Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus-1

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6: (9356 commits)
  [media] rc: update for bitop name changes
  fs: simplify iget & friends
  fs: pull inode->i_lock up out of writeback_single_inode
  fs: rename inode_lock to inode_hash_lock
  fs: move i_wb_list out from under inode_lock
  fs: move i_sb_list out from under inode_lock
  fs: remove inode_lock from iput_final and prune_icache
  fs: Lock the inode LRU list separately
  fs: factor inode disposal
  fs: protect inode->i_state with inode->i_lock
  lib, arch: add filter argument to show_mem and fix private implementations
  SLUB: Write to per cpu data when allocating it
  slub: Fix debugobjects with lockless fastpath
  autofs4: Do not potentially dereference NULL pointer returned by fget() in autofs_dev_ioctl_setpipefd()
  autofs4 - remove autofs4_lock
  autofs4 - fix d_manage() return on rcu-walk
  autofs4 - fix autofs4_expire_indirect() traversal
  autofs4 - fix dentry leak in autofs4_expire_direct()
  autofs4 - reinstate last used update on access
  vfs - check non-mountpoint dentry might block in __follow_mount_rcu()
  ...

NOTE!

This merge commit was created to fix compilation error. The block
tree was merged upstream and removed the 'elv_queue_empty()'
function which the new 'mtdswap' driver is using. So a simple
merge of the mtd tree with upstream does not compile. And the
mtd tree has already be published, so re-basing it is not an option.

To fix this unfortunate situation, I had to merge upstream into the
mtd-2.6.git tree without committing, put the fixup patch on top of
this, and then commit this. The result is that we do not have commits
which do not compile.

In other words, this merge commit "merges" 3 things: the MTD tree, the
upstream tree, and the fixup patch.

1 files changed, 118 insertions, 90 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9d096e82b201..5a670c11aeac 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -191,17 +191,20 @@ static int proc_root_link(struct inode *inode, struct path *path)
 	return result;
 }
 
-/*
- * Return zero if current may access user memory in @task, -error if not.
- */
-static int check_mem_permission(struct task_struct *task)
+static struct mm_struct *__check_mem_permission(struct task_struct *task)
 {
+	struct mm_struct *mm;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * A task can always look at itself, in case it chooses
 	 * to use system calls instead of load instructions.
 	 */
 	if (task == current)
-		return 0;
+		return mm;
 
 	/*
 	 * If current is actively ptrace'ing, and would also be
@@ -213,27 +216,53 @@ static int check_mem_permission(struct task_struct *task)
 		match = (tracehook_tracer_task(task) == current);
 		rcu_read_unlock();
 		if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
-			return 0;
+			return mm;
 	}
 
 	/*
 	 * Noone else is allowed.
 	 */
-	return -EPERM;
+	mmput(mm);
+	return ERR_PTR(-EPERM);
+}
+
+/*
+ * If current may access user memory in @task return a reference to the
+ * corresponding mm, otherwise ERR_PTR.
+ */
+static struct mm_struct *check_mem_permission(struct task_struct *task)
+{
+	struct mm_struct *mm;
+	int err;
+
+	/*
+	 * Avoid racing if task exec's as we might get a new mm but validate
+	 * against old credentials.
+	 */
+	err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	if (err)
+		return ERR_PTR(err);
+
+	mm = __check_mem_permission(task);
+	mutex_unlock(&task->signal->cred_guard_mutex);
+
+	return mm;
 }
 
 struct mm_struct *mm_for_maps(struct task_struct *task)
 {
 	struct mm_struct *mm;
+	int err;
 
-	if (mutex_lock_killable(&task->signal->cred_guard_mutex))
-		return NULL;
+	err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
+	if (err)
+		return ERR_PTR(err);
 
 	mm = get_task_mm(task);
 	if (mm && mm != current->mm &&
 			!ptrace_may_access(task, PTRACE_MODE_READ)) {
 		mmput(mm);
-		mm = NULL;
+		mm = ERR_PTR(-EACCES);
 	}
 	mutex_unlock(&task->signal->cred_guard_mutex);
 
@@ -279,9 +308,9 @@ out:
 
 static int proc_pid_auxv(struct task_struct *task, char *buffer)
 {
-	int res = 0;
-	struct mm_struct *mm = get_task_mm(task);
-	if (mm) {
+	struct mm_struct *mm = mm_for_maps(task);
+	int res = PTR_ERR(mm);
+	if (mm && !IS_ERR(mm)) {
 		unsigned int nwords = 0;
 		do {
 			nwords += 2;
@@ -318,6 +347,23 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
 }
 #endif /* CONFIG_KALLSYMS */
 
