linux/fs/logfs/super.c

654 lines
16 KiB
C
Raw Normal View History

/*
* fs/logfs/super.c
*
* As should be obvious for Linux kernel code, license is GPLv2
*
* Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
*
* Generally contains mount/umount code and also serves as a dump area for
* any functions that don't fit elsewhere and neither justify a file of their
* own.
*/
#include "logfs.h"
#include <linux/bio.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/mtd/mtd.h>
#include <linux/statfs.h>
#include <linux/buffer_head.h>
static DEFINE_MUTEX(emergency_mutex);
static struct page *emergency_page;
struct page *emergency_read_begin(struct address_space *mapping, pgoff_t index)
{
filler_t *filler = (filler_t *)mapping->a_ops->readpage;
struct page *page;
int err;
page = read_cache_page(mapping, index, filler, NULL);
if (page)
return page;
/* No more pages available, switch to emergency page */
printk(KERN_INFO"Logfs: Using emergency page\n");
mutex_lock(&emergency_mutex);
err = filler(NULL, emergency_page);
if (err) {
mutex_unlock(&emergency_mutex);
printk(KERN_EMERG"Logfs: Error reading emergency page\n");
return ERR_PTR(err);
}
return emergency_page;
}
void emergency_read_end(struct page *page)
{
if (page == emergency_page)
mutex_unlock(&emergency_mutex);
else
page_cache_release(page);
}
static void dump_segfile(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_segment_entry se;
u32 segno;
for (segno = 0; segno < super->s_no_segs; segno++) {
logfs_get_segment_entry(sb, segno, &se);
printk("%3x: %6x %8x", segno, be32_to_cpu(se.ec_level),
be32_to_cpu(se.valid));
if (++segno < super->s_no_segs) {
logfs_get_segment_entry(sb, segno, &se);
printk(" %6x %8x", be32_to_cpu(se.ec_level),
be32_to_cpu(se.valid));
}
if (++segno < super->s_no_segs) {
logfs_get_segment_entry(sb, segno, &se);
printk(" %6x %8x", be32_to_cpu(se.ec_level),
be32_to_cpu(se.valid));
}
if (++segno < super->s_no_segs) {
logfs_get_segment_entry(sb, segno, &se);
printk(" %6x %8x", be32_to_cpu(se.ec_level),
be32_to_cpu(se.valid));
}
printk("\n");
}
}
/*
* logfs_crash_dump - dump debug information to device
*
* The LogFS superblock only occupies part of a segment. This function will
* write as much debug information as it can gather into the spare space.
*/
void logfs_crash_dump(struct super_block *sb)
{
dump_segfile(sb);
}
/*
* FIXME: There should be a reserve for root, similar to ext2.
*/
int logfs_statfs(struct dentry *dentry, struct kstatfs *stats)
{
struct super_block *sb = dentry->d_sb;
struct logfs_super *super = logfs_super(sb);
stats->f_type = LOGFS_MAGIC_U32;
stats->f_bsize = sb->s_blocksize;
stats->f_blocks = super->s_size >> LOGFS_BLOCK_BITS >> 3;
stats->f_bfree = super->s_free_bytes >> sb->s_blocksize_bits;
stats->f_bavail = super->s_free_bytes >> sb->s_blocksize_bits;
stats->f_files = 0;
stats->f_ffree = 0;
stats->f_namelen = LOGFS_MAX_NAMELEN;
return 0;
}
static int logfs_sb_set(struct super_block *sb, void *_super)
{
struct logfs_super *super = _super;
sb->s_fs_info = super;
sb->s_mtd = super->s_mtd;
sb->s_bdev = super->s_bdev;
#ifdef CONFIG_BLOCK
if (sb->s_bdev)
sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
#endif
#ifdef CONFIG_MTD
if (sb->s_mtd)
sb->s_bdi = sb->s_mtd->backing_dev_info;
#endif
return 0;
}
static int logfs_sb_test(struct super_block *sb, void *_super)
{
struct logfs_super *super = _super;
struct mtd_info *mtd = super->s_mtd;
if (mtd && sb->s_mtd == mtd)
return 1;
if (super->s_bdev && sb->s_bdev == super->s_bdev)
return 1;
return 0;
}
static void set_segment_header(struct logfs_segment_header *sh, u8 type,
u8 level, u32 segno, u32 ec)
{
sh->pad = 0;
sh->type = type;
sh->level = level;
sh->segno = cpu_to_be32(segno);
sh->ec = cpu_to_be32(ec);
sh->gec = cpu_to_be64(segno);
sh->crc = logfs_crc32(sh, LOGFS_SEGMENT_HEADERSIZE, 4);
}
static void logfs_write_ds(struct super_block *sb, struct logfs_disk_super *ds,
u32 segno, u32 ec)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_segment_header *sh = &ds->ds_sh;
int i;
memset(ds, 0, sizeof(*ds));
set_segment_header(sh, SEG_SUPER, 0, segno, ec);
ds->ds_ifile_levels = super->s_ifile_levels;
ds->ds_iblock_levels = super->s_iblock_levels;
ds->ds_data_levels = super->s_data_levels; /* XXX: Remove */
ds->ds_segment_shift = super->s_segshift;
ds->ds_block_shift = sb->s_blocksize_bits;
ds->ds_write_shift = super->s_writeshift;
ds->ds_filesystem_size = cpu_to_be64(super->s_size);
ds->ds_segment_size = cpu_to_be32(super->s_segsize);
ds->ds_bad_seg_reserve = cpu_to_be32(super->s_bad_seg_reserve);
ds->ds_feature_incompat = cpu_to_be64(super->s_feature_incompat);
ds->ds_feature_ro_compat= cpu_to_be64(super->s_feature_ro_compat);
ds->ds_feature_compat = cpu_to_be64(super->s_feature_compat);
ds->ds_feature_flags = cpu_to_be64(super->s_feature_flags);
ds->ds_root_reserve = cpu_to_be64(super->s_root_reserve);
ds->ds_speed_reserve = cpu_to_be64(super->s_speed_reserve);
journal_for_each(i)
ds->ds_journal_seg[i] = cpu_to_be32(super->s_journal_seg[i]);
ds->ds_magic = cpu_to_be64(LOGFS_MAGIC);
ds->ds_crc = logfs_crc32(ds, sizeof(*ds),
LOGFS_SEGMENT_HEADERSIZE + 12);
}
static int write_one_sb(struct super_block *sb,
struct page *(*find_sb)(struct super_block *sb, u64 *ofs))
{
struct logfs_super *super = logfs_super(sb);
struct logfs_disk_super *ds;
struct logfs_segment_entry se;
struct page *page;
u64 ofs;
u32 ec, segno;
int err;
page = find_sb(sb, &ofs);
if (!page)
return -EIO;
ds = page_address(page);
segno = seg_no(sb, ofs);
logfs_get_segment_entry(sb, segno, &se);
ec = be32_to_cpu(se.ec_level) >> 4;
ec++;
logfs_set_segment_erased(sb, segno, ec, 0);
logfs_write_ds(sb, ds, segno, ec);
err = super->s_devops->write_sb(sb, page);
page_cache_release(page);
return err;
}
int logfs_write_sb(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
int err;
/* First superblock */
err = write_one_sb(sb, super->s_devops->find_first_sb);
if (err)
return err;
/* Last superblock */
err = write_one_sb(sb, super->s_devops->find_last_sb);
if (err)
return err;
return 0;
}
static int ds_cmp(const void *ds0, const void *ds1)
{
size_t len = sizeof(struct logfs_disk_super);
/* We know the segment headers differ, so ignore them */
len -= LOGFS_SEGMENT_HEADERSIZE;
ds0 += LOGFS_SEGMENT_HEADERSIZE;
