linux/fs/ubifs/super.c

2509 lines
65 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* This file is part of UBIFS.
*
* Copyright (C) 2006-2008 Nokia Corporation.
*
* Authors: Artem Bityutskiy (Битюцкий Артём)
* Adrian Hunter
*/
/*
* This file implements UBIFS initialization and VFS superblock operations. Some
* initialization stuff which is rather large and complex is placed at
* corresponding subsystems, but most of it is here.
*/
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/kthread.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/math64.h>
#include <linux/writeback.h>
#include "ubifs.h"
static int ubifs_default_version_set(const char *val, const struct kernel_param *kp)
{
int n = 0, ret;
ret = kstrtoint(val, 10, &n);
if (ret != 0 || n < 4 || n > UBIFS_FORMAT_VERSION)
return -EINVAL;
return param_set_int(val, kp);
}
static const struct kernel_param_ops ubifs_default_version_ops = {
.set = ubifs_default_version_set,
.get = param_get_int,
};
int ubifs_default_version = UBIFS_FORMAT_VERSION;
module_param_cb(default_version, &ubifs_default_version_ops, &ubifs_default_version, 0600);
/*
* Maximum amount of memory we may 'kmalloc()' without worrying that we are
* allocating too much.
*/
#define UBIFS_KMALLOC_OK (128*1024)
/* Slab cache for UBIFS inodes */
static struct kmem_cache *ubifs_inode_slab;
/* UBIFS TNC shrinker description */
ubifs: dynamically allocate the ubifs-slab shrinker Use new APIs to dynamically allocate the ubifs-slab shrinker. Link: https://lkml.kernel.org/r/20230911094444.68966-15-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Richard Weinberger <richard@nod.at> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: "Darrick J. Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sean Paul <sean@poorly.run> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 17:44:13 +08:00
static struct shrinker *ubifs_shrinker_info;
/**
* validate_inode - validate inode.
* @c: UBIFS file-system description object
* @inode: the inode to validate
*
* This is a helper function for 'ubifs_iget()' which validates various fields
* of a newly built inode to make sure they contain sane values and prevent
* possible vulnerabilities. Returns zero if the inode is all right and
* a non-zero error code if not.
*/
static int validate_inode(struct ubifs_info *c, const struct inode *inode)
{
int err;
const struct ubifs_inode *ui = ubifs_inode(inode);
if (inode->i_size > c->max_inode_sz) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "inode is too large (%lld)",
(long long)inode->i_size);
return 1;
}
if (ui->compr_type >= UBIFS_COMPR_TYPES_CNT) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "unknown compression type %d", ui->compr_type);
return 2;
}
if (ui->xattr_names + ui->xattr_cnt > XATTR_LIST_MAX)
return 3;
if (ui->data_len < 0 || ui->data_len > UBIFS_MAX_INO_DATA)
return 4;
if (ui->xattr && !S_ISREG(inode->i_mode))
return 5;
if (!ubifs_compr_present(c, ui->compr_type)) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_warn(c, "inode %lu uses '%s' compression, but it was not compiled in",
inode->i_ino, ubifs_compr_name(c, ui->compr_type));
}
err = dbg_check_dir(c, inode);
return err;
}
struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
{
int err;
union ubifs_key key;
struct ubifs_ino_node *ino;
struct ubifs_info *c = sb->s_fs_info;
struct inode *inode;
struct ubifs_inode *ui;
dbg_gen("inode %lu", inum);
inode = iget_locked(sb, inum);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
ui = ubifs_inode(inode);
ino = kmalloc(UBIFS_MAX_INO_NODE_SZ, GFP_NOFS);
if (!ino) {
err = -ENOMEM;
goto out;
}
ino_key_init(c, &key, inode->i_ino);
err = ubifs_tnc_lookup(c, &key, ino);
if (err)
goto out_ino;
inode->i_flags |= S_NOCMTIME;
if (!IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT))
inode->i_flags |= S_NOATIME;
set_nlink(inode, le32_to_cpu(ino->nlink));
i_uid_write(inode, le32_to_cpu(ino->uid));
i_gid_write(inode, le32_to_cpu(ino->gid));
inode_set_atime(inode, (int64_t)le64_to_cpu(ino->atime_sec),
le32_to_cpu(ino->atime_nsec));
inode_set_mtime(inode, (int64_t)le64_to_cpu(ino->mtime_sec),
le32_to_cpu(ino->mtime_nsec));
inode_set_ctime(inode, (int64_t)le64_to_cpu(ino->ctime_sec),
le32_to_cpu(ino->ctime_nsec));
inode->i_mode = le32_to_cpu(ino->mode);
inode->i_size = le64_to_cpu(ino->size);
ui->data_len = le32_to_cpu(ino->data_len);
ui->flags = le32_to_cpu(ino->flags);
ui->compr_type = le16_to_cpu(ino->compr_type);
ui->creat_sqnum = le64_to_cpu(ino->creat_sqnum);
ui->xattr_cnt = le32_to_cpu(ino->xattr_cnt);
ui->xattr_size = le32_to_cpu(ino->xattr_size);
ui->xattr_names = le32_to_cpu(ino->xattr_names);
ui->synced_i_size = ui->ui_size = inode->i_size;
ui->xattr = (ui->flags & UBIFS_XATTR_FL) ? 1 : 0;
err = validate_inode(c, inode);
if (err)
goto out_invalid;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &ubifs_file_address_operations;
inode->i_op = &ubifs_file_inode_operations;
inode->i_fop = &ubifs_file_operations;
if (ui->xattr) {
ui->data = kmalloc(ui->data_len + 1, GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_ino;
}
memcpy(ui->data, ino->data, ui->data_len);
((char *)ui->data)[ui->data_len] = '\0';
} else if (ui->data_len != 0) {
err = 10;
goto out_invalid;
}
break;
case S_IFDIR:
inode->i_op = &ubifs_dir_inode_operations;
inode->i_fop = &ubifs_dir_operations;
if (ui->data_len != 0) {
err = 11;
goto out_invalid;
}
break;
case S_IFLNK:
inode->i_op = &ubifs_symlink_inode_operations;
if (ui->data_len <= 0 || ui->data_len > UBIFS_MAX_INO_DATA) {
err = 12;
goto out_invalid;
}
ui->data = kmalloc(ui->data_len + 1, GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_ino;
}
memcpy(ui->data, ino->data, ui->data_len);
((char *)ui->data)[ui->data_len] = '\0';
break;
case S_IFBLK:
case S_IFCHR:
{
dev_t rdev;
union ubifs_dev_desc *dev;
ui->data = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_ino;
}
dev = (union ubifs_dev_desc *)ino->data;
if (ui->data_len == sizeof(dev->new))
rdev = new_decode_dev(le32_to_cpu(dev->new));
else if (ui->data_len == sizeof(dev->huge))
rdev = huge_decode_dev(le64_to_cpu(dev->huge));
else {
err = 13;
goto out_invalid;
}
memcpy(ui->data, ino->data, ui->data_len);
inode->i_op = &ubifs_file_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
break;
}
case S_IFSOCK:
case S_IFIFO:
inode->i_op = &ubifs_file_inode_operations;
init_special_inode(inode, inode->i_mode, 0);
if (ui->data_len != 0) {
err = 14;
goto out_invalid;
}
break;
default:
err = 15;
goto out_invalid;
}
kfree(ino);
ubifs_set_inode_flags(inode);
unlock_new_inode(inode);
return inode;
out_invalid:
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "inode %lu validation failed, error %d", inode->i_ino, err);
ubifs_dump_node(c, ino, UBIFS_MAX_INO_NODE_SZ);
ubifs_dump_inode(c, inode);
err = -EINVAL;
out_ino:
kfree(ino);
out:
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "failed to read inode %lu, error %d", inode->i_ino, err);
iget_failed(inode);
return ERR_PTR(err);
}
static struct inode *ubifs_alloc_inode(struct super_block *sb)
{
struct ubifs_inode *ui;
ui = alloc_inode_sb(sb, ubifs_inode_slab, GFP_NOFS);
if (!ui)
return NULL;
memset((void *)ui + sizeof(struct inode), 0,
sizeof(struct ubifs_inode) - sizeof(struct inode));
mutex_init(&ui->ui_mutex);
init_rwsem(&ui->xattr_sem);
spin_lock_init(&ui->ui_lock);
return &ui->vfs_inode;
};
static void ubifs_free_inode(struct inode *inode)
2011-01-07 14:49:49 +08:00
{
struct ubifs_inode *ui = ubifs_inode(inode);
kfree(ui->data);
fscrypt_free_inode(inode);
2011-01-07 14:49:49 +08:00
kmem_cache_free(ubifs_inode_slab, ui);
}
/*
* Note, Linux write-back code calls this without 'i_mutex'.
*/
static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err = 0;
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct ubifs_inode *ui = ubifs_inode(inode);
ubifs_assert(c, !ui->xattr);
if (is_bad_inode(inode))
return 0;
mutex_lock(&ui->ui_mutex);
/*
* Due to races between write-back forced by budgeting
* (see 'sync_some_inodes()') and background write-back, the inode may
* have already been synchronized, do not do this again. This might
* also happen if it was synchronized in an VFS operation, e.g.
* 'ubifs_link()'.
*/
if (!ui->dirty) {
mutex_unlock(&ui->ui_mutex);
return 0;
}
/*
* As an optimization, do not write orphan inodes to the media just
* because this is not needed.
*/
dbg_gen("inode %lu, mode %#x, nlink %u",
inode->i_ino, (int)inode->i_mode, inode->i_nlink);
if (inode->i_nlink) {
err = ubifs_jnl_write_inode(c, inode);
if (err)
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "can't write inode %lu, error %d",
inode->i_ino, err);
else
err = dbg_check_inode_size(c, inode, ui->ui_size);
}
ui->dirty = 0;
mutex_unlock(&ui->ui_mutex);
ubifs_release_dirty_inode_budget(c, ui);
return err;
}
static int ubifs_drop_inode(struct inode *inode)
{
int drop = generic_drop_inode(inode);
if (!drop)
drop = fscrypt_drop_inode(inode);
return drop;
}
static void ubifs_evict_inode(struct inode *inode)
{
int err;
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct ubifs_inode *ui = ubifs_inode(inode);
if (ui->xattr)
/*
* Extended attribute inode deletions are fully handled in
* 'ubifs_removexattr()'. These inodes are special and have
* limited usage, so there is nothing to do here.
*/
goto out;
dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
ubifs_assert(c, !atomic_read(&inode->i_count));
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-04 05:47:49 +08:00
truncate_inode_pages_final(&inode->i_data);
if (inode->i_nlink)
goto done;
if (is_bad_inode(inode))
goto out;
ui->ui_size = inode->i_size = 0;
err = ubifs_jnl_delete_inode(c, inode);
if (err)
/*
* Worst case we have a lost orphan inode wasting space, so a
* simple error message is OK here.
*/
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "can't delete inode %lu, error %d",
inode->i_ino, err);
out:
if (ui->dirty)
ubifs_release_dirty_inode_budget(c, ui);
else {
/* We've deleted something - clean the "no space" flags */
c->bi.nospace = c->bi.nospace_rp = 0;
smp_wmb();
}
done:
clear_inode(inode);
fscrypt_put_encryption_info(inode);
}
static void ubifs_dirty_inode(struct inode *inode, int flags)
{
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct ubifs_inode *ui = ubifs_inode(inode);
ubifs_assert(c, mutex_is_locked(&ui->ui_mutex));
if (!ui->dirty) {
ui->dirty = 1;
dbg_gen("inode %lu", inode->i_ino);
}
}
static int ubifs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct ubifs_info *c = dentry->d_sb->s_fs_info;
unsigned long long free;
__le32 *uuid = (__le32 *)c->uuid;
UBIFS: improve statfs reporting even more Since free space we report in statfs is file size which should fit to the FS - change the way we calculate free space and use leb_overhead instead of dark_wm in calculations. Results of "freespace" test (120MiB volume, 16KiB LEB size, 512 bytes page size). Before the change: freespace: Test 1: fill the space we have 3 times freespace: was free: 85204992 bytes 81.3 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 11284480 bytes 10.8 MiB, wrote 13.2% more than predicted freespace: was free: 83554304 bytes 79.7 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 12935168 bytes 12.3 MiB, wrote 15.5% more than predicted freespace: was free: 83554304 bytes 79.7 MiB, wrote: 96493568 bytes 92.0 MiB, delta: 12939264 bytes 12.3 MiB, wrote 15.5% more than predicted freespace: Test 1 finished freespace: Test 2: gradually lessen amount of free space and fill the FS freespace: do 10 steps, lessen free space by 7596218 bytes 7.2 MiB each time freespace: was free: 78675968 bytes 75.0 MiB, wrote: 88903680 bytes 84.8 MiB, delta: 10227712 bytes 9.8 MiB, wrote 13.0% more than predicted freespace: was free: 72015872 bytes 68.7 MiB, wrote: 81514496 bytes 77.7 MiB, delta: 9498624 bytes 9.1 MiB, wrote 13.2% more than predicted freespace: was free: 63938560 bytes 61.0 MiB, wrote: 72589312 bytes 69.2 MiB, delta: 8650752 bytes 8.2 MiB, wrote 13.5% more than predicted freespace: was free: 56127488 bytes 53.5 MiB, wrote: 63762432 bytes 60.8 MiB, delta: 7634944 bytes 7.3 MiB, wrote 13.6% more than predicted freespace: was free: 48336896 bytes 46.1 MiB, wrote: 54935552 bytes 52.4 MiB, delta: 6598656 bytes 6.3 MiB, wrote 13.7% more than predicted freespace: was free: 40587264 bytes 38.7 MiB, wrote: 46157824 bytes 44.0 MiB, delta: 5570560 bytes 5.3 MiB, wrote 13.7% more than predicted freespace: was free: 32841728 bytes 31.3 MiB, wrote: 37384192 bytes 35.7 MiB, delta: 4542464 bytes 4.3 MiB, wrote 13.8% more than predicted freespace: was free: 25100288 bytes 23.9 MiB, wrote: 28618752 bytes 27.3 MiB, delta: 3518464 bytes 3.4 MiB, wrote 14.0% more than predicted freespace: was free: 17342464 bytes 16.5 MiB, wrote: 19841024 bytes 18.9 MiB, delta: 2498560 bytes 2.4 MiB, wrote 14.4% more than predicted freespace: was free: 9605120 bytes 9.2 MiB, wrote: 11063296 bytes 10.6 MiB, delta: 1458176 bytes 1.4 MiB, wrote 15.2% more than predicted freespace: Test 2 finished freespace: Test 3: gradually lessen amount of free space by trashing and fill the FS freespace: do 10 steps, lessen free space by 7606272 bytes 7.3 MiB each time freespace: trashing: was free: 83668992 bytes 79.8 MiB, need free: 7606272 bytes 7.3 MiB, files created: 248297, delete 225724 (90.9% of them) freespace: was free: 70803456 bytes 67.5 MiB, wrote: 82485248 bytes 78.7 MiB, delta: 11681792 bytes 11.1 MiB, wrote 16.5% more than predicted freespace: trashing: was free: 81080320 bytes 77.3 MiB, need free: 15212544 bytes 14.5 MiB, files created: 248711, delete 202047 (81.2% of them) freespace: was free: 59867136 bytes 57.1 MiB, wrote: 71897088 bytes 68.6 MiB, delta: 12029952 bytes 11.5 MiB, wrote 20.1% more than predicted freespace: trashing: was free: 82243584 bytes 78.4 MiB, need free: 22818816 bytes 21.8 MiB, files created: 248866, delete 179817 (72.3% of them) freespace: was free: 50905088 bytes 48.5 MiB, wrote: 63168512 bytes 60.2 MiB, delta: 12263424 bytes 11.7 MiB, wrote 24.1% more than predicted freespace: trashing: was free: 83402752 bytes 79.5 MiB, need free: 30425088 bytes 29.0 MiB, files created: 248920, delete 158114 (63.5% of them) freespace: was free: 42651648 bytes 40.7 MiB, wrote: 55406592 bytes 52.8 MiB, delta: 12754944 bytes 12.2 MiB, wrote 29.9% more than predicted freespace: trashing: was free: 84402176 bytes 80.5 MiB, need free: 38031360 bytes 36.3 MiB, files created: 248709, delete 136641 (54.9% of them) freespace: was free: 35233792 bytes 33.6 MiB, wrote: 48250880 bytes 46.0 MiB, delta: 13017088 bytes 12.4 MiB, wrote 36.9% more than predicted freespace: trashing: was free: 82530304 bytes 78.7 MiB, need free: 45637632 bytes 43.5 MiB, files created: 248778, delete 111208 (44.7% of them) freespace: was free: 27287552 bytes 26.0 MiB, wrote: 40267776 bytes 38.4 MiB, delta: 12980224 bytes 12.4 MiB, wrote 47.6% more than predicted freespace: trashing: was free: 85114880 bytes 81.2 MiB, need free: 53243904 bytes 50.8 MiB, files created: 248508, delete 93052 (37.4% of them) freespace: was free: 22437888 bytes 21.4 MiB, wrote: 35328000 bytes 33.7 MiB, delta: 12890112 bytes 12.3 MiB, wrote 57.4% more than predicted freespace: trashing: was free: 84103168 bytes 80.2 MiB, need free: 60850176 bytes 58.0 MiB, files created: 248637, delete 68743 (27.6% of them) freespace: was free: 15536128 bytes 14.8 MiB, wrote: 28319744 bytes 27.0 MiB, delta: 12783616 bytes 12.2 MiB, wrote 82.3% more than predicted freespace: trashing: was free: 84357120 bytes 80.4 MiB, need free: 68456448 bytes 65.3 MiB, files created: 248567, delete 46852 (18.8% of them) freespace: was free: 9015296 bytes 8.6 MiB, wrote: 22044672 bytes 21.0 MiB, delta: 13029376 bytes 12.4 MiB, wrote 144.5% more than predicted freespace: trashing: was free: 84942848 bytes 81.0 MiB, need free: 76062720 bytes 72.5 MiB, files created: 248636, delete 25993 (10.5% of them) freespace: was free: 6086656 bytes 5.8 MiB, wrote: 8331264 bytes 7.9 MiB, delta: 2244608 