Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  deal with races in /proc/*/{syscall,stack,personality}
  proc: enable writing to /proc/pid/mem
  proc: make check_mem_permission() return an mm_struct on success
  proc: hold cred_guard_mutex in check_mem_permission()
  proc: disable mem_write after exec
  mm: implement access_remote_vm
  mm: factor out main logic of access_process_vm
  mm: use mm_struct to resolve gate vma's in __get_user_pages
  mm: arch: rename in_gate_area_no_task to in_gate_area_no_mm
  mm: arch: make in_gate_area take an mm_struct instead of a task_struct
  mm: arch: make get_gate_vma take an mm_struct instead of a task_struct
  x86: mark associated mm when running a task in 32 bit compatibility mode
  x86: add context tag to mark mm when running a task in 32-bit compatibility mode
  auxv: require the target to be tracable (or yourself)
  close race in /proc/*/environ
  report errors in /proc/*/*map* sanely
  pagemap: close races with suid execve
  make sessionid permissions in /proc/*/task/* match those in /proc/*
  fix leaks in path_lookupat()

Fix up trivial conflicts in fs/proc/base.c

5 files changed, 138 insertions, 81 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index b2fae009..f34078d 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1906,7 +1906,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	segs = current->mm->map_count;
 	segs += elf_core_extra_phdrs();
 
-	gate_vma = get_gate_vma(current);
+	gate_vma = get_gate_vma(current->mm);
 	if (gate_vma != NULL)
 		segs++;
 
diff --git a/fs/namei.c b/fs/namei.c
index fc858b1..d0066e1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1650,13 +1650,16 @@ static int path_lookupat(int dfd, const char *name,
 			err = -ECHILD;
 	}
 
-	if (!err)
+	if (!err) {
 		err = handle_reval_path(nd);
+		if (err)
+			path_put(&nd->path);
+	}
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY) {
 		if (!nd->inode->i_op->lookup) {
 			path_put(&nd->path);
-			return -ENOTDIR;
+			err = -ENOTDIR;
 		}
 	}
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index daba136..5a670c1 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, "[<%pK>] %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 */
 
@@ -775,19 +831,14 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 	if (!task)
 		goto out_no_task;
 
-	ret = check_mem_permission(task);
-	if (ret)
-		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;
@@ -801,8 +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;
@@ -830,10 +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)
 {
@@ -841,19 +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;
 
-	copied = check_mem_permission(task);
-	if (copied)
-		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) {
@@ -864,7 +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;
@@ -877,12 +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)
 {
@@ -919,21 +973,18 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 	if (!task)
 		goto out_no_task;
 
-	ret = -EPERM;
-	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;
 
@@ -2751,8 +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;
 }
 
 /*
@@ -2771,7 +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),
@@ -2781,7 +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),
@@ -2800,7 +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),
@@ -2809,7 +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),
@@ -3111,14 +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),
@@ -3136,7 +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),
@@ -3145,7 +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),
@@ -3164,7 +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),
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 636f1a1..7c708a4 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -121,14 +121,14 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
 	if (!priv->task)
-		return NULL;
+		return ERR_PTR(-ESRCH);
 
 	mm = mm_for_maps(priv->task);
-	if (!mm)
-		return NULL;
+	if (!mm || IS_ERR(mm))
+		return mm;
 	down_read(&mm->mmap_sem);
 
-	tail_vma = get_gate_vma(priv->task);
+	tail_vma = get_gate_vma(priv->task->mm);
 	priv->tail_vma = tail_vma;
 
 	/* Start with last addr hint */
@@ -279,7 +279,8 @@ static int show_map(struct seq_file *m, void *v)
 	show_map_vma(m, vma);
 
 	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
+		m->version = (vma != get_gate_vma(task->mm))
+			? vma->vm_start : 0;
 	return 0;
 }
 
@@ -468,7 +469,8 @@ static int show_smap(struct seq_file *m, void *v)
 			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
 	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+		m->version = (vma != get_gate_vma(task->mm))
+			? vma->vm_start : 0;
 	return 0;
 }
 
@@ -764,8 +766,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!task)
 		goto out;
 
-	ret = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	mm = mm_for_maps(task);
+	ret = PTR_ERR(mm);
+	if (!mm || IS_ERR(mm))
 		goto out_task;
 
 	ret = -EINVAL;
@@ -778,10 +781,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!count)
 		goto out_task;
 
-	mm = get_task_mm(task);
-	if (!mm)
-		goto out_task;
-
 	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
 	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
 	ret = -ENOMEM;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index b535d3e..980de54 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -199,13 +199,13 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	/* pin the task and mm whilst we play with them */
 	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
 	if (!priv->task)
-		return NULL;
+		return ERR_PTR(-ESRCH);
 
 	mm = mm_for_maps(priv->task);
-	if (!mm) {
+	if (!mm || IS_ERR(mm)) {
 		put_task_struct(priv->task);
 		priv->task = NULL;
-		return NULL;
+		return mm;
 	}
 	down_read(&mm->mmap_sem);