ds1 += LOGFS_SEGMENT_HEADERSIZE;
return memcmp(ds0, ds1, len);
}
static int logfs_recover_sb(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct logfs_disk_super _ds0, *ds0 = &_ds0;
struct logfs_disk_super _ds1, *ds1 = &_ds1;
int err, valid0, valid1;
/* read first superblock */
err = wbuf_read(sb, super->s_sb_ofs[0], sizeof(*ds0), ds0);
if (err)
return err;
/* read last superblock */
err = wbuf_read(sb, super->s_sb_ofs[1], sizeof(*ds1), ds1);
if (err)
return err;
valid0 = logfs_check_ds(ds0) == 0;
valid1 = logfs_check_ds(ds1) == 0;
if (!valid0 && valid1) {
printk(KERN_INFO"First superblock is invalid - fixing.\n");
return write_one_sb(sb, super->s_devops->find_first_sb);
}
if (valid0 && !valid1) {
printk(KERN_INFO"Last superblock is invalid - fixing.\n");
return write_one_sb(sb, super->s_devops->find_last_sb);
}
if (valid0 && valid1 && ds_cmp(ds0, ds1)) {
printk(KERN_INFO"Superblocks don't match - fixing.\n");
return logfs_write_sb(sb);
}
/* If neither is valid now, something's wrong. Didn't we properly
* check them before?!? */
BUG_ON(!valid0 && !valid1);
return 0;
}
static int logfs_make_writeable(struct super_block *sb)
{
int err;
err = logfs_open_segfile(sb);
if (err)
return err;
/* Repair any broken superblock copies */
err = logfs_recover_sb(sb);
if (err)
return err;
/* Check areas for trailing unaccounted data */
err = logfs_check_areas(sb);
if (err)
return err;
/* Do one GC pass before any data gets dirtied */
logfs_gc_pass(sb);
/* after all initializations are done, replay the journal
* for rw-mounts, if necessary */
err = logfs_replay_journal(sb);
if (err)
return err;
return 0;
}
static int logfs_get_sb_final(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct inode *rootdir;
int err;
/* root dir */
rootdir = logfs_iget(sb, LOGFS_INO_ROOT);
if (IS_ERR(rootdir))
goto fail;
sb->s_root = d_make_root(rootdir);
if (!sb->s_root)
goto fail;
/* at that point we know that ->put_super() will be called */
super->s_erase_page = alloc_pages(GFP_KERNEL, 0);
if (!super->s_erase_page)
return -ENOMEM;
memset(page_address(super->s_erase_page), 0xFF, PAGE_SIZE);
/* FIXME: check for read-only mounts */
err = logfs_make_writeable(sb);
if (err) {
__free_page(super->s_erase_page);
return err;
}
log_super("LogFS: Finished mounting\n");
return 0;
fail:
iput(super->s_master_inode);
iput(super->s_segfile_inode);
iput(super->s_mapping_inode);
return -EIO;
}
int logfs_check_ds(struct logfs_disk_super *ds)
{
struct logfs_segment_header *sh = &ds->ds_sh;
if (ds->ds_magic != cpu_to_be64(LOGFS_MAGIC))
return -EINVAL;
if (sh->crc != logfs_crc32(sh, LOGFS_SEGMENT_HEADERSIZE, 4))
return -EINVAL;
if (ds->ds_crc != logfs_crc32(ds, sizeof(*ds),
LOGFS_SEGMENT_HEADERSIZE + 12))
return -EINVAL;
return 0;
}
static struct page *find_super_block(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct page *first, *last;
first = super->s_devops->find_first_sb(sb, &super->s_sb_ofs[0]);
if (!first || IS_ERR(first))
return NULL;
last = super->s_devops->find_last_sb(sb, &super->s_sb_ofs[1]);
if (!last || IS_ERR(last)) {
page_cache_release(first);
return NULL;
}
if (!logfs_check_ds(page_address(first))) {