bytes 2.1 MiB, wrote 36.9% more than predicted freespace: Test 3 finished freespace: finished successfully After the change: freespace: Test 1: fill the space we have 3 times freespace: was free: 94048256 bytes 89.7 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 2441216 bytes 2.3 MiB, wrote 2.6% more than predicted freespace: was free: 92246016 bytes 88.0 MiB, wrote: 96493568 bytes 92.0 MiB, delta: 4247552 bytes 4.1 MiB, wrote 4.6% more than predicted freespace: was free: 92254208 bytes 88.0 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 4235264 bytes 4.0 MiB, wrote 4.6% more than predicted freespace: Test 1 finished freespace: Test 2: gradually lessen amount of free space and fill the FS freespace: do 10 steps, lessen free space by 8386001 bytes 8.0 MiB each time freespace: was free: 86605824 bytes 82.6 MiB, wrote: 88252416 bytes 84.2 MiB, delta: 1646592 bytes 1.6 MiB, wrote 1.9% more than predicted freespace: was free: 78667776 bytes 75.0 MiB, wrote: 80715776 bytes 77.0 MiB, delta: 2048000 bytes 2.0 MiB, wrote 2.6% more than predicted freespace: was free: 69615616 bytes 66.4 MiB, wrote: 71630848 bytes 68.3 MiB, delta: 2015232 bytes 1.9 MiB, wrote 2.9% more than predicted freespace: was free: 61018112 bytes 58.2 MiB, wrote: 62783488 bytes 59.9 MiB, delta: 1765376 bytes 1.7 MiB, wrote 2.9% more than predicted freespace: was free: 52424704 bytes 50.0 MiB, wrote: 53968896 bytes 51.5 MiB, delta: 1544192 bytes 1.5 MiB, wrote 2.9% more than predicted freespace: was free: 43880448 bytes 41.8 MiB, wrote: 45199360 bytes 43.1 MiB, delta: 1318912 bytes 1.3 MiB, wrote 3.0% more than predicted freespace: was free: 35332096 bytes 33.7 MiB, wrote: 36425728 bytes 34.7 MiB, delta: 1093632 bytes 1.0 MiB, wrote 3.1% more than predicted freespace: was free: 26771456 bytes 25.5 MiB, wrote: 27643904 bytes 26.4 MiB, delta: 872448 bytes 852.0 KiB, wrote 3.3% more than predicted freespace: was free: 18231296 bytes 17.4 MiB, wrote: 18878464 bytes 18.0 MiB, delta: 647168 bytes 632.0 KiB, wrote 3.5% more than predicted freespace: was free: 9674752 bytes 9.2 MiB, wrote: 10088448 bytes 9.6 MiB, delta: 413696 bytes 404.0 KiB, wrote 4.3% more than predicted freespace: Test 2 finished freespace: Test 3: gradually lessen amount of free space by trashing and fill the FS freespace: do 10 steps, lessen free space by 8397544 bytes 8.0 MiB each time freespace: trashing: was free: 92372992 bytes 88.1 MiB, need free: 8397552 bytes 8.0 MiB, files created: 248296, delete 225723 (90.9% of them) freespace: was free: 71909376 bytes 68.6 MiB, wrote: 82472960 bytes 78.7 MiB, delta: 10563584 bytes 10.1 MiB, wrote 14.7% more than predicted freespace: trashing: was free: 88989696 bytes 84.9 MiB, need free: 16795096 bytes 16.0 MiB, files created: 248794, delete 201838 (81.1% of them) freespace: was free: 60354560 bytes 57.6 MiB, wrote: 71782400 bytes 68.5 MiB, delta: 11427840 bytes 10.9 MiB, wrote 18.9% more than predicted freespace: trashing: was free: 90304512 bytes 86.1 MiB, need free: 25192640 bytes 24.0 MiB, files created: 248733, delete 179342 (72.1% of them) freespace: was free: 51187712 bytes 48.8 MiB, wrote: 62943232 bytes 60.0 MiB, delta: 11755520 bytes 11.2 MiB, wrote 23.0% more than predicted freespace: trashing: was free: 91209728 bytes 87.0 MiB, need free: 33590184 bytes 32.0 MiB, files created: 248779, delete 157160 (63.2% of them) freespace: was free: 42704896 bytes 40.7 MiB, wrote: 55050240 bytes 52.5 MiB, delta: 12345344 bytes 11.8 MiB, wrote 28.9% more than predicted freespace: trashing: was free: 92700672 bytes 88.4 MiB, need free: 41987728 bytes 40.0 MiB, files created: 248848, delete 136135 (54.7% of them) freespace: was free: 35250176 bytes 33.6 MiB, wrote: 48115712 bytes 45.9 MiB, delta: 12865536 bytes 12.3 MiB, wrote 36.5% more than predicted freespace: trashing: was free: 93986816 bytes 89.6 MiB, need free: 50385272 bytes 48.1 MiB, files created: 248723, delete 115385 (46.4% of them) freespace: was free: 29995008 bytes 28.6 MiB, wrote: 41582592 bytes 39.7 MiB, delta: 11587584 bytes 11.1 MiB, wrote 38.6% more than predicted freespace: trashing: was free: 91881472 bytes 87.6 MiB, need free: 58782816 bytes 56.1 MiB, files created: 248645, delete 89569 (36.0% of them) freespace: was free: 22511616 bytes 21.5 MiB, wrote: 34705408 bytes 33.1 MiB, delta: 12193792 bytes 11.6 MiB, wrote 54.2% more than predicted freespace: trashing: was free: 91774976 bytes 87.5 MiB, need free: 67180360 bytes 64.1 MiB, files created: 248580, delete 66616 (26.8% of them) freespace: was free: 16908288 bytes 16.1 MiB, wrote: 26898432 bytes 25.7 MiB, delta: 9990144 bytes 9.5 MiB, wrote 59.1% more than predicted freespace: trashing: was free: 92450816 bytes 88.2 MiB, need free: 75577904 bytes 72.1 MiB, files created: 248654, delete 45381 (18.3% of them) freespace: was free: 10170368 bytes 9.7 MiB, wrote: 19111936 bytes 18.2 MiB, delta: 8941568 bytes 8.5 MiB, wrote 87.9% more than predicted freespace: trashing: was free: 93282304 bytes 89.0 MiB, need free: 83975448 bytes 80.1 MiB, files created: 248513, delete 24794 (10.0% of them) freespace: was free: 3911680 bytes 3.7 MiB, wrote: 7872512 bytes 7.5 MiB, delta: 3960832 bytes 3.8 MiB, wrote 101.3% more than predicted freespace: Test 3 finished freespace: finished successfully Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
2008-08-25 23:58:19 +08:00
free = ubifs_get_free_space(c);
dbg_gen("free space %lld bytes (%lld blocks)",
free, free >> UBIFS_BLOCK_SHIFT);
buf->f_type = UBIFS_SUPER_MAGIC;
buf->f_bsize = UBIFS_BLOCK_SIZE;
buf->f_blocks = c->block_cnt;
buf->f_bfree = free >> UBIFS_BLOCK_SHIFT;
if (free > c->report_rp_size)
buf->f_bavail = (free - c->report_rp_size) >> UBIFS_BLOCK_SHIFT;
else
buf->f_bavail = 0;
buf->f_files = 0;
buf->f_ffree = 0;
buf->f_namelen = UBIFS_MAX_NLEN;
buf->f_fsid.val[0] = le32_to_cpu(uuid[0]) ^ le32_to_cpu(uuid[2]);
buf->f_fsid.val[1] = le32_to_cpu(uuid[1]) ^ le32_to_cpu(uuid[3]);
ubifs_assert(c, buf->f_bfree <= c->block_cnt);
return 0;
}
static int ubifs_show_options(struct seq_file *s, struct dentry *root)
{
struct ubifs_info *c = root->d_sb->s_fs_info;
if (c->mount_opts.unmount_mode == 2)
seq_puts(s, ",fast_unmount");
else if (c->mount_opts.unmount_mode == 1)
seq_puts(s, ",norm_unmount");
if (c->mount_opts.bulk_read == 2)
seq_puts(s, ",bulk_read");
else if (c->mount_opts.bulk_read == 1)
seq_puts(s, ",no_bulk_read");
if (c->mount_opts.chk_data_crc == 2)
seq_puts(s, ",chk_data_crc");
else if (c->mount_opts.chk_data_crc == 1)
seq_puts(s, ",no_chk_data_crc");
if (c->mount_opts.override_compr) {
seq_printf(s, ",compr=%s",
ubifs_compr_name(c, c->mount_opts.compr_type));
}
seq_printf(s, ",assert=%s", ubifs_assert_action_name(c));
seq_printf(s, ",ubi=%d,vol=%d", c->vi.ubi_num, c->vi.vol_id);
return 0;
}
static int ubifs_sync_fs(struct super_block *sb, int wait)
{
int i, err;
struct ubifs_info *c = sb->s_fs_info;
/*
* Zero @wait is just an advisory thing to help the file system shove
* lots of data into the queues, and there will be the second
* '->sync_fs()' call, with non-zero @wait.
*/
if (!wait)
return 0;
/*
* Synchronize write buffers, because 'ubifs_run_commit()' does not
* do this if it waits for an already running commit.
*/
for (i = 0; i < c->jhead_cnt; i++) {
err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
if (err)
return err;
}
/*
* Strictly speaking, it is not necessary to commit the journal here,
* synchronizing write-buffers would be enough. But committing makes
* UBIFS free space predictions much more accurate, so we want to let
* the user be able to get more accurate results of 'statfs()' after
* they synchronize the file system.
*/
err = ubifs_run_commit(c);
if (err)
return err;
return ubi_sync(c->vi.ubi_num);
}
/**
* init_constants_early - initialize UBIFS constants.
* @c: UBIFS file-system description object
*
* This function initialize UBIFS constants which do not need the superblock to
* be read. It also checks that the UBI volume satisfies basic UBIFS
* requirements. Returns zero in case of success and a negative error code in
* case of failure.
*/
static int init_constants_early(struct ubifs_info *c)
{
if (c->vi.corrupted) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_warn(c, "UBI volume is corrupted - read-only mode");
c->ro_media = 1;
}
if (c->di.ro_mode) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "read-only UBI device");
c->ro_media = 1;
}
if (c->vi.vol_type == UBI_STATIC_VOLUME) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "static UBI volume - read-only mode");
c->ro_media = 1;
}
c->leb_cnt = c->vi.size;
c->leb_size = c->vi.usable_leb_size;
c->leb_start = c->di.leb_start;
c->half_leb_size = c->leb_size / 2;
c->min_io_size = c->di.min_io_size;
c->min_io_shift = fls(c->min_io_size) - 1;
c->max_write_size = c->di.max_write_size;
c->max_write_shift = fls(c->max_write_size) - 1;
if (c->leb_size < UBIFS_MIN_LEB_SZ) {
ubifs_errc(c, "too small LEBs (%d bytes), min. is %d bytes",
c->leb_size, UBIFS_MIN_LEB_SZ);
return -EINVAL;
}
if (c->leb_cnt < UBIFS_MIN_LEB_CNT) {
ubifs_errc(c, "too few LEBs (%d), min. is %d",
c->leb_cnt, UBIFS_MIN_LEB_CNT);
return -EINVAL;
}
if (!is_power_of_2(c->min_io_size)) {
ubifs_errc(c, "bad min. I/O size %d", c->min_io_size);
return -EINVAL;
}
/*
* Maximum write size has to be greater or equivalent to min. I/O
* size, and be multiple of min. I/O size.
*/
if (c->max_write_size < c->min_io_size ||
c->max_write_size % c->min_io_size ||
!is_power_of_2(c->max_write_size)) {
ubifs_errc(c, "bad write buffer size %d for %d min. I/O unit",
c->max_write_size, c->min_io_size);
return -EINVAL;
}
/*
* UBIFS aligns all node to 8-byte boundary, so to make function in
* io.c simpler, assume minimum I/O unit size to be 8 bytes if it is
* less than 8.
*/
if (c->min_io_size < 8) {
c->min_io_size = 8;
c->min_io_shift = 3;
if (c->max_write_size < c->min_io_size) {
c->max_write_size = c->min_io_size;
c->max_write_shift = c->min_io_shift;
}
}
c->ref_node_alsz = ALIGN(UBIFS_REF_NODE_SZ, c->min_io_size);
c->mst_node_alsz = ALIGN(UBIFS_MST_NODE_SZ, c->min_io_size);
/*
* Initialize node length ranges which are mostly needed for node
* length validation.
*/
c->ranges[UBIFS_PAD_NODE].len = UBIFS_PAD_NODE_SZ;
c->ranges[UBIFS_SB_NODE].len = UBIFS_SB_NODE_SZ;
c->ranges[UBIFS_MST_NODE].len = UBIFS_MST_NODE_SZ;
c->ranges[UBIFS_REF_NODE].len = UBIFS_REF_NODE_SZ;
c->ranges[UBIFS_TRUN_NODE].len = UBIFS_TRUN_NODE_SZ;
c->ranges[UBIFS_CS_NODE].len = UBIFS_CS_NODE_SZ;
c->ranges[UBIFS_AUTH_NODE].min_len = UBIFS_AUTH_NODE_SZ;
c->ranges[UBIFS_AUTH_NODE].max_len = UBIFS_AUTH_NODE_SZ +
UBIFS_MAX_HMAC_LEN;
ubifs: support offline signed images HMACs can only be generated on the system the UBIFS image is running on. To support offline signed images we add a PKCS#7 signature to the UBIFS image which can be created by mkfs.ubifs. Both the master node and the superblock need to be authenticated, during normal runtime both are protected with HMACs. For offline signature support however only a single signature is desired. We add a signature covering the superblock node directly behind it. To protect the master node a hash of the master node is added to the superblock which is used when the master node doesn't contain a HMAC. Transition to a read/write filesystem is also supported. During transition first the master node is rewritten with a HMAC (implicitly, it is written anyway as the FS is marked dirty). Afterwards the superblock is rewritten with a HMAC. Once after the image has been mounted read/write it is HMAC only, the signature is no longer required or even present on the filesystem. In an offline signed image the master node is authenticated by the superblock. In a transition to r/w we have to make sure that the master node is rewritten before the superblock node. In this case the master node gets a HMAC and its authenticity no longer depends on the superblock node. There are some cases in which the current code first writes the superblock node though, so with this patch writing of the superblock node is delayed until the master node is written. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2019-05-14 16:33:22 +08:00
c->ranges[UBIFS_SIG_NODE].min_len = UBIFS_SIG_NODE_SZ;
c->ranges[UBIFS_SIG_NODE].max_len = c->leb_size - UBIFS_SB_NODE_SZ;
c->ranges[UBIFS_INO_NODE].min_len = UBIFS_INO_NODE_SZ;
c->ranges[UBIFS_INO_NODE].max_len = UBIFS_MAX_INO_NODE_SZ;
c->ranges[UBIFS_ORPH_NODE].min_len =
UBIFS_ORPH_NODE_SZ + sizeof(__le64);
c->ranges[UBIFS_ORPH_NODE].max_len = c->leb_size;
c->ranges[UBIFS_DENT_NODE].min_len = UBIFS_DENT_NODE_SZ;
c->ranges[UBIFS_DENT_NODE].max_len = UBIFS_MAX_DENT_NODE_SZ;
c->ranges[UBIFS_XENT_NODE].min_len = UBIFS_XENT_NODE_SZ;
c->ranges[UBIFS_XENT_NODE].max_len = UBIFS_MAX_XENT_NODE_SZ;
c->ranges[UBIFS_DATA_NODE].min_len = UBIFS_DATA_NODE_SZ;
c->ranges[UBIFS_DATA_NODE].max_len = UBIFS_MAX_DATA_NODE_SZ;
/*
* Minimum indexing node size is amended later when superblock is
* read and the key length is known.
*/
c->ranges[UBIFS_IDX_NODE].min_len = UBIFS_IDX_NODE_SZ + UBIFS_BRANCH_SZ;
/*
* Maximum indexing node size is amended later when superblock is
* read and the fanout is known.
*/
c->ranges[UBIFS_IDX_NODE].max_len = INT_MAX;
/*
* Initialize dead and dark LEB space watermarks. See gc.c for comments
* about these values.
*/
c->dead_wm = ALIGN(MIN_WRITE_SZ, c->min_io_size);
c->dark_wm = ALIGN(UBIFS_MAX_NODE_SZ, c->min_io_size);
/*
* Calculate how many bytes would be wasted at the end of LEB if it was
* fully filled with data nodes of maximum size. This is used in
* calculations when reporting free space.
*/
c->leb_overhead = c->leb_size % UBIFS_MAX_DATA_NODE_SZ;
/* Buffer size for bulk-reads */
c->max_bu_buf_len = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ;
if (c->max_bu_buf_len > c->leb_size)
c->max_bu_buf_len = c->leb_size;
/* Log is ready, preserve one LEB for commits. */
c->min_log_bytes = c->leb_size;
return 0;
}
/**
* bud_wbuf_callback - bud LEB write-buffer synchronization call-back.
* @c: UBIFS file-system description object
* @lnum: LEB the write-buffer was synchronized to
* @free: how many free bytes left in this LEB
* @pad: how many bytes were padded
*
* This is a callback function which is called by the I/O unit when the
* write-buffer is synchronized. We need this to correctly maintain space
* accounting in bud logical eraseblocks. This function returns zero in case of
* success and a negative error code in case of failure.
*
* This function actually belongs to the journal, but we keep it here because
* we want to keep it static.
*/
static int bud_wbuf_callback(struct ubifs_info *c, int lnum, int free, int pad)
{
return ubifs_update_one_lp(c, lnum, free, pad, 0, 0);
}
/*
* init_constants_sb - initialize UBIFS constants.
* @c: UBIFS file-system description object
*
* This is a helper function which initializes various UBIFS constants after
* the superblock has been read. It also checks various UBIFS parameters and
* makes sure they are all right. Returns zero in case of success and a
* negative error code in case of failure.
*/
static int init_constants_sb(struct ubifs_info *c)
{
int tmp, err;
long long tmp64;
c->main_bytes = (long long)c->main_lebs * c->leb_size;
c->max_znode_sz = sizeof(struct ubifs_znode) +
c->fanout * sizeof(struct ubifs_zbranch);
tmp = ubifs_idx_node_sz(c, 1);
c->ranges[UBIFS_IDX_NODE].min_len = tmp;
c->min_idx_node_sz = ALIGN(tmp, 8);
tmp = ubifs_idx_node_sz(c, c->fanout);
c->ranges[UBIFS_IDX_NODE].max_len = tmp;
c->max_idx_node_sz = ALIGN(tmp, 8);
/* Make sure LEB size is large enough to fit full commit */
tmp = UBIFS_CS_NODE_SZ + UBIFS_REF_NODE_SZ * c->jhead_cnt;
tmp = ALIGN(tmp, c->min_io_size);
if (tmp > c->leb_size) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "too small LEB size %d, at least %d needed",
c->leb_size, tmp);
return -EINVAL;
}
/*
* Make sure that the log is large enough to fit reference nodes for
* all buds plus one reserved LEB.
