| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1313334832-1150-5-git-send-email-glommer@parallels.com>
Date: Sun, 14 Aug 2011 19:13:52 +0400
From: Glauber Costa <glommer@...allels.com>
To: linux-kernel@...r.kernel.org
Cc: linux-fsdevel@...r.kernel.org,
containers@...ts.linux-foundation.org,
Pavel Emelyanov <xemul@...allels.com>,
Al Viro <viro@...iv.linux.org.uk>,
Hugh Dickins <hughd@...gle.com>,
Nick Piggin <npiggin@...nel.dk>,
Andrea Arcangeli <aarcange@...hat.com>,
Rik van Riel <riel@...hat.com>,
Dave Hansen <dave@...ux.vnet.ibm.com>,
James Bottomley <JBottomley@...allels.com>,
David Chinner <david@...morbit.com>,
Glauber Costa <glommer@...allels.com>,
Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH v3 4/4] parse options in the vfs level
This patch introduces a simple generic vfs option parser.
Right now, the only option we have is to limit the size of the dcache.
So any user that wants to have a dcache entries limit, can specify:
mount -o whatever_options,vfs_dcache_size=XXX <dev> <mntpoint>
It is supposed to work well with remounts, allowing it to change
multiple over the course of the filesystem's lifecycle.
I find mount a natural interface for handling filesystem options,
so that's what I've choosen. Feel free to yell at it at will if
you disagree.
Signed-off-by: Glauber Costa <glommer@...allels.com>
CC: Dave Chinner <david@...morbit.com>
CC: Eric Dumazet <eric.dumazet@...il.com>
---
fs/dcache.c | 7 +++
fs/namespace.c | 105 ++++++++++++++++++++++++++++++++++++++++++++++++
include/linux/dcache.h | 4 ++
3 files changed, 116 insertions(+), 0 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index ddd02a2..0551305 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1205,6 +1205,13 @@ static inline int dcache_mem_check(struct super_block *sb)
return -ENOMEM;
}
+int vfs_set_dcache_size(struct super_block *sb, int size)
+{
+ sb->s_nr_dentry_max = size;
+
+ return dcache_mem_check(sb);
+}
+
/**
* __d_alloc - allocate a dcache entry
* @sb: filesystem it will belong to
diff --git a/fs/namespace.c b/fs/namespace.c
index 22bfe82..43b2cdb 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -31,6 +31,7 @@
#include <linux/idr.h>
#include <linux/fs_struct.h>
#include <linux/fsnotify.h>
+#include <linux/parser.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include "pnode.h"
@@ -958,6 +959,9 @@ static int show_sb_opts(struct seq_file *m, struct super_block *sb)
};
const struct proc_fs_info *fs_infop;
+ if (sb->s_nr_dentry_max != INT_MAX)
+ seq_printf(m, ",vfs_dcache_size=%d",sb->s_nr_dentry_max);
+
for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
if (sb->s_flags & fs_infop->flag)
seq_puts(m, fs_infop->str);
@@ -2271,6 +2275,94 @@ int copy_mount_string(const void __user *data, char **where)
return 0;
}
+static const match_table_t tokens = {
+ {1, "vfs_dcache_size=%u"},
+};
+
+struct vfs_options {
+ unsigned long vfs_dcache_size;
+};
+
+/**
+ * Generic option parsing for the VFS.
+ *
+ * Since most of the filesystems already do their own option parsing, and with
+ * very few code shared between them, this function strips out any options that
+ * we succeed in parsing ourselves. Passing them forward would just give the
+ * underlying fs an option it does not expect, leading it to fail.
+ *
+ * We don't yet have a pointer to the super block as well, since this is
+ * pre-mount. We accumulate in struct vfs_options whatever data we collected,
+ * and act on it later.
+ */
+static int vfs_parse_options(char *options, struct vfs_options *ops)
+{
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+ char *p;
+ char *opt;
+ char *start = NULL;
+ int ret;
+
+ if (!options)
+ return 0;
+
+ opt = kstrdup(options, GFP_KERNEL);
+ if (!opt)
+ return 1;
+
+ ret = 1;
+
+ start = opt;
+ while ((p = strsep(&opt, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+
+ /*
+ * Initialize args struct so we know whether arg was
+ * found; some options take optional arguments.
+ */
+ args[0].to = args[0].from = 0;
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case 1:
+ if (!args[0].from)
+ break;
+
+ if (match_int(&args[0], &option))
+ break;
+
+ if (option < DCACHE_MIN_SIZE) {
+ printk(KERN_INFO "dcache size %d smaller than "
+ "minimum (%d)\n", option, DCACHE_MIN_SIZE);
+ option = DCACHE_MIN_SIZE;
+ }
+
+ ops->vfs_dcache_size = option;
+
+ /*
+ * The actual filesystems don't expect any option
+ * they don't understand to be received in the option
+ * string. So we strip off anything we processed, and
+ * give them a clean options string.
+ */
+ ret = 0;
+ if (!opt) /* it is the last option listed */
+ *(options + (p - start)) = '\0';
+ else
+ strcpy(options + (p - start), opt);
+ break;
+ default:
+ ret = 0;
+ break;
+ }
+ }
+
+ kfree(start);
+ return ret;
+}
+
/*
* Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
* be given to the mount() call (ie: read-only, no-dev, no-suid etc).
@@ -2291,6 +2383,7 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
struct path path;
int retval = 0;
int mnt_flags = 0;
+ struct vfs_options vfs_options;
/* Discard magic */
if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
@@ -2318,6 +2411,12 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
if (!(flags & MS_NOATIME))
mnt_flags |= MNT_RELATIME;
+
+ vfs_options.vfs_dcache_size = INT_MAX;
+ retval = vfs_parse_options(data_page, &vfs_options);
+ if (retval)
+ goto dput_out;
+
/* Separate the per-mountpoint flags */
if (flags & MS_NOSUID)
mnt_flags |= MNT_NOSUID;
@@ -2350,6 +2449,12 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
else
retval = do_new_mount(&path, type_page, flags, mnt_flags,
dev_name, data_page);
+
+ /* bind mounts get to respect their parents decision */
+ if (!retval && !(flags & MS_BIND))
+ vfs_set_dcache_size(path.mnt->mnt_sb,
+ vfs_options.vfs_dcache_size);
+
dput_out:
path_put(&path);
return retval;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d37d2a7..1a309f3 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -251,6 +251,10 @@ extern int d_invalidate(struct dentry *);
/* only used at mount-time */
extern struct dentry * d_alloc_root(struct inode *);
+extern int vfs_set_dcache_size(struct super_block *sb, int size);
+
+#define DCACHE_MIN_SIZE 1024
+extern int vfs_set_dcache_size(struct super_block *sb, int size);
/* <clickety>-<click> the ramfs-type tree */
extern void d_genocide(struct dentry *);
--
1.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists