Merge branch 'next' into for-linus

Prepare first set of updates for 3.10 merge window.

1 files changed, 142 insertions, 200 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 144a96732dd7..69078c7cef1f 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -73,6 +73,7 @@
 #include <linux/security.h>
 #include <linux/ptrace.h>
 #include <linux/tracehook.h>
+#include <linux/printk.h>
 #include <linux/cgroup.h>
 #include <linux/cpuset.h>
 #include <linux/audit.h>
@@ -383,7 +384,7 @@ static int lstats_open(struct inode *inode, struct file *file)
 static ssize_t lstats_write(struct file *file, const char __user *buf,
 			    size_t count, loff_t *offs)
 {
-	struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+	struct task_struct *task = get_proc_task(file_inode(file));
 
 	if (!task)
 		return -ESRCH;
@@ -542,13 +543,6 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr)
 	if (error)
 		return error;
 
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
-		if (error)
-			return error;
-	}
-
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
@@ -609,7 +603,7 @@ static const struct inode_operations proc_def_inode_operations = {
 static ssize_t proc_info_read(struct file * file, char __user * buf,
 			  size_t count, loff_t *ppos)
 {
-	struct inode * inode = file->f_path.dentry->d_inode;
+	struct inode * inode = file_inode(file);
 	unsigned long page;
 	ssize_t length;
 	struct task_struct *task = get_proc_task(inode);
@@ -675,7 +669,7 @@ static const struct file_operations proc_single_file_operations = {
 
 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 task_struct *task = get_proc_task(file_inode(file));
 	struct mm_struct *mm;
 
 	if (!task)
@@ -873,12 +867,119 @@ static const struct file_operations proc_environ_operations = {
 	.release	= mem_release,
 };
 
+static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
+			    loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	char buffer[PROC_NUMBUF];
+	int oom_adj = OOM_ADJUST_MIN;
+	size_t len;
+	unsigned long flags;
+
+	if (!task)
+		return -ESRCH;
+	if (lock_task_sighand(task, &flags)) {
+		if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+			oom_adj = OOM_ADJUST_MAX;
+		else
+			oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+				  OOM_SCORE_ADJ_MAX;
+		unlock_task_sighand(task, &flags);
+	}
+	put_task_struct(task);
+	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
+	return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_adj_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[PROC_NUMBUF];
+	int oom_adj;
+	unsigned long flags;
+	int err;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	err = kstrtoint(strstrip(buffer), 0, &oom_adj);
+	if (err)
+		goto out;
+	if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) &&
+	     oom_adj != OOM_DISABLE) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	task = get_proc_task(file_inode(file));
+	if (!task) {
+		err = -ESRCH;
+		goto out;
+	}
+
+	task_lock(task);
+	if (!task->mm) {
+		err = -EINVAL;
+		goto err_task_lock;
+	}
+
+	if (!lock_task_sighand(task, &flags)) {
+		err = -ESRCH;
+		goto err_task_lock;
+	}
+
+	/*
+	 * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+	 * value is always attainable.
+	 */
+	if (oom_adj == OOM_ADJUST_MAX)
+		oom_adj = OOM_SCORE_ADJ_MAX;
+	else
+		oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+
+	if (oom_adj < task->signal->oom_score_adj &&
+	    !capable(CAP_SYS_RESOURCE)) {
+		err = -EACCES;
+		goto err_sighand;
+	}
+
+	/*
+	 * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+	 * /proc/pid/oom_score_adj instead.
+	 */
+	pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+		  current->comm, task_pid_nr(current), task_pid_nr(task),
+		  task_pid_nr(task));
+
+	task->signal->oom_score_adj = oom_adj;
+	trace_oom_score_adj_update(task);
+err_sighand:
+	unlock_task_sighand(task, &flags);
+err_task_lock:
+	task_unlock(task);
+	put_task_struct(task);
+out:
+	return err < 0 ? err : count;
+}
+
+static const struct file_operations proc_oom_adj_operations = {
+	.read		= oom_adj_read,
+	.write		= oom_adj_write,
+	.llseek		= generic_file_llseek,
+};
+
 static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 					size_t count, loff_t *ppos)
 {
-	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+	struct task_struct *task = get_proc_task(file_inode(file));
 	char buffer[PROC_NUMBUF];
-	int oom_score_adj = OOM_SCORE_ADJ_MIN;
+	short oom_score_adj = OOM_SCORE_ADJ_MIN;
 	unsigned long flags;
 	size_t len;
 