*/
tmp64 = c->max_bud_bytes + c->leb_size - 1;
c->max_bud_cnt = div_u64(tmp64, c->leb_size);
tmp = (c->ref_node_alsz * c->max_bud_cnt + c->leb_size - 1);
tmp /= c->leb_size;
tmp += 1;
if (c->log_lebs < tmp) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "too small log %d LEBs, required min. %d LEBs",
c->log_lebs, tmp);
return -EINVAL;
}
/*
* When budgeting we assume worst-case scenarios when the pages are not
* be compressed and direntries are of the maximum size.
*
* Note, data, which may be stored in inodes is budgeted separately, so
* it is not included into 'c->bi.inode_budget'.
*/
c->bi.page_budget = UBIFS_MAX_DATA_NODE_SZ * UBIFS_BLOCKS_PER_PAGE;
c->bi.inode_budget = UBIFS_INO_NODE_SZ;
c->bi.dent_budget = UBIFS_MAX_DENT_NODE_SZ;
/*
* When the amount of flash space used by buds becomes
* 'c->max_bud_bytes', UBIFS just blocks all writers and starts commit.
* The writers are unblocked when the commit is finished. To avoid
* writers to be blocked UBIFS initiates background commit in advance,
* when number of bud bytes becomes above the limit defined below.
*/
c->bg_bud_bytes = (c->max_bud_bytes * 13) >> 4;
/*
* Ensure minimum journal size. All the bytes in the journal heads are
* considered to be used, when calculating the current journal usage.
* Consequently, if the journal is too small, UBIFS will treat it as
* always full.
*/
tmp64 = (long long)(c->jhead_cnt + 1) * c->leb_size + 1;
if (c->bg_bud_bytes < tmp64)
c->bg_bud_bytes = tmp64;
if (c->max_bud_bytes < tmp64 + c->leb_size)
c->max_bud_bytes = tmp64 + c->leb_size;
err = ubifs_calc_lpt_geom(c);
if (err)
return err;
/* Initialize effective LEB size used in budgeting calculations */
c->idx_leb_size = c->leb_size - c->max_idx_node_sz;
return 0;
}
/*
* init_constants_master - initialize UBIFS constants.
* @c: UBIFS file-system description object
*
* This is a helper function which initializes various UBIFS constants after
* the master node has been read. It also checks various UBIFS parameters and
* makes sure they are all right.
*/
static void init_constants_master(struct ubifs_info *c)
{
long long tmp64;
c->bi.min_idx_lebs = ubifs_calc_min_idx_lebs(c);
c->report_rp_size = ubifs_reported_space(c, c->rp_size);
/*
* Calculate total amount of FS blocks. This number is not used
* internally because it does not make much sense for UBIFS, but it is
* necessary to report something for the 'statfs()' call.
*
UBIFS: improve statfs reporting even more Since free space we report in statfs is file size which should fit to the FS - change the way we calculate free space and use leb_overhead instead of dark_wm in calculations. Results of "freespace" test (120MiB volume, 16KiB LEB size, 512 bytes page size). Before the change: freespace: Test 1: fill the space we have 3 times freespace: was free: 85204992 bytes 81.3 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 11284480 bytes 10.8 MiB, wrote 13.2% more than predicted freespace: was free: 83554304 bytes 79.7 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 12935168 bytes 12.3 MiB, wrote 15.5% more than predicted freespace: was free: 83554304 bytes 79.7 MiB, wrote: 96493568 bytes 92.0 MiB, delta: 12939264 bytes 12.3 MiB, wrote 15.5% more than predicted freespace: Test 1 finished freespace: Test 2: gradually lessen amount of free space and fill the FS freespace: do 10 steps, lessen free space by 7596218 bytes 7.2 MiB each time freespace: was free: 78675968 bytes 75.0 MiB, wrote: 88903680 bytes 84.8 MiB, delta: 10227712 bytes 9.8 MiB, wrote 13.0% more than predicted freespace: was free: 72015872 bytes 68.7 MiB, wrote: 81514496 bytes 77.7 MiB, delta: 9498624 bytes 9.1 MiB, wrote 13.2% more than predicted freespace: was free: 63938560 bytes 61.0 MiB, wrote: 72589312 bytes 69.2 MiB, delta: 8650752 bytes 8.2 MiB, wrote 13.5% more than predicted freespace: was free: 56127488 bytes 53.5 MiB, wrote: 63762432 bytes 60.8 MiB, delta: 7634944 bytes 7.3 MiB, wrote 13.6% more than predicted freespace: was free: 48336896 bytes 46.1 MiB, wrote: 54935552 bytes 52.4 MiB, delta: 6598656 bytes 6.3 MiB, wrote 13.7% more than predicted freespace: was free: 40587264 bytes 38.7 MiB, wrote: 46157824 bytes 44.0 MiB, delta: 5570560 bytes 5.3 MiB, wrote 13.7% more than predicted freespace: was free: 32841728 bytes 31.3 MiB, wrote: 37384192 bytes 35.7 MiB, delta: 4542464 bytes 4.3 MiB, wrote 13.8% more than predicted freespace: was free: 25100288 bytes 23.9 MiB, wrote: 28618752 bytes 27.3 MiB, delta: 3518464 bytes 3.4 MiB, wrote 14.0% more than predicted freespace: was free: 17342464 bytes 16.5 MiB, wrote: 19841024 bytes 18.9 MiB, delta: 2498560 bytes 2.4 MiB, wrote 14.4% more than predicted freespace: was free: 9605120 bytes 9.2 MiB, wrote: 11063296 bytes 10.6 MiB, delta: 1458176 bytes 1.4 MiB, wrote 15.2% more than predicted freespace: Test 2 finished freespace: Test 3: gradually lessen amount of free space by trashing and fill the FS freespace: do 10 steps, lessen free space by 7606272 bytes 7.3 MiB each time freespace: trashing: was free: 83668992 bytes 79.8 MiB, need free: 7606272 bytes 7.3 MiB, files created: 248297, delete 225724 (90.9% of them) freespace: was free: 70803456 bytes 67.5 MiB, wrote: 82485248 bytes 78.7 MiB, delta: 11681792 bytes 11.1 MiB, wrote 16.5% more than predicted freespace: trashing: was free: 81080320 bytes 77.3 MiB, need free: 15212544 bytes 14.5 MiB, files created: 248711, delete 202047 (81.2% of them) freespace: was free: 59867136 bytes 57.1 MiB, wrote: 71897088 bytes 68.6 MiB, delta: 12029952 bytes 11.5 MiB, wrote 20.1% more than predicted freespace: trashing: was free: 82243584 bytes 78.4 MiB, need free: 22818816 bytes 21.8 MiB, files created: 248866, delete 179817 (72.3% of them) freespace: was free: 50905088 bytes 48.5 MiB, wrote: 63168512 bytes 60.2 MiB, delta: 12263424 bytes 11.7 MiB, wrote 24.1% more than predicted freespace: trashing: was free: 83402752 bytes 79.5 MiB, need free: 30425088 bytes 29.0 MiB, files created: 248920, delete 158114 (63.5% of them) freespace: was free: 42651648 bytes 40.7 MiB, wrote: 55406592 bytes 52.8 MiB, delta: 12754944 bytes 12.2 MiB, wrote 29.9% more than predicted freespace: trashing: was free: 84402176 bytes 80.5 MiB, need free: 38031360 bytes 36.3 MiB, files created: 248709, delete 136641 (54.9% of them) freespace: was free: 35233792 bytes 33.6 MiB, wrote: 48250880 bytes 46.0 MiB, delta: 13017088 bytes 12.4 MiB, wrote 36.9% more than predicted freespace: trashing: was free: 82530304 bytes 78.7 MiB, need free: 45637632 bytes 43.5 MiB, files created: 248778, delete 111208 (44.7% of them) freespace: was free: 27287552 bytes 26.0 MiB, wrote: 40267776 bytes 38.4 MiB, delta: 12980224 bytes 12.4 MiB, wrote 47.6% more than predicted freespace: trashing: was free: 85114880 bytes 81.2 MiB, need free: 53243904 bytes 50.8 MiB, files created: 248508, delete 93052 (37.4% of them) freespace: was free: 22437888 bytes 21.4 MiB, wrote: 35328000 bytes 33.7 MiB, delta: 12890112 bytes 12.3 MiB, wrote 57.4% more than predicted freespace: trashing: was free: 84103168 bytes 80.2 MiB, need free: 60850176 bytes 58.0 MiB, files created: 248637, delete 68743 (27.6% of them) freespace: was free: 15536128 bytes 14.8 MiB, wrote: 28319744 bytes 27.0 MiB, delta: 12783616 bytes 12.2 MiB, wrote 82.3% more than predicted freespace: trashing: was free: 84357120 bytes 80.4 MiB, need free: 68456448 bytes 65.3 MiB, files created: 248567, delete 46852 (18.8% of them) freespace: was free: 9015296 bytes 8.6 MiB, wrote: 22044672 bytes 21.0 MiB, delta: 13029376 bytes 12.4 MiB, wrote 144.5% more than predicted freespace: trashing: was free: 84942848 bytes 81.0 MiB, need free: 76062720 bytes 72.5 MiB, files created: 248636, delete 25993 (10.5% of them) freespace: was free: 6086656 bytes 5.8 MiB, wrote: 8331264 bytes 7.9 MiB, delta: 2244608 bytes 2.1 MiB, wrote 36.9% more than predicted freespace: Test 3 finished freespace: finished successfully After the change: freespace: Test 1: fill the space we have 3 times freespace: was free: 94048256 bytes 89.7 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 2441216 bytes 2.3 MiB, wrote 2.6% more than predicted freespace: was free: 92246016 bytes 88.0 MiB, wrote: 96493568 bytes 92.0 MiB, delta: 4247552 bytes 4.1 MiB, wrote 4.6% more than predicted freespace: was free: 92254208 bytes 88.0 MiB, wrote: 96489472 bytes 92.0 MiB, delta: 4235264 bytes 4.0 MiB, wrote 4.6% more than predicted freespace: Test 1 finished freespace: Test 2: gradually lessen amount of free space and fill the FS freespace: do 10 steps, lessen free space by 8386001 bytes 8.0 MiB each time freespace: was free: 86605824 bytes 82.6 MiB, wrote: 88252416 bytes 84.2 MiB, delta: 1646592 bytes 1.6 MiB, wrote 1.9% more than predicted freespace: was free: 78667776 bytes 75.0 MiB, wrote: 80715776 bytes 77.0 MiB, delta: 2048000 bytes 2.0 MiB, wrote 2.6% more than predicted freespace: was free: 69615616 bytes 66.4 MiB, wrote: 71630848 bytes 68.3 MiB, delta: 2015232 bytes 1.9 MiB, wrote 2.9% more than predicted freespace: was free: 61018112 bytes 58.2 MiB, wrote: 62783488 bytes 59.9 MiB, delta: 1765376 bytes 1.7 MiB, wrote 2.9% more than predicted freespace: was free: 52424704 bytes 50.0 MiB, wrote: 53968896 bytes 51.5 MiB, delta: 1544192 bytes 1.5 MiB, wrote 2.9% more than predicted freespace: was free: 43880448 bytes 41.8 MiB, wrote: 45199360 bytes 43.1 MiB, delta: 1318912 bytes 1.3 MiB, wrote 3.0% more than predicted freespace: was free: 35332096 bytes 33.7 MiB, wrote: 36425728 bytes 34.7 MiB, delta: 1093632 bytes 1.0 MiB, wrote 3.1% more than predicted freespace: was free: 26771456 bytes 25.5 MiB, wrote: 27643904 bytes 26.4 MiB, delta: 872448 bytes 852.0 KiB, wrote 3.3% more than predicted freespace: was free: 18231296 bytes 17.4 MiB, wrote: 18878464 bytes 18.0 MiB, delta: 647168 bytes 632.0 KiB, wrote 3.5% more than predicted freespace: was free: 9674752 bytes 9.2 MiB, wrote: 10088448 bytes 9.6 MiB, delta: 413696 bytes 404.0 KiB, wrote 4.3% more than predicted freespace: Test 2 finished freespace: Test 3: gradually lessen amount of free space by trashing and fill the FS freespace: do 10 steps, lessen free space by 8397544 bytes 8.0 MiB each time freespace: trashing: was free: 92372992 bytes 88.1 MiB, need free: 8397552 bytes 8.0 MiB, files created: 248296, delete 225723 (90.9% of them) freespace: was free: 71909376 bytes 68.6 MiB, wrote: 82472960 bytes 78.7 MiB, delta: 10563584 bytes 10.1 MiB, wrote 14.7% more than predicted freespace: trashing: was free: 88989696 bytes 84.9 MiB, need free: 16795096 bytes 16.0 MiB, files created: 248794, delete 201838 (81.1% of them) freespace: was free: 60354560 bytes 57.6 MiB, wrote: 71782400 bytes 68.5 MiB, delta: 11427840 bytes 10.9 MiB, wrote 18.9% more than predicted freespace: trashing: was free: 90304512 bytes 86.1 MiB, need free: 25192640 bytes 24.0 MiB, files created: 248733, delete 179342 (72.1% of them) freespace: was free: 51187712 bytes 48.8 MiB, wrote: 62943232 bytes 60.0 MiB, delta: 11755520 bytes 11.2 MiB, wrote 23.0% more than predicted freespace: trashing: was free: 91209728 bytes 87.0 MiB, need free: 33590184 bytes 32.0 MiB, files created: 248779, delete 157160 (63.2% of them) freespace: was free: 42704896 bytes 40.7 MiB, wrote: 55050240 bytes 52.5 MiB, delta: 12345344 bytes 11.8 MiB, wrote 28.9% more than predicted freespace: trashing: was free: 92700672 bytes 88.4 MiB, need free: 41987728 bytes 40.0 MiB, files created: 248848, delete 136135 (54.7% of them) freespace: was free: 35250176 bytes 33.6 MiB, wrote: 48115712 bytes 45.9 MiB, delta: 12865536 bytes 12.3 MiB, wrote 36.5% more than predicted freespace: trashing: was free: 93986816 bytes 89.6 MiB, need free: 50385272 bytes 48.1 MiB, files created: 248723, delete 115385 (46.4% of them) freespace: was free: 29995008 bytes 28.6 MiB, wrote: 41582592 bytes 39.7 MiB, delta: 11587584 bytes 11.1 MiB, wrote 38.6% more than predicted freespace: trashing: was free: 91881472 bytes 87.6 MiB, need free: 58782816 bytes 56.1 MiB, files created: 248645, delete 89569 (36.0% of them) freespace: was free: 22511616 bytes 21.5 MiB, wrote: 34705408 bytes 33.1 MiB, delta: 12193792 bytes 11.6 MiB, wrote 54.2% more than predicted freespace: trashing: was free: 91774976 bytes 87.5 MiB, need free: 67180360 bytes 64.1 MiB, files created: 248580, delete 66616 (26.8% of them) freespace: was free: 16908288 bytes 16.1 MiB, wrote: 26898432 bytes 25.7 MiB, delta: 9990144 bytes 9.5 MiB, wrote 59.1% more than predicted freespace: trashing: was free: 92450816 bytes 88.2 MiB, need free: 75577904 bytes 72.1 MiB, files created: 248654, delete 45381 (18.3% of them) freespace: was free: 10170368 bytes 9.7 MiB, wrote: 19111936 bytes 18.2 MiB, delta: 8941568 bytes 8.5 MiB, wrote 87.9% more than predicted freespace: trashing: was free: 93282304 bytes 89.0 MiB, need free: 83975448 bytes 80.1 MiB, files created: 248513, delete 24794 (10.0% of them) freespace: was free: 3911680 bytes 3.7 MiB, wrote: 7872512 bytes 7.5 MiB, delta: 3960832 bytes 3.8 MiB, wrote 101.3% more than predicted freespace: Test 3 finished freespace: finished successfully Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
2008-08-25 23:58:19 +08:00
* Subtract the LEB reserved for GC, the LEB which is reserved for
* deletions, minimum LEBs for the index, and assume only one journal
* head is available.
*/
tmp64 = c->main_lebs - 1 - 1 - MIN_INDEX_LEBS - c->jhead_cnt + 1;
tmp64 *= (long long)c->leb_size - c->leb_overhead;
tmp64 = ubifs_reported_space(c, tmp64);
c->block_cnt = tmp64 >> UBIFS_BLOCK_SHIFT;
}
/**
* take_gc_lnum - reserve GC LEB.
* @c: UBIFS file-system description object
*
* This function ensures that the LEB reserved for garbage collection is marked
* as "taken" in lprops. We also have to set free space to LEB size and dirty
* space to zero, because lprops may contain out-of-date information if the
* file-system was un-mounted before it has been committed. This function
* returns zero in case of success and a negative error code in case of
* failure.
*/
static int take_gc_lnum(struct ubifs_info *c)
{
int err;
if (c->gc_lnum == -1) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "no LEB for GC");
return -EINVAL;
}
/* And we have to tell lprops that this LEB is taken */
err = ubifs_change_one_lp(c, c->gc_lnum, c->leb_size, 0,
LPROPS_TAKEN, 0, 0);
return err;
}
/**
* alloc_wbufs - allocate write-buffers.
* @c: UBIFS file-system description object
*
* This helper function allocates and initializes UBIFS write-buffers. Returns
* zero in case of success and %-ENOMEM in case of failure.
*/
static int alloc_wbufs(struct ubifs_info *c)
{
int i, err;
c->jheads = kcalloc(c->jhead_cnt, sizeof(struct ubifs_jhead),
GFP_KERNEL);
if (!c->jheads)
return -ENOMEM;
/* Initialize journal heads */
for (i = 0; i < c->jhead_cnt; i++) {
INIT_LIST_HEAD(&c->jheads[i].buds_list);
err = ubifs_wbuf_init(c, &c->jheads[i].wbuf);
if (err)
ubifs: Fix memory leak in alloc_wbufs() kmemleak reported a sequence of memory leaks, and show them as following: unreferenced object 0xffff8881575f8400 (size 1024): comm "mount", pid 19625, jiffies 4297119604 (age 20.383s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0406b2b>] ubifs_mount+0x307b/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff8881798a6e00 (size 512): comm "mount", pid 19677, jiffies 4297121912 (age 37.816s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0418342>] ubifs_wbuf_init+0x52/0x480 [ubifs] [<ffffffffa0406ca5>] ubifs_mount+0x31f5/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 The problem is that the ubifs_wbuf_init() returns an error in the loop which in the alloc_wbufs(), then the wbuf->buf and wbuf->inodes that were successfully alloced before are not freed. Fix it by adding error hanging path in alloc_wbufs() which frees the memory alloced before when ubifs_wbuf_init() returns an error. Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Li Zetao <lizetao1@huawei.com> Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com> Signed-off-by: Richard Weinberger <richard@nod.at>
2022-10-22 19:52:11 +08:00
goto out_wbuf;
c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback;
c->jheads[i].wbuf.jhead = i;
c->jheads[i].grouped = 1;
ubifs: Add authentication nodes to journal Nodes that are written to flash can only be authenticated through the index after the next commit. When a journal replay is necessary the nodes are not yet referenced by the index and thus can't be authenticated. This patch overcomes this situation by creating a hash over all nodes beginning from the commit start node over the reference node(s) and the buds themselves. From time to time we insert authentication nodes. Authentication nodes contain a HMAC from the current hash state, so that they can be used to authenticate a journal replay up to the point where the authentication node is. The hash is continued afterwards so that theoretically we would only have to check the HMAC of the last authentication node we find. Overall we get this picture: ,,,,,,,, ,......,........................................... ,. CS , hash1.----. hash2.----. ,. | , . |hmac . |hmac ,. v , . v . v ,.REF#0,-> bud -> bud -> bud.-> auth -> bud -> bud.-> auth ... ,..|...,........................................... , | , , | ,,,,,,,,,,,,,,, . | hash3,----. , | , |hmac , v , v , REF#1 -> bud -> bud,-> auth ... ,,,|,,,,,,,,,,,,,,,,,, v REF#2 -> ... | V ... Note how hash3 covers CS, REF#0 and REF#1 so that it is not possible to exchange or skip any reference nodes. Unlike the picture suggests the auth nodes themselves are not hashed. With this it is possible for an offline attacker to cut each journal head or to drop the last reference node(s), but not to skip any journal heads or to reorder any operations. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2018-09-07 20:36:36 +08:00
c->jheads[i].log_hash = ubifs_hash_get_desc(c);
if (IS_ERR(c->jheads[i].log_hash)) {
err = PTR_ERR(c->jheads[i].log_hash);
ubifs: Fix memory leak in alloc_wbufs() kmemleak reported a sequence of memory leaks, and show them as following: unreferenced object 0xffff8881575f8400 (size 1024): comm "mount", pid 19625, jiffies 4297119604 (age 20.383s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0406b2b>] ubifs_mount+0x307b/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff8881798a6e00 (size 512): comm "mount", pid 19677, jiffies 4297121912 (age 37.816s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0418342>] ubifs_wbuf_init+0x52/0x480 [ubifs] [<ffffffffa0406ca5>] ubifs_mount+0x31f5/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 The problem is that the ubifs_wbuf_init() returns an error in the loop which in the alloc_wbufs(), then the wbuf->buf and wbuf->inodes that were successfully alloced before are not freed. Fix it by adding error hanging path in alloc_wbufs() which frees the memory alloced before when ubifs_wbuf_init() returns an error. Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Li Zetao <lizetao1@huawei.com> Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com> Signed-off-by: Richard Weinberger <richard@nod.at>
2022-10-22 19:52:11 +08:00
goto out_log_hash;
}
}
/*
* Garbage Collector head does not need to be synchronized by timer.
* Also GC head nodes are not grouped.
*/
c->jheads[GCHD].wbuf.no_timer = 1;
c->jheads[GCHD].grouped = 0;
return 0;
ubifs: Add authentication nodes to journal Nodes that are written to flash can only be authenticated through the index after the next commit. When a journal replay is necessary the nodes are not yet referenced by the index and thus can't be authenticated. This patch overcomes this situation by creating a hash over all nodes beginning from the commit start node over the reference node(s) and the buds themselves. From time to time we insert authentication nodes. Authentication nodes contain a HMAC from the current hash state, so that they can be used to authenticate a journal replay up to the point where the authentication node is. The hash is continued afterwards so that theoretically we would only have to check the HMAC of the last authentication node we find. Overall we get this picture: ,,,,,,,, ,......,........................................... ,. CS , hash1.----. hash2.----. ,. | , . |hmac . |hmac ,. v , . v . v ,.REF#0,-> bud -> bud -> bud.-> auth -> bud -> bud.-> auth ... ,..|...,........................................... , | , , | ,,,,,,,,,,,,,,, . | hash3,----. , | , |hmac , v , v , REF#1 -> bud -> bud,-> auth ... ,,,|,,,,,,,,,,,,,,,,,, v REF#2 -> ... | V ... Note how hash3 covers CS, REF#0 and REF#1 so that it is not possible to exchange or skip any reference nodes. Unlike the picture suggests the auth nodes themselves are not hashed. With this it is possible for an offline attacker to cut each journal head or to drop the last reference node(s), but not to skip any journal heads or to reorder any operations. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2018-09-07 20:36:36 +08:00
ubifs: Fix memory leak in alloc_wbufs() kmemleak reported a sequence of memory leaks, and show them as following: unreferenced object 0xffff8881575f8400 (size 1024): comm "mount", pid 19625, jiffies 4297119604 (age 20.383s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0406b2b>] ubifs_mount+0x307b/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff8881798a6e00 (size 512): comm "mount", pid 19677, jiffies 4297121912 (age 37.816s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0418342>] ubifs_wbuf_init+0x52/0x480 [ubifs] [<ffffffffa0406ca5>] ubifs_mount+0x31f5/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 The problem is that the ubifs_wbuf_init() returns an error in the loop which in the alloc_wbufs(), then the wbuf->buf and wbuf->inodes that were successfully alloced before are not freed. Fix it by adding error hanging path in alloc_wbufs() which frees the memory alloced before when ubifs_wbuf_init() returns an error. Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Li Zetao <lizetao1@huawei.com> Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com> Signed-off-by: Richard Weinberger <richard@nod.at>
2022-10-22 19:52:11 +08:00
out_log_hash:
kfree(c->jheads[i].wbuf.buf);
kfree(c->jheads[i].wbuf.inodes);
out_wbuf:
while (i--) {
kfree(c->jheads[i].wbuf.buf);
kfree(c->jheads[i].wbuf.inodes);
ubifs: Add authentication nodes to journal Nodes that are written to flash can only be authenticated through the index after the next commit. When a journal replay is necessary the nodes are not yet referenced by the index and thus can't be authenticated. This patch overcomes this situation by creating a hash over all nodes beginning from the commit start node over the reference node(s) and the buds themselves. From time to time we insert authentication nodes. Authentication nodes contain a HMAC from the current hash state, so that they can be used to authenticate a journal replay up to the point where the authentication node is. The hash is continued afterwards so that theoretically we would only have to check the HMAC of the last authentication node we find. Overall we get this picture: ,,,,,,,, ,......,........................................... ,. CS , hash1.----. hash2.----. ,. | , . |hmac . |hmac ,. v , . v . v ,.REF#0,-> bud -> bud -> bud.-> auth -> bud -> bud.-> auth ... ,..|...,........................................... , | , , | ,,,,,,,,,,,,,,, . | hash3,----. , | , |hmac , v , v , REF#1 -> bud -> bud,-> auth ... ,,,|,,,,,,,,,,,,,,,,,, v REF#2 -> ... | V ... Note how hash3 covers CS, REF#0 and REF#1 so that it is not possible to exchange or skip any reference nodes. Unlike the picture suggests the auth nodes themselves are not hashed. With this it is possible for an offline attacker to cut each journal head or to drop the last reference node(s), but not to skip any journal heads or to reorder any operations. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2018-09-07 20:36:36 +08:00
kfree(c->jheads[i].log_hash);
ubifs: Fix memory leak in alloc_wbufs() kmemleak reported a sequence of memory leaks, and show them as following: unreferenced object 0xffff8881575f8400 (size 1024): comm "mount", pid 19625, jiffies 4297119604 (age 20.383s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0406b2b>] ubifs_mount+0x307b/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff8881798a6e00 (size 512): comm "mount", pid 19677, jiffies 4297121912 (age 37.816s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace: [<ffffffff8176cecd>] __kmalloc+0x4d/0x150 [<ffffffffa0418342>] ubifs_wbuf_init+0x52/0x480 [ubifs] [<ffffffffa0406ca5>] ubifs_mount+0x31f5/0x7170 [ubifs] [<ffffffff819fa8fd>] legacy_get_tree+0xed/0x1d0 [<ffffffff81936f2d>] vfs_get_tree+0x7d/0x230 [<ffffffff819b2bd4>] path_mount+0xdd4/0x17b0 [<ffffffff819b37aa>] __x64_sys_mount+0x1fa/0x270 [<ffffffff83c14295>] do_syscall_64+0x35/0x80 [<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 The problem is that the ubifs_wbuf_init() returns an error in the loop which in the alloc_wbufs(), then the wbuf->buf and wbuf->inodes that were successfully alloced before are not freed. Fix it by adding error hanging path in alloc_wbufs() which frees the memory alloced before when ubifs_wbuf_init() returns an error. Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Li Zetao <lizetao1@huawei.com> Reviewed-by: Zhihao Cheng <chengzhihao1@huawei.com> Signed-off-by: Richard Weinberger <richard@nod.at>
2022-10-22 19:52:11 +08:00
}
kfree(c->jheads);
c->jheads = NULL;
ubifs: Add authentication nodes to journal Nodes that are written to flash can only be authenticated through the index after the next commit. When a journal replay is necessary the nodes are not yet referenced by the index and thus can't be authenticated. This patch overcomes this situation by creating a hash over all nodes beginning from the commit start node over the reference node(s) and the buds themselves. From time to time we insert authentication nodes. Authentication nodes contain a HMAC from the current hash state, so that they can be used to authenticate a journal replay up to the point where the authentication node is. The hash is continued afterwards so that theoretically we would only have to check the HMAC of the last authentication node we find. Overall we get this picture: ,,,,,,,, ,......,........................................... ,. CS , hash1.----. hash2.----. ,. | , . |hmac . |hmac ,. v , . v . v ,.REF#0,-> bud -> bud -> bud.-> auth -> bud -> bud.-> auth ... ,..|...,........................................... , | , , | ,,,,,,,,,,,,,,, . | hash3,----. , | , |hmac , v , v , REF#1 -> bud -> bud,-> auth ... ,,,|,,,,,,,,,,,,,,,,,, v REF#2 -> ... | V ... Note how hash3 covers CS, REF#0 and REF#1 so that it is not possible to exchange or skip any reference nodes. Unlike the picture suggests the auth nodes themselves are not hashed. With this it is possible for an offline attacker to cut each journal head or to drop the last reference node(s), but not to skip any journal heads or to reorder any operations. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2018-09-07 20:36:36 +08:00
return err;
}
/**
* free_wbufs - free write-buffers.
* @c: UBIFS file-system description object
*/
static void free_wbufs(struct ubifs_info *c)
{
int i;
if (c->jheads) {
for (i = 0; i < c->jhead_cnt; i++) {
kfree(c->jheads[i].wbuf.buf);
kfree(c->jheads[i].wbuf.inodes);
ubifs: Add authentication nodes to journal Nodes that are written to flash can only be authenticated through the index after the next commit. When a journal replay is necessary the nodes are not yet referenced by the index and thus can't be authenticated. This patch overcomes this situation by creating a hash over all nodes beginning from the commit start node over the reference node(s) and the buds themselves. From time to time we insert authentication nodes. Authentication nodes contain a HMAC from the current hash state, so that they can be used to authenticate a journal replay up to the point where the authentication node is. The hash is continued afterwards so that theoretically we would only have to check the HMAC of the last authentication node we find. Overall we get this picture: ,,,,,,,, ,......,........................................... ,. CS , hash1.----. hash2.----. ,. | , . |hmac . |hmac ,. v , . v . v ,.REF#0,-> bud -> bud -> bud.-> auth -> bud -> bud.-> auth ... ,..|...,........................................... , | , , | ,,,,,,,,,,,,,,, . | hash3,----. , | , |hmac , v , v , REF#1 -> bud -> bud,-> auth ... ,,,|,,,,,,,,,,,,,,,,,, v REF#2 -> ... | V ... Note how hash3 covers CS, REF#0 and REF#1 so that it is not possible to exchange or skip any reference nodes. Unlike the picture suggests the auth nodes themselves are not hashed. With this it is possible for an offline attacker to cut each journal head or to drop the last reference node(s), but not to skip any journal heads or to reorder any operations. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2018-09-07 20:36:36 +08:00
kfree(c->jheads[i].log_hash);
}
kfree(c->jheads);
c->jheads = NULL;
}
}
/**
* free_orphans - free orphans.
* @c: UBIFS file-system description object
*/
static void free_orphans(struct ubifs_info *c)
{
struct ubifs_orphan *orph;
while (c->orph_dnext) {
orph = c->orph_dnext;
c->orph_dnext = orph->dnext;
list_del(&orph->list);
kfree(orph);
}
while (!list_empty(&c->orph_list)) {
orph = list_entry(c->orph_list.next, struct ubifs_orphan, list);
list_del(&orph->list);
kfree(orph);
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "orphan list not empty at unmount");
}
vfree(c->orph_buf);
c->orph_buf = NULL;
}
/**
* free_buds - free per-bud objects.
* @c: UBIFS file-system description object
*/
static void free_buds(struct ubifs_info *c)
{
struct ubifs_bud *bud, *n;
rbtree_postorder_for_each_entry_safe(bud, n, &c->buds, rb) {
kfree(bud->log_hash);
kfree(bud);
}
}
/**
* check_volume_empty - check if the UBI volume is empty.
* @c: UBIFS file-system description object
*
* This function checks if the UBIFS volume is empty by looking if its LEBs are
* mapped or not. The result of checking is stored in the @c->empty variable.
* Returns zero in case of success and a negative error code in case of
* failure.
*/
static int check_volume_empty(struct ubifs_info *c)
{
int lnum, err;
c->empty = 1;
for (lnum = 0; lnum < c->leb_cnt; lnum++) {
err = ubifs_is_mapped(c, lnum);
if (unlikely(err < 0))
return err;
if (err == 1) {
c->empty = 0;
break;
}
cond_resched();
}
return 0;
}
/*
* UBIFS mount options.
*
* Opt_fast_unmount: do not run a journal commit before un-mounting
* Opt_norm_unmount: run a journal commit before un-mounting
* Opt_bulk_read: enable bulk-reads
* Opt_no_bulk_read: disable bulk-reads
* Opt_chk_data_crc: check CRCs when reading data nodes
* Opt_no_chk_data_crc: do not check CRCs when reading data nodes
* Opt_override_compr: override default compressor
* Opt_assert: set ubifs_assert() action
* Opt_auth_key: The key name used for authentication
* Opt_auth_hash_name: The hash type used for authentication
* Opt_err: just end of array marker
*/
enum {
Opt_fast_unmount,
Opt_norm_unmount,
Opt_bulk_read,
Opt_no_bulk_read,
Opt_chk_data_crc,
Opt_no_chk_data_crc,
Opt_override_compr,
Opt_assert,
Opt_auth_key,
Opt_auth_hash_name,
Opt_ignore,
Opt_err,
};
static const match_table_t tokens = {
{Opt_fast_unmount, "fast_unmount"},
{Opt_norm_unmount, "norm_unmount"},
{Opt_bulk_read, "bulk_read"},
{Opt_no_bulk_read, "no_bulk_read"},
{Opt_chk_data_crc, "chk_data_crc"},
{Opt_no_chk_data_crc, "no_chk_data_crc"},
{Opt_override_compr, "compr=%s"},
{Opt_auth_key, "auth_key=%s"},
{Opt_auth_hash_name, "auth_hash_name=%s"},
{Opt_ignore, "ubi=%s"},
{Opt_ignore, "vol=%s"},
{Opt_assert, "assert=%s"},
{Opt_err, NULL},
};
/**
* parse_standard_option - parse a standard mount option.
* @option: the option to parse
*
* Normally, standard mount options like "sync" are passed to file-systems as
* flags. However, when a "rootflags=" kernel boot parameter is used, they may
* be present in the options string. This function tries to deal with this
* situation and parse standard options. Returns 0 if the option was not
* recognized, and the corresponding integer flag if it was.
*
* UBIFS is only interested in the "sync" option, so do not check for anything
* else.
*/
static int parse_standard_option(const char *option)
{
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
pr_notice("UBIFS: parse %s\n", option);
if (!strcmp(option, "sync"))
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
return SB_SYNCHRONOUS;
return 0;
}
/**
* ubifs_parse_options - parse mount parameters.
* @c: UBIFS file-system description object
* @options: parameters to parse
* @is_remount: non-zero if this is FS re-mount
*
* This function parses UBIFS mount options and returns zero in case success
* and a negative error code in case of failure.
*/
static int ubifs_parse_options(struct ubifs_info *c, char *options,
int is_remount)
{
char *p;
substring_t args[MAX_OPT_ARGS];
if (!options)
return 0;
while ((p = strsep(&options, ","))) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
/*
* %Opt_fast_unmount and %Opt_norm_unmount options are ignored.
* We accept them in order to be backward-compatible. But this
* should be removed at some point.
*/
case Opt_fast_unmount:
c->mount_opts.unmount_mode = 2;
break;
case Opt_norm_unmount:
c->mount_opts.unmount_mode = 1;
break;
case Opt_bulk_read:
c->mount_opts.bulk_read = 2;
c->bulk_read = 1;
break;
case Opt_no_bulk_read:
c->mount_opts.bulk_read = 1;
c->bulk_read = 0;
break;
case Opt_chk_data_crc:
c->mount_opts.chk_data_crc = 2;
c->no_chk_data_crc = 0;
break;
case Opt_no_chk_data_crc:
c->mount_opts.chk_data_crc = 1;
c->no_chk_data_crc = 1;
break;
case Opt_override_compr:
{
char *name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
if (!strcmp(name, "none"))
c->mount_opts.compr_type = UBIFS_COMPR_NONE;
else if (!strcmp(name, "lzo"))
c->mount_opts.compr_type = UBIFS_COMPR_LZO;
else if (!strcmp(name, "zlib"))
c->mount_opts.compr_type = UBIFS_COMPR_ZLIB;
else if (!strcmp(name, "zstd"))
c->mount_opts.compr_type = UBIFS_COMPR_ZSTD;
else {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "unknown compressor \"%s\"", name); //FIXME: is c ready?
kfree(name);
return -EINVAL;
}
kfree(name);
c->mount_opts.override_compr = 1;
c->default_compr = c->mount_opts.compr_type;
break;
}
case Opt_assert:
{
char *act = match_strdup(&args[0]);
if (!act)
return -ENOMEM;
if (!strcmp(act, "report"))
c->assert_action = ASSACT_REPORT;
else if (!strcmp(act, "read-only"))
c->assert_action = ASSACT_RO;
else if (!strcmp(act, "panic"))
c->assert_action = ASSACT_PANIC;
else {
ubifs_err(c, "unknown assert action \"%s\"", act);
kfree(act);
return -EINVAL;
}
kfree(act);
break;
}
case Opt_auth_key:
if (!is_remount) {
c->auth_key_name = kstrdup(args[0].from,
GFP_KERNEL);
if (!c->auth_key_name)
return -ENOMEM;
}
break;
case Opt_auth_hash_name:
if (!is_remount) {
c->auth_hash_name = kstrdup(args[0].from,
GFP_KERNEL);
if (!c->auth_hash_name)
return -ENOMEM;
}
break;
case Opt_ignore:
break;
default:
{
unsigned long flag;
struct super_block *sb = c->vfs_sb;
flag = parse_standard_option(p);
if (!flag) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "unrecognized mount option \"%s\" or missing value",
p);
return -EINVAL;
}
sb->s_flags |= flag;
break;
}
}
}
return 0;
}
/*
* ubifs_release_options - release mount parameters which have been dumped.
