Merge branch 'akpm' (Andrew's patch-bomb)

Merge misc patches from Andrew Morton:

 - the "misc" tree - stuff from all over the map

 - checkpatch updates

 - fatfs

 - kmod changes

 - procfs

 - cpumask

 - UML

 - kexec

 - mqueue

 - rapidio

 - pidns

 - some checkpoint-restore feature work.  Reluctantly.  Most of it
   delayed a release.  I'm still rather worried that we don't have a
   clear roadmap to completion for this work.

* emailed from Andrew Morton <akpm@linux-foundation.org>: (78 patches)
  kconfig: update compression algorithm info
  c/r: prctl: add ability to set new mm_struct::exe_file
  c/r: prctl: extend PR_SET_MM to set up more mm_struct entries
  c/r: procfs: add arg_start/end, env_start/end and exit_code members to /proc/$pid/stat
  syscalls, x86: add __NR_kcmp syscall
  fs, proc: introduce /proc/<pid>/task/<tid>/children entry
  sysctl: make kernel.ns_last_pid control dependent on CHECKPOINT_RESTORE
  aio/vfs: cleanup of rw_copy_check_uvector() and compat_rw_copy_check_uvector()
  eventfd: change int to __u64 in eventfd_signal()
  fs/nls: add Apple NLS
  pidns: make killed children autoreap
  pidns: use task_active_pid_ns in do_notify_parent
  rapidio/tsi721: add DMA engine support
  rapidio: add DMA engine support for RIO data transfers
  ipc/mqueue: add rbtree node caching support
  tools/selftests: add mq_perf_tests
  ipc/mqueue: strengthen checks on mqueue creation
  ipc/mqueue: correct mq_attr_ok test
  ipc/mqueue: improve performance of send/recv
  selftests: add mq_open_tests
  ...

5 files changed, 238 insertions, 77 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index dc4c5a7..c1c207c 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -370,7 +370,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 			struct pid *pid, struct task_struct *task, int whole)
 {
 	unsigned long vsize, eip, esp, wchan = ~0UL;
-	long priority, nice;
+	int priority, nice;
 	int tty_pgrp = -1, tty_nr = 0;
 	sigset_t sigign, sigcatch;
 	char state;
@@ -492,7 +492,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, ' ', 0);
 	seq_put_decimal_ull(m, ' ', start_time);
 	seq_put_decimal_ull(m, ' ', vsize);
-	seq_put_decimal_ll(m, ' ', mm ? get_mm_rss(mm) : 0);
+	seq_put_decimal_ull(m, ' ', mm ? get_mm_rss(mm) : 0);
 	seq_put_decimal_ull(m, ' ', rsslim);
 	seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0);
 	seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0);
@@ -517,9 +517,23 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task));
 	seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime));
 	seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime));
-	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_data : 0);
-	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->end_data : 0);
-	seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_brk : 0);
+
+	if (mm && permitted) {
+		seq_put_decimal_ull(m, ' ', mm->start_data);
+		seq_put_decimal_ull(m, ' ', mm->end_data);
+		seq_put_decimal_ull(m, ' ', mm->start_brk);
+		seq_put_decimal_ull(m, ' ', mm->arg_start);
+		seq_put_decimal_ull(m, ' ', mm->arg_end);
+		seq_put_decimal_ull(m, ' ', mm->env_start);
+		seq_put_decimal_ull(m, ' ', mm->env_end);
+	} else
+		seq_printf(m, " 0 0 0 0 0 0 0");
+
+	if (permitted)
+		seq_put_decimal_ll(m, ' ', task->exit_code);
+	else
+		seq_put_decimal_ll(m, ' ', 0);
+
 	seq_putc(m, '\n');
 	if (mm)
 		mmput(mm);
@@ -565,3 +579,126 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 
 	return 0;
 }
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static struct pid *
+get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
+{
+	struct task_struct *start, *task;
+	struct pid *pid = NULL;
+
+	read_lock(&tasklist_lock);
+
+	start = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (!start)
+		goto out;
+
+	/*
+	 * Lets try to continue searching first, this gives
+	 * us significant speedup on children-rich processes.
+	 */
+	if (pid_prev) {
+		task = pid_task(pid_prev, PIDTYPE_PID);
+		if (task && task->real_parent == start &&
+		    !(list_empty(&task->sibling))) {
+			if (list_is_last(&task->sibling, &start->children))
+				goto out;
+			task = list_first_entry(&task->sibling,
+						struct task_struct, sibling);
+			pid = get_pid(task_pid(task));
+			goto out;
+		}
+	}
+
+	/*
+	 * Slow search case.
+	 *
+	 * We might miss some children here if children
+	 * are exited while we were not holding the lock,
+	 * but it was never promised to be accurate that
+	 * much.
+	 *
+	 * "Just suppose that the parent sleeps, but N children
+	 *  exit after we printed their tids. Now the slow paths
+	 *  skips N extra children, we miss N tasks." (c)
+	 *
+	 * So one need to stop or freeze the leader and all
+	 * its children to get a precise result.
+	 */
+	list_for_each_entry(task, &start->children, sibling) {
+		if (pos-- == 0) {
+			pid = get_pid(task_pid(task));
+			break;
+		}
+	}
+
+out:
+	read_unlock(&tasklist_lock);
+	return pid;
+}
+
+static int children_seq_show(struct seq_file *seq, void *v)
+{
+	struct inode *inode = seq->private;
+	pid_t pid;
+
+	pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
+	return seq_printf(seq, "%d ", pid);
+}
+
+static void *children_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return get_children_pid(seq->private, NULL, *pos);
+}
+
+static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct pid *pid;
+
+	pid = get_children_pid(seq->private, v, *pos + 1);
+	put_pid(v);
+
+	++*pos;
+	return pid;
+}
+
+static void children_seq_stop(struct seq_file *seq, void *v)
+{
+	put_pid(v);
+}
+
+static const struct seq_operations children_seq_ops = {
+	.start	= children_seq_start,
+	.next	= children_seq_next,
+	.stop	= children_seq_stop,
+	.show	= children_seq_show,
+};
+
+static int children_seq_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &children_seq_ops);
+	if (ret)
+		return ret;
+
+	m = file->private_data;
+	m->private = inode;
+
+	return ret;
+}
+
+int children_seq_release(struct inode *inode, struct file *file)
+{
+	seq_release(inode, file);
+	return 0;
+}
+
+const struct file_operations proc_tid_children_operations = {
+	.open    = children_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = children_seq_release,
+};
+#endif /* CONFIG_CHECKPOINT_RESTORE */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d7d7118..616f41a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -199,11 +199,6 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
 	return result;
 }
 