@@ -889,7 +990,7 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 		unlock_task_sighand(task, &flags);
 	}
 	put_task_struct(task);
-	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_score_adj);
+	len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
 }
 
@@ -919,7 +1020,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	task = get_proc_task(file->f_path.dentry->d_inode);
+	task = get_proc_task(file_inode(file));
 	if (!task) {
 		err = -ESRCH;
 		goto out;
@@ -936,15 +1037,15 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		goto err_task_lock;
 	}
 
-	if (oom_score_adj < task->signal->oom_score_adj_min &&
+	if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
 			!capable(CAP_SYS_RESOURCE)) {
 		err = -EACCES;
 		goto err_sighand;
 	}
 
-	task->signal->oom_score_adj = oom_score_adj;
+	task->signal->oom_score_adj = (short)oom_score_adj;
 	if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
-		task->signal->oom_score_adj_min = oom_score_adj;
+		task->signal->oom_score_adj_min = (short)oom_score_adj;
 	trace_oom_score_adj_update(task);
 
 err_sighand:
@@ -967,7 +1068,7 @@ static const struct file_operations proc_oom_score_adj_operations = {
 static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
 				  size_t count, loff_t *ppos)
 {
-	struct inode * inode = file->f_path.dentry->d_inode;
+	struct inode * inode = file_inode(file);
 	struct task_struct *task = get_proc_task(inode);
 	ssize_t length;
 	char tmpbuf[TMPBUFLEN];
@@ -984,7 +1085,7 @@ static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
 static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 				   size_t count, loff_t *ppos)
 {
-	struct inode * inode = file->f_path.dentry->d_inode;
+	struct inode * inode = file_inode(file);
 	char *page, *tmp;
 	ssize_t length;
 	uid_t loginuid;
@@ -1042,7 +1143,7 @@ static const struct file_operations proc_loginuid_operations = {
 static ssize_t proc_sessionid_read(struct file * file, char __user * buf,
 				  size_t count, loff_t *ppos)
 {
-	struct inode * inode = file->f_path.dentry->d_inode;
+	struct inode * inode = file_inode(file);
 	struct task_struct *task = get_proc_task(inode);
 	ssize_t length;
 	char tmpbuf[TMPBUFLEN];
@@ -1065,7 +1166,7 @@ static const struct file_operations proc_sessionid_operations = {
 static ssize_t proc_fault_inject_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);
+	struct task_struct *task = get_proc_task(file_inode(file));
 	char buffer[PROC_NUMBUF];
 	size_t len;
 	int make_it_fail;
@@ -1097,7 +1198,7 @@ static ssize_t proc_fault_inject_write(struct file * file,
 	make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
 	if (*end)
 		return -EINVAL;
-	task = get_proc_task(file->f_dentry->d_inode);
+	task = get_proc_task(file_inode(file));
 	if (!task)
 		return -ESRCH;
 	task->make_it_fail = make_it_fail;
@@ -1137,7 +1238,7 @@ static ssize_t
 sched_write(struct file *file, const char __user *buf,
 	    size_t count, loff_t *offset)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	struct task_struct *p;
 
 	p = get_proc_task(inode);
@@ -1188,7 +1289,7 @@ static ssize_t
 sched_autogroup_write(struct file *file, const char __user *buf,
 	    size_t count, loff_t *offset)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	struct task_struct *p;
 	char buffer[PROC_NUMBUF];
 	int nice;
@@ -1243,7 +1344,7 @@ static const struct file_operations proc_pid_sched_autogroup_operations = {
 static ssize_t comm_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *offset)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(file);
 	struct task_struct *p;
 	char buffer[TASK_COMM_LEN];
 
@@ -1611,7 +1712,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
 		return -ECHILD;
 
 	if (!capable(CAP_SYS_ADMIN)) {
-		status = -EACCES;
+		status = -EPERM;
 		goto out_notask;
 	}
 
@@ -1744,7 +1845,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 	struct dentry *result;
 	struct mm_struct *mm;
 
-	result = ERR_PTR(-EACCES);
+	result = ERR_PTR(-EPERM);
 	if (!capable(CAP_SYS_ADMIN))
 		goto out;
 
@@ -1770,8 +1871,9 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 	if (!vma)
 		goto out_no_vma;
 
-	result = proc_map_files_instantiate(dir, dentry, task,
-			(void *)(unsigned long)vma->vm_file->f_mode);
+	if (vma->vm_file)
+		result = proc_map_files_instantiate(dir, dentry, task,
+				(void *)(unsigned long)vma->vm_file->f_mode);
 
 out_no_vma:
 	up_read(&mm->mmap_sem);
@@ -1799,7 +1901,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	ino_t ino;
 	int ret;
 