* @c: UBIFS file-system description object
*/
static void ubifs_release_options(struct ubifs_info *c)
{
kfree(c->auth_key_name);
c->auth_key_name = NULL;
kfree(c->auth_hash_name);
c->auth_hash_name = NULL;
}
/**
* destroy_journal - destroy journal data structures.
* @c: UBIFS file-system description object
*
* This function destroys journal data structures including those that may have
* been created by recovery functions.
*/
static void destroy_journal(struct ubifs_info *c)
{
while (!list_empty(&c->unclean_leb_list)) {
struct ubifs_unclean_leb *ucleb;
ucleb = list_entry(c->unclean_leb_list.next,
struct ubifs_unclean_leb, list);
list_del(&ucleb->list);
kfree(ucleb);
}
while (!list_empty(&c->old_buds)) {
struct ubifs_bud *bud;
bud = list_entry(c->old_buds.next, struct ubifs_bud, list);
list_del(&bud->list);
kfree(bud->log_hash);
kfree(bud);
}
ubifs_destroy_idx_gc(c);
ubifs_destroy_size_tree(c);
ubifs_tnc_close(c);
free_buds(c);
}
/**
* bu_init - initialize bulk-read information.
* @c: UBIFS file-system description object
*/
static void bu_init(struct ubifs_info *c)
{
ubifs_assert(c, c->bulk_read == 1);
if (c->bu.buf)
return; /* Already initialized */
again:
c->bu.buf = kmalloc(c->max_bu_buf_len, GFP_KERNEL | __GFP_NOWARN);
if (!c->bu.buf) {
if (c->max_bu_buf_len > UBIFS_KMALLOC_OK) {
c->max_bu_buf_len = UBIFS_KMALLOC_OK;
goto again;
}
/* Just disable bulk-read */
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_warn(c, "cannot allocate %d bytes of memory for bulk-read, disabling it",
c->max_bu_buf_len);
c->mount_opts.bulk_read = 1;
c->bulk_read = 0;
return;
}
}
/**
* check_free_space - check if there is enough free space to mount.
* @c: UBIFS file-system description object
*
* This function makes sure UBIFS has enough free space to be mounted in
* read/write mode. UBIFS must always have some free space to allow deletions.
*/
static int check_free_space(struct ubifs_info *c)
{
ubifs_assert(c, c->dark_wm > 0);
if (c->lst.total_free + c->lst.total_dirty < c->dark_wm) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "insufficient free space to mount in R/W mode");
ubifs_dump_budg(c, &c->bi);
ubifs_dump_lprops(c);
return -ENOSPC;
}
return 0;
}
/**
* mount_ubifs - mount UBIFS file-system.
* @c: UBIFS file-system description object
*
* This function mounts UBIFS file system. Returns zero in case of success and
* a negative error code in case of failure.
*/
static int mount_ubifs(struct ubifs_info *c)
{
int err;
long long x, y;
size_t sz;
c->ro_mount = !!sb_rdonly(c->vfs_sb);
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
/* Suppress error messages while probing if SB_SILENT is set */
c->probing = !!(c->vfs_sb->s_flags & SB_SILENT);
err = init_constants_early(c);
if (err)
return err;
err = ubifs_debugging_init(c);
if (err)
return err;
err = ubifs_sysfs_register(c);
if (err)
goto out_debugging;
err = check_volume_empty(c);
if (err)
goto out_free;
if (c->empty && (c->ro_mount || c->ro_media)) {
/*
* This UBI volume is empty, and read-only, or the file system
* is mounted read-only - we cannot format it.
*/
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "can't format empty UBI volume: read-only %s",
c->ro_media ? "UBI volume" : "mount");
err = -EROFS;
goto out_free;
}
if (c->ro_media && !c->ro_mount) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "cannot mount read-write - read-only media");
err = -EROFS;
goto out_free;
}
/*
* The requirement for the buffer is that it should fit indexing B-tree
* height amount of integers. We assume the height if the TNC tree will
* never exceed 64.
*/
err = -ENOMEM;
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:55:00 +08:00
c->bottom_up_buf = kmalloc_array(BOTTOM_UP_HEIGHT, sizeof(int),
GFP_KERNEL);
if (!c->bottom_up_buf)
goto out_free;
c->sbuf = vmalloc(c->leb_size);
if (!c->sbuf)
goto out_free;
if (!c->ro_mount) {
c->ileb_buf = vmalloc(c->leb_size);
if (!c->ileb_buf)
goto out_free;
}
if (c->bulk_read == 1)
bu_init(c);
if (!c->ro_mount) {
c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ + \
UBIFS_CIPHER_BLOCK_SIZE,
GFP_KERNEL);
if (!c->write_reserve_buf)
goto out_free;
}
c->mounting = 1;
if (c->auth_key_name) {
if (IS_ENABLED(CONFIG_UBIFS_FS_AUTHENTICATION)) {
err = ubifs_init_authentication(c);
if (err)
goto out_free;
} else {
ubifs_err(c, "auth_key_name, but UBIFS is built without"
" authentication support");
err = -EINVAL;
goto out_free;
}
}
err = ubifs_read_superblock(c);
if (err)
goto out_auth;
c->probing = 0;
/*
* Make sure the compressor which is set as default in the superblock
* or overridden by mount options is actually compiled in.
*/
if (!ubifs_compr_present(c, c->default_compr)) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "'compressor \"%s\" is not compiled in",
ubifs_compr_name(c, c->default_compr));
err = -ENOTSUPP;
goto out_auth;
}
err = init_constants_sb(c);
if (err)
goto out_auth;
sz = ALIGN(c->max_idx_node_sz, c->min_io_size) * 2;
c->cbuf = kmalloc(sz, GFP_NOFS);
if (!c->cbuf) {
err = -ENOMEM;
goto out_auth;
}
UBIFS: do not free write-buffers when in R/O mode Currently UBIFS has a small optimization - it frees write-buffers when it is re-mounted from R/W mode to R/O mode. Of course, when it is mounted R/O, it does not allocate write-buffers as well. This optimization is nice but it leads to subtle problems and complications in recovery, which I can reproduce using the integck test. The symptoms are that after a power cut the file-system cannot be mounted if we first mount it R/O, and then re-mount R/W - 'ubifs_rcvry_gc_commit()' prints: UBIFS error (pid 34456): could not find an empty LEB Analysis of the problem. When mounting R/W, the reply process sets journal heads to buds [1], but when mounting R/O - it does not do this, because the write-buffers are not allocated. So 'ubifs_rcvry_gc_commit()' works completely differently for the same file-system but for the following 2 cases: 1. mounting R/W after a power cut and recover 2. mounting R/O after a power cut, re-mounting R/W and run deferred recovery In the former case, we have journal heads seeked to the a bud, in the latter case, they are non-seeked (wbuf->lnum == -1). So in the latter case we do not try to recover the GC LEB by garbage-collecting to the GC head, but we just try to find an empty LEB, and there may be no empty LEBs, so we just fail. On the other hand, in the former case (mount R/W), we are able to make a GC LEB (@c->gc_lnum) by garbage-collecting. Thus, let's remove this small nice optimization and always allocate write-buffers. This should not make too big difference - we have only 3 of them, each of max. write unit size, which is usually 2KiB. So this is about 6KiB of RAM for the typical case, and only when mounted R/O. [1]: Note, currently the replay process is setting (seeking) the journal heads to _some_ buds, not necessarily to the buds which had been the journal heads before the power cut happened. This will be fixed separately. Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> Cc: stable@kernel.org
2011-04-25 23:17:09 +08:00
err = alloc_wbufs(c);
if (err)
goto out_cbuf;
sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id);
if (!c->ro_mount) {
/* Create background thread */
c->bgt = kthread_run(ubifs_bg_thread, c, "%s", c->bgt_name);
if (IS_ERR(c->bgt)) {
err = PTR_ERR(c->bgt);
c->bgt = NULL;
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "cannot spawn \"%s\", error %d",
c->bgt_name, err);
goto out_wbufs;
}
}
err = ubifs_read_master(c);
if (err)
goto out_master;
init_constants_master(c);
if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "recovery needed");
c->need_recovery = 1;
}
if (c->need_recovery && !c->ro_mount) {
err = ubifs_recover_inl_heads(c, c->sbuf);
if (err)
goto out_master;
}
err = ubifs_lpt_init(c, 1, !c->ro_mount);
if (err)
goto out_master;
if (!c->ro_mount && c->space_fixup) {
err = ubifs_fixup_free_space(c);
if (err)
goto out_lpt;
}
if (!c->ro_mount && !c->need_recovery) {
/*
* Set the "dirty" flag so that if we reboot uncleanly we
* will notice this immediately on the next mount.
*/
c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
err = ubifs_write_master(c);
if (err)
goto out_lpt;
}
ubifs: support offline signed images HMACs can only be generated on the system the UBIFS image is running on. To support offline signed images we add a PKCS#7 signature to the UBIFS image which can be created by mkfs.ubifs. Both the master node and the superblock need to be authenticated, during normal runtime both are protected with HMACs. For offline signature support however only a single signature is desired. We add a signature covering the superblock node directly behind it. To protect the master node a hash of the master node is added to the superblock which is used when the master node doesn't contain a HMAC. Transition to a read/write filesystem is also supported. During transition first the master node is rewritten with a HMAC (implicitly, it is written anyway as the FS is marked dirty). Afterwards the superblock is rewritten with a HMAC. Once after the image has been mounted read/write it is HMAC only, the signature is no longer required or even present on the filesystem. In an offline signed image the master node is authenticated by the superblock. In a transition to r/w we have to make sure that the master node is rewritten before the superblock node. In this case the master node gets a HMAC and its authenticity no longer depends on the superblock node. There are some cases in which the current code first writes the superblock node though, so with this patch writing of the superblock node is delayed until the master node is written. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2019-05-14 16:33:22 +08:00
/*
* Handle offline signed images: Now that the master node is
* written and its validation no longer depends on the hash
* in the superblock, we can update the offline signed
* superblock with a HMAC version,
*/
if (ubifs_authenticated(c) && ubifs_hmac_zero(c, c->sup_node->hmac)) {
err = ubifs_hmac_wkm(c, c->sup_node->hmac_wkm);
if (err)
goto out_lpt;
c->superblock_need_write = 1;
}
if (!c->ro_mount && c->superblock_need_write) {
err = ubifs_write_sb_node(c, c->sup_node);
if (err)
goto out_lpt;
c->superblock_need_write = 0;
}
err = dbg_check_idx_size(c, c->bi.old_idx_sz);
if (err)
goto out_lpt;
err = ubifs_replay_journal(c);
if (err)
goto out_journal;
/* Calculate 'min_idx_lebs' after journal replay */
c->bi.min_idx_lebs = ubifs_calc_min_idx_lebs(c);
err = ubifs_mount_orphans(c, c->need_recovery, c->ro_mount);
if (err)
goto out_orphans;
if (!c->ro_mount) {
int lnum;
err = check_free_space(c);
if (err)
goto out_orphans;
/* Check for enough log space */
lnum = c->lhead_lnum + 1;
if (lnum >= UBIFS_LOG_LNUM + c->log_lebs)
lnum = UBIFS_LOG_LNUM;
if (lnum == c->ltail_lnum) {
err = ubifs_consolidate_log(c);
if (err)
goto out_orphans;
}
if (c->need_recovery) {
if (!ubifs_authenticated(c)) {
err = ubifs_recover_size(c, true);
if (err)
goto out_orphans;
}
err = ubifs_rcvry_gc_commit(c);
if (err)
goto out_orphans;
if (ubifs_authenticated(c)) {
err = ubifs_recover_size(c, false);
if (err)
goto out_orphans;
}
} else {
err = take_gc_lnum(c);
if (err)
goto out_orphans;
/*
* GC LEB may contain garbage if there was an unclean
* reboot, and it should be un-mapped.
*/
err = ubifs_leb_unmap(c, c->gc_lnum);
if (err)
goto out_orphans;
}
err = dbg_check_lprops(c);
if (err)
goto out_orphans;
} else if (c->need_recovery) {
err = ubifs_recover_size(c, false);
if (err)
goto out_orphans;
} else {
/*
* Even if we mount read-only, we have to set space in GC LEB
* to proper value because this affects UBIFS free space
* reporting. We do not want to have a situation when
* re-mounting from R/O to R/W changes amount of free space.
*/
err = take_gc_lnum(c);
if (err)
goto out_orphans;
}
spin_lock(&ubifs_infos_lock);
list_add_tail(&c->infos_list, &ubifs_infos);
spin_unlock(&ubifs_infos_lock);
if (c->need_recovery) {
if (c->ro_mount)
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "recovery deferred");
else {
c->need_recovery = 0;
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "recovery completed");
/*
* GC LEB has to be empty and taken at this point. But
* the journal head LEBs may also be accounted as
* "empty taken" if they are empty.
*/
ubifs_assert(c, c->lst.taken_empty_lebs > 0);
}
} else
ubifs_assert(c, c->lst.taken_empty_lebs > 0);
err = dbg_check_filesystem(c);
if (err)
goto out_infos;
dbg_debugfs_init_fs(c);
c->mounting = 0;
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "UBIFS: mounted UBI device %d, volume %d, name \"%s\"%s",
c->vi.ubi_num, c->vi.vol_id, c->vi.name,
c->ro_mount ? ", R/O mode" : "");
x = (long long)c->main_lebs * c->leb_size;
y = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes;
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "LEB size: %d bytes (%d KiB), min./max. I/O unit sizes: %d bytes/%d bytes",
c->leb_size, c->leb_size >> 10, c->min_io_size,
c->max_write_size);
ubifs_msg(c, "FS size: %lld bytes (%lld MiB, %d LEBs), max %d LEBs, journal size %lld bytes (%lld MiB, %d LEBs)",
x, x >> 20, c->main_lebs, c->max_leb_cnt,
y, y >> 20, c->log_lebs + c->max_bud_cnt);
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "reserved for root: %llu bytes (%llu KiB)",
c->report_rp_size, c->report_rp_size >> 10);
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "media format: w%d/r%d (latest is w%d/r%d), UUID %pUB%s",
c->fmt_version, c->ro_compat_version,
UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION, c->uuid,
c->big_lpt ? ", big LPT model" : ", small LPT model");
dbg_gen("default compressor: %s", ubifs_compr_name(c, c->default_compr));
dbg_gen("data journal heads: %d",
c->jhead_cnt - NONDATA_JHEADS_CNT);
dbg_gen("log LEBs: %d (%d - %d)",
c->log_lebs, UBIFS_LOG_LNUM, c->log_last);
dbg_gen("LPT area LEBs: %d (%d - %d)",
c->lpt_lebs, c->lpt_first, c->lpt_last);
dbg_gen("orphan area LEBs: %d (%d - %d)",
c->orph_lebs, c->orph_first, c->orph_last);
dbg_gen("main area LEBs: %d (%d - %d)",
c->main_lebs, c->main_first, c->leb_cnt - 1);
dbg_gen("index LEBs: %d", c->lst.idx_lebs);
dbg_gen("total index bytes: %llu (%llu KiB, %llu MiB)",
c->bi.old_idx_sz, c->bi.old_idx_sz >> 10,
c->bi.old_idx_sz >> 20);
dbg_gen("key hash type: %d", c->key_hash_type);
dbg_gen("tree fanout: %d", c->fanout);
dbg_gen("reserved GC LEB: %d", c->gc_lnum);
dbg_gen("max. znode size %d", c->max_znode_sz);
dbg_gen("max. index node size %d", c->max_idx_node_sz);
dbg_gen("node sizes: data %zu, inode %zu, dentry %zu",
UBIFS_DATA_NODE_SZ, UBIFS_INO_NODE_SZ, UBIFS_DENT_NODE_SZ);
dbg_gen("node sizes: trun %zu, sb %zu, master %zu",
UBIFS_TRUN_NODE_SZ, UBIFS_SB_NODE_SZ, UBIFS_MST_NODE_SZ);
dbg_gen("node sizes: ref %zu, cmt. start %zu, orph %zu",
UBIFS_REF_NODE_SZ, UBIFS_CS_NODE_SZ, UBIFS_ORPH_NODE_SZ);
dbg_gen("max. node sizes: data %zu, inode %zu dentry %zu, idx %d",
UBIFS_MAX_DATA_NODE_SZ, UBIFS_MAX_INO_NODE_SZ,
UBIFS_MAX_DENT_NODE_SZ, ubifs_idx_node_sz(c, c->fanout));
dbg_gen("dead watermark: %d", c->dead_wm);
dbg_gen("dark watermark: %d", c->dark_wm);
dbg_gen("LEB overhead: %d", c->leb_overhead);
x = (long long)c->main_lebs * c->dark_wm;
dbg_gen("max. dark space: %lld (%lld KiB, %lld MiB)",
x, x >> 10, x >> 20);
dbg_gen("maximum bud bytes: %lld (%lld KiB, %lld MiB)",
c->max_bud_bytes, c->max_bud_bytes >> 10,
c->max_bud_bytes >> 20);
dbg_gen("BG commit bud bytes: %lld (%lld KiB, %lld MiB)",
c->bg_bud_bytes, c->bg_bud_bytes >> 10,
c->bg_bud_bytes >> 20);
dbg_gen("current bud bytes %lld (%lld KiB, %lld MiB)",
c->bud_bytes, c->bud_bytes >> 10, c->bud_bytes >> 20);
dbg_gen("max. seq. number: %llu", c->max_sqnum);
dbg_gen("commit number: %llu", c->cmt_no);
dbg_gen("max. xattrs per inode: %d", ubifs_xattr_max_cnt(c));
dbg_gen("max orphans: %d", c->max_orphans);
return 0;
out_infos:
spin_lock(&ubifs_infos_lock);
list_del(&c->infos_list);
spin_unlock(&ubifs_infos_lock);
out_orphans:
free_orphans(c);
out_journal:
destroy_journal(c);
out_lpt:
ubifs_lpt_free(c, 0);
out_master:
kfree(c->mst_node);
kfree(c->rcvrd_mst_node);
if (c->bgt)
kthread_stop(c->bgt);
out_wbufs:
free_wbufs(c);
out_cbuf:
kfree(c->cbuf);
out_auth:
ubifs_exit_authentication(c);
out_free:
kfree(c->write_reserve_buf);
kfree(c->bu.buf);
vfree(c->ileb_buf);
vfree(c->sbuf);
kfree(c->bottom_up_buf);
kfree(c->sup_node);
ubifs_sysfs_unregister(c);
out_debugging:
ubifs_debugging_exit(c);
return err;
}
/**
* ubifs_umount - un-mount UBIFS file-system.