+static int lock_trace(struct task_struct *task)
+{
+	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	if (err)
+		return err;
+	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+		mutex_unlock(&task->signal->cred_guard_mutex);
+		return -EPERM;
+	}
+	return 0;
+}
+
+static void unlock_trace(struct task_struct *task)
+{
+	mutex_unlock(&task->signal->cred_guard_mutex);
+}
+
 #ifdef CONFIG_STACKTRACE
 
 #define MAX_STACK_TRACE_DEPTH	64
@@ -327,6 +373,7 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 {
 	struct stack_trace trace;
 	unsigned long *entries;
+	int err;
 	int i;
 
 	entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
@@ -337,15 +384,20 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 	trace.max_entries	= MAX_STACK_TRACE_DEPTH;
 	trace.entries		= entries;
 	trace.skip		= 0;
-	save_stack_trace_tsk(task, &trace);
 
-	for (i = 0; i < trace.nr_entries; i++) {
-		seq_printf(m, "[<%p>] %pS\n",
-			   (void *)entries[i], (void *)entries[i]);
+	err = lock_trace(task);
+	if (!err) {
+		save_stack_trace_tsk(task, &trace);
+
+		for (i = 0; i < trace.nr_entries; i++) {
+			seq_printf(m, "[<%pK>] %pS\n",
+				   (void *)entries[i], (void *)entries[i]);
+		}
+		unlock_trace(task);
 	}
 	kfree(entries);
 
-	return 0;
+	return err;
 }
 #endif
 
@@ -508,18 +560,22 @@ static int proc_pid_syscall(struct task_struct *task, char *buffer)
 {
 	long nr;
 	unsigned long args[6], sp, pc;
+	int res = lock_trace(task);
+	if (res)
+		return res;
 
 	if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
-		return sprintf(buffer, "running\n");
-
-	if (nr < 0)
-		return sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
-
-	return sprintf(buffer,
+		res = sprintf(buffer, "running\n");
+	else if (nr < 0)
+		res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+	else
+		res = sprintf(buffer,
 		       "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
 		       nr,
 		       args[0], args[1], args[2], args[3], args[4], args[5],
 		       sp, pc);
+	unlock_trace(task);
+	return res;
 }
 #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
 
@@ -775,18 +831,14 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 	if (!task)
 		goto out_no_task;
 
-	if (check_mem_permission(task))
-		goto out;
-
 	ret = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
 		goto out;
 
-	ret = 0;
- 
-	mm = get_task_mm(task);
-	if (!mm)
+	mm = check_mem_permission(task);
+	ret = PTR_ERR(mm);
+	if (IS_ERR(mm))
 		goto out_free;
 
 	ret = -EIO;
@@ -800,8 +852,8 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 		int this_len, retval;
 
 		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		retval = access_process_vm(task, src, page, this_len, 0);
-		if (!retval || check_mem_permission(task)) {
+		retval = access_remote_vm(mm, src, page, this_len, 0);
+		if (!retval) {
 			if (!ret)
 				ret = -EIO;
 			break;
@@ -829,10 +881,6 @@ out_no_task:
 	return ret;
 }
 
-#define mem_write NULL
-
-#ifndef mem_write
-/* This is a security hazard */
 static ssize_t mem_write(struct file * file, const char __user *buf,
 			 size_t count, loff_t *ppos)
 {
@@ -840,18 +888,25 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 	char *page;
 	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
 	unsigned long dst = *ppos;
+	struct mm_struct *mm;
 
 	copied = -ESRCH;
 	if (!task)
 		goto out_no_task;
 
-	if (check_mem_permission(task))
-		goto out;
+	mm = check_mem_permission(task);
+	copied = PTR_ERR(mm);
+	if (IS_ERR(mm))
+		goto out_task;
+
+	copied = -EIO;
+	if (file->private_data != (void *)((long)current->self_exec_id))
+		goto out_mm;
 
 	copied = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
-		goto out;
+		goto out_mm;
 
 	copied = 0;
 	while (count > 0) {
@@ -862,7 +917,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 			copied = -EFAULT;
 			break;
 		}
-		retval = access_process_vm(task, dst, page, this_len, 1);
+		retval = access_remote_vm(mm, dst, page, this_len, 1);
 		if (!retval) {
 			if (!copied)
 				copied = -EIO;
@@ -875,12 +930,13 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 	}
 	*ppos = dst;
 	free_page((unsigned long) page);
-out:
+out_mm:
+	mmput(mm);
+out_task:
 	put_task_struct(task);
 out_no_task:
 	return copied;
 }
-#endif
 
 loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 {
@@ -917,20 +973,18 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 	if (!task)
 		goto out_no_task;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
-		goto out;
-
 	ret = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
 		goto out;
 
-	ret = 0;
 
-	mm = get_task_mm(task);
-	if (!mm)
+	mm = mm_for_maps(task);
+	ret = PTR_ERR(mm);
+	if (!mm || IS_ERR(mm))
 		goto out_free;
 