-	ret = -EACCES;
+	ret = -EPERM;
 	if (!capable(CAP_SYS_ADMIN))
 		goto out;
 
@@ -2045,7 +2147,7 @@ out_no_task:
 static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
 				  size_t count, loff_t *ppos)
 {
-	struct inode * inode = file->f_path.dentry->d_inode;
+	struct inode * inode = file_inode(file);
 	char *p = NULL;
 	ssize_t length;
 	struct task_struct *task = get_proc_task(inode);
@@ -2066,7 +2168,7 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
 static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 				   size_t count, loff_t *ppos)
 {
-	struct inode * inode = file->f_path.dentry->d_inode;
+	struct inode * inode = file_inode(file);
 	char *page;
 	ssize_t length;
 	struct task_struct *task = get_proc_task(inode);
@@ -2155,7 +2257,7 @@ static const struct inode_operations proc_attr_dir_inode_operations = {
 static ssize_t proc_coredump_filter_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);
+	struct task_struct *task = get_proc_task(file_inode(file));
 	struct mm_struct *mm;
 	char buffer[PROC_NUMBUF];
 	size_t len;
@@ -2207,7 +2309,7 @@ static ssize_t proc_coredump_filter_write(struct file *file,
 		goto out_no_task;
 
 	ret = -ESRCH;
-	task = get_proc_task(file->f_dentry->d_inode);
+	task = get_proc_task(file_inode(file));
 	if (!task)
 		goto out_no_task;
 
@@ -2237,146 +2339,6 @@ static const struct file_operations proc_coredump_filter_operations = {
 };
 #endif
 
-/*
- * /proc/self:
- */
-static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
-			      int buflen)
-{
-	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
-	pid_t tgid = task_tgid_nr_ns(current, ns);
-	char tmp[PROC_NUMBUF];
-	if (!tgid)
-		return -ENOENT;
-	sprintf(tmp, "%d", tgid);
-	return vfs_readlink(dentry,buffer,buflen,tmp);
-}
-
-static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	struct pid_namespace *ns = dentry->d_sb->s_fs_info;
-	pid_t tgid = task_tgid_nr_ns(current, ns);
-	char *name = ERR_PTR(-ENOENT);
-	if (tgid) {
-		/* 11 for max length of signed int in decimal + NULL term */
-		name = kmalloc(12, GFP_KERNEL);
-		if (!name)
-			name = ERR_PTR(-ENOMEM);
-		else
-			sprintf(name, "%d", tgid);
-	}
-	nd_set_link(nd, name);
-	return NULL;
-}
-
-static void proc_self_put_link(struct dentry *dentry, struct nameidata *nd,
-				void *cookie)
-{
-	char *s = nd_get_link(nd);
-	if (!IS_ERR(s))
-		kfree(s);
-}
-
-static const struct inode_operations proc_self_inode_operations = {
-	.readlink	= proc_self_readlink,
-	.follow_link	= proc_self_follow_link,
-	.put_link	= proc_self_put_link,
-};
-
-/*
- * proc base
- *
- * These are the directory entries in the root directory of /proc
- * that properly belong to the /proc filesystem, as they describe
- * describe something that is process related.
- */
-static const struct pid_entry proc_base_stuff[] = {
-	NOD("self", S_IFLNK|S_IRWXUGO,
-		&proc_self_inode_operations, NULL, {}),
-};
-
-static struct dentry *proc_base_instantiate(struct inode *dir,
-	struct dentry *dentry, struct task_struct *task, const void *ptr)
-{
-	const struct pid_entry *p = ptr;
-	struct inode *inode;
-	struct proc_inode *ei;
-	struct dentry *error;
-
-	/* Allocate the inode */
-	error = ERR_PTR(-ENOMEM);
-	inode = new_inode(dir->i_sb);
-	if (!inode)
-		goto out;
-
-	/* Initialize the inode */
-	ei = PROC_I(inode);
-	inode->i_ino = get_next_ino();
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-
-	/*
-	 * grab the reference to the task.
-	 */
-	ei->pid = get_task_pid(task, PIDTYPE_PID);
-	if (!ei->pid)
-		goto out_iput;
-
-	inode->i_mode = p->mode;
-	if (S_ISDIR(inode->i_mode))
-		set_nlink(inode, 2);
-	if (S_ISLNK(inode->i_mode))
-		inode->i_size = 64;
-	if (p->iop)
-		inode->i_op = p->iop;
-	if (p->fop)
-		inode->i_fop = p->fop;
-	ei->op = p->op;
-	d_add(dentry, inode);
-	error = NULL;
-out:
-	return error;
-out_iput:
-	iput(inode);
-	goto out;
-}
-
-static struct dentry *proc_base_lookup(struct inode *dir, struct dentry *dentry)
-{
-	struct dentry *error;
-	struct task_struct *task = get_proc_task(dir);
-	const struct pid_entry *p, *last;
-
-	error = ERR_PTR(-ENOENT);
-
-	if (!task)
-		goto out_no_task;
-
-	/* Lookup the directory entry */
-	last = &proc_base_stuff[ARRAY_SIZE(proc_base_stuff) - 1];
-	for (p = proc_base_stuff; p <= last; p++) {
-		if (p->len != dentry->d_name.len)
-			continue;
-		if (!memcmp(dentry->d_name.name, p->name, p->len))
-			break;
-	}
-	if (p > last)
-		goto out;
-
-	error = proc_base_instantiate(dir, dentry, task, p);
-
-out:
-	put_task_struct(task);
-out_no_task:
-	return error;
-}
-
-static int proc_base_fill_cache(struct file *filp, void *dirent,
-	filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
-{
-	return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
-				proc_base_instantiate, task, p);
-}
-
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
 {
@@ -2598,6 +2560,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
 	INF("oom_score",  S_IRUGO, proc_oom_score),
+	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
 	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
 	REG("loginuid",   S_IWUSR|S_IRUGO, proc_loginuid_operations),
@@ -2656,6 +2619,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
 
