pipe: change /proc/sys/fs/pipe-max-pages to byte sized interface

This changes the interface to be based on bytes instead. The API
matches that of F_SETPIPE_SZ in that it rounds up the passed in
size so that the resulting page array is a power-of-2 in size.

The proc file is renamed to /proc/sys/fs/pipe-max-size to
reflect this change.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

3 files changed, 49 insertions, 17 deletions

diff --git a/fs/pipe.c b/fs/pipe.c
index f98fae3..69c4c7c 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -26,9 +26,14 @@
 
 /*
  * The max size that a non-root user is allowed to grow the pipe. Can
- * be set by root in /proc/sys/fs/pipe-max-pages
+ * be set by root in /proc/sys/fs/pipe-max-size
  */
-unsigned int pipe_max_pages = PIPE_DEF_BUFFERS * 16;
+unsigned int pipe_max_size = 1048576;
+
+/*
+ * Minimum pipe size, as required by POSIX
+ */
+unsigned int pipe_min_size = PAGE_SIZE;
 
 /*
  * We use a start+len construction, which provides full use of the 
@@ -1156,6 +1161,35 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 	return nr_pages * PAGE_SIZE;
 }
 
+/*
+ * Currently we rely on the pipe array holding a power-of-2 number
+ * of pages.
+ */
+static inline unsigned int round_pipe_size(unsigned int size)
+{
+	unsigned long nr_pages;
+
+	nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	return roundup_pow_of_two(nr_pages) << PAGE_SHIFT;
+}
+
+/*
+ * This should work even if CONFIG_PROC_FS isn't set, as proc_dointvec_minmax
+ * will return an error.
+ */
+int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
+		 size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buf, lenp, ppos);
+	if (ret < 0 || !write)
+		return ret;
+
+	pipe_max_size = round_pipe_size(pipe_max_size);
+	return ret;
+}
+
 long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct pipe_inode_info *pipe;
@@ -1169,23 +1203,19 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case F_SETPIPE_SZ: {
-		unsigned long nr_pages;
+		unsigned int size, nr_pages;
 
-		/*
-		 * Currently the array must be a power-of-2 size, so adjust
-		 * upwards if needed.
-		 */
-		nr_pages = (arg + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		nr_pages = roundup_pow_of_two(nr_pages);
+		size = round_pipe_size(arg);
+		nr_pages = size >> PAGE_SHIFT;
 
-		if (!capable(CAP_SYS_RESOURCE) && nr_pages > pipe_max_pages) {
+		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
 			ret = -EPERM;
 			goto out;
-		} else if (nr_pages < 1) {
+		} else if (nr_pages < PAGE_SIZE) {
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = pipe_set_size(pipe, arg);
+		ret = pipe_set_size(pipe, nr_pages);
 		break;
 		}
 	case F_GETPIPE_SZ:
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 16de393..4457969 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -139,7 +139,9 @@ void pipe_lock(struct pipe_inode_info *);
 void pipe_unlock(struct pipe_inode_info *);
 void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
 
-extern unsigned int pipe_max_pages;
+extern unsigned int pipe_max_size, pipe_min_size;
+int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *);
+
 
 /* Drop the inode semaphore and wait for a pipe event, atomically */
 void pipe_wait(struct pipe_inode_info *pipe);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 997080f..d24f761 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1471,12 +1471,12 @@ static struct ctl_table fs_table[] = {
 	},
 #endif
 	{
-		.procname	= "pipe-max-pages",
-		.data		= &pipe_max_pages,
+		.procname	= "pipe-max-size",
+		.data		= &pipe_max_size,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.extra1		= &two,
+		.proc_handler	= &pipe_proc_fn,
+		.extra1		= &pipe_min_size,
 	},
 /*
  * NOTE: do not add new entries to this table unless you have read