Merge linux-stable 3.0.28 into android-3.0

Change-Id: Iee820738e53627f5d0447a87ceff34443aa72786
Signed-off-by: Todd Poynor <toddpoynor@google.com>

5 files changed, 110 insertions, 162 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1a8d756..6a938aa 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -200,65 +200,7 @@ static int proc_root_link(struct inode *inode, struct path *path)
 	return result;
 }
 
-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 mm;
-
-	/*
-	 * If current is actively ptrace'ing, and would also be
-	 * permitted to freshly attach with ptrace now, permit it.
-	 */
-	if (task_is_stopped_or_traced(task)) {
-		int match;
-		rcu_read_lock();
-		match = (tracehook_tracer_task(task) == current);
-		rcu_read_unlock();
-		if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
-			return mm;
-	}
-
-	/*
-	 * No one else is allowed.
-	 */
-	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)
+static struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 {
 	struct mm_struct *mm;
 	int err;
@@ -269,7 +211,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
 
 	mm = get_task_mm(task);
 	if (mm && mm != current->mm &&
-			!ptrace_may_access(task, PTRACE_MODE_READ) &&
+			!ptrace_may_access(task, mode) &&
 			!capable(CAP_SYS_RESOURCE)) {
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
@@ -279,6 +221,11 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
 	return mm;
 }
 
+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;
@@ -823,136 +770,99 @@ static const struct file_operations proc_single_file_operations = {
 
 static int mem_open(struct inode* inode, struct file* file)
 {
-	file->private_data = (void*)((long)current->self_exec_id);
-	/* OK to pass negative loff_t, we can catch out-of-range */
-	file->f_mode |= FMODE_UNSIGNED_OFFSET;
-	return 0;
-}
-
-static ssize_t mem_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);
-	char *page;
-	unsigned long src = *ppos;
-	int ret = -ESRCH;
 	struct mm_struct *mm;
 
 	if (!task)
-		goto out_no_task;
+		return -ESRCH;
 
-	ret = -ENOMEM;
-	page = (char *)__get_free_page(GFP_TEMPORARY);
-	if (!page)
-		goto out;
+	mm = mm_access(task, PTRACE_MODE_ATTACH);
+	put_task_struct(task);
 
-	mm = check_mem_permission(task);
-	ret = PTR_ERR(mm);
 	if (IS_ERR(mm))
-		goto out_free;
-
-	ret = -EIO;
- 
-	if (file->private_data != (void*)((long)current->self_exec_id))
-		goto out_put;
+		return PTR_ERR(mm);
 
-	ret = 0;
- 
-	while (count > 0) {
-		int this_len, retval;
-
-		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		retval = access_remote_vm(mm, src, page, this_len, 0);
-		if (!retval) {
-			if (!ret)
-				ret = -EIO;
-			break;
-		}
-
-		if (copy_to_user(buf, page, retval)) {
-			ret = -EFAULT;
-			break;
-		}
- 
-		ret += retval;
-		src += retval;
-		buf += retval;
-		count -= retval;
+	if (mm) {
+		/* ensure this mm_struct can't be freed */
+		atomic_inc(&mm->mm_count);
+		/* but do not pin its memory */
+		mmput(mm);
 	}
-	*ppos = src;
 
-out_put:
-	mmput(mm);
-out_free:
-	free_page((unsigned long) page);
-out:
-	put_task_struct(task);
-out_no_task:
-	return ret;
-}
+	/* OK to pass negative loff_t, we can catch out-of-range */
+	file->f_mode |= FMODE_UNSIGNED_OFFSET;
+	file->private_data = mm;
 
-#define mem_write NULL
+	return 0;
+}
 
-#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)
+static ssize_t mem_rw(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos, int write)
 {
-	int copied;
+	struct mm_struct *mm = file->private_data;
+	unsigned long addr = *ppos;
+	ssize_t copied;
 	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 (!mm)
+		return 0;
 
-	copied = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
-		goto out_task;
-
-	mm = check_mem_permission(task);
-	copied = PTR_ERR(mm);
-	if (IS_ERR(mm))
-		goto out_free;
-
-	copied = -EIO;
-	if (file->private_data != (void *)((long)current->self_exec_id))
-		goto out_mm;
+		return -ENOMEM;
 
 	copied = 0;
+	if (!atomic_inc_not_zero(&mm->mm_users))
+		goto free;
+
 	while (count > 0) {
-		int this_len, retval;
+		int this_len = min_t(int, count, PAGE_SIZE);
 
-		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		if (copy_from_user(page, buf, this_len)) {
+		if (write && copy_from_user(page, buf, this_len)) {
 			copied = -EFAULT;
 			break;
 		}
-		retval = access_remote_vm(mm, dst, page, this_len, 1);
-		if (!retval) {
+
+		this_len = access_remote_vm(mm, addr, page, this_len, write);
+		if (!this_len) {
 			if (!copied)
 				copied = -EIO;
 			break;
 		}
-		copied += retval;
-		buf += retval;
-		dst += retval;
-		count -= retval;			
+
+		if (!write && copy_to_user(buf, page, this_len)) {
+			copied = -EFAULT;
+			break;
+		}
+
+		buf += this_len;
+		addr += this_len;
+		copied += this_len;
+		count -= this_len;
 	}
-	*ppos = dst;
+	*ppos = addr;
 