-struct mm_struct *mm_for_maps(struct task_struct *task)
-{
-	return mm_access(task, PTRACE_MODE_READ);
-}
-
 static int proc_pid_cmdline(struct task_struct *task, char * buffer)
 {
 	int res = 0;
@@ -243,7 +238,7 @@ out:
 
 static int proc_pid_auxv(struct task_struct *task, char *buffer)
 {
-	struct mm_struct *mm = mm_for_maps(task);
+	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
 	int res = PTR_ERR(mm);
 	if (mm && !IS_ERR(mm)) {
 		unsigned int nwords = 0;
@@ -679,7 +674,7 @@ static const struct file_operations proc_single_file_operations = {
 	.release	= single_release,
 };
 
-static int mem_open(struct inode* inode, struct file* file)
+static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
 {
 	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
 	struct mm_struct *mm;
@@ -687,7 +682,7 @@ static int mem_open(struct inode* inode, struct file* file)
 	if (!task)
 		return -ESRCH;
 
-	mm = mm_access(task, PTRACE_MODE_ATTACH);
+	mm = mm_access(task, mode);
 	put_task_struct(task);
 
 	if (IS_ERR(mm))
@@ -707,6 +702,11 @@ static int mem_open(struct inode* inode, struct file* file)
 	return 0;
 }
 
+static int mem_open(struct inode *inode, struct file *file)
+{
+	return __mem_open(inode, file, PTRACE_MODE_ATTACH);
+}
+
 static ssize_t mem_rw(struct file *file, char __user *buf,
 			size_t count, loff_t *ppos, int write)
 {
@@ -803,30 +803,29 @@ static const struct file_operations proc_mem_operations = {
 	.release	= mem_release,
 };
 
+static int environ_open(struct inode *inode, struct file *file)
+{
+	return __mem_open(inode, file, PTRACE_MODE_READ);
+}
+
 static ssize_t environ_read(struct file *file, char __user *buf,
 			size_t count, loff_t *ppos)
 {
-	struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
 	char *page;
 	unsigned long src = *ppos;
-	int ret = -ESRCH;
-	struct mm_struct *mm;
+	int ret = 0;
+	struct mm_struct *mm = file->private_data;
 
-	if (!task)
-		goto out_no_task;
+	if (!mm)
+		return 0;
 
-	ret = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
-		goto out;
-
-
-	mm = mm_for_maps(task);
-	ret = PTR_ERR(mm);
-	if (!mm || IS_ERR(mm))
-		goto out_free;
+		return -ENOMEM;
 
 	ret = 0;
+	if (!atomic_inc_not_zero(&mm->mm_users))
+		goto free;
 	while (count > 0) {
 		int this_len, retval, max_len;
 
@@ -838,7 +837,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 		max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
 		this_len = (this_len > max_len) ? max_len : this_len;
 