page_cache_release(last);
return first;
}
/* First one didn't work, try the second superblock */
if (!logfs_check_ds(page_address(last))) {
page_cache_release(first);
return last;
}
/* Neither worked, sorry folks */
page_cache_release(first);
page_cache_release(last);
return NULL;
}
static int __logfs_read_sb(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
struct page *page;
struct logfs_disk_super *ds;
int i;
page = find_super_block(sb);
if (!page)
return -EINVAL;
ds = page_address(page);
super->s_size = be64_to_cpu(ds->ds_filesystem_size);
super->s_root_reserve = be64_to_cpu(ds->ds_root_reserve);
super->s_speed_reserve = be64_to_cpu(ds->ds_speed_reserve);
super->s_bad_seg_reserve = be32_to_cpu(ds->ds_bad_seg_reserve);
super->s_segsize = 1 << ds->ds_segment_shift;
super->s_segmask = (1 << ds->ds_segment_shift) - 1;
super->s_segshift = ds->ds_segment_shift;
sb->s_blocksize = 1 << ds->ds_block_shift;
sb->s_blocksize_bits = ds->ds_block_shift;
super->s_writesize = 1 << ds->ds_write_shift;
super->s_writeshift = ds->ds_write_shift;
super->s_no_segs = super->s_size >> super->s_segshift;
super->s_no_blocks = super->s_segsize >> sb->s_blocksize_bits;
super->s_feature_incompat = be64_to_cpu(ds->ds_feature_incompat);
super->s_feature_ro_compat = be64_to_cpu(ds->ds_feature_ro_compat);
super->s_feature_compat = be64_to_cpu(ds->ds_feature_compat);
super->s_feature_flags = be64_to_cpu(ds->ds_feature_flags);
journal_for_each(i)
super->s_journal_seg[i] = be32_to_cpu(ds->ds_journal_seg[i]);
super->s_ifile_levels = ds->ds_ifile_levels;
super->s_iblock_levels = ds->ds_iblock_levels;
super->s_data_levels = ds->ds_data_levels;
super->s_total_levels = super->s_ifile_levels + super->s_iblock_levels
+ super->s_data_levels;
page_cache_release(page);
return 0;
}
2010-03-05 16:07:04 +01:00
static int logfs_read_sb(struct super_block *sb, int read_only)
{
struct logfs_super *super = logfs_super(sb);
int ret;
super->s_btree_pool = mempool_create(32, btree_alloc, btree_free, NULL);
if (!super->s_btree_pool)
return -ENOMEM;
btree_init_mempool64(&super->s_shadow_tree.new, super->s_btree_pool);
btree_init_mempool64(&super->s_shadow_tree.old, super->s_btree_pool);
btree_init_mempool32(&super->s_shadow_tree.segment_map,
super->s_btree_pool);
ret = logfs_init_mapping(sb);
if (ret)
return ret;
ret = __logfs_read_sb(sb);
if (ret)
return ret;
2010-03-05 16:07:04 +01:00
if (super->s_feature_incompat & ~LOGFS_FEATURES_INCOMPAT)
return -EIO;
if ((super->s_feature_ro_compat & ~LOGFS_FEATURES_RO_COMPAT) &&
!read_only)
return -EIO;
ret = logfs_init_rw(sb);
if (ret)
return ret;
ret = logfs_init_areas(sb);
if (ret)
return ret;
ret = logfs_init_gc(sb);
if (ret)
return ret;
ret = logfs_init_journal(sb);
if (ret)
return ret;
return 0;
}
static void logfs_kill_sb(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
log_super("LogFS: Start unmounting\n");
/* Alias entries slow down mount, so evict as many as possible */
sync_filesystem(sb);
logfs_write_anchor(sb);
free_areas(sb);
/*
* From this point on alias entries are simply dropped - and any
* writes to the object store are considered bugs.