* @c: UBIFS file-system description object
*
* Note, this function is called to free allocated resourced when un-mounting,
* as well as free resources when an error occurred while we were half way
* through mounting (error path cleanup function). So it has to make sure the
* resource was actually allocated before freeing it.
*/
static void ubifs_umount(struct ubifs_info *c)
{
dbg_gen("un-mounting UBI device %d, volume %d", c->vi.ubi_num,
c->vi.vol_id);
dbg_debugfs_exit_fs(c);
spin_lock(&ubifs_infos_lock);
list_del(&c->infos_list);
spin_unlock(&ubifs_infos_lock);
if (c->bgt)
kthread_stop(c->bgt);
destroy_journal(c);
free_wbufs(c);
free_orphans(c);
ubifs_lpt_free(c, 0);
ubifs_exit_authentication(c);
ubifs_release_options(c);
kfree(c->cbuf);
kfree(c->rcvrd_mst_node);
kfree(c->mst_node);
kfree(c->write_reserve_buf);
kfree(c->bu.buf);
vfree(c->ileb_buf);
vfree(c->sbuf);
kfree(c->bottom_up_buf);
kfree(c->sup_node);
ubifs_debugging_exit(c);
ubifs_sysfs_unregister(c);
}
/**
* ubifs_remount_rw - re-mount in read-write mode.
* @c: UBIFS file-system description object
*
* UBIFS avoids allocating many unnecessary resources when mounted in read-only
* mode. This function allocates the needed resources and re-mounts UBIFS in
* read-write mode.
*/
static int ubifs_remount_rw(struct ubifs_info *c)
{
int err, lnum;
if (c->rw_incompat) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "the file-system is not R/W-compatible");
ubifs_msg(c, "on-flash format version is w%d/r%d, but software only supports up to version w%d/r%d",
c->fmt_version, c->ro_compat_version,
UBIFS_FORMAT_VERSION, UBIFS_RO_COMPAT_VERSION);
return -EROFS;
}
mutex_lock(&c->umount_mutex);
dbg_save_space_info(c);
c->remounting_rw = 1;
c->ro_mount = 0;
if (c->space_fixup) {
err = ubifs_fixup_free_space(c);
if (err)
goto out;
}
err = check_free_space(c);
if (err)
goto out;
if (c->need_recovery) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "completing deferred recovery");
err = ubifs_write_rcvrd_mst_node(c);
if (err)
goto out;
if (!ubifs_authenticated(c)) {
err = ubifs_recover_size(c, true);
if (err)
goto out;
}
err = ubifs_clean_lebs(c, c->sbuf);
if (err)
goto out;
err = ubifs_recover_inl_heads(c, c->sbuf);
if (err)
goto out;
} else {
/* A readonly mount is not allowed to have orphans */
ubifs_assert(c, c->tot_orphans == 0);
err = ubifs_clear_orphans(c);
if (err)
goto out;
}
if (!(c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY))) {
c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
err = ubifs_write_master(c);
if (err)
goto out;
}
ubifs: support offline signed images HMACs can only be generated on the system the UBIFS image is running on. To support offline signed images we add a PKCS#7 signature to the UBIFS image which can be created by mkfs.ubifs. Both the master node and the superblock need to be authenticated, during normal runtime both are protected with HMACs. For offline signature support however only a single signature is desired. We add a signature covering the superblock node directly behind it. To protect the master node a hash of the master node is added to the superblock which is used when the master node doesn't contain a HMAC. Transition to a read/write filesystem is also supported. During transition first the master node is rewritten with a HMAC (implicitly, it is written anyway as the FS is marked dirty). Afterwards the superblock is rewritten with a HMAC. Once after the image has been mounted read/write it is HMAC only, the signature is no longer required or even present on the filesystem. In an offline signed image the master node is authenticated by the superblock. In a transition to r/w we have to make sure that the master node is rewritten before the superblock node. In this case the master node gets a HMAC and its authenticity no longer depends on the superblock node. There are some cases in which the current code first writes the superblock node though, so with this patch writing of the superblock node is delayed until the master node is written. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Richard Weinberger <richard@nod.at>
2019-05-14 16:33:22 +08:00
if (c->superblock_need_write) {
struct ubifs_sb_node *sup = c->sup_node;
err = ubifs_write_sb_node(c, sup);
if (err)
goto out;
c->superblock_need_write = 0;
}
c->ileb_buf = vmalloc(c->leb_size);
if (!c->ileb_buf) {
err = -ENOMEM;
goto out;
}
c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ + \
UBIFS_CIPHER_BLOCK_SIZE, GFP_KERNEL);
if (!c->write_reserve_buf) {
err = -ENOMEM;
goto out;
}
err = ubifs_lpt_init(c, 0, 1);
if (err)
goto out;
/* Create background thread */
c->bgt = kthread_run(ubifs_bg_thread, c, "%s", c->bgt_name);
if (IS_ERR(c->bgt)) {
err = PTR_ERR(c->bgt);
c->bgt = NULL;
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "cannot spawn \"%s\", error %d",
c->bgt_name, err);
goto out;
}
c->orph_buf = vmalloc(c->leb_size);
if (!c->orph_buf) {
err = -ENOMEM;
goto out;
}
/* Check for enough log space */
lnum = c->lhead_lnum + 1;
if (lnum >= UBIFS_LOG_LNUM + c->log_lebs)
lnum = UBIFS_LOG_LNUM;
if (lnum == c->ltail_lnum) {
err = ubifs_consolidate_log(c);
if (err)
goto out;
}
if (c->need_recovery) {
err = ubifs_rcvry_gc_commit(c);
if (err)
goto out;
if (ubifs_authenticated(c)) {
err = ubifs_recover_size(c, false);
if (err)
goto out;
}
} else {
err = ubifs_leb_unmap(c, c->gc_lnum);
}
if (err)
goto out;
dbg_gen("re-mounted read-write");
c->remounting_rw = 0;
if (c->need_recovery) {
c->need_recovery = 0;
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "deferred recovery completed");
} else {
/*
* Do not run the debugging space check if the were doing
* recovery, because when we saved the information we had the
* file-system in a state where the TNC and lprops has been
* modified in memory, but all the I/O operations (including a
* commit) were deferred. So the file-system was in
* "non-committed" state. Now the file-system is in committed
* state, and of course the amount of free space will change
* because, for example, the old index size was imprecise.
*/
err = dbg_check_space_info(c);
}
mutex_unlock(&c->umount_mutex);
return err;
out:
c->ro_mount = 1;
vfree(c->orph_buf);
c->orph_buf = NULL;
if (c->bgt) {
kthread_stop(c->bgt);
c->bgt = NULL;
}
kfree(c->write_reserve_buf);
c->write_reserve_buf = NULL;
vfree(c->ileb_buf);
c->ileb_buf = NULL;
ubifs_lpt_free(c, 1);
c->remounting_rw = 0;
mutex_unlock(&c->umount_mutex);
return err;
}
/**
* ubifs_remount_ro - re-mount in read-only mode.
* @c: UBIFS file-system description object
*
* We assume VFS has stopped writing. Possibly the background thread could be
* running a commit, however kthread_stop will wait in that case.
*/
static void ubifs_remount_ro(struct ubifs_info *c)
{
int i, err;
ubifs_assert(c, !c->need_recovery);
ubifs_assert(c, !c->ro_mount);
mutex_lock(&c->umount_mutex);
if (c->bgt) {
kthread_stop(c->bgt);
c->bgt = NULL;
}
dbg_save_space_info(c);
for (i = 0; i < c->jhead_cnt; i++) {
err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
if (err)
ubifs_ro_mode(c, err);
}
c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum);
err = ubifs_write_master(c);
if (err)
ubifs_ro_mode(c, err);
vfree(c->orph_buf);
c->orph_buf = NULL;
kfree(c->write_reserve_buf);
c->write_reserve_buf = NULL;
vfree(c->ileb_buf);
c->ileb_buf = NULL;
ubifs_lpt_free(c, 1);
c->ro_mount = 1;
err = dbg_check_space_info(c);
if (err)
ubifs_ro_mode(c, err);
mutex_unlock(&c->umount_mutex);
}
static void ubifs_put_super(struct super_block *sb)
{
int i;
struct ubifs_info *c = sb->s_fs_info;
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "un-mount UBI device %d", c->vi.ubi_num);
/*
* The following asserts are only valid if there has not been a failure
* of the media. For example, there will be dirty inodes if we failed
* to write them back because of I/O errors.
*/
if (!c->ro_error) {
ubifs_assert(c, c->bi.idx_growth == 0);
ubifs_assert(c, c->bi.dd_growth == 0);
ubifs_assert(c, c->bi.data_growth == 0);
}
/*
* The 'c->umount_lock' prevents races between UBIFS memory shrinker
* and file system un-mount. Namely, it prevents the shrinker from
* picking this superblock for shrinking - it will be just skipped if
* the mutex is locked.
*/
mutex_lock(&c->umount_mutex);
if (!c->ro_mount) {
/*
* First of all kill the background thread to make sure it does
* not interfere with un-mounting and freeing resources.
*/
if (c->bgt) {
kthread_stop(c->bgt);
c->bgt = NULL;
}
/*
* On fatal errors c->ro_error is set to 1, in which case we do
* not write the master node.
*/
if (!c->ro_error) {
int err;
/* Synchronize write-buffers */
for (i = 0; i < c->jhead_cnt; i++) {
err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
if (err)
ubifs_ro_mode(c, err);
}
/*
* We are being cleanly unmounted which means the
* orphans were killed - indicate this in the master
* node. Also save the reserved GC LEB number.
*/
c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum);
err = ubifs_write_master(c);
if (err)
/*
* Recovery will attempt to fix the master area
* next mount, so we just print a message and
* continue to unmount normally.
*/
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "failed to write master node, error %d",
err);
} else {
for (i = 0; i < c->jhead_cnt; i++)
/* Make sure write-buffer timers are canceled */
hrtimer_cancel(&c->jheads[i].wbuf.timer);
}
}
ubifs_umount(c);
ubi_close_volume(c->ubi);
mutex_unlock(&c->umount_mutex);
}
static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
{
int err;
struct ubifs_info *c = sb->s_fs_info;
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 22:14:33 +08:00
sync_filesystem(sb);
dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, *flags);
err = ubifs_parse_options(c, data, 1);
if (err) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_err(c, "invalid or unknown remount parameter");
return err;
}
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
if (c->ro_mount && !(*flags & SB_RDONLY)) {
if (c->ro_error) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "cannot re-mount R/W due to prior errors");
return -EROFS;
}
if (c->ro_media) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "cannot re-mount R/W - UBI volume is R/O");
return -EROFS;
}
err = ubifs_remount_rw(c);
if (err)
return err;
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
} else if (!c->ro_mount && (*flags & SB_RDONLY)) {
if (c->ro_error) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
ubifs_msg(c, "cannot re-mount R/O due to prior errors");
return -EROFS;
}
ubifs_remount_ro(c);
}
if (c->bulk_read == 1)
bu_init(c);
else {
dbg_gen("disable bulk-read");
ubifs: Fix oops when remounting with no_bulk_read. When remounting with the no_bulk_read option, there is a problem accessing the "bulk_read buffer(bu.buf)" which has already been freed. If the bulk_read option is enabled, ubifs_tnc_bulk_read uses the pre-allocated bu.buf. While bu.buf is being used by ubifs_tnc_bulk_read, remounting with no_bulk_read frees bu.buf. So I added code to check the use of "bu.buf" to avoid this situation. ------ I tested as follows(kernel v3.18) : Use the script to repeat "no_bulk_read <-> bulk_read" remount.sh #!/bin/sh while true do; mount -o remount,no_bulk_read ${MOUNT_POINT}; sleep 1; mount -o remount,bulk_read ${MOUNT_POINT}; sleep 1; done Perform read operation cat ${MOUNT_POINT}/* > /dev/null The problem is reproduced immediately. [ 234.256845][kernel.0]Internal error: Oops: 17 [#1] PREEMPT ARM [ 234.258557][kernel.0]CPU: 0 PID: 2752 Comm: cat Tainted: G W O 3.18.31+ #51 [ 234.259531][kernel.0]task: cbff8580 ti: cbd66000 task.ti: cbd66000 [ 234.260306][kernel.0]PC is at validate_data_node+0x10/0x264 [ 234.260994][kernel.0]LR is at ubifs_tnc_bulk_read+0x388/0x3ec [ 234.261712][kernel.0]pc : [<c01d98fc>] lr : [<c01dc300>] psr: 80000013 [ 234.261712][kernel.0]sp : cbd67ba0 ip : 00000001 fp : 00000000 [ 234.263337][kernel.0]r10: cd3e0260 r9 : c0df2008 r8 : 00000000 [ 234.264087][kernel.0]r7 : cd3e0000 r6 : 00000000 r5 : cd3e0278 r4 : cd3e0000 [ 234.264999][kernel.0]r3 : 00000003 r2 : cd3e0280 r1 : 00000000 r0 : cd3e0000 [ 234.265910][kernel.0]Flags: Nzcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user [ 234.266896][kernel.0]Control: 10c53c7d Table: 8c40c059 DAC: 00000015 [ 234.267711][kernel.0]Process cat (pid: 2752, stack limit = 0xcbd66400) [ 234.268525][kernel.0]Stack: (0xcbd67ba0 to 0xcbd68000) [ 234.269169][kernel.0]7ba0: cd7c3940 c03d8650 0001bfe0 00002ab2 00000000 cbd67c5c cbd67c58 0001bfe0 [ 234.270287][kernel.0]7bc0: cd3e0000 00002ab2 0001bfe0 00000014 cbd66000 cd3e0260 00000000 c01d6660 [ 234.271403][kernel.0]7be0: 00002ab2 00000000 c82a5800 ffffffff cd3e0298 cd3e0278 00000000 cd3e0000 [ 234.272520][kernel.0]7c00: 00000000 00000000 cd3e0260 c01dc300 00002ab2 00000000 60000013 d663affa [ 234.273639][kernel.0]7c20: cd3e01f0 cd3e01f0 60000013 c09397ec 00000000 cd3e0278 00002ab2 00000000 [ 234.274755][kernel.0]7c40: cd3e0000 c01dbf48 00000014 00000003 00000160 00000015 00000004 d663affa [ 234.275874][kernel.0]7c60: ccdaa978 cd3e0278 cd3e0000 cf32a5f4 ccdaa820 00000044 cbd66000 cd3e0260 [ 234.276992][kernel.0]7c80: 00000003 c01cec84 ccdaa8dc cbd67cc4 cbd67ec0 00000010 ccdaa978 00000000 [ 234.278108][kernel.0]7ca0: 0000015e ccdaa8dc 00000000 00000000 cf32a5d0 00000000 0000015f ccdaa8dc [ 234.279228][kernel.0]7cc0: 00000000 c8488300 0009e5a4 0000000e cbd66000 0000015e cf32a5f4 c0113c04 [ 234.280346][kernel.0]7ce0: 0000009f 0000003c c00098c4 ffffffff 00001000 00000000 000000ad 00000010 [ 234.281463][kernel.0]7d00: 00000038 cd68f580 00000150 c8488360 00000000 cbd67d30 cbd67d70 0000000e [ 234.282579][kernel.0]7d20: 00000010 00000000 c0951874 c0112a9c cf379b60 cf379b84 cf379890 cf3798b4 [ 234.283699][kernel.0]7d40: cf379578 cf37959c cf379380 cf3793a4 cf3790b0 cf3790d4 cf378fd8 cf378ffc [ 234.284814][kernel.0]7d60: cf378f48 cf378f6c cf32a5f4 cf32a5d0 00000000 00001000 00000018 00000000 [ 234.285932][kernel.0]7d80: 00001000 c0050da4 00000000 00001000 cec04c00 00000000 00001000 c0e11328 [ 234.287049][kernel.0]7da0: 00000000 00001000 cbd66000 00000000 00001000 c0012a60 00000000 00001000 [ 234.288166][kernel.0]7dc0: cbd67dd4 00000000 00001000 80000013 00000000 00001000 cd68f580 00000000 [ 234.289285][kernel.0]7de0: 00001000 c915d600 00000000 00001000 cbd67e48 00000000 00001000 00000018 [ 234.290402][kernel.0]7e00: 00000000 00001000 00000000 00000000 00001000 c915d768 c915d768 c0113550 [ 234.291522][kernel.0]7e20: cd68f580 cbd67e48 cd68f580 cb6713c0 00010000 000ac5a4 00000000 001fc5a4 [ 234.292637][kernel.0]7e40: 00000000 c8488300 cbd67ec0 00eb0000 cd68f580 c0113ee4 00000000 cbd67ec0 [ 234.293754][kernel.0]7e60: cd68f580 c8488300 cbd67ec0 00eb0000 cd68f580 00150000 c8488300 00eb0000 [ 234.294874][kernel.0]7e80: 00010000 c0112fd0 00000000 cbd67ec0 cd68f580 00150000 00000000 cd68f580 [ 234.295991][kernel.0]7ea0: cbd67ef0 c011308c 00000000 00000002 cd768850 00010000 00000000 c01133fc [ 234.297110][kernel.0]7ec0: 00150000 00000000 cbd67f50 00000000 00000000 cb6713c0 01000000 cbd67f48 [ 234.298226][kernel.0]7ee0: cbd67f50 c8488300 00000000 c0113204 00010000 01000000 00000000 cb6713c0 [ 234.299342][kernel.0]7f00: 00150000 00000000 cbd67f50 00000000 00000000 00000000 00000000 00000000 [ 234.300462][kernel.0]7f20: cbd67f50 01000000 01000000 cb6713c0 c8488300 c00ebba8 01000000 00000000 [ 234.301577][kernel.0]7f40: c8488300 cb6713c0 00000000 00000000 00000000 00000000 ccdaa820 00000000 [ 234.302697][kernel.0]7f60: 00000000 01000000 00000003 00000001 cbd66000 00000000 00000001 c00ec678 [ 234.303813][kernel.0]7f80: 00000000 00000200 00000000 01000000 01000000 00000000 00000000 000000ef [ 234.304933][kernel.0]7fa0: c000e904 c000e780 01000000 00000000 00000001 00000003 00000000 01000000 [ 234.306049][kernel.0]7fc0: 01000000 00000000 00000000 000000ef 00000001 00000003 01000000 00000001 [ 234.307165][kernel.0]7fe0: 00000000 beafb78c 0000ad08 00128d1c 60000010 00000001 00000000 00000000 [ 234.308292][kernel.0][<c01d98fc>] (validate_data_node) from [<c01dc300>] (ubifs_tnc_bulk_read+0x388/0x3ec) [ 234.309493][kernel.0][<c01dc300>] (ubifs_tnc_bulk_read) from [<c01cec84>] (ubifs_readpage+0x1dc/0x46c) [ 234.310656][kernel.0][<c01cec84>] (ubifs_readpage) from [<c0113c04>] (__generic_file_splice_read+0x29c/0x4cc) [ 234.311890][kernel.0][<c0113c04>] (__generic_file_splice_read) from [<c0113ee4>] (generic_file_splice_read+0xb0/0xf4) [ 234.313214][kernel.0][<c0113ee4>] (generic_file_splice_read) from [<c0112fd0>] (do_splice_to+0x68/0x7c) [ 234.314386][kernel.0][<c0112fd0>] (do_splice_to) from [<c011308c>] (splice_direct_to_actor+0xa8/0x190) [ 234.315544][kernel.0][<c011308c>] (splice_direct_to_actor) from [<c0113204>] (do_splice_direct+0x90/0xb8) [ 234.316741][kernel.0][<c0113204>] (do_splice_direct) from [<c00ebba8>] (do_sendfile+0x17c/0x2b8) [ 234.317838][kernel.0][<c00ebba8>] (do_sendfile) from [<c00ec678>] (SyS_sendfile64+0xc4/0xcc) [ 234.318890][kernel.0][<c00ec678>] (SyS_sendfile64) from [<c000e780>] (ret_fast_syscall+0x0/0x38) [ 234.319983][kernel.0]Code: e92d47f0 e24dd050 e59f9228 e1a04000 (e5d18014) Signed-off-by: karam.lee <karam.lee@lge.com> Signed-off-by: Richard Weinberger <richard@nod.at>
