From: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Subject: fs/seq_file: fallback to vmalloc allocation
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:
[62129.701569] sadc: page allocation failure: order:4, mode:0x1040d0
[62129.701573] CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1
[...]
[62129.701586] Call Trace:
[62129.701588] ([<0000000000111fbe>] show_trace+0xe6/0x130)
[62129.701591] [<0000000000112074>] show_stack+0x6c/0xe8
[62129.701593] [<000000000020d356>] warn_alloc_failed+0xd6/0x138
[62129.701596] [<00000000002114d2>] __alloc_pages_nodemask+0x9da/0xb68
[62129.701598] [<000000000021168e>] __get_free_pages+0x2e/0x58
[62129.701599] [<000000000025a05c>] kmalloc_order_trace+0x44/0xc0
[62129.701602] [<00000000002f3ffa>] stat_open+0x5a/0xd8
[62129.701604] [<00000000002e9aaa>] proc_reg_open+0x8a/0x140
[62129.701606] [<0000000000273b64>] do_dentry_open+0x1bc/0x2c8
[62129.701608] [<000000000027411e>] finish_open+0x46/0x60
[62129.701610] [<000000000028675a>] do_last+0x382/0x10d0
[62129.701612] [<0000000000287570>] path_openat+0xc8/0x4f8
[62129.701614] [<0000000000288bde>] do_filp_open+0x46/0xa8
[62129.701616] [<000000000027541c>] do_sys_open+0x114/0x1f0
[62129.701618] [<00000000005b1c1c>] sysc_tracego+0x14/0x1a
Signed-off-by: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Tested-by: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Ian Kent <raven@xxxxxxxxxx>
Cc: Hendrik Brueckner <brueckner@xxxxxxxxxxxxxxxxxx>
Cc: Thorsten Diehl <thorsten.diehl@xxxxxxxxxx>
Cc: Andrea Righi <andrea@xxxxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Stefan Bader <stefan.bader@xxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/seq_file.c | 30 +++++++++++++++++++++---------
1 file changed, 21 insertions(+), 9 deletions(-)
diff -puN fs/seq_file.c~fs-seq_file-fallback-to-vmalloc-allocation fs/seq_file.c
--- a/fs/seq_file.c~fs-seq_file-fallback-to-vmalloc-allocation
+++ a/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_
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,
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,
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
/* 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
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;
_
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html