*/
log_super("LogFS: Now in shutdown\n");
generic_shutdown_super(sb);
logfs: set superblock shutdown flag after generic sb shutdown While unmounting the file system LogFS calls generic_shutdown_super. The function does file system independent superblock shutdown. However, it might result in call file system specific inode eviction. LogFS marks FS shutting down by setting bit LOGFS_SB_FLAG_SHUTDOWN in super->s_flags. Since, inode eviction might call truncate on inode, following BUG is observed when file system is unmounted: ------------[ cut here ]------------ kernel BUG at /home/prasad/logfs/segment.c:362! invalid opcode: 0000 [#1] PREEMPT SMP CPU 3 Modules linked in: logfs binfmt_misc ppdev virtio_blk parport_pc lp parport psmouse floppy virtio_pci serio_raw virtio_ring virtio Pid: 1933, comm: umount Not tainted 3.0.0+ #4 Bochs Bochs RIP: 0010:[<ffffffffa008c841>] [<ffffffffa008c841>] logfs_segment_write+0x211/0x230 [logfs] RSP: 0018:ffff880062d7b9e8 EFLAGS: 00010202 RAX: 000000000000000e RBX: ffff88006eca9000 RCX: 0000000000000000 RDX: ffff88006fd87c40 RSI: ffffea00014ff468 RDI: ffff88007b68e000 RBP: ffff880062d7ba48 R08: 8000000020451430 R09: 0000000000000000 R10: dead000000100100 R11: 0000000000000000 R12: ffff88006fd87c40 R13: ffffea00014ff468 R14: ffff88005ad0a460 R15: 0000000000000000 FS: 00007f25d50ea760(0000) GS:ffff88007fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000d05e48 CR3: 0000000062c72000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process umount (pid: 1933, threadinfo ffff880062d7a000, task ffff880070b44500) Stack: ffff880062d7ba38 ffff88005ad0a508 0000000000001000 0000000000000000 8000000020451430 ffffea00014ff468 ffff880062d7ba48 ffff88005ad0a460 ffff880062d7bad8 ffffea00014ff468 ffff88006fd87c40 0000000000000000 Call Trace: [<ffffffffa0088fee>] logfs_write_i0+0x12e/0x190 [logfs] [<ffffffffa0089360>] __logfs_write_rec+0x140/0x220 [logfs] [<ffffffffa0089312>] __logfs_write_rec+0xf2/0x220 [logfs] [<ffffffffa00894a4>] logfs_write_rec+0x64/0xd0 [logfs] [<ffffffffa0089616>] __logfs_write_buf+0x106/0x110 [logfs] [<ffffffffa008a19e>] logfs_write_buf+0x4e/0x80 [logfs] [<ffffffffa008a6b8>] __logfs_write_inode+0x98/0x110 [logfs] [<ffffffffa008a7c4>] logfs_truncate+0x54/0x290 [logfs] [<ffffffffa008abfc>] logfs_evict_inode+0xdc/0x190 [logfs] [<ffffffff8115eef5>] evict+0x85/0x170 [<ffffffff8115f126>] iput+0xe6/0x1b0 [<ffffffff8115b4a8>] shrink_dcache_for_umount_subtree+0x218/0x280 [<ffffffff8115ce91>] shrink_dcache_for_umount+0x51/0x90 [<ffffffff8114796c>] generic_shutdown_super+0x2c/0x100 [<ffffffffa008cc47>] logfs_kill_sb+0x57/0xf0 [logfs] [<ffffffff81147de5>] deactivate_locked_super+0x45/0x70 [<ffffffff811487ea>] deactivate_super+0x4a/0x70 [<ffffffff81163934>] mntput_no_expire+0xa4/0xf0 [<ffffffff8116469f>] sys_umount+0x6f/0x380 [<ffffffff814dd46b>] system_call_fastpath+0x16/0x1b Code: 55 c8 49 8d b6 a8 00 00 00 45 89 f9 45 89 e8 4c 89 e1 4c 89 55 b8 c7 04 24 00 00 00 00 e8 68 fc ff ff 4c 8b 55 b8 e9 3c ff ff ff <0f> 0b 0f 0b c7 45 c0 00 00 00 00 e9 44 fe ff ff 66 66 66 66 66 RIP [<ffffffffa008c841>] logfs_segment_write+0x211/0x230 [logfs] RSP <ffff880062d7b9e8> ---[ end trace fe6b040cea952290 ]--- Therefore, move super->s_flags setting after the fs-indenpendent work has been finished. Reviewed-by: Joern Engel <joern@logfs.org> Signed-off-by: Prasad Joshi <prasadjoshi.linux@gmail.com>
2011-10-30 17:45:32 +01:00
super->s_flags |= LOGFS_SB_FLAG_SHUTDOWN;
BUG_ON(super->s_dirty_used_bytes || super->s_dirty_free_bytes);
logfs_cleanup_gc(sb);
logfs_cleanup_journal(sb);
logfs_cleanup_areas(sb);
logfs_cleanup_rw(sb);
if (super->s_erase_page)
__free_page(super->s_erase_page);
super->s_devops->put_device(super);
logfs_mempool_destroy(super->s_btree_pool);
logfs_mempool_destroy(super->s_alias_pool);
kfree(super);
log_super("LogFS: Finished unmounting\n");
}
static struct dentry *logfs_get_sb_device(struct logfs_super *super,
struct file_system_type *type, int flags)
{
struct super_block *sb;
int err = -ENOMEM;
static int mount_count;
log_super("LogFS: Start mount %x\n", mount_count++);
err = -EINVAL;
sb = sget(type, logfs_sb_test, logfs_sb_set, flags | MS_NOATIME, super);
if (IS_ERR(sb)) {
super->s_devops->put_device(super);
kfree(super);
return ERR_CAST(sb);
}
if (sb->s_root) {
/* Device is already in use */
super->s_devops->put_device(super);
kfree(super);
return dget(sb->s_root);
}
/*
* sb->s_maxbytes is limited to 8TB. On 32bit systems, the page cache
* only covers 16TB and the upper 8TB are used for indirect blocks.