2017-06-12 09:46:31 +08:00
mutex_lock(&c->bu_mutex);
kfree(c->bu.buf);
c->bu.buf = NULL;
ubifs: Fix oops when remounting with no_bulk_read. When remounting with the no_bulk_read option, there is a problem accessing the "bulk_read buffer(bu.buf)" which has already been freed. If the bulk_read option is enabled, ubifs_tnc_bulk_read uses the pre-allocated bu.buf. While bu.buf is being used by ubifs_tnc_bulk_read, remounting with no_bulk_read frees bu.buf. So I added code to check the use of "bu.buf" to avoid this situation. ------ I tested as follows(kernel v3.18) : Use the script to repeat "no_bulk_read <-> bulk_read" remount.sh #!/bin/sh while true do; mount -o remount,no_bulk_read ${MOUNT_POINT}; sleep 1; mount -o remount,bulk_read ${MOUNT_POINT}; sleep 1; done Perform read operation cat ${MOUNT_POINT}/* > /dev/null The problem is reproduced immediately. [ 234.256845][kernel.0]Internal error: Oops: 17 [#1] PREEMPT ARM [ 234.258557][kernel.0]CPU: 0 PID: 2752 Comm: cat Tainted: G W O 3.18.31+ #51 [ 234.259531][kernel.0]task: cbff8580 ti: cbd66000 task.ti: cbd66000 [ 234.260306][kernel.0]PC is at validate_data_node+0x10/0x264 [ 234.260994][kernel.0]LR is at ubifs_tnc_bulk_read+0x388/0x3ec [ 234.261712][kernel.0]pc : [<c01d98fc>] lr : [<c01dc300>] psr: 80000013 [ 234.261712][kernel.0]sp : cbd67ba0 ip : 00000001 fp : 00000000 [ 234.263337][kernel.0]r10: cd3e0260 r9 : c0df2008 r8 : 00000000 [ 234.264087][kernel.0]r7 : cd3e0000 r6 : 00000000 r5 : cd3e0278 r4 : cd3e0000 [ 234.264999][kernel.0]r3 : 00000003 r2 : cd3e0280 r1 : 00000000 r0 : cd3e0000 [ 234.265910][kernel.0]Flags: Nzcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user [ 234.266896][kernel.0]Control: 10c53c7d Table: 8c40c059 DAC: 00000015 [ 234.267711][kernel.0]Process cat (pid: 2752, stack limit = 0xcbd66400) [ 234.268525][kernel.0]Stack: (0xcbd67ba0 to 0xcbd68000) [ 234.269169][kernel.0]7ba0: cd7c3940 c03d8650 0001bfe0 00002ab2 00000000 cbd67c5c cbd67c58 0001bfe0 [ 234.270287][kernel.0]7bc0: cd3e0000 00002ab2 0001bfe0 00000014 cbd66000 cd3e0260 00000000 c01d6660 [ 234.271403][kernel.0]7be0: 00002ab2 00000000 c82a5800 ffffffff cd3e0298 cd3e0278 00000000 cd3e0000 [ 234.272520][kernel.0]7c00: 00000000 00000000 cd3e0260 c01dc300 00002ab2 00000000 60000013 d663affa [ 234.273639][kernel.0]7c20: cd3e01f0 cd3e01f0 60000013 c09397ec 00000000 cd3e0278 00002ab2 00000000 [ 234.274755][kernel.0]7c40: cd3e0000 c01dbf48 00000014 00000003 00000160 00000015 00000004 d663affa [ 234.275874][kernel.0]7c60: ccdaa978 cd3e0278 cd3e0000 cf32a5f4 ccdaa820 00000044 cbd66000 cd3e0260 [ 234.276992][kernel.0]7c80: 00000003 c01cec84 ccdaa8dc cbd67cc4 cbd67ec0 00000010 ccdaa978 00000000 [ 234.278108][kernel.0]7ca0: 0000015e ccdaa8dc 00000000 00000000 cf32a5d0 00000000 0000015f ccdaa8dc [ 234.279228][kernel.0]7cc0: 00000000 c8488300 0009e5a4 0000000e cbd66000 0000015e cf32a5f4 c0113c04 [ 234.280346][kernel.0]7ce0: 0000009f 0000003c c00098c4 ffffffff 00001000 00000000 000000ad 00000010 [ 234.281463][kernel.0]7d00: 00000038 cd68f580 00000150 c8488360 00000000 cbd67d30 cbd67d70 0000000e [ 234.282579][kernel.0]7d20: 00000010 00000000 c0951874 c0112a9c cf379b60 cf379b84 cf379890 cf3798b4 [ 234.283699][kernel.0]7d40: cf379578 cf37959c cf379380 cf3793a4 cf3790b0 cf3790d4 cf378fd8 cf378ffc [ 234.284814][kernel.0]7d60: cf378f48 cf378f6c cf32a5f4 cf32a5d0 00000000 00001000 00000018 00000000 [ 234.285932][kernel.0]7d80: 00001000 c0050da4 00000000 00001000 cec04c00 00000000 00001000 c0e11328 [ 234.287049][kernel.0]7da0: 00000000 00001000 cbd66000 00000000 00001000 c0012a60 00000000 00001000 [ 234.288166][kernel.0]7dc0: cbd67dd4 00000000 00001000 80000013 00000000 00001000 cd68f580 00000000 [ 234.289285][kernel.0]7de0: 00001000 c915d600 00000000 00001000 cbd67e48 00000000 00001000 00000018 [ 234.290402][kernel.0]7e00: 00000000 00001000 00000000 00000000 00001000 c915d768 c915d768 c0113550 [ 234.291522][kernel.0]7e20: cd68f580 cbd67e48 cd68f580 cb6713c0 00010000 000ac5a4 00000000 001fc5a4 [ 234.292637][kernel.0]7e40: 00000000 c8488300 cbd67ec0 00eb0000 cd68f580 c0113ee4 00000000 cbd67ec0 [ 234.293754][kernel.0]7e60: cd68f580 c8488300 cbd67ec0 00eb0000 cd68f580 00150000 c8488300 00eb0000 [ 234.294874][kernel.0]7e80: 00010000 c0112fd0 00000000 cbd67ec0 cd68f580 00150000 00000000 cd68f580 [ 234.295991][kernel.0]7ea0: cbd67ef0 c011308c 00000000 00000002 cd768850 00010000 00000000 c01133fc [ 234.297110][kernel.0]7ec0: 00150000 00000000 cbd67f50 00000000 00000000 cb6713c0 01000000 cbd67f48 [ 234.298226][kernel.0]7ee0: cbd67f50 c8488300 00000000 c0113204 00010000 01000000 00000000 cb6713c0 [ 234.299342][kernel.0]7f00: 00150000 00000000 cbd67f50 00000000 00000000 00000000 00000000 00000000 [ 234.300462][kernel.0]7f20: cbd67f50 01000000 01000000 cb6713c0 c8488300 c00ebba8 01000000 00000000 [ 234.301577][kernel.0]7f40: c8488300 cb6713c0 00000000 00000000 00000000 00000000 ccdaa820 00000000 [ 234.302697][kernel.0]7f60: 00000000 01000000 00000003 00000001 cbd66000 00000000 00000001 c00ec678 [ 234.303813][kernel.0]7f80: 00000000 00000200 00000000 01000000 01000000 00000000 00000000 000000ef [ 234.304933][kernel.0]7fa0: c000e904 c000e780 01000000 00000000 00000001 00000003 00000000 01000000 [ 234.306049][kernel.0]7fc0: 01000000 00000000 00000000 000000ef 00000001 00000003 01000000 00000001 [ 234.307165][kernel.0]7fe0: 00000000 beafb78c 0000ad08 00128d1c 60000010 00000001 00000000 00000000 [ 234.308292][kernel.0][<c01d98fc>] (validate_data_node) from [<c01dc300>] (ubifs_tnc_bulk_read+0x388/0x3ec) [ 234.309493][kernel.0][<c01dc300>] (ubifs_tnc_bulk_read) from [<c01cec84>] (ubifs_readpage+0x1dc/0x46c) [ 234.310656][kernel.0][<c01cec84>] (ubifs_readpage) from [<c0113c04>] (__generic_file_splice_read+0x29c/0x4cc) [ 234.311890][kernel.0][<c0113c04>] (__generic_file_splice_read) from [<c0113ee4>] (generic_file_splice_read+0xb0/0xf4) [ 234.313214][kernel.0][<c0113ee4>] (generic_file_splice_read) from [<c0112fd0>] (do_splice_to+0x68/0x7c) [ 234.314386][kernel.0][<c0112fd0>] (do_splice_to) from [<c011308c>] (splice_direct_to_actor+0xa8/0x190) [ 234.315544][kernel.0][<c011308c>] (splice_direct_to_actor) from [<c0113204>] (do_splice_direct+0x90/0xb8) [ 234.316741][kernel.0][<c0113204>] (do_splice_direct) from [<c00ebba8>] (do_sendfile+0x17c/0x2b8) [ 234.317838][kernel.0][<c00ebba8>] (do_sendfile) from [<c00ec678>] (SyS_sendfile64+0xc4/0xcc) [ 234.318890][kernel.0][<c00ec678>] (SyS_sendfile64) from [<c000e780>] (ret_fast_syscall+0x0/0x38) [ 234.319983][kernel.0]Code: e92d47f0 e24dd050 e59f9228 e1a04000 (e5d18014) Signed-off-by: karam.lee <karam.lee@lge.com> Signed-off-by: Richard Weinberger <richard@nod.at>
2017-06-12 09:46:31 +08:00
mutex_unlock(&c->bu_mutex);
}
if (!c->need_recovery)
ubifs_assert(c, c->lst.taken_empty_lebs > 0);
return 0;
}
const struct super_operations ubifs_super_operations = {
.alloc_inode = ubifs_alloc_inode,
.free_inode = ubifs_free_inode,
.put_super = ubifs_put_super,
.write_inode = ubifs_write_inode,
.drop_inode = ubifs_drop_inode,
.evict_inode = ubifs_evict_inode,
.statfs = ubifs_statfs,
.dirty_inode = ubifs_dirty_inode,
.remount_fs = ubifs_remount_fs,
.show_options = ubifs_show_options,
.sync_fs = ubifs_sync_fs,
};
/**
* open_ubi - parse UBI device name string and open the UBI device.
* @name: UBI volume name
* @mode: UBI volume open mode
*
* The primary method of mounting UBIFS is by specifying the UBI volume
* character device node path. However, UBIFS may also be mounted without any
* character device node using one of the following methods:
*
* o ubiX_Y - mount UBI device number X, volume Y;
* o ubiY - mount UBI device number 0, volume Y;
* o ubiX:NAME - mount UBI device X, volume with name NAME;
* o ubi:NAME - mount UBI device 0, volume with name NAME.
*
* Alternative '!' separator may be used instead of ':' (because some shells
* like busybox may interpret ':' as an NFS host name separator). This function
* returns UBI volume description object in case of success and a negative
* error code in case of failure.
*/
static struct ubi_volume_desc *open_ubi(const char *name, int mode)
{
struct ubi_volume_desc *ubi;
int dev, vol;
char *endptr;
if (!name || !*name)
return ERR_PTR(-EINVAL);
/* First, try to open using the device node path method */
ubi = ubi_open_volume_path(name, mode);
if (!IS_ERR(ubi))
return ubi;
/* Try the "nodev" method */
if (name[0] != 'u' || name[1] != 'b' || name[2] != 'i')
return ERR_PTR(-EINVAL);
/* ubi:NAME method */
if ((name[3] == ':' || name[3] == '!') && name[4] != '\0')
return ubi_open_volume_nm(0, name + 4, mode);
if (!isdigit(name[3]))
return ERR_PTR(-EINVAL);
dev = simple_strtoul(name + 3, &endptr, 0);
/* ubiY method */
if (*endptr == '\0')
return ubi_open_volume(0, dev, mode);
/* ubiX_Y method */
if (*endptr == '_' && isdigit(endptr[1])) {
vol = simple_strtoul(endptr + 1, &endptr, 0);
if (*endptr != '\0')
return ERR_PTR(-EINVAL);
return ubi_open_volume(dev, vol, mode);
}
/* ubiX:NAME method */
if ((*endptr == ':' || *endptr == '!') && endptr[1] != '\0')
return ubi_open_volume_nm(dev, ++endptr, mode);
return ERR_PTR(-EINVAL);
}
static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
{
struct ubifs_info *c;
c = kzalloc(sizeof(struct ubifs_info), GFP_KERNEL);
if (c) {
spin_lock_init(&c->cnt_lock);
spin_lock_init(&c->cs_lock);
spin_lock_init(&c->buds_lock);
spin_lock_init(&c->space_lock);
spin_lock_init(&c->orphan_lock);
init_rwsem(&c->commit_sem);
mutex_init(&c->lp_mutex);
mutex_init(&c->tnc_mutex);
mutex_init(&c->log_mutex);
mutex_init(&c->umount_mutex);
mutex_init(&c->bu_mutex);
mutex_init(&c->write_reserve_mutex);
init_waitqueue_head(&c->cmt_wq);
ubifs: Queue up space reservation tasks if retrying many times Recently we catched ENOSPC returned by make_reservation() while doing fsstress on UBIFS, we got following information when it occurred (See details in Link): UBIFS error (ubi0:0 pid 3640152): make_reservation [ubifs]: cannot reserve 112 bytes in jhead 2, error -28 CPU: 2 PID: 3640152 Comm: kworker/u16:2 Tainted: G B W Hardware name: Hisilicon PhosphorHi1230 EMU (DT) Workqueue: writeback wb_workfn (flush-ubifs_0_0) Call trace: dump_stack+0x114/0x198 make_reservation+0x564/0x610 [ubifs] ubifs_jnl_write_data+0x328/0x48c [ubifs] do_writepage+0x2a8/0x3e4 [ubifs] ubifs_writepage+0x16c/0x374 [ubifs] generic_writepages+0xb4/0x114 do_writepages+0xcc/0x11c writeback_sb_inodes+0x2d0/0x564 wb_writeback+0x20c/0x2b4 wb_workfn+0x404/0x510 process_one_work+0x304/0x4ac worker_thread+0x31c/0x4e4 kthread+0x23c/0x290 Budgeting info: data budget sum 17576, total budget sum 17768 budg_data_growth 4144, budg_dd_growth 13432, budg_idx_growth 192 min_idx_lebs 13, old_idx_sz 988640, uncommitted_idx 0 page_budget 4144, inode_budget 160, dent_budget 312 nospace 0, nospace_rp 0 dark_wm 8192, dead_wm 4096, max_idx_node_sz 192 freeable_cnt 0, calc_idx_sz 988640, idx_gc_cnt 0 dirty_pg_cnt 4, dirty_zn_cnt 0, clean_zn_cnt 4811 gc_lnum 21, ihead_lnum 14 jhead 0 (GC) LEB 16 jhead 1 (base) LEB 34 jhead 2 (data) LEB 23 bud LEB 16 bud LEB 23 bud LEB 34 old bud LEB 33 old bud LEB 31 old bud LEB 15 commit state 4 Budgeting predictions: available: 33832, outstanding 17576, free 15356 (pid 3640152) start dumping LEB properties (pid 3640152) Lprops statistics: empty_lebs 3, idx_lebs 11 taken_empty_lebs 1, total_free 1253376, total_dirty 2445736 total_used 3438712, total_dark 65536, total_dead 17248 LEB 15 free 0 dirty 248000 used 5952 (taken) LEB 16 free 110592 dirty 896 used 142464 (taken, jhead 0 (GC)) LEB 21 free 253952 dirty 0 used 0 (taken, GC LEB) LEB 23 free 0 dirty 248104 used 5848 (taken, jhead 2 (data)) LEB 29 free 253952 dirty 0 used 0 (empty) LEB 33 free 0 dirty 253952 used 0 (taken) LEB 34 free 217088 dirty 36544 used 320 (taken, jhead 1 (base)) LEB 37 free 253952 dirty 0 used 0 (empty) OTHERS: index lebs, zero-available non-index lebs According to the budget algorithm, there are 5 LEBs reserved for budget: three journal heads(16,23,34), 1 GC LEB(21) and 1 deletion LEB(can be used in make_reservation()). There are 2 empty LEBs used for index nodes, which is calculated as min_idx_lebs - idx_lebs = 2. In theory, LEB 15 and 33 should be reclaimed as free state after committing, but it is now in taken state. After looking the realization of reserve_space(), there's a possible situation: LEB 15: free 2000 dirty 248000 used 3952 (jhead 2) LEB 23: free 2000 dirty 248104 used 3848 (bud, taken) LEB 33: free 2000 dirty 251952 used 0 (bud, taken) wb_workfn wb_workfn_2 do_writepage // write 3000 bytes ubifs_jnl_write_data make_reservation reserve_space ubifs_garbage_collect ubifs_find_dirty_leb // ret ENOSPC, dirty LEBs are taken nospc_retries++ // 1 ubifs_run_commit do_commit LEB 15: free 2000 dirty 248000 used 3952 (jhead 2) LEB 23: free 2000 dirty 248104 used 3848 (dirty) LEB 33: free 2000 dirty 251952 used 0 (dirty) do_writepage // write 2000 bytes for 3 times ubifs_jnl_write_data // grabs 15\23\33 LEB 15: free 0 dirty 248000 used 5952 (bud, taken) LEB 23: free 0 dirty 248104 used 5848 (jhead 2) LEB 33: free 0 dirty 253952 used 0 (bud, taken) reserve_space ubifs_garbage_collect ubifs_find_dirty_leb // ret ENOSPC, dirty LEBs are taken if (nospc_retries++ < 2) // false ubifs_ro_mode ! Fetch a reproducer in Link. The dirty LEBs could be grabbed by other threads, which fails finding dirty LEBs of GC in current thread, so make_reservation() could try many times to invoke GC&&committing, but current realization limits the times of retrying as 'nospc_retries'(twice). Fix it by adding a wait queue, start queuing up space reservation tasks when someone task has retried gc + commit for many times. Then there is only one task making space reservation at any time, and it can always make success under the premise of correct budgeting. Link: https://bugzilla.kernel.org/show_bug.cgi?id=218164 Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com> Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Richard Weinberger <richard@nod.at>
2024-01-22 14:31:03 +08:00
init_waitqueue_head(&c->reserve_space_wq);
atomic_set(&c->need_wait_space, 0);
c->buds = RB_ROOT;
c->old_idx = RB_ROOT;
c->size_tree = RB_ROOT;
c->orph_tree = RB_ROOT;
INIT_LIST_HEAD(&c->infos_list);
INIT_LIST_HEAD(&c->idx_gc);
INIT_LIST_HEAD(&c->replay_list);
INIT_LIST_HEAD(&c->replay_buds);
INIT_LIST_HEAD(&c->uncat_list);
INIT_LIST_HEAD(&c->empty_list);
INIT_LIST_HEAD(&c->freeable_list);
INIT_LIST_HEAD(&c->frdi_idx_list);
INIT_LIST_HEAD(&c->unclean_leb_list);
INIT_LIST_HEAD(&c->old_buds);
INIT_LIST_HEAD(&c->orph_list);
INIT_LIST_HEAD(&c->orph_new);
c->no_chk_data_crc = 1;
c->assert_action = ASSACT_RO;
c->highest_inum = UBIFS_FIRST_INO;
c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM;
ubi_get_volume_info(ubi, &c->vi);
ubi_get_device_info(c->vi.ubi_num, &c->di);
}
return c;
}
static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
{
struct ubifs_info *c = sb->s_fs_info;
struct inode *root;
int err;
c->vfs_sb = sb;
/* Re-open the UBI device in read-write mode */
c->ubi = ubi_open_volume(c->vi.ubi_num, c->vi.vol_id, UBI_READWRITE);
if (IS_ERR(c->ubi)) {
err = PTR_ERR(c->ubi);
goto out;
}
err = ubifs_parse_options(c, data, 0);
if (err)
goto out_close;
/*
* UBIFS provides 'backing_dev_info' in order to disable read-ahead. For
* UBIFS, I/O is not deferred, it is done immediately in read_folio,
* which means the user would have to wait not just for their own I/O
* but the read-ahead I/O as well i.e. completely pointless.