+	ret = 0;
 	while (count > 0) {
 		int this_len, retval, max_len;
 
@@ -2620,35 +2674,6 @@ static const struct pid_entry proc_base_stuff[] = {
 		&proc_self_inode_operations, NULL, {}),
 };
 
-/*
- *	Exceptional case: normally we are not allowed to unhash a busy
- * directory. In this case, however, we can do it - no aliasing problems
- * due to the way we treat inodes.
- */
-static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
-	struct inode *inode;
-	struct task_struct *task;
-
-	if (nd->flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	inode = dentry->d_inode;
-	task = get_proc_task(inode);
-	if (task) {
-		put_task_struct(task);
-		return 1;
-	}
-	d_drop(dentry);
-	return 0;
-}
-
-static const struct dentry_operations proc_base_dentry_operations =
-{
-	.d_revalidate	= proc_base_revalidate,
-	.d_delete	= pid_delete_dentry,
-};
-
 static struct dentry *proc_base_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
 {
@@ -2685,7 +2710,6 @@ static struct dentry *proc_base_instantiate(struct inode *dir,
 	if (p->fop)
 		inode->i_fop = p->fop;
 	ei->op = p->op;
-	d_set_d_op(dentry, &proc_base_dentry_operations);
 	d_add(dentry, inode);
 	error = NULL;
 out:
@@ -2778,8 +2802,12 @@ static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
 static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task)
 {
-	seq_printf(m, "%08x\n", task->personality);
-	return 0;
+	int err = lock_trace(task);
+	if (!err) {
+		seq_printf(m, "%08x\n", task->personality);
+		unlock_trace(task);
+	}
+	return err;
 }
 
 /*
@@ -2798,7 +2826,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("environ",    S_IRUSR, proc_environ_operations),
 	INF("auxv",       S_IRUSR, proc_pid_auxv),
 	ONE("status",     S_IRUGO, proc_pid_status),
-	ONE("personality", S_IRUSR, proc_pid_personality),
+	ONE("personality", S_IRUGO, proc_pid_personality),
 	INF("limits",	  S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
@@ -2808,7 +2836,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-	INF("syscall",    S_IRUSR, proc_pid_syscall),
+	INF("syscall",    S_IRUGO, proc_pid_syscall),
 #endif
 	INF("cmdline",    S_IRUGO, proc_pid_cmdline),
 	ONE("stat",       S_IRUGO, proc_tgid_stat),
@@ -2827,7 +2855,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
 	REG("smaps",      S_IRUGO, proc_smaps_operations),
-	REG("pagemap",    S_IRUSR, proc_pagemap_operations),
+	REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
 	DIR("attr",       S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
@@ -2836,7 +2864,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("wchan",      S_IRUGO, proc_pid_wchan),
 #endif
 #ifdef CONFIG_STACKTRACE
-	ONE("stack",      S_IRUSR, proc_pid_stack),
+	ONE("stack",      S_IRUGO, proc_pid_stack),
 #endif
 #ifdef CONFIG_SCHEDSTATS
 	INF("schedstat",  S_IRUGO, proc_pid_schedstat),
@@ -3138,14 +3166,14 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("environ",   S_IRUSR, proc_environ_operations),
 	INF("auxv",      S_IRUSR, proc_pid_auxv),
 	ONE("status",    S_IRUGO, proc_pid_status),
-	ONE("personality", S_IRUSR, proc_pid_personality),
+	ONE("personality", S_IRUGO, proc_pid_personality),
 	INF("limits",	 S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-	INF("syscall",   S_IRUSR, proc_pid_syscall),
+	INF("syscall",   S_IRUGO, proc_pid_syscall),
 #endif
 	INF("cmdline",   S_IRUGO, proc_pid_cmdline),
 	ONE("stat",      S_IRUGO, proc_tid_stat),
@@ -3163,7 +3191,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
 	REG("smaps",     S_IRUGO, proc_smaps_operations),
-	REG("pagemap",    S_IRUSR, proc_pagemap_operations),
+	REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
 	DIR("attr",      S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
@@ -3172,7 +3200,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	INF("wchan",     S_IRUGO, proc_pid_wchan),
 #endif
 #ifdef CONFIG_STACKTRACE
-	ONE("stack",      S_IRUSR, proc_pid_stack),
+	ONE("stack",      S_IRUGO, proc_pid_stack),
 #endif
 #ifdef CONFIG_SCHEDSTATS
 	INF("schedstat", S_IRUGO, proc_pid_schedstat),
@@ -3191,7 +3219,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	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),
-	REG("sessionid",  S_IRUSR, proc_sessionid_operations),
+	REG("sessionid",  S_IRUGO, proc_sessionid_operations),
 #endif
 #ifdef CONFIG_FAULT_INJECTION
 	REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),