-		retval = access_process_vm(task, (mm->env_start + src),
+		retval = access_remote_vm(mm, (mm->env_start + src),
 			page, this_len, 0);
 
 		if (retval <= 0) {
@@ -857,19 +856,18 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 		count -= retval;
 	}
 	*ppos = src;
-
 	mmput(mm);
-out_free:
+
+free:
 	free_page((unsigned long) page);
-out:
-	put_task_struct(task);
-out_no_task:
 	return ret;
 }
 
 static const struct file_operations proc_environ_operations = {
+	.open		= environ_open,
 	.read		= environ_read,
 	.llseek		= generic_file_llseek,
+	.release	= mem_release,
 };
 
 static ssize_t oom_adjust_read(struct file *file, char __user *buf,
@@ -1850,7 +1848,7 @@ static const struct dentry_operations tid_fd_dentry_operations =
 static struct dentry *proc_fd_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
 {
-	unsigned fd = *(const unsigned *)ptr;
+	unsigned fd = (unsigned long)ptr;
  	struct inode *inode;
  	struct proc_inode *ei;
 	struct dentry *error = ERR_PTR(-ENOENT);
@@ -1887,7 +1885,7 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
 	if (fd == ~0U)
 		goto out;
 
-	result = instantiate(dir, dentry, task, &fd);
+	result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
 out:
 	put_task_struct(task);
 out_no_task:
@@ -1930,21 +1928,22 @@ static int proc_readfd_common(struct file * filp, void * dirent,
 			     fd++, filp->f_pos++) {
 				char name[PROC_NUMBUF];
 				int len;
+				int rv;
 
 				if (!fcheck_files(files, fd))
 					continue;
 				rcu_read_unlock();
 
 				len = snprintf(name, sizeof(name), "%d", fd);
-				if (proc_fill_cache(filp, dirent, filldir,
-						    name, len, instantiate,
-						    p, &fd) < 0) {
-					rcu_read_lock();
-					break;
-				}
+				rv = proc_fill_cache(filp, dirent, filldir,
+						     name, len, instantiate, p,
+						     (void *)(unsigned long)fd);
+				if (rv < 0)
+					goto out_fd_loop;
 				rcu_read_lock();
 			}
 			rcu_read_unlock();
+out_fd_loop:
 			put_files_struct(files);
 	}
 out:
@@ -2024,11 +2023,8 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 	if (!task)
 		goto out_notask;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
-		goto out;
-
-	mm = get_task_mm(task);
-	if (!mm)
+	mm = mm_access(task, PTRACE_MODE_READ);
+	if (IS_ERR_OR_NULL(mm))
 		goto out;
 
 	if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
@@ -2357,7 +2353,7 @@ static const struct inode_operations proc_fd_inode_operations = {
 static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
 {
-	unsigned fd = *(unsigned *)ptr;
+	unsigned fd = (unsigned long)ptr;
  	struct inode *inode;
  	struct proc_inode *ei;
 	struct dentry *error = ERR_PTR(-ENOENT);
@@ -3404,6 +3400,9 @@ static const struct pid_entry tid_base_stuff[] = {
 	ONE("stat",      S_IRUGO, proc_tid_stat),
 	ONE("statm",     S_IRUGO, proc_pid_statm),
 	REG("maps",      S_IRUGO, proc_tid_maps_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	REG("children",  S_IRUGO, proc_tid_children_operations),
+#endif
 #ifdef CONFIG_NUMA
 	REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
 #endif
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5f79bb8..eca4aca 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -31,8 +31,6 @@ struct vmalloc_info {
 	unsigned long	largest_chunk;
 };
 
-extern struct mm_struct *mm_for_maps(struct task_struct *);
-
 #ifdef CONFIG_MMU
 #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
 extern void get_vmalloc_info(struct vmalloc_info *vmi);
@@ -56,6 +54,7 @@ extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
 extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
 
+extern const struct file_operations proc_tid_children_operations;
 extern const struct file_operations proc_pid_maps_operations;
 extern const struct file_operations proc_tid_maps_operations;
 extern const struct file_operations proc_pid_numa_maps_operations;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7faaf2a..4540b8f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -125,7 +125,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	if (!priv->task)
 		return ERR_PTR(-ESRCH);
 
-	mm = mm_for_maps(priv->task);
+	mm = mm_access(priv->task, PTRACE_MODE_READ);
 	if (!mm || IS_ERR(mm))
 		return mm;
 	down_read(&mm->mmap_sem);
@@ -393,6 +393,7 @@ struct mem_size_stats {
 	unsigned long anonymous;
 	unsigned long anonymous_thp;
 	unsigned long swap;
+	unsigned long nonlinear;
 	u64 pss;
 };
 
@@ -402,24 +403,33 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr,
 {
 	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = mss->vma;
-	struct page *page;
+	pgoff_t pgoff = linear_page_index(vma, addr);
+	struct page *page = NULL;
 	int mapcount;
 