*
* Read-ahead will be disabled because @sb->s_bdi->ra_pages is 0. Also
* @sb->s_bdi->capabilities are initialized to 0 so there won't be any
* writeback happening.
*/
err = super_setup_bdi_name(sb, "ubifs_%d_%d", c->vi.ubi_num,
c->vi.vol_id);
if (err)
goto out_close;
sb->s_bdi->ra_pages = 0;
sb->s_bdi->io_pages = 0;
sb->s_fs_info = c;
sb->s_magic = UBIFS_SUPER_MAGIC;
sb->s_blocksize = UBIFS_BLOCK_SIZE;
sb->s_blocksize_bits = UBIFS_BLOCK_SHIFT;
sb->s_maxbytes = c->max_inode_sz = key_max_inode_size(c);
if (c->max_inode_sz > MAX_LFS_FILESIZE)
sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE;
sb->s_op = &ubifs_super_operations;
sb->s_xattr = ubifs_xattr_handlers;
fscrypt_set_ops(sb, &ubifs_crypt_operations);
mutex_lock(&c->umount_mutex);
err = mount_ubifs(c);
if (err) {
ubifs_assert(c, err < 0);
goto out_unlock;
}
/* Read the root inode */
root = ubifs_iget(sb, UBIFS_ROOT_INO);
if (IS_ERR(root)) {
err = PTR_ERR(root);
goto out_umount;
}
generic_set_sb_d_ops(sb);
sb->s_root = d_make_root(root);
if (!sb->s_root) {
err = -ENOMEM;
goto out_umount;
}
super_set_uuid(sb, c->uuid, sizeof(c->uuid));
mutex_unlock(&c->umount_mutex);
return 0;
out_umount:
ubifs_umount(c);
out_unlock:
mutex_unlock(&c->umount_mutex);
out_close:
ubifs_release_options(c);
ubi_close_volume(c->ubi);
out:
return err;
}
static int sb_test(struct super_block *sb, void *data)
{
struct ubifs_info *c1 = data;
struct ubifs_info *c = sb->s_fs_info;
return c->vi.cdev == c1->vi.cdev;
}
static int sb_set(struct super_block *sb, void *data)
{
sb->s_fs_info = data;
return set_anon_super(sb, NULL);
}
static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
const char *name, void *data)
{
struct ubi_volume_desc *ubi;
struct ubifs_info *c;
struct super_block *sb;
int err;
dbg_gen("name %s, flags %#x", name, flags);
/*
* Get UBI device number and volume ID. Mount it read-only so far
* because this might be a new mount point, and UBI allows only one
* read-write user at a time.
*/
ubi = open_ubi(name, UBI_READONLY);
if (IS_ERR(ubi)) {
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
if (!(flags & SB_SILENT))
pr_err("UBIFS error (pid: %d): cannot open \"%s\", error %d",
current->pid, name, (int)PTR_ERR(ubi));
return ERR_CAST(ubi);
}
c = alloc_ubifs_info(ubi);
if (!c) {
err = -ENOMEM;
goto out_close;
}
dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id);
sb = sget(fs_type, sb_test, sb_set, flags, c);
if (IS_ERR(sb)) {
err = PTR_ERR(sb);
kfree(c);
goto out_close;
}
if (sb->s_root) {
struct ubifs_info *c1 = sb->s_fs_info;
kfree(c);
/* A new mount point for already mounted UBIFS */
dbg_gen("this ubi volume is already mounted");
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
if (!!(flags & SB_RDONLY) != c1->ro_mount) {
err = -EBUSY;
goto out_deact;
}
} else {
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
err = ubifs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0);
if (err)
goto out_deact;
/* We do not support atime */
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 05:05:09 +08:00
sb->s_flags |= SB_ACTIVE;
if (IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT))
ubifs_msg(c, "full atime support is enabled.");
else
sb->s_flags |= SB_NOATIME;
}
/* 'fill_super()' opens ubi again so we must close it here */
ubi_close_volume(ubi);
return dget(sb->s_root);
out_deact:
deactivate_locked_super(sb);
out_close:
ubi_close_volume(ubi);
return ERR_PTR(err);
}
static void kill_ubifs_super(struct super_block *s)
{
struct ubifs_info *c = s->s_fs_info;
kill_anon_super(s);
kfree(c);
}
static struct file_system_type ubifs_fs_type = {
.name = "ubifs",
.owner = THIS_MODULE,
.mount = ubifs_mount,
.kill_sb = kill_ubifs_super,
};
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 11:39:14 +08:00
MODULE_ALIAS_FS("ubifs");
/*
* Inode slab cache constructor.
*/
static void inode_slab_ctor(void *obj)
{
struct ubifs_inode *ui = obj;
inode_init_once(&ui->vfs_inode);
}
static int __init ubifs_init(void)
{
ubifs: dynamically allocate the ubifs-slab shrinker Use new APIs to dynamically allocate the ubifs-slab shrinker. Link: https://lkml.kernel.org/r/20230911094444.68966-15-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Richard Weinberger <richard@nod.at> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: "Darrick J. Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sean Paul <sean@poorly.run> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 17:44:13 +08:00
int err = -ENOMEM;
BUILD_BUG_ON(sizeof(struct ubifs_ch) != 24);
/* Make sure node sizes are 8-byte aligned */
BUILD_BUG_ON(UBIFS_CH_SZ & 7);
BUILD_BUG_ON(UBIFS_INO_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_DENT_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_XENT_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_DATA_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_TRUN_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_SB_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_MST_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_REF_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_CS_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_ORPH_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_MAX_DENT_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_MAX_XENT_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_MAX_DATA_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_MAX_INO_NODE_SZ & 7);
BUILD_BUG_ON(UBIFS_MAX_NODE_SZ & 7);
BUILD_BUG_ON(MIN_WRITE_SZ & 7);
/* Check min. node size */
BUILD_BUG_ON(UBIFS_INO_NODE_SZ < MIN_WRITE_SZ);
BUILD_BUG_ON(UBIFS_DENT_NODE_SZ < MIN_WRITE_SZ);
BUILD_BUG_ON(UBIFS_XENT_NODE_SZ < MIN_WRITE_SZ);
BUILD_BUG_ON(UBIFS_TRUN_NODE_SZ < MIN_WRITE_SZ);
BUILD_BUG_ON(UBIFS_MAX_DENT_NODE_SZ > UBIFS_MAX_NODE_SZ);
BUILD_BUG_ON(UBIFS_MAX_XENT_NODE_SZ > UBIFS_MAX_NODE_SZ);
BUILD_BUG_ON(UBIFS_MAX_DATA_NODE_SZ > UBIFS_MAX_NODE_SZ);
BUILD_BUG_ON(UBIFS_MAX_INO_NODE_SZ > UBIFS_MAX_NODE_SZ);
/* Defined node sizes */
BUILD_BUG_ON(UBIFS_SB_NODE_SZ != 4096);
BUILD_BUG_ON(UBIFS_MST_NODE_SZ != 512);
BUILD_BUG_ON(UBIFS_INO_NODE_SZ != 160);
BUILD_BUG_ON(UBIFS_REF_NODE_SZ != 64);
/*
* We use 2 bit wide bit-fields to store compression type, which should
* be amended if more compressors are added. The bit-fields are:
* @compr_type in 'struct ubifs_inode', @default_compr in
* 'struct ubifs_info' and @compr_type in 'struct ubifs_mount_opts'.
*/
BUILD_BUG_ON(UBIFS_COMPR_TYPES_CNT > 4);
/*
* We require that PAGE_SIZE is greater-than-or-equal-to
* UBIFS_BLOCK_SIZE. It is assumed that both are powers of 2.
*/
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
if (PAGE_SIZE < UBIFS_BLOCK_SIZE) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
pr_err("UBIFS error (pid %d): VFS page cache size is %u bytes, but UBIFS requires at least 4096 bytes",
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
current->pid, (unsigned int)PAGE_SIZE);
return -EINVAL;
}
ubifs_inode_slab = kmem_cache_create("ubifs_inode_slab",
sizeof(struct ubifs_inode), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
&inode_slab_ctor);
if (!ubifs_inode_slab)
return -ENOMEM;
ubifs: dynamically allocate the ubifs-slab shrinker Use new APIs to dynamically allocate the ubifs-slab shrinker. Link: https://lkml.kernel.org/r/20230911094444.68966-15-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Richard Weinberger <richard@nod.at> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: "Darrick J. Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sean Paul <sean@poorly.run> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 17:44:13 +08:00
ubifs_shrinker_info = shrinker_alloc(0, "ubifs-slab");
if (!ubifs_shrinker_info)
goto out_slab;
ubifs: dynamically allocate the ubifs-slab shrinker Use new APIs to dynamically allocate the ubifs-slab shrinker. Link: https://lkml.kernel.org/r/20230911094444.68966-15-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Richard Weinberger <richard@nod.at> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: "Darrick J. Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sean Paul <sean@poorly.run> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 17:44:13 +08:00
ubifs_shrinker_info->count_objects = ubifs_shrink_count;
ubifs_shrinker_info->scan_objects = ubifs_shrink_scan;
shrinker_register(ubifs_shrinker_info);
err = ubifs_compressors_init();
if (err)
goto out_shrinker;
dbg_debugfs_init();
err = ubifs_sysfs_init();
if (err)
goto out_dbg;
err = register_filesystem(&ubifs_fs_type);
if (err) {
UBIFS: extend debug/message capabilities In the case where we have more than one volumes on different UBI devices, it may be not that easy to tell which volume prints the messages. Add ubi number and volume id in ubifs_msg/warn/error to help debug. These two values are passed by struct ubifs_info. For those where ubifs_info is not initialized yet, ubifs_* is replaced by pr_*. For those where ubifs_info is not avaliable, ubifs_info is passed to the calling function as a const parameter. The output looks like, [ 95.444879] UBIFS (ubi0:1): background thread "ubifs_bgt0_1" started, PID 696 [ 95.484688] UBIFS (ubi0:1): UBIFS: mounted UBI device 0, volume 1, name "test1" [ 95.484694] UBIFS (ubi0:1): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.484699] UBIFS (ubi0:1): FS size: 30220288 bytes (28 MiB, 238 LEBs), journal size 1523712 bytes (1 MiB, 12 LEBs) [ 95.484703] UBIFS (ubi0:1): reserved for root: 1427378 bytes (1393 KiB) [ 95.484709] UBIFS (ubi0:1): media format: w4/r0 (latest is w4/r0), UUID 40DFFC0E-70BE-4193-8905-F7D6DFE60B17, small LPT model [ 95.489875] UBIFS (ubi1:0): background thread "ubifs_bgt1_0" started, PID 699 [ 95.529713] UBIFS (ubi1:0): UBIFS: mounted UBI device 1, volume 0, name "test2" [ 95.529718] UBIFS (ubi1:0): LEB size: 126976 bytes (124 KiB), min./max. I/O unit sizes: 2048 bytes/2048 bytes [ 95.529724] UBIFS (ubi1:0): FS size: 19808256 bytes (18 MiB, 156 LEBs), journal size 1015809 bytes (0 MiB, 8 LEBs) [ 95.529727] UBIFS (ubi1:0): reserved for root: 935592 bytes (913 KiB) [ 95.529733] UBIFS (ubi1:0): media format: w4/r0 (latest is w4/r0), UUID EEB7779D-F419-4CA9-811B-831CAC7233D4, small LPT model [ 954.264767] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node type (255 but expected 6) [ 954.367030] UBIFS error (ubi1:0 pid 756): ubifs_read_node: bad node at LEB 0:0, LEB mapping status 1 Signed-off-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
2015-03-20 18:39:42 +08:00
pr_err("UBIFS error (pid %d): cannot register file system, error %d",
current->pid, err);
goto out_sysfs;
}
return 0;
out_sysfs:
ubifs_sysfs_exit();
out_dbg:
dbg_debugfs_exit();
ubifs_compressors_exit();
out_shrinker:
ubifs: dynamically allocate the ubifs-slab shrinker Use new APIs to dynamically allocate the ubifs-slab shrinker. Link: https://lkml.kernel.org/r/20230911094444.68966-15-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Richard Weinberger <richard@nod.at> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: "Darrick J. Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sean Paul <sean@poorly.run> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 17:44:13 +08:00
shrinker_free(ubifs_shrinker_info);
out_slab:
kmem_cache_destroy(ubifs_inode_slab);
return err;
}
/* late_initcall to let compressors initialize first */
late_initcall(ubifs_init);
static void __exit ubifs_exit(void)
{
WARN_ON(!list_empty(&ubifs_infos));
WARN_ON(atomic_long_read(&ubifs_clean_zn_cnt) != 0);
dbg_debugfs_exit();
ubifs_sysfs_exit();
ubifs_compressors_exit();
ubifs: dynamically allocate the ubifs-slab shrinker Use new APIs to dynamically allocate the ubifs-slab shrinker. Link: https://lkml.kernel.org/r/20230911094444.68966-15-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Muchun Song <songmuchun@bytedance.com> Cc: Richard Weinberger <richard@nod.at> Cc: Abhinav Kumar <quic_abhinavk@quicinc.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Anna Schumaker <anna@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bob Peterson <rpeterso@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Carlos Llamas <cmllamas@google.com> Cc: Chandan Babu R <chandan.babu@oracle.com> Cc: Chao Yu <chao@kernel.org> Cc: Chris Mason <clm@fb.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Chuck Lever <cel@kernel.org> Cc: Coly Li <colyli@suse.de> Cc: Dai Ngo <Dai.Ngo@oracle.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: "Darrick J. Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Airlie <airlied@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Sterba <dsterba@suse.com> Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Cc: Gao Xiang <hsiangkao@linux.alibaba.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Huang Rui <ray.huang@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jason Wang <jasowang@redhat.com> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jeffle Xu <jefflexu@linux.alibaba.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Juergen Gross <jgross@suse.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Kirill Tkhai <tkhai@ya.ru> Cc: Marijn Suijten <marijn.suijten@somainline.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Mike Snitzer <snitzer@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nadav Amit <namit@vmware.com> Cc: Neil Brown <neilb@suse.de> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Olga Kornievskaia <kolga@netapp.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Rob Clark <robdclark@gmail.com> Cc: Rob Herring <robh@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Sean Paul <sean@poorly.run> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Song Liu <song@kernel.org> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: Steven Price <steven.price@arm.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com> Cc: Tom Talpey <tom@talpey.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Cc: Yue Hu <huyue2@coolpad.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-09-11 17:44:13 +08:00
shrinker_free(ubifs_shrinker_info);
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(ubifs_inode_slab);
unregister_filesystem(&ubifs_fs_type);
}
module_exit(ubifs_exit);
MODULE_LICENSE("GPL");
MODULE_VERSION(__stringify(UBIFS_VERSION));
MODULE_AUTHOR("Artem Bityutskiy, Adrian Hunter");
MODULE_DESCRIPTION("UBIFS - UBI File System");