zone do not pass the end of zone
  mm, memory_hotplug: is_mem_section_removable do not pass the end of a zone
  oom, oom_reaper: do not enqueue same task twice
  mm: migrate: make buffer_migrate_page_norefs() actually succeed
  kernel/exit.c: release ptraced tasks before zap_pid_ns_processes
  x86_64: increase stack size for KASAN_EXTRA
  ...

arch/c6x/include/asm/Kbuild

@@ -30,6 +30,7 @@ generic-y += pgalloc.h
 generic-y += preempt.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += tlbflush.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/c6x/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/h8300/include/asm/Kbuild

@@ -40,6 +40,7 @@ generic-y += preempt.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += spinlock.h
 generic-y += timex.h

arch/h8300/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/hexagon/include/asm/Kbuild

@@ -30,6 +30,7 @@ generic-y += rwsem.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/hexagon/include/uapi/asm/Kbuild

@@ -1,4 +1,3 @@
 include include/uapi/asm-generic/Kbuild.asm
 
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/m68k/include/asm/Kbuild

@@ -20,6 +20,7 @@ generic-y += mm-arch-hooks.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += sections.h
+generic-y += shmparam.h
 generic-y += spinlock.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/m68k/include/uapi/asm/Kbuild

@@ -2,4 +2,3 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generated-y += unistd_32.h
 generic-y += kvm_para.h
-generic-y += shmparam.h

arch/microblaze/include/asm/Kbuild

@@ -26,6 +26,7 @@ generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += syscalls.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/microblaze/include/uapi/asm/Kbuild

@@ -2,5 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generated-y += unistd_32.h
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/openrisc/include/asm/Kbuild

@@ -34,6 +34,7 @@ generic-y += qrwlock_types.h
 generic-y += qrwlock.h
 generic-y += sections.h
 generic-y += segment.h
+generic-y += shmparam.h
 generic-y += string.h
 generic-y += switch_to.h
 generic-y += topology.h

arch/openrisc/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/unicore32/include/asm/Kbuild

@@ -28,6 +28,7 @@ generic-y += preempt.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += syscalls.h
 generic-y += topology.h

arch/unicore32/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/x86/include/asm/page_64_types.h

@@ -7,7 +7,11 @@
 #endif
 
 #ifdef CONFIG_KASAN
+#ifdef CONFIG_KASAN_EXTRA
+#define KASAN_STACK_ORDER 2
+#else
 #define KASAN_STACK_ORDER 1
+#endif
 #else
 #define KASAN_STACK_ORDER 0
 #endif

fs/autofs/expire.c

@@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb,
 	pkt.len = dentry->d_name.len;
 	memcpy(pkt.name, dentry->d_name.name, pkt.len);
 	pkt.name[pkt.len] = '\0';
-	dput(dentry);
 
 	if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
 		ret = -EFAULT;
@@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb,
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
+	dput(dentry);
+
 	return ret;
 }
 

fs/autofs/inode.c

@@ -266,8 +266,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
 	}
 	root_inode = autofs_get_inode(s, S_IFDIR | 0755);
 	root = d_make_root(root_inode);
-	if (!root)
+	if (!root) {
+		ret = -ENOMEM;
 		goto fail_ino;
+	}
 	pipe = NULL;
 
 	root->d_fsdata = ino;

fs/drop_caches.c

@@ -21,15 +21,21 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
+		/*
+		 * We must skip inodes in unusual state. We may also skip
+		 * inodes without pages but we deliberately won't in case
+		 * we need to reschedule to avoid softlockups.
+		 */
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
-		    (inode->i_mapping->nrpages == 0)) {
+		    (inode->i_mapping->nrpages == 0 && !need_resched())) {
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb->s_inode_list_lock);
 
+		cond_resched();
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;

fs/proc/generic.c

@@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
 		inode = proc_get_inode(dir->i_sb, de);
 		if (!inode)
 			return ERR_PTR(-ENOMEM);
-		d_set_d_op(dentry, &proc_misc_dentry_ops);
+		d_set_d_op(dentry, de->proc_dops);
 		return d_splice_alias(inode, dentry);
 	}
 	read_unlock(&proc_subdir_lock);
@@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 	INIT_LIST_HEAD(&ent->pde_openers);
 	proc_set_user(ent, (*parent)->uid, (*parent)->gid);
 
+	ent->proc_dops = &proc_misc_dentry_ops;
+
 out:
 	return ent;
 }

fs/proc/internal.h

@@ -44,6 +44,7 @@ struct proc_dir_entry {
 	struct completion *pde_unload_completion;
 	const struct inode_operations *proc_iops;
 	const struct file_operations *proc_fops;
+	const struct dentry_operations *proc_dops;
 	union {
 		const struct seq_operations *seq_ops;
 		int (*single_show)(struct seq_file *, void *);

fs/proc/proc_net.c

@@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode)
 	return maybe_get_net(PDE_NET(PDE(inode)));
 }
 