-	if (is_swap_pte(ptent)) {
-		mss->swap += ptent_size;
-		return;
+	if (pte_present(ptent)) {
+		page = vm_normal_page(vma, addr, ptent);
+	} else if (is_swap_pte(ptent)) {
+		swp_entry_t swpent = pte_to_swp_entry(ptent);
+
+		if (!non_swap_entry(swpent))
+			mss->swap += ptent_size;
+		else if (is_migration_entry(swpent))
+			page = migration_entry_to_page(swpent);
+	} else if (pte_file(ptent)) {
+		if (pte_to_pgoff(ptent) != pgoff)
+			mss->nonlinear += ptent_size;
 	}
 
-	if (!pte_present(ptent))
-		return;
-
-	page = vm_normal_page(vma, addr, ptent);
 	if (!page)
 		return;
 
 	if (PageAnon(page))
 		mss->anonymous += ptent_size;
 
+	if (page->index != pgoff)
+		mss->nonlinear += ptent_size;
+
 	mss->resident += ptent_size;
 	/* Accumulate the size in pages that have been accessed. */
 	if (pte_young(ptent) || PageReferenced(page))
@@ -521,6 +531,10 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   (vma->vm_flags & VM_LOCKED) ?
 			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
+	if (vma->vm_flags & VM_NONLINEAR)
+		seq_printf(m, "Nonlinear:      %8lu kB\n",
+				mss.nonlinear >> 10);
+
 	if (m->count < m->size)  /* vma is copied successfully */
 		m->version = (vma != get_gate_vma(task->mm))
 			? vma->vm_start : 0;
@@ -700,6 +714,7 @@ struct pagemapread {
 
 #define PM_PRESENT          PM_STATUS(4LL)
 #define PM_SWAP             PM_STATUS(2LL)
+#define PM_FILE             PM_STATUS(1LL)
 #define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
 #define PM_END_OF_BUFFER    1
 
@@ -733,22 +748,33 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	return err;
 }
 
-static u64 swap_pte_to_pagemap_entry(pte_t pte)
+static void pte_to_pagemap_entry(pagemap_entry_t *pme,
+		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
-	swp_entry_t e = pte_to_swp_entry(pte);
-	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
-}
-
-static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte)
-{
-	if (is_swap_pte(pte))
-		*pme = make_pme(PM_PFRAME(swap_pte_to_pagemap_entry(pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP);
-	else if (pte_present(pte))
-		*pme = make_pme(PM_PFRAME(pte_pfn(pte))
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
-	else
+	u64 frame, flags;
+	struct page *page = NULL;
+
+	if (pte_present(pte)) {
+		frame = pte_pfn(pte);
+		flags = PM_PRESENT;
+		page = vm_normal_page(vma, addr, pte);
+	} else if (is_swap_pte(pte)) {
+		swp_entry_t entry = pte_to_swp_entry(pte);
+
+		frame = swp_type(entry) |
+			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+		flags = PM_SWAP;
+		if (is_migration_entry(entry))
+			page = migration_entry_to_page(entry);
+	} else {
 		*pme = make_pme(PM_NOT_PRESENT);
+		return;
+	}
+
+	if (page && !PageAnon(page))
+		flags |= PM_FILE;
+
+	*pme = make_pme(PM_PFRAME(frame) | PM_PSHIFT(PAGE_SHIFT) | flags);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -815,7 +841,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pte_to_pagemap_entry(&pme, *pte);
+			pte_to_pagemap_entry(&pme, vma, addr, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
@@ -869,11 +895,11 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
  * For each page in the address space, this file contains one 64-bit entry
  * consisting of the following:
  *
- * Bits 0-55  page frame number (PFN) if present
+ * Bits 0-54  page frame number (PFN) if present
  * Bits 0-4   swap type if swapped
- * Bits 5-55  swap offset if swapped
+ * Bits 5-54  swap offset if swapped
  * Bits 55-60 page shift (page size = 1<<page shift)
- * Bit  61    reserved for future use
+ * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present
  *
@@ -919,7 +945,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!pm.buffer)
 		goto out_task;
 
-	mm = mm_for_maps(task);
+	mm = mm_access(task, PTRACE_MODE_READ);
 	ret = PTR_ERR(mm);
 	if (!mm || IS_ERR(mm))
 		goto out_free;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 74fe164..1ccfa53 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -223,7 +223,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	if (!priv->task)
 		return ERR_PTR(-ESRCH);
 
-	mm = mm_for_maps(priv->task);
+	mm = mm_access(priv->task, PTRACE_MODE_READ);
 	if (!mm || IS_ERR(mm)) {
 		put_task_struct(priv->task);
 		priv->task = NULL;