[3.13.y.z extended stable] Patch "fs/seq_file: fallback to vmalloc allocation" has been added to staging queue

[Kamal Mostafa]

This is a note to let you know that I have just added a patch titled

    fs/seq_file: fallback to vmalloc allocation

to the linux-3.13.y-queue branch of the 3.13.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.13.y-queue

This patch is scheduled to be released in version 3.13.11.6.

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.13.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Kamal

------

>From faaf76686e1a13e043f144cb6c0988c7470825be Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens at de.ibm.com>
Date: Wed, 2 Jul 2014 15:22:37 -0700
Subject: fs/seq_file: fallback to vmalloc allocation

commit 058504edd02667eef8fac9be27ab3ea74332e9b4 upstream.

There are a couple of seq_files which use the single_open() interface.
This interface requires that the whole output must fit into a single
buffer.

E.g.  for /proc/stat allocation failures have been observed because an
order-4 memory allocation failed due to memory fragmentation.  In such
situations reading /proc/stat is not possible anymore.

Therefore change the seq_file code to fallback to vmalloc allocations
which will usually result in a couple of order-0 allocations and hence
also work if memory is fragmented.

For reference a call trace where reading from /proc/stat failed:

  sadc: page allocation failure: order:4, mode:0x1040d0
  CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1
  [...]
  Call Trace:
    show_stack+0x6c/0xe8
    warn_alloc_failed+0xd6/0x138
    __alloc_pages_nodemask+0x9da/0xb68
    __get_free_pages+0x2e/0x58
    kmalloc_order_trace+0x44/0xc0
    stat_open+0x5a/0xd8
    proc_reg_open+0x8a/0x140
    do_dentry_open+0x1bc/0x2c8
    finish_open+0x46/0x60
    do_last+0x382/0x10d0
    path_openat+0xc8/0x4f8
    do_filp_open+0x46/0xa8
    do_sys_open+0x114/0x1f0
    sysc_tracego+0x14/0x1a

Signed-off-by: Heiko Carstens <heiko.carstens at de.ibm.com>
Tested-by: David Rientjes <rientjes at google.com>
Cc: Ian Kent <raven at themaw.net>
Cc: Hendrik Brueckner <brueckner at linux.vnet.ibm.com>
Cc: Thorsten Diehl <thorsten.diehl at de.ibm.com>
Cc: Andrea Righi <andrea at betterlinux.com>
Cc: Christoph Hellwig <hch at infradead.org>
Cc: Al Viro <viro at zeniv.linux.org.uk>
Cc: Stefan Bader <stefan.bader at canonical.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 fs/seq_file.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/fs/seq_file.c b/fs/seq_file.c
index 1d641bb..3857b72 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -8,8 +8,10 @@
 #include <linux/fs.h>
 #include <linux/export.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/cred.h>
+#include <linux/mm.h>

 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -30,6 +32,16 @@ static void seq_set_overflow(struct seq_file *m)
 	m->count = m->size;
 }

+static void *seq_buf_alloc(unsigned long size)
+{
+	void *buf;
+
+	buf = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
+	if (!buf && size > PAGE_SIZE)
+		buf = vmalloc(size);
+	return buf;
+}
+
 /**
  *	seq_open -	initialize sequential file
  *	@file: file we initialize
@@ -96,7 +108,7 @@ static int traverse(struct seq_file *m, loff_t offset)
 		return 0;
 	}
 	if (!m->buf) {
-		m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
 		if (!m->buf)
 			return -ENOMEM;
 	}
@@ -135,9 +147,9 @@ static int traverse(struct seq_file *m, loff_t offset)

 Eoverflow:
 	m->op->stop(m, p);
-	kfree(m->buf);
+	kvfree(m->buf);
 	m->count = 0;
-	m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+	m->buf = seq_buf_alloc(m->size <<= 1);
 	return !m->buf ? -ENOMEM : -EAGAIN;
 }

@@ -192,7 +204,7 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)

 	/* grab buffer if we didn't have one */
 	if (!m->buf) {
-		m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
 		if (!m->buf)
 			goto Enomem;
 	}
@@ -232,9 +244,9 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 		if (m->count < m->size)
 			goto Fill;
 		m->op->stop(m, p);
-		kfree(m->buf);
+		kvfree(m->buf);
 		m->count = 0;
-		m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size <<= 1);
 		if (!m->buf)
 			goto Enomem;
 		m->version = 0;
@@ -350,7 +362,7 @@ EXPORT_SYMBOL(seq_lseek);
 int seq_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = file->private_data;
-	kfree(m->buf);
+	kvfree(m->buf);
 	kfree(m);
 	return 0;
 }
@@ -605,13 +617,13 @@ EXPORT_SYMBOL(single_open);
 int single_open_size(struct file *file, int (*show)(struct seq_file *, void *),
 		void *data, size_t size)
 {
-	char *buf = kmalloc(size, GFP_KERNEL);
+	char *buf = seq_buf_alloc(size);
 	int ret;
 	if (!buf)
 		return -ENOMEM;
 	ret = single_open(file, show, data);
 	if (ret) {
-		kfree(buf);
+		kvfree(buf);
 		return ret;
 	}
 	((struct seq_file *)file->private_data)->buf = buf;
--
1.9.1