 	name.name = buf;
 	name.len = snprintf(buf, sizeof(buf), "%d", pid);
+	/* no ->d_hash() rejects on procfs */
 	dentry = d_hash_and_lookup(mnt->mnt_root, &name);
 	if (dentry) {
 		shrink_dcache_parent(dentry);
@@ -2730,10 +2694,6 @@ void proc_flush_task(struct task_struct *task)
 		proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
 					tgid->numbers[i].nr);
 	}
-
-	upid = &pid->numbers[pid->level];
-	if (upid->nr == 1)
-		pid_ns_release_proc(upid->ns);
 }
 
 static struct dentry *proc_pid_instantiate(struct inode *dir,
@@ -2767,15 +2727,11 @@ out:
 
 struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
-	struct dentry *result;
+	struct dentry *result = NULL;
 	struct task_struct *task;
 	unsigned tgid;
 	struct pid_namespace *ns;
 
-	result = proc_base_lookup(dir, dentry);
-	if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT)
-		goto out;
-
 	tgid = name_to_int(dentry);
 	if (tgid == ~0U)
 		goto out;
@@ -2838,7 +2794,7 @@ retry:
 	return iter;
 }
 
-#define TGID_OFFSET (FIRST_PROCESS_ENTRY + ARRAY_SIZE(proc_base_stuff))
+#define TGID_OFFSET (FIRST_PROCESS_ENTRY)
 
 static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
 	struct tgid_iter iter)
@@ -2858,25 +2814,12 @@ static int fake_filldir(void *buf, const char *name, int namelen,
 /* for the /proc/ directory itself, after non-process stuff has been done */
 int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
 {
-	unsigned int nr;
-	struct task_struct *reaper;
 	struct tgid_iter iter;
 	struct pid_namespace *ns;
 	filldir_t __filldir;
 
 	if (filp->f_pos >= PID_MAX_LIMIT + TGID_OFFSET)
-		goto out_no_task;
-	nr = filp->f_pos - FIRST_PROCESS_ENTRY;
-
-	reaper = get_proc_task(filp->f_path.dentry->d_inode);
-	if (!reaper)
-		goto out_no_task;
-
-	for (; nr < ARRAY_SIZE(proc_base_stuff); filp->f_pos++, nr++) {
-		const struct pid_entry *p = &proc_base_stuff[nr];
-		if (proc_base_fill_cache(filp, dirent, filldir, reaper, p) < 0)
-			goto out;
-	}
+		goto out;
 
 	ns = filp->f_dentry->d_sb->s_fs_info;
 	iter.task = NULL;
@@ -2897,8 +2840,6 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	}
 	filp->f_pos = PID_MAX_LIMIT + TGID_OFFSET;
 out:
-	put_task_struct(reaper);
-out_no_task:
 	return 0;
 }
 
@@ -2964,6 +2905,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
 	INF("oom_score", S_IRUGO, proc_oom_score),
+	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
 	REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
 	REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),