* On 64bit system we could bump up the limit, but that would make
* the filesystem incompatible with 32bit systems.
*/
sb->s_maxbytes = (1ull << 43) - 1;
sb->s_max_links = LOGFS_LINK_MAX;
sb->s_op = &logfs_super_operations;
2010-03-05 16:07:04 +01:00
err = logfs_read_sb(sb, sb->s_flags & MS_RDONLY);
if (err)
goto err1;
sb->s_flags |= MS_ACTIVE;
err = logfs_get_sb_final(sb);
if (err) {
deactivate_locked_super(sb);
return ERR_PTR(err);
}
return dget(sb->s_root);
err1:
/* no ->s_root, no ->put_super() */
iput(super->s_master_inode);
iput(super->s_segfile_inode);
iput(super->s_mapping_inode);
deactivate_locked_super(sb);
return ERR_PTR(err);
}
static struct dentry *logfs_mount(struct file_system_type *type, int flags,
const char *devname, void *data)
{
ulong mtdnr;
struct logfs_super *super;
int err;
super = kzalloc(sizeof(*super), GFP_KERNEL);
if (!super)
return ERR_PTR(-ENOMEM);
mutex_init(&super->s_dirop_mutex);
mutex_init(&super->s_object_alias_mutex);
INIT_LIST_HEAD(&super->s_freeing_list);
if (!devname)
err = logfs_get_sb_bdev(super, type, devname);
else if (strncmp(devname, "mtd", 3))
err = logfs_get_sb_bdev(super, type, devname);
else {
char *garbage;
mtdnr = simple_strtoul(devname+3, &garbage, 0);
if (*garbage)
err = -EINVAL;
else
err = logfs_get_sb_mtd(super, mtdnr);
}
if (err) {
kfree(super);
return ERR_PTR(err);
}
return logfs_get_sb_device(super, type, flags);
}
static struct file_system_type logfs_fs_type = {
.owner = THIS_MODULE,
.name = "logfs",
.mount = logfs_mount,
.kill_sb = logfs_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 04:39:14 +01:00
MODULE_ALIAS_FS("logfs");
static int __init logfs_init(void)
{
int ret;
emergency_page = alloc_pages(GFP_KERNEL, 0);
if (!emergency_page)
return -ENOMEM;
ret = logfs_compr_init();
if (ret)
goto out1;
ret = logfs_init_inode_cache();
if (ret)
goto out2;
ret = register_filesystem(&logfs_fs_type);
if (!ret)
return 0;
logfs_destroy_inode_cache();
out2:
logfs_compr_exit();
out1:
__free_pages(emergency_page, 0);
return ret;
}
static void __exit logfs_exit(void)
{
unregister_filesystem(&logfs_fs_type);
logfs_destroy_inode_cache();
logfs_compr_exit();
__free_pages(emergency_page, 0);
}
module_init(logfs_init);
module_exit(logfs_exit);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Joern Engel <joern@logfs.org>");
MODULE_DESCRIPTION("scalable flash filesystem");