+static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	return 0;
+}
+
+static const struct dentry_operations proc_net_dentry_ops = {
+	.d_revalidate	= proc_net_d_revalidate,
+	.d_delete	= always_delete_dentry,
+};
+
+static void pde_force_lookup(struct proc_dir_entry *pde)
+{
+	/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+	pde->proc_dops = &proc_net_dentry_ops;
+}
+
 static int seq_open_net(struct inode *inode, struct file *file)
 {
 	unsigned int state_size = PDE(inode)->state_size;
@@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_seq_fops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
@@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_seq_fops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
@@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_single_fops;
 	p->single_show = show;
 	return proc_register(parent, p);
@@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_single_fops;
 	p->single_show = show;
 	p->write = write;

include/linux/memory_hotplug.h

@@ -21,14 +21,16 @@ struct vmem_altmap;
  * walkers which rely on the fully initialized page->flags and others
  * should use this rather than pfn_valid && pfn_to_page
  */
-#define pfn_to_online_page(pfn)				\
-({							\
-	struct page *___page = NULL;			\
-	unsigned long ___nr = pfn_to_section_nr(pfn);	\
-							\
-	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\
-		___page = pfn_to_page(pfn);		\
-	___page;					\
+#define pfn_to_online_page(pfn)					   \
+({								   \
+	struct page *___page = NULL;				   \
+	unsigned long ___pfn = pfn;				   \
+	unsigned long ___nr = pfn_to_section_nr(___pfn);	   \
+								   \
+	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \
+	    pfn_valid_within(___pfn))				   \
+		___page = pfn_to_page(___pfn);			   \
+	___page;						   \
 })
 
 /*

include/linux/sched/coredump.h

@@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
 #define MMF_OOM_VICTIM		25	/* mm is the oom victim */
+#define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\

init/Kconfig

@@ -512,6 +512,17 @@ config PSI_DEFAULT_DISABLED
 	  per default but can be enabled through passing psi=1 on the
 	  kernel commandline during boot.
 
+	  This feature adds some code to the task wakeup and sleep
+	  paths of the scheduler. The overhead is too low to affect
+	  common scheduling-intense workloads in practice (such as
+	  webservers, memcache), but it does show up in artificial
+	  scheduler stress tests, such as hackbench.
+
+	  If you are paranoid and not sure what the kernel will be
+	  used for, say Y.
+
+	  Say N if unsure.
+
 endmenu # "CPU/Task time and stats accounting"
 
 config CPU_ISOLATION
@@ -825,7 +836,7 @@ config CGROUP_PIDS
 	  PIDs controller is designed to stop this from happening.
 
 	  It should be noted that organisational operations (such as attaching
-	  to a cgroup hierarchy will *not* be blocked by the PIDs controller),
+	  to a cgroup hierarchy) will *not* be blocked by the PIDs controller,
 	  since the PIDs limit only affects a process's ability to fork, not to
 	  attach to a cgroup.
 

kernel/exit.c

@@ -558,12 +558,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p)
 	return NULL;
 }
 
-static struct task_struct *find_child_reaper(struct task_struct *father)
+static struct task_struct *find_child_reaper(struct task_struct *father,
+						struct list_head *dead)
 	__releases(&tasklist_lock)
 	__acquires(&tasklist_lock)
 {
 	struct pid_namespace *pid_ns = task_active_pid_ns(father);
 	struct task_struct *reaper = pid_ns->child_reaper;
+	struct task_struct *p, *n;
 
 	if (likely(reaper != father))
 		return reaper;
@@ -579,6 +581,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father)
 		panic("Attempted to kill init! exitcode=0x%08x\n",
 			father->signal->group_exit_code ?: father->exit_code);
 	}
+
+	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
+		release_task(p);
+	}
+
 	zap_pid_ns_processes(pid_ns);
 	write_lock_irq(&tasklist_lock);
 
@@ -668,7 +676,7 @@ static void forget_original_parent(struct task_struct *father,
 		exit_ptrace(father, dead);
 
 	/* Can drop and reacquire tasklist_lock */
-	reaper = find_child_reaper(father);
+	reaper = find_child_reaper(father, dead);
 	if (list_empty(&father->children))
 		return;
 

kernel/sched/psi.c

@@ -124,6 +124,7 @@
  * sampling of the aggregate task states would be.
  */
 
+#include "../workqueue_internal.h"
 #include <linux/sched/loadavg.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
@@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
 			groupc->tasks[t]++;
 
 	write_seqcount_end(&groupc->seq);
-
-	if (!delayed_work_pending(&group->clock_work))
-		schedule_delayed_work(&group->clock_work, PSI_FREQ);
 }
 
 static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
 	struct psi_group *group;
+	bool wake_clock = true;
 	void *iter = NULL;
 
 	if (!task->pid)
@@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 	task->psi_flags &= ~clear;
 	task->psi_flags |= set;
 
-	while ((group = iterate_groups(task, &iter)))
+	/*
+	 * Periodic aggregation shuts off if there is a period of no
+	 * task changes, so we wake it back up if necessary. However,
+	 * don't do this if the task change is the aggregation worker
+	 * itself going to sleep, or we'll ping-pong forever.
+	 */
+	if (unlikely((clear & TSK_RUNNING) &&
+		     (task->flags & PF_WQ_WORKER) &&
+		     wq_worker_last_func(task) == psi_update_work))
+		wake_clock = false;
+
+	while ((group = iterate_groups(task, &iter))) {
 		psi_group_change(group, cpu, clear, set);
+		if (wake_clock && !delayed_work_pending(&group->clock_work))
+			schedule_delayed_work(&group->clock_work, PSI_FREQ);
+	}
 }
 
 void psi_memstall_tick(struct task_struct *task, int cpu)