-out_mm:
 	mmput(mm);
-out_free:
+free:
 	free_page((unsigned long) page);
-out_task:
-	put_task_struct(task);
-out_no_task:
 	return copied;
 }
+
+static ssize_t mem_read(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	return mem_rw(file, buf, count, ppos, 0);
+}
+
+#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)
+{
+	return mem_rw(file, (char __user*)buf, count, ppos, 1);
+}
 #endif
 
 loff_t mem_lseek(struct file *file, loff_t offset, int orig)
@@ -971,11 +881,20 @@ loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 	return file->f_pos;
 }
 
+static int mem_release(struct inode *inode, struct file *file)
+{
+	struct mm_struct *mm = file->private_data;
+	if (mm)
+		mmdrop(mm);
+	return 0;
+}
+
 static const struct file_operations proc_mem_operations = {
 	.llseek		= mem_lseek,
 	.read		= mem_read,
 	.write		= mem_write,
 	.open		= mem_open,
+	.release	= mem_release,
 };
 
 static ssize_t environ_read(struct file *file, char __user *buf,
@@ -1965,6 +1884,14 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
 		spin_lock(&files->file_lock);
 		file = fcheck_files(files, fd);
 		if (file) {
+			unsigned int f_flags;
+			struct fdtable *fdt;
+
+			fdt = files_fdtable(files);
+			f_flags = file->f_flags & ~O_CLOEXEC;
+			if (FD_ISSET(fd, fdt->close_on_exec))
+				f_flags |= O_CLOEXEC;
+
 			if (path) {
 				*path = file->f_path;
 				path_get(&file->f_path);
@@ -1974,7 +1901,7 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
 					 "pos:\t%lli\n"
 					 "flags:\t0%o\n",
 					 (long long) file->f_pos,
-					 file->f_flags);
+					 f_flags);
 			spin_unlock(&files->file_lock);
 			put_files_struct(files);
 			return 0;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index ed257d1..a962827 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -131,12 +131,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		K(i.freeswap),
 		K(global_page_state(NR_FILE_DIRTY)),
 		K(global_page_state(NR_WRITEBACK)),
-		K(global_page_state(NR_ANON_PAGES)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		K(global_page_state(NR_ANON_PAGES)
 		  + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
-		  HPAGE_PMD_NR
+		  HPAGE_PMD_NR),
+#else
+		K(global_page_state(NR_ANON_PAGES)),
 #endif
-		  ),
 		K(global_page_state(NR_FILE_MAPPED)),
 		K(global_page_state(NR_SHMEM)),
 		K(global_page_state(NR_SLAB_RECLAIMABLE) +
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index be177f7..d6c078e 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -54,7 +54,7 @@ static struct dentry *proc_ns_instantiate(struct inode *dir,
 	ei->ns_ops    = ns_ops;
 	ei->ns	      = ns;
 
-	dentry->d_op = &pid_dentry_operations;
+	d_set_d_op(dentry, &pid_dentry_operations);
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
 	if (pid_revalidate(dentry, NULL))
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5afaa58..55a1f49 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -407,6 +407,9 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	} else {
 		spin_unlock(&walk->mm->page_table_lock);
 	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	/*
 	 * The mmap_sem held all the way back in m_start() is what
 	 * keeps khugepaged out of here and from collapsing things
@@ -505,6 +508,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -516,6 +521,9 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		if (!page)
 			continue;
 
+		if (PageReserved(page))
+			continue;
+
 		/* Clear accessed and referenced bits. */
 		ptep_test_and_clear_young(vma, addr, pte);
 		ClearPageReferenced(page);
@@ -665,6 +673,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	int err = 0;
 
 	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
@@ -956,6 +966,8 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		spin_unlock(&walk->mm->page_table_lock);
 	}
 
+	if (pmd_trans_unstable(pmd))
+		return 0;
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
@@ -1039,6 +1051,9 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_printf(m, " stack");
 	}
 
+	if (is_vm_hugetlb_page(vma))
+		seq_printf(m, " huge");
+
 	walk_page_range(vma->vm_start, vma->vm_end, &walk);
 
 	if (!md->pages)
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 766b1d4..29166ec 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -11,15 +11,20 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec uptime;
 	struct timespec idle;
+	cputime64_t idletime;
+	u64 nsec;
+	u32 rem;
 	int i;
-	cputime_t idletime = cputime_zero;
 
+	idletime = 0;
 	for_each_possible_cpu(i)
 		idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle);
 
 	do_posix_clock_monotonic_gettime(&uptime);
 	monotonic_to_bootbased(&uptime);
-	cputime_to_timespec(idletime, &idle);
+	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
+	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
+	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
 			(unsigned long) uptime.tv_sec,
 			(uptime.tv_nsec / (NSEC_PER_SEC / 100)),